Training in progress, step 99, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d0906dafafacad4fd7c6dd642f606d715301f892dc90563b17b1fdf7b9b89570
+oid sha256:1a05995bb6723803a1f1c888f185735db868aea5c8f32f2e1a26f59b7df1e379
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05f476881adf3509ac4808fc2610c6087b09ad384bc933e61e7e7d245d5e6575
+oid sha256:7b2aea331aee2efd79a9fc3a3637fdfb69c313cda494c512817d14817c27c50c
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f80f0860cc8070af2741dc81f3890ed89de3af90f304dfb698658cfc28a915c
+oid sha256:db9d4c8129b0272e8b86974fffc8b78c159383969a397743547b858b994d7956
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0569f9f06b6a114946825bdc699040cc55958cfef46aba8eb5fb625896d49025
+oid sha256:5b64833e2721bfb57dae2a544bde34ace02492c2f80bfbff48034c9946dc6b4a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5325443786982249,
+  "epoch": 0.5857988165680473,
   "eval_steps": 9,
-  "global_step": 90,
+  "global_step": 99,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -305,6 +305,35 @@
       "eval_samples_per_second": 6.929,
       "eval_steps_per_second": 0.875,
       "step": 90
+    },
+    {
+      "epoch": 0.5502958579881657,
+      "grad_norm": 0.24370835721492767,
+      "learning_rate": 7.426068431000882e-07,
+      "loss": 0.6293,
+      "step": 93
+    },
+    {
+      "epoch": 0.5680473372781065,
+      "grad_norm": 0.25430381298065186,
+      "learning_rate": 2.4329828146074095e-07,
+      "loss": 0.6013,
+      "step": 96
+    },
+    {
+      "epoch": 0.5857988165680473,
+      "grad_norm": 0.2393229901790619,
+      "learning_rate": 1.522932452260595e-08,
+      "loss": 0.6499,
+      "step": 99
+    },
+    {
+      "epoch": 0.5857988165680473,
+      "eval_loss": 0.5817607641220093,
+      "eval_runtime": 41.1312,
+      "eval_samples_per_second": 6.929,
+      "eval_steps_per_second": 0.875,
+      "step": 99
     }
   ],
   "logging_steps": 3,
@@ -324,7 +353,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.6670847843998106e+17,
+  "total_flos": 2.934164206481572e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null