Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f52cf92ccea26d70fff979f290f24fc3be73a4ab201982f479ef76236d94f5a
+oid sha256:c1c0cec808826c5634287a6c619785e483b3d8c057966fa7d02ff71a3febbda0
 size 50899792

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16d56c7b94f90c2ec8b1cdac71a3de5f57d53253d3f038a267e1f13cc5806c1f
+oid sha256:cac687267b611175ff1f8b1035c57fff2a84293bf688dbad181d3dee90da3443
 size 26231300

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60197ddd2b9e7ee46919c36404e76c5aca074008f3439670b71d1d51cb8b8db7
+oid sha256:d9a8129b15783fce809c3d71373b8daf1f14f9ed4a08489d93cdef55470a4373
 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": 0.0009212290139896894,
+  "epoch": 0.0011810628384483195,
   "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": 1.9824,
       "step": 35
+    },
+    {
+      "epoch": 0.0009448502707586557,
+      "grad_norm": 1.50521719455719,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.86,
+      "step": 40
+    },
+    {
+      "epoch": 0.0009448502707586557,
+      "eval_loss": 1.9020222425460815,
+      "eval_runtime": 1103.6246,
+      "eval_samples_per_second": 16.152,
+      "eval_steps_per_second": 8.076,
+      "step": 40
+    },
+    {
+      "epoch": 0.0010629565546034876,
+      "grad_norm": 1.6052892208099365,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.779,
+      "step": 45
+    },
+    {
+      "epoch": 0.0011810628384483195,
+      "grad_norm": 1.7195042371749878,
+      "learning_rate": 0.0,
+      "loss": 1.8553,
+      "step": 50
+    },
+    {
+      "epoch": 0.0011810628384483195,
+      "eval_loss": 1.8959852457046509,
+      "eval_runtime": 1102.5425,
+      "eval_samples_per_second": 16.168,
+      "eval_steps_per_second": 8.084,
+      "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": 6109362554142720.0,
+  "total_flos": 7810963533987840.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null