rbelanec commited on
Commit
bd48d88
verified
1 Parent(s): fdf644a

Training in progress, step 441

Browse files
Files changed (2) hide show
  1. adapter_model.safetensors +1 -1
  2. trainer_log.jsonl +14 -0
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b9405e8de61a8bb137f2b71969fe11a54604b641b55fd25043d7aca2a22c446a
3
  size 819328
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:989a9e2d310ab1f06e39a1b2513c5f45976db727abb7071f7b5c3ccdf6d2b004
3
  size 819328
trainer_log.jsonl CHANGED
@@ -82,3 +82,17 @@
82
  {"current_steps": 380, "total_steps": 1250, "loss": 0.3542, "lr": 0.026382251943462682, "epoch": 3.04, "percentage": 30.4, "elapsed_time": "0:00:56", "remaining_time": "0:02:10", "throughput": 2630.81, "total_tokens": 149472}
83
  {"current_steps": 385, "total_steps": 1250, "loss": 0.4196, "lr": 0.026244738061397325, "epoch": 3.08, "percentage": 30.8, "elapsed_time": "0:00:57", "remaining_time": "0:02:08", "throughput": 2641.0, "total_tokens": 151552}
84
  {"current_steps": 390, "total_steps": 1250, "loss": 0.4161, "lr": 0.026105031995366672, "epoch": 3.12, "percentage": 31.2, "elapsed_time": "0:00:57", "remaining_time": "0:02:07", "throughput": 2650.07, "total_tokens": 153568}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
82
  {"current_steps": 380, "total_steps": 1250, "loss": 0.3542, "lr": 0.026382251943462682, "epoch": 3.04, "percentage": 30.4, "elapsed_time": "0:00:56", "remaining_time": "0:02:10", "throughput": 2630.81, "total_tokens": 149472}
83
  {"current_steps": 385, "total_steps": 1250, "loss": 0.4196, "lr": 0.026244738061397325, "epoch": 3.08, "percentage": 30.8, "elapsed_time": "0:00:57", "remaining_time": "0:02:08", "throughput": 2641.0, "total_tokens": 151552}
84
  {"current_steps": 390, "total_steps": 1250, "loss": 0.4161, "lr": 0.026105031995366672, "epoch": 3.12, "percentage": 31.2, "elapsed_time": "0:00:57", "remaining_time": "0:02:07", "throughput": 2650.07, "total_tokens": 153568}
85
+ {"current_steps": 395, "total_steps": 1250, "loss": 0.4733, "lr": 0.025963160981345105, "epoch": 3.16, "percentage": 31.6, "elapsed_time": "0:00:58", "remaining_time": "0:02:06", "throughput": 2659.41, "total_tokens": 155616}
86
+ {"current_steps": 400, "total_steps": 1250, "loss": 0.408, "lr": 0.02581915267736791, "epoch": 3.2, "percentage": 32.0, "elapsed_time": "0:00:59", "remaining_time": "0:02:05", "throughput": 2666.02, "total_tokens": 157728}
87
+ {"current_steps": 405, "total_steps": 1250, "loss": 0.3754, "lr": 0.025673035158139283, "epoch": 3.24, "percentage": 32.4, "elapsed_time": "0:00:59", "remaining_time": "0:02:04", "throughput": 2670.88, "total_tokens": 159488}
88
+ {"current_steps": 410, "total_steps": 1250, "loss": 0.3989, "lr": 0.02552483690955911, "epoch": 3.2800000000000002, "percentage": 32.8, "elapsed_time": "0:01:00", "remaining_time": "0:02:03", "throughput": 2680.04, "total_tokens": 161600}
89
+ {"current_steps": 415, "total_steps": 1250, "loss": 0.3847, "lr": 0.0253745868231696, "epoch": 3.32, "percentage": 33.2, "elapsed_time": "0:01:00", "remaining_time": "0:02:02", "throughput": 2688.97, "total_tokens": 163712}
90
+ {"current_steps": 420, "total_steps": 1250, "loss": 0.3272, "lr": 0.025222314190522798, "epoch": 3.36, "percentage": 33.6, "elapsed_time": "0:01:01", "remaining_time": "0:02:01", "throughput": 2694.22, "total_tokens": 165536}
91
+ {"current_steps": 425, "total_steps": 1250, "loss": 0.4486, "lr": 0.02506804869747014, "epoch": 3.4, "percentage": 34.0, "elapsed_time": "0:01:02", "remaining_time": "0:02:00", "throughput": 2705.71, "total_tokens": 167872}
92
+ {"current_steps": 430, "total_steps": 1250, "loss": 0.4475, "lr": 0.024911820418375166, "epoch": 3.44, "percentage": 34.4, "elapsed_time": "0:01:02", "remaining_time": "0:01:59", "throughput": 2715.49, "total_tokens": 170112}
93
+ {"current_steps": 435, "total_steps": 1250, "loss": 0.428, "lr": 0.02475365981025043, "epoch": 3.48, "percentage": 34.8, "elapsed_time": "0:01:03", "remaining_time": "0:01:58", "throughput": 2721.48, "total_tokens": 172000}
94
+ {"current_steps": 440, "total_steps": 1250, "loss": 0.4076, "lr": 0.02459359770681987, "epoch": 3.52, "percentage": 35.2, "elapsed_time": "0:01:03", "remaining_time": "0:01:57", "throughput": 2728.69, "total_tokens": 174016}
95
+ {"current_steps": 441, "total_steps": 1250, "eval_loss": 0.42745479941368103, "epoch": 3.528, "percentage": 35.28, "elapsed_time": "0:01:04", "remaining_time": "0:01:58", "throughput": 2689.29, "total_tokens": 174432}
96
+ {"current_steps": 445, "total_steps": 1250, "loss": 0.3735, "lr": 0.02443166531250769, "epoch": 3.56, "percentage": 35.6, "elapsed_time": "0:01:06", "remaining_time": "0:01:59", "throughput": 2651.79, "total_tokens": 175776}
97
+ {"current_steps": 450, "total_steps": 1250, "loss": 0.3547, "lr": 0.024267894196355017, "epoch": 3.6, "percentage": 36.0, "elapsed_time": "0:01:06", "remaining_time": "0:01:58", "throughput": 2660.56, "total_tokens": 177952}
98
+ {"current_steps": 455, "total_steps": 1250, "loss": 0.3795, "lr": 0.024102316285865434, "epoch": 3.64, "percentage": 36.4, "elapsed_time": "0:01:07", "remaining_time": "0:01:57", "throughput": 2668.02, "total_tokens": 179968}