Training in progress, step 5000

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35138e02f00180ba409c55612bb905d56597e6c2af9b7a6fc003432c6359d577
+oid sha256:bb2225bac3d428c7bb22907e1cc9c73111ba7e29a9fe0ca49bfc182a9d9a71a4
 size 1421491284

run-1/checkpoint-3500/config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "roberta-large",
+  "architectures": [
+    "RobertaForMultipleChoice"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.40.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

run-1/checkpoint-3500/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:262b4ff509e246d26d5caa001b40d2f02ba22c0ab0bda032f4e95b653fee45bd
+size 1421491284

run-1/checkpoint-3500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f90c1c7322138d1e85fc3115ce54a99f48ba3828cd3d861abc62a6250f0ecc15
+size 2843215085

run-1/checkpoint-3500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e82d442b070ff7458e0d35e45695fc8f63ed716771fa7b3fb390da429c1d4a27
+size 14244

run-1/checkpoint-3500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:424105615e17bd24f3427f1b0fdfb4abc9102032cebe4e109a2afd2c99061bfa
+size 1064

run-1/checkpoint-3500/special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

run-1/checkpoint-3500/tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50264": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

run-1/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": 23.28346824645996,
+      "learning_rate": 9.798511296679954e-06,
+      "loss": 0.5531,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8025477528572083,
+      "eval_loss": 0.4079710841178894,
+      "eval_runtime": 9.2612,
+      "eval_samples_per_second": 322.097,
+      "eval_steps_per_second": 20.192,
+      "step": 746
+    },
+    {
+      "epoch": 1.3404825737265416,
+      "grad_norm": 38.64032745361328,
+      "learning_rate": 9.094595255251797e-06,
+      "loss": 0.3957,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8276902437210083,
+      "eval_loss": 0.42224231362342834,
+      "eval_runtime": 9.5099,
+      "eval_samples_per_second": 313.673,
+      "eval_steps_per_second": 19.664,
+      "step": 1492
+    },
+    {
+      "epoch": 2.0107238605898123,
+      "grad_norm": 34.970176696777344,
+      "learning_rate": 8.390679213823639e-06,
+      "loss": 0.3185,
+      "step": 1500
+    },
+    {
+      "epoch": 2.680965147453083,
+      "grad_norm": 13.735482215881348,
+      "learning_rate": 7.686763172395482e-06,
+      "loss": 0.1887,
+      "step": 2000
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.819309413433075,
+      "eval_loss": 0.49816903471946716,
+      "eval_runtime": 9.3819,
+      "eval_samples_per_second": 317.952,
+      "eval_steps_per_second": 19.932,
+      "step": 2238
+    },
+    {
+      "epoch": 3.351206434316354,
+      "grad_norm": 10.144265174865723,
+      "learning_rate": 6.982847130967324e-06,
+      "loss": 0.1522,
+      "step": 2500
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8313778042793274,
+      "eval_loss": 0.6922349333763123,
+      "eval_runtime": 9.2835,
+      "eval_samples_per_second": 321.324,
+      "eval_steps_per_second": 20.143,
+      "step": 2984
+    },
+    {
+      "epoch": 4.021447721179625,
+      "grad_norm": 39.181697845458984,
+      "learning_rate": 6.278931089539166e-06,
+      "loss": 0.1152,
+      "step": 3000
+    },
+    {
+      "epoch": 4.6916890080428955,
+      "grad_norm": 5.586261749267578,
+      "learning_rate": 5.575015048111009e-06,
+      "loss": 0.0669,
+      "step": 3500
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 7460,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "total_flos": 9234076239853272.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.0502427338108112e-05,
+    "per_device_train_batch_size": 16
+  }
+}

run-1/checkpoint-3500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:347fad0a6bce6c8dd37383686ed909149e39a499f89f9086cdd2be432928a800
+size 5048

run-1/checkpoint-4000/config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "roberta-large",
+  "architectures": [
+    "RobertaForMultipleChoice"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.40.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

run-1/checkpoint-4000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3bc4dc70933602e5f2dd07555b5fc96333d5cad46f380b4d55b56ee83bb6459
+size 1421491284

run-1/checkpoint-4000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7602d165e9abd62642c707d99cddd7e8b5260a4d43a60e87311e3dda0734b9d3
+size 2843215085

