Hugging Face's logo

mlfoundations-dev
/
a1_science_stackexchange_physics_1k

Text Generation
Transformers
Safetensors
qwen2
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Model card Files
xet
Community
sedrickkeh commited on
Commit
5c9d05c
·
verified ·
1 Parent(s): e516f22

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 +10 -0
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f1a734d457a573f1ad8218b40c9a7cfb78d6f06244213702dd4df408c8cc1b53
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc81739891d66892d7e43f1542b909319c4653934cbfd7e2c6d9d40c40f48111
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5802e89cd07f28584fb1788ea43cd961e692c79c54d5518677d6a995b711321b
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af524f63f6a2919813484f1dfcc1ad6a8ff102839bd008b51050f8fec3018c7e
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1088501e3db5e44415498d562a6d43d716d0af8411d034a09c0e74e1082ba663
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bcdb745772050ce777312feec9a4cf68ca5d53470cfe087e14b252055db1f803
3
  size 4330865200
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:21e971a790fa729e866526e8e1ab91ad20eb8cc27e2df9b2e537be3d381376a1
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5c230166c7d5a00c8ce9f5e0caf1e918c3de57478589ce60a384bb5f61820a1
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -14,3 +14,13 @@
14
  {"current_steps": 14, "total_steps": 70, "loss": 0.8237, "lr": 1.9396926207859085e-05, "epoch": 1.3439999999999999, "percentage": 20.0, "elapsed_time": "0:09:48", "remaining_time": "0:39:15"}
15
  {"current_steps": 15, "total_steps": 70, "loss": 0.822, "lr": 1.921476211870408e-05, "epoch": 1.44, "percentage": 21.43, "elapsed_time": "0:10:33", "remaining_time": "0:38:41"}
16
  {"current_steps": 16, "total_steps": 70, "loss": 0.8114, "lr": 1.900968867902419e-05, "epoch": 1.536, "percentage": 22.86, "elapsed_time": "0:11:04", "remaining_time": "0:37:23"}
 
 
 
 
 
 
 
 
 
 
 
14
  {"current_steps": 14, "total_steps": 70, "loss": 0.8237, "lr": 1.9396926207859085e-05, "epoch": 1.3439999999999999, "percentage": 20.0, "elapsed_time": "0:09:48", "remaining_time": "0:39:15"}
15
  {"current_steps": 15, "total_steps": 70, "loss": 0.822, "lr": 1.921476211870408e-05, "epoch": 1.44, "percentage": 21.43, "elapsed_time": "0:10:33", "remaining_time": "0:38:41"}
16
  {"current_steps": 16, "total_steps": 70, "loss": 0.8114, "lr": 1.900968867902419e-05, "epoch": 1.536, "percentage": 22.86, "elapsed_time": "0:11:04", "remaining_time": "0:37:23"}
17
+ {"current_steps": 17, "total_steps": 70, "loss": 0.7602, "lr": 1.8782215733702286e-05, "epoch": 1.6320000000000001, "percentage": 24.29, "elapsed_time": "0:11:58", "remaining_time": "0:37:20"}
18
+ {"current_steps": 18, "total_steps": 70, "loss": 0.7715, "lr": 1.8532908816321557e-05, "epoch": 1.728, "percentage": 25.71, "elapsed_time": "0:12:50", "remaining_time": "0:37:07"}
19
+ {"current_steps": 19, "total_steps": 70, "loss": 0.7711, "lr": 1.826238774315995e-05, "epoch": 1.8239999999999998, "percentage": 27.14, "elapsed_time": "0:13:32", "remaining_time": "0:36:21"}
20
+ {"current_steps": 20, "total_steps": 70, "loss": 0.7636, "lr": 1.7971325072229227e-05, "epoch": 1.92, "percentage": 28.57, "elapsed_time": "0:14:02", "remaining_time": "0:35:07"}
21
+ {"current_steps": 21, "total_steps": 70, "loss": 0.7409, "lr": 1.766044443118978e-05, "epoch": 2.016, "percentage": 30.0, "elapsed_time": "0:15:26", "remaining_time": "0:36:01"}
22
+ {"current_steps": 22, "total_steps": 70, "loss": 0.6265, "lr": 1.7330518718298263e-05, "epoch": 2.112, "percentage": 31.43, "elapsed_time": "0:15:55", "remaining_time": "0:34:45"}
23
+ {"current_steps": 23, "total_steps": 70, "loss": 0.5932, "lr": 1.698236818086073e-05, "epoch": 2.208, "percentage": 32.86, "elapsed_time": "0:16:31", "remaining_time": "0:33:47"}
24
+ {"current_steps": 24, "total_steps": 70, "loss": 0.5744, "lr": 1.6616858375968596e-05, "epoch": 2.304, "percentage": 34.29, "elapsed_time": "0:17:13", "remaining_time": "0:33:00"}
25
+ {"current_steps": 25, "total_steps": 70, "loss": 0.5856, "lr": 1.6234898018587336e-05, "epoch": 2.4, "percentage": 35.71, "elapsed_time": "0:17:57", "remaining_time": "0:32:20"}
26
+ {"current_steps": 26, "total_steps": 70, "loss": 0.5833, "lr": 1.5837436722347902e-05, "epoch": 2.496, "percentage": 37.14, "elapsed_time": "0:18:44", "remaining_time": "0:31:43"}