Training in progress, step 1500

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4e34b2203ee8078c1abdd7ff566811f7c85414db9b43f161a3f78d00c414945
+oid sha256:9f4654de31a606c58f6239a22491fba62f5fc7354aacd5b7c33a96d6b3f3222a
 size 268290900

run-0/checkpoint-1500/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2be9a9b7ff0b2ae89f8a3a6895506e4640ff6ada1c52b4f420f22a69760294e3
+oid sha256:9f4654de31a606c58f6239a22491fba62f5fc7354aacd5b7c33a96d6b3f3222a
 size 268290900

run-0/checkpoint-1500/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e8ea349a3c9ba233a1fda24675d599f27874b07a0bc29d85f51909946b6a34b
+oid sha256:3a8787ff30461a5792698515d5b3116213c2a1126ad6cbe4ae8dc009c08ad7b4
 size 536643898

run-0/checkpoint-1500/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad4d7d251acf36e559c362893a1fb310c9f46b20e8a330025a14b6829ce4ab07
+oid sha256:693ec081eb0fa0af7d13e289edb194450dd19fdada23346e2af4292ea228535f
 size 1064

run-0/checkpoint-1500/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
     },
@@ -28,24 +28,24 @@
       "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
     },
@@ -53,23 +53,23 @@
       "epoch": 4.0,
       "eval_accuracy": 0.0064516129032258064,
       "eval_loss": NaN,
-      "eval_runtime": 6.0124,
-      "eval_samples_per_second": 515.601,
-      "eval_steps_per_second": 10.811,
+      "eval_runtime": 6.0513,
+      "eval_samples_per_second": 512.289,
+      "eval_steps_per_second": 10.742,
       "step": 1272
     },
     {
       "epoch": 4.716981132075472,
-      "grad_norm": 884346.875,
-      "learning_rate": 6.522911051212939e-06,
+      "grad_norm": 1599939.625,
+      "learning_rate": 9.517819706498952e-06,
       "loss": 0.0,
       "step": 1500
     }
   ],
   "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": {
@@ -87,8 +87,8 @@
   "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-1500/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:f68e7d437eb61ac478c4819d666ed8252b6398e6c8a17ac45c82f67cb357c203
-size 13848
+oid sha256:f32591b4dea909157a6563abe39c694bb1d920562df2010bac46765c73c3d747
+size 14705