Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d4f20eae1e27ffb9f3287eeb347fabd5213a34afd143f36314f53f1c6044983
+oid sha256:f54513fe94280a5622a80db4b0b2454804dc07b9ce33ad5ecc82ecc665b433c1
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77946dd31d1617081df53c56999459380f808a3fb0ceef2c6a68ac7896730089
+oid sha256:58d37d755673c1e9a6fe0e69becf18b9037bfe648d75d61b9fb12691335ef9fe
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cfbfd95051ee0b329c6f0a314fa883d27a94f47705d1e9935da3b653adde21a9
+oid sha256:f9d34437b2482b21504781a93aeb8e867dc80d43eae8bb0a75dc8554115eec6c
 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": 0.0074285714285714285,
+  "epoch": 0.009523809523809525,
   "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": 0.0915,
       "step": 35
+    },
+    {
+      "epoch": 0.007619047619047619,
+      "grad_norm": 0.002745690755546093,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.0003,
+      "step": 40
+    },
+    {
+      "epoch": 0.007619047619047619,
+      "eval_loss": 0.03260380029678345,
+      "eval_runtime": 130.4906,
+      "eval_samples_per_second": 16.944,
+      "eval_steps_per_second": 8.476,
+      "step": 40
+    },
+    {
+      "epoch": 0.008571428571428572,
+      "grad_norm": 0.0005702447961084545,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.0,
+      "step": 45
+    },
+    {
+      "epoch": 0.009523809523809525,
+      "grad_norm": 0.01588163711130619,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.009523809523809525,
+      "eval_loss": 0.0321432463824749,
+      "eval_runtime": 130.4634,
+      "eval_samples_per_second": 16.947,
+      "eval_steps_per_second": 8.477,
+      "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": 6392777558458368.0,
+  "total_flos": 8225102336360448.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null