Training in progress, step 400, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8f90adadd98f816d43d5f9bf59fcc41095fe2b5e1d15f9807581089eebed8b9
+oid sha256:cf8d88266600b800452ac768b5345fc2c5e2125f8ca0dc6da5a809548c1b4701
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff388910fba3c1db8fa1508313b2b1728d680ecfc4bd395c1ba29939b3871436
+oid sha256:37044f223fc40fb62ec3e1d7bac450c33c7bb6d698c7a7bbb0615762a79a84c0
 size 170920532

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:08df764ba3a826da606e5be74bf6c0678d02c018b2820915cdce1158a3ff69c6
+oid sha256:3f1e51ce000dd278674085907731f0619de6016da63aed846562fbbcc89a81ef
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f9c4f24febed8904edd77d7c3dfeceec80ce8ac46f187c13cc543808d5fa2a7b
+oid sha256:3b222f50cf4019bf2a4af9801ee61ced983584829f5aab356a024b6284fbfaea
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.040958427196395655,
+  "epoch": 0.05461123626186088,
   "eval_steps": 100,
-  "global_step": 300,
+  "global_step": 400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -81,6 +81,28 @@
       "eval_samples_per_second": 35.217,
       "eval_steps_per_second": 8.804,
       "step": 300
+    },
+    {
+      "epoch": 0.04778483172912827,
+      "grad_norm": 119.89105987548828,
+      "learning_rate": 0.00025,
+      "loss": 8.7543,
+      "step": 350
+    },
+    {
+      "epoch": 0.05461123626186088,
+      "grad_norm": 105.20377349853516,
+      "learning_rate": 0.00025,
+      "loss": 8.8703,
+      "step": 400
+    },
+    {
+      "epoch": 0.05461123626186088,
+      "eval_loss": 2.3381218910217285,
+      "eval_runtime": 175.3225,
+      "eval_samples_per_second": 35.181,
+      "eval_steps_per_second": 8.795,
+      "step": 400
     }
   ],
   "logging_steps": 50,
@@ -95,12 +117,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.060879000928256e+17,
+  "total_flos": 1.414505334571008e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null