End of training

README.md

@@ -4,6 +4,7 @@ license: llama3.1
 base_model: meta-llama/Meta-Llama-3.1-8B
 tags:
 - llama-factory
+- full
 - generated_from_trainer
 model-index:
 - name: oh_v1-2_only_opengpt
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # oh_v1-2_only_opengpt
 
-This model is a fine-tuned version of [meta-llama/Meta-Llama-3.1-8B](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B) on an unknown dataset.
+This model is a fine-tuned version of [meta-llama/Meta-Llama-3.1-8B](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B) on the mlfoundations-dev/oh_v1-2_only_opengpt dataset.
 It achieves the following results on the evaluation set:
 - Loss: 1.1227
 

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 2.3333333333333335,
+    "eval_loss": 1.1227176189422607,
+    "eval_runtime": 2.2375,
+    "eval_samples_per_second": 8.939,
+    "eval_steps_per_second": 0.447,
+    "total_flos": 1675037245440.0,
+    "train_loss": 3.629718780517578,
+    "train_runtime": 220.1293,
+    "train_samples_per_second": 5.056,
+    "train_steps_per_second": 0.014
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 2.3333333333333335,
+    "eval_loss": 1.1227176189422607,
+    "eval_runtime": 2.2375,
+    "eval_samples_per_second": 8.939,
+    "eval_steps_per_second": 0.447
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.3333333333333335,
+    "total_flos": 1675037245440.0,
+    "train_loss": 3.629718780517578,
+    "train_runtime": 220.1293,
+    "train_samples_per_second": 5.056,
+    "train_steps_per_second": 0.014
+}

trainer_state.json

@@ -0,0 +1,66 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.3333333333333335,
+  "eval_steps": 500,
+  "global_step": 1,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0,
+      "eval_loss": 1.260661005973816,
+      "eval_runtime": 2.6668,
+      "eval_samples_per_second": 7.5,
+      "eval_steps_per_second": 0.375,
+      "step": 0
+    },
+    {
+      "epoch": 0,
+      "eval_loss": 1.260661005973816,
+      "eval_runtime": 2.6411,
+      "eval_samples_per_second": 7.573,
+      "eval_steps_per_second": 0.379,
+      "step": 0
+    },
+    {
+      "epoch": 2.3333333333333335,
+      "eval_loss": 1.1227176189422607,
+      "eval_runtime": 2.4322,
+      "eval_samples_per_second": 8.223,
+      "eval_steps_per_second": 0.411,
+      "step": 1
+    },
+    {
+      "epoch": 2.3333333333333335,
+      "step": 1,
+      "total_flos": 1675037245440.0,
+      "train_loss": 3.629718780517578,
+      "train_runtime": 220.1293,
+      "train_samples_per_second": 5.056,
+      "train_steps_per_second": 0.014
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 3,
+  "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": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1675037245440.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}