Training in progress, epoch 3, checkpoint

checkpoint-1605/config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "bert-base-uncased",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "finetuning_task": "cola",
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "acceptable": 1,
+    "unacceptable": 0
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.45.0.dev0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

checkpoint-1605/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be45c6a99770051816b57f518d2275a64eb31c68755ff73c47022f26774a8fae
+size 437958648

checkpoint-1605/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6967460553984040d1f13f974125676afef82e6d78809c1879469f40d5f1a37
+size 876038394

checkpoint-1605/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a55345f8eff1a9b65a6802737d84c263421781faa5874b8c81811790624e1622
+size 14244

checkpoint-1605/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:920e0bbda21c75fc7cac58a3bd57de64d4e8057fabfe0e03dd126ce6ec38d845
+size 1064

checkpoint-1605/special_tokens_map.json

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

checkpoint-1605/tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

checkpoint-1605/trainer_state.json

@@ -0,0 +1,81 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 1605,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 14.7899808883667,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 0.4866,
+      "step": 535
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.42115479707717896,
+      "eval_matthews_correlation": 0.5497032501894998,
+      "eval_runtime": 4.7251,
+      "eval_samples_per_second": 220.738,
+      "eval_steps_per_second": 27.724,
+      "step": 535
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 33.17850112915039,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 0.2848,
+      "step": 1070
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.5097023844718933,
+      "eval_matthews_correlation": 0.5726999708077573,
+      "eval_runtime": 4.4553,
+      "eval_samples_per_second": 234.104,
+      "eval_steps_per_second": 29.403,
+      "step": 1070
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.3264881372451782,
+      "learning_rate": 0.0,
+      "loss": 0.1867,
+      "step": 1605
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.6564142107963562,
+      "eval_matthews_correlation": 0.5577353353156735,
+      "eval_runtime": 4.4818,
+      "eval_samples_per_second": 232.721,
+      "eval_steps_per_second": 29.23,
+      "step": 1605
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1605,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 6749587903150080.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1605/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a16dd18bcd0b40ae39532cb90cfd5f464ded8538b2de52f1f0c207c291c7e3b
+size 5240