Training in progress, step 8500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de8370a89098799b71237e612054920263df6d1fa175f21ccf53b8ed240ffdb6
+oid sha256:92fbc32009da591364abce330f09876aefab330907f022aa0293aa8909e9b7cd
 size 8137792

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d0ac78dc8e07849fb5b0f446a91e51499ff51084f47059105638957fa8432b2
+oid sha256:9ef625bb6d9a65f5cb9577f2225bae63c198d7bbd3c71d6a05e421c61103e98a
 size 16386426

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43586a12a1f1a1656afbe533913ee12ee24da90d99646d52ced4707fe1bd8499
+oid sha256:8f8a4e875d42a98f19d4701a30042716aae453e5c567be74882c3e9ee7d0eb58
 size 15006

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0047015d0721b0c126368d59e019c347276787f4f12e23900714a55171f7db55
+oid sha256:77fe410e64d56cea4d1dcf53986c60d9ad170e47b5387f87fe71f374d0ad1807
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 16.797375410092172,
+  "epoch": 16.997344164974223,
   "eval_steps": 500,
-  "global_step": 8400,
+  "global_step": 8500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -723,6 +723,21 @@
       "learning_rate": 4.4000000000000006e-05,
       "loss": 1.2349,
       "step": 8400
+    },
+    {
+      "epoch": 16.997344164974223,
+      "grad_norm": 0.22797927260398865,
+      "learning_rate": 4.3333333333333334e-05,
+      "loss": 1.2311,
+      "step": 8500
+    },
+    {
+      "epoch": 16.997344164974223,
+      "eval_loss": 1.1013116836547852,
+      "eval_runtime": 780.8183,
+      "eval_samples_per_second": 19.879,
+      "eval_steps_per_second": 2.486,
+      "step": 8500
     }
   ],
   "logging_steps": 100,
@@ -742,7 +757,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.3110151069881598e+19,
+  "total_flos": 1.3266226041069765e+19,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null