Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:57b38e30178be84fca14e28f4f3c3cf2c1b2b0ae3291096e7373a17a4ba23fec
+oid sha256:42dfdd183c3788b4242d1017817ff9dd55611c7993233cbd342d920e938e109a
 size 267832560

run-3/checkpoint-428/config.json

@@ -20,6 +20,6 @@
   "sinusoidal_pos_embds": false,
   "tie_weights_": true,
   "torch_dtype": "float32",
-  "transformers_version": "4.38.1",
+  "transformers_version": "4.38.2",
   "vocab_size": 30522
 }

run-3/checkpoint-428/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c6fb55b3747408fdc3ab6dcdcba41856d9e0deddf9d3d8b5d09e7a48e14bcfdf
+oid sha256:90c1edc8a53919a052e7aaee01879f338cf798f6fcb9dada984a0781ef9728ba
 size 267832560

run-3/checkpoint-428/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ff09b5c87857451fcdf983d76f806d4b6930474e8b02bc3384087e8688457a8
+oid sha256:292f9904b4015abb3c2deae1fd71d56937306387af4af9931b0124a3cdd3c010
 size 535727290

run-3/checkpoint-428/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a278725aaf4e54f71a409ba78aeff1b2947efa64196ea5116a194139c68354b3
-size 14244
+oid sha256:6971122f447c3356127c3fb46d626a7fc962b1b70ea0c33fec3e44e13660e911
+size 14308

run-3/checkpoint-428/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8762181072e981fd071f4ecc1742e9e7a0d802d9a541b03f3aaa11dbf5edf9bf
+oid sha256:fe06f4be4df0c1835196c43f5e119dde5e116259913ec4959807bfd5e2316fb5
 size 1064

run-3/checkpoint-428/trainer_state.json

@@ -1,6 +1,6 @@
 {
-  "best_metric": 0.1077683109552469,
-  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-3/checkpoint-428",
+  "best_metric": 0.0,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-3/checkpoint-214",
   "epoch": 2.0,
   "eval_steps": 500,
   "global_step": 428,
@@ -10,35 +10,35 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_loss": 0.5915305018424988,
+      "eval_loss": 0.6153979301452637,
       "eval_matthews_correlation": 0.0,
-      "eval_runtime": 0.7414,
-      "eval_samples_per_second": 1406.855,
-      "eval_steps_per_second": 89.024,
+      "eval_runtime": 0.6974,
+      "eval_samples_per_second": 1495.562,
+      "eval_steps_per_second": 94.638,
       "step": 214
     },
     {
       "epoch": 2.0,
-      "eval_loss": 0.5806905627250671,
-      "eval_matthews_correlation": 0.1077683109552469,
-      "eval_runtime": 0.8746,
-      "eval_samples_per_second": 1192.555,
-      "eval_steps_per_second": 75.464,
+      "eval_loss": 0.602848470211029,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.782,
+      "eval_samples_per_second": 1333.833,
+      "eval_steps_per_second": 84.404,
       "step": 428
     }
   ],
   "logging_steps": 500,
-  "max_steps": 428,
+  "max_steps": 856,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 2,
+  "num_train_epochs": 4,
   "save_steps": 500,
   "total_flos": 0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": {
-    "learning_rate": 9.511207398100714e-06,
-    "num_train_epochs": 2,
+    "learning_rate": 3.459372063317158e-06,
+    "num_train_epochs": 4,
     "per_device_train_batch_size": 4,
-    "seed": 3
+    "seed": 33
   }
 }

run-3/checkpoint-428/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d6d0e3c171d892a7137b0069a11b5916f7df841be4d6e7a33f7fda92ec2c1986
+oid sha256:725d82177b4cbfe5fdec00f2a98d04c02900a76cd950f04ef533ba2d33dfbdfa
 size 4984

run-3/checkpoint-642/config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "distilbert-base-uncased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "initializer_range": 0.02,
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.2",
+  "vocab_size": 30522
+}

run-3/checkpoint-642/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8694ed2dffe54bf73962bfd7844e188742a7fdae234e0655f8f86ad2da17f564
+size 267832560

run-3/checkpoint-642/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1ac15c6ec8ddfc557e78454d835fbe786e0ac12bf492ba412d7097546d5d000
+size 535727290

run-3/checkpoint-642/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a8b207d92892eda073f4c2a92de7093fd567c2e2128c6bd434a05ca58224849
+size 14308

run-3/checkpoint-642/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:154350f647e63df432156515552f0d7044d360b5ecc25d9dafd7ad8a9f0f56a3
+size 1064

run-3/checkpoint-642/special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

run-3/checkpoint-642/tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}

run-3/checkpoint-642/trainer_state.json

@@ -0,0 +1,60 @@
+{
+  "best_metric": 0.0,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-3/checkpoint-214",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 642,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.6153979301452637,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.6974,
+      "eval_samples_per_second": 1495.562,
+      "eval_steps_per_second": 94.638,
+      "step": 214
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.602848470211029,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.782,
+      "eval_samples_per_second": 1333.833,
+      "eval_steps_per_second": 84.404,
+      "step": 428
+    },
+    {
+      "epoch": 2.34,
+      "grad_norm": 4.680042266845703,
+      "learning_rate": 1.4387108113795659e-06,
+      "loss": 0.6121,
+      "step": 500
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.6024530529975891,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.7955,
+      "eval_samples_per_second": 1311.133,
+      "eval_steps_per_second": 82.967,
+      "step": 642
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 856,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 8371318654128.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 3.459372063317158e-06,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 4,
+    "seed": 33
+  }
+}

run-3/checkpoint-642/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:725d82177b4cbfe5fdec00f2a98d04c02900a76cd950f04ef533ba2d33dfbdfa
+size 4984

