Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a5efabf1f88cd44ea53f885c75e4a7636dd8f42a9d952269e26691757825d813
+oid sha256:eb613738e3ffdeb001374669941f1252a00de402f496459f82b20ed8886589ca
 size 437958648

run-2/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-2/checkpoint-1684/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb613738e3ffdeb001374669941f1252a00de402f496459f82b20ed8886589ca
+size 437958648

run-2/checkpoint-1684/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44a5c6d5a656ac7d3e2cc2addcc4aedc63c5cf7878138d7d2859c01f27069c59
+size 876038394

run-2/checkpoint-1684/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc93202deb3c5569360fb9c9c21c4e09f6147edd63c0d92d9b5861f7112a9d98
+size 14308

run-2/checkpoint-1684/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d770bfc35626f498f5d3c5e0dc15b73670a01186e4e002b2705d76d56a23c52
+size 1064

run-2/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-2/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-2/checkpoint-1684/trainer_state.json

@@ -0,0 +1,56 @@
+{
+  "best_metric": 0.8635321100917431,
+  "best_model_checkpoint": "bert-base-uncased-finetuned-sst2/run-2/checkpoint-1684",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 1684,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.3,
+      "grad_norm": 267.4592590332031,
+      "learning_rate": 6.490431462154475e-05,
+      "loss": 0.6127,
+      "step": 500
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 9.022435188293457,
+      "learning_rate": 3.749539797393294e-05,
+      "loss": 0.5862,
+      "step": 1000
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 10.805120468139648,
+      "learning_rate": 1.0086481326321143e-05,
+      "loss": 0.4922,
+      "step": 1500
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8635321100917431,
+      "eval_loss": 0.47688528895378113,
+      "eval_runtime": 2.4,
+      "eval_samples_per_second": 363.329,
+      "eval_steps_per_second": 22.916,
+      "step": 1684
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1684,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "total_flos": 73089373401840.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 9.231323126915654e-05,
+    "num_train_epochs": 1,
+    "per_device_train_batch_size": 4,
+    "seed": 29
+  }
+}

run-2/checkpoint-1684/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3c310707a9a9b300e8afc3494c59ee9399bd8e941233ac893f5f90c0f97df1e
+size 4920

runs/Mar03_17-42-01_90708aaa767a/events.out.tfevents.1709492338.90708aaa767a.21824.9

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7acc82389160444d0ad3482cd7f87237fe7da2aac0dbf55b09ad170573424987
+size 5933

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d58728a4c98462c056199818a16dc9ffabb0131d677c081afc7148b4da7bd4e
+oid sha256:d3c310707a9a9b300e8afc3494c59ee9399bd8e941233ac893f5f90c0f97df1e
 size 4920