Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2571973e05d829a0d634c77845cb457681b1131a49420f5d8f47febfa4e140a8
+oid sha256:f88a28ef9de9eea17dd9e641ec60832eb2308a16e9898d3948e5ca4ed042ce6e
 size 267832560

run-4/checkpoint-1069/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": "4.36.2",
+  "vocab_size": 30522
+}

run-4/checkpoint-1069/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2571973e05d829a0d634c77845cb457681b1131a49420f5d8f47febfa4e140a8
+size 267832560

run-4/checkpoint-1069/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a987172dab3e158f8e61ce10088550abe61bc5bc40132d21dff4c51908419b6
+size 535727290

run-4/checkpoint-1069/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0c5611e67a5ac13cbd4609a24db947366c3c5eda9baa3775b51533a395102f4
+size 14244

run-4/checkpoint-1069/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46f431a03a0a8eadc4f93f46af2a87bbaf45aa67c853e7dead4e8d1d857c3540
+size 1064

run-4/checkpoint-1069/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-1069/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-1069/trainer_state.json

@@ -0,0 +1,47 @@
+{
+  "best_metric": 0.33521556405671804,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-4/checkpoint-1069",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 1069,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.47,
+      "learning_rate": 3.970511622906794e-05,
+      "loss": 0.5963,
+      "step": 500
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 2.75851173801461e-05,
+      "loss": 0.5523,
+      "step": 1000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.5371980667114258,
+      "eval_matthews_correlation": 0.33521556405671804,
+      "eval_runtime": 0.7629,
+      "eval_samples_per_second": 1367.128,
+      "eval_steps_per_second": 86.51,
+      "step": 1069
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2138,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "total_flos": 37629020430720.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 5.182511507798978e-05,
+    "num_train_epochs": 2,
+    "per_device_train_batch_size": 8,
+    "seed": 28
+  }
+}

run-4/checkpoint-1069/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17638a515ffeb321f2de273e152e67a1344ce75c21b4f40728fc3724450aa377
+size 4792

run-4/checkpoint-2138/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": "4.36.2",
+  "vocab_size": 30522
+}

run-4/checkpoint-2138/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22cfdca086862c8c2dc68d396be874ee9a81dc61188a790cd65ed80dc599e007
+size 267832560

run-4/checkpoint-2138/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d40a550899e118cfebac140cc4638045ebc06f60d3f32ee0cc3bd797efd5add
+size 535727290

run-4/checkpoint-2138/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c661a9c4d57c47536ee322346f60ba03644363fd4ac0853e42e71f5c265d983e
+size 14244

run-4/checkpoint-2138/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f39e18229b9b2df898571191e7b6577a0c3d3fecfa6404b97641d77d79acaa1d
+size 1064

run-4/checkpoint-2138/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-2138/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-2138/trainer_state.json

@@ -0,0 +1,68 @@
+{
+  "best_metric": 0.446244823436024,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-4/checkpoint-2138",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 2138,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.47,
+      "learning_rate": 3.970511622906794e-05,
+      "loss": 0.5963,
+      "step": 500
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 2.75851173801461e-05,
+      "loss": 0.5523,
+      "step": 1000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.5371980667114258,
+      "eval_matthews_correlation": 0.33521556405671804,
+      "eval_runtime": 0.7629,
+      "eval_samples_per_second": 1367.128,
+      "eval_steps_per_second": 86.51,
+      "step": 1069
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 1.5465118531224263e-05,
+      "loss": 0.3918,
+      "step": 1500
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 3.3451196823024276e-06,
+      "loss": 0.3683,
+      "step": 2000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.6115844249725342,
+      "eval_matthews_correlation": 0.446244823436024,
+      "eval_runtime": 0.8682,
+      "eval_samples_per_second": 1201.294,
+      "eval_steps_per_second": 76.017,
+      "step": 2138
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2138,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "total_flos": 75396458944020.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 5.182511507798978e-05,
+    "num_train_epochs": 2,
+    "per_device_train_batch_size": 8,
+    "seed": 28
+  }
+}

run-4/checkpoint-2138/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17638a515ffeb321f2de273e152e67a1344ce75c21b4f40728fc3724450aa377
+size 4792

run-5/checkpoint-268/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": "4.36.2",
+  "vocab_size": 30522
+}

run-5/checkpoint-268/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f88a28ef9de9eea17dd9e641ec60832eb2308a16e9898d3948e5ca4ed042ce6e
+size 267832560

run-5/checkpoint-268/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0acb12810269a8905e4ffcda734ccd1f543f719620fc4f0786617432b6da0d67
+size 535727290

run-5/checkpoint-268/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9bbb5257ccd22b0ce5ae0c12d9db2a410c156d40fbf77fcc623fb844aa50d05a
+size 14244

run-5/checkpoint-268/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce0fa234803da47b2054098bddee0e9574dcb05dc53bba3cb0073038ef8d9018
+size 1064

run-5/checkpoint-268/special_tokens_map.json

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

run-5/checkpoint-268/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-5/checkpoint-268/trainer_state.json

@@ -0,0 +1,35 @@
+{
+  "best_metric": 0.0,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-5/checkpoint-268",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 268,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.5973381996154785,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.8179,
+      "eval_samples_per_second": 1275.195,
+      "eval_steps_per_second": 80.693,
+      "step": 268
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 804,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 2.3714262410540132e-06,
+    "num_train_epochs": 3,
+    "per_device_train_batch_size": 32,
+    "seed": 36
+  }
+}

run-5/checkpoint-268/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3687b889ed80357afc881c9979d2fdb1e97e7760add524df7377e5905d2d940
+size 4792

runs/Dec22_07-12-50_84c4b1f8dc6c/events.out.tfevents.1703230451.84c4b1f8dc6c.518.7

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a927df1cb6bd182103eeb32b1b022ac127c7adb4005c5aa748083370b351bca
+size 5858

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:17638a515ffeb321f2de273e152e67a1344ce75c21b4f40728fc3724450aa377
+oid sha256:b3687b889ed80357afc881c9979d2fdb1e97e7760add524df7377e5905d2d940
 size 4792