chancharikm commited on
Commit
f8c0a03
·
verified ·
1 Parent(s): 5cb6da8

Training in progress, step 500, checkpoint

Browse files
Files changed (31) hide show
  1. last-checkpoint/global_step500/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +3 -0
  2. last-checkpoint/global_step500/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +3 -0
  3. last-checkpoint/global_step500/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +3 -0
  4. last-checkpoint/global_step500/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +3 -0
  5. last-checkpoint/global_step500/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt +3 -0
  6. last-checkpoint/global_step500/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt +3 -0
  7. last-checkpoint/global_step500/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt +3 -0
  8. last-checkpoint/global_step500/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt +3 -0
  9. last-checkpoint/global_step500/zero_pp_rank_0_mp_rank_00_model_states.pt +3 -0
  10. last-checkpoint/global_step500/zero_pp_rank_1_mp_rank_00_model_states.pt +3 -0
  11. last-checkpoint/global_step500/zero_pp_rank_2_mp_rank_00_model_states.pt +3 -0
  12. last-checkpoint/global_step500/zero_pp_rank_3_mp_rank_00_model_states.pt +3 -0
  13. last-checkpoint/global_step500/zero_pp_rank_4_mp_rank_00_model_states.pt +3 -0
  14. last-checkpoint/global_step500/zero_pp_rank_5_mp_rank_00_model_states.pt +3 -0
  15. last-checkpoint/global_step500/zero_pp_rank_6_mp_rank_00_model_states.pt +3 -0
  16. last-checkpoint/global_step500/zero_pp_rank_7_mp_rank_00_model_states.pt +3 -0
  17. last-checkpoint/latest +1 -1
  18. last-checkpoint/model-00001-of-00004.safetensors +1 -1
  19. last-checkpoint/model-00002-of-00004.safetensors +1 -1
  20. last-checkpoint/model-00003-of-00004.safetensors +1 -1
  21. last-checkpoint/model-00004-of-00004.safetensors +1 -1
  22. last-checkpoint/rng_state_0.pth +1 -1
  23. last-checkpoint/rng_state_1.pth +1 -1
  24. last-checkpoint/rng_state_2.pth +1 -1
  25. last-checkpoint/rng_state_3.pth +1 -1
  26. last-checkpoint/rng_state_4.pth +1 -1
  27. last-checkpoint/rng_state_5.pth +1 -1
  28. last-checkpoint/rng_state_6.pth +1 -1
  29. last-checkpoint/rng_state_7.pth +1 -1
  30. last-checkpoint/scheduler.pt +1 -1
  31. last-checkpoint/trainer_state.json +353 -3
last-checkpoint/global_step500/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:354033308deba3453420da0e1a90a16edc959f5690ee41dd1842a5cf666abac3
3
+ size 1558836997
last-checkpoint/global_step500/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:36f625c1bf9e258809a45c609feebb296fbea7a7c069b8112390f73940abf78e
3
+ size 1558836997
last-checkpoint/global_step500/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e49a51bdf0eb7b438d47f40c1d16990f417e397a7f59e3c5782b8abee94e611b
3
+ size 1558836997
last-checkpoint/global_step500/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79b93cc63c6264ab1aa2754ff1f0c4e5f59d1a7ac196425b918844f6eecd639b
3
+ size 1558836997
last-checkpoint/global_step500/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a9dea42ea8ff11dd9be0602929f3bae89b7f598e659e466a91d06560a8b5425
3
+ size 1558836997
