Uploading /ephemeral/hossein/output/prog-y--tiny-llama-CDL-16
Browse files- README.md +61 -0
- all_results.json +8 -0
- checkpoint-150/config.json +30 -0
- checkpoint-150/generation_config.json +7 -0
- checkpoint-150/latest +1 -0
- checkpoint-150/model.safetensors +3 -0
- checkpoint-150/rng_state_0.pth +3 -0
- checkpoint-150/rng_state_1.pth +3 -0
- checkpoint-150/rng_state_2.pth +3 -0
- checkpoint-150/rng_state_3.pth +3 -0
- checkpoint-150/rng_state_4.pth +3 -0
- checkpoint-150/rng_state_5.pth +3 -0
- checkpoint-150/rng_state_6.pth +3 -0
- checkpoint-150/rng_state_7.pth +3 -0
- checkpoint-150/scheduler.pt +3 -0
- checkpoint-150/special_tokens_map.json +30 -0
- checkpoint-150/tokenizer.json +0 -0
- checkpoint-150/tokenizer.model +3 -0
- checkpoint-150/tokenizer_config.json +44 -0
- checkpoint-150/trainer_state.json +1083 -0
- checkpoint-150/training_args.bin +3 -0
- checkpoint-150/zero_to_fp32.py +674 -0
- config.json +1 -0
- generation_config.json +7 -0
- model.safetensors +3 -0
- runs/Nov25_12-49-05_creative-turing-2/events.out.tfevents.1732539135.creative-turing-2.1351148.0 +3 -0
- special_tokens_map.json +30 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +44 -0
- train_results.json +8 -0
- trainer_log.jsonl +151 -0
- trainer_state.json +1092 -0
- training_args.bin +3 -0
- training_loss.png +0 -0
README.md
ADDED
|
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
license: other
|
| 4 |
+
base_model: TinyLlama/TinyLlama_v1.1
|
| 5 |
+
tags:
|
| 6 |
+
- llama-factory
|
| 7 |
+
- full
|
| 8 |
+
- generated_from_trainer
|
| 9 |
+
model-index:
|
| 10 |
+
- name: progressive-yoco-tiny-llama-CDL-16
|
| 11 |
+
results: []
|
| 12 |
+
---
|
| 13 |
+
|
| 14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 15 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 16 |
+
|
| 17 |
+
# progressive-yoco-tiny-llama-CDL-16
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [/ephemeral/hossein/output/progressive-yoco-tiny-llama-CDL-17](https://huggingface.co//ephemeral/hossein/output/progressive-yoco-tiny-llama-CDL-17) on the reformatted_ultrachat_200k, the reformatted_MathInstruct and the small_slim_pajama datasets.
|
| 20 |
+
|
| 21 |
+
## Model description
|
| 22 |
+
|
| 23 |
+
More information needed
|
| 24 |
+
|
| 25 |
+
## Intended uses & limitations
|
| 26 |
+
|
| 27 |
+
More information needed
|
| 28 |
+
|
| 29 |
+
## Training and evaluation data
|
| 30 |
+
|
| 31 |
+
More information needed
|
| 32 |
+
|
| 33 |
+
## Training procedure
|
| 34 |
+
|
| 35 |
+
### Training hyperparameters
|
| 36 |
+
|
| 37 |
+
The following hyperparameters were used during training:
|
| 38 |
+
- learning_rate: 2e-05
|
| 39 |
+
- train_batch_size: 42
|
| 40 |
+
- eval_batch_size: 1
|
| 41 |
+
- seed: 42
|
| 42 |
+
- distributed_type: multi-GPU
|
| 43 |
+
- num_devices: 8
|
| 44 |
+
- gradient_accumulation_steps: 6
|
| 45 |
+
- total_train_batch_size: 2016
|
| 46 |
+
- total_eval_batch_size: 8
|
| 47 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 48 |
+
- lr_scheduler_type: cosine
|
| 49 |
+
- lr_scheduler_warmup_ratio: 0.005
|
| 50 |
+
- training_steps: 150
|
| 51 |
+
|
| 52 |
+
### Training results
|
| 53 |
+
|
| 54 |
+
|
| 55 |
+
|
| 56 |
+
### Framework versions
|
| 57 |
+
|
| 58 |
+
- Transformers 4.45.2
|
| 59 |
+
- Pytorch 2.5.1+cu124
|
| 60 |
+
- Datasets 3.1.0
|
| 61 |
+
- Tokenizers 0.20.3
|
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 0.19745502413339183,
|
| 3 |
+
"total_flos": 349677715193856.0,
|
| 4 |
+
"train_loss": 1.9421729667981467,
|
| 5 |
+
"train_runtime": 5209.8016,
|
| 6 |
+
"train_samples_per_second": 58.044,
|
| 7 |
+
"train_steps_per_second": 0.029
|
| 8 |
+
}
|
checkpoint-150/config.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "/ephemeral/hossein/output/progressive-yoco-tiny-llama-CDL-17",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"ProgressiveYocoLlamaForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_bias": false,
|
| 7 |
+
"attention_dropout": 0.0,
|
| 8 |
+
"bos_token_id": 1,
|
| 9 |
+
"crossDecoder_start_idx": 5,
|
| 10 |
+
"eos_token_id": 2,
|
| 11 |
+
"hidden_act": "silu",
|
| 12 |
+
"hidden_size": 2048,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 5632,
|
| 15 |
+
"max_position_embeddings": 2048,
|
| 16 |
+
"mlp_bias": false,
|
| 17 |
+
"model_type": "progressive_yoco_llama",
|
| 18 |
+
"num_attention_heads": 32,
|
| 19 |
+
"num_hidden_layers": 22,
|
| 20 |
+
"num_key_value_heads": 4,
|
| 21 |
+
"pretraining_tp": 1,
|
| 22 |
+
"rms_norm_eps": 1e-05,
|
| 23 |
+
"rope_scaling": null,
|
| 24 |
+
"rope_theta": 10000.0,
|
| 25 |
+
"tie_word_embeddings": false,
|
| 26 |
+
"torch_dtype": "bfloat16",
|
| 27 |
+
"transformers_version": "4.45.2",
|
| 28 |
+
"use_cache": false,
|
| 29 |
+
"vocab_size": 32000
|
| 30 |
+
}
|
checkpoint-150/generation_config.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 1,
|
| 3 |
+
"eos_token_id": 2,
|
| 4 |
+
"max_length": 2048,
|
| 5 |
+
"pad_token_id": 0,
|
| 6 |
+
"transformers_version": "4.45.2"
|
| 7 |
+
}
|
checkpoint-150/latest
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
global_step150
|
checkpoint-150/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:80623834a487bac356b6ec93fec2507ae5c5a7a8b6346c6eb768ed41ecb25c26
|
| 3 |
+
size 2191734544
|
checkpoint-150/rng_state_0.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:575119a228f98110923ffa2dedcb50e3317251b26054355d015e0b2240d566f2
|
| 3 |
+
size 15984
|
checkpoint-150/rng_state_1.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0728b56dab7abb5ef8a0d4bae3519c5767c97467bdd886d26bf19cc8599d0312
|
| 3 |
+
size 15984
|
checkpoint-150/rng_state_2.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f4e481d4ef1546694da7337f6bb6c658b866dcb79b85deeb477da0d27ebe851e
|
| 3 |
+
size 15984
|
checkpoint-150/rng_state_3.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:353c60be37ea56fc992fca446598ceca5d1fd002aa3bd6dbb9ad740e6f47ebb3
|
| 3 |
+
size 15984
|
checkpoint-150/rng_state_4.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e9107fe964ba7205e354084b85210e5a5ea1c98cfd4d38adb9cd3926945dcae4
|
| 3 |
+
size 15984
|
checkpoint-150/rng_state_5.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:69d1bb1abee38b92e53f3f23549b642ce0f1edcdccf7b6129847ac61636e96d5
|
| 3 |
+
size 15984
|
checkpoint-150/rng_state_6.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:afd5516048e20f36959601574e29e40106085a7d3cdc7bf425ce5e84633490e6
|
| 3 |
+
size 15984
|
checkpoint-150/rng_state_7.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8e2c46927fc06939b4c976a01e4b95dec1f8b98ceaea86d31a5d756fc30ff006
|
| 3 |
+
size 15984
|
checkpoint-150/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e3b70ad0cd9144ba90ee64e944e2b60fd1ed7029d14b16795ae00ff3af0741cb
|
| 3 |
+
size 1064
|
checkpoint-150/special_tokens_map.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "</s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "</s>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"unk_token": {
|
| 24 |
+
"content": "<unk>",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
}
|
| 30 |
+
}
|
checkpoint-150/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-150/tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
| 3 |
+
size 499723
|
checkpoint-150/tokenizer_config.json
ADDED
|
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"add_prefix_space": null,
|
| 5 |
+
"added_tokens_decoder": {
|
| 6 |
+
"0": {
|
| 7 |
+
"content": "<unk>",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": false,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false,
|
| 12 |
+
"special": true
|
| 13 |
+
},
|
| 14 |
+
"1": {
|
| 15 |
+
"content": "<s>",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": false,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false,
|
| 20 |
+
"special": true
|
| 21 |
+
},
|
| 22 |
+
"2": {
|
| 23 |
+
"content": "</s>",
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"normalized": false,
|
| 26 |
+
"rstrip": false,
|
| 27 |
+
"single_word": false,
|
| 28 |
+
"special": true
|
| 29 |
+
}
|
| 30 |
+
},
|
| 31 |
+
"bos_token": "<s>",
|
| 32 |
+
"chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ system_message }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ content }}{% elif message['role'] == 'assistant' %}{{ content }}{% endif %}{% endfor %}",
|
| 33 |
+
"clean_up_tokenization_spaces": false,
|
| 34 |
+
"eos_token": "</s>",
|
| 35 |
+
"legacy": false,
|
| 36 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 37 |
+
"pad_token": "</s>",
|
| 38 |
+
"padding_side": "right",
|
| 39 |
+
"sp_model_kwargs": {},
|
| 40 |
+
"split_special_tokens": false,
|
| 41 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 42 |
+
"unk_token": "<unk>",
|
| 43 |
+
"use_default_system_prompt": false
|
| 44 |
+
}
|
checkpoint-150/trainer_state.json
ADDED
|
@@ -0,0 +1,1083 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.19745502413339183,
|
| 5 |
+
"eval_steps": 50,
|
| 6 |
+
"global_step": 150,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.0013163668275559457,
|
| 13 |
+
"grad_norm": 1.1889708603566411,
|
| 14 |
+
"learning_rate": 2e-05,
|
| 15 |
+
"loss": 1.819,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.0026327336551118913,
|
| 20 |
+
"grad_norm": 1.2487402928615228,
|
| 21 |
+
"learning_rate": 1.999777729859618e-05,
|
| 22 |
+
"loss": 1.786,
|
| 23 |
+
"step": 2
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.003949100482667837,
|
| 27 |
+
"grad_norm": 11.818568585279303,
|
| 28 |
+
"learning_rate": 1.9991110182465032e-05,
|
| 29 |
+
"loss": 2.1123,
|
| 30 |
+
"step": 3
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.005265467310223783,
|
| 34 |
+
"grad_norm": 9.670771499171282,
|
| 35 |
+
"learning_rate": 1.9980001615408228e-05,
|
| 36 |
+
"loss": 2.1052,
|
| 37 |
+
"step": 4
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.006581834137779728,
|
| 41 |
+
"grad_norm": 6.7296227669578945,
|
| 42 |
+
"learning_rate": 1.9964456535631287e-05,
|
| 43 |
+
"loss": 2.0417,
|
| 44 |
+
"step": 5
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.007898200965335674,
|
| 48 |
+
"grad_norm": 2.9490730461911254,
|
| 49 |
+
"learning_rate": 1.9944481853548335e-05,
|
| 50 |
+
"loss": 1.9756,
|
| 51 |
+
"step": 6
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.009214567792891619,
|
| 55 |
+
"grad_norm": 2.8814574350373383,
|
| 56 |
+
"learning_rate": 1.9920086448710162e-05,
|
| 57 |
+
"loss": 1.9305,
|
| 58 |
+
"step": 7
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.010530934620447565,
|
| 62 |
+
"grad_norm": 2.360259343454192,
|
| 63 |
+
"learning_rate": 1.9891281165856876e-05,
|
| 64 |
+
"loss": 1.9001,
|
| 65 |
+
"step": 8
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.01184730144800351,
|
| 69 |
+
"grad_norm": 1.6478415946047946,
|
| 70 |
+
"learning_rate": 1.9858078810097004e-05,
|
| 71 |
+
"loss": 1.9285,
|
| 72 |
+
"step": 9
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.013163668275559455,
|
| 76 |
+
"grad_norm": 1.865513115308653,
|
| 77 |
+
"learning_rate": 1.98204941412151e-05,
|
| 78 |
+
"loss": 1.9158,
|
| 79 |
+
"step": 10
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.014480035103115402,
|
| 83 |
+
"grad_norm": 1.2039798356530171,
|
| 84 |
+
"learning_rate": 1.9778543867110428e-05,
|
| 85 |
+
"loss": 1.9177,
|
| 86 |
+
"step": 11
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.015796401930671347,
|
| 90 |
+
"grad_norm": 1.1202568182839863,
|
| 91 |
+
"learning_rate": 1.9732246636369605e-05,
|
| 92 |
+
"loss": 1.9124,
|
| 93 |
+
"step": 12
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.017112768758227294,
|
| 97 |
+
"grad_norm": 0.9613691948096944,
|
| 98 |
+
"learning_rate": 1.968162302997659e-05,
|
| 99 |
+
"loss": 1.9048,
|
| 100 |
+
"step": 13
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.018429135585783237,
|
| 104 |
+
"grad_norm": 0.893717907926126,
|
| 105 |
+
"learning_rate": 1.962669555216358e-05,
|
| 106 |
+
"loss": 1.8905,
|
| 107 |
+
"step": 14
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.019745502413339184,
|
| 111 |
+
"grad_norm": 0.9042103319398382,
|
| 112 |
+
"learning_rate": 1.9567488620406984e-05,
|
| 113 |
+
"loss": 1.9179,
|
| 114 |
+
"step": 15
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.02106186924089513,
|
| 118 |
+
"grad_norm": 0.8537257879688175,
|
| 119 |
+
"learning_rate": 1.9504028554572865e-05,
|
| 120 |
+
"loss": 1.8956,
|
| 121 |
+
"step": 16
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.022378236068451074,
|
| 125 |
+
"grad_norm": 0.7723152246718353,
|
| 126 |
+
"learning_rate": 1.943634356521671e-05,
|
| 127 |
+
"loss": 1.9106,
|
| 128 |
+
"step": 17
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.02369460289600702,
|
| 132 |
+
"grad_norm": 0.788599031919039,
|
| 133 |
+
"learning_rate": 1.9364463741042694e-05,
|
| 134 |
+
"loss": 1.8714,
|
| 135 |
+
"step": 18
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.025010969723562967,
|
| 139 |
+
"grad_norm": 0.7138782811411121,
|
| 140 |
+
"learning_rate": 1.928842103552803e-05,
|
| 141 |
+
"loss": 1.8805,
|
| 142 |
+
"step": 19
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.02632733655111891,
|
| 146 |
+
"grad_norm": 0.6526275706400243,
|
| 147 |
+
"learning_rate": 1.920824925271838e-05,
|
| 148 |
+
"loss": 1.8992,
|
| 149 |
+
"step": 20
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.027643703378674857,
|
| 153 |
+
"grad_norm": 0.7018291273940191,
|
| 154 |
+
"learning_rate": 1.9123984032200586e-05,
|
| 155 |
+
"loss": 1.8774,
|
| 156 |
+
"step": 21
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.028960070206230804,
|
| 160 |
+
"grad_norm": 0.7136424568096796,
|
| 161 |
+
"learning_rate": 1.9035662833259433e-05,
|
| 162 |
+
"loss": 1.8978,
|
| 163 |
+
"step": 22
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.030276437033786747,
|
| 167 |
+
"grad_norm": 0.7147862026041938,
|
| 168 |
+
"learning_rate": 1.8943324918225495e-05,
|
| 169 |
+
"loss": 1.8965,
|
| 170 |
+
"step": 23
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.031592803861342694,
|
| 174 |
+
"grad_norm": 0.7049064442746601,
|
| 175 |
+
"learning_rate": 1.8847011335021447e-05,
|
| 176 |
+
"loss": 1.8831,
|
| 177 |
+
"step": 24
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.03290917068889864,
|
| 181 |
+
"grad_norm": 0.6689369768605253,
|
| 182 |
+
"learning_rate": 1.874676489891461e-05,
|
| 183 |
+
"loss": 1.8881,
|
| 184 |
+
"step": 25
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.03422553751645459,
|
| 188 |
+
"grad_norm": 0.6425593648258924,
|
| 189 |
+
"learning_rate": 1.8642630173483832e-05,
|
| 190 |
+
"loss": 1.889,
|
| 191 |
+
"step": 26
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.03554190434401053,
|
| 195 |
+
"grad_norm": 0.6931260970545167,
|
| 196 |
+
"learning_rate": 1.85346534508092e-05,
|
| 197 |
+
"loss": 1.8936,
|
| 198 |
+
"step": 27
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.036858271171566474,
|
| 202 |
+
"grad_norm": 0.5855894301604793,
|
| 203 |
+
"learning_rate": 1.8422882730893323e-05,
|
| 204 |
+
"loss": 1.9131,
|
| 205 |
+
"step": 28
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.03817463799912242,
|
| 209 |
+
"grad_norm": 0.6403065763687231,
|
| 210 |
+
"learning_rate": 1.8307367700323412e-05,
|
| 211 |
+
"loss": 1.9104,
|
| 212 |
+
"step": 29
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.03949100482667837,
|
| 216 |
+
"grad_norm": 0.667165710149791,
|
| 217 |
+
"learning_rate": 1.8188159710183595e-05,
|
| 218 |
+
"loss": 1.8807,
|
| 219 |
+
"step": 30
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.040807371654234315,
|
| 223 |
+
"grad_norm": 0.601710689560651,
|
| 224 |
+
"learning_rate": 1.8065311753227272e-05,
|
| 225 |
+
"loss": 1.9261,
|
| 226 |
+
"step": 31
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.04212373848179026,
|
| 230 |
+
"grad_norm": 0.6543848114887616,
|
| 231 |
+
"learning_rate": 1.7938878440319722e-05,
|
| 232 |
+
"loss": 1.9178,
|
| 233 |
+
"step": 32
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.0434401053093462,
|
| 237 |
+
"grad_norm": 0.7216887863002542,
|
| 238 |
+
"learning_rate": 1.7808915976161364e-05,
|
| 239 |
+
"loss": 1.9212,
|
| 240 |
+
"step": 33
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.04475647213690215,
|
| 244 |
+
"grad_norm": 0.6605220221485377,
|
| 245 |
+
"learning_rate": 1.7675482134302503e-05,
|
| 246 |
+
"loss": 1.9019,
|
| 247 |
+
"step": 34
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.046072838964458095,
|
| 251 |
+
"grad_norm": 0.5651946270062499,
|
| 252 |
+
"learning_rate": 1.753863623146066e-05,
|
| 253 |
+
"loss": 1.9065,
|
| 254 |
+
"step": 35
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.04738920579201404,
|
| 258 |
+
"grad_norm": 0.6283354866608959,
|
| 259 |
+
"learning_rate": 1.7398439101151908e-05,
|
| 260 |
+
"loss": 1.8926,
|
| 261 |
+
"step": 36
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.04870557261956999,
|
| 265 |
+
"grad_norm": 0.591339280937863,
|
| 266 |
+
"learning_rate": 1.7254953066647915e-05,
|
| 267 |
+
"loss": 1.898,
|
| 268 |
+
"step": 37
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.050021939447125935,
|
| 272 |
+
"grad_norm": 0.566891433067587,
|
| 273 |
+
"learning_rate": 1.710824191327075e-05,
|
| 274 |
+
"loss": 1.9314,
|
| 275 |
+
"step": 38
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.051338306274681875,
|
| 279 |
+
"grad_norm": 0.5036303737690743,
|
| 280 |
+
"learning_rate": 1.695837086003772e-05,
|
| 281 |
+
"loss": 1.908,
|
| 282 |
+
"step": 39
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.05265467310223782,
|
| 286 |
+
"grad_norm": 0.5732998210738149,
|
| 287 |
+
"learning_rate": 1.680540653066891e-05,
|
| 288 |
+
"loss": 1.907,
|
| 289 |
+
"step": 40
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.05397103992979377,
|
| 293 |
+
"grad_norm": 0.600054956243109,
|
| 294 |
+
"learning_rate": 1.6649416923970248e-05,
|
| 295 |
+
"loss": 1.908,
|
| 296 |
+
"step": 41
