Training in progress, epoch 3

checkpoint-1080/config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "bert-base-cased",
+  "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": "4.11.0.dev0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 28996
+}

checkpoint-1080/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74a0428d566bf2612d992d0356a417474f057f1e94b408a75887a01500961fb2
+size 866604829

checkpoint-1080/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:419f92630e6c3b339faa54ba4a1917f4bcc6e81d1b1c37d9749dfff49abfc52f
+size 433328301

checkpoint-1080/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e33452d79fe2971dcbfdcffea9d2d0a3605071c359254914fc09924efbef32d4
+size 14503

checkpoint-1080/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:527295045d2586065b1903e97996e4dbfc999e3944d447aefd0d55843d2c92d2
+size 623

checkpoint-1080/special_tokens_map.json

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

checkpoint-1080/tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": false, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "bert-base-cased", "tokenizer_class": "BertTokenizer"}

checkpoint-1080/trainer_state.json

@@ -0,0 +1,67 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "global_step": 1080,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 1.1174,
+      "step": 360
+    },
+    {
+      "epoch": 1.0,
+      "eval_combined_score": 0.8815940360468737,
+      "eval_loss": 0.5000496506690979,
+      "eval_pearson": 0.8832304460348288,
+      "eval_runtime": 15.5329,
+      "eval_samples_per_second": 96.569,
+      "eval_spearmanr": 0.8799576260589187,
+      "eval_steps_per_second": 12.103,
+      "step": 360
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 0.3835,
+      "step": 720
+    },
+    {
+      "epoch": 2.0,
+      "eval_combined_score": 0.8901405153644659,
+      "eval_loss": 0.4672209620475769,
+      "eval_pearson": 0.8914800693934992,
+      "eval_runtime": 15.3324,
+      "eval_samples_per_second": 97.832,
+      "eval_spearmanr": 0.8888009613354327,
+      "eval_steps_per_second": 12.262,
+      "step": 720
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 0.0,
+      "loss": 0.2388,
+      "step": 1080
+    },
+    {
+      "epoch": 3.0,
+      "eval_combined_score": 0.8911934607933856,
+      "eval_loss": 0.48608845472335815,
+      "eval_pearson": 0.8925961944446151,
+      "eval_runtime": 15.3291,
+      "eval_samples_per_second": 97.853,
+      "eval_spearmanr": 0.8897907271421561,
+      "eval_steps_per_second": 12.264,
+      "step": 1080
+    }
+  ],
+  "max_steps": 1080,
+  "num_train_epochs": 3,
+  "total_flos": 4537835628033024.0,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1080/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c6a436467da6af93ad95e8ae44ad2dd506ae1137356476d8737342b024b9aaf
+size 2799

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c6c137dec9d2e881fff47a12da0f9723ac4643bc6f0e11b2c008e5502c116d0
+oid sha256:419f92630e6c3b339faa54ba4a1917f4bcc6e81d1b1c37d9749dfff49abfc52f
 size 433328301

runs/Sep19_13-18-31_patrick-general-gpu/events.out.tfevents.1632057532.patrick-general-gpu.502385.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8eeb96ec956bf19a259c4abdae963f273d04b2c5fd108520ddcc494c52b79fa4
-size 4368
+oid sha256:a1f8fa42dbca16738cc0bacc6e4126c5b4f724d3f61a549777a2eec76ae11ec3
+size 4958