Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe98fdb395c9aef482bd73af6217491bad126e0a423730728c03984f83574264
+oid sha256:9ab60e591437b747ffd6dcf2921953fe17acd894a9384286ceb3e9d1b30a8434
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cdc087f95012abf1acaf4e8a51b83a57044078de1a7af6ae258d85ec696d479e
+oid sha256:eaf4766f45ba23a93d9d0500bdbe594fec30e81f0182ee8875933c40a4c65b41
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e7b14d0c915e2c4063f110f3dbec036a026b529b8820509b2913f154771be18b
+oid sha256:e9ed9626ba6e412f40126198b85320c11d70caab3bee87c19069e3aea6dd4f83
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
+oid sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.013753581661891117,
+  "epoch": 0.020630372492836675,
   "eval_steps": 3,
-  "global_step": 6,
+  "global_step": 9,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -73,6 +73,35 @@
       "eval_samples_per_second": 17.652,
       "eval_steps_per_second": 8.826,
       "step": 6
+    },
+    {
+      "epoch": 0.016045845272206302,
+      "grad_norm": 5.96946382522583,
+      "learning_rate": 0.00014,
+      "loss": 2.1551,
+      "step": 7
+    },
+    {
+      "epoch": 0.01833810888252149,
+      "grad_norm": 4.590500354766846,
+      "learning_rate": 0.00016,
+      "loss": 1.9279,
+      "step": 8
+    },
+    {
+      "epoch": 0.020630372492836675,
+      "grad_norm": 5.2422919273376465,
+      "learning_rate": 0.00018,
+      "loss": 2.0522,
+      "step": 9
+    },
+    {
+      "epoch": 0.020630372492836675,
+      "eval_loss": 0.4911685287952423,
+      "eval_runtime": 10.4201,
+      "eval_samples_per_second": 17.658,
+      "eval_steps_per_second": 8.829,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2103206159056896.0,
+  "total_flos": 3154809238585344.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null