Hugging Face's logo

mlfoundations-dev
/
oh_v1-2_only_evol_instruct

Text Generation
Transformers
Safetensors
llama
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Model card Files
xet
Community
esfrankel17 commited on
Commit
0dde0bd
·
verified ·
1 Parent(s): 91b9efe

Training in progress, epoch 2

Browse files
Files changed (5) hide show
  1. model-00001-of-00004.safetensors +1 -1
  2. model-00002-of-00004.safetensors +1 -1
  3. model-00003-of-00004.safetensors +1 -1
  4. model-00004-of-00004.safetensors +1 -1
  5. trainer_log.jsonl +3 -0
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:12f66d9579fe829f3238198aa1d2653740b38af732d6ffabf05feebf3eb3864f
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd8375c299cd303703eaa82d93dcb12a6166fddebeb767b6ed8e68b804d4f58d
3
  size 4976698672
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8f38e20637b52749450b99e02e32f8e71cf9f9967d46c9b4e77d641ef9ea1185
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:703e26711abc4d6ac566e22495ef15af12b8d04ba3730483ab905e16895ee6d0
3
  size 4999802720
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:30089c8c72478b2f312e1b4ec48d156f8d653f2f11bc836f5f052278080a3e87
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:31cb0c129728363d39cdbb9a62d99bdb872cc6d0fa532fd642944fcf2ab51f85
3
  size 4915916176
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a7e22c64259c2eeb28dc57e8efe4eaf0112810b7786a84f5c5b1bd3e6d4ef0e2
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1632dbea5cfca5ad2d186b81bbcb0d471d4d772744c2396d600160ba8742fdc0
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -1,3 +1,6 @@
1
  {"current_steps": 10, "total_steps": 69, "loss": 1.0498, "learning_rate": 5e-06, "epoch": 0.43478260869565216, "percentage": 14.49, "elapsed_time": "0:45:10", "remaining_time": "4:26:30"}
2
  {"current_steps": 20, "total_steps": 69, "loss": 0.9524, "learning_rate": 5e-06, "epoch": 0.8695652173913043, "percentage": 28.99, "elapsed_time": "1:30:18", "remaining_time": "3:41:15"}
3
  {"current_steps": 23, "total_steps": 69, "eval_loss": 0.9243873357772827, "epoch": 1.0, "percentage": 33.33, "elapsed_time": "1:44:46", "remaining_time": "3:29:33"}
 
 
 
 
1
  {"current_steps": 10, "total_steps": 69, "loss": 1.0498, "learning_rate": 5e-06, "epoch": 0.43478260869565216, "percentage": 14.49, "elapsed_time": "0:45:10", "remaining_time": "4:26:30"}
2
  {"current_steps": 20, "total_steps": 69, "loss": 0.9524, "learning_rate": 5e-06, "epoch": 0.8695652173913043, "percentage": 28.99, "elapsed_time": "1:30:18", "remaining_time": "3:41:15"}
3
  {"current_steps": 23, "total_steps": 69, "eval_loss": 0.9243873357772827, "epoch": 1.0, "percentage": 33.33, "elapsed_time": "1:44:46", "remaining_time": "3:29:33"}
4
+ {"current_steps": 30, "total_steps": 69, "loss": 0.9035, "learning_rate": 5e-06, "epoch": 1.3043478260869565, "percentage": 43.48, "elapsed_time": "2:17:38", "remaining_time": "2:58:56"}
5
+ {"current_steps": 40, "total_steps": 69, "loss": 0.8651, "learning_rate": 5e-06, "epoch": 1.7391304347826086, "percentage": 57.97, "elapsed_time": "3:02:47", "remaining_time": "2:12:31"}
6
+ {"current_steps": 46, "total_steps": 69, "eval_loss": 0.889980673789978, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "3:30:48", "remaining_time": "1:45:24"}