Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:63afbd2bee33889c42d7b9c7a39195eb4164da436a606381544b6e523dc60f3c
+oid sha256:959d57e387671c4c4a9119a9ba868aee09c1ffc5f9a7827a5d1172cd6fe85eed
 size 437958648

run-1/checkpoint-78/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dcb68bc7ff852a5d13734eaca10fe516e98ffe17dde64dbacb171e33a223c644
+oid sha256:3706c9f0cbd2e6c64bf8c363379c367bf91e8cbab1a4fac29773a5f9cf9360b1
 size 437958648

run-1/checkpoint-78/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b3e8b8ed5b10a09a1aaaa9944baed1e17ca4c87a4afb998e8ce11dfde75e659
+oid sha256:78ba53cc5531e0959e0a3b998a45022e4425b3f040501c54625064bb96079d22
 size 876038394

run-1/checkpoint-78/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:00f50f59a23557f937f2829c75fd144723e73b303da30d483f6a2bc596b131ef
+oid sha256:5a742d2c1b0c0de7337763219c339041494e1753af0074f32de6839513ee1d4e
 size 14244

run-1/checkpoint-78/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d3bc91ddbbd84810ed5453ce1dd44da4fdbe8b608c504fc9b27f76ebc6fe3ed0
+oid sha256:52042878a195f196916f08a2df87bb5abc6f00902f5a591e2449264f6541d0c7
 size 1064

run-1/checkpoint-78/tokenizer.json

@@ -2,11 +2,20 @@
   "version": "1.0",
   "truncation": {
     "direction": "Right",
-    "max_length": 512,
+    "max_length": 256,
     "strategy": "LongestFirst",
     "stride": 0
   },
-  "padding": null,
+  "padding": {
+    "strategy": {
+      "Fixed": 256
+    },
+    "direction": "Right",
+    "pad_to_multiple_of": null,
+    "pad_id": 0,
+    "pad_type_id": 0,
+    "pad_token": "[PAD]"
+  },
   "added_tokens": [
     {
       "id": 0,

run-1/checkpoint-78/trainer_state.json

@@ -1,7 +1,7 @@
 {
-  "best_global_step": 39,
-  "best_metric": 0.4693140794223827,
-  "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_3/run-1/checkpoint-39",
+  "best_global_step": 78,
+  "best_metric": 0.5270758122743683,
+  "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_3/run-1/checkpoint-78",
   "epoch": 2.0,
   "eval_steps": 500,
   "global_step": 78,
@@ -11,27 +11,27 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.4693140794223827,
-      "eval_loss": 0.7058208584785461,
-      "eval_runtime": 2.8637,
-      "eval_samples_per_second": 96.729,
-      "eval_steps_per_second": 1.746,
+      "eval_accuracy": 0.4729241877256318,
+      "eval_loss": 0.7516165375709534,
+      "eval_runtime": 3.8016,
+      "eval_samples_per_second": 72.865,
+      "eval_steps_per_second": 1.315,
       "step": 39
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.4657039711191336,
-      "eval_loss": 0.6973794102668762,
-      "eval_runtime": 2.8482,
-      "eval_samples_per_second": 97.255,
-      "eval_steps_per_second": 1.756,
+      "eval_accuracy": 0.5270758122743683,
+      "eval_loss": 0.6921609044075012,
+      "eval_runtime": 3.9174,
+      "eval_samples_per_second": 70.711,
+      "eval_steps_per_second": 1.276,
       "step": 78
     }
   ],
   "logging_steps": 500,
-  "max_steps": 117,
+  "max_steps": 78,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 3,
+  "num_train_epochs": 2,
   "save_steps": 500,
   "stateful_callbacks": {
     "TrainerControl": {
@@ -40,7 +40,7 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
@@ -49,8 +49,8 @@
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": {
-    "learning_rate": 4.078731299580254e-06,
-    "num_train_epochs": 3,
+    "learning_rate": 0.00033946339006054595,
+    "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:c66a3d7315e7f83d1445c5e75259f488e1a408ab0d6bc08d3b16faa3da147c81
+oid sha256:d9b368af41ce4afd44935db5297324010c04a9a83b0a818f781da96fa84252ba
 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 sha256:959d57e387671c4c4a9119a9ba868aee09c1ffc5f9a7827a5d1172cd6fe85eed
+size 437958648

run-2/checkpoint-39/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db12af96426d3e941615fa49765848305f4d5a5cff2bb8a11bcde88b15afdb93
+size 876038394

run-2/checkpoint-39/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:afca84cca3e41f31adc342431bd2ff157dddd1608dfba762abc0e1c205d7595e
+size 14244

run-2/checkpoint-39/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b7be206bb4e434dd3ac4b6561c3ca55ce666b7a7a0b37bcfacd1071fcb360af
+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 +1,47 @@
+{
+  "best_global_step": 39,
+  "best_metric": 0.5992779783393501,
+  "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_3/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": 0.5992779783393501,
+      "eval_loss": 0.6908167004585266,
+      "eval_runtime": 3.998,
+      "eval_samples_per_second": 69.284,
+      "eval_steps_per_second": 1.251,
+      "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": {
+    "learning_rate": 1.599585445913243e-05,
+    "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:bc294f134e484f8ece790b17bfb13e67344add26a9b283afde34aa1cade14b79
+size 5432

runs/Apr10_11-55-59_972d5d989ccb/events.out.tfevents.1744288079.972d5d989ccb.224.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75655ba3ff161e516f1b522094a40afa3bd392ed3f3b13d2750ef3347f946775
+size 5766

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d9b368af41ce4afd44935db5297324010c04a9a83b0a818f781da96fa84252ba
+oid sha256:bc294f134e484f8ece790b17bfb13e67344add26a9b283afde34aa1cade14b79
 size 5432