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:ce266de161b1d39ae18bba42227c49bea5b5af7c1509e84463edee8bf44aee66
+oid sha256:aef4ef8d12f13c645e3c2ecf321a3a9580b0eab937e90eb4c70a9d615e8f5bfc
 size 27024

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:41f7874f66fed4d4f4f52f57559867136cfb8f85fbfb8c23297354baff66aa02
+oid sha256:85fdfc54731d8855a8c47a346e529709f27b57ea7478cc99c9a1f5a39ddc65c1
 size 63974

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": 0.042455333451264815,
+  "epoch": 0.056607111268353084,
   "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": 645.281,
       "eval_steps_per_second": 323.183,
       "step": 15
+    },
+    {
+      "epoch": 0.04528568901468247,
+      "grad_norm": 0.21131035685539246,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 10.4549,
+      "step": 16
+    },
+    {
+      "epoch": 0.04811604457810013,
+      "grad_norm": 0.2003251314163208,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 10.4232,
+      "step": 17
+    },
+    {
+      "epoch": 0.05094640014151778,
+      "grad_norm": 0.2581706941127777,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 10.4216,
+      "step": 18
+    },
+    {
+      "epoch": 0.05377675570493543,
+      "grad_norm": 0.2147359549999237,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 10.4219,
+      "step": 19
+    },
+    {
+      "epoch": 0.056607111268353084,
+      "grad_norm": 0.27223360538482666,
+      "learning_rate": 0.0,
+      "loss": 10.404,
+      "step": 20
+    },
+    {
+      "epoch": 0.056607111268353084,
+      "eval_loss": 10.43026065826416,
+      "eval_runtime": 0.9038,
+      "eval_samples_per_second": 658.328,
+      "eval_steps_per_second": 329.717,
+      "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": 775854489600.0,
+  "total_flos": 1034472652800.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null