Training in progress, step 2500

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc6d5d7b39b3893580c52210ee5a58e9a8c2eccf9e6ffe2680b58d66f2c31759
+oid sha256:76b5fc112f19e1e61989372bf7b85c3848aae1444cee51aaf7132943bcf9e811
 size 1340618660

run-4/checkpoint-1000/config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "bert-large-uncased",
+  "architectures": [
+    "BertForMultipleChoice"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.40.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-4/checkpoint-1000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e1923b2a6a946b350f79374babb391c067b2ee10f912ccf38a00036599f4e3f
+size 1340618660

run-4/checkpoint-1000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86c372f316ec973a24a5e57e0a4ded7280d014a2cc9d17ff313270cd3626fde3
+size 2681472237

run-4/checkpoint-1000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e1a256d949d074cb5d76270949caf88a9f9cee6049fc1f352d070a28cfba690
+size 14244

run-4/checkpoint-1000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5b883c32af12226887f29ce5708b7e1f2646bafa6d23f9f3a52f29e7c100ab4
+size 1064

run-4/checkpoint-1000/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-1000/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": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

run-4/checkpoint-1000/trainer_state.json

@@ -0,0 +1,47 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.3404825737265416,
+  "eval_steps": 500,
+  "global_step": 1000,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.6702412868632708,
+      "grad_norm": 13.804513931274414,
+      "learning_rate": 1.2284160000241888e-05,
+      "loss": 0.5698,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7532685399055481,
+      "eval_loss": 0.4876743257045746,
+      "eval_runtime": 9.5369,
+      "eval_samples_per_second": 312.785,
+      "eval_steps_per_second": 19.608,
+      "step": 746
+    },
+    {
+      "epoch": 1.3404825737265416,
+      "grad_norm": 23.23216438293457,
+      "learning_rate": 1.1401677241603822e-05,
+      "loss": 0.4247,
+      "step": 1000
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 7460,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "total_flos": 2602962871446816.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.3166642758879955e-05,
+    "per_device_train_batch_size": 16
+  }
+}

run-4/checkpoint-1000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27b6f814d1d31383705935d6e962b569d93dc7baa4de5cb209ef031fca6730c2
+size 5048

run-4/checkpoint-1500/config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "bert-large-uncased",
+  "architectures": [
+    "BertForMultipleChoice"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.40.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-4/checkpoint-1500/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d57e7f003f5a89a77a6f126c64498fb296c576485cd73138602f117760a201e6
+size 1340618660

run-4/checkpoint-1500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:498d35d12b55496b9e0d5d538f58834cfa1cca345f121a6f1657c6108a133c81
+size 2681472237

run-4/checkpoint-1500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec6c109e0b81728091fd53d38fe23ff184b43ac15b141962e34b108757cda4da
+size 14244

run-4/checkpoint-1500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a52cb0a20e7783e935e08652ee237e4ff9861e0f620de11824f8ca5f2d025409
+size 1064

run-4/checkpoint-1500/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-1500/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": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

run-4/checkpoint-1500/trainer_state.json

@@ -0,0 +1,63 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0107238605898123,
+  "eval_steps": 500,
+  "global_step": 1500,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.6702412868632708,
+      "grad_norm": 13.804513931274414,
+      "learning_rate": 1.2284160000241888e-05,
+      "loss": 0.5698,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7532685399055481,
+      "eval_loss": 0.4876743257045746,
+      "eval_runtime": 9.5369,
+      "eval_samples_per_second": 312.785,
+      "eval_steps_per_second": 19.608,
+      "step": 746
+    },
+    {
+      "epoch": 1.3404825737265416,
+      "grad_norm": 23.23216438293457,
+      "learning_rate": 1.1401677241603822e-05,
+      "loss": 0.4247,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7777405381202698,
+      "eval_loss": 0.5234329700469971,
+      "eval_runtime": 9.4342,
+      "eval_samples_per_second": 316.19,
+      "eval_steps_per_second": 19.821,
+      "step": 1492
+    },
+    {
+      "epoch": 2.0107238605898123,
+      "grad_norm": 6.197817325592041,
+      "learning_rate": 1.0519194482965755e-05,
+      "loss": 0.3313,
+      "step": 1500
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 7460,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "total_flos": 3914742842009676.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.3166642758879955e-05,
+    "per_device_train_batch_size": 16
+  }
+}

run-4/checkpoint-1500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27b6f814d1d31383705935d6e962b569d93dc7baa4de5cb209ef031fca6730c2
+size 5048

run-4/checkpoint-2000/config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "bert-large-uncased",
+  "architectures": [
+    "BertForMultipleChoice"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.40.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-4/checkpoint-2000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:576398d1636b2ef91e1375404fb259e9fde6dd0aad790584a608748cfb89f639
+size 1340618660

run-4/checkpoint-2000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a49714dca0db2b6df162b518f6791931c74eb83d5300e79ab3340fdb70e2605a
+size 2681472237

run-4/checkpoint-2000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f58a3d1eb6b21b20dd7b0d4230faa8548ab3124fbf5bb32e938d1276eb9a4c73
+size 14244

