Hugging Face's logo

prosecalign
/
phi3m0128-wds-0.7-kendall-onof-ofif-corr-max-2-simpo-max1500-default

Transformers
Safetensors
Generated from Trainer
llama-factory
Inference Endpoints
Model card Files Community
ziansu commited on
Commit
53790d9
·
verified ·
1 Parent(s): 07e2dd1

Training in progress, step 1250

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 sha256:00a9d3cb3ab97088cb7560e3bce8604508b98f02472f2b1bab89fd858338ad1c
3
  size 25200088
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b7db9ab3f6be7df165471d843086ffe9ebe8fc537e0d87ccd5681782028cf9b
3
  size 25200088
trainer_log.jsonl CHANGED
@@ -142,3 +142,9 @@
142
  {"current_steps": 1190, "total_steps": 1500, "loss": 0.1798, "accuracy": 0.949999988079071, "learning_rate": 5.086752049395094e-07, "epoch": 1.0927988974388423, "percentage": 79.33, "elapsed_time": "2:44:50", "remaining_time": "0:42:56", "throughput": "0.00", "total_tokens": 0}
143
  {"current_steps": 1200, "total_steps": 1500, "loss": 0.2005, "accuracy": 0.9375, "learning_rate": 4.774575140626317e-07, "epoch": 1.1019869070862525, "percentage": 80.0, "elapsed_time": "2:46:12", "remaining_time": "0:41:33", "throughput": "0.00", "total_tokens": 0}
144
  {"current_steps": 1200, "total_steps": 1500, "eval_loss": 0.2008148729801178, "epoch": 1.1019869070862525, "percentage": 80.0, "elapsed_time": "2:46:36", "remaining_time": "0:41:39", "throughput": "0.00", "total_tokens": 0}
 
 
 
 
 
 
 
142
  {"current_steps": 1190, "total_steps": 1500, "loss": 0.1798, "accuracy": 0.949999988079071, "learning_rate": 5.086752049395094e-07, "epoch": 1.0927988974388423, "percentage": 79.33, "elapsed_time": "2:44:50", "remaining_time": "0:42:56", "throughput": "0.00", "total_tokens": 0}
143
  {"current_steps": 1200, "total_steps": 1500, "loss": 0.2005, "accuracy": 0.9375, "learning_rate": 4.774575140626317e-07, "epoch": 1.1019869070862525, "percentage": 80.0, "elapsed_time": "2:46:12", "remaining_time": "0:41:33", "throughput": "0.00", "total_tokens": 0}
144
  {"current_steps": 1200, "total_steps": 1500, "eval_loss": 0.2008148729801178, "epoch": 1.1019869070862525, "percentage": 80.0, "elapsed_time": "2:46:36", "remaining_time": "0:41:39", "throughput": "0.00", "total_tokens": 0}
145
+ {"current_steps": 1210, "total_steps": 1500, "loss": 0.1796, "accuracy": 0.9375, "learning_rate": 4.4712697716573994e-07, "epoch": 1.1111749167336626, "percentage": 80.67, "elapsed_time": "2:48:01", "remaining_time": "0:40:16", "throughput": "0.00", "total_tokens": 0}
146
+ {"current_steps": 1220, "total_steps": 1500, "loss": 0.1742, "accuracy": 0.9375, "learning_rate": 4.1769689822475147e-07, "epoch": 1.1203629263810726, "percentage": 81.33, "elapsed_time": "2:49:21", "remaining_time": "0:38:52", "throughput": "0.00", "total_tokens": 0}
147
+ {"current_steps": 1230, "total_steps": 1500, "loss": 0.1811, "accuracy": 0.949999988079071, "learning_rate": 3.891801862449629e-07, "epoch": 1.1295509360284828, "percentage": 82.0, "elapsed_time": "2:50:34", "remaining_time": "0:37:26", "throughput": "0.00", "total_tokens": 0}
148
+ {"current_steps": 1240, "total_steps": 1500, "loss": 0.1942, "accuracy": 0.949999988079071, "learning_rate": 3.615893495987335e-07, "epoch": 1.138738945675893, "percentage": 82.67, "elapsed_time": "2:51:50", "remaining_time": "0:36:01", "throughput": "0.00", "total_tokens": 0}
149
+ {"current_steps": 1250, "total_steps": 1500, "loss": 0.2088, "accuracy": 0.9125000238418579, "learning_rate": 3.3493649053890325e-07, "epoch": 1.1479269553233031, "percentage": 83.33, "elapsed_time": "2:53:04", "remaining_time": "0:34:36", "throughput": "0.00", "total_tokens": 0}
150
+ {"current_steps": 1250, "total_steps": 1500, "eval_loss": 0.20090900361537933, "epoch": 1.1479269553233031, "percentage": 83.33, "elapsed_time": "2:53:28", "remaining_time": "0:34:41", "throughput": "0.00", "total_tokens": 0}