Training in progress, step 1800, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc8d4620e45e3023852d6db363117d2149bf91809954eab034e0f3df6b2e9a53
+oid sha256:e1fdfb8dfcb901505d88cb8a470e308efd9e0925381c391ffc384136b1ebd88d
 size 847599616

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5bbab7f145dce1b83f41efbeae326f52ae177bc04e5b4bcb5acd73f2e563e608
+oid sha256:fec21f808a923bf61ae943ab35e94b8cc5c8bae8a15db1f8728417fdb5514516
 size 1386414411

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b0d1a4257bdb1e850f5a1f4f1d426b1aff1480f1f1be49a43a9b59e27d1626c
+oid sha256:29ddf99768976dfa1ee6d0925d35e9cc22f598f3ea5118aa848b2b6342be72c1
 size 14917

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9156180c20e717a1c296208930ef03eb900f1c8749f9b5001b6e2a8c9e24d691
+oid sha256:5fd13efabdb0e66816b180aa0d21e252da318cce2ddf5d9d38e39eb7b38ab940
 size 14917

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1eb3b2f44ae75601267d4a6c3582add2f5156f5a074e6f3b9a7a8115e10aac03
+oid sha256:423108cec97a3ca65f7a856a6a60f5138d6147e68a603ecfb19ab83adf2f9fe9
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.7142857142857143,
+  "epoch": 0.8571428571428571,
   "eval_steps": 150,
-  "global_step": 1500,
+  "global_step": 1800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1148,6 +1148,234 @@
       "eval_samples_per_second": 19.908,
       "eval_steps_per_second": 2.508,
       "step": 1500
+    },
+    {
+      "epoch": 0.719047619047619,
+      "grad_norm": 25.103525161743164,
+      "learning_rate": 8.054021393243589e-07,
+      "loss": 16.271298217773438,
+      "step": 1510
+    },
+    {
+      "epoch": 0.7238095238095238,
+      "grad_norm": 20.621360778808594,
+      "learning_rate": 7.80291988787982e-07,
+      "loss": 16.023663330078126,
+      "step": 1520
+    },
+    {
+      "epoch": 0.7285714285714285,
+      "grad_norm": 14.038392066955566,
+      "learning_rate": 7.554842933063619e-07,
+      "loss": 16.03165283203125,
+      "step": 1530
+    },
+    {
+      "epoch": 0.7333333333333333,
+      "grad_norm": 11.327874183654785,
+      "learning_rate": 7.30985204526309e-07,
+      "loss": 16.745071411132812,
+      "step": 1540
+    },
+    {
+      "epoch": 0.7380952380952381,
+      "grad_norm": 12.739700317382812,
+      "learning_rate": 7.068007975684009e-07,
+      "loss": 16.04017791748047,
+      "step": 1550
+    },
+    {
+      "epoch": 0.7428571428571429,
+      "grad_norm": 9.787664413452148,
+      "learning_rate": 6.829370695205175e-07,
+      "loss": 16.20958251953125,
+      "step": 1560
+    },
+    {
+      "epoch": 0.7476190476190476,
+      "grad_norm": 12.524157524108887,
+      "learning_rate": 6.593999379507207e-07,
+      "loss": 16.128921508789062,
+      "step": 1570
+    },
+    {
+      "epoch": 0.7523809523809524,
+      "grad_norm": 6.589555263519287,
+      "learning_rate": 6.3619523943986e-07,
+      "loss": 16.84815368652344,
+      "step": 1580
+    },
+    {
+      "epoch": 0.7571428571428571,
+      "grad_norm": 9.732259750366211,
+      "learning_rate": 6.133287281342496e-07,
+      "loss": 16.412393188476564,
+      "step": 1590
+    },
+    {
+      "epoch": 0.7619047619047619,
+      "grad_norm": 13.840083122253418,
+      "learning_rate": 5.908060743187979e-07,
+      "loss": 16.528514099121093,
+      "step": 1600
+    },
+    {
+      "epoch": 0.7666666666666667,
+      "grad_norm": 12.243499755859375,
+      "learning_rate": 5.686328630109287e-07,
+      "loss": 16.269061279296874,
+      "step": 1610
+    },
+    {
+      "epoch": 0.7714285714285715,
+      "grad_norm": 12.514222145080566,
+      "learning_rate": 5.468145925756424e-07,
+      "loss": 16.259161376953124,
+      "step": 1620
+    },
+    {
+      "epoch": 0.7761904761904762,
+      "grad_norm": 9.389951705932617,
+      "learning_rate": 5.253566733620706e-07,
