Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1282c2da93a10f875761d10363fbb5ab67026b95c76e9f3a5e2276759968fdab
+oid sha256:a99f8e2f451020963cc862630e225027c3a59459785f9d414c18cf527bf0df0c
 size 437958648

run-0/checkpoint-78/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:983079b3c184b69976e3e922ab414401c8dd25219df83429805a59bd095053dd
+oid sha256:3e73a6a94dabb0efcd0fee951b4bb269e4bcbfd86b038cdb1f05f69be224987f
 size 437958648

run-0/checkpoint-78/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d628c74667cf811dff5a038d36527982b4b400445b151449a6ee357bf4659fe
+oid sha256:a0b9e49c0f111404bf3bb75f8aa46ebfe532888c0089618f9fee7181e88ff866
 size 876038394

run-0/checkpoint-78/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d5ea817570194d8e0e85204e3f66b3bc8aa9d4419d9d0feda444e6993af6a1e
+oid sha256:ca3cccd11b77d5d203a4466ecd61d7de95628051c1e10e12242d864bf481cb9f
 size 1064

run-0/checkpoint-78/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a0f87a8069f7eac17becb3abe4f91c5f6d7edf26c85de5367deed4737c39966
+oid sha256:60d0f60e33d97e1e0e5b10975bfd55ba2fc1145f2d1c8aa831504b116b1fc39f
 size 5432

run-1/checkpoint-39/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aab3944602ff17de830dca74c2c3bdcf3ca2357a2c3946ff27d56be6f4489301
+oid sha256:9d59550c1dea5879e3a1aec7065f8590e7113f652b84472de96c6c9c1e27d705
 size 437958648

run-1/checkpoint-39/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4fac6b678ea4e78123eebb2a57863cdcb7d5a6c102493d6beaba5f58b16a9ac7
+oid sha256:e45c157362ad69595478c4daeb665be40748e26b910672812955c6656252fe88
 size 876038394

run-1/checkpoint-39/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e728d62168539e162cfd12980713e2c0a527faec5a51cc3eef8e80293c895d1
+oid sha256:1357d27d6dcc07f61181342425227d9ce57d5241166fc1b33bb5b5fbf50cf5e6
 size 1064

run-1/checkpoint-39/trainer_state.json

@@ -12,10 +12,10 @@
     {
       "epoch": 1.0,
       "eval_accuracy": 0.4729241877256318,
-      "eval_loss": 0.7139573693275452,
-      "eval_runtime": 1.9882,
-      "eval_samples_per_second": 139.325,
-      "eval_steps_per_second": 4.527,
+      "eval_loss": 0.7221417427062988,
+      "eval_runtime": 2.0129,
+      "eval_samples_per_second": 137.615,
+      "eval_steps_per_second": 2.484,
       "step": 39
     }
   ],
@@ -40,8 +40,8 @@
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": {
-    "dropout_rate": 0.32964696479911365,
-    "learning_rate": 2.707454604407671e-06,
+    "dropout_rate": 0.1016397017464123,
+    "learning_rate": 1.2050894848379789e-06,
     "max_seq_length": 256,
     "num_train_epochs": 2,
     "per_device_train_batch_size": 64

run-1/checkpoint-39/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f20413c6f4f1baa91041a9640292f4bb307c9f460181077fcc3c0a98556ef3cb
+oid sha256:8b58a714467b799b6a0ccb9002f056087cc69c203d1b9db91e56a40aedfe1659
 size 5432

run-1/checkpoint-78/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:54d7b95993061f4281902d35e5f3f462aad9fc8d79bebc829b5984d7b9f88290
+oid sha256:3934f42aedd032f285b4f5eb2d0bb0a9fb0739bfcdaf37c0d888b00008339c9b
 size 437958648

run-1/checkpoint-78/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7388507902d618d4a5636970d22e834775a6fc97b9789f3763f810c1ba3ce5a0
+oid sha256:650808565c7da7432db3554c69ce9024029ee48e9fcbfcba3fd875017715c8a6
 size 876038394

