Training in progress, step 99, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a2b91aa6ca483f4d727f84845bc2e395b80799336360d39235c0d732338cd32
+oid sha256:7f83e35d03f14ea7d1e28f0f362dcfa306d3c58778edb8480f43f768e79abf0d
 size 161533192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e6753caeb57b7c6e30077bc22f303369c454b404d6b6835b6e73d2b3cd132b5d
+oid sha256:32799cc0db394f5fe63318eb67afcd79e0dbcab3c56248ee450eac3ddf30b4d5
 size 82460660

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:abdf165e69bde774f8fbea9f6c3d36d1ada3cc287696d8d7f1f4bbb7eabb61c2
+oid sha256:559a56abe133f70f0c158660df033798eafbff8c03f389114580f7cd21e35f15
 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": 0.043897085721253504,
+  "epoch": 0.04828679429337886,
   "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": 12.129,
       "eval_steps_per_second": 1.517,
       "step": 90
+    },
+    {
+      "epoch": 0.04536032191196195,
+      "grad_norm": 0.42109906673431396,
+      "learning_rate": 7.426068431000882e-07,
+      "loss": 0.7546,
+      "step": 93
+    },
+    {
+      "epoch": 0.04682355810267041,
+      "grad_norm": 0.47802457213401794,
+      "learning_rate": 2.4329828146074095e-07,
+      "loss": 0.6932,
+      "step": 96
+    },
+    {
+      "epoch": 0.04828679429337886,
+      "grad_norm": 0.36127352714538574,
+      "learning_rate": 1.522932452260595e-08,
+      "loss": 0.8052,
+      "step": 99
+    },
+    {
+      "epoch": 0.04828679429337886,
+      "eval_loss": 0.7704710364341736,
+      "eval_runtime": 284.3211,
+      "eval_samples_per_second": 12.145,
+      "eval_steps_per_second": 1.519,
+      "step": 99
     }
   ],
   "logging_steps": 3,
@@ -324,7 +353,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.4819620298529178e+17,
+  "total_flos": 1.6497313162513613e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null