Hugging Face's logo

mlfoundations-dev
/
316_globalbatchsize64_lr2e5_epochs15

Text Generation
Transformers
Safetensors
qwen2
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Model card Files Community
sedrickkeh commited on
Commit
31b7c0b
·
verified ·
1 Parent(s): a3f4022

Training in progress, epoch 15

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 +4 -0
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d8a5063f1cd057edd024c6ed92d87fa8ecdfe77b05189b696071d6eb8b973a08
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2750b0110bf64064e668471b8fbc1f46ab842bac6a2bab12f70d249d00a44293
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8400aaf33665cfac0af432cbf924fec70eb160013cbd96300f82831b45c5f473
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:abb2ad0213beb7d386cc1d7bd4ecd64671f50b039cf7eb6bc584a94993c14428
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7378d7b4976b65921264b1741a649175f3061c53c8662e8d837f342592a10b3f
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:979818cdee924f15b21a215b14e946d5e8629c8a6eef558fbe45090a057cd8ad
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:e87997ce3d51519fa0b4712214bce54ef0080edc17a94659edd8e99391ea9845
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9963be85a496ae699ac1e5ae4346a59fe744b3d45979c58b4a7b525e68b52d9d
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -70,3 +70,7 @@
70
  {"current_steps": 70, "total_steps": 75, "loss": 0.0134, "lr": 2.735709467518699e-07, "epoch": 14.0, "percentage": 93.33, "elapsed_time": "1:34:46", "remaining_time": "0:06:46"}
71
  {"current_steps": 71, "total_steps": 75, "loss": 0.0134, "lr": 1.7537457124423896e-07, "epoch": 14.2, "percentage": 94.67, "elapsed_time": "1:36:57", "remaining_time": "0:05:27"}
72
  {"current_steps": 72, "total_steps": 75, "loss": 0.0152, "lr": 9.877485465349057e-08, "epoch": 14.4, "percentage": 96.0, "elapsed_time": "1:37:56", "remaining_time": "0:04:04"}
 
 
 
 
 
70
  {"current_steps": 70, "total_steps": 75, "loss": 0.0134, "lr": 2.735709467518699e-07, "epoch": 14.0, "percentage": 93.33, "elapsed_time": "1:34:46", "remaining_time": "0:06:46"}
71
  {"current_steps": 71, "total_steps": 75, "loss": 0.0134, "lr": 1.7537457124423896e-07, "epoch": 14.2, "percentage": 94.67, "elapsed_time": "1:36:57", "remaining_time": "0:05:27"}
72
  {"current_steps": 72, "total_steps": 75, "loss": 0.0152, "lr": 9.877485465349057e-08, "epoch": 14.4, "percentage": 96.0, "elapsed_time": "1:37:56", "remaining_time": "0:04:04"}
73
+ {"current_steps": 73, "total_steps": 75, "loss": 0.0137, "lr": 4.394017978101905e-08, "epoch": 14.6, "percentage": 97.33, "elapsed_time": "1:39:11", "remaining_time": "0:02:43"}
74
+ {"current_steps": 74, "total_steps": 75, "loss": 0.0161, "lr": 1.099108514288627e-08, "epoch": 14.8, "percentage": 98.67, "elapsed_time": "1:40:16", "remaining_time": "0:01:21"}
75
+ {"current_steps": 75, "total_steps": 75, "loss": 0.0168, "lr": 0.0, "epoch": 15.0, "percentage": 100.0, "elapsed_time": "1:41:33", "remaining_time": "0:00:00"}
76
+ {"current_steps": 75, "total_steps": 75, "epoch": 15.0, "percentage": 100.0, "elapsed_time": "1:44:01", "remaining_time": "0:00:00"}