Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a25a8059c3029b9de30789699c137dc8b5ce341a94cb07d79ca20bf334b98b2
+oid sha256:e3a1eb309bec98e4c0bf7dfee033a0074f1dde2d1f2ad466a0454ff6be9c67fd
 size 267829484

run-1/checkpoint-36/config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "distilbert-base-uncased",
+  "_name_or_path": "SjardiWillems/distilbert-base-uncased-finetuned-stsb",
   "activation": "gelu",
   "architectures": [
     "DistilBertForSequenceClassification"

run-1/checkpoint-36/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d71b32cea93a13e65fb14e2fc8beae286d6e8c37cc9edc267f549243fa953ccd
+oid sha256:8fce7fd94d9aa9ee2e72ccc9878f25c8a5d30b856594e58faa20f893cd362005
 size 267829484

run-1/checkpoint-36/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cc758a5a11f93d4802a01a0465aabb4c041345512208392c4087a59703da2a66
+oid sha256:c0a8f5042fe84dc19a93b01885cf29ca4ba9f632352ac0655469290de35980be
 size 535721146

run-1/checkpoint-36/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:71dd98df860a2a12ecaee2faaee7fd8582fb939b0cf63cc256890c4f1556100b
-size 14180
+oid sha256:763dc2936cffbb83623d0ff45da566347251e3a91775ab2c2f890cd3bfb51264
+size 14244

run-1/checkpoint-36/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:495f5230a9c80420d8a0ce028f2af2e250d5ca1607cf3451970d0238e01e0583
+oid sha256:694314996efb1877aa61a45d179b77a8f24e61fc5567f5cdb506339b9ef5587d
 size 1064

run-1/checkpoint-36/trainer_state.json

@@ -1,6 +1,6 @@
 {
-  "best_metric": 0.7009517245792942,
-  "best_model_checkpoint": "distilbert-base-uncased-finetuned-stsb/run-1/checkpoint-18",
+  "best_metric": 0.8700848426046829,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-stsb/run-1/checkpoint-36",
   "epoch": 2.0,
   "eval_steps": 500,
   "global_step": 36,
@@ -10,37 +10,37 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_loss": 1.5346204042434692,
-      "eval_pearson": 0.7009517245792942,
-      "eval_runtime": 0.7943,
-      "eval_samples_per_second": 1888.564,
-      "eval_spearmanr": 0.7023215368118,
-      "eval_steps_per_second": 118.35,
+      "eval_loss": 0.557124674320221,
+      "eval_pearson": 0.8691249759376469,
+      "eval_runtime": 0.7812,
+      "eval_samples_per_second": 1920.155,
+      "eval_spearmanr": 0.8666509292845571,
+      "eval_steps_per_second": 120.33,
       "step": 18
     },
     {
       "epoch": 2.0,
-      "eval_loss": 1.7851035594940186,
-      "eval_pearson": 0.6869651194383046,
-      "eval_runtime": 0.8033,
-      "eval_samples_per_second": 1867.276,
-      "eval_spearmanr": 0.619343622594654,
-      "eval_steps_per_second": 117.016,
+      "eval_loss": 0.5615702271461487,
+      "eval_pearson": 0.8700848426046829,
+      "eval_runtime": 0.7956,
+      "eval_samples_per_second": 1885.306,
+      "eval_spearmanr": 0.8669432177419766,
+      "eval_steps_per_second": 118.146,
       "step": 36
     }
   ],
   "logging_steps": 500,
-  "max_steps": 90,
+  "max_steps": 72,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 5,
+  "num_train_epochs": 4,
   "save_steps": 500,
   "total_flos": 0,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": {
-    "learning_rate": 9.415997134117997e-05,
-    "num_train_epochs": 5,
+    "learning_rate": 7.44467340014099e-06,
+    "num_train_epochs": 4,
     "per_device_train_batch_size": 32,
-    "seed": 10
+    "seed": 30
   }
 }

run-1/checkpoint-36/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:51a139e4fa7709c7bede3ad4026fd0ba3a4115364cd5d45e61fa50850707d74a
+oid sha256:d8bbecda551ee7774c80dd57136f1f1d264226e7fa9fd5f1198bdad5c555c247
 size 4920

run-1/checkpoint-54/config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "distilbert-base-uncased",
+  "_name_or_path": "SjardiWillems/distilbert-base-uncased-finetuned-stsb",
   "activation": "gelu",
   "architectures": [
     "DistilBertForSequenceClassification"

