Training in progress, epoch 2

logs/events.out.tfevents.1699910323.b18f42e49ba4.3021.22

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9baa1f9a8931663d89030e696f660ba2bbf771412da79d64dc405abb9a840a7
-size 4773
+oid sha256:ae0426d3cbdf139ee9ea0a640ebf18ff3961955a3536492336ac759c32c18094
+size 5253

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e38cc5ba5e818f31af0b64ec8e8ed6691e3bb8a5ede94923612049376a9e8ef
+oid sha256:11ac06fd0758b28a577a25b1f5635d689997ac4ce45727516b156a19b16c5b59
 size 17549312

run-21/checkpoint-1054/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": "4.35.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-21/checkpoint-1054/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11ac06fd0758b28a577a25b1f5635d689997ac4ce45727516b156a19b16c5b59
+size 17549312

run-21/checkpoint-1054/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f51aeb832c885f8fdf603f645eecba8deb808436d86683dc02b904b21f450c76
+size 35123898

run-21/checkpoint-1054/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57fdff683e14337980bac7da3d561a7fdab384be06942739a4198db7026ad4c6
+size 14308

run-21/checkpoint-1054/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad1ab1400ab6f5c5fad9177bb1025246d59dda4b537d810fdb41615b5fb150e3
+size 1064

run-21/checkpoint-1054/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-1054/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-1054/trainer_state.json

@@ -0,0 +1,54 @@
+{
+  "best_metric": 0.8211009174311926,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-21/checkpoint-527",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 1054,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.0007813674039938339,
+      "loss": 1.4569,
+      "step": 527
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8211009174311926,
+      "eval_loss": 1.8369688987731934,
+      "eval_runtime": 0.957,
+      "eval_samples_per_second": 911.136,
+      "eval_steps_per_second": 7.314,
+      "step": 527
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 0.0006251532075201045,
+      "loss": 0.6203,
+      "step": 1054
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.819954128440367,
+      "eval_loss": 2.187230110168457,
+      "eval_runtime": 0.833,
+      "eval_samples_per_second": 1046.865,
+      "eval_steps_per_second": 8.404,
+      "step": 1054
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 3162,
+  "num_train_epochs": 6,
+  "save_steps": 500,
+  "total_flos": 16194449161860.0,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.12545237557795993,
+    "learning_rate": 0.0009372851788423759,
+    "num_train_epochs": 6,
+    "temperature": 30
+  }
+}

run-21/checkpoint-1054/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9cf4805dbdf09e6f5258853c790c37af35f2cbe2f2d5a284a8389b7ec93b9b40
+size 4600