Model save

README.md

@@ -0,0 +1,63 @@
+---
+license: apache-2.0
+base_model: JackFram/llama-68m
+tags:
+- trl
+- sft
+- generated_from_trainer
+datasets:
+- generator
+model-index:
+- name: gpt2-sft-lima
+  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. -->
+
+# gpt2-sft-lima
+
+This model is a fine-tuned version of [JackFram/llama-68m](https://huggingface.co/JackFram/llama-68m) on the generator dataset.
+It achieves the following results on the evaluation set:
+- Loss: 5.4846
+
+## 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: 2e-05
+- train_batch_size: 32
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 2.0
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 3.4931        | 1.0   | 24   | 5.5962          |
+| 3.4278        | 2.0   | 48   | 5.4846          |
+
+
+### Framework versions
+
+- Transformers 4.40.1
+- Pytorch 2.1.2
+- Datasets 2.14.6
+- Tokenizers 0.19.1

all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 2.0,
+    "total_flos": 394600362541056.0,
+    "train_loss": 3.4869212259848914,
+    "train_runtime": 14.4504,
+    "train_samples": 1030,
+    "train_samples_per_second": 102.281,
+    "train_steps_per_second": 3.322
+}

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "JackFram/llama-68m",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "max_position_embeddings": 2048,
+  "model_type": "llama",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 2,
+  "num_key_value_heads": 12,
+  "pad_token_id": 1,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.40.1",
+  "use_cache": false,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "pad_token_id": 1,
+  "transformers_version": "4.40.1"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8806bf32cff7ec1911f05503bac5b2c0db8784dc06f7b1ec97ab24b7c4851c2
+size 136062744

runs/Apr25_13-08-35_noveens/events.out.tfevents.1714075723.noveens.2735246.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d522c8d2aec3088031ea7be2280b090dd94462a43adb439f7aaff3c819979a6
+size 7762

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "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": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "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 +1,44 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "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": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '### Human\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '### System\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '### Assistant\n'  + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '### Assistant' }}\n{% endif %}\n{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 2048,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false,
+  "use_fast": true
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 2.0,
+    "total_flos": 394600362541056.0,
+    "train_loss": 3.4869212259848914,
+    "train_runtime": 14.4504,
+    "train_samples": 1030,
+    "train_samples_per_second": 102.281,
+    "train_steps_per_second": 3.322
+}

trainer_state.json

@@ -0,0 +1,116 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 48,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.041666666666666664,
+      "grad_norm": 6.875,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 3.886,
+      "step": 1
+    },
+    {
+      "epoch": 0.20833333333333334,
+      "grad_norm": 5.15625,
+      "learning_rate": 2e-05,
+      "loss": 3.5195,
+      "step": 5
+    },
+    {
+      "epoch": 0.4166666666666667,
+      "grad_norm": 3.546875,
+      "learning_rate": 1.9340161087325483e-05,
+      "loss": 3.6848,
+      "step": 10
+    },
+    {
+      "epoch": 0.625,
+      "grad_norm": 3.0625,
+      "learning_rate": 1.744772182743782e-05,
+      "loss": 3.5055,
+      "step": 15
+    },
+    {
+      "epoch": 0.8333333333333334,
+      "grad_norm": 3.0,
+      "learning_rate": 1.4572423233046386e-05,
+      "loss": 3.4931,
+      "step": 20
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 5.596227169036865,
+      "eval_runtime": 0.0423,
+      "eval_samples_per_second": 283.93,
+      "eval_steps_per_second": 47.322,
+      "step": 24
+    },
+    {
+      "epoch": 1.0416666666666667,
+      "grad_norm": 2.90625,
+      "learning_rate": 1.1093712083778748e-05,
+      "loss": 3.4722,
+      "step": 25
+    },
+    {
+      "epoch": 1.25,
+      "grad_norm": 2.828125,
+      "learning_rate": 7.470666176083193e-06,
+      "loss": 3.4108,
+      "step": 30
+    },
+    {
+      "epoch": 1.4583333333333333,
+      "grad_norm": 2.5,
+      "learning_rate": 4.181410844420473e-06,
+      "loss": 3.4187,
+      "step": 35
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "grad_norm": 2.8125,
+      "learning_rate": 1.660021821101222e-06,
+      "loss": 3.4852,
+      "step": 40
+    },
+    {
+      "epoch": 1.875,
+      "grad_norm": 2.484375,
+      "learning_rate": 2.392412244407294e-07,
+      "loss": 3.4278,
+      "step": 45
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 5.484647274017334,
+      "eval_runtime": 0.0423,
+      "eval_samples_per_second": 283.999,
+      "eval_steps_per_second": 47.333,
+      "step": 48
+    },
+    {
+      "epoch": 2.0,
+      "step": 48,
+      "total_flos": 394600362541056.0,
+      "train_loss": 3.4869212259848914,
+      "train_runtime": 14.4504,
+      "train_samples_per_second": 102.281,
+      "train_steps_per_second": 3.322
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 48,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 1000000000,
+  "total_flos": 394600362541056.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2c9ebcd5bf35bdc52b59db2bc7861d16777727aab05faf5f6fe289107775724
+size 5048