Training in progress, epoch 6

logs/events.out.tfevents.1702270246.joseph_legion.22340.16

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49f041dc550f0aa404f547d0eb7763f981b8af96bb30dcffb99edc92d22fa811
-size 6846
+oid sha256:1f5309726505a3bf26f2031488b2c2e796207065bd85d39ab00f2d70a6e16d0d
+size 7326

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1042331325b4dd2e5979f994a7b309addd682d6c3a326375a26139c0943cf7a4
+oid sha256:c5f1ef2f93330d4a540ae32a090ba2020c00801a70c1574eff1f08cfa5f80c06
 size 44692608

run-3/checkpoint-1182/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-3/checkpoint-1182/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5f1ef2f93330d4a540ae32a090ba2020c00801a70c1574eff1f08cfa5f80c06
+size 44692608

run-3/checkpoint-1182/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dbf36e89b024ec5d12edc95e35112247ca07736c5b179766d14665119470c28e
+size 89430010

run-3/checkpoint-1182/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a9511e5e4163d669edd4526e0777794d8936c52493f7e77dc7be042cfeed886
+size 14308

run-3/checkpoint-1182/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e1dcee7c3b51fbbd325197226e7de2274e7ded0532e080fd8267226f53887be
+size 1064

run-3/checkpoint-1182/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-1182/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-3/checkpoint-1182/trainer_state.json

@@ -0,0 +1,115 @@
+{
+  "best_metric": 0.8246247915508615,
+  "best_model_checkpoint": "tinybert-TG-HS-HX-parentpretrained\\run-3\\checkpoint-985",
+  "epoch": 6.0,
+  "eval_steps": 500,
+  "global_step": 1182,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 4.53412212955664e-05,
+      "loss": 0.2002,
+      "step": 197
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.796692607003891,
+      "eval_loss": 0.19448761641979218,
+      "eval_runtime": 125.5379,
+      "eval_samples_per_second": 57.321,
+      "eval_steps_per_second": 0.454,
+      "step": 197
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 3.778435107963867e-05,
+      "loss": 0.1946,
+      "step": 394
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8086436909394108,
+      "eval_loss": 0.19145084917545319,
+      "eval_runtime": 125.3349,
+      "eval_samples_per_second": 57.414,
+      "eval_steps_per_second": 0.455,
+      "step": 394
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 3.0227480863710935e-05,
+      "loss": 0.1912,
+      "step": 591
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8153140633685381,
+      "eval_loss": 0.1914054900407791,
+      "eval_runtime": 125.3098,
+      "eval_samples_per_second": 57.426,
+      "eval_steps_per_second": 0.455,
+      "step": 591
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 2.26706106477832e-05,
+      "loss": 0.189,
+      "step": 788
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8187882156753752,
+      "eval_loss": 0.1904531717300415,
+      "eval_runtime": 125.5411,
+      "eval_samples_per_second": 57.32,
+      "eval_steps_per_second": 0.454,
+      "step": 788
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 1.5113740431855467e-05,
+      "loss": 0.1871,
+      "step": 985
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.8246247915508615,
+      "eval_loss": 0.19075776636600494,
+      "eval_runtime": 125.5068,
+      "eval_samples_per_second": 57.336,
+      "eval_steps_per_second": 0.454,
+      "step": 985
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 7.556870215927734e-06,
+      "loss": 0.1853,
+      "step": 1182
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.8246247915508615,
+      "eval_loss": 0.1908973753452301,
+      "eval_runtime": 125.4292,
+      "eval_samples_per_second": 57.371,
+      "eval_steps_per_second": 0.454,
+      "step": 1182
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1379,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 7,
+  "save_steps": 500,
+  "total_flos": 265501203931764.0,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.3140746400350408,
+    "learning_rate": 5.2898091511494136e-05,
+    "num_train_epochs": 7,
+    "temperature": 24
+  }
+}

run-3/checkpoint-1182/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c517abc0104d666a32411c6a107164f2cf5b4407241697f095cff05f4bfaf0a
+size 4792