Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:36010d9975dc9459267a502aaca2ecd8f5edcf766161e026f392634be0122d9d
+oid sha256:e33924f9cdb98a93251b06b94c0849f3fba614512f1298d1d0a9f9c893679636
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c0de126de300a1fa23cc02946195a84bf90f2c16bc178142db9242b533563716
+oid sha256:b1c8b327c3a50ead211e7dbe60f073fa972e3c33c42e6f0f0f9a7efb0ad88925
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de94d80877c889f25ec36d51d0b33d7e85be1e8ae9f493495fdb65abc744238b
+oid sha256:793e49fa41f48955d210aed6c8e1fbdcac43ce6a8f0ab68ba7c6dfbae402f000
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc78163c347c258a17d5fa38a4e22e79b63c35d2cfce0e026e30c38b9ae55f80
+oid sha256:92b4cf85d7ba7a497f88ff799bf4dec5af7dd95be6e00f78bf46ba5deb56bbf8
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0007841984021957555,
+  "epoch": 0.001568396804391511,
   "eval_steps": 3,
-  "global_step": 3,
+  "global_step": 6,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -44,6 +44,35 @@
       "eval_samples_per_second": 6.321,
       "eval_steps_per_second": 3.161,
       "step": 3
+    },
+    {
+      "epoch": 0.0010455978695943407,
+      "grad_norm": 0.9703998565673828,
+      "learning_rate": 4e-05,
+      "loss": 0.3465,
+      "step": 4
+    },
+    {
+      "epoch": 0.0013069973369929258,
+      "grad_norm": 0.7693590521812439,
+      "learning_rate": 5e-05,
+      "loss": 0.2594,
+      "step": 5
+    },
+    {
+      "epoch": 0.001568396804391511,
+      "grad_norm": 0.8005192279815674,
+      "learning_rate": 6e-05,
+      "loss": 0.2363,
+      "step": 6
+    },
+    {
+      "epoch": 0.001568396804391511,
+      "eval_loss": NaN,
+      "eval_runtime": 1020.151,
+      "eval_samples_per_second": 6.316,
+      "eval_steps_per_second": 3.158,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.7805294805450752e+16,
+  "total_flos": 3.5610589610901504e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null