Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:03df3b09f08222fdc42ce750df361fb769617fa1dbfbcdadc2e82a88216710eb
+oid sha256:aedb7851d99090f11bbb9b725dc4bc3c9c95f78016e6bf69d67126e0e0dbef22
 size 27024

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c89e311646341b2393646a9ce8724685a3f68fcf7f659ea44cba11674bdb2fc
+oid sha256:7441bd72a8ab80be22f71af324b422d12ab914e62dd40255b7c372817037b6db
 size 63974

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd3d8c26246428e8b509d69e481e99fb79255caea9279fb6313413f7aa567a3a
+oid sha256:af2202558662bca10e0fe13d768ab39eb3cf9190e25153973e536077ff3dcd4b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75c3c8ae7ddabeca3cb69703f6b35f00b9125a4c27b56ccba4ed0e4669bb5433
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.09352517985611511,
+  "epoch": 0.11990407673860912,
   "eval_steps": 10,
-  "global_step": 39,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -60,6 +60,36 @@
       "eval_samples_per_second": 609.561,
       "eval_steps_per_second": 76.358,
       "step": 30
+    },
+    {
+      "epoch": 0.09592326139088729,
+      "grad_norm": 0.029737740755081177,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 10.373,
+      "step": 40
+    },
+    {
+      "epoch": 0.09592326139088729,
+      "eval_loss": 10.37285327911377,
+      "eval_runtime": 4.5931,
+      "eval_samples_per_second": 611.788,
+      "eval_steps_per_second": 76.637,
+      "step": 40
+    },
+    {
+      "epoch": 0.11990407673860912,
+      "grad_norm": 0.02912091463804245,
+      "learning_rate": 0.0,
+      "loss": 10.3727,
+      "step": 50
+    },
+    {
+      "epoch": 0.11990407673860912,
+      "eval_loss": 10.372833251953125,
+      "eval_runtime": 4.5186,
+      "eval_samples_per_second": 621.881,
+      "eval_steps_per_second": 77.901,
+      "step": 50
     }
   ],
   "logging_steps": 10,
@@ -74,12 +104,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 8068886691840.0,
+  "total_flos": 10344726528000.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null