Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3cad3bec39311015119b7dfa375dc1421ffe9b0de1ad0cbb90bdd9aa8c739653
+oid sha256:47c17417d672bd20caf8ed0e96486192dfd2053ee1fbde3c4c0ac0aefaf32be0
 size 267832560

run-3/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-3/checkpoint-108/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91de754713445d365e5264f8dc05818377593b139a6e5d819362f7f87a88e56e
+size 267832560

run-3/checkpoint-108/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2de505713c1b45e6608513c44ab65942c73424d47b2a83f25853d374382531d
+size 535727290

run-3/checkpoint-108/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8aedd330d6aee94fe2d02b0e7c300d5f4210042276bd84d0e2dce51481ef2f1
+size 14180

run-3/checkpoint-108/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a5021860bd06f36ae5cd613edb73c175da24feb1cc3c6dc753485c2daf18f58
+size 1064

run-3/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-3/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-3/checkpoint-108/trainer_state.json

@@ -0,0 +1,44 @@
+{
+  "best_metric": 0.266518375829597,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-3/checkpoint-108",
+  "epoch": 2.0,
+  "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": 0.5955775380134583,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.7491,
+      "eval_samples_per_second": 1392.423,
+      "eval_steps_per_second": 88.111,
+      "step": 54
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.5488455891609192,
+      "eval_matthews_correlation": 0.266518375829597,
+      "eval_runtime": 0.8071,
+      "eval_samples_per_second": 1292.246,
+      "eval_steps_per_second": 81.772,
+      "step": 108
+    }
+  ],
+  "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": 2.716173223067957e-05,
+    "num_train_epochs": 3,
+    "per_device_train_batch_size": 16,
+    "seed": 10
+  }
+}

run-3/checkpoint-108/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:457d71fbe5d06a11599f2e59168c79b295728a8b2d6abae56269e3868b1e3edf
+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:ecc624c517c1a09d9cbc0be04e97a77c3c0add68b77bccc0acd9a20e3ed69630
+size 267832560

run-3/checkpoint-162/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f81540c50062301cc9512d4198cffc776dff44592da00436b00fea7ea2a4238f
+size 535727290

run-3/checkpoint-162/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c498ec3d348942b3c6a4824c25f4176d7d31ff6ddf6001d1dad51f191153df39
+size 14180

run-3/checkpoint-162/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c079107469375077b931383b831faeb8faeb5140638f8dce36b6a9e1759f1625
+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": 0.303605157359776,
+  "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": 0.5955775380134583,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.7491,
+      "eval_samples_per_second": 1392.423,
+      "eval_steps_per_second": 88.111,
+      "step": 54
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.5488455891609192,
+      "eval_matthews_correlation": 0.266518375829597,
+      "eval_runtime": 0.8071,
+      "eval_samples_per_second": 1292.246,
+      "eval_steps_per_second": 81.772,
+      "step": 108
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.5810102224349976,
+      "eval_matthews_correlation": 0.303605157359776,
+      "eval_runtime": 0.8088,
+      "eval_samples_per_second": 1289.593,
+      "eval_steps_per_second": 81.604,
+      "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": 2.716173223067957e-05,
+    "num_train_epochs": 3,
+    "per_device_train_batch_size": 16,
+    "seed": 10
+  }
+}

run-3/checkpoint-162/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:457d71fbe5d06a11599f2e59168c79b295728a8b2d6abae56269e3868b1e3edf
+size 4984

run-4/checkpoint-14/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-4/checkpoint-14/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47c17417d672bd20caf8ed0e96486192dfd2053ee1fbde3c4c0ac0aefaf32be0
+size 267832560

run-4/checkpoint-14/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ea7af5a8d50690383351d2c5a5c5567efb249fbfba0ad05871d961b01881c35
+size 535727290

run-4/checkpoint-14/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:efff6a055e51106e1bfb05798118133b144de27b9f96579315439ec96b7428bc
+size 14244

run-4/checkpoint-14/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e47e9cd7fece75467756c0c8c628adf7c509d99dccd73d1f161ebdf1015597f2
+size 1064

run-4/checkpoint-14/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-14/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-14/trainer_state.json

@@ -0,0 +1,35 @@
+{
+  "best_metric": -0.02929206145132745,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-4/checkpoint-14",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 14,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.6642347574234009,
+      "eval_matthews_correlation": -0.02929206145132745,
+      "eval_runtime": 0.7449,
+      "eval_samples_per_second": 1400.248,
+      "eval_steps_per_second": 88.606,
+      "step": 14
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 56,
+  "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": 3.972386455212293e-06,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 64,
+    "seed": 30
+  }
+}

run-4/checkpoint-14/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a52a85e5fede16923648ee8411e447df94a81e0233ecd072a487e540b641f6ae
+size 4984

runs/Feb27_13-00-12_87e3b7a5c20d/events.out.tfevents.1709039652.87e3b7a5c20d.10887.6

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3ea88b9bdc0248a861ac4fff5cb503ffe5bbef042f39820bbffd37d7865bf80
+size 6206

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:457d71fbe5d06a11599f2e59168c79b295728a8b2d6abae56269e3868b1e3edf
+oid sha256:a52a85e5fede16923648ee8411e447df94a81e0233ecd072a487e540b641f6ae
 size 4984