Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb5ded2d8837a663201a30e2fdd4c372dbd041adbea6fbb11f8318d354748fa3
+oid sha256:02caef41fefa36cf5f027762072464d39baa40817c70225bb534790af6f857bf
 size 267832560

run-3/checkpoint-108/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2049d4ff235930194209bcadba68c9f28941831d6be8afb9ab23bc11cad98cf8
+oid sha256:642d76e7cafeab26ef3b6b0e615ba8c803a310d9ea436c6591c9c7398171fa59
 size 267832560

run-3/checkpoint-108/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ee583b89c741c6d92754ea2b2acf8a5bd79e33ef5565146603053c67e8cd7737
+oid sha256:6944dd1154c9965be4b93a2d85a0a4673484630eec4a0f52b3ae37dfc1f0641a
 size 535727290

run-3/checkpoint-108/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f3e297b7ae7c4df82a1ce845cf84be286dc57704c50dd059929e95c24abad79b
+oid sha256:00e7e60447fe6b0b398d23f91b0df5696220d68e25fe4da0911193612264b803
 size 14244

run-3/checkpoint-108/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:19359dc969a3dad51efa9a2d6f6d5e94a562a510034e89ecbf12473bedf87e37
+oid sha256:94f038ef9a5ad66a472c64034862a7278e5094b40e5d1c995ba1d16aa99930e3
 size 1064

run-3/checkpoint-108/trainer_state.json

@@ -1,6 +1,6 @@
 {
-  "best_metric": 0.0,
-  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-3/checkpoint-54",
+  "best_metric": 0.3349942831439903,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-3/checkpoint-108",
   "epoch": 2.0,
   "eval_steps": 500,
   "global_step": 108,
@@ -10,35 +10,35 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_loss": 0.6135343909263611,
-      "eval_matthews_correlation": 0.0,
-      "eval_runtime": 0.6686,
-      "eval_samples_per_second": 1560.01,
-      "eval_steps_per_second": 98.716,
+      "eval_loss": 0.5624595880508423,
+      "eval_matthews_correlation": 0.10385466804655791,
+      "eval_runtime": 1.2797,
+      "eval_samples_per_second": 815.034,
+      "eval_steps_per_second": 102.368,
       "step": 54
     },
     {
       "epoch": 2.0,
-      "eval_loss": 0.6109986901283264,
-      "eval_matthews_correlation": 0.0,
-      "eval_runtime": 1.2142,
-      "eval_samples_per_second": 859.036,
-      "eval_steps_per_second": 54.359,
+      "eval_loss": 0.6093302965164185,
+      "eval_matthews_correlation": 0.3349942831439903,
+      "eval_runtime": 1.2473,
+      "eval_samples_per_second": 836.218,
+      "eval_steps_per_second": 105.028,
       "step": 108
     }
   ],
   "logging_steps": 500,
-  "max_steps": 108,
+  "max_steps": 162,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 2,
+  "num_train_epochs": 3,
   "save_steps": 500,
   "total_flos": 0,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": {
-    "learning_rate": 7.371411848219159e-06,
-    "num_train_epochs": 2,
+    "learning_rate": 5.503532571253603e-05,
+    "num_train_epochs": 3,
     "per_device_train_batch_size": 16,
-    "seed": 35
+    "seed": 28
   }
 }

run-3/checkpoint-108/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c6ae447073f49fbe1616e5d8dd0fa3e8b79bcfd527890bf6b4740cb1b9964bfc
+oid sha256:5e3db3d5ec943b438ad149fa26941b66a79396dd3ca6343d9f839d70c53ba46e
 size 4984

run-3/checkpoint-162/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": "4.38.1",
+  "vocab_size": 30522
+}

run-3/checkpoint-162/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6abceff8f22a2cfd12053432245d5933303321858fe56f5c7fb47d0632575343
+size 267832560

run-3/checkpoint-162/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6dac662f6204023e4b708390d71585cbfe36afa461bddbc778c15d7fc7327a0d
+size 535727290

run-3/checkpoint-162/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:210f6311babf339b2041dd94e325452cfc47bb4600ce72bcc997b3fc1f605149
+size 14244

run-3/checkpoint-162/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8057fb71e85d5890ca5afa2a056fc36a323c67edad6e2652270aca621736ccbd
+size 1064

run-3/checkpoint-162/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-162/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-162/trainer_state.json

