Hugging Face's logo

mlfoundations-dev
/
d1_math_gpt_1k

Text Generation
Transformers
Safetensors
qwen2
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Model card Files
xet
Community
ryanmarten commited on
Commit
cbcf251
·
verified ·
1 Parent(s): 2d461ae

Training in progress, epoch 6

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 +7 -0
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7d0aefbd1a9b6351f8b831a4f3c7000fdc6ef8992bd5a16de72ba1ace56a88af
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a009749e188aaee7a73d371e52154a5e589386e5c3239d577f64b2f1a47e462d
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0d90698d12730f3ac24aa94646669753e0b4835696c90bd495a5ffb75195ea86
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:940be04624c352f98a98a0c6f975fa6eeeb2d6598af22e2f82d75cb68efb05d1
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8a529f32de9a079aaf8d0febbe9c42ecab277416f29360ce450120011cdf5d64
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ac615c2579621ad3f9d1928e9a9aa5eeac026b247f446e07bd2543339e2674d
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:ae5ab9791daec69d29adbb707ccd194ba6f5df2808eb88003109d7f7fe4ce50f
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0458025ac5d03fbd07ceda71749503bbc1abaa98dd9c8f237d5c903ee6a2c9e2
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -62,3 +62,10 @@
62
  {"current_steps": 62, "total_steps": 70, "loss": 0.3392, "lr": 7.852378812959227e-07, "epoch": 5.952, "percentage": 88.57, "elapsed_time": "1:59:31", "remaining_time": "0:15:25"}
63
  {"current_steps": 63, "total_steps": 70, "loss": 0.3318, "lr": 6.030737921409169e-07, "epoch": 6.048, "percentage": 90.0, "elapsed_time": "2:02:22", "remaining_time": "0:13:35"}
64
  {"current_steps": 64, "total_steps": 70, "loss": 0.3343, "lr": 4.4427194213859216e-07, "epoch": 6.144, "percentage": 91.43, "elapsed_time": "2:04:26", "remaining_time": "0:11:40"}
 
 
 
 
 
 
 
 
62
  {"current_steps": 62, "total_steps": 70, "loss": 0.3392, "lr": 7.852378812959227e-07, "epoch": 5.952, "percentage": 88.57, "elapsed_time": "1:59:31", "remaining_time": "0:15:25"}
63
  {"current_steps": 63, "total_steps": 70, "loss": 0.3318, "lr": 6.030737921409169e-07, "epoch": 6.048, "percentage": 90.0, "elapsed_time": "2:02:22", "remaining_time": "0:13:35"}
64
  {"current_steps": 64, "total_steps": 70, "loss": 0.3343, "lr": 4.4427194213859216e-07, "epoch": 6.144, "percentage": 91.43, "elapsed_time": "2:04:26", "remaining_time": "0:11:40"}
65
+ {"current_steps": 65, "total_steps": 70, "loss": 0.3397, "lr": 3.0922713770922155e-07, "epoch": 6.24, "percentage": 92.86, "elapsed_time": "2:06:10", "remaining_time": "0:09:42"}
66
+ {"current_steps": 66, "total_steps": 70, "loss": 0.3218, "lr": 1.9827512151456175e-07, "epoch": 6.336, "percentage": 94.29, "elapsed_time": "2:08:09", "remaining_time": "0:07:46"}
67
+ {"current_steps": 67, "total_steps": 70, "loss": 0.3173, "lr": 1.1169173774871478e-07, "epoch": 6.432, "percentage": 95.71, "elapsed_time": "2:09:57", "remaining_time": "0:05:49"}
68
+ {"current_steps": 68, "total_steps": 70, "loss": 0.3301, "lr": 4.9692246345985905e-08, "epoch": 6.5280000000000005, "percentage": 97.14, "elapsed_time": "2:11:52", "remaining_time": "0:03:52"}
69
+ {"current_steps": 69, "total_steps": 70, "loss": 0.3322, "lr": 1.2430787810776556e-08, "epoch": 6.624, "percentage": 98.57, "elapsed_time": "2:13:39", "remaining_time": "0:01:56"}
70
+ {"current_steps": 70, "total_steps": 70, "loss": 0.3134, "lr": 0.0, "epoch": 6.72, "percentage": 100.0, "elapsed_time": "2:15:36", "remaining_time": "0:00:00"}
71
+ {"current_steps": 70, "total_steps": 70, "epoch": 6.72, "percentage": 100.0, "elapsed_time": "2:17:29", "remaining_time": "0:00:00"}