Upload folder using huggingface_hub

config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "FacebookAI/roberta-large",
+  "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": 1024,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "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",
+  "problem_type": "regression",
+  "torch_dtype": "float32",
+  "transformers_version": "4.40.0.dev0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa9eb7c0bf079c371ab0eed94ed0e1bf280c22f0dfc4899cdcc15875be93a765
+size 1421491316

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:219799fafb9c53a896a39ea040efaf0c1e565b20ff5ab4ad2c32e59fa17b2f84
+size 2843215085

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66219010fef9d238a14f76d64e32db0e715da326b33426ae4acb932817a3b642
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09d27902d0d8540b2fb117b8f9311920dcc728063412faaeca074be74bead2d5
+size 1064

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 +1,57 @@
+{
+  "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>"
+}

trainer_state.json

@@ -0,0 +1,147 @@
+{
+  "best_metric": 0.03419998660683632,
+  "best_model_checkpoint": "logs/FacebookAI/roberta-large_accuracy-coverage/checkpoint-772",
+  "epoch": 7.0,
+  "eval_steps": 500,
+  "global_step": 1351,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 7.81976318359375,
+      "learning_rate": 1.901554404145078e-05,
+      "loss": 0.0819,
+      "step": 193
+    },
+    {
+      "epoch": 1.0,
+      "eval_MAE": 0.1725175678730011,
+      "eval_R2": -0.1497003860798276,
+      "eval_RMSE": 0.2353871762752533,
+      "eval_loss": 0.05540712550282478,
+      "eval_runtime": 14.0688,
+      "eval_samples_per_second": 204.779,
+      "eval_steps_per_second": 3.483,
+      "step": 193
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 13.916872024536133,
+      "learning_rate": 1.8015544041450778e-05,
+      "loss": 0.0552,
+      "step": 386
+    },
+    {
+      "epoch": 2.0,
+      "eval_MAE": 0.14744172990322113,
+      "eval_R2": 0.2686269017946187,
+      "eval_RMSE": 0.18774136900901794,
+      "eval_loss": 0.035246819257736206,
+      "eval_runtime": 14.01,
+      "eval_samples_per_second": 205.64,
+      "eval_steps_per_second": 3.498,
+      "step": 386
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 1.4010157585144043,
+      "learning_rate": 1.7015544041450777e-05,
+      "loss": 0.044,
+      "step": 579
+    },
+    {
+      "epoch": 3.0,
+      "eval_MAE": 0.1637636125087738,
+      "eval_R2": -0.005046362468473786,
+      "eval_RMSE": 0.22008149325847626,
+      "eval_loss": 0.048435866832733154,
+      "eval_runtime": 13.9579,
+      "eval_samples_per_second": 206.406,
+      "eval_steps_per_second": 3.511,
+      "step": 579
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 5.166985034942627,
+      "learning_rate": 1.601554404145078e-05,
+      "loss": 0.0377,
+      "step": 772
+    },
+    {
+      "epoch": 4.0,
+      "eval_MAE": 0.13679075241088867,
+      "eval_R2": 0.2903487127030966,
+      "eval_RMSE": 0.1849323809146881,
+      "eval_loss": 0.03419998660683632,
+      "eval_runtime": 13.9498,
+      "eval_samples_per_second": 206.527,
+      "eval_steps_per_second": 3.513,
+      "step": 772
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 5.7769083976745605,
+      "learning_rate": 1.5015544041450778e-05,
+      "loss": 0.0309,
+      "step": 965
+    },
+    {
+      "epoch": 5.0,
+      "eval_MAE": 0.1612362116575241,
+      "eval_R2": 0.01970298411235538,
+      "eval_RMSE": 0.21735484898090363,
+      "eval_loss": 0.04724312946200371,
+      "eval_runtime": 13.9679,
+      "eval_samples_per_second": 206.259,
+      "eval_steps_per_second": 3.508,
+      "step": 965
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 4.735123157501221,
+      "learning_rate": 1.4015544041450779e-05,
+      "loss": 0.0269,
+      "step": 1158
+    },
+    {
+      "epoch": 6.0,
+      "eval_MAE": 0.1395827978849411,
+      "eval_R2": 0.2431203329693593,
+      "eval_RMSE": 0.19098703563213348,
+      "eval_loss": 0.036476049572229385,
+      "eval_runtime": 14.0051,
+      "eval_samples_per_second": 205.711,
+      "eval_steps_per_second": 3.499,
+      "step": 1158
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 11.766636848449707,
+      "learning_rate": 1.3015544041450778e-05,
+      "loss": 0.0232,
+      "step": 1351
+    },
+    {
+      "epoch": 7.0,
+      "eval_MAE": 0.1361502856016159,
+      "eval_R2": 0.28310775750843686,
+      "eval_RMSE": 0.18587347865104675,
+      "eval_loss": 0.03454894945025444,
+      "eval_runtime": 13.9169,
+      "eval_samples_per_second": 207.014,
+      "eval_steps_per_second": 3.521,
+      "step": 1351
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 3860,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 20,
+  "save_steps": 500,
+  "total_flos": 7.515640838071338e+16,
+  "train_batch_size": 60,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5ef18774ff45f032c5338f653bc7f6b39b33853d01e8747b3f0e7097568fea8
+size 5048