Training in progress, epoch 1

logs/events.out.tfevents.1709699573.a2333cf40ebd.21010.10

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:74a80c0d3ab62a0fa626e8b75d0139975fbfc23c421938b426ea598551984455
-size 5314
+oid sha256:691e4e36a980bb0f161aa236a92896d33e5e395c8d850ea8559e2087628dc7af
+size 6351

logs/events.out.tfevents.1709699817.a2333cf40ebd.21010.11

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae777abbdf7a5d754696fbf31b20722f9af071ae847d4a1e3c41ade546551d2a
+size 5314

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26d6c85c4ceec4a9a3fb6856efcb1766f01d5e299ee63335f6b44ebb0dcb903b
+oid sha256:136877ee651c62ba812d0f99f96161f0f3ecf647b0689286df48d749d4976c6b
 size 17549312

run-10/checkpoint-192/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8218b0b49358a4f2c91ebc8c843961cecc26366dde2821fd7b7fcdb07a6f52db
+oid sha256:922deef942c3aaef3de0ceeee840acb1cb8e44cd603d4c22ccbd1439fed6d234
 size 17549312

run-10/checkpoint-192/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60cc74a23a3dca814a6e6dc4b91f9d9e9e5f067c9b46395a12259a7a57ccf5fa
+oid sha256:64bb182718f00fd3667d57c0ca14bb29f0a7c9bb1d9b8ff93a41dd5d60195655
 size 35122746

run-10/checkpoint-192/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:289123c16907c5b1f306770de8e3858f3c794d2c2c173b5931335d4f72bfe74e
+oid sha256:2561b76476c8b2b523cb705d3cd5aab66e705c29f938b9ce833590caedcf6005
 size 1064

run-10/checkpoint-192/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.824853228962818,
+  "best_metric": 0.7720156555772995,
   "best_model_checkpoint": "tiny-bert-sst2-distilled/run-10/checkpoint-192",
   "epoch": 2.0,
   "eval_steps": 500,
@@ -10,55 +10,55 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "grad_norm": 1.9170680046081543,
-      "learning_rate": 0.0005212663608648181,
-      "loss": 0.5641,
+      "grad_norm": 2.535670757293701,
+      "learning_rate": 0.00048723007690763744,
+      "loss": 0.5767,
       "step": 96
     },
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.799412915851272,
-      "eval_f1": 0.8197009674582234,
-      "eval_loss": 0.47259676456451416,
-      "eval_precision": 0.744408945686901,
-      "eval_recall": 0.9119373776908023,
-      "eval_runtime": 30.8424,
-      "eval_samples_per_second": 33.136,
-      "eval_steps_per_second": 1.038,
+      "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,
       "step": 96
     },
     {
       "epoch": 2.0,
-      "grad_norm": 2.4848690032958984,
-      "learning_rate": 0.00026063318043240905,
-      "loss": 0.456,
+      "grad_norm": 3.952514171600342,
+      "learning_rate": 0.0,
+      "loss": 0.4909,
       "step": 192
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.824853228962818,
-      "eval_f1": 0.8406055209260909,
-      "eval_loss": 0.4349122643470764,
-      "eval_precision": 0.7712418300653595,
-      "eval_recall": 0.923679060665362,
-      "eval_runtime": 31.1515,
-      "eval_samples_per_second": 32.807,
-      "eval_steps_per_second": 1.027,
+      "eval_accuracy": 0.7720156555772995,
+      "eval_f1": 0.8006843455945253,
+      "eval_loss": 0.46037518978118896,
+      "eval_precision": 0.7112462006079028,
+      "eval_recall": 0.9158512720156555,
+      "eval_runtime": 30.68,
+      "eval_samples_per_second": 33.312,
+      "eval_steps_per_second": 1.043,
       "step": 192
     }
   ],
   "logging_steps": 500,
-  "max_steps": 288,
+  "max_steps": 192,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 3,
+  "num_train_epochs": 2,
   "save_steps": 500,
   "total_flos": 471390394560.0,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": {
-    "alpha": 0.9610512963031814,
-    "learning_rate": 0.0007818995412972273,
-    "num_train_epochs": 3,
-    "temperature": 24
+    "alpha": 0.964566953098255,
+    "learning_rate": 0.0009744601538152749,
+    "num_train_epochs": 2,
+    "temperature": 30
   }
 }

run-10/checkpoint-192/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c48cb920a64a7322ad1d6d741321a643be4ed10af970a24a154150a0def2990
+oid sha256:b603cc11f59a882aaaffb8f9536f958187e41d9698ff3658445388c161757421
 size 4920

run-11/checkpoint-96/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-11/checkpoint-96/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:136877ee651c62ba812d0f99f96161f0f3ecf647b0689286df48d749d4976c6b
+size 17549312

run-11/checkpoint-96/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:161aac7bcb6524ec9d72a681761a2576fed030a34ed7d6606ea3214ed68f32ae
+size 35122746

run-11/checkpoint-96/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24aa86019b8aea1c551cc1adaf38c4db2fc01de75a22af312230f6b592e0fd81
+size 14054

run-11/checkpoint-96/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90937cac39589ae65d6cafbc79eb7a81e4c6f2ab317854f1cdbef198f243a770
+size 1064

run-11/checkpoint-96/special_tokens_map.json

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

run-11/checkpoint-96/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-11/checkpoint-96/trainer_state.json

@@ -0,0 +1,45 @@
+{
+  "best_metric": 0.7514677103718199,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-11/checkpoint-96",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 96,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 8.867341995239258,
+      "learning_rate": 0.00047267095070335774,
+      "loss": 0.5752,
+      "step": 96
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7514677103718199,
+      "eval_f1": 0.765249537892791,
+      "eval_loss": 0.501445472240448,
+      "eval_precision": 0.7250437828371279,
+      "eval_recall": 0.8101761252446184,
+      "eval_runtime": 30.0696,
+      "eval_samples_per_second": 33.988,
+      "eval_steps_per_second": 1.064,
+      "step": 96
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 192,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "total_flos": 235695197280.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.9981740599737018,
+    "learning_rate": 0.0009453419014067155,
+    "num_train_epochs": 2,
+    "temperature": 30
+  }
+}

run-11/checkpoint-96/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7ad2a3b631ed3da14471b5ac8c719b5c11baabf1e37c311322e42839c08f1d3
+size 4920

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eca285e074f5751b46e77605d55ec46cae8a3b205f294ab4811aec331d54f279
+oid sha256:e7ad2a3b631ed3da14471b5ac8c719b5c11baabf1e37c311322e42839c08f1d3
 size 4920