Training in progress, epoch 1

config.json

@@ -15,8 +15,8 @@
   "initializer_range": 0.02,
   "intermediate_size": 512,
   "label2id": {
-    "negative": 0,
-    "positive": 1
+    "negative": "0",
+    "positive": "1"
   },
   "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,

logs/events.out.tfevents.1711295423.73e3a81c01ef.4225.24

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b6424598aad99ea77edb4c97da14b185a7cef4322d61f37dea3d4b03373a965e
-size 6137
+oid sha256:8b411f56f015cebad52fe9baad3b3b749cc7ebd5bb124a55133cc1a0462335ee
+size 7221

logs/events.out.tfevents.1711296275.73e3a81c01ef.4225.25

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e96d7bb6c30b59d2eebc2e076bf3a0f3faed5042ee80b7d757e27db7fe32eec
+size 5406

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a81fe74feab7b6727debbee2a209a3074c785943bd0a6ddd5ee240e4037e6027
+oid sha256:ebdf0abd015bfcd72046638dd2af7d5be4de28268a5c065b2ac8ec7db2247c8c
 size 17549312

run-24/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": "4.39.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-24/checkpoint-576/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e15e7cb8d694b46da301b683d00bfe9789f2a1ac974ea993f0cd78cbe26ad03
+size 17549312

run-24/checkpoint-576/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:affc998f1da02af5090b93ce798cdf096c33844a0973ba9bef9c16dd7bd1022e
+size 35122746

run-24/checkpoint-576/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77649db78380b105203c3be0753a0a47e20be3ccd8ec2455a7d4db9d8ae85766
+size 14054

run-24/checkpoint-576/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6819350976b51c656129c9b4f23ac2b820d60412303eb90c52d56911ccf1c848
+size 1064

run-24/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-24/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-24/checkpoint-576/trainer_state.json

@@ -0,0 +1,87 @@
+{
+  "best_metric": 0.8160469667318982,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-24/checkpoint-576",
+  "epoch": 3.0,
+  "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": 4.648065090179443,
+      "learning_rate": 0.00012494952559183724,
+      "loss": 0.5711,
+      "step": 192
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8043052837573386,
+      "eval_f1": 0.8178506375227687,
+      "eval_loss": 0.44779932498931885,
+      "eval_mcc": 0.6154555748616207,
+      "eval_precision": 0.7649063032367973,
+      "eval_recall": 0.8786692759295499,
+      "eval_runtime": 66.7583,
+      "eval_samples_per_second": 15.309,
+      "eval_steps_per_second": 0.479,
+      "step": 192
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 13.388855934143066,
+      "learning_rate": 6.247476279591862e-05,
+      "loss": 0.461,
+      "step": 384
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8131115459882583,
+      "eval_f1": 0.8239631336405531,
+      "eval_loss": 0.4190569818019867,
+      "eval_mcc": 0.631037291856266,
+      "eval_precision": 0.7787456445993032,
+      "eval_recall": 0.8747553816046967,
+      "eval_runtime": 66.8351,
+      "eval_samples_per_second": 15.291,
+      "eval_steps_per_second": 0.479,
+      "step": 384
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 5.122457504272461,
+      "learning_rate": 0.0,
+      "loss": 0.4197,
+      "step": 576
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8160469667318982,
+      "eval_f1": 0.8312387791741472,
+      "eval_loss": 0.4178280830383301,
+      "eval_mcc": 0.6425942790851412,
+      "eval_precision": 0.7678275290215588,
+      "eval_recall": 0.9060665362035225,
+      "eval_runtime": 67.021,
+      "eval_samples_per_second": 15.249,
+      "eval_steps_per_second": 0.477,
+      "step": 576
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 576,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 707085591840.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.9973571924957664,
+    "learning_rate": 0.00018742428838775587,
+    "num_train_epochs": 3,
+    "per_device_train_batch_size": 16,
+    "temperature": 50
+  }
+}

run-24/checkpoint-576/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3c5d3018229d2667ade19316e65e309d90ed770cbee817143182a01f8c881eb
+size 4984

run-25/checkpoint-192/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-25/checkpoint-192/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e25ee0cb7b2449845032b3dfcc16415f929b4ab92039e01f8b92a8f2b222457e
+oid sha256:ebdf0abd015bfcd72046638dd2af7d5be4de28268a5c065b2ac8ec7db2247c8c
 size 17549312

