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:fa518ce0175b110a07fda9ead090047f69fb61f680a68292c3b14162175d497e
+oid sha256:6a2be0ddfb39ace0e195c32248046fb12747323e5e38520a4a4c9a4f20bb1f65
 size 100059752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:209afbef6c9df20a2ac532c038dd75d1b6b46acbeefc06ec36d2d2789b196e9b
+oid sha256:b04e5300dbdae005af0a04a81cec116771a6e7cb9d5fb495f0ba00474f22425b
 size 51244020

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:61a8e0a151dd98e594ef8e043b5fe855d94534ed6384f4867496734a3beedb85
+oid sha256:d0a84dbb38d5b712d65eddda86623f12b793e19214fa7222422c8a4b83035478
 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": 0.00045799778634403267,
+  "epoch": 0.0005088864292711474,
   "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": 6.852,
       "eval_steps_per_second": 3.426,
       "step": 9
+    },
+    {
+      "epoch": 0.0005088864292711474,
+      "grad_norm": 4.704765319824219,
+      "learning_rate": 0.0002,
+      "loss": 2.5608,
+      "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": 3439964549283840.0,
+  "total_flos": 3822182832537600.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null