Training in progress, step 45, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a21533af7d9286c4b85780d46f63ce82bc91a1a07fd2463f5b31f9fb0bfd3cb
+oid sha256:89e5ec929a682f97f7a13dca1fbedfae442596450072376d826c8737e1abe091
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:31dfba638d24043d7d0d46c0441998abf40483767c96d96f896be0faa8ace428
+oid sha256:616e2d330f75688d41851622885c80eac2ebfde7d4687f8bbb98231e0b6d400b
 size 81730196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:408a06755b519bb846de2707ae71844004b4b1bde9426470048a53e0c32a92b3
+oid sha256:71b07cdafd3b5e2145088a8972b9442b008f1502e71d5096045be99cb1c123be
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:694a539f11c8d87dcdc9a0523d10086c9a55d2b245bea58f425e64a8cd3022da
+oid sha256:8a8be797a494f7bdae3ea44e950170e2b372b107c6dbe1015cbf67e384b5238e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.05884516366311144,
+  "epoch": 0.06620080912100036,
   "eval_steps": 5,
-  "global_step": 40,
+  "global_step": 45,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -170,6 +170,28 @@
       "eval_samples_per_second": 11.032,
       "eval_steps_per_second": 1.387,
       "step": 40
+    },
+    {
+      "epoch": 0.06178742184626701,
+      "grad_norm": 1.4031445980072021,
+      "learning_rate": 4.7745751406263165e-06,
+      "loss": 6.9848,
+      "step": 42
+    },
+    {
+      "epoch": 0.06620080912100036,
+      "grad_norm": 1.314190149307251,
+      "learning_rate": 1.9030116872178316e-06,
+      "loss": 7.0053,
+      "step": 45
+    },
+    {
+      "epoch": 0.06620080912100036,
+      "eval_loss": 1.7448129653930664,
+      "eval_runtime": 103.8,
+      "eval_samples_per_second": 11.031,
+      "eval_steps_per_second": 1.387,
+      "step": 45
     }
   ],
   "logging_steps": 3,
@@ -189,7 +211,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.227717154832384e+16,
+  "total_flos": 5.881181799186432e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null