Hugging Face's logo

mlfoundations-dev
/
top_3_ranking_stackexchange

Text Generation
Transformers
Safetensors
llama
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Model card Files Community
sedrickkeh commited on
Commit
db05154
·
verified ·
1 Parent(s): 5871c19

Training in progress, epoch 3

Browse files
Files changed (5) hide show
  1. model-00001-of-00004.safetensors +1 -1
  2. model-00002-of-00004.safetensors +1 -1
  3. model-00003-of-00004.safetensors +1 -1
  4. model-00004-of-00004.safetensors +1 -1
  5. trainer_log.jsonl +15 -0
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c13a3486e1515052b88f7263452465e51d8b297a4397781c16f6ada5a10f5063
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5560738244e7f8b767a0f4a61358b86d26453e8b600532cb3f4fbbe63808478a
3
  size 4976698672
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1cac61d221597e6d4371d39dae728509df13ddf5f9cabc03b21cdc64cedd773b
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c23de1ddcd0271cd8f36cb81968a41049269c6ee40cfca108469456c0ce709d
3
  size 4999802720
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0057dc9a255f67e90da1637c6995f5ee15156f64cbdafca4b02f25b04d6b479c
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f5bbb73f0c15b6f0f8dcced27b40f7b633fd294e7d5183f0a816d0855e0f685d
3
  size 4915916176
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1897a24bfdfac4a3b78beafb66a2bdbee654bf85d4633e2885c1209df1591bc8
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cff045f40204f2ea8e4eb75dd33ee1fedc2e50f3b099c6778aff3f793f1a7852
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -25,3 +25,18 @@
25
  {"current_steps": 240, "total_steps": 384, "loss": 0.7012, "lr": 5e-06, "epoch": 1.875, "percentage": 62.5, "elapsed_time": "3:54:52", "remaining_time": "2:20:55"}
26
  {"current_steps": 250, "total_steps": 384, "loss": 0.7023, "lr": 5e-06, "epoch": 1.953125, "percentage": 65.1, "elapsed_time": "4:04:30", "remaining_time": "2:11:03"}
27
  {"current_steps": 256, "total_steps": 384, "eval_loss": 0.732055127620697, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "4:12:33", "remaining_time": "2:06:16"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
25
  {"current_steps": 240, "total_steps": 384, "loss": 0.7012, "lr": 5e-06, "epoch": 1.875, "percentage": 62.5, "elapsed_time": "3:54:52", "remaining_time": "2:20:55"}
26
  {"current_steps": 250, "total_steps": 384, "loss": 0.7023, "lr": 5e-06, "epoch": 1.953125, "percentage": 65.1, "elapsed_time": "4:04:30", "remaining_time": "2:11:03"}
27
  {"current_steps": 256, "total_steps": 384, "eval_loss": 0.732055127620697, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "4:12:33", "remaining_time": "2:06:16"}
28
+ {"current_steps": 260, "total_steps": 384, "loss": 0.6879, "lr": 5e-06, "epoch": 2.03125, "percentage": 67.71, "elapsed_time": "4:17:37", "remaining_time": "2:02:52"}
29
+ {"current_steps": 270, "total_steps": 384, "loss": 0.6546, "lr": 5e-06, "epoch": 2.109375, "percentage": 70.31, "elapsed_time": "4:27:15", "remaining_time": "1:52:50"}
30
+ {"current_steps": 280, "total_steps": 384, "loss": 0.6547, "lr": 5e-06, "epoch": 2.1875, "percentage": 72.92, "elapsed_time": "4:36:53", "remaining_time": "1:42:50"}
31
+ {"current_steps": 290, "total_steps": 384, "loss": 0.6556, "lr": 5e-06, "epoch": 2.265625, "percentage": 75.52, "elapsed_time": "4:46:31", "remaining_time": "1:32:52"}
32
+ {"current_steps": 300, "total_steps": 384, "loss": 0.6514, "lr": 5e-06, "epoch": 2.34375, "percentage": 78.12, "elapsed_time": "4:56:09", "remaining_time": "1:22:55"}
33
+ {"current_steps": 310, "total_steps": 384, "loss": 0.6553, "lr": 5e-06, "epoch": 2.421875, "percentage": 80.73, "elapsed_time": "5:05:48", "remaining_time": "1:12:59"}
34
+ {"current_steps": 320, "total_steps": 384, "loss": 0.6547, "lr": 5e-06, "epoch": 2.5, "percentage": 83.33, "elapsed_time": "5:15:27", "remaining_time": "1:03:05"}
35
+ {"current_steps": 330, "total_steps": 384, "loss": 0.6618, "lr": 5e-06, "epoch": 2.578125, "percentage": 85.94, "elapsed_time": "5:25:05", "remaining_time": "0:53:11"}
36
+ {"current_steps": 340, "total_steps": 384, "loss": 0.66, "lr": 5e-06, "epoch": 2.65625, "percentage": 88.54, "elapsed_time": "5:34:43", "remaining_time": "0:43:19"}
37
+ {"current_steps": 350, "total_steps": 384, "loss": 0.6627, "lr": 5e-06, "epoch": 2.734375, "percentage": 91.15, "elapsed_time": "5:44:21", "remaining_time": "0:33:27"}
38
+ {"current_steps": 360, "total_steps": 384, "loss": 0.6586, "lr": 5e-06, "epoch": 2.8125, "percentage": 93.75, "elapsed_time": "5:53:59", "remaining_time": "0:23:35"}
39
+ {"current_steps": 370, "total_steps": 384, "loss": 0.6632, "lr": 5e-06, "epoch": 2.890625, "percentage": 96.35, "elapsed_time": "6:03:38", "remaining_time": "0:13:45"}
40
+ {"current_steps": 380, "total_steps": 384, "loss": 0.6572, "lr": 5e-06, "epoch": 2.96875, "percentage": 98.96, "elapsed_time": "6:13:16", "remaining_time": "0:03:55"}
41
+ {"current_steps": 384, "total_steps": 384, "eval_loss": 0.7316058278083801, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "6:20:36", "remaining_time": "0:00:00"}
42
+ {"current_steps": 384, "total_steps": 384, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "6:21:52", "remaining_time": "0:00:00"}