Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f91234e83dbce56155401ad1d694d158623c6dbcb479b1db268fcce8bb17a34
+oid sha256:b70b25fb624ba97ba62cf6366699b1804f9ade1a5d4b0d8d7726632eb25e5f31
 size 267829484

run-2/checkpoint-36/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b93dca996de1e2a65bd2b8805ca12671d565a8759726dc118ad227d9b8a09a73
+oid sha256:f930b8e96467ee59dea52bcf8712dae91677530f12e1f7ea5a39a7a4572f96e9
 size 267829484

run-2/checkpoint-36/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db01303a5cc2dc9a4a9e3c24747961298061cde5ee891e6791759338af31118b
+oid sha256:bb506fecce1fb0b394149d81f89c829a9f59f5e9b82210e2b4a2581d50a25010
 size 535721146

run-2/checkpoint-36/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e487ea155a05ba923a32158dbff6d5c2aab0ce8eb78432409ac273e66fbed356
-size 14308
+oid sha256:e301dfdefa0bdcaf96abb4785d80c44201447f4b6cd7ecb8a0638b8d695f8a09
+size 14244

run-2/checkpoint-36/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:403f70790ff34bbca23e584bfb0794bfebba32bd031bfb3c3bdd4e30525f3966
+oid sha256:79c8286a4eb3ca2b934455ad2ce9ed451db18e27aab2aa7fe20c57a9ac5c9294
 size 1064

run-2/checkpoint-36/trainer_state.json

@@ -1,7 +1,7 @@
 {
-  "best_metric": 0.22535612418664588,
+  "best_metric": 0.6951648539564048,
   "best_model_checkpoint": "distilbert-base-uncased-finetuned-stsb/run-2/checkpoint-36",
-  "epoch": 1.0,
+  "epoch": 2.0,
   "eval_steps": 500,
   "global_step": 36,
   "is_hyper_param_search": true,
@@ -10,27 +10,37 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_loss": 2.3542871475219727,
-      "eval_pearson": 0.22535612418664588,
-      "eval_runtime": 0.7946,
-      "eval_samples_per_second": 1887.683,
-      "eval_spearmanr": 0.2439162232725169,
-      "eval_steps_per_second": 118.295,
+      "eval_loss": 2.5358598232269287,
+      "eval_pearson": 0.3111201117407732,
+      "eval_runtime": 0.9088,
+      "eval_samples_per_second": 1650.59,
+      "eval_spearmanr": 0.30189341919396323,
+      "eval_steps_per_second": 103.437,
+      "step": 18
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 1.8630882501602173,
+      "eval_pearson": 0.6951648539564048,
+      "eval_runtime": 1.1428,
+      "eval_samples_per_second": 1312.613,
+      "eval_spearmanr": 0.6897209166518194,
+      "eval_steps_per_second": 82.257,
       "step": 36
     }
   ],
   "logging_steps": 500,
   "max_steps": 72,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 2,
+  "num_train_epochs": 4,
   "save_steps": 500,
   "total_flos": 0,
-  "train_batch_size": 16,
+  "train_batch_size": 32,
   "trial_name": null,
   "trial_params": {
-    "learning_rate": 1.2299344669970108e-05,
-    "num_train_epochs": 2,
-    "per_device_train_batch_size": 16,
-    "seed": 20
+    "learning_rate": 3.9708935486543325e-05,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 32,
+    "seed": 27
   }
 }

run-2/checkpoint-36/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:51b688100c0cb9752c8b835323e5f372a383d39c54fd09c2eb9daa32a890cbaf
+oid sha256:6a58e573bd94f8beb9db88df304942d0e9c8bc04406d12b1190de70c7fae2b2b
 size 4920

run-2/checkpoint-54/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-2/checkpoint-54/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91e2fd1ef5146e50eb9baf4b2ea056a8b941e57b7330f8528890747cf130cfd5
+size 267829484

run-2/checkpoint-54/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:314294de985d48b69f286bfdbdc0c24dde29dd4e30302a8ec1f6370f8b6dd8a4
+size 535721146

run-2/checkpoint-54/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4361cea3d3d8ce7a89125be20940a43801b702940949fa871b6f67941b49be0b
+size 14244

run-2/checkpoint-54/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:669c83ee761ed1353fa2c840d4a223f3405f88d3b7d3ac6c85bb8bd834d630f1
+size 1064

run-2/checkpoint-54/special_tokens_map.json

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

run-2/checkpoint-54/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-2/checkpoint-54/trainer_state.json

