Model save

README.md

@@ -0,0 +1,59 @@
+---
+license: gemma
+base_model: google/gemma-2-2b
+tags:
+- trl
+- sft
+- generated_from_trainer
+model-index:
+- name: easylm-hs-sft-gemma-2-2b
+  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. -->
+
+# easylm-hs-sft-gemma-2-2b
+
+This model is a fine-tuned version of [google/gemma-2-2b](https://huggingface.co/google/gemma-2-2b) 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: 3e-06
+- train_batch_size: 2
+- eval_batch_size: 2
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 4
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 32
+- total_eval_batch_size: 8
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- num_epochs: 1
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.43.3
+- Pytorch 2.3.0+cu121
+- Datasets 2.20.0
+- Tokenizers 0.19.1

all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 0.9988545246277205,
+    "total_flos": 5.419062457584845e+16,
+    "train_loss": 1.1514144337505376,
+    "train_runtime": 718.1022,
+    "train_samples": 6981,
+    "train_samples_per_second": 9.721,
+    "train_steps_per_second": 0.304
+}

generation_config.json

@@ -0,0 +1,8 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 2,
+  "cache_implementation": "hybrid",
+  "eos_token_id": 1,
+  "pad_token_id": 0,
+  "transformers_version": "4.43.3"
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 0.9988545246277205,
+    "total_flos": 5.419062457584845e+16,
+    "train_loss": 1.1514144337505376,
+    "train_runtime": 718.1022,
+    "train_samples": 6981,
+    "train_samples_per_second": 9.721,
+    "train_steps_per_second": 0.304
+}

trainer_state.json

@@ -0,0 +1,42 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9988545246277205,
+  "eval_steps": 500,
+  "global_step": 218,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.9988545246277205,
+      "step": 218,
+      "total_flos": 5.419062457584845e+16,
+      "train_loss": 1.1514144337505376,
+      "train_runtime": 718.1022,
+      "train_samples_per_second": 9.721,
+      "train_steps_per_second": 0.304
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 218,
+  "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": 5.419062457584845e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}