Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:25a7197e8efc57ac411679cbee8d9b1e64a59cef81446b6d1613615082078f1d
+oid sha256:62e02e31d15a8cfeabb187b11e790e86985e17bf18116fc0a34bf49f3d2b521d
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b35d6d46b4261ec803e6ce9c5bb51c6ba521112bd58810a8cfcf693df0c96432
+oid sha256:3c61c76fee99b9a4e289be8d96c7c49eb997784cac02133c5e038b64b28af506
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f9d63457fb0762bec521007b4b65dfde2dbfedf3cf13f579982482514a7d902
+oid sha256:094837089fa2ed1c4f9dc6c25bac04422ed41c22630725ca5cdf86ffa65f03cf
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
+oid sha256:26a93b2a1f4b5368650119fe6e0d6eec6d19cda6badeba4d21943ab48964fa00
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.020851433536055605,
+  "epoch": 0.03127715030408341,
   "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": 4.788,
       "eval_steps_per_second": 4.788,
       "step": 6
+    },
+    {
+      "epoch": 0.02432667245873154,
+      "grad_norm": 3.534543037414551,
+      "learning_rate": 0.00014,
+      "loss": 3.5841,
+      "step": 7
+    },
+    {
+      "epoch": 0.02780191138140747,
+      "grad_norm": NaN,
+      "learning_rate": 0.00014,
+      "loss": 2.8247,
+      "step": 8
+    },
+    {
+      "epoch": 0.03127715030408341,
+      "grad_norm": 4.276378154754639,
+      "learning_rate": 0.00016,
+      "loss": 2.4532,
+      "step": 9
+    },
+    {
+      "epoch": 0.03127715030408341,
+      "eval_loss": 2.911003828048706,
+      "eval_runtime": 12.7634,
+      "eval_samples_per_second": 4.779,
+      "eval_steps_per_second": 4.779,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4451323701362688.0,
+  "total_flos": 6676985552044032.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null