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: seed_math_open2math
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # seed_math_open2math
 
-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/seed_math_open2math dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.4229
 

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 2.9655172413793105,
+    "eval_loss": 0.4229108989238739,
+    "eval_runtime": 35.6209,
+    "eval_samples_per_second": 24.648,
+    "eval_steps_per_second": 0.393,
+    "total_flos": 160594195906560.0,
+    "train_loss": 0.4670579458276431,
+    "train_runtime": 5974.442,
+    "train_samples_per_second": 8.369,
+    "train_steps_per_second": 0.016
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 2.9655172413793105,
+    "eval_loss": 0.4229108989238739,
+    "eval_runtime": 35.6209,
+    "eval_samples_per_second": 24.648,
+    "eval_steps_per_second": 0.393
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.9655172413793105,
+    "total_flos": 160594195906560.0,
+    "train_loss": 0.4670579458276431,
+    "train_runtime": 5974.442,
+    "train_samples_per_second": 8.369,
+    "train_steps_per_second": 0.016
+}

trainer_state.json

@@ -0,0 +1,129 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.9655172413793105,
+  "eval_steps": 500,
+  "global_step": 96,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.3065134099616858,
+      "grad_norm": 4.517764402748671,
+      "learning_rate": 5e-06,
+      "loss": 0.6144,
+      "step": 10
+    },
+    {
+      "epoch": 0.6130268199233716,
+      "grad_norm": 1.352739293142765,
+      "learning_rate": 5e-06,
+      "loss": 0.5117,
+      "step": 20
+    },
+    {
+      "epoch": 0.9195402298850575,
+      "grad_norm": 0.6046612962937553,
+      "learning_rate": 5e-06,
+      "loss": 0.4837,
+      "step": 30
+    },
+    {
+      "epoch": 0.9808429118773946,
+      "eval_loss": 0.45525598526000977,
+      "eval_runtime": 35.589,
+      "eval_samples_per_second": 24.671,
+      "eval_steps_per_second": 0.393,
+      "step": 32
+    },
+    {
+      "epoch": 1.2375478927203065,
+      "grad_norm": 0.4935023674158882,
+      "learning_rate": 5e-06,
+      "loss": 0.4907,
+      "step": 40
+    },
+    {
+      "epoch": 1.5440613026819925,
+      "grad_norm": 0.91971618583963,
+      "learning_rate": 5e-06,
+      "loss": 0.4442,
+      "step": 50
+    },
+    {
+      "epoch": 1.8505747126436782,
+      "grad_norm": 0.5574214844021306,
+      "learning_rate": 5e-06,
+      "loss": 0.4322,
+      "step": 60
+    },
+    {
+      "epoch": 1.9731800766283525,
+      "eval_loss": 0.4297981858253479,
+      "eval_runtime": 35.7933,
+      "eval_samples_per_second": 24.53,
+      "eval_steps_per_second": 0.391,
+      "step": 64
+    },
+    {
+      "epoch": 2.1685823754789273,
+      "grad_norm": 0.7652672478398252,
+      "learning_rate": 5e-06,
+      "loss": 0.4571,
+      "step": 70
+    },
+    {
+      "epoch": 2.475095785440613,
+      "grad_norm": 0.8676349922789872,
+      "learning_rate": 5e-06,
+      "loss": 0.4056,
+      "step": 80
+    },
+    {
+      "epoch": 2.781609195402299,
+      "grad_norm": 0.4148384551300883,
+      "learning_rate": 5e-06,
+      "loss": 0.4044,
+      "step": 90
+    },
+    {
+      "epoch": 2.9655172413793105,
+      "eval_loss": 0.4229108989238739,
+      "eval_runtime": 34.6095,
+      "eval_samples_per_second": 25.369,
+      "eval_steps_per_second": 0.405,
+      "step": 96
+    },
+    {
+      "epoch": 2.9655172413793105,
+      "step": 96,
+      "total_flos": 160594195906560.0,
+      "train_loss": 0.4670579458276431,
+      "train_runtime": 5974.442,
+      "train_samples_per_second": 8.369,
+      "train_steps_per_second": 0.016
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 96,
+  "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": 160594195906560.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}