Training in progress, step 90, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d7e2cd2dbf78c54ea3f0f06d49fd1af5b70a3e03ac9e6c82cb1d62722b2593b6
+oid sha256:5cd39093da46c760bf0ad6acee7d3afbdc458b320613d02a1b9b87bf1dfd3d57
 size 763470136

last-checkpoint/global_step90/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43a27a4dddf9f2faeaf94ce4b93f01574aced05b3161789cd7daf355b557ac4f
+size 1152331664

last-checkpoint/global_step90/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bce11d1aa5e058c4096f50eaefdce8b585234e4a66af48e9e3ec4f8497934da3
+size 1152331664

last-checkpoint/global_step90/zero_pp_rank_0_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29a0796cc9183991e8ebdefaea1a53aa52c5ae33fb8faea94492f5f5b948af0a
+size 348711830

last-checkpoint/global_step90/zero_pp_rank_1_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:860d64ab323625107a1e3ec5efc33674241ef63698c7df279d798fe80ac1b076
+size 348711830

last-checkpoint/latest

@@ -1 +1 @@
-global_step60
+global_step90

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13d47ce3a312fdef8e844802a1273de45b2a1adbfb4848f261f3e8b747e28be5
+oid sha256:402dc8f05e787a8bd1f6017a51a44dd402264604e6e8b23372c047903d00e275
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df4302bd5b366946b267764b57680418f02385ae358386a07ebe9d879f34434f
+oid sha256:385e4b7d88dae501cd7416828b65c0f6787ac9f75fe1a28f84bf64ac6675909d
 size 14512

