Training in progress, step 1500

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:59aaa84190c52a039f51c36d7cdf7843a54ba9681c4aa7cdfc1a073f739fbed5
+oid sha256:49ea815675a34cbac9041de1da9a12ba61041e70f135f09a49e7225458df2955
 size 268290900

run-0/checkpoint-1500/trainer_state.json

@@ -11,9 +11,9 @@
     {
       "epoch": 1.0,
       "eval_loss": 0.4282287061214447,
-      "eval_runtime": 3.2301,
-      "eval_samples_per_second": 959.713,
-      "eval_steps_per_second": 20.123,
+      "eval_runtime": 3.2319,
+      "eval_samples_per_second": 959.178,
+      "eval_steps_per_second": 20.112,
       "step": 318
     },
     {
@@ -26,17 +26,17 @@
     {
       "epoch": 2.0,
       "eval_loss": 0.1691545695066452,
-      "eval_runtime": 3.3122,
-      "eval_samples_per_second": 935.929,
-      "eval_steps_per_second": 19.624,
+      "eval_runtime": 3.2816,
+      "eval_samples_per_second": 944.667,
+      "eval_steps_per_second": 19.808,
       "step": 636
     },
     {
       "epoch": 3.0,
       "eval_loss": 0.09601032733917236,
-      "eval_runtime": 3.3191,
-      "eval_samples_per_second": 933.993,
-      "eval_steps_per_second": 19.584,
+      "eval_runtime": 3.3082,
+      "eval_samples_per_second": 937.058,
+      "eval_steps_per_second": 19.648,
       "step": 954
     },
     {
@@ -49,9 +49,9 @@
     {
       "epoch": 4.0,
       "eval_loss": 0.07325955480337143,
-      "eval_runtime": 3.3266,
-      "eval_samples_per_second": 931.889,
-      "eval_steps_per_second": 19.54,
+      "eval_runtime": 3.4009,
+      "eval_samples_per_second": 911.523,
+      "eval_steps_per_second": 19.113,
       "step": 1272
     },
     {
@@ -71,7 +71,7 @@
   "train_batch_size": 48,
   "trial_name": null,
   "trial_params": {
-    "alpha": 0.10630408646687006,
+    "alpha": 0.31661862639116345,
     "num_train_epochs": 9,
     "temperature": 2
   }