+      "loss": 16.349365234375,
+      "step": 1630
+    },
+    {
+      "epoch": 0.780952380952381,
+      "grad_norm": 36.1035041809082,
+      "learning_rate": 5.042644263618525e-07,
+      "loss": 16.16446533203125,
+      "step": 1640
+    },
+    {
+      "epoch": 0.7857142857142857,
+      "grad_norm": 9.599213600158691,
+      "learning_rate": 4.835430818896733e-07,
+      "loss": 16.311676025390625,
+      "step": 1650
+    },
+    {
+      "epoch": 0.7857142857142857,
+      "eval_accuracy": 0.06944881889763779,
+      "eval_loss": 16.275449752807617,
+      "eval_runtime": 26.1826,
+      "eval_samples_per_second": 19.097,
+      "eval_steps_per_second": 2.406,
+      "step": 1650
+    },
+    {
+      "epoch": 0.7904761904761904,
+      "grad_norm": 8.050191879272461,
+      "learning_rate": 4.6319777828628237e-07,
+      "loss": 16.19422607421875,
+      "step": 1660
+    },
+    {
+      "epoch": 0.7952380952380952,
+      "grad_norm": 15.81093692779541,
+      "learning_rate": 4.432335606443234e-07,
+      "loss": 16.439752197265626,
+      "step": 1670
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 16.138633728027344,
+      "learning_rate": 4.236553795572875e-07,
+      "loss": 16.333755493164062,
+      "step": 1680
+    },
+    {
+      "epoch": 0.8047619047619048,
+      "grad_norm": 16.733367919921875,
+      "learning_rate": 4.0446808989189485e-07,
+      "loss": 16.334153747558595,
+      "step": 1690
+    },
+    {
+      "epoch": 0.8095238095238095,
+      "grad_norm": 8.272436141967773,
+      "learning_rate": 3.856764495842197e-07,
+      "loss": 16.340499877929688,
+      "step": 1700
+    },
+    {
+      "epoch": 0.8142857142857143,
+      "grad_norm": 34.05455017089844,
+      "learning_rate": 3.6728511845984776e-07,
+      "loss": 16.4441162109375,
+      "step": 1710
+    },
+    {
+      "epoch": 0.819047619047619,
+      "grad_norm": 16.842851638793945,
+      "learning_rate": 3.4929865707836535e-07,
+      "loss": 16.022296142578124,
+      "step": 1720
+    },
+    {
+      "epoch": 0.8238095238095238,
+      "grad_norm": 10.098868370056152,
+      "learning_rate": 3.317215256024606e-07,
+      "loss": 16.09764404296875,
+      "step": 1730
+    },
+    {
+      "epoch": 0.8285714285714286,
+      "grad_norm": 8.483038902282715,
+      "learning_rate": 3.1455808269192164e-07,
+      "loss": 16.11446533203125,
+      "step": 1740
+    },
+    {
+      "epoch": 0.8333333333333334,
+      "grad_norm": 10.998558044433594,
+      "learning_rate": 2.9781258442280877e-07,
+      "loss": 16.22391357421875,
+      "step": 1750
+    },
+    {
+      "epoch": 0.8380952380952381,
+      "grad_norm": 10.043136596679688,
+      "learning_rate": 2.814891832320565e-07,
+      "loss": 16.850048828125,
+      "step": 1760
+    },
+    {
+      "epoch": 0.8428571428571429,
+      "grad_norm": 13.000489234924316,
+      "learning_rate": 2.6559192688778263e-07,
+      "loss": 16.31856689453125,
+      "step": 1770
+    },
+    {
+      "epoch": 0.8476190476190476,
+      "grad_norm": 11.428621292114258,
+      "learning_rate": 2.5012475748554916e-07,
+      "loss": 16.24926300048828,
+      "step": 1780
+    },
+    {
+      "epoch": 0.8523809523809524,
+      "grad_norm": 21.403606414794922,
+      "learning_rate": 2.3509151047082866e-07,
+      "loss": 16.078160095214844,
+      "step": 1790
+    },
+    {
+      "epoch": 0.8571428571428571,
+      "grad_norm": 9.761038780212402,
+      "learning_rate": 2.2049591368791386e-07,
+      "loss": 15.990585327148438,
+      "step": 1800
+    },
+    {
+      "epoch": 0.8571428571428571,
+      "eval_accuracy": 0.0696771653543307,
+      "eval_loss": 16.194637298583984,
+      "eval_runtime": 25.3768,
+      "eval_samples_per_second": 19.703,
+      "eval_steps_per_second": 2.483,
+      "step": 1800
     }
   ],
   "logging_steps": 10,