Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5bed83cbf30195b0409d913080a886a87db72479b93608c38d32d6813e7073a4
+oid sha256:37dfc8beb93cfd93a8027ba4ae4334467b2f306ff9da3027062b18b7b70abd57
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0890a0f9b813ae6f0635fa6a23d5e853a1cca9ebd7f28606040c2f8483067153
+oid sha256:973651008a5401f812ec6d4ad8c086dde0648a084d9fa66e12ccdbd0dc452405
 size 64219860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07d77b60a4a6ac9b1290011cfbb000725f2f3c555f2baada62884afb493a185f
+oid sha256:76d05d926a13e2b0db86e596e2ee777dcc8276585d379e27b6ca55897b2ce7fe
 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": 0.005252790544977019,
+  "epoch": 0.007879185817465528,
   "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": 10.553,
       "eval_steps_per_second": 5.287,
       "step": 6
+    },
+    {
+      "epoch": 0.006128255635806522,
+      "grad_norm": 0.4593210816383362,
+      "learning_rate": 0.00014,
+      "loss": 1.3637,
+      "step": 7
+    },
+    {
+      "epoch": 0.007003720726636025,
+      "grad_norm": 0.3701046407222748,
+      "learning_rate": 0.00016,
+      "loss": 0.7937,
+      "step": 8
+    },
+    {
+      "epoch": 0.007879185817465528,
+      "grad_norm": 0.4593477249145508,
+      "learning_rate": 0.00018,
+      "loss": 0.5974,
+      "step": 9
+    },
+    {
+      "epoch": 0.007879185817465528,
+      "eval_loss": 0.8962156176567078,
+      "eval_runtime": 45.6067,
+      "eval_samples_per_second": 10.547,
+      "eval_steps_per_second": 5.284,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3799446517186560.0,
+  "total_flos": 5699169775779840.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null