@@ -0,0 +1,53 @@
+{
+  "best_metric": 0.346176833033057,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-3/checkpoint-162",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 162,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.5624595880508423,
+      "eval_matthews_correlation": 0.10385466804655791,
+      "eval_runtime": 1.2797,
+      "eval_samples_per_second": 815.034,
+      "eval_steps_per_second": 102.368,
+      "step": 54
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.6093302965164185,
+      "eval_matthews_correlation": 0.3349942831439903,
+      "eval_runtime": 1.2473,
+      "eval_samples_per_second": 836.218,
+      "eval_steps_per_second": 105.028,
+      "step": 108
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.7864214777946472,
+      "eval_matthews_correlation": 0.346176833033057,
+      "eval_runtime": 1.4034,
+      "eval_samples_per_second": 743.189,
+      "eval_steps_per_second": 93.344,
+      "step": 162
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 162,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 5.503532571253603e-05,
+    "num_train_epochs": 3,
+    "per_device_train_batch_size": 16,
+    "seed": 28
+  }
+}

run-3/checkpoint-162/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e3db3d5ec943b438ad149fa26941b66a79396dd3ca6343d9f839d70c53ba46e
+size 4984

run-3/checkpoint-54/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a07b3521cc8479b97635017fd08648a7bea2791ad6ec7bace28d41fb6d5321c4
+oid sha256:fb5ded2d8837a663201a30e2fdd4c372dbd041adbea6fbb11f8318d354748fa3
 size 267832560

run-3/checkpoint-54/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d3c9bdaa0c6dd042796f0553c74172060ba3f9ff26517f16579571c24bcf23ae
+oid sha256:6eaa5dd6b072e42070f8bc0572641f570e5d8203f8d3d310146222a81e68a48c
 size 535727290

run-3/checkpoint-54/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b760589f8554fc9a823461802d959d20ee6933034d468005d9e9650985646e1
+oid sha256:29c2d4d1404a256eed2965ed677a952e14f2bcce3c6968bd06bbea290182bad5
 size 14244

run-3/checkpoint-54/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e821cd8c0cea6045dab45710ac190a0970d06aa7c327d90cc1165ca399b6078
+oid sha256:1527b641c9f756a5765a3afc0eb992211442419cc2281db17ece7b38dc9271c0
 size 1064

run-3/checkpoint-54/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.0,
+  "best_metric": 0.10385466804655791,
   "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-3/checkpoint-54",
   "epoch": 1.0,
   "eval_steps": 500,
@@ -10,26 +10,26 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_loss": 0.6135343909263611,
-      "eval_matthews_correlation": 0.0,
-      "eval_runtime": 0.6686,
-      "eval_samples_per_second": 1560.01,
-      "eval_steps_per_second": 98.716,
+      "eval_loss": 0.5624595880508423,
+      "eval_matthews_correlation": 0.10385466804655791,
+      "eval_runtime": 1.2797,
+      "eval_samples_per_second": 815.034,
+      "eval_steps_per_second": 102.368,
       "step": 54
     }
   ],
   "logging_steps": 500,
-  "max_steps": 108,
+  "max_steps": 162,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 2,
+  "num_train_epochs": 3,
   "save_steps": 500,
   "total_flos": 0,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": {
-    "learning_rate": 7.371411848219159e-06,
-    "num_train_epochs": 2,
+    "learning_rate": 5.503532571253603e-05,
+    "num_train_epochs": 3,
     "per_device_train_batch_size": 16,
-    "seed": 35
+    "seed": 28
   }
 }

run-3/checkpoint-54/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c6ae447073f49fbe1616e5d8dd0fa3e8b79bcfd527890bf6b4740cb1b9964bfc
+oid sha256:5e3db3d5ec943b438ad149fa26941b66a79396dd3ca6343d9f839d70c53ba46e
 size 4984

run-4/checkpoint-27/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c4542ea02296c83bed04f3c54cf00db1bc8503bfaad3f396b82b3e6187ab61d9
+oid sha256:02caef41fefa36cf5f027762072464d39baa40817c70225bb534790af6f857bf
 size 267832560

run-4/checkpoint-27/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b3047b77b90fa6d77cafeafdcbc70682204686a1d2c84e65c2d0e9e3d85bf779
+oid sha256:7ecd5623494e65cfa6c6677d1d9819c3f3c662876a8aed41ae386887f83058da
 size 535727290

run-4/checkpoint-27/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48abff7665a73e9406f2b3a959d01e6695705f7feda5c2b9fb6e70fad11bc462
-size 14244
+oid sha256:3a4a2560c602f523c91c485207028a3dbcb7126aebac96a22736d83aa2ec429e
+size 14308

run-4/checkpoint-27/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:89c5e803b7810f245162c0c757de90c445efa6c3ac6f29e78ca07f90ca825d2a
+oid sha256:6aa53b3d0a4d6382222988653cd7469ec80a1749702e6aee6c8c16d249816344
 size 1064

