Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18aa82aa33dca06bde6c49f9e202405400e7e7a650ce7de66db26cd721eecf0c
+oid sha256:42234aff9deb5205185c5f5e9985c56a2ff457015d70dfc6191d53776e52b0c1
 size 50899792

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed38e9eb1c6d37227afc777c160b95f1fafc60d5d8a35fe6bbd4c194a0df52c0
+oid sha256:9ae85030de8c7af6d93173ab0ce30fd156711516eac01f3dafbe01fb080b8333
 size 26231300

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c5f55d8c80f0b8ecb9579b4ac101b89a3b162fdabe30e550777e6b4023d4d60
+oid sha256:10ad5a169fac1f6319a215b77a09582ed522537554e0f693b1642997163dc5c2
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c50dbaa792cda4a28fbbc2acb2a3e03c59530712bbc5107212d33064d193da4
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.002991084268047167,
+  "epoch": 0.003834723420573291,
   "eval_steps": 10,
-  "global_step": 39,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -88,6 +88,43 @@
       "learning_rate": 3.086582838174551e-05,
       "loss": 0.4469,
       "step": 35
+    },
+    {
+      "epoch": 0.003067778736458633,
+      "grad_norm": 0.9363953471183777,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.2449,
+      "step": 40
+    },
+    {
+      "epoch": 0.003067778736458633,
+      "eval_loss": 0.3529892861843109,
+      "eval_runtime": 271.127,
+      "eval_samples_per_second": 20.249,
+      "eval_steps_per_second": 10.124,
+      "step": 40
+    },
+    {
+      "epoch": 0.003451251078515962,
+      "grad_norm": 1.0287480354309082,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.2746,
+      "step": 45
+    },
+    {
+      "epoch": 0.003834723420573291,
+      "grad_norm": 0.04178006201982498,
+      "learning_rate": 0.0,
+      "loss": 0.2152,
+      "step": 50
+    },
+    {
+      "epoch": 0.003834723420573291,
+      "eval_loss": 0.3511003851890564,
+      "eval_runtime": 270.9294,
+      "eval_samples_per_second": 20.264,
+      "eval_steps_per_second": 10.132,
+      "step": 50
     }
   ],
   "logging_steps": 5,
@@ -102,12 +139,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 4776783473541120.0,
+  "total_flos": 6047858904268800.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null