Training in progress, step 4500

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b526edd84671d37896c07e86daf99cf2884cbeb1b0b9db3392b06b857b681d4
+oid sha256:498d2da2ab31920cf0cd8bacea0c0c200dbe8e0fe068e052a803669c1ebb82f3
 size 1340618660

run-3/checkpoint-3500/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-3/checkpoint-3500/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03f960eef97328eb75ca45ad213ab9880a71be6391d7c4ed6e96fa821182d664
+size 1340618660

run-3/checkpoint-3500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:190064f96e578da6271b2a041e7a11b7a8d088ed0258ab8b1018e1bcb51b19dd
+size 2681472237

run-3/checkpoint-3500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:661d7cc347d4d84b3f5bfbea2148f5922eb3a76fa7cc1053de1e26c08c4bdd72
+size 14244

run-3/checkpoint-3500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c779c2cbb6f1a312a4128a72a9ec5100b05e774b9409b78a47569457ef4df87
+size 1064

run-3/checkpoint-3500/special_tokens_map.json

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

run-3/checkpoint-3500/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-3/checkpoint-3500/trainer_state.json

@@ -0,0 +1,109 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.6916890080428955,
+  "eval_steps": 500,
+  "global_step": 3500,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.6702412868632708,
+      "grad_norm": 1.8121609687805176,
+      "learning_rate": 4.400558387583305e-05,
+      "loss": 0.6264,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5072075128555298,
+      "eval_loss": 0.6931472420692444,
+      "eval_runtime": 9.1548,
+      "eval_samples_per_second": 325.839,
+      "eval_steps_per_second": 20.426,
+      "step": 746
+    },
+    {
+      "epoch": 1.3404825737265416,
+      "grad_norm": 1.8386740684509277,
+      "learning_rate": 4.0844263195097915e-05,
+      "loss": 0.7039,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.49882668256759644,
+      "eval_loss": 0.6931472420692444,
+      "eval_runtime": 9.1028,
+      "eval_samples_per_second": 327.702,
+      "eval_steps_per_second": 20.543,
+      "step": 1492
+    },
+    {
+      "epoch": 2.0107238605898123,
+      "grad_norm": 1.775593876838684,
+      "learning_rate": 3.768294251436278e-05,
+      "loss": 0.7008,
+      "step": 1500
+    },
+    {
+      "epoch": 2.680965147453083,
+      "grad_norm": 1.6979082822799683,
+      "learning_rate": 3.452162183362765e-05,
+      "loss": 0.7034,
+      "step": 2000
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.5015085339546204,
+      "eval_loss": 0.6931472420692444,
+      "eval_runtime": 9.1903,
+      "eval_samples_per_second": 324.583,
+      "eval_steps_per_second": 20.348,
+      "step": 2238
+    },
+    {
+      "epoch": 3.351206434316354,
+      "grad_norm": 1.7350631952285767,
+      "learning_rate": 3.136030115289252e-05,
+      "loss": 0.7017,
+      "step": 2500
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.5065370202064514,
+      "eval_loss": 0.6931472420692444,
+      "eval_runtime": 9.2185,
+      "eval_samples_per_second": 323.589,
+      "eval_steps_per_second": 20.285,
+      "step": 2984
+    },
+    {
+      "epoch": 4.021447721179625,
+      "grad_norm": 1.841038465499878,
+      "learning_rate": 2.8198980472157382e-05,
+      "loss": 0.7019,
+      "step": 3000
+    },
+    {
+      "epoch": 4.6916890080428955,
+      "grad_norm": 1.6272307634353638,
+      "learning_rate": 2.5037659791422253e-05,
+      "loss": 0.6994,
+      "step": 3500
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 7460,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "total_flos": 9120071568390876.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 4.716690455656818e-05,
+    "per_device_train_batch_size": 16
+  }
+}

run-3/checkpoint-3500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0537522960a235b809ea329ec1396888a29088f8f8ec27bb9dbf5e7701ff29d
+size 5048

run-3/checkpoint-4000/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-3/checkpoint-4000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c6abfa93adcfd8b301dd28aa5275549c29c65e9eff2a495bc40587ea8dded8a
+size 1340618660

run-3/checkpoint-4000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d06dcfba74bd1e8666ee05b2129ec92726dd81e2d6f7c1f7f16b035f7753e129
+size 2681472237

run-3/checkpoint-4000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:964f4b0fc1ae48263176e28a78d31a31267f7cb8f04acc9b199d89800cfff478
+size 14244

run-3/checkpoint-4000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:536b460f23f6347bb54af8c72c9dd28c1331341be7c4818c934ca1dabdc49abc
+size 1064

run-3/checkpoint-4000/special_tokens_map.json

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

run-3/checkpoint-4000/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-3/checkpoint-4000/trainer_state.json

