Training in progress, epoch 10

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:85aec8408aa93343feab194e19cff6a63780c6278ba2b50892595cdc75715051
+oid sha256:e3ddbf1e02f794c55a2a4d41f529b4ca99adf7c36866ccc63b992bc19cec9d5c
 size 437958648

run-0/checkpoint-351/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-0/checkpoint-351/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69aa732121ee7ae7dcc0665e8aaab0f1840de77c23b66376a8dc9771fc22b96b
+size 437958648

run-0/checkpoint-351/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85e6ba5122dccd90d1b6ef4cf3e06aa64c16650bd2d76498cf605ca8717f61a5
+size 876038394

run-0/checkpoint-351/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f87d6c38902bbee8598838f3e21d5f33bc8ea37e45662fc2ef9133ed58462b90
+size 14244

run-0/checkpoint-351/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:debcc834d85e62017e9a69328d4b50fec49231759204e6cfe626246d3b1af956
+size 1064

run-0/checkpoint-351/special_tokens_map.json

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

run-0/checkpoint-351/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-0/checkpoint-351/trainer_state.json

@@ -0,0 +1,119 @@
+{
+  "best_global_step": 234,
+  "best_metric": 0.6859205776173285,
+  "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_3/run-0/checkpoint-234",
+  "epoch": 9.0,
+  "eval_steps": 500,
+  "global_step": 351,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.47653429602888087,
+      "eval_loss": 0.7069262266159058,
+      "eval_runtime": 4.0056,
+      "eval_samples_per_second": 69.154,
+      "eval_steps_per_second": 1.248,
+      "step": 39
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6570397111913358,
+      "eval_loss": 0.6297017931938171,
+      "eval_runtime": 4.0147,
+      "eval_samples_per_second": 68.997,
+      "eval_steps_per_second": 1.245,
+      "step": 78
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.6498194945848376,
+      "eval_loss": 0.6359551548957825,
+      "eval_runtime": 4.0761,
+      "eval_samples_per_second": 67.957,
+      "eval_steps_per_second": 1.227,
+      "step": 117
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.6787003610108303,
+      "eval_loss": 0.8057953119277954,
+      "eval_runtime": 4.0736,
+      "eval_samples_per_second": 67.999,
+      "eval_steps_per_second": 1.227,
+      "step": 156
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.6714801444043321,
+      "eval_loss": 0.9200972318649292,
+      "eval_runtime": 4.0463,
+      "eval_samples_per_second": 68.457,
+      "eval_steps_per_second": 1.236,
+      "step": 195
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.6859205776173285,
+      "eval_loss": 1.1093758344650269,
+      "eval_runtime": 4.0725,
+      "eval_samples_per_second": 68.018,
+      "eval_steps_per_second": 1.228,
+      "step": 234
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.6714801444043321,
+      "eval_loss": 1.3535076379776,
+      "eval_runtime": 4.0328,
+      "eval_samples_per_second": 68.687,
+      "eval_steps_per_second": 1.24,
+      "step": 273
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.6787003610108303,
+      "eval_loss": 1.634671926498413,
+      "eval_runtime": 4.14,
+      "eval_samples_per_second": 66.908,
+      "eval_steps_per_second": 1.208,
+      "step": 312
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.6642599277978339,
+      "eval_loss": 1.6656347513198853,
+      "eval_runtime": 4.1039,
+      "eval_samples_per_second": 67.496,
+      "eval_steps_per_second": 1.218,
+      "step": 351
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 390,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 3.263973351967308e-05,
+    "num_train_epochs": 10,
+    "per_device_train_batch_size": 64
+  }
+}

run-0/checkpoint-351/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4450788371fb90f9aaf99fe95189079f7e2037113d51373730f9c8f0518bae8
+size 5432

run-0/checkpoint-390/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-0/checkpoint-390/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3ddbf1e02f794c55a2a4d41f529b4ca99adf7c36866ccc63b992bc19cec9d5c
+size 437958648

