Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5fc8d05ca8601162a3941aef97b7b7be4861d409c650abb34a64e504d84bde4e
+oid sha256:539ee6052e65d89ce8a24ff066bb67443915d81853a6961f07e2de45d1016250
 size 14696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:21b15ddb292312a0067448b0ea5bb2d86573d044d834b9e1708642b1962f62cf
+oid sha256:2e2c5ae67e7f8cd2ea22b327454b6e3b484901f3c931e82bfcd549ffcfcb9e35
 size 39398

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48d41985628b63b1f03308534e42f5f4fade1dc9f1a7ca147144af3b829d1153
+oid sha256:3a2809375c44051deea8394ef4e524b537561ea599f6f054cbc21229ed9516f2
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28418a35cb7e15ebbce37743b08fd366c25ee320167b307a3e449a74781d02de
+oid sha256:439e51f57871ee9c2bc8b35458a0c03f9b948af7a0d15ffe5e1cf9789955c6c8
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.14233576642335766,
+  "epoch": 0.18248175182481752,
   "eval_steps": 13,
-  "global_step": 39,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -60,6 +60,20 @@
       "eval_samples_per_second": 293.694,
       "eval_steps_per_second": 146.847,
       "step": 39
+    },
+    {
+      "epoch": 0.145985401459854,
+      "grad_norm": 0.008573858067393303,
+      "learning_rate": 7.3223304703363135e-06,
+      "loss": 11.9364,
+      "step": 40
+    },
+    {
+      "epoch": 0.18248175182481752,
+      "grad_norm": 0.011130424216389656,
+      "learning_rate": 0.0,
+      "loss": 11.9372,
+      "step": 50
     }
   ],
   "logging_steps": 10,
@@ -74,12 +88,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 4608294912.0,
+  "total_flos": 5908070400.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null