Model save

.ipynb_checkpoints/all_results-checkpoint.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.8,
+    "total_flos": 2.2539726376402944e+16,
+    "train_loss": 2.351849317550659,
+    "train_runtime": 289.1969,
+    "train_samples_per_second": 1.107,
+    "train_steps_per_second": 0.003
+}

.ipynb_checkpoints/trainer_state-checkpoint.json

@@ -0,0 +1,38 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.8,
+  "eval_steps": 500,
+  "global_step": 1,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.8,
+      "eval_loss": 2.3482213020324707,
+      "eval_runtime": 27.1303,
+      "eval_samples_per_second": 2.949,
+      "eval_steps_per_second": 1.474,
+      "step": 1
+    },
+    {
+      "epoch": 0.8,
+      "step": 1,
+      "total_flos": 2.2539726376402944e+16,
+      "train_loss": 2.351849317550659,
+      "train_runtime": 289.1969,
+      "train_samples_per_second": 1.107,
+      "train_steps_per_second": 0.003
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 1,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "total_flos": 2.2539726376402944e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

README.md

@@ -0,0 +1,76 @@
+---
+license: apache-2.0
+library_name: peft
+tags:
+- trl
+- sft
+- generated_from_trainer
+datasets:
+- generator
+base_model: mistralai/Mistral-7B-v0.1
+model-index:
+- name: Project5_V3_Mistral7b_V2.1
+  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. -->
+
+# Project5_V3_Mistral7b_V2.1
+
+This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the generator dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.3036
+
+## 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: 2
+- eval_batch_size: 2
+- seed: 42
+- gradient_accumulation_steps: 128
+- total_train_batch_size: 256
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- num_epochs: 15
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| No log        | 0.8   | 1    | 2.3482          |
+| No log        | 1.6   | 2    | 2.3439          |
+| No log        | 2.4   | 3    | 2.3386          |
+| 2.3422        | 4.0   | 5    | 2.3264          |
+| 2.3422        | 4.8   | 6    | 2.3212          |
+| 2.3422        | 5.6   | 7    | 2.3166          |
+| 2.3422        | 6.4   | 8    | 2.3126          |
+| 2.3191        | 8.0   | 10   | 2.3072          |
+| 2.3191        | 8.8   | 11   | 2.3055          |
+| 2.3191        | 9.6   | 12   | 2.3045          |
+| 2.3191        | 10.4  | 13   | 2.3039          |
+| 2.3082        | 12.0  | 15   | 2.3036          |
+
+
+### Framework versions
+
+- PEFT 0.7.1
+- Transformers 4.37.0
+- Pytorch 2.1.2+cu121
+- Datasets 2.16.1
+- Tokenizers 0.15.1

adapter_config.json

@@ -0,0 +1,28 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-v0.1",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "k_proj",
+    "o_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed588fc1b694baa6f08f342c3efbce54f7fa1cb3d6f423ffa035ba944baaddd1
+size 109086672

all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 12.0,
+    "total_flos": 3.3809589564604416e+17,
+    "train_loss": 2.323172187805176,
+    "train_runtime": 4255.0402,
+    "train_samples": 60,
+    "train_samples_per_second": 1.128,
+    "train_steps_per_second": 0.004
+}

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\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
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 12.0,
+    "total_flos": 3.3809589564604416e+17,
+    "train_loss": 2.323172187805176,
+    "train_runtime": 4255.0402,
+    "train_samples": 60,
+    "train_samples_per_second": 1.128,
+    "train_steps_per_second": 0.004
+}

trainer_state.json

@@ -0,0 +1,144 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 12.0,
+  "eval_steps": 500,
+  "global_step": 15,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.8,
+      "eval_loss": 2.348168134689331,
+      "eval_runtime": 27.1441,
+      "eval_samples_per_second": 2.947,
+      "eval_steps_per_second": 1.474,
+      "step": 1
+    },
+    {
+      "epoch": 1.6,
+      "eval_loss": 2.343932628631592,
+      "eval_runtime": 27.1355,
+      "eval_samples_per_second": 2.948,
+      "eval_steps_per_second": 1.474,
+      "step": 2
+    },
+    {
+      "epoch": 2.4,
+      "eval_loss": 2.338569164276123,
+      "eval_runtime": 27.1328,
+      "eval_samples_per_second": 2.948,
+      "eval_steps_per_second": 1.474,
+      "step": 3
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 1.5000000000000002e-05,
+      "loss": 2.3422,
+      "step": 5
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 2.3264243602752686,
+      "eval_runtime": 27.1569,
+      "eval_samples_per_second": 2.946,
+      "eval_steps_per_second": 1.473,
+      "step": 5
+    },
+    {
+      "epoch": 4.8,
+      "eval_loss": 2.321211576461792,
+      "eval_runtime": 27.1325,
+      "eval_samples_per_second": 2.948,
+      "eval_steps_per_second": 1.474,
+      "step": 6
+    },
+    {
+      "epoch": 5.6,
+      "eval_loss": 2.3165886402130127,
+      "eval_runtime": 27.1266,
+      "eval_samples_per_second": 2.949,
+      "eval_steps_per_second": 1.475,
+      "step": 7
+    },
+    {
+      "epoch": 6.4,
+      "eval_loss": 2.3125572204589844,
+      "eval_runtime": 27.13,
+      "eval_samples_per_second": 2.949,
+      "eval_steps_per_second": 1.474,
+      "step": 8
+    },
+    {
+      "epoch": 8.0,
+      "learning_rate": 5.000000000000003e-06,
+      "loss": 2.3191,
+      "step": 10
+    },
+    {
+      "epoch": 8.0,
+      "eval_loss": 2.307173252105713,
+      "eval_runtime": 27.1321,
+      "eval_samples_per_second": 2.949,
+      "eval_steps_per_second": 1.474,
+      "step": 10
+    },
+    {
+      "epoch": 8.8,
+      "eval_loss": 2.3055243492126465,
+      "eval_runtime": 27.1317,
+      "eval_samples_per_second": 2.949,
+      "eval_steps_per_second": 1.474,
+      "step": 11
+    },
+    {
+      "epoch": 9.6,
+      "eval_loss": 2.3045384883880615,
+      "eval_runtime": 27.1304,
+      "eval_samples_per_second": 2.949,
+      "eval_steps_per_second": 1.474,
+      "step": 12
+    },
+    {
+      "epoch": 10.4,
+      "eval_loss": 2.3039393424987793,
+      "eval_runtime": 27.1363,
+      "eval_samples_per_second": 2.948,
+      "eval_steps_per_second": 1.474,
+      "step": 13
+    },
+    {
+      "epoch": 12.0,
+      "learning_rate": 0.0,
+      "loss": 2.3082,
+      "step": 15
+    },
+    {
+      "epoch": 12.0,
+      "eval_loss": 2.3035786151885986,
+      "eval_runtime": 27.1238,
+      "eval_samples_per_second": 2.949,
+      "eval_steps_per_second": 1.475,
+      "step": 15
+    },
+    {
+      "epoch": 12.0,
+      "step": 15,
+      "total_flos": 3.3809589564604416e+17,
+      "train_loss": 2.323172187805176,
+      "train_runtime": 4255.0402,
+      "train_samples_per_second": 1.128,
+      "train_steps_per_second": 0.004
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 15,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 15,
+  "save_steps": 500,
+  "total_flos": 3.3809589564604416e+17,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d78e4cef540d4143335d20d0aa2d51cff93b79b672b0da42cd4de55f3118736e
+size 4792