Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48596a169185f521df08e35ec268747c422451c879ec47a843d0bf92643b48f6
+oid sha256:c568f9a7d3f7320dc968b2fe1b6236f889013f157d0e205e74348bb9382efd2a
 size 50624

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22379ad5e6ebd189d639e2d0c6c3e682300cd146c5c3e0cb0a031403e2de7f3a
+oid sha256:8793ba32a1d75db3e5b02135b4451672c7d1d2ade6c5807b1aad863993b71dc8
 size 111142

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": 0.006659267480577136,
+  "epoch": 0.013318534961154272,
   "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": 153.67,
       "eval_steps_per_second": 76.835,
       "step": 3
+    },
+    {
+      "epoch": 0.008879023307436182,
+      "grad_norm": 0.025835813954472542,
+      "learning_rate": 8e-05,
+      "loss": 10.3749,
+      "step": 4
+    },
+    {
+      "epoch": 0.011098779134295227,
+      "grad_norm": 0.0256224162876606,
+      "learning_rate": 0.0001,
+      "loss": 10.3748,
+      "step": 5
+    },
+    {
+      "epoch": 0.013318534961154272,
+      "grad_norm": 0.018543493002653122,
+      "learning_rate": 0.00012,
+      "loss": 10.3791,
+      "step": 6
+    },
+    {
+      "epoch": 0.013318534961154272,
+      "eval_loss": 10.377586364746094,
+      "eval_runtime": 1.268,
+      "eval_samples_per_second": 149.84,
+      "eval_steps_per_second": 74.92,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 313814679552.0,
+  "total_flos": 627629359104.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null