Training in progress, epoch 3

checkpoint-690/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": "mrpc",
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "not_equivalent",
+    "1": "equivalent"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "equivalent": 1,
+    "not_equivalent": 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-690/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44333210a41f8f722a14c634c132a6971c7505fded43615215c51b68d423ca20
+size 866610973

checkpoint-690/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4fabae069113093bf77363be8d61ecf606460e2e1aad081ad6a4d49e997ec672
+size 433331373

checkpoint-690/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f0fbfcf3d17fc9addecbbd47e7c29d55cdda8c9cff807dc50dcddef421176d8
+size 14503

checkpoint-690/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0cf3ce8e7365e59eba2550cf0339839704f78b96897c1e66c20f680f3730989
+size 623

checkpoint-690/special_tokens_map.json

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

checkpoint-690/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-690/trainer_state.json

@@ -0,0 +1,67 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "global_step": 690,
+  "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": 0.5981,
+      "step": 230
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7892156862745098,
+      "eval_combined_score": 0.8227014886222047,
+      "eval_f1": 0.8561872909698997,
+      "eval_loss": 0.45800894498825073,
+      "eval_runtime": 4.1966,
+      "eval_samples_per_second": 97.221,
+      "eval_steps_per_second": 12.153,
+      "step": 230
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 1.2e-05,
+      "loss": 0.3739,
+      "step": 460
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8480392156862745,
+      "eval_combined_score": 0.8711185839523523,
+      "eval_f1": 0.89419795221843,
+      "eval_loss": 0.38060691952705383,
+      "eval_runtime": 4.1663,
+      "eval_samples_per_second": 97.928,
+      "eval_steps_per_second": 12.241,
+      "step": 460
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 0.1991,
+      "step": 690
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8529411764705882,
+      "eval_combined_score": 0.8743872549019608,
+      "eval_f1": 0.8958333333333334,
+      "eval_loss": 0.4879474937915802,
+      "eval_runtime": 4.1609,
+      "eval_samples_per_second": 98.056,
+      "eval_steps_per_second": 12.257,
+      "step": 690
+    }
+  ],
+  "max_steps": 1150,
+  "num_train_epochs": 5,
+  "total_flos": 2895274053181440.0,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-690/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8281bedb20092f0f04f54b17beca2ef4df4174a4f98ca39b9bf37f14eac3ae9
+size 2799

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:965d23effd7512f42278b810a84a409210dd8e32d685053be959c109af316e2e
+oid sha256:4fabae069113093bf77363be8d61ecf606460e2e1aad081ad6a4d49e997ec672
 size 433331373

runs/Sep16_16-48-11_patrick-general-gpu/events.out.tfevents.1631810908.patrick-general-gpu.172718.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb3b565cba8d5deb5daf3ef1fa0ef067e1b9e32dadd7e958f5013ae9eb76e3a9
-size 4414
+oid sha256:b8ff62853c23f71bb9ec7bbc8f8b73704f7e6dd5089af01b7a620a147287aff9
+size 4998