Hugging Face's logo

sedrickkeh
/
checkpoints

Text Generation
Transformers
Safetensors
gemma2
llama-factory
full
trl
dpo
Generated from Trainer
conversational
text-generation-inference
Model card Files
xet
 Community
sedrickkeh commited on
Commit
16ba6cf
·
verified ·
1 Parent(s): b6e5f96

Model save

Browse files
Files changed (16) hide show
  1. README.md +2 -0
  2. README.md.sagemaker-uploaded +0 -0
  3. all_results.json +12 -0
  4. all_results.json.sagemaker-uploaded +0 -0
  5. eval_results.json +7 -0
  6. eval_results.json.sagemaker-uploaded +0 -0
  7. model-00001-of-00003.safetensors +1 -1
  8. model-00002-of-00003.safetensors +1 -1
  9. model-00003-of-00003.safetensors +1 -1
  10. train_results.json +8 -0
  11. train_results.json.sagemaker-uploaded +0 -0
  12. trainer_state.json +50 -0
  13. trainer_state.json.sagemaker-uploaded +0 -0
  14. training_args.bin +1 -1
  15. training_eval_loss.png +0 -0
  16. training_eval_loss.png.sagemaker-uploaded +0 -0
README.md CHANGED
@@ -16,6 +16,8 @@ should probably proofread and complete it, then remove this comment. -->
16
  # checkpoints
17
 
18
  This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on an unknown dataset.
 
 
19
 
20
  ## Model description
21
 
 
16
  # checkpoints
17
 
18
  This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on an unknown dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 1.6953
21
 
22
  ## Model description
23
 
README.md.sagemaker-uploaded ADDED
File without changes
all_results.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 0.13043478260869565,
3
+ "eval_loss": 1.6952797174453735,
4
+ "eval_runtime": 2.2512,
5
+ "eval_samples_per_second": 274.076,
6
+ "eval_steps_per_second": 4.442,
7
+ "total_flos": 3.355230384370483e+16,
8
+ "train_loss": 1.4136702219645183,
9
+ "train_runtime": 204.3723,
10
+ "train_samples_per_second": 7.516,
11
+ "train_steps_per_second": 0.015
12
+ }
all_results.json.sagemaker-uploaded ADDED
File without changes
eval_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 0.13043478260869565,
3
+ "eval_loss": 1.6952797174453735,
4
+ "eval_runtime": 2.2512,
5
+ "eval_samples_per_second": 274.076,
6
+ "eval_steps_per_second": 4.442
7
+ }
eval_results.json.sagemaker-uploaded ADDED
File without changes
model-00001-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7ee6b0483c655c8f927d85233354ec5564188ee19f414da0ec1b0636888e345a
3
  size 4943162336
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:370eaa5179722f54e74f081398b3a7d40e1233daee98192d4ec14b278a8c0f76
3
  size 4943162336
model-00002-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0d63400f39bfaa3b510c6d6d01336ce8ee448d93ae03ed5c27bfadf7085d146c
3
  size 4999819336
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d432155046b2c474b4e47bb4876fb47d214736dc45fb388cd803b026cbbcb06
3
  size 4999819336
model-00003-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:04b95ab745ac9310c4ee740598a5c987c13d70ad061d019e5515001e01f01c6a
3
  size 4540516344
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f593d9685e3919788f1bbdb9c787e48f9ae37c349ed10796b146267a2d55e906
3
  size 4540516344
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 0.13043478260869565,
3
+ "total_flos": 3.355230384370483e+16,
4
+ "train_loss": 1.4136702219645183,
5
+ "train_runtime": 204.3723,
6
+ "train_samples_per_second": 7.516,
7
+ "train_steps_per_second": 0.015
8
+ }
train_results.json.sagemaker-uploaded ADDED
File without changes
trainer_state.json ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.13043478260869565,
5
+ "eval_steps": 500,
6
+ "global_step": 3,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.13043478260869565,
13
+ "eval_loss": 1.6952797174453735,
14
+ "eval_runtime": 1.8822,
15
+ "eval_samples_per_second": 327.804,
16
+ "eval_steps_per_second": 5.313,
17
+ "step": 3
18
+ },
19
+ {
20
+ "epoch": 0.13043478260869565,
21
+ "step": 3,
22
+ "total_flos": 3.355230384370483e+16,
23
+ "train_loss": 1.4136702219645183,
24
+ "train_runtime": 204.3723,
25
+ "train_samples_per_second": 7.516,
26
+ "train_steps_per_second": 0.015
27
+ }
28
+ ],
29
+ "logging_steps": 10,
30
+ "max_steps": 3,
31
+ "num_input_tokens_seen": 0,
32
+ "num_train_epochs": 1,
33
+ "save_steps": 500,
34
+ "stateful_callbacks": {
35
+ "TrainerControl": {
36
+ "args": {
37
+ "should_epoch_stop": false,
38
+ "should_evaluate": false,
39
+ "should_log": false,
40
+ "should_save": true,
41
+ "should_training_stop": true
42
+ },
43
+ "attributes": {}
44
+ }
45
+ },
46
+ "total_flos": 3.355230384370483e+16,
47
+ "train_batch_size": 16,
48
+ "trial_name": null,
49
+ "trial_params": null
50
+ }
trainer_state.json.sagemaker-uploaded ADDED
File without changes
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b004b8ecc53af2f5aa6018afbdcfb055134bdd973aa4067e4e5f1da512ed7679
3
  size 6520
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:441bf1d619e881a2104e88d655daeeb8872b3ba8a79f41c69e024e0d02716a9e
3
  size 6520
training_eval_loss.png ADDED
training_eval_loss.png.sagemaker-uploaded ADDED
File without changes