Training in progress, epoch 1

logs/events.out.tfevents.1706261444.A-FVFFG2C4Q05P.18450.21

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:043d076a72417eb40faf963884d7a46845e8e57a8796f830bd5ebd888be89b43
-size 5396
+oid sha256:70b3f81981b99a22a2b4dfdc336bf0a355c612880099fe159bf5942bb7a1d708
+size 6710

logs/events.out.tfevents.1706265079.A-FVFFG2C4Q05P.18450.22

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a403755184bdee42a0aea585b652f2679e4c4a5f415c71cea5d865001de5735
+size 4436

logs/events.out.tfevents.1706265130.A-FVFFG2C4Q05P.18450.23

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a802463db9f947701e76361445bf6812f86090831c1eef4aefda8c1608ded33
+size 4435

logs/events.out.tfevents.1706265238.A-FVFFG2C4Q05P.18450.24

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:163f4c6ab12aa9ac3b9e3fdf1076137852ff3da1a7c34f63654266de25c8e7e3
+size 6229

logs/events.out.tfevents.1706267654.A-FVFFG2C4Q05P.18450.25

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52e8a45c581fb5b3516f4cb4889b959907d751513b182ded83870e5a483005e9
+size 4916

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6919625a06013ebf0b5d09d591d72059ecaacfd149aa6039620747ce130d8c89
+oid sha256:87568c0afc5ae5e4ff718507f68ad4943997f13f2f2353ed7480c5872143ba54
 size 17549312

run-0/checkpoint-1054/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:908638c4664a16b2be1e4378ceae2501bd6c5c8980ac2e8e1c440c2a13417b84
+oid sha256:a961afa01da16a24f2c49a0338f504c6969c49dea807a0163eb712ec19e5d2a5
 size 17549312

run-0/checkpoint-1054/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2820bc83db3bc05fcedc9b2e3c0814ef2ae544eaacfc2e20c898ca87db47f3a3
+oid sha256:7081d3ab29e701c70aee56961c84534d54087a4a96d123288ab8300123271256
 size 35122373

run-0/checkpoint-1054/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16e276f2a6209f1be03f0c62afe640f64e06f172ce4dd0006b8d39aabb5c7bee
+oid sha256:af1bf4840b29f03f6ccc15b1112ac510b2f94f820d4116b07a73af95409537ee
 size 627

run-0/checkpoint-1054/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.8245412844036697,
+  "best_metric": 0.8348623853211009,
   "best_model_checkpoint": "tiny-bert-sst2-distilled/run-0/checkpoint-1054",
   "epoch": 2.0,
   "eval_steps": 500,
@@ -10,47 +10,47 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "learning_rate": 9.507440967713177e-05,
-      "loss": 1.6043,
+      "learning_rate": 0.00017521452501048488,
+      "loss": 1.4337,
       "step": 527
     },
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.8107798165137615,
-      "eval_loss": 1.3382474184036255,
-      "eval_runtime": 7.7477,
-      "eval_samples_per_second": 112.55,
-      "eval_steps_per_second": 0.903,
+      "eval_accuracy": 0.8211009174311926,
+      "eval_loss": 1.309804081916809,
+      "eval_runtime": 7.7796,
+      "eval_samples_per_second": 112.088,
+      "eval_steps_per_second": 0.9,
       "step": 527
     },
     {
       "epoch": 2.0,
-      "learning_rate": 6.338293978475452e-05,
-      "loss": 0.7901,
+      "learning_rate": 8.760726250524244e-05,
+      "loss": 0.6599,
       "step": 1054
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.8245412844036697,
-      "eval_loss": 1.3008999824523926,
-      "eval_runtime": 7.5885,
-      "eval_samples_per_second": 114.91,
-      "eval_steps_per_second": 0.922,
+      "eval_accuracy": 0.8348623853211009,
+      "eval_loss": 1.4746311902999878,
+      "eval_runtime": 10.2236,
+      "eval_samples_per_second": 85.293,
+      "eval_steps_per_second": 0.685,
       "step": 1054
     }
   ],
   "logging_steps": 500,
-  "max_steps": 2108,
+  "max_steps": 1581,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 4,
+  "num_train_epochs": 3,
   "save_steps": 500,
   "total_flos": 16162868129520.0,
   "train_batch_size": 128,
   "trial_name": null,
   "trial_params": {
-    "alpha": 0.46638270752374766,
-    "learning_rate": 0.00012676587956950903,
-    "num_train_epochs": 4,
-    "temperature": 20
+    "alpha": 0.3828930992000458,
+    "learning_rate": 0.0002628217875157273,
+    "num_train_epochs": 3,
+    "temperature": 27
   }
 }

