Training in progress, epoch 1

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05019f8debddeaf2687c7ff431130fba8edbe6091838e7e06c05ca0f50cfd770
-size 6137
+oid sha256:1925abcc8274c601132ae17f39d706664977f859d5ee72b2b6f0c3821eef1c4e
+size 12331

logs/events.out.tfevents.1711271348.73e3a81c01ef.4225.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2b97de26d61f3863b5dc528a7834184a133d16afeae8566cc9f02ea1d9d8f6f
+size 5407

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f4bd1e41228ce60e7db1f309c5021b3fb9f752fe33a5186b455f760000d0132e
+oid sha256:5b4b5dc69cb0469a967756916d6a6944e64d282b3dddd187d83bb80ec725cf81
 size 17549312

run-1/checkpoint-1728/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-1/checkpoint-1728/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2ed70f89430a26892fcb8c553676ea9b04c8af08cd61e5ec015e08484f9d87b
+size 17549312

run-1/checkpoint-1728/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75e44aa1d4c053438b6eba6bc8837fbc97b2754b15f50ffbe16aef677f0c32e1
+size 35122746

run-1/checkpoint-1728/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22ce57172701cdbf3a53fe63e803b2f4575217c8a22952e12bc858ec1ba8d4ec
+size 14054

run-1/checkpoint-1728/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba6dfba9a64dabf0423e8e64c628acbf9c5ecbacc27346381d991a602ccbb9ae
+size 1064

run-1/checkpoint-1728/special_tokens_map.json

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

run-1/checkpoint-1728/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-1/checkpoint-1728/trainer_state.json

@@ -0,0 +1,207 @@
+{
+  "best_metric": 0.8268101761252447,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-1/checkpoint-1728",
+  "epoch": 9.0,
+  "eval_steps": 500,
+  "global_step": 1728,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.8947777152061462,
+      "learning_rate": 0.0005181908296523575,
+      "loss": 0.4457,
+      "step": 192
+    },
+    {
+      "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
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.971238613128662,
+      "learning_rate": 0.0004606140708020956,
+      "loss": 0.4163,
+      "step": 384
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7915851272015656,
+      "eval_f1": 0.7957813998082454,
+      "eval_loss": 0.39958736300468445,
+      "eval_mcc": 0.5836633290639656,
+      "eval_precision": 0.7800751879699248,
+      "eval_recall": 0.812133072407045,
+      "eval_runtime": 66.5614,
+      "eval_samples_per_second": 15.354,
+      "eval_steps_per_second": 0.481,
+      "step": 384
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 2.333700656890869,
+      "learning_rate": 0.00040303731195183364,
+      "loss": 0.4018,
+      "step": 576
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7915851272015656,
+      "eval_f1": 0.7909715407262021,
+      "eval_loss": 0.40145382285118103,
+      "eval_mcc": 0.5831803046632951,
+      "eval_precision": 0.7933070866141733,
+      "eval_recall": 0.7886497064579256,
+      "eval_runtime": 66.8237,
+      "eval_samples_per_second": 15.294,
+      "eval_steps_per_second": 0.479,
+      "step": 576
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 1.9171998500823975,
+      "learning_rate": 0.00034546055310157167,
+      "loss": 0.3976,
+      "step": 768
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.786692759295499,
+      "eval_f1": 0.783300198807157,
+      "eval_loss": 0.40033411979675293,
+      "eval_mcc": 0.5736667956847438,
