Hugging Face's logo

mlfoundations-dev
/
hp_ablations_grid_mistral_bsz4096_lr5e-6_scheduler-cosine-warmup0.15-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
e197c1f
·
verified ·
1 Parent(s): 6323e3a

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 sha256:5b3b7357104233c1c7bf5b0cb3529dc59a1e867b47a590d972e96d07cd6db992
3
  size 4943162336
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5862fd12ad654e9b46b620c6e1260996106fe51e4a0566747954e42ffff7412d
3
  size 4943162336
model-00002-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8cb6440181d9474a472266b14b5340db3c3096d72451e7ff6341e5b63eee63fa
3
  size 4999819336
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b90b5c70703fc9a29130d2136cfad75fd6946e6254b4e9cc010c2ba8bb1a7142
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:b763ac547d46a82d997b04574ca84c53f4768adee696aea04d62e3d6b6d0b5f7
3
  size 4540516344
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:972bd34dc13b46ee22ea73be5e332b81cf1c8c73ed0d964edbd65b4944c8722c
3
  size 4540516344
trainer_log.jsonl CHANGED
@@ -17,3 +17,13 @@
17
  {"current_steps": 160, "total_steps": 252, "loss": 0.4675, "lr": 2.258533022500071e-06, "epoch": 1.9047619047619047, "percentage": 63.49, "elapsed_time": "2:36:19", "remaining_time": "1:29:53"}
18
  {"current_steps": 168, "total_steps": 252, "eval_loss": 0.06080044060945511, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "2:45:30", "remaining_time": "1:22:45"}
19
  {"current_steps": 170, "total_steps": 252, "loss": 0.4609, "lr": 1.9426443142839448e-06, "epoch": 2.0238095238095237, "percentage": 67.46, "elapsed_time": "2:48:09", "remaining_time": "1:21:06"}
 
 
 
 
 
 
 
 
 
 
 
17
  {"current_steps": 160, "total_steps": 252, "loss": 0.4675, "lr": 2.258533022500071e-06, "epoch": 1.9047619047619047, "percentage": 63.49, "elapsed_time": "2:36:19", "remaining_time": "1:29:53"}
18
  {"current_steps": 168, "total_steps": 252, "eval_loss": 0.06080044060945511, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "2:45:30", "remaining_time": "1:22:45"}
19
  {"current_steps": 170, "total_steps": 252, "loss": 0.4609, "lr": 1.9426443142839448e-06, "epoch": 2.0238095238095237, "percentage": 67.46, "elapsed_time": "2:48:09", "remaining_time": "1:21:06"}
20
+ {"current_steps": 180, "total_steps": 252, "loss": 0.4413, "lr": 1.6441238936454482e-06, "epoch": 2.142857142857143, "percentage": 71.43, "elapsed_time": "2:57:47", "remaining_time": "1:11:07"}
21
+ {"current_steps": 190, "total_steps": 252, "loss": 0.4393, "lr": 1.369393699025314e-06, "epoch": 2.261904761904762, "percentage": 75.4, "elapsed_time": "3:07:25", "remaining_time": "1:01:09"}
22
+ {"current_steps": 200, "total_steps": 252, "loss": 0.4354, "lr": 1.1243638802011956e-06, "epoch": 2.380952380952381, "percentage": 79.37, "elapsed_time": "3:17:03", "remaining_time": "0:51:14"}
23
+ {"current_steps": 210, "total_steps": 252, "loss": 0.4341, "lr": 9.143056558363464e-07, "epoch": 2.5, "percentage": 83.33, "elapsed_time": "3:26:41", "remaining_time": "0:41:20"}
24
+ {"current_steps": 220, "total_steps": 252, "loss": 0.4356, "lr": 7.437379160722046e-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": 0.4342, "lr": 6.163300096333806e-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": 0.4331, "lr": 5.348228067433014e-07, "epoch": 2.857142857142857, "percentage": 95.24, "elapsed_time": "3:55:33", "remaining_time": "0:11:46"}
27
+ {"current_steps": 250, "total_steps": 252, "loss": 0.4307, "lr": 5.009697359892537e-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": 0.059506773948669434, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "4:09:19", "remaining_time": "0:00:00"}
29
+ {"current_steps": 252, "total_steps": 252, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "4:09:58", "remaining_time": "0:00:00"}