Training in progress, step 26, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46b0a02ce114ba44f9af855cd27de865daca8d4e4db304200c4144e09da24c52
+oid sha256:f0964da93fafaace82eb60e1dda07e8a124b1339762e80d952ffee42b96bbddd
 size 161714

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:405c0e5c6f9c6bff74d097cb5fd9de736ea0dca6e70fb4e53d2ee4f78cdb237d
+oid sha256:565f43c81d9c6bfa355c20e652170b295c39c706735d090c05c1c0142ab54d15
 size 64750

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:872c1161ac0d8b2e9f04a948a3b27a13cec6f9ed82cefc1f06cd5658419b5833
+oid sha256:27e993de387eaf1c76836fe66cd1e5dad0a9ea203c11a45d9654a843d94d4d08
 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": 0.010021198689535556,
+  "epoch": 0.02004239737907111,
   "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": 53.151,
       "eval_steps_per_second": 26.624,
       "step": 10
+    },
+    {
+      "epoch": 0.011562921564848718,
+      "grad_norm": 0.2759840488433838,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 6.9246,
+      "step": 15
+    },
+    {
+      "epoch": 0.015417228753131625,
+      "grad_norm": 0.2750642001628876,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 6.9265,
+      "step": 20
+    },
+    {
+      "epoch": 0.015417228753131625,
+      "eval_loss": 6.918467044830322,
+      "eval_runtime": 10.2873,
+      "eval_samples_per_second": 53.172,
+      "eval_steps_per_second": 26.635,
+      "step": 20
+    },
+    {
+      "epoch": 0.01927153594141453,
+      "grad_norm": 0.313626229763031,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 6.9111,
+      "step": 25
     }
   ],
   "logging_steps": 5,
@@ -56,7 +85,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 34276589568.0,
+  "total_flos": 68553179136.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null