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:ade2847a58db8b6423a5f4fa8082d97cfa75fd0f71d3775ae81d566b1f48ab5d
+oid sha256:063b6e7b123cd0b0d531bdcc9a5a582f479116b38763244730344118cd444d37
 size 22573704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c77475810e399bb2c1186bbcd668401c86bf133df0c5589bdef1ad205621b206
+oid sha256:bfc04eccaefdae34d8c191c216f5f0c28718ffaa3677c8029cd1deb8b359cd38
 size 11710970

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8aa98b654a6ad98d9998c44f95a9ec59c7edf25202ad9a4080fb894c3b37d6e0
+oid sha256:e430790c418395df8ca73708b8c4c3a500f2ad56804e8db2527f4c5b2ee2f2c1
 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": 0.0009370607527721381,
+  "epoch": 0.001405591129158207,
   "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": 47.662,
       "eval_steps_per_second": 23.84,
       "step": 6
+    },
+    {
+      "epoch": 0.0010932375449008277,
+      "grad_norm": 5.162273406982422,
+      "learning_rate": 0.00014,
+      "loss": 5.2246,
+      "step": 7
+    },
+    {
+      "epoch": 0.0012494143370295175,
+      "grad_norm": 6.320584774017334,
+      "learning_rate": 0.00016,
+      "loss": 5.386,
+      "step": 8
+    },
+    {
+      "epoch": 0.001405591129158207,
+      "grad_norm": 5.657876491546631,
+      "learning_rate": 0.00018,
+      "loss": 5.5206,
+      "step": 9
+    },
+    {
+      "epoch": 0.001405591129158207,
+      "eval_loss": 5.303591251373291,
+      "eval_runtime": 56.6066,
+      "eval_samples_per_second": 47.645,
+      "eval_steps_per_second": 23.831,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 144327309262848.0,
+  "total_flos": 216490963894272.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null