Training in progress, epoch 2

logs/events.out.tfevents.1709854817.013ec1551212.75384.20

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c1ebcece0040768f5b7009ef28cdef47ee33fb0c9c064b2690a6d4d752d44b94
-size 5326
+oid sha256:3a1914e063d920ff07922d7b06fe2959ffa5e70cf846079b148f7d8ff8ee2109
+size 6009

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:65360a638b477d7acd92099477ca94f58dc222a7dade21e9ede8253d774e1424
+oid sha256:0d13bb328c8f04fe9d8b210073add43cc3240f951bc16f783b9c277b86bbe723
 size 17549312

run-20/checkpoint-1532/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-20/checkpoint-1532/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d13bb328c8f04fe9d8b210073add43cc3240f951bc16f783b9c277b86bbe723
+size 17549312

run-20/checkpoint-1532/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:101eea7e907e47e171273d556c6cd2c779ee92d70e0810173af6fe0b4407d985
+size 35122746

run-20/checkpoint-1532/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16aaf318a00ee2d6780264865ac856fcd3f746d06b5d79fd7d77f53b35786488
+size 14054

run-20/checkpoint-1532/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7247972532f218e1e4ecb9cd3aedb5e9e94c4a0ee6dd9ac39edf85ee5d4c4f72
+size 1064

run-20/checkpoint-1532/special_tokens_map.json

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

run-20/checkpoint-1532/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-20/checkpoint-1532/trainer_state.json

@@ -0,0 +1,64 @@
+{
+  "best_metric": 0.815068493150685,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-20/checkpoint-1532",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 1532,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 2.1449050903320312,
+      "learning_rate": 0.00010427761773013143,
+      "loss": 0.5295,
+      "step": 766
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8043052837573386,
+      "eval_f1": 0.82174688057041,
+      "eval_loss": 0.44088178873062134,
+      "eval_precision": 0.7545008183306056,
+      "eval_recall": 0.9021526418786693,
+      "eval_runtime": 133.3851,
+      "eval_samples_per_second": 7.662,
+      "eval_steps_per_second": 1.919,
+      "step": 766
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 32.69517517089844,
+      "learning_rate": 7.820821329759857e-05,
+      "loss": 0.4623,
+      "step": 1532
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.815068493150685,
+      "eval_f1": 0.832,
+      "eval_loss": 0.4221538305282593,
+      "eval_precision": 0.762214983713355,
+      "eval_recall": 0.9158512720156555,
+      "eval_runtime": 131.8748,
+      "eval_samples_per_second": 7.75,
+      "eval_steps_per_second": 1.941,
+      "step": 1532
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 3830,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 471390394560.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.8705195866732912,
+    "learning_rate": 0.00013034702216266429,
+    "num_train_epochs": 5,
+    "temperature": 7
+  }
+}

run-20/checkpoint-1532/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1dcf84980d391e8dfe049bf36dfb13241b79c0135fa7de15b04f0125742f71b
+size 4920