Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7aefaacdacfff3d5e98d9b6aa86967c2545b6d06feaa518877c0803d3d427943
+oid sha256:f874697c872f55002ba13791f794c5e587ef93f5b05f3cc117bc92818e98f6a2
 size 267832560

run-0/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-0/checkpoint-27/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7aefaacdacfff3d5e98d9b6aa86967c2545b6d06feaa518877c0803d3d427943
+size 267832560

run-0/checkpoint-27/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58543ac3acbccbd1c7db5946e3c7ba7cf2042bfdc40b2069d97e8cbcc095c4a3
+size 535727290

run-0/checkpoint-27/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27a2607d6885b5cd1aa3da56fad6371e1baa0405d806981364c77cb6467fa6c8
+size 14244

run-0/checkpoint-27/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b17f7b52106f1dcd381ec64377f05612d99fd6a594c3620cb590cea38f642fa
+size 1064

run-0/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-0/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-0/checkpoint-27/trainer_state.json

@@ -0,0 +1,35 @@
+{
+  "best_metric": -0.03275330289169992,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-0/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": 0.6779281497001648,
+      "eval_matthews_correlation": -0.03275330289169992,
+      "eval_runtime": 1.2689,
+      "eval_samples_per_second": 821.945,
+      "eval_steps_per_second": 52.012,
+      "step": 27
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 27,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 2.5849381037834706e-06,
+    "num_train_epochs": 1,
+    "per_device_train_batch_size": 32,
+    "seed": 6
+  }
+}

run-0/checkpoint-27/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56504ee7ae3337bd20217bba7b03520b4a4610857cdd2abfe493426a64c3e625
+size 4984

run-1/checkpoint-108/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-1/checkpoint-108/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12662ea68fe9954d53cda21958bc3cbd2eaf311e8b6417390d4fc8b5d3cef70f
+size 267832560

run-1/checkpoint-108/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f0f26ed40b4113984cb70fc29bfa9d30959352f114eb8be1d07f43d9325dc73
+size 535727290

run-1/checkpoint-108/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6d08e5e7cc27f099578a87aafdab211980ce65d5543db099a078fad53510271
+size 14244

run-1/checkpoint-108/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1105807ebac95f9cbd739f354bfe103a042098e861a6b92e807778b93a90c08d
+size 1064

run-1/checkpoint-108/special_tokens_map.json

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

run-1/checkpoint-108/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-1/checkpoint-108/trainer_state.json

@@ -0,0 +1,62 @@
+{
+  "best_metric": 0.2850901164380653,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-1/checkpoint-108",
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 108,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.5991902351379395,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 1.1489,
+      "eval_samples_per_second": 907.806,
+      "eval_steps_per_second": 57.445,
+      "step": 27
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.5640003085136414,
+      "eval_matthews_correlation": 0.06558874629318973,
+      "eval_runtime": 0.8097,
+      "eval_samples_per_second": 1288.172,
+      "eval_steps_per_second": 81.514,
+      "step": 54
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.5829469561576843,
+      "eval_matthews_correlation": 0.2156721922221702,
+      "eval_runtime": 0.8082,
+      "eval_samples_per_second": 1290.461,
+      "eval_steps_per_second": 81.659,
+      "step": 81
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.5779740214347839,
+      "eval_matthews_correlation": 0.2850901164380653,
+      "eval_runtime": 0.9659,
+      "eval_samples_per_second": 1079.775,
+      "eval_steps_per_second": 68.327,
+      "step": 108
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 108,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 2.7132752645283815e-05,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 32,
+    "seed": 11
+  }
+}

run-1/checkpoint-108/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18ecf3e4cdd742291df73ade32c66811e3f3e816ddbe839f407b1f3a322c8ec9
+size 4984

run-1/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-1/checkpoint-27/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1cd86b0ce750ae1a5a09af8370b2eea241c39f53bffc1a8c03b4a8a14f1e2edf
+size 267832560

run-1/checkpoint-27/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c6800dd79642f82cae9aa42ead97530a80efb0f31718a0fd849fb776fb0cd55
+size 535727290

run-1/checkpoint-27/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09277ee62e69c41b5a1294ae25ca6ea35a705b91436a421b631d6d8b8116f5c9
+size 14244

run-1/checkpoint-27/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ca5050d9259e7b41e44fc96b2e1a69942c916efe15012d7085b6fbb63b4b79e
+size 1064

run-1/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-1/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-1/checkpoint-27/trainer_state.json

@@ -0,0 +1,35 @@
+{
+  "best_metric": 0.0,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-1/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": 0.5991902351379395,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 1.1489,
+      "eval_samples_per_second": 907.806,
+      "eval_steps_per_second": 57.445,
+      "step": 27
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 108,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 2.7132752645283815e-05,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 32,
+    "seed": 11
+  }
+}

run-1/checkpoint-27/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18ecf3e4cdd742291df73ade32c66811e3f3e816ddbe839f407b1f3a322c8ec9
+size 4984

run-1/checkpoint-54/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-1/checkpoint-54/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87ce0f923e5463771a5b6b8f2800460e93ba910a41d185a57e3c34ee4137d490
+size 267832560

run-1/checkpoint-54/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:655a14ee3855c9a48d88451c38b5ac73ac38fbb2f7172d2df68ab28e1d8a5c53
+size 535727290

run-1/checkpoint-54/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e42e2747302ca66575567cd2ad92e4c499840df43d7c74871abe2a004c812c2b
+size 14244

run-1/checkpoint-54/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d820639886bc3678d3a9bea0b240ddffc08779d46f4808d4509f65e1733e0a3c
+size 1064

run-1/checkpoint-54/special_tokens_map.json

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

run-1/checkpoint-54/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-1/checkpoint-54/trainer_state.json

@@ -0,0 +1,44 @@
+{
+  "best_metric": 0.06558874629318973,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-1/checkpoint-54",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 54,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.5991902351379395,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 1.1489,
+      "eval_samples_per_second": 907.806,
+      "eval_steps_per_second": 57.445,
+      "step": 27
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.5640003085136414,
+      "eval_matthews_correlation": 0.06558874629318973,
+      "eval_runtime": 0.8097,
+      "eval_samples_per_second": 1288.172,
+      "eval_steps_per_second": 81.514,
+      "step": 54
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 108,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 2.7132752645283815e-05,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 32,
+    "seed": 11
+  }
+}

run-1/checkpoint-54/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18ecf3e4cdd742291df73ade32c66811e3f3e816ddbe839f407b1f3a322c8ec9
+size 4984

run-1/checkpoint-81/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-1/checkpoint-81/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e5e404f6d6f40471574d623a0546bf2e2445e97bf9410fc1bf140af5f71de48
+size 267832560

run-1/checkpoint-81/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87354af09c52a4f7dd02fa60ee29ad616a85533fa6c85a6c4f36e58a6f694faa
+size 535727290

run-1/checkpoint-81/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5dae41a659a7e169ccb25d03d75764e0a3e0b457ebd805deda168932be6a6d48
+size 14244

run-1/checkpoint-81/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:217afcbf73702431a019fcce4a320b403a53d45d192b14353fa71c7a0fece122
+size 1064