+      "eval_precision": 0.795959595959596,
+      "eval_recall": 0.7710371819960861,
+      "eval_runtime": 66.6803,
+      "eval_samples_per_second": 15.327,
+      "eval_steps_per_second": 0.48,
+      "step": 768
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 1.3183633089065552,
+      "learning_rate": 0.00028788379425130975,
+      "loss": 0.3869,
+      "step": 960
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.8013698630136986,
+      "eval_f1": 0.8031037827352084,
+      "eval_loss": 0.39175575971603394,
+      "eval_mcc": 0.60283323302071,
+      "eval_precision": 0.7961538461538461,
+      "eval_recall": 0.8101761252446184,
+      "eval_runtime": 66.5306,
+      "eval_samples_per_second": 15.361,
+      "eval_steps_per_second": 0.481,
+      "step": 960
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 1.770856499671936,
+      "learning_rate": 0.0002303070354010478,
+      "loss": 0.3843,
+      "step": 1152
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.8228962818003914,
+      "eval_f1": 0.8350045578851412,
+      "eval_loss": 0.38628602027893066,
+      "eval_mcc": 0.6528627457969611,
+      "eval_precision": 0.7815699658703071,
+      "eval_recall": 0.8962818003913894,
+      "eval_runtime": 67.0562,
+      "eval_samples_per_second": 15.241,
+      "eval_steps_per_second": 0.477,
+      "step": 1152
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 1.1659635305404663,
+      "learning_rate": 0.00017273027655078583,
+      "loss": 0.3793,
+      "step": 1344
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.8111545988258317,
+      "eval_f1": 0.8269058295964126,
+      "eval_loss": 0.39157727360725403,
+      "eval_mcc": 0.6328787442530197,
+      "eval_precision": 0.7632450331125827,
+      "eval_recall": 0.9021526418786693,
+      "eval_runtime": 66.5334,
+      "eval_samples_per_second": 15.361,
+      "eval_steps_per_second": 0.481,
+      "step": 1344
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 2.5721819400787354,
+      "learning_rate": 0.0001151535177005239,
+      "loss": 0.3727,
+      "step": 1536
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.821917808219178,
+      "eval_f1": 0.8311688311688312,
+      "eval_loss": 0.3822523355484009,
+      "eval_mcc": 0.6477369472991997,
+      "eval_precision": 0.7901234567901234,
+      "eval_recall": 0.8767123287671232,
+      "eval_runtime": 67.4301,
+      "eval_samples_per_second": 15.156,
+      "eval_steps_per_second": 0.475,
+      "step": 1536
+    },
+    {
+      "epoch": 9.0,
+      "grad_norm": 1.5437999963760376,
+      "learning_rate": 5.757675885026195e-05,
+      "loss": 0.3692,
+      "step": 1728
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.8268101761252447,
+      "eval_f1": 0.8334901222953904,
+      "eval_loss": 0.37901678681373596,
+      "eval_mcc": 0.655734447578894,
+      "eval_precision": 0.802536231884058,
+      "eval_recall": 0.8669275929549902,
+      "eval_runtime": 67.6441,
+      "eval_samples_per_second": 15.108,
+      "eval_steps_per_second": 0.473,
+      "step": 1728
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1920,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "total_flos": 2121256775520.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.6664545915670365,
+    "learning_rate": 0.0005757675885026195,
+    "num_train_epochs": 10,
+    "per_device_train_batch_size": 16,
+    "temperature": 37
+  }
+}

