Training in progress, step 10000, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd74e6589d3e456165c757752a4ea537b0dce0f12a9239822f8f0b87e6fcab08
+oid sha256:de0e6e5db5288feee0fefc4357eafb906c01848da238f0f1b9aac0e997510dec
 size 1442699

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c0b03c00b2afb37434503ce30b41dc6f4cc779bf2123b15db0c1a37a46bde51
+oid sha256:644b3d86f34c31a15e3fe76473fa14f4c704b8d59e60d78e4d6f10a6e753b1b8
 size 499774435

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b43fdf0f4b166ccbde53eac22fd3e3b4db7ae9dc053939b2b5bbebd405317f8
+oid sha256:86bc1651483ec7d90230200f2b53b997a19bb41b19e2710e0f81a67f62f0b352
 size 14455

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": 145.531,
       "eval_steps_per_second": 18.191,
       "step": 8000
+    },
+    {
+      "epoch": 0.162,
+      "grad_norm": 0.712541401386261,
+      "learning_rate": 0.0019322148017972016,
+      "loss": 4.847081909179687,
+      "step": 8100
+    },
+    {
+      "epoch": 0.164,
+      "grad_norm": 0.47257572412490845,
+      "learning_rate": 0.001929800831168135,
+      "loss": 4.90064453125,
+      "step": 8200
+    },
+    {
+      "epoch": 0.166,
+      "grad_norm": 0.3497978150844574,
+      "learning_rate": 0.001927346188038576,
+      "loss": 4.955650329589844,
+      "step": 8300
+    },
+    {
+      "epoch": 0.168,
+      "grad_norm": 0.3204037845134735,
+      "learning_rate": 0.0019248509797825672,
+      "loss": 4.851766967773438,
+      "step": 8400
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 0.3258970379829407,
+      "learning_rate": 0.0019223153155486009,
+      "loss": 4.883788452148438,
+      "step": 8500
+    },
+    {
+      "epoch": 0.172,
+      "grad_norm": 0.4524133503437042,
+      "learning_rate": 0.0019197393062548454,
+      "loss": 4.840924682617188,
+      "step": 8600
+    },
+    {
+      "epoch": 0.174,
+      "grad_norm": 0.28501275181770325,
+      "learning_rate": 0.0019171230645842923,
+      "loss": 4.877713317871094,
+      "step": 8700
+    },
+    {
+      "epoch": 0.176,
+      "grad_norm": 0.4920591711997986,
+      "learning_rate": 0.0019144667049798272,
+      "loss": 4.900206298828125,
+      "step": 8800
+    },
+    {
+      "epoch": 0.178,
+      "grad_norm": 0.30207598209381104,
+      "learning_rate": 0.0019117703436392253,
+      "loss": 4.907836303710938,
+      "step": 8900
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 0.3460649251937866,
+      "learning_rate": 0.001909034098510066,
+      "loss": 4.8303515625,
+      "step": 9000
+    },
+    {
+      "epoch": 0.18,
+      "eval_accuracy": 0.22981996086105674,
+      "eval_loss": 4.851044178009033,
+      "eval_runtime": 6.9243,
+      "eval_samples_per_second": 144.418,
+      "eval_steps_per_second": 18.052,
+      "step": 9000
+    },
+    {
+      "epoch": 0.182,
+      "grad_norm": 0.26366087794303894,
+      "learning_rate": 0.001906258089284576,
+      "loss": 4.757725524902344,
+      "step": 9100
+    },
+    {
+      "epoch": 0.184,
+      "grad_norm": 0.3308315873146057,
+      "learning_rate": 0.0019034424373943915,
+      "loss": 4.747350769042969,
+      "step": 9200
+    },
+    {
+      "epoch": 0.186,
+      "grad_norm": 0.24568253755569458,
+      "learning_rate": 0.0019005872660052478,
+      "loss": 4.785510559082031,
+      "step": 9300
+    },
+    {
+      "epoch": 0.188,
+      "grad_norm": 0.43289270997047424,
+      "learning_rate": 0.001897692700011591,
+      "loss": 4.789692687988281,
+      "step": 9400
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 0.25019797682762146,
+      "learning_rate": 0.0018947588660311143,
+      "loss": 4.792172241210937,
+      "step": 9500
+    },
+    {
+      "epoch": 0.192,
+      "grad_norm": 0.6229330897331238,
+      "learning_rate": 0.0018917858923992211,
+      "loss": 4.777132873535156,
+      "step": 9600
+    },
+    {
+      "epoch": 0.194,
+      "grad_norm": 0.350772500038147,
+      "learning_rate": 0.0018887739091634085,
+      "loss": 4.744659423828125,
+      "step": 9700
+    },
+    {
+      "epoch": 0.196,
+      "grad_norm": 0.23172135651111603,
+      "learning_rate": 0.0018857230480775807,
+      "loss": 4.748968811035156,
+      "step": 9800
+    },
+    {
+      "epoch": 0.198,
+      "grad_norm": 0.3821462392807007,
+      "learning_rate": 0.0018826334425962855,
+      "loss": 4.802294616699219,
+      "step": 9900
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.2725774645805359,
+      "learning_rate": 0.0018795052278688753,
+      "loss": 4.774011535644531,
+      "step": 10000
+    },
+    {
+      "epoch": 0.2,
+      "eval_accuracy": 0.23221135029354206,
+      "eval_loss": 4.819427967071533,
+      "eval_runtime": 6.9031,
+      "eval_samples_per_second": 144.863,
+      "eval_steps_per_second": 18.108,
+      "step": 10000
     }
   ],
   "logging_steps": 100,