Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b2e0c4c6b9f3c2af24b4908bd8450398968eeba7917eb0d0db201acdf4a5c200
+oid sha256:48657bba1f20e6fcb598c229f439fe27db878bd253e13443a1b962a4b711ec47
 size 267832560

run-5/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-5/checkpoint-28/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5deb8b4541dc0f9d0e5a8ac75094cb04da05da76402c6149cb500b52d0bf76d
+size 267832560

run-5/checkpoint-28/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf61a4634581f1e8400b83eabb2648bff35954d386b252922b001da6f9a47a12
+size 535727290

run-5/checkpoint-28/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2fc36f9eb920a6c89e2fa6d5af3217dfa8b6a4addb2fd9e3640535336f63d888
+size 14308

run-5/checkpoint-28/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7acb96b8095cac67b7a5bc6b019d0c751670b8787118e22be9b1fb861a888611
+size 1064

run-5/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-5/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-5/checkpoint-28/trainer_state.json

@@ -0,0 +1,44 @@
+{
+  "best_metric": 0.0,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-5/checkpoint-14",
+  "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": 0.611514151096344,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.6874,
+      "eval_samples_per_second": 1517.237,
+      "eval_steps_per_second": 96.009,
+      "step": 14
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.6048123240470886,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.8008,
+      "eval_samples_per_second": 1302.373,
+      "eval_steps_per_second": 82.413,
+      "step": 28
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 42,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.5731331990343205e-05,
+    "num_train_epochs": 3,
+    "per_device_train_batch_size": 64,
+    "seed": 17
+  }
+}

run-5/checkpoint-28/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd8500f89c2644285773c3b4e3865488fe68508949b967a2ebcb93d0944a319f
+size 4984

run-5/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-5/checkpoint-42/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7cadd18825f614a2263bbf00c0ad3fb90058731063e00af62d412e7b29938b63
+size 267832560

run-5/checkpoint-42/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2aa53469682a9dd17d2c2ac3e87e2cbbd178f02bfcf187ec37673f1cd1da73ef
+size 535727290

run-5/checkpoint-42/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4351b22bdcc61e76de8acd65d8fb65e5aa258557cf250f57ae4aace13f907a65
+size 14308

run-5/checkpoint-42/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6c976be105165db2463b1e102c0b2a833ff235bd6c58c120d409b58f491664d
+size 1064

run-5/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-5/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-5/checkpoint-42/trainer_state.json

@@ -0,0 +1,53 @@
+{
+  "best_metric": 0.0,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-5/checkpoint-14",
+  "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": 0.611514151096344,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.6874,
+      "eval_samples_per_second": 1517.237,
+      "eval_steps_per_second": 96.009,
+      "step": 14
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.6048123240470886,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.8008,
+      "eval_samples_per_second": 1302.373,
+      "eval_steps_per_second": 82.413,
+      "step": 28
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.6018168330192566,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 1.2779,
+      "eval_samples_per_second": 816.17,
+      "eval_steps_per_second": 51.646,
+      "step": 42
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 42,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.5731331990343205e-05,
+    "num_train_epochs": 3,
+    "per_device_train_batch_size": 64,
+    "seed": 17
+  }
+}

run-5/checkpoint-42/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd8500f89c2644285773c3b4e3865488fe68508949b967a2ebcb93d0944a319f
+size 4984

run-6/checkpoint-107/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-6/checkpoint-107/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48657bba1f20e6fcb598c229f439fe27db878bd253e13443a1b962a4b711ec47
+size 267832560

run-6/checkpoint-107/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73ecb54cf596c8e2e2f423b652dd2a9e25b900eecc753dad07f58429ab1473df
+size 535727290

run-6/checkpoint-107/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:328ffa495e1e4a83e08c021d81a1d6bac1dea304dd8bd3de6941cfe88349f7a9
+size 14244

run-6/checkpoint-107/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7373eb569bfbe862b39e13f1c417d4c0d9174f53d5674eaf3c502e0c45372f4
+size 1064

run-6/checkpoint-107/special_tokens_map.json

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

run-6/checkpoint-107/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-6/checkpoint-107/trainer_state.json

@@ -0,0 +1,35 @@
+{
+  "best_metric": 0.0,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-6/checkpoint-107",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 107,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.6131327748298645,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.6781,
+      "eval_samples_per_second": 1538.142,
+      "eval_steps_per_second": 97.332,
+      "step": 107
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 321,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 3.500338179632791e-06,
+    "num_train_epochs": 3,
+    "per_device_train_batch_size": 8,
+    "seed": 7
+  }
+}

run-6/checkpoint-107/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64332805f41b28264f8c6f4e5472000eaaf4fcfb1e34125831a97ed73fb13c28
+size 4984

runs/Feb27_12-32-24_dc4ea0da08d6/events.out.tfevents.1709040012.dc4ea0da08d6.176.8

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3083ccbb75bcec3bd982fd327051df0ee2ced5740245f2bb527b3603c76685a
+size 5893

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd8500f89c2644285773c3b4e3865488fe68508949b967a2ebcb93d0944a319f
+oid sha256:64332805f41b28264f8c6f4e5472000eaaf4fcfb1e34125831a97ed73fb13c28
 size 4984