Training in progress, epoch 1

logs/events.out.tfevents.1709719691.adc675a344d5.67573.9

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d6588be274fd9059f10dc3234a404872773c5fc716b3ea37a0f62cdfe68b5fd4
-size 5997
+oid sha256:2ac45da079f268c47c6db4119746b7d1aafab43c387df808ee9dd1698809dbb0
+size 9083

logs/events.out.tfevents.1709720374.adc675a344d5.67573.10

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8af69329463c57c82d1755446497a87fdeab400f1b9fa491c357ad10f991b542
+size 5314

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f27a2fe7cfd98bf67fb9c444d1d23322c1c79e80038361ca09e84db6b0d80380
+oid sha256:239dd84c1acbf3926d1b2ffcc0c8dbbb872ee0abbb6b9b92cf4944b98a755de2
 size 17549312

run-8/checkpoint-480/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": "4.38.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-8/checkpoint-480/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c736d470d5a41220393fa68d74643956fee087e3b4f73f5739cd0edb879b6c1d
+size 17549312

run-8/checkpoint-480/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ed9625c3872157209ff033e279a19680f0e64dfdf689f650fcee09aef417c10
+size 35122746

run-8/checkpoint-480/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d93f4cfe67413cd27374342b3b9f13806d5fb593a9dc59106a8b24dedb590a8
+size 14054

run-8/checkpoint-480/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9912b02b8fd0a8af6b3ff3e8c7938eb3db51fba65f7a74f1e6725b8dbbca5426
+size 1064

run-8/checkpoint-480/special_tokens_map.json

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

run-8/checkpoint-480/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-8/checkpoint-480/trainer_state.json

@@ -0,0 +1,121 @@
+{
+  "best_metric": 0.8258317025440313,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-8/checkpoint-480",
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 480,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 3.2297720909118652,
+      "learning_rate": 0.0003356185870926135,
+      "loss": 0.5529,
+      "step": 96
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7602739726027398,
+      "eval_f1": 0.7973531844499586,
+      "eval_loss": 0.4773445129394531,
+      "eval_precision": 0.6905444126074498,
+      "eval_recall": 0.9432485322896281,
+      "eval_runtime": 28.1534,
+      "eval_samples_per_second": 36.301,
+      "eval_steps_per_second": 1.137,
+      "step": 96
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.981153130531311,
+      "learning_rate": 0.00026849486967409075,
+      "loss": 0.4542,
+      "step": 192
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8199608610567515,
+      "eval_f1": 0.8365896980461812,
+      "eval_loss": 0.42821842432022095,
+      "eval_precision": 0.7658536585365854,
+      "eval_recall": 0.9217221135029354,
+      "eval_runtime": 28.2265,
+      "eval_samples_per_second": 36.207,
+      "eval_steps_per_second": 1.134,
+      "step": 192
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 4.941507339477539,
+      "learning_rate": 0.0002013711522555681,
+      "loss": 0.4191,
+      "step": 288
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.821917808219178,
+      "eval_f1": 0.8311688311688312,
+      "eval_loss": 0.44406670331954956,
+      "eval_precision": 0.7901234567901234,
+      "eval_recall": 0.8767123287671232,
+      "eval_runtime": 28.0469,
+      "eval_samples_per_second": 36.439,
+      "eval_steps_per_second": 1.141,
+      "step": 288
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 7.470360279083252,
+      "learning_rate": 0.00013424743483704538,
+      "loss": 0.4059,
+      "step": 384
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8170254403131115,
+      "eval_f1": 0.8186226964112512,
+      "eval_loss": 0.4284485876560211,
+      "eval_precision": 0.8115384615384615,
+      "eval_recall": 0.8258317025440313,
+      "eval_runtime": 28.1941,
+      "eval_samples_per_second": 36.249,
+      "eval_steps_per_second": 1.135,
+      "step": 384
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 2.5780177116394043,
+      "learning_rate": 6.712371741852269e-05,
+      "loss": 0.398,
+      "step": 480
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.8258317025440313,
+      "eval_f1": 0.8378870673952642,
+      "eval_loss": 0.4101215600967407,
+      "eval_precision": 0.7836456558773425,
+      "eval_recall": 0.9001956947162426,
+      "eval_runtime": 28.0686,
+      "eval_samples_per_second": 36.411,
+      "eval_steps_per_second": 1.14,
+      "step": 480
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 576,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 6,
+  "save_steps": 500,
+  "total_flos": 1178475986400.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.8957226795607325,
+    "learning_rate": 0.0004027423045111362,
+    "num_train_epochs": 6,
+    "temperature": 3
+  }
+}

