Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:134295f78680c4b14d57ba4a5ae818fb73a1119a698d946345cfeed50a7e13bd
+oid sha256:5505005090bdfb76a750a4a1cb7a860a52a5a342be611266196bb8fa345322ba
 size 28351000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:76f6909aaaf82ca57e3487d3e8c1e5691b520d9c02a7793fc4b61d8c15358fee
+oid sha256:38d24bff863ceb0a7a4d0aebff01055bbe2e59d0dc5ef0b86360ab5042a416d0
 size 14714068

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0bd0c719b07becd12707f516b5805a0c5e7f44255f91a52de0c74a2609cd57ec
+oid sha256:c6fd42b640f00a8092cbcf8172f91307bcc479d2b1c5085a4ff026b0254ba8aa
 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": 0.0007736112603416783,
+  "epoch": 0.0008595680670463093,
   "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": 32.501,
       "eval_steps_per_second": 16.254,
       "step": 9
+    },
+    {
+      "epoch": 0.0008595680670463093,
+      "grad_norm": 23.379283905029297,
+      "learning_rate": 0.0002,
+      "loss": 11.8631,
+      "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": 268889078366208.0,
+  "total_flos": 298765642629120.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null