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:fa8dcaa92cdad44f692e7a53ade4409827565ab12d249564503e3381902a885f
+oid sha256:1c2171e730d15571e62bd1680955fd19ae833882d1a4698336faadfd53a40dee
 size 36981072

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:453d294245b806d60124f5a22e7a38b6bc868b32fe28fdb1b6abb19484242db4
+oid sha256:f711bdd4522a4cb6599494975540f4ecd5fed33c21d59e453c8712a7a796771b
 size 19859140

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c158abb1290faa386d5662dd18d37e1778c62c35aba6e76d3ce8d6145626bb6e
+oid sha256:118dfa0cbe03e75032b8d28766a92789e26dbdff4b5a258076d82c544f587623
 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": 0.0010488100040338846,
+  "epoch": 0.001344628210299852,
   "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": 1.0158,
       "step": 35
+    },
+    {
+      "epoch": 0.0010757025682398816,
+      "grad_norm": 0.47830018401145935,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.0883,
+      "step": 40
+    },
+    {
+      "epoch": 0.0010757025682398816,
+      "eval_loss": 1.1898620128631592,
+      "eval_runtime": 638.7298,
+      "eval_samples_per_second": 24.513,
+      "eval_steps_per_second": 12.257,
+      "step": 40
+    },
+    {
+      "epoch": 0.0012101653892698668,
+      "grad_norm": 0.695751965045929,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.0682,
+      "step": 45
+    },
+    {
+      "epoch": 0.001344628210299852,
+      "grad_norm": 0.46239423751831055,
+      "learning_rate": 0.0,
+      "loss": 0.9861,
+      "step": 50
+    },
+    {
+      "epoch": 0.001344628210299852,
+      "eval_loss": 1.1852054595947266,
+      "eval_runtime": 639.9704,
+      "eval_samples_per_second": 24.465,
+      "eval_steps_per_second": 12.233,
+      "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": 1743103139512320.0,
+  "total_flos": 2229550527283200.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null