@@ -0,0 +1,125 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.361930294906166,
+  "eval_steps": 500,
+  "global_step": 4000,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.6702412868632708,
+      "grad_norm": 1.8121609687805176,
+      "learning_rate": 4.400558387583305e-05,
+      "loss": 0.6264,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5072075128555298,
+      "eval_loss": 0.6931472420692444,
+      "eval_runtime": 9.1548,
+      "eval_samples_per_second": 325.839,
+      "eval_steps_per_second": 20.426,
+      "step": 746
+    },
+    {
+      "epoch": 1.3404825737265416,
+      "grad_norm": 1.8386740684509277,
+      "learning_rate": 4.0844263195097915e-05,
+      "loss": 0.7039,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.49882668256759644,
+      "eval_loss": 0.6931472420692444,
+      "eval_runtime": 9.1028,
+      "eval_samples_per_second": 327.702,
+      "eval_steps_per_second": 20.543,
+      "step": 1492
+    },
+    {
+      "epoch": 2.0107238605898123,
+      "grad_norm": 1.775593876838684,
+      "learning_rate": 3.768294251436278e-05,
+      "loss": 0.7008,
+      "step": 1500
+    },
+    {
+      "epoch": 2.680965147453083,
+      "grad_norm": 1.6979082822799683,
+      "learning_rate": 3.452162183362765e-05,
+      "loss": 0.7034,
+      "step": 2000
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.5015085339546204,
+      "eval_loss": 0.6931472420692444,
+      "eval_runtime": 9.1903,
+      "eval_samples_per_second": 324.583,
+      "eval_steps_per_second": 20.348,
+      "step": 2238
+    },
+    {
+      "epoch": 3.351206434316354,
+      "grad_norm": 1.7350631952285767,
+      "learning_rate": 3.136030115289252e-05,
+      "loss": 0.7017,
+      "step": 2500
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.5065370202064514,
+      "eval_loss": 0.6931472420692444,
+      "eval_runtime": 9.2185,
+      "eval_samples_per_second": 323.589,
+      "eval_steps_per_second": 20.285,
+      "step": 2984
+    },
+    {
+      "epoch": 4.021447721179625,
+      "grad_norm": 1.841038465499878,
+      "learning_rate": 2.8198980472157382e-05,
+      "loss": 0.7019,
+      "step": 3000
+    },
+    {
+      "epoch": 4.6916890080428955,
+      "grad_norm": 1.6272307634353638,
+      "learning_rate": 2.5037659791422253e-05,
+      "loss": 0.6994,
+      "step": 3500
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.5095541477203369,
+      "eval_loss": 0.6931472420692444,
+      "eval_runtime": 9.0976,
+      "eval_samples_per_second": 327.89,
+      "eval_steps_per_second": 20.555,
+      "step": 3730
+    },
+    {
+      "epoch": 5.361930294906166,
+      "grad_norm": 1.7355244159698486,
+      "learning_rate": 2.1876339110687117e-05,
+      "loss": 0.7006,
+      "step": 4000
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 7460,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "total_flos": 1.0420730286237396e+16,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 4.716690455656818e-05,
+    "per_device_train_batch_size": 16
+  }
+}

run-3/checkpoint-4000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0537522960a235b809ea329ec1396888a29088f8f8ec27bb9dbf5e7701ff29d
+size 5048

run-3/checkpoint-4500/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-3/checkpoint-4500/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:498d2da2ab31920cf0cd8bacea0c0c200dbe8e0fe068e052a803669c1ebb82f3
+size 1340618660

run-3/checkpoint-4500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66700a3a7c19672e1f2bf2aacfaf2b7db35ad0cfbf5fa9532afe78a63ee7485f
+size 2681472237

run-3/checkpoint-4500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c65c81fd3021fa5a65673197784a1bfa7af04999304bdf6b50fc4ee0d7de006
+size 14244

run-3/checkpoint-4500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80cf1d2d505fd99c754cdb23eb1a37a200517bb0accb261f2a8169cbae809756
+size 1064

run-3/checkpoint-4500/special_tokens_map.json

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

run-3/checkpoint-4500/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-3/checkpoint-4500/trainer_state.json

