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:acae508858dd3e461721fc512b8fa6e6bff8ae03f0d5387d34d691d3573023c3
+oid sha256:b006e075b5558ef7c6adb23fb7f16e51402785594c26bf57efeb3dcc5e24da62
 size 767856

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f475e9a613b138efd5f93385ab70af8135ea7cd389b55dd228d75468933d2ea
+oid sha256:4b61c14112728d2ade6ec3f8a437bfb9cb458bc83a5ed74623b83549c39b13c0
 size 1003002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f146e771caadf61177d3f4ac41547e6e67b9b4f5456644cb35680903e92b1413
+oid sha256:a7ecc63df12c57baa58797cbad45fd25f5504b307a5ad4ad822f1c6c0804d66f
 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": 0.001037254732474717,
+  "epoch": 0.0015558820987120754,
   "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": 23.153,
       "eval_steps_per_second": 11.577,
       "step": 6
+    },
+    {
+      "epoch": 0.001210130521220503,
+      "grad_norm": 3.7763233184814453,
+      "learning_rate": 0.00014,
+      "loss": 10.4266,
+      "step": 7
+    },
+    {
+      "epoch": 0.0013830063099662892,
+      "grad_norm": 3.3314616680145264,
+      "learning_rate": 0.00016,
+      "loss": 10.0965,
+      "step": 8
+    },
+    {
+      "epoch": 0.0015558820987120754,
+      "grad_norm": 3.2022037506103516,
+      "learning_rate": 0.00018,
+      "loss": 10.0676,
+      "step": 9
+    },
+    {
+      "epoch": 0.0015558820987120754,
+      "eval_loss": 9.950599670410156,
+      "eval_runtime": 106.7503,
+      "eval_samples_per_second": 22.82,
+      "eval_steps_per_second": 11.41,
+      "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