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:a9f8dd5137ab509cf19c08ce56da3b8b2584d6e86d67419313826e30d8cf70ec
+oid sha256:9a924e6bfa1ca0687de7a9338e58e32b11a2a5abd3bc0f3909336d36d4b0aa88
 size 41581360

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:981b34d49485fb43b031402f8985bfc7bf4b354925c42fae14fe4f3c4fdec569
+oid sha256:0f71a8774a3057892796b42202c1666cb88a0d22a7fa5f03b1e95967155c247b
 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": 0.14233576642335766,
+  "epoch": 0.18248175182481752,
   "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": 0.1365,
       "step": 35
+    },
+    {
+      "epoch": 0.145985401459854,
+      "grad_norm": 1.1791236400604248,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.0655,
+      "step": 40
+    },
+    {
+      "epoch": 0.145985401459854,
+      "eval_loss": 0.045773398131132126,
+      "eval_runtime": 6.3415,
+      "eval_samples_per_second": 18.292,
+      "eval_steps_per_second": 9.146,
+      "step": 40
+    },
+    {
+      "epoch": 0.16423357664233576,
+      "grad_norm": 1.3011243343353271,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.0399,
+      "step": 45
+    },
+    {
+      "epoch": 0.18248175182481752,
+      "grad_norm": 0.8173432946205139,
+      "learning_rate": 0.0,
+      "loss": 0.0427,
+      "step": 50
+    },
+    {
+      "epoch": 0.18248175182481752,
+      "eval_loss": 0.03340202569961548,
+      "eval_runtime": 6.2937,
+      "eval_samples_per_second": 18.431,
+      "eval_steps_per_second": 9.216,
+      "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