Training in progress, epoch 5

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f99449b19193cf4d5814322f895ef1423d2cb42c546ac37cc6ccdd903b4c3921
+oid sha256:114db4844a0e530eebfad5a1e5bf3c98415e4c2ce83af4d900f07dc8eea7de4f
 size 438014016

run-2/checkpoint-3580/config.json

@@ -0,0 +1,71 @@
+{
+  "_name_or_path": "google-bert/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,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5",
+    "6": "LABEL_6",
+    "7": "LABEL_7",
+    "8": "LABEL_8",
+    "9": "LABEL_9",
+    "10": "LABEL_10",
+    "11": "LABEL_11",
+    "12": "LABEL_12",
+    "13": "LABEL_13",
+    "14": "LABEL_14",
+    "15": "LABEL_15",
+    "16": "LABEL_16",
+    "17": "LABEL_17",
+    "18": "LABEL_18",
+    "19": "LABEL_19"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_10": 10,
+    "LABEL_11": 11,
+    "LABEL_12": 12,
+    "LABEL_13": 13,
+    "LABEL_14": 14,
+    "LABEL_15": 15,
+    "LABEL_16": 16,
+    "LABEL_17": 17,
+    "LABEL_18": 18,
+    "LABEL_19": 19,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5,
+    "LABEL_6": 6,
+    "LABEL_7": 7,
+    "LABEL_8": 8,
+    "LABEL_9": 9
+  },
+  "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-3580/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:114db4844a0e530eebfad5a1e5bf3c98415e4c2ce83af4d900f07dc8eea7de4f
+size 438014016

run-2/checkpoint-3580/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74310bd7985ec40f258ee9006f8015859443835946dbc4528c8649cc4eb2266e
+size 876149114

run-2/checkpoint-3580/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a9c508ec66c4a63109bee5f3f7d1cdcbe407cfb2f00df61a68e1f124277af5b
+size 14244

run-2/checkpoint-3580/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:314bc83ea0e12c68c7f6fe45cfd00335b8619198a1ed27a57f8dd91e7859981c
+size 1064

run-2/checkpoint-3580/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-3580/tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "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_basic_tokenize": true,
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

run-2/checkpoint-3580/trainer_state.json

@@ -0,0 +1,120 @@
+{
+  "best_metric": 0.71284019947052,
+  "best_model_checkpoint": "./results/run-2/checkpoint-3580",
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 3580,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.7,
+      "grad_norm": 10.922755241394043,
+      "learning_rate": 1.0268278922473237e-06,
+      "loss": 1.8219,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5350694444444445,
+      "eval_loss": 0.9786161780357361,
+      "eval_runtime": 9.9795,
+      "eval_samples_per_second": 95.696,
+      "eval_steps_per_second": 12.025,
+      "step": 716
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 14.039722442626953,
+      "learning_rate": 8.601350525967841e-07,
+      "loss": 1.0057,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.5836805555555554,
+      "eval_loss": 0.7821939587593079,
+      "eval_runtime": 9.9454,
+      "eval_samples_per_second": 96.025,
+      "eval_steps_per_second": 12.066,
+      "step": 1432
+    },
+    {
+      "epoch": 2.09,
+      "grad_norm": 10.68411636352539,
+      "learning_rate": 6.934422129462446e-07,
+      "loss": 0.8145,
+      "step": 1500
+    },
+    {
+      "epoch": 2.79,
+      "grad_norm": 9.355574607849121,
+      "learning_rate": 5.26749373295705e-07,
+      "loss": 0.7562,
+      "step": 2000
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.5756944444444445,
+      "eval_loss": 0.7393563389778137,
+      "eval_runtime": 9.9607,
+      "eval_samples_per_second": 95.877,
+      "eval_steps_per_second": 12.047,
+      "step": 2148
+    },
+    {
+      "epoch": 3.49,
+      "grad_norm": 12.277854919433594,
+      "learning_rate": 3.6005653364516544e-07,
+      "loss": 0.7289,
+      "step": 2500
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.5923611111111112,
+      "eval_loss": 0.7192526459693909,
+      "eval_runtime": 9.9856,
+      "eval_samples_per_second": 95.638,
+      "eval_steps_per_second": 12.017,
+      "step": 2864
+    },
+    {
+      "epoch": 4.19,
+      "grad_norm": 10.423462867736816,
+      "learning_rate": 1.9336369399462588e-07,
+      "loss": 0.7056,
+      "step": 3000
+    },
+    {
+      "epoch": 4.89,
+      "grad_norm": 9.153046607971191,
+      "learning_rate": 2.667085434408633e-08,
+      "loss": 0.6996,
+      "step": 3500
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.5965277777777779,
+      "eval_loss": 0.71284019947052,
+      "eval_runtime": 9.9519,
+      "eval_samples_per_second": 95.962,
+      "eval_steps_per_second": 12.058,
+      "step": 3580
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 3580,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 3682044863152128.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.1935207318978632e-06,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 4,
+    "seed": 35
+  }
+}

run-2/checkpoint-3580/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4dcb125fe81c7d99e9454aab3c9911931319e605501befb442c6ac23c0f43e6
+size 4920

runs/Mar09_22-25-05_f7c164b07abc/events.out.tfevents.1710024069.f7c164b07abc.1664.5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:316e07d30cdeda5845f40cc4fc0a1fe6f95658a19f0fd768d2375ccb429b0adc
-size 7961
+oid sha256:663c58b785deabfe46566ccf2efb24e82709244e902c9e15184aa5383052f91a
+size 8849