Training in progress, step 1900, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8db2f6985dbe7da967b42697a9825dabf00cd15fef676dbf892abbe1872ae130
+oid sha256:3522f9d6763b3e2a2886ac64a274160c319429a72882ce822b247c019b802365
 size 6304192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d101e117e5ae64c831f414d37d3053dc22bf54c6574ca78e63664cdebf124063
+oid sha256:d89bf17b190871c60b01654b546ca3feb7c85da7e8e46ddd3cdad3bbf13fbad0
 size 12639429

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:86ef024fdb50d2b5245e358e85c40ce33acc74b982ce82b2769eebe5c2cafd32
+oid sha256:9721883eeb5dfd58d4927218422ce48028e14bf282115382a00d7498ac3281ed
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c0e0a1736a46fd1627af3c246e44261aaac909256abbd413b5ee5c968f6b2d8e
+oid sha256:b2d4b4cadcabd3e17adcc39c43d8312038a1f5c7f53125f288ba4de5ed25396b
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.2427366971969604,
-  "best_model_checkpoint": "./outputs/checkpoint-1800",
-  "epoch": 2.4,
+  "best_metric": 1.2404277324676514,
+  "best_model_checkpoint": "./outputs/checkpoint-1900",
+  "epoch": 2.533333333333333,
   "eval_steps": 100,
-  "global_step": 1800,
+  "global_step": 1900,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -259,6 +259,20 @@
       "eval_samples_per_second": 15.29,
       "eval_steps_per_second": 1.917,
       "step": 1800
+    },
+    {
+      "epoch": 2.53,
+      "learning_rate": 0.0002,
+      "loss": 1.0604,
+      "step": 1900
+    },
+    {
+      "epoch": 2.53,
+      "eval_loss": 1.2404277324676514,
+      "eval_runtime": 126.4354,
+      "eval_samples_per_second": 15.265,
+      "eval_steps_per_second": 1.914,
+      "step": 1900
     }
   ],
   "logging_steps": 100,
@@ -266,7 +280,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 6.382682082163507e+16,
+  "total_flos": 6.736067175819264e+16,
   "trial_name": null,
   "trial_params": null
 }