Training in progress, epoch 1

logs/events.out.tfevents.1711265653.73e3a81c01ef.4225.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de2dbc4a46dedb66ca18a4084f06ef7d814451bb56e6f5ec8f784252448c5cd6
-size 6137
+oid sha256:7409308422d11460594d156ee4373d70b235f994d1473771161bb3299c88bd96
+size 12331

logs/events.out.tfevents.1711268522.73e3a81c01ef.4225.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99ceb99c83a28303dc0707086ba59041ed6cfb94bbc378d22d39503b81d5ba07
+size 5407

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d900e4f6cb14316af78ee923303ad84861c097630cd22630ae781e3dd5558d9
+oid sha256:a2d4121a32bc2cf425af53a9c9bfb122ad0023ed687f7c582052bbf48bd2b911
 size 17549312

run-0/checkpoint-1344/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-0/checkpoint-1344/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e691cdcba7783035f8cc0069fb1e90f7ac6a33065f0f4383af4d65200a0f0c5
+size 17549312

run-0/checkpoint-1344/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:775397efe6bbcacea3c68998d8f2f5576617461a26b3d51cac2d6acf7dbac78c
+size 35122746

run-0/checkpoint-1344/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5daa194f252973a6e638902bc960b7e07ea23884d291e0a3c2a48ccf865c60f8
+size 14054

run-0/checkpoint-1344/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0c5c54b5654619aac21175d8f8dc1316befd335f466ddee7e8bb788138b4537
+size 1064

run-0/checkpoint-1344/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-1344/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-1344/trainer_state.json

@@ -0,0 +1,167 @@
+{
+  "best_metric": 0.8131115459882583,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-0/checkpoint-1344",
+  "epoch": 7.0,
+  "eval_steps": 500,
+  "global_step": 1344,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.7846055030822754,
+      "learning_rate": 4.610177667546352e-05,
+      "loss": 0.4587,
+      "step": 192
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6976516634050881,
+      "eval_f1": 0.6419466975666281,
+      "eval_loss": 0.4008609354496002,
+      "eval_mcc": 0.41595144404027,
+      "eval_precision": 0.7869318181818182,
+      "eval_recall": 0.5420743639921722,
+      "eval_runtime": 66.5688,
+      "eval_samples_per_second": 15.353,
+      "eval_steps_per_second": 0.481,
+      "step": 192
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 6.001947402954102,
+      "learning_rate": 4.0979357044856464e-05,
+      "loss": 0.4016,
+      "step": 384
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7181996086105675,
+      "eval_f1": 0.6778523489932886,
+      "eval_loss": 0.3820359408855438,
+      "eval_mcc": 0.4507700437564526,
+      "eval_precision": 0.7911227154046997,
+      "eval_recall": 0.5929549902152642,
+      "eval_runtime": 66.6005,
+      "eval_samples_per_second": 15.345,
+      "eval_steps_per_second": 0.48,
+      "step": 384
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 2.8345351219177246,
+      "learning_rate": 3.5856937414249405e-05,
+      "loss": 0.3879,
+      "step": 576
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8062622309197651,
+      "eval_f1": 0.8159851301115242,
+      "eval_loss": 0.37824752926826477,
+      "eval_mcc": 0.6159734786715062,
+      "eval_precision": 0.7769911504424779,
+      "eval_recall": 0.8590998043052838,
+      "eval_runtime": 66.7443,
+      "eval_samples_per_second": 15.312,
+      "eval_steps_per_second": 0.479,
+      "step": 576
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 2.9280295372009277,
+      "learning_rate": 3.0734517783642345e-05,
+      "loss": 0.3803,
+      "step": 768
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.7681017612524462,
+      "eval_f1": 0.7569230769230769,
+      "eval_loss": 0.37255340814590454,
+      "eval_mcc": 0.5384860699767601,
+      "eval_precision": 0.7952586206896551,
+      "eval_recall": 0.7221135029354208,
+      "eval_runtime": 67.0029,
+      "eval_samples_per_second": 15.253,
+      "eval_steps_per_second": 0.478,
+      "step": 768
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 3.7051830291748047,
+      "learning_rate": 2.561209815303529e-05,
+      "loss": 0.3773,
+      "step": 960
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.7964774951076321,
+      "eval_f1": 0.7932405566600398,
+      "eval_loss": 0.3688918650150299,
+      "eval_mcc": 0.5932458672098203,
+      "eval_precision": 0.806060606060606,
+      "eval_recall": 0.7808219178082192,
+      "eval_runtime": 68.0849,
+      "eval_samples_per_second": 15.011,
+      "eval_steps_per_second": 0.47,
+      "step": 960
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 3.5727412700653076,
+      "learning_rate": 2.0489678522428232e-05,
+      "loss": 0.3741,
+      "step": 1152
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.8101761252446184,
+      "eval_f1": 0.8197026022304833,
+      "eval_loss": 0.37157630920410156,
+      "eval_mcc": 0.623845344213634,
+      "eval_precision": 0.7805309734513274,
+      "eval_recall": 0.863013698630137,
+      "eval_runtime": 66.833,
+      "eval_samples_per_second": 15.292,
+      "eval_steps_per_second": 0.479,
+      "step": 1152
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 1.87214994430542,
+      "learning_rate": 1.5367258891821172e-05,
+      "loss": 0.3712,
+      "step": 1344
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.8131115459882583,
+      "eval_f1": 0.8203198494825964,
+      "eval_loss": 0.3685600161552429,
+      "eval_mcc": 0.6282485725306769,
+      "eval_precision": 0.7898550724637681,
+      "eval_recall": 0.8532289628180039,
+      "eval_runtime": 66.8069,
+      "eval_samples_per_second": 15.298,
+      "eval_steps_per_second": 0.479,
+      "step": 1344
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1920,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "total_flos": 1649866380960.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.6226480553446316,
+    "learning_rate": 5.122419630607058e-05,
+    "num_train_epochs": 10,
+    "per_device_train_batch_size": 16,
+    "temperature": 20
+  }
+}