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.055287406757349715,
|
| 300 |
+
"grad_norm": 0.5780718337975314,
|
| 301 |
+
"learning_rate": 1.649047138360529e-05,
|
| 302 |
+
"loss": 1.9006,
|
| 303 |
+
"step": 42
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.05660377358490566,
|
| 307 |
+
"grad_norm": 0.5998379136280807,
|
| 308 |
+
"learning_rate": 1.632864056726917e-05,
|
| 309 |
+
"loss": 1.9023,
|
| 310 |
+
"step": 43
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.05792014041246161,
|
| 314 |
+
"grad_norm": 0.630710242272472,
|
| 315 |
+
"learning_rate": 1.6163996415278423e-05,
|
| 316 |
+
"loss": 1.9284,
|
| 317 |
+
"step": 44
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.05923650724001755,
|
| 321 |
+
"grad_norm": 0.5104566997273228,
|
| 322 |
+
"learning_rate": 1.5996612118590604e-05,
|
| 323 |
+
"loss": 1.9089,
|
| 324 |
+
"step": 45
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.060552874067573495,
|
| 328 |
+
"grad_norm": 0.6521533677979531,
|
| 329 |
+
"learning_rate": 1.5826562086267956e-05,
|
| 330 |
+
"loss": 1.9285,
|
| 331 |
+
"step": 46
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.06186924089512944,
|
| 335 |
+
"grad_norm": 0.5098826190359927,
|
| 336 |
+
"learning_rate": 1.565392191239959e-05,
|
| 337 |
+
"loss": 1.916,
|
| 338 |
+
"step": 47
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.06318560772268539,
|
| 342 |
+
"grad_norm": 0.62515291794207,
|
| 343 |
+
"learning_rate": 1.5478768342496872e-05,
|
| 344 |
+
"loss": 1.9069,
|
| 345 |
+
"step": 48
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.06450197455024133,
|
| 349 |
+
"grad_norm": 0.5918382830263713,
|
| 350 |
+
"learning_rate": 1.5301179239376936e-05,
|
| 351 |
+
"loss": 1.9224,
|
| 352 |
+
"step": 49
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.06581834137779728,
|
| 356 |
+
"grad_norm": 0.6387295926323716,
|
| 357 |
+
"learning_rate": 1.512123354854955e-05,
|
| 358 |
+
"loss": 1.9022,
|
| 359 |
+
"step": 50
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.06713470820535322,
|
| 363 |
+
"grad_norm": 0.5484211324952757,
|
| 364 |
+
"learning_rate": 1.4939011263122635e-05,
|
| 365 |
+
"loss": 1.9024,
|
| 366 |
+
"step": 51
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.06845107503290918,
|
| 370 |
+
"grad_norm": 0.6838268591901047,
|
| 371 |
+
"learning_rate": 1.4754593388242117e-05,
|
| 372 |
+
"loss": 1.9133,
|
| 373 |
+
"step": 52
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.06976744186046512,
|
| 377 |
+
"grad_norm": 0.49026244529365287,
|
| 378 |
+
"learning_rate": 1.4568061905081874e-05,
|
| 379 |
+
"loss": 1.9044,
|
| 380 |
+
"step": 53
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.07108380868802106,
|
| 384 |
+
"grad_norm": 0.617101630668953,
|
| 385 |
+
"learning_rate": 1.4379499734399797e-05,
|
| 386 |
+
"loss": 1.9176,
|
| 387 |
+
"step": 54
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.07240017551557701,
|
| 391 |
+
"grad_norm": 0.5185658207760714,
|
| 392 |
+
"learning_rate": 1.4188990699676186e-05,
|
| 393 |
+
"loss": 1.915,
|
| 394 |
+
"step": 55
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.07371654234313295,
|
| 398 |
+
"grad_norm": 0.5509987613832577,
|
| 399 |
+
"learning_rate": 1.3996619489850822e-05,
|
| 400 |
+
"loss": 1.9282,
|
| 401 |
+
"step": 56
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.0750329091706889,
|
| 405 |
+
"grad_norm": 0.5404326350759733,
|
| 406 |
+
"learning_rate": 1.3802471621675337e-05,
|
| 407 |
+
"loss": 1.9121,
|
| 408 |
+
"step": 57
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.07634927599824484,
|
| 412 |
+
"grad_norm": 0.45194626257894893,
|
| 413 |
+
"learning_rate": 1.3606633401697557e-05,
|
| 414 |
+
"loss": 1.9348,
|
| 415 |
+
"step": 58
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.0776656428258008,
|
| 419 |
+
"grad_norm": 0.44319095497602445,
|
| 420 |
+
"learning_rate": 1.340919188789477e-05,
|
| 421 |
+
"loss": 1.9162,
|
| 422 |
+
"step": 59
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.07898200965335674,
|
| 426 |
+
"grad_norm": 0.45917008340300286,
|
| 427 |
+
"learning_rate": 1.3210234850972966e-05,
|
| 428 |
+
"loss": 1.9349,
|
| 429 |
+
"step": 60
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.08029837648091268,
|
| 433 |
+
"grad_norm": 0.4397437065658123,
|
| 434 |
+
"learning_rate": 1.300985073534919e-05,
|
| 435 |
+
"loss": 1.9344,
|
| 436 |
+
"step": 61
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.08161474330846863,
|
| 440 |
+
"grad_norm": 0.43586654360169025,
|
| 441 |
+
"learning_rate": 1.280812861983446e-05,
|
| 442 |
+
"loss": 1.9144,
|
| 443 |
+
"step": 62
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.08293111013602457,
|
| 447 |
+
"grad_norm": 0.4334759261856198,
|
| 448 |
+
"learning_rate": 1.2605158178034656e-05,
|
| 449 |
+
"loss": 1.9202,
|
| 450 |
+
"step": 63
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.08424747696358052,
|
| 454 |
+
"grad_norm": 0.41957147456515964,
|
| 455 |
+
"learning_rate": 1.2401029638486952e-05,
|
| 456 |
+
"loss": 1.8986,
|
| 457 |
+
"step": 64
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.08556384379113646,
|
| 461 |
+
"grad_norm": 0.41703972877231255,
|
| 462 |
+
"learning_rate": 1.219583374454963e-05,
|
| 463 |
+
"loss": 1.9367,
|
| 464 |
+
"step": 65
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.0868802106186924,
|
| 468 |
+
"grad_norm": 0.3885734477047593,
|
| 469 |
+
"learning_rate": 1.1989661714063e-05,
|
| 470 |
+
"loss": 1.9536,
|
| 471 |
+
"step": 66
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.08819657744624836,
|
| 475 |
+
"grad_norm": 0.3629396674080558,
|
| 476 |
+
"learning_rate": 1.1782605198799371e-05,
|
| 477 |
+
"loss": 1.942,
|
| 478 |
+
"step": 67
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 0.0895129442738043,
|
| 482 |
+
"grad_norm": 0.41851931328687847,
|
| 483 |
+
"learning_rate": 1.157475624372018e-05,
|
| 484 |
+
"loss": 1.9149,
|
| 485 |
+
"step": 68
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.09082931110136025,
|
| 489 |
+
"grad_norm": 0.38254555542206087,
|
| 490 |
+
"learning_rate": 1.1366207246058269e-05,
|
| 491 |
+
"loss": 1.9258,
|
| 492 |
+
"step": 69
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 0.09214567792891619,
|
| 496 |
+
"grad_norm": 0.3760396216126684,
|
| 497 |
+
"learning_rate": 1.1157050914243614e-05,
|
| 498 |
+
"loss": 1.9395,
|
| 499 |
+
"step": 70
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.09346204475647214,
|
| 503 |
+
"grad_norm": 0.3802671210811049,
|
| 504 |
+
"learning_rate": 1.0947380226690686e-05,
|
| 505 |
+
"loss": 1.9354,
|
| 506 |
+
"step": 71
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.09477841158402808,
|
| 510 |
+
"grad_norm": 0.346627059727759,
|
| 511 |
+
"learning_rate": 1.0737288390465792e-05,
|
| 512 |
+
"loss": 1.9259,
|
| 513 |
+
"step": 72
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.09609477841158402,
|
| 517 |
+
"grad_norm": 0.3873365911679245,
|
| 518 |
+
"learning_rate": 1.0526868799852797e-05,
|
| 519 |
+
"loss": 1.9493,
|
| 520 |
+
"step": 73
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 0.09741114523913998,
|
| 524 |
+
"grad_norm": 0.3805418724228647,
|
| 525 |
+
"learning_rate": 1.031621499483559e-05,
|
| 526 |
+
"loss": 1.9429,
|
| 527 |
+
"step": 74
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.09872751206669592,
|
| 531 |
+
"grad_norm": 0.3477296159832507,
|
| 532 |
+
"learning_rate": 1.0105420619515798e-05,
|
| 533 |
+
"loss": 1.9348,
|
| 534 |
+
"step": 75
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.10004387889425187,
|
| 538 |
+
"grad_norm": 0.36081350820036023,
|
| 539 |
+
"learning_rate": 9.894579380484206e-06,
|
| 540 |
+
"loss": 1.951,
|
| 541 |
+
"step": 76
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.10136024572180781,
|
| 545 |
+
"grad_norm": 0.3603157658181124,
|
| 546 |
+
"learning_rate": 9.683785005164412e-06,
|
| 547 |
+
"loss": 1.9568,
|
| 548 |
+
"step": 77
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 0.10267661254936375,
|
| 552 |
+
"grad_norm": 0.3344964866298326,
|
| 553 |
+
"learning_rate": 9.473131200147205e-06,
|
| 554 |
+
"loss": 1.9635,
|
| 555 |
+
"step": 78
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.1039929793769197,
|
| 559 |
+
"grad_norm": 0.3577372410086672,
|
| 560 |
+
"learning_rate": 9.262711609534211e-06,
|
| 561 |
+
"loss": 1.9493,
|
| 562 |
+
"step": 79
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 0.10530934620447564,
|
| 566 |
+
"grad_norm": 0.32166763062706677,
|
| 567 |
+
"learning_rate": 9.052619773309318e-06,
|
| 568 |
+
"loss": 1.9416,
|
| 569 |
+
"step": 80
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.1066257130320316,
|
| 573 |
+
"grad_norm": 0.3642098555682263,
|
| 574 |
+
"learning_rate": 8.842949085756389e-06,
|
| 575 |
+
"loss": 1.9375,
|
| 576 |
+
"step": 81
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 0.10794207985958754,
|
| 580 |
+
"grad_norm": 0.31313176156525635,
|
| 581 |
+
"learning_rate": 8.633792753941733e-06,
|
| 582 |
+
"loss": 1.9482,
|
| 583 |
+
"step": 82
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.10925844668714349,
|
| 587 |
+
"grad_norm": 0.32357294734122866,
|
| 588 |
+
"learning_rate": 8.425243756279824e-06,
|
| 589 |
+
"loss": 1.9274,
|
| 590 |
+
"step": 83
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 0.11057481351469943,
|
| 594 |
+
"grad_norm": 0.3149933190799516,
|
| 595 |
+
"learning_rate": 8.217394801200632e-06,
|
| 596 |
+
"loss": 1.9494,
|
| 597 |
+
"step": 84
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.11189118034225537,
|
| 601 |
+
"grad_norm": 0.3145273258487357,
|
| 602 |
+
"learning_rate": 8.010338285937006e-06,
|
| 603 |
+
"loss": 1.9383,
|
| 604 |
+
"step": 85
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 0.11320754716981132,
|
| 608 |
+
"grad_norm": 0.3293525045662984,
|
| 609 |
+
"learning_rate": 7.804166255450372e-06,
|
| 610 |
+
"loss": 1.9438,
|
| 611 |
+
"step": 86
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.11452391399736726,
|
| 615 |
+
"grad_norm": 0.29338737195487413,
|
| 616 |
+
"learning_rate": 7.598970361513052e-06,
|
| 617 |
+
"loss": 1.9486,
|
| 618 |
+
"step": 87
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 0.11584028082492322,
|
| 622 |
+
"grad_norm": 0.3103457426467627,
|
| 623 |
+
"learning_rate": 7.394841821965345e-06,
|
| 624 |
+
"loss": 1.9274,
|
| 625 |
+
"step": 88
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.11715664765247916,
|
| 629 |
+
"grad_norm": 0.3143049571743679,
|
| 630 |
+
"learning_rate": 7.191871380165538e-06,
|
| 631 |
+
"loss": 1.9524,
|
| 632 |
+
"step": 89
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 0.1184730144800351,
|
| 636 |
+
"grad_norm": 0.29504032042698036,
|
| 637 |
+
"learning_rate": 6.990149264650814e-06,
|
| 638 |
+
"loss": 1.9445,
|
| 639 |
+
"step": 90
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.11978938130759105,
|
| 643 |
+
"grad_norm": 0.3210704673929567,
|
| 644 |
+
"learning_rate": 6.789765149027039e-06,
|
| 645 |
+
"loss": 1.9515,
|
| 646 |
+
"step": 91
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 0.12110574813514699,
|
| 650 |
+
"grad_norm": 0.28621542114599363,
|
| 651 |
+
"learning_rate": 6.590808112105232e-06,
|
| 652 |
+
"loss": 1.969,
|
| 653 |
+
"step": 92
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 0.12242211496270294,
|
| 657 |
+
"grad_norm": 0.2882677076447023,
|
| 658 |
+
"learning_rate": 6.3933665983024465e-06,
|
| 659 |
+
"loss": 1.954,
|
| 660 |
+
"step": 93
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 0.12373848179025888,
|
| 664 |
+
"grad_norm": 0.287930909134049,
|
| 665 |
+
"learning_rate": 6.197528378324664e-06,
|
| 666 |
+
"loss": 1.9313,
|
| 667 |
+
"step": 94
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 0.12505484861781482,
|
| 671 |
+
"grad_norm": 0.31023728939120476,
|
| 672 |
+
"learning_rate": 6.003380510149179e-06,
|
| 673 |
+
"loss": 1.9602,
|
| 674 |
+
"step": 95
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 0.12637121544537078,
|
| 678 |
+
"grad_norm": 0.2752773114898817,
|
| 679 |
+
"learning_rate": 5.8110093003238175e-06,
|
| 680 |
+
"loss": 1.9831,
|
| 681 |
+
"step": 96
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.12768758227292673,
|
| 685 |
+
"grad_norm": 0.2972076509810327,
|
| 686 |
+
"learning_rate": 5.620500265600206e-06,
|
| 687 |
+
"loss": 1.9562,
|
| 688 |
+
"step": 97
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 0.12900394910048266,
|
| 692 |
+
"grad_norm": 0.28344306622056237,
|
| 693 |
+
"learning_rate": 5.431938094918132e-06,
|
| 694 |
+
"loss": 1.9679,
|
| 695 |
+
"step": 98
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 0.1303203159280386,
|
| 699 |
+
"grad_norm": 0.27862896188615965,
|
| 700 |
+
"learning_rate": 5.245406611757882e-06,
|
| 701 |
+
"loss": 1.9667,
|
| 702 |
+
"step": 99
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 0.13163668275559456,
|
| 706 |
+
"grad_norm": 0.2775069903986726,
|
| 707 |
+
"learning_rate": 5.060988736877366e-06,
|
| 708 |
+
"loss": 1.9486,
|
| 709 |
+
"step": 100
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 0.13295304958315052,
|
| 713 |
+
"grad_norm": 0.2750571862770337,
|
| 714 |
+
"learning_rate": 4.878766451450451e-06,
|
| 715 |
+
"loss": 1.9557,
|
| 716 |
+
"step": 101
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 0.13426941641070644,
|
| 720 |
+
"grad_norm": 0.2680704001161532,
|
| 721 |
+
"learning_rate": 4.698820760623064e-06,
|
| 722 |
+
"loss": 1.9506,
|
| 723 |
+
"step": 102
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 0.1355857832382624,
|
| 727 |
+
"grad_norm": 0.2782630531024094,
|
| 728 |
+
"learning_rate": 4.5212316575031325e-06,
|
| 729 |
+
"loss": 1.9639,
|
| 730 |
+
"step": 103
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 0.13690215006581835,
|
| 734 |
+
"grad_norm": 0.25617683357697074,
|
| 735 |
+
"learning_rate": 4.346078087600411e-06,
|
| 736 |
+
"loss": 1.9683,
|
| 737 |
+
"step": 104
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 0.13821851689337428,
|
| 741 |
+
"grad_norm": 0.2444943371569369,
|
| 742 |
+
"learning_rate": 4.173437913732048e-06,
|
| 743 |
+
"loss": 1.9659,
|
| 744 |
+
"step": 105
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 0.13953488372093023,
|
| 748 |
+
"grad_norm": 0.2597397835336073,
|
| 749 |
+
"learning_rate": 4.003387881409397e-06,
|
| 750 |
+
"loss": 1.9704,
|
| 751 |
+
"step": 106
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 0.14085125054848618,
|
| 755 |
+
"grad_norm": 0.26063366143876027,
|
| 756 |
+
"learning_rate": 3.836003584721577e-06,
|
| 757 |
+
"loss": 1.97,
|
| 758 |
+
"step": 107
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 0.1421676173760421,
|
| 762 |
+
"grad_norm": 0.23235593032133328,
|
| 763 |
+
"learning_rate": 3.6713594327308343e-06,
|
| 764 |
+
"loss": 1.9554,
|
| 765 |
+
"step": 108
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 0.14348398420359806,
|
| 769 |
+
"grad_norm": 0.22701215505987368,
|
| 770 |
+
"learning_rate": 3.509528616394716e-06,
|
| 771 |
+
"loss": 1.9737,
|
| 772 |
+
"step": 109
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 0.14480035103115402,
|
| 776 |
+
"grad_norm": 0.24108913765275466,
|
| 777 |
+
"learning_rate": 3.3505830760297543e-06,
|
| 778 |
+
"loss": 1.9699,
|
| 779 |
+
"step": 110
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 0.14611671785870997,
|
| 783 |
+
"grad_norm": 0.24405476026520742,
|
| 784 |
+
"learning_rate": 3.1945934693310897e-06,
|
| 785 |
+
"loss": 1.9767,
|
| 786 |
+
"step": 111
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 0.1474330846862659,
|
| 790 |
+
"grad_norm": 0.23175867510438058,
|
| 791 |
+
"learning_rate": 3.0416291399622834e-06,
|
| 792 |
+
"loss": 2.0023,
|
| 793 |
+
"step": 112
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 0.14874945151382185,
|
| 797 |
+
"grad_norm": 0.22596129228759587,
|
| 798 |
+
"learning_rate": 2.891758086729253e-06,
|
| 799 |
+
"loss": 1.955,
|
| 800 |
+
"step": 113
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 0.1500658183413778,
|
| 804 |
+
"grad_norm": 0.24851949999567013,
|
| 805 |
+
"learning_rate": 2.7450469333520856e-06,
|
| 806 |
+
"loss": 1.9611,
|
| 807 |
+
"step": 114
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 0.15138218516893373,
|
| 811 |
+
"grad_norm": 0.22293156665441605,
|
| 812 |
+
"learning_rate": 2.6015608988480956e-06,
|
| 813 |
+
"loss": 1.9658,
|
| 814 |
+
"step": 115
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 0.15269855199648968,
|
| 818 |
+
"grad_norm": 0.21616202749444716,
|
| 819 |
+
"learning_rate": 2.4613637685393433e-06,
|
| 820 |
+
"loss": 1.9753,
|
| 821 |
+
"step": 116
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 0.15401491882404564,
|
| 825 |
+
"grad_norm": 0.22185470586350384,
|
| 826 |
+
"learning_rate": 2.324517865697501e-06,
|
| 827 |
+
"loss": 1.9495,
|
| 828 |
+
"step": 117
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 0.1553312856516016,
|
| 832 |
+
"grad_norm": 0.21722679538918865,
|
| 833 |
+
"learning_rate": 2.19108402383864e-06,
|
| 834 |
+
"loss": 1.9628,
|
| 835 |
+
"step": 118
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 0.15664765247915752,
|
| 839 |
+
"grad_norm": 0.21205900012695214,
|
| 840 |
+
"learning_rate": 2.06112155968028e-06,
|
| 841 |
+
"loss": 1.9823,
|
| 842 |
+
"step": 119
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 0.15796401930671347,
|
| 846 |
+
"grad_norm": 0.2182253662134732,
|
| 847 |
+
"learning_rate": 1.9346882467727323e-06,
|
| 848 |
+
"loss": 1.9875,
|
| 849 |
+
"step": 120
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 0.15928038613426942,
|
| 853 |
+
"grad_norm": 0.22007111443224736,
|
| 854 |
+
"learning_rate": 1.811840289816409e-06,
|
| 855 |
+
"loss": 1.9805,
|
| 856 |
+
"step": 121
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 0.16059675296182535,
|
| 860 |
+
"grad_norm": 0.20406970469647664,
|
| 861 |
+
"learning_rate": 1.6926322996765899e-06,
|
