Training in progress, step 2862

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cfc628babb555ae2f429f83e3f16920bfaec2d248c3d76ec9666551db0f681ab
+oid sha256:653b0e018e72d692bf7628138f5d4a36847a2a672b4dbcdcc6ed9cf77b0428aa
 size 268290900

run-17/checkpoint-2862/config.json

@@ -326,6 +326,6 @@
   "sinusoidal_pos_embds": false,
   "tie_weights_": true,
   "torch_dtype": "float32",
-  "transformers_version": "4.47.1",
+  "transformers_version": "4.47.0",
   "vocab_size": 30522
 }

run-17/checkpoint-2862/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c18c4a133656b004cd6c65fc4815e9ef62f1ec3522774d37fb11c5daa779d3e2
+oid sha256:653b0e018e72d692bf7628138f5d4a36847a2a672b4dbcdcc6ed9cf77b0428aa
 size 268290900

run-17/checkpoint-2862/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a81143e1443ee75c0758f59ffc911f4898c4f4e07b40479ce205da7301c876f7
-size 536643898
+oid sha256:c9431bd5195dc5efa71f284143d1f44afc0195adc6d056b4cefa0075f55e7845
+size 536641018

run-17/checkpoint-2862/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:41b5282f1cde964bf5a382eb03f1cdd87f1c8e2f60e43277b3453f63947f5933
-size 14244
+oid sha256:e29353d4954fcf585947caa6a0a3fa59c7379d49f3bc56c6a4bd276fef18ca98
+size 13990

run-17/checkpoint-2862/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a738824491ff8b261b6db2a842e15bf80355d04a07892a16df2c4715b2ee556
+oid sha256:3c64bfaed33db311081ee0596530a03699ac7659f0cf4f57a488fea34df98816
 size 1064

