Hugging Face's logo

prosecalign
/
clm7b0129-kendall-onof-ofif-corr-max-2-simpo-max1500-decay-sft-beta1.5-gamma0.5-lr5e-6

Transformers
Safetensors
Generated from Trainer
llama-factory
Model card Files Community
ziansu commited on
Commit
9f43c1f
·
verified ·
1 Parent(s): 53a633e

Training in progress, step 1350

Browse files
Files changed (2) hide show
  1. adapter_model.safetensors +1 -1
  2. trainer_log.jsonl +6 -0
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d941c77fde9e8bc38586d83a9d0a72ffc10c9314ba1cb84fc4e81b2caad833e3
3
  size 40036488
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a12d579687529127242685c92518ad316f0c79435b272c04f35b7ca43a314af
3
  size 40036488
trainer_log.jsonl CHANGED
@@ -154,3 +154,9 @@
154
  {"current_steps": 1290, "total_steps": 1500, "loss": 1.1599, "accuracy": 1.0, "learning_rate": 2.3793236883495164e-07, "epoch": 0.9350366947540092, "percentage": 86.0, "elapsed_time": "2:58:27", "remaining_time": "0:29:03", "throughput": "0.00", "total_tokens": 0}
155
  {"current_steps": 1300, "total_steps": 1500, "loss": 0.5808, "accuracy": 0.9624999761581421, "learning_rate": 2.1613635589349756e-07, "epoch": 0.9422850412249706, "percentage": 86.67, "elapsed_time": "2:59:43", "remaining_time": "0:27:38", "throughput": "0.00", "total_tokens": 0}
156
  {"current_steps": 1300, "total_steps": 1500, "eval_loss": 0.09216763824224472, "epoch": 0.9422850412249706, "percentage": 86.67, "elapsed_time": "3:00:13", "remaining_time": "0:27:43", "throughput": "0.00", "total_tokens": 0}
 
 
 
 
 
 
 
154
  {"current_steps": 1290, "total_steps": 1500, "loss": 1.1599, "accuracy": 1.0, "learning_rate": 2.3793236883495164e-07, "epoch": 0.9350366947540092, "percentage": 86.0, "elapsed_time": "2:58:27", "remaining_time": "0:29:03", "throughput": "0.00", "total_tokens": 0}
155
  {"current_steps": 1300, "total_steps": 1500, "loss": 0.5808, "accuracy": 0.9624999761581421, "learning_rate": 2.1613635589349756e-07, "epoch": 0.9422850412249706, "percentage": 86.67, "elapsed_time": "2:59:43", "remaining_time": "0:27:38", "throughput": "0.00", "total_tokens": 0}
156
  {"current_steps": 1300, "total_steps": 1500, "eval_loss": 0.09216763824224472, "epoch": 0.9422850412249706, "percentage": 86.67, "elapsed_time": "3:00:13", "remaining_time": "0:27:43", "throughput": "0.00", "total_tokens": 0}
157
+ {"current_steps": 1310, "total_steps": 1500, "loss": 0.8332, "accuracy": 0.987500011920929, "learning_rate": 1.95342121028749e-07, "epoch": 0.9495333876959319, "percentage": 87.33, "elapsed_time": "3:01:40", "remaining_time": "0:26:20", "throughput": "0.00", "total_tokens": 0}
158
+ {"current_steps": 1320, "total_steps": 1500, "loss": 0.642, "accuracy": 0.987500011920929, "learning_rate": 1.7555878527937164e-07, "epoch": 0.9567817341668932, "percentage": 88.0, "elapsed_time": "3:02:53", "remaining_time": "0:24:56", "throughput": "0.00", "total_tokens": 0}
159
+ {"current_steps": 1330, "total_steps": 1500, "loss": 0.4295, "accuracy": 1.0, "learning_rate": 1.567950262702714e-07, "epoch": 0.9640300806378544, "percentage": 88.67, "elapsed_time": "3:04:07", "remaining_time": "0:23:32", "throughput": "0.00", "total_tokens": 0}
160
+ {"current_steps": 1340, "total_steps": 1500, "loss": 1.3939, "accuracy": 0.9750000238418579, "learning_rate": 1.3905907440629752e-07, "epoch": 0.9712784271088158, "percentage": 89.33, "elapsed_time": "3:05:22", "remaining_time": "0:22:08", "throughput": "0.00", "total_tokens": 0}
161
+ {"current_steps": 1350, "total_steps": 1500, "loss": 0.7096, "accuracy": 1.0, "learning_rate": 1.223587092621162e-07, "epoch": 0.9785267735797771, "percentage": 90.0, "elapsed_time": "3:06:38", "remaining_time": "0:20:44", "throughput": "0.00", "total_tokens": 0}
162
+ {"current_steps": 1350, "total_steps": 1500, "eval_loss": 0.08608455955982208, "epoch": 0.9785267735797771, "percentage": 90.0, "elapsed_time": "3:07:08", "remaining_time": "0:20:47", "throughput": "0.00", "total_tokens": 0}