| 862 |
+
"loss": 1.9818,
|
| 863 |
+
"step": 122
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 0.1619131197893813,
|
| 867 |
+
"grad_norm": 0.2024904864715853,
|
| 868 |
+
"learning_rate": 1.5771172691066793e-06,
|
| 869 |
+
"loss": 1.9859,
|
| 870 |
+
"step": 123
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 0.16322948661693726,
|
| 874 |
+
"grad_norm": 0.20299971001174535,
|
| 875 |
+
"learning_rate": 1.4653465491908003e-06,
|
| 876 |
+
"loss": 2.0096,
|
| 877 |
+
"step": 124
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 0.1645458534444932,
|
| 881 |
+
"grad_norm": 0.21516178859981677,
|
| 882 |
+
"learning_rate": 1.3573698265161683e-06,
|
| 883 |
+
"loss": 1.9654,
|
| 884 |
+
"step": 125
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 0.16586222027204914,
|
| 888 |
+
"grad_norm": 0.20722629324747893,
|
| 889 |
+
"learning_rate": 1.2532351010853916e-06,
|
| 890 |
+
"loss": 1.9708,
|
| 891 |
+
"step": 126
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 0.1671785870996051,
|
| 895 |
+
"grad_norm": 0.21213871178644442,
|
| 896 |
+
"learning_rate": 1.152988664978556e-06,
|
| 897 |
+
"loss": 1.9787,
|
| 898 |
+
"step": 127
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 0.16849495392716105,
|
| 902 |
+
"grad_norm": 0.20023503307538396,
|
| 903 |
+
"learning_rate": 1.0566750817745076e-06,
|
| 904 |
+
"loss": 1.9858,
|
| 905 |
+
"step": 128
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 0.16981132075471697,
|
| 909 |
+
"grad_norm": 0.1924700263570635,
|
| 910 |
+
"learning_rate": 9.6433716674057e-07,
|
| 911 |
+
"loss": 1.9781,
|
| 912 |
+
"step": 129
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 0.17112768758227292,
|
| 916 |
+
"grad_norm": 0.20779051083187167,
|
| 917 |
+
"learning_rate": 8.760159677994174e-07,
|
| 918 |
+
"loss": 1.9827,
|
| 919 |
+
"step": 130
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 0.17244405440982888,
|
| 923 |
+
"grad_norm": 0.20230044677950978,
|
| 924 |
+
"learning_rate": 7.91750747281621e-07,
|
| 925 |
+
"loss": 1.9741,
|
| 926 |
+
"step": 131
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 0.1737604212373848,
|
| 930 |
+
"grad_norm": 0.19683020520485797,
|
| 931 |
+
"learning_rate": 7.115789644719728e-07,
|
| 932 |
+
"loss": 1.9949,
|
| 933 |
+
"step": 132
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 0.17507678806494076,
|
| 937 |
+
"grad_norm": 0.19524340774257554,
|
| 938 |
+
"learning_rate": 6.355362589573078e-07,
|
| 939 |
+
"loss": 1.9762,
|
| 940 |
+
"step": 133
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 0.1763931548924967,
|
| 944 |
+
"grad_norm": 0.20098123761556075,
|
| 945 |
+
"learning_rate": 5.636564347832907e-07,
|
| 946 |
+
"loss": 1.9818,
|
| 947 |
+
"step": 134
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 0.17770952172005267,
|
| 951 |
+
"grad_norm": 0.18935262395702177,
|
| 952 |
+
"learning_rate": 4.95971445427137e-07,
|
| 953 |
+
"loss": 1.983,
|
| 954 |
+
"step": 135
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 0.1790258885476086,
|
| 958 |
+
"grad_norm": 0.1906817912560046,
|
| 959 |
+
"learning_rate": 4.3251137959302023e-07,
|
| 960 |
+
"loss": 1.9708,
|
| 961 |
+
"step": 136
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 0.18034225537516455,
|
| 965 |
+
"grad_norm": 0.19470612058115894,
|
| 966 |
+
"learning_rate": 3.733044478364234e-07,
|
| 967 |
+
"loss": 1.967,
|
| 968 |
+
"step": 137
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 0.1816586222027205,
|
| 972 |
+
"grad_norm": 0.18636115957247928,
|
| 973 |
+
"learning_rate": 3.1837697002341293e-07,
|
| 974 |
+
"loss": 1.9791,
|
| 975 |
+
"step": 138
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 0.18297498903027642,
|
| 979 |
+
"grad_norm": 0.18877431556550928,
|
| 980 |
+
"learning_rate": 2.677533636303964e-07,
|
| 981 |
+
"loss": 1.9694,
|
| 982 |
+
"step": 139
|
| 983 |
+
},
|
| 984 |
+
{
|
| 985 |
+
"epoch": 0.18429135585783238,
|
| 986 |
+
"grad_norm": 0.1955087203028538,
|
| 987 |
+
"learning_rate": 2.214561328895748e-07,
|
| 988 |
+
"loss": 1.9741,
|
| 989 |
+
"step": 140
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 0.18560772268538833,
|
| 993 |
+
"grad_norm": 0.196549286904382,
|
| 994 |
+
"learning_rate": 1.7950585878489856e-07,
|
| 995 |
+
"loss": 1.979,
|
| 996 |
+
"step": 141
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 0.18692408951294429,
|
| 1000 |
+
"grad_norm": 0.19224460294869852,
|
| 1001 |
+
"learning_rate": 1.419211899029971e-07,
|
| 1002 |
+
"loss": 1.9707,
|
| 1003 |
+
"step": 142
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 0.1882404563405002,
|
| 1007 |
+
"grad_norm": 0.18853581462437616,
|
| 1008 |
+
"learning_rate": 1.0871883414312778e-07,
|
| 1009 |
+
"loss": 1.981,
|
| 1010 |
+
"step": 143
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 0.18955682316805617,
|
| 1014 |
+
"grad_norm": 0.1838928559361403,
|
| 1015 |
+
"learning_rate": 7.99135512898408e-08,
|
| 1016 |
+
"loss": 1.9731,
|
| 1017 |
+
"step": 144
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 0.19087318999561212,
|
| 1021 |
+
"grad_norm": 0.190162401461088,
|
| 1022 |
+
"learning_rate": 5.55181464516652e-08,
|
| 1023 |
+
"loss": 1.975,
|
| 1024 |
+
"step": 145
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 0.19218955682316805,
|
| 1028 |
+
"grad_norm": 0.19003523312950812,
|
| 1029 |
+
"learning_rate": 3.554346436871581e-08,
|
| 1030 |
+
"loss": 1.9704,
|
| 1031 |
+
"step": 146
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 0.193505923650724,
|
| 1035 |
+
"grad_norm": 0.19021539316010605,
|
| 1036 |
+
"learning_rate": 1.9998384591773945e-08,
|
| 1037 |
+
"loss": 1.979,
|
| 1038 |
+
"step": 147
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"epoch": 0.19482229047827995,
|
| 1042 |
+
"grad_norm": 0.18754432655782285,
|
| 1043 |
+
"learning_rate": 8.889817534969425e-09,
|
| 1044 |
+
"loss": 1.9867,
|
| 1045 |
+
"step": 148
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 0.1961386573058359,
|
| 1049 |
+
"grad_norm": 0.1897467195961825,
|
| 1050 |
+
"learning_rate": 2.222701403818972e-09,
|
| 1051 |
+
"loss": 1.9756,
|
| 1052 |
+
"step": 149
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 0.19745502413339183,
|
| 1056 |
+
"grad_norm": 0.20302937860642753,
|
| 1057 |
+
"learning_rate": 0.0,
|
| 1058 |
+
"loss": 1.9877,
|
| 1059 |
+
"step": 150
|
| 1060 |
+
}
|
| 1061 |
+
],
|
| 1062 |
+
"logging_steps": 1,
|
| 1063 |
+
"max_steps": 150,
|
| 1064 |
+
"num_input_tokens_seen": 0,
|
| 1065 |
+
"num_train_epochs": 1,
|
| 1066 |
+
"save_steps": 50,
|
| 1067 |
+
"stateful_callbacks": {
|
| 1068 |
+
"TrainerControl": {
|
| 1069 |
+
"args": {
|
| 1070 |
+
"should_epoch_stop": false,
|
| 1071 |
+
"should_evaluate": false,
|
| 1072 |
+
"should_log": false,
|
| 1073 |
+
"should_save": true,
|
| 1074 |
+
"should_training_stop": true
|
| 1075 |
+
},
|
| 1076 |
+
"attributes": {}
|
| 1077 |
+
}
|
| 1078 |
+
},
|
| 1079 |
+
"total_flos": 349677715193856.0,
|
| 1080 |
+
"train_batch_size": 42,
|
| 1081 |
+
"trial_name": null,
|
| 1082 |
+
"trial_params": null
|
| 1083 |
+
}
|
checkpoint-150/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:740b7b8a2a5af5fe75fa4a3755ea7b3cb437cad50b07e933078a8d7b44af963f
|
| 3 |
+
size 7224
|
checkpoint-150/zero_to_fp32.py
ADDED
|
@@ -0,0 +1,674 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
#!/usr/bin/env python
|
| 2 |
+
|
| 3 |
+
# Copyright (c) Microsoft Corporation.
|
| 4 |
+
# SPDX-License-Identifier: Apache-2.0
|
| 5 |
+
|
| 6 |
+
# DeepSpeed Team
|
| 7 |
+
|
| 8 |
+
# This script extracts fp32 consolidated weights from a zero 1, 2 and 3 DeepSpeed checkpoints. It gets
|
| 9 |
+
# copied into the top level checkpoint dir, so the user can easily do the conversion at any point in
|
| 10 |
+
# the future. Once extracted, the weights don't require DeepSpeed and can be used in any
|
| 11 |
+
# application.
|
| 12 |
+
#
|
| 13 |
+
# example:
|
| 14 |
+
# python zero_to_fp32.py . output_dir/
|
| 15 |
+
# or
|
| 16 |
+
# python zero_to_fp32.py . output_dir/ --safe_serialization
|
| 17 |
+
|
| 18 |
+
import argparse
|
| 19 |
+
import torch
|
| 20 |
+
import glob
|
| 21 |
+
import math
|
| 22 |
+
import os
|
| 23 |
+
import re
|
| 24 |
+
import json
|
| 25 |
+
from tqdm import tqdm
|
| 26 |
+
from collections import OrderedDict
|
| 27 |
+
from dataclasses import dataclass
|
| 28 |
+
|
| 29 |
+
# while this script doesn't use deepspeed to recover data, since the checkpoints are pickled with
|
| 30 |
+
# DeepSpeed data structures it has to be available in the current python environment.
|
| 31 |
+
from deepspeed.utils import logger
|
| 32 |
+
from deepspeed.checkpoint.constants import (DS_VERSION, OPTIMIZER_STATE_DICT, SINGLE_PARTITION_OF_FP32_GROUPS,
|
| 33 |
+
FP32_FLAT_GROUPS, ZERO_STAGE, PARTITION_COUNT, PARAM_SHAPES, BUFFER_NAMES,
|
| 34 |
+
FROZEN_PARAM_SHAPES, FROZEN_PARAM_FRAGMENTS)
|
| 35 |
+
|
| 36 |
+
|
| 37 |
+
@dataclass
|
| 38 |
+
class zero_model_state:
|
| 39 |
+
buffers: dict()
|
| 40 |
+
param_shapes: dict()
|
| 41 |
+
shared_params: list
|
| 42 |
+
ds_version: int
|
| 43 |
+
frozen_param_shapes: dict()
|
| 44 |
+
frozen_param_fragments: dict()
|
| 45 |
+
|
| 46 |
+
|
| 47 |
+
debug = 0
|
| 48 |
+
|
| 49 |
+
# load to cpu
|
| 50 |
+
device = torch.device('cpu')
|
| 51 |
+
|
| 52 |
+
|
| 53 |
+
def atoi(text):
|
| 54 |
+
return int(text) if text.isdigit() else text
|
| 55 |
+
|
| 56 |
+
|
| 57 |
+
def natural_keys(text):
|
| 58 |
+
'''
|
| 59 |
+
alist.sort(key=natural_keys) sorts in human order
|
| 60 |
+
http://nedbatchelder.com/blog/200712/human_sorting.html
|
| 61 |
+
(See Toothy's implementation in the comments)
|
| 62 |
+
'''
|
| 63 |
+
return [atoi(c) for c in re.split(r'(\d+)', text)]
|
| 64 |
+
|
| 65 |
+
|
| 66 |
+
def get_model_state_file(checkpoint_dir, zero_stage):
|
| 67 |
+
if not os.path.isdir(checkpoint_dir):
|
| 68 |
+
raise FileNotFoundError(f"Directory '{checkpoint_dir}' doesn't exist")
|
| 69 |
+
|
| 70 |
+
# there should be only one file
|
| 71 |
+
if zero_stage <= 2:
|
| 72 |
+
file = os.path.join(checkpoint_dir, "mp_rank_00_model_states.pt")
|
| 73 |
+
elif zero_stage == 3:
|
| 74 |
+
file = os.path.join(checkpoint_dir, "zero_pp_rank_0_mp_rank_00_model_states.pt")
|
| 75 |
+
|
| 76 |
+
if not os.path.exists(file):
|
| 77 |
+
raise FileNotFoundError(f"can't find model states file at '{file}'")
|
| 78 |
+
|
| 79 |
+
return file
|
| 80 |
+
|
| 81 |
+
|
| 82 |
+
def get_checkpoint_files(checkpoint_dir, glob_pattern):
|
| 83 |
+
# XXX: need to test that this simple glob rule works for multi-node setup too
|
| 84 |
+
ckpt_files = sorted(glob.glob(os.path.join(checkpoint_dir, glob_pattern)), key=natural_keys)
|
| 85 |
+
|
| 86 |
+
if len(ckpt_files) == 0:
|
| 87 |
+
raise FileNotFoundError(f"can't find {glob_pattern} files in directory '{checkpoint_dir}'")
|
| 88 |
+
|
| 89 |
+
return ckpt_files
|
| 90 |
+
|
| 91 |
+
|
| 92 |
+
def get_optim_files(checkpoint_dir):
|
| 93 |
+
return get_checkpoint_files(checkpoint_dir, "*_optim_states.pt")
|
| 94 |
+
|
| 95 |
+
|
| 96 |
+
def get_model_state_files(checkpoint_dir):
|
| 97 |
+
return get_checkpoint_files(checkpoint_dir, "*_model_states.pt")
|
| 98 |
+
|
| 99 |
+
|
| 100 |
+
def parse_model_states(files):
|
| 101 |
+
zero_model_states = []
|
| 102 |
+
for file in files:
|
| 103 |
+
state_dict = torch.load(file, map_location=device)
|
| 104 |
+
|
| 105 |
+
if BUFFER_NAMES not in state_dict:
|
| 106 |
+
raise ValueError(f"{file} is not a model state checkpoint")
|
| 107 |
+
buffer_names = state_dict[BUFFER_NAMES]
|
| 108 |
+
if debug:
|
| 109 |
+
print("Found buffers:", buffer_names)
|
| 110 |
+
|
| 111 |
+
# recover just the buffers while restoring them to fp32 if they were saved in fp16
|
| 112 |
+
buffers = {k: v.float() for k, v in state_dict["module"].items() if k in buffer_names}
|
| 113 |
+
param_shapes = state_dict[PARAM_SHAPES]
|
| 114 |
+
|
| 115 |
+
# collect parameters that are included in param_shapes
|
| 116 |
+
param_names = []
|
| 117 |
+
for s in param_shapes:
|
| 118 |
+
for name in s.keys():
|
| 119 |
+
param_names.append(name)
|
| 120 |
+
|
| 121 |
+
# update with frozen parameters
|
| 122 |
+
frozen_param_shapes = state_dict.get(FROZEN_PARAM_SHAPES, None)
|
| 123 |
+
if frozen_param_shapes is not None:
|
| 124 |
+
if debug:
|
| 125 |
+
print(f"Found frozen_param_shapes: {frozen_param_shapes}")
|
| 126 |
+
param_names += list(frozen_param_shapes.keys())
|
| 127 |
+
|
| 128 |
+
# handle shared params
|
| 129 |
+
shared_params = [[k, v] for k, v in state_dict["shared_params"].items()]
|
| 130 |
+
|
| 131 |
+
ds_version = state_dict.get(DS_VERSION, None)
|
| 132 |
+
|
| 133 |
+
frozen_param_fragments = state_dict.get(FROZEN_PARAM_FRAGMENTS, None)
|
| 134 |
+
|
| 135 |
+
z_model_state = zero_model_state(buffers=buffers,
|
| 136 |
+
param_shapes=param_shapes,
|
| 137 |
+
shared_params=shared_params,
|
| 138 |
+
ds_version=ds_version,
|
| 139 |
+
frozen_param_shapes=frozen_param_shapes,
|
| 140 |
+
frozen_param_fragments=frozen_param_fragments)
|
| 141 |
+
zero_model_states.append(z_model_state)
|
| 142 |
+
|
| 143 |
+
return zero_model_states
|
| 144 |
+
|
| 145 |
+
|
| 146 |
+
def parse_optim_states(files, ds_checkpoint_dir):
|
| 147 |
+
total_files = len(files)
|
| 148 |
+
state_dicts = []
|
| 149 |
+
for f in files:
|
| 150 |
+
state_dict = torch.load(f, map_location=device)
|
| 151 |
+
# immediately discard the potentially huge 2 optimizer states as we only care for fp32 master weights
|
| 152 |
+
# and also handle the case where it was already removed by another helper script
|
| 153 |
+
state_dict["optimizer_state_dict"].pop("optimizer_state_dict", None)
|
| 154 |
+
state_dicts.append(state_dict)
|
| 155 |
+
|
| 156 |
+
if not ZERO_STAGE in state_dicts[0][OPTIMIZER_STATE_DICT]:
|
| 157 |
+
raise ValueError(f"{files[0]} is not a zero checkpoint")
|
| 158 |
+
zero_stage = state_dicts[0][OPTIMIZER_STATE_DICT][ZERO_STAGE]
|
| 159 |
+
world_size = state_dicts[0][OPTIMIZER_STATE_DICT][PARTITION_COUNT]
|
| 160 |
+
|
| 161 |
+
# For ZeRO-2 each param group can have different partition_count as data parallelism for expert
|
| 162 |
+
# parameters can be different from data parallelism for non-expert parameters. So we can just
|
| 163 |
+
# use the max of the partition_count to get the dp world_size.
|
| 164 |
+
|
| 165 |
+
if type(world_size) is list:
|
| 166 |
+
world_size = max(world_size)
|
| 167 |
+
|
| 168 |
+
if world_size != total_files:
|
| 169 |
+
raise ValueError(
|
| 170 |
+
f"Expected {world_size} of '*_optim_states.pt' under '{ds_checkpoint_dir}' but found {total_files} files. "
|
| 171 |
+
"Possibly due to an overwrite of an old checkpoint, or a checkpoint didn't get saved by one or more processes."
|
| 172 |
+
)
|
| 173 |
+
|
| 174 |
+
# the groups are named differently in each stage
|
| 175 |
+
if zero_stage <= 2:
|
| 176 |
+
fp32_groups_key = SINGLE_PARTITION_OF_FP32_GROUPS
|
| 177 |
+
elif zero_stage == 3:
|
| 178 |
+
fp32_groups_key = FP32_FLAT_GROUPS
|
| 179 |
+
else:
|
| 180 |
+
raise ValueError(f"unknown zero stage {zero_stage}")
|
| 181 |
+
|
| 182 |
+
if zero_stage <= 2:
|
| 183 |
+
fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] for i in range(len(state_dicts))]
|
| 184 |
+
elif zero_stage == 3:
|
| 185 |
+
# if there is more than one param group, there will be multiple flattened tensors - one
|
| 186 |
+
# flattened tensor per group - for simplicity merge them into a single tensor
|
| 187 |
+
#
|
| 188 |
+
# XXX: could make the script more memory efficient for when there are multiple groups - it
|
| 189 |
+
# will require matching the sub-lists of param_shapes for each param group flattened tensor
|
| 190 |
+
|
| 191 |
+
fp32_flat_groups = [
|
| 192 |
+
torch.cat(state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key], 0) for i in range(len(state_dicts))
|
| 193 |
+
]
|
| 194 |
+
|
| 195 |
+
return zero_stage, world_size, fp32_flat_groups
|
| 196 |
+
|
| 197 |
+
|
| 198 |
+
def _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters):
|
| 199 |
+
"""
|
| 200 |
+
Returns fp32 state_dict reconstructed from ds checkpoint
|
| 201 |
+
|
| 202 |
+
Args:
|
| 203 |
+
- ``ds_checkpoint_dir``: path to the deepspeed checkpoint folder (where the optimizer files are)
|
| 204 |
+
|
| 205 |
+
"""
|
| 206 |
+
print(f"Processing zero checkpoint '{ds_checkpoint_dir}'")
|
| 207 |
+
|
| 208 |
+
optim_files = get_optim_files(ds_checkpoint_dir)
|
| 209 |
+
zero_stage, world_size, fp32_flat_groups = parse_optim_states(optim_files, ds_checkpoint_dir)
|
| 210 |
+
print(f"Detected checkpoint of type zero stage {zero_stage}, world_size: {world_size}")
|
| 211 |
+
|
| 212 |
+
model_files = get_model_state_files(ds_checkpoint_dir)
|
| 213 |
+
|
| 214 |
+
zero_model_states = parse_model_states(model_files)
|
| 215 |
+
print(f'Parsing checkpoint created by deepspeed=={zero_model_states[0].ds_version}')
|
| 216 |
+
|
| 217 |
+
if zero_stage <= 2:
|
| 218 |
+
return _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
|
| 219 |
+
exclude_frozen_parameters)
|
| 220 |
+
elif zero_stage == 3:
|
| 221 |
+
return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
|
| 222 |
+
exclude_frozen_parameters)
|
| 223 |
+
|
| 224 |
+
|
| 225 |
+
def _zero2_merge_frozen_params(state_dict, zero_model_states):
|
| 226 |
+
if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
|
| 227 |
+
return
|
| 228 |
+
|
| 229 |
+
frozen_param_shapes = zero_model_states[0].frozen_param_shapes
|
| 230 |
+
frozen_param_fragments = zero_model_states[0].frozen_param_fragments
|
| 231 |
+
|
| 232 |
+
if debug:
|
| 233 |
+
num_elem = sum(s.numel() for s in frozen_param_shapes.values())
|
| 234 |
+
print(f'rank 0: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
|
| 235 |
+
|
| 236 |
+
wanted_params = len(frozen_param_shapes)
|
| 237 |
+
wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
|
| 238 |
+
avail_numel = sum([p.numel() for p in frozen_param_fragments.values()])
|
| 239 |
+
print(f'Frozen params: Have {avail_numel} numels to process.')
