Model save

README.md

@@ -0,0 +1,68 @@
+---
+library_name: transformers
+license: llama3
+base_model: meta-llama/Meta-Llama-3-70B
+tags:
+- trl
+- sft
+- generated_from_trainer
+datasets:
+- generator
+model-index:
+- name: llama3-70b-lora-alpaca-11-v1
+  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. -->
+
+# llama3-70b-lora-alpaca-11-v1
+
+This model is a fine-tuned version of [meta-llama/Meta-Llama-3-70B](https://huggingface.co/meta-llama/Meta-Llama-3-70B) on the generator dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.4919
+
+## 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: 16
+- eval_batch_size: 16
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 8
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 256
+- total_eval_batch_size: 128
+- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 1
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 1.4916        | 1.0   | 68   | 1.4919          |
+
+
+### Framework versions
+
+- Transformers 4.46.3
+- Pytorch 2.5.1+cu124
+- Datasets 3.1.0
+- Tokenizers 0.20.3

all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 1.0,
+    "total_flos": 4.647146244454482e+17,
+    "train_loss": 1.5711571276187897,
+    "train_runtime": 2260.7477,
+    "train_samples": 51241,
+    "train_samples_per_second": 7.666,
+    "train_steps_per_second": 0.03
+}

runs/Nov22_05-45-55_agile-light-runs-fin-02/events.out.tfevents.1732255294.agile-light-runs-fin-02.54277.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6aae388abe177a5ababfab200fe3a3f4a6b919d5b4217a046713f2a5dd4cf19e
-size 8517
+oid sha256:ff22e18b1399db7cd4587f3ce03c311128b0daf1c6f98f605eb93c6846a85f91
+size 9131

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 1.0,
+    "total_flos": 4.647146244454482e+17,
+    "train_loss": 1.5711571276187897,
+    "train_runtime": 2260.7477,
+    "train_samples": 51241,
+    "train_samples_per_second": 7.666,
+    "train_steps_per_second": 0.03
+}

trainer_state.json

@@ -0,0 +1,148 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 68,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.014705882352941176,
+      "grad_norm": 0.29233628511428833,
+      "learning_rate": 2.857142857142857e-05,
+      "loss": 1.8412,
+      "step": 1
+    },
+    {
+      "epoch": 0.07352941176470588,
+      "grad_norm": 0.21557892858982086,
+      "learning_rate": 0.00014285714285714287,
+      "loss": 1.8158,
+      "step": 5
+    },
+    {
+      "epoch": 0.14705882352941177,
+      "grad_norm": 0.27912023663520813,
+      "learning_rate": 0.00019880878960910772,
+      "loss": 1.7702,
+      "step": 10
+    },
+    {
+      "epoch": 0.22058823529411764,
+      "grad_norm": 0.19626685976982117,
+      "learning_rate": 0.0001916316904487005,
+      "loss": 1.6706,
+      "step": 15
+    },
+    {
+      "epoch": 0.29411764705882354,
+      "grad_norm": 0.15178152918815613,
+      "learning_rate": 0.00017841198065767107,
+      "loss": 1.5842,
+      "step": 20
+    },
+    {
+      "epoch": 0.36764705882352944,
+      "grad_norm": 0.10677345097064972,
+      "learning_rate": 0.00016002142805483685,
+      "loss": 1.5496,
+      "step": 25
+    },
+    {
+      "epoch": 0.4411764705882353,
+      "grad_norm": 0.08041682839393616,
+      "learning_rate": 0.00013767278936351854,
+      "loss": 1.5281,
+      "step": 30
+    },
+    {
+      "epoch": 0.5147058823529411,
+      "grad_norm": 0.07561662793159485,
+      "learning_rate": 0.00011283983551465511,
+      "loss": 1.5326,
+      "step": 35
+    },
+    {
+      "epoch": 0.5882352941176471,
+      "grad_norm": 0.09348361939191818,
+      "learning_rate": 8.71601644853449e-05,
+      "loss": 1.5256,
+      "step": 40
+    },
+    {
+      "epoch": 0.6617647058823529,
+      "grad_norm": 0.08627992123365402,
+      "learning_rate": 6.232721063648148e-05,
+      "loss": 1.5018,
+      "step": 45
+    },
+    {
+      "epoch": 0.7352941176470589,
+      "grad_norm": 0.09307563304901123,
+      "learning_rate": 3.997857194516319e-05,
+      "loss": 1.526,
+      "step": 50
+    },
+    {
+      "epoch": 0.8088235294117647,
+      "grad_norm": 0.08465312421321869,
+      "learning_rate": 2.1588019342328968e-05,
+      "loss": 1.495,
+      "step": 55
+    },
+    {
+      "epoch": 0.8823529411764706,
+      "grad_norm": 0.08478015661239624,
+      "learning_rate": 8.368309551299536e-06,
+      "loss": 1.4859,
+      "step": 60
+    },
+    {
+      "epoch": 0.9558823529411765,
+      "grad_norm": 0.07574094086885452,
+      "learning_rate": 1.1912103908922945e-06,
+      "loss": 1.4916,
+      "step": 65
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 1.4919378757476807,
+      "eval_runtime": 11.3628,
+      "eval_samples_per_second": 15.137,
+      "eval_steps_per_second": 0.176,
+      "step": 68
+    },
+    {
+      "epoch": 1.0,
+      "step": 68,
+      "total_flos": 4.647146244454482e+17,
+      "train_loss": 1.5711571276187897,
+      "train_runtime": 2260.7477,
+      "train_samples_per_second": 7.666,
+      "train_steps_per_second": 0.03
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 68,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4.647146244454482e+17,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}