Training in progress, epoch 1

logs/events.out.tfevents.1711290023.73e3a81c01ef.4225.19

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d661c5ed38b99f8b4a244a763de87c36f1474b5cd0bcf81a80fe9d2f64d5d43
-size 6137
+oid sha256:603a7689bf1f87344058d138ad73425068e8406d41569ef4f71420f9e859d1cc
+size 7951

logs/events.out.tfevents.1711291158.73e3a81c01ef.4225.20

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6f12a786de501f26e320208b4a843361e32a7531dd14ea6a23c45bbba0c191c
+size 5406

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db5a8f0da88c1a5d505e9818514ad26fafa73dce33f262d1578f98621ba27902
+oid sha256:486cd084a89a5552697042acc919521bc935f54fbd58f9c45867f40b67ae8c5f
 size 17549312

run-19/checkpoint-576/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-19/checkpoint-576/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87121f75bef159bbe27be0bcc46935d813567ea77a2e4d070e855a265ed1c1f0
+size 17549312

run-19/checkpoint-576/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7c2b5c31fc3113f447717cf5f9804348f7cfa8294242bbdf698680097ffda26
+size 35122746

run-19/checkpoint-576/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77649db78380b105203c3be0753a0a47e20be3ccd8ec2455a7d4db9d8ae85766
+size 14054

run-19/checkpoint-576/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5537d50cee4a10a8a51abcfa58e75986060d4f49d787b4bb8b3e25fd201d9bac
+size 1064

run-19/checkpoint-576/special_tokens_map.json

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

run-19/checkpoint-576/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-19/checkpoint-576/trainer_state.json

@@ -0,0 +1,87 @@
+{
+  "best_metric": 0.8209393346379648,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-19/checkpoint-576",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 576,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 4.367055416107178,
+      "learning_rate": 0.00018610347830365945,
+      "loss": 0.5762,
+      "step": 192
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7778864970645792,
+      "eval_f1": 0.7781036168132942,
+      "eval_loss": 0.4806343615055084,
+      "eval_mcc": 0.5557740583380701,
+      "eval_precision": 0.77734375,
+      "eval_recall": 0.7788649706457925,
+      "eval_runtime": 69.8858,
+      "eval_samples_per_second": 14.624,
+      "eval_steps_per_second": 0.458,
+      "step": 192
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 6.6895294189453125,
+      "learning_rate": 0.00012406898553577296,
+      "loss": 0.4725,
+      "step": 384
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8189823874755382,
+      "eval_f1": 0.8304307974335472,
+      "eval_loss": 0.42346441745758057,
+      "eval_mcc": 0.6438615171758961,
+      "eval_precision": 0.7810344827586206,
+      "eval_recall": 0.8864970645792564,
+      "eval_runtime": 67.0224,
+      "eval_samples_per_second": 15.249,
+      "eval_steps_per_second": 0.477,
+      "step": 384
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 10.282877922058105,
+      "learning_rate": 6.203449276788648e-05,
+      "loss": 0.4208,
+      "step": 576
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8209393346379648,
+      "eval_f1": 0.8325709057639525,
+      "eval_loss": 0.4079805314540863,
+      "eval_mcc": 0.6481656523622785,
+      "eval_precision": 0.781786941580756,
+      "eval_recall": 0.8904109589041096,
+      "eval_runtime": 66.8138,
+      "eval_samples_per_second": 15.296,
+      "eval_steps_per_second": 0.479,
+      "step": 576
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 768,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 707085591840.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.9975127064980498,
+    "learning_rate": 0.00024813797107154593,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 16,
+    "temperature": 45
+  }
+}

run-19/checkpoint-576/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81ee653df3ea16a1b2bbfdcd97a7977653aab8c01cd99bc68896f565fbf95c0c
+size 4984

run-19/checkpoint-768/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-19/checkpoint-768/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2a2d60412db7e20e91e1fc8d550218b38ce4766928c2eb6f53f47a2a65c52fc
+size 17549312

run-19/checkpoint-768/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea30dd0dc6e9683003197da54d525b5dd79c146e7a53885c3e053d36ca74ed78
+size 35122746

run-19/checkpoint-768/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ed72394efd052c27a025cbbb902950bb9336778a32545e8b891d3c9c80c35d9
+size 14054

run-19/checkpoint-768/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27a9903e7d6ca76eddaabd92d4e680c72589dc423857c218da3fa6e593dd47f3
+size 1064

run-19/checkpoint-768/special_tokens_map.json

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

run-19/checkpoint-768/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-19/checkpoint-768/trainer_state.json

