Hugging Face's logo

mlfoundations-dev
/
stackexchange_philosophy

Text Generation
Transformers
Safetensors
llama
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Model card Files Community
sedrickkeh commited on
Commit
99d0b52
·
verified ·
1 Parent(s): 4b5eb63

Training in progress, epoch 3

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 +5 -0
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e41a153efbf7014e9cc426096c717375a4dd829ae1ac8b830edd217831a63d5c
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c4ad4ebb5ef6c4e1f54d8ea6a2b33a65fb59808610bf16576eab064c60e9623
3
  size 4976698672
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9d61e73b4d8ff24e13a5a4a0aced993c9ffb5f5fb8b3a16f8a5a386edb0e35ce
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1054ba90b2cf62caa5e032c6b195614e951be66dadaa50d64ee4f50e6ce71fba
3
  size 4999802720
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:512cac94484c9cc6fc92680286d357e1f4b50ec028eb94f6fe83c817feb4f60e
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2bc3b8bfb5bb7d8730d6a3b425f7fd72df7046520cb32d877e391f8203cc4599
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:d4a8b3993d06556d08bd78b73e6a529b87923017c1958169076d86a4ebdc6e56
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b8a2eaf80a729ea32363562e6667a2b62efb7fe84334eea8164fb9007a7935b
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -6,3 +6,8 @@
6
  {"current_steps": 50, "total_steps": 99, "loss": 0.992, "lr": 5e-06, "epoch": 1.5151515151515151, "percentage": 50.51, "elapsed_time": "0:28:33", "remaining_time": "0:27:59"}
7
  {"current_steps": 60, "total_steps": 99, "loss": 0.9788, "lr": 5e-06, "epoch": 1.8181818181818183, "percentage": 60.61, "elapsed_time": "0:33:54", "remaining_time": "0:22:02"}
8
  {"current_steps": 66, "total_steps": 99, "eval_loss": 0.9927644729614258, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "0:37:30", "remaining_time": "0:18:45"}
 
 
 
 
 
 
6
  {"current_steps": 50, "total_steps": 99, "loss": 0.992, "lr": 5e-06, "epoch": 1.5151515151515151, "percentage": 50.51, "elapsed_time": "0:28:33", "remaining_time": "0:27:59"}
7
  {"current_steps": 60, "total_steps": 99, "loss": 0.9788, "lr": 5e-06, "epoch": 1.8181818181818183, "percentage": 60.61, "elapsed_time": "0:33:54", "remaining_time": "0:22:02"}
8
  {"current_steps": 66, "total_steps": 99, "eval_loss": 0.9927644729614258, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "0:37:30", "remaining_time": "0:18:45"}
9
+ {"current_steps": 70, "total_steps": 99, "loss": 0.9522, "lr": 5e-06, "epoch": 2.121212121212121, "percentage": 70.71, "elapsed_time": "0:41:04", "remaining_time": "0:17:00"}
10
+ {"current_steps": 80, "total_steps": 99, "loss": 0.9176, "lr": 5e-06, "epoch": 2.4242424242424243, "percentage": 80.81, "elapsed_time": "0:46:25", "remaining_time": "0:11:01"}
11
+ {"current_steps": 90, "total_steps": 99, "loss": 0.9123, "lr": 5e-06, "epoch": 2.7272727272727275, "percentage": 90.91, "elapsed_time": "0:51:47", "remaining_time": "0:05:10"}
12
+ {"current_steps": 99, "total_steps": 99, "eval_loss": 0.9767674207687378, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "0:58:29", "remaining_time": "0:00:00"}
13
+ {"current_steps": 99, "total_steps": 99, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "0:59:57", "remaining_time": "0:00:00"}