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 sha256:769d52cd0ec7a0292b955ce20b3ad6e8278096c6d5b9f824d8268da16f0af7c5
+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 +1,172 @@
+{
+  "best_metric": 0.636893310208111,
+  "best_model_checkpoint": "./save_models/cola/roberta-base_lr1e-05_run0/checkpoint-3848",
+  "epoch": 10.0,
+  "eval_steps": 500,
+  "global_step": 4810,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.45413094758987427,
+      "eval_matthews_correlation": 0.47785514722622213,
+      "eval_runtime": 0.5981,
+      "eval_samples_per_second": 1431.104,
+      "eval_steps_per_second": 90.28,
+      "step": 481
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 9.533289095332891e-06,
+      "loss": 0.5451,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.4294413626194,
+      "eval_matthews_correlation": 0.5559024469662472,
+      "eval_runtime": 0.6646,
+      "eval_samples_per_second": 1288.013,
+      "eval_steps_per_second": 81.253,
+      "step": 962
+    },
+    {
+      "epoch": 2.08,
+      "learning_rate": 8.427339084273391e-06,
+      "loss": 0.3643,
+      "step": 1000
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.5282544493675232,
+      "eval_matthews_correlation": 0.6061655951679263,
+      "eval_runtime": 0.5226,
+      "eval_samples_per_second": 1638.098,
+      "eval_steps_per_second": 103.338,
+      "step": 1443
+    },
+    {
+      "epoch": 3.12,
+      "learning_rate": 7.3213890732138915e-06,
+      "loss": 0.263,
+      "step": 1500
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.5712747573852539,
+      "eval_matthews_correlation": 0.6315329091741146,
+      "eval_runtime": 0.5375,
+      "eval_samples_per_second": 1592.64,
+      "eval_steps_per_second": 100.47,
+      "step": 1924
+    },
+    {
+      "epoch": 4.16,
+      "learning_rate": 6.2154390621543915e-06,
+      "loss": 0.2115,
+      "step": 2000
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 0.6360122561454773,
+      "eval_matthews_correlation": 0.6312355301626161,
+      "eval_runtime": 0.5144,
+      "eval_samples_per_second": 1664.168,
+      "eval_steps_per_second": 104.983,
+      "step": 2405
+    },
+    {
+      "epoch": 5.2,
+      "learning_rate": 5.1094890510948916e-06,
+      "loss": 0.1785,
+      "step": 2500
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 0.8011564612388611,
+      "eval_matthews_correlation": 0.6138643516919586,
+      "eval_runtime": 0.5202,
+      "eval_samples_per_second": 1645.404,
+      "eval_steps_per_second": 103.799,
+      "step": 2886
+    },
+    {
+      "epoch": 6.24,
+      "learning_rate": 4.003539040035391e-06,
+      "loss": 0.1659,
+      "step": 3000
+    },
+    {
+      "epoch": 7.0,
+      "eval_loss": 0.812069833278656,
+      "eval_matthews_correlation": 0.6262286365318072,
+      "eval_runtime": 0.5378,
+      "eval_samples_per_second": 1591.669,
+      "eval_steps_per_second": 100.409,
+      "step": 3367
+    },
+    {
+      "epoch": 7.28,
+      "learning_rate": 2.897589028975891e-06,
+      "loss": 0.1218,
+      "step": 3500
+    },
+    {
+      "epoch": 8.0,
+      "eval_loss": 0.7686376571655273,
+      "eval_matthews_correlation": 0.636893310208111,
+      "eval_runtime": 0.5131,
+      "eval_samples_per_second": 1668.28,
+      "eval_steps_per_second": 105.242,
+      "step": 3848
+    },
+    {
+      "epoch": 8.32,
+      "learning_rate": 1.7916390179163902e-06,
+      "loss": 0.1063,
+      "step": 4000
+    },
+    {
+      "epoch": 9.0,
+      "eval_loss": 0.8879063129425049,
+      "eval_matthews_correlation": 0.6314014927014334,
+      "eval_runtime": 0.5155,
+      "eval_samples_per_second": 1660.431,
+      "eval_steps_per_second": 104.747,
+      "step": 4329
+    },
+    {
+      "epoch": 9.36,
+      "learning_rate": 6.856890068568902e-07,
+      "loss": 0.0838,
+      "step": 4500
+    },
+    {
+      "epoch": 10.0,
+      "eval_loss": 0.8707919716835022,
+      "eval_matthews_correlation": 0.6253690295963492,
+      "eval_runtime": 0.5401,
+      "eval_samples_per_second": 1584.804,
+      "eval_steps_per_second": 99.976,
+      "step": 4810
+    },
+    {
+      "epoch": 10.0,
+      "step": 4810,
+      "total_flos": 808993009136460.0,
+      "train_loss": 0.21800182366321588,
+      "train_runtime": 226.2198,
+      "train_samples_per_second": 340.156,
+      "train_steps_per_second": 21.263
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 4810,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "total_flos": 808993009136460.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f105f3efde4732d7bfbb62ddd33fe996ca550c7c990c745187f28514c8c60c83
+size 4091