run-1/checkpoint-4000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7bbe533c035adff08e655183172f00ff24f8307f7645c0afd68ef36b90b420a
+size 14244

run-1/checkpoint-4000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74aaca0c9a45c69f5d7eb4650938c4be110142d94bb071a7ececa1659faf33a0
+size 1064

run-1/checkpoint-4000/special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

run-1/checkpoint-4000/tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50264": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

run-1/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": 23.28346824645996,
+      "learning_rate": 9.798511296679954e-06,
+      "loss": 0.5531,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8025477528572083,
+      "eval_loss": 0.4079710841178894,
+      "eval_runtime": 9.2612,
+      "eval_samples_per_second": 322.097,
+      "eval_steps_per_second": 20.192,
+      "step": 746
+    },
+    {
+      "epoch": 1.3404825737265416,
+      "grad_norm": 38.64032745361328,
+      "learning_rate": 9.094595255251797e-06,
+      "loss": 0.3957,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8276902437210083,
+      "eval_loss": 0.42224231362342834,
+      "eval_runtime": 9.5099,
+      "eval_samples_per_second": 313.673,
+      "eval_steps_per_second": 19.664,
+      "step": 1492
+    },
+    {
+      "epoch": 2.0107238605898123,
+      "grad_norm": 34.970176696777344,
+      "learning_rate": 8.390679213823639e-06,
+      "loss": 0.3185,
+      "step": 1500
+    },
+    {
+      "epoch": 2.680965147453083,
+      "grad_norm": 13.735482215881348,
+      "learning_rate": 7.686763172395482e-06,
+      "loss": 0.1887,
+      "step": 2000
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.819309413433075,
+      "eval_loss": 0.49816903471946716,
+      "eval_runtime": 9.3819,
+      "eval_samples_per_second": 317.952,
+      "eval_steps_per_second": 19.932,
+      "step": 2238
+    },
+    {
+      "epoch": 3.351206434316354,
+      "grad_norm": 10.144265174865723,
+      "learning_rate": 6.982847130967324e-06,
+      "loss": 0.1522,
+      "step": 2500
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8313778042793274,
+      "eval_loss": 0.6922349333763123,
+      "eval_runtime": 9.2835,
+      "eval_samples_per_second": 321.324,
+      "eval_steps_per_second": 20.143,
+      "step": 2984
+    },
+    {
+      "epoch": 4.021447721179625,
+      "grad_norm": 39.181697845458984,
+      "learning_rate": 6.278931089539166e-06,
+      "loss": 0.1152,
+      "step": 3000
+    },
+    {
+      "epoch": 4.6916890080428955,
+      "grad_norm": 5.586261749267578,
+      "learning_rate": 5.575015048111009e-06,
+      "loss": 0.0669,
+      "step": 3500
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.8253436088562012,
+      "eval_loss": 0.8140854835510254,
+      "eval_runtime": 9.3552,
+      "eval_samples_per_second": 318.859,
+      "eval_steps_per_second": 19.989,
+      "step": 3730
+    },
+    {
+      "epoch": 5.361930294906166,
+      "grad_norm": 0.027025775983929634,
+      "learning_rate": 4.871099006682851e-06,
+      "loss": 0.0526,
+      "step": 4000
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 7460,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "total_flos": 1.0553606504043984e+16,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.0502427338108112e-05,
+    "per_device_train_batch_size": 16
+  }
+}

run-1/checkpoint-4000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:347fad0a6bce6c8dd37383686ed909149e39a499f89f9086cdd2be432928a800
+size 5048

run-1/checkpoint-4500/config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "roberta-large",
+  "architectures": [
+    "RobertaForMultipleChoice"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.40.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

run-1/checkpoint-4500/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4f5abf1146e97c4be8863e5d925be8e9354f304b5b93a69ccc88a5883c617f7
+size 1421491284

run-1/checkpoint-4500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d342466653241d8bcea2e7d468a552d66bd457bb0811d86d3411582efdc9be6b
+size 2843215085

run-1/checkpoint-4500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4aed53fc665adbf77d994c3bc0edbf49f0201b7562ed8d0aa8c30e3b4d98a624
+size 14244

run-1/checkpoint-4500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d37dc81a4179611a691e98634fb12e7efb5175e88e35c4b989a5881a2e6206c6
+size 1064

