Training in progress, epoch 2

logs/events.out.tfevents.1709697132.a2333cf40ebd.21010.3

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a291ac31fba750739770fa01afde949394278bdc98f20828e00ff7238845a6ab
-size 5315
+oid sha256:a42c66a4dbc9c15a1e11e4420cc6cee1f17955c58c47c1150747c7eacb505a57
+size 5998

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:446c2c31d01eea9266672f75b6ffe66317a4cdf5130baa8b7dd4d988ec7f3dd9
+oid sha256:cb4d5e48b7b7dcbc4c6a78ba6f64447d41c31642b436b85f9712ebc3f1eb4e10
 size 17549312

run-3/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-3/checkpoint-192/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb4d5e48b7b7dcbc4c6a78ba6f64447d41c31642b436b85f9712ebc3f1eb4e10
+size 17549312

run-3/checkpoint-192/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed70a7588f0522641062b0d7a3e3b4990f0e2467607917b4e82af82ed85fe05c
+size 35122746

run-3/checkpoint-192/rng_state.pth

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

run-3/checkpoint-192/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bbb03ae8de430d092285c0e0abd694736b22b9adda00f4f93056103d08f6a645
+size 1064

run-3/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-3/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-3/checkpoint-192/trainer_state.json

@@ -0,0 +1,64 @@
+{
+  "best_metric": 0.5,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-3/checkpoint-96",
+  "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": 2.101290702819824,
+      "learning_rate": 1.1962059637335337e-06,
+      "loss": 0.5173,
+      "step": 96
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5,
+      "eval_f1": 0.6666666666666666,
+      "eval_loss": 0.5046124458312988,
+      "eval_precision": 0.5,
+      "eval_recall": 1.0,
+      "eval_runtime": 28.251,
+      "eval_samples_per_second": 36.176,
+      "eval_steps_per_second": 1.133,
+      "step": 96
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.6350829005241394,
+      "learning_rate": 1.0466802182668422e-06,
+      "loss": 0.4989,
+      "step": 192
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.4843444227005871,
+      "eval_f1": 0.6216798277099785,
+      "eval_loss": 0.48798972368240356,
+      "eval_precision": 0.4909297052154195,
+      "eval_recall": 0.8473581213307241,
+      "eval_runtime": 28.492,
+      "eval_samples_per_second": 35.87,
+      "eval_steps_per_second": 1.123,
+      "step": 192
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 864,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 9,
+  "save_steps": 500,
+  "total_flos": 471390394560.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.586704262013931,
+    "learning_rate": 1.3457317092002255e-06,
+    "num_train_epochs": 9,
+    "temperature": 21
+  }
+}

run-3/checkpoint-192/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b765cab6920f955460cc4f812305ba7f085db0f4dbb906f08e22ff912fece657
+size 4920