Training in progress, step 39, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2cd08d6eeb1fc46ab2ca1e4746b1d344f4cb50be3d4df3b71811c2248e1eac7e
+oid sha256:276c056549951afba8da14eaf7e11be8c205052d13993819d8c2089d82e16f46
 size 125040

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:877ca9eddabeea2e2880f8471a285c544012d09d541a72b76ab03b8629b9bd5c
+oid sha256:b19d318c5b87040a6a50aaab0e97d9c4395c30655dcd16ba7712e0c2d724e7dc
 size 162868

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f0301aae68db5017871275fbfdb6928fd6f7537f55caa23bacf0eda6ec47376
+oid sha256:46c784a60f4659800f3c4472f150d377d77a69d88547c6e5e024a7e54b3ef12b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:59af5f5d66ecb18e9abb84f5d5074a625502d490e59b29de1e9974286a967cbf
+oid sha256:216e1a9a1c53e7de93f56319b4855910155cb98dd7ebb5fa08b3717fd303059f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0011099252934898612,
+  "epoch": 0.0016648879402347918,
   "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": 376.218,
       "eval_steps_per_second": 188.109,
       "step": 26
+    },
+    {
+      "epoch": 0.0012806830309498398,
+      "grad_norm": 1.0222114324569702,
+      "learning_rate": 8.263518223330697e-05,
+      "loss": 44.3223,
+      "step": 30
+    },
+    {
+      "epoch": 0.0016648879402347918,
+      "eval_loss": 11.067981719970703,
+      "eval_runtime": 26.3157,
+      "eval_samples_per_second": 374.834,
+      "eval_steps_per_second": 187.417,
+      "step": 39
     }
   ],
   "logging_steps": 10,
@@ -64,7 +79,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 349624074240.0,
+  "total_flos": 528052912128.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null