Training in progress, step 5000

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c04ced4e95104bc5ec0123541b73b7f8b1f5cb81b734fc7031750ea9106c9345
+oid sha256:55dcf2d90f757876dbb7c4b94eea3ec94f5166a71b3fbe4f0e962072d7107aec
 size 1340618660

run-2/checkpoint-2000/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80be31897bb33d8733d34cb040a72548acaf95ec030cad91f812ad2d751b03f6
+oid sha256:8c937134533537f70741285bafdedc919a45c37f4f3c5cb4a9752ec17f80e655
 size 1340618660

run-2/checkpoint-2000/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d7016afb7575f22f823ba59a2ed54e03975b7460a99333e0965e0b82fab07c37
+oid sha256:7f579ae5cd8cf4a42fb18f7cf72ad5583140a9f3001ca2787f7dfc16fbc518f0
 size 2681472237

run-2/checkpoint-2000/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b9d5ad379b9f68a63bde5e9feb70202a4bac9f73ede32d42805b751fb116db2
+oid sha256:75c227961e4ca5d0f7ba2c4abe0a18977107a0b2c234fd11994cf5a6ecf20ea8
 size 14244

run-2/checkpoint-2000/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dbc2fa08caf53304049c3848b18ec3060455d8ffeb5c9cd19698e31caac544f8
+oid sha256:8aa401363c5642a0d7d02cb12727b21c4af1ac34c56e546410d0594de5848ac1
 size 1064

run-2/checkpoint-2000/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9bd2df48f0748d34c1c3fee4978f0787dadcf2710571d4f013f6d6ab8c4ed57f
+oid sha256:c68cfe34dae325096495265befbc04045f52f535badd4f779e9c272d3d0b0f80
 size 5048

run-2/checkpoint-2500/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5aa625202d359484e27339370cfa0ad63333f2ed449370c6cebf8a7d3192716a
+oid sha256:6a4823de534c03cd8365c4d1063243e9562f9ad233f8e5b72c4faf9e5d30e9a9
 size 1340618660

run-2/checkpoint-2500/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:839ba8a0f9db97f00f54cb996da0768a42e6ee244af22e007566323932b8d145
+oid sha256:900bdd243dc7019f81b887d4d33268ba44e786303120f092f21956eaffde22c5
 size 2681472237

run-2/checkpoint-2500/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2702ae7042e84a4d25961cb512df6b14a1bf275d9b4501d054d3df0921900717
+oid sha256:59660cfbae90c75aff22fbb936299b2868fa9acddf052cbe56f2d442145f3b8b
 size 14244

run-2/checkpoint-2500/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a454750792090fbe5cba64cf2aa476ecefd03183473b3e4c55bf7bf4d19d3bb1
+oid sha256:dc5b41e5527ab73bd9c8d7179f5eb7befb77760a1f96a4dd58ff327d4748a0c9
 size 1064

run-2/checkpoint-2500/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9bd2df48f0748d34c1c3fee4978f0787dadcf2710571d4f013f6d6ab8c4ed57f
+oid sha256:c68cfe34dae325096495265befbc04045f52f535badd4f779e9c272d3d0b0f80
 size 5048

run-2/checkpoint-3000/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35290cd19848b1e2ee531e859619964f6b551a24d3d8a1c19f6c3956d92955c2
+oid sha256:ee681dc84fac79d1d9d643c003b15bd7ccdee1fb48cb870b660bb2ee31378926
 size 1340618660

run-2/checkpoint-3000/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9ad35e44551783db2d965142529db5fd25716889829f5b013dfd67b6aa3f5a6
+oid sha256:2782860aba135a87310c45e9585c94228cb176d6a10f199e3b982b07a1496824
 size 2681472237

run-2/checkpoint-3000/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f0fa2dd4d5b10d8deb66aff62fa136a2da8e05b383756e331dd5cc91ded1e42
+oid sha256:6db288463401544c237747deaf541285079a7fac434ce2c87fca0252ed44b357
 size 14244

run-2/checkpoint-3000/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b6dca56106351aeda5c12694b9b78d952bfb74380030b089006c7bc16ed43590
+oid sha256:f6502a7770a12ff2e084bd7551eb23352078f9a6fdfa8b4cb93b3ae1994b447c
 size 1064

run-2/checkpoint-3000/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9bd2df48f0748d34c1c3fee4978f0787dadcf2710571d4f013f6d6ab8c4ed57f
+oid sha256:c68cfe34dae325096495265befbc04045f52f535badd4f779e9c272d3d0b0f80
 size 5048

run-2/checkpoint-3500/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78bc6d683c21d6a2be3177dc35f3a8880af1d8229aefb6d3ebf403c09fca9416
+oid sha256:f507d33e2ac708b2aebe24a9e2832e2c9ca8ebfb0f277b02a31df18d9f9893b7
 size 1340618660

