Training in progress, step 12000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1010df5598a57f3107191c355d0821d0298565ed53102d05d42a80266f4acd01
+oid sha256:e4ba67ca4bf7c6745ce3da9bc2e2f0a0c83e78b6b644d910324362c803bcf9f2
 size 847599616

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:66d9db11aeb77fe2fa3bbb095fdaa33941577676015deecc0a95e5769fbe593a
+oid sha256:befa4bc7ac75a8200a418f6ce90c047aad5ae982fbd5659cc7c120634c58eaec
 size 1386414411

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:61466e9412c0d194297480cf7f0e3a714d962a2892349d2aadf71260158ae2fe
+oid sha256:0e98febf4471a4dec1877ac02b945fce7c4deb248cf77bee1819b50cbf8a3806
 size 14917

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a7eb88890e8a1c0d8205803f09e7feb7113f18f444391d019b68607e3c736e37
+oid sha256:bf0257cbbbe26fb21736af967573c2602d7e7f0f3c9ac904351cb86bd58064a3
 size 14917

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb18b777ebcd388d89ae9a04b334b4e4327bc4436d4f89f04f67b009aa0dea99
+oid sha256:cc677d4cbf29c6599dc35f2fc4173c838893b9ae384275df973375a34da97e73
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.6666666666666666,
+  "epoch": 0.8,
   "eval_steps": 1000,
-  "global_step": 10000,
+  "global_step": 12000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -798,6 +798,164 @@
       "eval_samples_per_second": 7.614,
       "eval_steps_per_second": 0.381,
       "step": 10000
+    },
+    {
+      "epoch": 0.6733333333333333,
+      "grad_norm": 0.9764471650123596,
+      "learning_rate": 0.00010582031340402582,
+      "loss": 8.11692138671875,
+      "step": 10100
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 1.0789597034454346,
+      "learning_rate": 0.00010195372756105512,
+      "loss": 8.137109375,
+      "step": 10200
+    },
+    {
+      "epoch": 0.6866666666666666,
+      "grad_norm": 1.0786553621292114,
+      "learning_rate": 9.813479397926537e-05,
+      "loss": 8.17680419921875,
+      "step": 10300
+    },
+    {
+      "epoch": 0.6933333333333334,
+      "grad_norm": 1.3332428932189941,
+      "learning_rate": 9.436536872942766e-05,
+      "loss": 8.15776123046875,
+      "step": 10400
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 1.0370911359786987,
+      "learning_rate": 9.064728382036833e-05,
+      "loss": 8.137608642578124,
+      "step": 10500
+    },
+    {
+      "epoch": 0.7066666666666667,
+      "grad_norm": 1.081002950668335,
+      "learning_rate": 8.698234630857997e-05,
+      "loss": 8.0797705078125,
+      "step": 10600
+    },
+    {
+      "epoch": 0.7133333333333334,
+      "grad_norm": 1.0866549015045166,
+      "learning_rate": 8.337233741995907e-05,
+      "loss": 8.10765625,
+      "step": 10700
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 1.4178708791732788,
+      "learning_rate": 7.9819011684098e-05,
+      "loss": 8.233140258789062,
+      "step": 10800
+    },
+    {
+      "epoch": 0.7266666666666667,
+      "grad_norm": 1.0158106088638306,
+      "learning_rate": 7.632409608155228e-05,
+      "loss": 8.12737060546875,
+      "step": 10900
+    },
+    {
+      "epoch": 0.7333333333333333,
+      "grad_norm": 1.0095257759094238,
+      "learning_rate": 7.288928920449636e-05,
+      "loss": 8.0778955078125,
+      "step": 11000
+    },
+    {
+      "epoch": 0.7333333333333333,
+      "eval_accuracy": 0.3137651663405088,
+      "eval_loss": 8.122584342956543,
+      "eval_runtime": 65.3252,
+      "eval_samples_per_second": 7.654,
+      "eval_steps_per_second": 0.383,
+      "step": 11000
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 1.1707996129989624,
+      "learning_rate": 6.951626043117705e-05,
+      "loss": 8.111912841796874,
+      "step": 11100
+    },
+    {
+      "epoch": 0.7466666666666667,
+      "grad_norm": 1.1220096349716187,
+      "learning_rate": 6.620664911456616e-05,
+      "loss": 8.153399047851563,
+      "step": 11200
+    },
+    {
+      "epoch": 0.7533333333333333,
+      "grad_norm": 1.053057312965393,
+      "learning_rate": 6.296206378560454e-05,
+      "loss": 8.083673095703125,
+      "step": 11300
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 1.0960450172424316,
+      "learning_rate": 5.978408137142759e-05,
+      "loss": 8.193185424804687,
+      "step": 11400
+    },
+    {
+      "epoch": 0.7666666666666667,
+      "grad_norm": 1.1686227321624756,
+      "learning_rate": 5.667424642894974e-05,
+      "loss": 8.13611572265625,
+      "step": 11500
+    },
+    {
+      "epoch": 0.7733333333333333,
+      "grad_norm": 1.103230595588684,
+      "learning_rate": 5.363407039418178e-05,
+      "loss": 8.102085571289063,
+      "step": 11600
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 1.3868330717086792,
+      "learning_rate": 5.0665030847646266e-05,
+      "loss": 8.002344970703126,
+      "step": 11700
+    },
+    {
+      "epoch": 0.7866666666666666,
+      "grad_norm": 1.0746208429336548,
+      "learning_rate": 4.776857079624599e-05,
+      "loss": 8.036705322265625,
+      "step": 11800
+    },
+    {
+      "epoch": 0.7933333333333333,
+      "grad_norm": 1.161407470703125,
+      "learning_rate": 4.494609797193681e-05,
+      "loss": 7.990054931640625,
+      "step": 11900
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 1.1083136796951294,
+      "learning_rate": 4.219898414754464e-05,
+      "loss": 8.060489501953125,
+      "step": 12000
+    },
+    {
+      "epoch": 0.8,
+      "eval_accuracy": 0.3169706457925636,
+      "eval_loss": 8.059541702270508,
+      "eval_runtime": 65.8107,
+      "eval_samples_per_second": 7.598,
+      "eval_steps_per_second": 0.38,
+      "step": 12000
     }
   ],
   "logging_steps": 100,