Training in progress, step 7000

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb2225bac3d428c7bb22907e1cc9c73111ba7e29a9fe0ca49bfc182a9d9a71a4
+oid sha256:13bc38d638baa336cd43e84bba0909ef3b954bb908b943441e83c2c01aa837e6
 size 1421491284

run-1/checkpoint-5500/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-5500/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7768fd71f84699352b27e2be9789f9964cca58b8a9c87d80e8f71e5d01f7c073
+size 1421491284

run-1/checkpoint-5500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09eedc1cd31adb4b3f38423718903e89e98e1a7584d06e8352d2b396db794bb3
+size 2843215085

run-1/checkpoint-5500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63173e34626dd2e805a1c2aece01e15115f50bb184692c261277396ff8425ea0
+size 14244

run-1/checkpoint-5500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a2deca502826726507eafd3ad91352de9439bc30c14481f74ab84dd5a9db2a3
+size 1064

run-1/checkpoint-5500/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-5500/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-5500/trainer_state.json

@@ -0,0 +1,164 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 7.372654155495979,
+  "eval_steps": 500,
+  "global_step": 5500,
+  "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
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.8266845345497131,
+      "eval_loss": 0.9764488339424133,
+      "eval_runtime": 9.3516,
+      "eval_samples_per_second": 318.981,
+      "eval_steps_per_second": 19.996,
+      "step": 5222
+    },
+    {
+      "epoch": 7.372654155495979,
+      "grad_norm": 0.9753480553627014,
+      "learning_rate": 2.759350882398378e-06,
+      "loss": 0.0218,
+      "step": 5500
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 7460,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "total_flos": 1.4496754954873824e+16,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.0502427338108112e-05,
+    "per_device_train_batch_size": 16
+  }
+}

run-1/checkpoint-5500/training_args.bin

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

run-1/checkpoint-6000/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-6000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec8fa7dc3471df5fc0628c7ce48cfe12ccce41c746e7fbb8227650efa2e5f676
+size 1421491284

run-1/checkpoint-6000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08bbeb4ab06447835a55589d0d5a5bc68f924ac942a90050f0f11bb4808c4921
+size 2843215085

run-1/checkpoint-6000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2efa21f5ec6574455232fc351e43e3a758aa0ce6dd97daf984872740eafd451c
+size 14244

run-1/checkpoint-6000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba411dae17b9be209be2f0b5017f4f550a054d3dacc9f8ec47b44bfb531379a7
+size 1064

run-1/checkpoint-6000/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-6000/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-6000/trainer_state.json

@@ -0,0 +1,180 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 8.04289544235925,
+  "eval_steps": 500,
+  "global_step": 6000,
+  "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
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.8266845345497131,
+      "eval_loss": 0.9764488339424133,
+      "eval_runtime": 9.3516,
+      "eval_samples_per_second": 318.981,
+      "eval_steps_per_second": 19.996,
+      "step": 5222
+    },
+    {
+      "epoch": 7.372654155495979,
+      "grad_norm": 0.9753480553627014,
+      "learning_rate": 2.759350882398378e-06,
+      "loss": 0.0218,
+      "step": 5500
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.8320482969284058,
+      "eval_loss": 0.9748868346214294,
+      "eval_runtime": 9.391,
+      "eval_samples_per_second": 317.644,
+      "eval_steps_per_second": 19.913,
+      "step": 5968
+    },
+    {
+      "epoch": 8.04289544235925,
+      "grad_norm": 65.11773681640625,
+      "learning_rate": 2.0554348409702203e-06,
+      "loss": 0.0196,
+      "step": 6000
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 7460,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "total_flos": 1.5818666004425088e+16,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.0502427338108112e-05,
+    "per_device_train_batch_size": 16
+  }
+}

run-1/checkpoint-6000/training_args.bin

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

run-1/checkpoint-6500/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-6500/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:225561cab48ac5681efcfc3c3831315ed8515bcd287beea748bae7b3fd48d6d1
+size 1421491284

run-1/checkpoint-6500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9af30f0b5343c6c8f8ce9394db183960677f33acc28877c1769a7c3309c7afb
+size 2843215085

run-1/checkpoint-6500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d0b2e108c83574954922cbd3e83b425dff940ee00fa1d5eb63c0457f942c6b8
+size 14244

run-1/checkpoint-6500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7004a830c5f920ab2f5e51936bbf1a6d227df720fe64341598572c95d4640fba
+size 1064

run-1/checkpoint-6500/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-6500/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-6500/trainer_state.json

