Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9841ae879ceda66c9e314118e127310095aa902b35709421139c61549f69d947
+oid sha256:0a8f7e7ee7efca1f145b5d3dd168056c45cec2c524d3efe73f7ef19f5a48ede7
 size 267832560

run-3/checkpoint-8552/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-8552/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10f8d737617cf40ee78fa01f8389ac7f8ae3c0b1b798646022fde08e323434d5
+size 267832560

run-3/checkpoint-8552/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98de4f439e38a7d9193333d11565ba7c48314bfc28278ef853fd25cc5fc73f7b
+size 535727290

run-3/checkpoint-8552/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82029a828dfb0cf969f7b5abb76fb6a3c1ed50742e44717ef854b0b51d85a351
+size 14180

run-3/checkpoint-8552/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:874985c5852c9d22047d18f36fc1fc1bbcf46141aec4db381b2f89ce91b25dc6
+size 1064

run-3/checkpoint-8552/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-8552/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-8552/trainer_state.json

@@ -0,0 +1,181 @@
+{
+  "best_metric": 0.5422278243727644,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-3/checkpoint-4276",
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 8552,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.23,
+      "grad_norm": 11.004450798034668,
+      "learning_rate": 2.0214687462514598e-05,
+      "loss": 0.598,
+      "step": 500
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 15.662084579467773,
+      "learning_rate": 1.8959428678205447e-05,
+      "loss": 0.5617,
+      "step": 1000
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 28.870677947998047,
+      "learning_rate": 1.7704169893896296e-05,
+      "loss": 0.5375,
+      "step": 1500
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 64.57504272460938,
+      "learning_rate": 1.6448911109587142e-05,
+      "loss": 0.5691,
+      "step": 2000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.5517680048942566,
+      "eval_matthews_correlation": 0.4384136507504086,
+      "eval_runtime": 0.737,
+      "eval_samples_per_second": 1415.216,
+      "eval_steps_per_second": 89.553,
+      "step": 2138
+    },
+    {
+      "epoch": 1.17,
+      "grad_norm": 25.73099708557129,
+      "learning_rate": 1.5193652325277987e-05,
+      "loss": 0.4513,
+      "step": 2500
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 63.40884017944336,
+      "learning_rate": 1.3938393540968835e-05,
+      "loss": 0.442,
+      "step": 3000
+    },
+    {
+      "epoch": 1.64,
+      "grad_norm": 0.524051308631897,
+      "learning_rate": 1.268313475665968e-05,
+      "loss": 0.4237,
+      "step": 3500
+    },
+    {
+      "epoch": 1.87,
+      "grad_norm": 135.24822998046875,
+      "learning_rate": 1.1427875972350528e-05,
+      "loss": 0.4295,
+      "step": 4000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.7380757331848145,
+      "eval_matthews_correlation": 0.5422278243727644,
+      "eval_runtime": 0.7356,
+      "eval_samples_per_second": 1417.881,
+      "eval_steps_per_second": 89.722,
+      "step": 4276
+    },
+    {
+      "epoch": 2.1,
+      "grad_norm": 0.07921259105205536,
+      "learning_rate": 1.0172617188041375e-05,
+      "loss": 0.3849,
+      "step": 4500
+    },
+    {
+      "epoch": 2.34,
+      "grad_norm": 0.08474227786064148,
+      "learning_rate": 8.917358403732224e-06,
+      "loss": 0.2999,
+      "step": 5000
+    },
+    {
+      "epoch": 2.57,
+      "grad_norm": 0.9242565631866455,
+      "learning_rate": 7.66209961942307e-06,
+      "loss": 0.2708,
+      "step": 5500
+    },
+    {
+      "epoch": 2.81,
+      "grad_norm": 0.1333150714635849,
+      "learning_rate": 6.406840835113916e-06,
+      "loss": 0.2846,
+      "step": 6000
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.9644601345062256,
+      "eval_matthews_correlation": 0.5304969997797532,
+      "eval_runtime": 0.7379,
+      "eval_samples_per_second": 1413.493,
+      "eval_steps_per_second": 89.444,
+      "step": 6414
+    },
+    {
+      "epoch": 3.04,
+      "grad_norm": 0.13025422394275665,
+      "learning_rate": 5.151582050804764e-06,
+      "loss": 0.267,
+      "step": 6500
+    },
+    {
+      "epoch": 3.27,
+      "grad_norm": 0.015170727856457233,
+      "learning_rate": 3.896323266495611e-06,
+      "loss": 0.1489,
+      "step": 7000
+    },
+    {
+      "epoch": 3.51,
+      "grad_norm": 0.03684037923812866,
+      "learning_rate": 2.641064482186458e-06,
+      "loss": 0.1797,
+      "step": 7500
+    },
+    {
+      "epoch": 3.74,
+      "grad_norm": 0.15966422855854034,
+      "learning_rate": 1.385805697877305e-06,
+      "loss": 0.1557,
+      "step": 8000
+    },
+    {
+      "epoch": 3.98,
+      "grad_norm": 0.05443466454744339,
+      "learning_rate": 1.3054691356815192e-07,
+      "loss": 0.1708,
+      "step": 8500
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 1.0916093587875366,
+      "eval_matthews_correlation": 0.5421747077088894,
+      "eval_runtime": 0.8194,
+      "eval_samples_per_second": 1272.83,
+      "eval_steps_per_second": 80.543,
+      "step": 8552
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 8552,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 138657403563900.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 2.1469946246823753e-05,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 4,
+    "seed": 10
+  }
+}

