Training in progress, step 99, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:185a685272d646667fa7e6b1cf7efc1c6db628fdcfa4f1d9791765507cb816c1
+oid sha256:1cf1bcd9ad1f3e51578ae2ece4da4e7a36a22e15ded20224f93b42db47ed17da
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba2382fc68c12a701c6e6f0e4af2f0d9652c258bdacfe93f35e225fa8424442f
+oid sha256:f82487c560eea9c7d988d3c14a40b8f946903af7af2653250757198bca46823d
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b202cc35d4d82828b46ac25c2aa3b0d5b24c9fdd644bb03957f013b307cbc71d
+oid sha256:0ca5ed7077b7e80b15b5b40bb67c00bb6aeb10626f97d2892620cc3f79d1da45
 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": 0.0076592485426152076,
+  "epoch": 0.008425173396876729,
   "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": 13.845,
       "eval_steps_per_second": 1.731,
       "step": 90
+    },
+    {
+      "epoch": 0.007914556827369048,
+      "grad_norm": 2.819993734359741,
+      "learning_rate": 7.426068431000882e-07,
+      "loss": 4.5155,
+      "step": 93
+    },
+    {
+      "epoch": 0.00816986511212289,
+      "grad_norm": 2.8105878829956055,
+      "learning_rate": 2.4329828146074095e-07,
+      "loss": 4.5114,
+      "step": 96
+    },
+    {
+      "epoch": 0.008425173396876729,
+      "grad_norm": 2.747713327407837,
+      "learning_rate": 1.522932452260595e-08,
+      "loss": 4.4013,
+      "step": 99
+    },
+    {
+      "epoch": 0.008425173396876729,
+      "eval_loss": 1.1103698015213013,
+      "eval_runtime": 1428.4413,
+      "eval_samples_per_second": 13.855,
+      "eval_steps_per_second": 1.732,
+      "step": 99
     }
   ],
   "logging_steps": 3,
@@ -324,7 +353,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.2656345471778816e+17,
+  "total_flos": 1.3921980018956698e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null