@@ -0,0 +1,187 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 8.71313672922252,
+  "eval_steps": 500,
+  "global_step": 6500,
+  "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
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.8266845345497131,
+      "eval_loss": 0.9764488339424133,
+      "eval_runtime": 9.3516,
+      "eval_samples_per_second": 318.981,
+      "eval_steps_per_second": 19.996,
+      "step": 5222
+    },
+    {
+      "epoch": 7.372654155495979,
+      "grad_norm": 0.9753480553627014,
+      "learning_rate": 2.759350882398378e-06,
+      "loss": 0.0218,
+      "step": 5500
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.8320482969284058,
+      "eval_loss": 0.9748868346214294,
+      "eval_runtime": 9.391,
+      "eval_samples_per_second": 317.644,
+      "eval_steps_per_second": 19.913,
+      "step": 5968
+    },
+    {
+      "epoch": 8.04289544235925,
+      "grad_norm": 65.11773681640625,
+      "learning_rate": 2.0554348409702203e-06,
+      "loss": 0.0196,
+      "step": 6000
+    },
+    {
+      "epoch": 8.71313672922252,
+      "grad_norm": 0.08348937332630157,
+      "learning_rate": 1.3515187995420628e-06,
+      "loss": 0.0136,
+      "step": 6500
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 7460,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "total_flos": 1.713641249976768e+16,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.0502427338108112e-05,
+    "per_device_train_batch_size": 16
+  }
+}

run-1/checkpoint-6500/training_args.bin

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

run-1/checkpoint-7000/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-7000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13bc38d638baa336cd43e84bba0909ef3b954bb908b943441e83c2c01aa837e6
+size 1421491284

run-1/checkpoint-7000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b44bdca3a54104286ce9566e3c7ac5af53e3e3791e508c263c18dafa4c560ee
+size 2843215085

run-1/checkpoint-7000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b973398ef7c7e0a2d340d2fe91ffa3d6534f9192ba7b527da622359a56e746f
+size 14244

run-1/checkpoint-7000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96affa2682e229146b28fdf5ffedd59926fd2b01bde4902f74484dfd0c05e79e
+size 1064

run-1/checkpoint-7000/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-7000/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-7000/trainer_state.json

@@ -0,0 +1,203 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 9.383378016085791,
+  "eval_steps": 500,
+  "global_step": 7000,
+  "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
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.8266845345497131,
+      "eval_loss": 0.9764488339424133,
+      "eval_runtime": 9.3516,
+      "eval_samples_per_second": 318.981,
+      "eval_steps_per_second": 19.996,
+      "step": 5222
+    },
+    {
+      "epoch": 7.372654155495979,
+      "grad_norm": 0.9753480553627014,
+      "learning_rate": 2.759350882398378e-06,
+      "loss": 0.0218,
+      "step": 5500
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.8320482969284058,
+      "eval_loss": 0.9748868346214294,
+      "eval_runtime": 9.391,
+      "eval_samples_per_second": 317.644,
+      "eval_steps_per_second": 19.913,
+      "step": 5968
+    },
+    {
+      "epoch": 8.04289544235925,
+      "grad_norm": 65.11773681640625,
+      "learning_rate": 2.0554348409702203e-06,
+      "loss": 0.0196,
+      "step": 6000
+    },
+    {
+      "epoch": 8.71313672922252,
+      "grad_norm": 0.08348937332630157,
+      "learning_rate": 1.3515187995420628e-06,
+      "loss": 0.0136,
+      "step": 6500
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.8246731758117676,
+      "eval_loss": 1.0319347381591797,
+      "eval_runtime": 9.3631,
+      "eval_samples_per_second": 318.591,
+      "eval_steps_per_second": 19.972,
+      "step": 6714
+    },
+    {
+      "epoch": 9.383378016085791,
+      "grad_norm": 5.880457401275635,
+      "learning_rate": 6.476027581139051e-07,
+      "loss": 0.0095,
+      "step": 7000
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 7460,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "total_flos": 1.845415899511027e+16,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.0502427338108112e-05,
+    "per_device_train_batch_size": 16
+  }
+}

run-1/checkpoint-7000/training_args.bin

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