last-checkpoint/global_step500/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37f83331ca45198aedfe239208f5bf557d5101f856387795beaa5231f4bb2e14
3
+ size 1558836997
last-checkpoint/global_step500/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1294bcbc27ddf09749378242685830044a4e3ed365e2c28df581c31e7d6348f5
3
+ size 1558836997
last-checkpoint/global_step500/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b506e2dfba3e3d7980454f93f383b46469237a14d6e8cadbcdc691f1402b28e7
3
+ size 1558836997
last-checkpoint/global_step500/zero_pp_rank_0_mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c0cafb80f7244a22629f5b479eacedd652313b060dd60047d97f8529992b45c9
3
+ size 14663005
last-checkpoint/global_step500/zero_pp_rank_1_mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f804d1295b89e01e8fdaf93814473500099bd801e63f77dcbcdd1f7494349eaf
3
+ size 14663005
last-checkpoint/global_step500/zero_pp_rank_2_mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:84b6ef8100c8444788c439a2ca57d9348287cc8ceaee35a2311bd80082de2607
3
+ size 14663005
last-checkpoint/global_step500/zero_pp_rank_3_mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe2acacc7d1d7cc7b4f9ade89522bb394d091f51e56be6add13eb8c3d39822d1
3
+ size 14663005
last-checkpoint/global_step500/zero_pp_rank_4_mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:80144fe182354aea10f12afcee16733ef35974d90b67f8edef04a4ce97b002a3
3
+ size 14663005
last-checkpoint/global_step500/zero_pp_rank_5_mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a37a179209f48fa9f265900c3c6eeb016396a4d4978f9ad3b3ef501ab067e649
3
+ size 14663005
last-checkpoint/global_step500/zero_pp_rank_6_mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e97440ba48e9c4e407af8584d43f1fc3147e291011c8f8773fdda3a00f4c40c
3
+ size 14663005
last-checkpoint/global_step500/zero_pp_rank_7_mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db614de2c34331195ec77f702ba47d0ef50da4b426d55ae11ed65f137da37782
3
+ size 14663005
last-checkpoint/latest CHANGED
@@ -1 +1 @@
1
- global_step450
 
1
+ global_step500
last-checkpoint/model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4ef8eebadefb621e848467670494d2423e979bb52f3ff8e1559cdf7a71e34a86
3
  size 4998056552
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e64ebc182d8b059d555d573fcf68ff59aeafe97038f7054d0521d6e4072b1db
3
  size 4998056552
last-checkpoint/model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2d30c217315ae67192d3106058f0ad14f2b61c465d76ce2ab5f552f0a11e7af1
3
  size 4915962464
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da5067f199d6eb7f2f664257611d1bb9fdf1e82e37b4b7771f248f71542f6de4
3
  size 4915962464
last-checkpoint/model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cafaacaaf19d32637e69d4b982db1ac8c999f4dc4898e02565bc5f1e03465d78
3
  size 4915962496
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc761dc73ab830b4c09670b9e21a1ada44f833147dcd578f376cf4d0dbff668b
3
  size 4915962496
last-checkpoint/model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:931dfaaeadcac0f858deaa6cfa12b7bb1da588942a303cf3fc91d951ac021049
3
  size 2704357976
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:459fe728209431d88c5bc3ead19ffc36990be90719c27b25ee0fe69292f10645
3
  size 2704357976
