Model save

README.md

@@ -0,0 +1,72 @@
+---
+library_name: peft
+license: llama3.3
+base_model: meta-llama/Llama-3.3-70B-Instruct
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: Output_llama70B_70-15-15
+  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_llama70B_70-15-15
+
+This model is a fine-tuned version of [meta-llama/Llama-3.3-70B-Instruct](https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.5734
+- Balanced Accuracy: 0.7044
+- Accuracy: 0.6923
+
+## 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 | Balanced Accuracy | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:-----------------:|:--------:|
+| No log        | 1.0   | 46   | 0.7989          | 0.5634            | 0.5449   |
+| No log        | 2.0   | 92   | 0.6930          | 0.5440            | 0.5449   |
+| No log        | 3.0   | 138  | 0.6273          | 0.6321            | 0.6026   |
+| No log        | 4.0   | 184  | 0.6713          | 0.5862            | 0.5833   |
+| No log        | 5.0   | 230  | 0.6085          | 0.6298            | 0.6218   |
+| No log        | 6.0   | 276  | 0.6010          | 0.6623            | 0.6538   |
+| No log        | 7.0   | 322  | 0.5909          | 0.6800            | 0.6731   |
+| No log        | 8.0   | 368  | 0.5874          | 0.6646            | 0.6603   |
+| No log        | 9.0   | 414  | 0.5819          | 0.6722            | 0.6667   |
+| No log        | 10.0  | 460  | 0.5734          | 0.7044            | 0.6923   |
+
+
+### Framework versions
+
+- PEFT 0.10.0
+- Transformers 4.45.2
+- Pytorch 2.5.1+cu124
+- Datasets 2.18.0
+- Tokenizers 0.20.3

all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 10.0,
+    "total_flos": 2.4377643132882125e+18,
+    "train_loss": 0.6270130323327106,
+    "train_runtime": 147963.5893,
+    "train_samples": 730,
+    "train_samples_per_second": 0.049,
+    "train_steps_per_second": 0.003
+}

runs/Dec19_13-44-36_LCEEE-HAL/events.out.tfevents.1734637477.LCEEE-HAL.1165129.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e5d485a8f0394659f935b3b9c462ce22deb02ac63cfc5286c41a1b5dac166f3
-size 9202
+oid sha256:3acf0b78cfa827a2d55add9683de79a7a2a32a455dc1ff67ba44aab1e24897de
+size 9940

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f2f90a0ee1b41702c7b233b02234294a53bc0684a08d3bcd8c8ff702e9a12f64
-size 17210019
+oid sha256:33d3874e937e6dc42804e6951339c78ad2c4842fb35e0019f080b6fff5cece4e
+size 17210184

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 10.0,
+    "total_flos": 2.4377643132882125e+18,
+    "train_loss": 0.6270130323327106,
+    "train_runtime": 147963.5893,
+    "train_samples": 730,
+    "train_samples_per_second": 0.049,
+    "train_steps_per_second": 0.003
+}

trainer_state.json

@@ -0,0 +1,151 @@
+{
+  "best_metric": 0.6923076923076923,
+  "best_model_checkpoint": "Output_llama70B_70-15-15/checkpoint-460",
+  "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": 0.5448717948717948,
+      "eval_balanced_accuracy": 0.5634387351778656,
+      "eval_loss": 0.7988640069961548,
+      "eval_runtime": 1019.3156,
+      "eval_samples_per_second": 0.153,
+      "eval_steps_per_second": 0.01,
+      "step": 46
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.5448717948717948,
+      "eval_balanced_accuracy": 0.5440013183915623,
+      "eval_loss": 0.6930041909217834,
+      "eval_runtime": 1019.1843,
+      "eval_samples_per_second": 0.153,
+      "eval_steps_per_second": 0.01,
+      "step": 92
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.6025641025641025,
+      "eval_balanced_accuracy": 0.6321133412042503,
+      "eval_loss": 0.6272755861282349,
+      "eval_runtime": 1019.1074,
+      "eval_samples_per_second": 0.153,
+      "eval_steps_per_second": 0.01,
+      "step": 138
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.5833333333333334,
+      "eval_balanced_accuracy": 0.5862126245847177,
+      "eval_loss": 0.6713263988494873,
+      "eval_runtime": 1019.4022,
+      "eval_samples_per_second": 0.153,
+      "eval_steps_per_second": 0.01,
+      "step": 184
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.6217948717948718,
+      "eval_balanced_accuracy": 0.6298076923076923,
+      "eval_loss": 0.6084591746330261,
+      "eval_runtime": 1018.424,
+      "eval_samples_per_second": 0.153,
+      "eval_steps_per_second": 0.01,
+      "step": 230
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.6538461538461539,
+      "eval_balanced_accuracy": 0.6622862286228623,
+      "eval_loss": 0.600964367389679,
+      "eval_runtime": 1018.008,
+      "eval_samples_per_second": 0.153,
+      "eval_steps_per_second": 0.01,
+      "step": 276
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.6730769230769231,
+      "eval_balanced_accuracy": 0.6799788881069668,
+      "eval_loss": 0.5909102559089661,
+      "eval_runtime": 1019.21,
+      "eval_samples_per_second": 0.153,
+      "eval_steps_per_second": 0.01,
+      "step": 322
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.6602564102564102,
+      "eval_balanced_accuracy": 0.6645833333333333,
+      "eval_loss": 0.5873510837554932,
+      "eval_runtime": 1019.1861,
+      "eval_samples_per_second": 0.153,
+      "eval_steps_per_second": 0.01,
+      "step": 368
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.6666666666666666,
+      "eval_balanced_accuracy": 0.6721998951598812,
+      "eval_loss": 0.5819327235221863,
+      "eval_runtime": 1019.2331,
+      "eval_samples_per_second": 0.153,
+      "eval_steps_per_second": 0.01,
+      "step": 414
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.6923076923076923,
+      "eval_balanced_accuracy": 0.7044104410441044,
+      "eval_loss": 0.573430061340332,
+      "eval_runtime": 1019.4135,
+      "eval_samples_per_second": 0.153,
+      "eval_steps_per_second": 0.01,
+      "step": 460
+    },
+    {
+      "epoch": 10.0,
+      "step": 460,
+      "total_flos": 2.4377643132882125e+18,
+      "train_loss": 0.6270130323327106,
+      "train_runtime": 147963.5893,
+      "train_samples_per_second": 0.049,
+      "train_steps_per_second": 0.003
+    }
+  ],
+  "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": 2.4377643132882125e+18,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}