Training in progress, step 250, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec70dca35bdb9bd43cc20ce3d797ec78f3b6fdd1149271b48013c4c312d77233
+oid sha256:9d59d67df5d4a457e07e3cfe46c0ed6470f3f08c6d2fdb6ce193a8ac70597e76
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b856bb390bbac8d0d1e1a97e40477499f94bd2ea5470d3bab3ed71479d69c83
+oid sha256:ba3ecb314bf09f70d1516d366a4ce837640bc7af4dcf4633dddfddddbc3f220c
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:47bf36b9af78cdb67bc2c32f13c186891d1b3b5f49109538cfacf741287891da
+oid sha256:da580027ee1b9160d781064356720fd173a2f46c611f2b21fa33b345587ab72a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:65558e26afbfb87dd1928966282919939bdee4084add607d42e008ed52d680cd
+oid sha256:6088f970b1f0429ad85e576795204ef9269ce142d6ce9c2595b5649efde833b6
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0013265345513119708,
+  "epoch": 0.0017546753324232417,
   "eval_steps": 63,
-  "global_step": 189,
+  "global_step": 250,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -165,6 +165,55 @@
       "eval_samples_per_second": 34.246,
       "eval_steps_per_second": 17.123,
       "step": 189
+    },
+    {
+      "epoch": 0.0013335532526416638,
+      "grad_norm": 1.0346105098724365,
+      "learning_rate": 2.8165064990227252e-05,
+      "loss": 1.0024,
+      "step": 190
+    },
+    {
+      "epoch": 0.0014037402659385933,
+      "grad_norm": 0.9557493329048157,
+      "learning_rate": 1.985863781320435e-05,
+      "loss": 1.0653,
+      "step": 200
+    },
+    {
+      "epoch": 0.001473927279235523,
+      "grad_norm": 1.2075986862182617,
+      "learning_rate": 1.286812958766106e-05,
+      "loss": 1.0735,
+      "step": 210
+    },
+    {
+      "epoch": 0.0015441142925324528,
+      "grad_norm": 1.0695114135742188,
+      "learning_rate": 7.308324265397836e-06,
+      "loss": 0.9855,
+      "step": 220
+    },
+    {
+      "epoch": 0.0016143013058293825,
+      "grad_norm": 0.9340460300445557,
+      "learning_rate": 3.270513696097055e-06,
+      "loss": 1.0546,
+      "step": 230
+    },
+    {
+      "epoch": 0.001684488319126312,
+      "grad_norm": 1.0297428369522095,
+      "learning_rate": 8.209986176753948e-07,
+      "loss": 1.0474,
+      "step": 240
+    },
+    {
+      "epoch": 0.0017546753324232417,
+      "grad_norm": 1.0664470195770264,
+      "learning_rate": 0.0,
+      "loss": 1.1008,
+      "step": 250
     }
   ],
   "logging_steps": 10,
@@ -179,12 +228,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.557192662581248e+16,
+  "total_flos": 2.059778654208e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null