|
| 240 |
+
print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
|
| 241 |
+
|
| 242 |
+
total_params = 0
|
| 243 |
+
total_numel = 0
|
| 244 |
+
for name, shape in frozen_param_shapes.items():
|
| 245 |
+
total_params += 1
|
| 246 |
+
unpartitioned_numel = shape.numel()
|
| 247 |
+
total_numel += unpartitioned_numel
|
| 248 |
+
|
| 249 |
+
state_dict[name] = frozen_param_fragments[name]
|
| 250 |
+
|
| 251 |
+
if debug:
|
| 252 |
+
print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
|
| 253 |
+
|
| 254 |
+
print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
|
| 255 |
+
|
| 256 |
+
|
| 257 |
+
def _has_callable(obj, fn):
|
| 258 |
+
attr = getattr(obj, fn, None)
|
| 259 |
+
return callable(attr)
|
| 260 |
+
|
| 261 |
+
|
| 262 |
+
def _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
|
| 263 |
+
param_shapes = zero_model_states[0].param_shapes
|
| 264 |
+
|
| 265 |
+
# Reconstruction protocol:
|
| 266 |
+
#
|
| 267 |
+
# XXX: document this
|
| 268 |
+
|
| 269 |
+
if debug:
|
| 270 |
+
for i in range(world_size):
|
| 271 |
+
for j in range(len(fp32_flat_groups[0])):
|
| 272 |
+
print(f"{FP32_FLAT_GROUPS}[{i}][{j}].shape={fp32_flat_groups[i][j].shape}")
|
| 273 |
+
|
| 274 |
+
# XXX: memory usage doubles here (zero2)
|
| 275 |
+
num_param_groups = len(fp32_flat_groups[0])
|
| 276 |
+
merged_single_partition_of_fp32_groups = []
|
| 277 |
+
for i in range(num_param_groups):
|
| 278 |
+
merged_partitions = [sd[i] for sd in fp32_flat_groups]
|
| 279 |
+
full_single_fp32_vector = torch.cat(merged_partitions, 0)
|
| 280 |
+
merged_single_partition_of_fp32_groups.append(full_single_fp32_vector)
|
| 281 |
+
avail_numel = sum(
|
| 282 |
+
[full_single_fp32_vector.numel() for full_single_fp32_vector in merged_single_partition_of_fp32_groups])
|
| 283 |
+
|
| 284 |
+
if debug:
|
| 285 |
+
wanted_params = sum([len(shapes) for shapes in param_shapes])
|
| 286 |
+
wanted_numel = sum([sum(shape.numel() for shape in shapes.values()) for shapes in param_shapes])
|
| 287 |
+
# not asserting if there is a mismatch due to possible padding
|
| 288 |
+
print(f"Have {avail_numel} numels to process.")
|
| 289 |
+
print(f"Need {wanted_numel} numels in {wanted_params} params.")
|
| 290 |
+
|
| 291 |
+
# params
|
| 292 |
+
# XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
|
| 293 |
+
# out-of-core computing solution
|
| 294 |
+
total_numel = 0
|
| 295 |
+
total_params = 0
|
| 296 |
+
for shapes, full_single_fp32_vector in zip(param_shapes, merged_single_partition_of_fp32_groups):
|
| 297 |
+
offset = 0
|
| 298 |
+
avail_numel = full_single_fp32_vector.numel()
|
| 299 |
+
for name, shape in shapes.items():
|
| 300 |
+
|
| 301 |
+
unpartitioned_numel = shape.numel() if _has_callable(shape, 'numel') else math.prod(shape)
|
| 302 |
+
total_numel += unpartitioned_numel
|
| 303 |
+
total_params += 1
|
| 304 |
+
|
| 305 |
+
if debug:
|
| 306 |
+
print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
|
| 307 |
+
state_dict[name] = full_single_fp32_vector.narrow(0, offset, unpartitioned_numel).view(shape)
|
| 308 |
+
offset += unpartitioned_numel
|
| 309 |
+
|
| 310 |
+
# Z2 started to align to 2*world_size to improve nccl performance. Therefore both offset and
|
| 311 |
+
# avail_numel can differ by anywhere between 0..2*world_size. Due to two unrelated complex
|
| 312 |
+
# paddings performed in the code it's almost impossible to predict the exact numbers w/o the
|
| 313 |
+
# live optimizer object, so we are checking that the numbers are within the right range
|
| 314 |
+
align_to = 2 * world_size
|
| 315 |
+
|
| 316 |
+
def zero2_align(x):
|
| 317 |
+
return align_to * math.ceil(x / align_to)
|
| 318 |
+
|
| 319 |
+
if debug:
|
| 320 |
+
print(f"original offset={offset}, avail_numel={avail_numel}")
|
| 321 |
+
|
| 322 |
+
offset = zero2_align(offset)
|
| 323 |
+
avail_numel = zero2_align(avail_numel)
|
| 324 |
+
|
| 325 |
+
if debug:
|
| 326 |
+
print(f"aligned offset={offset}, avail_numel={avail_numel}")
|
| 327 |
+
|
| 328 |
+
# Sanity check
|
| 329 |
+
if offset != avail_numel:
|
| 330 |
+
raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
|
| 331 |
+
|
| 332 |
+
print(f"Reconstructed fp32 state dict with {total_params} params {total_numel} elements")
|
| 333 |
+
|
| 334 |
+
|
| 335 |
+
def _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
|
| 336 |
+
exclude_frozen_parameters):
|
| 337 |
+
state_dict = OrderedDict()
|
| 338 |
+
|
| 339 |
+
# buffers
|
| 340 |
+
buffers = zero_model_states[0].buffers
|
| 341 |
+
state_dict.update(buffers)
|
| 342 |
+
if debug:
|
| 343 |
+
print(f"added {len(buffers)} buffers")
|
| 344 |
+
|
| 345 |
+
if not exclude_frozen_parameters:
|
| 346 |
+
_zero2_merge_frozen_params(state_dict, zero_model_states)
|
| 347 |
+
|
| 348 |
+
_zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
|
| 349 |
+
|
| 350 |
+
# recover shared parameters
|
| 351 |
+
for pair in zero_model_states[0].shared_params:
|
| 352 |
+
if pair[1] in state_dict:
|
| 353 |
+
state_dict[pair[0]] = state_dict[pair[1]]
|
| 354 |
+
|
| 355 |
+
return state_dict
|
| 356 |
+
|
| 357 |
+
|
| 358 |
+
def zero3_partitioned_param_info(unpartitioned_numel, world_size):
|
| 359 |
+
remainder = unpartitioned_numel % world_size
|
| 360 |
+
padding_numel = (world_size - remainder) if remainder else 0
|
| 361 |
+
partitioned_numel = math.ceil(unpartitioned_numel / world_size)
|
| 362 |
+
return partitioned_numel, padding_numel
|
| 363 |
+
|
| 364 |
+
|
| 365 |
+
def _zero3_merge_frozen_params(state_dict, world_size, zero_model_states):
|
| 366 |
+
if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
|
| 367 |
+
return
|
| 368 |
+
|
| 369 |
+
if debug:
|
| 370 |
+
for i in range(world_size):
|
| 371 |
+
num_elem = sum(s.numel() for s in zero_model_states[i].frozen_param_fragments.values())
|
| 372 |
+
print(f'rank {i}: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
|
| 373 |
+
|
| 374 |
+
frozen_param_shapes = zero_model_states[0].frozen_param_shapes
|
| 375 |
+
wanted_params = len(frozen_param_shapes)
|
| 376 |
+
wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
|
| 377 |
+
avail_numel = sum([p.numel() for p in zero_model_states[0].frozen_param_fragments.values()]) * world_size
|
| 378 |
+
print(f'Frozen params: Have {avail_numel} numels to process.')
|
| 379 |
+
print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
|
| 380 |
+
|
| 381 |
+
total_params = 0
|
| 382 |
+
total_numel = 0
|
| 383 |
+
for name, shape in zero_model_states[0].frozen_param_shapes.items():
|
| 384 |
+
total_params += 1
|
| 385 |
+
unpartitioned_numel = shape.numel()
|
| 386 |
+
total_numel += unpartitioned_numel
|
| 387 |
+
|
| 388 |
+
param_frags = tuple(model_state.frozen_param_fragments[name] for model_state in zero_model_states)
|
| 389 |
+
state_dict[name] = torch.cat(param_frags, 0).narrow(0, 0, unpartitioned_numel).view(shape)
|
| 390 |
+
|
| 391 |
+
partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
|
| 392 |
+
|
| 393 |
+
if debug:
|
| 394 |
+
print(
|
| 395 |
+
f"Frozen params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
|
| 396 |
+
)
|
| 397 |
+
|
| 398 |
+
print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
|
| 399 |
+
|
| 400 |
+
|
| 401 |
+
def _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
|
| 402 |
+
param_shapes = zero_model_states[0].param_shapes
|
| 403 |
+
avail_numel = fp32_flat_groups[0].numel() * world_size
|
| 404 |
+
# Reconstruction protocol: For zero3 we need to zip the partitions together at boundary of each
|
| 405 |
+
# param, re-consolidating each param, while dealing with padding if any
|
| 406 |
+
|
| 407 |
+
# merge list of dicts, preserving order
|
| 408 |
+
param_shapes = {k: v for d in param_shapes for k, v in d.items()}
|
| 409 |
+
|
| 410 |
+
if debug:
|
| 411 |
+
for i in range(world_size):
|
| 412 |
+
print(f"{FP32_FLAT_GROUPS}[{i}].shape={fp32_flat_groups[i].shape}")
|
| 413 |
+
|
| 414 |
+
wanted_params = len(param_shapes)
|
| 415 |
+
wanted_numel = sum(shape.numel() for shape in param_shapes.values())
|
| 416 |
+
# not asserting if there is a mismatch due to possible padding
|
| 417 |
+
avail_numel = fp32_flat_groups[0].numel() * world_size
|
| 418 |
+
print(f"Trainable params: Have {avail_numel} numels to process.")
|
| 419 |
+
print(f"Trainable params: Need {wanted_numel} numels in {wanted_params} params.")
|
| 420 |
+
|
| 421 |
+
# params
|
| 422 |
+
# XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
|
| 423 |
+
# out-of-core computing solution
|
| 424 |
+
offset = 0
|
| 425 |
+
total_numel = 0
|
| 426 |
+
total_params = 0
|
| 427 |
+
for name, shape in tqdm(param_shapes.items(), desc='Gathering Sharded Weights'):
|
| 428 |
+
unpartitioned_numel = shape.numel()
|
| 429 |
+
total_numel += unpartitioned_numel
|
| 430 |
+
total_params += 1
|
| 431 |
+
partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
|
| 432 |
+
|
| 433 |
+
if debug:
|
| 434 |
+
print(
|
| 435 |
+
f"Trainable params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
|
| 436 |
+
)
|
| 437 |
+
|
| 438 |
+
# XXX: memory usage doubles here
|
| 439 |
+
state_dict[name] = torch.cat(
|
| 440 |
+
tuple(fp32_flat_groups[i].narrow(0, offset, partitioned_numel) for i in range(world_size)),
|
| 441 |
+
0).narrow(0, 0, unpartitioned_numel).view(shape)
|
| 442 |
+
offset += partitioned_numel
|
| 443 |
+
|
| 444 |
+
offset *= world_size
|
| 445 |
+
|
| 446 |
+
# Sanity check
|
| 447 |
+
if offset != avail_numel:
|
| 448 |
+
raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
|
| 449 |
+
|
| 450 |
+
print(f"Reconstructed Trainable fp32 state dict with {total_params} params {total_numel} elements")
|
| 451 |
+
|
| 452 |
+
|
| 453 |
+
def _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
|
| 454 |
+
exclude_frozen_parameters):
|
| 455 |
+
state_dict = OrderedDict()
|
| 456 |
+
|
| 457 |
+
# buffers
|
| 458 |
+
buffers = zero_model_states[0].buffers
|
| 459 |
+
state_dict.update(buffers)
|
| 460 |
+
if debug:
|
| 461 |
+
print(f"added {len(buffers)} buffers")
|
| 462 |
+
|
| 463 |
+
if not exclude_frozen_parameters:
|
| 464 |
+
_zero3_merge_frozen_params(state_dict, world_size, zero_model_states)
|
| 465 |
+
|
| 466 |
+
_zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
|
| 467 |
+
|
| 468 |
+
# recover shared parameters
|
| 469 |
+
for pair in zero_model_states[0].shared_params:
|
| 470 |
+
if pair[1] in state_dict:
|
| 471 |
+
state_dict[pair[0]] = state_dict[pair[1]]
|
| 472 |
+
|
| 473 |
+
return state_dict
|
| 474 |
+
|
| 475 |
+
|
| 476 |
+
def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag=None, exclude_frozen_parameters=False):
|
| 477 |
+
"""
|
| 478 |
+
Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated state_dict that can be loaded with
|
| 479 |
+
``load_state_dict()`` and used for training without DeepSpeed or shared with others, for example
|
| 480 |
+
via a model hub.
|
| 481 |
+
|
| 482 |
+
Args:
|
| 483 |
+
- ``checkpoint_dir``: path to the desired checkpoint folder
|
| 484 |
+
- ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in 'latest' file. e.g., ``global_step14``
|
| 485 |
+
- ``exclude_frozen_parameters``: exclude frozen parameters
|
| 486 |
+
|
| 487 |
+
Returns:
|
| 488 |
+
- pytorch ``state_dict``
|
| 489 |
+
|
| 490 |
+
Note: this approach may not work if your application doesn't have sufficient free CPU memory and
|
| 491 |
+
you may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with
|
| 492 |
+
the checkpoint.
|
| 493 |
+
|
| 494 |
+
A typical usage might be ::
|
| 495 |
+
|
| 496 |
+
from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
|
| 497 |
+
# do the training and checkpoint saving
|
| 498 |
+
state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir) # already on cpu
|
| 499 |
+
model = model.cpu() # move to cpu
|
| 500 |
+
model.load_state_dict(state_dict)
|
| 501 |
+
# submit to model hub or save the model to share with others
|
| 502 |
+
|
| 503 |
+
In this example the ``model`` will no longer be usable in the deepspeed context of the same
|
| 504 |
+
application. i.e. you will need to re-initialize the deepspeed engine, since
|
| 505 |
+
``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
|
| 506 |
+
|
| 507 |
+
If you want it all done for you, use ``load_state_dict_from_zero_checkpoint`` instead.
|
| 508 |
+
|
| 509 |
+
"""
|
| 510 |
+
if tag is None:
|
| 511 |
+
latest_path = os.path.join(checkpoint_dir, 'latest')
|
| 512 |
+
if os.path.isfile(latest_path):
|
| 513 |
+
with open(latest_path, 'r') as fd:
|
| 514 |
+
tag = fd.read().strip()
|
| 515 |
+
else:
|
| 516 |
+
raise ValueError(f"Unable to find 'latest' file at {latest_path}")
|
| 517 |
+
|
| 518 |
+
ds_checkpoint_dir = os.path.join(checkpoint_dir, tag)
|
| 519 |
+
|
| 520 |
+
if not os.path.isdir(ds_checkpoint_dir):
|
| 521 |
+
raise FileNotFoundError(f"Directory '{ds_checkpoint_dir}' doesn't exist")
|
| 522 |
+
|
| 523 |
+
return _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters)
|
| 524 |
+
|
| 525 |
+
|
| 526 |
+
def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir,
|
| 527 |
+
output_dir,
|
| 528 |
+
max_shard_size="5GB",
|
| 529 |
+
safe_serialization=False,
|
| 530 |
+
tag=None,
|
| 531 |
+
exclude_frozen_parameters=False):
|
| 532 |
+
"""
|
| 533 |
+
Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict`` file that can be
|
| 534 |
+
loaded with ``torch.load(file)`` + ``load_state_dict()`` and used for training without DeepSpeed.
|
| 535 |
+
|
| 536 |
+
Args:
|
| 537 |
+
- ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
|
| 538 |
+
- ``output_dir``: directory to the pytorch fp32 state_dict output files
|
| 539 |
+
- ``max_shard_size``: the maximum size for a checkpoint before being sharded, default value is 5GB
|
| 540 |
+
- ``safe_serialization``: whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).
|
| 541 |
+
- ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
|
| 542 |
+
- ``exclude_frozen_parameters``: exclude frozen parameters
|
| 543 |
+
"""
|
| 544 |
+
# Dependency pre-check
|
| 545 |
+
if safe_serialization:
|
| 546 |
+
try:
|
| 547 |
+
from safetensors.torch import save_file
|
| 548 |
+
except ImportError:
|
| 549 |
+
print('If you want to use `safe_serialization`, please `pip install safetensors`')
|
| 550 |
+
raise
|
| 551 |
+
if max_shard_size is not None:
|
| 552 |
+
try:
|
| 553 |
+
from huggingface_hub import split_torch_state_dict_into_shards
|
| 554 |
+
except ImportError:
|
| 555 |
+
print('If you want to use `max_shard_size`, please `pip install huggingface_hub`')
|
| 556 |
+
raise
|
| 557 |
+
|
| 558 |
+
# Convert zero checkpoint to state_dict
|
| 559 |
+
state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag, exclude_frozen_parameters)
|
| 560 |
+
|
| 561 |
+
# Shard the model if it is too big.
|
| 562 |
+
weights_name = "model.safetensors" if safe_serialization else "pytorch_model.bin"
|
| 563 |
+
if max_shard_size is not None:
|
| 564 |
+
filename_pattern = weights_name.replace(".bin", "{suffix}.bin").replace(".safetensors", "{suffix}.safetensors")
|
| 565 |
+
state_dict_split = split_torch_state_dict_into_shards(state_dict,
|
| 566 |
+
filename_pattern=filename_pattern,
|
| 567 |
+
max_shard_size=max_shard_size)
|
| 568 |
+
else:
|
| 569 |
+
from collections import namedtuple
|
| 570 |
+
StateDictSplit = namedtuple("StateDictSplit", ["is_sharded", "filename_to_tensors"])
|
| 571 |
+
state_dict_split = StateDictSplit(is_sharded=False,
|
| 572 |
+
filename_to_tensors={weights_name: list(state_dict.keys())})
|
| 573 |
+
|
| 574 |
+
# Save the model
|
| 575 |
+
filename_to_tensors = state_dict_split.filename_to_tensors.items()
|
| 576 |
+
for shard_file, tensors in tqdm(filename_to_tensors, desc="Saving checkpoint shards"):
|
| 577 |
+
shard = {tensor: state_dict[tensor].contiguous() for tensor in tensors}
|
| 578 |
+
output_path = os.path.join(output_dir, shard_file)
|
| 579 |
+
if safe_serialization:
|
| 580 |
+
save_file(shard, output_path, metadata={"format": "pt"})
|
| 581 |
+
else:
|
| 582 |
+
torch.save(shard, output_path)
|
| 583 |
+
|
| 584 |
+
# Save index if sharded
|
| 585 |
+
if state_dict_split.is_sharded:
|
| 586 |
+
index = {
|
| 587 |
+
"metadata": state_dict_split.metadata,
|
| 588 |
+
"weight_map": state_dict_split.tensor_to_filename,
|
| 589 |
+
}
|
| 590 |
+
save_index_file = "model.safetensors.index.json" if safe_serialization else "pytorch_model.bin.index.json"
|
| 591 |
+
save_index_file = os.path.join(output_dir, save_index_file)
|
| 592 |
+
with open(save_index_file, "w", encoding="utf-8") as f:
|
| 593 |
+
content = json.dumps(index, indent=2, sort_keys=True) + "\n"
|
| 594 |
+
f.write(content)
|
| 595 |
+
|
| 596 |
+
|
| 597 |
+
def load_state_dict_from_zero_checkpoint(model, checkpoint_dir, tag=None):
|
| 598 |
+
"""
|
| 599 |
+
1. Put the provided model to cpu
|
| 600 |
+
2. Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict``
|
| 601 |
+
3. Load it into the provided model
|
| 602 |
+
|
| 603 |
+
Args:
|
| 604 |
+
- ``model``: the model object to update
|
| 605 |
+
- ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
|
| 606 |
+
- ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
|
| 607 |
+
|
| 608 |
+
Returns:
|
| 609 |
+
- ``model`: modified model
|
| 610 |
+
|
| 611 |
+
Make sure you have plenty of CPU memory available before you call this function. If you don't
|
| 612 |
+
have enough use the ``zero_to_fp32.py`` utility to do the conversion. You will find it
|
| 613 |
+
conveniently placed for you in the checkpoint folder.
|
| 614 |
+
|
| 615 |
+
A typical usage might be ::
|
| 616 |
+
|
| 617 |
+
from deepspeed.utils.zero_to_fp32 import load_state_dict_from_zero_checkpoint
|
| 618 |
+
model = load_state_dict_from_zero_checkpoint(trainer.model, checkpoint_dir)
|
| 619 |
+
# submit to model hub or save the model to share with others
|
| 620 |
+
|
| 621 |
+
Note, that once this was run, the ``model`` will no longer be usable in the deepspeed context
|
| 622 |
+
of the same application. i.e. you will need to re-initialize the deepspeed engine, since
|
| 623 |
+
``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
|
| 624 |
+
|
| 625 |
+
"""
|
| 626 |
+
logger.info(f"Extracting fp32 weights")
|
| 627 |
+
state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
|
| 628 |
+
|
| 629 |
+
logger.info(f"Overwriting model with fp32 weights")
|
| 630 |
+
model = model.cpu()
|
| 631 |
+
model.load_state_dict(state_dict, strict=False)
|
| 632 |
+
|
| 633 |
+
return model
|
| 634 |
+
|
| 635 |
+
|
| 636 |
+
if __name__ == "__main__":
|
| 637 |
+
parser = argparse.ArgumentParser()
|
| 638 |
+
parser.add_argument("checkpoint_dir",
|
| 639 |
+
type=str,
|
| 640 |
+
help="path to the desired checkpoint folder, e.g., path/checkpoint-12")
|
| 641 |
+
parser.add_argument("output_dir",
|
| 642 |
+
type=str,
|
| 643 |
+
help="directory to the pytorch fp32 state_dict output files"
|
| 644 |
+
"(e.g. path/checkpoint-12-output/)")
|
| 645 |
+
parser.add_argument(
|
| 646 |
+
"--max_shard_size",
|
| 647 |
+
type=str,
|
| 648 |
+
default="5GB",
|
| 649 |
+
help="The maximum size for a checkpoint before being sharded. Checkpoints shard will then be each of size"
|
| 650 |
+
"lower than this size. If expressed as a string, needs to be digits followed by a unit (like `5MB`"
|
| 651 |
+
"We default it to 5GB in order for models to be able to run easily on free-tier google colab instances"
|
| 652 |
+
"without CPU OOM issues.")
