Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b70b25fb624ba97ba62cf6366699b1804f9ade1a5d4b0d8d7726632eb25e5f31
+oid sha256:84bec32edce0c34ec348a06616c8c7aa85c9f1a33d5d27ae77ad3e090d412754
 size 267829484

run-3/checkpoint-288/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d61c763c886dbb531d62293ccddf79a5802b2bb562413c4d5db455ce0ca8a2fb
+oid sha256:e70149ba23dd0d2f866d218b9336961ec98113bb1af5729569e5b571ffd29e9f
 size 267829484

run-3/checkpoint-288/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3dbce5211cc54e0465ac8be2041b7c2acfcfc05c146d963020091964689ca99d
+oid sha256:89a83c71a35c4c8a47c9f9d461682720d58447a2d19c908bf8f73ad93239b467
 size 535721146

run-3/checkpoint-288/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b4567d37c30077318ed7ca2fd6ed8c79fd4e9422f26b3d853c9c457274f3e99
+oid sha256:fa0756249ef89554273490d3f25c592cf35d7de3c714c99d3ee3ec2bbb73a5d4
 size 14244

run-3/checkpoint-288/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6873788c8492efd7d168b02739521070490d7c8a8f85aee5192671cdda219904
+oid sha256:e813b361e3bb66e575ae412545ecddb9e1a2907d17551c0c7b2959b9d9137cd8
 size 1064

run-3/checkpoint-288/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.8252063306594624,
+  "best_metric": 0.8294526923897652,
   "best_model_checkpoint": "distilbert-base-uncased-finetuned-stsb/run-3/checkpoint-288",
   "epoch": 2.0,
   "eval_steps": 500,
@@ -10,22 +10,22 @@
   "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
     },
     {
       "epoch": 2.0,
-      "eval_loss": 0.7606285810470581,
-      "eval_pearson": 0.8252063306594624,
-      "eval_runtime": 0.7878,
-      "eval_samples_per_second": 1904.014,
-      "eval_spearmanr": 0.8218529358151725,
-      "eval_steps_per_second": 119.318,
+      "eval_loss": 0.7027656435966492,
+      "eval_pearson": 0.8294526923897652,
+      "eval_runtime": 1.1203,
+      "eval_samples_per_second": 1338.921,
+      "eval_spearmanr": 0.8239919782128128,
+      "eval_steps_per_second": 83.906,
       "step": 288
     }
   ],
@@ -38,9 +38,9 @@
   "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-288/training_args.bin

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

run-3/checkpoint-432/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:54ee921761736374c58efdf205e400cb47f16270af5b9033facba3bb7383e53a
+oid sha256:4868147f9f64d8d4e4ba0994d128b9aa79ef2693115460ecba2d47291a2e064f
 size 267829484

run-3/checkpoint-432/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ac1fa64753adc4283dbcfd47227812a681fdced7ace3e7ccdb93f6e6b9336a5
+oid sha256:700b4b368b7b1f8c8ce908d043229c8e86e8657842ed24bba642b02baecb35c6
 size 535721146

run-3/checkpoint-432/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a35f605eedd2102adde6198f38cba143faaed4ee12b11d5ffe4f701e82b262f2
+oid sha256:808e511081723cb6acf19ed232057cc3dd2d7b62e1a05317219f9befc0215f61
 size 14244

run-3/checkpoint-432/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9422fdad9996632c1797fb4769bcfaa4d1bf52fc06a431fa4296855752c582f2
+oid sha256:fb739c138f564a5262bc1447b75225686d934caaecccce181d2b86227142035c
 size 1064

run-3/checkpoint-432/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.8325197619129224,
+  "best_metric": 0.8371525320180763,
   "best_model_checkpoint": "distilbert-base-uncased-finetuned-stsb/run-3/checkpoint-432",
   "epoch": 3.0,
   "eval_steps": 500,
@@ -10,32 +10,32 @@
   "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
     },
     {
       "epoch": 2.0,
-      "eval_loss": 0.7606285810470581,
-      "eval_pearson": 0.8252063306594624,
-      "eval_runtime": 0.7878,
-      "eval_samples_per_second": 1904.014,
-      "eval_spearmanr": 0.8218529358151725,
-      "eval_steps_per_second": 119.318,
+      "eval_loss": 0.7027656435966492,
+      "eval_pearson": 0.8294526923897652,
+      "eval_runtime": 1.1203,
+      "eval_samples_per_second": 1338.921,
+      "eval_spearmanr": 0.8239919782128128,
+      "eval_steps_per_second": 83.906,
       "step": 288
     },
     {
       "epoch": 3.0,
-      "eval_loss": 0.7174907326698303,
-      "eval_pearson": 0.8325197619129224,
-      "eval_runtime": 0.7962,
-      "eval_samples_per_second": 1883.934,
-      "eval_spearmanr": 0.8279573830775626,
-      "eval_steps_per_second": 118.06,
+      "eval_loss": 0.6792955994606018,
+      "eval_pearson": 0.8371525320180763,
+      "eval_runtime": 1.1241,
+      "eval_samples_per_second": 1334.415,
+      "eval_spearmanr": 0.8358915789303897,
+      "eval_steps_per_second": 83.623,
       "step": 432
     }
   ],
@@ -48,9 +48,9 @@
   "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-432/training_args.bin

