uploading checkpoints

checkpoint-1800/config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "distilbert-base-uncased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "problem_type": "regression",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.28.1",
+  "vocab_size": 30522
+}

checkpoint-1800/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3a2d6fdeeb6b81a263cff477e43509163c903be6229e3f90b25fa9eaa392202
+size 535694917

checkpoint-1800/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de3c6b8b645143e34020a86dcc60494609f4d513ddd09d1b1efa4c21067cf12e
+size 267852461

checkpoint-1800/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d7cfadc429050136476e4ad7ac18ced8e8bbc5432cbb43aefadbd026b218526
+size 14575

checkpoint-1800/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9ba239a84321c2abae169d7cdc34c2fbcb36b18cb56d4fbbc439409fba7c93a
+size 627

checkpoint-1800/special_tokens_map.json

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

checkpoint-1800/tokenizer_config.json

@@ -0,0 +1,13 @@
+{
+  "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": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}

checkpoint-1800/trainer_state.json

@@ -0,0 +1,84 @@
+{
+  "best_metric": 0.8698014238103634,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-stsb/checkpoint-720",
+  "epoch": 5.0,
+  "global_step": 1800,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.6088840961456299,
+      "eval_pearson": 0.8561182619213418,
+      "eval_runtime": 2.024,
+      "eval_samples_per_second": 741.123,
+      "eval_spearmanr": 0.8534001593563577,
+      "eval_steps_per_second": 46.444,
+      "step": 360
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 2.1666666666666667e-05,
+      "loss": 0.9675,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.5479667782783508,
+      "eval_pearson": 0.8698014238103634,
+      "eval_runtime": 2.0245,
+      "eval_samples_per_second": 740.939,
+      "eval_spearmanr": 0.8658536661602265,
+      "eval_steps_per_second": 46.432,
+      "step": 720
+    },
+    {
+      "epoch": 2.78,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 0.3413,
+      "step": 1000
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.5835986733436584,
+      "eval_pearson": 0.8689650534527504,
+      "eval_runtime": 2.0226,
+      "eval_samples_per_second": 741.633,
+      "eval_spearmanr": 0.8660077089710224,
+      "eval_steps_per_second": 46.476,
+      "step": 1080
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.598821759223938,
+      "eval_pearson": 0.867708427260652,
+      "eval_runtime": 2.0301,
+      "eval_samples_per_second": 738.883,
+      "eval_spearmanr": 0.8645612951627347,
+      "eval_steps_per_second": 46.303,
+      "step": 1440
+    },
+    {
+      "epoch": 4.17,
+      "learning_rate": 4.9999999999999996e-06,
+      "loss": 0.1884,
+      "step": 1500
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 0.5626319050788879,
+      "eval_pearson": 0.8685442874565625,
+      "eval_runtime": 2.0298,
+      "eval_samples_per_second": 738.996,
+      "eval_spearmanr": 0.8650090339054896,
+      "eval_steps_per_second": 46.31,
+      "step": 1800
+    }
+  ],
+  "max_steps": 1800,
+  "num_train_epochs": 5,
+  "total_flos": 461713093280400.0,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1800/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6acf1dfa4bac406a4ad91d918e608946483ca5219fbbdd80e083c24cf5c1c91f
+size 3643