Delete model

Browse files

Files changed (10) hide show

model/config.json +0 -33
model/model.safetensors +0 -3
model/rng_state.pth +0 -3
model/scheduler.pt +0 -3
model/special_tokens_map.json +0 -7
model/tokenizer.json +0 -0
model/tokenizer_config.json +0 -58
model/trainer_state.json +0 -138
model/training_args.bin +0 -3
model/vocab.txt +0 -0

model/config.json DELETED Viewed

@@ -1,33 +0,0 @@
-{
-  "_num_labels": 5,
-  "architectures": [
-    "BertForSequenceClassification"
-  ],
-  "attention_probs_dropout_prob": 0.1,
-  "classifier_dropout": null,
-  "directionality": "bidi",
-  "hidden_act": "gelu",
-  "hidden_dropout_prob": 0.1,
-  "hidden_size": 768,
-  "initializer_range": 0.02,
-  "intermediate_size": 3072,
-  "layer_norm_eps": 1e-12,
-  "max_position_embeddings": 512,
-  "model_type": "bert",
-  "num_attention_heads": 12,
-  "num_hidden_layers": 12,
-  "output_past": true,
-  "pad_token_id": 0,
-  "pooler_fc_size": 768,
-  "pooler_num_attention_heads": 12,
-  "pooler_num_fc_layers": 3,
-  "pooler_size_per_head": 128,
-  "pooler_type": "first_token_transform",
-  "position_embedding_type": "absolute",
-  "problem_type": "single_label_classification",
-  "torch_dtype": "float32",
-  "transformers_version": "4.53.0",
-  "type_vocab_size": 2,
-  "use_cache": true,
-  "vocab_size": 50000
-}

model/model.safetensors DELETED Viewed

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:1b77759f6e48e19327283f7aa046636c56f35df289513e89f0508ac1fcda1d65
-size 497795072

model/rng_state.pth DELETED Viewed

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:29cdcf8500d611a361d036d2b7218fd90ffe4602e304fbb914499aec7cc6a78c
-size 14244

model/scheduler.pt DELETED Viewed

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:9730cc2f43833b3fafd0b4b66e946e0d26b98894ecb5c30d664e39273ab16d55
-size 1064

model/special_tokens_map.json DELETED Viewed

@@ -1,7 +0,0 @@
-{
-  "cls_token": "[CLS]",
-  "mask_token": "[MASK]",
-  "pad_token": "[PAD]",
-  "sep_token": "[SEP]",
-  "unk_token": "[UNK]"
-}

model/tokenizer.json DELETED Viewed

The diff for this file is too large to render. See raw diff

model/tokenizer_config.json DELETED Viewed

@@ -1,58 +0,0 @@
-{
-  "added_tokens_decoder": {
-    "0": {
-      "content": "[PAD]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "1": {
-      "content": "[UNK]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "2": {
-      "content": "[CLS]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "3": {
-      "content": "[SEP]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "4": {
-      "content": "[MASK]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    }
-  },
-  "clean_up_tokenization_spaces": true,
-  "cls_token": "[CLS]",
-  "do_basic_tokenize": true,
-  "do_lower_case": true,
-  "extra_special_tokens": {},
-  "mask_token": "[MASK]",
-  "model_max_length": 1000000000000000019884624838656,
-  "never_split": null,
-  "pad_token": "[PAD]",
-  "sep_token": "[SEP]",
-  "strip_accents": null,
-  "tokenize_chinese_chars": true,
-  "tokenizer_class": "BertTokenizer",
-  "unk_token": "[UNK]"
-}

