End of training

README.md

@@ -4,6 +4,7 @@ license: apache-2.0
 base_model: mistralai/Mistral-7B-v0.1
 tags:
 - llama-factory
+- full
 - generated_from_trainer
 model-index:
 - name: mistral_alpaca_sft_sample_8
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # mistral_alpaca_sft_sample_8
 
-This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on an unknown dataset.
+This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the llamafactory/alpaca_en dataset.
 It achieves the following results on the evaluation set:
 - Loss: 1.0601
 

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 1.06005859375,
+    "eval_runtime": 3.7206,
+    "eval_samples_per_second": 165.834,
+    "eval_steps_per_second": 2.688,
+    "total_flos": 2.572343380583383e+17,
+    "train_loss": 1.2183260710343071,
+    "train_runtime": 428.2271,
+    "train_samples_per_second": 27.366,
+    "train_steps_per_second": 0.054
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 1.06005859375,
+    "eval_runtime": 3.7206,
+    "eval_samples_per_second": 165.834,
+    "eval_steps_per_second": 2.688
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "total_flos": 2.572343380583383e+17,
+    "train_loss": 1.2183260710343071,
+    "train_runtime": 428.2271,
+    "train_samples_per_second": 27.366,
+    "train_steps_per_second": 0.054
+}

trainer_state.json

@@ -0,0 +1,64 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 23,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.43478260869565216,
+      "grad_norm": 9.880785942077637,
+      "learning_rate": 1.4539904997395468e-05,
+      "loss": 1.3665,
+      "step": 10
+    },
+    {
+      "epoch": 0.8695652173913043,
+      "grad_norm": 2.127349615097046,
+      "learning_rate": 1.0899347581163222e-06,
+      "loss": 1.1054,
+      "step": 20
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 1.06005859375,
+      "eval_runtime": 3.648,
+      "eval_samples_per_second": 169.134,
+      "eval_steps_per_second": 2.741,
+      "step": 23
+    },
+    {
+      "epoch": 1.0,
+      "step": 23,
+      "total_flos": 2.572343380583383e+17,
+      "train_loss": 1.2183260710343071,
+      "train_runtime": 428.2271,
+      "train_samples_per_second": 27.366,
+      "train_steps_per_second": 0.054
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 23,
+  "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": 2.572343380583383e+17,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}