last-checkpoint/rng_state_0.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b0418786c564bb001fc5f4215375b1a99ed3ea3f30771057e1d8682214a0108f
3
  size 16389
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f0d51a89f706019e82a1bece244691bbef31c0dc9544212f828d427b8052b077
3
  size 16389
last-checkpoint/rng_state_1.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:35deaabe10396919e53b2274736981b26bc690165c8839845f178b355a6a7588
3
  size 16389
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9db2a9d890a3bdfb6477301adcccedc994df442a5cf1f4f617b4737086e632ef
3
  size 16389
last-checkpoint/rng_state_2.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1c5deee061a76a9e05b4634f5abad786b4042e744cc4c156a2ab76dc3c94fcac
3
  size 16389
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:74f99367832c29a5aff6042c0dc14d87a3ffc16ce9cc6466678227421d213c43
3
  size 16389
last-checkpoint/rng_state_3.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:13579f7ca365ea6f9cef83929c34833cd97f9b5764a434989b4e3e2db87dce56
3
  size 16389
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2984cd1dfb7f3fdddf5cc99bb1dab2759a14eef425d83154d76b310151f5d01c
3
  size 16389
last-checkpoint/rng_state_4.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:073d0b1d7e2e3930e5c29fc418e6246462ab2a00396c3a86e1448d373503f1b2
3
  size 16389
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4cb1eac572046e66de7e9c52bba4d61d758728542e4fdc6d8b194a6c29e10f96
3
  size 16389
last-checkpoint/rng_state_5.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7c60731015889939e665a308a0933ac6c327734a4699cf5615217db0cfaf03ca
3
  size 16389
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41da76e42d56dcd9ee4821dcdf66fd5f2e82e821081ec3e07cb7e1e952647992
3
  size 16389
last-checkpoint/rng_state_6.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:416648e7a35618f28d73625751a8fc2ad066533414d19f6fc0c39932429023fc
3
  size 16389
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1ef332606e64d74e7d5d444ae550c6edf2fe161722c5d652fd47845e2aa1894
3
  size 16389
last-checkpoint/rng_state_7.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:619b5c49446c94dca2b233ad17098e42f7d58a945c2eced1aa23e50469a75431
3
  size 16389
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4b125a8a8f1fcea8543fd480628a947fbdff2ec9452d6a7be7e77a426d76b0c
3
  size 16389
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:56ad7fcc8e12a38fe90579ad64148b6a27fb94472a83cc1cd838e05828beb4ac
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:42d62bfdc248756d4ec63d89100a00afd3418d2c0d0f0099fd29e5601c7206ec
3
  size 1465
last-checkpoint/trainer_state.json CHANGED
@@ -2,9 +2,9 @@
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
- "epoch": 1.8235294117647058,
6
  "eval_steps": 500,
7
- "global_step": 450,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -3158,6 +3158,356 @@
3158
  "learning_rate": 1.105839428897216e-05,
3159
  "loss": 0.0341,
3160
  "step": 450
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3161
  }
3162
  ],
3163
  "logging_steps": 1,
@@ -3177,7 +3527,7 @@
3177
  "attributes": {}
3178
  }
3179
  },
3180
- "total_flos": 3048087294050304.0,
3181
  "train_batch_size": 10,
3182
  "trial_name": null,
3183
