Model save

README.md

@@ -0,0 +1,61 @@
+---
+library_name: peft
+license: mit
+base_model: deepseek-ai/DeepSeek-R1-Distill-Qwen-32B
+tags:
+- trl
+- sft
+- generated_from_trainer
+model-index:
+- name: models-p10-ttt-021125-scratch-final-run-continue-step2
+  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. -->
+
+# models-p10-ttt-021125-scratch-final-run-continue-step2
+
+This model is a fine-tuned version of [deepseek-ai/DeepSeek-R1-Distill-Qwen-32B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B) on an unknown dataset.
+
+## 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: 5e-05
+- train_batch_size: 1
+- eval_batch_size: 1
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 8
+- total_train_batch_size: 8
+- total_eval_batch_size: 8
+- 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: 2
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.13.2
+- Transformers 4.47.0.dev0
+- Pytorch 2.4.0+cu121
+- Datasets 3.1.0
+- Tokenizers 0.20.3

all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 2.0,
+    "total_flos": 119607675322368.0,
+    "train_loss": 0.12844415986910462,
+    "train_runtime": 361.5711,
+    "train_samples": 64,
+    "train_samples_per_second": 0.354,
+    "train_steps_per_second": 0.044
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 2.0,
+    "total_flos": 119607675322368.0,
+    "train_loss": 0.12844415986910462,
+    "train_runtime": 361.5711,
+    "train_samples": 64,
+    "train_samples_per_second": 0.354,
+    "train_steps_per_second": 0.044
+}

trainer_state.json

@@ -0,0 +1,154 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 16,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.125,
+      "grad_norm": 0.031228310501700943,
+      "learning_rate": 2.5e-05,
+      "loss": 0.158,
+      "step": 1
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 0.027729531542315396,
+      "learning_rate": 5e-05,
+      "loss": 0.1409,
+      "step": 2
+    },
+    {
+      "epoch": 0.375,
+      "grad_norm": 0.027708645363386786,
+      "learning_rate": 4.937319780454559e-05,
+      "loss": 0.1542,
+      "step": 3
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.036723870178071855,
+      "learning_rate": 4.752422169756048e-05,
+      "loss": 0.1481,
+      "step": 4
+    },
+    {
+      "epoch": 0.625,
+      "grad_norm": 0.04255229647136804,
+      "learning_rate": 4.454578706170075e-05,
+      "loss": 0.1515,
+      "step": 5
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 0.03624295478970934,
+      "learning_rate": 4.058724504646834e-05,
+      "loss": 0.1405,
+      "step": 6
+    },
+    {
+      "epoch": 0.875,
+      "grad_norm": 0.04036433106644355,
+      "learning_rate": 3.5847093477938956e-05,
+      "loss": 0.1333,
+      "step": 7
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.03018836711305969,
+      "learning_rate": 3.056302334890786e-05,
+      "loss": 0.1256,
+      "step": 8
+    },
+    {
+      "epoch": 1.125,
+      "grad_norm": 0.033638020258037256,
+      "learning_rate": 2.5e-05,
+      "loss": 0.124,
+      "step": 9
+    },
+    {
+      "epoch": 1.25,
+      "grad_norm": 0.028956928799089322,
+      "learning_rate": 1.9436976651092144e-05,
+      "loss": 0.1083,
+      "step": 10
+    },
+    {
+      "epoch": 1.375,
+      "grad_norm": 0.028358770524407436,
+      "learning_rate": 1.4152906522061048e-05,
+      "loss": 0.1161,
+      "step": 11
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 0.031706185427414185,
+      "learning_rate": 9.412754953531663e-06,
+      "loss": 0.1197,
+      "step": 12
+    },
+    {
+      "epoch": 1.625,
+      "grad_norm": 0.026949979451069313,
+      "learning_rate": 5.454212938299255e-06,
+      "loss": 0.1091,
+      "step": 13
+    },
+    {
+      "epoch": 1.75,
+      "grad_norm": 0.0275028444563397,
+      "learning_rate": 2.475778302439524e-06,
+      "loss": 0.1054,
+      "step": 14
+    },
+    {
+      "epoch": 1.875,
+      "grad_norm": 0.030444812563220625,
+      "learning_rate": 6.268021954544096e-07,
+      "loss": 0.1054,
+      "step": 15
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.02629836230788519,
+      "learning_rate": 0.0,
+      "loss": 0.115,
+      "step": 16
+    },
+    {
+      "epoch": 2.0,
+      "step": 16,
+      "total_flos": 119607675322368.0,
+      "train_loss": 0.12844415986910462,
+      "train_runtime": 361.5711,
+      "train_samples_per_second": 0.354,
+      "train_steps_per_second": 0.044
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 16,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "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": 119607675322368.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}