End of training

README.md

@@ -4,6 +4,7 @@ license: llama3
 base_model: meta-llama/Meta-Llama-3-70B-Instruct
 tags:
 - llama-factory
+- lora
 - generated_from_trainer
 model-index:
 - name: llama_3_70b_lora_sft_crafting
@@ -15,7 +16,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # llama_3_70b_lora_sft_crafting
 
-This model is a fine-tuned version of [meta-llama/Meta-Llama-3-70B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-70B-Instruct) on the None dataset.
+This model is a fine-tuned version of [meta-llama/Meta-Llama-3-70B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-70B-Instruct) on the identity and the filtered_crafting_train_data datasets.
+It achieves the following results on the evaluation set:
+- Loss: 0.3451
 
 ## Model description
 

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 0.34508389234542847,
+    "eval_runtime": 15.1966,
+    "eval_samples_per_second": 4.869,
+    "eval_steps_per_second": 0.658,
+    "total_flos": 2776730917928960.0,
+    "train_loss": 0.6443910087857928,
+    "train_runtime": 2329.4992,
+    "train_samples_per_second": 1.538,
+    "train_steps_per_second": 0.012
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 0.34508389234542847,
+    "eval_runtime": 15.1966,
+    "eval_samples_per_second": 4.869,
+    "eval_steps_per_second": 0.658
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "total_flos": 2776730917928960.0,
+    "train_loss": 0.6443910087857928,
+    "train_runtime": 2329.4992,
+    "train_samples_per_second": 1.538,
+    "train_steps_per_second": 0.012
+}

trainer_state.json

@@ -0,0 +1,56 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 30,
+  "global_step": 28,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.35714285714285715,
+      "grad_norm": 0.4569597298761558,
+      "learning_rate": 8.18711994874345e-05,
+      "loss": 0.9004,
+      "step": 10
+    },
+    {
+      "epoch": 0.7142857142857143,
+      "grad_norm": 0.4078513107441401,
+      "learning_rate": 2.3208660251050158e-05,
+      "loss": 0.548,
+      "step": 20
+    },
+    {
+      "epoch": 1.0,
+      "step": 28,
+      "total_flos": 2776730917928960.0,
+      "train_loss": 0.6443910087857928,
+      "train_runtime": 2329.4992,
+      "train_samples_per_second": 1.538,
+      "train_steps_per_second": 0.012
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 28,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "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": 2776730917928960.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}