Training in progress, step 10000, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f5abc00b30afb0cc7f11475da5329ddda7a8b54916957489c98976e9146772bb
+oid sha256:b1e13a85964ab8808bfc2b3469a4b76bee0bd96f331a8f39748e7032dc454ef7
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:20b2d331cc999028b7772cec2bf035150343c98c155579a40021dd1b08f46b51
+oid sha256:ac5ecf7fc68ce9f8cbd917b2dbb333c1ccbe8c2f546fdb594ee0191e94f36b9b
 size 84581014

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c05839636fd5cb5be586f924cedf0045977d387805f980599c45c147e0e837b6
+oid sha256:4453b9d90bd6b82be8e97e83b1ca59d9d5397ee45aa220e04d942e0915e20392
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8d0791f87a560d6e6d8a6da6d811e646baa7dcb34edbb7ffc991631590e30ba
+oid sha256:acbeb015d4bc7f990999b8518ed60979c4618ba57aa1e5c62c07a2978164609d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.007287897999174534,
+  "epoch": 0.007436630611402585,
   "eval_steps": 2000,
-  "global_step": 9800,
+  "global_step": 10000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -350,6 +350,13 @@
       "learning_rate": 1.9999895393491484e-05,
       "loss": 1.566,
       "step": 9800
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 4.078786849975586,
+      "learning_rate": 1.9999891075382195e-05,
+      "loss": 1.5554,
+      "step": 10000
     }
   ],
   "logging_steps": 200,
@@ -357,7 +364,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 5,
   "save_steps": 200,
-  "total_flos": 1.2813345198044774e+17,
+  "total_flos": 1.3069591544338022e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null