Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:195bf9d81f051b86b75272ecf1c1959686558995094cdb78b55eb7508f770326
+oid sha256:b59ae0c65fd66d333a6afa6a3e0eb355737767312007a55a6e7f7a51aaecf029
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf2ab33f906e69acdb920c591de3d56714dc590e5c690fed6de7aea9a2ca0120
+oid sha256:57aa5093bb35041d5edb05277f65db2ae0cf0daed8d75ddfdbc54b9b4f44896b
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d267add0f57facc2bcd1f0495b322eae339f52c0bf72ab67697d1854f1fd656
+oid sha256:7da9f1139f61cc766662dec9be1a789e9af6ce81829e82037fdc4fc6fe2c5c18
 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": 0.0012104940522840316,
+  "epoch": 0.0015519154516461943,
   "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": 0.4837,
       "step": 35
+    },
+    {
+      "epoch": 0.0012415323613169554,
+      "grad_norm": 1.2722738981246948,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.4368,
+      "step": 40
+    },
+    {
+      "epoch": 0.0012415323613169554,
+      "eval_loss": 0.4388025104999542,
+      "eval_runtime": 1356.999,
+      "eval_samples_per_second": 9.997,
+      "eval_steps_per_second": 4.999,
+      "step": 40
+    },
+    {
+      "epoch": 0.0013967239064815748,
+      "grad_norm": 1.1449508666992188,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.3963,
+      "step": 45
+    },
+    {
+      "epoch": 0.0015519154516461943,
+      "grad_norm": 0.7516467571258545,
+      "learning_rate": 0.0,
+      "loss": 0.403,
+      "step": 50
+    },
+    {
+      "epoch": 0.0015519154516461943,
+      "eval_loss": 0.41470852494239807,
+      "eval_runtime": 1355.9699,
+      "eval_samples_per_second": 10.005,
+      "eval_steps_per_second": 5.002,
+      "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": 1.1971306928996352e+16,
+  "total_flos": 1.547311779938304e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null