Training in progress, step 980, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd6935101c95c7a3fcf35393fcef907ca744d140d002e80f3e1ab8bc68740781
+oid sha256:a38c93e994650fe4c83da9cfce04fe1541ec31a2ec6907ff09b91f14be34ad4d
 size 13982248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:efbc01513003cd4778a5d7c40f35733a97acc954ec9ed9a205fe5bb1048cad2d
+oid sha256:46cbd28b8ea82d833a6eeaf797d7e79113fcfd64f188a19553eb3bcd4a1e3573
 size 7062522

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a60dce02b424b527030edce82260ee74eebf81dd57466a5e2b83b22d49a22b4a
+oid sha256:7c5410d295859629eb5c5221ec007a76d5ecce5c325cbaeb984aecc19e1cfef7
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b961e5bd3f5ce2b76de5850c52ad545f91b84e33c7fc906eadd1fa38681efcd4
+oid sha256:1deaeac856492d3d5086d74c9dfcab210016322b2b2c1701903eaa6e0b81545c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0768,
+  "epoch": 0.0784,
   "eval_steps": 500,
-  "global_step": 960,
+  "global_step": 980,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -343,6 +343,13 @@
       "learning_rate": 2.997451764584951e-05,
       "loss": 3.7494,
       "step": 960
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 33.610286712646484,
+      "learning_rate": 2.9971608542252175e-05,
+      "loss": 3.7077,
+      "step": 980
     }
   ],
   "logging_steps": 20,
@@ -350,7 +357,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 2,
   "save_steps": 20,
-  "total_flos": 2278337822490624.0,
+  "total_flos": 2331220953563136.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null