run-1/checkpoint-4500/special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

run-1/checkpoint-4500/tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50264": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

run-1/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": 23.28346824645996,
+      "learning_rate": 9.798511296679954e-06,
+      "loss": 0.5531,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8025477528572083,
+      "eval_loss": 0.4079710841178894,
+      "eval_runtime": 9.2612,
+      "eval_samples_per_second": 322.097,
+      "eval_steps_per_second": 20.192,
+      "step": 746
+    },
+    {
+      "epoch": 1.3404825737265416,
+      "grad_norm": 38.64032745361328,
+      "learning_rate": 9.094595255251797e-06,
+      "loss": 0.3957,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8276902437210083,
+      "eval_loss": 0.42224231362342834,
+      "eval_runtime": 9.5099,
+      "eval_samples_per_second": 313.673,
+      "eval_steps_per_second": 19.664,
+      "step": 1492
+    },
+    {
+      "epoch": 2.0107238605898123,
+      "grad_norm": 34.970176696777344,
+      "learning_rate": 8.390679213823639e-06,
+      "loss": 0.3185,
+      "step": 1500
+    },
+    {
+      "epoch": 2.680965147453083,
+      "grad_norm": 13.735482215881348,
+      "learning_rate": 7.686763172395482e-06,
+      "loss": 0.1887,
+      "step": 2000
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.819309413433075,
+      "eval_loss": 0.49816903471946716,
+      "eval_runtime": 9.3819,
+      "eval_samples_per_second": 317.952,
+      "eval_steps_per_second": 19.932,
+      "step": 2238
+    },
+    {
+      "epoch": 3.351206434316354,
+      "grad_norm": 10.144265174865723,
+      "learning_rate": 6.982847130967324e-06,
+      "loss": 0.1522,
+      "step": 2500
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8313778042793274,
+      "eval_loss": 0.6922349333763123,
+      "eval_runtime": 9.2835,
+      "eval_samples_per_second": 321.324,
+      "eval_steps_per_second": 20.143,
+      "step": 2984
+    },
+    {
+      "epoch": 4.021447721179625,
+      "grad_norm": 39.181697845458984,
+      "learning_rate": 6.278931089539166e-06,
+      "loss": 0.1152,
+      "step": 3000
+    },
+    {
+      "epoch": 4.6916890080428955,
+      "grad_norm": 5.586261749267578,
+      "learning_rate": 5.575015048111009e-06,
+      "loss": 0.0669,
+      "step": 3500
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.8253436088562012,
+      "eval_loss": 0.8140854835510254,
+      "eval_runtime": 9.3552,
+      "eval_samples_per_second": 318.859,
+      "eval_steps_per_second": 19.989,
+      "step": 3730
+    },
+    {
+      "epoch": 5.361930294906166,
+      "grad_norm": 0.027025775983929634,
+      "learning_rate": 4.871099006682851e-06,
+      "loss": 0.0526,
+      "step": 4000
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.8223265409469604,
+      "eval_loss": 0.9023452997207642,
+      "eval_runtime": 9.2601,
+      "eval_samples_per_second": 322.135,
+      "eval_steps_per_second": 20.194,
+      "step": 4476
+    },
+    {
+      "epoch": 6.032171581769437,
+      "grad_norm": 0.05576400086283684,
+      "learning_rate": 4.167182965254693e-06,
+      "loss": 0.0417,
+      "step": 4500
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 7460,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "total_flos": 1.1865626737349652e+16,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.0502427338108112e-05,
+    "per_device_train_batch_size": 16
+  }
+}

run-1/checkpoint-4500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:347fad0a6bce6c8dd37383686ed909149e39a499f89f9086cdd2be432928a800
+size 5048

run-1/checkpoint-5000/config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "roberta-large",
+  "architectures": [
+    "RobertaForMultipleChoice"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.40.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

run-1/checkpoint-5000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb2225bac3d428c7bb22907e1cc9c73111ba7e29a9fe0ca49bfc182a9d9a71a4
+size 1421491284

run-1/checkpoint-5000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4cf3c02bbfe56331368eeaec385f70e98a044fe82c9ec9e944bdfaf18e8fe639
+size 2843215085

run-1/checkpoint-5000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9844239aff3f7cb8641a80df2698d38165609179f399a01b2a7b586aced8b37a
+size 14244

