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:d07255efb840fc61c2b41c1a62155b4f032c311dedceeb27e954e26245d7c0b7
+oid sha256:ca3a1ae43dc7eb86a871d603a5f90334ea99bf9b453d65bc807cc2d02aa715ab
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d5681a0c5a37600703dfc0691cefe2b30680fa1a465414bc2f9cefd37945814a
+oid sha256:49f145830cf619ed8a0a8948e506d31442b5a97f8fb355a998e6aedddb49e554
 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": 0.06696428571428571,
+  "epoch": 0.07366071428571429,
   "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": 14.021,
       "eval_steps_per_second": 1.753,
       "step": 90
+    },
+    {
+      "epoch": 0.06919642857142858,
+      "grad_norm": 6.10594367980957,
+      "learning_rate": 7.426068431000882e-07,
+      "loss": 4.0287,
+      "step": 93
+    },
+    {
+      "epoch": 0.07142857142857142,
+      "grad_norm": 6.208632946014404,
+      "learning_rate": 2.4329828146074095e-07,
+      "loss": 3.8063,
+      "step": 96
+    },
+    {
+      "epoch": 0.07366071428571429,
+      "grad_norm": 5.615017414093018,
+      "learning_rate": 1.522932452260595e-08,
+      "loss": 3.8605,
+      "step": 99
+    },
+    {
+      "epoch": 0.07366071428571429,
+      "eval_loss": 4.03863525390625,
+      "eval_runtime": 161.5774,
+      "eval_samples_per_second": 14.012,
+      "eval_steps_per_second": 1.751,
+      "step": 99
     }
   ],
   "logging_steps": 3,
@@ -324,7 +353,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.3353971104088064e+17,
+  "total_flos": 1.468936821449687e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null