Training in progress, epoch 1

logs/events.out.tfevents.1701752681.joseph_legion.10272.1

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4f2f117a22160bea0fab1b93e388a89cd5bac03a062d44a503dc1cc734c2964
-size 8615
+oid sha256:d1c27a89fbb238b6c6e9ab420ace0b5870b73d072befcbfc2743dc5638cb8f57
+size 9449

logs/events.out.tfevents.1701754017.joseph_legion.10272.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5c4e80b0a29453b008edfbb72253094d7b19e403588ea4c5a589e56118a3d54
+size 4773

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ade0197b9d4f319c45bc9a16c02d87d798f85d10f48a66f567186e3a44803390
+oid sha256:8b42feb9c25b5b10729bab4e06b68b448548b4e12db6fe73bb89e80daedfc3a5
 size 17549312

run-0/checkpoint-5270/config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "google/bert_uncased_L-2_H-128_A-2",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 128,
+  "id2label": {
+    "0": "negative",
+    "1": "positive"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 512,
+  "label2id": {
+    "negative": "0",
+    "positive": "1"
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 2,
+  "num_hidden_layers": 2,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-0/checkpoint-5270/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:999c6b6eca476402432eef98536d4608b409f8ca6f93b67622b1f73f823fdcd1
+size 17549312

run-0/checkpoint-5270/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e66d383ffd63c81bb9bc7cea9330dc9e176e0004e45948d01f78d6f8bc8a9689
+size 35123898

run-0/checkpoint-5270/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71c0dda4b94b10e4fc1e32a56760fc1082191c0d7648074d0613c1dd333eb78f
+size 14308

run-0/checkpoint-5270/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1327aad48b977ea901f4d3e5e7fe100eaa0a2a46309f49de18390243494c686
+size 1064

run-0/checkpoint-5270/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-5270/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-5270/trainer_state.json

@@ -0,0 +1,174 @@
+{
+  "best_metric": 0.8153669724770642,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled\\run-0\\checkpoint-4216",
+  "epoch": 10.0,
+  "eval_steps": 500,
+  "global_step": 5270,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.0006568555243553003,
+      "loss": 0.9823,
+      "step": 527
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8084862385321101,
+      "eval_loss": 1.3724825382232666,
+      "eval_runtime": 1.7972,
+      "eval_samples_per_second": 485.194,
+      "eval_steps_per_second": 3.895,
+      "step": 527
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 0.0005838715772047113,
+      "loss": 0.4476,
+      "step": 1054
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8096330275229358,
+      "eval_loss": 1.3287416696548462,
+      "eval_runtime": 1.7495,
+      "eval_samples_per_second": 498.417,
+      "eval_steps_per_second": 4.001,
+      "step": 1054
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 0.0005108876300541224,
+      "loss": 0.2956,
+      "step": 1581
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7993119266055045,
+      "eval_loss": 1.4336999654769897,
+      "eval_runtime": 1.943,
+      "eval_samples_per_second": 448.795,
+      "eval_steps_per_second": 3.603,
+      "step": 1581
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 0.0004379036829035335,
+      "loss": 0.2249,
+      "step": 2108
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8107798165137615,
+      "eval_loss": 1.5175449848175049,
+      "eval_runtime": 1.8297,
+      "eval_samples_per_second": 476.582,
+      "eval_steps_per_second": 3.826,
+      "step": 2108
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 0.0003649197357529446,
+      "loss": 0.1785,
+      "step": 2635
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.8119266055045872,
+      "eval_loss": 1.4446643590927124,
+      "eval_runtime": 1.7803,
+      "eval_samples_per_second": 489.8,
+      "eval_steps_per_second": 3.932,
+      "step": 2635
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 0.0002919357886023557,
+      "loss": 0.1453,
+      "step": 3162
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.8096330275229358,
+      "eval_loss": 1.5748971700668335,
+      "eval_runtime": 1.8056,
+      "eval_samples_per_second": 482.953,
+      "eval_steps_per_second": 3.877,
+      "step": 3162
+    },
+    {
+      "epoch": 7.0,
+      "learning_rate": 0.00021895184145176674,
+      "loss": 0.126,
+      "step": 3689
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.8130733944954128,
+      "eval_loss": 1.5490596294403076,
+      "eval_runtime": 1.8202,
+      "eval_samples_per_second": 479.074,
+      "eval_steps_per_second": 3.846,
+      "step": 3689
+    },
+    {
+      "epoch": 8.0,
+      "learning_rate": 0.00014596789430117784,
+      "loss": 0.1041,
+      "step": 4216
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.8153669724770642,
+      "eval_loss": 1.499665379524231,
+      "eval_runtime": 1.7762,
+      "eval_samples_per_second": 490.924,
+      "eval_steps_per_second": 3.941,
+      "step": 4216
+    },
+    {
+      "epoch": 9.0,
+      "learning_rate": 7.298394715058892e-05,
+      "loss": 0.092,
+      "step": 4743
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.8073394495412844,
+      "eval_loss": 1.5526666641235352,
+      "eval_runtime": 1.7756,
+      "eval_samples_per_second": 491.105,
+      "eval_steps_per_second": 3.942,
+      "step": 4743
+    },
+    {
+      "epoch": 10.0,
+      "learning_rate": 0.0,
+      "loss": 0.0818,
+      "step": 5270
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.8130733944954128,
+      "eval_loss": 1.5200265645980835,
+      "eval_runtime": 1.8109,
+      "eval_samples_per_second": 481.538,
+      "eval_steps_per_second": 3.866,
+      "step": 5270
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 5270,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "total_flos": 80921406476340.0,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.5351224538156584,
+    "learning_rate": 0.0007298394715058892,
+    "num_train_epochs": 10,
+    "temperature": 24
+  }
+}

