Training in progress, epoch 2

logs/events.out.tfevents.1702267900.joseph_legion.22340.15

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7793f3d5fc98636d74490f33b7eec49df847d92ebcb1ff25926b17ac80a96d16
-size 4924
+oid sha256:8abd9b6dab9832c0d3f92fbdd6e3a04c699eafcacdf00ddb8d04a1d9f3c2fd5a
+size 5404

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:099969a8f9094d860312b22490b527b3f2eebc0134ba7da3c3ff41f683603a11
+oid sha256:2b346f9a604944be9d0766f923a39024f08d03e88258336da81cd5f7b176af4d
 size 44692608

run-2/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-2/checkpoint-394/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b346f9a604944be9d0766f923a39024f08d03e88258336da81cd5f7b176af4d
+size 44692608

run-2/checkpoint-394/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da213b98adeb513d05b43a64a0d5e21a6364bcc8b30c2b6dd1bd803960141e58
+size 89430010

run-2/checkpoint-394/rng_state.pth

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

run-2/checkpoint-394/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd083817409028671fee5aae82c2ed1c1e24caefb2c3e0d657ce5d64354065f2
+size 1064

run-2/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-2/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-2/checkpoint-394/trainer_state.json

@@ -0,0 +1,55 @@
+{
+  "best_metric": 0.7388827126181212,
+  "best_model_checkpoint": "tinybert-TG-HS-HX-parentpretrained\\run-2\\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": 1.6784454644765522e-06,
+      "loss": 0.564,
+      "step": 197
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6989994441356309,
+      "eval_loss": 0.5322139859199524,
+      "eval_runtime": 125.0015,
+      "eval_samples_per_second": 57.567,
+      "eval_steps_per_second": 0.456,
+      "step": 197
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 1.258834098357414e-06,
+      "loss": 0.5261,
+      "step": 394
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7388827126181212,
+      "eval_loss": 0.496852844953537,
+      "eval_runtime": 124.8189,
+      "eval_samples_per_second": 57.652,
+      "eval_steps_per_second": 0.457,
+      "step": 394
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 985,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 88890104312136.0,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.8786599620319323,
+    "learning_rate": 2.09805683059569e-06,
+    "num_train_epochs": 5,
+    "temperature": 9
+  }
+}

run-2/checkpoint-394/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c03531167986b5590a04d8bd7d50baf3ca6f53132698a5ba9216e4386d4bf3c
+size 4792