Training in progress, epoch 1

logs/events.out.tfevents.1710504474.af351b5edcca.3142.2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f36684de03a0a4bb0090cb9abc27bc835509235bef0d3d77561e8dcb1f972153
-size 5713
+oid sha256:3630beedda41ccdc447fea0783d91547dfb3156409a2777b2c04f9cceeabd853
+size 9805

logs/events.out.tfevents.1710507175.af351b5edcca.3142.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f06198ee44361a23f2d4fd39293a6cc026d37caaed7434826721619e1347790
+size 5178

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:20315271c1affdb4108e833ced469196b45121eac51b5d41049233a683a2a17e
+oid sha256:76220d7fcfb19b8bac2ae99022cae216a90b830bf00b3012d8b613a63d0bf947
 size 17549312

run-2/checkpoint-2673/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-2/checkpoint-2673/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24d3b3773a2cb5eb4fe5d0510281ec4afc468d94f153ea1c4e42557acc72d031
+size 17549312

run-2/checkpoint-2673/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aaaf77f832395c735d2ca2829839fa8b3de3e358a4b7cfb575a266ac248c48c0
+size 35122746

run-2/checkpoint-2673/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb49527a73de8c97b0805cc04f8d3e06cb2a963ae0f111d98648316d291a7702
+size 14054

run-2/checkpoint-2673/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d88a949c40227921ebbc201965ce805890fc5d6557c00c377fb1db010a9e5d7
+size 1064

run-2/checkpoint-2673/special_tokens_map.json

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

run-2/checkpoint-2673/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-2/checkpoint-2673/trainer_state.json

@@ -0,0 +1,170 @@
+{
+  "best_metric": 0.5207920792079208,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-2/checkpoint-594",
+  "epoch": 9.0,
+  "eval_steps": 500,
+  "global_step": 2673,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.46941760182380676,
+      "learning_rate": 1.0066413527942762e-05,
+      "loss": 0.2155,
+      "step": 297
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.497029702970297,
+      "eval_loss": 0.18417517840862274,
+      "eval_runtime": 14.6034,
+      "eval_samples_per_second": 34.581,
+      "eval_steps_per_second": 1.096,
+      "step": 297
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.3071568012237549,
+      "learning_rate": 8.808111836949918e-06,
+      "loss": 0.1831,
+      "step": 594
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.5207920792079208,
+      "eval_loss": 0.17807520925998688,
+      "eval_runtime": 14.6044,
+      "eval_samples_per_second": 34.579,
+      "eval_steps_per_second": 1.096,
+      "step": 594
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.35216400027275085,
+      "learning_rate": 7.549810145957073e-06,
+      "loss": 0.1804,
+      "step": 891
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.5207920792079208,
+      "eval_loss": 0.17647753655910492,
+      "eval_runtime": 15.4786,
+      "eval_samples_per_second": 32.626,
+      "eval_steps_per_second": 1.034,
+      "step": 891
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.26479315757751465,
+      "learning_rate": 6.291508454964228e-06,
+      "loss": 0.179,
+      "step": 1188
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.5168316831683168,
+      "eval_loss": 0.1757788509130478,
+      "eval_runtime": 13.9632,
+      "eval_samples_per_second": 36.166,
+      "eval_steps_per_second": 1.146,
+      "step": 1188
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.33599618077278137,
+      "learning_rate": 5.033206763971381e-06,
+      "loss": 0.1781,
+      "step": 1485
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.5168316831683168,
+      "eval_loss": 0.17515264451503754,
+      "eval_runtime": 14.2891,
+      "eval_samples_per_second": 35.342,
+      "eval_steps_per_second": 1.12,
+      "step": 1485
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 0.21752449870109558,
+      "learning_rate": 3.7749050729785363e-06,
+      "loss": 0.1781,
+      "step": 1782
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.5168316831683168,
+      "eval_loss": 0.17485138773918152,
+      "eval_runtime": 13.9491,
+      "eval_samples_per_second": 36.203,
+      "eval_steps_per_second": 1.147,
+      "step": 1782
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 0.2491326630115509,
+      "learning_rate": 2.5166033819856906e-06,
+      "loss": 0.1777,
+      "step": 2079
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.5168316831683168,
+      "eval_loss": 0.17470771074295044,
+      "eval_runtime": 14.4075,
+      "eval_samples_per_second": 35.051,
+      "eval_steps_per_second": 1.111,
+      "step": 2079
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 0.5971789956092834,
+      "learning_rate": 1.2583016909928453e-06,
+      "loss": 0.1776,
+      "step": 2376
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.5168316831683168,
+      "eval_loss": 0.17442195117473602,
+      "eval_runtime": 14.8484,
+      "eval_samples_per_second": 34.011,
+      "eval_steps_per_second": 1.078,
+      "step": 2376
+    },
+    {
+      "epoch": 9.0,
+      "grad_norm": 0.2817859947681427,
+      "learning_rate": 0.0,
+      "loss": 0.1773,
+      "step": 2673
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.5168316831683168,
+      "eval_loss": 0.17444071173667908,
+      "eval_runtime": 13.7553,
+      "eval_samples_per_second": 36.713,
+      "eval_steps_per_second": 1.163,
+      "step": 2673
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2673,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 9,
+  "save_steps": 500,
+  "total_flos": 7000589548260.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.20650329892275032,
+    "learning_rate": 1.1324715218935609e-05,
+    "num_train_epochs": 9,
+    "temperature": 10
+  }
+}

