Training in progress, epoch 2

logs/events.out.tfevents.1709878343.6c1c016b0e3e.7263.16

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f66fbe2b30759a779431ee345986991f1ca9078664ae104ce5b1254f2249647b
-size 5315
+oid sha256:f5208271e97b80f006885f363d4916be48498fa36257caded30d489269c48f7b
+size 5985

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6686bb2537fd44affb628e87f3476f2ed8535e617f7a8a0d48ddbc9d84f18e28
+oid sha256:88bdd4dc338ef9c8a968b0df5b17e6aa84927b6e6c113d0aeb7a52cf148234d0
 size 17549312

run-16/checkpoint-96/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": "4.38.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-16/checkpoint-96/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88bdd4dc338ef9c8a968b0df5b17e6aa84927b6e6c113d0aeb7a52cf148234d0
+size 17549312

run-16/checkpoint-96/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:690005196f53b048810c4d905cea3d597310f6f37ffc2dc4daf0d82f2d84c891
+size 35122746

run-16/checkpoint-96/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6bc13e09b59a62b6fb29cad756bfeefcce6f512c71a9054cc39e336db0b532a5
+size 14054

run-16/checkpoint-96/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d2d214a08217f8b1f276906a783446beff63736536863cb4d982ed404b8b4a7
+size 1064

run-16/checkpoint-96/special_tokens_map.json

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

run-16/checkpoint-96/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-16/checkpoint-96/trainer_state.json

@@ -0,0 +1,64 @@
+{
+  "best_metric": 0.700587084148728,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-16/checkpoint-48",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 96,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.2878928184509277,
+      "learning_rate": 0.00013115653902338105,
+      "loss": 0.4962,
+      "step": 48
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.700587084148728,
+      "eval_f1": 0.662251655629139,
+      "eval_loss": 0.4426267147064209,
+      "eval_precision": 0.759493670886076,
+      "eval_recall": 0.5870841487279843,
+      "eval_runtime": 27.3,
+      "eval_samples_per_second": 37.436,
+      "eval_steps_per_second": 0.586,
+      "step": 48
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 3.258302688598633,
+      "learning_rate": 0.00011241989059146946,
+      "loss": 0.4374,
+      "step": 96
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6898238747553816,
+      "eval_f1": 0.6248520710059171,
+      "eval_loss": 0.41270217299461365,
+      "eval_precision": 0.7904191616766467,
+      "eval_recall": 0.5166340508806262,
+      "eval_runtime": 27.1797,
+      "eval_samples_per_second": 37.602,
+      "eval_steps_per_second": 0.589,
+      "step": 96
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 384,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 8,
+  "save_steps": 500,
+  "total_flos": 471390394560.0,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.6758158495370239,
+    "learning_rate": 0.00014989318745529262,
+    "num_train_epochs": 8,
+    "temperature": 20
+  }
+}

run-16/checkpoint-96/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63572106dff22a09912a371bd397d01ccf0c92ef49dec03568516e174c66f6b6
+size 4920