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

run-3/checkpoint-576/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d3d6088776c555a453aba313194e46ee79702e29ce42f01cfa8a9c6961bc9c8
+oid sha256:e0252f09672f42eb2def3a2d92dafa09af532b35ad3edace25eb853de6dc06ba
 size 267829484

run-3/checkpoint-576/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:266bfd784fb8d7d7deff582f100b5c733e610ba4b2b088848056436bc04f81be
+oid sha256:64ecde12fc2a704b464816f349a6de99b4e9647b5ec943f520b69c97f3f472e6
 size 535721146

run-3/checkpoint-576/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:866764b15a22ef1ff0938a6647b07c0c9c90e6d2381339fde66f0f71097dcc37
+oid sha256:aa277fec9a04a686204af70247a8b4e3568d8153e92f5bd3a9eb50c7d3e807a1
 size 14244

run-3/checkpoint-576/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb27dabe46c6c138fbd2a477aac978f51b59d763c234a73ac470f1f9c0286e4a
+oid sha256:f3bfa2eaedf155ed3818f2d7439057a71e6beb4a37ac73fd5d2e8e33136054d8
 size 1064

run-3/checkpoint-576/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.8407800570738724,
+  "best_metric": 0.8416256812127808,
   "best_model_checkpoint": "distilbert-base-uncased-finetuned-stsb/run-3/checkpoint-576",
   "epoch": 4.0,
   "eval_steps": 500,
@@ -10,49 +10,49 @@
   "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
     },
     {
       "epoch": 2.0,
-      "eval_loss": 0.7606285810470581,
-      "eval_pearson": 0.8252063306594624,
-      "eval_runtime": 0.7878,
-      "eval_samples_per_second": 1904.014,
-      "eval_spearmanr": 0.8218529358151725,
-      "eval_steps_per_second": 119.318,
+      "eval_loss": 0.7027656435966492,
+      "eval_pearson": 0.8294526923897652,
+      "eval_runtime": 1.1203,
+      "eval_samples_per_second": 1338.921,
+      "eval_spearmanr": 0.8239919782128128,
+      "eval_steps_per_second": 83.906,
       "step": 288
     },
     {
       "epoch": 3.0,
-      "eval_loss": 0.7174907326698303,
-      "eval_pearson": 0.8325197619129224,
-      "eval_runtime": 0.7962,
-      "eval_samples_per_second": 1883.934,
-      "eval_spearmanr": 0.8279573830775626,
-      "eval_steps_per_second": 118.06,
+      "eval_loss": 0.6792955994606018,
+      "eval_pearson": 0.8371525320180763,
+      "eval_runtime": 1.1241,
+      "eval_samples_per_second": 1334.415,
+      "eval_spearmanr": 0.8358915789303897,
+      "eval_steps_per_second": 83.623,
       "step": 432
     },
     {
       "epoch": 3.47,
-      "grad_norm": 10.061558723449707,
-      "learning_rate": 1.654094764408208e-05,
-      "loss": 0.9316,
+      "grad_norm": 24.244155883789062,
+      "learning_rate": 1.052427584566897e-05,
+      "loss": 0.9809,
       "step": 500
     },
     {
       "epoch": 4.0,
-      "eval_loss": 0.7175036072731018,
-      "eval_pearson": 0.8407800570738724,
-      "eval_runtime": 0.7992,
-      "eval_samples_per_second": 1876.812,
-      "eval_spearmanr": 0.8358993750524432,
-      "eval_steps_per_second": 117.614,
+      "eval_loss": 0.6611331105232239,
+      "eval_pearson": 0.8416256812127808,
+      "eval_runtime": 1.1415,
+      "eval_samples_per_second": 1314.012,
+      "eval_spearmanr": 0.8371352595017586,
+      "eval_steps_per_second": 82.345,
       "step": 576
     }
   ],
@@ -61,13 +61,13 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 5,
   "save_steps": 500,
-  "total_flos": 22512846870384.0,
+  "total_flos": 22488785838402.0,
   "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-576/training_args.bin

