Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d549372ecda0aabd1980c9049d511b784d28fbea1ab6cba08ab7f7c2958ba61
+oid sha256:082ef65c5f8f31e5eedfd2b64d32a1f9fc6d116d1f263249961e49c1a5b57fd8
 size 125040

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:93f034a6cac0630266d66989c2e0e876e0339c9a916b63e5a87073c4acb56a21
+oid sha256:d1704afd26e800a803c9115581e1891a8e64dc493c252ed7c600a325ec5f3c05
 size 162868

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff5440c0314dadc3defe4b4803f353543d71edfcba882e67961bec9458fb6240
+oid sha256:9ea24ba22f005ab5531315a7c25fe17ce3b0d82d32e4d057cd4a8d9beeaa0eb4
 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": 0.022800684020520615,
+  "epoch": 0.03040091202736082,
   "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": 756.813,
       "eval_steps_per_second": 378.406,
       "step": 15
+    },
+    {
+      "epoch": 0.024320729621888658,
+      "grad_norm": 5.064575672149658,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 177.4375,
+      "step": 16
+    },
+    {
+      "epoch": 0.025840775223256698,
+      "grad_norm": 4.720963478088379,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 177.5625,
+      "step": 17
+    },
+    {
+      "epoch": 0.027360820824624738,
+      "grad_norm": 4.923408031463623,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 177.8125,
+      "step": 18
+    },
+    {
+      "epoch": 0.02888086642599278,
+      "grad_norm": 5.069203853607178,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 177.25,
+      "step": 19
+    },
+    {
+      "epoch": 0.03040091202736082,
+      "grad_norm": 4.987614631652832,
+      "learning_rate": 0.0,
+      "loss": 177.5,
+      "step": 20
+    },
+    {
+      "epoch": 0.03040091202736082,
+      "eval_loss": 11.086868286132812,
+      "eval_runtime": 1.4842,
+      "eval_samples_per_second": 746.535,
+      "eval_steps_per_second": 373.267,
+      "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": 583510523904.0,
+  "total_flos": 776406564864.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null