Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8df23a34fff6106c674cfa449cebe353dc52f8e19e68422c6659c24d3d691429
+oid sha256:2fd755dce9317178a93ac174473599aca72a5eab56a9f5e00edaa658c70507b4
 size 267832560

run-7/checkpoint-428/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-7/checkpoint-428/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ee37b5af54bdb3ec1d68c4b64780b072140982068ac9dacec675a56227932a4
+size 267832560

run-7/checkpoint-428/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7d2cf5c0c3fc0993a19f05fb328c69ca20c6d344e60914ca4c4baa84a01d0f2
+size 535727290

run-7/checkpoint-428/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5289e6f487516c6d29fd17e358b6dc9e182debf2f09313a433e78e12cf3ac01a
+size 14308

run-7/checkpoint-428/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a27a5c613096bc8d599664745fd6027e54ef492ffdd489eb241fa0bd685ed0b1
+size 1064

run-7/checkpoint-428/special_tokens_map.json

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

run-7/checkpoint-428/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-7/checkpoint-428/trainer_state.json

@@ -0,0 +1,44 @@
+{
+  "best_metric": 0.16332238121235196,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-7/checkpoint-428",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 428,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.5970603823661804,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.7189,
+      "eval_samples_per_second": 1450.923,
+      "eval_steps_per_second": 91.813,
+      "step": 214
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.5912891030311584,
+      "eval_matthews_correlation": 0.16332238121235196,
+      "eval_runtime": 0.8277,
+      "eval_samples_per_second": 1260.144,
+      "eval_steps_per_second": 79.741,
+      "step": 428
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 856,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 8.218219989388813e-06,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 4,
+    "seed": 21
+  }
+}

run-7/checkpoint-428/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7278b5f24278a36bf75b2679827e7995b422ea99ce0fdbcab832d6d3c92da90c
+size 4984

run-7/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": "4.38.1",
+  "vocab_size": 30522
+}

run-7/checkpoint-642/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e282fa4d1b14efed619481b855381a9891204f420b6294e409834819a683daba
+size 267832560

run-7/checkpoint-642/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5282737245ccc3be210bbe42f4fb49bc3ab0f6afac325e3d6af0b28f661875e
+size 535727290

run-7/checkpoint-642/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8aa1d46993a45889981ccea6754a306d9587c2210f097e27f7348c42c39b3503
+size 14308

run-7/checkpoint-642/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a844c7379c94f50bd8795a805e8a20127c98b7d0c9d4fcbf02d7979dcd4d6701
+size 1064

run-7/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-7/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-7/checkpoint-642/trainer_state.json

@@ -0,0 +1,60 @@
+{
+  "best_metric": 0.2313832094979208,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-7/checkpoint-642",
+  "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": 0.5970603823661804,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.7189,
+      "eval_samples_per_second": 1450.923,
+      "eval_steps_per_second": 91.813,
+      "step": 214
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.5912891030311584,
+      "eval_matthews_correlation": 0.16332238121235196,
+      "eval_runtime": 0.8277,
+      "eval_samples_per_second": 1260.144,
+      "eval_steps_per_second": 79.741,
+      "step": 428
+    },
+    {
+      "epoch": 2.34,
+      "grad_norm": 14.575504302978516,
+      "learning_rate": 3.417857846054226e-06,
+      "loss": 0.5722,
+      "step": 500
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.6588433980941772,
+      "eval_matthews_correlation": 0.2313832094979208,
+      "eval_runtime": 0.8191,
+      "eval_samples_per_second": 1273.42,
+      "eval_steps_per_second": 80.581,
+      "step": 642
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 856,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 8328370239720.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 8.218219989388813e-06,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 4,
+    "seed": 21
+  }
+}

run-7/checkpoint-642/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7278b5f24278a36bf75b2679827e7995b422ea99ce0fdbcab832d6d3c92da90c
+size 4984

run-7/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": "4.38.1",
+  "vocab_size": 30522
+}

