Training in progress, step 880, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a7261173c6cc37f0af738ac4f62cf733cb9f189924cfe1daf21367523618d8ed
+oid sha256:122f732830a82f1a7a3a7425537e862e7ee1d697cd8187d0044646345b434143
 size 13982248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cac75987c36eb3aed135202de0ad0e205dc153c722e06aec3f39d75285a9d2aa
+oid sha256:aa28364534d96be46cefdbe1b76cf7a40940e1cf04c4f5a6cf3ccbb915f922bc
 size 7062522

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9216bd0d63331af67d42e3e886e98fe378c7f9e63ccf40fc65dc43479bba4269
+oid sha256:dea0e7f5f0c188c2ee6e729843388c15e47a905456029356105d7ca29f2d0fef
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:edcbda48b98381d2804df29839fc6b7baea1aebc4a5832ba4c600db41135c488
+oid sha256:52aa474262a07e7da5493acb71323699d3a95e420cf1220730538dffbf9e1ae4
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0688,
+  "epoch": 0.0704,
   "eval_steps": 500,
-  "global_step": 860,
+  "global_step": 880,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -308,6 +308,13 @@
       "learning_rate": 2.9986706477143436e-05,
       "loss": 3.6594,
       "step": 860
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 49.44480895996094,
+      "learning_rate": 2.9984583023761318e-05,
+      "loss": 3.7271,
+      "step": 880
     }
   ],
   "logging_steps": 20,
@@ -315,7 +322,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 2,
   "save_steps": 20,
-  "total_flos": 2034589892050944.0,
+  "total_flos": 2079501186367488.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null