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:acdbec0bbcab23d35877d6db397ae779338a764ecf51f9e0d908487a335a9b57
+oid sha256:4cdc0ac44e2859cebc2b8c66c3f4c10cbecac14443275238f99137a91088ef79
 size 327040

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ced72bb4a403160aa9420b9c0e3ecb3f1792e98d3603768e29097e55e443823d
+oid sha256:855727e78bc330e598a093730bbeb6dd36caaff87568c3b1ef8b49dda9021213
 size 739258

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4403875ec607cf3108caac6354185aadd4588ae4b29cc7dad762431733537e30
+oid sha256:6d2b27ee9d6ec517a7aac5a6da30ff7a8f8e7211f6b8e068136b883f0618057f
 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": 0.055934026532807456,
+  "epoch": 0.07171029042667623,
   "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": 67.64,
       "eval_steps_per_second": 33.82,
       "step": 39
+    },
+    {
+      "epoch": 0.05736823234134098,
+      "grad_norm": 0.13573527336120605,
+      "learning_rate": 7.3223304703363135e-06,
+      "loss": 11.9285,
+      "step": 40
+    },
+    {
+      "epoch": 0.05880243814987451,
+      "grad_norm": 0.09894472360610962,
+      "learning_rate": 5.989850859999227e-06,
+      "loss": 11.9341,
+      "step": 41
+    },
+    {
+      "epoch": 0.06023664395840803,
+      "grad_norm": 0.0890652984380722,
+      "learning_rate": 4.7745751406263165e-06,
+      "loss": 11.9347,
+      "step": 42
+    },
+    {
+      "epoch": 0.06167084976694156,
+      "grad_norm": 0.11416501551866531,
+      "learning_rate": 3.6839958911476957e-06,
+      "loss": 11.9257,
+      "step": 43
+    },
+    {
+      "epoch": 0.06310505557547508,
+      "grad_norm": 0.15674228966236115,
+      "learning_rate": 2.7248368952908053e-06,
+      "loss": 11.9237,
+      "step": 44
+    },
+    {
+      "epoch": 0.0645392613840086,
+      "grad_norm": 0.10576747357845306,
+      "learning_rate": 1.9030116872178316e-06,
+      "loss": 11.937,
+      "step": 45
+    },
+    {
+      "epoch": 0.06597346719254213,
+      "grad_norm": 0.11372304707765579,
+      "learning_rate": 1.2235870926211619e-06,
+      "loss": 11.9422,
+      "step": 46
+    },
+    {
+      "epoch": 0.06740767300107565,
+      "grad_norm": 0.11770571023225784,
+      "learning_rate": 6.907519900580861e-07,
+      "loss": 11.9412,
+      "step": 47
+    },
+    {
+      "epoch": 0.06884187880960918,
+      "grad_norm": 0.10780180245637894,
+      "learning_rate": 3.077914851215585e-07,
+      "loss": 11.9313,
+      "step": 48
+    },
+    {
+      "epoch": 0.0702760846181427,
+      "grad_norm": 0.17825394868850708,
+      "learning_rate": 7.706665667180091e-08,
+      "loss": 11.9304,
+      "step": 49
+    },
+    {
+      "epoch": 0.07171029042667623,
+      "grad_norm": 0.1269485503435135,
+      "learning_rate": 0.0,
+      "loss": 11.9362,
+      "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": 9730873884672.0,
+  "total_flos": 12453015453696.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null