Training in progress, step 5720, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:59d1f0fae334930ed8079d00f44c27d89643fc0441c8182fd6c384af44315cb0
+oid sha256:544a421be52957d5613621601224858dfd162233e6428573b09ec9d5573dc77a
 size 13982248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dbf70e69484ef4930af6adb3972e5d151c2e40923012c6e59178aa5b08fc0f62
+oid sha256:d9e2d9f85dd6f1706fbaa505cbb386e14ca466c6dd237557e0df4b31602f92b2
 size 7062522

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e9d9c35639598e4263e7ecc7045b5427db463c314e637805772291b54322a1a
+oid sha256:cad25d74c98e57d04d591e95b20be1467f4abee9743346612ed99c4d529ebe19
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d31553c5ae8347a198cb4d56280c26db3af2cfa5039328d122439d6a52e0f08
+oid sha256:1bad31e19ad1444caf40fc8eed23cdbd3a28f5e4fbb3a28184d66d17da83ca16
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.456,
+  "epoch": 0.4576,
   "eval_steps": 500,
-  "global_step": 5700,
+  "global_step": 5720,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2002,6 +2002,13 @@
       "learning_rate": 2.516862579011255e-05,
       "loss": 3.3665,
       "step": 5700
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 28.95624542236328,
+      "learning_rate": 2.5132858131187446e-05,
+      "loss": 3.4688,
+      "step": 5720
     }
   ],
   "logging_steps": 20,
@@ -2009,7 +2016,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 2,
   "save_steps": 20,
-  "total_flos": 1.3500387561013248e+16,
+  "total_flos": 1.3547988940161024e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null