Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:44465e943e4228d97e0ae916c2e41240d841e1ea0c0fbf381d0f392524b1ab24
+oid sha256:29f7f47934004cef4ffae0b94d172af25b71c37a6827926c520db5ef8e7ff920
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b854a453bd55536f7addd69283a4fdf811a12c08fe2dbbe755ca4580a60df028
+oid sha256:0a93c1f824c764258269ac7ea79b1d2d349b18ec35b28b83346296384e8c057e
 size 64219860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:354fcbfab35beb320321fc72abe28e2ba17d63b820a2c10b34cfe337af85be52
+oid sha256:cd9f9fa4f12eb656180c05ab6d0e11868fa1b817f9a6c422f3c0302601735f4e
 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": 0.025275437459494492,
+  "epoch": 0.03240440699935191,
   "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": 18.721,
       "eval_steps_per_second": 9.361,
       "step": 39
+    },
+    {
+      "epoch": 0.02592352559948153,
+      "grad_norm": 0.4833146929740906,
+      "learning_rate": 7.3223304703363135e-06,
+      "loss": 0.0381,
+      "step": 40
+    },
+    {
+      "epoch": 0.026571613739468567,
+      "grad_norm": 1.2130305767059326,
+      "learning_rate": 5.989850859999227e-06,
+      "loss": 0.145,
+      "step": 41
+    },
+    {
+      "epoch": 0.027219701879455604,
+      "grad_norm": 1.8364264965057373,
+      "learning_rate": 4.7745751406263165e-06,
+      "loss": 0.0214,
+      "step": 42
+    },
+    {
+      "epoch": 0.027867790019442645,
+      "grad_norm": 0.2733038365840912,
+      "learning_rate": 3.6839958911476957e-06,
+      "loss": 0.0173,
+      "step": 43
+    },
+    {
+      "epoch": 0.028515878159429683,
+      "grad_norm": 2.3136823177337646,
+      "learning_rate": 2.7248368952908053e-06,
+      "loss": 0.256,
+      "step": 44
+    },
+    {
+      "epoch": 0.02916396629941672,
+      "grad_norm": 2.228217840194702,
+      "learning_rate": 1.9030116872178316e-06,
+      "loss": 0.0597,
+      "step": 45
+    },
+    {
+      "epoch": 0.029812054439403757,
+      "grad_norm": 1.7385436296463013,
+      "learning_rate": 1.2235870926211619e-06,
+      "loss": 0.1846,
+      "step": 46
+    },
+    {
+      "epoch": 0.0304601425793908,
+      "grad_norm": 3.9748942852020264,
+      "learning_rate": 6.907519900580861e-07,
+      "loss": 0.2335,
+      "step": 47
+    },
+    {
+      "epoch": 0.031108230719377836,
+      "grad_norm": 0.39631471037864685,
+      "learning_rate": 3.077914851215585e-07,
+      "loss": 0.0189,
+      "step": 48
+    },
+    {
+      "epoch": 0.031756318859364877,
+      "grad_norm": 0.7878240942955017,
+      "learning_rate": 7.706665667180091e-08,
+      "loss": 0.0195,
+      "step": 49
+    },
+    {
+      "epoch": 0.03240440699935191,
+      "grad_norm": 2.092984437942505,
+      "learning_rate": 0.0,
+      "loss": 0.1064,
+      "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": 1.234819627352064e+16,
+  "total_flos": 1.5831020863488e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null