Training in progress, epoch 7

logs/events.out.tfevents.1702273519.joseph_legion.22340.17

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc51d248172f8ef7352d832142190e4371f0a583919646117484f5267f2f7ab5
-size 7326
+oid sha256:be9ceeb65a2d4c542e2bd5f292fa093efdb9f206a40e01665a4f766bd6681061
+size 7806

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:463a5a58a1288d9b59ec70e26332339c418051de4fb4dc2c4a7c738a68f8338f
+oid sha256:4d7c9b620b2968a05857cf53a1d2e01d7da46688609b42ec4641f33a64ea5cb7
 size 44692608

run-4/checkpoint-1379/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-4/checkpoint-1379/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d7c9b620b2968a05857cf53a1d2e01d7da46688609b42ec4641f33a64ea5cb7
+size 44692608

run-4/checkpoint-1379/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:481ee3f2b10bc513b4382e557c82f4437c85613fde108c1f9faf6080bdaaed20
+size 89430010

run-4/checkpoint-1379/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90950b6bd01ee491d86df75c6186784a03589a99164b435c5e7a35996764ac98
+size 14308

run-4/checkpoint-1379/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8cf63170ae0792daf93bcab639b0b42c707c7ef9d6bfed0238d044186fbdcd76
+size 1064

run-4/checkpoint-1379/special_tokens_map.json

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

run-4/checkpoint-1379/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-4/checkpoint-1379/trainer_state.json

@@ -0,0 +1,130 @@
+{
+  "best_metric": 0.7722345747637577,
+  "best_model_checkpoint": "tinybert-TG-HS-HX-parentpretrained\\run-4\\checkpoint-1182",
+  "epoch": 7.0,
+  "eval_steps": 500,
+  "global_step": 1379,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 2.1327047597286744e-06,
+      "loss": 0.3205,
+      "step": 197
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7181767648693719,
+      "eval_loss": 0.3056386411190033,
+      "eval_runtime": 125.6972,
+      "eval_samples_per_second": 57.249,
+      "eval_steps_per_second": 0.453,
+      "step": 197
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 1.8280326511960069e-06,
+      "loss": 0.3065,
+      "step": 394
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7493051695386326,
+      "eval_loss": 0.2966243028640747,
+      "eval_runtime": 125.6168,
+      "eval_samples_per_second": 57.285,
+      "eval_steps_per_second": 0.454,
+      "step": 394
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 1.523360542663339e-06,
+      "loss": 0.3012,
+      "step": 591
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7602834908282379,
+      "eval_loss": 0.292987197637558,
+      "eval_runtime": 125.5971,
+      "eval_samples_per_second": 57.294,
+      "eval_steps_per_second": 0.454,
+      "step": 591
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 1.2186884341306712e-06,
+      "loss": 0.2993,
+      "step": 788
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.7659811006114509,
+      "eval_loss": 0.2911587357521057,
+      "eval_runtime": 125.8135,
+      "eval_samples_per_second": 57.196,
+      "eval_steps_per_second": 0.453,
+      "step": 788
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 9.140163255980034e-07,
+      "loss": 0.2978,
+      "step": 985
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.7695942190105615,
+      "eval_loss": 0.2902683913707733,
+      "eval_runtime": 125.6067,
+      "eval_samples_per_second": 57.29,
+      "eval_steps_per_second": 0.454,
+      "step": 985
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 6.093442170653356e-07,
+      "loss": 0.2964,
+      "step": 1182
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.7722345747637577,
+      "eval_loss": 0.2897145748138428,
+      "eval_runtime": 125.7458,
+      "eval_samples_per_second": 57.227,
+      "eval_steps_per_second": 0.453,
+      "step": 1182
+    },
+    {
+      "epoch": 7.0,
+      "learning_rate": 3.046721085326678e-07,
+      "loss": 0.2959,
+      "step": 1379
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.7718176764869372,
+      "eval_loss": 0.28957682847976685,
+      "eval_runtime": 125.8315,
+      "eval_samples_per_second": 57.188,
+      "eval_steps_per_second": 0.453,
+      "step": 1379
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1576,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 8,
+  "save_steps": 500,
+  "total_flos": 309665393535204.0,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.4889425582875847,
+    "learning_rate": 2.4373768682613424e-06,
+    "num_train_epochs": 8,
+    "temperature": 30
+  }
+}

run-4/checkpoint-1379/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:981a91f79573183152619d189d97ff4841d075d34b88f159d3995abce38af003
+size 4792