Training in progress, epoch 4

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:20de1271d45976872a3d9607f167199e26cba8e9e35aafd0b8b566f404600dc3
+oid sha256:e2aa66ab677ffcedd91bf0c2a6e49b99f67d3c8a75638fbe90ad01dd1dbb000d
 size 437958648

run-6/checkpoint-33676/config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "bert-base-uncased",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.4,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.4,
+  "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-6/checkpoint-33676/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2aa66ab677ffcedd91bf0c2a6e49b99f67d3c8a75638fbe90ad01dd1dbb000d
+size 437958648

run-6/checkpoint-33676/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe3e77147da24efaf23c6ed65c66d716ee1d44f8a6e8a3c624b9a6e6745f6b1b
+size 876038394

run-6/checkpoint-33676/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:177dc709bd4f455148f8d492829020f53b97c3074e30c75eb65f3e2b1d24d7ff
+size 14308

run-6/checkpoint-33676/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:050b3e0513445fdc91c583cd0329c09bf76aad4e171b2cf71faf76fcc8e3bb89
+size 1064

run-6/checkpoint-33676/special_tokens_map.json

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

run-6/checkpoint-33676/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-6/checkpoint-33676/trainer_state.json

@@ -0,0 +1,119 @@
+{
+  "best_metric": 0.9151376146788991,
+  "best_model_checkpoint": "Tech-oriented/best_model_bert_uncasedbert-base-uncased-finetuned-sst2/run-6/checkpoint-33676",
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 33676,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.5,
+      "grad_norm": 35.4764289855957,
+      "learning_rate": 1.4625672140464685e-05,
+      "loss": 0.452,
+      "step": 4209
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 2.615936040878296,
+      "learning_rate": 1.2536574029383954e-05,
+      "loss": 0.354,
+      "step": 8418
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9139908256880734,
+      "eval_loss": 0.36559009552001953,
+      "eval_runtime": 2.4317,
+      "eval_samples_per_second": 358.596,
+      "eval_steps_per_second": 22.618,
+      "step": 8419
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 1.231093406677246,
+      "learning_rate": 1.0447475918303226e-05,
+      "loss": 0.3236,
+      "step": 12627
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 66.64139556884766,
+      "learning_rate": 8.358377807222495e-06,
+      "loss": 0.303,
+      "step": 16836
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9025229357798165,
+      "eval_loss": 0.4449034631252289,
+      "eval_runtime": 2.4314,
+      "eval_samples_per_second": 358.637,
+      "eval_steps_per_second": 22.62,
+      "step": 16838
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 15.909801483154297,
+      "learning_rate": 6.269279696141766e-06,
+      "loss": 0.2693,
+      "step": 21045
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 3.272183895111084,
+      "learning_rate": 4.180181585061036e-06,
+      "loss": 0.2588,
+      "step": 25254
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9105504587155964,
+      "eval_loss": 0.4759577810764313,
+      "eval_runtime": 2.4404,
+      "eval_samples_per_second": 357.326,
+      "eval_steps_per_second": 22.538,
+      "step": 25257
+    },
+    {
+      "epoch": 3.5,
+      "grad_norm": 21.020828247070312,
+      "learning_rate": 2.0910834739803075e-06,
+      "loss": 0.2357,
+      "step": 29463
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 8.535745620727539,
+      "learning_rate": 1.98536289957779e-09,
+      "loss": 0.232,
+      "step": 33672
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.9151376146788991,
+      "eval_loss": 0.4764806628227234,
+      "eval_runtime": 2.4265,
+      "eval_samples_per_second": 359.361,
+      "eval_steps_per_second": 22.666,
+      "step": 33676
+    }
+  ],
+  "logging_steps": 4209,
+  "max_steps": 33676,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 5500248223430640.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.6714770251545413e-05,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 8,
+    "seed": 32,
+    "weight_decay": 0.41710891288145024
+  }
+}

run-6/checkpoint-33676/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f473f968b7e87229e13a2aa91b256ae59a2f8fb544c7ea1c0d31b1fdaca756e5
+size 4984

runs/Mar06_18-14-36_e017d622c671/events.out.tfevents.1709764768.e017d622c671.539.6

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d3137e5a85d91b219b11436af4cd8aabb1b001ebf24195df31b8792c2dce5190
-size 7010
+oid sha256:94b84b93659009fa1c274614f7d6ec89099e34393208aaa645d61e2aff31dc0b
+size 8129