run-8/checkpoint-480/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c62ca979c251b24426f83ee19cf958429aed20a5e41a6549bd0708ed8286fb21
+size 4920

run-8/checkpoint-576/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": "4.38.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-8/checkpoint-576/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0adb974261e322677d2847253a5c4a21a46be28306251779e1adf065e839183
+size 17549312

run-8/checkpoint-576/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3013239df35c22047a7747ea5243edb03f5166310e7688a301a6b0f128ba4227
+size 35122746

run-8/checkpoint-576/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d4ad45514321df5f64172bb2de61ac319a093d9f31cf01031977fb88be20551
+size 14054

run-8/checkpoint-576/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d7e2ebd25cf260da536690b7ddb5df8ab6da6d1f55572f6b8e08b2629e5bf4b
+size 1064

run-8/checkpoint-576/special_tokens_map.json

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

run-8/checkpoint-576/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-8/checkpoint-576/trainer_state.json

@@ -0,0 +1,140 @@
+{
+  "best_metric": 0.8297455968688845,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-8/checkpoint-576",
+  "epoch": 6.0,
+  "eval_steps": 500,
+  "global_step": 576,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 3.2297720909118652,
+      "learning_rate": 0.0003356185870926135,
+      "loss": 0.5529,
+      "step": 96
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7602739726027398,
+      "eval_f1": 0.7973531844499586,
+      "eval_loss": 0.4773445129394531,
+      "eval_precision": 0.6905444126074498,
+      "eval_recall": 0.9432485322896281,
+      "eval_runtime": 28.1534,
+      "eval_samples_per_second": 36.301,
+      "eval_steps_per_second": 1.137,
+      "step": 96
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.981153130531311,
+      "learning_rate": 0.00026849486967409075,
+      "loss": 0.4542,
+      "step": 192
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8199608610567515,
+      "eval_f1": 0.8365896980461812,
+      "eval_loss": 0.42821842432022095,
+      "eval_precision": 0.7658536585365854,
+      "eval_recall": 0.9217221135029354,
+      "eval_runtime": 28.2265,
+      "eval_samples_per_second": 36.207,
+      "eval_steps_per_second": 1.134,
+      "step": 192
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 4.941507339477539,
+      "learning_rate": 0.0002013711522555681,
+      "loss": 0.4191,
+      "step": 288
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.821917808219178,
+      "eval_f1": 0.8311688311688312,
+      "eval_loss": 0.44406670331954956,
+      "eval_precision": 0.7901234567901234,
+      "eval_recall": 0.8767123287671232,
+      "eval_runtime": 28.0469,
+      "eval_samples_per_second": 36.439,
+      "eval_steps_per_second": 1.141,
+      "step": 288
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 7.470360279083252,
+      "learning_rate": 0.00013424743483704538,
+      "loss": 0.4059,
+      "step": 384
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8170254403131115,
+      "eval_f1": 0.8186226964112512,
+      "eval_loss": 0.4284485876560211,
+      "eval_precision": 0.8115384615384615,
+      "eval_recall": 0.8258317025440313,
+      "eval_runtime": 28.1941,
+      "eval_samples_per_second": 36.249,
+      "eval_steps_per_second": 1.135,
+      "step": 384
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 2.5780177116394043,
+      "learning_rate": 6.712371741852269e-05,
+      "loss": 0.398,
+      "step": 480
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.8258317025440313,
+      "eval_f1": 0.8378870673952642,
+      "eval_loss": 0.4101215600967407,
+      "eval_precision": 0.7836456558773425,
+      "eval_recall": 0.9001956947162426,
+      "eval_runtime": 28.0686,
+      "eval_samples_per_second": 36.411,
+      "eval_steps_per_second": 1.14,
+      "step": 480
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 4.741052150726318,
+      "learning_rate": 0.0,
+      "loss": 0.3876,
+      "step": 576
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.8297455968688845,
+      "eval_f1": 0.8370786516853934,
+      "eval_loss": 0.4097915291786194,
+      "eval_precision": 0.8025134649910234,
+      "eval_recall": 0.8747553816046967,
+      "eval_runtime": 29.2803,
+      "eval_samples_per_second": 34.904,
+      "eval_steps_per_second": 1.093,
+      "step": 576
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 576,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 6,
+  "save_steps": 500,
+  "total_flos": 1414171183680.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.8957226795607325,
+    "learning_rate": 0.0004027423045111362,
+    "num_train_epochs": 6,
+    "temperature": 3
+  }
+}

