Training in progress, step 5, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b6d86e9fb0a528c43f602c74714266145b6aa6662b7405ccb76fbea539d0d292
+oid sha256:2cc988ae07c49b16f715c16c66dcd131ab5bec98cd0cf70671ba06e46f94be8a
 size 50365768

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c81102da50313443baeb5ae4866aa1807e37b8dc1d7f9ced7334d87fcc22789
+oid sha256:43bf6739fbb6a2bb3b9bab203206707fdb694a62215f17db98e358e68992d565
 size 25859156

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b6d72637e6cf5ac03358ca59d9f0e56e73e8fcc3ca2a82aeac8e0c5dca17bd18
+oid sha256:d851545478967cc7c2e593b62f547a51df81d646f155d97e969bce2c2b83f681
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7adb031dc938779259a07e684ea318126e92e52b40c256b93ef474d2ac57a5b
+oid sha256:2d63217b923cb177f669d6bc2174b89abdc6a56d968d279b505491b37976d9bb
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.007322654462242563,
+  "epoch": 0.009153318077803204,
   "eval_steps": 2,
-  "global_step": 4,
+  "global_step": 5,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -59,6 +59,13 @@
       "eval_samples_per_second": 57.391,
       "eval_steps_per_second": 28.696,
       "step": 4
+    },
+    {
+      "epoch": 0.009153318077803204,
+      "grad_norm": 65.52117156982422,
+      "learning_rate": 5e-05,
+      "loss": 174.0482,
+      "step": 5
     }
   ],
   "logging_steps": 1,
@@ -73,12 +80,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1468725404368896.0,
+  "total_flos": 1835906755461120.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null