Training in progress, epoch 5

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:939271f6ad84d6a30c3af3110ecb1a45e8b84279a83c889e1e6f1c15a1782651
+oid sha256:32e471fba9fc82c67a4b574b100126083bdec7689d71add216b3e83c33f8b78f
 size 267832560

run-6/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": "4.36.2",
+  "vocab_size": 30522
+}

run-6/checkpoint-1070/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fc608177f0ee1d2ffaca5310ebee7d8eb01ffb83ec0d9b77eb9828934414c0c
+size 267832560

run-6/checkpoint-1070/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd36c11a73a2b3cffb886544a8c7f903850c2f4720f07bf94cd6859e2cf9cdcf
+size 535727290

run-6/checkpoint-1070/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8933c7a8628eb86ba73fde23c3294603d45d0ccc6afbf52bebe8d2594bc9a6ec
+size 14180

run-6/checkpoint-1070/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5b2888dddf3ced89bfcaeb7bf32784e99afd983abcaf71e4500566b13acc3af
+size 1064

run-6/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-6/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-6/checkpoint-1070/trainer_state.json

@@ -0,0 +1,56 @@
+{
+  "best_metric": 0.5083396333380269,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-6/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,
+      "learning_rate": 1.3543559458705673e-05,
+      "loss": 0.5213,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.48579296469688416,
+      "eval_matthews_correlation": 0.4326078706030828,
+      "eval_runtime": 0.7405,
+      "eval_samples_per_second": 1408.497,
+      "eval_steps_per_second": 89.128,
+      "step": 535
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 1.0430097514175634e-05,
+      "loss": 0.3536,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.4809291660785675,
+      "eval_matthews_correlation": 0.5083396333380269,
+      "eval_runtime": 0.8098,
+      "eval_samples_per_second": 1287.978,
+      "eval_steps_per_second": 81.502,
+      "step": 1070
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2675,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 86023345530732.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.6657021403235714e-05,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 16,
+    "seed": 10
+  }
+}

run-6/checkpoint-1070/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1602644d43508d97754d969043bdfa579484259dbb7a0f5abcd3f731f492e3d4
+size 4792

run-6/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": "4.36.2",
+  "vocab_size": 30522
+}

run-6/checkpoint-1605/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ad2941304c0236ecfb47b05935046594de3ed267c51b107739bf7690e24da51
+size 267832560

run-6/checkpoint-1605/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b41670a9285f7877c08e50b95649b10406309f2a7a7f601892f08bd1600f6e4
+size 535727290

run-6/checkpoint-1605/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55422e97fdab2cedd4ba5f190285c572d0556927c14cf6adb271a4e79cb9d456
+size 14180

run-6/checkpoint-1605/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:babfe145444bac6dbbf23bed61a282b20fde8f73dc4e1c18b9f05ec348bb3ec5
+size 1064

run-6/checkpoint-1605/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-1605/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-1605/trainer_state.json

@@ -0,0 +1,71 @@
+{
+  "best_metric": 0.5268164418763311,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-6/checkpoint-1605",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 1605,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.93,
+      "learning_rate": 1.3543559458705673e-05,
+      "loss": 0.5213,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.48579296469688416,
+      "eval_matthews_correlation": 0.4326078706030828,
+      "eval_runtime": 0.7405,
+      "eval_samples_per_second": 1408.497,
+      "eval_steps_per_second": 89.128,
+      "step": 535
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 1.0430097514175634e-05,
+      "loss": 0.3536,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.4809291660785675,
+      "eval_matthews_correlation": 0.5083396333380269,
+      "eval_runtime": 0.8098,
+      "eval_samples_per_second": 1287.978,
+      "eval_steps_per_second": 81.502,
+      "step": 1070
+    },
+    {
+      "epoch": 2.8,
+      "learning_rate": 7.316635569645593e-06,
+      "loss": 0.2508,
+      "step": 1500
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.5551302433013916,
+      "eval_matthews_correlation": 0.5268164418763311,
+      "eval_runtime": 1.2059,
+      "eval_samples_per_second": 864.931,
+      "eval_steps_per_second": 54.732,
+      "step": 1605
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2675,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 129007464042276.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.6657021403235714e-05,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 16,
+    "seed": 10
+  }
+}

run-6/checkpoint-1605/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1602644d43508d97754d969043bdfa579484259dbb7a0f5abcd3f731f492e3d4
+size 4792

run-6/checkpoint-2140/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-6/checkpoint-2140/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bfe5bfa9ce4e86c48eb3779e052cf44ebfa92862b1bcd5a78b0df871fd96b197
+size 267832560

run-6/checkpoint-2140/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e816fb2e616588e0d71b97cbda22f2a8f909901e8b3dfff807cf4742ce63922c
+size 535727290

run-6/checkpoint-2140/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f94426a7cc595df6983cf496c1d42a7c10bc37dbfe537d67cc15d952232e3cb
+size 14180

run-6/checkpoint-2140/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e77a60d37aa0fc96b2f662b19d685bf8a21234a711b9e836706a8251a63bca0e
+size 1064

run-6/checkpoint-2140/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-2140/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-2140/trainer_state.json

