Training in progress, epoch 1

logs/events.out.tfevents.1711287195.73e3a81c01ef.4225.15

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:403f1a518bcc463138e66a72fadd414921820dfc01b7fa5fbd1395f6c258df54
-size 6136
+oid sha256:3acb017ff084734c6e31c4e3b0429d46cb839c5883ba6fcf3f720900356e7bb1
+size 7220

logs/events.out.tfevents.1711288042.73e3a81c01ef.4225.16

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:622a5b2bea83a6df8a3569b6755407dbbfe629b2cfecb026a9dd47aaea38c746
+size 5406

logs/events.out.tfevents.1711288324.73e3a81c01ef.4225.17

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:110b65c1c6add0e852ec28f9d6d59a96b923041f3a690de2d1e4516cc4cb0998
+size 5406

logs/events.out.tfevents.1711288606.73e3a81c01ef.4225.18

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7a33d4782cecda14e7d415c3540b2e5ac1832dbef69316f3ac908b452af71b3
+size 5406

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae22ee32134046dce88abbe8f3caaca150ec5660315c7d0bed8fdc804ffe2a26
+oid sha256:04862422b777979d1fe4725bb12ed1938258cd3e48a71752c0a8cb26e3e7f9cf
 size 17549312

run-15/checkpoint-576/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-15/checkpoint-576/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:810bb1837ff14155e2013d49dabaf358aabc882fad6d18f9a2318b986f8a874f
+oid sha256:f50ca442546a6339ab9afc62425b40e9f1e7df1536ff92c462cbd4e2d95511c3
 size 17549312

run-15/checkpoint-576/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca9413a6ba0adc77578e1c39bc1eed1c63d653c009fc069b97a6598e0a575c6c
+oid sha256:45c6cea254f9c37183697951585f5f0de5cacf27e3cff35e818106adeade3cee
 size 35122746

run-15/checkpoint-576/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d4ad45514321df5f64172bb2de61ac319a093d9f31cf01031977fb88be20551
+oid sha256:77649db78380b105203c3be0753a0a47e20be3ccd8ec2455a7d4db9d8ae85766
 size 14054

run-15/checkpoint-576/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ac1be509a32168fc2a739e40ec4d12bcac2778128aeda547e1dfcfb74440e9f
+oid sha256:5fe6275fcc6f801b747f85b74e826f57f4af00678bf6263fa3218fd4d9ebaf7e
 size 1064

