Hugging Face's logo

mlfoundations-dev
/
b1_code_top_8_0.3k

Text Generation
Transformers
Safetensors
qwen2
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Model card Files
xet
Community
1
ryanmarten commited on
Commit
bebe361
·
verified ·
1 Parent(s): 387d4e4

Training in progress, epoch 11

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 +6 -0
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:543f9c6225c6035f97887029013ed016cf897747896f26e771fbe346cec1bd8f
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a8bf475f367352998a73d1ad25148f53ad39001238b7551d3c9de5bea52317f9
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:ac9672bfa9b185713457494d9ae1ad4c3d1026750870d8a3d69e568d09ce7d44
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:447f1c7a31e1101803f7f99fc3cf1e25e98502a5303db4193bba0af0b961ad5a
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6c0a0bdddeaab066c4969479caebb97698fa864e810c67445545930005b0a5ee
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c0d73e12b6aaf61d4e030d9aea8c2a5ccb55edaf967b090dff24b59697885a3e
3
  size 4330865200
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9eb2bd2445ce5ba8d40c917fcb34a81eb38c214f35f632f68861b29b3f770778
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49a8f0de59f9d7fc4ac276eddb690a64fb0cc02de660f127f4dae7a642c98b96
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -110,3 +110,9 @@
110
  {"current_steps": 110, "total_steps": 117, "loss": 0.0965, "lr": 1.0926199633097156e-07, "epoch": 11.556962025316455, "percentage": 94.02, "elapsed_time": "0:55:09", "remaining_time": "0:03:30"}
111
  {"current_steps": 111, "total_steps": 117, "loss": 0.0865, "lr": 8.035205700685167e-08, "epoch": 11.658227848101266, "percentage": 94.87, "elapsed_time": "0:55:23", "remaining_time": "0:02:59"}
112
  {"current_steps": 112, "total_steps": 117, "loss": 0.1094, "lr": 5.584586887435739e-08, "epoch": 11.759493670886076, "percentage": 95.73, "elapsed_time": "0:55:46", "remaining_time": "0:02:29"}
 
 
 
 
 
 
 
110
  {"current_steps": 110, "total_steps": 117, "loss": 0.0965, "lr": 1.0926199633097156e-07, "epoch": 11.556962025316455, "percentage": 94.02, "elapsed_time": "0:55:09", "remaining_time": "0:03:30"}
111
  {"current_steps": 111, "total_steps": 117, "loss": 0.0865, "lr": 8.035205700685167e-08, "epoch": 11.658227848101266, "percentage": 94.87, "elapsed_time": "0:55:23", "remaining_time": "0:02:59"}
112
  {"current_steps": 112, "total_steps": 117, "loss": 0.1094, "lr": 5.584586887435739e-08, "epoch": 11.759493670886076, "percentage": 95.73, "elapsed_time": "0:55:46", "remaining_time": "0:02:29"}
113
+ {"current_steps": 113, "total_steps": 117, "loss": 0.1841, "lr": 3.576536829081323e-08, "epoch": 11.860759493670885, "percentage": 96.58, "elapsed_time": "0:56:15", "remaining_time": "0:01:59"}
114
+ {"current_steps": 114, "total_steps": 117, "loss": 0.1457, "lr": 2.012853002380466e-08, "epoch": 11.962025316455696, "percentage": 97.44, "elapsed_time": "0:56:41", "remaining_time": "0:01:29"}
115
+ {"current_steps": 115, "total_steps": 117, "loss": 0.1491, "lr": 8.949351161324227e-09, "epoch": 12.10126582278481, "percentage": 98.29, "elapsed_time": "0:58:04", "remaining_time": "0:01:00"}
116
+ {"current_steps": 116, "total_steps": 117, "loss": 0.1698, "lr": 2.237838582483387e-09, "epoch": 12.20253164556962, "percentage": 99.15, "elapsed_time": "0:58:36", "remaining_time": "0:00:30"}
117
+ {"current_steps": 117, "total_steps": 117, "loss": 0.1431, "lr": 0.0, "epoch": 12.30379746835443, "percentage": 100.0, "elapsed_time": "0:59:02", "remaining_time": "0:00:00"}
118
+ {"current_steps": 117, "total_steps": 117, "epoch": 12.30379746835443, "percentage": 100.0, "elapsed_time": "1:00:39", "remaining_time": "0:00:00"}