Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5533beb9ec45cdbd53610981a17eac8a26c5fdf39738c39c07a76bcc50498e71
+oid sha256:c3cbffdb092803c61cf37199f0a64a35762181795756f8428079bf265fa781a3
 size 27024

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ded1a3b63153e6e64de8ebb7dc2cefdc59e80b1bfa08f1af4808ef736dcd2cf
+oid sha256:7ce0e615fd2dfaf4af2fde5fda481f7ba0bb24c648d4d8865e2be930f31e5f7b
 size 63974

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9df170cb6acde393f26f26d8b291e01ba34281d10b477edb2225f4b80d02e472
+oid sha256:e97ead28242dd097af80112cb3bd8d751944021cbf255fca1535e0f2a22344d9
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
+oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.003827751196172249,
+  "epoch": 0.004253056884635832,
   "eval_steps": 3,
-  "global_step": 9,
+  "global_step": 10,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -94,6 +94,13 @@
       "eval_samples_per_second": 65.063,
       "eval_steps_per_second": 32.531,
       "step": 9
+    },
+    {
+      "epoch": 0.004253056884635832,
+      "grad_norm": 0.021488409489393234,
+      "learning_rate": 0.0002,
+      "loss": 10.3733,
+      "step": 10
     }
   ],
   "logging_steps": 1,
@@ -108,12 +115,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 229523619840.0,
+  "total_flos": 255385436160.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null