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
3adffb6
•
1 Parent(s): 43e4f1b

Training in progress, step 1000, 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 +16 -3
  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 sha256:7928893400b46dcb29642a403c24b8f22b024fddc25b60538a31c85c1ad8865b
3
  size 40036040
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f00956cad5b242d28d69ef7f923e91b71ba0e20a0414975ebf772dd8e9f57161
3
  size 40036040
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1086fe9363f82aec5d220614e79a6fc2421d31fe34ca1c9fa9612a1c28fc43ba
3
  size 21689885
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57a9fdefbec929aa5b96d3138d9e4e530cab3e268afb55db0aaf843cc8c9e4c9
3
  size 21689885
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9c31fdd7bc052e2da00f42fa4208407109642b65360d36af47981ba37b94fb7b
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4907f2830ba6f2777cd22e1a2deb95c664e378deb1ca91ebe14c24ed9b4dbb72
3
  size 14575
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:41ec64ba9e76742780de858ce14668285049f1680bae66c1352aa2d20d3be491
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a1969c6d78c022e21e37f015f4d4c5f85f6638038ce809e096a3a6a48192ec9d
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": 1.6,
5
  "eval_steps": 100,
6
- "global_step": 900,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -124,13 +124,26 @@
124
  "eval_samples_per_second": 1.782,
125
  "eval_steps_per_second": 0.223,
126
  "step": 900
 
 
 
 
 
 
 
 
 
 
 
 
 
127
  }
128
  ],
129
  "logging_steps": 100,
130
  "max_steps": 1686,
131
  "num_train_epochs": 3,
132
  "save_steps": 100,
133
- "total_flos": 3.259733737734144e+17,
134
  "trial_name": null,
135
  "trial_params": null
136
  }
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 1.7786666666666666,
5
  "eval_steps": 100,
6
+ "global_step": 1000,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
124
  "eval_samples_per_second": 1.782,
125
  "eval_steps_per_second": 0.223,
126
  "step": 900
127
+ },
128
+ {
129
+ "epoch": 1.78,
130
+ "learning_rate": 4.5352669742913644e-05,
131
+ "loss": 0.5422,
132
+ "step": 1000
133
+ },
134
+ {
135
+ "epoch": 1.78,
136
+ "eval_runtime": 1405.4811,
137
+ "eval_samples_per_second": 1.779,
138
+ "eval_steps_per_second": 0.223,
139
+ "step": 1000
140
  }
141
  ],
142
  "logging_steps": 100,
143
  "max_steps": 1686,
144
  "num_train_epochs": 3,
145
  "save_steps": 100,
146
+ "total_flos": 3.674986443177984e+17,
147
  "trial_name": null,
148
  "trial_params": null
149
  }
last-checkpoint/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4c7a5b1bc80c24e0650a1b3d844796825e1fb9e3e5503b2ad01dc469f57f7630
3
  size 4027
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b70405a73c4fcdb106d1d45a297270d5842bf95dec19efac48fa6e39c2b6cac8
3
  size 4027