Training in progress, step 39, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d6789cc6290b6106838534ea1a900b7ce119f88c67b6b5c6f7a037b58d7aa6e5
+oid sha256:cac85607c9fbf9d10eeaf69d96434458e5a0fdb9ad0d730fa7c65ea94dada29c
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80e50d2bd97cb110afa0d465ebebdb6c908ceddda0484e75223c141007c67ae1
+oid sha256:d52b055aa13043e4e6a6b82c9147848c07a8ec4b1cfe7238d12bf4d1ec04b3c5
 size 64219860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1524d6216e42e36e3ae993ad521ab277b184f833ce70f98c345e5a3bfe1d0cf
+oid sha256:19fe7f4523f948a940f0c9bcc718353f7ff70e31ee7567f30f2aa6254ec62566
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:562360b448a53e7366b8643d15ad250a0f706aaefd28e30d76b7f5f4480c7196
+oid sha256:e2ff6f184064d83b8d06f27cab522b7fa1e27d3258094d54e6a8c251936b5ccb
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.021834977955070334,
+  "epoch": 0.0327524669326055,
   "eval_steps": 13,
-  "global_step": 26,
+  "global_step": 39,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -45,6 +45,21 @@
       "eval_samples_per_second": 10.879,
       "eval_steps_per_second": 5.439,
       "step": 26
+    },
+    {
+      "epoch": 0.025194205332773462,
+      "grad_norm": 1.608473300933838,
+      "learning_rate": 0.0002,
+      "loss": 2.1019,
+      "step": 30
+    },
+    {
+      "epoch": 0.0327524669326055,
+      "eval_loss": 0.4722355604171753,
+      "eval_runtime": 46.1649,
+      "eval_samples_per_second": 10.874,
+      "eval_steps_per_second": 5.437,
+      "step": 39
     }
   ],
   "logging_steps": 10,
@@ -64,7 +79,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.646426169802752e+16,
+  "total_flos": 2.469639254704128e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null