Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35ecff1a7557bb201d00ede9a13f8ac9e318a99dc0fd792ec10764f46dae01ee
+oid sha256:04d3ecd38862a314282f5581eb90a47baa9335a387ad0e74eaf86f77347e626f
 size 27024

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b5695dfd872a3bdd9d6589ea9e1642cc0d12c9a8a54f45b389382199b099baac
+oid sha256:53b34cac7663d1e2f704ae33489aa9d8782da6b9ab4a6ec7cae7c30d29c46ef5
 size 63974

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:464e6cdff3f8548ba79ace3859c72e6b06d1e045e69932eb75c584ad0e8918c8
+oid sha256:e9b931b5fc0c1bd85ac8b5cf7dfdfe32425d1d78ecf18cf7fdcddc467f06765e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ffd8c58e5d02492554dbaa495f8cf80dff41fabc0e1288cb2fd18a103d402219
+oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.00473186119873817,
+  "epoch": 0.00946372239747634,
   "eval_steps": 3,
-  "global_step": 3,
+  "global_step": 6,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -44,6 +44,35 @@
       "eval_samples_per_second": 274.671,
       "eval_steps_per_second": 137.85,
       "step": 3
+    },
+    {
+      "epoch": 0.006309148264984227,
+      "grad_norm": 0.06943820416927338,
+      "learning_rate": 8e-05,
+      "loss": 10.3774,
+      "step": 4
+    },
+    {
+      "epoch": 0.007886435331230283,
+      "grad_norm": 0.06262843310832977,
+      "learning_rate": 0.0001,
+      "loss": 10.3788,
+      "step": 5
+    },
+    {
+      "epoch": 0.00946372239747634,
+      "grad_norm": 0.05760049447417259,
+      "learning_rate": 0.00012,
+      "loss": 10.3752,
+      "step": 6
+    },
+    {
+      "epoch": 0.00946372239747634,
+      "eval_loss": 10.378085136413574,
+      "eval_runtime": 0.9756,
+      "eval_samples_per_second": 273.679,
+      "eval_steps_per_second": 137.352,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 77585448960.0,
+  "total_flos": 151938170880.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null