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

run-3/checkpoint-720/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa0d60c076141cf7c557f9e6e5ee5c4f86e889eb8bdf0a92abb93ba722721f86
+oid sha256:a5bc1b531032dd209d8612697b6d66430437909170e4f5e9db1464a69cb7170b
 size 267829484

run-3/checkpoint-720/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a301924ca24aae6f1fb2c1c6ee9db250640a15a1a2d472c44a832785935b9318
+oid sha256:85bd33f89e970d5eed5b1700ce0879d341256f399b5e49a28441dea48ec6ef7d
 size 535721146

run-3/checkpoint-720/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f67419749962139f0cc43ca20b49e9704d0edbf7d5f97a6d0cab6b36fcd9155
+oid sha256:c107ae0ea3f1f1b34f3b300cf1b0955ef489d70d5f2d9e4aa62d79e0bebdc5cf
 size 14244

run-3/checkpoint-720/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:423272412d97a885928e6da28e6e2e5c0c8b0cd8ad24d0ecdfd83d3aefd966c8
+oid sha256:e936e0aaf767fe7e9ef1cc507adb5e75f602c8f4ddb24d590baff19f29fe3662
 size 1064

run-3/checkpoint-720/trainer_state.json

@@ -1,6 +1,6 @@
 {
-  "best_metric": 0.8407800570738724,
-  "best_model_checkpoint": "distilbert-base-uncased-finetuned-stsb/run-3/checkpoint-576",
+  "best_metric": 0.8422757387186379,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-stsb/run-3/checkpoint-720",
   "epoch": 5.0,
   "eval_steps": 500,
   "global_step": 720,
@@ -10,59 +10,59 @@
   "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
     },
     {
       "epoch": 2.0,
-      "eval_loss": 0.7606285810470581,
-      "eval_pearson": 0.8252063306594624,
-      "eval_runtime": 0.7878,
-      "eval_samples_per_second": 1904.014,
-      "eval_spearmanr": 0.8218529358151725,
-      "eval_steps_per_second": 119.318,
+      "eval_loss": 0.7027656435966492,
+      "eval_pearson": 0.8294526923897652,
+      "eval_runtime": 1.1203,
+      "eval_samples_per_second": 1338.921,
+      "eval_spearmanr": 0.8239919782128128,
+      "eval_steps_per_second": 83.906,
       "step": 288
     },
     {
       "epoch": 3.0,
-      "eval_loss": 0.7174907326698303,
-      "eval_pearson": 0.8325197619129224,
-      "eval_runtime": 0.7962,
-      "eval_samples_per_second": 1883.934,
-      "eval_spearmanr": 0.8279573830775626,
-      "eval_steps_per_second": 118.06,
+      "eval_loss": 0.6792955994606018,
+      "eval_pearson": 0.8371525320180763,
+      "eval_runtime": 1.1241,
+      "eval_samples_per_second": 1334.415,
+      "eval_spearmanr": 0.8358915789303897,
+      "eval_steps_per_second": 83.623,
       "step": 432
     },
     {
       "epoch": 3.47,
-      "grad_norm": 10.061558723449707,
-      "learning_rate": 1.654094764408208e-05,
-      "loss": 0.9316,
+      "grad_norm": 24.244155883789062,
+      "learning_rate": 1.052427584566897e-05,
+      "loss": 0.9809,
       "step": 500
     },
     {
       "epoch": 4.0,
-      "eval_loss": 0.7175036072731018,
-      "eval_pearson": 0.8407800570738724,
-      "eval_runtime": 0.7992,
-      "eval_samples_per_second": 1876.812,
-      "eval_spearmanr": 0.8358993750524432,
-      "eval_steps_per_second": 117.614,
+      "eval_loss": 0.6611331105232239,
+      "eval_pearson": 0.8416256812127808,
+      "eval_runtime": 1.1415,
+      "eval_samples_per_second": 1314.012,
+      "eval_spearmanr": 0.8371352595017586,
+      "eval_steps_per_second": 82.345,
       "step": 576
     },
     {
       "epoch": 5.0,
-      "eval_loss": 0.67606520652771,
-      "eval_pearson": 0.8389162758555168,
-      "eval_runtime": 0.8221,
-      "eval_samples_per_second": 1824.653,
-      "eval_spearmanr": 0.8352930144614386,
-      "eval_steps_per_second": 114.345,
+      "eval_loss": 0.6691386699676514,
+      "eval_pearson": 0.8422757387186379,
+      "eval_runtime": 1.0993,
+      "eval_samples_per_second": 1364.543,
+      "eval_spearmanr": 0.8374301458257349,
+      "eval_steps_per_second": 85.511,
       "step": 720
     }
   ],
@@ -71,13 +71,13 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 5,
   "save_steps": 500,
-  "total_flos": 22512846870384.0,
+  "total_flos": 22488785838402.0,
   "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-720/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.1709773116.758c92e55f7e.2638.6

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17e4d54666ff128c9e9ff7873136a55131dae24f207cacad191725739f7f7b43
+size 6426

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4821c7433b1b1cc47986c64fa81c811ca3c1f9863a29a79f5e5c8b19c0b27c05
+oid sha256:bf3f62aadffc261f72a51d4b7c87acc76e6bc2705585514f61113a84b0e34fd3
 size 4920