Model save

README.md

@@ -0,0 +1,77 @@
+---
+base_model: meta-llama/Meta-Llama-3-8B
+library_name: peft
+license: llama3
+metrics:
+- accuracy
+- precision
+- recall
+- f1
+tags:
+- generated_from_trainer
+model-index:
+- name: Output_llama2_70-15-15_new
+  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. -->
+
+# Output_llama2_70-15-15_new
+
+This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.6310
+- Accuracy: 0.6474
+- Precision: 0.6760
+- Recall: 0.6474
+- F1: 0.6376
+
+## 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: 1e-05
+- train_batch_size: 16
+- eval_batch_size: 16
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 10
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1     |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
+| No log        | 1.0   | 46   | 0.7791          | 0.4808   | 0.2311    | 0.4808 | 0.3122 |
+| No log        | 2.0   | 92   | 0.7556          | 0.4872   | 0.7519    | 0.4872 | 0.3262 |
+| No log        | 3.0   | 138  | 0.7071          | 0.5064   | 0.5708    | 0.5064 | 0.4086 |
+| No log        | 4.0   | 184  | 0.7045          | 0.5      | 0.5549    | 0.5    | 0.3971 |
+| No log        | 5.0   | 230  | 0.6714          | 0.5705   | 0.6227    | 0.5705 | 0.5340 |
+| No log        | 6.0   | 276  | 0.6976          | 0.4936   | 0.5303    | 0.4936 | 0.3932 |
+| No log        | 7.0   | 322  | 0.6453          | 0.6603   | 0.6906    | 0.6603 | 0.6507 |
+| No log        | 8.0   | 368  | 0.6640          | 0.5769   | 0.6429    | 0.5769 | 0.5354 |
+| No log        | 9.0   | 414  | 0.6460          | 0.6154   | 0.6643    | 0.6154 | 0.5928 |
+| No log        | 10.0  | 460  | 0.6310          | 0.6474   | 0.6760    | 0.6474 | 0.6376 |
+
+
+### Framework versions
+
+- PEFT 0.10.0
+- Transformers 4.41.2
+- Pytorch 2.3.1+cu121
+- Datasets 3.2.0
+- Tokenizers 0.19.1

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd9699fb1d45c7ebc6f9f10f31db2b5656a06c1cc7aa55d67d95e5fa1b1ca7c7
+oid sha256:e107e3c746763fc822ee728479f4440ed39dc0e64cdc37fe10f99651e23267c9
 size 54593240

all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 10.0,
+    "total_flos": 2.488087619686564e+17,
+    "train_loss": 0.5811269345490829,
+    "train_runtime": 16870.9489,
+    "train_samples": 730,
+    "train_samples_per_second": 0.433,
+    "train_steps_per_second": 0.027
+}

runs/Dec18_13-29-32_LCEEE-HAL/events.out.tfevents.1734550172.LCEEE-HAL.1086441.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b14beea7e1cef9f3bf77da962e5e3ca400c90cab04e182553e064b53526777e6
-size 9660
+oid sha256:ee607ee86e8a870237c0836f98e80ce80a8713bf8a3602af4db976118d94113b
+size 10486

tokenizer.json

@@ -6,7 +6,14 @@
     "strategy": "LongestFirst",
     "stride": 0
   },
-  "padding": null,
+  "padding": {
+    "strategy": "BatchLongest",
+    "direction": "Right",
+    "pad_to_multiple_of": null,
+    "pad_id": 128001,
+    "pad_type_id": 0,
+    "pad_token": "<|end_of_text|>"
+  },
   "added_tokens": [
     {
       "id": 128000,

