Training in progress, step 1000

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:536a9ee9dbd08b8bea86c191c81974e31d8a0e16ae6bbd22d8d46671d81d979f
+oid sha256:a4e34b2203ee8078c1abdd7ff566811f7c85414db9b43f161a3f78d00c414945
 size 268290900

run-0/checkpoint-1000/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:537894e7e16b80bbca293d5c82b0651bea7c62a0def8dd8897636638cca7acb1
+oid sha256:a4e34b2203ee8078c1abdd7ff566811f7c85414db9b43f161a3f78d00c414945
 size 268290900

run-0/checkpoint-1000/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6387db917a5dc58afaa3ec6e06850c3635ec46505d0833a4be24a3725676762a
+oid sha256:e72f59dc823a2ba98d454b7f7b154cc865b14a331823a6c6f67413766acde939
 size 536643898

run-0/checkpoint-1000/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed9da1cbe846856af516cf037dd225e7f48e2737ef84c42a9bee0753b8c140ef
+oid sha256:72a4307cca951ef6d42c7f184774e8b1259c78b2bf130b8443ec0b62f6dbf689
 size 1064

run-0/checkpoint-1000/trainer_state.json

@@ -12,15 +12,15 @@
       "epoch": 1.0,
       "eval_accuracy": 0.0064516129032258064,
       "eval_loss": NaN,
-      "eval_runtime": 6.5628,
-      "eval_samples_per_second": 472.357,
-      "eval_steps_per_second": 9.904,
+      "eval_runtime": 5.5627,
+      "eval_samples_per_second": 557.281,
+      "eval_steps_per_second": 11.685,
       "step": 318
     },
     {
       "epoch": 1.5723270440251573,
-      "grad_norm": 98073.078125,
-      "learning_rate": 1.550763701707098e-05,
+      "grad_norm": 107346.4609375,
+      "learning_rate": 1.650593990216632e-05,
       "loss": 0.0,
       "step": 500
     },
@@ -28,32 +28,32 @@
       "epoch": 2.0,
       "eval_accuracy": 0.0064516129032258064,
       "eval_loss": NaN,
-      "eval_runtime": 5.4917,
-      "eval_samples_per_second": 564.492,
-      "eval_steps_per_second": 11.836,
+      "eval_runtime": 6.3989,
+      "eval_samples_per_second": 484.455,
+      "eval_steps_per_second": 10.158,
       "step": 636
     },
     {
       "epoch": 3.0,
       "eval_accuracy": 0.0064516129032258064,
       "eval_loss": NaN,
-      "eval_runtime": 5.7325,
-      "eval_samples_per_second": 540.78,
-      "eval_steps_per_second": 11.339,
+      "eval_runtime": 5.2542,
+      "eval_samples_per_second": 590.003,
+      "eval_steps_per_second": 12.371,
       "step": 954
     },
     {
       "epoch": 3.1446540880503147,
-      "grad_norm": 376953.0,
-      "learning_rate": 1.101527403414196e-05,
+      "grad_norm": 456344.875,
+      "learning_rate": 1.3011879804332637e-05,
       "loss": 0.0,
       "step": 1000
     }
   ],
   "logging_steps": 500,
-  "max_steps": 2226,
+  "max_steps": 2862,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 7,
+  "num_train_epochs": 9,
   "save_steps": 500,
   "stateful_callbacks": {
     "TrainerControl": {
@@ -71,8 +71,8 @@
   "train_batch_size": 48,
   "trial_name": null,
   "trial_params": {
-    "alpha": 0.8432205176909278,
-    "num_train_epochs": 7,
-    "temperature": 11
+    "alpha": 0.3670751935915354,
+    "num_train_epochs": 9,
+    "temperature": 12
   }
 }

run-0/checkpoint-1000/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46d741cf066443975a5eff35413584c615754d6648b0bbbe079a1f1cc886d738
+oid sha256:43bd7cfd55720aa0e94faf0c4ced4f0bf32323b22dee95376cb1f23d04dc327c
 size 5304

runs/Nov11_11-16-16_921d9136ef3a/events.out.tfevents.1731324503.921d9136ef3a.798.4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a33980fa02e25e4dda3fb46372a4e82d6e32e9f3f75b6e787811542cbd1683b
-size 13314
+oid sha256:f68e7d437eb61ac478c4819d666ed8252b6398e6c8a17ac45c82f67cb357c203
+size 13848