Training in progress, epoch 1

logs/events.out.tfevents.1711293435.73e3a81c01ef.4225.22

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d018368c8d23742a0bf21ddbebca05f04def17cdc750fb9362b5ef6b6071a448
-size 6866
+oid sha256:07e3d5e969a283a35ec44cc78c0b7ab7022225e4c713687aeaf28cc6375a3f6a
+size 7950

logs/events.out.tfevents.1711294573.73e3a81c01ef.4225.23

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24d3b6cb52817ca63af63d91ae17ce4d9d3ce27aeb399ab6fd6980e3ea9989f3
+size 5406

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:609a49676de3f288302c9ea32b4c05014e9da1acd55839559c592513cd7750e9
+oid sha256:5232039d97d4db99e7ba6271deeedb0c6527fc47119f8e18fad59ab2cd36f0ae
 size 17549312

run-22/checkpoint-768/config.json

@@ -27,7 +27,7 @@
   "position_embedding_type": "absolute",
   "problem_type": "single_label_classification",
   "torch_dtype": "float32",
-  "transformers_version": "4.38.2",
+  "transformers_version": "4.39.1",
   "type_vocab_size": 2,
   "use_cache": true,
   "vocab_size": 30522

run-22/checkpoint-768/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b57cafbb8e48fb5903d46ff2e9249ecf67abede5242cf13bf2be71f485980b4
+oid sha256:2660522f3f61ad11613ebd20dc63c24a1df03f2e77a3458f5313438bb64b72a3
 size 17549312

run-22/checkpoint-768/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc25cb8b5e9caa5eb64f5a05755f30df44c467da9ded5af1dd782659b5afdce9
+oid sha256:1f352f7dfe2bed7e58160bf262f617600c06c6a128e81171aa0da47cb47d3888
 size 35122746

run-22/checkpoint-768/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33d55a7a7e131cd196205e2fe9c7e3f3a3d61ed6d79c468c68d4163c6b46138d
+oid sha256:1ed72394efd052c27a025cbbb902950bb9336778a32545e8b891d3c9c80c35d9
 size 14054

run-22/checkpoint-768/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:194b2bcad0b65c198819c73bdb4afeb3cb08e5349e435e338a3c60c1c604d53f
+oid sha256:87d0a7398c4812feab42cc83f5a64621597262a04f434af87b31905dd2d6350a
 size 1064

