Training in progress, step 725, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a4972d945aaf79f38a6385891c2c6bf16c9ab13d1387a9a314a9ae88e2af9d7
+oid sha256:59d4b20c39e023774f653c79696e7bf1a0895c40499204e0da55c8972f138d66
 size 97307544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:263b3898d405f513a3d751718a8e4459efbe49762bd2d59a834f0b0bd5f9c305
+oid sha256:e425df4cff4f5a833435a908df13e0e68fb91e068e65be0350970182c98532fe
 size 49846644

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:92e2bed38537091b1b6847ec894ec446f212f658d47a8eafa5ceedcd4769dcc4
+oid sha256:1cf257bb73c12dfb0ceb40ef8d7dab03fb8c678e0b5befc5cb019048e159abe6
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa5e57bbef4d99689575267a9a61782e3d42e915f722a8a205895c6faf79e5c7
+oid sha256:93cb95f675bf4560789b437cb4b6409914c75b59d4784dc1ea4e7bea55c15059
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.9317373018440634,
+  "epoch": 0.938207699773536,
   "eval_steps": 386,
-  "global_step": 720,
+  "global_step": 725,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -5063,6 +5063,41 @@
       "learning_rate": 9.256184469043851e-05,
       "loss": 0.7484,
       "step": 720
+    },
+    {
+      "epoch": 0.9330313814299579,
+      "grad_norm": 0.7698187232017517,
+      "learning_rate": 9.254019439590835e-05,
+      "loss": 0.7563,
+      "step": 721
+    },
+    {
+      "epoch": 0.9343254610158525,
+      "grad_norm": 0.8331950306892395,
+      "learning_rate": 9.251851517798514e-05,
+      "loss": 0.8826,
+      "step": 722
+    },
+    {
+      "epoch": 0.935619540601747,
+      "grad_norm": 0.7643804550170898,
+      "learning_rate": 9.24968070514087e-05,
+      "loss": 1.0688,
+      "step": 723
+    },
+    {
+      "epoch": 0.9369136201876416,
+      "grad_norm": 0.802943229675293,
+      "learning_rate": 9.247507003093858e-05,
+      "loss": 0.8872,
+      "step": 724
+    },
+    {
+      "epoch": 0.938207699773536,
+      "grad_norm": 0.8977981209754944,
+      "learning_rate": 9.245330413135395e-05,
+      "loss": 0.8946,
+      "step": 725
     }
   ],
   "logging_steps": 1,
@@ -5082,7 +5117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8.04914763619369e+17,
+  "total_flos": 8.105044494778368e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null