Training in progress, epoch 5

checkpoint-4585/config.json

@@ -0,0 +1,42 @@
+{
+  "_name_or_path": "bert-large-cased",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "finetuning_task": "mrpc",
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "not_equivalent",
+    "1": "equivalent"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "equivalent": 1,
+    "not_equivalent": 0
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "pooler_fc_size": 768,
+  "pooler_num_attention_heads": 12,
+  "pooler_num_fc_layers": 3,
+  "pooler_size_per_head": 128,
+  "pooler_type": "first_token_transform",
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.11.0.dev0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 28996
+}

checkpoint-4585/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be80d7210646c4c587defe43009a233e4b43ba233093ed2a62826fc6630f6ee3
+size 2668879261

checkpoint-4585/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99588fce1233c87cbcbf252b411f104744217d89bedddb0b8367c12874458236
+size 1334486957

checkpoint-4585/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3cdbfb606ed13e6117ab79360a7cf39c68e985232f8ee7fcdea08a3fde6d3d67
+size 14503

checkpoint-4585/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48688126a59fae40e267a1bd071af22215d80a668d94a1f68f1b2d61d4012a9e
+size 623

checkpoint-4585/special_tokens_map.json

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

checkpoint-4585/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-large-cased", "tokenizer_class": "BertTokenizer"}

checkpoint-4585/trainer_state.json

@@ -0,0 +1,101 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.0,
+  "global_step": 4585,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 0.6441,
+      "step": 917
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6838235294117647,
+      "eval_combined_score": 0.7480253018237863,
+      "eval_f1": 0.8122270742358079,
+      "eval_loss": 0.6369990706443787,
+      "eval_runtime": 13.1449,
+      "eval_samples_per_second": 31.039,
+      "eval_steps_per_second": 3.88,
+      "step": 917
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 1.2e-05,
+      "loss": 0.6451,
+      "step": 1834
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6838235294117647,
+      "eval_combined_score": 0.7480253018237863,
+      "eval_f1": 0.8122270742358079,
+      "eval_loss": 0.6552556157112122,
+      "eval_runtime": 13.1957,
+      "eval_samples_per_second": 30.919,
+      "eval_steps_per_second": 3.865,
+      "step": 1834
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 0.6428,
+      "step": 2751
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.6838235294117647,
+      "eval_combined_score": 0.7480253018237863,
+      "eval_f1": 0.8122270742358079,
+      "eval_loss": 0.6332471966743469,
+      "eval_runtime": 13.1447,
+      "eval_samples_per_second": 31.039,
+      "eval_steps_per_second": 3.88,
+      "step": 2751
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 0.6476,
+      "step": 3668
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.6838235294117647,
+      "eval_combined_score": 0.7480253018237863,
+      "eval_f1": 0.8122270742358079,
+      "eval_loss": 0.6247974634170532,
+      "eval_runtime": 13.1288,
+      "eval_samples_per_second": 31.077,
+      "eval_steps_per_second": 3.885,
+      "step": 3668
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 0.0,
+      "loss": 0.6499,
+      "step": 4585
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.6838235294117647,
+      "eval_combined_score": 0.7480253018237863,
+      "eval_f1": 0.8122270742358079,
+      "eval_loss": 0.6273975968360901,
+      "eval_runtime": 13.1363,
+      "eval_samples_per_second": 31.059,
+      "eval_steps_per_second": 3.882,
+      "step": 4585
+    }
+  ],
+  "max_steps": 4585,
+  "num_train_epochs": 5,
+  "total_flos": 1.709162120343552e+16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-4585/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b497fdf35eb49ca9dc4a49ae7289bd94d2105c9dfbca8e37d973c3bb6758058d
+size 2799

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c08bf7442608b6a2697ed2786c764408299d061d63e1eac5c2c4d34677aa343b
+oid sha256:99588fce1233c87cbcbf252b411f104744217d89bedddb0b8367c12874458236
 size 1334486957

runs/Sep22_06-07-26_patrick-general-gpu/events.out.tfevents.1632290866.patrick-general-gpu.751022.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e348dd702912706743d2e5010fc98144c5b6a38731aaae094e36ca639653c654
-size 5777
+oid sha256:f20be43a1789526d4ddd05d0eeaf4160c5fac433a3b0bd05a031699013abcbd2
+size 6361