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_7
@@ -15,7 +16,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # mistral_alpaca_sft_sample_7
 
-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: 1.6995
 
 ## Model description
 

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 0.13043478260869565,
+    "eval_loss": 1.6994578838348389,
+    "eval_runtime": 3.777,
+    "eval_samples_per_second": 163.355,
+    "eval_steps_per_second": 2.648,
+    "total_flos": 3.355230384370483e+16,
+    "train_loss": 1.413620154062907,
+    "train_runtime": 210.9071,
+    "train_samples_per_second": 7.283,
+    "train_steps_per_second": 0.014
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 0.13043478260869565,
+    "eval_loss": 1.6994578838348389,
+    "eval_runtime": 3.777,
+    "eval_samples_per_second": 163.355,
+    "eval_steps_per_second": 2.648
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.13043478260869565,
+    "total_flos": 3.355230384370483e+16,
+    "train_loss": 1.413620154062907,
+    "train_runtime": 210.9071,
+    "train_samples_per_second": 7.283,
+    "train_steps_per_second": 0.014
+}

trainer_state.json

@@ -0,0 +1,50 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.13043478260869565,
+  "eval_steps": 500,
+  "global_step": 3,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.13043478260869565,
+      "eval_loss": 1.6994578838348389,
+      "eval_runtime": 3.6897,
+      "eval_samples_per_second": 167.221,
+      "eval_steps_per_second": 2.71,
+      "step": 3
+    },
+    {
+      "epoch": 0.13043478260869565,
+      "step": 3,
+      "total_flos": 3.355230384370483e+16,
+      "train_loss": 1.413620154062907,
+      "train_runtime": 210.9071,
+      "train_samples_per_second": 7.283,
+      "train_steps_per_second": 0.014
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 3,
+  "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": 3.355230384370483e+16,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}