run-1/checkpoint-1728/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a9fe6e98582646cabde3e8596aaf7d6306e98b72fcfb66153c430972f11d98c
+size 4984

run-1/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-1/checkpoint-1920/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfdb847337672e382e5f8b6983aa90c1c60d04312269f8da02af866947c30254
+size 17549312

run-1/checkpoint-1920/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98c837effb9cdd3fe0b1b6cbc494aabf4b6deb0fe18579e7dbd39a3910b86511
+size 35122746

run-1/checkpoint-1920/rng_state.pth

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

run-1/checkpoint-1920/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76c7166858e4b7cc9fbe31f604106fc5f4e1cb4ccdc24cdc5722c0d07011af94
+size 1064

run-1/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-1/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-1/checkpoint-1920/trainer_state.json

@@ -0,0 +1,227 @@
+{
+  "best_metric": 0.8277886497064579,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-1/checkpoint-1920",
+  "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": 0.8947777152061462,
+      "learning_rate": 0.0005181908296523575,
+      "loss": 0.4457,
+      "step": 192
+    },
+    {
+      "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
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.971238613128662,
+      "learning_rate": 0.0004606140708020956,
+      "loss": 0.4163,
+      "step": 384
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7915851272015656,
+      "eval_f1": 0.7957813998082454,
+      "eval_loss": 0.39958736300468445,
+      "eval_mcc": 0.5836633290639656,
+      "eval_precision": 0.7800751879699248,
+      "eval_recall": 0.812133072407045,
+      "eval_runtime": 66.5614,
+      "eval_samples_per_second": 15.354,
+      "eval_steps_per_second": 0.481,
+      "step": 384
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 2.333700656890869,
+      "learning_rate": 0.00040303731195183364,
+      "loss": 0.4018,
+      "step": 576
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7915851272015656,
+      "eval_f1": 0.7909715407262021,
+      "eval_loss": 0.40145382285118103,
+      "eval_mcc": 0.5831803046632951,
+      "eval_precision": 0.7933070866141733,
+      "eval_recall": 0.7886497064579256,
+      "eval_runtime": 66.8237,
+      "eval_samples_per_second": 15.294,
+      "eval_steps_per_second": 0.479,
+      "step": 576
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 1.9171998500823975,
+      "learning_rate": 0.00034546055310157167,
+      "loss": 0.3976,
+      "step": 768
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.786692759295499,
+      "eval_f1": 0.783300198807157,
+      "eval_loss": 0.40033411979675293,
+      "eval_mcc": 0.5736667956847438,
+      "eval_precision": 0.795959595959596,
+      "eval_recall": 0.7710371819960861,
+      "eval_runtime": 66.6803,
+      "eval_samples_per_second": 15.327,
+      "eval_steps_per_second": 0.48,
+      "step": 768
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 1.3183633089065552,
+      "learning_rate": 0.00028788379425130975,
+      "loss": 0.3869,
+      "step": 960
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.8013698630136986,
+      "eval_f1": 0.8031037827352084,
+      "eval_loss": 0.39175575971603394,
+      "eval_mcc": 0.60283323302071,
+      "eval_precision": 0.7961538461538461,
+      "eval_recall": 0.8101761252446184,
+      "eval_runtime": 66.5306,
+      "eval_samples_per_second": 15.361,
+      "eval_steps_per_second": 0.481,
+      "step": 960
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 1.770856499671936,
+      "learning_rate": 0.0002303070354010478,
+      "loss": 0.3843,
+      "step": 1152
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.8228962818003914,
+      "eval_f1": 0.8350045578851412,
+      "eval_loss": 0.38628602027893066,
+      "eval_mcc": 0.6528627457969611,
+      "eval_precision": 0.7815699658703071,
+      "eval_recall": 0.8962818003913894,
+      "eval_runtime": 67.0562,
+      "eval_samples_per_second": 15.241,
+      "eval_steps_per_second": 0.477,
+      "step": 1152
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 1.1659635305404663,
+      "learning_rate": 0.00017273027655078583,
+      "loss": 0.3793,
+      "step": 1344
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.8111545988258317,
+      "eval_f1": 0.8269058295964126,
+      "eval_loss": 0.39157727360725403,
+      "eval_mcc": 0.6328787442530197,
+      "eval_precision": 0.7632450331125827,
+      "eval_recall": 0.9021526418786693,
+      "eval_runtime": 66.5334,
+      "eval_samples_per_second": 15.361,
+      "eval_steps_per_second": 0.481,
+      "step": 1344
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 2.5721819400787354,
+      "learning_rate": 0.0001151535177005239,
+      "loss": 0.3727,
+      "step": 1536
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.821917808219178,
+      "eval_f1": 0.8311688311688312,
+      "eval_loss": 0.3822523355484009,
+      "eval_mcc": 0.6477369472991997,
+      "eval_precision": 0.7901234567901234,
+      "eval_recall": 0.8767123287671232,
+      "eval_runtime": 67.4301,
+      "eval_samples_per_second": 15.156,
+      "eval_steps_per_second": 0.475,
+      "step": 1536
+    },
+    {
+      "epoch": 9.0,
+      "grad_norm": 1.5437999963760376,
+      "learning_rate": 5.757675885026195e-05,
+      "loss": 0.3692,
+      "step": 1728
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.8268101761252447,
+      "eval_f1": 0.8334901222953904,
+      "eval_loss": 0.37901678681373596,
+      "eval_mcc": 0.655734447578894,
+      "eval_precision": 0.802536231884058,
+      "eval_recall": 0.8669275929549902,
+      "eval_runtime": 67.6441,
+      "eval_samples_per_second": 15.108,
+      "eval_steps_per_second": 0.473,
+      "step": 1728
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 1.2340621948242188,
+      "learning_rate": 0.0,
+      "loss": 0.3673,
+      "step": 1920
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.8277886497064579,
+      "eval_f1": 0.8352059925093633,
+      "eval_loss": 0.37935787439346313,
+      "eval_mcc": 0.6582497957275898,
+      "eval_precision": 0.800718132854578,
+      "eval_recall": 0.87279843444227,
+      "eval_runtime": 67.2953,
+      "eval_samples_per_second": 15.187,
+      "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": 0.6664545915670365,
+    "learning_rate": 0.0005757675885026195,
+    "num_train_epochs": 10,
+    "per_device_train_batch_size": 16,
+    "temperature": 37
+  }
+}

