Training in progress, step 2400, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bcab562e1493fe477a7c20ee6a0a13264f4074f59fe17386f1f54313e0affd31
+oid sha256:714e6464882a12977f9161b0725f0f293b62727654edea6c7cd1304a993dfac9
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:541ed47aef8de3fc9ecaad697a0d31b1c0a1072555098f060f3ddcaf5be9e36e
+oid sha256:40a8ffb4f5658e0682ef76e7152bbe595d7237d7f6021f8772ee7e472eef8d29
 size 84581014

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d8e5a18dcaad5f8475df8da26bc9a7d22093bbe9d0a345c2378f89417d170e6
+oid sha256:f378a879622820d825a4a635bf9928d84f866b9daa73fe1f9fc42587e2508c66
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7810aa3073ddaced1f3726a0a416fba70e639094f5582e572c65214d83662981
+oid sha256:41fd41f1ab3b29e88abab4e0f95a7542016a4426d0de6a4edad353ac7f02e3e5
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.001636058734508569,
+  "epoch": 0.0017847913467366205,
   "eval_steps": 2000,
-  "global_step": 2200,
+  "global_step": 2400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -84,6 +84,13 @@
       "learning_rate": 1.999999475956276e-05,
       "loss": 1.6152,
       "step": 2200
+    },
+    {
+      "epoch": 0.0,
+      "grad_norm": 4.141517162322998,
+      "learning_rate": 1.9999993759176304e-05,
+      "loss": 1.564,
+      "step": 2400
     }
   ],
   "logging_steps": 200,
@@ -91,7 +98,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 5,
   "save_steps": 200,
-  "total_flos": 2.860341350272205e+16,
+  "total_flos": 3.125489981718528e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null