Training in progress, step 900, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fec3e662918181e81fec2617a5f9f5de6a01b3e7022f265f73654bbc50438347
+oid sha256:ce638fe074432886d0a23f98a8f165e69d1e6fee84a526cf594d00f8534028a1
 size 847599616

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:38ffba74dde1d2bade94cf7d477b69f097fefa5eddd6cbfa453ed04630627cc1
+oid sha256:0caa91a435695f3ccebbf12966391316e72dc5ad6f9cc2e90bacdd64a48fdc1c
 size 1386414411

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af6ae550ab924258b75cba7b10f460b254db57e2f0ee1e6652ad45c4ae51f55f
+oid sha256:2be637d2dd60e3cec1955d0241821cbcccd2af3688716d84100a306b44dad4a4
 size 14917

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e216a9e826d4c344530b7e6d00074e0b36744d381337d9fe3838255770b48b79
+oid sha256:b8d05de60c66749991154136b82121e270010e0cf03e7ae880dd38dcbbe6fd4a
 size 14917

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:303505cecb97596e2f53b5d89a1eed07f741f9537510242aaeccaa44a51fbf19
+oid sha256:f617c1b6753801a9d80064eb68997fd29d2b80564fcc110cff0fa781e09b8683
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.2857142857142857,
+  "epoch": 0.42857142857142855,
   "eval_steps": 150,
-  "global_step": 600,
+  "global_step": 900,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -464,6 +464,234 @@
       "eval_samples_per_second": 19.689,
       "eval_steps_per_second": 2.481,
       "step": 600
+    },
+    {
+      "epoch": 0.2904761904761905,
+      "grad_norm": 20.064794540405273,
+      "learning_rate": 3.4024735685449766e-06,
+      "loss": 17.788371276855468,
+      "step": 610
+    },
+    {
+      "epoch": 0.29523809523809524,
+      "grad_norm": 19.219192504882812,
+      "learning_rate": 3.379847167149008e-06,
+      "loss": 17.86636962890625,
+      "step": 620
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 23.365055084228516,
+      "learning_rate": 3.3568786004588363e-06,
+      "loss": 17.805162048339845,
+      "step": 630
+    },
+    {
+      "epoch": 0.3047619047619048,
+      "grad_norm": 16.860742568969727,
+      "learning_rate": 3.333573564066385e-06,
+      "loss": 17.576748657226563,
+      "step": 640
+    },
+    {
+      "epoch": 0.30952380952380953,
+      "grad_norm": 23.96249008178711,
+      "learning_rate": 3.3099378369990875e-06,
+      "loss": 17.694325256347657,
+      "step": 650
+    },
+    {
+      "epoch": 0.3142857142857143,
+      "grad_norm": 16.125730514526367,
+      "learning_rate": 3.285977280286845e-06,
+      "loss": 17.539736938476562,
+      "step": 660
+    },
+    {
+      "epoch": 0.319047619047619,
+      "grad_norm": 16.924381256103516,
+      "learning_rate": 3.261697835508648e-06,
+      "loss": 17.864358520507814,
+      "step": 670
+    },
+    {
+      "epoch": 0.3238095238095238,
+      "grad_norm": 24.52809715270996,
+      "learning_rate": 3.2371055233192185e-06,
+      "loss": 17.447659301757813,
+      "step": 680
+    },
+    {
+      "epoch": 0.32857142857142857,
+      "grad_norm": 24.08842658996582,
+      "learning_rate": 3.2122064419560557e-06,
+      "loss": 17.473863220214845,
+      "step": 690
+    },
+    {
+      "epoch": 0.3333333333333333,
+      "grad_norm": 26.00309944152832,
+      "learning_rate": 3.1870067657272295e-06,
+      "loss": 17.199142456054688,
+      "step": 700
+    },
+    {
+      "epoch": 0.3380952380952381,
+      "grad_norm": 29.389789581298828,
+      "learning_rate": 3.1615127434803192e-06,
+      "loss": 17.315379333496093,
+      "step": 710
+    },
+    {
+      "epoch": 0.34285714285714286,
+      "grad_norm": 30.414424896240234,
+      "learning_rate": 3.1357306970528665e-06,
+      "loss": 17.431112670898436,
+      "step": 720
+    },
+    {
+      "epoch": 0.3476190476190476,
+      "grad_norm": 32.14336395263672,
+      "learning_rate": 3.1096670197047267e-06,
