Training in progress, epoch 1

logs/events.out.tfevents.1710499824.af351b5edcca.3142.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:648f00876221799fcecb38155d9e1d54854561e0fdfcc6ce5485e37118dae261
-size 5713
+oid sha256:ae936c102de7fa2736922821fc2e92000363564e46c2c1689353af4d6a3dc9c4
+size 7669

logs/events.out.tfevents.1710501374.af351b5edcca.3142.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13eca046958b79bcb48a669b7a32c2a75f247bbd5402228ac1868725d364b56c
+size 5180

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:088e63b4c3a6c6cb565263cdb3909e74387b189e23b1faa39d6a055b6133c1f9
+oid sha256:066d0a0f3dedf60356cd0dcc29d0f03304cc10f4cdfea716a97548f7a62e9428
 size 17549312

run-0/checkpoint-1485/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-0/checkpoint-1485/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97696da066c4917212eea7b3878fad9b85f970534d7a4002f4806732c828446d
+size 17549312

run-0/checkpoint-1485/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c2dcc1f997f2652a8225c8fde5f8e85b462e4ec04e70ab788dd3da41e400177
+size 35122746

run-0/checkpoint-1485/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef3b88c0c6d034b48bef8b689e5ae0d1730de3acc34d7d2e10f12c5161fc0753
+size 14054

run-0/checkpoint-1485/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:319754326f9d189f724be5421b676e9e6f12ab16fbb6652e0345d5c6275bee82
+size 1064

run-0/checkpoint-1485/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-1485/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-1485/trainer_state.json

@@ -0,0 +1,106 @@
+{
+  "best_metric": 0.5227722772277228,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-0/checkpoint-594",
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 1485,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.48113372921943665,
+      "learning_rate": 1.1539601014308473e-05,
+      "loss": 0.265,
+      "step": 297
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.502970297029703,
+      "eval_loss": 0.24101482331752777,
+      "eval_runtime": 14.0847,
+      "eval_samples_per_second": 35.854,
+      "eval_steps_per_second": 1.136,
+      "step": 297
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.3685588538646698,
+      "learning_rate": 8.654700760731354e-06,
+      "loss": 0.2411,
+      "step": 594
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.5227722772277228,
+      "eval_loss": 0.23663455247879028,
+      "eval_runtime": 15.2033,
+      "eval_samples_per_second": 33.216,
+      "eval_steps_per_second": 1.052,
+      "step": 594
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.46092164516448975,
+      "learning_rate": 5.769800507154237e-06,
+      "loss": 0.2391,
+      "step": 891
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.5207920792079208,
+      "eval_loss": 0.23553016781806946,
+      "eval_runtime": 15.2473,
+      "eval_samples_per_second": 33.121,
+      "eval_steps_per_second": 1.049,
+      "step": 891
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.48338672518730164,
+      "learning_rate": 2.8849002535771184e-06,
+      "loss": 0.2381,
+      "step": 1188
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.5207920792079208,
+      "eval_loss": 0.23503994941711426,
+      "eval_runtime": 15.2316,
+      "eval_samples_per_second": 33.155,
+      "eval_steps_per_second": 1.05,
+      "step": 1188
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.43587103486061096,
+      "learning_rate": 0.0,
+      "loss": 0.2374,
+      "step": 1485
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.5207920792079208,
+      "eval_loss": 0.2346782386302948,
+      "eval_runtime": 14.1441,
+      "eval_samples_per_second": 35.704,
+      "eval_steps_per_second": 1.131,
+      "step": 1485
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1485,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 3889216415700.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.28450461852175,
+    "learning_rate": 1.4424501267885591e-05,
+    "num_train_epochs": 5,
+    "temperature": 8
+  }
+}

run-0/checkpoint-1485/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:077f4108dc0cc2deb6d8b370dcd0cd733cd0d0661416c4baa607e842107e384b
+size 4984

run-1/checkpoint-297/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf78f191f8ec19931f9cd904378746a6b65295ee17e7e52a6a382fd0d4c8a6dd
+oid sha256:066d0a0f3dedf60356cd0dcc29d0f03304cc10f4cdfea716a97548f7a62e9428
 size 17549312

run-1/checkpoint-297/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:acd6c9baeefb8f102b3b39c4118c7136ac58f455f69bd550edb68349840eb054
+oid sha256:e809e38aec10c01a3656170dae7afd04ffce171ba128b8f0a39bd53aecb92ebb
 size 35122746

run-1/checkpoint-297/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:883a13d0ce4b22682af6eb4d99c939f3ce2e855ed8d1ade27c75e0163ba553ff
+oid sha256:f4bc2610084f26204ada03fd51932556b7db63f33cd61e0cfcf38c603da8b8ae
 size 1064

run-1/checkpoint-297/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.5841584158415841,
+  "best_metric": 0.5188118811881188,
   "best_model_checkpoint": "tiny-bert-sst2-distilled/run-1/checkpoint-297",
   "epoch": 1.0,
   "eval_steps": 500,
@@ -10,33 +10,33 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "grad_norm": 1.3426679372787476,
-      "learning_rate": 0.0003560526201910554,
-      "loss": 0.6371,
+      "grad_norm": 0.8816747665405273,
+      "learning_rate": 0.0001319007893143593,
+      "loss": 0.4812,
       "step": 297
     },
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.5841584158415841,
-      "eval_loss": 0.637409508228302,
-      "eval_runtime": 56.7978,
-      "eval_samples_per_second": 8.891,
-      "eval_steps_per_second": 0.282,
+      "eval_accuracy": 0.5188118811881188,
+      "eval_loss": 0.4719693958759308,
+      "eval_runtime": 14.5929,
+      "eval_samples_per_second": 34.606,
+      "eval_steps_per_second": 1.096,
       "step": 297
     }
   ],
   "logging_steps": 500,
-  "max_steps": 1188,
+  "max_steps": 2970,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 4,
+  "num_train_epochs": 10,
   "save_steps": 500,
   "total_flos": 777843283140.0,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": {
-    "alpha": 0.900582717199523,
-    "learning_rate": 0.0004747368269214072,
-    "num_train_epochs": 4,
-    "temperature": 18
+    "alpha": 0.6312656697409034,
+    "learning_rate": 0.00014655643257151032,
+    "num_train_epochs": 10,
+    "temperature": 21
   }
 }

run-1/checkpoint-297/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a6f636dbab8b5e516bcd85051f9f0732a28727ed1675f1d1f3076c7baf2be402
+oid sha256:af3594179603e2d274700519c77f184614d6b83fa0b91f253fa6d184fb0aa0e2
 size 4984

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:077f4108dc0cc2deb6d8b370dcd0cd733cd0d0661416c4baa607e842107e384b
+oid sha256:af3594179603e2d274700519c77f184614d6b83fa0b91f253fa6d184fb0aa0e2
 size 4984