Training in progress, epoch 3

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:783161ee1ee1daad24c4949d0fe9f7e7ae5902eb60425e91c09243943879a80d
+oid sha256:35741f9e902b5be55147f3057ff5f19dc876a8ee71e37a455fbfaf2902dc5d35
 size 437958648

run-3/checkpoint-5052/config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "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,
+  "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-3/checkpoint-5052/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35741f9e902b5be55147f3057ff5f19dc876a8ee71e37a455fbfaf2902dc5d35
+size 437958648

run-3/checkpoint-5052/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4a892a174c2e2b3f7b875d41b3923a0329146d638bef1963221dc5245cc6f5c
+size 876038394

run-3/checkpoint-5052/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:704c2ed4f121b8f2b6c25ecc1806b8fba6c0b4f83acc5da0d151546087ab7ccf
+size 14244

run-3/checkpoint-5052/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58d7d5e9371bd7b4bf87545b0fdddf9e76918e1ac74f259fccdb96de0be7f11a
+size 1064

run-3/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-3/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-3/checkpoint-5052/trainer_state.json

@@ -0,0 +1,123 @@
+{
+  "best_metric": 0.9048165137614679,
+  "best_model_checkpoint": "bert-base-uncased-finetuned-sst2/run-3/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": 0.3,
+      "grad_norm": 7.637521743774414,
+      "learning_rate": 3.0568943955117345e-06,
+      "loss": 0.5094,
+      "step": 500
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 104.65070343017578,
+      "learning_rate": 2.721119527814927e-06,
+      "loss": 0.4332,
+      "step": 1000
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 0.10155901312828064,
+      "learning_rate": 2.3853446601181197e-06,
+      "loss": 0.4318,
+      "step": 1500
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8899082568807339,
+      "eval_loss": 0.4135288596153259,
+      "eval_runtime": 2.3891,
+      "eval_samples_per_second": 364.998,
+      "eval_steps_per_second": 23.022,
+      "step": 1684
+    },
+    {
+      "epoch": 1.19,
+      "grad_norm": 0.4222470819950104,
+      "learning_rate": 2.0495697924213124e-06,
+      "loss": 0.4108,
+      "step": 2000
+    },
+    {
+      "epoch": 1.48,
+      "grad_norm": 0.46430423855781555,
+      "learning_rate": 1.7137949247245048e-06,
+      "loss": 0.3485,
+      "step": 2500
+    },
+    {
+      "epoch": 1.78,
+      "grad_norm": 0.1579820215702057,
+      "learning_rate": 1.3780200570276975e-06,
+      "loss": 0.3125,
+      "step": 3000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8967889908256881,
+      "eval_loss": 0.4881651997566223,
+      "eval_runtime": 2.45,
+      "eval_samples_per_second": 355.915,
+      "eval_steps_per_second": 22.449,
+      "step": 3368
+    },
+    {
+      "epoch": 2.08,
+      "grad_norm": 0.662672221660614,
+      "learning_rate": 1.0422451893308901e-06,
+      "loss": 0.3239,
+      "step": 3500
+    },
+    {
+      "epoch": 2.38,
+      "grad_norm": 10.589339256286621,
+      "learning_rate": 7.064703216340827e-07,
+      "loss": 0.2529,
+      "step": 4000
+    },
+    {
+      "epoch": 2.67,
+      "grad_norm": 0.06143077090382576,
+      "learning_rate": 3.7069545393727534e-07,
+      "loss": 0.2671,
+      "step": 4500
+    },
+    {
+      "epoch": 2.97,
+      "grad_norm": 0.06450512260198593,
+      "learning_rate": 3.492058624046797e-08,
+      "loss": 0.2994,
+      "step": 5000
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9048165137614679,
+      "eval_loss": 0.4830039441585541,
+      "eval_runtime": 2.4197,
+      "eval_samples_per_second": 360.376,
+      "eval_steps_per_second": 22.73,
+      "step": 5052
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 5052,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 246789433818420.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 3.3926692632085418e-06,
+    "num_train_epochs": 3,
+    "per_device_train_batch_size": 4,
+    "seed": 6
+  }
+}

run-3/checkpoint-5052/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0cce3c6e72492bb7c1a4c484b82ee3bdab0e12eac30e90df01d84b713c962136
+size 4920

runs/Mar03_17-42-01_90708aaa767a/events.out.tfevents.1709492526.90708aaa767a.21824.10

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c03847e9f6fca420a792f501be92a289ee0f2fb4d94804fe033809757d51d563
-size 6746
+oid sha256:5041c93d3f05a7c50a853e39a6f6bb2007358b1b391ce6085e75cb2f91441863
+size 8056