run-17/checkpoint-2862/trainer_state.json

@@ -10,137 +10,137 @@
   "log_history": [
     {
       "epoch": 0.9968553459119497,
-      "grad_norm": 0.9016032814979553,
+      "grad_norm": 0.6738103628158569,
       "learning_rate": 1.7784765897973445e-05,
-      "loss": 0.8053,
+      "loss": 0.4958,
       "step": 317
     },
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.6696774193548387,
-      "eval_loss": 0.40919938683509827,
-      "eval_runtime": 1.6439,
-      "eval_samples_per_second": 1885.749,
-      "eval_steps_per_second": 39.54,
+      "eval_accuracy": 0.6290322580645161,
+      "eval_loss": 0.24582983553409576,
+      "eval_runtime": 3.3797,
+      "eval_samples_per_second": 917.252,
+      "eval_steps_per_second": 19.233,
       "step": 318
     },
     {
       "epoch": 1.9937106918238994,
-      "grad_norm": 0.7222766876220703,
+      "grad_norm": 0.5609093308448792,
       "learning_rate": 1.556953179594689e-05,
-      "loss": 0.3073,
+      "loss": 0.2002,
       "step": 634
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.844516129032258,
-      "eval_loss": 0.13953416049480438,
-      "eval_runtime": 1.6434,
-      "eval_samples_per_second": 1886.366,
-      "eval_steps_per_second": 39.553,
+      "eval_accuracy": 0.8429032258064516,
+      "eval_loss": 0.10813045501708984,
+      "eval_runtime": 3.0019,
+      "eval_samples_per_second": 1032.674,
+      "eval_steps_per_second": 21.653,
       "step": 636
     },
     {
       "epoch": 2.990566037735849,
-      "grad_norm": 0.6133838891983032,
+      "grad_norm": 0.587248682975769,
       "learning_rate": 1.3354297693920338e-05,
-      "loss": 0.1428,
+      "loss": 0.1161,
       "step": 951
     },
     {
       "epoch": 3.0,
-      "eval_accuracy": 0.8964516129032258,
-      "eval_loss": 0.0722731500864029,
-      "eval_runtime": 1.6496,
-      "eval_samples_per_second": 1879.251,
-      "eval_steps_per_second": 39.404,
+      "eval_accuracy": 0.8893548387096775,
+      "eval_loss": 0.06641113013029099,
+      "eval_runtime": 3.0082,
+      "eval_samples_per_second": 1030.502,
+      "eval_steps_per_second": 21.607,
       "step": 954
     },
     {
       "epoch": 3.9874213836477987,
-      "grad_norm": 0.5777781009674072,
+      "grad_norm": 0.4174334406852722,
       "learning_rate": 1.1139063591893781e-05,
-      "loss": 0.0917,
+      "loss": 0.0829,
       "step": 1268
     },
     {
       "epoch": 4.0,
-      "eval_accuracy": 0.9180645161290323,
-      "eval_loss": 0.050948865711688995,
-      "eval_runtime": 1.4494,
-      "eval_samples_per_second": 2138.806,
-      "eval_steps_per_second": 44.846,
+      "eval_accuracy": 0.9048387096774193,
+      "eval_loss": 0.04835071042180061,
+      "eval_runtime": 3.0244,
+      "eval_samples_per_second": 1025.01,
+      "eval_steps_per_second": 21.492,
       "step": 1272
     },
     {
       "epoch": 4.984276729559748,
-      "grad_norm": 0.4380759596824646,
+      "grad_norm": 0.3136546015739441,
       "learning_rate": 8.923829489867226e-06,
-      "loss": 0.0715,
+      "loss": 0.0669,
       "step": 1585
     },
     {
       "epoch": 5.0,
-      "eval_accuracy": 0.9232258064516129,
-      "eval_loss": 0.042863838374614716,
-      "eval_runtime": 1.6395,
-      "eval_samples_per_second": 1890.819,
-      "eval_steps_per_second": 39.646,
+      "eval_accuracy": 0.9148387096774193,
+      "eval_loss": 0.039326973259449005,
+      "eval_runtime": 3.0031,
+      "eval_samples_per_second": 1032.25,
+      "eval_steps_per_second": 21.644,
       "step": 1590
     },
     {
       "epoch": 5.981132075471698,
-      "grad_norm": 0.46454158425331116,
+      "grad_norm": 0.3310624957084656,
       "learning_rate": 6.708595387840672e-06,
-      "loss": 0.0617,
+      "loss": 0.058,
       "step": 1902
     },
     {
       "epoch": 6.0,
-      "eval_accuracy": 0.9261290322580645,
-      "eval_loss": 0.03817891329526901,
-      "eval_runtime": 1.8355,
-      "eval_samples_per_second": 1688.925,
-      "eval_steps_per_second": 35.413,
+      "eval_accuracy": 0.9212903225806451,
+      "eval_loss": 0.03441833332180977,
+      "eval_runtime": 3.0173,
+      "eval_samples_per_second": 1027.407,
+      "eval_steps_per_second": 21.542,
       "step": 1908
     },
     {
       "epoch": 6.977987421383648,
-      "grad_norm": 0.34600403904914856,
+      "grad_norm": 0.366222620010376,
       "learning_rate": 4.4933612858141165e-06,
-      "loss": 0.0562,
+      "loss": 0.0526,
       "step": 2219
     },
     {
       "epoch": 7.0,
-      "eval_accuracy": 0.9303225806451613,
-      "eval_loss": 0.035540465265512466,
-      "eval_runtime": 1.8369,
-      "eval_samples_per_second": 1687.632,
-      "eval_steps_per_second": 35.386,
+      "eval_accuracy": 0.9241935483870968,
+      "eval_loss": 0.03173591569066048,
+      "eval_runtime": 3.0023,
+      "eval_samples_per_second": 1032.538,
+      "eval_steps_per_second": 21.65,
       "step": 2226
     },
     {
       "epoch": 7.9748427672955975,
-      "grad_norm": 0.32331326603889465,
+      "grad_norm": 0.3408018946647644,
       "learning_rate": 2.2781271837875614e-06,
-      "loss": 0.053,
+      "loss": 0.0495,
       "step": 2536
     },
     {
       "epoch": 8.0,
-      "eval_accuracy": 0.932258064516129,
-      "eval_loss": 0.034126147627830505,
-      "eval_runtime": 1.8294,
-      "eval_samples_per_second": 1694.566,
-      "eval_steps_per_second": 35.531,
+      "eval_accuracy": 0.9258064516129032,
+      "eval_loss": 0.03004557453095913,
+      "eval_runtime": 3.0017,
+      "eval_samples_per_second": 1032.734,
+      "eval_steps_per_second": 21.654,
       "step": 2544
     },
     {
       "epoch": 8.971698113207546,
-      "grad_norm": 0.3256802558898926,
+      "grad_norm": 0.5218478441238403,
       "learning_rate": 6.289308176100629e-08,
-      "loss": 0.0511,
+      "loss": 0.0479,
       "step": 2853
     }
   ],
@@ -161,12 +161,12 @@
       "attributes": {}
     }
   },
-  "total_flos": 744918075986196.0,
+  "total_flos": 745151547572796.0,
   "train_batch_size": 48,
   "trial_name": null,
   "trial_params": {
-    "alpha": 0.8523684644932737,
+    "alpha": 0.8675533183457913,
     "num_train_epochs": 9,
-    "temperature": 2
+    "temperature": 4
   }
 }

run-17/checkpoint-2862/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2604ed4b06bd9bd0b94d7de27f6549fd8ad42a818c36e531355fafadbef23c48
-size 5368
+oid sha256:d55f72d033e4da62205f611e22d64151820ef3799975ce2ff32a7cb5cd94ac1d
+size 5432

runs/Dec20_17-34-05_bogon/events.out.tfevents.1734707491.bogon.92058.38

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8cd3abb7c9385905eb508f413556cc1c806fd77d480e6f41d3dc159af803ce7
+size 17362

runs/Dec20_17-34-05_bogon/events.out.tfevents.1734707831.bogon.92058.39

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d457f3d0626a8525903d0030376ce1c802313696d461f6239ffd3e7338d5a0de
+size 17361

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1bd9708c89b147ce5b970a39b5ef0e4e1fc9f7f54c09c1ab92bd452299bbe14b
+oid sha256:d55f72d033e4da62205f611e22d64151820ef3799975ce2ff32a7cb5cd94ac1d
 size 5432