Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a5cf07bd09106ceac21d28422a3fa5adf3d76e63cf13424e42dfa762903316f6
+oid sha256:a836277aeed5836e4c3ec9bbda5e18df97f6060d4d2d0c9203dc0e9049e3f837
 size 9864

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d31eb5f012b1c1a4cf9c6abd31e502ce1b7717457c6499a76bcba66bcc1660b
+oid sha256:820b0ae5315cdba0c1ffda7a649f6ef63cba8feb9948c3611f35f39d49135fdf
 size 27002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8f56528b2b76cb96fdbaeedcd2bc1a7c80bcd9d88cbac90fd5655ce599b9d75
+oid sha256:1a608beb21ca290f1f1a46eb926ba60cee938b7bd70879e0f0bbd7f5e8fe5fe2
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46d68217ddf3e899bf1495ee33b9ec14e2c91ed912ffcb460a7bb01192b04b7d
+oid sha256:f0e9cc72c20ddd925ef39b6005e82a4d8730b1dde32cfcd070d74c83a8a3564a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.001011186247867029,
+  "epoch": 0.0015167793718005435,
   "eval_steps": 5,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -89,6 +89,50 @@
       "eval_samples_per_second": 140.584,
       "eval_steps_per_second": 70.292,
       "step": 20
+    },
+    {
+      "epoch": 0.0010617455602603804,
+      "grad_norm": 1.8329679733142257e-05,
+      "learning_rate": 4.2178276747988446e-05,
+      "loss": 46.0,
+      "step": 21
+    },
+    {
+      "epoch": 0.001213423497440435,
+      "grad_norm": 2.1915997422183864e-05,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 46.0,
+      "step": 24
+    },
+    {
+      "epoch": 0.0012639828098337863,
+      "eval_loss": 11.5,
+      "eval_runtime": 59.078,
+      "eval_samples_per_second": 140.966,
+      "eval_steps_per_second": 70.483,
+      "step": 25
+    },
+    {
+      "epoch": 0.0013651014346204892,
+      "grad_norm": 2.4743134417803958e-05,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 46.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.0015167793718005435,
+      "grad_norm": 5.412183963926509e-05,
+      "learning_rate": 0.0,
+      "loss": 46.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.0015167793718005435,
+      "eval_loss": 11.5,
+      "eval_runtime": 59.0675,
+      "eval_samples_per_second": 140.991,
+      "eval_steps_per_second": 70.496,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -103,12 +147,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1127064502272.0,
+  "total_flos": 1635739631616.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null