system A checkpoint 4000

config.json

@@ -0,0 +1,93 @@
+{
+  "_name_or_path": "roberta-base",
+  "architectures": [
+    "RobertaForTokenClassification"
+  ],
+  "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": "O",
+    "1": "B-PER",
+    "10": "I-BIO",
+    "11": "B-CEL",
+    "12": "I-CEL",
+    "13": "B-DIS",
+    "14": "I-DIS",
+    "15": "B-EVE",
+    "16": "I-EVE",
+    "17": "B-FOOD",
+    "18": "I-FOOD",
+    "19": "B-INST",
+    "2": "I-PER",
+    "20": "I-INST",
+    "21": "B-MEDIA",
+    "22": "I-MEDIA",
+    "23": "B-MYTH",
+    "24": "I-MYTH",
+    "25": "B-PLANT",
+    "26": "I-PLANT",
+    "27": "B-TIME",
+    "28": "I-TIME",
+    "29": "B-VEHI",
+    "3": "B-ORG",
+    "30": "I-VEHI",
+    "4": "I-ORG",
+    "5": "B-LOC",
+    "6": "I-LOC",
+    "7": "B-ANIM",
+    "8": "I-ANIM",
+    "9": "B-BIO"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-ANIM": 7,
+    "B-BIO": 9,
+    "B-CEL": 11,
+    "B-DIS": 13,
+    "B-EVE": 15,
+    "B-FOOD": 17,
+    "B-INST": 19,
+    "B-LOC": 5,
+    "B-MEDIA": 21,
+    "B-MYTH": 23,
+    "B-ORG": 3,
+    "B-PER": 1,
+    "B-PLANT": 25,
+    "B-TIME": 27,
+    "B-VEHI": 29,
+    "I-ANIM": 8,
+    "I-BIO": 10,
+    "I-CEL": 12,
+    "I-DIS": 14,
+    "I-EVE": 16,
+    "I-FOOD": 18,
+    "I-INST": 20,
+    "I-LOC": 6,
+    "I-MEDIA": 22,
+    "I-MYTH": 24,
+    "I-ORG": 4,
+    "I-PER": 2,
+    "I-PLANT": 26,
+    "I-TIME": 28,
+    "I-VEHI": 30,
+    "O": 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": "4.35.2",
+  "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 sha256:481e4627e3457b928a5e160578402025e42f50afe059ca5ea15f87664ab740bb
+size 496339452

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bef93d8b7b99af7a81f742706115933b17eb2ca891f7577b9870e08b71499502
+size 992797370

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef4877bb76af7155553bed487f45ed48cd16c815f1c6e4a5f3688a9aa56dccd8
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0acd1dd8634f9eb82171400dc990fc3f5742a8f7c08cbc9f0c189754ac18b98
+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": true,
+  "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 +1,163 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9748964172556666,
+  "eval_steps": 500,
+  "global_step": 4000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.12,
+      "learning_rate": 4.879469122426869e-05,
+      "loss": 0.3842,
+      "step": 500
+    },
+    {
+      "epoch": 0.12,
+      "eval_accuracy": 0.9771378667109926,
+      "eval_f1": 0.8381009137862535,
+      "eval_loss": 0.07010635733604431,
+      "eval_precision": 0.8681427219227129,
+      "eval_recall": 0.8100687377596867,
+      "eval_runtime": 73.0194,
+      "eval_samples_per_second": 224.735,
+      "eval_steps_per_second": 7.026,
+      "step": 500
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 4.202329360780065e-05,
+      "loss": 0.0597,
+      "step": 1000
+    },
+    {
+      "epoch": 0.24,
+      "eval_accuracy": 0.9804913313861603,
+      "eval_f1": 0.8726274509803922,
+      "eval_loss": 0.05635998398065567,
+      "eval_precision": 0.8915421290917104,
+      "eval_recall": 0.8544986751660842,
+      "eval_runtime": 75.0428,
+      "eval_samples_per_second": 218.675,
+      "eval_steps_per_second": 6.836,
+      "step": 1000
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 3.525189599133261e-05,
+      "loss": 0.0524,
+      "step": 1500
+    },
+    {
+      "epoch": 0.37,
+      "eval_accuracy": 0.9802354021387242,
+      "eval_f1": 0.8719290536491832,
+      "eval_loss": 0.05560198798775673,
+      "eval_precision": 0.9085119667013527,
+      "eval_recall": 0.8381782573633885,
+      "eval_runtime": 72.6323,
+      "eval_samples_per_second": 225.933,
+      "eval_steps_per_second": 7.063,
+      "step": 1500
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 2.8480498374864572e-05,
+      "loss": 0.0448,
+      "step": 2000
+    },
+    {
+      "epoch": 0.49,
+      "eval_accuracy": 0.9826548569830427,
+      "eval_f1": 0.8893414799728445,
+      "eval_loss": 0.04828519746661186,
+      "eval_precision": 0.8985262992866662,
+      "eval_recall": 0.8803425367689413,
+      "eval_runtime": 74.6781,
+      "eval_samples_per_second": 219.743,
+      "eval_steps_per_second": 6.869,
+      "step": 2000
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 2.1709100758396535e-05,
+      "loss": 0.0433,
+      "step": 2500
+    },
+    {
+      "epoch": 0.61,
+      "eval_accuracy": 0.9829266169055779,
+      "eval_f1": 0.8900519485573087,
+      "eval_loss": 0.046879906207323074,
+      "eval_precision": 0.902074459693958,
+      "eval_recall": 0.8783456856495526,
+      "eval_runtime": 75.3332,
+      "eval_samples_per_second": 217.832,
+      "eval_steps_per_second": 6.81,
+      "step": 2500
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 1.4937703141928494e-05,
+      "loss": 0.04,
+      "step": 3000
+    },
+    {
+      "epoch": 0.73,
+      "eval_accuracy": 0.983201015273963,
+      "eval_f1": 0.8977493905780533,
+      "eval_loss": 0.04475250095129013,
+      "eval_precision": 0.8837711139221668,
+      "eval_recall": 0.9121769517299643,
+      "eval_runtime": 73.7339,
+      "eval_samples_per_second": 222.557,
+      "eval_steps_per_second": 6.957,
+      "step": 3000
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 8.166305525460455e-06,
+      "loss": 0.0365,
+      "step": 3500
+    },
+    {
+      "epoch": 0.85,
+      "eval_accuracy": 0.9843672083395997,
+      "eval_f1": 0.9045125132863078,
+      "eval_loss": 0.04261544719338417,
+      "eval_precision": 0.9104419545596016,
+      "eval_recall": 0.8986598056910257,
+      "eval_runtime": 74.7052,
+      "eval_samples_per_second": 219.663,
+      "eval_steps_per_second": 6.867,
+      "step": 3500
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 1.394907908992416e-06,
+      "loss": 0.0366,
+      "step": 4000
+    },
+    {
+      "epoch": 0.97,
+      "eval_accuracy": 0.9845123228613417,
+      "eval_f1": 0.9050084368768215,
+      "eval_loss": 0.041375741362571716,
+      "eval_precision": 0.9037953352992991,
+      "eval_recall": 0.9062247993548634,
+      "eval_runtime": 75.1389,
+      "eval_samples_per_second": 218.396,
+      "eval_steps_per_second": 6.827,
+      "step": 4000
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 4103,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "total_flos": 4183330761475008.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9a9d7a58bc9223dee1d333461ebe1123ca065bf8f9aa6bbd0e7f5bb70632e31
+size 4600