Training in progress, step 1500

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ef3d7b0babe94fa5166a9ac6f9db248a8c3aed522dd161e1d5841de8689beec
+oid sha256:744965fc651adbb182875f98c309e15905b940ddfa5ac317af007d18b2f3085e
 size 268290900

run-0/checkpoint-1500/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:47afa4b1b0e62979dcb337995ecb8132628b8d4047de18856ac4bcbd1e6513f1
+oid sha256:744965fc651adbb182875f98c309e15905b940ddfa5ac317af007d18b2f3085e
 size 268290900

run-0/checkpoint-1500/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f408329e8427921d1ee2f6906f49ee54e354b00ecc489e9e35993246bc35364
+oid sha256:e93e14489b8389f84f048b08257878674ed1df885fa0f27111119a629e822b54
 size 536643898

run-0/checkpoint-1500/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb7b4645e59a5c5cb66f63e8bcb5f006c535fd0ea63db9ae152dd586fd465b28
+oid sha256:ad4d7d251acf36e559c362893a1fb310c9f46b20e8a330025a14b6829ce4ab07
 size 1064

run-0/checkpoint-1500/trainer_state.json

@@ -10,66 +10,66 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.5796774193548387,
-      "eval_loss": 0.19598601758480072,
-      "eval_runtime": 5.7949,
-      "eval_samples_per_second": 534.952,
-      "eval_steps_per_second": 11.217,
+      "eval_accuracy": 0.603225806451613,
+      "eval_loss": 0.23406817018985748,
+      "eval_runtime": 5.1784,
+      "eval_samples_per_second": 598.637,
+      "eval_steps_per_second": 12.552,
       "step": 318
     },
     {
       "epoch": 1.5723270440251573,
-      "grad_norm": 0.5235025882720947,
-      "learning_rate": 1.606918238993711e-05,
-      "loss": 0.3143,
+      "grad_norm": 0.57925945520401,
+      "learning_rate": 1.550763701707098e-05,
+      "loss": 0.3716,
       "step": 500
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.8158064516129032,
-      "eval_loss": 0.096437968313694,
-      "eval_runtime": 5.8632,
-      "eval_samples_per_second": 528.722,
-      "eval_steps_per_second": 11.086,
+      "eval_accuracy": 0.8309677419354838,
+      "eval_loss": 0.1094982922077179,
+      "eval_runtime": 5.4255,
+      "eval_samples_per_second": 571.371,
+      "eval_steps_per_second": 11.98,
       "step": 636
     },
     {
       "epoch": 3.0,
-      "eval_accuracy": 0.8754838709677419,
-      "eval_loss": 0.06548532098531723,
-      "eval_runtime": 5.6772,
-      "eval_samples_per_second": 546.048,
-      "eval_steps_per_second": 11.449,
+      "eval_accuracy": 0.8819354838709678,
+      "eval_loss": 0.07135984301567078,
+      "eval_runtime": 5.3165,
+      "eval_samples_per_second": 583.086,
+      "eval_steps_per_second": 12.226,
       "step": 954
     },
     {
       "epoch": 3.1446540880503147,
-      "grad_norm": 0.44506680965423584,
-      "learning_rate": 1.2138364779874214e-05,
-      "loss": 0.1116,
+      "grad_norm": 0.5091490149497986,
+      "learning_rate": 1.101527403414196e-05,
+      "loss": 0.1274,
       "step": 1000
     },
     {
       "epoch": 4.0,
-      "eval_accuracy": 0.8961290322580645,
-      "eval_loss": 0.05135016515851021,
-      "eval_runtime": 5.7349,
-      "eval_samples_per_second": 540.547,
-      "eval_steps_per_second": 11.334,
+      "eval_accuracy": 0.8980645161290323,
+      "eval_loss": 0.055049341171979904,
+      "eval_runtime": 5.431,
+      "eval_samples_per_second": 570.802,
+      "eval_steps_per_second": 11.968,
       "step": 1272
     },
     {
       "epoch": 4.716981132075472,
-      "grad_norm": 0.3050009608268738,
-      "learning_rate": 8.207547169811321e-06,
-      "loss": 0.0728,
+      "grad_norm": 0.3538859486579895,
+      "learning_rate": 6.522911051212939e-06,
+      "loss": 0.0809,
       "step": 1500
     }
   ],
   "logging_steps": 500,
-  "max_steps": 2544,
+  "max_steps": 2226,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 8,
+  "num_train_epochs": 7,
   "save_steps": 500,
   "stateful_callbacks": {
     "TrainerControl": {
@@ -87,8 +87,8 @@
   "train_batch_size": 48,
   "trial_name": null,
   "trial_params": {
-    "alpha": 0.2580849577581932,
-    "num_train_epochs": 8,
-    "temperature": 14
+    "alpha": 0.6968668210901579,
+    "num_train_epochs": 7,
+    "temperature": 5
   }
 }

run-0/checkpoint-1500/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa272c0492b3901fc1a76322efd782d0609261ca66d80f909b4731c779116aae
+oid sha256:30bdc23a7d8fb386178e976baa34d55beb56c6ffba63fe636be670468d00efc1
 size 5240

runs/Oct12_05-09-37_f46fcd247c16/events.out.tfevents.1728710432.f46fcd247c16.522.1

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9146608885308ae52b893829ab25f389758fd06bd5b244595e0881410b759737
-size 13832
+oid sha256:dbd969c14e5a7ee7921b8b862b23e75dd81bcf690e5a4ec6ac08b11a42af3070
+size 14366