Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:47c17417d672bd20caf8ed0e96486192dfd2053ee1fbde3c4c0ac0aefaf32be0
+oid sha256:d2dc504a4b8aabed0a2217abdba01d9f5714613ea86900135140841f0a042db9
 size 267832560

run-4/checkpoint-28/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-28/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92e05390fb11dbd71524d32e4d8c81959d99b8ff45e1d9a3f38342a9f1aee95c
+size 267832560

run-4/checkpoint-28/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bbe20af94a10a135c2fd4e52f77cf48dc77554e5c134e3d2073a948bd4cc783a
+size 535727290

run-4/checkpoint-28/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e912e7ecef29078a6c48456d4f7e532d6b36e345f1cb41383933e6de884412c5
+size 14244

run-4/checkpoint-28/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79e86da2637391d7b919c3e5a9c59e50e46628de26c9f37056fcc9a825b752e1
+size 1064

run-4/checkpoint-28/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-28/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-28/trainer_state.json

@@ -0,0 +1,44 @@
+{
+  "best_metric": 0.0,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-4/checkpoint-28",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 28,
+  "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
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.6394474506378174,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.8136,
+      "eval_samples_per_second": 1281.968,
+      "eval_steps_per_second": 81.122,
+      "step": 28
+    }
+  ],
+  "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-28/training_args.bin

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

run-4/checkpoint-42/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-42/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66fabfa48cf31ceb73a7387cd6e6bc32529d7248952373ddbce9270a7b8f9b77
+size 267832560

run-4/checkpoint-42/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bdd2c4f433dfa8af6168a5b35c3e67171f49a3fc4f459d51fb570c5ff9c0bce2
+size 535727290

run-4/checkpoint-42/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe09c6753fc1c749b648fb10309be621bc674a72204b8def36fb1c936c0810ae
+size 14244

run-4/checkpoint-42/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff52927e50a5a27401e5752ac014203e8d2d9caec3a4159ecfad2dd7288435bb
+size 1064

run-4/checkpoint-42/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-42/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-42/trainer_state.json

@@ -0,0 +1,53 @@
+{
+  "best_metric": 0.0,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-4/checkpoint-28",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 42,
+  "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
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.6394474506378174,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.8136,
+      "eval_samples_per_second": 1281.968,
+      "eval_steps_per_second": 81.122,
+      "step": 28
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.6284896731376648,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.8497,
+      "eval_samples_per_second": 1227.448,
+      "eval_steps_per_second": 77.672,
+      "step": 42
+    }
+  ],
+  "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-42/training_args.bin

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

run-4/checkpoint-56/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-56/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:877b9a4ced6b1da6bdfe179ac84daf285541ceeecd3a262d81b827c936f6406f
+size 267832560

run-4/checkpoint-56/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34ac44820e5206ddfbd00c16fd623e147af9caf182fc74dd8fe4474ba0c846e7
+size 535727290

run-4/checkpoint-56/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ed9ae1f8ecaff0f5baf02ae6b3028950f6d0d82bd1b00c374816e9b7b1f6b8b
+size 14244

run-4/checkpoint-56/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5226bd258c77ca31150cbc13539e211f4f51be94781c0e310ae2d1f10019d18
+size 1064

run-4/checkpoint-56/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-56/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-56/trainer_state.json

@@ -0,0 +1,62 @@
+{
+  "best_metric": 0.0,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-4/checkpoint-28",
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 56,
+  "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
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.6394474506378174,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.8136,
+      "eval_samples_per_second": 1281.968,
+      "eval_steps_per_second": 81.122,
+      "step": 28
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.6284896731376648,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.8497,
+      "eval_samples_per_second": 1227.448,
+      "eval_steps_per_second": 77.672,
+      "step": 42
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.625380277633667,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.8483,
+      "eval_samples_per_second": 1229.572,
+      "eval_steps_per_second": 77.806,
+      "step": 56
+    }
+  ],
+  "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-56/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.1709039760.87e3b7a5c20d.10887.7

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3dce64e8c714cabbdaf4d464049dac47c229fe346709b7eb9336810793853515
+size 5859

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a52a85e5fede16923648ee8411e447df94a81e0233ecd072a487e540b641f6ae
+oid sha256:f8486417c5d1f918e41cbd6e1e94759219245b1d65af9add0edeecf915dbf090
 size 4984