Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35504ea7564e47d67c3cd9765c3a044e3e2f196fb9147f4240050d39fba8aaa8
+oid sha256:60ff59db0a029272789bf94aeb507cbcfc623be0b358304a70cdfa6afa9c6c61
 size 59933632

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f9748f6cca7a124ad0cc56659c38e19847fbf9179bfe597a405063f3fd8fd1bc
+oid sha256:d9c2848f6a9c20a1f611acb71b0983ab54d9ba96477b65bf0c4c6fe786372ec8
 size 31822948

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1aada43105c6045283b983b1091df926343e16e8b0d677632cc4f8f8df364a9e
+oid sha256:ab82b86b5065b167437179890e6c582b0652f14a82e9b777ffa33a5669b374ae
 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": 0.0015218769816106531,
+  "epoch": 0.0016909744240118367,
   "eval_steps": 3,
-  "global_step": 9,
+  "global_step": 10,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -102,6 +102,13 @@
       "eval_samples_per_second": 29.177,
       "eval_steps_per_second": 14.588,
       "step": 9
+    },
+    {
+      "epoch": 0.0016909744240118367,
+      "grad_norm": 5.417690753936768,
+      "learning_rate": 0.0002,
+      "loss": 3.5436,
+      "step": 10
     }
   ],
   "logging_steps": 1,
@@ -116,12 +123,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1096970617749504.0,
+  "total_flos": 1199811613163520.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null