run-22/checkpoint-768/trainer_state.json

@@ -1,7 +1,7 @@
 {
-  "best_metric": 0.8395303326810176,
+  "best_metric": 0.8365949119373777,
   "best_model_checkpoint": "tiny-bert-sst2-distilled/run-22/checkpoint-768",
-  "epoch": 8.0,
+  "epoch": 4.0,
   "eval_steps": 500,
   "global_step": 768,
   "is_hyper_param_search": true,
@@ -10,169 +10,98 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "grad_norm": 2.464465618133545,
-      "learning_rate": 0.0001794635836369996,
-      "loss": 0.565,
-      "step": 96
+      "grad_norm": 4.364559650421143,
+      "learning_rate": 0.0002529924510479742,
+      "loss": 0.5381,
+      "step": 192
     },
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.7788649706457925,
-      "eval_f1": 0.8078231292517007,
-      "eval_loss": 0.4691426157951355,
-      "eval_precision": 0.7142857142857143,
-      "eval_recall": 0.9295499021526419,
-      "eval_runtime": 25.0337,
-      "eval_samples_per_second": 40.825,
-      "eval_steps_per_second": 1.278,
-      "step": 96
-    },
-    {
-      "epoch": 2.0,
-      "grad_norm": 4.053184509277344,
-      "learning_rate": 0.00015703063568237466,
-      "loss": 0.4676,
+      "eval_accuracy": 0.7896281800391389,
+      "eval_f1": 0.8071748878923767,
+      "eval_loss": 0.45070555806159973,
+      "eval_mcc": 0.5890946801852007,
+      "eval_precision": 0.7450331125827815,
+      "eval_recall": 0.8806262230919765,
+      "eval_runtime": 67.3745,
+      "eval_samples_per_second": 15.169,
+      "eval_steps_per_second": 0.475,
       "step": 192
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.7984344422700587,
-      "eval_f1": 0.8170515097690941,
-      "eval_loss": 0.4367915391921997,
-      "eval_precision": 0.7479674796747967,
-      "eval_recall": 0.9001956947162426,
-      "eval_runtime": 25.2941,
-      "eval_samples_per_second": 40.405,
-      "eval_steps_per_second": 1.265,
-      "step": 192
-    },
-    {
-      "epoch": 3.0,
-      "grad_norm": 2.9524621963500977,
-      "learning_rate": 0.00013459768772774972,
-      "loss": 0.4358,
-      "step": 288
-    },
-    {
-      "epoch": 3.0,
-      "eval_accuracy": 0.8209393346379648,
-      "eval_f1": 0.8334849863512284,
-      "eval_loss": 0.4263817071914673,
-      "eval_precision": 0.7789115646258503,
-      "eval_recall": 0.8962818003913894,
-      "eval_runtime": 24.9367,
-      "eval_samples_per_second": 40.984,
-      "eval_steps_per_second": 1.283,
-      "step": 288
-    },
-    {
-      "epoch": 4.0,
-      "grad_norm": 6.636496067047119,
-      "learning_rate": 0.00011216473977312478,
-      "loss": 0.4174,
+      "grad_norm": 9.345165252685547,
+      "learning_rate": 0.0001686616340319828,
+      "loss": 0.4554,
       "step": 384
     },
     {
-      "epoch": 4.0,
-      "eval_accuracy": 0.8160469667318982,
-      "eval_f1": 0.8181818181818182,
-      "eval_loss": 0.41675594449043274,
-      "eval_precision": 0.8087954110898662,
-      "eval_recall": 0.8277886497064579,
-      "eval_runtime": 24.9785,
-      "eval_samples_per_second": 40.915,
-      "eval_steps_per_second": 1.281,
+      "epoch": 2.0,
+      "eval_accuracy": 0.8043052837573386,
+      "eval_f1": 0.8127340823970037,
+      "eval_loss": 0.4277065694332123,
+      "eval_mcc": 0.6110916014068072,
+      "eval_precision": 0.7791741472172352,
+      "eval_recall": 0.8493150684931506,
+      "eval_runtime": 67.2822,
+      "eval_samples_per_second": 15.19,
+      "eval_steps_per_second": 0.476,
       "step": 384
     },
     {
-      "epoch": 5.0,
-      "grad_norm": 2.0662448406219482,
-      "learning_rate": 8.97317918184998e-05,
-      "loss": 0.4077,
-      "step": 480
-    },
-    {
-      "epoch": 5.0,
-      "eval_accuracy": 0.8356164383561644,
-      "eval_f1": 0.8502673796791443,
-      "eval_loss": 0.40537795424461365,
-      "eval_precision": 0.7806873977086743,
-      "eval_recall": 0.9334637964774951,
-      "eval_runtime": 25.8814,
-      "eval_samples_per_second": 39.488,
-      "eval_steps_per_second": 1.236,
-      "step": 480
-    },
-    {
-      "epoch": 6.0,
-      "grad_norm": 4.637610912322998,
-      "learning_rate": 6.729884386387486e-05,
-      "loss": 0.4004,
+      "epoch": 3.0,
+      "grad_norm": 6.078808307647705,
+      "learning_rate": 8.43308170159914e-05,
+      "loss": 0.418,
       "step": 576
     },
     {
-      "epoch": 6.0,
-      "eval_accuracy": 0.8258317025440313,
-      "eval_f1": 0.842756183745583,
-      "eval_loss": 0.40995147824287415,
-      "eval_precision": 0.7681159420289855,
-      "eval_recall": 0.9334637964774951,
-      "eval_runtime": 25.8126,
-      "eval_samples_per_second": 39.593,
-      "eval_steps_per_second": 1.24,
+      "epoch": 3.0,
+      "eval_accuracy": 0.8238747553816047,
+      "eval_f1": 0.8387096774193549,
+      "eval_loss": 0.4266253113746643,
+      "eval_mcc": 0.6589952419988697,
+      "eval_precision": 0.7735537190082644,
+      "eval_recall": 0.9158512720156555,
+      "eval_runtime": 67.2428,
+      "eval_samples_per_second": 15.199,
+      "eval_steps_per_second": 0.476,
       "step": 576
     },
     {
-      "epoch": 7.0,
-      "grad_norm": 3.4253664016723633,
-      "learning_rate": 4.48658959092499e-05,
-      "loss": 0.391,
-      "step": 672
-    },
-    {
-      "epoch": 7.0,
-      "eval_accuracy": 0.8326810176125244,
-      "eval_f1": 0.8488063660477454,
-      "eval_loss": 0.40309804677963257,
-      "eval_precision": 0.7741935483870968,
-      "eval_recall": 0.9393346379647749,
-      "eval_runtime": 26.0268,
-      "eval_samples_per_second": 39.267,
-      "eval_steps_per_second": 1.23,
-      "step": 672
-    },
-    {
-      "epoch": 8.0,
-      "grad_norm": 4.7185893058776855,
-      "learning_rate": 2.243294795462495e-05,
-      "loss": 0.3869,
+      "epoch": 4.0,
+      "grad_norm": 2.4011917114257812,
+      "learning_rate": 0.0,
+      "loss": 0.3997,
       "step": 768
     },
     {
-      "epoch": 8.0,
-      "eval_accuracy": 0.8395303326810176,
-      "eval_f1": 0.851985559566787,
-      "eval_loss": 0.39594146609306335,
-      "eval_precision": 0.7906197654941374,
-      "eval_recall": 0.923679060665362,
-      "eval_runtime": 25.1887,
-      "eval_samples_per_second": 40.574,
-      "eval_steps_per_second": 1.27,
+      "epoch": 4.0,
+      "eval_accuracy": 0.8365949119373777,
+      "eval_f1": 0.8477666362807658,
+      "eval_loss": 0.41222792863845825,
+      "eval_mcc": 0.680559953194408,
+      "eval_precision": 0.7935153583617748,
+      "eval_recall": 0.9099804305283757,
+      "eval_runtime": 67.3829,
+      "eval_samples_per_second": 15.167,
+      "eval_steps_per_second": 0.475,
       "step": 768
     }
   ],
   "logging_steps": 500,
-  "max_steps": 864,
+  "max_steps": 768,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 9,
+  "num_train_epochs": 4,
   "save_steps": 500,
-  "total_flos": 1885561578240.0,
-  "train_batch_size": 32,
+  "total_flos": 942780789120.0,
+  "train_batch_size": 16,
   "trial_name": null,
   "trial_params": {
-    "alpha": 0.8956145079239534,
-    "learning_rate": 0.00020189653159162458,
-    "num_train_epochs": 9,
-    "temperature": 8
+    "alpha": 0.885980659186716,
+    "learning_rate": 0.0003373232680639656,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 16,
+    "temperature": 44
   }
 }

