Training in progress, epoch 1

logs/events.out.tfevents.1713612042.a9446dbff3d4.7440.21

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:307d771b10e90819fbfcb6ef2b5c7c6c5ad0871b1bd93ae2e35212d85b559ef6
-size 5483
+oid sha256:bb09800a62e872c554502e6aedcb18699792455b6e93b21fcb872da830ce9fd0
+size 6213

logs/events.out.tfevents.1713612062.a9446dbff3d4.7440.22

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2bfac59d9b933c223fd8f0ee6df0b416a2f98cdde3597800601b260bba69c969
+size 5482

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b48b1494ca5dd5a6fb9bfd96f6c7ba5ff0866019753885e030f14d77971f34ec
+oid sha256:fb42659c81d9c4fb9bbb572a06752648b3d14267294dd6c8f876ac182b6601ea
 size 17549312

run-20/checkpoint-160/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": "4.40.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-20/checkpoint-160/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb42659c81d9c4fb9bbb572a06752648b3d14267294dd6c8f876ac182b6601ea
+size 17549312

run-20/checkpoint-160/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c99d9ecef479555a2b93e6809105a8079fec8b8001fecfb6ff04d7d69b9908f
+size 35123898

run-20/checkpoint-160/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0792eaff268dd73c8e104b5060a487f4ef56535ad3b58888006338b8bc298137
+size 14308

run-20/checkpoint-160/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0d7fe050af48f30e2f2e4d079eb70b8544cb46aa2b23890f7b47f238e24b714
+size 1064

run-20/checkpoint-160/special_tokens_map.json

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

run-20/checkpoint-160/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-20/checkpoint-160/trainer_state.json

@@ -0,0 +1,46 @@
+{
+  "best_metric": 0.6909803921568628,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-20/checkpoint-160",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 160,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 2.297672986984253,
+      "learning_rate": 0.0004503757705353633,
+      "loss": 0.5065,
+      "step": 160
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6909803921568628,
+      "eval_f1": 0.286231884057971,
+      "eval_loss": 0.46740272641181946,
+      "eval_mcc": 0.20370649805068908,
+      "eval_precision": 0.6220472440944882,
+      "eval_recall": 0.18588235294117647,
+      "eval_runtime": 1.8709,
+      "eval_samples_per_second": 681.504,
+      "eval_steps_per_second": 21.381,
+      "step": 160
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1120,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 7,
+  "save_steps": 500,
+  "total_flos": 291755437920.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.796338716906447,
+    "learning_rate": 0.0005254383989579239,
+    "num_train_epochs": 7,
+    "temperature": 7
+  }
+}

run-20/checkpoint-160/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e549ae8cec45a4c9c1359d1cb3b93e561c5ec74fee27d5f1fce2fbd04ef853a4
+size 5048

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e97703b0e3834e198a1287acc47276ca2385cec87992e03e387a2de7b6032697
+oid sha256:e549ae8cec45a4c9c1359d1cb3b93e561c5ec74fee27d5f1fce2fbd04ef853a4
 size 5048