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-replicate-problem-10-ttt-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-replicate-problem-10-ttt-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": 34572331909120.0,
+    "train_loss": 0.15067443996667862,
+    "train_runtime": 191.5186,
+    "train_samples": 9,
+    "train_samples_per_second": 0.094,
+    "train_steps_per_second": 0.021
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 2.0,
+    "total_flos": 34572331909120.0,
+    "train_loss": 0.15067443996667862,
+    "train_runtime": 191.5186,
+    "train_samples": 9,
+    "train_samples_per_second": 0.094,
+    "train_steps_per_second": 0.021
+}

trainer_state.json

@@ -0,0 +1,70 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 4,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.023849153128757124,
+      "learning_rate": 5e-05,
+      "loss": 0.1507,
+      "step": 1
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.023633934332332938,
+      "learning_rate": 3.7500000000000003e-05,
+      "loss": 0.1489,
+      "step": 2
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 0.024147454548812466,
+      "learning_rate": 1.2500000000000006e-05,
+      "loss": 0.1522,
+      "step": 3
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.02564623663563028,
+      "learning_rate": 0.0,
+      "loss": 0.1509,
+      "step": 4
+    },
+    {
+      "epoch": 2.0,
+      "step": 4,
+      "total_flos": 34572331909120.0,
+      "train_loss": 0.15067443996667862,
+      "train_runtime": 191.5186,
+      "train_samples_per_second": 0.094,
+      "train_steps_per_second": 0.021
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 4,
+  "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": 34572331909120.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}