Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79bbbdb8ed88a9b010704705143f72be58ccb68307cc2297530b76a8e136a769
+oid sha256:475be2c7e113d40683406e8823d7389e3567d12d4398a875869febd179abda22
 size 267829484

run-0/checkpoint-144/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d4ebbc80bdea594e9c45d0bd1ee785cd4c4ab9a369a7e11a11992bda11abc75a
+oid sha256:24a5f7a8fe85b355597918b531bd148f2610dab6811eed29b4bdd0dd62e2ba26
 size 267829484

run-0/checkpoint-144/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6026f14ddf7e680eff17afcb685b793d514094ea5fb7ce8906f8bf669b00658b
+oid sha256:0627630a5b8b7064b694b2d490e2239ba6f226c5b73473e1bd215b592cb87b1d
 size 535721146

run-0/checkpoint-144/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe3f45e7bb011fde7b10a81464c1dd03589c1e07ef2a99a155cfb9643dcdd4a2
+oid sha256:0f6b60aad452bff3447ffca2a36beeee0343938e34ba314a3008c1ede5f8c3f6
 size 14244

run-0/checkpoint-144/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ab6969c1d44574bdac80efcf373e8f30eba03534ab366addb8f4801a983bbe7
+oid sha256:3ed78427fd57c9e2deb308e475e266ba8a5ec7c042923d27ac3e7597ad3b96c7
 size 1064

run-0/checkpoint-144/trainer_state.json

@@ -1,7 +1,7 @@
 {
-  "best_metric": 0.7966375426002391,
+  "best_metric": 0.8184498144194529,
   "best_model_checkpoint": "distilbert-base-uncased-finetuned-stsb/run-0/checkpoint-144",
-  "epoch": 1.0,
+  "epoch": 2.0,
   "eval_steps": 500,
   "global_step": 144,
   "is_hyper_param_search": true,
@@ -10,27 +10,37 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_loss": 0.9918314814567566,
-      "eval_pearson": 0.7966375426002391,
-      "eval_runtime": 0.8021,
-      "eval_samples_per_second": 1870.124,
-      "eval_spearmanr": 0.7909051383387676,
-      "eval_steps_per_second": 117.194,
+      "eval_loss": 1.1317814588546753,
+      "eval_pearson": 0.7925397117075783,
+      "eval_runtime": 0.9029,
+      "eval_samples_per_second": 1661.35,
+      "eval_spearmanr": 0.7981526098929177,
+      "eval_steps_per_second": 104.111,
+      "step": 72
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.8140504360198975,
+      "eval_pearson": 0.8184498144194529,
+      "eval_runtime": 1.1042,
+      "eval_samples_per_second": 1358.431,
+      "eval_spearmanr": 0.8199506621029472,
+      "eval_steps_per_second": 85.128,
       "step": 144
     }
   ],
   "logging_steps": 500,
-  "max_steps": 720,
+  "max_steps": 360,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 5,
   "save_steps": 500,
   "total_flos": 0,
-  "train_batch_size": 4,
+  "train_batch_size": 8,
   "trial_name": null,
   "trial_params": {
-    "learning_rate": 4.325876846375602e-05,
+    "learning_rate": 7.503545930910804e-05,
     "num_train_epochs": 5,
-    "per_device_train_batch_size": 4,
-    "seed": 34
+    "per_device_train_batch_size": 8,
+    "seed": 19
   }
 }

run-0/checkpoint-144/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a012d40728dc244700f11825615a9f3164fccd8635d4eae2a798016634c8eb7
+oid sha256:34840284466eb2205f9f10ed091682dc9319569f75d63faf8795d5f603abf328
 size 4920

run-0/checkpoint-216/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f5418acaf01f7db94af0b54792b6d4d366668bbd0a5d0b667448131120c5418
+oid sha256:426c255c1ce8b20c685bae6f9ffad5d09a0a071cc92c4c571006322e326ed012
 size 267829484