|
| 653 |
+
parser.add_argument(
|
| 654 |
+
"--safe_serialization",
|
| 655 |
+
default=False,
|
| 656 |
+
action='store_true',
|
| 657 |
+
help="Whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).")
|
| 658 |
+
parser.add_argument("-t",
|
| 659 |
+
"--tag",
|
| 660 |
+
type=str,
|
| 661 |
+
default=None,
|
| 662 |
+
help="checkpoint tag used as a unique identifier for checkpoint. e.g., global_step1")
|
| 663 |
+
parser.add_argument("--exclude_frozen_parameters", action='store_true', help="exclude frozen parameters")
|
| 664 |
+
parser.add_argument("-d", "--debug", action='store_true', help="enable debug")
|
| 665 |
+
args = parser.parse_args()
|
| 666 |
+
|
| 667 |
+
debug = args.debug
|
| 668 |
+
|
| 669 |
+
convert_zero_checkpoint_to_fp32_state_dict(args.checkpoint_dir,
|
| 670 |
+
args.output_dir,
|
| 671 |
+
max_shard_size=args.max_shard_size,
|
| 672 |
+
safe_serialization=args.safe_serialization,
|
| 673 |
+
tag=args.tag,
|
| 674 |
+
exclude_frozen_parameters=args.exclude_frozen_parameters)
|
config.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"_name_or_path": "TinyLlama/TinyLlama_v1.1", "architectures": ["ProgressiveYocoLlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 1, "crossDecoder_start_idx": 5, "eos_token_id": 2, "hidden_act": "silu", "hidden_size": 2048, "initializer_range": 0.02, "intermediate_size": 5632, "max_position_embeddings": 2048, "mlp_bias": false, "model_type": "progressive_yoco_llama", "num_attention_heads": 32, "num_hidden_layers": 22, "num_key_value_heads": 4, "pretraining_tp": 1, "rms_norm_eps": 1e-05, "rope_scaling": null, "rope_theta": 10000.0, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "transformers_version": "4.45.2", "use_cache": false, "vocab_size": 32000}
|
generation_config.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 1,
|
| 3 |
+
"eos_token_id": 2,
|
| 4 |
+
"max_length": 2048,
|
| 5 |
+
"pad_token_id": 0,
|
| 6 |
+
"transformers_version": "4.45.2"
|
| 7 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:80623834a487bac356b6ec93fec2507ae5c5a7a8b6346c6eb768ed41ecb25c26
|
| 3 |
+
size 2191734544
|
runs/Nov25_12-49-05_creative-turing-2/events.out.tfevents.1732539135.creative-turing-2.1351148.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:75f595fe45c2bdf73e2de42115fa4aad2fdcb2c1d5f2fb6c979d31a8a7b3babd
|
| 3 |
+
size 36911
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "</s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "</s>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"unk_token": {
|
| 24 |
+
"content": "<unk>",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
}
|
| 30 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
| 3 |
+
size 499723
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"add_prefix_space": null,
|
| 5 |
+
"added_tokens_decoder": {
|
| 6 |
+
"0": {
|
| 7 |
+
"content": "<unk>",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": false,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false,
|
| 12 |
+
"special": true
|
| 13 |
+
},
|
| 14 |
+
"1": {
|
| 15 |
+
"content": "<s>",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": false,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false,
|
| 20 |
+
"special": true
|
| 21 |
+
},
|
| 22 |
+
"2": {
|
| 23 |
+
"content": "</s>",
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"normalized": false,
|
| 26 |
+
"rstrip": false,
|
| 27 |
+
"single_word": false,
|
| 28 |
+
"special": true
|
| 29 |
+
}
|
| 30 |
+
},
|
| 31 |
+
"bos_token": "<s>",
|
| 32 |
+
"chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ system_message }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ content }}{% elif message['role'] == 'assistant' %}{{ content }}{% endif %}{% endfor %}",
|
| 33 |
+
"clean_up_tokenization_spaces": false,
|
| 34 |
+
"eos_token": "</s>",
|
| 35 |
+
"legacy": false,
|
| 36 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 37 |
+
"pad_token": "</s>",
|
| 38 |
+
"padding_side": "right",
|
| 39 |
+
"sp_model_kwargs": {},
|
| 40 |
+
"split_special_tokens": false,
|
| 41 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 42 |
+
"unk_token": "<unk>",
|
| 43 |
+
"use_default_system_prompt": false
|
| 44 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 0.19745502413339183,
|
| 3 |
+
"total_flos": 349677715193856.0,
|
| 4 |
+
"train_loss": 1.9421729667981467,
|
| 5 |
+
"train_runtime": 5209.8016,
|
| 6 |
+
"train_samples_per_second": 58.044,
|
| 7 |
+
"train_steps_per_second": 0.029
|
| 8 |
+
}
|
trainer_log.jsonl
ADDED
|
@@ -0,0 +1,151 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{"current_steps": 1, "total_steps": 150, "loss": 1.819, "lr": 2e-05, "epoch": 0.0013163668275559457, "percentage": 0.67, "elapsed_time": "0:00:37", "remaining_time": "1:33:47"}
|
| 2 |
+
{"current_steps": 2, "total_steps": 150, "loss": 1.786, "lr": 1.999777729859618e-05, "epoch": 0.0026327336551118913, "percentage": 1.33, "elapsed_time": "0:01:11", "remaining_time": "1:28:42"}
|
| 3 |
+
{"current_steps": 3, "total_steps": 150, "loss": 2.1123, "lr": 1.9991110182465032e-05, "epoch": 0.003949100482667837, "percentage": 2.0, "elapsed_time": "0:01:46", "remaining_time": "1:26:47"}
|
| 4 |
+
{"current_steps": 4, "total_steps": 150, "loss": 2.1052, "lr": 1.9980001615408228e-05, "epoch": 0.005265467310223783, "percentage": 2.67, "elapsed_time": "0:02:20", "remaining_time": "1:25:35"}
|
| 5 |
+
{"current_steps": 5, "total_steps": 150, "loss": 2.0417, "lr": 1.9964456535631287e-05, "epoch": 0.006581834137779728, "percentage": 3.33, "elapsed_time": "0:02:55", "remaining_time": "1:24:40"}
|
| 6 |
+
{"current_steps": 6, "total_steps": 150, "loss": 1.9756, "lr": 1.9944481853548335e-05, "epoch": 0.007898200965335674, "percentage": 4.0, "elapsed_time": "0:03:29", "remaining_time": "1:23:52"}
|
| 7 |
+
{"current_steps": 7, "total_steps": 150, "loss": 1.9305, "lr": 1.9920086448710162e-05, "epoch": 0.009214567792891619, "percentage": 4.67, "elapsed_time": "0:04:04", "remaining_time": "1:23:08"}
|
| 8 |
+
{"current_steps": 8, "total_steps": 150, "loss": 1.9001, "lr": 1.9891281165856876e-05, "epoch": 0.010530934620447565, "percentage": 5.33, "elapsed_time": "0:04:38", "remaining_time": "1:22:27"}
|
| 9 |
+
{"current_steps": 9, "total_steps": 150, "loss": 1.9285, "lr": 1.9858078810097004e-05, "epoch": 0.01184730144800351, "percentage": 6.0, "elapsed_time": "0:05:13", "remaining_time": "1:21:47"}
|
| 10 |
+
{"current_steps": 10, "total_steps": 150, "loss": 1.9158, "lr": 1.98204941412151e-05, "epoch": 0.013163668275559455, "percentage": 6.67, "elapsed_time": "0:05:47", "remaining_time": "1:21:09"}
|
| 11 |
+
{"current_steps": 11, "total_steps": 150, "loss": 1.9177, "lr": 1.9778543867110428e-05, "epoch": 0.014480035103115402, "percentage": 7.33, "elapsed_time": "0:06:22", "remaining_time": "1:20:31"}
|
| 12 |
+
{"current_steps": 12, "total_steps": 150, "loss": 1.9124, "lr": 1.9732246636369605e-05, "epoch": 0.015796401930671347, "percentage": 8.0, "elapsed_time": "0:06:56", "remaining_time": "1:19:54"}
|
| 13 |
+
{"current_steps": 13, "total_steps": 150, "loss": 1.9048, "lr": 1.968162302997659e-05, "epoch": 0.017112768758227294, "percentage": 8.67, "elapsed_time": "0:07:31", "remaining_time": "1:19:17"}
|
| 14 |
+
{"current_steps": 14, "total_steps": 150, "loss": 1.8905, "lr": 1.962669555216358e-05, "epoch": 0.018429135585783237, "percentage": 9.33, "elapsed_time": "0:08:05", "remaining_time": "1:18:40"}
|
| 15 |
+
{"current_steps": 15, "total_steps": 150, "loss": 1.9179, "lr": 1.9567488620406984e-05, "epoch": 0.019745502413339184, "percentage": 10.0, "elapsed_time": "0:08:40", "remaining_time": "1:18:04"}
|
| 16 |
+
{"current_steps": 16, "total_steps": 150, "loss": 1.8956, "lr": 1.9504028554572865e-05, "epoch": 0.02106186924089513, "percentage": 10.67, "elapsed_time": "0:09:15", "remaining_time": "1:17:28"}
|
| 17 |
+
{"current_steps": 17, "total_steps": 150, "loss": 1.9106, "lr": 1.943634356521671e-05, "epoch": 0.022378236068451074, "percentage": 11.33, "elapsed_time": "0:09:49", "remaining_time": "1:16:52"}
|
| 18 |
+
{"current_steps": 18, "total_steps": 150, "loss": 1.8714, "lr": 1.9364463741042694e-05, "epoch": 0.02369460289600702, "percentage": 12.0, "elapsed_time": "0:10:24", "remaining_time": "1:16:16"}
|
| 19 |
+
{"current_steps": 19, "total_steps": 150, "loss": 1.8805, "lr": 1.928842103552803e-05, "epoch": 0.025010969723562967, "percentage": 12.67, "elapsed_time": "0:10:58", "remaining_time": "1:15:41"}
|
| 20 |
+
{"current_steps": 20, "total_steps": 150, "loss": 1.8992, "lr": 1.920824925271838e-05, "epoch": 0.02632733655111891, "percentage": 13.33, "elapsed_time": "0:11:33", "remaining_time": "1:15:05"}
|
| 21 |
+
{"current_steps": 21, "total_steps": 150, "loss": 1.8774, "lr": 1.9123984032200586e-05, "epoch": 0.027643703378674857, "percentage": 14.0, "elapsed_time": "0:12:07", "remaining_time": "1:14:30"}
|
| 22 |
+
{"current_steps": 22, "total_steps": 150, "loss": 1.8978, "lr": 1.9035662833259433e-05, "epoch": 0.028960070206230804, "percentage": 14.67, "elapsed_time": "0:12:42", "remaining_time": "1:13:55"}
|
| 23 |
+
{"current_steps": 23, "total_steps": 150, "loss": 1.8965, "lr": 1.8943324918225495e-05, "epoch": 0.030276437033786747, "percentage": 15.33, "elapsed_time": "0:13:16", "remaining_time": "1:13:19"}
|
| 24 |
+
{"current_steps": 24, "total_steps": 150, "loss": 1.8831, "lr": 1.8847011335021447e-05, "epoch": 0.031592803861342694, "percentage": 16.0, "elapsed_time": "0:13:51", "remaining_time": "1:12:44"}
|
| 25 |
+
{"current_steps": 25, "total_steps": 150, "loss": 1.8881, "lr": 1.874676489891461e-05, "epoch": 0.03290917068889864, "percentage": 16.67, "elapsed_time": "0:14:25", "remaining_time": "1:12:09"}
|
| 26 |
+
{"current_steps": 26, "total_steps": 150, "loss": 1.889, "lr": 1.8642630173483832e-05, "epoch": 0.03422553751645459, "percentage": 17.33, "elapsed_time": "0:15:00", "remaining_time": "1:11:34"}
|
| 27 |
+
{"current_steps": 27, "total_steps": 150, "loss": 1.8936, "lr": 1.85346534508092e-05, "epoch": 0.03554190434401053, "percentage": 18.0, "elapsed_time": "0:15:34", "remaining_time": "1:10:59"}
|
| 28 |
+
{"current_steps": 28, "total_steps": 150, "loss": 1.9131, "lr": 1.8422882730893323e-05, "epoch": 0.036858271171566474, "percentage": 18.67, "elapsed_time": "0:16:09", "remaining_time": "1:10:24"}
|
| 29 |
+
{"current_steps": 29, "total_steps": 150, "loss": 1.9104, "lr": 1.8307367700323412e-05, "epoch": 0.03817463799912242, "percentage": 19.33, "elapsed_time": "0:16:44", "remaining_time": "1:09:49"}
|
| 30 |
+
{"current_steps": 30, "total_steps": 150, "loss": 1.8807, "lr": 1.8188159710183595e-05, "epoch": 0.03949100482667837, "percentage": 20.0, "elapsed_time": "0:17:18", "remaining_time": "1:09:14"}
|
| 31 |
+
{"current_steps": 31, "total_steps": 150, "loss": 1.9261, "lr": 1.8065311753227272e-05, "epoch": 0.040807371654234315, "percentage": 20.67, "elapsed_time": "0:17:53", "remaining_time": "1:08:39"}
|
| 32 |
+
{"current_steps": 32, "total_steps": 150, "loss": 1.9178, "lr": 1.7938878440319722e-05, "epoch": 0.04212373848179026, "percentage": 21.33, "elapsed_time": "0:18:27", "remaining_time": "1:08:04"}
|
| 33 |
+
{"current_steps": 33, "total_steps": 150, "loss": 1.9212, "lr": 1.7808915976161364e-05, "epoch": 0.0434401053093462, "percentage": 22.0, "elapsed_time": "0:19:02", "remaining_time": "1:07:29"}
|
| 34 |
+
{"current_steps": 34, "total_steps": 150, "loss": 1.9019, "lr": 1.7675482134302503e-05, "epoch": 0.04475647213690215, "percentage": 22.67, "elapsed_time": "0:19:36", "remaining_time": "1:06:54"}
|
| 35 |
+
{"current_steps": 35, "total_steps": 150, "loss": 1.9065, "lr": 1.753863623146066e-05, "epoch": 0.046072838964458095, "percentage": 23.33, "elapsed_time": "0:20:11", "remaining_time": "1:06:20"}
|
| 36 |
+
{"current_steps": 36, "total_steps": 150, "loss": 1.8926, "lr": 1.7398439101151908e-05, "epoch": 0.04738920579201404, "percentage": 24.0, "elapsed_time": "0:20:45", "remaining_time": "1:05:45"}
|
| 37 |
+
{"current_steps": 37, "total_steps": 150, "loss": 1.898, "lr": 1.7254953066647915e-05, "epoch": 0.04870557261956999, "percentage": 24.67, "elapsed_time": "0:21:20", "remaining_time": "1:05:10"}
|
| 38 |
+
{"current_steps": 38, "total_steps": 150, "loss": 1.9314, "lr": 1.710824191327075e-05, "epoch": 0.050021939447125935, "percentage": 25.33, "elapsed_time": "0:21:54", "remaining_time": "1:04:35"}
|
| 39 |
+
{"current_steps": 39, "total_steps": 150, "loss": 1.908, "lr": 1.695837086003772e-05, "epoch": 0.051338306274681875, "percentage": 26.0, "elapsed_time": "0:22:29", "remaining_time": "1:04:00"}
|
| 40 |
+
{"current_steps": 40, "total_steps": 150, "loss": 1.907, "lr": 1.680540653066891e-05, "epoch": 0.05265467310223782, "percentage": 26.67, "elapsed_time": "0:23:03", "remaining_time": "1:03:25"}
|
| 41 |
+
{"current_steps": 41, "total_steps": 150, "loss": 1.908, "lr": 1.6649416923970248e-05, "epoch": 0.05397103992979377, "percentage": 27.33, "elapsed_time": "0:23:38", "remaining_time": "1:02:51"}
|
| 42 |
+
{"current_steps": 42, "total_steps": 150, "loss": 1.9006, "lr": 1.649047138360529e-05, "epoch": 0.055287406757349715, "percentage": 28.0, "elapsed_time": "0:24:13", "remaining_time": "1:02:16"}
|
| 43 |
+
{"current_steps": 43, "total_steps": 150, "loss": 1.9023, "lr": 1.632864056726917e-05, "epoch": 0.05660377358490566, "percentage": 28.67, "elapsed_time": "0:24:47", "remaining_time": "1:01:41"}
|
| 44 |
+
{"current_steps": 44, "total_steps": 150, "loss": 1.9284, "lr": 1.6163996415278423e-05, "epoch": 0.05792014041246161, "percentage": 29.33, "elapsed_time": "0:25:22", "remaining_time": "1:01:06"}
|
| 45 |
+
{"current_steps": 45, "total_steps": 150, "loss": 1.9089, "lr": 1.5996612118590604e-05, "epoch": 0.05923650724001755, "percentage": 30.0, "elapsed_time": "0:25:56", "remaining_time": "1:00:32"}
|
| 46 |
+
{"current_steps": 46, "total_steps": 150, "loss": 1.9285, "lr": 1.5826562086267956e-05, "epoch": 0.060552874067573495, "percentage": 30.67, "elapsed_time": "0:26:31", "remaining_time": "0:59:57"}
|
| 47 |
+
{"current_steps": 47, "total_steps": 150, "loss": 1.916, "lr": 1.565392191239959e-05, "epoch": 0.06186924089512944, "percentage": 31.33, "elapsed_time": "0:27:05", "remaining_time": "0:59:22"}
|
| 48 |
+
{"current_steps": 48, "total_steps": 150, "loss": 1.9069, "lr": 1.5478768342496872e-05, "epoch": 0.06318560772268539, "percentage": 32.0, "elapsed_time": "0:27:40", "remaining_time": "0:58:48"}
|
| 49 |
+
{"current_steps": 49, "total_steps": 150, "loss": 1.9224, "lr": 1.5301179239376936e-05, "epoch": 0.06450197455024133, "percentage": 32.67, "elapsed_time": "0:28:14", "remaining_time": "0:58:13"}
|
| 50 |
+
{"current_steps": 50, "total_steps": 150, "loss": 1.9022, "lr": 1.512123354854955e-05, "epoch": 0.06581834137779728, "percentage": 33.33, "elapsed_time": "0:28:49", "remaining_time": "0:57:38"}
|
| 51 |
+
{"current_steps": 51, "total_steps": 150, "loss": 1.9024, "lr": 1.4939011263122635e-05, "epoch": 0.06713470820535322, "percentage": 34.0, "elapsed_time": "0:29:30", "remaining_time": "0:57:17"}
|
| 52 |
+
{"current_steps": 52, "total_steps": 150, "loss": 1.9133, "lr": 1.4754593388242117e-05, "epoch": 0.06845107503290918, "percentage": 34.67, "elapsed_time": "0:30:05", "remaining_time": "0:56:42"}
|
| 53 |
+
{"current_steps": 53, "total_steps": 150, "loss": 1.9044, "lr": 1.4568061905081874e-05, "epoch": 0.06976744186046512, "percentage": 35.33, "elapsed_time": "0:30:39", "remaining_time": "0:56:07"}
|
| 54 |
+
{"current_steps": 54, "total_steps": 150, "loss": 1.9176, "lr": 1.4379499734399797e-05, "epoch": 0.07108380868802106, "percentage": 36.0, "elapsed_time": "0:31:14", "remaining_time": "0:55:32"}
|
| 55 |
+
{"current_steps": 55, "total_steps": 150, "loss": 1.915, "lr": 1.4188990699676186e-05, "epoch": 0.07240017551557701, "percentage": 36.67, "elapsed_time": "0:31:48", "remaining_time": "0:54:57"}
|
| 56 |
+
{"current_steps": 56, "total_steps": 150, "loss": 1.9282, "lr": 1.3996619489850822e-05, "epoch": 0.07371654234313295, "percentage": 37.33, "elapsed_time": "0:32:23", "remaining_time": "0:54:22"}
|
| 57 |
+
{"current_steps": 57, "total_steps": 150, "loss": 1.9121, "lr": 1.3802471621675337e-05, "epoch": 0.0750329091706889, "percentage": 38.0, "elapsed_time": "0:32:57", "remaining_time": "0:53:47"}
|
| 58 |
+
{"current_steps": 58, "total_steps": 150, "loss": 1.9348, "lr": 1.3606633401697557e-05, "epoch": 0.07634927599824484, "percentage": 38.67, "elapsed_time": "0:33:32", "remaining_time": "0:53:12"}
|
| 59 |
+
{"current_steps": 59, "total_steps": 150, "loss": 1.9162, "lr": 1.340919188789477e-05, "epoch": 0.0776656428258008, "percentage": 39.33, "elapsed_time": "0:34:07", "remaining_time": "0:52:37"}
|
| 60 |
+
{"current_steps": 60, "total_steps": 150, "loss": 1.9349, "lr": 1.3210234850972966e-05, "epoch": 0.07898200965335674, "percentage": 40.0, "elapsed_time": "0:34:41", "remaining_time": "0:52:02"}
|
| 61 |
+
{"current_steps": 61, "total_steps": 150, "loss": 1.9344, "lr": 1.300985073534919e-05, "epoch": 0.08029837648091268, "percentage": 40.67, "elapsed_time": "0:35:16", "remaining_time": "0:51:27"}
|
| 62 |
+
{"current_steps": 62, "total_steps": 150, "loss": 1.9144, "lr": 1.280812861983446e-05, "epoch": 0.08161474330846863, "percentage": 41.33, "elapsed_time": "0:35:50", "remaining_time": "0:50:52"}
|
| 63 |
+
{"current_steps": 63, "total_steps": 150, "loss": 1.9202, "lr": 1.2605158178034656e-05, "epoch": 0.08293111013602457, "percentage": 42.0, "elapsed_time": "0:36:25", "remaining_time": "0:50:17"}
|
| 64 |
+
