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: llama3-1_8b_mlfoundations-dev-stackoverflow_25000tasks__75p
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # llama3-1_8b_mlfoundations-dev-stackoverflow_25000tasks__75p
 
-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/stackoverflow_25000tasks_.75p dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.7360
 

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 2.9855072463768115,
+    "eval_loss": 0.7359980344772339,
+    "eval_runtime": 110.7132,
+    "eval_samples_per_second": 8.4,
+    "eval_steps_per_second": 0.271,
+    "total_flos": 170644419379200.0,
+    "train_loss": 0.20854202555675133,
+    "train_runtime": 5455.4573,
+    "train_samples_per_second": 9.71,
+    "train_steps_per_second": 0.019
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 2.9855072463768115,
+    "eval_loss": 0.7359980344772339,
+    "eval_runtime": 110.7132,
+    "eval_samples_per_second": 8.4,
+    "eval_steps_per_second": 0.271
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.9855072463768115,
+    "total_flos": 170644419379200.0,
+    "train_loss": 0.20854202555675133,
+    "train_runtime": 5455.4573,
+    "train_samples_per_second": 9.71,
+    "train_steps_per_second": 0.019
+}

trainer_state.json

@@ -0,0 +1,136 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.9855072463768115,
+  "eval_steps": 500,
+  "global_step": 102,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.2898550724637681,
+      "grad_norm": 2.5293532067967024,
+      "learning_rate": 5e-06,
+      "loss": 0.927,
+      "step": 10
+    },
+    {
+      "epoch": 0.5797101449275363,
+      "grad_norm": 2.8349151948529334,
+      "learning_rate": 5e-06,
+      "loss": 0.8309,
+      "step": 20
+    },
+    {
+      "epoch": 0.8695652173913043,
+      "grad_norm": 3.4862733771047196,
+      "learning_rate": 5e-06,
+      "loss": 0.7986,
+      "step": 30
+    },
+    {
+      "epoch": 0.9855072463768116,
+      "eval_loss": 0.7891173958778381,
+      "eval_runtime": 117.5715,
+      "eval_samples_per_second": 7.91,
+      "eval_steps_per_second": 0.255,
+      "step": 34
+    },
+    {
+      "epoch": 1.1594202898550725,
+      "grad_norm": 1.6159916351048333,
+      "learning_rate": 5e-06,
+      "loss": 0.7623,
+      "step": 40
+    },
+    {
+      "epoch": 1.4492753623188406,
+      "grad_norm": 0.7186480347182584,
+      "learning_rate": 5e-06,
+      "loss": 0.7293,
+      "step": 50
+    },
+    {
+      "epoch": 1.7391304347826086,
+      "grad_norm": 1.0901658854060863,
+      "learning_rate": 5e-06,
+      "loss": 0.7198,
+      "step": 60
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.7413280606269836,
+      "eval_runtime": 109.5576,
+      "eval_samples_per_second": 8.489,
+      "eval_steps_per_second": 0.274,
+      "step": 69
+    },
+    {
+      "epoch": 2.0579710144927534,
+      "grad_norm": 1.4000062406023526,
+      "learning_rate": 5e-06,
+      "loss": 0.6561,
+      "step": 70
+    },
+    {
+      "epoch": 2.3478260869565215,
+      "grad_norm": 0.6440591722727258,
+      "learning_rate": 5e-06,
+      "loss": 0.6471,
+      "step": 80
+    },
+    {
+      "epoch": 2.63768115942029,
+      "grad_norm": 1.01198086901828,
+      "learning_rate": 5e-06,
+      "loss": 0.6426,
+      "step": 90
+    },
+    {
+      "epoch": 2.927536231884058,
+      "grad_norm": 0.8519839335212693,
+      "learning_rate": 5e-06,
+      "loss": 0.64,
+      "step": 100
+    },
+    {
+      "epoch": 2.9855072463768115,
+      "eval_loss": 0.7359980344772339,
+      "eval_runtime": 115.8139,
+      "eval_samples_per_second": 8.03,
+      "eval_steps_per_second": 0.259,
+      "step": 102
+    },
+    {
+      "epoch": 2.9855072463768115,
+      "step": 102,
+      "total_flos": 170644419379200.0,
+      "train_loss": 0.20854202555675133,
+      "train_runtime": 5455.4573,
+      "train_samples_per_second": 9.71,
+      "train_steps_per_second": 0.019
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 102,
+  "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": 170644419379200.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}