End of training

README.md

@@ -0,0 +1,228 @@
+---
+library_name: peft
+license: other
+base_model: facebook/opt-125m
+tags:
+- axolotl
+- generated_from_trainer
+model-index:
+- name: 31b2ce40-fe16-4b11-a7f2-c816733ae5bd
+  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. -->
+
+[<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl)
+<details><summary>See axolotl config</summary>
+
+axolotl version: `0.4.1`
+```yaml
+adapter: lora
+base_model: facebook/opt-125m
+bf16: auto
+chat_template: llama3
+dataset_prepared_path: null
+datasets:
+- data_files:
+  - e9426b45bbc30495_train_data.json
+  ds_type: json
+  format: custom
+  path: /workspace/input_data/e9426b45bbc30495_train_data.json
+  type:
+    field_input: original_version
+    field_instruction: title
+    field_output: french_version
+    format: '{instruction} {input}'
+    no_input_format: '{instruction}'
+    system_format: '{system}'
+    system_prompt: ''
+debug: null
+deepspeed: null
+device_map: auto
+do_eval: true
+early_stopping_patience: 3
+eval_batch_size: 4
+eval_max_new_tokens: 128
+eval_steps: 300
+eval_table_size: null
+evals_per_epoch: null
+flash_attention: true
+fp16: false
+fsdp: null
+fsdp_config: null
+gradient_accumulation_steps: 4
+gradient_checkpointing: false
+group_by_length: true
+hub_model_id: robiual-awal/31b2ce40-fe16-4b11-a7f2-c816733ae5bd
+hub_strategy: end
+learning_rate: 0.0002
+load_in_4bit: false
+load_in_8bit: false
+local_rank: null
+logging_steps: 50
+lora_alpha: 64
+lora_dropout: 0.05
+lora_fan_in_fan_out: null
+lora_model_dir: null
+lora_r: 32
+lora_target_linear: true
+lr_scheduler: constant
+max_grad_norm: 1.0
+max_memory:
+  0: 75GB
+max_steps: 20956
+micro_batch_size: 4
+mlflow_experiment_name: /tmp/e9426b45bbc30495_train_data.json
+model_type: AutoModelForCausalLM
+num_epochs: 10
+optim_args:
+  adam_beta1: 0.9
+  adam_beta2: 0.95
+  adam_epsilon: 1e-5
+optimizer: adamw_bnb_8bit
+output_dir: miner_id_24
+pad_to_sequence_len: true
+resume_from_checkpoint: null
+s2_attention: null
+sample_packing: false
+save_steps: 300
+saves_per_epoch: null
+sequence_len: 512
+strict: false
+tf32: true
+tokenizer_type: AutoTokenizer
+train_on_inputs: false
+trust_remote_code: true
+val_set_size: 0.05
+wandb_entity: null
+wandb_mode: online
+wandb_name: 4dbfff5d-e150-40fd-bcd9-78e926ac420c
+wandb_project: SN56-30
+wandb_run: your_name
+wandb_runid: 4dbfff5d-e150-40fd-bcd9-78e926ac420c
+warmup_steps: 50
+weight_decay: 0.0
+xformers_attention: null
+
+```
+
+</details><br>
+
+# 31b2ce40-fe16-4b11-a7f2-c816733ae5bd
+
+This model is a fine-tuned version of [facebook/opt-125m](https://huggingface.co/facebook/opt-125m) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.1069
+
+## 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: 0.0002
+- train_batch_size: 4
+- eval_batch_size: 4
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 16
+- optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=adam_beta1=0.9,adam_beta2=0.95,adam_epsilon=1e-5
+- lr_scheduler_type: constant
+- lr_scheduler_warmup_steps: 50
+- training_steps: 20956
+
+### Training results
+
+| Training Loss | Epoch  | Step  | Validation Loss |
+|:-------------:|:------:|:-----:|:---------------:|
+| No log        | 0.0002 | 1     | 2.5746          |
+| 8.1108        | 0.0510 | 300   | 1.9106          |
+| 7.0989        | 0.1021 | 600   | 1.6791          |
+| 6.6679        | 0.1531 | 900   | 1.5726          |
+| 6.261         | 0.2042 | 1200  | 1.4999          |
+| 6.0721        | 0.2552 | 1500  | 1.4423          |
+| 5.8807        | 0.3063 | 1800  | 1.4126          |
+| 5.6805        | 0.3573 | 2100  | 1.3783          |
+| 5.5754        | 0.4083 | 2400  | 1.3535          |
+| 5.7266        | 0.4594 | 2700  | 1.3309          |
+| 5.5338        | 0.5104 | 3000  | 1.3168          |
+| 5.6379        | 0.5615 | 3300  | 1.2952          |
+| 5.5449        | 0.6125 | 3600  | 1.2839          |
+| 5.3335        | 0.6635 | 3900  | 1.2721          |
+| 5.3477        | 0.7146 | 4200  | 1.2623          |
+| 5.2752        | 0.7656 | 4500  | 1.2513          |
+| 5.1171        | 0.8167 | 4800  | 1.2466          |
+| 5.1925        | 0.8677 | 5100  | 1.2335          |
+| 5.3031        | 0.9188 | 5400  | 1.2284          |
+| 5.2691        | 0.9698 | 5700  | 1.2237          |
+| 5.2285        | 1.0208 | 6000  | 1.2107          |
+| 5.2817        | 1.0719 | 6300  | 1.2072          |
+| 5.0723        | 1.1229 | 6600  | 1.2032          |
+| 5.0179        | 1.1740 | 6900  | 1.1982          |
+| 4.8939        | 1.2250 | 7200  | 1.1965          |
+| 4.8136        | 1.2761 | 7500  | 1.1892          |
+| 4.9914        | 1.3271 | 7800  | 1.1828          |
+| 5.074         | 1.3781 | 8100  | 1.1815          |
+| 5.0051        | 1.4292 | 8400  | 1.1753          |
+| 4.9578        | 1.4802 | 8700  | 1.1743          |
+| 5.1432        | 1.5313 | 9000  | 1.1683          |
+| 4.7522        | 1.5823 | 9300  | 1.1685          |
+| 5.0689        | 1.6333 | 9600  | 1.1632          |
+| 4.8908        | 1.6844 | 9900  | 1.1638          |
+| 4.8675        | 1.7354 | 10200 | 1.1558          |
+| 4.8574        | 1.7865 | 10500 | 1.1557          |
+| 4.889         | 1.8375 | 10800 | 1.1522          |
+| 4.9843        | 1.8886 | 11100 | 1.1552          |
+| 4.6065        | 1.9396 | 11400 | 1.1506          |
+| 4.9163        | 1.9906 | 11700 | 1.1473          |
+| 4.8699        | 2.0417 | 12000 | 1.1422          |
+| 4.7492        | 2.0927 | 12300 | 1.1431          |
+| 4.7051        | 2.1438 | 12600 | 1.1392          |
+| 4.772         | 2.1948 | 12900 | 1.1397          |
+| 4.9571        | 2.2459 | 13200 | 1.1376          |
+| 4.5603        | 2.2969 | 13500 | 1.1356          |
+| 4.6664        | 2.3479 | 13800 | 1.1337          |
+| 4.876         | 2.3990 | 14100 | 1.1300          |
+| 4.5775        | 2.4500 | 14400 | 1.1301          |
+| 4.764         | 2.5011 | 14700 | 1.1275          |
+| 4.6266        | 2.5521 | 15000 | 1.1246          |
+| 4.7234        | 2.6031 | 15300 | 1.1250          |
+| 4.722         | 2.6542 | 15600 | 1.1211          |
+| 4.9044        | 2.7052 | 15900 | 1.1202          |
+| 4.8683        | 2.7563 | 16200 | 1.1217          |
+| 4.5523        | 2.8073 | 16500 | 1.1161          |
+| 4.6435        | 2.8584 | 16800 | 1.1191          |
+| 4.8074        | 2.9094 | 17100 | 1.1175          |
+| 4.6395        | 2.9604 | 17400 | 1.1156          |
+| 4.5781        | 3.0115 | 17700 | 1.1167          |
+| 4.4496        | 3.0625 | 18000 | 1.1188          |
+| 4.6846        | 3.1136 | 18300 | 1.1130          |
+| 4.5808        | 3.1646 | 18600 | 1.1168          |
+| 4.3914        | 3.2157 | 18900 | 1.1123          |
+| 4.6832        | 3.2667 | 19200 | 1.1118          |
+| 4.5798        | 3.3177 | 19500 | 1.1123          |
+| 4.966         | 3.3688 | 19800 | 1.1107          |
+| 4.6667        | 3.4198 | 20100 | 1.1098          |
+| 4.4912        | 3.4709 | 20400 | 1.1077          |
+| 4.749         | 3.5219 | 20700 | 1.1069          |
+
+
+### Framework versions
+
+- PEFT 0.13.2
+- Transformers 4.46.0
+- Pytorch 2.5.0+cu124
+- Datasets 3.0.1
+- Tokenizers 0.20.1

