flytech commited on
Commit
fb957cd
·
1 Parent(s): 56e2bf4

Training in progress, step 1000, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:155b53f85365e9cf1a7178999397de9c728e2ff0b6e854a4d032226d05738e9b
3
  size 250422888
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e7b3ab78feaf72624f5c9d091dde8319bfbfa85c31e775dd9f99fbce2ad479d6
3
  size 250422888
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ec296342722d66b25ca019efda9529b79679288561f484f8ae43237a3ac48c92
3
  size 126034975
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ecf2e0a9b1a4b1904b4e740c1f81802741f5c215265df997f074115d2d8c8ec
3
  size 126034975
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c6ba1362912a8bc94ac2dddadec969cbdfaae88f02e0687f51e3f3c3aee75913
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e414c911760872e6234869f5ca2da36336ed18d14a1a8258cd3f51489c940e22
3
  size 14575
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:de7840bcb72f2f480fd301578d289cdfa174589e831b0d33e5772f3956b6beae
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3bb7339d1d2da342a44f3ba5e076fb6e5d93aee86f890c002703d2b3a0750820
3
  size 627
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 2.6058631921824107,
5
  "eval_steps": 200,
6
- "global_step": 800,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -59,13 +59,26 @@
59
  "eval_samples_per_second": 4.006,
60
  "eval_steps_per_second": 0.132,
61
  "step": 800
 
 
 
 
 
 
 
 
 
 
 
 
 
62
  }
63
  ],
64
  "logging_steps": 200,
65
  "max_steps": 1535,
66
  "num_train_epochs": 5,
67
  "save_steps": 200,
68
- "total_flos": 1.01366266724352e+18,
69
  "trial_name": null,
70
  "trial_params": null
71
  }
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 3.257328990228013,
5
  "eval_steps": 200,
6
+ "global_step": 1000,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
59
  "eval_samples_per_second": 4.006,
60
  "eval_steps_per_second": 0.132,
61
  "step": 800
62
+ },
63
+ {
64
+ "epoch": 3.26,
65
+ "learning_rate": 0.0002,
66
+ "loss": 0.0973,
67
+ "step": 1000
68
+ },
69
+ {
70
+ "epoch": 3.26,
71
+ "eval_runtime": 128.7836,
72
+ "eval_samples_per_second": 4.007,
73
+ "eval_steps_per_second": 0.132,
74
+ "step": 1000
75
  }
76
  ],
77
  "logging_steps": 200,
78
  "max_steps": 1535,
79
  "num_train_epochs": 5,
80
  "save_steps": 200,
81
+ "total_flos": 1.26658241298432e+18,
82
  "trial_name": null,
83
  "trial_params": null
84
  }