Training in progress, step 8000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:82a943209b657b15ff00004efcaa88da19c9f1fd4603f11587c023fc47eda605
+oid sha256:8b5b2537f5142e6fa774f5229435c8fe08d7962419f4ec779873d8e1778b6a5a
 size 579824888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13ae1bff671c06244b8db21ff756e241dc09da71f9f9dc4f2ec99c071e13b99f
+oid sha256:fde75f324a8d5912df33d74af3539f7d5c0a866216e75d10d52848057c5278fd
 size 1159794763

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:15bd918144b9671ae295d46e463180bdad2e73e51a7670636feb8fc58e14c426
+oid sha256:231a1d74fdd644709c48076ea6500b1a4f8ca1620a6f210d62a4c539f1ee0b0f
 size 14645

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2666cc7db576490d8041b6acfda665e20af01ea5f7120fdf1d1c04b59674d0ca
+oid sha256:0182b4495f3c647cd51b29236a0c27e55ac1c8000e2e254b23fc4d917b1a56da
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.12,
+  "epoch": 0.16,
   "eval_steps": 1000,
-  "global_step": 6000,
+  "global_step": 8000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -482,6 +482,164 @@
       "eval_samples_per_second": 306.4,
       "eval_steps_per_second": 19.259,
       "step": 6000
+    },
+    {
+      "epoch": 0.122,
+      "grad_norm": 0.18666808307170868,
+      "learning_rate": 0.000965270029838182,
+      "loss": 3.6821221923828125,
+      "step": 6100
+    },
+    {
+      "epoch": 0.124,
+      "grad_norm": 0.15751489996910095,
+      "learning_rate": 0.0009641069162834215,
+      "loss": 3.671753234863281,
+      "step": 6200
+    },
+    {
+      "epoch": 0.126,
+      "grad_norm": 0.22766178846359253,
+      "learning_rate": 0.0009629253701530875,
+      "loss": 3.6878753662109376,
+      "step": 6300
+    },
+    {
+      "epoch": 0.128,
+      "grad_norm": 0.1677054762840271,
+      "learning_rate": 0.0009617254383737343,
+      "loss": 3.6619857788085937,
+      "step": 6400
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 0.17945168912410736,
+      "learning_rate": 0.0009605071686021245,
+      "loss": 3.6484750366210936,
+      "step": 6500
+    },
+    {
+      "epoch": 0.132,
+      "grad_norm": 0.17799174785614014,
+      "learning_rate": 0.0009592706092233365,
+      "loss": 3.6635867309570314,
+      "step": 6600
+    },
+    {
+      "epoch": 0.134,
+      "grad_norm": 0.5586189031600952,
+      "learning_rate": 0.0009580158093488436,
+      "loss": 3.6489688110351564,
+      "step": 6700
+    },
+    {
+      "epoch": 0.136,
+      "grad_norm": 0.2055712342262268,
+      "learning_rate": 0.000956742818814562,
+      "loss": 3.6523666381835938,
+      "step": 6800
+    },
+    {
+      "epoch": 0.138,
+      "grad_norm": 0.1812128871679306,
+      "learning_rate": 0.0009554516881788724,
+      "loss": 3.6479287719726563,
+      "step": 6900
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 0.1664743423461914,
+      "learning_rate": 0.0009541424687206124,
+      "loss": 3.6319317626953125,
+      "step": 7000
+    },
+    {
+      "epoch": 0.14,
+      "eval_accuracy": 0.3448148965923309,
+      "eval_loss": 3.6666343212127686,
+      "eval_runtime": 6.38,
+      "eval_samples_per_second": 304.231,
+      "eval_steps_per_second": 19.122,
+      "step": 7000
+    },
+    {
+      "epoch": 0.142,
+      "grad_norm": 0.15217284858226776,
+      "learning_rate": 0.0009528152124370387,
+      "loss": 3.6308517456054688,
+      "step": 7100
+    },
+    {
+      "epoch": 0.144,
+      "grad_norm": 0.16507816314697266,
+      "learning_rate": 0.0009514699720417631,
+      "loss": 3.6217156982421876,
+      "step": 7200
+    },
+    {
+      "epoch": 0.146,
+      "grad_norm": 0.2040642648935318,
+      "learning_rate": 0.0009501068009626583,
+      "loss": 3.632703857421875,
+      "step": 7300
+    },
+    {
+      "epoch": 0.148,
+      "grad_norm": 0.18437133729457855,
+      "learning_rate": 0.0009487257533397361,
+      "loss": 3.6346307373046876,
+      "step": 7400
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 0.18760915100574493,
+      "learning_rate": 0.0009473268840229971,
+      "loss": 3.5973056030273436,
+      "step": 7500
+    },
+    {
+      "epoch": 0.152,
+      "grad_norm": 0.17388536036014557,
+      "learning_rate": 0.0009459102485702528,
+      "loss": 3.611794738769531,
+      "step": 7600
+    },
+    {
+      "epoch": 0.154,
+      "grad_norm": 0.18797264993190765,
+      "learning_rate": 0.0009444759032449177,
+      "loss": 3.609403381347656,
+      "step": 7700
+    },
+    {
+      "epoch": 0.156,
+      "grad_norm": 0.18140241503715515,
+      "learning_rate": 0.0009430239050137766,
+      "loss": 3.6027340698242187,
+      "step": 7800
+    },
+    {
+      "epoch": 0.158,
+      "grad_norm": 0.17433640360832214,
+      "learning_rate": 0.0009415543115447203,
+      "loss": 3.6214892578125,
+      "step": 7900
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.16605013608932495,
+      "learning_rate": 0.0009400671812044565,
+      "loss": 3.6061587524414063,
+      "step": 8000
+    },
+    {
+      "epoch": 0.16,
+      "eval_accuracy": 0.34762277801806923,
+      "eval_loss": 3.640489339828491,
+      "eval_runtime": 8.0453,
+      "eval_samples_per_second": 241.259,
+      "eval_steps_per_second": 15.164,
+      "step": 8000
     }
   ],
   "logging_steps": 100,
@@ -501,7 +659,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.3519765200896e+17,
+  "total_flos": 3.1359686934528e+17,
   "train_batch_size": 120,
   "trial_name": null,
   "trial_params": null