Training in progress, step 15, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:06643764a1f2860e8c121abd8b235374ba8481cefd703e8e0e45651676b9d2f0
+oid sha256:9cb9098e983c50bff4125913be120927f8e266079ca962f7ff35ad5ef8aa164d
 size 9864

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5cf8e14b4c6ca5224599283b548a40c8bb81b7086474880d2e516e6e0b0c8c9d
+oid sha256:7414c5b60048e908794eb366aa3618aa0cb141d067c8bfe881e48fd24bdf9d34
 size 27002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:deabd56c17b610f6d8e6c3c09d2dcb705e4d72db3bc1813e41a578dadc2811d7
+oid sha256:9aa473efab1261a29320d6ad268e7ec159fafb824b3f53d140f1f0fb43c8c484
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c188a6a4749e6ca627bb6d536eb7443f499d5b1b88d98a78f9c713443e010d9c
+oid sha256:b1b54721e238deb0df3f26476ead882995a6359d0720944551e4d045b099778f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.006351222610352493,
+  "epoch": 0.00952683391552874,
   "eval_steps": 8,
-  "global_step": 10,
+  "global_step": 15,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -44,6 +44,20 @@
       "learning_rate": 0.00018763066800438636,
       "loss": 46.0,
       "step": 9
+    },
+    {
+      "epoch": 0.007621467132422992,
+      "grad_norm": 2.1859506887267344e-05,
+      "learning_rate": 0.000163742398974869,
+      "loss": 46.0,
+      "step": 12
+    },
+    {
+      "epoch": 0.00952683391552874,
+      "grad_norm": 3.495635974104516e-05,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 46.0,
+      "step": 15
     }
   ],
   "logging_steps": 3,
@@ -63,7 +77,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 398960885760.0,
+  "total_flos": 598441328640.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null