End of training

README.md

@@ -4,6 +4,7 @@ library_name: peft
 license: apache-2.0
 tags:
 - llama-factory
+- lora
 - generated_from_trainer
 model-index:
 - name: Mistral-Nemo-12B-Instruct-SFT
@@ -15,7 +16,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # Mistral-Nemo-12B-Instruct-SFT
 
-This model is a fine-tuned version of [mistralai/Mistral-Nemo-Instruct-2407](https://huggingface.co/mistralai/Mistral-Nemo-Instruct-2407) on an unknown dataset.
+This model is a fine-tuned version of [mistralai/Mistral-Nemo-Instruct-2407](https://huggingface.co/mistralai/Mistral-Nemo-Instruct-2407) on the bct_non_cot_sft_1000 dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1009
 
 ## Model description
 

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 2.986666666666667,
+    "eval_loss": 0.10085082799196243,
+    "eval_runtime": 4.4417,
+    "eval_samples_per_second": 22.514,
+    "eval_steps_per_second": 11.257,
+    "total_flos": 2.198897954832384e+16,
+    "train_loss": 0.4042978783448537,
+    "train_runtime": 473.7973,
+    "train_samples_per_second": 5.699,
+    "train_steps_per_second": 0.355
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 2.986666666666667,
+    "eval_loss": 0.10085082799196243,
+    "eval_runtime": 4.4417,
+    "eval_samples_per_second": 22.514,
+    "eval_steps_per_second": 11.257
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.986666666666667,
+    "total_flos": 2.198897954832384e+16,
+    "train_loss": 0.4042978783448537,
+    "train_runtime": 473.7973,
+    "train_samples_per_second": 5.699,
+    "train_steps_per_second": 0.355
+}

trainer_state.json

@@ -0,0 +1,154 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.986666666666667,
+  "eval_steps": 500,
+  "global_step": 168,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.17777777777777778,
+      "grad_norm": 3.2556965351104736,
+      "learning_rate": 2.647058823529412e-06,
+      "loss": 1.2612,
+      "step": 10
+    },
+    {
+      "epoch": 0.35555555555555557,
+      "grad_norm": 4.027493000030518,
+      "learning_rate": 4.997836020254328e-06,
+      "loss": 1.2578,
+      "step": 20
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "grad_norm": 3.119051933288574,
+      "learning_rate": 4.922489359292928e-06,
+      "loss": 1.0594,
+      "step": 30
+    },
+    {
+      "epoch": 0.7111111111111111,
+      "grad_norm": 2.8886709213256836,
+      "learning_rate": 4.7426609101991605e-06,
+      "loss": 0.7524,
+      "step": 40
+    },
+    {
+      "epoch": 0.8888888888888888,
+      "grad_norm": 2.727381467819214,
+      "learning_rate": 4.466106660773884e-06,
+      "loss": 0.5438,
+      "step": 50
+    },
+    {
+      "epoch": 1.0666666666666667,
+      "grad_norm": 1.9826691150665283,
+      "learning_rate": 4.104754375481665e-06,
+      "loss": 0.481,
+      "step": 60
+    },
+    {
+      "epoch": 1.2444444444444445,
+      "grad_norm": 2.280515670776367,
+      "learning_rate": 3.674189151845515e-06,
+      "loss": 0.2657,
+      "step": 70
+    },
+    {
+      "epoch": 1.4222222222222223,
+      "grad_norm": 1.451013445854187,
+      "learning_rate": 3.1929812363354766e-06,
+      "loss": 0.1834,
+      "step": 80
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 1.2507127523422241,
+      "learning_rate": 2.68188509100236e-06,
+      "loss": 0.164,
+      "step": 90
+    },
+    {
+      "epoch": 1.7777777777777777,
+      "grad_norm": 0.7387431263923645,
+      "learning_rate": 2.1629442550539283e-06,
+      "loss": 0.1039,
+      "step": 100
+    },
+    {
+      "epoch": 1.9555555555555557,
+      "grad_norm": 0.8114812970161438,
+      "learning_rate": 1.6585406086279847e-06,
+      "loss": 0.1299,
+      "step": 110
+    },
+    {
+      "epoch": 2.1333333333333333,
+      "grad_norm": 1.0944963693618774,
+      "learning_rate": 1.1904290439459974e-06,
+      "loss": 0.0871,
+      "step": 120
+    },
+    {
+      "epoch": 2.311111111111111,
+      "grad_norm": 0.9579205513000488,
+      "learning_rate": 7.787991784095e-07,
+      "loss": 0.1068,
+      "step": 130
+    },
+    {
+      "epoch": 2.488888888888889,
+      "grad_norm": 1.7271074056625366,
+      "learning_rate": 4.414045778845144e-07,
+      "loss": 0.1238,
+      "step": 140
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "grad_norm": 1.8871749639511108,
+      "learning_rate": 1.927970467097573e-07,
+      "loss": 0.1024,
+      "step": 150
+    },
+    {
+      "epoch": 2.8444444444444446,
+      "grad_norm": 1.1750086545944214,
+      "learning_rate": 4.369900944435734e-08,
+      "loss": 0.0923,
+      "step": 160
+    },
+    {
+      "epoch": 2.986666666666667,
+      "step": 168,
+      "total_flos": 2.198897954832384e+16,
+      "train_loss": 0.4042978783448537,
+      "train_runtime": 473.7973,
+      "train_samples_per_second": 5.699,
+      "train_steps_per_second": 0.355
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 168,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "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": 2.198897954832384e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}