Upload folder using huggingface_hub

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "/mnt/data/yule/.cache/roberta-base",
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "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": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.33.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc62f9febb6e34f6a9209213f14a89ac2056f08d8a83c4561136d56e1d61e027
+size 498654833

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>"
+}

tokenizer_config.json

@@ -0,0 +1,15 @@
+{
+  "add_prefix_space": false,
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

trainer_state.json

@@ -0,0 +1,130 @@
+{
+  "best_metric": 0.7710843373493976,
+  "best_model_checkpoint": "./save_models/rte/roberta-base_lr1e-05_run0/checkpoint-705",
+  "epoch": 10.0,
+  "eval_steps": 500,
+  "global_step": 1410,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5220883534136547,
+      "eval_loss": 0.6918767690658569,
+      "eval_runtime": 0.7339,
+      "eval_samples_per_second": 339.261,
+      "eval_steps_per_second": 21.8,
+      "step": 141
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6546184738955824,
+      "eval_loss": 0.6190726161003113,
+      "eval_runtime": 0.5217,
+      "eval_samples_per_second": 477.309,
+      "eval_steps_per_second": 30.67,
+      "step": 282
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7349397590361446,
+      "eval_loss": 0.5996102690696716,
+      "eval_runtime": 0.5041,
+      "eval_samples_per_second": 493.968,
+      "eval_steps_per_second": 31.741,
+      "step": 423
+    },
+    {
+      "epoch": 3.55,
+      "learning_rate": 6.867924528301887e-06,
+      "loss": 0.5617,
+      "step": 500
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.678714859437751,
+      "eval_loss": 0.8101745247840881,
+      "eval_runtime": 0.4864,
+      "eval_samples_per_second": 511.902,
+      "eval_steps_per_second": 32.893,
+      "step": 564
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.7710843373493976,
+      "eval_loss": 0.6978227496147156,
+      "eval_runtime": 0.4777,
+      "eval_samples_per_second": 521.196,
+      "eval_steps_per_second": 33.491,
+      "step": 705
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.751004016064257,
+      "eval_loss": 0.9106957912445068,
+      "eval_runtime": 0.5496,
+      "eval_samples_per_second": 453.072,
+      "eval_steps_per_second": 29.113,
+      "step": 846
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.7389558232931727,
+      "eval_loss": 1.2450735569000244,
+      "eval_runtime": 0.5411,
+      "eval_samples_per_second": 460.179,
+      "eval_steps_per_second": 29.57,
+      "step": 987
+    },
+    {
+      "epoch": 7.09,
+      "learning_rate": 3.0943396226415094e-06,
+      "loss": 0.2292,
+      "step": 1000
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.7429718875502008,
+      "eval_loss": 1.3661861419677734,
+      "eval_runtime": 0.5209,
+      "eval_samples_per_second": 477.982,
+      "eval_steps_per_second": 30.714,
+      "step": 1128
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.7429718875502008,
+      "eval_loss": 1.373397946357727,
+      "eval_runtime": 0.5175,
+      "eval_samples_per_second": 481.183,
+      "eval_steps_per_second": 30.919,
+      "step": 1269
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.7429718875502008,
+      "eval_loss": 1.4039331674575806,
+      "eval_runtime": 0.4845,
+      "eval_samples_per_second": 513.899,
+      "eval_steps_per_second": 33.022,
+      "step": 1410
+    },
+    {
+      "epoch": 10.0,
+      "step": 1410,
+      "total_flos": 1453805233617060.0,
+      "train_loss": 0.31550021340661016,
+      "train_runtime": 316.3056,
+      "train_samples_per_second": 70.849,
+      "train_steps_per_second": 4.458
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1410,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "total_flos": 1453805233617060.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d4c3d10c7e13215209612832548edbd964196a4780d481fcb917af498764575
+size 4091