Training in progress, epoch 1

logs/events.out.tfevents.1709741585.1dcff7455174.7719.8

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:19c9bc913b8fa6bedf0b30430ed5a1abf15a6d23edfe4ededfc8f0f27caf3bd0
-size 5997
+oid sha256:f8e25f485f8bfd1004279e478e99c9038fd1c5a6d72cf50c9e73f520c8dc4f3d
+size 7363

logs/events.out.tfevents.1709741985.1dcff7455174.7719.9

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9917e0c11b3351b5ac3e4e0f9882c40e0544f3349c6b4fb2c43984f8cae832f
+size 5314

logs/events.out.tfevents.1709742084.1dcff7455174.7719.10

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07df09268f614c779ab99aeb721d58f2515a0570e168044f8447e0d08c9ce32d
+size 5315

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:86ff6db7c240bd772007d6c5e4992ba94e87ffe11a765944450a10be3f0a616c
+oid sha256:8d8853ef567f2ad2c26f3acedb2053492b0ba55673cd6330f1d48737fe000db7
 size 17549312

run-10/checkpoint-96/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e79087651dbe07597bcc519c0603106d4238d761309189dc1d8c49bbe9fbdd0
+oid sha256:8d8853ef567f2ad2c26f3acedb2053492b0ba55673cd6330f1d48737fe000db7
 size 17549312

run-10/checkpoint-96/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3771f7ce5a1e746e27d5b4f30b62b81054ea67cf657063408de78b4fac6385f5
+oid sha256:153954f49b9fa650cbe4f1b4a7ef3427e06f73c0a09d5ead3142daf3caed9def
 size 35122746

run-10/checkpoint-96/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35ad384a49732bbba66f365d68a02bf664cf1489238a42c775ec81b19b0b82fa
+oid sha256:cda17b0ef9e04e1234e3c9c4ab2b57b417935ba5084b708100bc14292d32cacc
 size 1064

run-10/checkpoint-96/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.7524461839530333,
+  "best_metric": 0.7837573385518591,
   "best_model_checkpoint": "tiny-bert-sst2-distilled/run-10/checkpoint-96",
   "epoch": 1.0,
   "eval_steps": 500,
@@ -10,21 +10,21 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "grad_norm": 2.535670757293701,
-      "learning_rate": 0.00048723007690763744,
-      "loss": 0.5767,
+      "grad_norm": 4.513129711151123,
+      "learning_rate": 0.00015497977730708463,
+      "loss": 0.5754,
       "step": 96
     },
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.7524461839530333,
-      "eval_f1": 0.7924528301886793,
-      "eval_loss": 0.4912106394767761,
-      "eval_precision": 0.6822033898305084,
-      "eval_recall": 0.9452054794520548,
-      "eval_runtime": 30.3562,
-      "eval_samples_per_second": 33.667,
-      "eval_steps_per_second": 1.054,
+      "eval_accuracy": 0.7837573385518591,
+      "eval_f1": 0.8122344944774851,
+      "eval_loss": 0.46778297424316406,
+      "eval_precision": 0.7177177177177178,
+      "eval_recall": 0.9354207436399217,
+      "eval_runtime": 24.9847,
+      "eval_samples_per_second": 40.905,
+      "eval_steps_per_second": 1.281,
       "step": 96
     }
   ],
@@ -37,9 +37,9 @@
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": {
-    "alpha": 0.964566953098255,
-    "learning_rate": 0.0009744601538152749,
+    "alpha": 0.9845885728988275,
+    "learning_rate": 0.00030995955461416927,
     "num_train_epochs": 2,
-    "temperature": 30
+    "temperature": 12
   }
 }

run-10/checkpoint-96/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b603cc11f59a882aaaffb8f9536f958187e41d9698ff3658445388c161757421
+oid sha256:1e0410bd8454c69a478d22b3efe1cb60edac0a98159c2117907a0cab3dda5d19
 size 4920

run-8/checkpoint-288/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-8/checkpoint-288/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f411103f9abbef0a3873a885c570d9f1b3e62951332b3a650b531d39e546c2b
+size 17549312

run-8/checkpoint-288/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:020b79004a05e9f5912ccde55b6555affa30e1a69a235dc7e4b042109275e8e4
+size 35122746

run-8/checkpoint-288/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba3c2bb1d96a39a28ae1b66f234e351e3c13c700fc97347efd6308798b151790
+size 14054

run-8/checkpoint-288/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ee19976bffe7779cff0dcba9b701ef8e1bfad6e14f31f2a315ae588aea085e1
+size 1064

run-8/checkpoint-288/special_tokens_map.json

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

run-8/checkpoint-288/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-8/checkpoint-288/trainer_state.json

@@ -0,0 +1,83 @@
+{
+  "best_metric": 0.761252446183953,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-8/checkpoint-288",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 288,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.6551002860069275,
+      "learning_rate": 6.801658733829082e-05,
+      "loss": 0.4365,
+      "step": 96
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.662426614481409,
+      "eval_f1": 0.558258642765685,
+      "eval_loss": 0.3849833011627197,
+      "eval_precision": 0.8074074074074075,
+      "eval_recall": 0.42661448140900193,
+      "eval_runtime": 25.2796,
+      "eval_samples_per_second": 40.428,
+      "eval_steps_per_second": 1.266,
+      "step": 96
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.109588384628296,
+      "learning_rate": 5.9514513921004466e-05,
+      "loss": 0.3828,
+      "step": 192
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7045009784735812,
+      "eval_f1": 0.6544622425629291,
+      "eval_loss": 0.3611763119697571,
+      "eval_precision": 0.7878787878787878,
+      "eval_recall": 0.5596868884540117,
+      "eval_runtime": 25.4122,
+      "eval_samples_per_second": 40.217,
+      "eval_steps_per_second": 1.259,
+      "step": 192
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 1.4850609302520752,
+      "learning_rate": 5.101244050371811e-05,
+      "loss": 0.3691,
+      "step": 288
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.761252446183953,
+      "eval_f1": 0.7525354969574035,
+      "eval_loss": 0.35745102167129517,
+      "eval_precision": 0.7810526315789473,
+      "eval_recall": 0.726027397260274,
+      "eval_runtime": 25.6214,
+      "eval_samples_per_second": 39.889,
+      "eval_steps_per_second": 1.249,
+      "step": 288
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 864,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 9,
+  "save_steps": 500,
+  "total_flos": 707085591840.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.5720238366992816,
+    "learning_rate": 7.651866075557717e-05,
+    "num_train_epochs": 9,
+    "temperature": 25
+  }
+}

run-8/checkpoint-288/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57c01c47cfb7f7d8530acb1f2f7c1e65992d8943357bd77df5af6cdccc8074cf
+size 4920

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc3160888fc83e22e4969d14bdc1e1ab59cf563521f038a2cd8ce1deb5244204
+oid sha256:1e0410bd8454c69a478d22b3efe1cb60edac0a98159c2117907a0cab3dda5d19
 size 4920