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:c14e8ef4e4b9ea9e2ad39643efd8f0932ab5cf0fe5b2b7e1d43ed6bdfb7349c0
+oid sha256:119fbe5ee6513bc80548850846fae3e1e770130d97c36b6f1cdc4035fe1119d9
 size 1579352

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02e836f4d258fd81234e912c154e4761012dfee3054140297c73af950727fb42
+oid sha256:b2ddd223e53524e1d684b9ce68d69cc0ccf7b7df5d101758f00dcac2b9c4d51d
 size 857338

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:06c544fcf1253df28f74138b72f941d4769da1e4d61b391fc740707b0bdacc30
+oid sha256:ce3cba626989b3129b5cc592384faaaf801514100877dbb0c4083dbea34413f8
 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": 0.00034957225949914063,
+  "epoch": 0.0003884136216657118,
   "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": 203.882,
       "eval_steps_per_second": 101.95,
       "step": 9
+    },
+    {
+      "epoch": 0.0003884136216657118,
+      "grad_norm": 2196.937255859375,
+      "learning_rate": 0.0002,
+      "loss": 43.7502,
+      "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": 16335589343232.0,
+  "total_flos": 17996835717120.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null