Hosein/MobileLLM-125M-e3.9.24.4.1

README.md

@@ -0,0 +1,66 @@
+---
+library_name: transformers
+license: cc-by-nc-4.0
+base_model: facebook/MobileLLM-125M
+tags:
+- trl
+- sft
+- generated_from_trainer
+model-index:
+- name: MobileLLM-125M-e3.9.24.4.1
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# MobileLLM-125M-e3.9.24.4.1
+
+This model is a fine-tuned version of [facebook/MobileLLM-125M](https://huggingface.co/facebook/MobileLLM-125M) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 5.0760
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 0.0001
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 32
+- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: constant
+- lr_scheduler_warmup_ratio: 0.05
+- num_epochs: 2
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 24.4975       | 0.4    | 125  | 6.1432          |
+| 22.49         | 0.8    | 250  | 5.5705          |
+| 19.6874       | 1.1984 | 375  | 5.2622          |
+| 18.0295       | 1.5984 | 500  | 5.0760          |
+
+
+### Framework versions
+
+- Transformers 4.47.1
+- Pytorch 2.6.0.dev20241231+cu118
+- Datasets 3.0.2
+- Tokenizers 0.21.0

config.json

@@ -0,0 +1,36 @@
+{
+  "_name_or_path": "facebook/MobileLLM-125M",
+  "architectures": [
+    "MobileLLMForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "auto_map": {
+    "AutoConfig": "facebook/MobileLLM-125M--configuration_mobilellm.MobileLLMConfig",
+    "AutoModelForCausalLM": "facebook/MobileLLM-125M--modeling_mobilellm.MobileLLMForCausalLM"
+  },
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 576,
+  "initializer_range": 0.02,
+  "intermediate_size": 1536,
+  "layer_sharing": false,
+  "max_position_embeddings": 2048,
+  "mlp_bias": false,
+  "model_type": "mobilellm",
+  "num_attention_heads": 9,
+  "num_hidden_layers": 30,
+  "num_key_value_heads": 3,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "share_embedding": true,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.47.1",
+  "use_cache": true,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.47.1"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91a0d8ef10dc7a12601e40fd7d1d8d6ce243348a15d5f8403790c971a4ecb448
+size 498572168

runs/Jan04_16-08-44_ip-10-192-12-219/events.out.tfevents.1736006930.ip-10-192-12-219.3859.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:593a6f5c541ae687b308f2f77cdfc12ce65dbac5fe82f123eccc3b2fc179d5b6
+size 72524

runs/Jan04_16-13-30_ip-10-192-12-219/events.out.tfevents.1736007210.ip-10-192-12-219.4394.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:100fdee0e2d00ebd2293a26175458f1211f469dce693710bd257a9cab84ad615
+size 72524

runs/Jan08_11-39-23_ip-10-192-12-179/events.out.tfevents.1736336364.ip-10-192-12-179.5901.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d323e707e7227d6719166c6a9551254a051e8ee1a6215961aa9a1c7af8e17f3b
+size 138361

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,18 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": true,
+  "added_tokens_decoder": {},
+  "bos_token": "",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "",
+  "extra_special_tokens": {},
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "",
+  "use_default_system_prompt": false
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2fee5f4d941bc0665fe887b80cdc1d452e60d17bff8c6019215450bc03d1fa93
+size 5624