Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:63db404981a8a6bb85e05dc7294190ed500234be5f1ed31c283ba0748bc0988e
+oid sha256:ee4401ee85060645b9859fc1c9ffcafdb717a9e27abcaa73cae55baf0fd07484
 size 25192688

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea8ed00aab7f294707ceb45341c4f3d7f1bdf982cd1c8f128239c943c9ab92c6
+oid sha256:d5e6f2d676530731ed90e8af67b4882e3679aa13b319f4e5b98d63edc3caa235
 size 50493050

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77a2fa9115c7d5c04ea0203640cd1ef4267fcc53f03e112044e2c03bbd36f855
+oid sha256:24268d68cd2144d5eb0a6d21f8cf0b27030c12131d82df42a3468a1c5df11630
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4849a6ac0a1d895740f1ab4eba9d346b8d898008d0cfe93dd108cd928d7c63e
+oid sha256:46d68217ddf3e899bf1495ee33b9ec14e2c91ed912ffcb460a7bb01192b04b7d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.03606853020739405,
+  "epoch": 0.0721370604147881,
   "eval_steps": 5,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -52,6 +52,43 @@
       "eval_samples_per_second": 22.491,
       "eval_steps_per_second": 11.342,
       "step": 10
+    },
+    {
+      "epoch": 0.04328223624887286,
+      "grad_norm": 2.9499218463897705,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 11.876,
+      "step": 12
+    },
+    {
+      "epoch": 0.05410279531109107,
+      "grad_norm": 177.76881408691406,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 12.124,
+      "step": 15
+    },
+    {
+      "epoch": 0.05410279531109107,
+      "eval_loss": 2.8049392700195312,
+      "eval_runtime": 5.2024,
+      "eval_samples_per_second": 22.489,
+      "eval_steps_per_second": 11.341,
+      "step": 15
+    },
+    {
+      "epoch": 0.06492335437330929,
+      "grad_norm": 3.8371005058288574,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 11.5471,
+      "step": 18
+    },
+    {
+      "epoch": 0.0721370604147881,
+      "eval_loss": 2.6382529735565186,
+      "eval_runtime": 5.2174,
+      "eval_samples_per_second": 22.425,
+      "eval_steps_per_second": 11.308,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -71,7 +108,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 235112516026368.0,
+  "total_flos": 489185718829056.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null