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:d0ec0af4433ae0e00fc852f9163d3af5d8db174d86563faafe1a4abd80e28831
+oid sha256:3463edaf8517b8bb6a43b2733cd0149593c3dfab6752cb7a32381dffb8381184
 size 12609312

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:860dcc3de448253ca64c8d7b37b89f11c6d63532113759d1773155553bb7dad4
+oid sha256:640d4ea89b4c7c3d76284b50de3df84ba2df493ef47f868d4795dda03719787b
 size 6615034

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bea10c03591055cf44e836c313c855f98bdb47188aa78f6fcad2d1f731802fd8
+oid sha256:13031e371b36fba6bb3646662eea9951ce21847cadb86dbb2b7494686efb8ec8
 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": 0.020850040096230954,
+  "epoch": 0.04170008019246191,
   "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": 48.291,
       "eval_steps_per_second": 24.237,
       "step": 10
+    },
+    {
+      "epoch": 0.024057738572574178,
+      "grad_norm": 42.92169189453125,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 11.0683,
+      "step": 15
+    },
+    {
+      "epoch": 0.03207698476343224,
+      "grad_norm": 44.35247802734375,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 10.8371,
+      "step": 20
+    },
+    {
+      "epoch": 0.03207698476343224,
+      "eval_loss": NaN,
+      "eval_runtime": 5.4284,
+      "eval_samples_per_second": 48.449,
+      "eval_steps_per_second": 24.316,
+      "step": 20
+    },
+    {
+      "epoch": 0.040096230954290296,
+      "grad_norm": 37.52597427368164,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 10.8294,
+      "step": 25
     }
   ],
   "logging_steps": 5,
@@ -56,7 +85,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 116240349659136.0,
+  "total_flos": 234673913462784.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null