run-2/checkpoint-3500/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d152595e28319d02b0a2298ac06e6fb3bc4b4ec789a14c81dff91e923e7fda33
+oid sha256:f4e47b93b237f3238d088c97ebb8c296c7735b81a7bc2954c8902b00452643ff
 size 2681472237

run-2/checkpoint-3500/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:25c6284cc8af4e58e03f9a13edd9ab9aea771e159ae47465226eaec7dd5cabda
+oid sha256:3f4337773f0e3eb3ebd819153d5c9547815b2eb781fb1b3b8acb5f2d3c9910ed
 size 14244

run-2/checkpoint-3500/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d197f56f518557db46188ed953667fc5c4cb9e88f48deb902f66253413f089cb
+oid sha256:b75a1a9f7ae761e7eb2cdacbdb01d35d249e5b0ce9653f5183e3f1e93019ba13
 size 1064

run-2/checkpoint-3500/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9bd2df48f0748d34c1c3fee4978f0787dadcf2710571d4f013f6d6ab8c4ed57f
+oid sha256:c68cfe34dae325096495265befbc04045f52f535badd4f779e9c272d3d0b0f80
 size 5048

run-2/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-2/checkpoint-4000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87d90823cf3527aad67f3666a1a658cabc0dbab731e6147be99e69e2088a5f09
+size 1340618660

run-2/checkpoint-4000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:805007eb8c09117ab5d6bb38560d087face4081479fac7447688249e3bc4dd7a
+size 2681472237

run-2/checkpoint-4000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23cd89f577f0659ddbd8c4a0e9ac86eb2003a5e05352e1a0338dfe9fb951fcfe
+size 14244

run-2/checkpoint-4000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca4d60300b89b032e5e3f23deab19eb2b4115e6ab4686a27751623f6e62aeecd
+size 1064

run-2/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-2/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-2/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": 17.923147201538086,
+      "learning_rate": 1.3001640168623715e-05,
+      "loss": 0.5514,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7683539986610413,
+      "eval_loss": 0.46452510356903076,
+      "eval_runtime": 8.9706,
+      "eval_samples_per_second": 332.531,
+      "eval_steps_per_second": 20.846,
+      "step": 746
+    },
+    {
+      "epoch": 1.3404825737265416,
+      "grad_norm": 19.32151222229004,
+      "learning_rate": 1.2067614294440976e-05,
+      "loss": 0.3969,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7643312215805054,
+      "eval_loss": 0.5671606063842773,
+      "eval_runtime": 9.0896,
+      "eval_samples_per_second": 328.177,
+      "eval_steps_per_second": 20.573,
+      "step": 1492
+    },
+    {
+      "epoch": 2.0107238605898123,
+      "grad_norm": 17.702476501464844,
+      "learning_rate": 1.1133588420258238e-05,
+      "loss": 0.2998,
+      "step": 1500
+    },
+    {
+      "epoch": 2.680965147453083,
+      "grad_norm": 6.516891956329346,
+      "learning_rate": 1.0199562546075501e-05,
+      "loss": 0.1319,
+      "step": 2000
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7770700454711914,
+      "eval_loss": 0.7936307191848755,
+      "eval_runtime": 9.0031,
+      "eval_samples_per_second": 331.332,
+      "eval_steps_per_second": 20.771,
+      "step": 2238
+    },
+    {
+      "epoch": 3.351206434316354,
+      "grad_norm": 0.19944968819618225,
+      "learning_rate": 9.265536671892763e-06,
+      "loss": 0.0932,
+      "step": 2500
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.7750586867332458,
+      "eval_loss": 1.1848183870315552,
+      "eval_runtime": 9.064,
+      "eval_samples_per_second": 329.104,
+      "eval_steps_per_second": 20.631,
+      "step": 2984
+    },
+    {
+      "epoch": 4.021447721179625,
+      "grad_norm": 0.03240065276622772,
+      "learning_rate": 8.331510797710023e-06,
+      "loss": 0.0618,
+      "step": 3000
+    },
+    {
+      "epoch": 4.6916890080428955,
+      "grad_norm": 23.173229217529297,
+      "learning_rate": 7.397484923527286e-06,
+      "loss": 0.0314,
+      "step": 3500
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.7707006335258484,
+      "eval_loss": 1.372557520866394,
+      "eval_runtime": 9.0505,
+      "eval_samples_per_second": 329.594,
+      "eval_steps_per_second": 20.662,
+      "step": 3730
+    },
+    {
+      "epoch": 5.361930294906166,
+      "grad_norm": 0.01009325310587883,
+      "learning_rate": 6.463459049344548e-06,
+      "loss": 0.0281,
+      "step": 4000
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 7460,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "total_flos": 9489198869269488.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.3935666042806453e-05,
+    "per_device_train_batch_size": 16
+  }
+}

run-2/checkpoint-4000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c68cfe34dae325096495265befbc04045f52f535badd4f779e9c272d3d0b0f80
+size 5048

