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-stackexchange_scifi
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # llama3-1_8b_mlfoundations-dev-stackexchange_scifi
 
-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_scifi dataset.
 It achieves the following results on the evaluation set:
 - Loss: 1.0987
 

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 2.991097922848665,
+    "eval_loss": 1.0986876487731934,
+    "eval_runtime": 65.2059,
+    "eval_samples_per_second": 8.696,
+    "eval_steps_per_second": 0.276,
+    "total_flos": 105422656634880.0,
+    "train_loss": 1.1566594176822238,
+    "train_runtime": 10280.3361,
+    "train_samples_per_second": 3.142,
+    "train_steps_per_second": 0.006
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 2.991097922848665,
+    "eval_loss": 1.0986876487731934,
+    "eval_runtime": 65.2059,
+    "eval_samples_per_second": 8.696,
+    "eval_steps_per_second": 0.276
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.991097922848665,
+    "total_flos": 105422656634880.0,
+    "train_loss": 1.1566594176822238,
+    "train_runtime": 10280.3361,
+    "train_samples_per_second": 3.142,
+    "train_steps_per_second": 0.006
+}

trainer_state.json

@@ -0,0 +1,108 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.991097922848665,
+  "eval_steps": 500,
+  "global_step": 63,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.47477744807121663,
+      "grad_norm": 7.287866142815707,
+      "learning_rate": 5e-06,
+      "loss": 1.3702,
+      "step": 10
+    },
+    {
+      "epoch": 0.9495548961424333,
+      "grad_norm": 11.95220386398438,
+      "learning_rate": 5e-06,
+      "loss": 1.2286,
+      "step": 20
+    },
+    {
+      "epoch": 0.9970326409495549,
+      "eval_loss": 1.193329095840454,
+      "eval_runtime": 65.8348,
+      "eval_samples_per_second": 8.612,
+      "eval_steps_per_second": 0.273,
+      "step": 21
+    },
+    {
+      "epoch": 1.4243323442136497,
+      "grad_norm": 2.603188301936332,
+      "learning_rate": 5e-06,
+      "loss": 1.162,
+      "step": 30
+    },
+    {
+      "epoch": 1.8991097922848663,
+      "grad_norm": 1.480853911439061,
+      "learning_rate": 5e-06,
+      "loss": 1.122,
+      "step": 40
+    },
+    {
+      "epoch": 1.9940652818991098,
+      "eval_loss": 1.1249243021011353,
+      "eval_runtime": 65.7564,
+      "eval_samples_per_second": 8.623,
+      "eval_steps_per_second": 0.274,
+      "step": 42
+    },
+    {
+      "epoch": 2.373887240356083,
+      "grad_norm": 1.09348710471121,
+      "learning_rate": 5e-06,
+      "loss": 1.0642,
+      "step": 50
+    },
+    {
+      "epoch": 2.8486646884272995,
+      "grad_norm": 1.193278031805213,
+      "learning_rate": 5e-06,
+      "loss": 1.0335,
+      "step": 60
+    },
+    {
+      "epoch": 2.991097922848665,
+      "eval_loss": 1.0986876487731934,
+      "eval_runtime": 65.1855,
+      "eval_samples_per_second": 8.698,
+      "eval_steps_per_second": 0.276,
+      "step": 63
+    },
+    {
+      "epoch": 2.991097922848665,
+      "step": 63,
+      "total_flos": 105422656634880.0,
+      "train_loss": 1.1566594176822238,
+      "train_runtime": 10280.3361,
+      "train_samples_per_second": 3.142,
+      "train_steps_per_second": 0.006
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 63,
+  "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": 105422656634880.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}