Hugging Face's logo

mlfoundations-dev
/
316_globalbatchsize64_lr1e5_epochs9

Text Generation
Transformers
Safetensors
qwen2
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Model card Files
xet
Community
1
sedrickkeh commited on
Commit
676c18e
·
verified ·
1 Parent(s): a005ca4

Training in progress, epoch 9

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:eb9b1871f24ccdfd12aa57a58a2728c473faae809e23d395f6da0fe86f79a1d3
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:906ffeba6b50ccc985ad0159f8737c7dd1a8ee49beb56baad88274f9189e515f
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:41ebab924149c9fc7753f6f4a9fd4b3cb99a17b9f886770cbb4065879c7e6209
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c1f143f78b3e395f3dd9fd480c7f87928e0a85c8653e518cdad24108d4612620
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:ad6921603572a95eec73a0838abf74503b00adfdeafdf51ae483e262adb26043
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:16a520a86b84a8ae3abeacf729189594415f19408bfdc1221dbb18bb202ea5e3
3
  size 4330865200
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2e58e91e36038ec4531db8222892161401d71d2050b4e384bf98d622c112286c
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4c884ca21ed6c3f78aa4d47f5d7e0a8c487b52051e454f0a80c2fb234818196
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -40,3 +40,7 @@
40
  {"current_steps": 40, "total_steps": 45, "loss": 0.4324, "lr": 3.8060233744356634e-07, "epoch": 8.0, "percentage": 88.89, "elapsed_time": "0:53:29", "remaining_time": "0:06:41"}
41
  {"current_steps": 41, "total_steps": 45, "loss": 0.3851, "lr": 2.447174185242324e-07, "epoch": 8.2, "percentage": 91.11, "elapsed_time": "0:55:29", "remaining_time": "0:05:24"}
42
  {"current_steps": 42, "total_steps": 45, "loss": 0.4473, "lr": 1.3815039801161723e-07, "epoch": 8.4, "percentage": 93.33, "elapsed_time": "0:56:47", "remaining_time": "0:04:03"}
 
 
 
 
 
40
  {"current_steps": 40, "total_steps": 45, "loss": 0.4324, "lr": 3.8060233744356634e-07, "epoch": 8.0, "percentage": 88.89, "elapsed_time": "0:53:29", "remaining_time": "0:06:41"}
41
  {"current_steps": 41, "total_steps": 45, "loss": 0.3851, "lr": 2.447174185242324e-07, "epoch": 8.2, "percentage": 91.11, "elapsed_time": "0:55:29", "remaining_time": "0:05:24"}
42
  {"current_steps": 42, "total_steps": 45, "loss": 0.4473, "lr": 1.3815039801161723e-07, "epoch": 8.4, "percentage": 93.33, "elapsed_time": "0:56:47", "remaining_time": "0:04:03"}
43
+ {"current_steps": 43, "total_steps": 45, "loss": 0.4257, "lr": 6.15582970243117e-08, "epoch": 8.6, "percentage": 95.56, "elapsed_time": "0:57:57", "remaining_time": "0:02:41"}
44
+ {"current_steps": 44, "total_steps": 45, "loss": 0.4344, "lr": 1.541333133436018e-08, "epoch": 8.8, "percentage": 97.78, "elapsed_time": "0:59:01", "remaining_time": "0:01:20"}
45
+ {"current_steps": 45, "total_steps": 45, "loss": 0.4391, "lr": 0.0, "epoch": 9.0, "percentage": 100.0, "elapsed_time": "1:00:14", "remaining_time": "0:00:00"}
46
+ {"current_steps": 45, "total_steps": 45, "epoch": 9.0, "percentage": 100.0, "elapsed_time": "1:02:40", "remaining_time": "0:00:00"}