Training in progress, step 1500

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c782defad607076aebecdb0e7eed54359fc0992ba5dbf59caea953da1fd39672
+oid sha256:ab1e630acee36a2e7b1c5ce64ebcea556b5c1b0186f663e348234450a9d839bf
 size 268290900

run-1/checkpoint-1500/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0645d9e8a66d2955542c0cff3e54bff3f0885b0665a55271d3a9932f769953fc
+oid sha256:ab1e630acee36a2e7b1c5ce64ebcea556b5c1b0186f663e348234450a9d839bf
 size 268290900

run-1/checkpoint-1500/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e858df0c07455f20f2468927f5855f2ea5805fed77e1079937df03ba47c86de
+oid sha256:a7c6a94a581b393bcb5c25fca86d63594a8d93ba1da7ba69428ef53e61a0b25b
 size 536643898

run-1/checkpoint-1500/trainer_state.json

@@ -10,55 +10,55 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_loss": 0.20451311767101288,
-      "eval_runtime": 3.3051,
-      "eval_samples_per_second": 937.956,
-      "eval_steps_per_second": 19.667,
+      "eval_loss": 0.19908840954303741,
+      "eval_runtime": 3.4704,
+      "eval_samples_per_second": 893.271,
+      "eval_steps_per_second": 18.73,
       "step": 318
     },
     {
       "epoch": 1.57,
-      "grad_norm": 0.5476486682891846,
+      "grad_norm": 0.5476423501968384,
       "learning_rate": 1.371069182389937e-05,
-      "loss": 0.3209,
+      "loss": 0.3126,
       "step": 500
     },
     {
       "epoch": 2.0,
-      "eval_loss": 0.10657776892185211,
-      "eval_runtime": 3.3488,
-      "eval_samples_per_second": 925.71,
-      "eval_steps_per_second": 19.41,
+      "eval_loss": 0.10444473475217819,
+      "eval_runtime": 3.4097,
+      "eval_samples_per_second": 909.18,
+      "eval_steps_per_second": 19.063,
       "step": 636
     },
     {
       "epoch": 3.0,
-      "eval_loss": 0.0766548365354538,
-      "eval_runtime": 3.3351,
-      "eval_samples_per_second": 929.509,
-      "eval_steps_per_second": 19.49,
+      "eval_loss": 0.07558976113796234,
+      "eval_runtime": 3.3435,
+      "eval_samples_per_second": 927.159,
+      "eval_steps_per_second": 19.44,
       "step": 954
     },
     {
       "epoch": 3.14,
-      "grad_norm": 0.5142484903335571,
+      "grad_norm": 0.5030196309089661,
       "learning_rate": 7.421383647798742e-06,
-      "loss": 0.1231,
+      "loss": 0.1205,
       "step": 1000
     },
     {
       "epoch": 4.0,
-      "eval_loss": 0.06451847404241562,
-      "eval_runtime": 3.3356,
-      "eval_samples_per_second": 929.38,
-      "eval_steps_per_second": 19.487,
+      "eval_loss": 0.06385820358991623,
+      "eval_runtime": 3.3553,
+      "eval_samples_per_second": 923.923,
+      "eval_steps_per_second": 19.373,
       "step": 1272
     },
     {
       "epoch": 4.72,
-      "grad_norm": 0.350432813167572,
+      "grad_norm": 0.3436085283756256,
       "learning_rate": 1.1320754716981133e-06,
-      "loss": 0.0885,
+      "loss": 0.0871,
       "step": 1500
     }
   ],
@@ -71,8 +71,8 @@
   "train_batch_size": 48,
   "trial_name": null,
   "trial_params": {
-    "alpha": 0.6466886043446713,
-    "num_train_epochs": 8,
-    "temperature": 13
+    "alpha": 0.20320499954717708,
+    "num_train_epochs": 6,
+    "temperature": 19
   }
 }

run-1/checkpoint-1500/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:787f17d4b84c91e9b55e9fd77b9b388ac3a69fb2918ab4a982181007a952d0ef
+oid sha256:e5f382a675383c3cd8b7905ca7bec8595abcd4866f9bbfeb75d8c432240eabdc
 size 4984