Hugging Face's logo

mlfoundations-dev
/
llama3-1_8b_mlfoundations-dev-stackexchange_quantumcomputing

Text Generation
Transformers
Safetensors
llama
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Model card Files Community
EtashGuha commited on
Commit
8c0bf6e
·
verified ·
1 Parent(s): 35f3466

Training in progress, epoch 1

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 +3 -0
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ea1f8a157be65124e588467838f205d761864551e5e396dfae2ada4b9ebe86d2
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96b6623dbdfcce2c2f81cdbf17e557661baf1a60d478276170044eeea4458643
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:b784d02b97e6a2b3007dbd03c7e3680695d40f1295dfe17307832c209c8a5598
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b638390605fd71504bb42cefa13a5474c3635e9f886721a88030a2f0efc333d
3
  size 4999802720
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:99a5ab05291478e90fd5385bacee813e0c5edf184dc3cf864963800e6ada26ac
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d89d98e1c0b77e3dd65a44e2ecb26e2f5d9a702a32f36fbea903398a784e7d47
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:b82897bf92abc2b04092343d4104344f8844d20ead91ff89a741166c26f58ecf
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de45aae9df896155672fa71a7990c1fff03467ba7437897f013b9ce2a4a353cf
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -1,3 +1,6 @@
1
  {"current_steps": 10, "total_steps": 60, "loss": 0.9931, "lr": 5e-06, "epoch": 0.49230769230769234, "percentage": 16.67, "elapsed_time": "0:24:07", "remaining_time": "2:00:36"}
2
  {"current_steps": 20, "total_steps": 60, "loss": 0.9091, "lr": 5e-06, "epoch": 0.9846153846153847, "percentage": 33.33, "elapsed_time": "0:48:11", "remaining_time": "1:36:22"}
3
  {"current_steps": 20, "total_steps": 60, "eval_loss": 0.8879945278167725, "epoch": 0.9846153846153847, "percentage": 33.33, "elapsed_time": "0:49:53", "remaining_time": "1:39:46"}
 
 
 
 
1
  {"current_steps": 10, "total_steps": 60, "loss": 0.9931, "lr": 5e-06, "epoch": 0.49230769230769234, "percentage": 16.67, "elapsed_time": "0:24:07", "remaining_time": "2:00:36"}
2
  {"current_steps": 20, "total_steps": 60, "loss": 0.9091, "lr": 5e-06, "epoch": 0.9846153846153847, "percentage": 33.33, "elapsed_time": "0:48:11", "remaining_time": "1:36:22"}
3
  {"current_steps": 20, "total_steps": 60, "eval_loss": 0.8879945278167725, "epoch": 0.9846153846153847, "percentage": 33.33, "elapsed_time": "0:49:53", "remaining_time": "1:39:46"}
4
+ {"current_steps": 30, "total_steps": 60, "loss": 0.8464, "lr": 5e-06, "epoch": 1.476923076923077, "percentage": 50.0, "elapsed_time": "1:13:48", "remaining_time": "1:13:48"}
5
+ {"current_steps": 40, "total_steps": 60, "loss": 0.8243, "lr": 5e-06, "epoch": 1.9692307692307693, "percentage": 66.67, "elapsed_time": "1:37:03", "remaining_time": "0:48:31"}
6
+ {"current_steps": 40, "total_steps": 60, "eval_loss": 0.840017557144165, "epoch": 1.9692307692307693, "percentage": 66.67, "elapsed_time": "1:39:25", "remaining_time": "0:49:42"}