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_bitcoin
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # stackexchange_bitcoin
 
-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_bitcoin dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.9112
 

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 2.9674796747967482,
+    "eval_loss": 0.91116863489151,
+    "eval_runtime": 31.7913,
+    "eval_samples_per_second": 26.013,
+    "eval_steps_per_second": 0.409,
+    "total_flos": 150543972433920.0,
+    "train_loss": 0.9690744717915852,
+    "train_runtime": 5576.6869,
+    "train_samples_per_second": 8.449,
+    "train_steps_per_second": 0.016
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 2.9674796747967482,
+    "eval_loss": 0.91116863489151,
+    "eval_runtime": 31.7913,
+    "eval_samples_per_second": 26.013,
+    "eval_steps_per_second": 0.409
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.9674796747967482,
+    "total_flos": 150543972433920.0,
+    "train_loss": 0.9690744717915852,
+    "train_runtime": 5576.6869,
+    "train_samples_per_second": 8.449,
+    "train_steps_per_second": 0.016
+}

trainer_state.json

@@ -0,0 +1,129 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.9674796747967482,
+  "eval_steps": 500,
+  "global_step": 90,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.3252032520325203,
+      "grad_norm": 9.994125425810577,
+      "learning_rate": 5e-06,
+      "loss": 1.1514,
+      "step": 10
+    },
+    {
+      "epoch": 0.6504065040650406,
+      "grad_norm": 2.2370187327756943,
+      "learning_rate": 5e-06,
+      "loss": 1.0455,
+      "step": 20
+    },
+    {
+      "epoch": 0.975609756097561,
+      "grad_norm": 1.9302488029482865,
+      "learning_rate": 5e-06,
+      "loss": 0.9924,
+      "step": 30
+    },
+    {
+      "epoch": 0.975609756097561,
+      "eval_loss": 0.9794577360153198,
+      "eval_runtime": 32.7605,
+      "eval_samples_per_second": 25.244,
+      "eval_steps_per_second": 0.397,
+      "step": 30
+    },
+    {
+      "epoch": 1.321138211382114,
+      "grad_norm": 1.6386206765417015,
+      "learning_rate": 5e-06,
+      "loss": 1.0272,
+      "step": 40
+    },
+    {
+      "epoch": 1.6463414634146343,
+      "grad_norm": 1.7008818307219944,
+      "learning_rate": 5e-06,
+      "loss": 0.9229,
+      "step": 50
+    },
+    {
+      "epoch": 1.9715447154471546,
+      "grad_norm": 1.4696210364640039,
+      "learning_rate": 5e-06,
+      "loss": 0.9124,
+      "step": 60
+    },
+    {
+      "epoch": 1.9715447154471546,
+      "eval_loss": 0.9315309524536133,
+      "eval_runtime": 32.8011,
+      "eval_samples_per_second": 25.213,
+      "eval_steps_per_second": 0.396,
+      "step": 60
+    },
+    {
+      "epoch": 2.317073170731707,
+      "grad_norm": 1.3499947575147127,
+      "learning_rate": 5e-06,
+      "loss": 0.9527,
+      "step": 70
+    },
+    {
+      "epoch": 2.642276422764228,
+      "grad_norm": 1.2132524643805997,
+      "learning_rate": 5e-06,
+      "loss": 0.859,
+      "step": 80
+    },
+    {
+      "epoch": 2.9674796747967482,
+      "grad_norm": 0.9264733186289283,
+      "learning_rate": 5e-06,
+      "loss": 0.8582,
+      "step": 90
+    },
+    {
+      "epoch": 2.9674796747967482,
+      "eval_loss": 0.91116863489151,
+      "eval_runtime": 31.463,
+      "eval_samples_per_second": 26.285,
+      "eval_steps_per_second": 0.413,
+      "step": 90
+    },
+    {
+      "epoch": 2.9674796747967482,
+      "step": 90,
+      "total_flos": 150543972433920.0,
+      "train_loss": 0.9690744717915852,
+      "train_runtime": 5576.6869,
+      "train_samples_per_second": 8.449,
+      "train_steps_per_second": 0.016
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 90,
+  "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": 150543972433920.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}