Hugging Face's logo

flytech
/
gpt-j-6b-devchat

Text Generation
Transformers
PyTorch
TensorBoard
Safetensors
gptj
Generated from Trainer
Model card Files
xet
 Metrics Community
flytech commited on
Commit
cdfbb66
·
1 Parent(s): 9009ea4

Training in progress, step 800, checkpoint

Browse files
Files changed (5) hide show
  1. last-checkpoint/adapter_model.safetensors +1 -1
  2. last-checkpoint/optimizer.pt +1 -1
  3. last-checkpoint/rng_state.pth +1 -1
  4. last-checkpoint/scheduler.pt +1 -1
  5. last-checkpoint/trainer_state.json +16 -3
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0e20e933cc061703253f661e0f6bd388aa33a50d5dcecd9cf3b472c694dd09bc
3
  size 14708920
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:528a1cb84c1fa9945abbc969e94dfcc649bbfcdffde5ed1d0bbfb31a6bc945cf
3
  size 14708920
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3b4d5f4ee881bff263950e2dd32fd230d2ea00dad59ff283198e9206f4238ab1
3
  size 7601989
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7867bb45f4fa0e7f5e4cc0ff28d910219ddfc1fd0301ca0e70a496143cd3e296
3
  size 7601989
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fabb06cac3fcdeaa6b35d148d1969e126efe43d12cb30a04536381719d9de872
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b945e413c47252104d7d309ecd70b494c59b461206abacd8f0ee381044585e6
3
  size 14575
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a71c14414e2ba5216437cae72b785c45cb16736956f3e9e068425fabd7f32a90
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:30b719cdc1f0ed508178a52385f5ad66b1ee8902b555924a5affd41a8c371317
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": 1.1292346298619824,
5
  "eval_steps": 200,
6
- "global_step": 600,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -46,13 +46,26 @@
46
  "eval_samples_per_second": 2.226,
47
  "eval_steps_per_second": 0.279,
48
  "step": 600
 
 
 
 
 
 
 
 
 
 
 
 
 
49
  }
50
  ],
51
  "logging_steps": 200,
52
  "max_steps": 1593,
53
  "num_train_epochs": 3,
54
  "save_steps": 200,
55
- "total_flos": 1.3399863499338547e+17,
56
  "trial_name": null,
57
  "trial_params": null
58
  }
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 1.50564617314931,
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,
 
46
  "eval_samples_per_second": 2.226,
47
  "eval_steps_per_second": 0.279,
48
  "step": 600
49
+ },
50
+ {
51
+ "epoch": 1.51,
52
+ "learning_rate": 2e-05,
53
+ "loss": 0.657,
54
+ "step": 800
55
+ },
56
+ {
57
+ "epoch": 1.51,
58
+ "eval_runtime": 1009.8349,
59
+ "eval_samples_per_second": 2.228,
60
+ "eval_steps_per_second": 0.279,
61
+ "step": 800
62
  }
63
  ],
64
  "logging_steps": 200,
65
  "max_steps": 1593,
66
  "num_train_epochs": 3,
67
  "save_steps": 200,
68
+ "total_flos": 1.7867105116009267e+17,
69
  "trial_name": null,
70
  "trial_params": null
71
  }