{"current_steps": 64, "total_steps": 150, "loss": 1.8986, "lr": 1.2401029638486952e-05, "epoch": 0.08424747696358052, "percentage": 42.67, "elapsed_time": "0:36:59", "remaining_time": "0:49:43"}
|
| 65 |
+
{"current_steps": 65, "total_steps": 150, "loss": 1.9367, "lr": 1.219583374454963e-05, "epoch": 0.08556384379113646, "percentage": 43.33, "elapsed_time": "0:37:34", "remaining_time": "0:49:08"}
|
| 66 |
+
{"current_steps": 66, "total_steps": 150, "loss": 1.9536, "lr": 1.1989661714063e-05, "epoch": 0.0868802106186924, "percentage": 44.0, "elapsed_time": "0:38:09", "remaining_time": "0:48:33"}
|
| 67 |
+
{"current_steps": 67, "total_steps": 150, "loss": 1.942, "lr": 1.1782605198799371e-05, "epoch": 0.08819657744624836, "percentage": 44.67, "elapsed_time": "0:38:43", "remaining_time": "0:47:58"}
|
| 68 |
+
{"current_steps": 68, "total_steps": 150, "loss": 1.9149, "lr": 1.157475624372018e-05, "epoch": 0.0895129442738043, "percentage": 45.33, "elapsed_time": "0:39:18", "remaining_time": "0:47:23"}
|
| 69 |
+
{"current_steps": 69, "total_steps": 150, "loss": 1.9258, "lr": 1.1366207246058269e-05, "epoch": 0.09082931110136025, "percentage": 46.0, "elapsed_time": "0:39:52", "remaining_time": "0:46:48"}
|
| 70 |
+
{"current_steps": 70, "total_steps": 150, "loss": 1.9395, "lr": 1.1157050914243614e-05, "epoch": 0.09214567792891619, "percentage": 46.67, "elapsed_time": "0:40:27", "remaining_time": "0:46:13"}
|
| 71 |
+
{"current_steps": 71, "total_steps": 150, "loss": 1.9354, "lr": 1.0947380226690686e-05, "epoch": 0.09346204475647214, "percentage": 47.33, "elapsed_time": "0:41:01", "remaining_time": "0:45:39"}
|
| 72 |
+
{"current_steps": 72, "total_steps": 150, "loss": 1.9259, "lr": 1.0737288390465792e-05, "epoch": 0.09477841158402808, "percentage": 48.0, "elapsed_time": "0:41:36", "remaining_time": "0:45:04"}
|
| 73 |
+
{"current_steps": 73, "total_steps": 150, "loss": 1.9493, "lr": 1.0526868799852797e-05, "epoch": 0.09609477841158402, "percentage": 48.67, "elapsed_time": "0:42:10", "remaining_time": "0:44:29"}
|
| 74 |
+
{"current_steps": 74, "total_steps": 150, "loss": 1.9429, "lr": 1.031621499483559e-05, "epoch": 0.09741114523913998, "percentage": 49.33, "elapsed_time": "0:42:45", "remaining_time": "0:43:54"}
|
| 75 |
+
{"current_steps": 75, "total_steps": 150, "loss": 1.9348, "lr": 1.0105420619515798e-05, "epoch": 0.09872751206669592, "percentage": 50.0, "elapsed_time": "0:43:19", "remaining_time": "0:43:19"}
|
| 76 |
+
{"current_steps": 76, "total_steps": 150, "loss": 1.951, "lr": 9.894579380484206e-06, "epoch": 0.10004387889425187, "percentage": 50.67, "elapsed_time": "0:43:54", "remaining_time": "0:42:45"}
|
| 77 |
+
{"current_steps": 77, "total_steps": 150, "loss": 1.9568, "lr": 9.683785005164412e-06, "epoch": 0.10136024572180781, "percentage": 51.33, "elapsed_time": "0:44:29", "remaining_time": "0:42:10"}
|
| 78 |
+
{"current_steps": 78, "total_steps": 150, "loss": 1.9635, "lr": 9.473131200147205e-06, "epoch": 0.10267661254936375, "percentage": 52.0, "elapsed_time": "0:45:03", "remaining_time": "0:41:35"}
|
| 79 |
+
{"current_steps": 79, "total_steps": 150, "loss": 1.9493, "lr": 9.262711609534211e-06, "epoch": 0.1039929793769197, "percentage": 52.67, "elapsed_time": "0:45:38", "remaining_time": "0:41:00"}
|
| 80 |
+
{"current_steps": 80, "total_steps": 150, "loss": 1.9416, "lr": 9.052619773309318e-06, "epoch": 0.10530934620447564, "percentage": 53.33, "elapsed_time": "0:46:12", "remaining_time": "0:40:26"}
|
| 81 |
+
{"current_steps": 81, "total_steps": 150, "loss": 1.9375, "lr": 8.842949085756389e-06, "epoch": 0.1066257130320316, "percentage": 54.0, "elapsed_time": "0:46:47", "remaining_time": "0:39:51"}
|
| 82 |
+
{"current_steps": 82, "total_steps": 150, "loss": 1.9482, "lr": 8.633792753941733e-06, "epoch": 0.10794207985958754, "percentage": 54.67, "elapsed_time": "0:47:21", "remaining_time": "0:39:16"}
|
| 83 |
+
{"current_steps": 83, "total_steps": 150, "loss": 1.9274, "lr": 8.425243756279824e-06, "epoch": 0.10925844668714349, "percentage": 55.33, "elapsed_time": "0:47:56", "remaining_time": "0:38:41"}
|
| 84 |
+
{"current_steps": 84, "total_steps": 150, "loss": 1.9494, "lr": 8.217394801200632e-06, "epoch": 0.11057481351469943, "percentage": 56.0, "elapsed_time": "0:48:30", "remaining_time": "0:38:07"}
|
| 85 |
+
{"current_steps": 85, "total_steps": 150, "loss": 1.9383, "lr": 8.010338285937006e-06, "epoch": 0.11189118034225537, "percentage": 56.67, "elapsed_time": "0:49:05", "remaining_time": "0:37:32"}
|
| 86 |
+
{"current_steps": 86, "total_steps": 150, "loss": 1.9438, "lr": 7.804166255450372e-06, "epoch": 0.11320754716981132, "percentage": 57.33, "elapsed_time": "0:49:39", "remaining_time": "0:36:57"}
|
| 87 |
+
{"current_steps": 87, "total_steps": 150, "loss": 1.9486, "lr": 7.598970361513052e-06, "epoch": 0.11452391399736726, "percentage": 58.0, "elapsed_time": "0:50:14", "remaining_time": "0:36:22"}
|
| 88 |
+
{"current_steps": 88, "total_steps": 150, "loss": 1.9274, "lr": 7.394841821965345e-06, "epoch": 0.11584028082492322, "percentage": 58.67, "elapsed_time": "0:50:48", "remaining_time": "0:35:48"}
|
| 89 |
+
{"current_steps": 89, "total_steps": 150, "loss": 1.9524, "lr": 7.191871380165538e-06, "epoch": 0.11715664765247916, "percentage": 59.33, "elapsed_time": "0:51:23", "remaining_time": "0:35:13"}
|
| 90 |
+
{"current_steps": 90, "total_steps": 150, "loss": 1.9445, "lr": 6.990149264650814e-06, "epoch": 0.1184730144800351, "percentage": 60.0, "elapsed_time": "0:51:58", "remaining_time": "0:34:38"}
|
| 91 |
+
{"current_steps": 91, "total_steps": 150, "loss": 1.9515, "lr": 6.789765149027039e-06, "epoch": 0.11978938130759105, "percentage": 60.67, "elapsed_time": "0:52:32", "remaining_time": "0:34:03"}
|
| 92 |
+
{"current_steps": 92, "total_steps": 150, "loss": 1.969, "lr": 6.590808112105232e-06, "epoch": 0.12110574813514699, "percentage": 61.33, "elapsed_time": "0:53:07", "remaining_time": "0:33:29"}
|
| 93 |
+
{"current_steps": 93, "total_steps": 150, "loss": 1.954, "lr": 6.3933665983024465e-06, "epoch": 0.12242211496270294, "percentage": 62.0, "elapsed_time": "0:53:41", "remaining_time": "0:32:54"}
|
| 94 |
+
{"current_steps": 94, "total_steps": 150, "loss": 1.9313, "lr": 6.197528378324664e-06, "epoch": 0.12373848179025888, "percentage": 62.67, "elapsed_time": "0:54:16", "remaining_time": "0:32:19"}
|
| 95 |
+
{"current_steps": 95, "total_steps": 150, "loss": 1.9602, "lr": 6.003380510149179e-06, "epoch": 0.12505484861781482, "percentage": 63.33, "elapsed_time": "0:54:50", "remaining_time": "0:31:45"}
|
| 96 |
+
{"current_steps": 96, "total_steps": 150, "loss": 1.9831, "lr": 5.8110093003238175e-06, "epoch": 0.12637121544537078, "percentage": 64.0, "elapsed_time": "0:55:25", "remaining_time": "0:31:10"}
|
| 97 |
+
{"current_steps": 97, "total_steps": 150, "loss": 1.9562, "lr": 5.620500265600206e-06, "epoch": 0.12768758227292673, "percentage": 64.67, "elapsed_time": "0:55:59", "remaining_time": "0:30:35"}
|
| 98 |
+
{"current_steps": 98, "total_steps": 150, "loss": 1.9679, "lr": 5.431938094918132e-06, "epoch": 0.12900394910048266, "percentage": 65.33, "elapsed_time": "0:56:34", "remaining_time": "0:30:01"}
|
| 99 |
+
{"current_steps": 99, "total_steps": 150, "loss": 1.9667, "lr": 5.245406611757882e-06, "epoch": 0.1303203159280386, "percentage": 66.0, "elapsed_time": "0:57:08", "remaining_time": "0:29:26"}
|
| 100 |
+
{"current_steps": 100, "total_steps": 150, "loss": 1.9486, "lr": 5.060988736877366e-06, "epoch": 0.13163668275559456, "percentage": 66.67, "elapsed_time": "0:57:43", "remaining_time": "0:28:51"}
|
| 101 |
+
{"current_steps": 101, "total_steps": 150, "loss": 1.9557, "lr": 4.878766451450451e-06, "epoch": 0.13295304958315052, "percentage": 67.33, "elapsed_time": "0:58:26", "remaining_time": "0:28:21"}
|
| 102 |
+
{"current_steps": 102, "total_steps": 150, "loss": 1.9506, "lr": 4.698820760623064e-06, "epoch": 0.13426941641070644, "percentage": 68.0, "elapsed_time": "0:59:01", "remaining_time": "0:27:46"}
|
| 103 |
+
{"current_steps": 103, "total_steps": 150, "loss": 1.9639, "lr": 4.5212316575031325e-06, "epoch": 0.1355857832382624, "percentage": 68.67, "elapsed_time": "0:59:35", "remaining_time": "0:27:11"}
|
| 104 |
+
{"current_steps": 104, "total_steps": 150, "loss": 1.9683, "lr": 4.346078087600411e-06, "epoch": 0.13690215006581835, "percentage": 69.33, "elapsed_time": "1:00:10", "remaining_time": "0:26:36"}
|
| 105 |
+
{"current_steps": 105, "total_steps": 150, "loss": 1.9659, "lr": 4.173437913732048e-06, "epoch": 0.13821851689337428, "percentage": 70.0, "elapsed_time": "1:00:44", "remaining_time": "0:26:02"}
|
| 106 |
+
{"current_steps": 106, "total_steps": 150, "loss": 1.9704, "lr": 4.003387881409397e-06, "epoch": 0.13953488372093023, "percentage": 70.67, "elapsed_time": "1:01:19", "remaining_time": "0:25:27"}
|
| 107 |
+
{"current_steps": 107, "total_steps": 150, "loss": 1.97, "lr": 3.836003584721577e-06, "epoch": 0.14085125054848618, "percentage": 71.33, "elapsed_time": "1:01:54", "remaining_time": "0:24:52"}
|
| 108 |
+
{"current_steps": 108, "total_steps": 150, "loss": 1.9554, "lr": 3.6713594327308343e-06, "epoch": 0.1421676173760421, "percentage": 72.0, "elapsed_time": "1:02:28", "remaining_time": "0:24:17"}
|
| 109 |
+
{"current_steps": 109, "total_steps": 150, "loss": 1.9737, "lr": 3.509528616394716e-06, "epoch": 0.14348398420359806, "percentage": 72.67, "elapsed_time": "1:03:03", "remaining_time": "0:23:43"}
|
| 110 |
+
{"current_steps": 110, "total_steps": 150, "loss": 1.9699, "lr": 3.3505830760297543e-06, "epoch": 0.14480035103115402, "percentage": 73.33, "elapsed_time": "1:03:37", "remaining_time": "0:23:08"}
|
| 111 |
+
{"current_steps": 111, "total_steps": 150, "loss": 1.9767, "lr": 3.1945934693310897e-06, "epoch": 0.14611671785870997, "percentage": 74.0, "elapsed_time": "1:04:12", "remaining_time": "0:22:33"}
|
| 112 |
+
{"current_steps": 112, "total_steps": 150, "loss": 2.0023, "lr": 3.0416291399622834e-06, "epoch": 0.1474330846862659, "percentage": 74.67, "elapsed_time": "1:04:46", "remaining_time": "0:21:58"}
|
| 113 |
+
{"current_steps": 113, "total_steps": 150, "loss": 1.955, "lr": 2.891758086729253e-06, "epoch": 0.14874945151382185, "percentage": 75.33, "elapsed_time": "1:05:21", "remaining_time": "0:21:23"}
|
| 114 |
+
{"current_steps": 114, "total_steps": 150, "loss": 1.9611, "lr": 2.7450469333520856e-06, "epoch": 0.1500658183413778, "percentage": 76.0, "elapsed_time": "1:05:55", "remaining_time": "0:20:49"}
|
| 115 |
+
{"current_steps": 115, "total_steps": 150, "loss": 1.9658, "lr": 2.6015608988480956e-06, "epoch": 0.15138218516893373, "percentage": 76.67, "elapsed_time": "1:06:30", "remaining_time": "0:20:14"}
|
| 116 |
+
{"current_steps": 116, "total_steps": 150, "loss": 1.9753, "lr": 2.4613637685393433e-06, "epoch": 0.15269855199648968, "percentage": 77.33, "elapsed_time": "1:07:04", "remaining_time": "0:19:39"}
|
| 117 |
+
{"current_steps": 117, "total_steps": 150, "loss": 1.9495, "lr": 2.324517865697501e-06, "epoch": 0.15401491882404564, "percentage": 78.0, "elapsed_time": "1:07:39", "remaining_time": "0:19:04"}
|
| 118 |
+
{"current_steps": 118, "total_steps": 150, "loss": 1.9628, "lr": 2.19108402383864e-06, "epoch": 0.1553312856516016, "percentage": 78.67, "elapsed_time": "1:08:14", "remaining_time": "0:18:30"}
|
| 119 |
+
{"current_steps": 119, "total_steps": 150, "loss": 1.9823, "lr": 2.06112155968028e-06, "epoch": 0.15664765247915752, "percentage": 79.33, "elapsed_time": "1:08:48", "remaining_time": "0:17:55"}
|
| 120 |
+
{"current_steps": 120, "total_steps": 150, "loss": 1.9875, "lr": 1.9346882467727323e-06, "epoch": 0.15796401930671347, "percentage": 80.0, "elapsed_time": "1:09:23", "remaining_time": "0:17:20"}
|
| 121 |
+
{"current_steps": 121, "total_steps": 150, "loss": 1.9805, "lr": 1.811840289816409e-06, "epoch": 0.15928038613426942, "percentage": 80.67, "elapsed_time": "1:09:57", "remaining_time": "0:16:46"}
|
| 122 |
+
{"current_steps": 122, "total_steps": 150, "loss": 1.9818, "lr": 1.6926322996765899e-06, "epoch": 0.16059675296182535, "percentage": 81.33, "elapsed_time": "1:10:32", "remaining_time": "0:16:11"}
|
| 123 |
+
{"current_steps": 123, "total_steps": 150, "loss": 1.9859, "lr": 1.5771172691066793e-06, "epoch": 0.1619131197893813, "percentage": 82.0, "elapsed_time": "1:11:06", "remaining_time": "0:15:36"}
|
| 124 |
+
{"current_steps": 124, "total_steps": 150, "loss": 2.0096, "lr": 1.4653465491908003e-06, "epoch": 0.16322948661693726, "percentage": 82.67, "elapsed_time": "1:11:41", "remaining_time": "0:15:01"}
|
| 125 |
+
{"current_steps": 125, "total_steps": 150, "loss": 1.9654, "lr": 1.3573698265161683e-06, "epoch": 0.1645458534444932, "percentage": 83.33, "elapsed_time": "1:12:15", "remaining_time": "0:14:27"}
|
| 126 |
+
{"current_steps": 126, "total_steps": 150, "loss": 1.9708, "lr": 1.2532351010853916e-06, "epoch": 0.16586222027204914, "percentage": 84.0, "elapsed_time": "1:12:50", "remaining_time": "0:13:52"}
|
| 127 |
+
{"current_steps": 127, "total_steps": 150, "loss": 1.9787, "lr": 1.152988664978556e-06, "epoch": 0.1671785870996051, "percentage": 84.67, "elapsed_time": "1:13:24", "remaining_time": "0:13:17"}
|
| 128 |
+
{"current_steps": 128, "total_steps": 150, "loss": 1.9858, "lr": 1.0566750817745076e-06, "epoch": 0.16849495392716105, "percentage": 85.33, "elapsed_time": "1:13:59", "remaining_time": "0:12:43"}
|
| 129 |
+
{"current_steps": 129, "total_steps": 150, "loss": 1.9781, "lr": 9.6433716674057e-07, "epoch": 0.16981132075471697, "percentage": 86.0, "elapsed_time": "1:14:33", "remaining_time": "0:12:08"}
|
| 130 |
+
{"current_steps": 130, "total_steps": 150, "loss": 1.9827, "lr": 8.760159677994174e-07, "epoch": 0.17112768758227292, "percentage": 86.67, "elapsed_time": "1:15:08", "remaining_time": "0:11:33"}
|
| 131 |
+
{"current_steps": 131, "total_steps": 150, "loss": 1.9741, "lr": 7.91750747281621e-07, "epoch": 0.17244405440982888, "percentage": 87.33, "elapsed_time": "1:15:42", "remaining_time": "0:10:58"}
|
| 132 |
+
{"current_steps": 132, "total_steps": 150, "loss": 1.9949, "lr": 7.115789644719728e-07, "epoch": 0.1737604212373848, "percentage": 88.0, "elapsed_time": "1:16:17", "remaining_time": "0:10:24"}
|
| 133 |
+
{"current_steps": 133, "total_steps": 150, "loss": 1.9762, "lr": 6.355362589573078e-07, "epoch": 0.17507678806494076, "percentage": 88.67, "elapsed_time": "1:16:51", "remaining_time": "0:09:49"}
|
| 134 |
+
{"current_steps": 134, "total_steps": 150, "loss": 1.9818, "lr": 5.636564347832907e-07, "epoch": 0.1763931548924967, "percentage": 89.33, "elapsed_time": "1:17:26", "remaining_time": "0:09:14"}
|
| 135 |
+
{"current_steps": 135, "total_steps": 150, "loss": 1.983, "lr": 4.95971445427137e-07, "epoch": 0.17770952172005267, "percentage": 90.0, "elapsed_time": "1:18:01", "remaining_time": "0:08:40"}
|
| 136 |
+
{"current_steps": 136, "total_steps": 150, "loss": 1.9708, "lr": 4.3251137959302023e-07, "epoch": 0.1790258885476086, "percentage": 90.67, "elapsed_time": "1:18:35", "remaining_time": "0:08:05"}
|
| 137 |
+
{"current_steps": 137, "total_steps": 150, "loss": 1.967, "lr": 3.733044478364234e-07, "epoch": 0.18034225537516455, "percentage": 91.33, "elapsed_time": "1:19:10", "remaining_time": "0:07:30"}
|
| 138 |
+
{"current_steps": 138, "total_steps": 150, "loss": 1.9791, "lr": 3.1837697002341293e-07, "epoch": 0.1816586222027205, "percentage": 92.0, "elapsed_time": "1:19:44", "remaining_time": "0:06:56"}
|
| 139 |
+
{"current_steps": 139, "total_steps": 150, "loss": 1.9694, "lr": 2.677533636303964e-07, "epoch": 0.18297498903027642, "percentage": 92.67, "elapsed_time": "1:20:19", "remaining_time": "0:06:21"}
|
| 140 |
+
{"current_steps": 140, "total_steps": 150, "loss": 1.9741, "lr": 2.214561328895748e-07, "epoch": 0.18429135585783238, "percentage": 93.33, "elapsed_time": "1:20:53", "remaining_time": "0:05:46"}
|
| 141 |
+
{"current_steps": 141, "total_steps": 150, "loss": 1.979, "lr": 1.7950585878489856e-07, "epoch": 0.18560772268538833, "percentage": 94.0, "elapsed_time": "1:21:28", "remaining_time": "0:05:12"}
|
| 142 |
+
{"current_steps": 142, "total_steps": 150, "loss": 1.9707, "lr": 1.419211899029971e-07, "epoch": 0.18692408951294429, "percentage": 94.67, "elapsed_time": "1:22:02", "remaining_time": "0:04:37"}
|
| 143 |
+
{"current_steps": 143, "total_steps": 150, "loss": 1.981, "lr": 1.0871883414312778e-07, "epoch": 0.1882404563405002, "percentage": 95.33, "elapsed_time": "1:22:37", "remaining_time": "0:04:02"}
|
| 144 |
+
{"current_steps": 144, "total_steps": 150, "loss": 1.9731, "lr": 7.99135512898408e-08, "epoch": 0.18955682316805617, "percentage": 96.0, "elapsed_time": "1:23:12", "remaining_time": "0:03:28"}
|
| 145 |
+
{"current_steps": 145, "total_steps": 150, "loss": 1.975, "lr": 5.55181464516652e-08, "epoch": 0.19087318999561212, "percentage": 96.67, "elapsed_time": "1:23:46", "remaining_time": "0:02:53"}
|
| 146 |
+
{"current_steps": 146, "total_steps": 150, "loss": 1.9704, "lr": 3.554346436871581e-08, "epoch": 0.19218955682316805, "percentage": 97.33, "elapsed_time": "1:24:21", "remaining_time": "0:02:18"}
|
| 147 |
+
{"current_steps": 147, "total_steps": 150, "loss": 1.979, "lr": 1.9998384591773945e-08, "epoch": 0.193505923650724, "percentage": 98.0, "elapsed_time": "1:24:55", "remaining_time": "0:01:43"}
|
| 148 |
+
{"current_steps": 148, "total_steps": 150, "loss": 1.9867, "lr": 8.889817534969425e-09, "epoch": 0.19482229047827995, "percentage": 98.67, "elapsed_time": "1:25:30", "remaining_time": "0:01:09"}
|
| 149 |
+
{"current_steps": 149, "total_steps": 150, "loss": 1.9756, "lr": 2.222701403818972e-09, "epoch": 0.1961386573058359, "percentage": 99.33, "elapsed_time": "1:26:04", "remaining_time": "0:00:34"}
