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_construction
@@ -15,9 +16,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # llama_3_70b_lora_sft_construction
 
-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_construction_train_data datasets.
 It achieves the following results on the evaluation set:
-- Loss: 0.3483
+- Loss: 0.3475
 
 ## Model description
 

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 0.9947460595446584,
+    "eval_loss": 0.34747257828712463,
+    "eval_runtime": 38.5498,
+    "eval_samples_per_second": 4.851,
+    "eval_steps_per_second": 0.623,
+    "total_flos": 8671839626723328.0,
+    "train_loss": 0.3312246486754485,
+    "train_runtime": 6300.0732,
+    "train_samples_per_second": 1.45,
+    "train_steps_per_second": 0.011
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 0.9947460595446584,
+    "eval_loss": 0.34747257828712463,
+    "eval_runtime": 38.5498,
+    "eval_samples_per_second": 4.851,
+    "eval_steps_per_second": 0.623
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.9947460595446584,
+    "total_flos": 8671839626723328.0,
+    "train_loss": 0.3312246486754485,
+    "train_runtime": 6300.0732,
+    "train_samples_per_second": 1.45,
+    "train_steps_per_second": 0.011
+}

trainer_state.json

@@ -0,0 +1,107 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9947460595446584,
+  "eval_steps": 30,
+  "global_step": 71,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.14010507880910683,
+      "grad_norm": 0.45420220075243706,
+      "learning_rate": 9.975153876827008e-05,
+      "loss": 0.5917,
+      "step": 10
+    },
+    {
+      "epoch": 0.28021015761821366,
+      "grad_norm": 0.4281694659811335,
+      "learning_rate": 9.131193871579975e-05,
+      "loss": 0.3715,
+      "step": 20
+    },
+    {
+      "epoch": 0.4203152364273205,
+      "grad_norm": 0.2752285164412833,
+      "learning_rate": 7.281053286765815e-05,
+      "loss": 0.2844,
+      "step": 30
+    },
+    {
+      "epoch": 0.4203152364273205,
+      "eval_loss": 0.3744376003742218,
+      "eval_runtime": 38.8917,
+      "eval_samples_per_second": 4.808,
+      "eval_steps_per_second": 0.617,
+      "step": 30
+    },
+    {
+      "epoch": 0.5604203152364273,
+      "grad_norm": 0.2616196043777537,
+      "learning_rate": 4.875346541309637e-05,
+      "loss": 0.2776,
+      "step": 40
+    },
+    {
+      "epoch": 0.7005253940455342,
+      "grad_norm": 0.2979118016206158,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.2932,
+      "step": 50
+    },
+    {
+      "epoch": 0.840630472854641,
+      "grad_norm": 0.2227457988487204,
+      "learning_rate": 7.33545591839222e-06,
+      "loss": 0.2646,
+      "step": 60
+    },
+    {
+      "epoch": 0.840630472854641,
+      "eval_loss": 0.3483392000198364,
+      "eval_runtime": 38.9637,
+      "eval_samples_per_second": 4.799,
+      "eval_steps_per_second": 0.616,
+      "step": 60
+    },
+    {
+      "epoch": 0.9807355516637478,
+      "grad_norm": 0.39490090028744906,
+      "learning_rate": 6.215393905388278e-08,
+      "loss": 0.2557,
+      "step": 70
+    },
+    {
+      "epoch": 0.9947460595446584,
+      "step": 71,
+      "total_flos": 8671839626723328.0,
+      "train_loss": 0.3312246486754485,
+      "train_runtime": 6300.0732,
+      "train_samples_per_second": 1.45,
+      "train_steps_per_second": 0.011
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 71,
+  "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": 8671839626723328.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}