Training in progress, epoch 1

logs/events.out.tfevents.1709544882.11df171e7ffa.529.1

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a09ebacdec6d7e09788db837c152a7b008529bc669f561e90d4407f17175295c
-size 7824
+oid sha256:f7ea051904a29987fa01d43ae175709bdd2a92b8805c31f5725e3e90242199c9
+size 8712

logs/events.out.tfevents.1709553057.11df171e7ffa.529.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2faecde3271971a45cae186718fe4afa43b854f9cd45e0a7a0e838a7c307c95b
+size 5171

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac9f1188e5d58ce7c0f41b61429a222244ee2b0caec89b72277cc7be004ab102
+oid sha256:698ec69330682d24c7e55a7c5f0df6b3af83ab39374aa4153ee428f4cf2b6b3b
 size 17549312

run-0/checkpoint-75/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-0/checkpoint-75/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:698ec69330682d24c7e55a7c5f0df6b3af83ab39374aa4153ee428f4cf2b6b3b
+size 17549312

run-0/checkpoint-75/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57640bab36617266fededee652571407294701938c6c9b0f657f98103b7e9ce0
+size 35122746

run-0/checkpoint-75/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ac8d6c67447a15b9d51f14179a6a091394591d74ba40110b627bf9167b78171
+size 14054

run-0/checkpoint-75/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4500b036366da4974c7b1c982eef291853f63fd4a0a2a18ca4267e23fbc70b24
+size 1064

run-0/checkpoint-75/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-75/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-75/trainer_state.json

@@ -0,0 +1,42 @@
+{
+  "best_metric": 0.5148514851485149,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-0/checkpoint-75",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 75,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.31773510575294495,
+      "learning_rate": 0.00019498896290528944,
+      "loss": 0.0964,
+      "step": 75
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5148514851485149,
+      "eval_loss": 0.077483631670475,
+      "eval_runtime": 57.3954,
+      "eval_samples_per_second": 8.799,
+      "eval_steps_per_second": 0.07,
+      "step": 75
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 375,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 777843283140.0,
+  "train_batch_size": 128,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.08009223161090917,
+    "learning_rate": 0.00024373620363161177,
+    "num_train_epochs": 5,
+    "temperature": 24
+  }
+}

run-0/checkpoint-75/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c07c5338ce9724729e2f99d42abdb57887932f817eb41546efc9c3b2ccad442
+size 4984

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f595b6b37b4ca480c988fc71775b6f7ad23276c5fedbdf77abe47e38b2c63d94
+oid sha256:3c07c5338ce9724729e2f99d42abdb57887932f817eb41546efc9c3b2ccad442
 size 4984