Training in progress, step 26, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:abb170f4eb21646db6da17b4cf06241d404c593d56772ab194e4bccc4dd1cb07
+oid sha256:ce188bbbb2c8d0e84d8c3e76eb9406cb2b0cddb8ff849d84b2497a5ec34f0dac
 size 25271744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98e7e9bc3f8ca023b4097d5fe32e80741f85bb5eaebd7b5df2a8110eec60bf91
+oid sha256:d8290fd3fa47cbf3c03a6b73222b4de58f3cfe2a234245edeb7da6a11761fa19
 size 13685516

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8584eb0606268fe40a7b607403caf1bbfdb0ed83707fc0a067fb7329a1dc8581
+oid sha256:4a997aa8bfab00a35d7cfa486126e3d295d226a899068a295415cfc8e8058a7c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4395bafb1cf8adc0d9dbfe550d1b98763496e37a8fadb76c1ca1168a4a757f4e
+oid sha256:37841e69eda911caeb33edeefa0b2f140e72dcce247aeb757b2fe89c00d7887b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.00017370332140793224,
+  "epoch": 0.0003474066428158645,
   "eval_steps": 10,
-  "global_step": 13,
+  "global_step": 26,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -37,6 +37,35 @@
       "eval_samples_per_second": 32.215,
       "eval_steps_per_second": 16.108,
       "step": 10
+    },
+    {
+      "epoch": 0.00020042690931684488,
+      "grad_norm": 10.010727882385254,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 1.2803,
+      "step": 15
+    },
+    {
+      "epoch": 0.0002672358790891265,
+      "grad_norm": 8.734306335449219,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 0.8639,
+      "step": 20
+    },
+    {
+      "epoch": 0.0002672358790891265,
+      "eval_loss": 0.7700777053833008,
+      "eval_runtime": 987.7208,
+      "eval_samples_per_second": 31.904,
+      "eval_steps_per_second": 15.952,
+      "step": 20
+    },
+    {
+      "epoch": 0.0003340448488614081,
+      "grad_norm": 2.2955048084259033,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 0.7105,
+      "step": 25
     }
   ],
   "logging_steps": 5,
@@ -56,7 +85,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 332529571725312.0,
+  "total_flos": 665059143450624.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null