Hugging Face's logo

mlfoundations-dev
/
seed_math_deepmind

Text Generation
Transformers
Safetensors
llama
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Model card Files Community
sedrickkeh commited on
Commit
d029103
·
verified ·
1 Parent(s): 01fd8f4

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 +3 -0
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:236bbbea338f5207dbb6ccb6646c3983e2a95dbec798e0b32d944daa6e883d53
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff62ff5c27ca321764be478da888ab980d8522a89097f1f853c361b537169c51
3
  size 4976698672
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4dff7960b174c3c17f0ca6d766d6ab236c05e38391e6e67775a3769813e9ed98
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db36d5b73621cac37529b12b83adfd421aa30f9f1e3b2f96775437fd78ba3a06
3
  size 4999802720
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:85cbfe75a941e8ddce76d3c0cd680b7dc2dbeb7a3c85b4a0c9fd6d1c4c169052
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a22d0e5a353ee93e29376e466e5f58d5cbbcdfdad7a4abf58f3195e32f30a1a4
3
  size 4915916176
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:15aec9fbbf9be261628fb8a8c7353c125ee5095e0aac942d57c791aa2f8ee0e1
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eafb15d860f59099dac70c161d040c5f5064fa073f0ba2bf3743bff80e48bded
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -2,3 +2,6 @@
2
  {"current_steps": 20, "total_steps": 81, "loss": 0.2081, "lr": 5e-06, "epoch": 0.7207207207207207, "percentage": 24.69, "elapsed_time": "0:19:17", "remaining_time": "0:58:50"}
3
  {"current_steps": 27, "total_steps": 81, "eval_loss": 0.18130172789096832, "epoch": 0.972972972972973, "percentage": 33.33, "elapsed_time": "0:26:39", "remaining_time": "0:53:19"}
4
  {"current_steps": 30, "total_steps": 81, "loss": 0.202, "lr": 5e-06, "epoch": 1.1036036036036037, "percentage": 37.04, "elapsed_time": "0:30:35", "remaining_time": "0:52:00"}
 
 
 
 
2
  {"current_steps": 20, "total_steps": 81, "loss": 0.2081, "lr": 5e-06, "epoch": 0.7207207207207207, "percentage": 24.69, "elapsed_time": "0:19:17", "remaining_time": "0:58:50"}
3
  {"current_steps": 27, "total_steps": 81, "eval_loss": 0.18130172789096832, "epoch": 0.972972972972973, "percentage": 33.33, "elapsed_time": "0:26:39", "remaining_time": "0:53:19"}
4
  {"current_steps": 30, "total_steps": 81, "loss": 0.202, "lr": 5e-06, "epoch": 1.1036036036036037, "percentage": 37.04, "elapsed_time": "0:30:35", "remaining_time": "0:52:00"}
5
+ {"current_steps": 40, "total_steps": 81, "loss": 0.1717, "lr": 5e-06, "epoch": 1.4639639639639639, "percentage": 49.38, "elapsed_time": "0:40:13", "remaining_time": "0:41:14"}
6
+ {"current_steps": 50, "total_steps": 81, "loss": 0.1642, "lr": 5e-06, "epoch": 1.8243243243243243, "percentage": 61.73, "elapsed_time": "0:49:51", "remaining_time": "0:30:54"}
7
+ {"current_steps": 54, "total_steps": 81, "eval_loss": 0.16076427698135376, "epoch": 1.9684684684684686, "percentage": 66.67, "elapsed_time": "0:54:27", "remaining_time": "0:27:13"}