Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8bc92a44977941e22d119544d4df657e820cb4fae4908b002feb1650f4bb93c3
+oid sha256:6271ea44ded79734497a903f1507823fbefd8e476faf9721b2923fbd5d711f09
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e785c3241469f3d50c77d2e70ef9a2b0da7437f989aea4bbb924aada3d49f15d
+oid sha256:058af6ad5959ec82def419c703c7b0a4c2e98464e257d904a02c9054429cdeef
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b5c24709107a16c4a366ef695fabf1bcf47b8db012ccbceb7d99c5d75c4b350
+oid sha256:8d67ec2502bdc1e0e180e8abf6116d9abc6b553d1b08b70fa10e367a53ed7cc9
 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": 0.016077501803565906,
+  "epoch": 0.02061218179944347,
   "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": 1.0748,
       "step": 35
+    },
+    {
+      "epoch": 0.016489745439554778,
+      "grad_norm": 1.5975080728530884,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.9761,
+      "step": 40
+    },
+    {
+      "epoch": 0.016489745439554778,
+      "eval_loss": 1.1080728769302368,
+      "eval_runtime": 85.784,
+      "eval_samples_per_second": 11.914,
+      "eval_steps_per_second": 5.957,
+      "step": 40
+    },
+    {
+      "epoch": 0.018550963619499122,
+      "grad_norm": 1.6504549980163574,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.1147,
+      "step": 45
+    },
+    {
+      "epoch": 0.02061218179944347,
+      "grad_norm": 1.9928545951843262,
+      "learning_rate": 0.0,
+      "loss": 0.9259,
+      "step": 50
+    },
+    {
+      "epoch": 0.02061218179944347,
+      "eval_loss": 1.1036310195922852,
+      "eval_runtime": 85.8891,
+      "eval_samples_per_second": 11.899,
+      "eval_steps_per_second": 5.95,
+      "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": 7352017886380032.0,
+  "total_flos": 9432777665544192.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null