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:a0b1015053509a9c55c521e6066eab35606bcefc26f705e49b5a9d746dc67594
+oid sha256:24868c77e8ef8cdb676d397ee0dcf1933a28f292fb18c250b309cb2dfd5d2e3b
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c94577d98dff91fb43ab70dc926e28874350fcb114d793dc7a11d56e09f2500c
+oid sha256:5b2e209227f1acdc472340d3c7f28e2f7ab887afe5d83bb7fac71f28bce61f9d
 size 64219860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:440bf16935ebee4c6c66320dbf007408fe2b065fc51f50b6bbb773ec635b29aa
+oid sha256:af4ccbd7dcdc84ec10dcb170ff5425532698eb9e9a63ec7fbe5ff2e27fce02ed
 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": 0.007481296758104738,
+  "epoch": 0.00831255195344971,
   "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": 16.194,
       "eval_steps_per_second": 8.113,
       "step": 9
+    },
+    {
+      "epoch": 0.00831255195344971,
+      "grad_norm": 2.356943368911743,
+      "learning_rate": 0.0002,
+      "loss": 8.5216,
+      "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": 3245379912990720.0,
+  "total_flos": 3562002343526400.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null