run-0/checkpoint-1054/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b149b247816d0d72efcc0fd576feb131fc41a6f49009ffa81023f2608190ff20
+oid sha256:816583fc783f300fde35f96ba82eb430b7b6945ff6b056fdd16b0cdcde5ee72d
 size 4283

run-0/checkpoint-1581/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": "4.37.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-0/checkpoint-1581/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f15d1272d95ede3fcd11cc383d65d589c95b329d53df77804d4b17b3294f11ff
+size 17549312

run-0/checkpoint-1581/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f8914ab56eff118e58441cdca24f376e5bb1b78ae89f796ed69a1f0b804169a
+size 35122373

run-0/checkpoint-1581/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8f1004ae2205b2fd82b8662eddc31a84c64c086e45e25c12d4a402a3d6a6e4d
+size 13617

run-0/checkpoint-1581/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a223f5e1fbd77cbb00143de3f5585b5cf5790cbe69b7bbadea1af2c81ba6dabc
+size 627

run-0/checkpoint-1581/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-1581/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-1581/trainer_state.json

@@ -0,0 +1,71 @@
+{
+  "best_metric": 0.8348623853211009,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-0/checkpoint-1054",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 1581,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.00017521452501048488,
+      "loss": 1.4337,
+      "step": 527
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8211009174311926,
+      "eval_loss": 1.309804081916809,
+      "eval_runtime": 7.7796,
+      "eval_samples_per_second": 112.088,
+      "eval_steps_per_second": 0.9,
+      "step": 527
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 8.760726250524244e-05,
+      "loss": 0.6599,
+      "step": 1054
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8348623853211009,
+      "eval_loss": 1.4746311902999878,
+      "eval_runtime": 10.2236,
+      "eval_samples_per_second": 85.293,
+      "eval_steps_per_second": 0.685,
+      "step": 1054
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 0.0,
+      "loss": 0.4906,
+      "step": 1581
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8348623853211009,
+      "eval_loss": 1.4973729848861694,
+      "eval_runtime": 8.919,
+      "eval_samples_per_second": 97.769,
+      "eval_steps_per_second": 0.785,
+      "step": 1581
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1581,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 24238892698680.0,
+  "train_batch_size": 128,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.3828930992000458,
+    "learning_rate": 0.0002628217875157273,
+    "num_train_epochs": 3,
+    "temperature": 27
+  }
+}

run-0/checkpoint-1581/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:816583fc783f300fde35f96ba82eb430b7b6945ff6b056fdd16b0cdcde5ee72d
+size 4283

run-1/checkpoint-527/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7bcd7d0aec1de757ac2cdfe0bc6f7c2b14a91f1a613b624a2f0093d80ca6355a
+oid sha256:87568c0afc5ae5e4ff718507f68ad4943997f13f2f2353ed7480c5872143ba54
 size 17549312

run-1/checkpoint-527/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d52e5de6bd8997ddf8ca3a2a1d76c2c6d88bf42dbd60546f3891044f28d441fa
+oid sha256:9e25ef891fdd6e5ede4e2fedcfccced541dbf26d70ac600869bb89500a94077d
 size 35122373

run-1/checkpoint-527/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4593c184c19c11a2f817520c5f5fdeb4ee376ac8d1c8d9f9c8b43128595f77d5
+oid sha256:7b5b16144d365fbd5d227d61884860fc872eaa13bdf9a8f761164c135d3e8bd5
 size 627

