Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:812030577cc007c08974c27a89cd87355ccdd1000bf23176c96fed643aad86f0
+oid sha256:f71b521d2681b3ef9d36dce6e8921c8879d659074a659c0b6356ba80f6a72430
 size 267832560

run-3/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": "4.38.2",
+  "vocab_size": 30522
+}

run-3/checkpoint-2138/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0ba2599df1a76d6ab32aa46efcb0d43213be1ccdd4ad523cb03c54d8163aa5a
+size 267832560

run-3/checkpoint-2138/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f4c651d65e3c1911ebb1bccea3c1dd86989f0ad228cd167a41ea09177f0d33a
+size 535727290

run-3/checkpoint-2138/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1341dc85794109fb7ce96bd99d1c83ea45d7e0c35c972d6e456775d50b7459b
+size 14244

run-3/checkpoint-2138/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83c834866f3831245ff46d22eae9541817b754880054bce754bb198243cc0f08
+size 1064

run-3/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-3/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-3/checkpoint-2138/trainer_state.json

@@ -0,0 +1,72 @@
+{
+  "best_metric": 0.46026235307744706,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-3/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,
+      "grad_norm": 8.771077156066895,
+      "learning_rate": 6.473083427439518e-06,
+      "loss": 0.5665,
+      "step": 500
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 4.481599807739258,
+      "learning_rate": 4.497172735302912e-06,
+      "loss": 0.4944,
+      "step": 1000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.516472339630127,
+      "eval_matthews_correlation": 0.409545749280308,
+      "eval_runtime": 0.3422,
+      "eval_samples_per_second": 3047.653,
+      "eval_steps_per_second": 192.852,
+      "step": 1069
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 10.60380744934082,
+      "learning_rate": 2.5212620431663077e-06,
+      "loss": 0.4065,
+      "step": 1500
+    },
+    {
+      "epoch": 1.87,
+      "grad_norm": 11.79504680633545,
+      "learning_rate": 5.453513510297029e-07,
+      "loss": 0.4059,
+      "step": 2000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.5145770311355591,
+      "eval_matthews_correlation": 0.46026235307744706,
+      "eval_runtime": 0.3809,
+      "eval_samples_per_second": 2738.388,
+      "eval_steps_per_second": 173.282,
+      "step": 2138
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2138,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "total_flos": 75192065887500.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 8.448994119576122e-06,
+    "num_train_epochs": 2,
+    "per_device_train_batch_size": 8,
+    "seed": 22
+  }
+}

run-3/checkpoint-2138/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64007b0868c2697da851f18219e28bd943844690e92026e92dcc32c8053cd01b
+size 4984

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": "4.38.2",
+  "vocab_size": 30522
+}

run-4/checkpoint-2138/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f71b521d2681b3ef9d36dce6e8921c8879d659074a659c0b6356ba80f6a72430
+size 267832560

run-4/checkpoint-2138/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6dce72cd1709c3fcb1d22f20c7f2098f8eeecdb396624fbe8d207242bcfcdc5f
+size 535727290

run-4/checkpoint-2138/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21acd9373ba2636a96a037599a124a8848e64458d7ed9a26ffc24cbd4056b661
+size 14244

run-4/checkpoint-2138/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d3ac596cdf39c8fff6203106e81795325a9b5301c4702c402f8460eb695a3e5
+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 +1,63 @@
+{
+  "best_metric": 0.08036809130702588,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-4/checkpoint-2138",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 2138,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.23,
+      "grad_norm": 4.632926940917969,
+      "learning_rate": 1.2946011611760917e-06,
+      "loss": 0.6259,
+      "step": 500
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 5.080592155456543,
+      "learning_rate": 1.2310780423745168e-06,
+      "loss": 0.6096,
+      "step": 1000
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 7.2639031410217285,
+      "learning_rate": 1.1675549235729423e-06,
+      "loss": 0.5698,
+      "step": 1500
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 12.567307472229004,
+      "learning_rate": 1.1040318047713676e-06,
+      "loss": 0.5589,
+      "step": 2000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.5995281934738159,
+      "eval_matthews_correlation": 0.08036809130702588,
+      "eval_runtime": 0.3414,
+      "eval_samples_per_second": 3055.256,
+      "eval_steps_per_second": 193.334,
+      "step": 2138
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 10690,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 32410011903984.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.3581242799776662e-06,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 4,
+    "seed": 5
+  }
+}

run-4/checkpoint-2138/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e09d686d744a0008ff792f3863883364cd703287c8e9332ee8d8209d508c0a5d
+size 4984

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:64007b0868c2697da851f18219e28bd943844690e92026e92dcc32c8053cd01b
+oid sha256:e09d686d744a0008ff792f3863883364cd703287c8e9332ee8d8209d508c0a5d
 size 4984