Training in progress, epoch 1

logs/events.out.tfevents.1719305887.852b1e905a9a.223.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f7abe327c70e3d2eab83ac1cdfe981eed5b3d0ecc26a4345490be2cb9f328403
-size 9702
+oid sha256:dc25b520b8abd7862c42e90b127ad6aac2779e39130d042efff8ec1bb8771c67
+size 10590

logs/events.out.tfevents.1719307811.852b1e905a9a.223.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d61a8e7f8441a98d13b2fc7109a4e918a085863ec9654b397902272fe1dedc5
+size 5429

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37ac3926e3a80b716d36842c9f5ebe2aef0572a91f37f0939c787f8676990812
+oid sha256:bb1ca79a9bf8b490a2f6783a131c6de76de46d7d9d225d392b55c2bf9992c8ad
 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": "4.41.2",
+  "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:d6a7d4ae1b0dc3255bf082a761c15353ab030bd5e37c33a76f3766f0508701ce
+size 17549312

run-0/checkpoint-5270/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:901672cef3b3b61d42b5bd6fd53517a0b062c4220efba56837b053c03ec4e23e
+size 35123898

run-0/checkpoint-5270/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a825f14b66ba01ee141ce262529689c9881cb7d12dc65b93a897ba115df075eb
+size 14308

run-0/checkpoint-5270/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c34f147ddb39d50062f5e41692f95b770808d54e67fb07105090c9d90a263583
+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 +1,198 @@
+{
+  "best_metric": 0.7970183486238532,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-0/checkpoint-4743",
+  "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,
+      "grad_norm": 5.95961856842041,
+      "learning_rate": 9.55389368279823e-06,
+      "loss": 1.5369,
+      "step": 527
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7339449541284404,
+      "eval_loss": 1.2773902416229248,
+      "eval_runtime": 2.5957,
+      "eval_samples_per_second": 335.939,
+      "eval_steps_per_second": 2.697,
+      "step": 527
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 15.252978324890137,
+      "learning_rate": 8.492349940265094e-06,
+      "loss": 1.2159,
+      "step": 1054
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7786697247706422,
+      "eval_loss": 1.022659182548523,
+      "eval_runtime": 2.5741,
+      "eval_samples_per_second": 338.753,
+      "eval_steps_per_second": 2.719,
+      "step": 1054
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 18.01114845275879,
+      "learning_rate": 7.430806197731956e-06,
+      "loss": 1.0132,
+      "step": 1581
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7844036697247706,
+      "eval_loss": 0.9622328281402588,
+      "eval_runtime": 2.5865,
+      "eval_samples_per_second": 337.137,
+      "eval_steps_per_second": 2.706,
+      "step": 1581
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 15.912079811096191,
+      "learning_rate": 6.371276769700781e-06,
+      "loss": 0.9206,
+      "step": 2108
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.7901376146788991,
+      "eval_loss": 0.9278557896614075,
+      "eval_runtime": 2.5808,
+      "eval_samples_per_second": 337.878,
+      "eval_steps_per_second": 2.712,
+      "step": 2108
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 10.149016380310059,
+      "learning_rate": 5.3097330271676446e-06,
+      "loss": 0.8564,
+      "step": 2635
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.7901376146788991,
+      "eval_loss": 0.9079629182815552,
+      "eval_runtime": 2.5658,
+      "eval_samples_per_second": 339.852,
+      "eval_steps_per_second": 2.728,
+      "step": 2635
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 16.081409454345703,
+      "learning_rate": 4.248189284634507e-06,
+      "loss": 0.8139,
+      "step": 3162
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.7947247706422018,
+      "eval_loss": 0.8956273794174194,
+      "eval_runtime": 2.6131,
+      "eval_samples_per_second": 333.701,
+      "eval_steps_per_second": 2.679,
+      "step": 3162
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 11.411503791809082,
+      "learning_rate": 3.1866455421013703e-06,
+      "loss": 0.7798,
+      "step": 3689
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.7924311926605505,
+      "eval_loss": 0.8861347436904907,
+      "eval_runtime": 2.6019,
+      "eval_samples_per_second": 335.138,
+      "eval_steps_per_second": 2.69,
+      "step": 3689
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": Infinity,
+      "learning_rate": 2.127116114070194e-06,
+      "loss": 0.7583,
+      "step": 4216
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.7958715596330275,
+      "eval_loss": 0.8804019093513489,
+      "eval_runtime": 2.543,
+      "eval_samples_per_second": 342.909,
+      "eval_steps_per_second": 2.753,
+      "step": 4216
+    },
+    {
+      "epoch": 9.0,
+      "grad_norm": 14.046510696411133,
+      "learning_rate": 1.0655723715370575e-06,
+      "loss": 0.7434,
+      "step": 4743
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.7970183486238532,
+      "eval_loss": 0.876382052898407,
+      "eval_runtime": 2.5646,
+      "eval_samples_per_second": 340.01,
+      "eval_steps_per_second": 2.729,
+      "step": 4743
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 25.306703567504883,
+      "learning_rate": 4.028629003920822e-09,
+      "loss": 0.7396,
+      "step": 5270
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.7947247706422018,
+      "eval_loss": 0.8762168288230896,
+      "eval_runtime": 2.5493,
+      "eval_samples_per_second": 342.058,
+      "eval_steps_per_second": 2.746,
+      "step": 5270
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 5270,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 80830646058420.0,
+  "train_batch_size": 128,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.27608826195592573,
+    "learning_rate": 1.0615437425331367e-05,
+    "num_train_epochs": 10,
+    "temperature": 2
+  }
+}

