Training in progress, epoch 3

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d15aa2df1e3cdb4dd0f5c65636b1af51abeeea65577228abd9f3d4e9af2897a
+oid sha256:c8d8a3c5387c1be10448a20b10a02d60caebb8bdd7b30e2a907376bb57b28c5b
 size 437958648

run-4/checkpoint-5052/config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "bert-base-uncased",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.3,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.3,
+  "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-4/checkpoint-5052/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8d8a3c5387c1be10448a20b10a02d60caebb8bdd7b30e2a907376bb57b28c5b
+size 437958648

run-4/checkpoint-5052/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24dfad2125788006f8dabbcc02b2fb048f1826fffd9257c32ea643527a3d1259
+size 876038394

run-4/checkpoint-5052/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5ff28bd3eef43d20c0949cdbc92850b6a0599685b257d53b8cd97c29f22139d
+size 14244

run-4/checkpoint-5052/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6347ff21b36ea579f39bccd9665df0da82c8d606f4d377b9ed4c6dc445cc77e
+size 1064

run-4/checkpoint-5052/special_tokens_map.json

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

run-4/checkpoint-5052/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-4/checkpoint-5052/trainer_state.json

@@ -0,0 +1,61 @@
+{
+  "best_metric": 0.9071100917431193,
+  "best_model_checkpoint": "Tech-oriented/best_model_bert_uncasedbert-base-uncased-finetuned-sst2/run-4/checkpoint-5052",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 5052,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9025229357798165,
+      "eval_loss": 0.38704702258110046,
+      "eval_runtime": 2.3419,
+      "eval_samples_per_second": 372.352,
+      "eval_steps_per_second": 23.486,
+      "step": 1684
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9059633027522935,
+      "eval_loss": 0.4139329493045807,
+      "eval_runtime": 2.3503,
+      "eval_samples_per_second": 371.023,
+      "eval_steps_per_second": 23.402,
+      "step": 3368
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 20.706912994384766,
+      "learning_rate": 2.349164848148445e-06,
+      "loss": 0.4762,
+      "step": 4209
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9071100917431193,
+      "eval_loss": 0.441041499376297,
+      "eval_runtime": 2.3527,
+      "eval_samples_per_second": 370.641,
+      "eval_steps_per_second": 23.378,
+      "step": 5052
+    }
+  ],
+  "logging_steps": 4209,
+  "max_steps": 5052,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 208766802986220.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.4078269054384274e-05,
+    "num_train_epochs": 3,
+    "per_device_train_batch_size": 4,
+    "seed": 34,
+    "weight_decay": 0.446398905246141
+  }
+}

run-4/checkpoint-5052/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29ae5b378da67d6d3b8366dbe235ab8607f31fbbf97b177d40ac47d54da34fd0
+size 4984

runs/Mar05_15-08-53_9d72474d753b/events.out.tfevents.1709652614.9d72474d753b.33271.5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f73f8272e84a84fe1aaa5b9d77975842668a86f5e6cc878153eb08b6e10ad68
-size 5395
+oid sha256:7b1b5f85500f3347d0d83c3f9e219630e75af9d06c644bae0aa40af03b512a0e
+size 6283