End of training

README.md

@@ -2,6 +2,7 @@
 library_name: peft
 tags:
 - llama-factory
+- lora
 - generated_from_trainer
 base_model: mistralai/Mistral-7B-v0.3
 model-index:
@@ -14,9 +15,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # Mistral_AAID_mixed_train_final
 
-This model is a fine-tuned version of [mistralai/Mistral-7B-v0.3](https://huggingface.co/mistralai/Mistral-7B-v0.3) on an unknown dataset.
+This model is a fine-tuned version of [mistralai/Mistral-7B-v0.3](https://huggingface.co/mistralai/Mistral-7B-v0.3) on the AAID_mixed dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.5532
+- Loss: 0.5356
 
 ## Model description
 

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 0.06562756357670221,
+    "eval_loss": 0.5355889797210693,
+    "eval_runtime": 2175.8335,
+    "eval_samples_per_second": 21.656,
+    "eval_steps_per_second": 0.677,
+    "total_flos": 1.143902298880082e+17,
+    "train_loss": 0.43926427761713666,
+    "train_runtime": 15865.2354,
+    "train_samples_per_second": 44.255,
+    "train_steps_per_second": 0.173
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 0.06562756357670221,
+    "eval_loss": 0.5355889797210693,
+    "eval_runtime": 2175.8335,
+    "eval_samples_per_second": 21.656,
+    "eval_steps_per_second": 0.677
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.06562756357670221,
+    "total_flos": 1.143902298880082e+17,
+    "train_loss": 0.43926427761713666,
+    "train_runtime": 15865.2354,
+    "train_samples_per_second": 44.255,
+    "train_steps_per_second": 0.173
+}

trainer_state.json

@@ -0,0 +1,141 @@
+{
+  "best_metric": 0.5355889797210693,
+  "best_model_checkpoint": "saves/Mistral-7B/lora/train_1/checkpoint-10",
+  "epoch": 0.06562756357670221,
+  "eval_steps": 10,
+  "global_step": 60,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.010937927262783703,
+      "grad_norm": 0.9827508330345154,
+      "learning_rate": 0.00029999015487222375,
+      "loss": 0.8548,
+      "step": 10
+    },
+    {
+      "epoch": 0.010937927262783703,
+      "eval_loss": 0.5355889797210693,
+      "eval_runtime": 2175.855,
+      "eval_samples_per_second": 21.656,
+      "eval_steps_per_second": 0.677,
+      "step": 10
+    },
+    {
+      "epoch": 0.021875854525567406,
+      "grad_norm": 0.6526839733123779,
+      "learning_rate": 0.00029996062078124905,
+      "loss": 0.4005,
+      "step": 20
+    },
+    {
+      "epoch": 0.021875854525567406,
+      "eval_loss": 0.579488217830658,
+      "eval_runtime": 2175.2344,
+      "eval_samples_per_second": 21.662,
+      "eval_steps_per_second": 0.677,
+      "step": 20
+    },
+    {
+      "epoch": 0.03281378178835111,
+      "grad_norm": 0.5257601141929626,
+      "learning_rate": 0.0002999114016039678,
+      "loss": 0.3521,
+      "step": 30
+    },
+    {
+      "epoch": 0.03281378178835111,
+      "eval_loss": 0.5633693337440491,
+      "eval_runtime": 2176.4963,
+      "eval_samples_per_second": 21.649,
+      "eval_steps_per_second": 0.677,
+      "step": 30
+    },
+    {
+      "epoch": 0.04375170905113481,
+      "grad_norm": 0.553675651550293,
+      "learning_rate": 0.00029984250380130117,
+      "loss": 0.3565,
+      "step": 40
+    },
+    {
+      "epoch": 0.04375170905113481,
+      "eval_loss": 0.5676367878913879,
+      "eval_runtime": 2173.2369,
+      "eval_samples_per_second": 21.682,
+      "eval_steps_per_second": 0.678,
+      "step": 40
+    },
+    {
+      "epoch": 0.05468963631391851,
+      "grad_norm": 0.3802327811717987,
+      "learning_rate": 0.0002997539364173515,
+      "loss": 0.3418,
+      "step": 50
+    },
+    {
+      "epoch": 0.05468963631391851,
+      "eval_loss": 0.5385285019874573,
+      "eval_runtime": 2174.1731,
+      "eval_samples_per_second": 21.673,
+      "eval_steps_per_second": 0.677,
+      "step": 50
+    },
+    {
+      "epoch": 0.06562756357670221,
+      "grad_norm": 0.5235214829444885,
+      "learning_rate": 0.00029964571107821494,
+      "loss": 0.3298,
+      "step": 60
+    },
+    {
+      "epoch": 0.06562756357670221,
+      "eval_loss": 0.5531513094902039,
+      "eval_runtime": 2176.9278,
+      "eval_samples_per_second": 21.645,
+      "eval_steps_per_second": 0.677,
+      "step": 60
+    },
+    {
+      "epoch": 0.06562756357670221,
+      "step": 60,
+      "total_flos": 1.143902298880082e+17,
+      "train_loss": 0.43926427761713666,
+      "train_runtime": 15865.2354,
+      "train_samples_per_second": 44.255,
+      "train_steps_per_second": 0.173
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 2742,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 10,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 5,
+        "early_stopping_threshold": 0.0
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 0
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.143902298880082e+17,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}