Training in progress, step 70, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e57994952775701010727b731745c577de0e9fe9d26c2a339a810c688b398388
+oid sha256:6c6fe37680fd272bd12e83c299da2de8a941fed2e05846e9b0fb79eaf4d933df
 size 97307544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c522a92351ac6bdc8c664ee803b651528514d928a5a42d1556a4e377d4283a97
+oid sha256:6caa8cd831d3f12a9b1f8ccf2bc8e8064c1a55d2d8500acf001c63e17c206492
 size 49846260

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2514d83dfe35d755cc78f91af8bb937820a9474979a674fc7a75720c6f7898b3
+oid sha256:6906a270ff60e8073c1da9b2c0c14e3c9bf9be88ace934c2db9cc71819c53244
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ccd2b573b1eec8d0fb3b8a132ed34c8ce03266e455024ff257bb21f3e84c3669
+oid sha256:aa31dbb84d2d88d6d0f470f52a27f418df5de72bdd7486af54580de0d6f8b614
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.08411517308314462,
+  "epoch": 0.09058557101261727,
   "eval_steps": 386,
-  "global_step": 65,
+  "global_step": 70,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -470,6 +470,41 @@
       "learning_rate": 9.999617556940085e-05,
       "loss": 0.9279,
       "step": 65
+    },
+    {
+      "epoch": 0.08540925266903915,
+      "grad_norm": 1.0130903720855713,
+      "learning_rate": 9.999564865549449e-05,
+      "loss": 0.9381,
+      "step": 66
+    },
+    {
+      "epoch": 0.08670333225493368,
+      "grad_norm": 1.1210829019546509,
+      "learning_rate": 9.999508774917652e-05,
+      "loss": 0.9607,
+      "step": 67
+    },
+    {
+      "epoch": 0.08799741184082821,
+      "grad_norm": 1.045749545097351,
+      "learning_rate": 9.999449285082831e-05,
+      "loss": 1.0037,
+      "step": 68
+    },
+    {
+      "epoch": 0.08929149142672274,
+      "grad_norm": 1.1308139562606812,
+      "learning_rate": 9.999386396085434e-05,
+      "loss": 0.9086,
+      "step": 69
+    },
+    {
+      "epoch": 0.09058557101261727,
+      "grad_norm": 1.1013413667678833,
+      "learning_rate": 9.999320107968219e-05,
+      "loss": 1.0712,
+      "step": 70
     }
   ],
   "logging_steps": 1,
@@ -489,7 +524,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7.266591616008192e+16,
+  "total_flos": 7.825560201854976e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null