|
| 150 |
+
{"current_steps": 150, "total_steps": 150, "loss": 1.9877, "lr": 0.0, "epoch": 0.19745502413339183, "percentage": 100.0, "elapsed_time": "1:26:39", "remaining_time": "0:00:00"}
|
| 151 |
+
{"current_steps": 150, "total_steps": 150, "epoch": 0.19745502413339183, "percentage": 100.0, "elapsed_time": "1:26:49", "remaining_time": "0:00:00"}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1092 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.19745502413339183,
|
| 5 |
+
"eval_steps": 50,
|
| 6 |
+
"global_step": 150,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.0013163668275559457,
|
| 13 |
+
"grad_norm": 1.1889708603566411,
|
| 14 |
+
"learning_rate": 2e-05,
|
| 15 |
+
"loss": 1.819,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.0026327336551118913,
|
| 20 |
+
"grad_norm": 1.2487402928615228,
|
| 21 |
+
"learning_rate": 1.999777729859618e-05,
|
| 22 |
+
"loss": 1.786,
|
| 23 |
+
"step": 2
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.003949100482667837,
|
| 27 |
+
"grad_norm": 11.818568585279303,
|
| 28 |
+
"learning_rate": 1.9991110182465032e-05,
|
| 29 |
+
"loss": 2.1123,
|
| 30 |
+
"step": 3
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.005265467310223783,
|
| 34 |
+
"grad_norm": 9.670771499171282,
|
| 35 |
+
"learning_rate": 1.9980001615408228e-05,
|
| 36 |
+
"loss": 2.1052,
|
| 37 |
+
"step": 4
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.006581834137779728,
|
| 41 |
+
"grad_norm": 6.7296227669578945,
|
| 42 |
+
"learning_rate": 1.9964456535631287e-05,
|
| 43 |
+
"loss": 2.0417,
|
| 44 |
+
"step": 5
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.007898200965335674,
|
| 48 |
+
"grad_norm": 2.9490730461911254,
|
| 49 |
+
"learning_rate": 1.9944481853548335e-05,
|
| 50 |
+
"loss": 1.9756,
|
| 51 |
+
"step": 6
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.009214567792891619,
|
| 55 |
+
"grad_norm": 2.8814574350373383,
|
| 56 |
+
"learning_rate": 1.9920086448710162e-05,
|
| 57 |
+
"loss": 1.9305,
|
| 58 |
+
"step": 7
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.010530934620447565,
|
| 62 |
+
"grad_norm": 2.360259343454192,
|
| 63 |
+
"learning_rate": 1.9891281165856876e-05,
|
| 64 |
+
"loss": 1.9001,
|
| 65 |
+
"step": 8
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.01184730144800351,
|
| 69 |
+
"grad_norm": 1.6478415946047946,
|
| 70 |
+
"learning_rate": 1.9858078810097004e-05,
|
| 71 |
+
"loss": 1.9285,
|
| 72 |
+
"step": 9
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.013163668275559455,
|
| 76 |
+
"grad_norm": 1.865513115308653,
|
| 77 |
+
"learning_rate": 1.98204941412151e-05,
|
| 78 |
+
"loss": 1.9158,
|
| 79 |
+
"step": 10
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.014480035103115402,
|
| 83 |
+
"grad_norm": 1.2039798356530171,
|
| 84 |
+
"learning_rate": 1.9778543867110428e-05,
|
| 85 |
+
"loss": 1.9177,
|
| 86 |
+
"step": 11
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.015796401930671347,
|
| 90 |
+
"grad_norm": 1.1202568182839863,
|
| 91 |
+
"learning_rate": 1.9732246636369605e-05,
|
| 92 |
+
"loss": 1.9124,
|
| 93 |
+
"step": 12
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.017112768758227294,
|
| 97 |
+
"grad_norm": 0.9613691948096944,
|
| 98 |
+
"learning_rate": 1.968162302997659e-05,
|
| 99 |
+
"loss": 1.9048,
|
| 100 |
+
"step": 13
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.018429135585783237,
|
| 104 |
+
"grad_norm": 0.893717907926126,
|
| 105 |
+
"learning_rate": 1.962669555216358e-05,
|
| 106 |
+
"loss": 1.8905,
|
| 107 |
+
"step": 14
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.019745502413339184,
|
| 111 |
+
"grad_norm": 0.9042103319398382,
|
| 112 |
+
"learning_rate": 1.9567488620406984e-05,
|
| 113 |
+
"loss": 1.9179,
|
| 114 |
+
"step": 15
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.02106186924089513,
|
| 118 |
+
"grad_norm": 0.8537257879688175,
|
| 119 |
+
"learning_rate": 1.9504028554572865e-05,
|
| 120 |
+
"loss": 1.8956,
|
| 121 |
+
"step": 16
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.022378236068451074,
|
| 125 |
+
"grad_norm": 0.7723152246718353,
|
| 126 |
+
"learning_rate": 1.943634356521671e-05,
|
| 127 |
+
"loss": 1.9106,
|
| 128 |
+
"step": 17
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.02369460289600702,
|
| 132 |
+
"grad_norm": 0.788599031919039,
|
| 133 |
+
"learning_rate": 1.9364463741042694e-05,
|
| 134 |
+
"loss": 1.8714,
|
| 135 |
+
"step": 18
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.025010969723562967,
|
| 139 |
+
"grad_norm": 0.7138782811411121,
|
| 140 |
+
"learning_rate": 1.928842103552803e-05,
|
| 141 |
+
"loss": 1.8805,
|
| 142 |
+
"step": 19
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.02632733655111891,
|
| 146 |
+
"grad_norm": 0.6526275706400243,
|
| 147 |
+
"learning_rate": 1.920824925271838e-05,
|
| 148 |
+
"loss": 1.8992,
|
| 149 |
+
"step": 20
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.027643703378674857,
|
| 153 |
+
"grad_norm": 0.7018291273940191,
|
| 154 |
+
"learning_rate": 1.9123984032200586e-05,
|
| 155 |
+
"loss": 1.8774,
|
| 156 |
+
"step": 21
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.028960070206230804,
|
| 160 |
+
"grad_norm": 0.7136424568096796,
|
| 161 |
+
"learning_rate": 1.9035662833259433e-05,
|
| 162 |
+
"loss": 1.8978,
|
| 163 |
+
"step": 22
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.030276437033786747,
|
| 167 |
+
"grad_norm": 0.7147862026041938,
|
| 168 |
+
"learning_rate": 1.8943324918225495e-05,
|
| 169 |
+
"loss": 1.8965,
|
| 170 |
+
"step": 23
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.031592803861342694,
|
| 174 |
+
"grad_norm": 0.7049064442746601,
|
| 175 |
+
"learning_rate": 1.8847011335021447e-05,
|
| 176 |
+
"loss": 1.8831,
|
| 177 |
+
"step": 24
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.03290917068889864,
|
| 181 |
+
"grad_norm": 0.6689369768605253,
|
| 182 |
+
"learning_rate": 1.874676489891461e-05,
|
| 183 |
+
"loss": 1.8881,
|
| 184 |
+
"step": 25
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.03422553751645459,
|
| 188 |
+
"grad_norm": 0.6425593648258924,
|
| 189 |
+
"learning_rate": 1.8642630173483832e-05,
|
| 190 |
+
"loss": 1.889,
|
| 191 |
+
"step": 26
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.03554190434401053,
|
| 195 |
+
"grad_norm": 0.6931260970545167,
|
| 196 |
+
"learning_rate": 1.85346534508092e-05,
|
| 197 |
+
"loss": 1.8936,
|
| 198 |
+
"step": 27
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.036858271171566474,
|
| 202 |
+
"grad_norm": 0.5855894301604793,
|
| 203 |
+
"learning_rate": 1.8422882730893323e-05,
|
| 204 |
+
"loss": 1.9131,
|
| 205 |
+
"step": 28
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.03817463799912242,
|
| 209 |
+
"grad_norm": 0.6403065763687231,
|
| 210 |
+
"learning_rate": 1.8307367700323412e-05,
|
| 211 |
+
"loss": 1.9104,
|
| 212 |
+
"step": 29
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.03949100482667837,
|
| 216 |
+
"grad_norm": 0.667165710149791,
|
| 217 |
+
"learning_rate": 1.8188159710183595e-05,
|
| 218 |
+
"loss": 1.8807,
|
| 219 |
+
"step": 30
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.040807371654234315,
|
| 223 |
+
"grad_norm": 0.601710689560651,
|
| 224 |
+
"learning_rate": 1.8065311753227272e-05,
|
| 225 |
+
"loss": 1.9261,
|
| 226 |
+
"step": 31
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.04212373848179026,
|
| 230 |
+
"grad_norm": 0.6543848114887616,
|
| 231 |
+
"learning_rate": 1.7938878440319722e-05,
|
| 232 |
+
"loss": 1.9178,
|
| 233 |
+
"step": 32
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.0434401053093462,
|
| 237 |
+
"grad_norm": 0.7216887863002542,
|
| 238 |
+
"learning_rate": 1.7808915976161364e-05,
|
| 239 |
+
"loss": 1.9212,
|
| 240 |
+
"step": 33
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.04475647213690215,
|
| 244 |
+
"grad_norm": 0.6605220221485377,
|
| 245 |
+
"learning_rate": 1.7675482134302503e-05,
|
| 246 |
+
"loss": 1.9019,
|
| 247 |
+
"step": 34
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.046072838964458095,
|
| 251 |
+
"grad_norm": 0.5651946270062499,
|
| 252 |
+
"learning_rate": 1.753863623146066e-05,
|
| 253 |
+
"loss": 1.9065,
|
| 254 |
+
"step": 35
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.04738920579201404,
|
| 258 |
+
"grad_norm": 0.6283354866608959,
|
| 259 |
+
"learning_rate": 1.7398439101151908e-05,
|
| 260 |
+
"loss": 1.8926,
|
| 261 |
+
"step": 36
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.04870557261956999,
|
| 265 |
+
"grad_norm": 0.591339280937863,
|
| 266 |
+
"learning_rate": 1.7254953066647915e-05,
|
| 267 |
+
"loss": 1.898,
|
| 268 |
+
"step": 37
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.050021939447125935,
|
| 272 |
+
"grad_norm": 0.566891433067587,
|
| 273 |
+
"learning_rate": 1.710824191327075e-05,
|
| 274 |
+
"loss": 1.9314,
|
| 275 |
+
"step": 38
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.051338306274681875,
|
| 279 |
+
"grad_norm": 0.5036303737690743,
|
| 280 |
+
"learning_rate": 1.695837086003772e-05,
|
| 281 |
+
"loss": 1.908,
|
| 282 |
+
"step": 39
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.05265467310223782,
|
| 286 |
+
"grad_norm": 0.5732998210738149,
|
| 287 |
+
"learning_rate": 1.680540653066891e-05,
|
| 288 |
+
"loss": 1.907,
|
| 289 |
+
"step": 40
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.05397103992979377,
|
| 293 |
+
"grad_norm": 0.600054956243109,
|
| 294 |
+
"learning_rate": 1.6649416923970248e-05,
|
| 295 |
+
"loss": 1.908,
|
| 296 |
+
"step": 41
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.055287406757349715,
|
| 300 |
+
"grad_norm": 0.5780718337975314,
|
| 301 |
+
"learning_rate": 1.649047138360529e-05,
|
| 302 |
+
"loss": 1.9006,
|
| 303 |
+
"step": 42
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.05660377358490566,
|
| 307 |
+
"grad_norm": 0.5998379136280807,
|
| 308 |
+
"learning_rate": 1.632864056726917e-05,
|
| 309 |
+
"loss": 1.9023,
|
| 310 |
+
"step": 43
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.05792014041246161,
|
| 314 |
+
"grad_norm": 0.630710242272472,
|
| 315 |
+
"learning_rate": 1.6163996415278423e-05,
|
| 316 |
+
"loss": 1.9284,
|
| 317 |
+
"step": 44
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.05923650724001755,
|
| 321 |
+
"grad_norm": 0.5104566997273228,
|
| 322 |
+
"learning_rate": 1.5996612118590604e-05,
|
| 323 |
+
"loss": 1.9089,
|
| 324 |
+
"step": 45
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.060552874067573495,
|
| 328 |
+
"grad_norm": 0.6521533677979531,
|
| 329 |
+
"learning_rate": 1.5826562086267956e-05,
|
| 330 |
+
"loss": 1.9285,
|
| 331 |
+
"step": 46
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.06186924089512944,
|
| 335 |
+
"grad_norm": 0.5098826190359927,
|
| 336 |
+
"learning_rate": 1.565392191239959e-05,
|
| 337 |
+
"loss": 1.916,
|
| 338 |
+
"step": 47
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.06318560772268539,
|
| 342 |
+
"grad_norm": 0.62515291794207,
|
| 343 |
+
"learning_rate": 1.5478768342496872e-05,
|
| 344 |
+
"loss": 1.9069,
|
| 345 |
+
"step": 48
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.06450197455024133,
|
| 349 |
+
"grad_norm": 0.5918382830263713,
|
| 350 |
+
"learning_rate": 1.5301179239376936e-05,
|
| 351 |
+
"loss": 1.9224,
|
| 352 |
+
"step": 49
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.06581834137779728,
|
| 356 |
+
"grad_norm": 0.6387295926323716,
|
| 357 |
+
"learning_rate": 1.512123354854955e-05,
|
| 358 |
+
"loss": 1.9022,
|
| 359 |
+
"step": 50
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.06713470820535322,
|
| 363 |
+
"grad_norm": 0.5484211324952757,
|
| 364 |
+
"learning_rate": 1.4939011263122635e-05,
|
| 365 |
+
"loss": 1.9024,
|
| 366 |
+
"step": 51
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.06845107503290918,
|
| 370 |
+
"grad_norm": 0.6838268591901047,
|
| 371 |
+
"learning_rate": 1.4754593388242117e-05,
|
| 372 |
+
"loss": 1.9133,
|
| 373 |
+
"step": 52
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.06976744186046512,
|
| 377 |
+
"grad_norm": 0.49026244529365287,
|
| 378 |
+
"learning_rate": 1.4568061905081874e-05,
|
| 379 |
+
"loss": 1.9044,
|
| 380 |
+
"step": 53
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.07108380868802106,
|
| 384 |
+
"grad_norm": 0.617101630668953,
|
| 385 |
+
"learning_rate": 1.4379499734399797e-05,
|
| 386 |
+
"loss": 1.9176,
|
| 387 |
+
"step": 54
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.07240017551557701,
|
| 391 |
+
"grad_norm": 0.5185658207760714,
|
| 392 |
+
"learning_rate": 1.4188990699676186e-05,
|
| 393 |
+
"loss": 1.915,
|
| 394 |
+
"step": 55
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.07371654234313295,
|
| 398 |
+
"grad_norm": 0.5509987613832577,
|
| 399 |
+
"learning_rate": 1.3996619489850822e-05,
|
| 400 |
+
"loss": 1.9282,
|
| 401 |
+
"step": 56
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.0750329091706889,
|
| 405 |
+
"grad_norm": 0.5404326350759733,
|
| 406 |
+
"learning_rate": 1.3802471621675337e-05,
|
| 407 |
+
"loss": 1.9121,
|
| 408 |
+
"step": 57
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.07634927599824484,
|
| 412 |
+
"grad_norm": 0.45194626257894893,
|
| 413 |
+
"learning_rate": 1.3606633401697557e-05,
|
| 414 |
+
"loss": 1.9348,
|
| 415 |
+
"step": 58
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.0776656428258008,
|
| 419 |
+
"grad_norm": 0.44319095497602445,
|
| 420 |
+
"learning_rate": 1.340919188789477e-05,
|
| 421 |
+
"loss": 1.9162,
|
| 422 |
+
"step": 59
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.07898200965335674,
|
| 426 |
+
"grad_norm": 0.45917008340300286,
|
| 427 |
+
"learning_rate": 1.3210234850972966e-05,
|
| 428 |
+
"loss": 1.9349,
|
| 429 |
+
"step": 60
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.08029837648091268,
|
| 433 |
+
"grad_norm": 0.4397437065658123,
|
| 434 |
+
"learning_rate": 1.300985073534919e-05,
|
| 435 |
+
"loss": 1.9344,
|
| 436 |
+
"step": 61
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.08161474330846863,
|
| 440 |
+
"grad_norm": 0.43586654360169025,
|
| 441 |
+
"learning_rate": 1.280812861983446e-05,
|
| 442 |
+
"loss": 1.9144,
|
| 443 |
+
"step": 62
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.08293111013602457,
|
| 447 |
+
"grad_norm": 0.4334759261856198,
|
| 448 |
+
"learning_rate": 1.2605158178034656e-05,
|
| 449 |
+
"loss": 1.9202,
|
| 450 |
+
"step": 63
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.08424747696358052,
|
| 454 |
+
"grad_norm": 0.41957147456515964,
|
| 455 |
+
"learning_rate": 1.2401029638486952e-05,
|
| 456 |
+
"loss": 1.8986,
|
| 457 |
+
"step": 64
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.08556384379113646,
|
| 461 |
+
"grad_norm": 0.41703972877231255,
|
| 462 |
+
"learning_rate": 1.219583374454963e-05,
|
| 463 |
+
"loss": 1.9367,
|
| 464 |
+
"step": 65
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.0868802106186924,
|
| 468 |
+
"grad_norm": 0.3885734477047593,
|
| 469 |
+
"learning_rate": 1.1989661714063e-05,
|
| 470 |
+
"loss": 1.9536,
|
| 471 |
+
"step": 66
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.08819657744624836,
|
| 475 |
+
"grad_norm": 0.3629396674080558,
|
| 476 |
+
"learning_rate": 1.1782605198799371e-05,
|
| 477 |
+
"loss": 1.942,
|
| 478 |
+
"step": 67
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 0.0895129442738043,
|
| 482 |
+
"grad_norm": 0.41851931328687847,
|
| 483 |
+
"learning_rate": 1.157475624372018e-05,
|
| 484 |
+
"loss": 1.9149,
|
| 485 |
+
"step": 68
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.09082931110136025,
|
| 489 |
+
"grad_norm": 0.38254555542206087,
|
| 490 |
+
"learning_rate": 1.1366207246058269e-05,
|
| 491 |
+
"loss": 1.9258,
|
| 492 |
+
"step": 69
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 0.09214567792891619,
|
| 496 |
+
"grad_norm": 0.3760396216126684,
|
| 497 |
+
"learning_rate": 1.1157050914243614e-05,
|
| 498 |
+
"loss": 1.9395,
|
| 499 |
+
"step": 70
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.09346204475647214,
|
| 503 |
+
"grad_norm": 0.3802671210811049,
|
| 504 |
+
"learning_rate": 1.0947380226690686e-05,
|
| 505 |
+
"loss": 1.9354,
|
| 506 |
+
"step": 71
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.09477841158402808,
|
| 510 |
+
"grad_norm": 0.346627059727759,
|
| 511 |
+
"learning_rate": 1.0737288390465792e-05,
|
| 512 |
+
"loss": 1.9259,
|
| 513 |
+
"step": 72
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.09609477841158402,
|
| 517 |
+
"grad_norm": 0.3873365911679245,
|
| 518 |
+
"learning_rate": 1.0526868799852797e-05,
|
| 519 |
+
"loss": 1.9493,
|
| 520 |
+
"step": 73
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 0.09741114523913998,
|
| 524 |
+
"grad_norm": 0.3805418724228647,
|
| 525 |
+
"learning_rate": 1.031621499483559e-05,
|
| 526 |
+
"loss": 1.9429,
|
| 527 |
+
"step": 74
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.09872751206669592,
|
| 531 |
+
"grad_norm": 0.3477296159832507,
|
| 532 |
+
"learning_rate": 1.0105420619515798e-05,
|
| 533 |
+
"loss": 1.9348,
|
| 534 |
+
"step": 75
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.10004387889425187,
|
| 538 |
+
"grad_norm": 0.36081350820036023,
|
| 539 |
+
"learning_rate": 9.894579380484206e-06,
|
| 540 |
+
"loss": 1.951,
|
| 541 |
+
"step": 76
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.10136024572180781,
|
| 545 |
+
"grad_norm": 0.3603157658181124,
|
| 546 |
+
"learning_rate": 9.683785005164412e-06,
|
| 547 |
+
"loss": 1.9568,
|
| 548 |
+
"step": 77