run-0/checkpoint-390/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e31a3c516722cc529c7e9ceb976009c435e2215354856c9a7253064998b2cf74
+size 876038394

run-0/checkpoint-390/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9cde2c2f2866704e921d935a0c571cf16816a2453c57dd231773838c773a775
+size 14244

run-0/checkpoint-390/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73351c261b026ef2325fb89f2dabf47a2fea9ccc0da6693a40f3ea50a23b7357
+size 1064

run-0/checkpoint-390/special_tokens_map.json

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

run-0/checkpoint-390/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-0/checkpoint-390/trainer_state.json

@@ -0,0 +1,128 @@
+{
+  "best_global_step": 234,
+  "best_metric": 0.6859205776173285,
+  "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_3/run-0/checkpoint-234",
+  "epoch": 10.0,
+  "eval_steps": 500,
+  "global_step": 390,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.47653429602888087,
+      "eval_loss": 0.7069262266159058,
+      "eval_runtime": 4.0056,
+      "eval_samples_per_second": 69.154,
+      "eval_steps_per_second": 1.248,
+      "step": 39
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6570397111913358,
+      "eval_loss": 0.6297017931938171,
+      "eval_runtime": 4.0147,
+      "eval_samples_per_second": 68.997,
+      "eval_steps_per_second": 1.245,
+      "step": 78
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.6498194945848376,
+      "eval_loss": 0.6359551548957825,
+      "eval_runtime": 4.0761,
+      "eval_samples_per_second": 67.957,
+      "eval_steps_per_second": 1.227,
+      "step": 117
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.6787003610108303,
+      "eval_loss": 0.8057953119277954,
+      "eval_runtime": 4.0736,
+      "eval_samples_per_second": 67.999,
+      "eval_steps_per_second": 1.227,
+      "step": 156
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.6714801444043321,
+      "eval_loss": 0.9200972318649292,
+      "eval_runtime": 4.0463,
+      "eval_samples_per_second": 68.457,
+      "eval_steps_per_second": 1.236,
+      "step": 195
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.6859205776173285,
+      "eval_loss": 1.1093758344650269,
+      "eval_runtime": 4.0725,
+      "eval_samples_per_second": 68.018,
+      "eval_steps_per_second": 1.228,
+      "step": 234
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.6714801444043321,
+      "eval_loss": 1.3535076379776,
+      "eval_runtime": 4.0328,
+      "eval_samples_per_second": 68.687,
+      "eval_steps_per_second": 1.24,
+      "step": 273
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.6787003610108303,
+      "eval_loss": 1.634671926498413,
+      "eval_runtime": 4.14,
+      "eval_samples_per_second": 66.908,
+      "eval_steps_per_second": 1.208,
+      "step": 312
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.6642599277978339,
+      "eval_loss": 1.6656347513198853,
+      "eval_runtime": 4.1039,
+      "eval_samples_per_second": 67.496,
+      "eval_steps_per_second": 1.218,
+      "step": 351
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.6750902527075813,
+      "eval_loss": 1.6671355962753296,
+      "eval_runtime": 3.9974,
+      "eval_samples_per_second": 69.295,
+      "eval_steps_per_second": 1.251,
+      "step": 390
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 390,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "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": 3.263973351967308e-05,
+    "num_train_epochs": 10,
+    "per_device_train_batch_size": 64
+  }
+}

run-0/checkpoint-390/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4450788371fb90f9aaf99fe95189079f7e2037113d51373730f9c8f0518bae8
+size 5432

runs/Apr10_11-55-59_972d5d989ccb/events.out.tfevents.1744286174.972d5d989ccb.224.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d84d9f45285411649e5c4b9f652829029921532881d0e4e607b25fc9d50dcfa5
-size 7703
+oid sha256:845b7855be1043b8a635e46308a81a316fb2154ac68c95a82c1bd9de0427c3e1
+size 8703