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: stackexchange_cstheory
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # stackexchange_cstheory
 
-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/stackexchange_cstheory dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.9938
 

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 2.962566844919786,
+    "eval_loss": 0.9938156008720398,
+    "eval_runtime": 25.2096,
+    "eval_samples_per_second": 24.911,
+    "eval_steps_per_second": 0.397,
+    "total_flos": 115368190279680.0,
+    "train_loss": 1.057357843371405,
+    "train_runtime": 4374.2005,
+    "train_samples_per_second": 8.182,
+    "train_steps_per_second": 0.016
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 2.962566844919786,
+    "eval_loss": 0.9938156008720398,
+    "eval_runtime": 25.2096,
+    "eval_samples_per_second": 24.911,
+    "eval_steps_per_second": 0.397
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.962566844919786,
+    "total_flos": 115368190279680.0,
+    "train_loss": 1.057357843371405,
+    "train_runtime": 4374.2005,
+    "train_samples_per_second": 8.182,
+    "train_steps_per_second": 0.016
+}

trainer_state.json

@@ -0,0 +1,108 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.962566844919786,
+  "eval_steps": 500,
+  "global_step": 69,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.42780748663101603,
+      "grad_norm": 3.0180720336296165,
+      "learning_rate": 5e-06,
+      "loss": 1.2052,
+      "step": 10
+    },
+    {
+      "epoch": 0.8556149732620321,
+      "grad_norm": 10.036727628332669,
+      "learning_rate": 5e-06,
+      "loss": 1.0858,
+      "step": 20
+    },
+    {
+      "epoch": 0.983957219251337,
+      "eval_loss": 1.0545072555541992,
+      "eval_runtime": 25.5428,
+      "eval_samples_per_second": 24.586,
+      "eval_steps_per_second": 0.391,
+      "step": 23
+    },
+    {
+      "epoch": 1.2887700534759359,
+      "grad_norm": 1.4497680469615883,
+      "learning_rate": 5e-06,
+      "loss": 1.1308,
+      "step": 30
+    },
+    {
+      "epoch": 1.7165775401069518,
+      "grad_norm": 1.75459704672845,
+      "learning_rate": 5e-06,
+      "loss": 1.0111,
+      "step": 40
+    },
+    {
+      "epoch": 1.9732620320855614,
+      "eval_loss": 1.0155441761016846,
+      "eval_runtime": 25.4843,
+      "eval_samples_per_second": 24.643,
+      "eval_steps_per_second": 0.392,
+      "step": 46
+    },
+    {
+      "epoch": 2.1497326203208558,
+      "grad_norm": 1.0208869779318053,
+      "learning_rate": 5e-06,
+      "loss": 1.0605,
+      "step": 50
+    },
+    {
+      "epoch": 2.5775401069518717,
+      "grad_norm": 1.6907414406638965,
+      "learning_rate": 5e-06,
+      "loss": 0.9514,
+      "step": 60
+    },
+    {
+      "epoch": 2.962566844919786,
+      "eval_loss": 0.9938156008720398,
+      "eval_runtime": 24.6524,
+      "eval_samples_per_second": 25.474,
+      "eval_steps_per_second": 0.406,
+      "step": 69
+    },
+    {
+      "epoch": 2.962566844919786,
+      "step": 69,
+      "total_flos": 115368190279680.0,
+      "train_loss": 1.057357843371405,
+      "train_runtime": 4374.2005,
+      "train_samples_per_second": 8.182,
+      "train_steps_per_second": 0.016
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 69,
+  "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": 115368190279680.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}