Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4335a77470eed6e3b244c985ea0153553e516ce3c547fb287e4492818e63ec38
+oid sha256:993a492c6082b91dcc13d5347711d8935a22a9ee8e8f16ba2fe960fd3f1d7a7c
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75c6645c872876d63a9af9078162525d88fb91039c15f6d4f6f00c8eb1c1ea5f
+oid sha256:7c54b83d6b7ad280c15694fd4abef28880057f189da9fbbc0d6984d7692ad3ca
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b3310387cc5a341c03eeb1a25b13f50577e28bbc426c3d9fcdfd93c3cdb18279
+oid sha256:8dd824ab7bf9f8eea6d9bd6e51d86488e2d9ca4852207360bea549e24419edb8
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ffd8c58e5d02492554dbaa495f8cf80dff41fabc0e1288cb2fd18a103d402219
+oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 4.4571887025123685e-05,
+  "epoch": 8.914377405024737e-05,
   "eval_steps": 3,
-  "global_step": 3,
+  "global_step": 6,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -44,6 +44,35 @@
       "eval_samples_per_second": 24.546,
       "eval_steps_per_second": 12.273,
       "step": 3
+    },
+    {
+      "epoch": 5.9429182700164916e-05,
+      "grad_norm": 9.358512878417969,
+      "learning_rate": 8e-05,
+      "loss": 10.6507,
+      "step": 4
+    },
+    {
+      "epoch": 7.428647837520615e-05,
+      "grad_norm": 10.204730987548828,
+      "learning_rate": 0.0001,
+      "loss": 10.2412,
+      "step": 5
+    },
+    {
+      "epoch": 8.914377405024737e-05,
+      "grad_norm": 10.428735733032227,
+      "learning_rate": 0.00012,
+      "loss": 9.6887,
+      "step": 6
+    },
+    {
+      "epoch": 8.914377405024737e-05,
+      "eval_loss": 2.4252917766571045,
+      "eval_runtime": 1153.3493,
+      "eval_samples_per_second": 24.572,
+      "eval_steps_per_second": 12.286,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 570056597569536.0,
+  "total_flos": 1099394866741248.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null