Training in progress, step 2900, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9dc2f178242b7550632df0df2c55f6420a674d51d6c09e421e0b4faf984b3402
+oid sha256:da640fbc591881183de45b32f07cc8fee34338139e347b8a1e288fa2c1d13c84
 size 8137792

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c32acf9f365e8764eb9dbf929e62f257e5badae056f82b4ddf195a6c1d8f23b
+oid sha256:1b312822f4291962f8a5dc3e79c4ab76a29a170a50ab21261d7ad7b98571dde8
 size 16386426

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:76ba8b738578f295e0a532463bd8e85b447498e4475e9410d6b141ead2ba5753
+oid sha256:a4f5a32345b1c262d82ac5d7149f3766a72e180fbc3ddbff149d8b4625601be4
 size 15006

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b5849322fb77b87af1a977898ab484962b1650e0f7a5019e778b3234f5454c07
+oid sha256:b3856a941506ce1f25fd994919a3acb32bb886abb24e043d06b143d642f43fae
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 5.599125136697391,
+  "epoch": 5.7990938915794406,
   "eval_steps": 500,
-  "global_step": 2800,
+  "global_step": 2900,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -243,6 +243,13 @@
       "learning_rate": 8.133333333333334e-05,
       "loss": 1.279,
       "step": 2800
+    },
+    {
+      "epoch": 5.7990938915794406,
+      "grad_norm": 0.17068877816200256,
+      "learning_rate": 8.066666666666667e-05,
+      "loss": 1.2726,
+      "step": 2900
     }
   ],
   "logging_steps": 100,
@@ -262,7 +269,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.370053408917291e+18,
+  "total_flos": 4.5261283801054577e+18,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null