Training in progress, step 2100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc72c15dfcf5711fb70f2cb68d673c7895270b34b117d6132862ad3fb8844720
+oid sha256:c62ca606aaf3a5e391ab79efbdbd6f136ff872fffc76bb44f3f93cc16aa7ee48
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae63a50b8ef2796c2e42054bfd7b04cb18331479058e64cec3b3f51f2b924764
+oid sha256:94c906645f5fa7e35290dbfc313513f00acb313f5a0c14568377f5e8a35a792e
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:581654e7247b86e5cf537a4f388a8b452ef6efcbea66ae5b2507bf4e41fdff67
+oid sha256:0770ff6204965e70605ce6b3d87c7de79ab315ff8e5a70f192ba4c9b0362a1ca
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:720bafe9a34b3041027dccef7d9c03bb23064e1fcdd80ae5f27e717d41b7cf31
+oid sha256:b1238b3bfa75e49a19396161e9e7b72ab89cdd1a3f63b51c0ab4d6e8d216c5a5
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.2992783784866333,
-  "best_model_checkpoint": "./outputs/checkpoint-2000",
-  "epoch": 2.6666666666666665,
+  "best_metric": 1.2948063611984253,
+  "best_model_checkpoint": "./outputs/checkpoint-2100",
+  "epoch": 2.8,
   "eval_steps": 100,
-  "global_step": 2000,
+  "global_step": 2100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -287,6 +287,20 @@
       "eval_samples_per_second": 30.674,
       "eval_steps_per_second": 3.847,
       "step": 2000
+    },
+    {
+      "epoch": 2.8,
+      "learning_rate": 0.0002,
+      "loss": 1.3869,
+      "step": 2100
+    },
+    {
+      "epoch": 2.8,
+      "eval_loss": 1.2948063611984253,
+      "eval_runtime": 47.587,
+      "eval_samples_per_second": 30.492,
+      "eval_steps_per_second": 3.825,
+      "step": 2100
     }
   ],
   "logging_steps": 100,
@@ -294,7 +308,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 6.706239746605056e+16,
+  "total_flos": 7.041614616723456e+16,
   "trial_name": null,
   "trial_params": null
 }