FormlessAI commited on
Commit
b136a99
·
verified ·
1 Parent(s): 28b17ab

Training in progress, epoch 3, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:944b6f22219a69d2695b1a5505b1595bc8c31ee2e66f22558a3fc6731a6585cf
3
  size 98088784
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79a74eface560a0d41d5e7193ececeda2cc88e07b85a0f131a7894a8c39c362c
3
  size 98088784
last-checkpoint/global_step3851/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 sha256:9fc6eef99cd48fd3bc2ed23dd9cfd3bb5baac5d71f7e1ec89ef4c45da7ca331d
3
+ size 73939813
last-checkpoint/global_step3851/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 sha256:07766c096cf500b4162c9dd1877c56fb6fc3f87c562ed089c7433c107bdff9fc
3
+ size 73939813
last-checkpoint/global_step3851/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 sha256:2fa27dee49ca0aac2129f497f1794f7e5446dbdb9e28247560f6ff2f36d6f2c2
3
+ size 73939877
last-checkpoint/global_step3851/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 sha256:67cde1093d143f538e650405908d4f9078adee036dd846ddacf71e29b2fd8a25
3
+ size 73939877
last-checkpoint/global_step3851/mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:811bf35c88ba06cea1c99ec602ca8143d9c73c9f671f870c9f08761819472227
3
+ size 564993061
last-checkpoint/latest CHANGED
@@ -1 +1 @@
1
- global_step3801
 
1
+ global_step3851
last-checkpoint/rng_state_0.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1a0e146edb1dd3f6ce8b95cdff5c6843e2baf0e41e3a44e36adaa70c9840cd49
3
  size 15429
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f8c4661cc8e3497c9dcc889e209837bc166321280810d1a0551c92c53bfdf4c
3
  size 15429
last-checkpoint/rng_state_1.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:30bfb3289f4b9f74faa1e15a82011098f2c1933b3f53b17359ea97a5fc11971e
3
  size 15429
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:627a6e765cdcbbf90b02e79df2177ac4639598c9fdcf297f4abfa4613bd417ac
3
  size 15429
last-checkpoint/rng_state_2.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9dd2bf542367f789abac3b0c3014e034a30538d2038e253bfe90d348bd7dc7c4
3
  size 15429
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:570f3d0203f97fe8aa9eef4ef51705c39955af6a291650decf2a16306fc2c37e
3
  size 15429
last-checkpoint/rng_state_3.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d1e2d97378fdd248b93104f94fcb505f43648f8d6300031aa7ab0759476bf33b
3
  size 15429
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ffc58f196a2233ab090012942dd37b4bd389e6f32ec590748ee94264f276c726
3
  size 15429
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:17bce8da61b43ce028a996a56e88e7fae5c06117bdb3d24146bd7503a4488b87
3
  size 1401
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c5cc97fbaa125ff18c9216f0408fc93d4996c91f171f312f5071297f73584f1
3
  size 1401
last-checkpoint/trainer_state.json CHANGED
@@ -1,10 +1,10 @@
1
  {
2
  "best_global_step": null,
3
- "best_metric": 0.6101014018058777,
4
  "best_model_checkpoint": null,
5
- "epoch": 3.7250459277403554,
6
  "eval_steps": 50,
7
- "global_step": 3800,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -5936,6 +5936,84 @@
5936
  "eval_samples_per_second": 122.974,
5937
  "eval_steps_per_second": 15.38,
5938
  "step": 3800
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5939
  }
5940
  ],
5941
  "logging_steps": 5,
@@ -5964,7 +6042,7 @@
5964
  "attributes": {}
5965
  }
5966
  },
5967
- "total_flos": 1.9594150539123753e+18,
5968
  "train_batch_size": 2,
5969
  "trial_name": null,
5970
  "trial_params": null
 
1
  {
2
  "best_global_step": null,
3
+ "best_metric": 0.6094754934310913,
4
  "best_model_checkpoint": null,
5
+ "epoch": 3.7740355174525413,
6
  "eval_steps": 50,
7
+ "global_step": 3850,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
5936
  "eval_samples_per_second": 122.974,
5937
  "eval_steps_per_second": 15.38,
5938
  "step": 3800
5939
+ },
5940
+ {
5941
+ "epoch": 3.7299448867115736,
5942
+ "grad_norm": 0.24481558799743652,
5943
+ "learning_rate": 1.5504355572295863e-05,
5944
+ "loss": 0.6353,
5945
+ "step": 3805
5946
+ },
5947
+ {
5948
+ "epoch": 3.7348438456827924,
5949
+ "grad_norm": 0.22643239796161652,
5950
+ "learning_rate": 1.5381340835126955e-05,
5951
+ "loss": 0.6205,
5952
+ "step": 3810
5953
+ },
5954
+ {
5955
+ "epoch": 3.739742804654011,
5956
+ "grad_norm": 0.22124996781349182,
5957
+ "learning_rate": 1.5258737337609558e-05,
5958
+ "loss": 0.6337,
5959
+ "step": 3815
5960
+ },
5961
+ {
5962
+ "epoch": 3.7446417636252294,
5963
+ "grad_norm": 0.18295590579509735,
5964
+ "learning_rate": 1.5136546339684282e-05,
5965
+ "loss": 0.666,
5966
+ "step": 3820
5967
+ },
5968
+ {
5969
+ "epoch": 3.749540722596448,
5970
+ "grad_norm": 0.22296933829784393,
5971
+ "learning_rate": 1.5014769097052723e-05,
5972
+ "loss": 0.6344,
5973
+ "step": 3825
5974
+ },
5975
+ {
5976
+ "epoch": 3.754439681567667,
5977
+ "grad_norm": 0.22792081534862518,
5978
+ "learning_rate": 1.489340686116442e-05,
5979
+ "loss": 0.6536,
5980
+ "step": 3830
5981
+ },
5982
+ {
5983
+ "epoch": 3.7593386405388856,
5984
+ "grad_norm": 0.2205907255411148,
5985
+ "learning_rate": 1.4772460879204163e-05,
5986
+ "loss": 0.6234,
5987
+ "step": 3835
5988
+ },
5989
+ {
5990
+ "epoch": 3.7642375995101043,
5991
+ "grad_norm": 0.24228990077972412,
5992
+ "learning_rate": 1.4651932394079013e-05,
5993
+ "loss": 0.6366,
5994
+ "step": 3840
5995
+ },
5996
+ {
5997
+ "epoch": 3.7691365584813226,
5998
+ "grad_norm": 0.2280125916004181,
5999
+ "learning_rate": 1.453182264440566e-05,
6000
+ "loss": 0.6307,
6001
+ "step": 3845
6002
+ },
6003
+ {
6004
+ "epoch": 3.7740355174525413,
6005
+ "grad_norm": 0.22570735216140747,
6006
+ "learning_rate": 1.4412132864497621e-05,
6007
+ "loss": 0.6433,
6008
+ "step": 3850
6009
+ },
6010
+ {
6011
+ "epoch": 3.7740355174525413,
6012
+ "eval_loss": 0.6094754934310913,
6013
+ "eval_runtime": 15.5627,
6014
+ "eval_samples_per_second": 125.878,
6015
+ "eval_steps_per_second": 15.743,
6016
+ "step": 3850
6017
  }
6018
  ],
6019
  "logging_steps": 5,
 
6042
  "attributes": {}
6043
  }
6044
  },
6045
+ "total_flos": 1.9855768094244864e+18,
6046
  "train_batch_size": 2,
6047
  "trial_name": null,
6048
  "trial_params": null