Training in progress, epoch 1

logs/events.out.tfevents.1709881034.6c1c016b0e3e.7263.23

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d2a2a5dffd2b03a2fd72a78de797cb87bfe7e824160716317e234015931b4468
-size 5983
+oid sha256:b3c9732893536e4b615f0fc9a3e50541aebe72d47ad59fc293c5a36e1097c1a2
+size 6666

logs/events.out.tfevents.1709881368.6c1c016b0e3e.7263.24

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b1195135b9ca9b0f8f15473db9b4ee1f48cbb1d61001d41c856e3c69f6b429d
+size 5314

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5123c79380722d239a861a74fe7216bf60d8262e3e6e043f3e265f8571f280ec
+oid sha256:484ca8b92fe3f5cd803dcdf1eb6ee5cfd5877d32291b850679f9c02bf16599a2
 size 17549312

run-24/checkpoint-48/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-24/checkpoint-48/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:484ca8b92fe3f5cd803dcdf1eb6ee5cfd5877d32291b850679f9c02bf16599a2
+size 17549312

run-24/checkpoint-48/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7ccaf192da5f14e4849d00606fca452c098aa9df200acfb3884f41ef066fb09
+size 35122746

run-24/checkpoint-48/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f731098665929ed6a815501631b54240caaac6508207c5c55cf0fe36ad39b17
+size 14054

run-24/checkpoint-48/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:509aa353a76d0653a8059578db497511f05c72ff01dc3670971837f90bce6fe8
+size 1064

run-24/checkpoint-48/special_tokens_map.json

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

run-24/checkpoint-48/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-24/checkpoint-48/trainer_state.json

@@ -0,0 +1,45 @@
+{
+  "best_metric": 0.7475538160469667,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-24/checkpoint-48",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 48,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.4524683952331543,
+      "learning_rate": 0.00041148401868626845,
+      "loss": 0.4958,
+      "step": 48
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7475538160469667,
+      "eval_f1": 0.7528735632183908,
+      "eval_loss": 0.4411579370498657,
+      "eval_precision": 0.7373358348968105,
+      "eval_recall": 0.7690802348336595,
+      "eval_runtime": 27.0601,
+      "eval_samples_per_second": 37.768,
+      "eval_steps_per_second": 0.591,
+      "step": 48
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 144,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 235695197280.0,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.720782515325305,
+    "learning_rate": 0.0006172260280294027,
+    "num_train_epochs": 3,
+    "temperature": 25
+  }
+}

run-24/checkpoint-48/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a651e1489f16b7a9f5d272a1de8767a729124774a1a2154ceef87a138c2c180d
+size 4920

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d72cddafb614267648e2058beccba005678ef941672ddb888715c22a753d1de0
+oid sha256:a651e1489f16b7a9f5d272a1de8767a729124774a1a2154ceef87a138c2c180d
 size 4920