run-7/checkpoint-856/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb696c508dbb1697cbc20d96c79f6ea05c4d2f789bf5fbec79a8e3764fca9305
+size 267832560

run-7/checkpoint-856/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c03c62fbab8cfd8584d64efbe21bdc1dfb863834c892d61958c8469c7c00018b
+size 535727290

run-7/checkpoint-856/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21fdd3c5f7e022d566aec7fd02c74531ebe842e272c187d0d2648dc7b5e2b77e
+size 14308

run-7/checkpoint-856/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47f638ed07e9f6c5b4d34e66eada885cf2b5ed6c41aefd75ac3e3f9bf065c6b3
+size 1064

run-7/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-7/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-7/checkpoint-856/trainer_state.json

@@ -0,0 +1,69 @@
+{
+  "best_metric": 0.26333420373394023,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-7/checkpoint-856",
+  "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": 0.5970603823661804,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.7189,
+      "eval_samples_per_second": 1450.923,
+      "eval_steps_per_second": 91.813,
+      "step": 214
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.5912891030311584,
+      "eval_matthews_correlation": 0.16332238121235196,
+      "eval_runtime": 0.8277,
+      "eval_samples_per_second": 1260.144,
+      "eval_steps_per_second": 79.741,
+      "step": 428
+    },
+    {
+      "epoch": 2.34,
+      "grad_norm": 14.575504302978516,
+      "learning_rate": 3.417857846054226e-06,
+      "loss": 0.5722,
+      "step": 500
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.6588433980941772,
+      "eval_matthews_correlation": 0.2313832094979208,
+      "eval_runtime": 0.8191,
+      "eval_samples_per_second": 1273.42,
+      "eval_steps_per_second": 80.581,
+      "step": 642
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.6612705588340759,
+      "eval_matthews_correlation": 0.26333420373394023,
+      "eval_runtime": 0.8249,
+      "eval_samples_per_second": 1264.388,
+      "eval_steps_per_second": 80.009,
+      "step": 856
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 856,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 8328370239720.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 8.218219989388813e-06,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 4,
+    "seed": 21
+  }
+}

run-7/checkpoint-856/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7278b5f24278a36bf75b2679827e7995b422ea99ce0fdbcab832d6d3c92da90c
+size 4984

run-8/checkpoint-27/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-8/checkpoint-27/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2fd755dce9317178a93ac174473599aca72a5eab56a9f5e00edaa658c70507b4
+size 267832560

run-8/checkpoint-27/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ecf9a7abec0308452b692bc378de751bcf83d2fa8ba5e02ab9a2859c2fe277a3
+size 535727290

run-8/checkpoint-27/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ead47b2f2567648ce574bbf6c0a46d8ef7b32e7fa89ee7b50934a8b9edfd7c75
+size 14308

run-8/checkpoint-27/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:367d2ac1d9dfb16739d4ed7970f129f833508e320dfeb0387adb49488f930f2a
+size 1064

run-8/checkpoint-27/special_tokens_map.json

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

run-8/checkpoint-27/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-8/checkpoint-27/trainer_state.json

@@ -0,0 +1,35 @@
+{
+  "best_metric": 0.0,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-8/checkpoint-27",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 27,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.6211336851119995,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.7302,
+      "eval_samples_per_second": 1428.291,
+      "eval_steps_per_second": 90.381,
+      "step": 27
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 135,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 5.001244990944814e-06,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 32,
+    "seed": 32
+  }
+}

run-8/checkpoint-27/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32337062a2f88896533152a591e4d651102d7397d2bdd329139d12fbe90d2e1a
+size 4984

runs/Feb27_14-43-24_1abfc43efc69/events.out.tfevents.1709046263.1abfc43efc69.155.10

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54ee5654bf6fde554b744127107e28cd883b95664426e45fde52e051b2f89a79
+size 6547

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7278b5f24278a36bf75b2679827e7995b422ea99ce0fdbcab832d6d3c92da90c
+oid sha256:32337062a2f88896533152a591e4d651102d7397d2bdd329139d12fbe90d2e1a
 size 4984