Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:314cc70a5541ec7286dd71b298cafde6559a2f2900b3df1b8e4d3d1f65ce6da8
+oid sha256:fc72f1e7c263101fe167d23359dc5d4a783753b031ab8cc50176132e203bd7c0
 size 111454040

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb20ca37bd130268dd5cdebddedea73732a9f3b1030a5ad9477f93baa8987c6b
+oid sha256:cd61caccf6d27f383aec60c2161418944a04fdd98d39e61a1586e2cb8d6ce3ba
 size 56950676

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46701aacbf54025d1d0ab0c4ac8a896380e50265c94b575814dba5115273f574
+oid sha256:4a427adcb42a5e21efe60aeff1fc331ce48c7ff904cf00d837fab2409ae1ed3f
 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": 0.0021409455842997323,
+  "epoch": 0.004281891168599465,
   "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": 9.378,
       "eval_steps_per_second": 4.689,
       "step": 3
+    },
+    {
+      "epoch": 0.002854594112399643,
+      "grad_norm": 0.3028983771800995,
+      "learning_rate": 8e-05,
+      "loss": 1.2691,
+      "step": 4
+    },
+    {
+      "epoch": 0.003568242640499554,
+      "grad_norm": 0.325924277305603,
+      "learning_rate": 0.0001,
+      "loss": 1.5082,
+      "step": 5
+    },
+    {
+      "epoch": 0.004281891168599465,
+      "grad_norm": 0.33345407247543335,
+      "learning_rate": 0.00012,
+      "loss": 1.5615,
+      "step": 6
+    },
+    {
+      "epoch": 0.004281891168599465,
+      "eval_loss": 0.3730396628379822,
+      "eval_runtime": 62.943,
+      "eval_samples_per_second": 9.374,
+      "eval_steps_per_second": 4.687,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2038420419379200.0,
+  "total_flos": 4076840838758400.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null