Hugging Face's logo

mlfoundations-dev
/
oh_scale_x.125_compute_equal

Text Generation
Transformers
Safetensors
llama
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Model card Files
xet
Community
sedrickkeh commited on
Commit
98af927
·
verified ·
1 Parent(s): f41365e

Training in progress, epoch 80

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 sha256:3f8ee349fa758afe45d8d90b3d0ce54ed65df755c01bcf34c44afb7831b462f0
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56fd6de91bc0c8300866de58997749bbc1ea31979f4918a8c348eecce6dcb35a
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:ed37d7c5ecc5ab7666e0e1ad06a0398f9a1f2ccdc23dd26be3e88272a7bd517b
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41731f02b2c1834d94df9c6a816b43e9a0e89aa4d20fe8be31d5aadbd2f3f5df
3
  size 4999802720
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:079d12f03040d3b9021a71d0b59836d0e9dd8cd92bbbb11d1b4f1a0b63a78dca
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5238f712a717ac6846964a31afd25dc326c11063549c109b60b2c157818815a4
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:d1ef42f571c64f2b74e5fe30b52e55f55667cd42f5f3ca2ad48e8b4fc0df2c35
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:35219238a0f7b97cd36afd46b3fd30f2f99d44438bad6e1fabec2d065f694840
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -455,3 +455,9 @@
455
  {"current_steps": 3760, "total_steps": 4183, "loss": 0.0034, "lr": 5e-06, "epoch": 79.78779840848806, "percentage": 89.89, "elapsed_time": "1 day, 12:09:45", "remaining_time": "4:04:05"}
456
  {"current_steps": 3770, "total_steps": 4183, "loss": 0.0035, "lr": 5e-06, "epoch": 80.0, "percentage": 90.13, "elapsed_time": "1 day, 12:15:13", "remaining_time": "3:58:17"}
457
  {"current_steps": 3770, "total_steps": 4183, "eval_loss": 2.0766139030456543, "epoch": 80.0, "percentage": 90.13, "elapsed_time": "1 day, 12:15:49", "remaining_time": "3:58:21"}
 
 
 
 
 
 
 
455
  {"current_steps": 3760, "total_steps": 4183, "loss": 0.0034, "lr": 5e-06, "epoch": 79.78779840848806, "percentage": 89.89, "elapsed_time": "1 day, 12:09:45", "remaining_time": "4:04:05"}
456
  {"current_steps": 3770, "total_steps": 4183, "loss": 0.0035, "lr": 5e-06, "epoch": 80.0, "percentage": 90.13, "elapsed_time": "1 day, 12:15:13", "remaining_time": "3:58:17"}
457
  {"current_steps": 3770, "total_steps": 4183, "eval_loss": 2.0766139030456543, "epoch": 80.0, "percentage": 90.13, "elapsed_time": "1 day, 12:15:49", "remaining_time": "3:58:21"}
458
+ {"current_steps": 3780, "total_steps": 4183, "loss": 0.003, "lr": 5e-06, "epoch": 80.21220159151194, "percentage": 90.37, "elapsed_time": "1 day, 12:22:40", "remaining_time": "3:52:42"}
459
+ {"current_steps": 3790, "total_steps": 4183, "loss": 0.0035, "lr": 5e-06, "epoch": 80.42440318302387, "percentage": 90.6, "elapsed_time": "1 day, 12:28:01", "remaining_time": "3:46:53"}
460
+ {"current_steps": 3800, "total_steps": 4183, "loss": 0.0033, "lr": 5e-06, "epoch": 80.63660477453581, "percentage": 90.84, "elapsed_time": "1 day, 12:33:22", "remaining_time": "3:41:04"}
461
+ {"current_steps": 3810, "total_steps": 4183, "loss": 0.0033, "lr": 5e-06, "epoch": 80.84880636604774, "percentage": 91.08, "elapsed_time": "1 day, 12:38:42", "remaining_time": "3:35:15"}
462
+ {"current_steps": 3817, "total_steps": 4183, "eval_loss": 2.028625011444092, "epoch": 80.9973474801061, "percentage": 91.25, "elapsed_time": "1 day, 12:43:02", "remaining_time": "3:31:14"}
463
+ {"current_steps": 3820, "total_steps": 4183, "loss": 0.0035, "lr": 5e-06, "epoch": 81.06100795755968, "percentage": 91.32, "elapsed_time": "1 day, 12:46:04", "remaining_time": "3:29:38"}