Training in progress, epoch 1

checkpoint-20000/config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "bert-base-uncased",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "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": "4.27.3",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

checkpoint-20000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:969ee019b9d403f39a851ee5c816071c3502efe1331c8f7a3cec7a65a1a5a900
+size 875988101

checkpoint-20000/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71291b79600fe0636c503d1578f01d2c4e551e4fee7b2da92f1c7e4a945af2b2
+size 438007925

checkpoint-20000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:342c160c7700f2a0e8d98f641c5b3e45a9caf17aad7fad4df802c20f8fa74538
+size 14575

checkpoint-20000/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b260b097b335330dbec1df86d40d8f4af3db8f42d0f8ac62f7315174c83ab65f
+size 557

checkpoint-20000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:548f93d9dd774745bdfbd8a130876e11cc023ddd8dfc4f3fa6e5d7dfd432f31e
+size 627

checkpoint-20000/special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

checkpoint-20000/tokenizer_config.json

@@ -0,0 +1,13 @@
+{
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "special_tokens_map_file": null,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

checkpoint-20000/trainer_state.json

@@ -0,0 +1,266 @@
+{
+  "best_metric": 0.7430530679085001,
+  "best_model_checkpoint": "bertbase-uncased-2-actual/checkpoint-20000",
+  "epoch": 1.0,
+  "global_step": 20000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03,
+      "learning_rate": 9.751e-06,
+      "loss": 0.6643,
+      "step": 500
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 9.501000000000001e-06,
+      "loss": 0.6215,
+      "step": 1000
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 9.251000000000002e-06,
+      "loss": 0.6165,
+      "step": 1500
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 9.0015e-06,
+      "loss": 0.6052,
+      "step": 2000
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 8.7515e-06,
+      "loss": 0.5804,
+      "step": 2500
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 8.5015e-06,
+      "loss": 0.5753,
+      "step": 3000
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 8.2515e-06,
+      "loss": 0.601,
+      "step": 3500
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 8.001500000000001e-06,
+      "loss": 0.5831,
+      "step": 4000
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 7.7515e-06,
+      "loss": 0.5854,
+      "step": 4500
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 7.502e-06,
+      "loss": 0.5882,
+      "step": 5000
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 7.252e-06,
+      "loss": 0.5659,
+      "step": 5500
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 7.002000000000001e-06,
+      "loss": 0.564,
+      "step": 6000
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 6.752000000000001e-06,
+      "loss": 0.5692,
+      "step": 6500
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 6.502000000000001e-06,
+      "loss": 0.5755,
+      "step": 7000
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 6.2520000000000004e-06,
+      "loss": 0.5547,
+      "step": 7500
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 6.002e-06,
+      "loss": 0.5676,
+      "step": 8000
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 5.752500000000001e-06,
+      "loss": 0.5788,
+      "step": 8500
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 5.5025e-06,
+      "loss": 0.5486,
+      "step": 9000
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 5.2525e-06,
+      "loss": 0.5601,
+      "step": 9500
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 5.0025e-06,
+      "loss": 0.5331,
+      "step": 10000
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 4.752500000000001e-06,
+      "loss": 0.5659,
+      "step": 10500
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 4.5025000000000005e-06,
+      "loss": 0.5652,
+      "step": 11000
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 4.2525e-06,
+      "loss": 0.5529,
+      "step": 11500
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 4.0025e-06,
+      "loss": 0.5531,
+      "step": 12000
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 3.7530000000000003e-06,
+      "loss": 0.5556,
+      "step": 12500
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 3.503e-06,
+      "loss": 0.5323,
+      "step": 13000
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 3.253e-06,
+      "loss": 0.5809,
+      "step": 13500
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 3.0030000000000003e-06,
+      "loss": 0.5367,
+      "step": 14000
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 2.753e-06,
+      "loss": 0.5706,
+      "step": 14500
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 2.5040000000000005e-06,
+      "loss": 0.5386,
+      "step": 15000
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 2.254e-06,
+      "loss": 0.552,
+      "step": 15500
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 2.004e-06,
+      "loss": 0.5468,
+      "step": 16000
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.754e-06,
+      "loss": 0.5546,
+      "step": 16500
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.5045000000000002e-06,
+      "loss": 0.5495,
+      "step": 17000
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 1.2545000000000002e-06,
+      "loss": 0.5439,
+      "step": 17500
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 1.0045e-06,
+      "loss": 0.562,
+      "step": 18000
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 7.545000000000001e-07,
+      "loss": 0.5589,
+      "step": 18500
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 5.045000000000001e-07,
+      "loss": 0.5585,
+      "step": 19000
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 2.545e-07,
+      "loss": 0.5288,
+      "step": 19500
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 4.500000000000001e-09,
+      "loss": 0.5205,
+      "step": 20000
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.74895,
+      "eval_f1": 0.7430530679085001,
+      "eval_loss": 0.5389962196350098,
+      "eval_runtime": 136.8617,
+      "eval_samples_per_second": 146.133,
+      "eval_steps_per_second": 36.533,
+      "step": 20000
+    }
+  ],
+  "max_steps": 20000,
+  "num_train_epochs": 1,
+  "total_flos": 6597569324250480.0,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-20000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b0835cd2de3cca5b5b96eebbcbec35c722f15a3b873f32c65766107e49f34b2
+size 3643

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "bert-base-uncased",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "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": "4.27.3",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71291b79600fe0636c503d1578f01d2c4e551e4fee7b2da92f1c7e4a945af2b2
+size 438007925

runs/Apr02_07-05-46_363d0ca62f6d/1680419156.9896233/events.out.tfevents.1680419156.363d0ca62f6d.23.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d03c36bd587a21a420bd7b67c73a6aa818a4ddb5231e1249a20b00f72a7909d8
+size 5815

runs/Apr02_07-05-46_363d0ca62f6d/events.out.tfevents.1680419156.363d0ca62f6d.23.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83a5ce7412604c76cf2b07d67ecdf3d36ffb04949a575da5a4368c5155794cd5
+size 10626

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,13 @@
+{
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "special_tokens_map_file": null,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b0835cd2de3cca5b5b96eebbcbec35c722f15a3b873f32c65766107e49f34b2
+size 3643