run-1/checkpoint-54/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:63d0a686e86ce4ef4393aa07b6b8db588c073feae27091860856c2808717d9f6
+oid sha256:92cf87857417fd5a271ff8e3f7f05cb8f2b3bf9ced6ab19218e0d44292e6e573
 size 267829484

run-1/checkpoint-54/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1cee84d246a9f8a291a2fb7c9fc68a8db6bdd89018ab9a07683058f26303c317
+oid sha256:602377490593dd37cc80e0dfaed2a31800416f9f3dd72174f881cf2bc10a80d3
 size 535721146

run-1/checkpoint-54/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e1308769279d9e4a20a12b45bd0f55bd93c1fb250d33283d3781958fc3b1640
-size 14180
+oid sha256:68f892555cbc4056068c9e64ae67a38154f7c60b59e48ad5d5c1ac881101373b
+size 14244

run-1/checkpoint-54/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb92ae17b5d1406007a94b5c248eb158200ab66a366c6ad164369a75ea34cc06
+oid sha256:237de7348e4b2b8379bbb720c2de796479774aa723e7c98c8e4695ddf53e3654
 size 1064

run-1/checkpoint-54/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.8285257169035537,
+  "best_metric": 0.8703279305082289,
   "best_model_checkpoint": "distilbert-base-uncased-finetuned-stsb/run-1/checkpoint-54",
   "epoch": 3.0,
   "eval_steps": 500,
@@ -10,47 +10,47 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_loss": 1.5346204042434692,
-      "eval_pearson": 0.7009517245792942,
-      "eval_runtime": 0.7943,
-      "eval_samples_per_second": 1888.564,
-      "eval_spearmanr": 0.7023215368118,
-      "eval_steps_per_second": 118.35,
+      "eval_loss": 0.557124674320221,
+      "eval_pearson": 0.8691249759376469,
+      "eval_runtime": 0.7812,
+      "eval_samples_per_second": 1920.155,
+      "eval_spearmanr": 0.8666509292845571,
+      "eval_steps_per_second": 120.33,
       "step": 18
     },
     {
       "epoch": 2.0,
-      "eval_loss": 1.7851035594940186,
-      "eval_pearson": 0.6869651194383046,
-      "eval_runtime": 0.8033,
-      "eval_samples_per_second": 1867.276,
-      "eval_spearmanr": 0.619343622594654,
-      "eval_steps_per_second": 117.016,
+      "eval_loss": 0.5615702271461487,
+      "eval_pearson": 0.8700848426046829,
+      "eval_runtime": 0.7956,
+      "eval_samples_per_second": 1885.306,
+      "eval_spearmanr": 0.8669432177419766,
+      "eval_steps_per_second": 118.146,
       "step": 36
     },
     {
       "epoch": 3.0,
-      "eval_loss": 0.7565258741378784,
-      "eval_pearson": 0.8285257169035537,
-      "eval_runtime": 0.8057,
-      "eval_samples_per_second": 1861.771,
-      "eval_spearmanr": 0.8319559534455686,
-      "eval_steps_per_second": 116.671,
+      "eval_loss": 0.5521649718284607,
+      "eval_pearson": 0.8703279305082289,
+      "eval_runtime": 0.7876,
+      "eval_samples_per_second": 1904.585,
+      "eval_spearmanr": 0.8674130106513307,
+      "eval_steps_per_second": 119.354,
       "step": 54
     }
   ],
   "logging_steps": 500,
-  "max_steps": 90,
+  "max_steps": 72,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 5,
+  "num_train_epochs": 4,
   "save_steps": 500,
   "total_flos": 0,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": {
-    "learning_rate": 9.415997134117997e-05,
-    "num_train_epochs": 5,
+    "learning_rate": 7.44467340014099e-06,
+    "num_train_epochs": 4,
     "per_device_train_batch_size": 32,
-    "seed": 10
+    "seed": 30
   }
 }

run-1/checkpoint-54/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:51a139e4fa7709c7bede3ad4026fd0ba3a4115364cd5d45e61fa50850707d74a
+oid sha256:d8bbecda551ee7774c80dd57136f1f1d264226e7fa9fd5f1198bdad5c555c247
 size 4920

run-1/checkpoint-72/config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "distilbert-base-uncased",
+  "_name_or_path": "SjardiWillems/distilbert-base-uncased-finetuned-stsb",
   "activation": "gelu",
   "architectures": [
     "DistilBertForSequenceClassification"

