Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:691a08ccf2b1b967d034c43e0b8d418078f72bf2666c3e5b7ec342696d720cf9
+oid sha256:97a29cf9165af3516d0b24d418facb7cb4690c23ab990c11d304809d5c2ab323
 size 12609416

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7688c80e59a5704772c8a39a2dfd7a2b24e10f5fa38e2c76865145bbd1a231ec
+oid sha256:ad724fd5e07a171c7f3b0a1b463e7797aa183a5d206bbfd5257f6de2e530fdeb
 size 6615034

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4db7649aa3d75e5d6374a79c834bacb769f27bfd7c17dce1ae63aba9b819ad74
+oid sha256:d04c7afdb7570a9aff6dc2cf01b65f852fca83da78161bbe9997eb4c29f9c539
 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": 0.022018348623853212,
+  "epoch": 0.028228652081863093,
   "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": 7.8261,
       "step": 35
+    },
+    {
+      "epoch": 0.022582921665490474,
+      "grad_norm": 3.3246023654937744,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 8.0502,
+      "step": 40
+    },
+    {
+      "epoch": 0.022582921665490474,
+      "eval_loss": 1.846505880355835,
+      "eval_runtime": 45.256,
+      "eval_samples_per_second": 16.484,
+      "eval_steps_per_second": 8.242,
+      "step": 40
+    },
+    {
+      "epoch": 0.025405786873676783,
+      "grad_norm": 5.303725719451904,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 8.4275,
+      "step": 45
+    },
+    {
+      "epoch": 0.028228652081863093,
+      "grad_norm": 4.683985233306885,
+      "learning_rate": 0.0,
+      "loss": 7.3733,
+      "step": 50
+    },
+    {
+      "epoch": 0.028228652081863093,
+      "eval_loss": 1.842321753501892,
+      "eval_runtime": 39.8642,
+      "eval_samples_per_second": 18.714,
+      "eval_steps_per_second": 9.357,
+      "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": 337813438464000.0,
+  "total_flos": 431650504704000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null