run-1/checkpoint-5000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8294e5368c636ce2ee798f1ec3f0e908929cf4434f6001f08ee159119f5f7ef
+size 1064

run-1/checkpoint-5000/special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

run-1/checkpoint-5000/tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50264": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

run-1/checkpoint-5000/trainer_state.json

@@ -0,0 +1,148 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 6.702412868632708,
+  "eval_steps": 500,
+  "global_step": 5000,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.6702412868632708,
+      "grad_norm": 23.28346824645996,
+      "learning_rate": 9.798511296679954e-06,
+      "loss": 0.5531,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8025477528572083,
+      "eval_loss": 0.4079710841178894,
+      "eval_runtime": 9.2612,
+      "eval_samples_per_second": 322.097,
+      "eval_steps_per_second": 20.192,
+      "step": 746
+    },
+    {
+      "epoch": 1.3404825737265416,
+      "grad_norm": 38.64032745361328,
+      "learning_rate": 9.094595255251797e-06,
+      "loss": 0.3957,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8276902437210083,
+      "eval_loss": 0.42224231362342834,
+      "eval_runtime": 9.5099,
+      "eval_samples_per_second": 313.673,
+      "eval_steps_per_second": 19.664,
+      "step": 1492
+    },
+    {
+      "epoch": 2.0107238605898123,
+      "grad_norm": 34.970176696777344,
+      "learning_rate": 8.390679213823639e-06,
+      "loss": 0.3185,
+      "step": 1500
+    },
+    {
+      "epoch": 2.680965147453083,
+      "grad_norm": 13.735482215881348,
+      "learning_rate": 7.686763172395482e-06,
+      "loss": 0.1887,
+      "step": 2000
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.819309413433075,
+      "eval_loss": 0.49816903471946716,
+      "eval_runtime": 9.3819,
+      "eval_samples_per_second": 317.952,
+      "eval_steps_per_second": 19.932,
+      "step": 2238
+    },
+    {
+      "epoch": 3.351206434316354,
+      "grad_norm": 10.144265174865723,
+      "learning_rate": 6.982847130967324e-06,
+      "loss": 0.1522,
+      "step": 2500
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8313778042793274,
+      "eval_loss": 0.6922349333763123,
+      "eval_runtime": 9.2835,
+      "eval_samples_per_second": 321.324,
+      "eval_steps_per_second": 20.143,
+      "step": 2984
+    },
+    {
+      "epoch": 4.021447721179625,
+      "grad_norm": 39.181697845458984,
+      "learning_rate": 6.278931089539166e-06,
+      "loss": 0.1152,
+      "step": 3000
+    },
+    {
+      "epoch": 4.6916890080428955,
+      "grad_norm": 5.586261749267578,
+      "learning_rate": 5.575015048111009e-06,
+      "loss": 0.0669,
+      "step": 3500
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.8253436088562012,
+      "eval_loss": 0.8140854835510254,
+      "eval_runtime": 9.3552,
+      "eval_samples_per_second": 318.859,
+      "eval_steps_per_second": 19.989,
+      "step": 3730
+    },
+    {
+      "epoch": 5.361930294906166,
+      "grad_norm": 0.027025775983929634,
+      "learning_rate": 4.871099006682851e-06,
+      "loss": 0.0526,
+      "step": 4000
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.8223265409469604,
+      "eval_loss": 0.9023452997207642,
+      "eval_runtime": 9.2601,
+      "eval_samples_per_second": 322.135,
+      "eval_steps_per_second": 20.194,
+      "step": 4476
+    },
+    {
+      "epoch": 6.032171581769437,
+      "grad_norm": 0.05576400086283684,
+      "learning_rate": 4.167182965254693e-06,
+      "loss": 0.0417,
+      "step": 4500
+    },
+    {
+      "epoch": 6.702412868632708,
+      "grad_norm": 55.70774841308594,
+      "learning_rate": 3.4632669238265355e-06,
+      "loss": 0.0301,
+      "step": 5000
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 7460,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "total_flos": 1.3185411825661524e+16,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.0502427338108112e-05,
+    "per_device_train_batch_size": 16
+  }
+}

run-1/checkpoint-5000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:347fad0a6bce6c8dd37383686ed909149e39a499f89f9086cdd2be432928a800
+size 5048