Training in progress, step 40, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e7540ab2b292d8927a6b5738960e8e7f17510d20f3137871c434e0f53e377f9f
+oid sha256:ba1d39e6a45ce9ca1b6f5d86750724a1060d903084f981ece045a95b1a2e2ea8
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f15ba1adfe6077c7b4ca8934ef8ebae59c59ec2a0c801b20ce98b018c7beca2
+oid sha256:25ce3f812a1821964e3c9ff02f3162d5a5ab2d9838b9da7bed8f94ed403fd57d
 size 64219860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7dc5592da1a3cb80376e55f119251ca87a8ed699fbde26682507d52881495a65
+oid sha256:11e0b90ee7b667b22c2f940fcda75f532eb85336078df18089de67b77b3b833c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ef0e768220ab06b0b8ca60bf0cb82c3ba1ffa61503120e1cf6e3622be29cf83
+oid sha256:053f8a597fb71bde446a175404cc18fe6996cf501293c3abfb94953dfd03d780
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.028780429308070513,
+  "epoch": 0.038373905744094015,
   "eval_steps": 10,
-  "global_step": 30,
+  "global_step": 40,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -39,6 +39,21 @@
       "eval_samples_per_second": 5.656,
       "eval_steps_per_second": 2.828,
       "step": 30
+    },
+    {
+      "epoch": 0.038373905744094015,
+      "grad_norm": 18.934436798095703,
+      "learning_rate": 2.9289321881345257e-06,
+      "loss": 33.3571,
+      "step": 40
+    },
+    {
+      "epoch": 0.038373905744094015,
+      "eval_loss": 1.7879064083099365,
+      "eval_runtime": 310.5118,
+      "eval_samples_per_second": 5.655,
+      "eval_steps_per_second": 2.828,
+      "step": 40
     }
   ],
   "logging_steps": 40,
@@ -58,7 +73,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.79946916642816e+16,
+  "total_flos": 5.06595888857088e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null