Training in progress, epoch 4

logs/events.out.tfevents.1711298948.8cc2eef2edb7.2942.32

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a855f501d4b2aae5efa613aaa9f6cefbcf3e75866922f50806c7365489ee6fa5
-size 6866
+oid sha256:eb998d370cdb74cb9cc737cb5710c4bbfcc5acc8c3df6464ee663cfbd3df3974
+size 7596

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cfce8120ed1e63f2e8626305ef126950eda03f5050d3010f93d62e4c04996131
+oid sha256:4d82fc5f3aaf394eff59c5a24a9883eb23e209e7bc488d192170510cce66cc23
 size 17549312

run-32/checkpoint-1188/config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "google/bert_uncased_L-2_H-128_A-2",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 128,
+  "id2label": {
+    "0": "negative",
+    "1": "positive"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 512,
+  "label2id": {
+    "negative": "0",
+    "positive": "1"
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 2,
+  "num_hidden_layers": 2,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.39.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-32/checkpoint-1188/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d82fc5f3aaf394eff59c5a24a9883eb23e209e7bc488d192170510cce66cc23
+size 17549312

run-32/checkpoint-1188/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c149d7e934c56f310800a081305165ff718cdbb2900f599a721f02150920e0bc
+size 35123898

run-32/checkpoint-1188/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47a05bef4801db254faeaae411c6646dc08c36b663ea365ca6cd58d95d1762f2
+size 14308

run-32/checkpoint-1188/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6722b0b0d207124a8736a3984157f3d99d45ca85c1a182263928370ab59a8c41
+size 1064

run-32/checkpoint-1188/special_tokens_map.json

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

run-32/checkpoint-1188/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-32/checkpoint-1188/trainer_state.json

@@ -0,0 +1,106 @@
+{
+  "best_metric": 0.6574257425742575,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-32/checkpoint-891",
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 1188,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 2.0489678382873535,
+      "learning_rate": 0.00030782109688346106,
+      "loss": 0.6591,
+      "step": 297
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5366336633663367,
+      "eval_f1": 0.20945945945945946,
+      "eval_loss": 0.6587525606155396,
+      "eval_mcc": 0.12699706368366073,
+      "eval_precision": 0.7045454545454546,
+      "eval_recall": 0.12301587301587301,
+      "eval_runtime": 0.9347,
+      "eval_samples_per_second": 540.253,
+      "eval_steps_per_second": 17.117,
+      "step": 297
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.570565104484558,
+      "learning_rate": 0.00024625687750676884,
+      "loss": 0.6201,
+      "step": 594
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6514851485148515,
+      "eval_f1": 0.7095709570957095,
+      "eval_loss": 0.6164775490760803,
+      "eval_mcc": 0.33175059993848016,
+      "eval_precision": 0.6073446327683616,
+      "eval_recall": 0.8531746031746031,
+      "eval_runtime": 0.94,
+      "eval_samples_per_second": 537.23,
+      "eval_steps_per_second": 17.021,
+      "step": 594
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 1.9003602266311646,
+      "learning_rate": 0.00018469265813007664,
+      "loss": 0.6,
+      "step": 891
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.6574257425742575,
+      "eval_f1": 0.7131011608623549,
+      "eval_loss": 0.6146110892295837,
+      "eval_mcc": 0.3427822124548935,
+      "eval_precision": 0.6125356125356125,
+      "eval_recall": 0.8531746031746031,
+      "eval_runtime": 0.9324,
+      "eval_samples_per_second": 541.638,
+      "eval_steps_per_second": 17.161,
+      "step": 891
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 2.194995880126953,
+      "learning_rate": 0.00012312843875338442,
+      "loss": 0.5817,
+      "step": 1188
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.6574257425742575,
+      "eval_f1": 0.7082630691399663,
+      "eval_loss": 0.598789632320404,
+      "eval_mcc": 0.3369187333704843,
+      "eval_precision": 0.6158357771260997,
+      "eval_recall": 0.8333333333333334,
+      "eval_runtime": 0.9317,
+      "eval_samples_per_second": 542.019,
+      "eval_steps_per_second": 17.173,
+      "step": 1188
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1782,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 6,
+  "save_steps": 500,
+  "total_flos": 2922805063920.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.9361124407975862,
+    "learning_rate": 0.0003693853162601533,
+    "num_train_epochs": 6,
+    "temperature": 21
+  }
+}

run-32/checkpoint-1188/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b8392c48e77ef3e277bb806e38539adfe405c083ee9826264540c767c93e40b
+size 4920