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 2.024340770791075,
6
  "eval_steps": 500,
7
+ "global_step": 500,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
3158
  "learning_rate": 1.105839428897216e-05,
3159
  "loss": 0.0341,
3160
  "step": 450
3161
+ },
3162
+ {
3163
+ "epoch": 1.8275862068965516,
3164
+ "grad_norm": 0.337431774628168,
3165
+ "learning_rate": 1.0993756994379178e-05,
3166
+ "loss": 0.0453,
3167
+ "step": 451
3168
+ },
3169
+ {
3170
+ "epoch": 1.8316430020283976,
3171
+ "grad_norm": 0.36965782178837847,
3172
+ "learning_rate": 1.0929199706357906e-05,
3173
+ "loss": 0.0419,
3174
+ "step": 452
3175
+ },
3176
+ {
3177
+ "epoch": 1.8356997971602436,
3178
+ "grad_norm": 0.33955413410890395,
3179
+ "learning_rate": 1.0864723714147975e-05,
3180
+ "loss": 0.0371,
3181
+ "step": 453
3182
+ },
3183
+ {
3184
+ "epoch": 1.839756592292089,
3185
+ "grad_norm": 0.37702859177437276,
3186
+ "learning_rate": 1.0800330305365526e-05,
3187
+ "loss": 0.0447,
3188
+ "step": 454
3189
+ },
3190
+ {
3191
+ "epoch": 1.843813387423935,
3192
+ "grad_norm": 0.43380541102915904,
3193
+ "learning_rate": 1.0736020765977434e-05,
3194
+ "loss": 0.0525,
3195
+ "step": 455
3196
+ },
3197
+ {
3198
+ "epoch": 1.847870182555781,
3199
+ "grad_norm": 0.3308232636624218,
3200
+ "learning_rate": 1.0671796380275705e-05,
3201
+ "loss": 0.0275,
3202
+ "step": 456
3203
+ },
3204
+ {
3205
+ "epoch": 1.8519269776876268,
3206
+ "grad_norm": 0.30675776077260075,
3207
+ "learning_rate": 1.0607658430851745e-05,
3208
+ "loss": 0.0387,
3209
+ "step": 457
3210
+ },
3211
+ {
3212
+ "epoch": 1.8559837728194726,
3213
+ "grad_norm": 0.3441545600958111,
3214
+ "learning_rate": 1.0543608198570815e-05,
3215
+ "loss": 0.0351,
3216
+ "step": 458
3217
+ },
3218
+ {
3219
+ "epoch": 1.8600405679513186,
3220
+ "grad_norm": 0.3574675624451796,
3221
+ "learning_rate": 1.0479646962546401e-05,
3222
+ "loss": 0.0395,
3223
+ "step": 459
3224
+ },
3225
+ {
3226
+ "epoch": 1.8640973630831643,
3227
+ "grad_norm": 0.41572429982747455,
3228
+ "learning_rate": 1.0415776000114716e-05,
3229
+ "loss": 0.0488,
3230
+ "step": 460
3231
+ },
3232
+ {
3233
+ "epoch": 1.86815415821501,
3234
+ "grad_norm": 0.39369896529868187,
3235
+ "learning_rate": 1.0351996586809145e-05,
3236
+ "loss": 0.0418,
3237
+ "step": 461
3238
+ },
3239
+ {
3240
+ "epoch": 1.872210953346856,
3241
+ "grad_norm": 0.34363426124475344,
3242
+ "learning_rate": 1.0288309996334802e-05,
3243
+ "loss": 0.0394,
3244
+ "step": 462
3245
+ },
3246
+ {
3247
+ "epoch": 1.8762677484787018,
3248
+ "grad_norm": 0.327289268468903,
3249
+ "learning_rate": 1.0224717500543087e-05,
3250
+ "loss": 0.0407,
3251
+ "step": 463
3252
+ },
3253
+ {
3254
+ "epoch": 1.8803245436105476,
3255
+ "grad_norm": 0.504229258734072,
3256
+ "learning_rate": 1.0161220369406283e-05,
3257
+ "loss": 0.0339,
3258
+ "step": 464
3259
+ },
3260
+ {
3261
+ "epoch": 1.8843813387423936,
3262
+ "grad_norm": 0.32336927283271066,
3263
+ "learning_rate": 1.0097819870992196e-05,
3264
+ "loss": 0.0399,
3265
+ "step": 465
3266
+ },
3267
+ {
3268
+ "epoch": 1.8884381338742393,
3269
+ "grad_norm": 0.30534018999460294,
3270
+ "learning_rate": 1.0034517271438826e-05,
3271
+ "loss": 0.0363,
3272
+ "step": 466
3273
