Training in progress, epoch 5

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:30e44500db62347e2c36c7ce5602fcfb87b44cf322d4b6e425dbb06c9a002901
+oid sha256:863c33a1cb468f2008ffdde686b883d199a5fee31fc90514c4067bbcf6840f8b
 size 437958648

run-0/checkpoint-4210/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-0/checkpoint-4210/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:863c33a1cb468f2008ffdde686b883d199a5fee31fc90514c4067bbcf6840f8b
+size 437958648

run-0/checkpoint-4210/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3bff0101c093f8a3bf391fbfa083b896c3e2fcd6cffc59e5d4a27e0074b4f84
+size 876038394

run-0/checkpoint-4210/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6a54526ad07f53f1243758b2e15721f8f6a7963324a419c1ae593c555df7f04
+size 14308

run-0/checkpoint-4210/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9b170ccc3d057539a04ffbde738b698d9d371208b4dc506fff8cecf999c5005
+size 1064

run-0/checkpoint-4210/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-4210/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-0/checkpoint-4210/trainer_state.json

@@ -0,0 +1,127 @@
+{
+  "best_metric": 0.9071100917431193,
+  "best_model_checkpoint": "bert-base-uncased-finetuned-sst2/run-0/checkpoint-4210",
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 4210,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.59,
+      "grad_norm": 14.076563835144043,
+      "learning_rate": 2.1488708627178514e-06,
+      "loss": 0.4976,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8646788990825688,
+      "eval_loss": 0.33198288083076477,
+      "eval_runtime": 2.248,
+      "eval_samples_per_second": 387.892,
+      "eval_steps_per_second": 24.466,
+      "step": 842
+    },
+    {
+      "epoch": 1.19,
+      "grad_norm": 16.497121810913086,
+      "learning_rate": 1.8592656251547983e-06,
+      "loss": 0.3072,
+      "step": 1000
+    },
+    {
+      "epoch": 1.78,
+      "grad_norm": 50.02860641479492,
+      "learning_rate": 1.5696603875917459e-06,
+      "loss": 0.3036,
+      "step": 1500
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8876146788990825,
+      "eval_loss": 0.3288116455078125,
+      "eval_runtime": 2.3363,
+      "eval_samples_per_second": 373.233,
+      "eval_steps_per_second": 23.541,
+      "step": 1684
+    },
+    {
+      "epoch": 2.38,
+      "grad_norm": 0.35839420557022095,
+      "learning_rate": 1.280055150028693e-06,
+      "loss": 0.2703,
+      "step": 2000
+    },
+    {
+      "epoch": 2.97,
+      "grad_norm": 65.75403594970703,
+      "learning_rate": 9.904499124656404e-07,
+      "loss": 0.2546,
+      "step": 2500
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8990825688073395,
+      "eval_loss": 0.3764495253562927,
+      "eval_runtime": 2.384,
+      "eval_samples_per_second": 365.774,
+      "eval_steps_per_second": 23.071,
+      "step": 2526
+    },
+    {
+      "epoch": 3.56,
+      "grad_norm": 1.3372397422790527,
+      "learning_rate": 7.008446749025876e-07,
+      "loss": 0.2424,
+      "step": 3000
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.9025229357798165,
+      "eval_loss": 0.38221538066864014,
+      "eval_runtime": 2.405,
+      "eval_samples_per_second": 362.58,
+      "eval_steps_per_second": 22.869,
+      "step": 3368
+    },
+    {
+      "epoch": 4.16,
+      "grad_norm": 0.42396441102027893,
+      "learning_rate": 4.1123943733953484e-07,
+      "loss": 0.2215,
+      "step": 3500
+    },
+    {
+      "epoch": 4.75,
+      "grad_norm": 40.10260772705078,
+      "learning_rate": 1.2163419977648214e-07,
+      "loss": 0.2049,
+      "step": 4000
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.9071100917431193,
+      "eval_loss": 0.3858252763748169,
+      "eval_runtime": 2.444,
+      "eval_samples_per_second": 356.791,
+      "eval_steps_per_second": 22.504,
+      "step": 4210
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 4210,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 490559257165560.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 2.438476100280904e-06,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 8,
+    "seed": 29
+  }
+}

run-0/checkpoint-4210/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97abbdcb1d4ff26ff452c134035ac092df99b9eac097f1e25dcf4b4c26f6558b
+size 4920

runs/Mar03_17-42-01_90708aaa767a/events.out.tfevents.1709491671.90708aaa767a.21824.7

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d1c845b52197edc3651e90905ca6c428f1b8ae0e54094bc1441883cc620fb53
-size 7392
+oid sha256:848e2cbdeb5990036414559f0415ffb0e61af04800ee4319db41a968fd192a90
+size 8280