run-3/checkpoint-856/config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "distilbert-base-uncased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "initializer_range": 0.02,
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.2",
+  "vocab_size": 30522
+}

run-3/checkpoint-856/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ad425449a5ee5856bd7ce04a58b7a45df3021a7c5bb6a76befc027cc85db51e
+size 267832560

run-3/checkpoint-856/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc33132e7cf0bc49afa6fea8fd4c75a179fdf6d80476d3dac69f58538fbb8fe9
+size 535727290

run-3/checkpoint-856/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2fe5ed12336027e2e1723ebf2522d1c978491ef588d3de8178fc5dcb7fe8a3d0
+size 14308

run-3/checkpoint-856/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3b30541748c05903d7b9d248a81a399b654915d49bdba3b678f6e3555633bf4
+size 1064

run-3/checkpoint-856/special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

run-3/checkpoint-856/tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}

run-3/checkpoint-856/trainer_state.json

@@ -0,0 +1,69 @@
+{
+  "best_metric": 0.0,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-3/checkpoint-214",
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 856,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.6153979301452637,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.6974,
+      "eval_samples_per_second": 1495.562,
+      "eval_steps_per_second": 94.638,
+      "step": 214
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.602848470211029,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.782,
+      "eval_samples_per_second": 1333.833,
+      "eval_steps_per_second": 84.404,
+      "step": 428
+    },
+    {
+      "epoch": 2.34,
+      "grad_norm": 4.680042266845703,
+      "learning_rate": 1.4387108113795659e-06,
+      "loss": 0.6121,
+      "step": 500
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.6024530529975891,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.7955,
+      "eval_samples_per_second": 1311.133,
+      "eval_steps_per_second": 82.967,
+      "step": 642
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.604614794254303,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 1.0834,
+      "eval_samples_per_second": 962.722,
+      "eval_steps_per_second": 60.92,
+      "step": 856
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 856,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 8371318654128.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 3.459372063317158e-06,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 4,
+    "seed": 33
+  }
+}

run-3/checkpoint-856/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:725d82177b4cbfe5fdec00f2a98d04c02900a76cd950f04ef533ba2d33dfbdfa
+size 4984

run-4/checkpoint-54/config.json

@@ -20,6 +20,6 @@
   "sinusoidal_pos_embds": false,
   "tie_weights_": true,
   "torch_dtype": "float32",
-  "transformers_version": "4.38.1",
+  "transformers_version": "4.38.2",
   "vocab_size": 30522
 }

run-4/checkpoint-54/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:221bc5b3bc6d154997d73493ddf825ec8644c5bb3e6a7e0b5f1084bcc34ded26
+oid sha256:42dfdd183c3788b4242d1017817ff9dd55611c7993233cbd342d920e938e109a
 size 267832560

run-4/checkpoint-54/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28bde85d7efe7c5d5f88c3d3e909f2a567d6102431814a31565d7b1870648492
+oid sha256:d6e3dddc621cb38b6bc64affb151d43d05af3f56248b23803f2460be1bd046ea
 size 535727290

run-4/checkpoint-54/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22c4539a3373a39b5f436ae551f8411907d7eb1864e0a338f1b98cd650809cd7
-size 14308
+oid sha256:43a074823da1eb902f5c67a0ce389433db5bce4f6bbd7b918649fd11918fe35b
+size 14244

run-4/checkpoint-54/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ccc14a551d1cc2a201ba467b25be9cab596b8cd09d7aafa8c51968763945df24
+oid sha256:ae4b1ea1e9de01b580ca1e3707e80f04dad1594e9f380c6a3aff2297f1cf7e9c
 size 1064

run-4/checkpoint-54/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.0,
+  "best_metric": 0.16819290962378772,
   "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-4/checkpoint-54",
   "epoch": 1.0,
   "eval_steps": 500,
@@ -10,26 +10,26 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_loss": 0.6367063522338867,
-      "eval_matthews_correlation": 0.0,
-      "eval_runtime": 0.8014,
-      "eval_samples_per_second": 1301.404,
-      "eval_steps_per_second": 82.352,
+      "eval_loss": 0.617885172367096,
+      "eval_matthews_correlation": 0.16819290962378772,
+      "eval_runtime": 0.6977,
+      "eval_samples_per_second": 1494.903,
+      "eval_steps_per_second": 94.596,
       "step": 54
     }
   ],
   "logging_steps": 500,
-  "max_steps": 270,
+  "max_steps": 108,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 5,
+  "num_train_epochs": 2,
   "save_steps": 500,
   "total_flos": 0,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": {
-    "learning_rate": 2.7629511862320974e-06,
-    "num_train_epochs": 5,
+    "learning_rate": 3.476632842490513e-05,
+    "num_train_epochs": 2,
     "per_device_train_batch_size": 16,
-    "seed": 33
+    "seed": 25
   }
 }

run-4/checkpoint-54/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bcfecc084c88ab85212c10896ff8e5a1e28970a19db9d6c9677c556c7df4aac2
+oid sha256:a9b99851e8ad2a46a372cfe02c0e991612e192697b473e1fe009373e293ea561
 size 4984

runs/Mar04_18-27-47_c54f83add3d5/events.out.tfevents.1709577701.c54f83add3d5.171.6

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:154618927d24d0f0e74fe5134175af92caef9fdaef35b2ea7ca58a205bdbd052
+size 5548

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:725d82177b4cbfe5fdec00f2a98d04c02900a76cd950f04ef533ba2d33dfbdfa
+oid sha256:a9b99851e8ad2a46a372cfe02c0e991612e192697b473e1fe009373e293ea561
 size 4984