run-4/checkpoint-2000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8eb96e57562a71108cc733e425fb39f1ab30f8ddb630ebd6149e4b804464c4c8
+size 1064

run-4/checkpoint-2000/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-2000/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": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

run-4/checkpoint-2000/trainer_state.json

@@ -0,0 +1,70 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.680965147453083,
+  "eval_steps": 500,
+  "global_step": 2000,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.6702412868632708,
+      "grad_norm": 13.804513931274414,
+      "learning_rate": 1.2284160000241888e-05,
+      "loss": 0.5698,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7532685399055481,
+      "eval_loss": 0.4876743257045746,
+      "eval_runtime": 9.5369,
+      "eval_samples_per_second": 312.785,
+      "eval_steps_per_second": 19.608,
+      "step": 746
+    },
+    {
+      "epoch": 1.3404825737265416,
+      "grad_norm": 23.23216438293457,
+      "learning_rate": 1.1401677241603822e-05,
+      "loss": 0.4247,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7777405381202698,
+      "eval_loss": 0.5234329700469971,
+      "eval_runtime": 9.4342,
+      "eval_samples_per_second": 316.19,
+      "eval_steps_per_second": 19.821,
+      "step": 1492
+    },
+    {
+      "epoch": 2.0107238605898123,
+      "grad_norm": 6.197817325592041,
+      "learning_rate": 1.0519194482965755e-05,
+      "loss": 0.3313,
+      "step": 1500
+    },
+    {
+      "epoch": 2.680965147453083,
+      "grad_norm": 20.681987762451172,
+      "learning_rate": 9.63671172432769e-06,
+      "loss": 0.1575,
+      "step": 2000
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 7460,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "total_flos": 5210880251877900.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.3166642758879955e-05,
+    "per_device_train_batch_size": 16
+  }
+}

run-4/checkpoint-2000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27b6f814d1d31383705935d6e962b569d93dc7baa4de5cb209ef031fca6730c2
+size 5048

run-4/checkpoint-2500/config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "bert-large-uncased",
+  "architectures": [
+    "BertForMultipleChoice"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.40.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-4/checkpoint-2500/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76b5fc112f19e1e61989372bf7b85c3848aae1444cee51aaf7132943bcf9e811
+size 1340618660

run-4/checkpoint-2500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9179ecc99abfb359d5cbb128c3a2d094ac6cb76d4866f1bd8f42631910af0c0e
+size 2681472237

run-4/checkpoint-2500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c60cac06bde3137dc5e45389d38d5cf66579dc186b1bafb1402f6e093666502
+size 14244

run-4/checkpoint-2500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cadcf8664e62f038b5f54a0b45c839f54b6c73e088f5e94ef39d1a38c7603347
+size 1064

run-4/checkpoint-2500/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-2500/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": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

run-4/checkpoint-2500/trainer_state.json

@@ -0,0 +1,86 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.351206434316354,
+  "eval_steps": 500,
+  "global_step": 2500,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.6702412868632708,
+      "grad_norm": 13.804513931274414,
+      "learning_rate": 1.2284160000241888e-05,
+      "loss": 0.5698,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7532685399055481,
+      "eval_loss": 0.4876743257045746,
+      "eval_runtime": 9.5369,
+      "eval_samples_per_second": 312.785,
+      "eval_steps_per_second": 19.608,
+      "step": 746
+    },
+    {
+      "epoch": 1.3404825737265416,
+      "grad_norm": 23.23216438293457,
+      "learning_rate": 1.1401677241603822e-05,
+      "loss": 0.4247,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7777405381202698,
+      "eval_loss": 0.5234329700469971,
+      "eval_runtime": 9.4342,
+      "eval_samples_per_second": 316.19,
+      "eval_steps_per_second": 19.821,
+      "step": 1492
+    },
+    {
+      "epoch": 2.0107238605898123,
+      "grad_norm": 6.197817325592041,
+      "learning_rate": 1.0519194482965755e-05,
+      "loss": 0.3313,
+      "step": 1500
+    },
+    {
+      "epoch": 2.680965147453083,
+      "grad_norm": 20.681987762451172,
+      "learning_rate": 9.63671172432769e-06,
+      "loss": 0.1575,
+      "step": 2000
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7740529775619507,
+      "eval_loss": 0.6654106378555298,
+      "eval_runtime": 9.4207,
+      "eval_samples_per_second": 316.642,
+      "eval_steps_per_second": 19.85,
+      "step": 2238
+    },
+    {
+      "epoch": 3.351206434316354,
+      "grad_norm": 0.6577324271202087,
+      "learning_rate": 8.754228965689622e-06,
+      "loss": 0.1178,
+      "step": 2500
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 7460,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "total_flos": 6517632906564732.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.3166642758879955e-05,
+    "per_device_train_batch_size": 16
+  }
+}

run-4/checkpoint-2500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27b6f814d1d31383705935d6e962b569d93dc7baa4de5cb209ef031fca6730c2
+size 5048