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:ca27984ef7ac6d1b29eb9636107430dc660956e230c49c57192aa2ed7c90b35a
+oid sha256:e520e2062390f691677e43549d67e7ceb52992764853048fc01c6eb453a69a98
 size 17640136

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0cbc660716f36c0c8edaec864b633559a9cf41e551798bec5d111c6f15deda48
+oid sha256:c9c97edca254d40069d81d01d48b3dd97ccc236e726f8736f69e1bb0a85fc738
 size 9568884

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:54a660fe1685e8a6b7a3af3fc232b2540a63f4d3847dc6daad940db92f4e5b7e
+oid sha256:bbba3e37f3da5eebd20241eda5b6317a6fa8037aef8c40511f6d82de78527891
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8712da1b2787df41952a507984ec77e0f72c59fac7ee6cf21606445686249de
+oid sha256:ccc7e73cc5879da996ace4c3a10d9efe08a100111973e801d61997747e95e982
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.002935199819372319,
+  "epoch": 0.004402799729058478,
   "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": 56.537,
       "eval_steps_per_second": 28.268,
       "step": 26
+    },
+    {
+      "epoch": 0.0033867690223526757,
+      "grad_norm": 5.793719291687012,
+      "learning_rate": 0.0001,
+      "loss": 3.5491,
+      "step": 30
+    },
+    {
+      "epoch": 0.004402799729058478,
+      "eval_loss": 3.3603410720825195,
+      "eval_runtime": 66.8815,
+      "eval_samples_per_second": 55.77,
+      "eval_steps_per_second": 27.885,
+      "step": 39
     }
   ],
   "logging_steps": 10,
@@ -64,7 +79,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 231499225890816.0,
+  "total_flos": 347248838836224.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null