run-0/checkpoint-216/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac8e9f3709f2d455f24f61a19d17d420e4f680e5bc3fb8b0655be37df65a418b
+oid sha256:827578c0047df3cab5efc5e50feadc32d168495e61866ef91c832f1ce5782b47
 size 535721146

run-0/checkpoint-216/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:038e71594f5547a63cb7e467f33b50c0377a188cf2dc5dbbab756833f58c85c4
+oid sha256:dea1e3237b5de73b8d4f4afa8a389d9785cb7e1f3d1738843f3cd66c39f997fb
 size 14244

run-0/checkpoint-216/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fbe1117b504cf6be0206f1a8b7f9b6d990c0681fd1da4c1855e91c3864469c71
+oid sha256:b69465340872716a81e7ec58bbb9c8e5c56bb0b96c0110eacff6410fc47830bb
 size 1064

run-0/checkpoint-216/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.8284186695774568,
+  "best_metric": 0.8350533952135925,
   "best_model_checkpoint": "distilbert-base-uncased-finetuned-stsb/run-0/checkpoint-216",
   "epoch": 3.0,
   "eval_steps": 500,
@@ -10,47 +10,47 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_loss": 1.0813779830932617,
-      "eval_pearson": 0.7567095621264116,
-      "eval_runtime": 0.9163,
-      "eval_samples_per_second": 1637.038,
-      "eval_spearmanr": 0.7572162649891061,
-      "eval_steps_per_second": 102.588,
+      "eval_loss": 1.1317814588546753,
+      "eval_pearson": 0.7925397117075783,
+      "eval_runtime": 0.9029,
+      "eval_samples_per_second": 1661.35,
+      "eval_spearmanr": 0.7981526098929177,
+      "eval_steps_per_second": 104.111,
       "step": 72
     },
     {
       "epoch": 2.0,
-      "eval_loss": 0.8653174042701721,
-      "eval_pearson": 0.8253446259273143,
-      "eval_runtime": 1.0205,
-      "eval_samples_per_second": 1469.804,
-      "eval_spearmanr": 0.8213518482816455,
-      "eval_steps_per_second": 92.108,
+      "eval_loss": 0.8140504360198975,
+      "eval_pearson": 0.8184498144194529,
+      "eval_runtime": 1.1042,
+      "eval_samples_per_second": 1358.431,
+      "eval_spearmanr": 0.8199506621029472,
+      "eval_steps_per_second": 85.128,
       "step": 144
     },
     {
       "epoch": 3.0,
-      "eval_loss": 0.7286169528961182,
-      "eval_pearson": 0.8284186695774568,
-      "eval_runtime": 0.9489,
-      "eval_samples_per_second": 1580.844,
-      "eval_spearmanr": 0.8248712386045135,
-      "eval_steps_per_second": 99.066,
+      "eval_loss": 0.7895862460136414,
+      "eval_pearson": 0.8350533952135925,
+      "eval_runtime": 1.2556,
+      "eval_samples_per_second": 1194.637,
+      "eval_spearmanr": 0.8311768906317339,
+      "eval_steps_per_second": 74.864,
       "step": 216
     }
   ],
   "logging_steps": 500,
-  "max_steps": 288,
+  "max_steps": 360,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 4,
+  "num_train_epochs": 5,
   "save_steps": 500,
   "total_flos": 0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": {
-    "learning_rate": 3.8584811748752325e-05,
-    "num_train_epochs": 4,
+    "learning_rate": 7.503545930910804e-05,
+    "num_train_epochs": 5,
     "per_device_train_batch_size": 8,
-    "seed": 40
+    "seed": 19
   }
 }

run-0/checkpoint-216/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd9a09d3e6d841ee4f64161d2a8c27492f996273463a537d8f3f6e05968d37fe
+oid sha256:34840284466eb2205f9f10ed091682dc9319569f75d63faf8795d5f603abf328
 size 4920