@@ -0,0 +1,107 @@
+{
+  "best_metric": 0.8297455968688845,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-19/checkpoint-768",
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 768,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 4.367055416107178,
+      "learning_rate": 0.00018610347830365945,
+      "loss": 0.5762,
+      "step": 192
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7778864970645792,
+      "eval_f1": 0.7781036168132942,
+      "eval_loss": 0.4806343615055084,
+      "eval_mcc": 0.5557740583380701,
+      "eval_precision": 0.77734375,
+      "eval_recall": 0.7788649706457925,
+      "eval_runtime": 69.8858,
+      "eval_samples_per_second": 14.624,
+      "eval_steps_per_second": 0.458,
+      "step": 192
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 6.6895294189453125,
+      "learning_rate": 0.00012406898553577296,
+      "loss": 0.4725,
+      "step": 384
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8189823874755382,
+      "eval_f1": 0.8304307974335472,
+      "eval_loss": 0.42346441745758057,
+      "eval_mcc": 0.6438615171758961,
+      "eval_precision": 0.7810344827586206,
+      "eval_recall": 0.8864970645792564,
+      "eval_runtime": 67.0224,
+      "eval_samples_per_second": 15.249,
+      "eval_steps_per_second": 0.477,
+      "step": 384
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 10.282877922058105,
+      "learning_rate": 6.203449276788648e-05,
+      "loss": 0.4208,
+      "step": 576
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8209393346379648,
+      "eval_f1": 0.8325709057639525,
+      "eval_loss": 0.4079805314540863,
+      "eval_mcc": 0.6481656523622785,
+      "eval_precision": 0.781786941580756,
+      "eval_recall": 0.8904109589041096,
+      "eval_runtime": 66.8138,
+      "eval_samples_per_second": 15.296,
+      "eval_steps_per_second": 0.479,
+      "step": 576
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 4.1248297691345215,
+      "learning_rate": 0.0,
+      "loss": 0.3917,
+      "step": 768
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8297455968688845,
+      "eval_f1": 0.8418181818181818,
+      "eval_loss": 0.407410204410553,
+      "eval_mcc": 0.6673110329610854,
+      "eval_precision": 0.7860780984719864,
+      "eval_recall": 0.9060665362035225,
+      "eval_runtime": 66.7713,
+      "eval_samples_per_second": 15.306,
+      "eval_steps_per_second": 0.479,
+      "step": 768
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 768,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 942780789120.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.9975127064980498,
+    "learning_rate": 0.00024813797107154593,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 16,
+    "temperature": 45
+  }
+}

run-19/checkpoint-768/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81ee653df3ea16a1b2bbfdcd97a7977653aab8c01cd99bc68896f565fbf95c0c
+size 4984

run-20/checkpoint-192/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-20/checkpoint-192/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:209127b9070b40d5d9a05283bd1fbbf2e5898e248a0c2af43a736572d1174533
+oid sha256:486cd084a89a5552697042acc919521bc935f54fbd58f9c45867f40b67ae8c5f
 size 17549312

run-20/checkpoint-192/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:54af01f41587a8372ae059608690e373c4cce641e2562fbd5757fe130b52ddb8
+oid sha256:b1ddd581f8739a0e5f6112615dee174489663d6ea8c13e4bb32372addedb1025
 size 35122746

run-20/checkpoint-192/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d267b33c0df8c744bb62ca8fc0e243d0ddded8c46ea62639c56f51d1dc7a548
+oid sha256:ee09ea0d216727b799a80771850b95d7d61b646360702c64b2ec889cdc725399
 size 14054

run-20/checkpoint-192/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:21a205a4cfbee85a4201f9150903db3f7783bb70c6604b622c636e9fb910cc7d
+oid sha256:781956dff95a3ca374f5637193e9253f73a0ce163bd5ac055aa3229c57635035
 size 1064