run-8/checkpoint-576/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c62ca979c251b24426f83ee19cf958429aed20a5e41a6549bd0708ed8286fb21
+size 4920

run-9/checkpoint-96/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d8d6934d852376a5bc13fbfb17016d4c3adcd7b7bdd42a9aab8b9b5d9f62a1b
+oid sha256:239dd84c1acbf3926d1b2ffcc0c8dbbb872ee0abbb6b9b92cf4944b98a755de2
 size 17549312

run-9/checkpoint-96/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:45b565c370bd07ca4b61cdb8cbc27c9334a05f68332f9e1d6be3633edc32ad6c
+oid sha256:cb67d3ee336b55baf61cb096cd593c5a926ac525753c86191a6d55862e3338d9
 size 35122746

run-9/checkpoint-96/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:50d2214d797b0d557f68148a57b0b4d53efab48f681a8a8f578594a80924ae16
+oid sha256:e91027d86c4ea0d43b412d03e2ef80532fe534e4a3c1c0000c6005738343a2bd
 size 1064

run-9/checkpoint-96/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.50293542074364,
+  "best_metric": 0.7514677103718199,
   "best_model_checkpoint": "tiny-bert-sst2-distilled/run-9/checkpoint-96",
   "epoch": 1.0,
   "eval_steps": 500,
@@ -10,36 +10,36 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "grad_norm": 0.7869714498519897,
-      "learning_rate": 1.3073475217173054e-05,
-      "loss": 0.6637,
+      "grad_norm": 2.0101799964904785,
+      "learning_rate": 5.9842495749639135e-05,
+      "loss": 0.6452,
       "step": 96
     },
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.50293542074364,
-      "eval_f1": 0.03422053231939163,
-      "eval_loss": 0.6569339036941528,
-      "eval_precision": 0.6,
-      "eval_recall": 0.01761252446183953,
-      "eval_runtime": 28.4278,
-      "eval_samples_per_second": 35.951,
-      "eval_steps_per_second": 1.126,
+      "eval_accuracy": 0.7514677103718199,
+      "eval_f1": 0.7806563039723661,
+      "eval_loss": 0.5494381785392761,
+      "eval_precision": 0.6986089644513137,
+      "eval_recall": 0.8845401174168297,
+      "eval_runtime": 28.605,
+      "eval_samples_per_second": 35.728,
+      "eval_steps_per_second": 1.119,
       "step": 96
     }
   ],
   "logging_steps": 500,
-  "max_steps": 768,
+  "max_steps": 384,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 8,
+  "num_train_epochs": 4,
   "save_steps": 500,
   "total_flos": 235695197280.0,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": {
-    "alpha": 0.9372925528810219,
-    "learning_rate": 1.4941114533912061e-05,
-    "num_train_epochs": 8,
-    "temperature": 17
+    "alpha": 0.9656943950307342,
+    "learning_rate": 7.978999433285218e-05,
+    "num_train_epochs": 4,
+    "temperature": 18
   }
 }

run-9/checkpoint-96/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c88ab003cb8d443d320a7d2a50b7663500e4bdf0605d3f2691a06db8acbcf72
+oid sha256:bb87382f1b3aca8f77e985c5e3b04a5f9ce84af6f6fa934f965157269a10afa9
 size 4920

tokenizer.json

@@ -2,7 +2,7 @@
   "version": "1.0",
   "truncation": {
     "direction": "Right",
-    "max_length": 33,
+    "max_length": 31,
     "strategy": "LongestFirst",
     "stride": 0
   },

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:019a0c30743454578a20e039f50246add333dec6abb36273bd6bc2339b797b34
+oid sha256:bb87382f1b3aca8f77e985c5e3b04a5f9ce84af6f6fa934f965157269a10afa9
 size 4920