Training in progress, epoch 4

logs/events.out.tfevents.1702277265.joseph_legion.22340.18

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea3d9456d4fdbae91808d96b1e824f63ca6430a0d18dd57078e8e4880c49ec70
-size 5886
+oid sha256:e6d971f34a17188a90f33332eaaff310eac82a96cab088bc2f72d5a06934c8d7
+size 6366

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c473860e1ef9908e4e50672c2a62a704b94e337caf61ae28ca147a183da5f60
+oid sha256:b5750d27525e32c5a53e301db202b2ef1c356243e137f2537a9026aeb55309bd
 size 44692608

run-5/checkpoint-788/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-5/checkpoint-788/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5750d27525e32c5a53e301db202b2ef1c356243e137f2537a9026aeb55309bd
+size 44692608

run-5/checkpoint-788/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46f1570758ecc553fe160dae3309bee7e9fffa24850fbe03e25ce863ac351648
+size 89430010

run-5/checkpoint-788/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e39bb59d0602913d0446fb1b887e3bef027f47ac31f57a5e1aad549eeef7f347
+size 14308

run-5/checkpoint-788/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4cf15b8ab7051ca1bc938cf9c7140ecc47adfb7f3c809d64b8d276990d77d5f
+size 1064

run-5/checkpoint-788/special_tokens_map.json

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

run-5/checkpoint-788/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-5/checkpoint-788/trainer_state.json

@@ -0,0 +1,85 @@
+{
+  "best_metric": 0.7812673707615342,
+  "best_model_checkpoint": "tinybert-TG-HS-HX-parentpretrained\\run-5\\checkpoint-788",
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 788,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 4.941433573951871e-06,
+      "loss": 0.3472,
+      "step": 197
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7540300166759311,
+      "eval_loss": 0.3264233469963074,
+      "eval_runtime": 125.6102,
+      "eval_samples_per_second": 57.288,
+      "eval_steps_per_second": 0.454,
+      "step": 197
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 4.117861311626559e-06,
+      "loss": 0.3304,
+      "step": 394
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7727904391328516,
+      "eval_loss": 0.3193582594394684,
+      "eval_runtime": 125.5179,
+      "eval_samples_per_second": 57.33,
+      "eval_steps_per_second": 0.454,
+      "step": 394
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 3.2942890493012468e-06,
+      "loss": 0.3247,
+      "step": 591
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7782101167315175,
+      "eval_loss": 0.31648218631744385,
+      "eval_runtime": 125.7064,
+      "eval_samples_per_second": 57.244,
+      "eval_steps_per_second": 0.453,
+      "step": 591
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 2.4707167869759353e-06,
+      "loss": 0.3224,
+      "step": 788
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.7812673707615342,
+      "eval_loss": 0.31448855996131897,
+      "eval_runtime": 125.4689,
+      "eval_samples_per_second": 57.353,
+      "eval_steps_per_second": 0.454,
+      "step": 788
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1379,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 7,
+  "save_steps": 500,
+  "total_flos": 177030409545900.0,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.5501861057464915,
+    "learning_rate": 5.7650058362771825e-06,
+    "num_train_epochs": 7,
+    "temperature": 15
+  }
+}

run-5/checkpoint-788/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28cc7611006f792e9dd8ff296313a535b356cc6a1bb6db2c1180dd69535d0c93
+size 4792