run-2/checkpoint-2673/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53af5913dd7a7ac18c4af82b6aa52534a7091d8ef8c41f1056aa7fa989430b5d
+size 4984

run-3/checkpoint-297/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f5eaa751d0a490c4ac39d6bc67606acb4865d19d4cd42b2254c17f3c8ac3348
+oid sha256:76220d7fcfb19b8bac2ae99022cae216a90b830bf00b3012d8b613a63d0bf947
 size 17549312

run-3/checkpoint-297/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:09b3669108422c0eef80f30114ca29a05e28889ea350d11575b1063ab741c250
+oid sha256:2774d92a34e603acd644175167e2e31366f8af947ecea6c85f0689d20f0ae0b8
 size 35122746

run-3/checkpoint-297/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:487a9fc1fcf4ef6096e63d27b22d80ce9b473dd668f3f8e1a318bd05c48bdea1
+oid sha256:7dc0e11b8c40cbed76dc3148c9dd20b9b6423efc82e18995f762ffefe8f96c5f
 size 1064

run-3/checkpoint-297/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.500990099009901,
+  "best_metric": 0.5128712871287129,
   "best_model_checkpoint": "tiny-bert-sst2-distilled/run-3/checkpoint-297",
   "epoch": 1.0,
   "eval_steps": 500,
@@ -10,33 +10,33 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "grad_norm": 0.8068264722824097,
-      "learning_rate": 1.8960352341732743e-05,
-      "loss": 0.5426,
+      "grad_norm": 0.9984288811683655,
+      "learning_rate": 9.995670829688553e-05,
+      "loss": 0.5706,
       "step": 297
     },
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.500990099009901,
-      "eval_loss": 0.5363946557044983,
-      "eval_runtime": 55.6857,
-      "eval_samples_per_second": 9.069,
-      "eval_steps_per_second": 0.287,
+      "eval_accuracy": 0.5128712871287129,
+      "eval_loss": 0.5624967217445374,
+      "eval_runtime": 13.6049,
+      "eval_samples_per_second": 37.119,
+      "eval_steps_per_second": 1.176,
       "step": 297
     }
   ],
   "logging_steps": 500,
-  "max_steps": 2079,
+  "max_steps": 891,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 7,
+  "num_train_epochs": 3,
   "save_steps": 500,
   "total_flos": 777843283140.0,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": {
-    "alpha": 0.7228353037734928,
-    "learning_rate": 2.212041106535487e-05,
-    "num_train_epochs": 7,
-    "temperature": 7
+    "alpha": 0.7785816803005383,
+    "learning_rate": 0.0001499350624453283,
+    "num_train_epochs": 3,
+    "temperature": 16
   }
 }

run-3/checkpoint-297/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef26fd1ddbade3db0c49006d3a63755bd6dceb7ec335f1b7b6f7abcb501f62b6
+oid sha256:9decda4f5411e0ed12b24ed68c82ec0237bdb8018a369738f83b0ca5fb77d628
 size 4984

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:53af5913dd7a7ac18c4af82b6aa52534a7091d8ef8c41f1056aa7fa989430b5d
+oid sha256:9decda4f5411e0ed12b24ed68c82ec0237bdb8018a369738f83b0ca5fb77d628
 size 4984