Training in progress, step 26, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02d99c99bc7c551fd395614eb397ccd0fc7df6fe0fb8186a84cb3f8a1ab79222
+oid sha256:bb290fc1ad5ec42962fc11c1d25272019c032f1f8702388e8191adfca662a8aa
 size 48679352

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:34c69ebf098637a4be6f262139082faf57936c54ffec5fb6712ebd0e261a4433
+oid sha256:d367a5380a328fecbd80875c580d669cd4df64c4065c6f3df02b5d101ecec26c
 size 25152500

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33e0496dcdb9c09786e531fcb26e12c27114121c2227d15a22d343188a83ccc7
+oid sha256:2128e47ed2e40d2cfe486fec9abc63fcf3bab8260c2a57f50edbff5866f86c2f
 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": 0.04343286698684485,
+  "epoch": 0.0868657339736897,
   "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": 32.89,
       "eval_steps_per_second": 4.126,
       "step": 10
+    },
+    {
+      "epoch": 0.0668197953643767,
+      "grad_norm": 0.8087164163589478,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 0.5268,
+      "step": 20
+    },
+    {
+      "epoch": 0.0668197953643767,
+      "eval_loss": NaN,
+      "eval_runtime": 61.2816,
+      "eval_samples_per_second": 32.914,
+      "eval_steps_per_second": 4.128,
+      "step": 20
     }
   ],
   "logging_steps": 10,
@@ -49,7 +64,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.447103935021056e+16,
+  "total_flos": 2.894207870042112e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null