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:a5e5b63540196b99e4d259dfab9288ee5c01d7c99fae4205a4f77da798b71bd4
+oid sha256:d1236da078cb62aa9dd35f7478c85d8f09da9add1976e5d12dc1fde3e84e29dc
 size 161714

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33e0e8be5b931c8c8a42c86bbf399fa652edad979ca06ec8b0208345b712dd56
+oid sha256:52d8e61567fb63276d17a6190fa37c47f5bc4153399656de20a6f28d22ef5c27
 size 64750

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6427ffbd65b4be1b2f3fbb643f167933e7260181d95492a2b6d8cd2d25b75737
+oid sha256:dae2cff01f9b0fc3a44f22c10b61e1a8883cd6f6a47e470e57981350e6a19d5d
 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": 0.055201698513800426,
+  "epoch": 0.07077140835102619,
   "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": 6.9226,
       "step": 35
+    },
+    {
+      "epoch": 0.056617126680820945,
+      "grad_norm": 0.10181432217359543,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 6.9217,
+      "step": 40
+    },
+    {
+      "epoch": 0.056617126680820945,
+      "eval_loss": 6.923534870147705,
+      "eval_runtime": 1.3597,
+      "eval_samples_per_second": 219.17,
+      "eval_steps_per_second": 109.585,
+      "step": 40
+    },
+    {
+      "epoch": 0.06369426751592357,
+      "grad_norm": 0.10488573461771011,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 6.9213,
+      "step": 45
+    },
+    {
+      "epoch": 0.07077140835102619,
+      "grad_norm": 0.10614355653524399,
+      "learning_rate": 0.0,
+      "loss": 6.9204,
+      "step": 50
+    },
+    {
+      "epoch": 0.07077140835102619,
+      "eval_loss": 6.923311233520508,
+      "eval_runtime": 1.3429,
+      "eval_samples_per_second": 221.909,
+      "eval_steps_per_second": 110.955,
+      "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": 102829768704.0,
+  "total_flos": 131833036800.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null