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:b93b8a7799aad2a7019ac73c5525afd10fe757d107ad826ca6d773e059ca5dc4
+oid sha256:da4e59738626bc85e3259f890644bb68d6c9ac73e0f5c07703991f51e238a9d7
 size 80792096

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8aae510a08662a833ecbc2d648d24760b23d84265627cfb5daf32ef95a9e5468
+oid sha256:27aa825ca7c164f630d80090b905490a003eb477a37ce2861a1d930f49c490c5
 size 41459700

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b6327c49ed4fee86bc5dba93496fcb7a4967f2e17aa3f29c39d85dc287da131a
+oid sha256:e27b25555a64d87b53ee622e762a5eca65f4880ac5f4e100f2a8561ddc76a6cf
 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": 0.045151953690303906,
+  "epoch": 0.05788712011577424,
   "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": 0.1307,
       "step": 35
+    },
+    {
+      "epoch": 0.04630969609261939,
+      "grad_norm": 0.8135068416595459,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.1207,
+      "step": 40
+    },
+    {
+      "epoch": 0.04630969609261939,
+      "eval_loss": 0.13451926410198212,
+      "eval_runtime": 23.1058,
+      "eval_samples_per_second": 15.754,
+      "eval_steps_per_second": 7.877,
+      "step": 40
+    },
+    {
+      "epoch": 0.05209840810419682,
+      "grad_norm": 0.9799630641937256,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.1372,
+      "step": 45
+    },
+    {
+      "epoch": 0.05788712011577424,
+      "grad_norm": 0.9424188733100891,
+      "learning_rate": 0.0,
+      "loss": 0.1075,
+      "step": 50
+    },
+    {
+      "epoch": 0.05788712011577424,
+      "eval_loss": 0.13253408670425415,
+      "eval_runtime": 23.0875,
+      "eval_samples_per_second": 15.766,
+      "eval_steps_per_second": 7.883,
+      "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": 6839846480904192.0,
+  "total_flos": 8756746131603456.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null