Training in progress, step 100000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:462c7e7ea68fc7b22e95e2c43de7584a6ca2aa50f1c7a5f94b55a91f45c8524a
-size 885324633
+oid sha256:401cceacc8e35e1e6ab2c8853528f5a7a039a3dac2bc053f0e6e6046b944a04d
+size 885325017

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f5dba4d736c66b63a1cd309a8573e58e2cf3b0e4e949ba1f613b06d39cfbd938
+oid sha256:3a5c8ebf78a4fd2d0ed0e95041d50d8203b3bb46201e372ea6a054237204580b
 size 442675755

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c5e7ceb2de2087a9513939858085a4759c447a91c205493e170ce0730856097
+oid sha256:474fe9f66ed10011e757bad091e876be5dd0b41d0f805bbd9c75b74f5a58d806
 size 13611

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c5e7ceb2de2087a9513939858085a4759c447a91c205493e170ce0730856097
+oid sha256:474fe9f66ed10011e757bad091e876be5dd0b41d0f805bbd9c75b74f5a58d806
 size 13611

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c5e7ceb2de2087a9513939858085a4759c447a91c205493e170ce0730856097
+oid sha256:474fe9f66ed10011e757bad091e876be5dd0b41d0f805bbd9c75b74f5a58d806
 size 13611

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c5e7ceb2de2087a9513939858085a4759c447a91c205493e170ce0730856097
+oid sha256:474fe9f66ed10011e757bad091e876be5dd0b41d0f805bbd9c75b74f5a58d806
 size 13611

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c5e7ceb2de2087a9513939858085a4759c447a91c205493e170ce0730856097
+oid sha256:474fe9f66ed10011e757bad091e876be5dd0b41d0f805bbd9c75b74f5a58d806
 size 13611

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c5e7ceb2de2087a9513939858085a4759c447a91c205493e170ce0730856097
+oid sha256:474fe9f66ed10011e757bad091e876be5dd0b41d0f805bbd9c75b74f5a58d806
 size 13611

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c5e7ceb2de2087a9513939858085a4759c447a91c205493e170ce0730856097
+oid sha256:474fe9f66ed10011e757bad091e876be5dd0b41d0f805bbd9c75b74f5a58d806
 size 13611

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c5e7ceb2de2087a9513939858085a4759c447a91c205493e170ce0730856097
+oid sha256:474fe9f66ed10011e757bad091e876be5dd0b41d0f805bbd9c75b74f5a58d806
 size 13611

