Training in progress, step 26, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:56d29b14109af0e68e21142079dd1632f9e502fb1a05cfc12a4cec329b9bc4c4
+oid sha256:e4bd723a82a3e2179d9478b331727447fa1ca5c87051a6025bfb970ebe967cb3
 size 31064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b3184205fa55c0c30cc8363889e43a3c17b0a3f43e22d3d9f47c370098613175
+oid sha256:7ce873bcf540bdac7c4f991d80645511516f0a07356d5979d7f3a1024c4a97cc
 size 71718

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:15160272ffddfe27c654df211d1192733c9457f0ce97b19578f9cd078fb647f8
+oid sha256:638f0e887c7eab30601fcd15f109e577ce9025b567cf9228ffde08282c0e880e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5adea6def46a60dd5782726d51a89bdf0f30226cd791e511d8af09a5644f99e2
+oid sha256:6e65bdb10468d12c8b6afa89fe8730e38a94a4f704431de04b0c1bf27440afce
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.01600985221674877,
+  "epoch": 0.03201970443349754,
   "eval_steps": 10,
-  "global_step": 13,
+  "global_step": 26,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -30,6 +30,21 @@
       "eval_samples_per_second": 618.711,
       "eval_steps_per_second": 77.353,
       "step": 10
+    },
+    {
+      "epoch": 0.024630541871921183,
+      "grad_norm": 0.390516996383667,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 166.0548,
+      "step": 20
+    },
+    {
+      "epoch": 0.024630541871921183,
+      "eval_loss": 10.377897262573242,
+      "eval_runtime": 8.643,
+      "eval_samples_per_second": 632.997,
+      "eval_steps_per_second": 79.139,
+      "step": 20
     }
   ],
   "logging_steps": 10,
@@ -49,7 +64,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5363946356736.0,
+  "total_flos": 10753557528576.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null