Training in progress, step 4000, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6fed8b037293eea965a891ec6faa4a8c5f09e500208437b6e0939687c63268f1
+oid sha256:ebfe5edf81138c978229a3a68b0fe6644c67b98edc7c5fe61004927e35302f75
 size 13982248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ec148549087fad601f78d26348f8c3cd657d46a252e419103abbe89a0a1b1b2
+oid sha256:9fb53f00fdd7fbcafad95bc9586286b21025aebe6a7a756c6a906a18324316bc
 size 7062522

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:51370fa33b9c13d5f80ae7fa8db4167f4b87b80a692d734ed71e92d3211caace
+oid sha256:43c690d898c7ec435e0a3e95049a4459dd3ca635c017bbe0a97e3303b2d233ca
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f79a2f74b522fa6033abd487865a5913aed0c5f19b8f644e33fa9a5d01b02ca
+oid sha256:ddd4c9ae93fd7d164e48abdd1f7e950a314350432c3244939b41b87291d2074a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.3184,
+  "epoch": 0.32,
   "eval_steps": 500,
-  "global_step": 3980,
+  "global_step": 4000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1400,6 +1400,13 @@
       "learning_rate": 2.780860247123153e-05,
       "loss": 3.4484,
       "step": 3980
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 30.727558135986328,
+      "learning_rate": 2.778325235483954e-05,
+      "loss": 3.5112,
+      "step": 4000
     }
   ],
   "logging_steps": 20,
@@ -1407,7 +1414,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 2,
   "save_steps": 20,
-  "total_flos": 9403552392609792.0,
+  "total_flos": 9444034888728576.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null