adapter_config.json

@@ -0,0 +1,33 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "facebook/opt-125m",
+  "bias": "none",
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 64,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "fc2",
+    "k_proj",
+    "q_proj",
+    "out_proj",
+    "fc1"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a51e2eeed55cf5b82306be83b12bbcd9708c9f02e75e042107579e5f423167bc
+size 21286218

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e84e47ffa29cf48d12f8de2fab4b6c5d109f398bf4bf8595ea3d5e415e03031e
+size 21253336

config.json

@@ -0,0 +1,32 @@
+{
+  "_attn_implementation_autoset": true,
+  "_name_or_path": "facebook/opt-125m",
+  "_remove_final_layer_norm": false,
+  "activation_dropout": 0.0,
+  "activation_function": "relu",
+  "architectures": [
+    "OPTForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 2,
+  "do_layer_norm_before": true,
+  "dropout": 0.1,
+  "enable_bias": true,
+  "eos_token_id": 2,
+  "ffn_dim": 3072,
+  "hidden_size": 768,
+  "init_std": 0.02,
+  "layer_norm_elementwise_affine": true,
+  "layerdrop": 0.0,
+  "max_position_embeddings": 2048,
+  "model_type": "opt",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "prefix": "</s>",
+  "torch_dtype": "float16",
+  "transformers_version": "4.46.0",
+  "use_cache": false,
+  "vocab_size": 50272,
+  "word_embed_proj_dim": 768
+}

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,31 @@
+{
+  "add_bos_token": true,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "</s>",
+  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "errors": "replace",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "</s>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:230a9451612b49b7175d91b54a9c1147440330e243f4554f50167323b81137ea
+size 6776