Training in progress, epoch 8

logs/events.out.tfevents.1713589040.1376c752d37a.9760.24

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef3548a7462a514b6572d24de8510b65bdda0188a431e25253cf14e57e48752c
-size 9862
+oid sha256:cb0400ce0552095d340b33acb1af784e68a1b15c0ed046329252193a51544c35
+size 10592

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:04ef49825a5969a0eeb028ab443fe74268e2aca9f24b5d4598c982abe29c77fb
+oid sha256:2fe6b2339130aa02bfa985d29a359318c8fca356a99e8eaf8e3499d66eeb55b1
 size 17549312

run-24/checkpoint-1712/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": "4.40.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-24/checkpoint-1712/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2fe6b2339130aa02bfa985d29a359318c8fca356a99e8eaf8e3499d66eeb55b1
+size 17549312

run-24/checkpoint-1712/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3f9a0b6ae746da9415931a5268ea816c079bee8764960da414dc280bc340558
+size 35123898

run-24/checkpoint-1712/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4989482a5a75709b5c8ca6795f7ae67e4569d30e28e8e6fcdef7d2324018c9b4
+size 14308

run-24/checkpoint-1712/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23904bb65fe49032c6392a50e8878a43b091e09746c5ed068a961cedd6e0f224
+size 1064

run-24/checkpoint-1712/special_tokens_map.json

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

run-24/checkpoint-1712/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-24/checkpoint-1712/trainer_state.json

@@ -0,0 +1,186 @@
+{
+  "best_metric": 0.7820738137082601,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-24/checkpoint-1712",
+  "epoch": 8.0,
+  "eval_steps": 500,
+  "global_step": 1712,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 7.816347122192383,
+      "learning_rate": 0.0002514027907655722,
+      "loss": 0.603,
+      "step": 214
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.705916813122437,
+      "eval_f1": 0.4670912951167728,
+      "eval_loss": 0.5544006824493408,
+      "eval_mcc": 0.2876964932013613,
+      "eval_precision": 0.5898123324396782,
+      "eval_recall": 0.3866432337434095,
+      "eval_runtime": 3.1616,
+      "eval_samples_per_second": 539.92,
+      "eval_steps_per_second": 17.08,
+      "step": 214
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 2.7939634323120117,
+      "learning_rate": 0.00021997744191987566,
+      "loss": 0.531,
+      "step": 428
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7352079671939075,
+      "eval_f1": 0.5368852459016393,
+      "eval_loss": 0.5183561444282532,
+      "eval_mcc": 0.3684302929196794,
+      "eval_precision": 0.6437346437346437,
+      "eval_recall": 0.46045694200351495,
+      "eval_runtime": 3.2232,
+      "eval_samples_per_second": 529.598,
+      "eval_steps_per_second": 16.754,
+      "step": 428
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 2.888092279434204,
+      "learning_rate": 0.00018855209307417915,
+      "loss": 0.502,
+      "step": 642
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7451669595782073,
+      "eval_f1": 0.48520710059171596,
+      "eval_loss": 0.5155817270278931,
+      "eval_mcc": 0.3814260429877007,
+      "eval_precision": 0.7427536231884058,
+      "eval_recall": 0.3602811950790861,
+      "eval_runtime": 3.1891,
+      "eval_samples_per_second": 535.256,
+      "eval_steps_per_second": 16.933,
+      "step": 642
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 3.3760223388671875,
+      "learning_rate": 0.00015712674422848263,
+      "loss": 0.4897,
+      "step": 856
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.7422378441710603,
+      "eval_f1": 0.45812807881773393,
+      "eval_loss": 0.5075758695602417,
+      "eval_mcc": 0.37344089980427997,
+      "eval_precision": 0.7654320987654321,
+      "eval_recall": 0.3268892794376098,
+      "eval_runtime": 3.1359,
+      "eval_samples_per_second": 544.344,
+      "eval_steps_per_second": 17.22,
+      "step": 856
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 11.075637817382812,
+      "learning_rate": 0.0001257013953827861,
+      "loss": 0.4761,
+      "step": 1070
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.7568834212067955,
+      "eval_f1": 0.5870646766169154,
+      "eval_loss": 0.49240508675575256,
+      "eval_mcc": 0.42649635439740835,
+      "eval_precision": 0.676605504587156,
+      "eval_recall": 0.5184534270650264,
+      "eval_runtime": 3.1156,
+      "eval_samples_per_second": 547.891,
+      "eval_steps_per_second": 17.332,
+      "step": 1070
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 6.270783424377441,
+      "learning_rate": 9.427604653708957e-05,
+      "loss": 0.4671,
+      "step": 1284
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.7697715289982425,
+      "eval_f1": 0.6288951841359773,
+      "eval_loss": 0.48595207929611206,
+      "eval_mcc": 0.4660789140327505,
+      "eval_precision": 0.6795918367346939,
+      "eval_recall": 0.5852372583479789,
+      "eval_runtime": 3.1299,
+      "eval_samples_per_second": 545.38,
+      "eval_steps_per_second": 17.253,
+      "step": 1284
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 6.990926742553711,
+      "learning_rate": 6.285069769139304e-05,
+      "loss": 0.4567,
+      "step": 1498
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.7633274751025191,
+      "eval_f1": 0.5692963752665245,
+      "eval_loss": 0.48252516984939575,
+      "eval_mcc": 0.43473790600905954,
+      "eval_precision": 0.7235772357723578,
+      "eval_recall": 0.46924428822495606,
+      "eval_runtime": 3.1545,
+      "eval_samples_per_second": 541.124,
+      "eval_steps_per_second": 17.118,
+      "step": 1498
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 4.125209331512451,
+      "learning_rate": 3.142534884569652e-05,
+      "loss": 0.4404,
+      "step": 1712
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.7820738137082601,
+      "eval_f1": 0.6395348837209303,
+      "eval_loss": 0.4758114218711853,
+      "eval_mcc": 0.4910151946014594,
+      "eval_precision": 0.712742980561555,
+      "eval_recall": 0.5799648506151143,
+      "eval_runtime": 3.146,
+      "eval_samples_per_second": 542.597,
+      "eval_steps_per_second": 17.165,
+      "step": 1712
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1926,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 9,
+  "save_steps": 500,
+  "total_flos": 4198205315520.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.9932022812512611,
+    "learning_rate": 0.0002828281396112687,
+    "num_train_epochs": 9,
+    "temperature": 23
+  }
+}

run-24/checkpoint-1712/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:056a4a07ea3eb275e3c290638752eb45bcffa89ead6519b5845088d41a30cf92
+size 5048