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 0.10267661254936375,
|
| 552 |
+
"grad_norm": 0.3344964866298326,
|
| 553 |
+
"learning_rate": 9.473131200147205e-06,
|
| 554 |
+
"loss": 1.9635,
|
| 555 |
+
"step": 78
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.1039929793769197,
|
| 559 |
+
"grad_norm": 0.3577372410086672,
|
| 560 |
+
"learning_rate": 9.262711609534211e-06,
|
| 561 |
+
"loss": 1.9493,
|
| 562 |
+
"step": 79
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 0.10530934620447564,
|
| 566 |
+
"grad_norm": 0.32166763062706677,
|
| 567 |
+
"learning_rate": 9.052619773309318e-06,
|
| 568 |
+
"loss": 1.9416,
|
| 569 |
+
"step": 80
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.1066257130320316,
|
| 573 |
+
"grad_norm": 0.3642098555682263,
|
| 574 |
+
"learning_rate": 8.842949085756389e-06,
|
| 575 |
+
"loss": 1.9375,
|
| 576 |
+
"step": 81
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 0.10794207985958754,
|
| 580 |
+
"grad_norm": 0.31313176156525635,
|
| 581 |
+
"learning_rate": 8.633792753941733e-06,
|
| 582 |
+
"loss": 1.9482,
|
| 583 |
+
"step": 82
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.10925844668714349,
|
| 587 |
+
"grad_norm": 0.32357294734122866,
|
| 588 |
+
"learning_rate": 8.425243756279824e-06,
|
| 589 |
+
"loss": 1.9274,
|
| 590 |
+
"step": 83
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 0.11057481351469943,
|
| 594 |
+
"grad_norm": 0.3149933190799516,
|
| 595 |
+
"learning_rate": 8.217394801200632e-06,
|
| 596 |
+
"loss": 1.9494,
|
| 597 |
+
"step": 84
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.11189118034225537,
|
| 601 |
+
"grad_norm": 0.3145273258487357,
|
| 602 |
+
"learning_rate": 8.010338285937006e-06,
|
| 603 |
+
"loss": 1.9383,
|
| 604 |
+
"step": 85
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 0.11320754716981132,
|
| 608 |
+
"grad_norm": 0.3293525045662984,
|
| 609 |
+
"learning_rate": 7.804166255450372e-06,
|
| 610 |
+
"loss": 1.9438,
|
| 611 |
+
"step": 86
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.11452391399736726,
|
| 615 |
+
"grad_norm": 0.29338737195487413,
|
| 616 |
+
"learning_rate": 7.598970361513052e-06,
|
| 617 |
+
"loss": 1.9486,
|
| 618 |
+
"step": 87
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 0.11584028082492322,
|
| 622 |
+
"grad_norm": 0.3103457426467627,
|
| 623 |
+
"learning_rate": 7.394841821965345e-06,
|
| 624 |
+
"loss": 1.9274,
|
| 625 |
+
"step": 88
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.11715664765247916,
|
| 629 |
+
"grad_norm": 0.3143049571743679,
|
| 630 |
+
"learning_rate": 7.191871380165538e-06,
|
| 631 |
+
"loss": 1.9524,
|
| 632 |
+
"step": 89
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 0.1184730144800351,
|
| 636 |
+
"grad_norm": 0.29504032042698036,
|
| 637 |
+
"learning_rate": 6.990149264650814e-06,
|
| 638 |
+
"loss": 1.9445,
|
| 639 |
+
"step": 90
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.11978938130759105,
|
| 643 |
+
"grad_norm": 0.3210704673929567,
|
| 644 |
+
"learning_rate": 6.789765149027039e-06,
|
| 645 |
+
"loss": 1.9515,
|
| 646 |
+
"step": 91
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 0.12110574813514699,
|
| 650 |
+
"grad_norm": 0.28621542114599363,
|
| 651 |
+
"learning_rate": 6.590808112105232e-06,
|
| 652 |
+
"loss": 1.969,
|
| 653 |
+
"step": 92
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 0.12242211496270294,
|
| 657 |
+
"grad_norm": 0.2882677076447023,
|
| 658 |
+
"learning_rate": 6.3933665983024465e-06,
|
| 659 |
+
"loss": 1.954,
|
| 660 |
+
"step": 93
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 0.12373848179025888,
|
| 664 |
+
"grad_norm": 0.287930909134049,
|
| 665 |
+
"learning_rate": 6.197528378324664e-06,
|
| 666 |
+
"loss": 1.9313,
|
| 667 |
+
"step": 94
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 0.12505484861781482,
|
| 671 |
+
"grad_norm": 0.31023728939120476,
|
| 672 |
+
"learning_rate": 6.003380510149179e-06,
|
| 673 |
+
"loss": 1.9602,
|
| 674 |
+
"step": 95
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 0.12637121544537078,
|
| 678 |
+
"grad_norm": 0.2752773114898817,
|
| 679 |
+
"learning_rate": 5.8110093003238175e-06,
|
| 680 |
+
"loss": 1.9831,
|
| 681 |
+
"step": 96
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.12768758227292673,
|
| 685 |
+
"grad_norm": 0.2972076509810327,
|
| 686 |
+
"learning_rate": 5.620500265600206e-06,
|
| 687 |
+
"loss": 1.9562,
|
| 688 |
+
"step": 97
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 0.12900394910048266,
|
| 692 |
+
"grad_norm": 0.28344306622056237,
|
| 693 |
+
"learning_rate": 5.431938094918132e-06,
|
| 694 |
+
"loss": 1.9679,
|
| 695 |
+
"step": 98
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 0.1303203159280386,
|
| 699 |
+
"grad_norm": 0.27862896188615965,
|
| 700 |
+
"learning_rate": 5.245406611757882e-06,
|
| 701 |
+
"loss": 1.9667,
|
| 702 |
+
"step": 99
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 0.13163668275559456,
|
| 706 |
+
"grad_norm": 0.2775069903986726,
|
| 707 |
+
"learning_rate": 5.060988736877366e-06,
|
| 708 |
+
"loss": 1.9486,
|
| 709 |
+
"step": 100
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 0.13295304958315052,
|
| 713 |
+
"grad_norm": 0.2750571862770337,
|
| 714 |
+
"learning_rate": 4.878766451450451e-06,
|
| 715 |
+
"loss": 1.9557,
|
| 716 |
+
"step": 101
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 0.13426941641070644,
|
| 720 |
+
"grad_norm": 0.2680704001161532,
|
| 721 |
+
"learning_rate": 4.698820760623064e-06,
|
| 722 |
+
"loss": 1.9506,
|
| 723 |
+
"step": 102
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 0.1355857832382624,
|
| 727 |
+
"grad_norm": 0.2782630531024094,
|
| 728 |
+
"learning_rate": 4.5212316575031325e-06,
|
| 729 |
+
"loss": 1.9639,
|
| 730 |
+
"step": 103
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 0.13690215006581835,
|
| 734 |
+
"grad_norm": 0.25617683357697074,
|
| 735 |
+
"learning_rate": 4.346078087600411e-06,
|
| 736 |
+
"loss": 1.9683,
|
| 737 |
+
"step": 104
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 0.13821851689337428,
|
| 741 |
+
"grad_norm": 0.2444943371569369,
|
| 742 |
+
"learning_rate": 4.173437913732048e-06,
|
| 743 |
+
"loss": 1.9659,
|
| 744 |
+
"step": 105
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 0.13953488372093023,
|
| 748 |
+
"grad_norm": 0.2597397835336073,
|
| 749 |
+
"learning_rate": 4.003387881409397e-06,
|
| 750 |
+
"loss": 1.9704,
|
| 751 |
+
"step": 106
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 0.14085125054848618,
|
| 755 |
+
"grad_norm": 0.26063366143876027,
|
| 756 |
+
"learning_rate": 3.836003584721577e-06,
|
| 757 |
+
"loss": 1.97,
|
| 758 |
+
"step": 107
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 0.1421676173760421,
|
| 762 |
+
"grad_norm": 0.23235593032133328,
|
| 763 |
+
"learning_rate": 3.6713594327308343e-06,
|
| 764 |
+
"loss": 1.9554,
|
| 765 |
+
"step": 108
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 0.14348398420359806,
|
| 769 |
+
"grad_norm": 0.22701215505987368,
|
| 770 |
+
"learning_rate": 3.509528616394716e-06,
|
| 771 |
+
"loss": 1.9737,
|
| 772 |
+
"step": 109
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 0.14480035103115402,
|
| 776 |
+
"grad_norm": 0.24108913765275466,
|
| 777 |
+
"learning_rate": 3.3505830760297543e-06,
|
| 778 |
+
"loss": 1.9699,
|
| 779 |
+
"step": 110
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 0.14611671785870997,
|
| 783 |
+
"grad_norm": 0.24405476026520742,
|
| 784 |
+
"learning_rate": 3.1945934693310897e-06,
|
| 785 |
+
"loss": 1.9767,
|
| 786 |
+
"step": 111
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 0.1474330846862659,
|
| 790 |
+
"grad_norm": 0.23175867510438058,
|
| 791 |
+
"learning_rate": 3.0416291399622834e-06,
|
| 792 |
+
"loss": 2.0023,
|
| 793 |
+
"step": 112
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 0.14874945151382185,
|
| 797 |
+
"grad_norm": 0.22596129228759587,
|
| 798 |
+
"learning_rate": 2.891758086729253e-06,
|
| 799 |
+
"loss": 1.955,
|
| 800 |
+
"step": 113
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 0.1500658183413778,
|
| 804 |
+
"grad_norm": 0.24851949999567013,
|
| 805 |
+
"learning_rate": 2.7450469333520856e-06,
|
| 806 |
+
"loss": 1.9611,
|
| 807 |
+
"step": 114
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 0.15138218516893373,
|
| 811 |
+
"grad_norm": 0.22293156665441605,
|
| 812 |
+
"learning_rate": 2.6015608988480956e-06,
|
| 813 |
+
"loss": 1.9658,
|
| 814 |
+
"step": 115
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 0.15269855199648968,
|
| 818 |
+
"grad_norm": 0.21616202749444716,
|
| 819 |
+
"learning_rate": 2.4613637685393433e-06,
|
| 820 |
+
"loss": 1.9753,
|
| 821 |
+
"step": 116
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 0.15401491882404564,
|
| 825 |
+
"grad_norm": 0.22185470586350384,
|
| 826 |
+
"learning_rate": 2.324517865697501e-06,
|
| 827 |
+
"loss": 1.9495,
|
| 828 |
+
"step": 117
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 0.1553312856516016,
|
| 832 |
+
"grad_norm": 0.21722679538918865,
|
| 833 |
+
"learning_rate": 2.19108402383864e-06,
|
| 834 |
+
"loss": 1.9628,
|
| 835 |
+
"step": 118
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 0.15664765247915752,
|
| 839 |
+
"grad_norm": 0.21205900012695214,
|
| 840 |
+
"learning_rate": 2.06112155968028e-06,
|
| 841 |
+
"loss": 1.9823,
|
| 842 |
+
"step": 119
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 0.15796401930671347,
|
| 846 |
+
"grad_norm": 0.2182253662134732,
|
| 847 |
+
"learning_rate": 1.9346882467727323e-06,
|
| 848 |
+
"loss": 1.9875,
|
| 849 |
+
"step": 120
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 0.15928038613426942,
|
| 853 |
+
"grad_norm": 0.22007111443224736,
|
| 854 |
+
"learning_rate": 1.811840289816409e-06,
|
| 855 |
+
"loss": 1.9805,
|
| 856 |
+
"step": 121
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 0.16059675296182535,
|
| 860 |
+
"grad_norm": 0.20406970469647664,
|
| 861 |
+
"learning_rate": 1.6926322996765899e-06,
|
| 862 |
+
"loss": 1.9818,
|
| 863 |
+
"step": 122
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 0.1619131197893813,
|
| 867 |
+
"grad_norm": 0.2024904864715853,
|
| 868 |
+
"learning_rate": 1.5771172691066793e-06,
|
| 869 |
+
"loss": 1.9859,
|
| 870 |
+
"step": 123
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 0.16322948661693726,
|
| 874 |
+
"grad_norm": 0.20299971001174535,
|
| 875 |
+
"learning_rate": 1.4653465491908003e-06,
|
| 876 |
+
"loss": 2.0096,
|
| 877 |
+
"step": 124
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 0.1645458534444932,
|
| 881 |
+
"grad_norm": 0.21516178859981677,
|
| 882 |
+
"learning_rate": 1.3573698265161683e-06,
|
| 883 |
+
"loss": 1.9654,
|
| 884 |
+
"step": 125
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 0.16586222027204914,
|
| 888 |
+
"grad_norm": 0.20722629324747893,
|
| 889 |
+
"learning_rate": 1.2532351010853916e-06,
|
| 890 |
+
"loss": 1.9708,
|
| 891 |
+
"step": 126
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 0.1671785870996051,
|
| 895 |
+
"grad_norm": 0.21213871178644442,
|
| 896 |
+
"learning_rate": 1.152988664978556e-06,
|
| 897 |
+
"loss": 1.9787,
|
| 898 |
+
"step": 127
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 0.16849495392716105,
|
| 902 |
+
"grad_norm": 0.20023503307538396,
|
| 903 |
+
"learning_rate": 1.0566750817745076e-06,
|
| 904 |
+
"loss": 1.9858,
|
| 905 |
+
"step": 128
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 0.16981132075471697,
|
| 909 |
+
"grad_norm": 0.1924700263570635,
|
| 910 |
+
"learning_rate": 9.6433716674057e-07,
|
| 911 |
+
"loss": 1.9781,
|
| 912 |
+
"step": 129
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 0.17112768758227292,
|
| 916 |
+
"grad_norm": 0.20779051083187167,
|
| 917 |
+
"learning_rate": 8.760159677994174e-07,
|
| 918 |
+
"loss": 1.9827,
|
| 919 |
+
"step": 130
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 0.17244405440982888,
|
| 923 |
+
"grad_norm": 0.20230044677950978,
|
| 924 |
+
"learning_rate": 7.91750747281621e-07,
|
| 925 |
+
"loss": 1.9741,
|
| 926 |
+
"step": 131
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 0.1737604212373848,
|
| 930 |
+
"grad_norm": 0.19683020520485797,
|
| 931 |
+
"learning_rate": 7.115789644719728e-07,
|
| 932 |
+
"loss": 1.9949,
|
| 933 |
+
"step": 132
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 0.17507678806494076,
|
| 937 |
+
"grad_norm": 0.19524340774257554,
|
| 938 |
+
"learning_rate": 6.355362589573078e-07,
|
| 939 |
+
"loss": 1.9762,
|
| 940 |
+
"step": 133
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 0.1763931548924967,
|
| 944 |
+
"grad_norm": 0.20098123761556075,
|
| 945 |
+
"learning_rate": 5.636564347832907e-07,
|
| 946 |
+
"loss": 1.9818,
|
| 947 |
+
"step": 134
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 0.17770952172005267,
|
| 951 |
+
"grad_norm": 0.18935262395702177,
|
| 952 |
+
"learning_rate": 4.95971445427137e-07,
|
| 953 |
+
"loss": 1.983,
|
| 954 |
+
"step": 135
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 0.1790258885476086,
|
| 958 |
+
"grad_norm": 0.1906817912560046,
|
| 959 |
+
"learning_rate": 4.3251137959302023e-07,
|
| 960 |
+
"loss": 1.9708,
|
| 961 |
+
"step": 136
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 0.18034225537516455,
|
| 965 |
+
"grad_norm": 0.19470612058115894,
|
| 966 |
+
"learning_rate": 3.733044478364234e-07,
|
| 967 |
+
"loss": 1.967,
|
| 968 |
+
"step": 137
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 0.1816586222027205,
|
| 972 |
+
"grad_norm": 0.18636115957247928,
|
| 973 |
+
"learning_rate": 3.1837697002341293e-07,
|
| 974 |
+
"loss": 1.9791,
|
| 975 |
+
"step": 138
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 0.18297498903027642,
|
| 979 |
+
"grad_norm": 0.18877431556550928,
|
| 980 |
+
"learning_rate": 2.677533636303964e-07,
|
| 981 |
+
"loss": 1.9694,
|
| 982 |
+
"step": 139
|
| 983 |
+
},
|
| 984 |
+
{
|
| 985 |
+
"epoch": 0.18429135585783238,
|
| 986 |
+
"grad_norm": 0.1955087203028538,
|
| 987 |
+
"learning_rate": 2.214561328895748e-07,
|
| 988 |
+
"loss": 1.9741,
|
| 989 |
+
"step": 140
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 0.18560772268538833,
|
| 993 |
+
"grad_norm": 0.196549286904382,
|
| 994 |
+
"learning_rate": 1.7950585878489856e-07,
|
| 995 |
+
"loss": 1.979,
|
| 996 |
+
"step": 141
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 0.18692408951294429,
|
| 1000 |
+
"grad_norm": 0.19224460294869852,
|
| 1001 |
+
"learning_rate": 1.419211899029971e-07,
|
| 1002 |
+
"loss": 1.9707,
|
| 1003 |
+
"step": 142
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 0.1882404563405002,
|
| 1007 |
+
"grad_norm": 0.18853581462437616,
|
| 1008 |
+
"learning_rate": 1.0871883414312778e-07,
|
| 1009 |
+
"loss": 1.981,
|
| 1010 |
+
"step": 143
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 0.18955682316805617,
|
| 1014 |
+
"grad_norm": 0.1838928559361403,
|
| 1015 |
+
"learning_rate": 7.99135512898408e-08,
|
| 1016 |
+
"loss": 1.9731,
|
| 1017 |
+
"step": 144
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 0.19087318999561212,
|
| 1021 |
+
"grad_norm": 0.190162401461088,
|
| 1022 |
+
"learning_rate": 5.55181464516652e-08,
|
| 1023 |
+
"loss": 1.975,
|
| 1024 |
+
"step": 145
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 0.19218955682316805,
|
| 1028 |
+
"grad_norm": 0.19003523312950812,
|
| 1029 |
+
"learning_rate": 3.554346436871581e-08,
|
| 1030 |
+
"loss": 1.9704,
|
| 1031 |
+
"step": 146
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 0.193505923650724,
|
| 1035 |
+
"grad_norm": 0.19021539316010605,
|
| 1036 |
+
"learning_rate": 1.9998384591773945e-08,
|
| 1037 |
+
"loss": 1.979,
|
| 1038 |
+
"step": 147
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"epoch": 0.19482229047827995,
|
| 1042 |
+
"grad_norm": 0.18754432655782285,
|
| 1043 |
+
"learning_rate": 8.889817534969425e-09,
|
| 1044 |
+
"loss": 1.9867,
|
| 1045 |
+
"step": 148
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 0.1961386573058359,
|
| 1049 |
+
"grad_norm": 0.1897467195961825,
|
| 1050 |
+
"learning_rate": 2.222701403818972e-09,
|
| 1051 |
+
"loss": 1.9756,
|
| 1052 |
+
"step": 149
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 0.19745502413339183,
|
| 1056 |
+
"grad_norm": 0.20302937860642753,
|
| 1057 |
+
"learning_rate": 0.0,
|
| 1058 |
+
"loss": 1.9877,
|
| 1059 |
+
"step": 150
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 0.19745502413339183,
|
| 1063 |
+
"step": 150,
|
| 1064 |
+
"total_flos": 349677715193856.0,
|
| 1065 |
+
"train_loss": 1.9421729667981467,
|
| 1066 |
+
"train_runtime": 5209.8016,
|
| 1067 |
+
"train_samples_per_second": 58.044,
|
| 1068 |
+
"train_steps_per_second": 0.029
|
| 1069 |
+
}
|
| 1070 |
+
],
|
| 1071 |
+
"logging_steps": 1,
|
| 1072 |
+
"max_steps": 150,
|
| 1073 |
+
"num_input_tokens_seen": 0,
|
| 1074 |
+
"num_train_epochs": 1,
|
| 1075 |
+
"save_steps": 50,
|
| 1076 |
+
"stateful_callbacks": {
|
| 1077 |
+
"TrainerControl": {
|
| 1078 |
+
"args": {
|
| 1079 |
+
"should_epoch_stop": false,
|
| 1080 |
+
"should_evaluate": false,
|
| 1081 |
+
"should_log": false,
|
| 1082 |
+
"should_save": true,
|
| 1083 |
+
"should_training_stop": true
|
| 1084 |
+
},
|
| 1085 |
+
"attributes": {}
|
| 1086 |
+
}
|
| 1087 |
+
},
|
| 1088 |
+
"total_flos": 349677715193856.0,
|
| 1089 |
+
"train_batch_size": 42,
|
| 1090 |
+
"trial_name": null,
|
| 1091 |
+
"trial_params": null
|
| 1092 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:740b7b8a2a5af5fe75fa4a3755ea7b3cb437cad50b07e933078a8d7b44af963f
|
| 3 |
+
size 7224
|
training_loss.png
ADDED
|