Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5993c4c4d163ab954dfe832519aca623bdad9e0764b4903b237e97f672c90d35
+oid sha256:e1f8ecc8054e63d9c6fb1829b5b02a32e8d845c5b8d6bb6d259d43344cabe9af
 size 100059752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:86b8d8a813490530fbba566b07f2c305142f58a531309e3c7b033a6ca7512e61
+oid sha256:64342d41f393bf778566987beb2141833f89aaceafedfa3aca4732431c0ea674
 size 51244020

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:adcef6bfbc179f9fd9fbbf02516b588576682520022367d731ffaa9dcbdda165
+oid sha256:72c97bc565cd4fb8a42b76a6ece2fcb3dd5e28308569908026f4f891351c64fa
 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": 0.000163036832737796,
+  "epoch": 0.000244555249106694,
   "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": 17.568,
       "eval_steps_per_second": 8.784,
       "step": 6
+    },
+    {
+      "epoch": 0.00019020963819409536,
+      "grad_norm": 2.5171914100646973,
+      "learning_rate": 0.00014,
+      "loss": 5.4049,
+      "step": 7
+    },
+    {
+      "epoch": 0.00021738244365039467,
+      "grad_norm": 2.4000532627105713,
+      "learning_rate": 0.00016,
+      "loss": 5.2732,
+      "step": 8
+    },
+    {
+      "epoch": 0.000244555249106694,
+      "grad_norm": 2.154792070388794,
+      "learning_rate": 0.00018,
+      "loss": 5.1387,
+      "step": 9
+    },
+    {
+      "epoch": 0.000244555249106694,
+      "eval_loss": 5.242025375366211,
+      "eval_runtime": 868.9503,
+      "eval_samples_per_second": 17.833,
+      "eval_steps_per_second": 8.917,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2054423272488960.0,
+  "total_flos": 2962191695216640.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null