Training completed

README.md

@@ -0,0 +1,63 @@
+---
+library_name: peft
+license: llama3.2
+base_model: meta-llama/Llama-3.2-1B
+tags:
+- base_model:adapter:meta-llama/Llama-3.2-1B
+- lora
+- transformers
+pipeline_tag: text-generation
+model-index:
+- name: testing_fsdp2_qwen2-5-7b
+  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. -->
+
+# testing_fsdp2_qwen2-5-7b
+
+This model is a fine-tuned version of [meta-llama/Llama-3.2-1B](https://huggingface.co/meta-llama/Llama-3.2-1B) 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: 0.0001
+- train_batch_size: 2
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 8
+- gradient_accumulation_steps: 10
+- total_train_batch_size: 160
+- total_eval_batch_size: 64
+- optimizer: Use OptimizerNames.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: 0.03
+- training_steps: 20
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.16.0
+- Transformers 4.53.2
+- Pytorch 2.7.1+cu126
+- Datasets 4.0.0
+- Tokenizers 0.21.2

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.0365296803652968,
+    "total_flos": 3.848728354383462e+16,
+    "train_loss": 2.1222381591796875,
+    "train_runtime": 286.5025,
+    "train_samples_per_second": 11.169,
+    "train_steps_per_second": 0.07
+}

metrics.json

@@ -0,0 +1 @@
+{"run_name": "./custom_code_fsdp2_qwen2-507b", "train_runtime": 286.9383, "train_samples_per_second": 11.152, "train_steps_per_second": 0.07, "total_flos": 3.848728354383462e+16, "train_loss": 2.134036064147949, "epoch": 0.0365296803652968}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.0365296803652968,
+    "total_flos": 3.848728354383462e+16,
+    "train_loss": 2.1222381591796875,
+    "train_runtime": 286.5025,
+    "train_samples_per_second": 11.169,
+    "train_steps_per_second": 0.07
+}

trainer_state.json

@@ -0,0 +1,43 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.0365296803652968,
+  "eval_steps": 0,
+  "global_step": 20,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0365296803652968,
+      "step": 20,
+      "total_flos": 3.848728354383462e+16,
+      "train_loss": 2.1222381591796875,
+      "train_runtime": 286.5025,
+      "train_samples_per_second": 11.169,
+      "train_steps_per_second": 0.07
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 20,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "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": 3.848728354383462e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}