Training in progress, epoch 1

logs/events.out.tfevents.1702270246.joseph_legion.22340.16

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f5309726505a3bf26f2031488b2c2e796207065bd85d39ab00f2d70a6e16d0d
-size 7326
+oid sha256:991910fdc86fb11114cd0bd31b655300c5cf11ba52efe772ecb43905f77d944c
+size 8160

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0032fcd41ba282c8dae3535450f5e1c8c76e18378de70a2a81541545709746b9
+size 4926

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c5f1ef2f93330d4a540ae32a090ba2020c00801a70c1574eff1f08cfa5f80c06
+oid sha256:66fc3e1b2ce65b6c9ff5b55ef9c473013d02c88989e592dcada3743111f07f84
 size 44692608

run-3/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-3/checkpoint-1379/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9260f8503efeae477b8feea9490dc199489a29a92fbcffb26f0a3617a33a960d
+size 44692608

run-3/checkpoint-1379/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ebb009fc800a765f93aeef32a4271c71022ba4e62da2b3f2a8ae915a0c0c3bc3
+size 89430010

run-3/checkpoint-1379/rng_state.pth

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

run-3/checkpoint-1379/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ae5e16472bebdf76963914853919f22f1c411747b9471adc37eafda974847cd
+size 1064

run-3/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-3/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-3/checkpoint-1379/trainer_state.json

@@ -0,0 +1,130 @@
+{
+  "best_metric": 0.8246247915508615,
+  "best_model_checkpoint": "tinybert-TG-HS-HX-parentpretrained\\run-3\\checkpoint-985",
+  "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": 4.53412212955664e-05,
+      "loss": 0.2002,
+      "step": 197
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.796692607003891,
+      "eval_loss": 0.19448761641979218,
+      "eval_runtime": 125.5379,
+      "eval_samples_per_second": 57.321,
+      "eval_steps_per_second": 0.454,
+      "step": 197
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 3.778435107963867e-05,
+      "loss": 0.1946,
+      "step": 394
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8086436909394108,
+      "eval_loss": 0.19145084917545319,
+      "eval_runtime": 125.3349,
+      "eval_samples_per_second": 57.414,
+      "eval_steps_per_second": 0.455,
+      "step": 394
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 3.0227480863710935e-05,
+      "loss": 0.1912,
+      "step": 591
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8153140633685381,
+      "eval_loss": 0.1914054900407791,
+      "eval_runtime": 125.3098,
+      "eval_samples_per_second": 57.426,
+      "eval_steps_per_second": 0.455,
+      "step": 591
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 2.26706106477832e-05,
+      "loss": 0.189,
+      "step": 788
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8187882156753752,
+      "eval_loss": 0.1904531717300415,
+      "eval_runtime": 125.5411,
+      "eval_samples_per_second": 57.32,
+      "eval_steps_per_second": 0.454,
+      "step": 788
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 1.5113740431855467e-05,
+      "loss": 0.1871,
+      "step": 985
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.8246247915508615,
+      "eval_loss": 0.19075776636600494,
+      "eval_runtime": 125.5068,
+      "eval_samples_per_second": 57.336,
+      "eval_steps_per_second": 0.454,
+      "step": 985
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 7.556870215927734e-06,
+      "loss": 0.1853,
+      "step": 1182
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.8246247915508615,
+      "eval_loss": 0.1908973753452301,
+      "eval_runtime": 125.4292,
+      "eval_samples_per_second": 57.371,
+      "eval_steps_per_second": 0.454,
+      "step": 1182
+    },
+    {
+      "epoch": 7.0,
+      "learning_rate": 0.0,
+      "loss": 0.1843,
+      "step": 1379
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.8232351306281267,
+      "eval_loss": 0.19087541103363037,
+      "eval_runtime": 125.4717,
+      "eval_samples_per_second": 57.352,
+      "eval_steps_per_second": 0.454,
+      "step": 1379
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1379,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 7,
+  "save_steps": 500,
+  "total_flos": 309665393535204.0,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.3140746400350408,
+    "learning_rate": 5.2898091511494136e-05,
+    "num_train_epochs": 7,
+    "temperature": 24
+  }
+}

run-3/checkpoint-1379/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c517abc0104d666a32411c6a107164f2cf5b4407241697f095cff05f4bfaf0a
+size 4792

run-4/checkpoint-197/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-197/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66fc3e1b2ce65b6c9ff5b55ef9c473013d02c88989e592dcada3743111f07f84
+size 44692608

run-4/checkpoint-197/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73a9d9e05b93e85d50f5d4f83a70a27be041a400981ffdabfad03b4026615d02
+size 89430010

run-4/checkpoint-197/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bfce427b13a79881b8dd7c1ca79db1eca136c641f9f35f4f0773c5f01a793672
+size 14308

run-4/checkpoint-197/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:abf302f42e4eb868fa23d198313a9916012abdbe1d168b0bf51a515b19430421
+size 1064

run-4/checkpoint-197/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-197/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-197/trainer_state.json

@@ -0,0 +1,40 @@
+{
+  "best_metric": 0.7181767648693719,
+  "best_model_checkpoint": "tinybert-TG-HS-HX-parentpretrained\\run-4\\checkpoint-197",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 197,
+  "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
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1576,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 8,
+  "save_steps": 500,
+  "total_flos": 44298765947484.0,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.4889425582875847,
+    "learning_rate": 2.4373768682613424e-06,
+    "num_train_epochs": 8,
+    "temperature": 30
+  }
+}

run-4/checkpoint-197/training_args.bin

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

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c517abc0104d666a32411c6a107164f2cf5b4407241697f095cff05f4bfaf0a
+oid sha256:981a91f79573183152619d189d97ff4841d075d34b88f159d3995abce38af003
 size 4792