Training in progress, epoch 5

checkpoint-1150/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-1150/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33f254c5404d3833932a4004b03dfd35dc1dc07ebd0413060508e7912873fca8
+size 866610973

checkpoint-1150/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5fa5d9dd2528952def71f866b05166fdbc8f697f69e0c0ce1b99429b369149bb
+size 433331373

checkpoint-1150/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2441cff2d79c2f95778be91088706e3936e5f0ade6204f40fbae3cc614dac5d3
+size 14503

checkpoint-1150/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d59441f08c42483b29933513683055a9830b6b0f5f682588da8f3b8a6e40bc9
+size 623

checkpoint-1150/special_tokens_map.json

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

checkpoint-1150/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-1150/trainer_state.json

@@ -0,0 +1,101 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.0,
+  "global_step": 1150,
+  "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
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 0.1286,
+      "step": 920
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8529411764705882,
+      "eval_combined_score": 0.8757949125596185,
+      "eval_f1": 0.8986486486486487,
+      "eval_loss": 0.6342187523841858,
+      "eval_runtime": 4.165,
+      "eval_samples_per_second": 97.959,
+      "eval_steps_per_second": 12.245,
+      "step": 920
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 0.0,
+      "loss": 0.0812,
+      "step": 1150
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.8602941176470589,
+      "eval_combined_score": 0.8814291101055808,
+      "eval_f1": 0.9025641025641027,
+      "eval_loss": 0.7132137417793274,
+      "eval_runtime": 4.1564,
+      "eval_samples_per_second": 98.161,
+      "eval_steps_per_second": 12.27,
+      "step": 1150
+    }
+  ],
+  "max_steps": 1150,
+  "num_train_epochs": 5,
+  "total_flos": 4825456755302400.0,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1150/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:ffc0e9faca4eef0d93b0e47c10f4ccd967150c7f0974c64dace7265c554bf767
+oid sha256:5fa5d9dd2528952def71f866b05166fdbc8f697f69e0c0ce1b99429b369149bb
 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 sha256:1570720fe1bebd27a5dab278309a24fd10d7e0275157509748a4b43fa082c7c2
-size 5582
+oid sha256:a3a12084a94ab8c6c0ce3e6c8493208c9c5f8e2d395018b431b36193d968fddc
+size 6166