Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ab7774cb1d61701c958ffed9d1a0170b3667c0268d1c47bae5213a129cd41dd
+oid sha256:f225ee9ed170b52276a581a078b61719c4a57e1f73f3504d661041cc716d0ad0
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:42cdf57f88294312d1a72ec0172504f7ecefda9ad0bf3faf993ea39db1998ec1
+oid sha256:834182e0e4853b884d1717563f4b44479a7cb7cf93dc6f5e97b00d7f003b2188
 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": 0.008492569002123142,
+  "epoch": 0.012738853503184714,
   "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": 8.979,
       "eval_steps_per_second": 4.49,
       "step": 6
+    },
+    {
+      "epoch": 0.009907997169143666,
+      "grad_norm": 0.4628216326236725,
+      "learning_rate": 0.00014,
+      "loss": 5.9544,
+      "step": 7
+    },
+    {
+      "epoch": 0.01132342533616419,
+      "grad_norm": 0.6455901861190796,
+      "learning_rate": 0.00016,
+      "loss": 6.0813,
+      "step": 8
+    },
+    {
+      "epoch": 0.012738853503184714,
+      "grad_norm": 0.606442391872406,
+      "learning_rate": 0.00018,
+      "loss": 6.0511,
+      "step": 9
+    },
+    {
+      "epoch": 0.012738853503184714,
+      "eval_loss": 1.4868851900100708,
+      "eval_runtime": 33.1917,
+      "eval_samples_per_second": 8.978,
+      "eval_steps_per_second": 4.489,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3799469166428160.0,
+  "total_flos": 5699203749642240.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null