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:ea8296502262505e846d860d2323039070852f38b610bf76235b52cad43c4657
+oid sha256:710ec4e03eb8a1329108f3caba576d4ae4c94af7679d016dbf0ba318396f818c
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd15d34e39d649fd0d3b0777707166420d3ae2eea0b7fc3d19f5f2c0397ed2ac
+oid sha256:7de3a0324555635d139d010ae1ff1034492289a5f889595d0cf58cd5e24f89ef
 size 64219860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:390edf6a33ff1f595e7f87de892b284ec2bccd3a3e2701a66d5055a476d66450
+oid sha256:7147ce296746812fb661325c4991f7755b45ce4a53a4d8bba05f4e3f80c1bd78
 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": 0.1305767138193689,
+  "epoch": 0.17410228509249184,
   "eval_steps": 10,
-  "global_step": 30,
+  "global_step": 40,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -60,6 +60,21 @@
       "eval_samples_per_second": 3.485,
       "eval_steps_per_second": 1.747,
       "step": 30
+    },
+    {
+      "epoch": 0.17410228509249184,
+      "grad_norm": 1.3489696979522705,
+      "learning_rate": 2.9289321881345257e-06,
+      "loss": 3.3521,
+      "step": 40
+    },
+    {
+      "epoch": 0.17410228509249184,
+      "eval_loss": 0.20708845555782318,
+      "eval_runtime": 110.1427,
+      "eval_samples_per_second": 3.514,
+      "eval_steps_per_second": 1.761,
+      "step": 40
     }
   ],
   "logging_steps": 10,
@@ -79,7 +94,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.997355714838528e+16,
+  "total_flos": 9.364108383092736e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null