Hugging Face's logo

flytech
/
togetherchat-dev-7b-v2

Text Generation
Transformers
PyTorch
TensorBoard
Safetensors
llama
Generated from Trainer
custom_code
text-generation-inference
Inference Endpoints
Model card Files Metrics Community
flytech commited on
Commit
cdecb83
•
1 Parent(s): 61b315a

Training in progress, step 400, checkpoint

Browse files
Files changed (6) 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 +17 -4
  6. last-checkpoint/training_args.bin +1 -1
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2e6cb7b4410cc9cb0084c7612cd4022f1deadf4ce55184f92fad73533c9e1d83
3
  size 40036040
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a7350375367de3d48a10e538a3050879e84b503b1959b0da7d0093feff845ef
3
  size 40036040
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d873e36c2fa59d6fa81c53bb037fa037211b5695b7a1ba48627b95393c5339a8
3
  size 21689885
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac19d3254e40752761ab54fe9665797707ac9761808e7a3784806260e52a9aa5
3
  size 21689885
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4593038e9fdb437086616d5c111b9636ca11131f8522c47b7dac4f9725e19849
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3eff52dc2b3b2759571223ff2e3ae868f8526d54b024b4d241353e192ef8ecfc
3
  size 14575
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:aa5aed090b001ddf62e969f8c3bdc8dc6e8972eaa9b18bd7770ed94cd8aac3ac
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78e928409b4775b7365d3492e3e7a2c02ce0e27b01495617e60e25eba9ee51dc
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": 0.13333333333333333,
5
  "eval_steps": 100,
6
- "global_step": 300,
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": 1.779,
47
  "eval_steps_per_second": 0.223,
48
  "step": 300
 
 
 
 
 
 
 
 
 
 
 
 
 
49
  }
50
  ],
51
  "logging_steps": 100,
52
- "max_steps": 6750,
53
  "num_train_epochs": 3,
54
  "save_steps": 100,
55
- "total_flos": 7.68217505071104e+16,
56
  "trial_name": null,
57
  "trial_params": null
58
  }
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.7111111111111111,
5
  "eval_steps": 100,
6
+ "global_step": 400,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
46
  "eval_samples_per_second": 1.779,
47
  "eval_steps_per_second": 0.223,
48
  "step": 300
49
+ },
50
+ {
51
+ "epoch": 0.71,
52
+ "learning_rate": 0.0001,
53
+ "loss": 0.6162,
54
+ "step": 400
55
+ },
56
+ {
57
+ "epoch": 0.71,
58
+ "eval_runtime": 1408.649,
59
+ "eval_samples_per_second": 1.775,
60
+ "eval_steps_per_second": 0.222,
61
+ "step": 400
62
  }
63
  ],
64
  "logging_steps": 100,
65
+ "max_steps": 1686,
66
  "num_train_epochs": 3,
67
  "save_steps": 100,
68
+ "total_flos": 1.183470210514944e+17,
69
  "trial_name": null,
70
  "trial_params": null
71
  }
last-checkpoint/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cfc879f829e293a0970e4937e200624ca05a1bbcda40ccf332847f1be93ea7fb
3
  size 4027
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c7a5b1bc80c24e0650a1b3d844796825e1fb9e3e5503b2ad01dc469f57f7630
3
  size 4027