Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:64d3f7c16ef2a25f7426beedbb4b5eee146c626bd26933d0dcadcf648ebe9a67
+oid sha256:abefcb5f93b2172a5b370509ab036a6f72d1bc699b3b45953406d4eb1fd8bfc3
 size 1579352

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4662ca77d1f4c618e82edac21c14a3d08b1bea564bf981d6bcda2f9536804aff
+oid sha256:282dab6f65bed9e2656ba5b32ac70c4249120111ac1b16924f478fb496d7103e
 size 857338

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1899d57d4b6564b7be4726769ff1c02b7197aad4b1175dae87a6f0b50f65a855
+oid sha256:a590542febf25332380709b3b87f5f4fb6b5bbacfdbf165bb93f2860385345f6
 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": 0.0009200337345702676,
+  "epoch": 0.0013800506018554013,
   "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": 233.593,
       "eval_steps_per_second": 116.796,
       "step": 6
+    },
+    {
+      "epoch": 0.0010733726903319788,
+      "grad_norm": 1016.6214599609375,
+      "learning_rate": 0.00014,
+      "loss": 21.5803,
+      "step": 7
+    },
+    {
+      "epoch": 0.0012267116460936902,
+      "grad_norm": 845.358642578125,
+      "learning_rate": 0.00016,
+      "loss": 20.2243,
+      "step": 8
+    },
+    {
+      "epoch": 0.0013800506018554013,
+      "grad_norm": 1010.66455078125,
+      "learning_rate": 0.00018,
+      "loss": 22.7055,
+      "step": 9
+    },
+    {
+      "epoch": 0.0013800506018554013,
+      "eval_loss": 6.1546950340271,
+      "eval_runtime": 11.7724,
+      "eval_samples_per_second": 233.257,
+      "eval_steps_per_second": 116.628,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 11628724617216.0,
+  "total_flos": 18273710112768.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null