Training in progress, epoch 1

logs/events.out.tfevents.1702259453.joseph_legion.22340.12

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:829eeeb217b32d8dbe2e67770889dbf67dd8bd0602b3daab25be5a6a26f5b655
-size 7309
+oid sha256:f44e68bf6769df07b6a8f22d6785fd4d83c12f10b47847641393168c6a4d1239
+size 8143

logs/events.out.tfevents.1702262698.joseph_legion.22340.13

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f782a7f52f6c74136e4e6126e07a8de478efbb138bd5cba11d96d7cec036d064
+size 4926

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7e1745c40019a1fb93009fbf55276fdc8afa3d154319dec6eb5f870de256b3f
+oid sha256:00f1e053bfc4a28d611867c70b30297bf401ee9536c7b7c61eea24998f1dddfd
 size 44692608

run-0/checkpoint-197/config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "google/bert_uncased_L-4_H-256_A-4",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 256,
+  "id2label": {
+    "0": 0,
+    "1": 1
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 1024,
+  "label2id": {
+    "0": 0,
+    "1": 1
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 4,
+  "num_hidden_layers": 4,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.36.0.dev0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-0/checkpoint-197/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00f1e053bfc4a28d611867c70b30297bf401ee9536c7b7c61eea24998f1dddfd
+size 44692608

run-0/checkpoint-197/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25aece20da47575581e096dee88e7dfc05cdc3a83a2fd46c7053d81940496f91
+size 89430010

run-0/checkpoint-197/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bfce427b13a79881b8dd7c1ca79db1eca136c641f9f35f4f0773c5f01a793672
+size 14308

run-0/checkpoint-197/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85ed753d7076ca8898c054244323bafb55cbc5cf1dbed455bf578a1f70082f16
+size 1064

run-0/checkpoint-197/special_tokens_map.json

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

run-0/checkpoint-197/tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "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_basic_tokenize": true,
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

run-0/checkpoint-197/trainer_state.json

@@ -0,0 +1,40 @@
+{
+  "best_metric": 0.7258198999444135,
+  "best_model_checkpoint": "tinybert-TG-HS-HX-parentpretrained\\run-0\\checkpoint-197",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 197,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 2.505784710419649e-06,
+      "loss": 0.6127,
+      "step": 197
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7258198999444135,
+      "eval_loss": 0.5620561838150024,
+      "eval_runtime": 127.1936,
+      "eval_samples_per_second": 56.575,
+      "eval_steps_per_second": 0.448,
+      "step": 197
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1182,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 6,
+  "save_steps": 500,
+  "total_flos": 44298765947484.0,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.9772734766942756,
+    "learning_rate": 3.0069416525035787e-06,
+    "num_train_epochs": 6,
+    "temperature": 16
+  }
+}

run-0/checkpoint-197/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c14d343496772a0c98c9be375e50811ca2ef09aafdfc61a6757d81f78c95d84
+size 4792

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a121ed872b68217fa268f8c6baba7eb1faa8c3dc1a208ea72284bfe6d28bfaa
+oid sha256:5c14d343496772a0c98c9be375e50811ca2ef09aafdfc61a6757d81f78c95d84
 size 4792