Training in progress, step 1500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bba34685d94bb36df6544b237fd9e510e461f8efb6e91c0e2fa89ee61630019a
+oid sha256:152a9be24b08d9a4f83ff7f91818a7bba1e1d1a35e6ede809963927b46b203c1
 size 25191576

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:edc00144513136faa46b27ae5acab1f53a9d5b635b29c43d51b646b209853a92
+oid sha256:6583cb3ef6fcb566b0b590387f148b427c487ef09f56e1cdb64c019f81050fa1
 size 50444805

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48d9d5fa72253e3d11b2a7ce24a2ae523c1872f22a41c74e73e62af9955db1fe
+oid sha256:1668bafc1fac3c40e5cf2fd65429ae578b48a366f50cc4885b2a5966b36e3dea
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d1351871b6e069a7a4437616d40b913152ecc2cd046e996fcfeb300a3cf60638
+oid sha256:d397c26ac1ddd7670b9ddd8b909580a771b707ad5b586b657ad627e8bc4e787f
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.9863357543945312,
-  "best_model_checkpoint": "./outputs/checkpoint-1400",
-  "epoch": 1.8666666666666667,
+  "best_metric": 0.9830333590507507,
+  "best_model_checkpoint": "./outputs/checkpoint-1500",
+  "epoch": 2.0,
   "eval_steps": 100,
-  "global_step": 1400,
+  "global_step": 1500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -203,6 +203,20 @@
       "eval_samples_per_second": 5.447,
       "eval_steps_per_second": 0.683,
       "step": 1400
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 0.0002,
+      "loss": 0.847,
+      "step": 1500
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.9830333590507507,
+      "eval_runtime": 353.3265,
+      "eval_samples_per_second": 5.462,
+      "eval_steps_per_second": 0.685,
+      "step": 1500
     }
   ],
   "logging_steps": 100,
@@ -210,7 +224,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 3.958031986924831e+17,
+  "total_flos": 4.240820711718666e+17,
   "trial_name": null,
   "trial_params": null
 }