run-0/checkpoint-1344/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dbca9cde0b156ba25d74ee6bc6ea4c2fa160afa3570e75ccc73231ac4a159c49
+size 4984

run-0/checkpoint-1920/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-0/checkpoint-1920/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca16dbcf1236e0615593f8729995a67bca8847b7e16e7cee9d770bd9e92839a4
+size 17549312

run-0/checkpoint-1920/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b43f7dc390624b86b0ab21c291a47845779f47082f3718af49954f87c445c37c
+size 35122746

run-0/checkpoint-1920/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6576731312903deffac513ce0e8c9b73d5d1c5e3728c00236425dd8af27824a
+size 14054

run-0/checkpoint-1920/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:464651b4180ef27ea97ca068dc100690a46502a06ba30eff69feffb22ac8105f
+size 1064

run-0/checkpoint-1920/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-1920/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-1920/trainer_state.json

@@ -0,0 +1,227 @@
+{
+  "best_metric": 0.8131115459882583,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-0/checkpoint-1344",
+  "epoch": 10.0,
+  "eval_steps": 500,
+  "global_step": 1920,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.7846055030822754,
+      "learning_rate": 4.610177667546352e-05,
+      "loss": 0.4587,
+      "step": 192
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6976516634050881,
+      "eval_f1": 0.6419466975666281,
+      "eval_loss": 0.4008609354496002,
+      "eval_mcc": 0.41595144404027,
+      "eval_precision": 0.7869318181818182,
+      "eval_recall": 0.5420743639921722,
+      "eval_runtime": 66.5688,
+      "eval_samples_per_second": 15.353,
+      "eval_steps_per_second": 0.481,
+      "step": 192
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 6.001947402954102,
+      "learning_rate": 4.0979357044856464e-05,
+      "loss": 0.4016,
+      "step": 384
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7181996086105675,
+      "eval_f1": 0.6778523489932886,
+      "eval_loss": 0.3820359408855438,
+      "eval_mcc": 0.4507700437564526,
+      "eval_precision": 0.7911227154046997,
+      "eval_recall": 0.5929549902152642,
+      "eval_runtime": 66.6005,
+      "eval_samples_per_second": 15.345,
+      "eval_steps_per_second": 0.48,
+      "step": 384
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 2.8345351219177246,
+      "learning_rate": 3.5856937414249405e-05,
+      "loss": 0.3879,
+      "step": 576
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8062622309197651,
+      "eval_f1": 0.8159851301115242,
+      "eval_loss": 0.37824752926826477,
+      "eval_mcc": 0.6159734786715062,
+      "eval_precision": 0.7769911504424779,
+      "eval_recall": 0.8590998043052838,
+      "eval_runtime": 66.7443,
+      "eval_samples_per_second": 15.312,
+      "eval_steps_per_second": 0.479,
+      "step": 576
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 2.9280295372009277,
+      "learning_rate": 3.0734517783642345e-05,
+      "loss": 0.3803,
+      "step": 768
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.7681017612524462,
+      "eval_f1": 0.7569230769230769,
+      "eval_loss": 0.37255340814590454,
+      "eval_mcc": 0.5384860699767601,
+      "eval_precision": 0.7952586206896551,
+      "eval_recall": 0.7221135029354208,
+      "eval_runtime": 67.0029,
+      "eval_samples_per_second": 15.253,
+      "eval_steps_per_second": 0.478,
+      "step": 768
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 3.7051830291748047,
+      "learning_rate": 2.561209815303529e-05,
+      "loss": 0.3773,
+      "step": 960
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.7964774951076321,
+      "eval_f1": 0.7932405566600398,
+      "eval_loss": 0.3688918650150299,
+      "eval_mcc": 0.5932458672098203,
