Training in progress, epoch 2

logs/events.out.tfevents.1709738692.d65e8524b0f6.5185.2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac31aaa9b3fd2475cb2759b94a5eac114fde5a207c04ca99f1f971acc746c1ee
-size 5315
+oid sha256:4b6cd896c1316ce38c1198f14fda687c1eb6cbbb76321c009a5ceb039772dc2b
+size 5998

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a84a4019c19e1375f4edf4cb296e8434aebd973f426f5b41c1b64f11aeb4c2c9
+oid sha256:186cd927bf5f88a728161666b86a89404a531ac5678ebc58f69043d1940cc11e
 size 17549312

run-2/checkpoint-246/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-2/checkpoint-246/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:186cd927bf5f88a728161666b86a89404a531ac5678ebc58f69043d1940cc11e
+size 17549312

run-2/checkpoint-246/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2fdf98a953435f9ff26b847c06619c3478fdaaa19b48a0214cba818ca23d63a5
+size 35122746

run-2/checkpoint-246/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74199c4a845f678c9eb0481b4813536d3e1b2620695d173ba2aa8c9e2fa07527
+size 14054

run-2/checkpoint-246/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4e9f91007733c2f7950fceca3489833fcd44708c2039c5cd08a49440a92666d
+size 1064

run-2/checkpoint-246/special_tokens_map.json

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

run-2/checkpoint-246/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-2/checkpoint-246/trainer_state.json

@@ -0,0 +1,65 @@
+{
+  "best_metric": 0.5322896281800391,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-2/checkpoint-246",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 246,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.0383042097091675,
+      "learning_rate": 2.0778074552979435e-05,
+      "loss": 0.4799,
+      "step": 123
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5,
+      "eval_f1": 0.0,
+      "eval_loss": 0.4709824323654175,
+      "eval_precision": 0.0,
+      "eval_recall": 0.0,
+      "eval_runtime": 29.6795,
+      "eval_samples_per_second": 34.435,
+      "eval_steps_per_second": 1.078,
+      "step": 123
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.8932008743286133,
+      "learning_rate": 1.780977818826809e-05,
+      "loss": 0.4618,
+      "step": 246
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.5322896281800391,
+      "eval_f1": 0.1758620689655172,
+      "eval_loss": 0.44377976655960083,
+      "eval_precision": 0.7391304347826086,
+      "eval_recall": 0.09980430528375733,
+      "eval_runtime": 29.7432,
+      "eval_samples_per_second": 34.361,
+      "eval_steps_per_second": 1.076,
+      "step": 246
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 984,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 8,
+  "save_steps": 500,
+  "total_flos": 471390394560.0,
+  "train_batch_size": 25,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.6164141606295046,
+    "learning_rate": 2.3746370917690784e-05,
+    "num_train_epochs": 8,
+    "per_device_train_batch_size": 25,
+    "temperature": 15
+  }
+}

run-2/checkpoint-246/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b12fae66bf7135cb37ed8647f139f4eb5fe8d802e6cb8a3640f287039e54b031
+size 4920