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_camel_math
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # oh_v3-1_only_camel_math
 
-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_camel_math dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.4514
 

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 2.966292134831461,
+    "eval_loss": 0.45137423276901245,
+    "eval_runtime": 24.17,
+    "eval_samples_per_second": 37.112,
+    "eval_steps_per_second": 0.621,
+    "total_flos": 165619307642880.0,
+    "train_loss": 0.47901475549948336,
+    "train_runtime": 3378.4389,
+    "train_samples_per_second": 15.12,
+    "train_steps_per_second": 0.029
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 2.966292134831461,
+    "eval_loss": 0.45137423276901245,
+    "eval_runtime": 24.17,
+    "eval_samples_per_second": 37.112,
+    "eval_steps_per_second": 0.621
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.966292134831461,
+    "total_flos": 165619307642880.0,
+    "train_loss": 0.47901475549948336,
+    "train_runtime": 3378.4389,
+    "train_samples_per_second": 15.12,
+    "train_steps_per_second": 0.029
+}

trainer_state.json

@@ -0,0 +1,129 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.966292134831461,
+  "eval_steps": 500,
+  "global_step": 99,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.299625468164794,
+      "grad_norm": 5.757345910987323,
+      "learning_rate": 5e-06,
+      "loss": 0.6175,
+      "step": 10
+    },
+    {
+      "epoch": 0.599250936329588,
+      "grad_norm": 0.6487365234702231,
+      "learning_rate": 5e-06,
+      "loss": 0.5275,
+      "step": 20
+    },
+    {
+      "epoch": 0.898876404494382,
+      "grad_norm": 0.523440762965817,
+      "learning_rate": 5e-06,
+      "loss": 0.4984,
+      "step": 30
+    },
+    {
+      "epoch": 0.9887640449438202,
+      "eval_loss": 0.4796934723854065,
+      "eval_runtime": 23.5376,
+      "eval_samples_per_second": 38.109,
+      "eval_steps_per_second": 0.637,
+      "step": 33
+    },
+    {
+      "epoch": 1.198501872659176,
+      "grad_norm": 0.6955838675332602,
+      "learning_rate": 5e-06,
+      "loss": 0.5026,
+      "step": 40
+    },
+    {
+      "epoch": 1.4981273408239701,
+      "grad_norm": 0.7028060911231481,
+      "learning_rate": 5e-06,
+      "loss": 0.4573,
+      "step": 50
+    },
+    {
+      "epoch": 1.797752808988764,
+      "grad_norm": 0.40607080730215483,
+      "learning_rate": 5e-06,
+      "loss": 0.4507,
+      "step": 60
+    },
+    {
+      "epoch": 1.9775280898876404,
+      "eval_loss": 0.4573969542980194,
+      "eval_runtime": 24.0307,
+      "eval_samples_per_second": 37.327,
+      "eval_steps_per_second": 0.624,
+      "step": 66
+    },
+    {
+      "epoch": 2.097378277153558,
+      "grad_norm": 1.1033961169170152,
+      "learning_rate": 5e-06,
+      "loss": 0.4661,
+      "step": 70
+    },
+    {
+      "epoch": 2.397003745318352,
+      "grad_norm": 0.6238806503968296,
+      "learning_rate": 5e-06,
+      "loss": 0.4286,
+      "step": 80
+    },
+    {
+      "epoch": 2.696629213483146,
+      "grad_norm": 0.46554230052456863,
+      "learning_rate": 5e-06,
+      "loss": 0.4134,
+      "step": 90
+    },
+    {
+      "epoch": 2.966292134831461,
+      "eval_loss": 0.45137423276901245,
+      "eval_runtime": 22.9266,
+      "eval_samples_per_second": 39.125,
+      "eval_steps_per_second": 0.654,
+      "step": 99
+    },
+    {
+      "epoch": 2.966292134831461,
+      "step": 99,
+      "total_flos": 165619307642880.0,
+      "train_loss": 0.47901475549948336,
+      "train_runtime": 3378.4389,
+      "train_samples_per_second": 15.12,
+      "train_steps_per_second": 0.029
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 99,
+  "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": 165619307642880.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}