Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:17589c8cb2b5ca9467475267a871507cf0cf3936ab0e2f5d5df26e4ea502d1e9
+oid sha256:c560603864782a6ac5e1f6e70f828d723d03654498691ac59a81c2deeb112691
 size 14696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a8b0a9e2ea1d3c5e4070cb43436395be67373df21f993e57bbee796b8da52faa
+oid sha256:5eae6ffa341afb19365f2bcb9df49967dd7899c96ba6fbfd252443d1370b91ba
 size 39398

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c1039e96a4ec12087edaa8ab2d18eba7c359b91687856664d415beaa872acc5
+oid sha256:85060d38305da5842ce5b70373bb3d7952ad87015fdb071fa07cc8695909737b
 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": 0.058624577226606536,
+  "epoch": 0.0751597143930853,
   "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": 162.611,
       "eval_steps_per_second": 81.595,
       "step": 39
+    },
+    {
+      "epoch": 0.06012777151446824,
+      "grad_norm": 0.018976975232362747,
+      "learning_rate": 7.3223304703363135e-06,
+      "loss": 11.9383,
+      "step": 40
+    },
+    {
+      "epoch": 0.06163096580232995,
+      "grad_norm": 0.02353368140757084,
+      "learning_rate": 5.989850859999227e-06,
+      "loss": 11.9376,
+      "step": 41
+    },
+    {
+      "epoch": 0.06313416009019165,
+      "grad_norm": 0.022516341879963875,
+      "learning_rate": 4.7745751406263165e-06,
+      "loss": 11.9376,
+      "step": 42
+    },
+    {
+      "epoch": 0.06463735437805336,
+      "grad_norm": 0.019928589463233948,
+      "learning_rate": 3.6839958911476957e-06,
+      "loss": 11.9401,
+      "step": 43
+    },
+    {
+      "epoch": 0.06614054866591507,
+      "grad_norm": 0.018361683934926987,
+      "learning_rate": 2.7248368952908053e-06,
+      "loss": 11.942,
+      "step": 44
+    },
+    {
+      "epoch": 0.06764374295377677,
+      "grad_norm": 0.02109694294631481,
+      "learning_rate": 1.9030116872178316e-06,
+      "loss": 11.94,
+      "step": 45
+    },
+    {
+      "epoch": 0.06914693724163848,
+      "grad_norm": 0.018863841891288757,
+      "learning_rate": 1.2235870926211619e-06,
+      "loss": 11.9402,
+      "step": 46
+    },
+    {
+      "epoch": 0.07065013152950018,
+      "grad_norm": 0.02119751088321209,
+      "learning_rate": 6.907519900580861e-07,
+      "loss": 11.9416,
+      "step": 47
+    },
+    {
+      "epoch": 0.07215332581736189,
+      "grad_norm": 0.02331853285431862,
+      "learning_rate": 3.077914851215585e-07,
+      "loss": 11.9389,
+      "step": 48
+    },
+    {
+      "epoch": 0.0736565201052236,
+      "grad_norm": 0.02491927705705166,
+      "learning_rate": 7.706665667180091e-08,
+      "loss": 11.9362,
+      "step": 49
+    },
+    {
+      "epoch": 0.0751597143930853,
+      "grad_norm": 0.02129458263516426,
+      "learning_rate": 0.0,
+      "loss": 11.9398,
+      "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": 9216589824.0,
+  "total_flos": 11816140800.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null