Hugging Face's logo

mlfoundations-dev
/
openthoughts_30k_32B

Text Generation
Transformers
Safetensors
qwen2
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Model card Files
xet
Community
1
reinhardh commited on
Commit
02a1c20
·
verified ·
1 Parent(s): e9c3bf7

Training in progress, epoch 4

Browse files
Files changed (15) hide show
  1. model-00001-of-00014.safetensors +1 -1
  2. model-00002-of-00014.safetensors +1 -1
  3. model-00003-of-00014.safetensors +1 -1
  4. model-00004-of-00014.safetensors +1 -1
  5. model-00005-of-00014.safetensors +1 -1
  6. model-00006-of-00014.safetensors +1 -1
  7. model-00007-of-00014.safetensors +1 -1
  8. model-00008-of-00014.safetensors +1 -1
  9. model-00009-of-00014.safetensors +1 -1
  10. model-00010-of-00014.safetensors +1 -1
  11. model-00011-of-00014.safetensors +1 -1
  12. model-00012-of-00014.safetensors +1 -1
  13. model-00013-of-00014.safetensors +1 -1
  14. model-00014-of-00014.safetensors +1 -1
  15. trainer_log.jsonl +22 -0
model-00001-of-00014.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:20ccc4fb0c0d079d59244ae566f2a05194f5460852b67a095a0e9500cfe2ec57
3
  size 4891730992
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eac15a37b692cbdbab069103cc798e6c0d85c57a1b08e6b6c9d56e05d8a66af2
3
  size 4891730992
model-00002-of-00014.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:215d6e362874f11426030c8cf028562b711997a78d5be4d5c2ffcdca768c0e7f
3
  size 4876059352
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:858e71b8359e43ae774e89a4eedff885d3ae88f9bf13e32b02c779a0f9efb349
3
  size 4876059352
model-00003-of-00014.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:68a21ac2be7c7f38f6148e41d0e6c1c2bba88b5668115af1371543d1048672f4
3
  size 4876059384
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d69acf4121b6dc3e7b35dd10484449eb32c5175bcab83000a738f97233e03e7
3
  size 4876059384
model-00004-of-00014.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5a879e95bb668b9401f26efb6f595d64e1fdfdd3a093f318b2df9824e10a5596
3
  size 4876059416
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd8bdb7ee7fb1d9fade35001777de2281a53c64576bb7e3d5a9893bf3fcde930
3
  size 4876059416
model-00005-of-00014.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b44ede08f94809f23bf210f4f567ff289f09ca53b1a529914f112f08011b1a6b
3
  size 4876059416
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a36e3c8e3321f82bbd7e3f864a5504d307d24a1350f61e943fbcc958e38ed855
3
  size 4876059416
model-00006-of-00014.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:46c34a268964d334d9dc58518da777d951a108844019780e7f711cfc135b2b8f
3
  size 4876059416
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:31d0d8477ef7a3b6e68cd402d7c60b8f645ad8ca111f60dd553c1be00f76f144
3
  size 4876059416
model-00007-of-00014.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cedfbe28c9d9aec7e07dc8c8b35598bf3a80e557fa692da51a41fa9a2449fa45
3
  size 4876059416
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a62e2eae25a6494236f35d4788a28161aa5defb6924631286de82f7558371942
3
  size 4876059416
model-00008-of-00014.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c79afe1e9d32daa8f1c6a0b229ca0af838e1af04a025ab7c2e0a628f5c9bb3ce
3
  size 4876059416
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:83bd2d7128a1a4df1518250ecce77f9182fd0c79cf3b4144b7fbbea7e1523b44
3
  size 4876059416
