Model save

README.md

@@ -0,0 +1,69 @@
+---
+base_model: cotarc0/COT2output-1B
+library_name: peft
+license: llama3.2
+tags:
+- trl
+- sft
+- generated_from_trainer
+model-index:
+- name: 007bbfb7_1B_ttt
+  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. -->
+
+# 007bbfb7_1B_ttt
+
+This model is a fine-tuned version of [cotarc0/COT2output-1B](https://huggingface.co/cotarc0/COT2output-1B) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0437
+
+## 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: 8
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 2
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 32
+- total_eval_batch_size: 16
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 3
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 0.0704        | 1.0   | 3    | 0.0594          |
+| 0.0379        | 2.0   | 6    | 0.0469          |
+| 0.0248        | 3.0   | 9    | 0.0437          |
+
+
+### Framework versions
+
+- PEFT 0.13.2
+- Transformers 4.45.0.dev0
+- Pytorch 2.4.0+cu121
+- Datasets 3.5.0
+- Tokenizers 0.19.1

all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "total_flos": 1111501938688.0,
+    "train_loss": 0.06581349981327851,
+    "train_runtime": 50.5729,
+    "train_samples": 85,
+    "train_samples_per_second": 5.042,
+    "train_steps_per_second": 0.178
+}

runs/Apr25_12-38-54_campbell-compute-01.mae.cornell.edu/events.out.tfevents.1745599172.campbell-compute-01.mae.cornell.edu.98922.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fef9e0d582bfb2d037ae41dd4cdb154ab793e2209ea35d6bc375ab0bc556a79a
-size 8526
+oid sha256:e212744cd07112e23acdecfd928c4228c91de4023402e237e768f3a4280d6740
+size 8874

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "total_flos": 1111501938688.0,
+    "train_loss": 0.06581349981327851,
+    "train_runtime": 50.5729,
+    "train_samples": 85,
+    "train_samples_per_second": 5.042,
+    "train_steps_per_second": 0.178
+}

trainer_state.json

@@ -0,0 +1,129 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 9,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.3333333333333333,
+      "grad_norm": 1.30759354865342,
+      "learning_rate": 0.0002,
+      "loss": 0.1652,
+      "step": 1
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 1.1131666477408941,
+      "learning_rate": 0.0001923879532511287,
+      "loss": 0.138,
+      "step": 2
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.47524766678471886,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 0.0704,
+      "step": 3
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.05938142538070679,
+      "eval_runtime": 0.4827,
+      "eval_samples_per_second": 10.359,
+      "eval_steps_per_second": 2.072,
+      "step": 3
+    },
+    {
+      "epoch": 1.3333333333333333,
+      "grad_norm": 0.4069628072320713,
+      "learning_rate": 0.000138268343236509,
+      "loss": 0.057,
+      "step": 4
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "grad_norm": 0.130205569009941,
+      "learning_rate": 0.0001,
+      "loss": 0.036,
+      "step": 5
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.1675979787627749,
+      "learning_rate": 6.173165676349103e-05,
+      "loss": 0.0379,
+      "step": 6
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.04690684378147125,
+      "eval_runtime": 0.3769,
+      "eval_samples_per_second": 13.268,
+      "eval_steps_per_second": 2.654,
+      "step": 6
+    },
+    {
+      "epoch": 2.3333333333333335,
+      "grad_norm": 0.12675730588511827,
+      "learning_rate": 2.9289321881345254e-05,
+      "loss": 0.0295,
+      "step": 7
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "grad_norm": 0.12228622531109234,
+      "learning_rate": 7.612046748871327e-06,
+      "loss": 0.0335,
+      "step": 8
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.10097323878812325,
+      "learning_rate": 0.0,
+      "loss": 0.0248,
+      "step": 9
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.04368260130286217,
+      "eval_runtime": 0.5921,
+      "eval_samples_per_second": 8.445,
+      "eval_steps_per_second": 1.689,
+      "step": 9
+    },
+    {
+      "epoch": 3.0,
+      "step": 9,
+      "total_flos": 1111501938688.0,
+      "train_loss": 0.06581349981327851,
+      "train_runtime": 50.5729,
+      "train_samples_per_second": 5.042,
+      "train_steps_per_second": 0.178
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 9,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1111501938688.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}