run-1/checkpoint-72/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:811c4d799018a30509db277150ca51e3dbc264fd2ca262396ed468c3be8c5023
+oid sha256:09010ab4aec3f4314a6fbf19d5d86f50e152065c1bdbf728595e8144b34007e0
 size 267829484

run-1/checkpoint-72/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7efdfc68e92672e3116ec19e5d4889bd91c69063beadb49a60cae687dff54702
+oid sha256:c87e402023ea08da918ecf79e43f22a594af2d86d852fabd48fc9b30c4cdc883
 size 535721146

run-1/checkpoint-72/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aeebcd636f12432b58e6760fde0af40330b6a347c141e044ab10daa9547a2507
+oid sha256:16a65aa2435b210924c288e0d36fb69e0b9ec9a6eedd973dd78c384345eb5385
 size 14244

run-1/checkpoint-72/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c45819f1ba1bdcf5c3eb2de79f8854ca776bacbc81caf6c93d4d9ed207f5c8be
+oid sha256:550af093d9b55e6aceb90b4bf22d2d160e1129317cef30da18d37429cab377a7
 size 1064

run-1/checkpoint-72/trainer_state.json

@@ -1,7 +1,7 @@
 {
-  "best_metric": 0.19568172531555392,
+  "best_metric": 0.8705613575789081,
   "best_model_checkpoint": "distilbert-base-uncased-finetuned-stsb/run-1/checkpoint-72",
-  "epoch": 1.0,
+  "epoch": 4.0,
   "eval_steps": 500,
   "global_step": 72,
   "is_hyper_param_search": true,
@@ -10,27 +10,57 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "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,
+      "eval_loss": 0.557124674320221,
+      "eval_pearson": 0.8691249759376469,
+      "eval_runtime": 0.7812,
+      "eval_samples_per_second": 1920.155,
+      "eval_spearmanr": 0.8666509292845571,
+      "eval_steps_per_second": 120.33,
+      "step": 18
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.5615702271461487,
+      "eval_pearson": 0.8700848426046829,
+      "eval_runtime": 0.7956,
+      "eval_samples_per_second": 1885.306,
+      "eval_spearmanr": 0.8669432177419766,
+      "eval_steps_per_second": 118.146,
+      "step": 36
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.5521649718284607,
+      "eval_pearson": 0.8703279305082289,
+      "eval_runtime": 0.7876,
+      "eval_samples_per_second": 1904.585,
+      "eval_spearmanr": 0.8674130106513307,
+      "eval_steps_per_second": 119.354,
+      "step": 54
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.5556716322898865,
+      "eval_pearson": 0.8705613575789081,
+      "eval_runtime": 0.8109,
+      "eval_samples_per_second": 1849.903,
+      "eval_spearmanr": 0.8677375225591853,
+      "eval_steps_per_second": 115.927,
       "step": 72
     }
   ],
   "logging_steps": 500,
-  "max_steps": 288,
+  "max_steps": 72,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 4,
   "save_steps": 500,
   "total_flos": 0,
-  "train_batch_size": 8,
+  "train_batch_size": 32,
   "trial_name": null,
   "trial_params": {
-    "learning_rate": 2.9518876446612178e-06,
+    "learning_rate": 7.44467340014099e-06,
     "num_train_epochs": 4,
-    "per_device_train_batch_size": 8,
-    "seed": 1
+    "per_device_train_batch_size": 32,
+    "seed": 30
   }
 }

run-1/checkpoint-72/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d9b02230c742da2d3d1d91021b9907baf4baff2dbddfb2a93f01fb7c904cc297
+oid sha256:d8bbecda551ee7774c80dd57136f1f1d264226e7fa9fd5f1198bdad5c555c247
 size 4920

run-2/checkpoint-144/config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "distilbert-base-uncased",
+  "_name_or_path": "SjardiWillems/distilbert-base-uncased-finetuned-stsb",
   "activation": "gelu",
   "architectures": [
     "DistilBertForSequenceClassification"

run-2/checkpoint-144/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:21f6582acf44517f58c26e691eb63d014825714aededbd69adac4d339c081105
+oid sha256:e3a1eb309bec98e4c0bf7dfee033a0074f1dde2d1f2ad466a0454ff6be9c67fd
 size 267829484