run-3/checkpoint-8552/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5794c39e5f32d9d04daa3a15f6f00d81e0613156566c68faaedd5643205dda11
+size 4984

run-4/checkpoint-134/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-4/checkpoint-134/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a8f7e7ee7efca1f145b5d3dd168056c45cec2c524d3efe73f7ef19f5a48ede7
+size 267832560

run-4/checkpoint-134/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cae5a177cfdca0fc764e05fc654c0f874c7af8bd59b2cd6808de6a3a84a5185d
+size 535727290

run-4/checkpoint-134/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a208b40e2f0aa886fa15a4a55da06d4448874802d6825c61697aad10fba501f
+size 14244

run-4/checkpoint-134/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67b92922507786b3944d00f1d8210c93ba17395ef75b681c310a422480f17593
+size 1064

run-4/checkpoint-134/special_tokens_map.json

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

run-4/checkpoint-134/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-4/checkpoint-134/trainer_state.json

@@ -0,0 +1,35 @@
+{
+  "best_metric": 0.0,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-4/checkpoint-134",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 134,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.5707044005393982,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.8134,
+      "eval_samples_per_second": 1282.322,
+      "eval_steps_per_second": 81.144,
+      "step": 134
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 536,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 4.585789875360977e-06,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 64,
+    "seed": 15
+  }
+}

run-4/checkpoint-134/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ef0ff731fdc2cae0b198ef145bbb3fe7f7944e070856b621fff8bb1f2969dcb
+size 4984

runs/Mar03_19-18-26_abc5bcbabcce/events.out.tfevents.1709494143.abc5bcbabcce.1176.32

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:717390a4d6edf679e2ab92383cc72335a7d3e962e65f15efa521a6a183b4444c
-size 8923
+oid sha256:a5ab5e22d249cb684375b4c2e22b66168603d11377d7c2f06427732afe161a57
+size 9823

runs/Mar03_19-18-26_abc5bcbabcce/events.out.tfevents.1709494631.abc5bcbabcce.1176.33

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:caf928318fec267d4fc74637e1d960b6de05a28ffef75f9b8315a701af10161f
+size 6447

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5794c39e5f32d9d04daa3a15f6f00d81e0613156566c68faaedd5643205dda11
+oid sha256:0ef0ff731fdc2cae0b198ef145bbb3fe7f7944e070856b621fff8bb1f2969dcb
 size 4984