model-00009-of-00014.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:07bc8cf15b603ff36c88f46cb72f7f24001a4ee549396ad1bba68dd51f72fb5a
3
  size 4876059416
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e902ce3108f3f4e92bd932fe00dbb00564439f11282c5f74e65e0e58cc6e42a2
3
  size 4876059416
model-00010-of-00014.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:08beb2f6d860ac60051d6589a5b0f3c25abc4644ad42518fe1bf5dee47e23406
3
  size 4876059416
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d249623cb8e49809ca0d274b7a5905254ad5a5fdf5c28aad8d6fb3c2f6db4bb9
3
  size 4876059416
model-00011-of-00014.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3b1303a90eaf081a59a0f2ce355068d2b095fda6e23a72ba1a96fd4357f06b42
3
  size 4876059416
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a021fa28cf3bee89f1f0c0593f1a7ef46d7245fec192932da2ff42388ec864f3
3
  size 4876059416
model-00012-of-00014.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:79a9215f5536953bbf3733f2005a880c6637ead742a4e8af6ae4ee3ea6e11d82
3
  size 4876059416
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a95b2dbccfbcab9411fdbc9e30d20c62e82c331e501b1150f51d8cf8703ed3de
3
  size 4876059416
model-00013-of-00014.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:33de150ba3566f7be6aecbf1f767c5791df275227a3868bdfa2f8c82772a1a4e
3
  size 4876059416
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b67282fe57d48383f2d016fb7c79dd3dc3c0c01b810178a82643cb639db7a08
3
  size 4876059416
model-00014-of-00014.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0cbe7538101dd686e204076cc8f1f04d71fdefb28366df0140eb9ce15820da0f
3
  size 2123397800
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6033eb4c79e01ece3621d39357c78a3d8329ab4781751d1b75601602e1a27f44
3
  size 2123397800
trainer_log.jsonl CHANGED
@@ -102,3 +102,25 @@
102
  {"current_steps": 102, "total_steps": 125, "loss": 0.3271, "lr": 8.039580585670047e-06, "epoch": 4.059113300492611, "percentage": 81.6, "elapsed_time": "5:38:37", "remaining_time": "1:16:21"}
103
  {"current_steps": 103, "total_steps": 125, "loss": 0.3298, "lr": 7.3775652416295936e-06, "epoch": 4.098522167487685, "percentage": 82.4, "elapsed_time": "5:41:46", "remaining_time": "1:13:00"}
104
  {"current_steps": 104, "total_steps": 125, "loss": 0.3295, "lr": 6.7412155078981865e-06, "epoch": 4.137931034482759, "percentage": 83.2, "elapsed_time": "5:45:00", "remaining_time": "1:09:39"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
102
  {"current_steps": 102, "total_steps": 125, "loss": 0.3271, "lr": 8.039580585670047e-06, "epoch": 4.059113300492611, "percentage": 81.6, "elapsed_time": "5:38:37", "remaining_time": "1:16:21"}
103
  {"current_steps": 103, "total_steps": 125, "loss": 0.3298, "lr": 7.3775652416295936e-06, "epoch": 4.098522167487685, "percentage": 82.4, "elapsed_time": "5:41:46", "remaining_time": "1:13:00"}
104
  {"current_steps": 104, "total_steps": 125, "loss": 0.3295, "lr": 6.7412155078981865e-06, "epoch": 4.137931034482759, "percentage": 83.2, "elapsed_time": "5:45:00", "remaining_time": "1:09:39"}
105
+ {"current_steps": 105, "total_steps": 125, "loss": 0.3274, "lr": 6.1310320308686354e-06, "epoch": 4.177339901477833, "percentage": 84.0, "elapsed_time": "5:48:11", "remaining_time": "1:06:19"}
106
+ {"current_steps": 106, "total_steps": 125, "loss": 0.3307, "lr": 5.547494870703642e-06, "epoch": 4.216748768472907, "percentage": 84.8, "elapsed_time": "5:51:21", "remaining_time": "1:02:58"}
107
