Hugging Face's logo

mlfoundations-dev
/
hp_ablations_grid_mistral_bsz4096_lr2e-6_scheduler-cosine-warmup0.05-minlr5e-7

Text Generation
Transformers
Safetensors
mistral
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
sedrickkeh commited on
Commit
1de4551
•
1 Parent(s): aa55706

Training in progress, epoch 3

Browse files
Files changed (4) hide show
  1. model-00001-of-00003.safetensors +1 -1
  2. model-00002-of-00003.safetensors +1 -1
  3. model-00003-of-00003.safetensors +1 -1
  4. trainer_log.jsonl +10 -0
model-00001-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ab13e1704a9cb36cc3a3b935743198e33f6514183e5281d822fb58d615ecb199
3
  size 4943162336
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bfd763f0231826e51ac7e54e0911bf5ae01e570c9795057e74ff41f1eaea634f
3
  size 4943162336
model-00002-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:37242f21d72ecd2f26430efedf2792a71db332d1e1c09132601721fcf2f44346
3
  size 4999819336
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df6939c56e5f29e9d52f574ae114dce1d6528885a52a29b3483f1b80831b4432
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:bf8eddd9dfbb3f82219322451203cef900f4276b9efe993def622160f74f8fda
3
  size 4540516344
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:001b9905cf095e9e315216f2642bb8285e1895e24b29b859744a40699c3bf9cd
3
  size 4540516344
trainer_log.jsonl CHANGED
@@ -17,3 +17,13 @@
17
  {"current_steps": 160, "total_steps": 252, "loss": 0.4983, "lr": 9.847555404323228e-07, "epoch": 1.9047619047619047, "percentage": 63.49, "elapsed_time": "2:36:21", "remaining_time": "1:29:54"}
18
  {"current_steps": 168, "total_steps": 252, "eval_loss": 0.06357834488153458, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "2:45:31", "remaining_time": "1:22:45"}
19
  {"current_steps": 170, "total_steps": 252, "loss": 0.4937, "lr": 8.95094683294048e-07, "epoch": 2.0238095238095237, "percentage": 67.46, "elapsed_time": "2:48:11", "remaining_time": "1:21:07"}
 
 
 
 
 
 
 
 
 
 
 
17
  {"current_steps": 160, "total_steps": 252, "loss": 0.4983, "lr": 9.847555404323228e-07, "epoch": 1.9047619047619047, "percentage": 63.49, "elapsed_time": "2:36:21", "remaining_time": "1:29:54"}
18
  {"current_steps": 168, "total_steps": 252, "eval_loss": 0.06357834488153458, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "2:45:31", "remaining_time": "1:22:45"}
19
  {"current_steps": 170, "total_steps": 252, "loss": 0.4937, "lr": 8.95094683294048e-07, "epoch": 2.0238095238095237, "percentage": 67.46, "elapsed_time": "2:48:11", "remaining_time": "1:21:07"}
20
+ {"current_steps": 180, "total_steps": 252, "loss": 0.4823, "lr": 8.115572036276285e-07, "epoch": 2.142857142857143, "percentage": 71.43, "elapsed_time": "2:57:48", "remaining_time": "1:11:07"}
21
+ {"current_steps": 190, "total_steps": 252, "loss": 0.4802, "lr": 7.355844197142121e-07, "epoch": 2.261904761904762, "percentage": 75.4, "elapsed_time": "3:07:25", "remaining_time": "1:01:09"}
22
+ {"current_steps": 200, "total_steps": 252, "loss": 0.4761, "lr": 6.684871319605308e-07, "epoch": 2.380952380952381, "percentage": 79.37, "elapsed_time": "3:17:03", "remaining_time": "0:51:14"}
23
+ {"current_steps": 210, "total_steps": 252, "loss": 0.4746, "lr": 6.114230069354231e-07, "epoch": 2.5, "percentage": 83.33, "elapsed_time": "3:26:40", "remaining_time": "0:41:20"}
24
+ {"current_steps": 220, "total_steps": 252, "loss": 0.4764, "lr": 5.653766035090493e-07, "epoch": 2.619047619047619, "percentage": 87.3, "elapsed_time": "3:36:18", "remaining_time": "0:31:27"}
25
+ {"current_steps": 230, "total_steps": 252, "loss": 0.4747, "lr": 5.311423857148533e-07, "epoch": 2.738095238095238, "percentage": 91.27, "elapsed_time": "3:45:56", "remaining_time": "0:21:36"}
26
+ {"current_steps": 240, "total_steps": 252, "loss": 0.4734, "lr": 5.093110154227483e-07, "epoch": 2.857142857142857, "percentage": 95.24, "elapsed_time": "3:55:34", "remaining_time": "0:11:46"}
27
+ {"current_steps": 250, "total_steps": 252, "loss": 0.4707, "lr": 5.002591613236042e-07, "epoch": 2.9761904761904763, "percentage": 99.21, "elapsed_time": "4:05:11", "remaining_time": "0:01:57"}
28
+ {"current_steps": 252, "total_steps": 252, "eval_loss": 0.062153831124305725, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "4:09:21", "remaining_time": "0:00:00"}
29
+ {"current_steps": 252, "total_steps": 252, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "4:10:00", "remaining_time": "0:00:00"}