Training in progress, epoch 2

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da03c42f7d21e72fcf2e35495731396193ad69891d1c94620346f9ea1b114f41
+oid sha256:a5efabf1f88cd44ea53f885c75e4a7636dd8f42a9d952269e26691757825d813
 size 437958648

run-1/checkpoint-1684/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-1/checkpoint-1684/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5efabf1f88cd44ea53f885c75e4a7636dd8f42a9d952269e26691757825d813
+size 437958648

run-1/checkpoint-1684/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0399d8b7c5b5f60b16511e086de8116831f8aceeaca33b5ace4521d5fae14571
+size 876038394

run-1/checkpoint-1684/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:802dbca11663e9f78fc58385ef96632f9c8202e35cc0f0af207cb5f9c7ca6cf9
+size 14308

run-1/checkpoint-1684/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32732bc4fdf005a2387820424092da13828d7704e2ef31410c899225e7739ee8
+size 1064

run-1/checkpoint-1684/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-1684/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-1684/trainer_state.json

@@ -0,0 +1,65 @@
+{
+  "best_metric": 0.9139908256880734,
+  "best_model_checkpoint": "bert-base-uncased-finetuned-sst2/run-1/checkpoint-1684",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 1684,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.59,
+      "grad_norm": 5.992064476013184,
+      "learning_rate": 2.846915930651389e-05,
+      "loss": 0.4119,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8646788990825688,
+      "eval_loss": 0.40675637125968933,
+      "eval_runtime": 2.35,
+      "eval_samples_per_second": 371.063,
+      "eval_steps_per_second": 23.404,
+      "step": 842
+    },
+    {
+      "epoch": 1.19,
+      "grad_norm": 0.04706716537475586,
+      "learning_rate": 1.6446710275046875e-05,
+      "loss": 0.2691,
+      "step": 1000
+    },
+    {
+      "epoch": 1.78,
+      "grad_norm": 0.055366575717926025,
+      "learning_rate": 4.424261243579861e-06,
+      "loss": 0.1703,
+      "step": 1500
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9139908256880734,
+      "eval_loss": 0.3520638048648834,
+      "eval_runtime": 2.3883,
+      "eval_samples_per_second": 365.121,
+      "eval_steps_per_second": 23.029,
+      "step": 1684
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1684,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "total_flos": 185893613388420.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 4.0491608337980904e-05,
+    "num_train_epochs": 2,
+    "per_device_train_batch_size": 8,
+    "seed": 26
+  }
+}

run-1/checkpoint-1684/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d58728a4c98462c056199818a16dc9ffabb0131d677c081afc7148b4da7bd4e
+size 4920

runs/Mar03_17-42-01_90708aaa767a/events.out.tfevents.1709492125.90708aaa767a.21824.8

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:967d0226d5209750da434efe71c3322229e36662bab925382dd80f45e3b4e698
-size 5369
+oid sha256:ef531be39c413076889a0df164536fa6cf9caf5b27610da551217024a015b910
+size 6257