Hugging Face's logo

mlfoundations-dev
/
llama3-1_8b_mlfoundations-dev-stackoverflow_25000tasks_1p

Text Generation
Transformers
Safetensors
llama
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Model card Files Community
EtashGuha commited on
Commit
1a50e67
·
verified ·
1 Parent(s): 6332ee4

Training in progress, epoch 3

Browse files
Files changed (6) 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 +5 -9
  6. training_args.bin +2 -2
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4231e4567e18667c3147949495a0a2e863e4a6575efd1e363559862ebe4277fd
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db390fa89d3e2f85fe9ea31482fb88738737678a54b00d984444de3299b39ef3
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:c691ce51a99c4a9e6f012127704bb67c140c6a16b9161cb7dd9a3184f19851a9
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae733ffa12de8901a4670087f6791f0a9b6e9dd8a120a8dbe2109dc3c4ac9d11
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:eef8841a0e77eacfb71ab553abefcf8196ad3f551266c06abb234a88399f3d0f
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9dc20a92c953c78a3725d3b4f277bedd663b97c14ca019c6862db44c61b3a005
3
  size 4915916176
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:618cca11d8e36ba513b0aa1819b86f492af3f9ff898829ded2f2fa9f2ecf77f6
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f73accac27fd813960d7ded9eaef147608f112a14172d31fe0344c054d8da770
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -1,9 +1,5 @@
1
- {"current_steps": 10, "total_steps": 105, "loss": 0.996, "lr": 5e-06, "epoch": 0.2857142857142857, "percentage": 9.52, "elapsed_time": "0:26:07", "remaining_time": "4:08:11"}
2
- {"current_steps": 20, "total_steps": 105, "loss": 0.8944, "lr": 5e-06, "epoch": 0.5714285714285714, "percentage": 19.05, "elapsed_time": "0:52:04", "remaining_time": "3:41:20"}
3
- {"current_steps": 30, "total_steps": 105, "loss": 0.8572, "lr": 5e-06, "epoch": 0.8571428571428571, "percentage": 28.57, "elapsed_time": "1:18:33", "remaining_time": "3:16:24"}
4
- {"current_steps": 35, "total_steps": 105, "eval_loss": 0.8312200307846069, "epoch": 1.0, "percentage": 33.33, "elapsed_time": "1:33:36", "remaining_time": "3:07:12"}
5
- {"current_steps": 40, "total_steps": 105, "loss": 0.8205, "lr": 5e-06, "epoch": 1.1428571428571428, "percentage": 38.1, "elapsed_time": "1:48:01", "remaining_time": "2:55:32"}
6
- {"current_steps": 50, "total_steps": 105, "loss": 0.792, "lr": 5e-06, "epoch": 1.4285714285714286, "percentage": 47.62, "elapsed_time": "2:14:02", "remaining_time": "2:27:26"}
7
- {"current_steps": 60, "total_steps": 105, "loss": 0.7814, "lr": 5e-06, "epoch": 1.7142857142857144, "percentage": 57.14, "elapsed_time": "2:40:03", "remaining_time": "2:00:02"}
8
- {"current_steps": 70, "total_steps": 105, "loss": 0.7768, "lr": 5e-06, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "3:06:04", "remaining_time": "1:33:02"}
9
- {"current_steps": 70, "total_steps": 105, "eval_loss": 0.8017017245292664, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "3:07:54", "remaining_time": "1:33:57"}
 
1
+ {"current_steps": 80, "total_steps": 105, "loss": 0.723, "lr": 5e-06, "epoch": 2.2857142857142856, "percentage": 76.19, "elapsed_time": "0:27:00", "remaining_time": "0:08:26"}
2
+ {"current_steps": 90, "total_steps": 105, "loss": 0.7163, "lr": 5e-06, "epoch": 2.571428571428571, "percentage": 85.71, "elapsed_time": "0:53:10", "remaining_time": "0:08:51"}
3
+ {"current_steps": 100, "total_steps": 105, "loss": 0.7145, "lr": 5e-06, "epoch": 2.857142857142857, "percentage": 95.24, "elapsed_time": "1:19:17", "remaining_time": "0:03:57"}
4
+ {"current_steps": 105, "total_steps": 105, "eval_loss": 0.7955389618873596, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "1:35:49", "remaining_time": "0:00:00"}
5
+ {"current_steps": 105, "total_steps": 105, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "1:36:46", "remaining_time": "0:00:00"}
 
 
 
 
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:59986cacbb9382d955bc0ab7d8baf052b77ebc8fff47509045b6b4ab4ae9c7b3
3
- size 7288
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95c1f0bf07a2e328cf99e487ad2f2bb7e4cae2f445a3ad420fd49f530ae83915
3
+ size 7480