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 10.0,
+    "total_flos": 2.488087619686564e+17,
+    "train_loss": 0.5811269345490829,
+    "train_runtime": 16870.9489,
+    "train_samples": 730,
+    "train_samples_per_second": 0.433,
+    "train_steps_per_second": 0.027
+}

trainer_state.json

@@ -0,0 +1,171 @@
+{
+  "best_metric": 0.6602564102564102,
+  "best_model_checkpoint": "Output_llama2_70-15-15_new/checkpoint-322",
+  "epoch": 10.0,
+  "eval_steps": 500,
+  "global_step": 460,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.4807692307692308,
+      "eval_f1": 0.3121878121878122,
+      "eval_loss": 0.779107391834259,
+      "eval_precision": 0.23113905325443787,
+      "eval_recall": 0.4807692307692308,
+      "eval_runtime": 111.4069,
+      "eval_samples_per_second": 1.4,
+      "eval_steps_per_second": 0.09,
+      "step": 46
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.48717948717948717,
+      "eval_f1": 0.3262093156048617,
+      "eval_loss": 0.755558967590332,
+      "eval_precision": 0.7518610421836228,
+      "eval_recall": 0.48717948717948717,
+      "eval_runtime": 111.1784,
+      "eval_samples_per_second": 1.403,
+      "eval_steps_per_second": 0.09,
+      "step": 92
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.5064102564102564,
+      "eval_f1": 0.40855426407209083,
+      "eval_loss": 0.7070600390434265,
+      "eval_precision": 0.5707901253675902,
+      "eval_recall": 0.5064102564102564,
+      "eval_runtime": 111.2413,
+      "eval_samples_per_second": 1.402,
+      "eval_steps_per_second": 0.09,
+      "step": 138
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.5,
+      "eval_f1": 0.39713058754635955,
+      "eval_loss": 0.7044801115989685,
+      "eval_precision": 0.5548682087143626,
+      "eval_recall": 0.5,
+      "eval_runtime": 111.1012,
+      "eval_samples_per_second": 1.404,
+      "eval_steps_per_second": 0.09,
+      "step": 184
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.5705128205128205,
+      "eval_f1": 0.5339812912754868,
+      "eval_loss": 0.6713973879814148,
+      "eval_precision": 0.622663378087679,
+      "eval_recall": 0.5705128205128205,
+      "eval_runtime": 111.3456,
+      "eval_samples_per_second": 1.401,
+      "eval_steps_per_second": 0.09,
+      "step": 230
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.4935897435897436,
+      "eval_f1": 0.3931920371648725,
+      "eval_loss": 0.6975941061973572,
+      "eval_precision": 0.530316514471444,
+      "eval_recall": 0.4935897435897436,
+      "eval_runtime": 111.0983,
+      "eval_samples_per_second": 1.404,
+      "eval_steps_per_second": 0.09,
+      "step": 276
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.6602564102564102,
+      "eval_f1": 0.6507378243632287,
+      "eval_loss": 0.6453418135643005,
+      "eval_precision": 0.6906434911242604,
+      "eval_recall": 0.6602564102564102,
+      "eval_runtime": 111.1451,
+      "eval_samples_per_second": 1.404,
+      "eval_steps_per_second": 0.09,
+      "step": 322
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.5769230769230769,
+      "eval_f1": 0.5353708791208791,
+      "eval_loss": 0.6639875769615173,
+      "eval_precision": 0.6429280397022332,
+      "eval_recall": 0.5769230769230769,
+      "eval_runtime": 111.2239,
+      "eval_samples_per_second": 1.403,
+      "eval_steps_per_second": 0.09,
+      "step": 368
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.6153846153846154,
+      "eval_f1": 0.5928187429481648,
+      "eval_loss": 0.645951509475708,
+      "eval_precision": 0.6643282486336569,
+      "eval_recall": 0.6153846153846154,
+      "eval_runtime": 111.2453,
+      "eval_samples_per_second": 1.402,
+      "eval_steps_per_second": 0.09,
+      "step": 414
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.6474358974358975,
+      "eval_f1": 0.6375581196222184,
+      "eval_loss": 0.6310403347015381,
+      "eval_precision": 0.6760355029585798,
+      "eval_recall": 0.6474358974358975,
+      "eval_runtime": 111.4617,
+      "eval_samples_per_second": 1.4,
+      "eval_steps_per_second": 0.09,
+      "step": 460
+    },
+    {
+      "epoch": 10.0,
+      "step": 460,
+      "total_flos": 2.488087619686564e+17,
+      "train_loss": 0.5811269345490829,
+      "train_runtime": 16870.9489,
+      "train_samples_per_second": 0.433,
+      "train_steps_per_second": 0.027
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 460,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 10,
+        "early_stopping_threshold": 0.0
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 0
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.488087619686564e+17,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}