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: evol_tt_5s
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # evol_tt_5s
 
-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/evol_tt_5s dataset.
 It achieves the following results on the evaluation set:
 - Loss: 1.0264
 

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 2.9871244635193133,
+    "eval_loss": 1.0264430046081543,
+    "eval_runtime": 32.0642,
+    "eval_samples_per_second": 24.451,
+    "eval_steps_per_second": 0.405,
+    "total_flos": 145518860697600.0,
+    "train_loss": 1.0589926599086017,
+    "train_runtime": 5388.1812,
+    "train_samples_per_second": 8.294,
+    "train_steps_per_second": 0.016
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 2.9871244635193133,
+    "eval_loss": 1.0264430046081543,
+    "eval_runtime": 32.0642,
+    "eval_samples_per_second": 24.451,
+    "eval_steps_per_second": 0.405
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.9871244635193133,
+    "total_flos": 145518860697600.0,
+    "train_loss": 1.0589926599086017,
+    "train_runtime": 5388.1812,
+    "train_samples_per_second": 8.294,
+    "train_steps_per_second": 0.016
+}

trainer_state.json

@@ -0,0 +1,122 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.9871244635193133,
+  "eval_steps": 500,
+  "global_step": 87,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.34334763948497854,
+      "grad_norm": 3.636873335855888,
+      "learning_rate": 5e-06,
+      "loss": 1.225,
+      "step": 10
+    },
+    {
+      "epoch": 0.6866952789699571,
+      "grad_norm": 1.8290279937259637,
+      "learning_rate": 5e-06,
+      "loss": 1.1183,
+      "step": 20
+    },
+    {
+      "epoch": 0.9957081545064378,
+      "eval_loss": 1.0753060579299927,
+      "eval_runtime": 32.6879,
+      "eval_samples_per_second": 23.984,
+      "eval_steps_per_second": 0.398,
+      "step": 29
+    },
+    {
+      "epoch": 1.0300429184549356,
+      "grad_norm": 4.264743501659714,
+      "learning_rate": 5e-06,
+      "loss": 1.1737,
+      "step": 30
+    },
+    {
+      "epoch": 1.3733905579399142,
+      "grad_norm": 1.2670359820273283,
+      "learning_rate": 5e-06,
+      "loss": 1.0339,
+      "step": 40
+    },
+    {
+      "epoch": 1.7167381974248928,
+      "grad_norm": 1.0741208963335582,
+      "learning_rate": 5e-06,
+      "loss": 1.0128,
+      "step": 50
+    },
+    {
+      "epoch": 1.9914163090128756,
+      "eval_loss": 1.036221981048584,
+      "eval_runtime": 32.6061,
+      "eval_samples_per_second": 24.045,
+      "eval_steps_per_second": 0.399,
+      "step": 58
+    },
+    {
+      "epoch": 2.060085836909871,
+      "grad_norm": 1.3252943883596882,
+      "learning_rate": 5e-06,
+      "loss": 1.0832,
+      "step": 60
+    },
+    {
+      "epoch": 2.40343347639485,
+      "grad_norm": 1.624384902795632,
+      "learning_rate": 5e-06,
+      "loss": 0.9573,
+      "step": 70
+    },
+    {
+      "epoch": 2.7467811158798283,
+      "grad_norm": 1.8266302286280618,
+      "learning_rate": 5e-06,
+      "loss": 0.9458,
+      "step": 80
+    },
+    {
+      "epoch": 2.9871244635193133,
+      "eval_loss": 1.0264430046081543,
+      "eval_runtime": 31.5871,
+      "eval_samples_per_second": 24.82,
+      "eval_steps_per_second": 0.412,
+      "step": 87
+    },
+    {
+      "epoch": 2.9871244635193133,
+      "step": 87,
+      "total_flos": 145518860697600.0,
+      "train_loss": 1.0589926599086017,
+      "train_runtime": 5388.1812,
+      "train_samples_per_second": 8.294,
+      "train_steps_per_second": 0.016
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 87,
+  "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": 145518860697600.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}