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:e0fb3e4c14ba606cb0a6c76287b6efb9009c93c055992dcd15bc012af34da2c2
+oid sha256:11d3418536905c80283441b35278ed954149dddd309dd03869dce2749838f526
 size 12609416

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8264f754f907f2d8c145b7816918f95bb12360bb75b254b24cdc5b8cf42d01e0
+oid sha256:420418f2f2f8ea74b8038b117819aa589af8102d023eaa098d321cf526f89c15
 size 6615034

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:248b83e156267aeaad0b24a8a39efe5d8e1a4161145b352741eb9e33a27f29d7
+oid sha256:37a1d57dcf6d6a809cbd33f03ec44415e52213e48cac682f33531386d9556ac5
 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": 0.0029809961495466403,
+  "epoch": 0.0044714942243199605,
   "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": 85.509,
       "eval_steps_per_second": 42.754,
       "step": 6
+    },
+    {
+      "epoch": 0.0034778288411377468,
+      "grad_norm": 10.729366302490234,
+      "learning_rate": 0.00014,
+      "loss": 16.1147,
+      "step": 7
+    },
+    {
+      "epoch": 0.003974661532728853,
+      "grad_norm": 18.95943832397461,
+      "learning_rate": 0.00016,
+      "loss": 20.5381,
+      "step": 8
+    },
+    {
+      "epoch": 0.0044714942243199605,
+      "grad_norm": 19.25127601623535,
+      "learning_rate": 0.00018,
+      "loss": 18.0612,
+      "step": 9
+    },
+    {
+      "epoch": 0.0044714942243199605,
+      "eval_loss": 3.78324556350708,
+      "eval_runtime": 9.6298,
+      "eval_samples_per_second": 88.06,
+      "eval_steps_per_second": 44.03,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 45041791795200.0,
+  "total_flos": 67562687692800.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null