run-22/checkpoint-768/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a59435df03122e4e47861365c1b2756f99313581e8b38e82a031f16aa354557d
-size 4920
+oid sha256:8c24fdecf1c90c419bf77f10ab570330e1370392bd9d70f58780b22b36367b96
+size 4984

run-23/checkpoint-192/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": "4.39.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-23/checkpoint-192/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5232039d97d4db99e7ba6271deeedb0c6527fc47119f8e18fad59ab2cd36f0ae
+size 17549312

run-23/checkpoint-192/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c157f8b1e6c757c6a1627b714248b67fb274338e597948892131f94097ac049b
+size 35122746

run-23/checkpoint-192/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee09ea0d216727b799a80771850b95d7d61b646360702c64b2ec889cdc725399
+size 14054

run-23/checkpoint-192/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b516bf36e657d8bce07aedbe1849132b97b28a9794479afcb0e8a12f37e729a
+size 1064

run-23/checkpoint-192/special_tokens_map.json

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

run-23/checkpoint-192/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-23/checkpoint-192/trainer_state.json

@@ -0,0 +1,47 @@
+{
+  "best_metric": 0.7935420743639922,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-23/checkpoint-192",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 192,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 5.60397481918335,
+      "learning_rate": 0.00021040106446320055,
+      "loss": 0.5452,
+      "step": 192
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7935420743639922,
+      "eval_f1": 0.809049773755656,
+      "eval_loss": 0.44930505752563477,
+      "eval_mcc": 0.5949851791037805,
+      "eval_precision": 0.7525252525252525,
+      "eval_recall": 0.8747553816046967,
+      "eval_runtime": 66.8274,
+      "eval_samples_per_second": 15.293,
+      "eval_steps_per_second": 0.479,
+      "step": 192
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 768,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 235695197280.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.9076998236532954,
+    "learning_rate": 0.0002805347526176007,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 16,
+    "temperature": 32
+  }
+}

run-23/checkpoint-192/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b1388c03a76bdbf0955d3ee662bb7d2ee1c5be7b9ed87ead1481458332e1acc
+size 4984

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f62d580257060cdaf08ca2f6bebff447fe36fd6a4ed09c360f3a936d71824ec
-size 4920
+oid sha256:6b1388c03a76bdbf0955d3ee662bb7d2ee1c5be7b9ed87ead1481458332e1acc
+size 4984