Hugging Face's logo

mlfoundations-dev
/
hp_ablations_grid_mistral_bsz4096_lr2e-6_scheduler-cosine-warmup0.15

Text Generation
Transformers
Safetensors
mistral
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
sedrickkeh commited on
Commit
8d8dc25
·
verified ·
1 Parent(s): a9360ba

Training in progress, epoch 3

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 +10 -0
model-00001-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5f94fda9210d42ce30111487726e174aaf7adcdb4bdc32e1aab1a6d405022a4c
3
  size 4943162336
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e4a51416b542de9c5a1e87079e55bd43fc1fdb8a51710e10a81f5f063cdb69cd
3
  size 4943162336
model-00002-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0b08ab75b1da861e9925acdd07ef4fed5cf480b3ff3880cdabc6a21b391aa053
3
  size 4999819336
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5cb70bcac2f8d859cf4e4c66de805eec3a6dc53a9f8bd8216bedfab2ab19c8d9
3
  size 4999819336
model-00003-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:556ea01f4f86ac74f49469e88edf62fc74b256d55d64d49acd5e60af02409f47
3
  size 4540516344
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d82ead7b079d2c8281c20d872e96053d56d1bb0851d144c9d18f5b85524802a8
3
  size 4540516344
trainer_log.jsonl CHANGED
@@ -17,3 +17,13 @@
17
  {"current_steps": 160, "total_steps": 252, "loss": 0.5032, "lr": 7.815702322222537e-07, "epoch": 1.9047619047619047, "percentage": 63.49, "elapsed_time": "2:38:24", "remaining_time": "1:31:04"}
18
  {"current_steps": 168, "total_steps": 252, "eval_loss": 0.06419934332370758, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "2:47:41", "remaining_time": "1:23:50"}
19
  {"current_steps": 170, "total_steps": 252, "loss": 0.4998, "lr": 6.411752507928641e-07, "epoch": 2.0238095238095237, "percentage": 67.46, "elapsed_time": "2:50:22", "remaining_time": "1:22:10"}
 
 
 
 
 
 
 
 
 
 
 
17
  {"current_steps": 160, "total_steps": 252, "loss": 0.5032, "lr": 7.815702322222537e-07, "epoch": 1.9047619047619047, "percentage": 63.49, "elapsed_time": "2:38:24", "remaining_time": "1:31:04"}
18
  {"current_steps": 168, "total_steps": 252, "eval_loss": 0.06419934332370758, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "2:47:41", "remaining_time": "1:23:50"}
19
  {"current_steps": 170, "total_steps": 252, "loss": 0.4998, "lr": 6.411752507928641e-07, "epoch": 2.0238095238095237, "percentage": 67.46, "elapsed_time": "2:50:22", "remaining_time": "1:22:10"}
20
+ {"current_steps": 180, "total_steps": 252, "loss": 0.4907, "lr": 5.084995082868657e-07, "epoch": 2.142857142857143, "percentage": 71.43, "elapsed_time": "3:00:07", "remaining_time": "1:12:03"}
21
+ {"current_steps": 190, "total_steps": 252, "loss": 0.4892, "lr": 3.8639719956680615e-07, "epoch": 2.261904761904762, "percentage": 75.4, "elapsed_time": "3:09:53", "remaining_time": "1:01:57"}
22
+ {"current_steps": 200, "total_steps": 252, "loss": 0.4856, "lr": 2.7749505786719795e-07, "epoch": 2.380952380952381, "percentage": 79.37, "elapsed_time": "3:19:39", "remaining_time": "0:51:54"}
23
+ {"current_steps": 210, "total_steps": 252, "loss": 0.4846, "lr": 1.8413584703837615e-07, "epoch": 2.5, "percentage": 83.33, "elapsed_time": "3:29:25", "remaining_time": "0:41:53"}
24
+ {"current_steps": 220, "total_steps": 252, "loss": 0.4871, "lr": 1.0832796269875755e-07, "epoch": 2.619047619047619, "percentage": 87.3, "elapsed_time": "3:39:10", "remaining_time": "0:31:52"}
25
+ {"current_steps": 230, "total_steps": 252, "loss": 0.4861, "lr": 5.170222650372469e-08, "epoch": 2.738095238095238, "percentage": 91.27, "elapsed_time": "3:48:56", "remaining_time": "0:21:53"}
26
+ {"current_steps": 240, "total_steps": 252, "loss": 0.4855, "lr": 1.547680299702281e-08, "epoch": 2.857142857142857, "percentage": 95.24, "elapsed_time": "3:58:42", "remaining_time": "0:11:56"}
27
+ {"current_steps": 250, "total_steps": 252, "loss": 0.4835, "lr": 4.309937730015978e-10, "epoch": 2.9761904761904763, "percentage": 99.21, "elapsed_time": "4:08:28", "remaining_time": "0:01:59"}
28
+ {"current_steps": 252, "total_steps": 252, "eval_loss": 0.06357227265834808, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "4:12:39", "remaining_time": "0:00:00"}
29
+ {"current_steps": 252, "total_steps": 252, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "4:13:18", "remaining_time": "0:00:00"}