Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:19ae7125d034ff264f330bc6f03491eb2bfd9b7f45c35a196594d643a3fa6207
+oid sha256:0178300e53c6f26fb59257bf6f078f4064212f12c08a93e97731cc5d02eaf41c
 size 390888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb73d85b76527f291eae9fef4fc14669ca986ff9a757fd5c5536cbed915ff4a7
+oid sha256:8741793e1065888c5b87ae38e304268c447146005edb40ed06ddd2cb7ee923ff
 size 819770

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:518e568369e71743f4b5da12a73c75b71f6b05b27911c3002446d907fd717c19
+oid sha256:4ee72a31d22052348c07102c08f84ab7849eb7e93d145abba650cffaf3eecd9b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75c3c8ae7ddabeca3cb69703f6b35f00b9125a4c27b56ccba4ed0e4669bb5433
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.37681159420289856,
+  "epoch": 0.4830917874396135,
   "eval_steps": 10,
-  "global_step": 39,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -60,6 +60,36 @@
       "eval_samples_per_second": 237.36,
       "eval_steps_per_second": 29.925,
       "step": 30
+    },
+    {
+      "epoch": 0.3864734299516908,
+      "grad_norm": 9.781479835510254,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 7.1231,
+      "step": 40
+    },
+    {
+      "epoch": 0.3864734299516908,
+      "eval_loss": 7.0239973068237305,
+      "eval_runtime": 3.0092,
+      "eval_samples_per_second": 231.954,
+      "eval_steps_per_second": 29.244,
+      "step": 40
+    },
+    {
+      "epoch": 0.4830917874396135,
+      "grad_norm": 9.775260925292969,
+      "learning_rate": 0.0,
+      "loss": 6.9844,
+      "step": 50
+    },
+    {
+      "epoch": 0.4830917874396135,
+      "eval_loss": 6.96579647064209,
+      "eval_runtime": 2.9634,
+      "eval_samples_per_second": 235.542,
+      "eval_steps_per_second": 29.696,
+      "step": 50
     }
   ],
   "logging_steps": 10,
@@ -74,12 +104,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 71458813378560.0,
+  "total_flos": 91781962137600.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null