flytech commited on
Commit
7f3e895
1 Parent(s): c0ec1a0

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 sha256:15b521fcb15385d1918536ac3c39b9f1d14122fd26694b28733b39d871cec929
3
  size 250422888
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37a81150462de1f5724816fc86eeb72708fdd41c2b9120a6c0fb0893e25e26a2
3
  size 250422888
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2bb170ed70180ed94328a739c6d7decbc6085fc6c9b7cf7df0f0fba3ef12e99b
3
  size 126034975
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b9b872563bae5226150d141d2458c477cc4944f5e1ef6209dfe23ed474e91ae
3
  size 126034975
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:234214404756568863f28a4eaac76b522ea0357e31db5dbccac728a1e475cb06
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:104cbb095e211a3aa51312000d657ebbe612e28bb6e9115038fb06d9d13e1bb5
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": 2.150537634408602,
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": 2.752,
60
  "eval_steps_per_second": 0.176,
61
  "step": 800
 
 
 
 
 
 
 
 
 
 
 
 
 
62
  }
63
  ],
64
  "logging_steps": 200,
65
  "max_steps": 2232,
66
  "num_train_epochs": 6,
67
  "save_steps": 200,
68
- "total_flos": 3.810843639558144e+17,
69
  "trial_name": null,
70
  "trial_params": null
71
  }
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 2.688172043010753,
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": 2.752,
60
  "eval_steps_per_second": 0.176,
61
  "step": 800
62
+ },
63
+ {
64
+ "epoch": 2.69,
65
+ "learning_rate": 0.0002,
66
+ "loss": 0.0418,
67
+ "step": 1000
68
+ },
69
+ {
70
+ "epoch": 2.69,
71
+ "eval_runtime": 113.7299,
72
+ "eval_samples_per_second": 2.752,
73
+ "eval_steps_per_second": 0.176,
74
+ "step": 1000
75
  }
76
  ],
77
  "logging_steps": 200,
78
  "max_steps": 2232,
79
  "num_train_epochs": 6,
80
  "save_steps": 200,
81
+ "total_flos": 4.764597717970944e+17,
82
  "trial_name": null,
83
  "trial_params": null
84
  }