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:caa68d43a099dcc1ca2fd5850819f795e2e52b4094a6a8e948b51b7911bb79df
+oid sha256:658cb825c8fbc9f03087c2713068fccf345105b8576457c8f9a845d091f44a46
 size 80792096

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:03f4451335d41697719dc191bee937cf883681268a7835a80057f03656c1e3c5
+oid sha256:ece8c5d7501d57bfb41a07a5d4092a5193e704d591fd506c7c22223a7015d4d2
 size 41459700

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a6df151c1db4e39f20b86799afe93a736aa768e2fb3b40047b3bc4341ece26bb
+oid sha256:0f77bc18fd26ad35e6b7268b0955d0a003545cef8d5e575884f8deb878342895
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e65bdb10468d12c8b6afa89fe8730e38a94a4f704431de04b0c1bf27440afce
+oid sha256:75c3c8ae7ddabeca3cb69703f6b35f00b9125a4c27b56ccba4ed0e4669bb5433
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.4135188866799205,
+  "epoch": 0.6202783300198808,
   "eval_steps": 10,
-  "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": 19.391,
       "eval_steps_per_second": 2.424,
       "step": 20
+    },
+    {
+      "epoch": 0.47713717693836977,
+      "grad_norm": 4.839845657348633,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.5005,
+      "step": 30
+    },
+    {
+      "epoch": 0.47713717693836977,
+      "eval_loss": 0.3772498667240143,
+      "eval_runtime": 21.9833,
+      "eval_samples_per_second": 19.287,
+      "eval_steps_per_second": 2.411,
+      "step": 30
     }
   ],
   "logging_steps": 10,
@@ -64,7 +79,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7.249365951735398e+16,
+  "total_flos": 1.0874048927603098e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null