Hugging Face's logo

mlfoundations-dev
/
evol_tt_2s

Text Generation
Transformers
Safetensors
llama
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
sedrickkeh commited on
Commit
7923c61
·
verified ·
1 Parent(s): 4616138

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 +4 -0
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:54848b76b0f58e8f09b9939229f873fecd3dad13124b3e6103b9b31004487c07
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef1d77589f38e4b0b62ac3966dbdffaf887a8170f3cd04047f72dbf3f3be3c1a
3
  size 4976698672
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:59c36a996e0a655bd806b4c73834182463fc8e59eee5d33ab03d269f6950318c
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:124ce9954e9f901bf6d0b7e72f374dfe450bdebbc739e79d6dccc583dca9e55e
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:ca489291ded2ba7e31716d0f6b4a2b5d56bc3487c57c67e6596bde0c61257216
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a571e8b5953df8a2653398556f994dd8980bbfd7d581b99b33e46ccccd68b254
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:e67c1544dc43f3a984421e814c7af57bdc0ca90b832a546f092655b3bae76b11
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b5a4b047029b36251403d2042afdccee266e59ccb21f1f5993d6cd7ddbb4740
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -2,3 +2,7 @@
2
  {"current_steps": 20, "total_steps": 87, "loss": 1.1268, "lr": 5e-06, "epoch": 0.6779661016949152, "percentage": 22.99, "elapsed_time": "0:19:09", "remaining_time": "1:04:10"}
3
  {"current_steps": 29, "total_steps": 87, "eval_loss": 1.0789530277252197, "epoch": 0.9830508474576272, "percentage": 33.33, "elapsed_time": "0:28:44", "remaining_time": "0:57:29"}
4
  {"current_steps": 30, "total_steps": 87, "loss": 1.1342, "lr": 5e-06, "epoch": 1.0169491525423728, "percentage": 34.48, "elapsed_time": "0:30:22", "remaining_time": "0:57:43"}
 
 
 
 
 
2
  {"current_steps": 20, "total_steps": 87, "loss": 1.1268, "lr": 5e-06, "epoch": 0.6779661016949152, "percentage": 22.99, "elapsed_time": "0:19:09", "remaining_time": "1:04:10"}
3
  {"current_steps": 29, "total_steps": 87, "eval_loss": 1.0789530277252197, "epoch": 0.9830508474576272, "percentage": 33.33, "elapsed_time": "0:28:44", "remaining_time": "0:57:29"}
4
  {"current_steps": 30, "total_steps": 87, "loss": 1.1342, "lr": 5e-06, "epoch": 1.0169491525423728, "percentage": 34.48, "elapsed_time": "0:30:22", "remaining_time": "0:57:43"}
5
+ {"current_steps": 40, "total_steps": 87, "loss": 1.0292, "lr": 5e-06, "epoch": 1.3559322033898304, "percentage": 45.98, "elapsed_time": "0:39:55", "remaining_time": "0:46:54"}
6
+ {"current_steps": 50, "total_steps": 87, "loss": 1.015, "lr": 5e-06, "epoch": 1.694915254237288, "percentage": 57.47, "elapsed_time": "0:49:27", "remaining_time": "0:36:35"}
7
+ {"current_steps": 59, "total_steps": 87, "eval_loss": 1.044095754623413, "epoch": 2.0, "percentage": 67.82, "elapsed_time": "0:58:28", "remaining_time": "0:27:45"}
8
+ {"current_steps": 60, "total_steps": 87, "loss": 1.0548, "lr": 5e-06, "epoch": 2.0338983050847457, "percentage": 68.97, "elapsed_time": "1:00:36", "remaining_time": "0:27:16"}