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4eda5fed79fbfae57d1a589b135999ab70f7c329a9938c428058fd62dc77c658
+oid sha256:4178362c6bd24374be7907f1b74df811389bf304534a9b4cb11df3bada4d661b
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
  "best_metric": null,
  "best_model_checkpoint": null,
- "epoch": 0.25,
- "global_step": 50000,
+ "epoch": 1.12574,
+ "global_step": 100000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
@@ -314,11 +314,319 @@
  "eval_samples_per_second": 290.001,
  "eval_steps_per_second": 2.32,
  "step": 50000
+ },
+ {
+ "epoch": 0.26,
+ "learning_rate": 8.894386393810563e-05,
+ "loss": 1.0566,
+ "step": 51000
+ },
+ {
+ "epoch": 0.26,
+ "learning_rate": 8.842005554284296e-05,
+ "loss": 0.9781,
+ "step": 52000
+ },
+ {
+ "epoch": 0.27,
+ "learning_rate": 8.788574348801675e-05,
+ "loss": 0.9931,
+ "step": 53000
+ },
+ {
+ "epoch": 0.27,
+ "learning_rate": 8.73410738492077e-05,
+ "loss": 1.0068,
+ "step": 54000
+ },
+ {
+ "epoch": 0.28,
+ "learning_rate": 8.678619553365659e-05,
+ "loss": 0.9655,
+ "step": 55000
+ },
+ {
+ "epoch": 0.28,
+ "learning_rate": 8.622126023955446e-05,
+ "loss": 1.0449,
+ "step": 56000
+ },
+ {
+ "epoch": 0.28,
+ "learning_rate": 8.564642241456986e-05,
+ "loss": 0.9349,
+ "step": 57000
+ },
+ {
+ "epoch": 0.29,
+ "learning_rate": 8.506183921362443e-05,
+ "loss": 1.0303,
+ "step": 58000
+ },
+ {
+ "epoch": 0.29,
+ "learning_rate": 8.44676704559283e-05,
+ "loss": 0.9429,
+ "step": 59000
+ },
+ {
+ "epoch": 0.3,
+ "learning_rate": 8.386407858128706e-05,
+ "loss": 0.9843,
+ "step": 60000
+ },
+ {
+ "epoch": 0.3,
+ "learning_rate": 8.32512286056924e-05,
+ "loss": 0.9846,
+ "step": 61000
+ },
+ {
+ "epoch": 0.31,
+ "learning_rate": 8.262928807620843e-05,
+ "loss": 0.9583,
+ "step": 62000
+ },
+ {
+ "epoch": 0.32,
+ "learning_rate": 8.199842702516583e-05,
+ "loss": 1.0354,
+ "step": 63000
+ },
+ {
+ "epoch": 0.32,
+ "learning_rate": 8.135881792367686e-05,
+ "loss": 0.896,
+ "step": 64000
+ },
+ {
+ "epoch": 0.33,
+ "learning_rate": 8.07106356344834e-05,
+ "loss": 1.0057,
+ "step": 65000
+ },
+ {
+ "epoch": 0.33,
+ "learning_rate": 8.005405736415126e-05,
+ "loss": 0.9293,
+ "step": 66000
+ },
+ {
+ "epoch": 0.34,
+ "learning_rate": 7.938926261462366e-05,
+ "loss": 0.9797,
+ "step": 67000
+ },
+ {
+ "epoch": 0.34,
+ "learning_rate": 7.871643313414718e-05,
+ "loss": 0.9689,
+ "step": 68000
+ },
+ {
+ "epoch": 0.34,
+ "learning_rate": 7.803575286758364e-05,
+ "loss": 0.942,
+ "step": 69000
+ },
+ {
+ "epoch": 0.35,
+ "learning_rate": 7.734740790612136e-05,
+ "loss": 1.0029,
+ "step": 70000
+ },
+ {
+ "epoch": 0.35,
+ "learning_rate": 7.66515864363997e-05,
+ "loss": 0.8798,
+ "step": 71000
+ },
+ {
+ "epoch": 0.36,
+ "learning_rate": 7.594847868906076e-05,
+ "loss": 1.0029,
+ "step": 72000
+ },
+ {
+ "epoch": 0.36,
+ "learning_rate": 7.52382768867422e-05,
+ "loss": 0.9163,
+ "step": 73000
+ },
+ {
+ "epoch": 0.37,
+ "learning_rate": 7.452117519152542e-05,
+ "loss": 0.9805,
+ "step": 74000
+ },
+ {
+ "epoch": 1.0,
+ "learning_rate": 7.379736965185368e-05,
+ "loss": 0.9385,
+ "step": 75000
+ },
+ {
+ "epoch": 1.01,
+ "learning_rate": 7.30670581489344e-05,
+ "loss": 0.92,
+ "step": 76000
+ },
+ {
+ "epoch": 1.01,
+ "learning_rate": 7.233044034264034e-05,
