Training in progress, epoch 3, checkpoint

checkpoint-1080/config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "bert-base-uncased",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "finetuning_task": "stsb",
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 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": "regression",
+  "torch_dtype": "float32",
+  "transformers_version": "4.45.0.dev0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

checkpoint-1080/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36699ffcb60accbdc40002760d717d4167c5d645e08434a8bebb635014d65596
+size 437955572

checkpoint-1080/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae7eca726d667b308c28b20166b0f80112c713018920e36281389c7523f23199
+size 876032250

checkpoint-1080/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b7450df9f4c5beabf64c7858a4ca90862ca1572426f656452eb56b705c761a4
+size 14244

checkpoint-1080/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c330159ff09e22567b8893e931b68051e068b0d0f02833cfddcd6a51d5d6b8d1
+size 1064

checkpoint-1080/special_tokens_map.json

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

checkpoint-1080/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-1080/trainer_state.json

@@ -0,0 +1,87 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 1080,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 36.04340744018555,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 1.1212,
+      "step": 360
+    },
+    {
+      "epoch": 1.0,
+      "eval_combined_score": 0.8775720604589583,
+      "eval_loss": 0.5732272267341614,
+      "eval_pearson": 0.8789818053039898,
+      "eval_runtime": 6.5665,
+      "eval_samples_per_second": 228.431,
+      "eval_spearmanr": 0.8761623156139267,
+      "eval_steps_per_second": 28.63,
+      "step": 360
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 15.674260139465332,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 0.4308,
+      "step": 720
+    },
+    {
+      "epoch": 2.0,
+      "eval_combined_score": 0.8794983049402647,
+      "eval_loss": 0.5606899261474609,
+      "eval_pearson": 0.881313245175558,
+      "eval_runtime": 6.5051,
+      "eval_samples_per_second": 230.59,
+      "eval_spearmanr": 0.8776833647049715,
+      "eval_steps_per_second": 28.901,
+      "step": 720
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 56.831668853759766,
+      "learning_rate": 0.0,
+      "loss": 0.2947,
+      "step": 1080
+    },
+    {
+      "epoch": 3.0,
+      "eval_combined_score": 0.8836428004813802,
+      "eval_loss": 0.5009750723838806,
+      "eval_pearson": 0.8856376463366951,
+      "eval_runtime": 6.5121,
+      "eval_samples_per_second": 230.341,
+      "eval_spearmanr": 0.8816479546260654,
+      "eval_steps_per_second": 28.869,
+      "step": 1080
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1080,
+  "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": 4537835628033024.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1080/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e0d659fb15047217b592c145027afdf80238bb71c47b69b20f81e1701934633
+size 5176