run-2/checkpoint-144/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:edbf6367e389ba399c49e51c1ee81b1addeb8c1c51c7cda327cee13a75fdfe1b
+oid sha256:6df663a46d003badc963eb0bb254e855924846efa666ebd7f71b034bc82e3d7a
 size 535721146

run-2/checkpoint-144/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83c69057d9a8716b83a57fd1bf30575ccb392f8cc39a8f0e55a46c81c9b5b431
-size 14308
+oid sha256:077f4a3002f49f9466f33d2622e7fdb5cb86e5761168a9f2f3bba8a5ee7f6694
+size 14244

run-2/checkpoint-144/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eaa559c16a11b6cfd5298e6bf6f570bf1e2be2e1785629c53d3a81a22fefc34d
+oid sha256:422ae6c60d9b7e721217d84cfa37769d43f300330524252f7d9f3c18abb48a49
 size 1064

run-2/checkpoint-144/trainer_state.json

@@ -1,7 +1,7 @@
 {
-  "best_metric": 0.820309116112808,
+  "best_metric": 0.8355986744784069,
   "best_model_checkpoint": "distilbert-base-uncased-finetuned-stsb/run-2/checkpoint-144",
-  "epoch": 4.0,
+  "epoch": 1.0,
   "eval_steps": 500,
   "global_step": 144,
   "is_hyper_param_search": true,
@@ -10,57 +10,27 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_loss": 2.4969136714935303,
-      "eval_pearson": 0.32223422122729983,
-      "eval_runtime": 0.9052,
-      "eval_samples_per_second": 1657.071,
-      "eval_spearmanr": 0.32647520010278785,
-      "eval_steps_per_second": 103.843,
-      "step": 36
-    },
-    {
-      "epoch": 2.0,
-      "eval_loss": 1.1902464628219604,
-      "eval_pearson": 0.774068032504475,
-      "eval_runtime": 0.9073,
-      "eval_samples_per_second": 1653.256,
-      "eval_spearmanr": 0.7685396079860547,
-      "eval_steps_per_second": 103.604,
-      "step": 72
-    },
-    {
-      "epoch": 3.0,
-      "eval_loss": 0.845661461353302,
-      "eval_pearson": 0.8156384301074189,
-      "eval_runtime": 0.9602,
-      "eval_samples_per_second": 1562.214,
-      "eval_spearmanr": 0.8142363416044488,
-      "eval_steps_per_second": 97.899,
-      "step": 108
-    },
-    {
-      "epoch": 4.0,
-      "eval_loss": 0.7359773516654968,
-      "eval_pearson": 0.820309116112808,
-      "eval_runtime": 0.9488,
-      "eval_samples_per_second": 1580.967,
-      "eval_spearmanr": 0.8207010328870485,
-      "eval_steps_per_second": 99.074,
+      "eval_loss": 0.9578061699867249,
+      "eval_pearson": 0.8355986744784069,
+      "eval_runtime": 0.7883,
+      "eval_samples_per_second": 1902.903,
+      "eval_spearmanr": 0.8478883362984728,
+      "eval_steps_per_second": 119.249,
       "step": 144
     }
   ],
   "logging_steps": 500,
-  "max_steps": 180,
+  "max_steps": 288,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 5,
+  "num_train_epochs": 2,
   "save_steps": 500,
   "total_flos": 0,
-  "train_batch_size": 16,
+  "train_batch_size": 4,
   "trial_name": null,
   "trial_params": {
-    "learning_rate": 2.5099285971844188e-05,
-    "num_train_epochs": 5,
-    "per_device_train_batch_size": 16,
-    "seed": 8
+    "learning_rate": 5.552203664807529e-05,
+    "num_train_epochs": 2,
+    "per_device_train_batch_size": 4,
+    "seed": 5
   }
 }

run-2/checkpoint-144/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:12643df0525ba3f2bf5dee245df6a74c3697e1dda56998a9dd617f86119470b4
+oid sha256:246413bd9d1435f6c7c69c70d1a2f8591cfec05c6bb21beef22e1bd41910e74b
 size 4920

runs/Mar10_22-33-58_0f0a24039c15/events.out.tfevents.1710110291.0f0a24039c15.273.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a8264c20603bb7a5d00d4cb5cf4d15adea2ce41c92307ca7b2f54048be5b298
+size 5812

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8bbecda551ee7774c80dd57136f1f1d264226e7fa9fd5f1198bdad5c555c247
+oid sha256:246413bd9d1435f6c7c69c70d1a2f8591cfec05c6bb21beef22e1bd41910e74b
 size 4920