Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:979c2f530ccc11395e32bb54cd6e1a8ad9121b7410ba57a4b99e74874bf07aef
+oid sha256:6dd0418a3840564d96f01f2db176a8b7a7f85e6fff598bc4f899202bb6189271
 size 27024

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce42d2691dc006a0dcfdd669bf1a55e5064e669313eb284ceb0d75ce226a6f98
+oid sha256:37fdfa315bf77ce2eeacf4ded6974c53e57beb674ee7fbf86bb39a1d506c8673
 size 63974

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": 0.027387640449438203,
+  "epoch": 0.0351123595505618,
   "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": 11.7447,
       "step": 35
+    },
+    {
+      "epoch": 0.028089887640449437,
+      "grad_norm": 0.18757085502147675,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 11.7128,
+      "step": 40
+    },
+    {
+      "epoch": 0.028089887640449437,
+      "eval_loss": 11.733393669128418,
+      "eval_runtime": 6.0275,
+      "eval_samples_per_second": 99.544,
+      "eval_steps_per_second": 49.772,
+      "step": 40
+    },
+    {
+      "epoch": 0.03160112359550562,
+      "grad_norm": 0.19444578886032104,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 11.7489,
+      "step": 45
+    },
+    {
+      "epoch": 0.0351123595505618,
+      "grad_norm": 0.2428700029850006,
+      "learning_rate": 0.0,
+      "loss": 11.7347,
+      "step": 50
+    },
+    {
+      "epoch": 0.0351123595505618,
+      "eval_loss": 11.733201026916504,
+      "eval_runtime": 6.0062,
+      "eval_samples_per_second": 99.896,
+      "eval_steps_per_second": 49.948,
+      "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": 2018517221376.0,
+  "total_flos": 2577100603392.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null