Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a85bbe0c5b3c0e6788e152f62f8ddc860035ecb0ef55c39b14a4cd1b7d04cde
+oid sha256:29022bff9b21dc6fdd4ed82c59bdc34d306e4d0355f8a49346ba76403a372b28
 size 267832560

run-1/checkpoint-5345/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-1/checkpoint-5345/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a85bbe0c5b3c0e6788e152f62f8ddc860035ecb0ef55c39b14a4cd1b7d04cde
+size 267832560

run-1/checkpoint-5345/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4568dc8f41a1ac8306fd67428a18975b79b671dc760c67663261c94dbd84dfb
+size 535727290

run-1/checkpoint-5345/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4eb13722790828df9594abbe46ec425f1fc72859849505d333180e4bd3171b73
+size 14244

run-1/checkpoint-5345/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dce6e9c02956c65909a35ee4c178b86a5c08abf78735ef927ef4fc3b2e1cf8be
+size 1064

run-1/checkpoint-5345/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-5345/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-5345/trainer_state.json

@@ -0,0 +1,131 @@
+{
+  "best_metric": 0.41805920073946057,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-1/checkpoint-4276",
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 5345,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.378211193526262e-06,
+      "loss": 0.6228,
+      "step": 500
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.2359809361964104e-06,
+      "loss": 0.5739,
+      "step": 1000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.5663976073265076,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.7509,
+      "eval_samples_per_second": 1388.989,
+      "eval_steps_per_second": 87.894,
+      "step": 1069
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 1.0937506788665588e-06,
+      "loss": 0.5243,
+      "step": 1500
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 9.515204215367072e-07,
+      "loss": 0.5246,
+      "step": 2000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.5383091568946838,
+      "eval_matthews_correlation": 0.3619330825728506,
+      "eval_runtime": 0.79,
+      "eval_samples_per_second": 1320.281,
+      "eval_steps_per_second": 83.546,
+      "step": 2138
+    },
+    {
+      "epoch": 2.34,
+      "learning_rate": 8.092901642068555e-07,
+      "loss": 0.4948,
+      "step": 2500
+    },
+    {
+      "epoch": 2.81,
+      "learning_rate": 6.67059906877004e-07,
+      "loss": 0.4814,
+      "step": 3000
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.5481904149055481,
+      "eval_matthews_correlation": 0.3794738324574525,
+      "eval_runtime": 0.8601,
+      "eval_samples_per_second": 1212.697,
+      "eval_steps_per_second": 76.738,
+      "step": 3207
+    },
+    {
+      "epoch": 3.27,
+      "learning_rate": 5.248296495471524e-07,
+      "loss": 0.4773,
+      "step": 3500
+    },
+    {
+      "epoch": 3.74,
+      "learning_rate": 3.8259939221730087e-07,
+      "loss": 0.4534,
+      "step": 4000
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.5383455753326416,
+      "eval_matthews_correlation": 0.41805920073946057,
+      "eval_runtime": 0.7864,
+      "eval_samples_per_second": 1326.374,
+      "eval_steps_per_second": 83.932,
+      "step": 4276
+    },
+    {
+      "epoch": 4.21,
+      "learning_rate": 2.403691348874492e-07,
+      "loss": 0.4445,
+      "step": 4500
+    },
+    {
+      "epoch": 4.68,
+      "learning_rate": 9.813887755759761e-08,
+      "loss": 0.4475,
+      "step": 5000
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 0.537183940410614,
+      "eval_matthews_correlation": 0.41512317023401185,
+      "eval_runtime": 0.7585,
+      "eval_samples_per_second": 1375.171,
+      "eval_steps_per_second": 87.019,
+      "step": 5345
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 5345,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 188309134049592.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.5204414508561137e-06,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 8,
+    "seed": 38
+  }
+}

run-1/checkpoint-5345/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:993e710895c7c98b68e7ca3c281cd68e387ca778109cb5f069d17f6faa72b348
+size 4792

run-2/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-2/checkpoint-268/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29022bff9b21dc6fdd4ed82c59bdc34d306e4d0355f8a49346ba76403a372b28
+size 267832560

run-2/checkpoint-268/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bcf5bcc734bf7c8e99cf85e483c00f1a0615a1964ce679c4b4c069e3b008fabd
+size 535727290

run-2/checkpoint-268/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9db2fff93daf69d36c69eed9c3ff45fff6d77549f2bf08725b36089f58ab80e6
+size 14244

run-2/checkpoint-268/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04e9473545200e195b2f3f328794c317894b974658440e270614e3ef295dd77b
+size 1064

run-2/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-2/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-2/checkpoint-268/trainer_state.json

@@ -0,0 +1,35 @@
+{
+  "best_metric": 0.0,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-2/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": 0.579799473285675,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.7752,
+      "eval_samples_per_second": 1345.537,
+      "eval_steps_per_second": 85.144,
+      "step": 268
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 268,
+  "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": 5.687873149823415e-06,
+    "num_train_epochs": 1,
+    "per_device_train_batch_size": 32,
+    "seed": 2
+  }
+}

run-2/checkpoint-268/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:919ebdb29df2c4dfd588105d7307257de4b882cebbc2d385c8ded06fba2a3ea0
+size 4792

runs/Dec23_02-21-58_39bac3413ec0/events.out.tfevents.1703299021.39bac3413ec0.1762.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b30ac209dff484bbd39c8512b1b2d7fd5a1d525a33a32e881d9035a353199691
+size 5039

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:993e710895c7c98b68e7ca3c281cd68e387ca778109cb5f069d17f6faa72b348
+oid sha256:919ebdb29df2c4dfd588105d7307257de4b882cebbc2d385c8ded06fba2a3ea0
 size 4792