Training in progress, epoch 3

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d1e72788aedca5450186d8039bee3998f07430ef893a1f6b3c5bc18ac23a0033
+oid sha256:6458b38be86ba67defe561c40e1db21ab4144316144239d277d7f1e512bde76b
 size 437958648

run-2/checkpoint-1670/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": "4.38.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-2/checkpoint-1670/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be35a3d411bc35fed7fdc809ce6545086982ff7d9fe890e9a4d30ec2fc6fc8d4
+size 437958648

run-2/checkpoint-1670/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f4d82a98e256f6420f3356ccfef7792f1366a52ccaa09ab70dbf72445a56699
+size 876038394

run-2/checkpoint-1670/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1973054123b1a43ae6bcf711559ed696684422d3bbbcfbcff810d254274a5564
+size 14308

run-2/checkpoint-1670/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad3af729c7d8ea65c4b10c86adab49e116200f20014cddeb5608a3b54dbbaf81
+size 1064

run-2/checkpoint-1670/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-1670/tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "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": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "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-1670/trainer_state.json

@@ -0,0 +1,65 @@
+{
+  "best_metric": 0.9615338526063512,
+  "best_model_checkpoint": "bert-base-uncased-finetuned-spam-real/run-2/checkpoint-1670",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 1670,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.6,
+      "grad_norm": 9.117546081542969,
+      "learning_rate": 1.8393158320232495e-06,
+      "loss": 0.4054,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9505692031156381,
+      "eval_loss": 0.14854364097118378,
+      "eval_runtime": 597.8505,
+      "eval_samples_per_second": 27.917,
+      "eval_steps_per_second": 1.746,
+      "step": 835
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 1.4320781230926514,
+      "learning_rate": 1.3806335796483742e-06,
+      "loss": 0.1311,
+      "step": 1000
+    },
+    {
+      "epoch": 1.8,
+      "grad_norm": 0.354846715927124,
+      "learning_rate": 9.219513272734991e-07,
+      "loss": 0.1227,
+      "step": 1500
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9615338526063512,
+      "eval_loss": 0.14428438246250153,
+      "eval_runtime": 598.1778,
+      "eval_samples_per_second": 27.901,
+      "eval_steps_per_second": 1.745,
+      "step": 1670
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2505,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 2989060811086560.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 2.2979980843981246e-06,
+    "num_train_epochs": 3,
+    "per_device_train_batch_size": 8,
+    "seed": 24
+  }
+}

run-2/checkpoint-1670/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:977ec9eece5f9e2273a7d887d95fb9be8edae8feee607dd3c107f6aa9ef3e0c5
+size 4920

run-2/checkpoint-2505/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": "4.38.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-2/checkpoint-2505/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6458b38be86ba67defe561c40e1db21ab4144316144239d277d7f1e512bde76b
+size 437958648

run-2/checkpoint-2505/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11c5aace133e1e21503f083a644ea260ac77a3f46956625250fd04508f88ec93
+size 876038394

run-2/checkpoint-2505/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e170e789601099e166fa7d94560bc4ef242e68f90d991a9bc880b71b78ec790f
+size 14308

run-2/checkpoint-2505/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ab76da5daacf986d3d66bf97f36600e932908880e195fdfbb9c18c426d6ae82
+size 1064

run-2/checkpoint-2505/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-2505/tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "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": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "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-2505/trainer_state.json

@@ -0,0 +1,88 @@
+{
+  "best_metric": 0.9615338526063512,
+  "best_model_checkpoint": "bert-base-uncased-finetuned-spam-real/run-2/checkpoint-1670",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 2505,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.6,
+      "grad_norm": 9.117546081542969,
+      "learning_rate": 1.8393158320232495e-06,
+      "loss": 0.4054,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9505692031156381,
+      "eval_loss": 0.14854364097118378,
+      "eval_runtime": 597.8505,
+      "eval_samples_per_second": 27.917,
+      "eval_steps_per_second": 1.746,
+      "step": 835
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 1.4320781230926514,
+      "learning_rate": 1.3806335796483742e-06,
+      "loss": 0.1311,
+      "step": 1000
+    },
+    {
+      "epoch": 1.8,
+      "grad_norm": 0.354846715927124,
+      "learning_rate": 9.219513272734991e-07,
+      "loss": 0.1227,
+      "step": 1500
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9615338526063512,
+      "eval_loss": 0.14428438246250153,
+      "eval_runtime": 598.1778,
+      "eval_samples_per_second": 27.901,
+      "eval_steps_per_second": 1.745,
+      "step": 1670
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 2.810948371887207,
+      "learning_rate": 4.6326907489862395e-07,
+      "loss": 0.1123,
+      "step": 2000
+    },
+    {
+      "epoch": 2.99,
+      "grad_norm": 0.04734252020716667,
+      "learning_rate": 4.586822523748751e-09,
+      "loss": 0.0837,
+      "step": 2500
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9608148591971241,
+      "eval_loss": 0.15702731907367706,
+      "eval_runtime": 598.8615,
+      "eval_samples_per_second": 27.87,
+      "eval_steps_per_second": 1.743,
+      "step": 2505
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2505,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 4990682275848000.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 2.2979980843981246e-06,
+    "num_train_epochs": 3,
+    "per_device_train_batch_size": 8,
+    "seed": 24
+  }
+}

run-2/checkpoint-2505/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:977ec9eece5f9e2273a7d887d95fb9be8edae8feee607dd3c107f6aa9ef3e0c5
+size 4920

runs/Mar21_16-50-03_43ee8d6b3d53/events.out.tfevents.1711044833.43ee8d6b3d53.2090.2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3103a90d444e3953a5f81fde2b7998c5cda27ffa490e5a3ba1654356367760ae
-size 5173
+oid sha256:5eba714a9ae2b41d127b7950dc58da826298510e121d9f21f7e8c3b4b6375afb
+size 7017