Training in progress, step 9500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a965268f22c4e79d69dbf95ac68df18131ac4a28a88a5d81432e568fd272e719
+oid sha256:412f4a8e77fea4f91ace0373bc44858601f6fee74390562d707e1b0da5b734e5
 size 1783055976

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b417a00b6bce03f65479ff59686f2d226987f315fc5c6151693c6b7ec367ec9
+oid sha256:2671390599f002f23fed81ebff0d7fc668bf97b893c07fdecb013bd970be245a
 size 3566173562

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:86a2aa7bca84d2b8e7dd4e04a286714ba9169af11c46c739950a52df4c45259f
+oid sha256:82be7d57b17f6620866913ecd4ff8b7c828f1f4bbbb44f8426b657efc6ab9fa7
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb8278e710e71ee2631a6ab6373f5d2bf3048e7d5a86c6ca348c577a5e8dd794
+oid sha256:c32cb22d4c11005c45aa3db5dc6b95531a493184497cbddb0017d1404b4885b5
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:695726e815b6f66e1dd703432b138d1f45b6d5a74f2a6894ef9031edc67f71e7
+oid sha256:cb61bd1c310810ff79b63ed62b4ac17e06120cede8cab76720775afb5619a32e
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.08052007018666119,
+  "epoch": 0.08499340741925347,
   "eval_steps": 500,
-  "global_step": 9000,
+  "global_step": 9500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1412,6 +1412,84 @@
       "eval_samples_per_second": 39.984,
       "eval_steps_per_second": 5.002,
       "step": 9000
+    },
+    {
+      "epoch": 0.08096740390992041,
+      "grad_norm": 0.4358559548854828,
+      "learning_rate": 4.49751491053678e-05,
+      "loss": 0.2933,
+      "step": 9050
+    },
+    {
+      "epoch": 0.08141473763317963,
+      "grad_norm": 0.4459361732006073,
+      "learning_rate": 4.5223658051689864e-05,
+      "loss": 0.293,
+      "step": 9100
+    },
+    {
+      "epoch": 0.08186207135643886,
+      "grad_norm": 0.5491781234741211,
+      "learning_rate": 4.547216699801193e-05,
+      "loss": 0.2874,
+      "step": 9150
+    },
+    {
+      "epoch": 0.0823094050796981,
+      "grad_norm": 0.38162198662757874,
+      "learning_rate": 4.5720675944333996e-05,
+      "loss": 0.2864,
+      "step": 9200
+    },
+    {
+      "epoch": 0.08275673880295732,
+      "grad_norm": 0.39891770482063293,
+      "learning_rate": 4.596918489065606e-05,
+      "loss": 0.3036,
+      "step": 9250
+    },
+    {
+      "epoch": 0.08320407252621655,
+      "grad_norm": 0.461846262216568,
+      "learning_rate": 4.6217693836978135e-05,
+      "loss": 0.2906,
+      "step": 9300
+    },
+    {
+      "epoch": 0.08365140624947578,
+      "grad_norm": 0.4161681830883026,
+      "learning_rate": 4.64662027833002e-05,
+      "loss": 0.2825,
+      "step": 9350
+    },
+    {
+      "epoch": 0.08409873997273501,
+      "grad_norm": 0.41477343440055847,
+      "learning_rate": 4.671471172962227e-05,
+      "loss": 0.2899,
+      "step": 9400
+    },
+    {
+      "epoch": 0.08454607369599423,
+      "grad_norm": 0.3996387720108032,
+      "learning_rate": 4.696322067594434e-05,
+      "loss": 0.2806,
+      "step": 9450
+    },
+    {
+      "epoch": 0.08499340741925347,
+      "grad_norm": 0.3911084830760956,
+      "learning_rate": 4.7211729622266405e-05,
+      "loss": 0.283,
+      "step": 9500
+    },
+    {
+      "epoch": 0.08499340741925347,
+      "eval_loss": 0.2821110785007477,
+      "eval_runtime": 226.0823,
+      "eval_samples_per_second": 39.954,
+      "eval_steps_per_second": 4.998,
+      "step": 9500
     }
   ],
   "logging_steps": 50,
@@ -1431,7 +1509,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.31299465494528e+17,
+  "total_flos": 1.53182709743616e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null