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_v3-1_only_platypus
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # oh_v3-1_only_platypus
 
-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_v3-1_only_platypus dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.4672
 

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 2.8514851485148514,
+    "eval_loss": 0.4672066271305084,
+    "eval_runtime": 9.2913,
+    "eval_samples_per_second": 36.378,
+    "eval_steps_per_second": 0.646,
+    "total_flos": 60091961180160.0,
+    "train_loss": 0.5310182438956367,
+    "train_runtime": 1402.3185,
+    "train_samples_per_second": 13.726,
+    "train_steps_per_second": 0.026
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 2.8514851485148514,
+    "eval_loss": 0.4672066271305084,
+    "eval_runtime": 9.2913,
+    "eval_samples_per_second": 36.378,
+    "eval_steps_per_second": 0.646
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.8514851485148514,
+    "total_flos": 60091961180160.0,
+    "train_loss": 0.5310182438956367,
+    "train_runtime": 1402.3185,
+    "train_samples_per_second": 13.726,
+    "train_steps_per_second": 0.026
+}

trainer_state.json

@@ -0,0 +1,87 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.8514851485148514,
+  "eval_steps": 500,
+  "global_step": 36,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.7920792079207921,
+      "grad_norm": 2.038469172009169,
+      "learning_rate": 5e-06,
+      "loss": 0.6264,
+      "step": 10
+    },
+    {
+      "epoch": 0.9504950495049505,
+      "eval_loss": 0.5223038792610168,
+      "eval_runtime": 10.2142,
+      "eval_samples_per_second": 33.091,
+      "eval_steps_per_second": 0.587,
+      "step": 12
+    },
+    {
+      "epoch": 1.5841584158415842,
+      "grad_norm": 0.7102748781551793,
+      "learning_rate": 5e-06,
+      "loss": 0.5367,
+      "step": 20
+    },
+    {
+      "epoch": 1.9801980198019802,
+      "eval_loss": 0.4788552224636078,
+      "eval_runtime": 10.4292,
+      "eval_samples_per_second": 32.409,
+      "eval_steps_per_second": 0.575,
+      "step": 25
+    },
+    {
+      "epoch": 2.376237623762376,
+      "grad_norm": 0.5465837757941338,
+      "learning_rate": 5e-06,
+      "loss": 0.4893,
+      "step": 30
+    },
+    {
+      "epoch": 2.8514851485148514,
+      "eval_loss": 0.4672066271305084,
+      "eval_runtime": 9.082,
+      "eval_samples_per_second": 37.216,
+      "eval_steps_per_second": 0.661,
+      "step": 36
+    },
+    {
+      "epoch": 2.8514851485148514,
+      "step": 36,
+      "total_flos": 60091961180160.0,
+      "train_loss": 0.5310182438956367,
+      "train_runtime": 1402.3185,
+      "train_samples_per_second": 13.726,
+      "train_steps_per_second": 0.026
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 36,
+  "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": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 60091961180160.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}