Training in progress, epoch 3

checkpoint-6414/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": "cola",
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "unacceptable",
+    "1": "acceptable"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "acceptable": 1,
+    "unacceptable": 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-6414/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64246163368e654fb79fe0194f156f48ca9f2ccee7f22e030ad861e34efd4809
+size 2668879261

checkpoint-6414/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85a3d8c5a334a51b6bf1fb0cf19a5280b9adcae39fefd62c0530fd13477d4027
+size 1334486957

checkpoint-6414/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57997cd078a4019b0088799585d0eae30e989d31e90c08468fa2a9d4d8b50df1
+size 14503

checkpoint-6414/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82054c3b19d4fadc2274f65789c87acd8de83c6e17e37efe0b1a438591a5e04f
+size 623

checkpoint-6414/special_tokens_map.json

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

checkpoint-6414/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-6414/trainer_state.json

@@ -0,0 +1,61 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "global_step": 6414,
+  "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": 0.5533,
+      "step": 2138
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.794291079044342,
+      "eval_matthews_correlation": 0.44394615350761574,
+      "eval_runtime": 33.9254,
+      "eval_samples_per_second": 30.744,
+      "eval_steps_per_second": 3.861,
+      "step": 2138
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 0.5004,
+      "step": 4276
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.7272064685821533,
+      "eval_matthews_correlation": 0.5678267214677118,
+      "eval_runtime": 33.839,
+      "eval_samples_per_second": 30.822,
+      "eval_steps_per_second": 3.871,
+      "step": 4276
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 0.0,
+      "loss": 0.2865,
+      "step": 6414
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.8384876251220703,
+      "eval_matthews_correlation": 0.5957317644481708,
+      "eval_runtime": 33.7835,
+      "eval_samples_per_second": 30.873,
+      "eval_steps_per_second": 3.878,
+      "step": 6414
+    }
+  ],
+  "max_steps": 6414,
+  "num_train_epochs": 3,
+  "total_flos": 2.3906835263453184e+16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-6414/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5e08ee36c363c8414e6988b7d0bd6135c0abd07da04ef00bf126d316cb97ce7
+size 2799

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c0f96175681192f904f6107cea32d96fac92b064f6896fb6d019b07ce100f822
+oid sha256:85a3d8c5a334a51b6bf1fb0cf19a5280b9adcae39fefd62c0530fd13477d4027
 size 1334486957

runs/Sep20_22-32-10_patrick-general-gpu/events.out.tfevents.1632177149.patrick-general-gpu.544040.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b28400bc539e8a19bf5e36c98815999c5cce4e63ef088136737313ca4c9bb24e
-size 4421
+oid sha256:dd0fc8d4a8c65e1994fe02ff89e0e2bbabc0a3d4439852b80a64f276d399a4f3
+size 4913