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:dded6c46c3b33e7248136bb010881aa2ea8a97984ca87d9b6471af4231ffb555
+oid sha256:d5423f7472b690b13a2ba07625afd27a921c6f215e8eae7c63c59a2ccc471f04
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8cf92d16ee0772f0b880757e42b440875db21bb7ddfae36a9b161497e54acd34
+oid sha256:2cb6e417f94ad5dcaa0df7428637bed45205cf3ebd08370da548ad91d4a7ab84
 size 64219860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c0959beb5dd920c9ccfebbe978a6ed55b1b8019cd326b9e373993e6fde2da87
+oid sha256:81116146975a92420009b655a029b07f332dec0936495a66f57dfbac72cda2f7
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28418a35cb7e15ebbce37743b08fd366c25ee320167b307a3e449a74781d02de
+oid sha256:439e51f57871ee9c2bc8b35458a0c03f9b948af7a0d15ffe5e1cf9789955c6c8
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.007357449417535254,
+  "epoch": 0.009432627458378532,
   "eval_steps": 13,
-  "global_step": 39,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -312,6 +312,83 @@
       "eval_samples_per_second": 13.748,
       "eval_steps_per_second": 6.874,
       "step": 39
+    },
+    {
+      "epoch": 0.007546101966702825,
+      "grad_norm": 1.4397048950195312,
+      "learning_rate": 7.3223304703363135e-06,
+      "loss": 3.136,
+      "step": 40
+    },
+    {
+      "epoch": 0.007734754515870396,
+      "grad_norm": 1.1612348556518555,
+      "learning_rate": 5.989850859999227e-06,
+      "loss": 2.6991,
+      "step": 41
+    },
+    {
+      "epoch": 0.007923407065037967,
+      "grad_norm": 1.1718542575836182,
+      "learning_rate": 4.7745751406263165e-06,
+      "loss": 3.4451,
+      "step": 42
+    },
+    {
+      "epoch": 0.008112059614205537,
+      "grad_norm": 16.019390106201172,
+      "learning_rate": 3.6839958911476957e-06,
+      "loss": 6.0125,
+      "step": 43
+    },
+    {
+      "epoch": 0.008300712163373107,
+      "grad_norm": 5.01461935043335,
+      "learning_rate": 2.7248368952908053e-06,
+      "loss": 6.5092,
+      "step": 44
+    },
+    {
+      "epoch": 0.008489364712540678,
+      "grad_norm": 1.373666763305664,
+      "learning_rate": 1.9030116872178316e-06,
+      "loss": 3.4825,
+      "step": 45
+    },
+    {
+      "epoch": 0.008678017261708248,
+      "grad_norm": 2.0518085956573486,
+      "learning_rate": 1.2235870926211619e-06,
+      "loss": 4.0741,
+      "step": 46
+    },
+    {
+      "epoch": 0.00886666981087582,
+      "grad_norm": 1.1679599285125732,
+      "learning_rate": 6.907519900580861e-07,
+      "loss": 3.921,
+      "step": 47
+    },
+    {
+      "epoch": 0.00905532236004339,
+      "grad_norm": 1.1631509065628052,
+      "learning_rate": 3.077914851215585e-07,
+      "loss": 4.894,
+      "step": 48
+    },
+    {
+      "epoch": 0.00924397490921096,
+      "grad_norm": 1.5388468503952026,
+      "learning_rate": 7.706665667180091e-08,
+      "loss": 3.711,
+      "step": 49
+    },
+    {
+      "epoch": 0.009432627458378532,
+      "grad_norm": 2.1205825805664062,
+      "learning_rate": 0.0,
+      "loss": 3.2165,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -326,12 +403,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.844313930596352e+16,
+  "total_flos": 2.382568639954944e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null