run-1/checkpoint-78/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:755c3933ed6cf784e3b07188774fc84009f398046b2422fd5db2b326826542cd
+oid sha256:bf714d04f8d03c499d62b8995b10cdcefa51102cbc9dc743e413e17551e3d5da
 size 1064

run-1/checkpoint-78/trainer_state.json

@@ -12,19 +12,19 @@
     {
       "epoch": 1.0,
       "eval_accuracy": 0.4729241877256318,
-      "eval_loss": 0.7139573693275452,
-      "eval_runtime": 1.9882,
-      "eval_samples_per_second": 139.325,
-      "eval_steps_per_second": 4.527,
+      "eval_loss": 0.7221417427062988,
+      "eval_runtime": 2.0129,
+      "eval_samples_per_second": 137.615,
+      "eval_steps_per_second": 2.484,
       "step": 39
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.4657039711191336,
-      "eval_loss": 0.7088006138801575,
-      "eval_runtime": 1.922,
-      "eval_samples_per_second": 144.117,
-      "eval_steps_per_second": 4.683,
+      "eval_accuracy": 0.4729241877256318,
+      "eval_loss": 0.7191658020019531,
+      "eval_runtime": 2.189,
+      "eval_samples_per_second": 126.544,
+      "eval_steps_per_second": 2.284,
       "step": 78
     }
   ],
@@ -49,8 +49,8 @@
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": {
-    "dropout_rate": 0.32964696479911365,
-    "learning_rate": 2.707454604407671e-06,
+    "dropout_rate": 0.1016397017464123,
+    "learning_rate": 1.2050894848379789e-06,
     "max_seq_length": 256,
     "num_train_epochs": 2,
     "per_device_train_batch_size": 64

run-1/checkpoint-78/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f20413c6f4f1baa91041a9640292f4bb307c9f460181077fcc3c0a98556ef3cb
+oid sha256:8b58a714467b799b6a0ccb9002f056087cc69c203d1b9db91e56a40aedfe1659
 size 5432

run-2/checkpoint-39/config.json

@@ -0,0 +1,26 @@
+{
+  "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": "4.50.3",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-2/checkpoint-39/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a99f8e2f451020963cc862630e225027c3a59459785f9d414c18cf527bf0df0c
+size 437958648

run-2/checkpoint-39/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7aa3db6cca0c2b46f6bb3cdc4192524791925aae96afeefadc5fc800c61f8590
+size 876038394

run-2/checkpoint-39/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb9d75225831e9955fede3b2d004809f8a35dbd2208354c70b53a96923288fdc
+size 14244

run-2/checkpoint-39/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51d0b00f673d1afb7ad79ca355e4162ad1ab39a84b5123bbca794c2d33f68972
+size 1064

run-2/checkpoint-39/special_tokens_map.json

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

run-2/checkpoint-39/tokenizer_config.json

@@ -0,0 +1,56 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

run-2/checkpoint-39/trainer_state.json

@@ -0,0 +1,49 @@
+{
+  "best_global_step": 39,
+  "best_metric": 0.4693140794223827,
+  "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_1/run-2/checkpoint-39",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 39,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.4693140794223827,
+      "eval_loss": 0.7152564525604248,
+      "eval_runtime": 2.0411,
+      "eval_samples_per_second": 135.708,
+      "eval_steps_per_second": 2.45,
+      "step": 39
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 39,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": {
+    "dropout_rate": 0.3750648367717625,
+    "learning_rate": 3.89885805363765e-06,
+    "max_seq_length": 256,
+    "num_train_epochs": 1,
+    "per_device_train_batch_size": 64
+  }
+}

run-2/checkpoint-39/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9262f528bfa4fcd0f8292f8cee23dda4c29b4b3acbfaca897c50fe6856e9e89
+size 5432

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60d0f60e33d97e1e0e5b10975bfd55ba2fc1145f2d1c8aa831504b116b1fc39f
+oid sha256:d9262f528bfa4fcd0f8292f8cee23dda4c29b4b3acbfaca897c50fe6856e9e89
 size 5432