Training in progress, epoch 1

logs/events.out.tfevents.1699904768.b18f42e49ba4.3021.2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:267737d5d53c51c872826240b5b7d847172ef87927ba640db1105251d7cddb93
-size 5253
+oid sha256:2f7645ef1dee739a7b884725200f3a138a95c6c54917d6e516717536f93e2205
+size 8487

logs/events.out.tfevents.1699905304.b18f42e49ba4.3021.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:062b4d67a5beae90310b618a1059fe862e4e6c57e1b6a6d1b5c93659620e5662
+size 4772

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:76f3373b281f0becff2bf2df60ef1e51e052d689c94e1bef2fe14f70514128eb
+oid sha256:b49505f88cd0852de12da893c481fe9a7ff1cdd75cdab1436704d4fa2f281f17
 size 17549312

run-1/checkpoint-4216/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": "4.35.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-1/checkpoint-4216/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0454fa62eef292dbffabe86bad21b2e52af60cedfd7ccffc4673477bf1ecf77
+size 17549312

run-1/checkpoint-4216/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e651c1b1ab327130f4f0f5c2f07e91e760659c70156b41b28cfa006169723f3e
+size 35123898

run-1/checkpoint-4216/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8cc4b5d3811a9bdab419053416300344cc89ce599bbd17ed6dd7156beee0ca8
+size 14308

run-1/checkpoint-4216/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4653080ef363aa0840768fdfbe2369098666f9b549b834cbd15ed600a7412d67
+size 1064

run-1/checkpoint-4216/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-4216/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-4216/trainer_state.json

@@ -0,0 +1,144 @@
+{
+  "best_metric": 0.8245412844036697,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-1/checkpoint-527",
+  "epoch": 8.0,
+  "eval_steps": 500,
+  "global_step": 4216,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.00045141101865322006,
+      "loss": 0.5612,
+      "step": 527
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8245412844036697,
+      "eval_loss": 0.6783895492553711,
+      "eval_runtime": 0.8215,
+      "eval_samples_per_second": 1061.44,
+      "eval_steps_per_second": 8.521,
+      "step": 527
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 0.0003869237302741886,
+      "loss": 0.2852,
+      "step": 1054
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.819954128440367,
+      "eval_loss": 0.8377854824066162,
+      "eval_runtime": 0.8301,
+      "eval_samples_per_second": 1050.523,
+      "eval_steps_per_second": 8.433,
+      "step": 1054
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 0.0003224364418951572,
+      "loss": 0.1993,
+      "step": 1581
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8176605504587156,
+      "eval_loss": 0.9829881191253662,
+      "eval_runtime": 0.8261,
+      "eval_samples_per_second": 1055.524,
+      "eval_steps_per_second": 8.473,
+      "step": 1581
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 0.00025794915351612575,
+      "loss": 0.146,
+      "step": 2108
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8084862385321101,
+      "eval_loss": 0.9591342806816101,
+      "eval_runtime": 0.8285,
+      "eval_samples_per_second": 1052.447,
+      "eval_steps_per_second": 8.449,
+      "step": 2108
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 0.0001934618651370943,
+      "loss": 0.1172,
+      "step": 2635
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.8084862385321101,
+      "eval_loss": 1.0657378435134888,
+      "eval_runtime": 0.827,
+      "eval_samples_per_second": 1054.452,
+      "eval_steps_per_second": 8.465,
+      "step": 2635
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 0.00012897457675806287,
+      "loss": 0.0954,
+      "step": 3162
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.8119266055045872,
+      "eval_loss": 1.0413739681243896,
+      "eval_runtime": 0.9248,
+      "eval_samples_per_second": 942.864,
+      "eval_steps_per_second": 7.569,
+      "step": 3162
+    },
+    {
+      "epoch": 7.0,
+      "learning_rate": 6.448728837903144e-05,
+      "loss": 0.0817,
+      "step": 3689
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.8107798165137615,
+      "eval_loss": 1.0220547914505005,
+      "eval_runtime": 0.9299,
+      "eval_samples_per_second": 937.75,
+      "eval_steps_per_second": 7.528,
+      "step": 3689
+    },
+    {
+      "epoch": 8.0,
+      "learning_rate": 1.223667711177067e-07,
+      "loss": 0.0704,
+      "step": 4216
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.8119266055045872,
+      "eval_loss": 1.052475929260254,
+      "eval_runtime": 0.9344,
+      "eval_samples_per_second": 933.196,
+      "eval_steps_per_second": 7.491,
+      "step": 4216
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 4216,
+  "num_train_epochs": 8,
+  "save_steps": 500,
+  "total_flos": 64677008811300.0,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.8589699796135158,
+    "learning_rate": 0.0005158983070322515,
+    "num_train_epochs": 8,
+    "temperature": 16
+  }
+}

run-1/checkpoint-4216/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49d7a5caea676734b267f55f7962360c61e8e1c37d482f58e91788323853117a
+size 4600

run-2/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": "4.35.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-2/checkpoint-527/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b49505f88cd0852de12da893c481fe9a7ff1cdd75cdab1436704d4fa2f281f17
+size 17549312

run-2/checkpoint-527/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8daa19f54ed728f459c104c60cc85c4494248d5266831697adfc0e68f8487ddb
+size 35123898

run-2/checkpoint-527/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ababcbf30496eb4976cce44a5faf0cf605467f452ba655745eb60d884a0042d8
+size 14308

run-2/checkpoint-527/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5e19e648367b1b296f4f6054065f2de4aa4c2bb39b737c64f7603e42c00dc68
+size 1064

run-2/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-2/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-2/checkpoint-527/trainer_state.json

@@ -0,0 +1,39 @@
+{
+  "best_metric": 0.7878440366972477,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-2/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": 5.2457406035051924e-05,
+      "loss": 2.0868,
+      "step": 527
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7878440366972477,
+      "eval_loss": 1.5512216091156006,
+      "eval_runtime": 0.9102,
+      "eval_samples_per_second": 958.05,
+      "eval_steps_per_second": 7.691,
+      "step": 527
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 3689,
+  "num_train_epochs": 7,
+  "save_steps": 500,
+  "total_flos": 8117476690260.0,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.3591745527435446,
+    "learning_rate": 6.11809582242512e-05,
+    "num_train_epochs": 7,
+    "temperature": 8
+  }
+}

run-2/checkpoint-527/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36745c74f4aff152ea75e4b4a1392a5ebf58336b5338239520d52ed4bf11ca7f
+size 4600

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49d7a5caea676734b267f55f7962360c61e8e1c37d482f58e91788323853117a
+oid sha256:36745c74f4aff152ea75e4b4a1392a5ebf58336b5338239520d52ed4bf11ca7f
 size 4600