Hugging Face's logo

mlfoundations-dev
/
oh_scale_x.25_compute_equal

Text Generation
Transformers
Safetensors
llama
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Model card Files Community
sedrickkeh commited on
Commit
1d0d1f1
·
verified ·
1 Parent(s): 85ee1ac

Training in progress, epoch 44

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 +10 -0
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d9c15d312973250fdbacd3bcc2462a73268b40e39fb805b5108d312a01834642
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf2cdfdf1afd362a70cf4d5f15181d8c42cc91ce927ae85e242a11c7d152eecc
3
  size 4976698672
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9331d431479240a4c61c5ff014dd623336c806d2150b159805dd69244ccf3600
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7cc4fbf210caf48e47a959368cbdcc6b911bd2e64ae4e960603c5a49e65bf0a
3
  size 4999802720
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4be83910ab968fddde390263b92791ebf51b135336b48e245790e1b4072c1de9
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd51e4cbb5d6befed13abc93e1ff40eba46b578e3f4259a012a5c9bc70487bd9
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:b96837dce525da829eda365ea69b1c33e50e9d50ccd95984216bf683876fa960
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:774f5c43af2c62b6596255d1ea39c239b5ef2a0c721ff02ed4b182c64a1b383a
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -430,3 +430,13 @@
430
  {"current_steps": 3870, "total_steps": 4048, "loss": 0.0059, "lr": 5e-06, "epoch": 43.91489361702128, "percentage": 95.6, "elapsed_time": "1 day, 12:35:18", "remaining_time": "1:40:58"}
431
  {"current_steps": 3877, "total_steps": 4048, "eval_loss": 2.413682222366333, "epoch": 43.99432624113475, "percentage": 95.78, "elapsed_time": "1 day, 12:40:18", "remaining_time": "1:37:02"}
432
  {"current_steps": 3880, "total_steps": 4048, "loss": 0.0062, "lr": 5e-06, "epoch": 44.02836879432624, "percentage": 95.85, "elapsed_time": "1 day, 12:43:12", "remaining_time": "1:35:23"}
 
 
 
 
 
 
 
 
 
 
 
430
  {"current_steps": 3870, "total_steps": 4048, "loss": 0.0059, "lr": 5e-06, "epoch": 43.91489361702128, "percentage": 95.6, "elapsed_time": "1 day, 12:35:18", "remaining_time": "1:40:58"}
431
  {"current_steps": 3877, "total_steps": 4048, "eval_loss": 2.413682222366333, "epoch": 43.99432624113475, "percentage": 95.78, "elapsed_time": "1 day, 12:40:18", "remaining_time": "1:37:02"}
432
  {"current_steps": 3880, "total_steps": 4048, "loss": 0.0062, "lr": 5e-06, "epoch": 44.02836879432624, "percentage": 95.85, "elapsed_time": "1 day, 12:43:12", "remaining_time": "1:35:23"}
433
+ {"current_steps": 3890, "total_steps": 4048, "loss": 0.0052, "lr": 5e-06, "epoch": 44.141843971631204, "percentage": 96.1, "elapsed_time": "1 day, 12:48:52", "remaining_time": "1:29:43"}
434
+ {"current_steps": 3900, "total_steps": 4048, "loss": 0.0053, "lr": 5e-06, "epoch": 44.255319148936174, "percentage": 96.34, "elapsed_time": "1 day, 12:54:32", "remaining_time": "1:24:02"}
435
+ {"current_steps": 3910, "total_steps": 4048, "loss": 0.0056, "lr": 5e-06, "epoch": 44.36879432624114, "percentage": 96.59, "elapsed_time": "1 day, 13:00:12", "remaining_time": "1:18:21"}
436
+ {"current_steps": 3920, "total_steps": 4048, "loss": 0.0054, "lr": 5e-06, "epoch": 44.4822695035461, "percentage": 96.84, "elapsed_time": "1 day, 13:05:52", "remaining_time": "1:12:40"}
437
+ {"current_steps": 3930, "total_steps": 4048, "loss": 0.0056, "lr": 5e-06, "epoch": 44.59574468085106, "percentage": 97.08, "elapsed_time": "1 day, 13:11:35", "remaining_time": "1:07:00"}
438
+ {"current_steps": 3940, "total_steps": 4048, "loss": 0.0055, "lr": 5e-06, "epoch": 44.709219858156025, "percentage": 97.33, "elapsed_time": "1 day, 13:17:16", "remaining_time": "1:01:19"}
439
+ {"current_steps": 3950, "total_steps": 4048, "loss": 0.0055, "lr": 5e-06, "epoch": 44.822695035460995, "percentage": 97.58, "elapsed_time": "1 day, 13:22:57", "remaining_time": "0:55:38"}
440
+ {"current_steps": 3960, "total_steps": 4048, "loss": 0.0057, "lr": 5e-06, "epoch": 44.93617021276596, "percentage": 97.83, "elapsed_time": "1 day, 13:28:40", "remaining_time": "0:49:58"}
441
+ {"current_steps": 3965, "total_steps": 4048, "eval_loss": 2.4166228771209717, "epoch": 44.99290780141844, "percentage": 97.95, "elapsed_time": "1 day, 13:32:56", "remaining_time": "0:47:09"}
442
+ {"current_steps": 3970, "total_steps": 4048, "loss": 0.0057, "lr": 5e-06, "epoch": 45.04964539007092, "percentage": 98.07, "elapsed_time": "1 day, 13:36:41", "remaining_time": "0:44:20"}