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
Model card Files Community
ziansu commited on
Commit
5997efe
·
verified ·
1 Parent(s): 260f7db

Training in progress, step 1300

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 sha256:4b7db9ab3f6be7df165471d843086ffe9ebe8fc537e0d87ccd5681782028cf9b
3
  size 25200088
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:94ebccd7741337cc28a9b8aa42e38fbc8e04cf920e987eb0f1664b87dabf3b0a
3
  size 25200088
trainer_log.jsonl CHANGED
@@ -148,3 +148,9 @@
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}
 
 
 
 
 
 
 
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}
151
+ {"current_steps": 1260, "total_steps": 1500, "loss": 0.1833, "accuracy": 0.9750000238418579, "learning_rate": 3.092332998903416e-07, "epoch": 1.1571149649707133, "percentage": 84.0, "elapsed_time": "2:54:55", "remaining_time": "0:33:19", "throughput": "0.00", "total_tokens": 0}
152
+ {"current_steps": 1270, "total_steps": 1500, "loss": 0.2073, "accuracy": 0.9125000238418579, "learning_rate": 2.844910519219632e-07, "epoch": 1.1663029746181233, "percentage": 84.67, "elapsed_time": "2:56:16", "remaining_time": "0:31:55", "throughput": "0.00", "total_tokens": 0}
153
+ {"current_steps": 1280, "total_steps": 1500, "loss": 0.2031, "accuracy": 0.9375, "learning_rate": 2.6072059940146775e-07, "epoch": 1.1754909842655334, "percentage": 85.33, "elapsed_time": "2:57:35", "remaining_time": "0:30:31", "throughput": "0.00", "total_tokens": 0}
154
+ {"current_steps": 1290, "total_steps": 1500, "loss": 0.2191, "accuracy": 0.9375, "learning_rate": 2.3793236883495164e-07, "epoch": 1.1846789939129436, "percentage": 86.0, "elapsed_time": "2:58:54", "remaining_time": "0:29:07", "throughput": "0.00", "total_tokens": 0}
155
+ {"current_steps": 1300, "total_steps": 1500, "loss": 0.2523, "accuracy": 0.9375, "learning_rate": 2.1613635589349756e-07, "epoch": 1.1938670035603538, "percentage": 86.67, "elapsed_time": "3:00:11", "remaining_time": "0:27:43", "throughput": "0.00", "total_tokens": 0}
156
+ {"current_steps": 1300, "total_steps": 1500, "eval_loss": 0.20123924314975739, "epoch": 1.1938670035603538, "percentage": 86.67, "elapsed_time": "3:00:36", "remaining_time": "0:27:47", "throughput": "0.00", "total_tokens": 0}