Training in progress, epoch 2

logs/events.out.tfevents.1709626841.404ecd1cf399.26000.53

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ade98877df669472b9a06965a564a748d436fc7d010bb4c3fbb36ca3bd76dbeb
-size 5315
+oid sha256:4e0776857fc0e1603478abb2492058c9859225ce77ac20e40986366cef842db9
+size 5998

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90e0f6ba198283f00aaa1b554b11a2fca511e92ed1166415610ba7cfabd50919
+oid sha256:b650efa919f6a4973bb634fc29f097f7b8f22afbce00a3634222130b8799584e
 size 17549312

run-47/checkpoint-192/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-47/checkpoint-192/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b650efa919f6a4973bb634fc29f097f7b8f22afbce00a3634222130b8799584e
+size 17549312

run-47/checkpoint-192/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1162fc127b4cd021624e70033605878611ce1ce20b393ac289567fc571860a54
+size 35122746

run-47/checkpoint-192/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c58c0607d97c986e9d4c30b0aa74b33350e0c7e86978aaaaadda4ebb78f21ad
+size 14054

run-47/checkpoint-192/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46ff4487f6324742fb6cf7e7658cb071ca8124651eeb533389b314bc24c7eb76
+size 1064

run-47/checkpoint-192/special_tokens_map.json

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

run-47/checkpoint-192/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-47/checkpoint-192/trainer_state.json

@@ -0,0 +1,64 @@
+{
+  "best_metric": 0.8297455968688845,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-47/checkpoint-192",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 192,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 10.090946197509766,
+      "learning_rate": 0.0002726931435690813,
+      "loss": 0.5743,
+      "step": 96
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7964774951076321,
+      "eval_f1": 0.8188153310104529,
+      "eval_loss": 0.4561440944671631,
+      "eval_precision": 0.7378335949764521,
+      "eval_recall": 0.9197651663405088,
+      "eval_runtime": 30.8585,
+      "eval_samples_per_second": 33.119,
+      "eval_steps_per_second": 1.037,
+      "step": 96
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 7.258547306060791,
+      "learning_rate": 0.00018179542904605417,
+      "loss": 0.4449,
+      "step": 192
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8297455968688845,
+      "eval_f1": 0.8406593406593407,
+      "eval_loss": 0.4051818251609802,
+      "eval_precision": 0.7900172117039587,
+      "eval_recall": 0.898238747553816,
+      "eval_runtime": 31.0429,
+      "eval_samples_per_second": 32.922,
+      "eval_steps_per_second": 1.031,
+      "step": 192
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 384,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 471390394560.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.999132297568699,
+    "learning_rate": 0.00036359085809210834,
+    "num_train_epochs": 4,
+    "temperature": 14
+  }
+}

run-47/checkpoint-192/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e52d4ef52e4ae3e7583492431957732ea2f0822ace3819ef8d07c56bc154648
+size 4920