Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:252efd3c2b6b81507ba571e987ec8fc57619490683dcb2b333bf54a1da6b0fd9
+oid sha256:3fd901918a50aacba1095c577026a25063b3d31d7a641e86a09ce8ef49390af4
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6189b3bfb6ede1d5c2409e46c45132d7126ba6b9357e8a3373512e73f85a1bf6
+oid sha256:2382c0838eee7ccf9f3552cae26a5337a64e708e4a2a7100e393e279224af195
 size 64219860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a2043fcab6393039914b1ae1d41f0b06c9cc65053e1770339d2cdf1b4d4fcd1
+oid sha256:8e530f1b21e6744a0cf36a8fe08347c58f3b9d879634a50ea15adbcbf7076b2f
 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": 0.2608695652173913,
+  "epoch": 0.5217391304347826,
   "eval_steps": 3,
-  "global_step": 3,
+  "global_step": 6,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -23,6 +23,21 @@
       "eval_samples_per_second": 6.603,
       "eval_steps_per_second": 3.962,
       "step": 3
+    },
+    {
+      "epoch": 0.43478260869565216,
+      "grad_norm": 17.402477264404297,
+      "learning_rate": 5e-05,
+      "loss": 37.8497,
+      "step": 5
+    },
+    {
+      "epoch": 0.5217391304347826,
+      "eval_loss": 8.449831008911133,
+      "eval_runtime": 0.757,
+      "eval_samples_per_second": 6.605,
+      "eval_steps_per_second": 3.963,
+      "step": 6
     }
   ],
   "logging_steps": 5,
@@ -42,7 +57,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1187334114508800.0,
+  "total_flos": 2532979444285440.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null