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:abda00331811fd9ca1dbe4ddfb11279dadf3f39872bdf46ef52da94e94d9b7ae
+oid sha256:ba391ee140e4b563e175da88fef3211878b4e2ba65ac694ce8ee1e26c7016af7
 size 27024

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ebebf95905c181a98bc466544a4774e36ff5efc2947a09382419b406b13fb28
+oid sha256:00e3936f73c5fe8e0d8b5ef05fcdbd30390e586244bcea5649a67f3933166a37
 size 63974

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48d41985628b63b1f03308534e42f5f4fade1dc9f1a7ca147144af3b829d1153
+oid sha256:3a2809375c44051deea8394ef4e524b537561ea599f6f054cbc21229ed9516f2
 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": 0.13978494623655913,
+  "epoch": 0.17921146953405018,
   "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": 386.843,
       "eval_steps_per_second": 193.421,
       "step": 39
+    },
+    {
+      "epoch": 0.14336917562724014,
+      "grad_norm": 0.03607841581106186,
+      "learning_rate": 7.3223304703363135e-06,
+      "loss": 10.3728,
+      "step": 40
+    },
+    {
+      "epoch": 0.14695340501792115,
+      "grad_norm": 0.046089813113212585,
+      "learning_rate": 5.989850859999227e-06,
+      "loss": 10.3654,
+      "step": 41
+    },
+    {
+      "epoch": 0.15053763440860216,
+      "grad_norm": 0.03673432394862175,
+      "learning_rate": 4.7745751406263165e-06,
+      "loss": 10.3703,
+      "step": 42
+    },
+    {
+      "epoch": 0.15412186379928317,
+      "grad_norm": 0.030522871762514114,
+      "learning_rate": 3.6839958911476957e-06,
+      "loss": 10.3856,
+      "step": 43
+    },
+    {
+      "epoch": 0.15770609318996415,
+      "grad_norm": 0.03903985396027565,
+      "learning_rate": 2.7248368952908053e-06,
+      "loss": 10.3796,
+      "step": 44
+    },
+    {
+      "epoch": 0.16129032258064516,
+      "grad_norm": 0.03888795152306557,
+      "learning_rate": 1.9030116872178316e-06,
+      "loss": 10.3767,
+      "step": 45
+    },
+    {
+      "epoch": 0.16487455197132617,
+      "grad_norm": 0.034167222678661346,
+      "learning_rate": 1.2235870926211619e-06,
+      "loss": 10.3753,
+      "step": 46
+    },
+    {
+      "epoch": 0.16845878136200718,
+      "grad_norm": 0.036168940365314484,
+      "learning_rate": 6.907519900580861e-07,
+      "loss": 10.3825,
+      "step": 47
+    },
+    {
+      "epoch": 0.17204301075268819,
+      "grad_norm": 0.03681221604347229,
+      "learning_rate": 3.077914851215585e-07,
+      "loss": 10.3729,
+      "step": 48
+    },
+    {
+      "epoch": 0.17562724014336917,
+      "grad_norm": 0.02774396538734436,
+      "learning_rate": 7.706665667180091e-08,
+      "loss": 10.3823,
+      "step": 49
+    },
+    {
+      "epoch": 0.17921146953405018,
+      "grad_norm": 0.02765418030321598,
+      "learning_rate": 0.0,
+      "loss": 10.3787,
+      "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": 504305418240.0,
+  "total_flos": 646545408000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null