Training in progress, epoch 3

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:96f563367d673cf42846fff8f51e9c99b86812c12e33fe83a6d3f46853d706be
+oid sha256:75e70c88a0960e4d39ff5381c1b978abfa7c2cd4cfa7e83dbc8e11e42e114756
 size 437958648

run-1/checkpoint-117/config.json

@@ -0,0 +1,26 @@
+{
+  "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": "4.50.3",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-1/checkpoint-117/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75e70c88a0960e4d39ff5381c1b978abfa7c2cd4cfa7e83dbc8e11e42e114756
+size 437958648

run-1/checkpoint-117/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23b889e941ebedc605d21c075fdc6b26580b54d78ac4b3f4ffb2d147612556a2
+size 876038394

run-1/checkpoint-117/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66062f09fb79eb516b32f1e74227740c5dc9e0025a015b9853db13b00b33e723
+size 14244

run-1/checkpoint-117/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b726972fb121999692911956948ec2f05553c2aa742d97e270c644fee861f36
+size 1064

run-1/checkpoint-117/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-117/tokenizer_config.json

@@ -0,0 +1,56 @@
+{
+  "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": false,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "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-117/trainer_state.json

@@ -0,0 +1,65 @@
+{
+  "best_global_step": 117,
+  "best_metric": 0.5234657039711191,
+  "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_3/run-1/checkpoint-117",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 117,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.4657039711191336,
+      "eval_loss": 0.7018395066261292,
+      "eval_runtime": 2.8409,
+      "eval_samples_per_second": 97.503,
+      "eval_steps_per_second": 3.168,
+      "step": 39
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.48375451263537905,
+      "eval_loss": 0.6944130063056946,
+      "eval_runtime": 2.8462,
+      "eval_samples_per_second": 97.323,
+      "eval_steps_per_second": 3.162,
+      "step": 78
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.5234657039711191,
+      "eval_loss": 0.6927844882011414,
+      "eval_runtime": 2.8454,
+      "eval_samples_per_second": 97.35,
+      "eval_steps_per_second": 3.163,
+      "step": 117
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 117,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 5.066704672162084e-06,
+    "num_train_epochs": 3,
+    "per_device_train_batch_size": 64
+  }
+}

run-1/checkpoint-117/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24ef18faae48258cf0a3192468fcb8f1767239f15152cfdf82684da31b63ec1d
+size 5432

runs/Apr04_20-48-10_65b1ef614a6a/events.out.tfevents.1743800200.65b1ef614a6a.1325.4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f77e5dac3e3111c524ae6c46055e213ea3901c7d3144c8f7021dae18d704561
-size 5735
+oid sha256:a85cfbeb1a684f82bf9b439dc36615db2d76af8db28c16a389b3b74c6ba245d9
+size 6400