Training in progress, epoch 3

logs/events.out.tfevents.1702283787.joseph_legion.22340.20

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:faf0fe3f0a677f42642fb2e635b3217234b640c869794e5b3fa509182cc92a93
-size 5405
+oid sha256:dfa6df5afaafda18c7fd256d84cdf2cdf007ecb201166a3f74a373193c2f13a6
+size 5885

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16d9ee558e11e486e2945b946cc31e3798c6c8fbb9486bb9736d098a07f228f7
+oid sha256:77c1c660e7ae4aa5c50f91c09d5d943ddf9f3a6f469c194fefb036985994b759
 size 44692608

run-7/checkpoint-591/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-7/checkpoint-591/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77c1c660e7ae4aa5c50f91c09d5d943ddf9f3a6f469c194fefb036985994b759
+size 44692608

run-7/checkpoint-591/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60fb2194ab0ab6ebc823964c5213ea2555b3afd23347adce60a1de27dcb4f9e6
+size 89430010

run-7/checkpoint-591/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70141f0acfe75a3d2817bbed9f14bb13efceb08fee84dae3818267566941c957
+size 14308

run-7/checkpoint-591/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6d8bb1b38155f724362238eff682f16ea846bf5752e699bfa2eb7a8c7a63ca2
+size 1064

run-7/checkpoint-591/special_tokens_map.json

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

run-7/checkpoint-591/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-7/checkpoint-591/trainer_state.json

@@ -0,0 +1,70 @@
+{
+  "best_metric": 0.7887715397443024,
+  "best_model_checkpoint": "tinybert-TG-HS-HX-parentpretrained\\run-7\\checkpoint-591",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 591,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 9.391769458408264e-06,
+      "loss": 0.4715,
+      "step": 197
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7722345747637577,
+      "eval_loss": 0.4253861606121063,
+      "eval_runtime": 125.844,
+      "eval_samples_per_second": 57.182,
+      "eval_steps_per_second": 0.453,
+      "step": 197
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 7.043827093806198e-06,
+      "loss": 0.4326,
+      "step": 394
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7833518621456365,
+      "eval_loss": 0.4118412137031555,
+      "eval_runtime": 125.7992,
+      "eval_samples_per_second": 57.202,
+      "eval_steps_per_second": 0.453,
+      "step": 394
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 4.695884729204132e-06,
+      "loss": 0.4188,
+      "step": 591
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7887715397443024,
+      "eval_loss": 0.40638259053230286,
+      "eval_runtime": 125.6755,
+      "eval_samples_per_second": 57.259,
+      "eval_steps_per_second": 0.454,
+      "step": 591
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 985,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 133009215775884.0,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.8077469751146494,
+    "learning_rate": 1.173971182301033e-05,
+    "num_train_epochs": 5,
+    "temperature": 8
+  }
+}

run-7/checkpoint-591/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70db95c03b5ec61903552b23f87fba482526d5ac793db9a315d0e5c1b37e6b11
+size 4792