Training in progress, epoch 2

logs/events.out.tfevents.1702286155.joseph_legion.22340.21

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4070902433aee0b479fbde5c40548b71b95614797c4568439a1ffb69622b8cb6
-size 4926
+oid sha256:d780c1e596f6950266700a47a7a3099743cb175d2ef5ff74890db59f944a7dcd
+size 5406

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78771c8f22d9b40ff96dee24dfd528a3e5dd5ada89bfc44ac09d1b9fb2cfaa20
+oid sha256:b23aedd0e49c2c041178a7ff5bee4f3a8ec6412a728426f7ec9fc26bde988632
 size 44692608

run-8/checkpoint-394/config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "google/bert_uncased_L-4_H-256_A-4",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 256,
+  "id2label": {
+    "0": 0,
+    "1": 1
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 1024,
+  "label2id": {
+    "0": 0,
+    "1": 1
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 4,
+  "num_hidden_layers": 4,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.36.0.dev0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-8/checkpoint-394/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b23aedd0e49c2c041178a7ff5bee4f3a8ec6412a728426f7ec9fc26bde988632
+size 44692608

run-8/checkpoint-394/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c638e620032c57d3475766722a5e5955f3f248fc429993430c687a41696cb947
+size 89430010

run-8/checkpoint-394/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0083669a8e03e9d38e7a194d1d1afd6ce0c7a81ecd92861e94a0d9384aa80747
+size 14308

run-8/checkpoint-394/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5dc61acf8a2945688f390523ae2f949c929eebc1d9cfe169494911cad6804add
+size 1064

run-8/checkpoint-394/special_tokens_map.json

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

run-8/checkpoint-394/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-8/checkpoint-394/trainer_state.json

@@ -0,0 +1,55 @@
+{
+  "best_metric": 0.783212896053363,
+  "best_model_checkpoint": "tinybert-TG-HS-HX-parentpretrained\\run-8\\checkpoint-394",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 394,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 9.45388964676361e-06,
+      "loss": 0.275,
+      "step": 197
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7752918287937743,
+      "eval_loss": 0.26254990696907043,
+      "eval_runtime": 125.5427,
+      "eval_samples_per_second": 57.319,
+      "eval_steps_per_second": 0.454,
+      "step": 197
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 4.726944823381805e-06,
+      "loss": 0.2662,
+      "step": 394
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.783212896053363,
+      "eval_loss": 0.25981640815734863,
+      "eval_runtime": 125.4546,
+      "eval_samples_per_second": 57.359,
+      "eval_steps_per_second": 0.454,
+      "step": 394
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 591,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 88890104312136.0,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.43662764362367845,
+    "learning_rate": 1.4180834470145417e-05,
+    "num_train_epochs": 3,
+    "temperature": 19
+  }
+}

run-8/checkpoint-394/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef3748f4fdacf1ee097e552e18bffbdfb276f83c94eb1a87d1aba98a3482f9c8
+size 4792