run-15/checkpoint-576/trainer_state.json

@@ -1,7 +1,7 @@
 {
-  "best_metric": 0.8287671232876712,
-  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-15/checkpoint-480",
-  "epoch": 6.0,
+  "best_metric": 0.8082191780821918,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-15/checkpoint-384",
+  "epoch": 3.0,
   "eval_steps": 500,
   "global_step": 576,
   "is_hyper_param_search": true,
@@ -10,131 +10,78 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "grad_norm": 2.341264247894287,
-      "learning_rate": 0.0003257774454972516,
-      "loss": 0.5225,
-      "step": 96
+      "grad_norm": 3.1954071521759033,
+      "learning_rate": 4.7129202867976326e-05,
+      "loss": 0.5731,
+      "step": 192
     },
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.7906066536203522,
-      "eval_f1": 0.8078994614003591,
-      "eval_loss": 0.4404396712779999,
-      "eval_precision": 0.746268656716418,
-      "eval_recall": 0.8806262230919765,
-      "eval_runtime": 24.9228,
-      "eval_samples_per_second": 41.007,
-      "eval_steps_per_second": 1.284,
-      "step": 96
-    },
-    {
-      "epoch": 2.0,
-      "grad_norm": 2.7467563152313232,
-      "learning_rate": 0.00028957995155311255,
-      "loss": 0.4443,
+      "eval_accuracy": 0.7896281800391389,
+      "eval_f1": 0.8088888888888889,
+      "eval_loss": 0.47491252422332764,
+      "eval_mcc": 0.5913947215491926,
+      "eval_precision": 0.741042345276873,
+      "eval_recall": 0.8904109589041096,
+      "eval_runtime": 66.6851,
+      "eval_samples_per_second": 15.326,
+      "eval_steps_per_second": 0.48,
       "step": 192
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.8189823874755382,
-      "eval_f1": 0.8322756119673618,
-      "eval_loss": 0.40899789333343506,
-      "eval_precision": 0.7753378378378378,
-      "eval_recall": 0.898238747553816,
-      "eval_runtime": 24.9291,
-      "eval_samples_per_second": 40.996,
-      "eval_steps_per_second": 1.284,
-      "step": 192
-    },
-    {
-      "epoch": 3.0,
-      "grad_norm": 3.382880210876465,
-      "learning_rate": 0.00025338245760897347,
-      "loss": 0.4106,
-      "step": 288
-    },
-    {
-      "epoch": 3.0,
-      "eval_accuracy": 0.8238747553816047,
-      "eval_f1": 0.8324022346368715,
-      "eval_loss": 0.4271247386932373,
-      "eval_precision": 0.7939609236234458,
-      "eval_recall": 0.8747553816046967,
-      "eval_runtime": 26.7353,
-      "eval_samples_per_second": 38.227,
-      "eval_steps_per_second": 1.197,
-      "step": 288
-    },
-    {
-      "epoch": 4.0,
-      "grad_norm": 2.9181997776031494,
-      "learning_rate": 0.00021718496366483439,
-      "loss": 0.4035,
+      "grad_norm": 7.988830089569092,
+      "learning_rate": 2.3564601433988163e-05,
+      "loss": 0.4767,
       "step": 384
     },
     {
-      "epoch": 4.0,
-      "eval_accuracy": 0.8170254403131115,
-      "eval_f1": 0.8172043010752689,
-      "eval_loss": 0.41200369596481323,
-      "eval_precision": 0.81640625,
-      "eval_recall": 0.8180039138943248,
-      "eval_runtime": 26.179,
-      "eval_samples_per_second": 39.039,
-      "eval_steps_per_second": 1.222,
+      "epoch": 2.0,
+      "eval_accuracy": 0.8082191780821918,
+      "eval_f1": 0.8208409506398537,
+      "eval_loss": 0.4437917172908783,
+      "eval_mcc": 0.6226500342007837,
+      "eval_precision": 0.7701543739279588,
+      "eval_recall": 0.8786692759295499,
+      "eval_runtime": 66.9186,
+      "eval_samples_per_second": 15.272,
+      "eval_steps_per_second": 0.478,
       "step": 384
     },
     {
-      "epoch": 5.0,
-      "grad_norm": 1.339964509010315,
-      "learning_rate": 0.00018098746972069533,
-      "loss": 0.3903,
-      "step": 480
-    },
-    {
-      "epoch": 5.0,
-      "eval_accuracy": 0.8287671232876712,
-      "eval_f1": 0.8362956033676333,
-      "eval_loss": 0.40260037779808044,
-      "eval_precision": 0.8010752688172043,
-      "eval_recall": 0.8747553816046967,
-      "eval_runtime": 25.7166,
-      "eval_samples_per_second": 39.741,
-      "eval_steps_per_second": 1.244,
-      "step": 480
-    },
-    {
-      "epoch": 6.0,
-      "grad_norm": 2.8921544551849365,
-      "learning_rate": 0.00014478997577655628,
-      "loss": 0.3906,
+      "epoch": 3.0,
+      "grad_norm": 3.454801082611084,
+      "learning_rate": 0.0,
+      "loss": 0.4554,
       "step": 576
     },
     {
-      "epoch": 6.0,
-      "eval_accuracy": 0.8277886497064579,
-      "eval_f1": 0.8408679927667269,
-      "eval_loss": 0.39854004979133606,
-      "eval_precision": 0.7815126050420168,
-      "eval_recall": 0.9099804305283757,
-      "eval_runtime": 25.134,
-      "eval_samples_per_second": 40.662,
-      "eval_steps_per_second": 1.273,
+      "epoch": 3.0,
+      "eval_accuracy": 0.8072407045009785,
+      "eval_f1": 0.8233183856502243,
+      "eval_loss": 0.4398359954357147,
+      "eval_mcc": 0.624918005331598,
+      "eval_precision": 0.7599337748344371,
+      "eval_recall": 0.898238747553816,
+      "eval_runtime": 66.52,
+      "eval_samples_per_second": 15.364,
+      "eval_steps_per_second": 0.481,
       "step": 576
     }
   ],
   "logging_steps": 500,
-  "max_steps": 960,
+  "max_steps": 576,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 10,
+  "num_train_epochs": 3,
   "save_steps": 500,
-  "total_flos": 1414171183680.0,
-  "train_batch_size": 32,
+  "total_flos": 707085591840.0,
+  "train_batch_size": 16,
   "trial_name": null,
   "trial_params": {
-    "alpha": 0.7955319016044536,
-    "learning_rate": 0.00036197493944139066,
-    "num_train_epochs": 10,
-    "temperature": 8
+    "alpha": 0.8612888560371268,
+    "learning_rate": 7.069380430196449e-05,
+    "num_train_epochs": 3,
+    "per_device_train_batch_size": 16,
+    "temperature": 23
   }
 }

run-15/checkpoint-576/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e3d9bd9e7f16ac97ca0e7e00ad365e1b9f7804af850a7b1faa4910402684f951
-size 4920
+oid sha256:d957ce0a97207c7175ba451db3f66fa371ed707404ff50f15e7363524a12dff1
+size 4984

run-18/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-18/checkpoint-192/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04862422b777979d1fe4725bb12ed1938258cd3e48a71752c0a8cb26e3e7f9cf
+size 17549312

run-18/checkpoint-192/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ee459216160ac2af9ebba953ef6691646f7c4e817a3b5b43517ab0bce7077d6
+size 35122746

run-18/checkpoint-192/rng_state.pth

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

run-18/checkpoint-192/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6107ba416dc9233ae686d41e832ade46253dacfd9374c15b71b6ab333c5dadda
+size 1064

run-18/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-18/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-18/checkpoint-192/trainer_state.json

@@ -0,0 +1,47 @@
+{
+  "best_metric": 0.7847358121330724,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-18/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": 1.9128750562667847,
+      "learning_rate": 0.000468107445983249,
+      "loss": 0.5305,
+      "step": 192
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7847358121330724,
+      "eval_f1": 0.7920604914933836,
+      "eval_loss": 0.45163166522979736,
+      "eval_mcc": 0.5708901120719992,
+      "eval_precision": 0.7659963436928702,
+      "eval_recall": 0.8199608610567515,
+      "eval_runtime": 67.0893,
+      "eval_samples_per_second": 15.233,
+      "eval_steps_per_second": 0.477,
+      "step": 192
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 960,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 235695197280.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.8570009057234442,
+    "learning_rate": 0.0005851343074790613,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 16,
+    "temperature": 44
+  }
+}

run-18/checkpoint-192/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d6d40790f42dee9a3e9e40c365698dad316d5c1906d822cd1942d3c13f8ae85
+size 4984

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f62d580257060cdaf08ca2f6bebff447fe36fd6a4ed09c360f3a936d71824ec
-size 4920
+oid sha256:6d6d40790f42dee9a3e9e40c365698dad316d5c1906d822cd1942d3c13f8ae85
+size 4984