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:b57f73aff51b1cd861000ec8bcede673223271aaea28784657e8370f287072d6
+oid sha256:7ff151412599dd010d934728eadbc7d093b1f31e112b25c3db17c1f33ac0debf
 size 14696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c7a59931677b6ed55b6404b2138a1b02544d0b4849f49b756722bd3c3189e99
+oid sha256:3397443887ad75297f2cfb2a69be35ef612bea0ae602db3f9eff68d6f6b6a0bd
 size 39398

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48d41985628b63b1f03308534e42f5f4fade1dc9f1a7ca147144af3b829d1153
+oid sha256:52c1e8dd4ba9ace9e6fcca937683862f29cfd6bf4fb3642d8d44c9c9a4359dc1
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c50dbaa792cda4a28fbbc2acb2a3e03c59530712bbc5107212d33064d193da4
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.01117798796216681,
+  "epoch": 0.014330753797649757,
   "eval_steps": 10,
-  "global_step": 39,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -88,6 +88,43 @@
       "learning_rate": 3.086582838174551e-05,
       "loss": 11.9437,
       "step": 35
+    },
+    {
+      "epoch": 0.011464603038119804,
+      "grad_norm": 0.024526268243789673,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 11.9457,
+      "step": 40
+    },
+    {
+      "epoch": 0.011464603038119804,
+      "eval_loss": 11.942913055419922,
+      "eval_runtime": 24.2726,
+      "eval_samples_per_second": 60.562,
+      "eval_steps_per_second": 30.281,
+      "step": 40
+    },
+    {
+      "epoch": 0.012897678417884782,
+      "grad_norm": 0.018200471997261047,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 11.9401,
+      "step": 45
+    },
+    {
+      "epoch": 0.014330753797649757,
+      "grad_norm": 0.030765095725655556,
+      "learning_rate": 0.0,
+      "loss": 11.9439,
+      "step": 50
+    },
+    {
+      "epoch": 0.014330753797649757,
+      "eval_loss": 11.942886352539062,
+      "eval_runtime": 23.8007,
+      "eval_samples_per_second": 61.763,
+      "eval_steps_per_second": 30.881,
+      "step": 50
     }
   ],
   "logging_steps": 5,
@@ -102,12 +139,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 4608294912.0,
+  "total_flos": 5908070400.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null