run-2/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-2/checkpoint-4500/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39327235f69c4c3b486cbf8df774ec52ff54ad18f8d7a4fa2bd6cfa2162b02be
+size 1340618660

run-2/checkpoint-4500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9b3c556ad2cfa779d1f7fed254a28a85de15b8ff152c89d60638befc4235b37
+size 2681472237

run-2/checkpoint-4500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:262bdc836bd571e5c7800d3eb88b8556fd1630b1fd434d2a0a61ec4f3d7402bd
+size 14244

run-2/checkpoint-4500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e557c4a78b60251d1a9d05fe3ad142e596b1da5e438c612f3802aea99dcf7618
+size 1064

run-2/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-2/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-2/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": 17.923147201538086,
+      "learning_rate": 1.3001640168623715e-05,
+      "loss": 0.5514,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7683539986610413,
+      "eval_loss": 0.46452510356903076,
+      "eval_runtime": 8.9706,
+      "eval_samples_per_second": 332.531,
+      "eval_steps_per_second": 20.846,
+      "step": 746
+    },
+    {
+      "epoch": 1.3404825737265416,
+      "grad_norm": 19.32151222229004,
+      "learning_rate": 1.2067614294440976e-05,
+      "loss": 0.3969,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7643312215805054,
+      "eval_loss": 0.5671606063842773,
+      "eval_runtime": 9.0896,
+      "eval_samples_per_second": 328.177,
+      "eval_steps_per_second": 20.573,
+      "step": 1492
+    },
+    {
+      "epoch": 2.0107238605898123,
+      "grad_norm": 17.702476501464844,
+      "learning_rate": 1.1133588420258238e-05,
+      "loss": 0.2998,
+      "step": 1500
+    },
+    {
+      "epoch": 2.680965147453083,
+      "grad_norm": 6.516891956329346,
+      "learning_rate": 1.0199562546075501e-05,
+      "loss": 0.1319,
+      "step": 2000
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7770700454711914,
+      "eval_loss": 0.7936307191848755,
+      "eval_runtime": 9.0031,
+      "eval_samples_per_second": 331.332,
+      "eval_steps_per_second": 20.771,
+      "step": 2238
+    },
+    {
+      "epoch": 3.351206434316354,
+      "grad_norm": 0.19944968819618225,
+      "learning_rate": 9.265536671892763e-06,
+      "loss": 0.0932,
+      "step": 2500
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.7750586867332458,
+      "eval_loss": 1.1848183870315552,
+      "eval_runtime": 9.064,
+      "eval_samples_per_second": 329.104,
+      "eval_steps_per_second": 20.631,
+      "step": 2984
+    },
+    {
+      "epoch": 4.021447721179625,
+      "grad_norm": 0.03240065276622772,
+      "learning_rate": 8.331510797710023e-06,
+      "loss": 0.0618,
+      "step": 3000
+    },
+    {
+      "epoch": 4.6916890080428955,
+      "grad_norm": 23.173229217529297,
+      "learning_rate": 7.397484923527286e-06,
+      "loss": 0.0314,
+      "step": 3500
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.7707006335258484,
+      "eval_loss": 1.372557520866394,
+      "eval_runtime": 9.0505,
+      "eval_samples_per_second": 329.594,
+      "eval_steps_per_second": 20.662,
+      "step": 3730
+    },
+    {
+      "epoch": 5.361930294906166,
+      "grad_norm": 0.01009325310587883,
+      "learning_rate": 6.463459049344548e-06,
+      "loss": 0.0281,
+      "step": 4000
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.777405321598053,
+      "eval_loss": 1.31714928150177,
+      "eval_runtime": 9.0862,
+      "eval_samples_per_second": 328.299,
+      "eval_steps_per_second": 20.581,
+      "step": 4476
+    },
+    {
+      "epoch": 6.032171581769437,
+      "grad_norm": 0.6762986779212952,
+      "learning_rate": 5.529433175161809e-06,
+      "loss": 0.0202,
+      "step": 4500
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 7460,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "total_flos": 1.0682602114519764e+16,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.3935666042806453e-05,
+    "per_device_train_batch_size": 16
+  }
+}

run-2/checkpoint-4500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c68cfe34dae325096495265befbc04045f52f535badd4f779e9c272d3d0b0f80
+size 5048

run-2/checkpoint-5000/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-2/checkpoint-5000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55dcf2d90f757876dbb7c4b94eea3ec94f5166a71b3fbe4f0e962072d7107aec
+size 1340618660

run-2/checkpoint-5000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:836c530bbcfaa88331ac4d39d8f145968a7f6cfd955cc1affc09fc971bb92ff1
+size 2681472237

run-2/checkpoint-5000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:350dce5f3fc8b9991f6e63d71d94cae07c7815692d88da1c6e0a2aa12455e53a
+size 14244

run-2/checkpoint-5000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ebca24fe91086601b79269e4a7200ab15b4e7ce37c65a3940fdb52ca7436d288
+size 1064

run-2/checkpoint-5000/special_tokens_map.json

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