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aad2d65943628ea6b328be0e7f3056643998d5e6f7a4812061e3d7f5ba16c03e
+oid sha256:ac3936d03564e869c0f8be0c0a24855f0fbaa9d17a65502bfe26d2b6f28ba7ad
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.4006677796327212,
+  "epoch": 0.6010016694490818,
   "eval_steps": 30,
-  "global_step": 60,
+  "global_step": 90,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -451,6 +451,224 @@
       "eval_samples_per_second": 0.314,
       "eval_steps_per_second": 0.157,
       "step": 60
+    },
+    {
+      "epoch": 0.4073455759599332,
+      "grad_norm": 0.8826173031830702,
+      "learning_rate": 3.6805066361746716e-05,
+      "loss": 1.249,
+      "step": 61
+    },
+    {
+      "epoch": 0.41402337228714525,
+      "grad_norm": 0.7923611594554809,
+      "learning_rate": 3.634306321221328e-05,
+      "loss": 1.391,
+      "step": 62
+    },
+    {
+      "epoch": 0.42070116861435725,
+      "grad_norm": 0.761557330941142,
+      "learning_rate": 3.587660731404377e-05,
+      "loss": 1.219,
+      "step": 63
+    },
+    {
+      "epoch": 0.4273789649415693,
+      "grad_norm": 0.5702377539149609,
+      "learning_rate": 3.5405933541830215e-05,
+      "loss": 1.0854,
+      "step": 64
+    },
+    {
+      "epoch": 0.4340567612687813,
+      "grad_norm": 0.5797801586198355,
+      "learning_rate": 3.493127889399126e-05,
+      "loss": 1.4702,
+      "step": 65
+    },
+    {
+      "epoch": 0.44073455759599334,
+      "grad_norm": 0.6326945902799598,
+      "learning_rate": 3.4452882373436316e-05,
+      "loss": 1.5134,
+      "step": 66
+    },
+    {
+      "epoch": 0.44741235392320533,
+      "grad_norm": 1.1126743861778277,
+      "learning_rate": 3.397098486722039e-05,
+      "loss": 1.0709,
+      "step": 67
+    },
+    {
+      "epoch": 0.4540901502504174,
+      "grad_norm": 0.7069612379078216,
+      "learning_rate": 3.348582902525019e-05,
+      "loss": 1.3329,
+      "step": 68
+    },
+    {
+      "epoch": 0.4607679465776294,
+      "grad_norm": 0.611072274240805,
+      "learning_rate": 3.2997659138102615e-05,
+      "loss": 1.4334,
+      "step": 69
+    },
+    {
+      "epoch": 0.4674457429048414,
+      "grad_norm": 1.103066910563406,
+      "learning_rate": 3.250672101401707e-05,
+      "loss": 1.1569,
+      "step": 70
+    },
+    {
+      "epoch": 0.4741235392320534,
+      "grad_norm": 0.8340276510866299,
+      "learning_rate": 3.201326185512364e-05,
+      "loss": 1.0757,
+      "step": 71
+    },
+    {
+      "epoch": 0.48080133555926546,
+      "grad_norm": 0.8188265127022848,
+      "learning_rate": 3.1517530132969326e-05,
+      "loss": 1.371,
+      "step": 72
+    },
+    {
+      "epoch": 0.48747913188647746,
+      "grad_norm": 0.5777487141982147,
+      "learning_rate": 3.1019775463405195e-05,
+      "loss": 1.2921,
+      "step": 73
+    },
+    {
+      "epoch": 0.4941569282136895,
+      "grad_norm": 0.5750437954715367,
+      "learning_rate": 3.052024848089725e-05,
+      "loss": 1.3945,
+      "step": 74
+    },
+    {
+      "epoch": 0.5008347245409015,
+      "grad_norm": 0.7900878178576927,
+      "learning_rate": 3.001920071232443e-05,
+      "loss": 1.2691,
+      "step": 75
+    },
+    {
+      "epoch": 0.5075125208681135,
+      "grad_norm": 0.5377760257503877,
+      "learning_rate": 2.951688445032726e-05,
+      "loss": 1.1235,
+      "step": 76
+    },
+    {
+      "epoch": 0.5141903171953256,
+      "grad_norm": 0.5732341950023626,
+      "learning_rate": 2.9013552626270894e-05,
+      "loss": 1.1105,
+      "step": 77
+    },
+    {
+      "epoch": 0.5208681135225376,
+      "grad_norm": 0.5765972783223694,
+      "learning_rate": 2.8509458682886592e-05,
+      "loss": 1.5025,
+      "step": 78
+    },
+    {
+      "epoch": 0.5275459098497496,
+      "grad_norm": 0.5473629053792197,
+      "learning_rate": 2.8004856446655614e-05,
+      "loss": 0.8961,
+      "step": 79
+    },
+    {
+      "epoch": 0.5342237061769616,
+      "grad_norm": 0.6328841066421724,
+      "learning_rate": 2.7500000000000004e-05,
+      "loss": 1.1652,
+      "step": 80
+    },
+    {
+      "epoch": 0.5409015025041736,
+      "grad_norm": 0.5537252916610816,
+      "learning_rate": 2.6995143553344394e-05,
+      "loss": 1.5573,
+      "step": 81
+    },
+    {
+      "epoch": 0.5475792988313857,
+      "grad_norm": 0.670737956141697,
+      "learning_rate": 2.6490541317113427e-05,
+      "loss": 1.2827,
+      "step": 82
+    },
+    {
+      "epoch": 0.5542570951585977,
+      "grad_norm": 0.8099350587885803,
+      "learning_rate": 2.598644737372911e-05,
+      "loss": 1.1264,
+      "step": 83
+    },
+    {
+      "epoch": 0.5609348914858097,
+      "grad_norm": 0.5790201863930161,
+      "learning_rate": 2.548311554967275e-05,
+      "loss": 1.25,
+      "step": 84
+    },
+    {
+      "epoch": 0.5676126878130217,
+      "grad_norm": 0.7651780955233705,
+      "learning_rate": 2.4980799287675578e-05,
+      "loss": 1.5117,
+      "step": 85
+    },
+    {
+      "epoch": 0.5742904841402338,
+      "grad_norm": 0.8401680884601399,
+      "learning_rate": 2.447975151910276e-05,
+      "loss": 1.0176,
+      "step": 86
+    },
+    {
+      "epoch": 0.5809682804674458,
+      "grad_norm": 0.7026724359120083,
+      "learning_rate": 2.3980224536594803e-05,
+      "loss": 1.2334,
+      "step": 87
+    },
+    {
+      "epoch": 0.5876460767946577,
+      "grad_norm": 1.434313668658568,
+      "learning_rate": 2.3482469867030676e-05,
+      "loss": 1.2272,
+      "step": 88
+    },
+    {
+      "epoch": 0.5943238731218697,
+      "grad_norm": 0.5970254035001638,
+      "learning_rate": 2.298673814487636e-05,
+      "loss": 1.2615,
+      "step": 89
+    },
+    {
+      "epoch": 0.6010016694490818,
+      "grad_norm": 0.5775454892942203,
+      "learning_rate": 2.249327898598293e-05,
+      "loss": 1.1957,
+      "step": 90
+    },
+    {
+      "epoch": 0.6010016694490818,
+      "eval_loss": 0.9956896305084229,
+      "eval_runtime": 318.961,
+      "eval_samples_per_second": 0.314,
+      "eval_steps_per_second": 0.157,
+      "step": 90
     }
   ],
   "logging_steps": 1,
@@ -470,7 +688,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7157458711609344.0,
+  "total_flos": 1.0736256317128704e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null