ben81828 commited on
Commit
49afea3
·
verified ·
1 Parent(s): 16cb6db

Training in progress, step 600

Browse files
Files changed (2) hide show
  1. adapter_model.safetensors +1 -1
  2. trainer_log.jsonl +11 -0
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4a60b889b7a54e23b958a8a26ed4e9fa41ab2f6dbc4276859d27d85e7f97cc2d
3
  size 29034840
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f3607f7be0eeae44a002686249cfd8440e2093656b0084bace7dafe752090325
3
  size 29034840
trainer_log.jsonl CHANGED
@@ -119,3 +119,14 @@
119
  {"current_steps": 545, "total_steps": 3400, "loss": 0.6325, "lr": 9.67108983539777e-05, "epoch": 0.1403553953129024, "percentage": 16.03, "elapsed_time": "2:49:14", "remaining_time": "14:46:35", "throughput": 563.58, "total_tokens": 5722936}
120
  {"current_steps": 550, "total_steps": 3400, "loss": 0.5596, "lr": 9.662361147021779e-05, "epoch": 0.141643059490085, "percentage": 16.18, "elapsed_time": "2:50:41", "remaining_time": "14:44:27", "throughput": 563.9, "total_tokens": 5774880}
121
  {"current_steps": 550, "total_steps": 3400, "eval_loss": 0.5832681059837341, "epoch": 0.141643059490085, "percentage": 16.18, "elapsed_time": "2:51:19", "remaining_time": "14:47:45", "throughput": 561.8, "total_tokens": 5774880}
 
 
 
 
 
 
 
 
 
 
 
 
119
  {"current_steps": 545, "total_steps": 3400, "loss": 0.6325, "lr": 9.67108983539777e-05, "epoch": 0.1403553953129024, "percentage": 16.03, "elapsed_time": "2:49:14", "remaining_time": "14:46:35", "throughput": 563.58, "total_tokens": 5722936}
120
  {"current_steps": 550, "total_steps": 3400, "loss": 0.5596, "lr": 9.662361147021779e-05, "epoch": 0.141643059490085, "percentage": 16.18, "elapsed_time": "2:50:41", "remaining_time": "14:44:27", "throughput": 563.9, "total_tokens": 5774880}
121
  {"current_steps": 550, "total_steps": 3400, "eval_loss": 0.5832681059837341, "epoch": 0.141643059490085, "percentage": 16.18, "elapsed_time": "2:51:19", "remaining_time": "14:47:45", "throughput": 561.8, "total_tokens": 5774880}
122
+ {"current_steps": 555, "total_steps": 3400, "loss": 0.5073, "lr": 9.653522193117013e-05, "epoch": 0.14293072366726758, "percentage": 16.32, "elapsed_time": "2:52:51", "remaining_time": "14:46:05", "throughput": 561.79, "total_tokens": 5826608}
123
+ {"current_steps": 560, "total_steps": 3400, "loss": 0.5652, "lr": 9.644573182726035e-05, "epoch": 0.14421838784445018, "percentage": 16.47, "elapsed_time": "2:54:18", "remaining_time": "14:43:58", "throughput": 562.21, "total_tokens": 5879776}
124
+ {"current_steps": 565, "total_steps": 3400, "loss": 0.5727, "lr": 9.63551432749426e-05, "epoch": 0.14550605202163275, "percentage": 16.62, "elapsed_time": "2:55:44", "remaining_time": "14:41:50", "throughput": 562.64, "total_tokens": 5932888}
125
+ {"current_steps": 570, "total_steps": 3400, "loss": 0.6251, "lr": 9.626345841664953e-05, "epoch": 0.14679371619881534, "percentage": 16.76, "elapsed_time": "2:57:12", "remaining_time": "14:39:49", "throughput": 562.87, "total_tokens": 5984648}
126
+ {"current_steps": 575, "total_steps": 3400, "loss": 0.6508, "lr": 9.617067942074153e-05, "epoch": 0.14808138037599794, "percentage": 16.91, "elapsed_time": "2:58:38", "remaining_time": "14:37:39", "throughput": 563.24, "total_tokens": 6037000}
127
+ {"current_steps": 580, "total_steps": 3400, "loss": 0.6686, "lr": 9.607680848145558e-05, "epoch": 0.14936904455318054, "percentage": 17.06, "elapsed_time": "3:00:06", "remaining_time": "14:35:39", "throughput": 563.62, "total_tokens": 6090512}
128
+ {"current_steps": 585, "total_steps": 3400, "loss": 0.5793, "lr": 9.598184781885318e-05, "epoch": 0.15065670873036313, "percentage": 17.21, "elapsed_time": "3:01:32", "remaining_time": "14:33:32", "throughput": 564.01, "total_tokens": 6143320}
129
+ {"current_steps": 590, "total_steps": 3400, "loss": 0.5954, "lr": 9.588579967876806e-05, "epoch": 0.1519443729075457, "percentage": 17.35, "elapsed_time": "3:02:59", "remaining_time": "14:31:33", "throughput": 564.28, "total_tokens": 6195720}
130
+ {"current_steps": 595, "total_steps": 3400, "loss": 0.5644, "lr": 9.578866633275288e-05, "epoch": 0.1532320370847283, "percentage": 17.5, "elapsed_time": "3:04:25", "remaining_time": "14:29:26", "throughput": 564.6, "total_tokens": 6247592}
131
+ {"current_steps": 600, "total_steps": 3400, "loss": 0.5794, "lr": 9.569045007802559e-05, "epoch": 0.1545197012619109, "percentage": 17.65, "elapsed_time": "3:05:53", "remaining_time": "14:27:29", "throughput": 564.81, "total_tokens": 6299656}
132
+ {"current_steps": 600, "total_steps": 3400, "eval_loss": 0.6039358973503113, "epoch": 0.1545197012619109, "percentage": 17.65, "elapsed_time": "3:06:31", "remaining_time": "14:30:28", "throughput": 562.88, "total_tokens": 6299656}