run-0/checkpoint-5270/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa8a46880b57d8b0b9e418b052abbb3948b438121f71f7c4ea0a153d96e30889
+size 4664

run-1/checkpoint-527/config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "google/bert_uncased_L-2_H-128_A-2",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 128,
+  "id2label": {
+    "0": "negative",
+    "1": "positive"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 512,
+  "label2id": {
+    "negative": "0",
+    "positive": "1"
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 2,
+  "num_hidden_layers": 2,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-1/checkpoint-527/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b42feb9c25b5b10729bab4e06b68b448548b4e12db6fe73bb89e80daedfc3a5
+size 17549312

run-1/checkpoint-527/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df560daa3df9363498940fa4ca37751194c674885c988f5dae088d116dfece48
+size 35123898

run-1/checkpoint-527/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:404cec57a6bbb572f62bd49cfe2447e0a3410a29e1c658f2617325852b27cc2d
+size 14308

run-1/checkpoint-527/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d02d4e8502d31687d061c8e2875e1ff3d9157ea2e46e6eeec10633408eea4fdf
+size 1064

run-1/checkpoint-527/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-527/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-527/trainer_state.json

@@ -0,0 +1,39 @@
+{
+  "best_metric": 0.8061926605504587,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled\\run-1\\checkpoint-527",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 527,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 7.193342816186545e-05,
+      "loss": 1.1191,
+      "step": 527
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8061926605504587,
+      "eval_loss": 0.9445732831954956,
+      "eval_runtime": 1.8865,
+      "eval_samples_per_second": 462.238,
+      "eval_steps_per_second": 3.711,
+      "step": 527
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 3689,
+  "num_train_epochs": 7,
+  "save_steps": 500,
+  "total_flos": 8057768762220.0,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.6227846651931359,
+    "learning_rate": 8.39223328555097e-05,
+    "num_train_epochs": 7,
+    "temperature": 4
+  }
+}

run-1/checkpoint-527/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41b6dd4b0cd50cfc8b6916f5bb0ffa702ddcb4610b47caf4b1109c9f79f26fdd
+size 4664

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa8a46880b57d8b0b9e418b052abbb3948b438121f71f7c4ea0a153d96e30889
+oid sha256:41b6dd4b0cd50cfc8b6916f5bb0ffa702ddcb4610b47caf4b1109c9f79f26fdd
 size 4664