Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:012f61e2dfb670cb2981ce592845edfd66cb637c0e28a6f02f458d198134bc73
+oid sha256:49f35e375a5ad2202d6f3af2c11cb9f9781e43eda8f3a09786476a882439b5cb
 size 41581360

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b79cc9a77f5688a283bbd745400f58f4fd63663b045112858b45c452c6302206
+oid sha256:85859ec662f4024e78aa63eb010c2af6e276804f5e6b14a6d6f5bc951bc6f006
 size 21505540

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c0473a82658c627429c106558fb3bb262aa9211c031722dafa14ae2d5bab0f9e
+oid sha256:fc8b30dc45df2e7849e049e2f88f3af04b8eb2fec3f79a4131192a96147a0392
 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": 0.017717206132879047,
+  "epoch": 0.022714366837024418,
   "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": 0.0018,
       "step": 35
+    },
+    {
+      "epoch": 0.018171493469619535,
+      "grad_norm": 0.01361869927495718,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.0004,
+      "step": 40
+    },
+    {
+      "epoch": 0.018171493469619535,
+      "eval_loss": 0.0021691254805773497,
+      "eval_runtime": 49.1642,
+      "eval_samples_per_second": 18.855,
+      "eval_steps_per_second": 9.438,
+      "step": 40
+    },
+    {
+      "epoch": 0.020442930153321975,
+      "grad_norm": 0.020270636305212975,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.001,
+      "step": 45
+    },
+    {
+      "epoch": 0.022714366837024418,
+      "grad_norm": 0.010211742483079433,
+      "learning_rate": 0.0,
+      "loss": 0.0019,
+      "step": 50
+    },
+    {
+      "epoch": 0.022714366837024418,
+      "eval_loss": 0.001980047207325697,
+      "eval_runtime": 49.0112,
+      "eval_samples_per_second": 18.914,
+      "eval_steps_per_second": 9.467,
+      "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": 1950379589763072.0,
+  "total_flos": 2500486653542400.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null