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_evol_instruct_70k
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # oh_v3-1_only_evol_instruct_70k
 
-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_evol_instruct_70k dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.7941
 

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 2.9254901960784316,
+    "eval_loss": 0.7940625548362732,
+    "eval_runtime": 22.979,
+    "eval_samples_per_second": 37.338,
+    "eval_steps_per_second": 0.609,
+    "total_flos": 155569084170240.0,
+    "train_loss": 0.7858432877448297,
+    "train_runtime": 3252.6741,
+    "train_samples_per_second": 15.036,
+    "train_steps_per_second": 0.029
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 2.9254901960784316,
+    "eval_loss": 0.7940625548362732,
+    "eval_runtime": 22.979,
+    "eval_samples_per_second": 37.338,
+    "eval_steps_per_second": 0.609
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.9254901960784316,
+    "total_flos": 155569084170240.0,
+    "train_loss": 0.7858432877448297,
+    "train_runtime": 3252.6741,
+    "train_samples_per_second": 15.036,
+    "train_steps_per_second": 0.029
+}

trainer_state.json

@@ -0,0 +1,129 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.9254901960784316,
+  "eval_steps": 500,
+  "global_step": 93,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.3137254901960784,
+      "grad_norm": 2.336262901028998,
+      "learning_rate": 5e-06,
+      "loss": 0.9512,
+      "step": 10
+    },
+    {
+      "epoch": 0.6274509803921569,
+      "grad_norm": 3.633942953576143,
+      "learning_rate": 5e-06,
+      "loss": 0.8626,
+      "step": 20
+    },
+    {
+      "epoch": 0.9411764705882353,
+      "grad_norm": 0.8555264735455949,
+      "learning_rate": 5e-06,
+      "loss": 0.8287,
+      "step": 30
+    },
+    {
+      "epoch": 0.9725490196078431,
+      "eval_loss": 0.8302477598190308,
+      "eval_runtime": 23.209,
+      "eval_samples_per_second": 36.968,
+      "eval_steps_per_second": 0.603,
+      "step": 31
+    },
+    {
+      "epoch": 1.2588235294117647,
+      "grad_norm": 2.2142492192485475,
+      "learning_rate": 5e-06,
+      "loss": 0.8027,
+      "step": 40
+    },
+    {
+      "epoch": 1.572549019607843,
+      "grad_norm": 0.7293421113890972,
+      "learning_rate": 5e-06,
+      "loss": 0.7677,
+      "step": 50
+    },
+    {
+      "epoch": 1.8862745098039215,
+      "grad_norm": 0.7379602742245062,
+      "learning_rate": 5e-06,
+      "loss": 0.7548,
+      "step": 60
+    },
+    {
+      "epoch": 1.9803921568627452,
+      "eval_loss": 0.7995137572288513,
+      "eval_runtime": 25.1383,
+      "eval_samples_per_second": 34.131,
+      "eval_steps_per_second": 0.557,
+      "step": 63
+    },
+    {
+      "epoch": 2.203921568627451,
+      "grad_norm": 0.8847804655288495,
+      "learning_rate": 5e-06,
+      "loss": 0.7385,
+      "step": 70
+    },
+    {
+      "epoch": 2.5176470588235293,
+      "grad_norm": 1.3342767524535535,
+      "learning_rate": 5e-06,
+      "loss": 0.6998,
+      "step": 80
+    },
+    {
+      "epoch": 2.831372549019608,
+      "grad_norm": 0.88474229556434,
+      "learning_rate": 5e-06,
+      "loss": 0.6929,
+      "step": 90
+    },
+    {
+      "epoch": 2.9254901960784316,
+      "eval_loss": 0.7940625548362732,
+      "eval_runtime": 21.2423,
+      "eval_samples_per_second": 40.391,
+      "eval_steps_per_second": 0.659,
+      "step": 93
+    },
+    {
+      "epoch": 2.9254901960784316,
+      "step": 93,
+      "total_flos": 155569084170240.0,
+      "train_loss": 0.7858432877448297,
+      "train_runtime": 3252.6741,
+      "train_samples_per_second": 15.036,
+      "train_steps_per_second": 0.029
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 93,
+  "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": 155569084170240.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}