Training in progress, step 22, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:57390f0424766fc521521a78654a0473551ec2262702e29aef3f285c0736bb47
+oid sha256:731578b2af9c311644065a442fb41daa4d0165862ecd1c048de4e212fe9a5e03
 size 50899792

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2975b4d5e280c53939fd82897690e37b98d8ad64b125d521807367dc220df843
+oid sha256:c824594e29b2696177e9560dc6ef538629e8e13a1a9b7f09c8ebaef4e4dbed13
 size 26231300

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:68136003587926badaf86ffa59fa37c8928a27b940ddaa0f1f4a32d5fe418847
+oid sha256:6cf1119d4745f968a1a36a68ef74bf603acd0ae4945edcc9ef4739604515c61d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0170cd66b3e88596263837356fe806f307966eb06b07f15d31c1341aa5a794f9
+oid sha256:673e63a495b7a57d30a536ff33ff871d542fcc70b7b123e80bf5435762100a07
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.8181818181818182,
+  "epoch": 1.0,
   "eval_steps": 6,
-  "global_step": 18,
+  "global_step": 22,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -46,6 +46,13 @@
       "eval_samples_per_second": 16.478,
       "eval_steps_per_second": 8.239,
       "step": 18
+    },
+    {
+      "epoch": 0.9090909090909091,
+      "grad_norm": 0.5334855318069458,
+      "learning_rate": 6.75277705956443e-06,
+      "loss": 1.7158,
+      "step": 20
     }
   ],
   "logging_steps": 10,
@@ -60,12 +67,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2952175193948160.0,
+  "total_flos": 3608214125936640.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null