run-0/checkpoint-288/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8c1a7903290ebee27e018fe7af64668477f1c58876727dd95847ead5c27d63b
+oid sha256:bd72cc626b9bd73f62e3b8bb9f804a912cd0093a5387220406ed93b8dbf25719
 size 267829484

run-0/checkpoint-288/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:03a4e7d16d9b7fc303ee20b231457bd7587b56276a8b12d313e29168dffc06dc
+oid sha256:92d34b6acb233e4eef89844a3cd9d9d458cb34b28d3d0af52769b21ba404bbf6
 size 535721146

run-0/checkpoint-288/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b38ba9e98db64db97c6caf6af07e786ff7f1f58032c6cccc3082d122f2284155
+oid sha256:83748ddeabe37c7bf34016f1f688ab7b86f864f4418190708ecf56161a5a5532
 size 14244

run-0/checkpoint-288/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8425eac3da69167f48985be7ad4006bec037e9307a080db2a5d39a3ec2bc86d
+oid sha256:e4e2fc1332c26a809e04b01288d2d96a106fb8f047fa634620469656307ec058
 size 1064

run-0/checkpoint-288/trainer_state.json

@@ -1,7 +1,7 @@
 {
-  "best_metric": 0.8281295598730645,
+  "best_metric": 0.8386197210710133,
   "best_model_checkpoint": "distilbert-base-uncased-finetuned-stsb/run-0/checkpoint-288",
-  "epoch": 2.0,
+  "epoch": 4.0,
   "eval_steps": 500,
   "global_step": 288,
   "is_hyper_param_search": true,
@@ -10,37 +10,57 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_loss": 0.9918314814567566,
-      "eval_pearson": 0.7966375426002391,
-      "eval_runtime": 0.8021,
-      "eval_samples_per_second": 1870.124,
-      "eval_spearmanr": 0.7909051383387676,
-      "eval_steps_per_second": 117.194,
-      "step": 144
+      "eval_loss": 1.1317814588546753,
+      "eval_pearson": 0.7925397117075783,
+      "eval_runtime": 0.9029,
+      "eval_samples_per_second": 1661.35,
+      "eval_spearmanr": 0.7981526098929177,
+      "eval_steps_per_second": 104.111,
+      "step": 72
     },
     {
       "epoch": 2.0,
-      "eval_loss": 0.8358427882194519,
-      "eval_pearson": 0.8281295598730645,
-      "eval_runtime": 0.826,
-      "eval_samples_per_second": 1815.925,
-      "eval_spearmanr": 0.8254389941774403,
-      "eval_steps_per_second": 113.798,
+      "eval_loss": 0.8140504360198975,
+      "eval_pearson": 0.8184498144194529,
+      "eval_runtime": 1.1042,
+      "eval_samples_per_second": 1358.431,
+      "eval_spearmanr": 0.8199506621029472,
+      "eval_steps_per_second": 85.128,
+      "step": 144
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.7895862460136414,
+      "eval_pearson": 0.8350533952135925,
+      "eval_runtime": 1.2556,
+      "eval_samples_per_second": 1194.637,
+      "eval_spearmanr": 0.8311768906317339,
+      "eval_steps_per_second": 74.864,
+      "step": 216
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.6798363924026489,
+      "eval_pearson": 0.8386197210710133,
+      "eval_runtime": 0.9324,
+      "eval_samples_per_second": 1608.739,
+      "eval_spearmanr": 0.835886505973161,
+      "eval_steps_per_second": 100.814,
       "step": 288
     }
   ],
   "logging_steps": 500,
-  "max_steps": 720,
+  "max_steps": 360,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 5,
   "save_steps": 500,
   "total_flos": 0,
-  "train_batch_size": 4,
+  "train_batch_size": 8,
   "trial_name": null,
   "trial_params": {
-    "learning_rate": 4.325876846375602e-05,
+    "learning_rate": 7.503545930910804e-05,
     "num_train_epochs": 5,
-    "per_device_train_batch_size": 4,
-    "seed": 34
+    "per_device_train_batch_size": 8,
+    "seed": 19
   }
 }

