Hugging Face's logo

mlfoundations-dev
/
llama2_oh_teknium_scaling_down_random_0.3

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
3adb2e5
•
1 Parent(s): 6052b37

Training in progress, epoch 2

Browse files
Files changed (4) hide show
  1. model-00001-of-00003.safetensors +1 -1
  2. model-00002-of-00003.safetensors +1 -1
  3. model-00003-of-00003.safetensors +1 -1
  4. trainer_log.jsonl +14 -0
model-00001-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f04cd5c5635e1e12a21d2bdca8b80a3c7fc566d02f6805de36f1e28b68475ddf
3
  size 4938985352
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:246d37d0c41fb0d3e308fa2f554fefa7f141206f05cc1ff07537183582fa1883
3
  size 4938985352
model-00002-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f8916961aa9cb7280bf8f9201445808a69d82824c221dd72ebe20874a537c438
3
  size 4947390880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c26bf42c9bf9c0b44ef533443d34d5c3412148d599ffd057290fb6974f7ae30
3
  size 4947390880
model-00003-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fa56db8d950e99b336b36242091b12fb5b2014983e89ac14431c2b366d836d49
3
  size 3590488816
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79761116b23a0c77cd134e2b7fc5ba239c56cf898002e32fcafa47919253b3c1
3
  size 3590488816
trainer_log.jsonl CHANGED
@@ -24,3 +24,17 @@
24
  {"current_steps": 230, "total_steps": 360, "loss": 0.491, "lr": 5e-06, "epoch": 1.908713692946058, "percentage": 63.89, "elapsed_time": "3:29:53", "remaining_time": "1:58:38"}
25
  {"current_steps": 240, "total_steps": 360, "loss": 0.4901, "lr": 5e-06, "epoch": 1.991701244813278, "percentage": 66.67, "elapsed_time": "3:38:53", "remaining_time": "1:49:26"}
26
  {"current_steps": 241, "total_steps": 360, "eval_loss": 0.5045989155769348, "epoch": 2.0, "percentage": 66.94, "elapsed_time": "3:41:45", "remaining_time": "1:49:29"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
24
  {"current_steps": 230, "total_steps": 360, "loss": 0.491, "lr": 5e-06, "epoch": 1.908713692946058, "percentage": 63.89, "elapsed_time": "3:29:53", "remaining_time": "1:58:38"}
25
  {"current_steps": 240, "total_steps": 360, "loss": 0.4901, "lr": 5e-06, "epoch": 1.991701244813278, "percentage": 66.67, "elapsed_time": "3:38:53", "remaining_time": "1:49:26"}
26
  {"current_steps": 241, "total_steps": 360, "eval_loss": 0.5045989155769348, "epoch": 2.0, "percentage": 66.94, "elapsed_time": "3:41:45", "remaining_time": "1:49:29"}
27
+ {"current_steps": 250, "total_steps": 360, "loss": 0.4945, "lr": 5e-06, "epoch": 2.074688796680498, "percentage": 69.44, "elapsed_time": "3:50:51", "remaining_time": "1:41:34"}
28
+ {"current_steps": 260, "total_steps": 360, "loss": 0.4617, "lr": 5e-06, "epoch": 2.1576763485477177, "percentage": 72.22, "elapsed_time": "3:59:50", "remaining_time": "1:32:14"}
29
+ {"current_steps": 270, "total_steps": 360, "loss": 0.4648, "lr": 5e-06, "epoch": 2.240663900414938, "percentage": 75.0, "elapsed_time": "4:08:51", "remaining_time": "1:22:57"}
30
+ {"current_steps": 280, "total_steps": 360, "loss": 0.4688, "lr": 5e-06, "epoch": 2.323651452282158, "percentage": 77.78, "elapsed_time": "4:17:50", "remaining_time": "1:13:40"}
31
+ {"current_steps": 290, "total_steps": 360, "loss": 0.46, "lr": 5e-06, "epoch": 2.4066390041493775, "percentage": 80.56, "elapsed_time": "4:26:50", "remaining_time": "1:04:24"}
32
+ {"current_steps": 300, "total_steps": 360, "loss": 0.4679, "lr": 5e-06, "epoch": 2.4896265560165975, "percentage": 83.33, "elapsed_time": "4:35:51", "remaining_time": "0:55:10"}
33
+ {"current_steps": 310, "total_steps": 360, "loss": 0.4642, "lr": 5e-06, "epoch": 2.572614107883817, "percentage": 86.11, "elapsed_time": "4:44:51", "remaining_time": "0:45:56"}
34
+ {"current_steps": 320, "total_steps": 360, "loss": 0.4597, "lr": 5e-06, "epoch": 2.6556016597510372, "percentage": 88.89, "elapsed_time": "4:53:52", "remaining_time": "0:36:44"}
35
+ {"current_steps": 330, "total_steps": 360, "loss": 0.4617, "lr": 5e-06, "epoch": 2.7385892116182573, "percentage": 91.67, "elapsed_time": "5:02:53", "remaining_time": "0:27:32"}
36
+ {"current_steps": 340, "total_steps": 360, "loss": 0.4597, "lr": 5e-06, "epoch": 2.821576763485477, "percentage": 94.44, "elapsed_time": "5:11:53", "remaining_time": "0:18:20"}
37
+ {"current_steps": 350, "total_steps": 360, "loss": 0.4545, "lr": 5e-06, "epoch": 2.904564315352697, "percentage": 97.22, "elapsed_time": "5:20:55", "remaining_time": "0:09:10"}
38
+ {"current_steps": 360, "total_steps": 360, "loss": 0.4618, "lr": 5e-06, "epoch": 2.987551867219917, "percentage": 100.0, "elapsed_time": "5:29:55", "remaining_time": "0:00:00"}
39
+ {"current_steps": 360, "total_steps": 360, "eval_loss": 0.49428611993789673, "epoch": 2.987551867219917, "percentage": 100.0, "elapsed_time": "5:32:57", "remaining_time": "0:00:00"}
40
+ {"current_steps": 360, "total_steps": 360, "epoch": 2.987551867219917, "percentage": 100.0, "elapsed_time": "5:34:00", "remaining_time": "0:00:00"}