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:dc8dcf948e4434180b877f017de000d561788078ae785e383ddd34e9ac004422
+oid sha256:e75b5e98c55bd6d007219c8b309741a5cca661be349e3e3aa02e9187930e7785
 size 32856

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a3d0ac92b9fb0a4aba8de585d77201d65c4003e2282f72fac1838b2d70e7b76f
+oid sha256:c1d671b4d671f76a443679970eaf7f4738c5a8bf95102ffe667a2d4d97ffdcc2
 size 71358

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46c784a60f4659800f3c4472f150d377d77a69d88547c6e5e024a7e54b3ef12b
+oid sha256:1ae59499d6fa89d93656a32994352236f76ecdb3c0d5d7d01bbf5e497aa8ee6c
 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": 0.00995787054768288,
+  "epoch": 0.012766500702157539,
   "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": 488.316,
       "eval_steps_per_second": 244.306,
       "step": 39
+    },
+    {
+      "epoch": 0.01021320056172603,
+      "grad_norm": 0.5495628714561462,
+      "learning_rate": 7.3223304703363135e-06,
+      "loss": 44.3716,
+      "step": 40
+    },
+    {
+      "epoch": 0.010468530575769183,
+      "grad_norm": 0.5957258939743042,
+      "learning_rate": 5.989850859999227e-06,
+      "loss": 44.3373,
+      "step": 41
+    },
+    {
+      "epoch": 0.010723860589812333,
+      "grad_norm": 0.6019204258918762,
+      "learning_rate": 4.7745751406263165e-06,
+      "loss": 44.3936,
+      "step": 42
+    },
+    {
+      "epoch": 0.010979190603855483,
+      "grad_norm": 0.6190346479415894,
+      "learning_rate": 3.6839958911476957e-06,
+      "loss": 44.3598,
+      "step": 43
+    },
+    {
+      "epoch": 0.011234520617898635,
+      "grad_norm": 0.6328054070472717,
+      "learning_rate": 2.7248368952908053e-06,
+      "loss": 44.3393,
+      "step": 44
+    },
+    {
+      "epoch": 0.011489850631941785,
+      "grad_norm": 0.6538673043251038,
+      "learning_rate": 1.9030116872178316e-06,
+      "loss": 44.3006,
+      "step": 45
+    },
+    {
+      "epoch": 0.011745180645984935,
+      "grad_norm": 0.6100254654884338,
+      "learning_rate": 1.2235870926211619e-06,
+      "loss": 44.4123,
+      "step": 46
+    },
+    {
+      "epoch": 0.012000510660028087,
+      "grad_norm": 0.6240978837013245,
+      "learning_rate": 6.907519900580861e-07,
+      "loss": 44.3846,
+      "step": 47
+    },
+    {
+      "epoch": 0.012255840674071237,
+      "grad_norm": 0.6546622514724731,
+      "learning_rate": 3.077914851215585e-07,
+      "loss": 44.3669,
+      "step": 48
+    },
+    {
+      "epoch": 0.012511170688114389,
+      "grad_norm": 0.7922203540802002,
+      "learning_rate": 7.706665667180091e-08,
+      "loss": 44.3199,
+      "step": 49
+    },
+    {
+      "epoch": 0.012766500702157539,
+      "grad_norm": 0.6066228151321411,
+      "learning_rate": 0.0,
+      "loss": 44.3383,
+      "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": 29137305600.0,
+  "total_flos": 37355520000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null