run-0/checkpoint-288/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a012d40728dc244700f11825615a9f3164fccd8635d4eae2a798016634c8eb7
+oid sha256:34840284466eb2205f9f10ed091682dc9319569f75d63faf8795d5f603abf328
 size 4920

run-0/checkpoint-360/config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "distilbert-base-uncased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "problem_type": "regression",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.2",
+  "vocab_size": 30522
+}

run-0/checkpoint-360/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:377a6302f6781628151f9f27723e49c3f1fad19613b8f58c132fe21f1455d934
+size 267829484

run-0/checkpoint-360/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b40d19c18b0bd55aacc51bb47d9bb6f8b44dd1cc52bef52a84c4f31857ed059c
+size 535721146

run-0/checkpoint-360/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:868503269df12d980e3bc129f108241731a66e8cdb1cca8a0afd2c4aa9be1618
+size 14244

run-0/checkpoint-360/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9916d34da97289ad0564254ee346eb70a822eaba405e175fb372d13279f5f367
+size 1064

run-0/checkpoint-360/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-360/tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "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_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}

run-0/checkpoint-360/trainer_state.json

@@ -0,0 +1,76 @@
+{
+  "best_metric": 0.842503947673261,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-stsb/run-0/checkpoint-360",
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 360,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 1.1317814588546753,
+      "eval_pearson": 0.7925397117075783,
+      "eval_runtime": 0.9029,
+      "eval_samples_per_second": 1661.35,
+      "eval_spearmanr": 0.7981526098929177,
+      "eval_steps_per_second": 104.111,
+      "step": 72
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.8140504360198975,
+      "eval_pearson": 0.8184498144194529,
+      "eval_runtime": 1.1042,
+      "eval_samples_per_second": 1358.431,
+      "eval_spearmanr": 0.8199506621029472,
+      "eval_steps_per_second": 85.128,
+      "step": 144
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.7895862460136414,
+      "eval_pearson": 0.8350533952135925,
+      "eval_runtime": 1.2556,
+      "eval_samples_per_second": 1194.637,
+      "eval_spearmanr": 0.8311768906317339,
+      "eval_steps_per_second": 74.864,
+      "step": 216
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.6798363924026489,
+      "eval_pearson": 0.8386197210710133,
+      "eval_runtime": 0.9324,
+      "eval_samples_per_second": 1608.739,
+      "eval_spearmanr": 0.835886505973161,
+      "eval_steps_per_second": 100.814,
+      "step": 288
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 0.6598748564720154,
+      "eval_pearson": 0.842503947673261,
+      "eval_runtime": 0.8801,
+      "eval_samples_per_second": 1704.325,
+      "eval_spearmanr": 0.8388055898329965,
+      "eval_steps_per_second": 106.804,
+      "step": 360
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 360,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 7.503545930910804e-05,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 8,
+    "seed": 19
+  }
+}

run-0/checkpoint-360/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34840284466eb2205f9f10ed091682dc9319569f75d63faf8795d5f603abf328
+size 4920

run-1/checkpoint-144/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:231fd2ee54d418a17a00516378fb3dabf0db2f6930f8e0b5f616e20837f6f545
+oid sha256:07638e968314d4f617e04e8bcec63075090eb03937772d78c457cbdbc0fd0233
 size 267829484

run-1/checkpoint-144/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b0542e79e390ff9cd28a0123e96a2dc934fd821b4e7742e984b8033d9f8c3d13
+oid sha256:575ac9ee9917d1142f451600d60b63b8abfdaf1465d1d6bb70dc81b153a9e497
 size 535721146

run-1/checkpoint-144/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d17c37c21f8a26c02de166075c5d25af74a3ab6e0a373bbb6f9364615a83185b
+oid sha256:005af92a12eb8f22863bb8349d3f12df2dc4d57ee802f0b6a578f36089f9bd80
 size 14244

