Training in progress, step 3980, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7889d14a2444a830b872f5e86d561143f2cbab0ea5ba81dbb788ecd497b6dc12
+oid sha256:6fed8b037293eea965a891ec6faa4a8c5f09e500208437b6e0939687c63268f1
 size 13982248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ef7e9ed4a471e46548d0b25542268f6f7e42b296dc835d21a4629297b643f8a
+oid sha256:2ec148549087fad601f78d26348f8c3cd657d46a252e419103abbe89a0a1b1b2
 size 7062522

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:94bb4d16678255f69acd3c6ad1f7e28dae58deeccef6c73a9ed3860161dd1747
+oid sha256:51370fa33b9c13d5f80ae7fa8db4167f4b87b80a692d734ed71e92d3211caace
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4aa728ff8dd68ad393219e062ef8c6a1fc7dc031ee553ad652965f2249179521
+oid sha256:9f79a2f74b522fa6033abd487865a5913aed0c5f19b8f644e33fa9a5d01b02ca
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.3168,
+  "epoch": 0.3184,
   "eval_steps": 500,
-  "global_step": 3960,
+  "global_step": 3980,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1393,6 +1393,13 @@
       "learning_rate": 2.783381823144452e-05,
       "loss": 3.6398,
       "step": 3960
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 28.959075927734375,
+      "learning_rate": 2.780860247123153e-05,
+      "loss": 3.4484,
+      "step": 3980
     }
   ],
   "logging_steps": 20,
@@ -1400,7 +1407,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 2,
   "save_steps": 20,
-  "total_flos": 9350734873362432.0,
+  "total_flos": 9403552392609792.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null