Upload folder using huggingface_hub

config.json

@@ -0,0 +1,33 @@
+{
+  "_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,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "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:da58f14267ac7aa7f87dd1ec0134f5216804facc2e5aadbf27bc1a248b95a76f
+size 498651761

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 +1,174 @@
+{
+  "best_metric": 0.9132375276225795,
+  "best_model_checkpoint": "./save_models/stsb/roberta-base_lr1e-05_run0/checkpoint-2916",
+  "epoch": 10.0,
+  "eval_steps": 500,
+  "global_step": 3240,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_averaged_scores": 0.8719844165680126,
+      "eval_loss": 0.5549536347389221,
+      "eval_pearson": 0.8792634862673233,
+      "eval_runtime": 1.0963,
+      "eval_samples_per_second": 524.504,
+      "eval_spearmanr": 0.8647053468687018,
+      "eval_steps_per_second": 32.838,
+      "step": 324
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 8.998357963875205e-06,
+      "loss": 1.9846,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "eval_averaged_scores": 0.8945047640614983,
+      "eval_loss": 0.603453516960144,
+      "eval_pearson": 0.9005924807835378,
+      "eval_runtime": 0.704,
+      "eval_samples_per_second": 816.784,
+      "eval_spearmanr": 0.8884170473394587,
+      "eval_steps_per_second": 51.138,
+      "step": 648
+    },
+    {
+      "epoch": 3.0,
+      "eval_averaged_scores": 0.9062316400464019,
+      "eval_loss": 0.4641549587249756,
+      "eval_pearson": 0.9128021174279124,
+      "eval_runtime": 0.7081,
+      "eval_samples_per_second": 811.986,
+      "eval_spearmanr": 0.8996611626648913,
+      "eval_steps_per_second": 50.837,
+      "step": 972
+    },
+    {
+      "epoch": 3.09,
+      "learning_rate": 7.35632183908046e-06,
+      "loss": 0.3739,
+      "step": 1000
+    },
+    {
+      "epoch": 4.0,
+      "eval_averaged_scores": 0.9065076507852758,
+      "eval_loss": 0.4377610683441162,
+      "eval_pearson": 0.9127118914783907,
+      "eval_runtime": 0.6286,
+      "eval_samples_per_second": 914.771,
+      "eval_spearmanr": 0.9003034100921611,
+      "eval_steps_per_second": 57.273,
+      "step": 1296
+    },
+    {
+      "epoch": 4.63,
+      "learning_rate": 5.7142857142857145e-06,
+      "loss": 0.2485,
+      "step": 1500
+    },
+    {
+      "epoch": 5.0,
+      "eval_averaged_scores": 0.908379700337028,
+      "eval_loss": 0.4117390811443329,
+      "eval_pearson": 0.9141856508223978,
+      "eval_runtime": 0.6332,
+      "eval_samples_per_second": 908.107,
+      "eval_spearmanr": 0.9025737498516583,
+      "eval_steps_per_second": 56.855,
+      "step": 1620
+    },
+    {
+      "epoch": 6.0,
+      "eval_averaged_scores": 0.9116822332416219,
+      "eval_loss": 0.4102296233177185,
+      "eval_pearson": 0.9173376535815415,
+      "eval_runtime": 0.617,
+      "eval_samples_per_second": 931.917,
+      "eval_spearmanr": 0.9060268129017023,
+      "eval_steps_per_second": 58.346,
+      "step": 1944
+    },
+    {
+      "epoch": 6.17,
+      "learning_rate": 4.072249589490969e-06,
+      "loss": 0.1894,
+      "step": 2000
+    },
+    {
+      "epoch": 7.0,
+      "eval_averaged_scores": 0.9117323593371983,
+      "eval_loss": 0.402465283870697,
+      "eval_pearson": 0.9170297139907337,
+      "eval_runtime": 0.6389,
+      "eval_samples_per_second": 899.99,
+      "eval_spearmanr": 0.9064350046836629,
+      "eval_steps_per_second": 56.347,
+      "step": 2268
+    },
+    {
+      "epoch": 7.72,
+      "learning_rate": 2.4302134646962236e-06,
+      "loss": 0.1519,
+      "step": 2500
+    },
+    {
+      "epoch": 8.0,
+      "eval_averaged_scores": 0.9119600828390606,
+      "eval_loss": 0.4155682921409607,
+      "eval_pearson": 0.9177323566058198,
+      "eval_runtime": 0.6403,
+      "eval_samples_per_second": 898.065,
+      "eval_spearmanr": 0.9061878090723013,
+      "eval_steps_per_second": 56.227,
+      "step": 2592
+    },
+    {
+      "epoch": 9.0,
+      "eval_averaged_scores": 0.9132375276225795,
+      "eval_loss": 0.39730867743492126,
+      "eval_pearson": 0.9183296123362426,
+      "eval_runtime": 0.6124,
+      "eval_samples_per_second": 938.861,
+      "eval_spearmanr": 0.9081454429089164,
+      "eval_steps_per_second": 58.781,
+      "step": 2916
+    },
+    {
+      "epoch": 9.26,
+      "learning_rate": 7.881773399014779e-07,
+      "loss": 0.1262,
+      "step": 3000
+    },
+    {
+      "epoch": 10.0,
+      "eval_averaged_scores": 0.9126844528170279,
+      "eval_loss": 0.41949743032455444,
+      "eval_pearson": 0.9177749306754028,
+      "eval_runtime": 0.6141,
+      "eval_samples_per_second": 936.342,
+      "eval_spearmanr": 0.907593974958653,
+      "eval_steps_per_second": 58.623,
+      "step": 3240
+    },
+    {
+      "epoch": 10.0,
+      "step": 3240,
+      "total_flos": 1693845460370892.0,
+      "train_loss": 0.4830472233854694,
+      "train_runtime": 291.8592,
+      "train_samples_per_second": 177.277,
+      "train_steps_per_second": 11.101
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 3240,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "total_flos": 1693845460370892.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a5f2837e97aaf6237b319db797c79d9727e219a900e23ce6045d0dae465aa11
+size 4091