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-2e-05
 
-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: 2.0089
+- Loss: 1.9962
 
 ## Model description
 

all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 10.0,
+    "eval_loss": 1.9962048530578613,
+    "eval_runtime": 2.1252,
+    "eval_samples": 1945,
+    "eval_samples_per_second": 915.193,
+    "eval_steps_per_second": 57.405,
+    "perplexity": 7.361066690824402,
+    "total_flos": 1536221652235776.0,
+    "train_loss": 1.731730433872768,
+    "train_runtime": 362.8983,
+    "train_samples": 9733,
+    "train_samples_per_second": 268.202,
+    "train_steps_per_second": 16.782
+}

eval_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 10.0,
+    "eval_loss": 1.9962048530578613,
+    "eval_runtime": 2.1252,
+    "eval_samples": 1945,
+    "eval_samples_per_second": 915.193,
+    "eval_steps_per_second": 57.405,
+    "perplexity": 7.361066690824402,
+    "total_flos": 1536221652235776.0,
+    "train_loss": 1.731730433872768,
+    "train_runtime": 362.8983,
+    "train_samples": 9733,
+    "train_samples_per_second": 268.202,
+    "train_steps_per_second": 16.782
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 10.0,
+    "total_flos": 1536221652235776.0,
+    "train_loss": 1.731730433872768,
+    "train_runtime": 362.8983,
+    "train_samples": 9733,
+    "train_samples_per_second": 268.202,
+    "train_steps_per_second": 16.782
+}

trainer_state.json

@@ -0,0 +1,192 @@
+{
+  "best_metric": 1.972524881362915,
+  "best_model_checkpoint": "./TAPT_data-V2_Bioformer-16L_LR-2e-05/checkpoint-2436",
+  "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": 25.086040496826172,
+      "learning_rate": 1.9150943396226415e-05,
+      "loss": 2.2144,
+      "step": 609
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 2.0326976776123047,
+      "eval_runtime": 2.0957,
+      "eval_samples_per_second": 928.082,
+      "eval_steps_per_second": 58.214,
+      "step": 609
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 25.068096160888672,
+      "learning_rate": 1.7023060796645702e-05,
+      "loss": 1.9612,
+      "step": 1218
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 1.9747841358184814,
+      "eval_runtime": 2.0904,
+      "eval_samples_per_second": 930.443,
+      "eval_steps_per_second": 58.362,
+      "step": 1218
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 24.59003448486328,
+      "learning_rate": 1.4895178197064991e-05,
+      "loss": 1.839,
+      "step": 1827
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 2.05035138130188,
+      "eval_runtime": 2.2132,
+      "eval_samples_per_second": 878.802,
+      "eval_steps_per_second": 55.123,
+      "step": 1827
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 24.1608829498291,
+      "learning_rate": 1.2767295597484276e-05,
+      "loss": 1.7475,
+      "step": 2436
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 1.972524881362915,
+      "eval_runtime": 2.1181,
+      "eval_samples_per_second": 918.286,
+      "eval_steps_per_second": 57.599,
+      "step": 2436
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 32.5782356262207,
+      "learning_rate": 1.0639412997903564e-05,
+      "loss": 1.6781,
+      "step": 3045
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 2.0161244869232178,
+      "eval_runtime": 2.1106,
+      "eval_samples_per_second": 921.539,
+      "eval_steps_per_second": 57.804,
+      "step": 3045
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 18.229835510253906,
+      "learning_rate": 8.511530398322851e-06,
+      "loss": 1.6427,
+      "step": 3654
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 1.9868873357772827,
+      "eval_runtime": 2.1141,
+      "eval_samples_per_second": 920.02,
+      "eval_steps_per_second": 57.708,
+      "step": 3654
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 19.829086303710938,
+      "learning_rate": 6.383647798742138e-06,
+      "loss": 1.6113,
+      "step": 4263
+    },
+    {
+      "epoch": 7.0,
+      "eval_loss": 2.0333664417266846,
+      "eval_runtime": 2.1163,
+      "eval_samples_per_second": 919.049,
+      "eval_steps_per_second": 57.647,
+      "step": 4263
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 24.086036682128906,
+      "learning_rate": 4.2557651991614255e-06,
+      "loss": 1.5701,
+      "step": 4872
+    },
+    {
+      "epoch": 8.0,
+      "eval_loss": 1.9919387102127075,
+      "eval_runtime": 2.1017,
+      "eval_samples_per_second": 925.423,
+      "eval_steps_per_second": 58.047,
+      "step": 4872
+    },
+    {
+      "epoch": 9.0,
+      "grad_norm": 32.23151397705078,
+      "learning_rate": 2.1278825995807127e-06,
+      "loss": 1.5342,
+      "step": 5481
+    },
+    {
+      "epoch": 9.0,
+      "eval_loss": 1.9797741174697876,
+      "eval_runtime": 2.1025,
+      "eval_samples_per_second": 925.096,
+      "eval_steps_per_second": 58.027,
+      "step": 5481
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 15.350183486938477,
+      "learning_rate": 0.0,
+      "loss": 1.5188,
+      "step": 6090
+    },
+    {
+      "epoch": 10.0,
+      "eval_loss": 2.00888991355896,
+      "eval_runtime": 2.1152,
+      "eval_samples_per_second": 919.522,
+      "eval_steps_per_second": 57.677,
+      "step": 6090
+    },
+    {
+      "epoch": 10.0,
+      "step": 6090,
+      "total_flos": 1536221652235776.0,
+      "train_loss": 1.731730433872768,
+      "train_runtime": 362.8983,
+      "train_samples_per_second": 268.202,
+      "train_steps_per_second": 16.782
+    }
+  ],
+  "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
+}