Training in progress, epoch 1

logs/events.out.tfevents.1709737100.d65e8524b0f6.2063.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85b8c83a67ea2bdf7164ee71447c93a7e24e3b9a6ddf672b2104cee3501769ae
+size 4184

logs/events.out.tfevents.1709737266.d65e8524b0f6.5185.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:319ac5c1bb07786f883edcccaae02cabf4fcf3f00f6e12cce3fad343e5d6ab2f
+size 5314

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7de1dc5175e7fff3bedf8ce976798a899489986f9911eca284b9b482c440c078
+oid sha256:c3f23050b635f2ea8a6ebefacc76753049fc76bd03375e3fb8a1a592289d0966
 size 17549312

run-0/checkpoint-81/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-81/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3f23050b635f2ea8a6ebefacc76753049fc76bd03375e3fb8a1a592289d0966
+size 17549312

run-0/checkpoint-81/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb813dcac541b1f671030d1cf27ffaef89eed06abbd7f55a8c7b851c4ecf1665
+size 35122746

run-0/checkpoint-81/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84a4423991462ba805318a1497ec3e4d0d13d424946210ddceeea55dbf315ffd
+size 14054

run-0/checkpoint-81/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cadf368127fcfd5b3b4882c5ba8e88ec6101d87ce1b54a31750aebf09c0b23c6
+size 1064

run-0/checkpoint-81/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-81/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-81/trainer_state.json

@@ -0,0 +1,46 @@
+{
+  "best_metric": 0.5,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-0/checkpoint-81",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 81,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.29800447821617126,
+      "learning_rate": 2.6647930950340397e-05,
+      "loss": 0.3887,
+      "step": 81
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5,
+      "eval_f1": 0.0,
+      "eval_loss": 0.3728242516517639,
+      "eval_precision": 0.0,
+      "eval_recall": 0.0,
+      "eval_runtime": 30.0921,
+      "eval_samples_per_second": 33.962,
+      "eval_steps_per_second": 1.063,
+      "step": 81
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 729,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 9,
+  "save_steps": 500,
+  "total_flos": 235695197280.0,
+  "train_batch_size": 38,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.462182377373202,
+    "learning_rate": 2.997892231913295e-05,
+    "num_train_epochs": 9,
+    "per_device_train_batch_size": 38,
+    "temperature": 10
+  }
+}

run-0/checkpoint-81/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c234fefe2007f16535ef723e1425baa7c9b3f0aec93243168de7f22031da2d1
+size 4920

tokenizer.json

@@ -2,7 +2,7 @@
   "version": "1.0",
   "truncation": {
     "direction": "Right",
-    "max_length": 33,
+    "max_length": 31,
     "strategy": "LongestFirst",
     "stride": 0
   },

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ccea265ae9122da077ff8def664c83c587f85ed26bee202b170a564116cd542
+oid sha256:6c234fefe2007f16535ef723e1425baa7c9b3f0aec93243168de7f22031da2d1
 size 4920