+      "eval_precision": 0.806060606060606,
+      "eval_recall": 0.7808219178082192,
+      "eval_runtime": 68.0849,
+      "eval_samples_per_second": 15.011,
+      "eval_steps_per_second": 0.47,
+      "step": 960
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 3.5727412700653076,
+      "learning_rate": 2.0489678522428232e-05,
+      "loss": 0.3741,
+      "step": 1152
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.8101761252446184,
+      "eval_f1": 0.8197026022304833,
+      "eval_loss": 0.37157630920410156,
+      "eval_mcc": 0.623845344213634,
+      "eval_precision": 0.7805309734513274,
+      "eval_recall": 0.863013698630137,
+      "eval_runtime": 66.833,
+      "eval_samples_per_second": 15.292,
+      "eval_steps_per_second": 0.479,
+      "step": 1152
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 1.87214994430542,
+      "learning_rate": 1.5367258891821172e-05,
+      "loss": 0.3712,
+      "step": 1344
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.8131115459882583,
+      "eval_f1": 0.8203198494825964,
+      "eval_loss": 0.3685600161552429,
+      "eval_mcc": 0.6282485725306769,
+      "eval_precision": 0.7898550724637681,
+      "eval_recall": 0.8532289628180039,
+      "eval_runtime": 66.8069,
+      "eval_samples_per_second": 15.298,
+      "eval_steps_per_second": 0.479,
+      "step": 1344
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 2.601350784301758,
+      "learning_rate": 1.0244839261214116e-05,
+      "loss": 0.3667,
+      "step": 1536
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.8091976516634051,
+      "eval_f1": 0.8179271708683473,
+      "eval_loss": 0.36975762248039246,
+      "eval_mcc": 0.6212581246070178,
+      "eval_precision": 0.7821428571428571,
+      "eval_recall": 0.8571428571428571,
+      "eval_runtime": 67.182,
+      "eval_samples_per_second": 15.212,
+      "eval_steps_per_second": 0.476,
+      "step": 1536
+    },
+    {
+      "epoch": 9.0,
+      "grad_norm": 1.19636869430542,
+      "learning_rate": 5.122419630607058e-06,
+      "loss": 0.3678,
+      "step": 1728
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.8062622309197651,
+      "eval_f1": 0.8062622309197651,
+      "eval_loss": 0.36616405844688416,
+      "eval_mcc": 0.6125244618395304,
+      "eval_precision": 0.8062622309197651,
+      "eval_recall": 0.8062622309197651,
+      "eval_runtime": 67.13,
+      "eval_samples_per_second": 15.224,
+      "eval_steps_per_second": 0.477,
+      "step": 1728
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 3.5874884128570557,
+      "learning_rate": 0.0,
+      "loss": 0.3677,
+      "step": 1920
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.8052837573385518,
+      "eval_f1": 0.8069835111542193,
+      "eval_loss": 0.3663344383239746,
+      "eval_mcc": 0.610662236046953,
+      "eval_precision": 0.8,
+      "eval_recall": 0.8140900195694716,
+      "eval_runtime": 67.1725,
+      "eval_samples_per_second": 15.215,
+      "eval_steps_per_second": 0.476,
+      "step": 1920
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1920,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "total_flos": 2356951972800.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.6226480553446316,
+    "learning_rate": 5.122419630607058e-05,
+    "num_train_epochs": 10,
+    "per_device_train_batch_size": 16,
+    "temperature": 20
+  }
+}

run-0/checkpoint-1920/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dbca9cde0b156ba25d74ee6bc6ea4c2fa160afa3570e75ccc73231ac4a159c49
+size 4984

run-1/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-1/checkpoint-192/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:691fe6dae22dbcf425f6968004894acb3404da27e32c1c6aaa864221b6e71a6b
+oid sha256:a2d4121a32bc2cf425af53a9c9bfb122ad0023ed687f7c582052bbf48bd2b911
 size 17549312

