Training in progress, epoch 3

checkpoint-1605/config.json

@@ -0,0 +1,36 @@
+{
+  "_name_or_path": "bert-base-cased",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "finetuning_task": "cola",
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "unacceptable",
+    "1": "acceptable"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "acceptable": 1,
+    "unacceptable": 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": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.11.0.dev0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 28996
+}

checkpoint-1605/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f235a1c260e34df3bd5c2d4ccb8d05362b6fa614863b0eeb46c09a44d25ba532
+size 866610973

checkpoint-1605/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe2163d3552f2846fd747ceaae7357dd4cd629634aa16df59974a0c97bdb6a84
+size 433331373

checkpoint-1605/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5391cf57c0f5c8f846b9d8ef7acacef437d581ab551a6b897300a4c03fa29bd0
+size 14503

checkpoint-1605/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1acca92a8b10bd06cc866eafb8aeb9d4f85bcdb2d57143bebcfe2bc573e5d33a
+size 623

checkpoint-1605/special_tokens_map.json

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

checkpoint-1605/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-1605/trainer_state.json

@@ -0,0 +1,61 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "global_step": 1605,
+  "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": 0.4921,
+      "step": 535
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.5283351540565491,
+      "eval_matthews_correlation": 0.5068375331988826,
+      "eval_runtime": 10.6748,
+      "eval_samples_per_second": 97.706,
+      "eval_steps_per_second": 12.272,
+      "step": 535
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 0.2837,
+      "step": 1070
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.5132979154586792,
+      "eval_matthews_correlation": 0.5521390429003941,
+      "eval_runtime": 10.6848,
+      "eval_samples_per_second": 97.616,
+      "eval_steps_per_second": 12.26,
+      "step": 1070
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 0.0,
+      "loss": 0.1775,
+      "step": 1605
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.6747468709945679,
+      "eval_matthews_correlation": 0.5956649094312695,
+      "eval_runtime": 10.6837,
+      "eval_samples_per_second": 97.625,
+      "eval_steps_per_second": 12.262,
+      "step": 1605
+    }
+  ],
+  "max_steps": 1605,
+  "num_train_epochs": 3,
+  "total_flos": 6749587903150080.0,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1605/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b87834190b4349f44daee6994b83db673da78267ee1f4f353723565d6835dfed
+size 2799

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1796072e33fe7d0b6619f82a26740bc357d2d43a50a344bca97a954d0ba103e0
+oid sha256:fe2163d3552f2846fd747ceaae7357dd4cd629634aa16df59974a0c97bdb6a84
 size 433331373

runs/Sep16_18-47-00_patrick-general-gpu/events.out.tfevents.1631818036.patrick-general-gpu.195949.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1efb3571f61a396a973c665f9a7c422577f2bf4b749afa3256b758e992dd8deb
-size 4226
+oid sha256:7c447af10216b49105989d4df5e3389964565ffe80b87aa63e1eddc7f19ce119
+size 4718