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 sha256:616cc256e78117e1d724807d452a1d577faa02f4716d1b2056d0b23d4781742d
+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 +1,162 @@
+{
+  "best_metric": 0.8596623807901907,
+  "best_model_checkpoint": "./save_models/mrpc/roberta-base_lr5e-05_run0/checkpoint-1449",
+  "epoch": 10.0,
+  "eval_steps": 500,
+  "global_step": 2070,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8010899182561307,
+      "eval_averaged_scores": 0.8262068735883505,
+      "eval_f1": 0.8513238289205703,
+      "eval_loss": 0.4088594615459442,
+      "eval_runtime": 0.8357,
+      "eval_samples_per_second": 439.143,
+      "eval_steps_per_second": 27.521,
+      "step": 207
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7602179836512262,
+      "eval_averaged_scores": 0.781009892726514,
+      "eval_f1": 0.8018018018018018,
+      "eval_loss": 0.4726070165634155,
+      "eval_runtime": 0.4955,
+      "eval_samples_per_second": 740.675,
+      "eval_steps_per_second": 46.418,
+      "step": 414
+    },
+    {
+      "epoch": 2.42,
+      "learning_rate": 4.0359897172236504e-05,
+      "loss": 0.4481,
+      "step": 500
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8283378746594006,
+      "eval_averaged_scores": 0.8527654285577706,
+      "eval_f1": 0.8771929824561405,
+      "eval_loss": 0.46944934129714966,
+      "eval_runtime": 0.4861,
+      "eval_samples_per_second": 754.978,
+      "eval_steps_per_second": 47.315,
+      "step": 621
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8365122615803815,
+      "eval_averaged_scores": 0.8587323212663813,
+      "eval_f1": 0.880952380952381,
+      "eval_loss": 0.716332197189331,
+      "eval_runtime": 0.4857,
+      "eval_samples_per_second": 755.614,
+      "eval_steps_per_second": 47.355,
+      "step": 828
+    },
+    {
+      "epoch": 4.83,
+      "learning_rate": 2.750642673521851e-05,
+      "loss": 0.2017,
+      "step": 1000
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.8283378746594006,
+      "eval_averaged_scores": 0.8510426848246903,
+      "eval_f1": 0.87374749498998,
+      "eval_loss": 0.9263336658477783,
+      "eval_runtime": 0.4853,
+      "eval_samples_per_second": 756.307,
+      "eval_steps_per_second": 47.398,
+      "step": 1035
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.8283378746594006,
+      "eval_averaged_scores": 0.8510426848246903,
+      "eval_f1": 0.87374749498998,
+      "eval_loss": 1.0142543315887451,
+      "eval_runtime": 0.4866,
+      "eval_samples_per_second": 754.169,
+      "eval_steps_per_second": 47.264,
+      "step": 1242
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.8365122615803815,
+      "eval_averaged_scores": 0.8596623807901907,
+      "eval_f1": 0.8828125,
+      "eval_loss": 1.0171551704406738,
+      "eval_runtime": 0.4871,
+      "eval_samples_per_second": 753.373,
+      "eval_steps_per_second": 47.214,
+      "step": 1449
+    },
+    {
+      "epoch": 7.25,
+      "learning_rate": 1.4652956298200515e-05,
+      "loss": 0.0593,
+      "step": 1500
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.8337874659400545,
+      "eval_averaged_scores": 0.8557714884810492,
+      "eval_f1": 0.8777555110220441,
+      "eval_loss": 1.0489568710327148,
+      "eval_runtime": 0.4847,
+      "eval_samples_per_second": 757.236,
+      "eval_steps_per_second": 47.456,
+      "step": 1656
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.8337874659400545,
+      "eval_averaged_scores": 0.8569723184317168,
+      "eval_f1": 0.8801571709233792,
+      "eval_loss": 1.2099965810775757,
+      "eval_runtime": 0.4891,
+      "eval_samples_per_second": 750.402,
+      "eval_steps_per_second": 47.028,
+      "step": 1863
+    },
+    {
+      "epoch": 9.66,
+      "learning_rate": 1.7994858611825194e-06,
+      "loss": 0.0183,
+      "step": 2000
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.8310626702997275,
+      "eval_averaged_scores": 0.8542665130154764,
+      "eval_f1": 0.8774703557312253,
+      "eval_loss": 1.2079670429229736,
+      "eval_runtime": 0.4843,
+      "eval_samples_per_second": 757.767,
+      "eval_steps_per_second": 47.489,
+      "step": 2070
+    },
+    {
+      "epoch": 10.0,
+      "step": 2070,
+      "total_flos": 1295111753354040.0,
+      "train_loss": 0.17568344080523737,
+      "train_runtime": 279.1119,
+      "train_samples_per_second": 118.268,
+      "train_steps_per_second": 7.416
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2070,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "total_flos": 1295111753354040.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ebc37108d69bdfafb90cbb1f1440787ba17d426b7bf64d0a5ed964b3056dbae
+size 4091