+ },
3274
+ {
3275
+ "epoch": 1.892494929006085,
3276
+ "grad_norm": 0.3363030481693883,
3277
+ "learning_rate": 9.9713138349291e-06,
3278
+ "loss": 0.0424,
3279
+ "step": 467
3280
+ },
3281
+ {
3282
+ "epoch": 1.896551724137931,
3283
+ "grad_norm": 0.3940025228623559,
3284
+ "learning_rate": 9.908210823665587e-06,
3285
+ "loss": 0.0475,
3286
+ "step": 468
3287
+ },
3288
+ {
3289
+ "epoch": 1.900608519269777,
3290
+ "grad_norm": 0.3465688297316223,
3291
+ "learning_rate": 9.84520949784535e-06,
3292
+ "loss": 0.0339,
3293
+ "step": 469
3294
+ },
3295
+ {
3296
+ "epoch": 1.9046653144016226,
3297
+ "grad_norm": 0.3304003434324526,
3298
+ "learning_rate": 9.782311115634706e-06,
3299
+ "loss": 0.0431,
3300
+ "step": 470
3301
+ },
3302
+ {
3303
+ "epoch": 1.9087221095334685,
3304
+ "grad_norm": 0.36499605332027524,
3305
+ "learning_rate": 9.719516933144183e-06,
3306
+ "loss": 0.0378,
3307
+ "step": 471
3308
+ },
3309
+ {
3310
+ "epoch": 1.9127789046653145,
3311
+ "grad_norm": 0.40038829914160073,
3312
+ "learning_rate": 9.656828204403352e-06,
3313
+ "loss": 0.0326,
3314
+ "step": 472
3315
+ },
3316
+ {
3317
+ "epoch": 1.9168356997971603,
3318
+ "grad_norm": 0.2998673014346592,
3319
+ "learning_rate": 9.594246181335844e-06,
3320
+ "loss": 0.0304,
3321
+ "step": 473
3322
+ },
3323
+ {
3324
+ "epoch": 1.920892494929006,
3325
+ "grad_norm": 0.3233930312542325,
3326
+ "learning_rate": 9.531772113734325e-06,
3327
+ "loss": 0.0337,
3328
+ "step": 474
3329
+ },
3330
+ {
3331
+ "epoch": 1.924949290060852,
3332
+ "grad_norm": 0.30650567980290994,
3333
+ "learning_rate": 9.469407249235532e-06,
3334
+ "loss": 0.0305,
3335
+ "step": 475
3336
+ },
3337
+ {
3338
+ "epoch": 1.9290060851926978,
3339
+ "grad_norm": 0.4514180300508764,
3340
+ "learning_rate": 9.407152833295373e-06,
3341
+ "loss": 0.0337,
3342
+ "step": 476
3343
+ },
3344
+ {
3345
+ "epoch": 1.9330628803245435,
3346
+ "grad_norm": 0.4313574733470663,
3347
+ "learning_rate": 9.345010109164038e-06,
3348
+ "loss": 0.047,
3349
+ "step": 477
3350
+ },
3351
+ {
3352
+ "epoch": 1.9371196754563895,
3353
+ "grad_norm": 0.36322481811838864,
3354
+ "learning_rate": 9.282980317861188e-06,
3355
+ "loss": 0.0411,
3356
+ "step": 478
3357
+ },
3358
+ {
3359
+ "epoch": 1.9411764705882353,
3360
+ "grad_norm": 0.31572498922793873,
3361
+ "learning_rate": 9.22106469815115e-06,
3362
+ "loss": 0.0302,
3363
+ "step": 479
3364
+ },
3365
+ {
3366
+ "epoch": 1.945233265720081,
3367
+ "grad_norm": 0.3623773378997451,
3368
+ "learning_rate": 9.1592644865182e-06,
3369
+ "loss": 0.043,
3370
+ "step": 480
3371
+ },
3372
+ {
3373
+ "epoch": 1.949290060851927,
3374
+ "grad_norm": 0.35603531168253105,
3375
+ "learning_rate": 9.097580917141862e-06,
3376
+ "loss": 0.0394,
3377
+ "step": 481
3378
+ },
3379
+ {
3380
+ "epoch": 1.9533468559837728,
3381
+ "grad_norm": 0.3298984695320802,
3382
+ "learning_rate": 9.03601522187224e-06,
3383
+ "loss": 0.0382,
3384
+ "step": 482
3385
+ },
3386
+ {
3387
+ "epoch": 1.9574036511156185,
3388
+ "grad_norm": 0.34985337949550965,
3389
+ "learning_rate": 8.974568630205462e-06,
3390
+ "loss": 0.0305,
3391
+ "step": 483
3392
+ },
3393
+ {
3394
+ "epoch": 1.9614604462474645,
3395
+ "grad_norm": 0.37580676659704776,
3396
