Training in progress, step 5900, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bfdf99e6f852b95893a3325daefaa73c742c59db09c48cc66ea0649d202b68dd
+oid sha256:fed6828ec7857824732422a9380f523d4a261f731255e8724086c998809eb12f
 size 13982248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d7c0b1c19403b05dff5d2f156acc8f562d4639998744603ace27077f57583525
+oid sha256:96485bcca91d9681dbf1765c2fec995608bba06ceae1c7ce1c615957959eb6d1
 size 7062522

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:deba6467959a028c18c0e5f6c3fa6485175e7329b2726569ff046ac69a14f7f1
+oid sha256:b24286519e547cddecce5ee08c5603972e0f911b2926a8070867f658fece3cf4
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a1d6152f3fb55aaaeaa756a21040c5678a3b19dbf109ed4dcfd1cac7331c190
+oid sha256:49478f629a8da642b92bfa489a04fa161c3d21da278e9c615a916a5a252b90a0
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.4704,
+  "epoch": 0.472,
   "eval_steps": 500,
-  "global_step": 5880,
+  "global_step": 5900,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2065,6 +2065,13 @@
       "learning_rate": 2.4842922208598996e-05,
       "loss": 3.3891,
       "step": 5880
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 51.836395263671875,
+      "learning_rate": 2.480621158933879e-05,
+      "loss": 3.5146,
+      "step": 5900
     }
   ],
   "logging_steps": 20,
@@ -2072,7 +2079,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 2,
   "save_steps": 20,
-  "total_flos": 1.3916136891088896e+16,
+  "total_flos": 1.3958882995175424e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null