Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:36de15e55977ad076e175a10296b009a208701c0c1282fed95b992249878ec82
+oid sha256:14db29d852bbbbbe8122c3347685f00bfbd52784a79d4aa41f5ea897300ebcba
 size 437958648

run-1/checkpoint-842/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-1/checkpoint-842/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14db29d852bbbbbe8122c3347685f00bfbd52784a79d4aa41f5ea897300ebcba
+size 437958648

run-1/checkpoint-842/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46c6b48315aec3b70ed6ac809cc545b86bcb895526024b3f0e95d7b919b63674
+size 876038394

run-1/checkpoint-842/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a40a489b0164b68c67bcc2d5c80a14a2ad8f6f08728bed9d54a5875f75cd8796
+size 14308

run-1/checkpoint-842/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f7ef57eacc14f0ca4d3ecf2172e3a4dd86587072eff002ea9247f384c002575
+size 1064

run-1/checkpoint-842/special_tokens_map.json

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

run-1/checkpoint-842/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-1/checkpoint-842/trainer_state.json

@@ -0,0 +1,36 @@
+{
+  "best_metric": 0.4919724770642202,
+  "best_model_checkpoint": "Tech-oriented/best_model_bert_uncasedbert-base-uncased-finetuned-sst2/run-1/checkpoint-842",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 842,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.4919724770642202,
+      "eval_loss": 0.7050859928131104,
+      "eval_runtime": 2.333,
+      "eval_samples_per_second": 373.767,
+      "eval_steps_per_second": 23.575,
+      "step": 842
+    }
+  ],
+  "logging_steps": 4209,
+  "max_steps": 842,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 2.448467959674245e-07,
+    "num_train_epochs": 1,
+    "per_device_train_batch_size": 8,
+    "seed": 24,
+    "weight_decay": 0.25466012721911674
+  }
+}

run-1/checkpoint-842/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0fb5001f730f350bcb73a91e26c7001a8226f7bdb8bab7e827a19b7bb6165db
+size 4984

runs/Mar05_15-08-53_9d72474d753b/events.out.tfevents.1709652012.9d72474d753b.33271.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1347f2bdd30edf5871b7fbfef5672793a2e37264611676d92229e6920d954844
+size 5427

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:44dc25bba6431ca36f2d7d667943561f905d13814eb88802e61a1b3a6032a237
+oid sha256:a0fb5001f730f350bcb73a91e26c7001a8226f7bdb8bab7e827a19b7bb6165db
 size 4984