+ "learning_rate": 8.913242369259076e-06,
3397
+ "loss": 0.0369,
3398
+ "step": 484
3399
+ },
3400
+ {
3401
+ "epoch": 1.9655172413793105,
3402
+ "grad_norm": 0.3578031464742577,
3403
+ "learning_rate": 8.852037663747595e-06,
3404
+ "loss": 0.041,
3405
+ "step": 485
3406
+ },
3407
+ {
3408
+ "epoch": 1.969574036511156,
3409
+ "grad_norm": 0.3055635144638437,
3410
+ "learning_rate": 8.790955735957984e-06,
3411
+ "loss": 0.0298,
3412
+ "step": 486
3413
+ },
3414
+ {
3415
+ "epoch": 1.973630831643002,
3416
+ "grad_norm": 0.4410780953526682,
3417
+ "learning_rate": 8.729997805725305e-06,
3418
+ "loss": 0.0342,
3419
+ "step": 487
3420
+ },
3421
+ {
3422
+ "epoch": 1.977687626774848,
3423
+ "grad_norm": 0.36929913708419226,
3424
+ "learning_rate": 8.669165090408303e-06,
3425
+ "loss": 0.0364,
3426
+ "step": 488
3427
+ },
3428
+ {
3429
+ "epoch": 1.9817444219066938,
3430
+ "grad_norm": 0.32405392390526616,
3431
+ "learning_rate": 8.60845880486516e-06,
3432
+ "loss": 0.0343,
3433
+ "step": 489
3434
+ },
3435
+ {
3436
+ "epoch": 1.9858012170385395,
3437
+ "grad_norm": 0.38038844185366744,
3438
+ "learning_rate": 8.54788016142915e-06,
3439
+ "loss": 0.039,
3440
+ "step": 490
3441
+ },
3442
+ {
3443
+ "epoch": 1.9898580121703855,
3444
+ "grad_norm": 0.3097549740680631,
3445
+ "learning_rate": 8.487430369884497e-06,
3446
+ "loss": 0.0265,
3447
+ "step": 491
3448
+ },
3449
+ {
3450
+ "epoch": 1.9939148073022313,
3451
+ "grad_norm": 0.33837296723283344,
3452
+ "learning_rate": 8.427110637442202e-06,
3453
+ "loss": 0.0423,
3454
+ "step": 492
3455
+ },
3456
+ {
3457
+ "epoch": 1.997971602434077,
3458
+ "grad_norm": 0.7548004728332394,
3459
+ "learning_rate": 8.366922168715907e-06,
3460
+ "loss": 0.0436,
3461
+ "step": 493
3462
+ },
3463
+ {
3464
+ "epoch": 2.0,
3465
+ "grad_norm": 0.3588161803270943,
3466
+ "learning_rate": 8.30686616569786e-06,
3467
+ "loss": 0.0218,
3468
+ "step": 494
3469
+ },
3470
+ {
3471
+ "epoch": 2.004056795131846,
3472
+ "grad_norm": 0.3166650742352506,
3473
+ "learning_rate": 8.246943827734899e-06,
3474
+ "loss": 0.0145,
3475
+ "step": 495
3476
+ },
3477
+ {
3478
+ "epoch": 2.0081135902636915,
3479
+ "grad_norm": 0.29379020109122056,
3480
+ "learning_rate": 8.18715635150453e-06,
3481
+ "loss": 0.0122,
3482
+ "step": 496
3483
+ },
3484
+ {
3485
+ "epoch": 2.0121703853955375,
3486
+ "grad_norm": 0.21926970559190412,
3487
+ "learning_rate": 8.127504930990986e-06,
3488
+ "loss": 0.0128,
3489
+ "step": 497
3490
+ },
3491
+ {
3492
+ "epoch": 2.0162271805273835,
3493
+ "grad_norm": 0.228510859709003,
3494
+ "learning_rate": 8.067990757461406e-06,
3495
+ "loss": 0.0122,
3496
+ "step": 498
3497
+ },
3498
+ {
3499
+ "epoch": 2.020283975659229,
3500
+ "grad_norm": 0.376799062256713,
3501
+ "learning_rate": 8.008615019442046e-06,
3502
+ "loss": 0.0114,
3503
+ "step": 499
3504
+ },
3505
+ {
3506
+ "epoch": 2.024340770791075,
3507
+ "grad_norm": 0.24226554064647018,
3508
+ "learning_rate": 7.94937890269453e-06,
3509
+ "loss": 0.015,
3510
+ "step": 500
3511
  }
3512
  ],
3513
  "logging_steps": 1,
 
3527
  "attributes": {}
3528
  }
3529
  },
3530
+ "total_flos": 3384333165920256.0,
3531
  "train_batch_size": 10,
3532
  "trial_name": null,
3533
  "trial_params": null