run-1/checkpoint-144/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f6c40e3ca32f1bc334f439faf448596239a766f7df302fbc08aef8e86d04bc54
+oid sha256:285714c93a29569e674c25b736b6240ba6fdf17837601450f031cdad2cd3175d
 size 1064

run-1/checkpoint-144/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.8284587255207476,
+  "best_metric": 0.3042437087139711,
   "best_model_checkpoint": "distilbert-base-uncased-finetuned-stsb/run-1/checkpoint-144",
   "epoch": 2.0,
   "eval_steps": 500,
@@ -10,37 +10,37 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_loss": 1.1846531629562378,
-      "eval_pearson": 0.7580884083785275,
-      "eval_runtime": 0.9281,
-      "eval_samples_per_second": 1616.21,
-      "eval_spearmanr": 0.7189361728033606,
-      "eval_steps_per_second": 101.283,
+      "eval_loss": 4.080541133880615,
+      "eval_pearson": 0.19568172531555392,
+      "eval_runtime": 0.8653,
+      "eval_samples_per_second": 1733.563,
+      "eval_spearmanr": 0.19374973140130425,
+      "eval_steps_per_second": 108.637,
       "step": 72
     },
     {
       "epoch": 2.0,
-      "eval_loss": 0.7327950596809387,
-      "eval_pearson": 0.8284587255207476,
-      "eval_runtime": 1.2039,
-      "eval_samples_per_second": 1245.935,
-      "eval_spearmanr": 0.828112162543533,
-      "eval_steps_per_second": 78.079,
+      "eval_loss": 2.333472728729248,
+      "eval_pearson": 0.3042437087139711,
+      "eval_runtime": 0.8835,
+      "eval_samples_per_second": 1697.883,
+      "eval_spearmanr": 0.3379135804732249,
+      "eval_steps_per_second": 106.401,
       "step": 144
     }
   ],
   "logging_steps": 500,
-  "max_steps": 216,
+  "max_steps": 288,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 3,
+  "num_train_epochs": 4,
   "save_steps": 500,
   "total_flos": 0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": {
-    "learning_rate": 3.662007760473047e-05,
-    "num_train_epochs": 3,
+    "learning_rate": 2.9518876446612178e-06,
+    "num_train_epochs": 4,
     "per_device_train_batch_size": 8,
-    "seed": 7
+    "seed": 1
   }
 }

run-1/checkpoint-144/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d9d6ad8c8350311ea1d6aba36edf2f4d0a654802f9f415e16121d01b0006f5ce
+oid sha256:d9b02230c742da2d3d1d91021b9907baf4baff2dbddfb2a93f01fb7c904cc297
 size 4920

run-1/checkpoint-216/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98dcab985bf50fbd71027e5c1880605c56cbf88fb3e3abdd4462e7bb9579593d
+oid sha256:e9212b4591b20e14593940687b34c11425984a576f8a383677b1c795cc5a31fe
 size 267829484

run-1/checkpoint-216/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d86183807d2d6bf2ece13503d2858a3621a37d1f9b303d2ad59fa37bdc948467
+oid sha256:15d5c55b91788e73c27a8e54b4ca2adcea4a7b08ba43305ef27d4704d6fe3f6d
 size 535721146

run-1/checkpoint-216/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:61d7c920da4f82ab032f2430a259bb48198d66da142345325137e9ea4c6d27f7
+oid sha256:91d838dfaadb054514ed3333fbb35c61371e290ca7af5f594cb2edf539f8db82
 size 14244

run-1/checkpoint-216/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:27a88e612d3ffdb4228535567e14c3e6c67d31f67f6cc37087bb95e64ead1caa
+oid sha256:45e7e74dd3e2e4a6fedaa2ace92b07f1c071e20a8d810bac800e1f24ac5cbe72
 size 1064

