Training in progress, step 90, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cbe6c44aabe032d0ae8403360ec1ed05fc822627c559034f364b9c555c7ee2ae
+oid sha256:17f43c4e908fa649a6e0b950bee7fe730e9026abb57ef9987595f257953777d9
 size 73911112

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1909c1ba4dc64d7d0fafca4fd0117377c3ac3195919c00e3b64344950908d260
+oid sha256:0b5dd0bb4b4e8b7983cdc0750220729df0689f1dfff0b58882450f989ac05d31
 size 37965300

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80e0912226767f30058f628d41e26838633adb7576b646df748b130328848c19
+oid sha256:18a55733c512b33a1d8d4cc1387f7f6f5a8dcc0f715abbe53c564c0d6e191dc6
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90f7a57653bcfdeb8d3e27706e79cc5f6e1f14bbd0ff72a8e33edaaa89ef8274
+oid sha256:7f7d03f1dba06dbe949e0b7294b5a80e81e1c97413b12e930c7d1d62b4e569ba
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.045531197301854974,
+  "epoch": 0.050590219224283306,
   "eval_steps": 9,
-  "global_step": 81,
+  "global_step": 90,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -276,6 +276,35 @@
       "eval_samples_per_second": 18.202,
       "eval_steps_per_second": 2.278,
       "step": 81
+    },
+    {
+      "epoch": 0.047217537942664416,
+      "grad_norm": 0.16453050076961517,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 0.7636,
+      "step": 84
+    },
+    {
+      "epoch": 0.048903878583473864,
+      "grad_norm": 0.17823824286460876,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 0.7473,
+      "step": 87
+    },
+    {
+      "epoch": 0.050590219224283306,
+      "grad_norm": 0.16380201280117035,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 0.7086,
+      "step": 90
+    },
+    {
+      "epoch": 0.050590219224283306,
+      "eval_loss": 0.7322941422462463,
+      "eval_runtime": 164.8671,
+      "eval_samples_per_second": 18.178,
+      "eval_steps_per_second": 2.275,
+      "step": 90
     }
   ],
   "logging_steps": 3,
@@ -295,7 +324,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.23231103130665e+16,
+  "total_flos": 4.702567812562944e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null