+      "loss": 17.360943603515626,
+      "step": 730
+    },
+    {
+      "epoch": 0.3523809523809524,
+      "grad_norm": 14.162923812866211,
+      "learning_rate": 3.0833281745327123e-06,
+      "loss": 17.168132019042968,
+      "step": 740
+    },
+    {
+      "epoch": 0.35714285714285715,
+      "grad_norm": 21.957395553588867,
+      "learning_rate": 3.056720692867918e-06,
+      "loss": 17.510189819335938,
+      "step": 750
+    },
+    {
+      "epoch": 0.35714285714285715,
+      "eval_accuracy": 0.057960629921259846,
+      "eval_loss": 17.25590705871582,
+      "eval_runtime": 25.9338,
+      "eval_samples_per_second": 19.28,
+      "eval_steps_per_second": 2.429,
+      "step": 750
+    },
+    {
+      "epoch": 0.3619047619047619,
+      "grad_norm": 22.730085372924805,
+      "learning_rate": 3.029851172656121e-06,
+      "loss": 17.168865966796876,
+      "step": 760
+    },
+    {
+      "epoch": 0.36666666666666664,
+      "grad_norm": 9.091358184814453,
+      "learning_rate": 3.0027262768216716e-06,
+      "loss": 17.32322540283203,
+      "step": 770
+    },
+    {
+      "epoch": 0.37142857142857144,
+      "grad_norm": 46.21049118041992,
+      "learning_rate": 2.9753527316152624e-06,
+      "loss": 17.2936767578125,
+      "step": 780
+    },
+    {
+      "epoch": 0.3761904761904762,
+      "grad_norm": 12.04414176940918,
+      "learning_rate": 2.9477373249459973e-06,
+      "loss": 17.235751342773437,
+      "step": 790
+    },
+    {
+      "epoch": 0.38095238095238093,
+      "grad_norm": 43.7669563293457,
+      "learning_rate": 2.919886904698173e-06,
+      "loss": 17.19912109375,
+      "step": 800
+    },
+    {
+      "epoch": 0.38571428571428573,
+      "grad_norm": 15.64034652709961,
+      "learning_rate": 2.8918083770331857e-06,
+      "loss": 17.119082641601562,
+      "step": 810
+    },
+    {
+      "epoch": 0.3904761904761905,
+      "grad_norm": 15.29228401184082,
+      "learning_rate": 2.8635087046769856e-06,
+      "loss": 17.21935119628906,
+      "step": 820
+    },
+    {
+      "epoch": 0.3952380952380952,
+      "grad_norm": 40.923484802246094,
+      "learning_rate": 2.83499490519351e-06,
+      "loss": 17.068731689453124,
+      "step": 830
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 18.847187042236328,
+      "learning_rate": 2.8062740492445104e-06,
+      "loss": 17.178439331054687,
+      "step": 840
+    },
+    {
+      "epoch": 0.40476190476190477,
+      "grad_norm": 10.75904369354248,
+      "learning_rate": 2.7773532588362205e-06,
+      "loss": 17.27076873779297,
+      "step": 850
+    },
+    {
+      "epoch": 0.4095238095238095,
+      "grad_norm": 22.709970474243164,
+      "learning_rate": 2.748239705553287e-06,
+      "loss": 17.397381591796876,
+      "step": 860
+    },
+    {
+      "epoch": 0.4142857142857143,
+      "grad_norm": 22.443639755249023,
+      "learning_rate": 2.718940608780408e-06,
+      "loss": 17.009933471679688,
+      "step": 870
+    },
+    {
+      "epoch": 0.41904761904761906,
+      "grad_norm": 9.636713027954102,
+      "learning_rate": 2.6894632339121183e-06,
+      "loss": 17.1143310546875,
+      "step": 880
+    },
+    {
+      "epoch": 0.4238095238095238,
+      "grad_norm": 11.698447227478027,
+      "learning_rate": 2.6598148905511656e-06,
+      "loss": 17.266459655761718,
+      "step": 890
+    },
+    {
+      "epoch": 0.42857142857142855,
+      "grad_norm": 34.808990478515625,
+      "learning_rate": 2.6300029306959236e-06,
+      "loss": 17.431172180175782,
+      "step": 900
+    },
+    {
+      "epoch": 0.42857142857142855,
+      "eval_accuracy": 0.059070866141732285,
+      "eval_loss": 16.987903594970703,
+      "eval_runtime": 25.5466,
+      "eval_samples_per_second": 19.572,
+      "eval_steps_per_second": 2.466,
+      "step": 900
     }
   ],
   "logging_steps": 10,