Training in progress, step 10000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5957954f25406e9df797421489d9b120ac7feff52692d5e5c70038c879f86412
+oid sha256:5380c87b8a1992262417a07584f7e2ad84f4c2f88005d931c232bf8ae2edd651
 size 529337896

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ee0d0e9122e67a2d2d94315cf19cbd6a916fcb06556d38abe0ccc77fd7feae8
+oid sha256:d345cb2206543c9c855d8cd93c9763b056b3b514641a19501f256c2c6ec77df7
 size 871247243

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dbcbab03d5bb70bb2a3066017b02040dc9b35585ddf112a4be38eb15410f67d9
+oid sha256:58c4ef51004bd7cb63819242ee70337c219b896f88e964689c3e3e6e457044c6
 size 14645

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9567d76a2efaa946d19913fd9fe6f6f70f6f7101d7dcb8866c09743534f2d4d
+oid sha256:833776bf99a0597a4bf38df86be38e8ac151736eba1d084c9cbb84cab1caf4e9
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.16,
+  "epoch": 0.2,
   "eval_steps": 1000,
-  "global_step": 8000,
+  "global_step": 10000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -640,6 +640,164 @@
       "eval_samples_per_second": 56.787,
       "eval_steps_per_second": 0.454,
       "step": 8000
+    },
+    {
+      "epoch": 0.162,
+      "grad_norm": 0.13911907374858856,
+      "learning_rate": 0.0019322148017972016,
+      "loss": 3.646,
+      "step": 8100
+    },
+    {
+      "epoch": 0.164,
+      "grad_norm": 0.1297680288553238,
+      "learning_rate": 0.001929800831168135,
+      "loss": 3.6412,
+      "step": 8200
+    },
+    {
+      "epoch": 0.166,
+      "grad_norm": 0.14803367853164673,
+      "learning_rate": 0.001927346188038576,
+      "loss": 3.6298,
+      "step": 8300
+    },
+    {
+      "epoch": 0.168,
+      "grad_norm": 0.1325535923242569,
+      "learning_rate": 0.0019248509797825672,
+      "loss": 3.6067,
+      "step": 8400
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 0.16948860883712769,
+      "learning_rate": 0.0019223153155486009,
+      "loss": 3.6284,
+      "step": 8500
+    },
+    {
+      "epoch": 0.172,
+      "grad_norm": 0.12973898649215698,
+      "learning_rate": 0.0019197393062548454,
+      "loss": 3.627,
+      "step": 8600
+    },
+    {
+      "epoch": 0.174,
+      "grad_norm": 0.1576964110136032,
+      "learning_rate": 0.0019171230645842923,
+      "loss": 3.6027,
+      "step": 8700
+    },
+    {
+      "epoch": 0.176,
+      "grad_norm": 0.15394999086856842,
+      "learning_rate": 0.0019144667049798272,
+      "loss": 3.6098,
+      "step": 8800
+    },
+    {
+      "epoch": 0.178,
+      "grad_norm": 0.12594962120056152,
+      "learning_rate": 0.0019117703436392253,
+      "loss": 3.6221,
+      "step": 8900
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 0.1420104056596756,
+      "learning_rate": 0.001909034098510066,
+      "loss": 3.5993,
+      "step": 9000
+    },
+    {
+      "epoch": 0.18,
+      "eval_accuracy": 0.3549628180039139,
+      "eval_loss": 3.570964813232422,
+      "eval_runtime": 12.4303,
+      "eval_samples_per_second": 80.449,
+      "eval_steps_per_second": 0.644,
+      "step": 9000
+    },
+    {
+      "epoch": 0.182,
+      "grad_norm": 0.12720872461795807,
+      "learning_rate": 0.001906258089284576,
+      "loss": 3.5913,
+      "step": 9100
+    },
+    {
+      "epoch": 0.184,
+      "grad_norm": 0.14890190958976746,
+      "learning_rate": 0.0019034424373943915,
+      "loss": 3.6113,
+      "step": 9200
+    },
+    {
+      "epoch": 0.186,
+      "grad_norm": 0.15023267269134521,
+      "learning_rate": 0.0019005872660052478,
+      "loss": 3.6011,
+      "step": 9300
+    },
+    {
+      "epoch": 0.188,
+      "grad_norm": 0.1637164056301117,
+      "learning_rate": 0.001897692700011591,
+      "loss": 3.5932,
+      "step": 9400
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 0.13102982938289642,
+      "learning_rate": 0.0018947588660311143,
+      "loss": 3.5889,
+      "step": 9500
+    },
+    {
+      "epoch": 0.192,
+      "grad_norm": 0.16267850995063782,
+      "learning_rate": 0.0018917858923992211,
+      "loss": 3.5939,
+      "step": 9600
+    },
+    {
+      "epoch": 0.194,
+      "grad_norm": 0.12798982858657837,
+      "learning_rate": 0.0018887739091634085,
+      "loss": 3.5896,
+      "step": 9700
+    },
+    {
+      "epoch": 0.196,
+      "grad_norm": 0.13872383534908295,
+      "learning_rate": 0.0018857230480775807,
+      "loss": 3.574,
+      "step": 9800
+    },
+    {
+      "epoch": 0.198,
+      "grad_norm": 0.11993825435638428,
+      "learning_rate": 0.0018826334425962855,
+      "loss": 3.589,
+      "step": 9900
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.13074541091918945,
+      "learning_rate": 0.0018795052278688753,
+      "loss": 3.5828,
+      "step": 10000
+    },
+    {
+      "epoch": 0.2,
+      "eval_accuracy": 0.35816046966731896,
+      "eval_loss": 3.540745973587036,
+      "eval_runtime": 17.8387,
+      "eval_samples_per_second": 56.058,
+      "eval_steps_per_second": 0.448,
+      "step": 10000
     }
   ],
   "logging_steps": 100,