run-20/checkpoint-192/trainer_state.json

@@ -1,7 +1,7 @@
 {
-  "best_metric": 0.8317025440313112,
+  "best_metric": 0.7906066536203522,
   "best_model_checkpoint": "tiny-bert-sst2-distilled/run-20/checkpoint-192",
-  "epoch": 4.0,
+  "epoch": 1.0,
   "eval_steps": 500,
   "global_step": 192,
   "is_hyper_param_search": true,
@@ -10,93 +10,38 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "grad_norm": 1.930127739906311,
-      "learning_rate": 0.00038924925342110863,
-      "loss": 0.5828,
-      "step": 48
-    },
-    {
-      "epoch": 1.0,
-      "eval_accuracy": 0.7553816046966731,
-      "eval_f1": 0.7967479674796748,
-      "eval_loss": 0.4942302703857422,
-      "eval_precision": 0.6815020862308763,
-      "eval_recall": 0.958904109589041,
-      "eval_runtime": 27.5665,
-      "eval_samples_per_second": 37.074,
-      "eval_steps_per_second": 0.58,
-      "step": 48
-    },
-    {
-      "epoch": 2.0,
-      "grad_norm": 4.047781944274902,
-      "learning_rate": 0.0002594995022807391,
-      "loss": 0.4792,
-      "step": 96
-    },
-    {
-      "epoch": 2.0,
-      "eval_accuracy": 0.8170254403131115,
-      "eval_f1": 0.8270120259019426,
-      "eval_loss": 0.4411511719226837,
-      "eval_precision": 0.7842105263157895,
-      "eval_recall": 0.8747553816046967,
-      "eval_runtime": 27.2029,
-      "eval_samples_per_second": 37.57,
-      "eval_steps_per_second": 0.588,
-      "step": 96
-    },
-    {
-      "epoch": 3.0,
-      "grad_norm": 3.387861967086792,
-      "learning_rate": 0.00012974975114036954,
-      "loss": 0.425,
-      "step": 144
-    },
-    {
-      "epoch": 3.0,
-      "eval_accuracy": 0.8209393346379648,
-      "eval_f1": 0.8278457196613358,
-      "eval_loss": 0.4288911819458008,
-      "eval_precision": 0.7971014492753623,
-      "eval_recall": 0.8610567514677103,
-      "eval_runtime": 28.248,
-      "eval_samples_per_second": 36.18,
-      "eval_steps_per_second": 0.566,
-      "step": 144
-    },
-    {
-      "epoch": 4.0,
-      "grad_norm": 3.795287847518921,
-      "learning_rate": 0.0,
-      "loss": 0.4056,
+      "grad_norm": 11.2067289352417,
+      "learning_rate": 0.00015355053489920167,
+      "loss": 0.5758,
       "step": 192
     },
     {
-      "epoch": 4.0,
-      "eval_accuracy": 0.8317025440313112,
-      "eval_f1": 0.8424908424908425,
-      "eval_loss": 0.4076713025569916,
-      "eval_precision": 0.7917383820998278,
-      "eval_recall": 0.9001956947162426,
-      "eval_runtime": 27.8879,
-      "eval_samples_per_second": 36.647,
-      "eval_steps_per_second": 0.574,
+      "epoch": 1.0,
+      "eval_accuracy": 0.7906066536203522,
+      "eval_f1": 0.7938342967244701,
+      "eval_loss": 0.4803670346736908,
+      "eval_mcc": 0.5814984242947744,
+      "eval_precision": 0.7817836812144212,
+      "eval_recall": 0.8062622309197651,
+      "eval_runtime": 66.3514,
+      "eval_samples_per_second": 15.403,
+      "eval_steps_per_second": 0.482,
       "step": 192
     }
   ],
   "logging_steps": 500,
-  "max_steps": 192,
+  "max_steps": 576,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 4,
+  "num_train_epochs": 3,
   "save_steps": 500,
-  "total_flos": 942780789120.0,
-  "train_batch_size": 64,
+  "total_flos": 235695197280.0,
+  "train_batch_size": 16,
   "trial_name": null,
   "trial_params": {
-    "alpha": 0.9873470402997029,
-    "learning_rate": 0.0005189990045614782,
-    "num_train_epochs": 4,
-    "temperature": 29
+    "alpha": 0.9932487320274002,
+    "learning_rate": 0.0002303258023488025,
+    "num_train_epochs": 3,
+    "per_device_train_batch_size": 16,
+    "temperature": 12
   }
 }

run-20/checkpoint-192/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:86ccdfa005aaa3037171e63b21106648822be6f97ddb8788a88937d2ac56456c
-size 4920
+oid sha256:7b0e429bbec35e18af3a3ef82e1dc022e68f0667714aa60a534134cce36648d2
+size 4984

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f62d580257060cdaf08ca2f6bebff447fe36fd6a4ed09c360f3a936d71824ec
-size 4920
+oid sha256:7b0e429bbec35e18af3a3ef82e1dc022e68f0667714aa60a534134cce36648d2
+size 4984