Training in progress, epoch 2

logs/events.out.tfevents.1713588781.1376c752d37a.9760.21

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eaf55a804e82a8774d8f511f2f505101da848771142ba2c3a02593efd0bce00f
-size 5483
+oid sha256:263d2061d9559c4b9a482484c86566f009293c766cc5824d77f21ba8fafbd9c0
+size 6567

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:51b863770c5b782d9cacddaf25e4963b1e0ebed2aad80517e1f4fede324ed078
+oid sha256:d669af47415e18127db56562822ec1129ed60d2f80f7ab8e270c64c3a3f764f3
 size 17549312

run-21/checkpoint-428/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-21/checkpoint-428/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d669af47415e18127db56562822ec1129ed60d2f80f7ab8e270c64c3a3f764f3
+size 17549312

run-21/checkpoint-428/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0af4eea02545a46e6cbc4e8195374449a2996a945f5af298929681f70fd43299
+size 35123898

run-21/checkpoint-428/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d0c3b463a8fb08b95f5c77916114776bad3339b633df010e4ffd9b5ddabab1e
+size 14308

run-21/checkpoint-428/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:054b3c22aedcfe5c1cbef6d19b9e95b6a46278e2a5d0128578e0adf91e4f8e12
+size 1064

run-21/checkpoint-428/special_tokens_map.json

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

run-21/checkpoint-428/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-21/checkpoint-428/trainer_state.json

@@ -0,0 +1,66 @@
+{
+  "best_metric": 0.7234915055653193,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-21/checkpoint-428",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 428,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 7.830043792724609,
+      "learning_rate": 9.118416079790422e-05,
+      "loss": 0.5332,
+      "step": 214
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.705916813122437,
+      "eval_f1": 0.49087221095334677,
+      "eval_loss": 0.4951828718185425,
+      "eval_mcc": 0.2979069251542787,
+      "eval_precision": 0.580335731414868,
+      "eval_recall": 0.4253075571177504,
+      "eval_runtime": 3.1297,
+      "eval_samples_per_second": 545.419,
+      "eval_steps_per_second": 17.254,
+      "step": 214
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 2.675640106201172,
+      "learning_rate": 0.0,
+      "loss": 0.4845,
+      "step": 428
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7234915055653193,
+      "eval_f1": 0.51440329218107,
+      "eval_loss": 0.4795408844947815,
+      "eval_mcc": 0.3384723199828929,
+      "eval_precision": 0.6203473945409429,
+      "eval_recall": 0.43936731107205623,
+      "eval_runtime": 3.1418,
+      "eval_samples_per_second": 543.315,
+      "eval_steps_per_second": 17.187,
+      "step": 428
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 428,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "total_flos": 1049551328880.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.864112168223305,
+    "learning_rate": 0.00018236832159580844,
+    "num_train_epochs": 2,
+    "temperature": 19
+  }
+}

run-21/checkpoint-428/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:726be031a7397cff6ef45b843163594c5b44a5e8dce5548e17dcb1e2f08bf77f
+size 5048