@@ -0,0 +1,86 @@
+{
+  "best_metric": 0.5279532549901665,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-6/checkpoint-2140",
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 2140,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.93,
+      "learning_rate": 1.3543559458705673e-05,
+      "loss": 0.5213,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.48579296469688416,
+      "eval_matthews_correlation": 0.4326078706030828,
+      "eval_runtime": 0.7405,
+      "eval_samples_per_second": 1408.497,
+      "eval_steps_per_second": 89.128,
+      "step": 535
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 1.0430097514175634e-05,
+      "loss": 0.3536,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.4809291660785675,
+      "eval_matthews_correlation": 0.5083396333380269,
+      "eval_runtime": 0.8098,
+      "eval_samples_per_second": 1287.978,
+      "eval_steps_per_second": 81.502,
+      "step": 1070
+    },
+    {
+      "epoch": 2.8,
+      "learning_rate": 7.316635569645593e-06,
+      "loss": 0.2508,
+      "step": 1500
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.5551302433013916,
+      "eval_matthews_correlation": 0.5268164418763311,
+      "eval_runtime": 1.2059,
+      "eval_samples_per_second": 864.931,
+      "eval_steps_per_second": 54.732,
+      "step": 1605
+    },
+    {
+      "epoch": 3.74,
+      "learning_rate": 4.203173625115553e-06,
+      "loss": 0.183,
+      "step": 2000
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.7043352723121643,
+      "eval_matthews_correlation": 0.5279532549901665,
+      "eval_runtime": 0.7939,
+      "eval_samples_per_second": 1313.838,
+      "eval_steps_per_second": 83.138,
+      "step": 2140
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2675,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 171484480793340.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.6657021403235714e-05,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 16,
+    "seed": 10
+  }
+}

run-6/checkpoint-2140/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1602644d43508d97754d969043bdfa579484259dbb7a0f5abcd3f731f492e3d4
+size 4792

run-6/checkpoint-2675/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-6/checkpoint-2675/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32e471fba9fc82c67a4b574b100126083bdec7689d71add216b3e83c33f8b78f
+size 267832560

run-6/checkpoint-2675/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4204d4e73a3e2b4b5632930764c121b35cb75de0eb43718d88f5a5452714531
+size 535727290

run-6/checkpoint-2675/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c78a6b4cf1992421f791eef10fc3b22145dcb2c986c4c04addf8dfd3e49d3b03
+size 14180

run-6/checkpoint-2675/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46a67f7db2154c0644ef791d70104cdbf3f45149f2674669385312593775c18f
+size 1064

run-6/checkpoint-2675/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-2675/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-2675/trainer_state.json

@@ -0,0 +1,101 @@
+{
+  "best_metric": 0.5465839960451542,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-6/checkpoint-2675",
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 2675,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.93,
+      "learning_rate": 1.3543559458705673e-05,
+      "loss": 0.5213,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.48579296469688416,
+      "eval_matthews_correlation": 0.4326078706030828,
+      "eval_runtime": 0.7405,
+      "eval_samples_per_second": 1408.497,
+      "eval_steps_per_second": 89.128,
+      "step": 535
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 1.0430097514175634e-05,
+      "loss": 0.3536,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.4809291660785675,
+      "eval_matthews_correlation": 0.5083396333380269,
+      "eval_runtime": 0.8098,
+      "eval_samples_per_second": 1287.978,
+      "eval_steps_per_second": 81.502,
+      "step": 1070
+    },
+    {
+      "epoch": 2.8,
+      "learning_rate": 7.316635569645593e-06,
+      "loss": 0.2508,
+      "step": 1500
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.5551302433013916,
+      "eval_matthews_correlation": 0.5268164418763311,
+      "eval_runtime": 1.2059,
+      "eval_samples_per_second": 864.931,
+      "eval_steps_per_second": 54.732,
+      "step": 1605
+    },
+    {
+      "epoch": 3.74,
+      "learning_rate": 4.203173625115553e-06,
+      "loss": 0.183,
+      "step": 2000
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.7043352723121643,
+      "eval_matthews_correlation": 0.5279532549901665,
+      "eval_runtime": 0.7939,
+      "eval_samples_per_second": 1313.838,
+      "eval_steps_per_second": 83.138,
+      "step": 2140
+    },
+    {
+      "epoch": 4.67,
+      "learning_rate": 1.0897116805855138e-06,
+      "loss": 0.154,
+      "step": 2500
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 0.7843744158744812,
+      "eval_matthews_correlation": 0.5465839960451542,
+      "eval_runtime": 0.7376,
+      "eval_samples_per_second": 1414.007,
+      "eval_steps_per_second": 89.477,
+      "step": 2675
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2675,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 214625645615400.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.6657021403235714e-05,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 16,
+    "seed": 10
+  }
+}

run-6/checkpoint-2675/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1602644d43508d97754d969043bdfa579484259dbb7a0f5abcd3f731f492e3d4
+size 4792

runs/Dec23_02-11-24_38c624d3e13b/events.out.tfevents.1703300275.38c624d3e13b.382.8

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5dbd8b5bc9f7dce6e3c13163b9f2e25bf20507f3c3068b1a901a118a368791c3
-size 6323
+oid sha256:44224152dc1d2a275a63d00e68aee6dc9a4651b189711c21a8930848813be857
+size 7169