Training in progress, step 5400, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a32a8472f24ac0ae5777096edb75d3f2a4dcd1c6f71a5a93bc0a5ae4a7fe3dcf
+oid sha256:c384964f20b4483c2dce965e9c67e9ca152e97453c6fa5c988961571c39a6be0
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3289ab88db5dbcb3be2060676922612848d1ca284d404ff24a82083e0a9f0264
+oid sha256:eed612f91b824abf83f39b9cc7a7625fa32c562e6a3aa09fb728224cdfad742d
 size 84581014

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49f463b5f7795e26b9e24462f96b39a52b6b97b5adfc046ad7d24a04ed313a17
+oid sha256:99397a5b0758fb455e37af8d56924ff252bf4671d377fdcae94b0d33fb047f96
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac1bdf201c735a2a3a0e28881f6c25b745bd1b24bb6cddaa05404a7fc4dbfa5a
+oid sha256:462980f0e92909d0da061075e591b7887d61fb7e5de134327d9d3fd672ebeb16
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0038670479179293447,
+  "epoch": 0.004015780530157396,
   "eval_steps": 2000,
-  "global_step": 5200,
+  "global_step": 5400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -189,6 +189,13 @@
       "learning_rate": 1.9999970595262297e-05,
       "loss": 1.5714,
       "step": 5200
+    },
+    {
+      "epoch": 0.0,
+      "grad_norm": 3.6416239738464355,
+      "learning_rate": 1.9999968297103373e-05,
+      "loss": 1.5909,
+      "step": 5400
     }
   ],
   "logging_steps": 200,
@@ -196,7 +203,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 5,
   "save_steps": 200,
-  "total_flos": 6.809650430179738e+16,
+  "total_flos": 7.091041430315827e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null