Training in progress, epoch 4

checkpoint-920/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-920/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d07c81836b4c0c0239db0603df038ec00b552ad1db905b4a0eaa92e481c6c36
+size 866610973

checkpoint-920/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ffc0e9faca4eef0d93b0e47c10f4ccd967150c7f0974c64dace7265c554bf767
+size 433331373

checkpoint-920/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:841d9d08b3f556819c25ac6cab77c3e7a70c4b7c70f6e8e7ea2fb8f6c5cdee57
+size 14503

checkpoint-920/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fadee31c0eb4f0928fb98267943debe14aaca6d7c279adf97c5bce0375a4f71e
+size 623

checkpoint-920/special_tokens_map.json

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

checkpoint-920/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-920/trainer_state.json

@@ -0,0 +1,84 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.0,
+  "global_step": 920,
+  "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
+    }
+  ],
+  "max_steps": 1150,
+  "num_train_epochs": 5,
+  "total_flos": 3860365404241920.0,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-920/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 sha256:4fabae069113093bf77363be8d61ecf606460e2e1aad081ad6a4d49e997ec672
+oid sha256:ffc0e9faca4eef0d93b0e47c10f4ccd967150c7f0974c64dace7265c554bf767
 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:b8ff62853c23f71bb9ec7bbc8f8b73704f7e6dd5089af01b7a620a147287aff9
-size 4998
+oid sha256:1570720fe1bebd27a5dab278309a24fd10d7e0275157509748a4b43fa082c7c2
+size 5582