Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a7a3a7cbf677bcaa3d09bbf754f3ef38d7d58607818fa57a01123ee7c0f18917
+oid sha256:662ac36374eb95cf6d0ecb8dc7383c2145e3272ede89caa37971de5727f0a3fc
 size 93608

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b3292ce93c0d19d6ed4fc537b2aad230e2d79b999c094e5706e198a420ef239
+oid sha256:e3d6d62df0d88f8721c4983a2ed8228845d9793a2cb4dddf86fe8eaa13227e64
 size 197158

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:372c9c91189dafe7a0013b948ff9907e60fc7ad4b32cc7ac3bccb3f603cf2268
+oid sha256:224258860bc5cff9f205d97ac5c1dc59aa62cd3755d71e40d0c636a476b22317
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a991012fbb3e0053bc41a0b782b67db27509c27d2801c8bf4a64c3687e55e582
+oid sha256:02d97e2af7e51ba89efcffc7f2a661ca0885e61db7f78987db5df30514ab62df
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.2696629213483146,
+  "epoch": 0.3595505617977528,
   "eval_steps": 5,
-  "global_step": 15,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -74,6 +74,21 @@
       "eval_samples_per_second": 95.669,
       "eval_steps_per_second": 24.426,
       "step": 15
+    },
+    {
+      "epoch": 0.3235955056179775,
+      "grad_norm": 0.3423050045967102,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 11.9214,
+      "step": 18
+    },
+    {
+      "epoch": 0.3595505617977528,
+      "eval_loss": 11.91664981842041,
+      "eval_runtime": 0.9795,
+      "eval_samples_per_second": 95.969,
+      "eval_steps_per_second": 24.503,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -93,7 +108,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 142214430720.0,
+  "total_flos": 189820108800.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null