Training in progress, step 5200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d3898deded357ae3f624f6da11d5a240cdabb03ebb6c20aaa1514ff2afc28f42
+oid sha256:a32a8472f24ac0ae5777096edb75d3f2a4dcd1c6f71a5a93bc0a5ae4a7fe3dcf
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b6589201aabf4474a11e89f074f30710b9c14f130975414126d44fac37ab285
+oid sha256:3289ab88db5dbcb3be2060676922612848d1ca284d404ff24a82083e0a9f0264
 size 84581014

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c2a46d21812f033b59f8253d10c55fd001488b63093ce2c9a28dd3b2087601c
+oid sha256:49f463b5f7795e26b9e24462f96b39a52b6b97b5adfc046ad7d24a04ed313a17
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dadb6c8212cca45778812f2e418e14e8bb1e227cbf578c8c3f0b8b32adfef7b7
+oid sha256:ac1bdf201c735a2a3a0e28881f6c25b745bd1b24bb6cddaa05404a7fc4dbfa5a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0037183153057012927,
+  "epoch": 0.0038670479179293447,
   "eval_steps": 2000,
-  "global_step": 5000,
+  "global_step": 5200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -182,6 +182,13 @@
       "learning_rate": 1.999997281785647e-05,
       "loss": 1.5405,
       "step": 5000
+    },
+    {
+      "epoch": 0.0,
+      "grad_norm": 2.7667906284332275,
+      "learning_rate": 1.9999970595262297e-05,
+      "loss": 1.5714,
+      "step": 5200
     }
   ],
   "logging_steps": 200,
@@ -189,7 +196,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 5,
   "save_steps": 200,
-  "total_flos": 6.541947938699674e+16,
+  "total_flos": 6.809650430179738e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null