Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49d1db1d3e55f52a434a8a016d34444eccdd6f7727311c4976272b40597d5fb8
+oid sha256:d2dd9da4ac0084eda2da4664c89440d6a672dd3b57c8ccbe2b962db2e97388be
 size 27024

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a8c475cb73ac6162cd70280525a1519eed05f519bbb3c4d94a5aec401f6f23a
+oid sha256:afbedb5a9078a942161dc0fdf663ecc53e23cde75e63aaf7d1f297fa891c15f7
 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": 0.15204678362573099,
+  "epoch": 0.1949317738791423,
   "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": 10.3709,
       "step": 35
+    },
+    {
+      "epoch": 0.15594541910331383,
+      "grad_norm": 0.18550260365009308,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 10.3873,
+      "step": 40
+    },
+    {
+      "epoch": 0.15594541910331383,
+      "eval_loss": NaN,
+      "eval_runtime": 0.7913,
+      "eval_samples_per_second": 137.752,
+      "eval_steps_per_second": 69.508,
+      "step": 40
+    },
+    {
+      "epoch": 0.17543859649122806,
+      "grad_norm": 0.26159873604774475,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 10.3978,
+      "step": 45
+    },
+    {
+      "epoch": 0.1949317738791423,
+      "grad_norm": 0.26113927364349365,
+      "learning_rate": 0.0,
+      "loss": 10.4081,
+      "step": 50
+    },
+    {
+      "epoch": 0.1949317738791423,
+      "eval_loss": NaN,
+      "eval_runtime": 0.8116,
+      "eval_samples_per_second": 134.301,
+      "eval_steps_per_second": 67.767,
+      "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": 504305418240.0,
+  "total_flos": 646545408000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null