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:c28411ab7e129dc19fe903e51a1bd4f1c71c4eca45b7fce3dec394a0b2a85c9b
+oid sha256:40e57d9025d5b2f71a951663bc998ef1cd74d4e3edccd91cbb96dbdfd2e15f2b
 size 767856

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e026144b5b4d6d9d8e50b34814855b05fa0f36bed2e2b4c123061a31e68c791e
+oid sha256:ba3a973fabb9a95ee826f04f2c2d0c480f3c6dd20783996a9772bf3de092ccc3
 size 1003002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4661b5fd937f7fc4ac64474a7a07bb8f9b1fb3a173ee34b9881690e1316152dd
+oid sha256:03b6cde79fbc4b5b26bf00e97c36fd2d90b042fd30be528f298072427e071121
 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": 0.002551834130781499,
+  "epoch": 0.003827751196172249,
   "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": 36.057,
       "eval_steps_per_second": 18.029,
       "step": 6
+    },
+    {
+      "epoch": 0.0029771398192450825,
+      "grad_norm": 2.6640219688415527,
+      "learning_rate": 0.00014,
+      "loss": 8.891,
+      "step": 7
+    },
+    {
+      "epoch": 0.0034024455077086655,
+      "grad_norm": 2.275404453277588,
+      "learning_rate": 0.00016,
+      "loss": 8.5015,
+      "step": 8
+    },
+    {
+      "epoch": 0.003827751196172249,
+      "grad_norm": 1.836250901222229,
+      "learning_rate": 0.00018,
+      "loss": 8.0423,
+      "step": 9
+    },
+    {
+      "epoch": 0.003827751196172249,
+      "eval_loss": 8.309639930725098,
+      "eval_runtime": 27.2243,
+      "eval_samples_per_second": 36.365,
+      "eval_steps_per_second": 18.182,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3257942409216.0,
+  "total_flos": 4886913613824.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null