Training in progress, epoch 5

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5e8fc4a8be0a8186e5f30fc603d2205d1bd51ee394fbf8d0cab63023c53d4bdb
+oid sha256:2311fe74bdbe7463c11d2d2d44b7b6e6fdf60647b1431c7dad8add6d5dc744e7
 size 267832560

run-0/checkpoint-1072/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": "4.39.1",
+  "vocab_size": 30522
+}

run-0/checkpoint-1072/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c4bc72f0c8260f7c3738d535a44ce6cf426fa9603ec35d8068c520f446ae018
+size 267832560

run-0/checkpoint-1072/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d5ca38c88cfe26bf18274a014472e136261f0231bf352b330091370f2fbb861
+size 535727290

run-0/checkpoint-1072/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d9cadd24885c458596d3d37b3f361c6cb88eaaf6604ecbdc11dd3254b5d79da
+size 14244

run-0/checkpoint-1072/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2bc6d92349afad44855429eb20561c2180c1c94f4a516ddf4c7d941e7e633df
+size 1064

run-0/checkpoint-1072/special_tokens_map.json

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

run-0/checkpoint-1072/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-0/checkpoint-1072/trainer_state.json

@@ -0,0 +1,76 @@
+{
+  "best_metric": 0.5285049056800905,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-0/checkpoint-804",
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 1072,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.4709893465042114,
+      "eval_matthews_correlation": 0.4646875240807597,
+      "eval_runtime": 0.7053,
+      "eval_samples_per_second": 1478.831,
+      "eval_steps_per_second": 93.579,
+      "step": 268
+    },
+    {
+      "epoch": 1.87,
+      "grad_norm": 8.366425514221191,
+      "learning_rate": 2.0599106326665043e-05,
+      "loss": 0.4229,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.5245255827903748,
+      "eval_matthews_correlation": 0.5006740079024256,
+      "eval_runtime": 0.7492,
+      "eval_samples_per_second": 1392.129,
+      "eval_steps_per_second": 88.093,
+      "step": 536
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.6040851473808289,
+      "eval_matthews_correlation": 0.5285049056800905,
+      "eval_runtime": 0.7702,
+      "eval_samples_per_second": 1354.275,
+      "eval_steps_per_second": 85.697,
+      "step": 804
+    },
+    {
+      "epoch": 3.73,
+      "grad_norm": 3.6857900619506836,
+      "learning_rate": 2.592894502657138e-06,
+      "loss": 0.1642,
+      "step": 1000
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.7166290283203125,
+      "eval_matthews_correlation": 0.509946898813958,
+      "eval_runtime": 1.2908,
+      "eval_samples_per_second": 808.054,
+      "eval_steps_per_second": 51.133,
+      "step": 1072
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1072,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 191499476809020.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 3.860531815067294e-05,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 32,
+    "seed": 11
+  }
+}

run-0/checkpoint-1072/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74dcc7968fbc21d463680c6fd4110462d41047a2dd7ed7725f977c17cc591327
+size 4984

run-0/checkpoint-536/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": "4.39.1",
+  "vocab_size": 30522
+}

run-0/checkpoint-536/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b204ec16e38edffbd26db14d10990d52da9696e58012b998c2cb5a0cf7c2b0d1
+size 267832560

run-0/checkpoint-536/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53557a1160de103fb4562ae87d03620b54d59be2b1caf2f320dc20cdf95380ac
+size 535727290

run-0/checkpoint-536/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:241a81787b21510f2a6b884a029024a8844162c71275b910022fddadaed11c47
+size 14244

run-0/checkpoint-536/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89372ed4aa118ae36e9c4fd0089c3fef94bdb13f0723a14de02cdacd0c230224
+size 1064

run-0/checkpoint-536/special_tokens_map.json

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

run-0/checkpoint-536/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-0/checkpoint-536/trainer_state.json

@@ -0,0 +1,51 @@
+{
+  "best_metric": 0.5006740079024256,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-0/checkpoint-536",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 536,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.4709893465042114,
+      "eval_matthews_correlation": 0.4646875240807597,
+      "eval_runtime": 0.7053,
+      "eval_samples_per_second": 1478.831,
+      "eval_steps_per_second": 93.579,
+      "step": 268
+    },
+    {
+      "epoch": 1.87,
+      "grad_norm": 8.366425514221191,
+      "learning_rate": 2.0599106326665043e-05,
+      "loss": 0.4229,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.5245255827903748,
+      "eval_matthews_correlation": 0.5006740079024256,
+      "eval_runtime": 0.7492,
+      "eval_samples_per_second": 1392.129,
+      "eval_steps_per_second": 88.093,
+      "step": 536
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1072,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 96476109931320.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 3.860531815067294e-05,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 32,
+    "seed": 11
+  }
+}

run-0/checkpoint-536/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74dcc7968fbc21d463680c6fd4110462d41047a2dd7ed7725f977c17cc591327
+size 4984