@@ -0,0 +1,56 @@
+{
+  "best_metric": 0.7873712707854975,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-stsb/run-2/checkpoint-54",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 54,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 2.5358598232269287,
+      "eval_pearson": 0.3111201117407732,
+      "eval_runtime": 0.9088,
+      "eval_samples_per_second": 1650.59,
+      "eval_spearmanr": 0.30189341919396323,
+      "eval_steps_per_second": 103.437,
+      "step": 18
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 1.8630882501602173,
+      "eval_pearson": 0.6951648539564048,
+      "eval_runtime": 1.1428,
+      "eval_samples_per_second": 1312.613,
+      "eval_spearmanr": 0.6897209166518194,
+      "eval_steps_per_second": 82.257,
+      "step": 36
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.9276750683784485,
+      "eval_pearson": 0.7873712707854975,
+      "eval_runtime": 1.0922,
+      "eval_samples_per_second": 1373.349,
+      "eval_spearmanr": 0.7874940623310164,
+      "eval_steps_per_second": 86.063,
+      "step": 54
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 72,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 3.9708935486543325e-05,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 32,
+    "seed": 27
+  }
+}

run-2/checkpoint-54/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a58e573bd94f8beb9db88df304942d0e9c8bc04406d12b1190de70c7fae2b2b
+size 4920

run-2/checkpoint-72/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:29762bedee45da925779652901931aaaa997ceed3f77ded17a0fc6f3db058cb0
+oid sha256:85a8a326ebecef0609119af813d21346bd97053374859f5036d703d872f65a62
 size 267829484

run-2/checkpoint-72/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:30e04af797359d85d3bcbd20632d6df2c1f4ec63907848ef6c461754000226da
+oid sha256:fe147bd59df360b6592c722d062fe7eacfd1f1e4977578496830e82db32380f6
 size 535721146

run-2/checkpoint-72/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4686679b5492922b658249d2e94e6f498b978fdd3a7bff4a48680a5cd459c4af
-size 14308
+oid sha256:12c9c069de2602063ed4d0022f0aa36d81821e2d6f69981ed3fd049dd2d60969
+size 14244

run-2/checkpoint-72/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bde2e00598c06b03eeecccf4acec830a76c4f4fee8368c10b212531b829e48b1
+oid sha256:7e9b08f9362b26f42671ec58ed673fe45a44e02a696398802e42e9db3cbc9c06
 size 1064

run-2/checkpoint-72/trainer_state.json

@@ -1,7 +1,7 @@
 {
-  "best_metric": 0.4052420655597578,
+  "best_metric": 0.7927050761913262,
   "best_model_checkpoint": "distilbert-base-uncased-finetuned-stsb/run-2/checkpoint-72",
-  "epoch": 2.0,
+  "epoch": 4.0,
   "eval_steps": 500,
   "global_step": 72,
   "is_hyper_param_search": true,
@@ -10,37 +10,57 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_loss": 2.3542871475219727,
-      "eval_pearson": 0.22535612418664588,
-      "eval_runtime": 0.7946,
-      "eval_samples_per_second": 1887.683,
-      "eval_spearmanr": 0.2439162232725169,
-      "eval_steps_per_second": 118.295,
-      "step": 36
+      "eval_loss": 2.5358598232269287,
+      "eval_pearson": 0.3111201117407732,
+      "eval_runtime": 0.9088,
+      "eval_samples_per_second": 1650.59,
+      "eval_spearmanr": 0.30189341919396323,
+      "eval_steps_per_second": 103.437,
+      "step": 18
     },
     {
       "epoch": 2.0,
-      "eval_loss": 2.184481382369995,
-      "eval_pearson": 0.4052420655597578,
-      "eval_runtime": 0.8115,
-      "eval_samples_per_second": 1848.458,
-      "eval_spearmanr": 0.4375008049819036,
-      "eval_steps_per_second": 115.837,
+      "eval_loss": 1.8630882501602173,
+      "eval_pearson": 0.6951648539564048,
+      "eval_runtime": 1.1428,
+      "eval_samples_per_second": 1312.613,
+      "eval_spearmanr": 0.6897209166518194,
+      "eval_steps_per_second": 82.257,
+      "step": 36
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.9276750683784485,
+      "eval_pearson": 0.7873712707854975,
+      "eval_runtime": 1.0922,
+      "eval_samples_per_second": 1373.349,
+      "eval_spearmanr": 0.7874940623310164,
+      "eval_steps_per_second": 86.063,
+      "step": 54
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.89371657371521,
+      "eval_pearson": 0.7927050761913262,
+      "eval_runtime": 1.0947,
+      "eval_samples_per_second": 1370.197,
+      "eval_spearmanr": 0.7933321012367246,
+      "eval_steps_per_second": 85.866,
       "step": 72
     }
   ],
   "logging_steps": 500,
   "max_steps": 72,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 2,
+  "num_train_epochs": 4,
   "save_steps": 500,
   "total_flos": 0,
-  "train_batch_size": 16,
+  "train_batch_size": 32,
   "trial_name": null,
   "trial_params": {
-    "learning_rate": 1.2299344669970108e-05,
-    "num_train_epochs": 2,
-    "per_device_train_batch_size": 16,
-    "seed": 20
+    "learning_rate": 3.9708935486543325e-05,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 32,
+    "seed": 27
   }
 }