run-1/checkpoint-1920/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a9fe6e98582646cabde3e8596aaf7d6306e98b72fcfb66153c430972f11d98c
+size 4984

run-2/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-2/checkpoint-192/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:50993681366f2d23fe5ca33204cdfec9eb3f0f0bcc3761f57c7e4bc82db10b2e
+oid sha256:5b4b5dc69cb0469a967756916d6a6944e64d282b3dddd187d83bb80ec725cf81
 size 17549312

run-2/checkpoint-192/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35dfdbb7c6d4fc74aca27ce0402a32b7cf9a9ac2f10aae53aebe1b27aad4b113
+oid sha256:5342e1668eca8910757395d7bdda19519f600e233e07422c9833da9c763350eb
 size 35122746

run-2/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-2/checkpoint-192/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c64434bd666dd3fe34fa8bfec2c00bc1ce93ea68c0aef0606a126126358891d8
+oid sha256:a9daa7e260cd19eafc39c76c5b2bf38f3a0d19cfdbadab961d72d1e7c52310c1
 size 1064

run-2/checkpoint-192/trainer_state.json

@@ -1,7 +1,7 @@
 {
-  "best_metric": 0.538160469667319,
+  "best_metric": 0.5499021526418787,
   "best_model_checkpoint": "tiny-bert-sst2-distilled/run-2/checkpoint-192",
-  "epoch": 2.0,
+  "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": 0.3969263434410095,
-      "learning_rate": 3.130245712253287e-05,
-      "loss": 0.081,
-      "step": 96
-    },
-    {
-      "epoch": 1.0,
-      "eval_accuracy": 0.512720156555773,
-      "eval_f1": 0.08118081180811808,
-      "eval_loss": 0.03750595450401306,
-      "eval_precision": 0.7096774193548387,
-      "eval_recall": 0.043052837573385516,
-      "eval_runtime": 25.4915,
-      "eval_samples_per_second": 40.092,
-      "eval_steps_per_second": 1.255,
-      "step": 96
-    },
-    {
-      "epoch": 2.0,
-      "grad_norm": 0.2545386254787445,
-      "learning_rate": 1.5651228561266437e-05,
-      "loss": 0.0372,
+      "grad_norm": 1.0371571779251099,
+      "learning_rate": 0.0001305282668790618,
+      "loss": 0.3216,
       "step": 192
     },
     {
-      "epoch": 2.0,
-      "eval_accuracy": 0.538160469667319,
-      "eval_f1": 0.1945392491467577,
-      "eval_loss": 0.030006052926182747,
-      "eval_precision": 0.76,
-      "eval_recall": 0.11154598825831702,
-      "eval_runtime": 26.0378,
-      "eval_samples_per_second": 39.251,
-      "eval_steps_per_second": 1.229,
+      "epoch": 1.0,
+      "eval_accuracy": 0.5499021526418787,
+      "eval_f1": 0.23841059602649006,
+      "eval_loss": 0.2955350875854492,
+      "eval_mcc": 0.17350853577425898,
+      "eval_precision": 0.7741935483870968,
+      "eval_recall": 0.14090019569471623,
+      "eval_runtime": 67.6225,
+      "eval_samples_per_second": 15.113,
+      "eval_steps_per_second": 0.473,
       "step": 192
     }
   ],
   "logging_steps": 500,
-  "max_steps": 288,
+  "max_steps": 1728,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 3,
+  "num_train_epochs": 9,
   "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": 0.022604047006827055,
-    "learning_rate": 4.6953685683799313e-05,
-    "num_train_epochs": 3,
-    "temperature": 5
+    "alpha": 0.4208671172864604,
+    "learning_rate": 0.00014684430023894452,
+    "num_train_epochs": 9,
+    "per_device_train_batch_size": 16,
+    "temperature": 48
   }
 }

run-2/checkpoint-192/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:25a5bc2ca31318692bb3d061ec3f8db53d887cf60ae54f3c3e0e26465b0b418c
-size 4920
+oid sha256:a9e5acc29cf7d39a1c2a69461e588dfa38fe51a74003ef00804ced1c8aab86d3
+size 4984

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a9fe6e98582646cabde3e8596aaf7d6306e98b72fcfb66153c430972f11d98c
+oid sha256:a9e5acc29cf7d39a1c2a69461e588dfa38fe51a74003ef00804ced1c8aab86d3
 size 4984