Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d349ce962d07d63fd419a1d0d3a9a4b343f8322dfeb153c6c47b771050f025e
+oid sha256:65587e07661f3fe3e5302e67ee38162964f53d1ead4d8cdcd9c3ecf2505dabb1
 size 2269195160

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:006b2a45f69345baf7dba60090536847d80a4c3a920cbaa974df732008239db1
+oid sha256:56f3193f302c902f67910d135321651ebd2d6ad32ac703a94dfe97a05efdfcc1
 size 335810490

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d1b8821978c7450bd2cb49e068182933549eb330933b29022697a95533c47a4
+oid sha256:8dd60e9ba809120cc78feb8bd27109edcdf93018d99882fdeecb2257ff3c3de7
 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": 0.036596523330283626,
+  "epoch": 0.05489478499542543,
   "eval_steps": 8,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -73,6 +73,42 @@
       "learning_rate": 6.545084971874738e-05,
       "loss": 2.0026,
       "step": 18
+    },
+    {
+      "epoch": 0.0384263494967978,
+      "grad_norm": 1.0747629404067993,
+      "learning_rate": 4.2178276747988446e-05,
+      "loss": 2.0571,
+      "step": 21
+    },
+    {
+      "epoch": 0.04391582799634035,
+      "grad_norm": 1.0367234945297241,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 2.1068,
+      "step": 24
+    },
+    {
+      "epoch": 0.04391582799634035,
+      "eval_loss": 2.0426266193389893,
+      "eval_runtime": 32.8578,
+      "eval_samples_per_second": 7.03,
+      "eval_steps_per_second": 3.53,
+      "step": 24
+    },
+    {
+      "epoch": 0.04940530649588289,
+      "grad_norm": 1.0442975759506226,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 1.9313,
+      "step": 27
+    },
+    {
+      "epoch": 0.05489478499542543,
+      "grad_norm": 0.9846899509429932,
+      "learning_rate": 0.0,
+      "loss": 1.9357,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -87,12 +123,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 7418876862136320.0,
+  "total_flos": 1.112831529320448e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null