Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d61827806ee7062968af2a5bbe7b72043c7992e3eb3b228560e8a0de6cc0fc6
+oid sha256:cd849c9cfb9b038b3dfaa6860c7812d7ec9b42a45aa740a6a9100bb6c71daacb
 size 41581360

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d1534cdbc7d4f35b38e2b44238660b119dadc5aa7b2e5cc5bbc258a8be9b3ef
+oid sha256:1b2e799ffd49f7ff58c594aa327f542f1384e30a225f5f2faa523759576ab9d0
 size 21505540

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f45c3db0d0efb69876dcff0bca8b932f89ffefcf63f5fd9fa87ae8c4d446282b
+oid sha256:ce23990253dbcb847c65b8e07df81d199b8cb35ee201419fc10370dd6bcc8fb2
 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": 0.0006359974560101759,
+  "epoch": 0.0012719949120203519,
   "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": 25.944,
       "eval_steps_per_second": 12.978,
       "step": 3
+    },
+    {
+      "epoch": 0.0008479966080135679,
+      "grad_norm": 1.0298770666122437,
+      "learning_rate": 8e-05,
+      "loss": 1.9841,
+      "step": 4
+    },
+    {
+      "epoch": 0.00105999576001696,
+      "grad_norm": 0.9741261005401611,
+      "learning_rate": 0.0001,
+      "loss": 2.2097,
+      "step": 5
+    },
+    {
+      "epoch": 0.0012719949120203519,
+      "grad_norm": 0.829294741153717,
+      "learning_rate": 0.00012,
+      "loss": 1.9574,
+      "step": 6
+    },
+    {
+      "epoch": 0.0012719949120203519,
+      "eval_loss": 1.9550093412399292,
+      "eval_runtime": 76.6274,
+      "eval_samples_per_second": 25.931,
+      "eval_steps_per_second": 12.972,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 300058398425088.0,
+  "total_flos": 600116796850176.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null