Training in progress, epoch 1

logs/events.out.tfevents.1706170796.A-FVFFG2C4Q05P.18450.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7f66c918ed4b1e873dd9a5e7f3be643167a01cc42bd9e3f4d38a63fef39cd5c
-size 7299
+oid sha256:f38bdeeda46dccbd1baa9a5f39d763bbab4fae66f600259622b5677b021bd92c
+size 8133

logs/events.out.tfevents.1706175299.A-FVFFG2C4Q05P.18450.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a4d0db3c48ada0b77c779b5020fea08aea26c28a05be97513507329065560e2
+size 4916

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:902a98e8d21a91fe2fcb0fee8725c3be33f69134eba1233f9ebeaf913c3854ef
+oid sha256:5c52e494c8a54e31d0905183277502473d55f04968f399572f68c03699d0896d
 size 17549312

run-0/checkpoint-527/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": "4.37.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-0/checkpoint-527/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c52e494c8a54e31d0905183277502473d55f04968f399572f68c03699d0896d
+size 17549312

run-0/checkpoint-527/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0fb6b69756fc374675072f45af86025909a30d480c089050cd759261787a8d5
+size 35122373

run-0/checkpoint-527/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f943a8d8f93fea7f44cad3b9bfb2d2b97d65b141eb704b9cba669cf42e776b14
+size 13617

run-0/checkpoint-527/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e413a6599730470af1f979f67d57be7e818e88c2f6d99694239a1b71f729996
+size 627

run-0/checkpoint-527/special_tokens_map.json

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

run-0/checkpoint-527/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-0/checkpoint-527/trainer_state.json

@@ -0,0 +1,41 @@
+{
+  "best_metric": 0.8107798165137615,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-0/checkpoint-527",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 527,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 9.507440967713177e-05,
+      "loss": 1.6043,
+      "step": 527
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8107798165137615,
+      "eval_loss": 1.3382474184036255,
+      "eval_runtime": 7.7477,
+      "eval_samples_per_second": 112.55,
+      "eval_steps_per_second": 0.903,
+      "step": 527
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2108,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 8069051778960.0,
+  "train_batch_size": 128,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.46638270752374766,
+    "learning_rate": 0.00012676587956950903,
+    "num_train_epochs": 4,
+    "temperature": 20
+  }
+}

run-0/checkpoint-527/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b149b247816d0d72efcc0fd576feb131fc41a6f49009ffa81023f2608190ff20
+size 4283

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79cfc47483084d21697cda4e5684f7ce9be58f53d75604ea2cf82348fe669690
+oid sha256:b149b247816d0d72efcc0fd576feb131fc41a6f49009ffa81023f2608190ff20
 size 4283