+ "loss": 0.9465,
+ "step": 77000
+ },
+ {
+ "epoch": 1.02,
+ "learning_rate": 7.158771761692464e-05,
+ "loss": 0.9328,
+ "step": 78000
+ },
+ {
+ "epoch": 1.02,
+ "learning_rate": 7.083909302476453e-05,
+ "loss": 0.9194,
+ "step": 79000
+ },
+ {
+ "epoch": 1.03,
+ "learning_rate": 7.008477123264848e-05,
+ "loss": 0.995,
+ "step": 80000
+ },
+ {
+ "epoch": 1.03,
+ "learning_rate": 6.932495846462261e-05,
+ "loss": 0.8828,
+ "step": 81000
+ },
+ {
+ "epoch": 1.04,
+ "learning_rate": 6.855986244591104e-05,
+ "loss": 0.9847,
+ "step": 82000
+ },
+ {
+ "epoch": 1.04,
+ "learning_rate": 6.778969234612584e-05,
+ "loss": 0.8884,
+ "step": 83000
+ },
+ {
+ "epoch": 1.05,
+ "learning_rate": 6.701465872208216e-05,
+ "loss": 0.9444,
+ "step": 84000
+ },
+ {
+ "epoch": 1.05,
+ "learning_rate": 6.623497346023418e-05,
+ "loss": 0.9171,
+ "step": 85000
+ },
+ {
+ "epoch": 1.06,
+ "learning_rate": 6.545084971874738e-05,
+ "loss": 0.9213,
+ "step": 86000
+ },
+ {
+ "epoch": 1.06,
+ "learning_rate": 6.466250186922325e-05,
+ "loss": 0.9893,
+ "step": 87000
+ },
+ {
+ "epoch": 1.07,
+ "learning_rate": 6.387014543809223e-05,
+ "loss": 0.8567,
+ "step": 88000
+ },
+ {
+ "epoch": 1.07,
+ "learning_rate": 6.307399704769099e-05,
+ "loss": 0.9598,
+ "step": 89000
+ },
+ {
+ "epoch": 1.08,
+ "learning_rate": 6.227427435703997e-05,
+ "loss": 0.8748,
+ "step": 90000
+ },
+ {
+ "epoch": 1.08,
+ "learning_rate": 6.147119600233758e-05,
+ "loss": 0.9477,
+ "step": 91000
+ },
+ {
+ "epoch": 1.09,
+ "learning_rate": 6.066498153718735e-05,
+ "loss": 0.9013,
+ "step": 92000
+ },
+ {
+ "epoch": 1.09,
+ "learning_rate": 5.985585137257401e-05,
+ "loss": 0.923,
+ "step": 93000
+ },
+ {
+ "epoch": 1.1,
+ "learning_rate": 5.90440267166055e-05,
+ "loss": 0.9442,
+ "step": 94000
+ },
+ {
+ "epoch": 1.1,
+ "learning_rate": 5.8229729514036705e-05,
+ "loss": 0.8553,
+ "step": 95000
+ },
+ {
+ "epoch": 1.11,
+ "learning_rate": 5.74131823855921e-05,
+ "loss": 0.9601,
+ "step": 96000
+ },
+ {
+ "epoch": 1.11,
+ "learning_rate": 5.6594608567103456e-05,
+ "loss": 0.8642,
+ "step": 97000
+ },
+ {
+ "epoch": 1.12,
+ "learning_rate": 5.577423184847932e-05,
+ "loss": 0.9563,
+ "step": 98000
+ },
+ {
+ "epoch": 1.12,
+ "learning_rate": 5.495227651252315e-05,
+ "loss": 0.8868,
+ "step": 99000
+ },
+ {
+ "epoch": 1.13,
+ "learning_rate": 5.4128967273616625e-05,
+ "loss": 0.8979,
+ "step": 100000
+ },
+ {
+ "epoch": 1.13,
+ "eval_loss": 0.6754369735717773,
+ "eval_runtime": 11.198,
+ "eval_samples_per_second": 446.509,
+ "eval_steps_per_second": 3.572,
+ "step": 100000
  }
  ],
  "max_steps": 200000,
  "num_train_epochs": 9223372036854775807,
- "total_flos": 8.422699302912e+17,
+ "total_flos": 1.684548283281703e+18,
  "trial_name": null,
  "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f5dba4d736c66b63a1cd309a8573e58e2cf3b0e4e949ba1f613b06d39cfbd938
+oid sha256:3a5c8ebf78a4fd2d0ed0e95041d50d8203b3bb46201e372ea6a054237204580b
 size 442675755

runs/Feb06_02-36-55_t1v-n-d0b02cf6-w-0/events.out.tfevents.1675651039.t1v-n-d0b02cf6-w-0.2462251.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07032aabc1e542c05642384645ba10eaa9554fb7c203f4524937afed763b9c70
-size 12008
+oid sha256:f6753ea63e451771bb8eec066f9874171bd70187880e1b0132a3d7103762c7aa
+size 20284