Hugging Face's logo

mlfoundations-dev
/
1k_globalbatchsize64_lr1e5_epochs3

Text Generation
Transformers
Safetensors
qwen2
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Model card Files
xet
Community
1
sedrickkeh commited on
Commit
36e4e37
·
verified ·
1 Parent(s): 46da08f

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 +13 -0
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9e950e3acf2df9cdd3c7ddf9fd8d8dd70935bae0edae2501098a0a9bde1b19e5
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:926824db36f3d79305d0bb2129ceecc0e2d913aeca2f1934b3dd7681eb0977de
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9bd8f2394cdae5914fddaf278524a64dc385273326da67884e73d333a01d0646
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c706c280d91c90f688f4e8077579eba03de5107bcf7c6789aba9bd8fbe8c9578
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8dbd528859e3b01fa2e4e8bbe872308ca440ee785ac5cf6bbf90d60696e8c912
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:366de72e49f3e380b3f72c98fa95c0404fab02afbdb7e125e6656a598b1f44cc
3
  size 4330865200
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:11a4950177fdc5ce016fba04c386a442c8d969e78958f1a63613264dd0b4fe09
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78838fba5a55ca16a0eabaf90ef87184f77d18ed214247b9b31833b357c108ba
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -31,3 +31,16 @@
31
  {"current_steps": 31, "total_steps": 45, "loss": 0.8237, "lr": 2.7300475013022666e-06, "epoch": 1.992, "percentage": 68.89, "elapsed_time": "0:34:44", "remaining_time": "0:15:41"}
32
  {"current_steps": 32, "total_steps": 45, "loss": 0.5648, "lr": 2.387507176420256e-06, "epoch": 2.064, "percentage": 71.11, "elapsed_time": "0:36:56", "remaining_time": "0:15:00"}
33
  {"current_steps": 33, "total_steps": 45, "loss": 0.514, "lr": 2.061073738537635e-06, "epoch": 2.128, "percentage": 73.33, "elapsed_time": "0:37:47", "remaining_time": "0:13:44"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
31
  {"current_steps": 31, "total_steps": 45, "loss": 0.8237, "lr": 2.7300475013022666e-06, "epoch": 1.992, "percentage": 68.89, "elapsed_time": "0:34:44", "remaining_time": "0:15:41"}
32
  {"current_steps": 32, "total_steps": 45, "loss": 0.5648, "lr": 2.387507176420256e-06, "epoch": 2.064, "percentage": 71.11, "elapsed_time": "0:36:56", "remaining_time": "0:15:00"}
33
  {"current_steps": 33, "total_steps": 45, "loss": 0.514, "lr": 2.061073738537635e-06, "epoch": 2.128, "percentage": 73.33, "elapsed_time": "0:37:47", "remaining_time": "0:13:44"}
34
+ {"current_steps": 34, "total_steps": 45, "loss": 0.5383, "lr": 1.7527597583490825e-06, "epoch": 2.192, "percentage": 75.56, "elapsed_time": "0:38:58", "remaining_time": "0:12:36"}
35
+ {"current_steps": 35, "total_steps": 45, "loss": 0.5411, "lr": 1.4644660940672628e-06, "epoch": 2.2560000000000002, "percentage": 77.78, "elapsed_time": "0:39:57", "remaining_time": "0:11:25"}
36
+ {"current_steps": 36, "total_steps": 45, "loss": 0.5695, "lr": 1.1979701719998454e-06, "epoch": 2.32, "percentage": 80.0, "elapsed_time": "0:41:00", "remaining_time": "0:10:15"}
37
+ {"current_steps": 37, "total_steps": 45, "loss": 0.5191, "lr": 9.549150281252633e-07, "epoch": 2.384, "percentage": 82.22, "elapsed_time": "0:42:00", "remaining_time": "0:09:04"}
38
+ {"current_steps": 38, "total_steps": 45, "loss": 0.5229, "lr": 7.367991782295392e-07, "epoch": 2.448, "percentage": 84.44, "elapsed_time": "0:43:02", "remaining_time": "0:07:55"}
39
+ {"current_steps": 39, "total_steps": 45, "loss": 0.5372, "lr": 5.449673790581611e-07, "epoch": 2.512, "percentage": 86.67, "elapsed_time": "0:44:18", "remaining_time": "0:06:49"}
40
+ {"current_steps": 40, "total_steps": 45, "loss": 0.5532, "lr": 3.8060233744356634e-07, "epoch": 2.576, "percentage": 88.89, "elapsed_time": "0:45:08", "remaining_time": "0:05:38"}
41
+ {"current_steps": 41, "total_steps": 45, "loss": 0.5248, "lr": 2.447174185242324e-07, "epoch": 2.64, "percentage": 91.11, "elapsed_time": "0:46:19", "remaining_time": "0:04:31"}
42
+ {"current_steps": 42, "total_steps": 45, "loss": 0.5512, "lr": 1.3815039801161723e-07, "epoch": 2.7039999999999997, "percentage": 93.33, "elapsed_time": "0:47:30", "remaining_time": "0:03:23"}
43
+ {"current_steps": 43, "total_steps": 45, "loss": 0.5395, "lr": 6.15582970243117e-08, "epoch": 2.768, "percentage": 95.56, "elapsed_time": "0:48:47", "remaining_time": "0:02:16"}
44
+ {"current_steps": 44, "total_steps": 45, "loss": 0.4979, "lr": 1.541333133436018e-08, "epoch": 2.832, "percentage": 97.78, "elapsed_time": "0:49:45", "remaining_time": "0:01:07"}
45
+ {"current_steps": 45, "total_steps": 45, "loss": 0.552, "lr": 0.0, "epoch": 2.896, "percentage": 100.0, "elapsed_time": "0:50:43", "remaining_time": "0:00:00"}
46
+ {"current_steps": 45, "total_steps": 45, "epoch": 2.896, "percentage": 100.0, "elapsed_time": "0:53:04", "remaining_time": "0:00:00"}