@@ -0,0 +1,141 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 6.032171581769437,
+  "eval_steps": 500,
+  "global_step": 4500,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.6702412868632708,
+      "grad_norm": 1.8121609687805176,
+      "learning_rate": 4.400558387583305e-05,
+      "loss": 0.6264,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5072075128555298,
+      "eval_loss": 0.6931472420692444,
+      "eval_runtime": 9.1548,
+      "eval_samples_per_second": 325.839,
+      "eval_steps_per_second": 20.426,
+      "step": 746
+    },
+    {
+      "epoch": 1.3404825737265416,
+      "grad_norm": 1.8386740684509277,
+      "learning_rate": 4.0844263195097915e-05,
+      "loss": 0.7039,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.49882668256759644,
+      "eval_loss": 0.6931472420692444,
+      "eval_runtime": 9.1028,
+      "eval_samples_per_second": 327.702,
+      "eval_steps_per_second": 20.543,
+      "step": 1492
+    },
+    {
+      "epoch": 2.0107238605898123,
+      "grad_norm": 1.775593876838684,
+      "learning_rate": 3.768294251436278e-05,
+      "loss": 0.7008,
+      "step": 1500
+    },
+    {
+      "epoch": 2.680965147453083,
+      "grad_norm": 1.6979082822799683,
+      "learning_rate": 3.452162183362765e-05,
+      "loss": 0.7034,
+      "step": 2000
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.5015085339546204,
+      "eval_loss": 0.6931472420692444,
+      "eval_runtime": 9.1903,
+      "eval_samples_per_second": 324.583,
+      "eval_steps_per_second": 20.348,
+      "step": 2238
+    },
+    {
+      "epoch": 3.351206434316354,
+      "grad_norm": 1.7350631952285767,
+      "learning_rate": 3.136030115289252e-05,
+      "loss": 0.7017,
+      "step": 2500
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.5065370202064514,
+      "eval_loss": 0.6931472420692444,
+      "eval_runtime": 9.2185,
+      "eval_samples_per_second": 323.589,
+      "eval_steps_per_second": 20.285,
+      "step": 2984
+    },
+    {
+      "epoch": 4.021447721179625,
+      "grad_norm": 1.841038465499878,
+      "learning_rate": 2.8198980472157382e-05,
+      "loss": 0.7019,
+      "step": 3000
+    },
+    {
+      "epoch": 4.6916890080428955,
+      "grad_norm": 1.6272307634353638,
+      "learning_rate": 2.5037659791422253e-05,
+      "loss": 0.6994,
+      "step": 3500
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.5095541477203369,
+      "eval_loss": 0.6931472420692444,
+      "eval_runtime": 9.0976,
+      "eval_samples_per_second": 327.89,
+      "eval_steps_per_second": 20.555,
+      "step": 3730
+    },
+    {
+      "epoch": 5.361930294906166,
+      "grad_norm": 1.7355244159698486,
+      "learning_rate": 2.1876339110687117e-05,
+      "loss": 0.7006,
+      "step": 4000
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.49446865916252136,
+      "eval_loss": 0.6931472420692444,
+      "eval_runtime": 9.0977,
+      "eval_samples_per_second": 327.885,
+      "eval_steps_per_second": 20.555,
+      "step": 4476
+    },
+    {
+      "epoch": 6.032171581769437,
+      "grad_norm": 1.6792231798171997,
+      "learning_rate": 1.8715018429951985e-05,
+      "loss": 0.7005,
+      "step": 4500
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 7460,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "total_flos": 1.17284621936184e+16,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 4.716690455656818e-05,
+    "per_device_train_batch_size": 16
+  }
+}

run-3/checkpoint-4500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0537522960a235b809ea329ec1396888a29088f8f8ec27bb9dbf5e7701ff29d
+size 5048