Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:227a4d083f7700256b4cbf57e711050fcb7780d95f558ab496ab8b1b9c7bb914
+oid sha256:e5fff6a734e9580916463add9af925cb68a720f2860d05dedce9726aa3027e48
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b66ed7335ffb213076c829b3e75e5f96e136016f10afa892af96522ea8548e0b
+oid sha256:9c9c7dec3f31bc6007fdd5be396e65bf2a16f79e5e1696c7e8028047593375d1
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:67d4ae498d6b04d7b171f16c571dee355aabf7bb9bc90e736b190c4954cfba67
+oid sha256:135e13563b86e986281c272de8f9ed76f293fecfb3da0d1602f4a9efd6fa5a33
 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": 0.0017047689819469337,
+  "epoch": 0.0021856012589063253,
   "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": 1.9451,
       "step": 35
+    },
+    {
+      "epoch": 0.0017484810071250602,
+      "grad_norm": 4.276152610778809,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.635,
+      "step": 40
+    },
+    {
+      "epoch": 0.0017484810071250602,
+      "eval_loss": 0.45457473397254944,
+      "eval_runtime": 1071.3804,
+      "eval_samples_per_second": 8.991,
+      "eval_steps_per_second": 4.496,
+      "step": 40
+    },
+    {
+      "epoch": 0.0019670411330156927,
+      "grad_norm": 4.214913845062256,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.7661,
+      "step": 45
+    },
+    {
+      "epoch": 0.0021856012589063253,
+      "grad_norm": 3.808881998062134,
+      "learning_rate": 0.0,
+      "loss": 1.8696,
+      "step": 50
+    },
+    {
+      "epoch": 0.0021856012589063253,
+      "eval_loss": 0.4522906243801117,
+      "eval_runtime": 1070.7411,
+      "eval_samples_per_second": 8.997,
+      "eval_steps_per_second": 4.499,
+      "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": 1.2838320929243136e+16,
+  "total_flos": 1.6562748502573056e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null