model/trainer_state.json DELETED Viewed

@@ -1,138 +0,0 @@
-{
-  "best_global_step": 3745,
-  "best_metric": 0.852929763290648,
-  "best_model_checkpoint": "output/checkpoint-3745",
-  "epoch": 5.0,
-  "eval_steps": 500,
-  "global_step": 3745,
-  "is_hyper_param_search": false,
-  "is_local_process_zero": true,
-  "is_world_process_zero": true,
-  "log_history": [
-    {
-      "epoch": 1.0,
-      "grad_norm": 0.5436127185821533,
-      "learning_rate": 1.739912917271408e-05,
-      "loss": 0.4559,
-      "step": 749
-    },
-    {
-      "epoch": 1.0,
-      "eval_accuracy": 0.8409356725146199,
-      "eval_f1": 0.8260869565217392,
-      "eval_loss": 0.3511916697025299,
-      "eval_precision": 0.9022346368715084,
-      "eval_recal": 0.7617924528301887,
-      "eval_runtime": 45.6908,
-      "eval_samples_per_second": 56.138,
-      "eval_steps_per_second": 1.773,
-      "step": 749
-    },
-    {
-      "epoch": 2.0,
-      "grad_norm": 0.8240299224853516,
-      "learning_rate": 1.305079825834543e-05,
-      "loss": 0.2491,
-      "step": 1498
-    },
-    {
-      "epoch": 2.0,
-      "eval_accuracy": 0.8339181286549707,
-      "eval_f1": 0.8458755426917511,
-      "eval_loss": 0.3923635184764862,
-      "eval_precision": 0.7835120643431636,
-      "eval_recal": 0.9190251572327044,
-      "eval_runtime": 45.7634,
-      "eval_samples_per_second": 56.049,
-      "eval_steps_per_second": 1.77,
-      "step": 1498
-    },
-    {
-      "epoch": 3.0,
-      "grad_norm": 0.05070347338914871,
-      "learning_rate": 8.702467343976778e-06,
-      "loss": 0.1198,
-      "step": 2247
-    },
-    {
-      "epoch": 3.0,
-      "eval_accuracy": 0.8428849902534113,
-      "eval_f1": 0.8470588235294118,
-      "eval_loss": 0.5979883670806885,
-      "eval_precision": 0.8187820983125459,
-      "eval_recal": 0.8773584905660378,
-      "eval_runtime": 45.2758,
-      "eval_samples_per_second": 56.653,
-      "eval_steps_per_second": 1.789,
-      "step": 2247
-    },
-    {
-      "epoch": 4.0,
-      "grad_norm": 119.22203826904297,
-      "learning_rate": 4.354136429608128e-06,
-      "loss": 0.0439,
-      "step": 2996
-    },
-    {
-      "epoch": 4.0,
-      "eval_accuracy": 0.8444444444444444,
-      "eval_f1": 0.8478841021730842,
-      "eval_loss": 0.9496913552284241,
-      "eval_precision": 0.8230940044411547,
-      "eval_recal": 0.8742138364779874,
-      "eval_runtime": 45.2408,
-      "eval_samples_per_second": 56.697,
-      "eval_steps_per_second": 1.79,
-      "step": 2996
-    },
-    {
-      "epoch": 5.0,
-      "grad_norm": 0.0039998251013457775,
-      "learning_rate": 5.8055152394775034e-09,
-      "loss": 0.0097,
-      "step": 3745
-    },
-    {
-      "epoch": 5.0,
-      "eval_accuracy": 0.8522417153996101,
-      "eval_f1": 0.852929763290648,
-      "eval_loss": 0.9962489008903503,
-      "eval_precision": 0.8421455938697318,
-      "eval_recal": 0.8639937106918238,
-      "eval_runtime": 45.309,
-      "eval_samples_per_second": 56.611,
-      "eval_steps_per_second": 1.788,
-      "step": 3745
-    }
-  ],
-  "logging_steps": 500,
-  "max_steps": 3745,
-  "num_input_tokens_seen": 0,
-  "num_train_epochs": 5,
-  "save_steps": 500,
-  "stateful_callbacks": {
-    "EarlyStoppingCallback": {
-      "args": {
-        "early_stopping_patience": 2,
-        "early_stopping_threshold": 0.001
-      },
-      "attributes": {
-        "early_stopping_patience_counter": 0
-      }
-    },
-    "TrainerControl": {
-      "args": {
-        "should_epoch_stop": false,
-        "should_evaluate": false,
-        "should_log": false,
-        "should_save": true,
-        "should_training_stop": true
-      },
-      "attributes": {}
-    }
-  },
-  "total_flos": 1.5747196663296e+16,
-  "train_batch_size": 16,
-  "trial_name": null,
-  "trial_params": null
-}

model/training_args.bin DELETED Viewed

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:665275b1a7c05f8b4200840f3e8b5b3bef7b1e2ba28de5b995e98e1a76176a42
-size 5304

model/vocab.txt DELETED Viewed

The diff for this file is too large to render. See raw diff