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:f4904327f8f063e6dd04283410bf202ab0ce2bb292aee0bf2045e14ddb36012c
+oid sha256:315ffa69ed604c387b950beb0d9d78ad3c20c37df98b6d58f88e570f41db8b58
 size 14293800

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6dbea85cb2b6f5557f7a76c8059d54fc8507f4620fd88b8e7d372d05ebf4147f
+oid sha256:406d30f541556b5dbf1ccda3236b3862992227c7ac597581163e2dcdf1728555
 size 7579748

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48a84c97558db5262111bb17d0395336ca03552f19e790c3b78562de97f26be3
+oid sha256:7144f07860e903d0de4cfb17115d344c0c4d0a05aa8552f2c9576c83ba256f73
 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": 0.001997835678015483,
+  "epoch": 0.002996753517023225,
   "eval_steps": 3,
-  "global_step": 6,
+  "global_step": 9,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -65,6 +65,35 @@
       "eval_samples_per_second": 34.454,
       "eval_steps_per_second": 17.241,
       "step": 6
+    },
+    {
+      "epoch": 0.0023308082910180636,
+      "grad_norm": 12.037104606628418,
+      "learning_rate": 0.00014,
+      "loss": 10.1633,
+      "step": 7
+    },
+    {
+      "epoch": 0.0026637809040206445,
+      "grad_norm": 12.180617332458496,
+      "learning_rate": 0.00016,
+      "loss": 12.9175,
+      "step": 8
+    },
+    {
+      "epoch": 0.002996753517023225,
+      "grad_norm": 11.945866584777832,
+      "learning_rate": 0.00018,
+      "loss": 13.2716,
+      "step": 9
+    },
+    {
+      "epoch": 0.002996753517023225,
+      "eval_loss": 3.0132131576538086,
+      "eval_runtime": 36.6413,
+      "eval_samples_per_second": 34.524,
+      "eval_steps_per_second": 17.276,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -84,7 +113,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 45257412575232.0,
+  "total_flos": 69771844386816.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null