Training in progress, epoch 3, checkpoint

checkpoint-19641/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": "qnli",
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "entailment": 0,
+    "not_entailment": 1
+  },
+  "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-19641/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05c4f4e027eaf1623a89cdda609908b220313e5f285ebc609b01e62baed6b4c1
+size 437958648

checkpoint-19641/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72d9d48f26ebcb55a943a148c81b842f05214b611c7ff27d9d9c33a47dc4c099
+size 876038394

checkpoint-19641/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ddcde089e9f09ae805e8ff80af210bcd1073e540b071c584eded5c4a7ec18eb
+size 14244

checkpoint-19641/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab43fb8473fb05dcb51ba15c1715bfcbda3cd075f5550955dc25896b7a78470f
+size 1064

checkpoint-19641/special_tokens_map.json

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

checkpoint-19641/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-19641/trainer_state.json

@@ -0,0 +1,81 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 19641,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 17.44370460510254,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 0.3365,
+      "step": 6547
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9064616511074501,
+      "eval_loss": 0.23984280228614807,
+      "eval_runtime": 23.1983,
+      "eval_samples_per_second": 235.492,
+      "eval_steps_per_second": 29.442,
+      "step": 6547
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.31856870651245117,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 0.1938,
+      "step": 13094
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9108548416620904,
+      "eval_loss": 0.2898029088973999,
+      "eval_runtime": 23.2441,
+      "eval_samples_per_second": 235.027,
+      "eval_steps_per_second": 29.384,
+      "step": 13094
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.2609856128692627,
+      "learning_rate": 0.0,
+      "loss": 0.1171,
+      "step": 19641
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9132344865458539,
+      "eval_loss": 0.3919076919555664,
+      "eval_runtime": 23.2022,
+      "eval_samples_per_second": 235.452,
+      "eval_steps_per_second": 29.437,
+      "step": 19641
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 19641,
+  "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": 8.267712381471744e+16,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-19641/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7bccc2292ef218f167a9661a6836b7411346d18d2cfb645616d3acde259dd3d4
+size 5176