End of training

README.md

@@ -14,9 +14,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # TAPT_data-V2_Bioformer-16L_LR-0.0001
 
-This model is a fine-tuned version of [bioformers/bioformer-16L](https://huggingface.co/bioformers/bioformer-16L) on an unknown dataset.
+This model is a fine-tuned version of [bioformers/bioformer-16L](https://huggingface.co/bioformers/bioformer-16L) on the Mardiyyah/TAPT_data_V2_split dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.2897
+- Loss: 2.3000
 
 ## Model description
 

all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 10.0,
+    "eval_loss": 2.299952745437622,
+    "eval_runtime": 2.1048,
+    "eval_samples": 1945,
+    "eval_samples_per_second": 924.096,
+    "eval_steps_per_second": 57.964,
+    "perplexity": 9.973711140323708,
+    "total_flos": 1536221652235776.0,
+    "train_loss": 1.5534028151939656,
+    "train_runtime": 363.1065,
+    "train_samples": 9733,
+    "train_samples_per_second": 268.048,
+    "train_steps_per_second": 16.772
+}

eval_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 10.0,
+    "eval_loss": 2.299952745437622,
+    "eval_runtime": 2.1048,
+    "eval_samples": 1945,
+    "eval_samples_per_second": 924.096,
+    "eval_steps_per_second": 57.964,
+    "perplexity": 9.973711140323708,
+    "total_flos": 1536221652235776.0,
+    "train_loss": 1.5534028151939656,
+    "train_runtime": 363.1065,
+    "train_samples": 9733,
+    "train_samples_per_second": 268.048,
+    "train_steps_per_second": 16.772
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 10.0,
+    "total_flos": 1536221652235776.0,
+    "train_loss": 1.5534028151939656,
+    "train_runtime": 363.1065,
+    "train_samples": 9733,
+    "train_samples_per_second": 268.048,
+    "train_steps_per_second": 16.772
+}

trainer_state.json

@@ -0,0 +1,192 @@
+{
+  "best_metric": 2.2633635997772217,
+  "best_model_checkpoint": "./TAPT_data-V2_Bioformer-16L_LR-0.0001/checkpoint-5481",
+  "epoch": 10.0,
+  "eval_steps": 500,
+  "global_step": 6090,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 22.574710845947266,
+      "learning_rate": 9.575471698113208e-05,
+      "loss": 2.1948,
+      "step": 609
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 2.278985023498535,
+      "eval_runtime": 2.0974,
+      "eval_samples_per_second": 927.339,
+      "eval_steps_per_second": 58.167,
+      "step": 609
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 21.863845825195312,
+      "learning_rate": 8.511530398322851e-05,
+      "loss": 1.9627,
+      "step": 1218
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 2.301274299621582,
+      "eval_runtime": 2.1066,
+      "eval_samples_per_second": 923.304,
+      "eval_steps_per_second": 57.914,
+      "step": 1218
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 31.829483032226562,
+      "learning_rate": 7.447589098532494e-05,
+      "loss": 1.7865,
+      "step": 1827
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 2.3832926750183105,
+      "eval_runtime": 2.1089,
+      "eval_samples_per_second": 922.269,
+      "eval_steps_per_second": 57.849,
+      "step": 1827
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 27.37325668334961,
+      "learning_rate": 6.383647798742139e-05,
+      "loss": 1.6375,
+      "step": 2436
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 2.314645528793335,
+      "eval_runtime": 2.1064,
+      "eval_samples_per_second": 923.362,
+      "eval_steps_per_second": 57.918,
+      "step": 2436
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 27.514528274536133,
+      "learning_rate": 5.319706498951782e-05,
+      "loss": 1.5212,
+      "step": 3045
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 2.3126285076141357,
+      "eval_runtime": 2.1144,
+      "eval_samples_per_second": 919.883,
+      "eval_steps_per_second": 57.7,
+      "step": 3045
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 16.764179229736328,
+      "learning_rate": 4.2557651991614255e-05,
+      "loss": 1.4298,
+      "step": 3654
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 2.300107002258301,
+      "eval_runtime": 2.1035,
+      "eval_samples_per_second": 924.65,
+      "eval_steps_per_second": 57.999,
+      "step": 3654
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 18.094470977783203,
+      "learning_rate": 3.1918238993710694e-05,
+      "loss": 1.361,
+      "step": 4263
+    },
+    {
+      "epoch": 7.0,
+      "eval_loss": 2.3267035484313965,
+      "eval_runtime": 2.0949,
+      "eval_samples_per_second": 928.437,
+      "eval_steps_per_second": 58.236,
+      "step": 4263
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 47.55793762207031,
+      "learning_rate": 2.1278825995807127e-05,
+      "loss": 1.2688,
+      "step": 4872
+    },
+    {
+      "epoch": 8.0,
+      "eval_loss": 2.3043582439422607,
+      "eval_runtime": 2.1027,
+      "eval_samples_per_second": 925.011,
+      "eval_steps_per_second": 58.021,
+      "step": 4872
+    },
+    {
+      "epoch": 9.0,
+      "grad_norm": 29.515283584594727,
+      "learning_rate": 1.0639412997903564e-05,
+      "loss": 1.2074,
+      "step": 5481
+    },
+    {
+      "epoch": 9.0,
+      "eval_loss": 2.2633635997772217,
+      "eval_runtime": 2.0972,
+      "eval_samples_per_second": 927.418,
+      "eval_steps_per_second": 58.172,
+      "step": 5481
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 13.775968551635742,
+      "learning_rate": 0.0,
+      "loss": 1.1643,
+      "step": 6090
+    },
+    {
+      "epoch": 10.0,
+      "eval_loss": 2.289745807647705,
+      "eval_runtime": 2.1117,
+      "eval_samples_per_second": 921.05,
+      "eval_steps_per_second": 57.773,
+      "step": 6090
+    },
+    {
+      "epoch": 10.0,
+      "step": 6090,
+      "total_flos": 1536221652235776.0,
+      "train_loss": 1.5534028151939656,
+      "train_runtime": 363.1065,
+      "train_samples_per_second": 268.048,
+      "train_steps_per_second": 16.772
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 6090,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "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": 1536221652235776.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}