Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:00359fdb910e3be8c90b01cb2d8e8ecc2431adee4d13baf9eb1179595ff4829d
+oid sha256:0334883006a400c0e44e6c821b31052c7b4b44b2cbb82cc7064809687af57a8d
 size 5327744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3cda9995be13e17f7b343bf7650f12d802ace1b1512fb68e57d9158daa20c905
+oid sha256:896848bfa142711e3ad42dc959a955265614b3b1f2f0619675436b62331e8f9c
 size 2857722

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7354c9c781a5a059133d478d3d1f3aa4e83aeeb7ad88f7537497ab1d2e30e160
+oid sha256:905d0dfa799c49acfb8c5c41693a228a98f7290d08b8bb110baf1121c4615b53
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff2736979009751c0c6b0ddcc5f6544d6f723aa752b4798eab0b70fb76cf0083
+oid sha256:532138a5ca880d8da393ae449e5715b2766def36b8838785ca08d07228b119b7
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.009765227651869634,
+  "epoch": 0.013020303535826179,
   "eval_steps": 5,
-  "global_step": 15,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -144,6 +144,49 @@
       "eval_samples_per_second": 230.55,
       "eval_steps_per_second": 115.275,
       "step": 15
+    },
+    {
+      "epoch": 0.010416242828660943,
+      "grad_norm": 16.40966033935547,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 41.2578,
+      "step": 16
+    },
+    {
+      "epoch": 0.011067258005452251,
+      "grad_norm": 15.669730186462402,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 44.1328,
+      "step": 17
+    },
+    {
+      "epoch": 0.011718273182243562,
+      "grad_norm": 16.64231300354004,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 44.6562,
+      "step": 18
+    },
+    {
+      "epoch": 0.01236928835903487,
+      "grad_norm": 15.17128849029541,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 41.8594,
+      "step": 19
+    },
+    {
+      "epoch": 0.013020303535826179,
+      "grad_norm": 17.088932037353516,
+      "learning_rate": 0.0,
+      "loss": 45.0234,
+      "step": 20
+    },
+    {
+      "epoch": 0.013020303535826179,
+      "eval_loss": 2.647012710571289,
+      "eval_runtime": 16.1732,
+      "eval_samples_per_second": 160.017,
+      "eval_steps_per_second": 80.009,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -158,12 +201,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 128969283207168.0,
+  "total_flos": 171959044276224.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null