Upload folder using huggingface_hub

added_tokens.json

@@ -0,0 +1,7 @@
+{
+  "</s>": 2,
+  "<mask>": 50264,
+  "<pad>": 1,
+  "<s>": 0,
+  "<unk>": 3
+}

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "roberta-base",
+  "architectures": [
+    "RobertaForQuestionAnswering"
+  ],
+  "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": "4.34.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa602398a1ffa4c5da5e93c757e4ea11280062033d3ec5256c85c4c79de31e0c
+size 992619066

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17ba528f3103b7a10c948793afbff99655b7d07ece344db03155d9f777ec726d
+size 496295078

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc3901c5e78db8dfecd4a40a0f18caca31434c760459a2305cdf1ab363e99c42
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:989935366fc9ee41649a69d799b25864bc75ed0b6701cad0acf3e049eaa6deec
+size 1064

special_tokens_map.json

@@ -0,0 +1,9 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50264": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "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 +1,95 @@
+{
+  "best_metric": 0.8387653827667236,
+  "best_model_checkpoint": "finetune_roberta-base/checkpoint-5476",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 5476,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.879474068663258e-05,
+      "loss": 1.7148,
+      "step": 500
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.7577307036766496e-05,
+      "loss": 1.075,
+      "step": 1000
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 1.6359873386900417e-05,
+      "loss": 0.9886,
+      "step": 1500
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 1.5142439737034334e-05,
+      "loss": 0.9376,
+      "step": 2000
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 1.3925006087168251e-05,
+      "loss": 0.9256,
+      "step": 2500
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.8695176839828491,
+      "eval_runtime": 78.4582,
+      "eval_samples_per_second": 134.721,
+      "eval_steps_per_second": 1.058,
+      "step": 2738
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 1.2707572437302169e-05,
+      "loss": 0.8303,
+      "step": 3000
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 1.1490138787436084e-05,
+      "loss": 0.7641,
+      "step": 3500
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 1.0275140004869735e-05,
+      "loss": 0.7347,
+      "step": 4000
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 9.060141222303384e-06,
+      "loss": 0.737,
+      "step": 4500
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 7.842707572437303e-06,
+      "loss": 0.7466,
+      "step": 5000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.8387653827667236,
+      "eval_runtime": 77.9854,
+      "eval_samples_per_second": 135.538,
+      "eval_steps_per_second": 1.064,
+      "step": 5476
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 8214,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 3.4334001889975296e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8bc89e2e64fa414dc4c0a103cb82e4fdc230c40d353a9e60416c2ee89c05cfb
+size 4472