Training in progress, step 3000, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da640fbc591881183de45b32f07cc8fee34338139e347b8a1e288fa2c1d13c84
+oid sha256:8d8e140e0920e282adf4d0c6e9dfb8f7f67871afabc912ca450a5166fa603af3
 size 8137792

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b312822f4291962f8a5dc3e79c4ab76a29a170a50ab21261d7ad7b98571dde8
+oid sha256:187f41deb527982f01dcf5fdb0b73457f252827d837cd7bdc2344004d3e43b69
 size 16386426

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4f5a32345b1c262d82ac5d7149f3766a72e180fbc3ddbff149d8b4625601be4
+oid sha256:cd9810c0055d5cdf8ec24828569cee75556cbfbb48adeeae7d4a0d0ebb31e3cb
 size 15006

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b3856a941506ce1f25fd994919a3acb32bb886abb24e043d06b143d642f43fae
+oid sha256:edca854ddd5ab8671af8a33c4bc63c5756a95d04ae74071e2d1b33c1e5e76671
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 5.7990938915794406,
+  "epoch": 5.99906264646149,
   "eval_steps": 500,
-  "global_step": 2900,
+  "global_step": 3000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -250,6 +250,21 @@
       "learning_rate": 8.066666666666667e-05,
       "loss": 1.2726,
       "step": 2900
+    },
+    {
+      "epoch": 5.99906264646149,
+      "grad_norm": 0.16409236192703247,
+      "learning_rate": 8e-05,
+      "loss": 1.2727,
+      "step": 3000
+    },
+    {
+      "epoch": 5.99906264646149,
+      "eval_loss": 1.1620852947235107,
+      "eval_runtime": 779.854,
+      "eval_samples_per_second": 19.904,
+      "eval_steps_per_second": 2.489,
+      "step": 3000
     }
   ],
   "logging_steps": 100,
@@ -269,7 +284,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.5261283801054577e+18,
+  "total_flos": 4.682203351293624e+18,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null