Training in progress, step 45, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c6b7224c96325fdb23a2226d1febe7c2c5c9b5c55b076eadc164126d96ef7df1
+oid sha256:60dd3854bf6d29a499964e4f11098e6810ae98c6bb0e872b79a72f6fa033c8c4
 size 247936

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d31b2fe81050c36ba30c6ac20a7091e3a16b90a8d8e9c5bb202fe93433602980
+oid sha256:6cb03c27b6f613e4ad09ed2d22c9aaee953dea497b1d6d962401a302e0756f3c
 size 263024

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:911e72134441cd7a162f9396575524d703f25ba390bc65bdb98456ed840ba960
+oid sha256:add90063e1e616d6ac6be40dd95ded3a73a340bb31303d1ec63f0b2f30524740
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b09cef78339a08679f2a6cf4a4b56eca3094fb6b859867afd839be3db1415460
+oid sha256:0896677f34f08366c4c71a3f69133212afc490296ec7ee225b8aefde1f38f24c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.04092071611253197,
+  "epoch": 0.05115089514066496,
   "eval_steps": 9,
-  "global_step": 36,
+  "global_step": 45,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -131,6 +131,35 @@
       "eval_samples_per_second": 155.978,
       "eval_steps_per_second": 39.152,
       "step": 36
+    },
+    {
+      "epoch": 0.0443307757885763,
+      "grad_norm": 1.2622820138931274,
+      "learning_rate": 7.649596321166024e-05,
+      "loss": 43.855,
+      "step": 39
+    },
+    {
+      "epoch": 0.04774083546462063,
+      "grad_norm": 1.1330219507217407,
+      "learning_rate": 7.191855733945387e-05,
+      "loss": 43.8811,
+      "step": 42
+    },
+    {
+      "epoch": 0.05115089514066496,
+      "grad_norm": 1.1096593141555786,
+      "learning_rate": 6.710100716628344e-05,
+      "loss": 43.8743,
+      "step": 45
+    },
+    {
+      "epoch": 0.05115089514066496,
+      "eval_loss": 10.961272239685059,
+      "eval_runtime": 4.7683,
+      "eval_samples_per_second": 155.4,
+      "eval_steps_per_second": 39.007,
+      "step": 45
     }
   ],
   "logging_steps": 3,
@@ -150,7 +179,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 318520688640.0,
+  "total_flos": 397116702720.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null