run-25/checkpoint-192/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5648fd3b6804b363a2e65e72e911ff2af9995e54240db6faebb6d62346f8bca4
+oid sha256:6bf321392e8f02aea63f864733ff633c433909f68e803c050dbb1839d8e3c2c1
 size 35122746

run-25/checkpoint-192/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c58c0607d97c986e9d4c30b0aa74b33350e0c7e86978aaaaadda4ebb78f21ad
+oid sha256:ee09ea0d216727b799a80771850b95d7d61b646360702c64b2ec889cdc725399
 size 14054

run-25/checkpoint-192/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f3b487be3684f52a2c59062676f652ecda3a6ba60459674c8690dbbb468cbf9e
+oid sha256:e12e258b95bcabdec97c40c2f3228e38169a42f3f573645f637b4993b3b3ccf9
 size 1064

run-25/checkpoint-192/trainer_state.json

@@ -1,7 +1,7 @@
 {
-  "best_metric": 0.8091976516634051,
+  "best_metric": 0.7945205479452054,
   "best_model_checkpoint": "tiny-bert-sst2-distilled/run-25/checkpoint-192",
-  "epoch": 2.0,
+  "epoch": 1.0,
   "eval_steps": 500,
   "global_step": 192,
   "is_hyper_param_search": true,
@@ -10,55 +10,38 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "grad_norm": 1.8755850791931152,
-      "learning_rate": 0.00020053170483737637,
-      "loss": 0.4801,
-      "step": 96
-    },
-    {
-      "epoch": 1.0,
-      "eval_accuracy": 0.7818003913894325,
-      "eval_f1": 0.8092386655260906,
-      "eval_loss": 0.42955365777015686,
-      "eval_precision": 0.7188449848024316,
-      "eval_recall": 0.9256360078277887,
-      "eval_runtime": 31.124,
-      "eval_samples_per_second": 32.836,
-      "eval_steps_per_second": 1.028,
-      "step": 96
-    },
-    {
-      "epoch": 2.0,
-      "grad_norm": 2.4842429161071777,
-      "learning_rate": 0.0001782504042998901,
-      "loss": 0.4182,
+      "grad_norm": 3.914764881134033,
+      "learning_rate": 7.983594966012216e-05,
+      "loss": 0.5279,
       "step": 192
     },
     {
-      "epoch": 2.0,
-      "eval_accuracy": 0.8091976516634051,
-      "eval_f1": 0.8232094288304623,
-      "eval_loss": 0.3939443826675415,
-      "eval_precision": 0.7668918918918919,
-      "eval_recall": 0.8884540117416829,
-      "eval_runtime": 32.508,
-      "eval_samples_per_second": 31.438,
-      "eval_steps_per_second": 0.984,
+      "epoch": 1.0,
+      "eval_accuracy": 0.7945205479452054,
+      "eval_f1": 0.8148148148148147,
+      "eval_loss": 0.43646204471588135,
+      "eval_mcc": 0.6037206409101726,
+      "eval_precision": 0.7415730337078652,
+      "eval_recall": 0.9041095890410958,
+      "eval_runtime": 67.0044,
+      "eval_samples_per_second": 15.253,
+      "eval_steps_per_second": 0.478,
       "step": 192
     }
   ],
   "logging_steps": 500,
-  "max_steps": 960,
+  "max_steps": 1152,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 10,
+  "num_train_epochs": 6,
   "save_steps": 500,
-  "total_flos": 471390394560.0,
-  "train_batch_size": 32,
+  "total_flos": 235695197280.0,
+  "train_batch_size": 16,
   "trial_name": null,
   "trial_params": {
-    "alpha": 0.6872599698926333,
-    "learning_rate": 0.00022281300537486262,
-    "num_train_epochs": 10,
-    "temperature": 15
+    "alpha": 0.7984848902449955,
+    "learning_rate": 9.580313959214659e-05,
+    "num_train_epochs": 6,
+    "per_device_train_batch_size": 16,
+    "temperature": 43
   }
 }

run-25/checkpoint-192/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:99da68eb3e23d3e605d1e77f3904ae2ee7244687e6e5e8018e151049999ab73d
-size 4920
+oid sha256:0df23de5f2d7c569f8878223b016d804cf54077b0824a5d63ecc274595ea3eea
+size 4984

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f62d580257060cdaf08ca2f6bebff447fe36fd6a4ed09c360f3a936d71824ec
-size 4920
+oid sha256:0df23de5f2d7c569f8878223b016d804cf54077b0824a5d63ecc274595ea3eea
+size 4984