run-1/checkpoint-527/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.6513761467889908,
+  "best_metric": 0.801605504587156,
   "best_model_checkpoint": "tiny-bert-sst2-distilled/run-1/checkpoint-527",
   "epoch": 1.0,
   "eval_steps": 500,
@@ -10,32 +10,32 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "learning_rate": 5.34694014828574e-06,
-      "loss": 4.485,
+      "learning_rate": 0.0006875917567735723,
+      "loss": 0.9069,
       "step": 527
     },
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.6513761467889908,
-      "eval_loss": 3.9686293601989746,
-      "eval_runtime": 9.1719,
-      "eval_samples_per_second": 95.073,
-      "eval_steps_per_second": 0.763,
+      "eval_accuracy": 0.801605504587156,
+      "eval_loss": 1.1160032749176025,
+      "eval_runtime": 9.4507,
+      "eval_samples_per_second": 92.269,
+      "eval_steps_per_second": 0.741,
       "step": 527
     }
   ],
   "logging_steps": 500,
-  "max_steps": 1054,
+  "max_steps": 5270,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 2,
+  "num_train_epochs": 10,
   "save_steps": 500,
   "total_flos": 8069051778960.0,
   "train_batch_size": 128,
   "trial_name": null,
   "trial_params": {
-    "alpha": 0.10705118382199963,
-    "learning_rate": 1.069388029657148e-05,
-    "num_train_epochs": 2,
-    "temperature": 16
+    "alpha": 0.5682681228180307,
+    "learning_rate": 0.0007639908408595248,
+    "num_train_epochs": 10,
+    "temperature": 8
   }
 }

run-1/checkpoint-527/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:70d09d03f84ec5e6f07e718b975ff8effb1d82efe0ca25ef5c8642902ec419c8
+oid sha256:d99816c97dcbe7250039b2fe72e8bb2c24840867dcd296d9eb6598b2afd2670d
 size 4283

run-20/checkpoint-2108/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": "4.37.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-20/checkpoint-2108/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0633e4058de509cac3a60d0a6d60e05ab3aa4011607a39e5a464cfdc3f3758a8
+size 17549312

run-20/checkpoint-2108/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96a4f3c21ead4b862b6583f29c96e128c3cae8817b7d70f2e2dac9f1b90b3d0d
+size 35122373

run-20/checkpoint-2108/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2aae3bffb74208d13dfae4d8b66eb00427742bd84752ee081ae0f135d90f179b
+size 13617

run-20/checkpoint-2108/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a5a8a2f6f77232a378bfada54063827d1b729af8eed15d1758da3d54babde72
+size 627

run-20/checkpoint-2108/special_tokens_map.json

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

run-20/checkpoint-2108/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-20/checkpoint-2108/trainer_state.json

@@ -0,0 +1,86 @@
+{
+  "best_metric": 0.8302752293577982,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-20/checkpoint-527",
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 2108,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.0003127843891708784,
+      "loss": 0.4678,
+      "step": 527
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8302752293577982,
+      "eval_loss": 0.5433254241943359,
+      "eval_runtime": 7.3448,
+      "eval_samples_per_second": 118.723,
+      "eval_steps_per_second": 0.953,
+      "step": 527
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 0.00020852292611391892,
+      "loss": 0.244,
+      "step": 1054
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8107798165137615,
+      "eval_loss": 0.7215615510940552,
+      "eval_runtime": 8.2206,
+      "eval_samples_per_second": 106.075,
+      "eval_steps_per_second": 0.852,
+      "step": 1054
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 0.00010426146305695946,
+      "loss": 0.1704,
+      "step": 1581
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8107798165137615,
+      "eval_loss": 0.7814552783966064,
+      "eval_runtime": 7.9178,
+      "eval_samples_per_second": 110.132,
+      "eval_steps_per_second": 0.884,
+      "step": 1581
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 0.0,
+      "loss": 0.1314,
+      "step": 2108
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8142201834862385,
+      "eval_loss": 0.8089592456817627,
+      "eval_runtime": 7.5447,
+      "eval_samples_per_second": 115.578,
+      "eval_steps_per_second": 0.928,
+      "step": 2108
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2108,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 32344049138640.0,
+  "train_batch_size": 128,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.7544223674187817,
+    "learning_rate": 0.00041704585222783784,
+    "num_train_epochs": 4,
+    "temperature": 2
+  }
+}

run-20/checkpoint-2108/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57025044228698d343c4abcfe17b305ab3bdbf218d07f2cabb4a08f29fbffe25
+size 4283

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:57025044228698d343c4abcfe17b305ab3bdbf218d07f2cabb4a08f29fbffe25
+oid sha256:d99816c97dcbe7250039b2fe72e8bb2c24840867dcd296d9eb6598b2afd2670d
 size 4283