Training in progress, epoch 2

logs/events.out.tfevents.1710434095.4cb0d5d7fb51.5918.1

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:026d7c7b4ff6d5b241f21c4d927c92019c5434ea2c4d35a0321fdafed4d6dee5
-size 5178
+oid sha256:e6069c9e5a9b4359ed272f493fd7287f36234da848f0a440570550e6871b20b7
+size 5712

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf78f191f8ec19931f9cd904378746a6b65295ee17e7e52a6a382fd0d4c8a6dd
+oid sha256:344b138dc88029e26487137bf04ab764bfd8c50b0c4e250209570c66a7a6e72a
 size 17549312

run-1/checkpoint-594/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-1/checkpoint-594/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:344b138dc88029e26487137bf04ab764bfd8c50b0c4e250209570c66a7a6e72a
+size 17549312

run-1/checkpoint-594/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3838bb012c26b6885a4d98683f23c3bac0ff6bc9a974e150f7cfc7e6a4ee6524
+size 35122746

run-1/checkpoint-594/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df6866d0dff400085edf68783c4718d94e08dcfa8f0d23f9d94ad3e230de2def
+size 14054

run-1/checkpoint-594/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ea0926647a95b27454bb746171324fe1e45de3f0490f428a4522f18ecbc78db
+size 1064

run-1/checkpoint-594/special_tokens_map.json

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

run-1/checkpoint-594/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-1/checkpoint-594/trainer_state.json

@@ -0,0 +1,58 @@
+{
+  "best_metric": 0.6277227722772277,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-1/checkpoint-594",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 594,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.3426679372787476,
+      "learning_rate": 0.0003560526201910554,
+      "loss": 0.6371,
+      "step": 297
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5841584158415841,
+      "eval_loss": 0.637409508228302,
+      "eval_runtime": 56.7978,
+      "eval_samples_per_second": 8.891,
+      "eval_steps_per_second": 0.282,
+      "step": 297
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.018396258354187,
+      "learning_rate": 0.0002373684134607036,
+      "loss": 0.603,
+      "step": 594
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6277227722772277,
+      "eval_loss": 0.6017976403236389,
+      "eval_runtime": 55.6441,
+      "eval_samples_per_second": 9.076,
+      "eval_steps_per_second": 0.288,
+      "step": 594
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1188,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 1555686566280.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.900582717199523,
+    "learning_rate": 0.0004747368269214072,
+    "num_train_epochs": 4,
+    "temperature": 18
+  }
+}

run-1/checkpoint-594/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6f636dbab8b5e516bcd85051f9f0732a28727ed1675f1d1f3076c7baf2be402
+size 4984