run-2/checkpoint-72/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:51b688100c0cb9752c8b835323e5f372a383d39c54fd09c2eb9daa32a890cbaf
+oid sha256:6a58e573bd94f8beb9db88df304942d0e9c8bc04406d12b1190de70c7fae2b2b
 size 4920

run-3/checkpoint-144/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:32f2b6344dbeefedd77c7295f5f43e3c60235bc524019549e354574302929153
+oid sha256:b70b25fb624ba97ba62cf6366699b1804f9ade1a5d4b0d8d7726632eb25e5f31
 size 267829484

run-3/checkpoint-144/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dce180cf84c457e26dbe5dc71e2cf60b9fb73806b95e73e9436ad0a1db34b15c
+oid sha256:0fcc96d702529fd8af4d9d37bfabfb97a47dc12866c40ea50aaecbfea35d4423
 size 535721146

run-3/checkpoint-144/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8dea8c3947bb8f5869ac25773574fc8e420bd3520749b6b82f0981d4e5526f48
+oid sha256:9239f6e1b345cf42f8f91aff57d30245662f3cbb704b9a8bc6f2063280a93b1c
 size 14244

run-3/checkpoint-144/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:38b6a327e093676a8bb58cd5a3fbc152f4e0b61b1785248363a0da24141a066b
+oid sha256:cc675f9f857df191f3c49050e7e98b2435cf51c554caf46536d902061117b5ce
 size 1064

run-3/checkpoint-144/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.7678320454774757,
+  "best_metric": 0.7754149460856693,
   "best_model_checkpoint": "distilbert-base-uncased-finetuned-stsb/run-3/checkpoint-144",
   "epoch": 1.0,
   "eval_steps": 500,
@@ -10,12 +10,12 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_loss": 0.9698190689086914,
-      "eval_pearson": 0.7678320454774757,
-      "eval_runtime": 0.8035,
-      "eval_samples_per_second": 1866.77,
-      "eval_spearmanr": 0.712509933248186,
-      "eval_steps_per_second": 116.984,
+      "eval_loss": 1.0159441232681274,
+      "eval_pearson": 0.7754149460856693,
+      "eval_runtime": 0.9276,
+      "eval_samples_per_second": 1617.073,
+      "eval_spearmanr": 0.7770625188634587,
+      "eval_steps_per_second": 101.337,
       "step": 144
     }
   ],
@@ -28,9 +28,9 @@
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": {
-    "learning_rate": 5.4134010471541346e-05,
+    "learning_rate": 3.444308458582572e-05,
     "num_train_epochs": 5,
     "per_device_train_batch_size": 4,
-    "seed": 4
+    "seed": 38
   }
 }

run-3/checkpoint-144/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a89dbe21e169d083920168fe1c35f86c15d94a0c3b9ca2615dabe1e0930b053d
+oid sha256:4821c7433b1b1cc47986c64fa81c811ca3c1f9863a29a79f5e5c8b19c0b27c05
 size 4920

runs/Mar07_00-50-37_758c92e55f7e/events.out.tfevents.1709772996.758c92e55f7e.2638.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dbc5046006d68577291ba905559c89b5f3607f3abf6e5b38ee0f973a8b062618
+size 7046

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a58e573bd94f8beb9db88df304942d0e9c8bc04406d12b1190de70c7fae2b2b
+oid sha256:4821c7433b1b1cc47986c64fa81c811ca3c1f9863a29a79f5e5c8b19c0b27c05
 size 4920