Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a26c8e128c5dc26d8ff4ccf250f97980b651ba6864cb77b0079a96e63616a97
+oid sha256:747420620b3c3f0064b2f5765237b4b1ce7e9acd25bbd270077c061224e1b29c
 size 108113968

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90cea94123626b1ac41d3c9bce9b81fac42a8037904ff15f17c174b594a85ca8
+oid sha256:4dcf869ad51c172a279ea30992851a8e6a983ed6766582195af29f6f4f2e0c42
 size 55549892

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb8533fae84b8bbe35ecff98d5d66a1e19344edfcde38ca202b781a73c8943ca
+oid sha256:6d3253e1657e0e5e1dce4606e0080d6574b33a3e708581e44bc5526ab5260da9
 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": 0.002319512902290519,
+  "epoch": 0.0034792693534357786,
   "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": 20.781,
       "eval_steps_per_second": 10.391,
       "step": 6
+    },
+    {
+      "epoch": 0.0027060983860056056,
+      "grad_norm": 3.7439322471618652,
+      "learning_rate": 0.00014,
+      "loss": 2.0192,
+      "step": 7
+    },
+    {
+      "epoch": 0.003092683869720692,
+      "grad_norm": 3.7384166717529297,
+      "learning_rate": 0.00016,
+      "loss": 1.8645,
+      "step": 8
+    },
+    {
+      "epoch": 0.0034792693534357786,
+      "grad_norm": 8.410094261169434,
+      "learning_rate": 0.00018,
+      "loss": 1.6249,
+      "step": 9
+    },
+    {
+      "epoch": 0.0034792693534357786,
+      "eval_loss": 1.3259292840957642,
+      "eval_runtime": 52.4965,
+      "eval_samples_per_second": 20.763,
+      "eval_steps_per_second": 10.382,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1231436170395648.0,
+  "total_flos": 1847154255593472.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null