Hugging Face's logo

mlfoundations-dev
/
llama3-1_8b_webinstruct_750k

Text Generation
Transformers
Safetensors
llama
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Model card Files
xet
 Community
gsmyrnis commited on
Commit
c51d7d0
·
verified ·
1 Parent(s): 19b103a

Training in progress, epoch 2

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 +11 -0
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9ef7c4a9dc6128494ff26ae796fbf21cde4d0ef25a45d7654e46750e08c4cd9e
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d9afe66544c6437ea435af8c6108f648bd0f9fe9a1da163f6121ce650a94167e
3
  size 4976698672
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7e1adcdc5d9f5d8b348b32e8d82745efc37c6064c2ebe928638b892b8eaced4a
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:11e49571d5ca4eeb0001921b93fee7dc8529107997bfd65bb51fb7453957d92f
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:d00193cb2c9ac3a42ade6a91529e9915dbafb759dd20e69412a6074e780c914f
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56a7e543d4706507626f86f72205192715a42a09a75f11e832f275cabda928ac
3
  size 4915916176
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8340f86cc4b1c9b1d343ef42f1e99b73ac7520519d8627160c96d529c5da3069
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:11433614fd936a70c1d5ef9767de04ace78359acca7d7518309c824057bfbba3
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -11,3 +11,14 @@
11
  {"current_steps": 100, "total_steps": 300, "eval_loss": 0.9628956317901611, "epoch": 1.0, "percentage": 33.33, "elapsed_time": "0:10:00", "remaining_time": "0:20:00"}
12
  {"current_steps": 110, "total_steps": 300, "loss": 0.9153, "learning_rate": 5e-06, "epoch": 1.1, "percentage": 36.67, "elapsed_time": "0:12:24", "remaining_time": "0:21:25"}
13
  {"current_steps": 120, "total_steps": 300, "loss": 0.9161, "learning_rate": 5e-06, "epoch": 1.2, "percentage": 40.0, "elapsed_time": "0:13:22", "remaining_time": "0:20:03"}
 
 
 
 
 
 
 
 
 
 
 
 
11
  {"current_steps": 100, "total_steps": 300, "eval_loss": 0.9628956317901611, "epoch": 1.0, "percentage": 33.33, "elapsed_time": "0:10:00", "remaining_time": "0:20:00"}
12
  {"current_steps": 110, "total_steps": 300, "loss": 0.9153, "learning_rate": 5e-06, "epoch": 1.1, "percentage": 36.67, "elapsed_time": "0:12:24", "remaining_time": "0:21:25"}
13
  {"current_steps": 120, "total_steps": 300, "loss": 0.9161, "learning_rate": 5e-06, "epoch": 1.2, "percentage": 40.0, "elapsed_time": "0:13:22", "remaining_time": "0:20:03"}
14
+ {"current_steps": 130, "total_steps": 300, "loss": 0.9052, "learning_rate": 5e-06, "epoch": 1.3, "percentage": 43.33, "elapsed_time": "0:14:22", "remaining_time": "0:18:47"}
15
+ {"current_steps": 140, "total_steps": 300, "loss": 0.9066, "learning_rate": 5e-06, "epoch": 1.4, "percentage": 46.67, "elapsed_time": "0:15:21", "remaining_time": "0:17:33"}
16
+ {"current_steps": 150, "total_steps": 300, "loss": 0.9017, "learning_rate": 5e-06, "epoch": 1.5, "percentage": 50.0, "elapsed_time": "0:16:20", "remaining_time": "0:16:20"}
17
+ {"current_steps": 160, "total_steps": 300, "loss": 0.8985, "learning_rate": 5e-06, "epoch": 1.6, "percentage": 53.33, "elapsed_time": "0:17:19", "remaining_time": "0:15:09"}
18
+ {"current_steps": 170, "total_steps": 300, "loss": 0.9017, "learning_rate": 5e-06, "epoch": 1.7, "percentage": 56.67, "elapsed_time": "0:18:19", "remaining_time": "0:14:00"}
19
+ {"current_steps": 180, "total_steps": 300, "loss": 0.8965, "learning_rate": 5e-06, "epoch": 1.8, "percentage": 60.0, "elapsed_time": "0:19:18", "remaining_time": "0:12:52"}
20
+ {"current_steps": 190, "total_steps": 300, "loss": 0.897, "learning_rate": 5e-06, "epoch": 1.9, "percentage": 63.33, "elapsed_time": "0:20:17", "remaining_time": "0:11:44"}
21
+ {"current_steps": 200, "total_steps": 300, "loss": 0.8934, "learning_rate": 5e-06, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "0:21:16", "remaining_time": "0:10:38"}
22
+ {"current_steps": 200, "total_steps": 300, "eval_loss": 0.9496641159057617, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "0:21:26", "remaining_time": "0:10:43"}
23
+ {"current_steps": 210, "total_steps": 300, "loss": 0.8388, "learning_rate": 5e-06, "epoch": 2.1, "percentage": 70.0, "elapsed_time": "0:24:10", "remaining_time": "0:10:21"}
24
+ {"current_steps": 220, "total_steps": 300, "loss": 0.8356, "learning_rate": 5e-06, "epoch": 2.2, "percentage": 73.33, "elapsed_time": "0:25:08", "remaining_time": "0:09:08"}