Hugging Face's logo

prosecalign
/
phi3m0128-cds-0.5-kendall-onof-ofif-corr-max-2-simpo-max1500-default

Transformers
Safetensors
Generated from Trainer
llama-factory
Model card Files Community
ziansu commited on
Commit
6a5a64e
·
verified ·
1 Parent(s): 9622a1b

Training in progress, step 1200

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:fffa5bf8f2c7174f7a34fc80feffe727a32ee04e14740dad38c907f2baca123f
3
  size 25200088
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:13eac32a7e5d4a007ae1f6859a2d7606e91e1f0a1d2056d3faeb17e3f9dbd074
3
  size 25200088
trainer_log.jsonl CHANGED
@@ -136,3 +136,9 @@
136
  {"current_steps": 1140, "total_steps": 1500, "loss": 0.2684, "accuracy": 0.887499988079071, "learning_rate": 6.775784314464717e-07, "epoch": 1.2153518123667377, "percentage": 76.0, "elapsed_time": "2:34:55", "remaining_time": "0:48:55", "throughput": "0.00", "total_tokens": 0}
137
  {"current_steps": 1150, "total_steps": 1500, "loss": 0.2625, "accuracy": 0.949999988079071, "learning_rate": 6.421379363065142e-07, "epoch": 1.2260127931769722, "percentage": 76.67, "elapsed_time": "2:36:13", "remaining_time": "0:47:32", "throughput": "0.00", "total_tokens": 0}
138
  {"current_steps": 1150, "total_steps": 1500, "eval_loss": 0.23817622661590576, "epoch": 1.2260127931769722, "percentage": 76.67, "elapsed_time": "2:36:34", "remaining_time": "0:47:39", "throughput": "0.00", "total_tokens": 0}
 
 
 
 
 
 
 
136
  {"current_steps": 1140, "total_steps": 1500, "loss": 0.2684, "accuracy": 0.887499988079071, "learning_rate": 6.775784314464717e-07, "epoch": 1.2153518123667377, "percentage": 76.0, "elapsed_time": "2:34:55", "remaining_time": "0:48:55", "throughput": "0.00", "total_tokens": 0}
137
  {"current_steps": 1150, "total_steps": 1500, "loss": 0.2625, "accuracy": 0.949999988079071, "learning_rate": 6.421379363065142e-07, "epoch": 1.2260127931769722, "percentage": 76.67, "elapsed_time": "2:36:13", "remaining_time": "0:47:32", "throughput": "0.00", "total_tokens": 0}
138
  {"current_steps": 1150, "total_steps": 1500, "eval_loss": 0.23817622661590576, "epoch": 1.2260127931769722, "percentage": 76.67, "elapsed_time": "2:36:34", "remaining_time": "0:47:39", "throughput": "0.00", "total_tokens": 0}
139
+ {"current_steps": 1160, "total_steps": 1500, "loss": 0.2479, "accuracy": 0.9125000238418579, "learning_rate": 6.075123608706093e-07, "epoch": 1.236673773987207, "percentage": 77.33, "elapsed_time": "2:37:55", "remaining_time": "0:46:17", "throughput": "0.00", "total_tokens": 0}
140
+ {"current_steps": 1170, "total_steps": 1500, "loss": 0.2096, "accuracy": 0.9125000238418579, "learning_rate": 5.737168930605272e-07, "epoch": 1.2473347547974414, "percentage": 78.0, "elapsed_time": "2:39:11", "remaining_time": "0:44:54", "throughput": "0.00", "total_tokens": 0}
141
+ {"current_steps": 1180, "total_steps": 1500, "loss": 0.2542, "accuracy": 0.925000011920929, "learning_rate": 5.407663566854008e-07, "epoch": 1.2579957356076759, "percentage": 78.67, "elapsed_time": "2:40:28", "remaining_time": "0:43:30", "throughput": "0.00", "total_tokens": 0}
142
+ {"current_steps": 1190, "total_steps": 1500, "loss": 0.26, "accuracy": 0.9624999761581421, "learning_rate": 5.086752049395094e-07, "epoch": 1.2686567164179103, "percentage": 79.33, "elapsed_time": "2:41:42", "remaining_time": "0:42:07", "throughput": "0.00", "total_tokens": 0}
143
+ {"current_steps": 1200, "total_steps": 1500, "loss": 0.2364, "accuracy": 0.9125000238418579, "learning_rate": 4.774575140626317e-07, "epoch": 1.279317697228145, "percentage": 80.0, "elapsed_time": "2:42:56", "remaining_time": "0:40:44", "throughput": "0.00", "total_tokens": 0}
144
+ {"current_steps": 1200, "total_steps": 1500, "eval_loss": 0.23450209200382233, "epoch": 1.279317697228145, "percentage": 80.0, "elapsed_time": "2:43:17", "remaining_time": "0:40:49", "throughput": "0.00", "total_tokens": 0}