Training in progress, epoch 1

logs/events.out.tfevents.1702262698.joseph_legion.22340.13

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f3a301c303f048a763a780d1ff1b0f22c57ba0572d8277689f31880875530f6
-size 6846
+oid sha256:bdccd217bac40e7967075caad0f4bbf852da80f0363ffc9e33919751a87edbfe
+size 7680

logs/events.out.tfevents.1702265532.joseph_legion.22340.14

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd080ac60b16dbafebdf3a6d772c84fad41f94f2b8172a5a3b5ab6ec24f42f17
+size 4926

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2cd53b5efdd5dad8109a5932889002ab4e2fe4a66330797dea18ef5c1357db76
+oid sha256:96bb9e3960a06b0771987537d6479849a09ef6cfe1298a22bd1b677c875b9aa2
 size 44692608

run-0/checkpoint-1182/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-0/checkpoint-1182/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5503b912d534e781081826a804a0bd710fc92ae0c28e3a92044244bcce4efa2d
+size 44692608

run-0/checkpoint-1182/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64ca71bdac5f665eae41916a386a5ac39d6ed0f8d4d111d7895ea9c25bf7149c
+size 89430010

run-0/checkpoint-1182/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a9511e5e4163d669edd4526e0777794d8936c52493f7e77dc7be042cfeed886
+size 14308

run-0/checkpoint-1182/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c9e73b7eb6d96ac6c2f934caefa0837e51e82537667ef2494b6285f709de632
+size 1064

run-0/checkpoint-1182/special_tokens_map.json

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

run-0/checkpoint-1182/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-0/checkpoint-1182/trainer_state.json

@@ -0,0 +1,115 @@
+{
+  "best_metric": 0.7679266259032796,
+  "best_model_checkpoint": "tinybert-TG-HS-HX-parentpretrained\\run-0\\checkpoint-985",
+  "epoch": 6.0,
+  "eval_steps": 500,
+  "global_step": 1182,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 2.505784710419649e-06,
+      "loss": 0.6127,
+      "step": 197
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7258198999444135,
+      "eval_loss": 0.5620561838150024,
+      "eval_runtime": 127.1936,
+      "eval_samples_per_second": 56.575,
+      "eval_steps_per_second": 0.448,
+      "step": 197
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 2.004627768335719e-06,
+      "loss": 0.5562,
+      "step": 394
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7523624235686492,
+      "eval_loss": 0.5172325372695923,
+      "eval_runtime": 127.1167,
+      "eval_samples_per_second": 56.609,
+      "eval_steps_per_second": 0.448,
+      "step": 394
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 1.5034708262517894e-06,
+      "loss": 0.5297,
+      "step": 591
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7601445247359644,
+      "eval_loss": 0.49815818667411804,
+      "eval_runtime": 127.1505,
+      "eval_samples_per_second": 56.594,
+      "eval_steps_per_second": 0.448,
+      "step": 591
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 1.0023138841678596e-06,
+      "loss": 0.5189,
+      "step": 788
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.7659811006114509,
+      "eval_loss": 0.488542765378952,
+      "eval_runtime": 127.0937,
+      "eval_samples_per_second": 56.62,
+      "eval_steps_per_second": 0.448,
+      "step": 788
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 5.011569420839298e-07,
+      "loss": 0.5117,
+      "step": 985
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.7679266259032796,
+      "eval_loss": 0.4839724898338318,
+      "eval_runtime": 127.1766,
+      "eval_samples_per_second": 56.583,
+      "eval_steps_per_second": 0.448,
+      "step": 985
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 0.0,
+      "loss": 0.5063,
+      "step": 1182
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.7675097276264592,
+      "eval_loss": 0.48275187611579895,
+      "eval_runtime": 126.9299,
+      "eval_samples_per_second": 56.693,
+      "eval_steps_per_second": 0.449,
+      "step": 1182
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1182,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 6,
+  "save_steps": 500,
+  "total_flos": 265501203931764.0,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.9772734766942756,
+    "learning_rate": 3.0069416525035787e-06,
+    "num_train_epochs": 6,
+    "temperature": 16
+  }
+}

run-0/checkpoint-1182/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c14d343496772a0c98c9be375e50811ca2ef09aafdfc61a6757d81f78c95d84
+size 4792

run-1/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-1/checkpoint-197/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96bb9e3960a06b0771987537d6479849a09ef6cfe1298a22bd1b677c875b9aa2
+size 44692608

run-1/checkpoint-197/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8fb403bdfb7d8ea0d523e3f5684cc544e168d7cea8e7efa068549fa995fd8d90
+size 89430010

run-1/checkpoint-197/rng_state.pth

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

run-1/checkpoint-197/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d245f23a36a1f81997522c743b72b4fb4eb583fb6a7697b0ac9d74006e26719
+size 1064

run-1/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-1/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-1/checkpoint-197/trainer_state.json

@@ -0,0 +1,40 @@
+{
+  "best_metric": 0.7523624235686492,
+  "best_model_checkpoint": "tinybert-TG-HS-HX-parentpretrained\\run-1\\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": 4.6037225390588216e-06,
+      "loss": 0.2825,
+      "step": 197
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7523624235686492,
+      "eval_loss": 0.26902320981025696,
+      "eval_runtime": 126.6156,
+      "eval_samples_per_second": 56.833,
+      "eval_steps_per_second": 0.45,
+      "step": 197
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 985,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 44298765947484.0,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.4394092153370026,
+    "learning_rate": 5.7546531738235265e-06,
+    "num_train_epochs": 5,
+    "temperature": 23
+  }
+}

run-1/checkpoint-197/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ebe907fa2c71e3e43a89d80ee43fe99adc34e72494d59b4f8a29ae3ebf5591db
+size 4792

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c14d343496772a0c98c9be375e50811ca2ef09aafdfc61a6757d81f78c95d84
+oid sha256:ebe907fa2c71e3e43a89d80ee43fe99adc34e72494d59b4f8a29ae3ebf5591db
 size 4792