run-0/checkpoint-5270/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8b6a60f7b85b38fa45cddf1a417ee51250fe5822237403416bf2406ff2cdb84
+size 5176

run-1/checkpoint-527/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f38b9ea491ce667f59ded0ccfbdfe75281aee028ae8d5466c274041caf164206
+oid sha256:bb1ca79a9bf8b490a2f6783a131c6de76de46d7d9d225d392b55c2bf9992c8ad
 size 17549312

run-1/checkpoint-527/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a52317e8696ae2d8b8beb30e707c3986d402de61f751253103bb2f0082b56a18
+oid sha256:6c745062c7e1e60a2fc3d1bc56b16a62f1c67a52915e29c53ed324c2ad2e257d
 size 35123898

run-1/checkpoint-527/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b6a438bddb76984d6c62348e4db9f39c76bfd074f83c6cc6f740e3e23d57662
+oid sha256:940589cb04f9e8ff6df41bbdafd8a68677bbf95c887b63d983f5df8e3c1182bb
 size 1064

run-1/checkpoint-527/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.8153669724770642,
+  "best_metric": 0.8107798165137615,
   "best_model_checkpoint": "tiny-bert-sst2-distilled/run-1/checkpoint-527",
   "epoch": 1.0,
   "eval_steps": 500,
@@ -10,25 +10,25 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "grad_norm": 30.242748260498047,
-      "learning_rate": 0.000111895725910844,
-      "loss": 2.3991,
+      "grad_norm": 17.658132553100586,
+      "learning_rate": 7.63128750557968e-05,
+      "loss": 1.3361,
       "step": 527
     },
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.8153669724770642,
-      "eval_loss": 1.9181628227233887,
-      "eval_runtime": 2.3714,
-      "eval_samples_per_second": 367.708,
-      "eval_steps_per_second": 2.952,
+      "eval_accuracy": 0.8107798165137615,
+      "eval_loss": 1.132369041442871,
+      "eval_runtime": 2.6024,
+      "eval_samples_per_second": 335.073,
+      "eval_steps_per_second": 2.69,
       "step": 527
     }
   ],
   "logging_steps": 500,
-  "max_steps": 3162,
+  "max_steps": 1581,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 6,
+  "num_train_epochs": 3,
   "save_steps": 500,
   "stateful_callbacks": {
     "TrainerControl": {
@@ -46,9 +46,9 @@
   "train_batch_size": 128,
   "trial_name": null,
   "trial_params": {
-    "alpha": 0.051381532356201576,
-    "learning_rate": 0.0001342239322193053,
-    "num_train_epochs": 6,
-    "temperature": 23
+    "alpha": 0.5918699224275719,
+    "learning_rate": 0.00011446931258369519,
+    "num_train_epochs": 3,
+    "temperature": 9
   }
 }

run-1/checkpoint-527/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa6a7f7b16042aa90d6a482b54cde9c8a264f21ae121942f35d43fb01c1ae0eb
+oid sha256:cdb44a8bec3049f59e3c6aa052eb44c31862f011784d5f05f8553620eb8f64a0
 size 5176

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c8b6a60f7b85b38fa45cddf1a417ee51250fe5822237403416bf2406ff2cdb84
+oid sha256:cdb44a8bec3049f59e3c6aa052eb44c31862f011784d5f05f8553620eb8f64a0
 size 5176