Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:39ed2cbeb6874cd071905b3ad8f61740c54d1333a40c4af252c8ab2d0e3abfee
+oid sha256:e3f00bc49460e28149eb1be3af4cf98af63868dc31f169a1cafa9799f5b31de4
 size 12609312

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c648a97188c8f0d434a07d611fb8be18bd0ef429c1d7eb78a20a8f36ebb6688e
+oid sha256:36eede2a944e1e04adde84db5ed9503ea015169413dfed669a0046eaa7fc96f7
 size 6615034

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:59dfd7e3c5f47e9c59dd82d5934b354dca1792ccd6d53d936783c3e96fc445c8
+oid sha256:fda5437f05e2eaed0597b85f69532d5c06b3025917ba7357f9b3d1d946872746
 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": 0.003767069533825145,
+  "epoch": 0.005650604300737718,
   "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": 82.712,
       "eval_steps_per_second": 41.418,
       "step": 6
+    },
+    {
+      "epoch": 0.004394914456129336,
+      "grad_norm": 76.38861083984375,
+      "learning_rate": 0.00014,
+      "loss": 17.475,
+      "step": 7
+    },
+    {
+      "epoch": 0.005022759378433527,
+      "grad_norm": 82.15962219238281,
+      "learning_rate": 0.00016,
+      "loss": 14.0928,
+      "step": 8
+    },
+    {
+      "epoch": 0.005650604300737718,
+      "grad_norm": 68.57530212402344,
+      "learning_rate": 0.00018,
+      "loss": 10.6811,
+      "step": 9
+    },
+    {
+      "epoch": 0.005650604300737718,
+      "eval_loss": 3.0674076080322266,
+      "eval_runtime": 8.1104,
+      "eval_samples_per_second": 82.734,
+      "eval_steps_per_second": 41.429,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 52637139468288.0,
+  "total_flos": 78955709202432.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null