run-4/checkpoint-27/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.0,
+  "best_metric": -0.020702674026557004,
   "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-4/checkpoint-27",
   "epoch": 1.0,
   "eval_steps": 500,
@@ -10,26 +10,26 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_loss": 0.6171508431434631,
-      "eval_matthews_correlation": 0.0,
-      "eval_runtime": 1.2254,
-      "eval_samples_per_second": 851.142,
-      "eval_steps_per_second": 106.903,
+      "eval_loss": 0.669028103351593,
+      "eval_matthews_correlation": -0.020702674026557004,
+      "eval_runtime": 0.9548,
+      "eval_samples_per_second": 1092.354,
+      "eval_steps_per_second": 137.199,
       "step": 27
     }
   ],
   "logging_steps": 500,
-  "max_steps": 135,
+  "max_steps": 54,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 5,
+  "num_train_epochs": 2,
   "save_steps": 500,
   "total_flos": 0,
-  "train_batch_size": 16,
+  "train_batch_size": 32,
   "trial_name": null,
   "trial_params": {
-    "learning_rate": 7.141254091425431e-06,
-    "num_train_epochs": 5,
-    "per_device_train_batch_size": 16,
-    "seed": 4
+    "learning_rate": 2.7461506090980817e-06,
+    "num_train_epochs": 2,
+    "per_device_train_batch_size": 32,
+    "seed": 24
   }
 }

run-4/checkpoint-27/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b272556a909ee8d46e26a918cf12e067d37cdfcdb6fc7bb9dd145e02aa9cb279
+oid sha256:9ef1f877c640f97e98c8da61a50566872c84628849589a156be7119b1ff81f04
 size 4984

run-4/checkpoint-54/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8ffa22d670fd8d875f0874f56277b766324b6c576424e31e03488878974f06c
+oid sha256:eb80a875bbe0413ac86706048ef604bc174b717e8166512c5cdf1e3ef4e86279
 size 267832560

run-4/checkpoint-54/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:711bd5c2eaa53854115a17390ce4ca1f9f8640bbf3bf3d9d3682e3ea030b8b2b
+oid sha256:10df1ad217933501acd883e6fa992bba33d96998aef9f160d25e699c875811fa
 size 535727290

run-4/checkpoint-54/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7daa4263b1198655a1441081a5b33c5bce53494dcd0610b8798d313ef92eff4e
-size 14244
+oid sha256:63d63a234463881e0d3edc4fc567ea7c1bae29e71ad748fcee605f8784baf6e3
+size 14308

run-4/checkpoint-54/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab38497e119d49371b53e85f5cfb7d41c0903e3c9879e2bb0e6b7c1e0e7bff52
+oid sha256:446a76f3ec584c657712cc0b5cb821862b8c52c9581d425f442d00177034fa3b
 size 1064

run-4/checkpoint-54/trainer_state.json

@@ -1,6 +1,6 @@
 {
   "best_metric": 0.0,
-  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-4/checkpoint-27",
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-4/checkpoint-54",
   "epoch": 2.0,
   "eval_steps": 500,
   "global_step": 54,
@@ -10,35 +10,35 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_loss": 0.6171508431434631,
-      "eval_matthews_correlation": 0.0,
-      "eval_runtime": 1.2254,
-      "eval_samples_per_second": 851.142,
-      "eval_steps_per_second": 106.903,
+      "eval_loss": 0.669028103351593,
+      "eval_matthews_correlation": -0.020702674026557004,
+      "eval_runtime": 0.9548,
+      "eval_samples_per_second": 1092.354,
+      "eval_steps_per_second": 137.199,
       "step": 27
     },
     {
       "epoch": 2.0,
-      "eval_loss": 0.6099013686180115,
+      "eval_loss": 0.6553832292556763,
       "eval_matthews_correlation": 0.0,
-      "eval_runtime": 1.2265,
-      "eval_samples_per_second": 850.398,
-      "eval_steps_per_second": 106.809,
+      "eval_runtime": 1.9693,
+      "eval_samples_per_second": 529.631,
+      "eval_steps_per_second": 66.521,
       "step": 54
     }
   ],
   "logging_steps": 500,
-  "max_steps": 135,
+  "max_steps": 54,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 5,
+  "num_train_epochs": 2,
   "save_steps": 500,
   "total_flos": 0,
-  "train_batch_size": 16,
+  "train_batch_size": 32,
   "trial_name": null,
   "trial_params": {
-    "learning_rate": 7.141254091425431e-06,
-    "num_train_epochs": 5,
-    "per_device_train_batch_size": 16,
-    "seed": 4
+    "learning_rate": 2.7461506090980817e-06,
+    "num_train_epochs": 2,
+    "per_device_train_batch_size": 32,
+    "seed": 24
   }
 }

run-4/checkpoint-54/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b272556a909ee8d46e26a918cf12e067d37cdfcdb6fc7bb9dd145e02aa9cb279
+oid sha256:9ef1f877c640f97e98c8da61a50566872c84628849589a156be7119b1ff81f04
 size 4984

runs/Feb27_18-29-22_d3d09c0dfc16/events.out.tfevents.1709062232.d3d09c0dfc16.836.15

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5542e74d80b551a338d73a53a7a3d383a29704cb6df5464aff0eea8b05f9741c
+size 5547

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5e3db3d5ec943b438ad149fa26941b66a79396dd3ca6343d9f839d70c53ba46e
+oid sha256:9ef1f877c640f97e98c8da61a50566872c84628849589a156be7119b1ff81f04
 size 4984