Training in progress, epoch 2

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b6f629c2db0cf6a2a1ceafca0ab21cb85fc9c5d8e585f947034e752a6b9bd6f2
+oid sha256:5d15aa2df1e3cdb4dd0f5c65636b1af51abeeea65577228abd9f3d4e9af2897a
 size 437958648

run-4/checkpoint-3368/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-3368/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d15aa2df1e3cdb4dd0f5c65636b1af51abeeea65577228abd9f3d4e9af2897a
+size 437958648

run-4/checkpoint-3368/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80770d078ac3416903abcc9e6cf8e839e2b0a0fcf18633c44494dd19cf5b2fbf
+size 876038394

run-4/checkpoint-3368/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:833377918d3793f03e2f2e7f181fb0f9812f1df06b40ee9928fe7c124041749a
+size 14244

run-4/checkpoint-3368/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46d0c30cef6db91811653baae37f7d55202299672e2d97d70776271ea72d86c2
+size 1064

run-4/checkpoint-3368/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-3368/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-3368/trainer_state.json

@@ -0,0 +1,45 @@
+{
+  "best_metric": 0.9059633027522935,
+  "best_model_checkpoint": "Tech-oriented/best_model_bert_uncasedbert-base-uncased-finetuned-sst2/run-4/checkpoint-3368",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 3368,
+  "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
+    }
+  ],
+  "logging_steps": 4209,
+  "max_steps": 5052,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 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-3368/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 sha256:17bd33a629df6b4aaf56c7327ab0f03959d11b7f8fe88ca460dc9b9e0e460fa1
-size 5072
+oid sha256:7f73f8272e84a84fe1aaa5b9d77975842668a86f5e6cc878153eb08b6e10ad68
+size 5395