run-0/checkpoint-804/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": "4.39.1",
+  "vocab_size": 30522
+}

run-0/checkpoint-804/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a2843d9a66d9bdfaf373c00b9337a579ca37ba0bf6551013f8389f95ba7e088
+size 267832560

run-0/checkpoint-804/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa827de344967e7785eec58a824c2ff1070990a45efefc94c6fbdc531569180d
+size 535727290

run-0/checkpoint-804/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:582c21eb84aa10322f3788b94a18dd05074cb11659db8937340301f7fd052f42
+size 14244

run-0/checkpoint-804/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ba3fcc0403a1b49aa8bc5f0f454bd7a703ad534f039dcd6455b9ffd059ba89b
+size 1064

run-0/checkpoint-804/special_tokens_map.json

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

run-0/checkpoint-804/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-0/checkpoint-804/trainer_state.json

@@ -0,0 +1,60 @@
+{
+  "best_metric": 0.5285049056800905,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-0/checkpoint-804",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 804,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.4709893465042114,
+      "eval_matthews_correlation": 0.4646875240807597,
+      "eval_runtime": 0.7053,
+      "eval_samples_per_second": 1478.831,
+      "eval_steps_per_second": 93.579,
+      "step": 268
+    },
+    {
+      "epoch": 1.87,
+      "grad_norm": 8.366425514221191,
+      "learning_rate": 2.0599106326665043e-05,
+      "loss": 0.4229,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.5245255827903748,
+      "eval_matthews_correlation": 0.5006740079024256,
+      "eval_runtime": 0.7492,
+      "eval_samples_per_second": 1392.129,
+      "eval_steps_per_second": 88.093,
+      "step": 536
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.6040851473808289,
+      "eval_matthews_correlation": 0.5285049056800905,
+      "eval_runtime": 0.7702,
+      "eval_samples_per_second": 1354.275,
+      "eval_steps_per_second": 85.697,
+      "step": 804
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1072,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 96476109931320.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 3.860531815067294e-05,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 32,
+    "seed": 11
+  }
+}

run-0/checkpoint-804/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74dcc7968fbc21d463680c6fd4110462d41047a2dd7ed7725f977c17cc591327
+size 4984

run-1/checkpoint-1070/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": "4.39.1",
+  "vocab_size": 30522
+}

run-1/checkpoint-1070/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9896f3b08bbf0c5f14bd809ad4e6a31036f6d006e719623339d689a40098608
+size 267832560

run-1/checkpoint-1070/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:068670e8c380ee42839ccf5655c6d0d9cea58d2f23679eb8b483d975d97514a9
+size 535727290

run-1/checkpoint-1070/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a8f6718c0b0c58f833e26408edaa90f1651508e8d07672d72d303d1bd9b3bbb
+size 14244

run-1/checkpoint-1070/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c207470e5faa1eb10eb7877712b73a07712acd3e608583d91ee8d9ed01ce90d2
+size 1064

run-1/checkpoint-1070/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-1070/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-1070/trainer_state.json

@@ -0,0 +1,58 @@
+{
+  "best_metric": 0.44251427534495513,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-1/checkpoint-1070",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 1070,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.93,
+      "grad_norm": 5.889455795288086,
+      "learning_rate": 4.212964989775573e-06,
+      "loss": 0.5566,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.524069607257843,
+      "eval_matthews_correlation": 0.38317232301443055,
+      "eval_runtime": 0.7238,
+      "eval_samples_per_second": 1441.015,
+      "eval_steps_per_second": 91.186,
+      "step": 535
+    },
+    {
+      "epoch": 1.87,
+      "grad_norm": 9.795114517211914,
+      "learning_rate": 2.9285244441122883e-06,
+      "loss": 0.457,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.5066272020339966,
+      "eval_matthews_correlation": 0.44251427534495513,
+      "eval_runtime": 0.7968,
+      "eval_samples_per_second": 1308.954,
+      "eval_steps_per_second": 82.829,
+      "step": 1070
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2140,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 85812225614124.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 5.4974055354388575e-06,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 16,
+    "seed": 38
+  }
+}

run-1/checkpoint-1070/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5acc9708bd966ef79b6adaeae60986df2de0bee8d46ea50e08932265e4057477
+size 4984

run-1/checkpoint-1605/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": "4.39.1",
+  "vocab_size": 30522
+}

run-1/checkpoint-1605/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37b4518980fee1c6dc878bf2f64bf32da0076e73131903aa5ac3f8e6b1756080
+size 267832560

run-1/checkpoint-1605/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e92ab526b6b35c5a097f6c6dd3521e69f251f7db2ac737c3921090b25ec1e07b
+size 535727290

run-1/checkpoint-1605/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:caea22f87aec0a1e84eba35379bdd65b13fd64e1cc2d2bc6a53f33df1678ec77
+size 14244

run-1/checkpoint-1605/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8775d5e7c6a6bd7733c5e139e99332b28f9d6758fdbe775c941d234ad370b13b
+size 1064