Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a97a5a5e4223d5d1a7b9d699505c3f2e27209c7080f28ee4c920665cf741fd1
+oid sha256:322b1adb1c2a13bbdb198735b13acdec6d29d7899af427e1e8ca47e474898505
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01eff959233dbf56448a96733fdb1bf847580c3278a09a0e4965850271000de6
+oid sha256:5f8c5e5180e20f329800cd9adc0dec24171fa6566abe84aa3fe102b1d0153bde
 size 64219860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ebefa66f685e689769adaafd457264ae6777a954ae0a77f34d7684be2682c30
+oid sha256:a6a629bcc4d1cf05d0ed241ade838414811cac61f7bea2bcdb22033b753ca109
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
+oid sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.014475271411338963,
+  "epoch": 0.021712907117008445,
   "eval_steps": 3,
-  "global_step": 6,
+  "global_step": 9,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -73,6 +73,35 @@
       "eval_samples_per_second": 9.155,
       "eval_steps_per_second": 4.603,
       "step": 6
+    },
+    {
+      "epoch": 0.016887816646562123,
+      "grad_norm": 53.515289306640625,
+      "learning_rate": 0.00014,
+      "loss": 31.9477,
+      "step": 7
+    },
+    {
+      "epoch": 0.019300361881785282,
+      "grad_norm": 38.597110748291016,
+      "learning_rate": 0.00016,
+      "loss": 27.3812,
+      "step": 8
+    },
+    {
+      "epoch": 0.021712907117008445,
+      "grad_norm": 32.72773742675781,
+      "learning_rate": 0.00018,
+      "loss": 20.9595,
+      "step": 9
+    },
+    {
+      "epoch": 0.021712907117008445,
+      "eval_loss": 3.9651339054107666,
+      "eval_runtime": 19.1412,
+      "eval_samples_per_second": 9.143,
+      "eval_steps_per_second": 4.597,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1899722503618560.0,
+  "total_flos": 2849583755427840.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null