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:a82711016f23303a415e3811866dbb2eca6c126773b5f9000cade1b817a508c1
+oid sha256:8c40f0e8bb258f9f74c7c7c96360abb2ee61313888324c2f8c6e2618a59a188a
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e14e219b1c6c5be37123a39a06078cccc1b8a45a425b5db4ea3611f09478327
+oid sha256:1f06cb90252ded61e8f8aa529248491ab791e14c249c9863a9dcbb2337eb0669
 size 41119636

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": 0.2617230098146129,
+  "epoch": 0.3489640130861505,
   "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": 41.96,
       "eval_steps_per_second": 21.196,
       "step": 15
+    },
+    {
+      "epoch": 0.2791712104689204,
+      "grad_norm": 20.12640380859375,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 23.8817,
+      "step": 16
+    },
+    {
+      "epoch": 0.2966194111232279,
+      "grad_norm": 19.669471740722656,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 14.4217,
+      "step": 17
+    },
+    {
+      "epoch": 0.31406761177753545,
+      "grad_norm": 27.434799194335938,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 17.2192,
+      "step": 18
+    },
+    {
+      "epoch": 0.33151581243184297,
+      "grad_norm": 24.257400512695312,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 15.3634,
+      "step": 19
+    },
+    {
+      "epoch": 0.3489640130861505,
+      "grad_norm": 18.00651741027832,
+      "learning_rate": 0.0,
+      "loss": 19.8399,
+      "step": 20
+    },
+    {
+      "epoch": 0.3489640130861505,
+      "eval_loss": NaN,
+      "eval_runtime": 2.2636,
+      "eval_samples_per_second": 42.852,
+      "eval_steps_per_second": 21.647,
+      "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": 9894651645394944.0,
+  "total_flos": 1.3152150129475584e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null