run-1/checkpoint-192/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a934e87408b233a8ea983945295f058bd23167055b3f8990bfd1682daa969cc9
+oid sha256:4a877815117eebed35759688972ae6fc35916c174c7a68ccdd92cfb11e2cd195
 size 35122746

run-1/checkpoint-192/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c58c0607d97c986e9d4c30b0aa74b33350e0c7e86978aaaaadda4ebb78f21ad
+oid sha256:ee09ea0d216727b799a80771850b95d7d61b646360702c64b2ec889cdc725399
 size 14054

run-1/checkpoint-192/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b3d1ec3eff6c7b0aaaccde3d1da3e3c2d398ec546ecd0a5fb3c9941dfe4127dd
+oid sha256:8d9ef37db26d27622d6db080bb379467a4784368a9bbf32af8344393044af9a9
 size 1064

run-1/checkpoint-192/trainer_state.json

@@ -1,7 +1,7 @@
 {
-  "best_metric": 0.5,
-  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-1/checkpoint-96",
-  "epoch": 2.0,
+  "best_metric": 0.7925636007827789,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-1/checkpoint-192",
+  "epoch": 1.0,
   "eval_steps": 500,
   "global_step": 192,
   "is_hyper_param_search": true,
@@ -10,55 +10,38 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "grad_norm": 0.40490686893463135,
-      "learning_rate": 1.4953262133881219e-05,
-      "loss": 0.1703,
-      "step": 96
-    },
-    {
-      "epoch": 1.0,
-      "eval_accuracy": 0.5,
-      "eval_f1": 0.0,
-      "eval_loss": 0.11485283076763153,
-      "eval_precision": 0.0,
-      "eval_recall": 0.0,
-      "eval_runtime": 25.7126,
-      "eval_samples_per_second": 39.747,
-      "eval_steps_per_second": 1.245,
-      "step": 96
-    },
-    {
-      "epoch": 2.0,
-      "grad_norm": 0.2503454089164734,
-      "learning_rate": 1.2817081829041045e-05,
-      "loss": 0.1095,
+      "grad_norm": 0.8947777152061462,
+      "learning_rate": 0.0005181908296523575,
+      "loss": 0.4457,
       "step": 192
     },
     {
-      "epoch": 2.0,
-      "eval_accuracy": 0.5,
-      "eval_f1": 0.0038986354775828462,
-      "eval_loss": 0.0978715717792511,
-      "eval_precision": 0.5,
-      "eval_recall": 0.0019569471624266144,
-      "eval_runtime": 25.921,
-      "eval_samples_per_second": 39.427,
-      "eval_steps_per_second": 1.235,
+      "epoch": 1.0,
+      "eval_accuracy": 0.7925636007827789,
+      "eval_f1": 0.8090090090090091,
+      "eval_loss": 0.41997030377388,
+      "eval_mcc": 0.59400157079309,
+      "eval_precision": 0.7495826377295493,
+      "eval_recall": 0.8786692759295499,
+      "eval_runtime": 66.1643,
+      "eval_samples_per_second": 15.446,
+      "eval_steps_per_second": 0.484,
       "step": 192
     }
   ],
   "logging_steps": 500,
-  "max_steps": 768,
+  "max_steps": 1920,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 8,
+  "num_train_epochs": 10,
   "save_steps": 500,
-  "total_flos": 471390394560.0,
-  "train_batch_size": 32,
+  "total_flos": 235695197280.0,
+  "train_batch_size": 16,
   "trial_name": null,
   "trial_params": {
-    "alpha": 0.09656764013507046,
-    "learning_rate": 1.7089442438721394e-05,
-    "num_train_epochs": 8,
-    "temperature": 20
+    "alpha": 0.6664545915670365,
+    "learning_rate": 0.0005757675885026195,
+    "num_train_epochs": 10,
+    "per_device_train_batch_size": 16,
+    "temperature": 37
   }
 }

run-1/checkpoint-192/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:40c83b924ef70318ad972d6c481c684f04bf59974ceae562e8816ac4c289de55
-size 4920
+oid sha256:1a9fe6e98582646cabde3e8596aaf7d6306e98b72fcfb66153c430972f11d98c
+size 4984

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dbca9cde0b156ba25d74ee6bc6ea4c2fa160afa3570e75ccc73231ac4a159c49
+oid sha256:1a9fe6e98582646cabde3e8596aaf7d6306e98b72fcfb66153c430972f11d98c
 size 4984