run-1/checkpoint-216/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.8329521060696066,
+  "best_metric": 0.40073101077295625,
   "best_model_checkpoint": "distilbert-base-uncased-finetuned-stsb/run-1/checkpoint-216",
   "epoch": 3.0,
   "eval_steps": 500,
@@ -10,47 +10,47 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_loss": 1.1846531629562378,
-      "eval_pearson": 0.7580884083785275,
-      "eval_runtime": 0.9281,
-      "eval_samples_per_second": 1616.21,
-      "eval_spearmanr": 0.7189361728033606,
-      "eval_steps_per_second": 101.283,
+      "eval_loss": 4.080541133880615,
+      "eval_pearson": 0.19568172531555392,
+      "eval_runtime": 0.8653,
+      "eval_samples_per_second": 1733.563,
+      "eval_spearmanr": 0.19374973140130425,
+      "eval_steps_per_second": 108.637,
       "step": 72
     },
     {
       "epoch": 2.0,
-      "eval_loss": 0.7327950596809387,
-      "eval_pearson": 0.8284587255207476,
-      "eval_runtime": 1.2039,
-      "eval_samples_per_second": 1245.935,
-      "eval_spearmanr": 0.828112162543533,
-      "eval_steps_per_second": 78.079,
+      "eval_loss": 2.333472728729248,
+      "eval_pearson": 0.3042437087139711,
+      "eval_runtime": 0.8835,
+      "eval_samples_per_second": 1697.883,
+      "eval_spearmanr": 0.3379135804732249,
+      "eval_steps_per_second": 106.401,
       "step": 144
     },
     {
       "epoch": 3.0,
-      "eval_loss": 0.709359347820282,
-      "eval_pearson": 0.8329521060696066,
-      "eval_runtime": 1.6126,
-      "eval_samples_per_second": 930.19,
-      "eval_spearmanr": 0.8346619410733134,
-      "eval_steps_per_second": 58.292,
+      "eval_loss": 2.1389713287353516,
+      "eval_pearson": 0.40073101077295625,
+      "eval_runtime": 0.8693,
+      "eval_samples_per_second": 1725.481,
+      "eval_spearmanr": 0.4525934449018444,
+      "eval_steps_per_second": 108.13,
       "step": 216
     }
   ],
   "logging_steps": 500,
-  "max_steps": 216,
+  "max_steps": 288,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 3,
+  "num_train_epochs": 4,
   "save_steps": 500,
   "total_flos": 0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": {
-    "learning_rate": 3.662007760473047e-05,
-    "num_train_epochs": 3,
+    "learning_rate": 2.9518876446612178e-06,
+    "num_train_epochs": 4,
     "per_device_train_batch_size": 8,
-    "seed": 7
+    "seed": 1
   }
 }

run-1/checkpoint-216/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d9d6ad8c8350311ea1d6aba36edf2f4d0a654802f9f415e16121d01b0006f5ce
+oid sha256:d9b02230c742da2d3d1d91021b9907baf4baff2dbddfb2a93f01fb7c904cc297
 size 4920

run-1/checkpoint-288/config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "distilbert-base-uncased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "problem_type": "regression",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.2",
+  "vocab_size": 30522
+}

run-1/checkpoint-288/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23b567d646bfe9cd39c54fca479e6e56c7970bad7a34c3a881d532deff562ca3
+size 267829484

run-1/checkpoint-288/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87ba4d89a069be34ba3b373ba06f061afc698dc5aa5101dca8f3659504b4754c
+size 535721146

run-1/checkpoint-288/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5588ffa63a15c785e79c68e9ea894c1c2c115cf05b0ca9f0064d62ed34f23c6
+size 14244

run-1/checkpoint-288/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7fcb7d8cc6e558b75f9bd94eca34ef2bc1a99e21838dd3708d69f9f5b8b55e1
+size 1064

run-1/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-1/checkpoint-288/tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "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_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}