+ {"current_steps": 107, "total_steps": 125, "loss": 0.326, "lr": 4.991063123649853e-06, "epoch": 4.25615763546798, "percentage": 85.6, "elapsed_time": "5:54:31", "remaining_time": "0:59:38"}
108
+ {"current_steps": 108, "total_steps": 125, "loss": 0.3273, "lr": 4.462174560845114e-06, "epoch": 4.295566502463054, "percentage": 86.4, "elapsed_time": "5:57:42", "remaining_time": "0:56:18"}
109
+ {"current_steps": 109, "total_steps": 125, "loss": 0.3304, "lr": 3.961245283903239e-06, "epoch": 4.334975369458128, "percentage": 87.2, "elapsed_time": "6:00:52", "remaining_time": "0:52:58"}
110
+ {"current_steps": 110, "total_steps": 125, "loss": 0.3285, "lr": 3.4886693975472443e-06, "epoch": 4.374384236453202, "percentage": 88.0, "elapsed_time": "6:04:03", "remaining_time": "0:49:38"}
111
+ {"current_steps": 111, "total_steps": 125, "loss": 0.328, "lr": 3.0448186995485307e-06, "epoch": 4.413793103448276, "percentage": 88.8, "elapsed_time": "6:07:13", "remaining_time": "0:46:19"}
112
+ {"current_steps": 112, "total_steps": 125, "loss": 0.3314, "lr": 2.630042388216012e-06, "epoch": 4.45320197044335, "percentage": 89.6, "elapsed_time": "6:10:23", "remaining_time": "0:42:59"}
113
+ {"current_steps": 113, "total_steps": 125, "loss": 0.3285, "lr": 2.244666787665297e-06, "epoch": 4.4926108374384235, "percentage": 90.4, "elapsed_time": "6:13:33", "remaining_time": "0:39:40"}
114
+ {"current_steps": 114, "total_steps": 125, "loss": 0.3267, "lr": 1.888995091084147e-06, "epoch": 4.532019704433497, "percentage": 91.2, "elapsed_time": "6:16:45", "remaining_time": "0:36:21"}
115
+ {"current_steps": 115, "total_steps": 125, "loss": 0.3199, "lr": 1.5633071221960205e-06, "epoch": 4.571428571428571, "percentage": 92.0, "elapsed_time": "6:19:55", "remaining_time": "0:33:02"}
116
+ {"current_steps": 116, "total_steps": 125, "loss": 0.3291, "lr": 1.2678591151095466e-06, "epoch": 4.610837438423645, "percentage": 92.8, "elapsed_time": "6:23:05", "remaining_time": "0:29:43"}
117
+ {"current_steps": 117, "total_steps": 125, "loss": 0.328, "lr": 1.0028835127270553e-06, "epoch": 4.650246305418719, "percentage": 93.6, "elapsed_time": "6:26:14", "remaining_time": "0:26:24"}
118
+ {"current_steps": 118, "total_steps": 125, "loss": 0.3282, "lr": 7.685887838707828e-07, "epoch": 4.689655172413794, "percentage": 94.4, "elapsed_time": "6:29:25", "remaining_time": "0:23:06"}
119
+ {"current_steps": 119, "total_steps": 125, "loss": 0.3358, "lr": 5.651592592705646e-07, "epoch": 4.7290640394088665, "percentage": 95.2, "elapsed_time": "6:32:35", "remaining_time": "0:19:47"}
120
+ {"current_steps": 120, "total_steps": 125, "loss": 0.3231, "lr": 3.9275498654217425e-07, "epoch": 4.768472906403941, "percentage": 96.0, "elapsed_time": "6:35:48", "remaining_time": "0:16:29"}
121
+ {"current_steps": 121, "total_steps": 125, "loss": 0.3273, "lr": 2.5151160427029584e-07, "epoch": 4.807881773399015, "percentage": 96.8, "elapsed_time": "6:38:58", "remaining_time": "0:13:11"}
122
+ {"current_steps": 122, "total_steps": 125, "loss": 0.3252, "lr": 1.4154023529523663e-07, "epoch": 4.847290640394089, "percentage": 97.6, "elapsed_time": "6:42:08", "remaining_time": "0:09:53"}
123
+ {"current_steps": 123, "total_steps": 125, "loss": 0.3251, "lr": 6.292739928733582e-08, "epoch": 4.886699507389163, "percentage": 98.4, "elapsed_time": "6:45:19", "remaining_time": "0:06:35"}
124
+ {"current_steps": 124, "total_steps": 125, "loss": 0.3261, "lr": 1.5734944677885388e-08, "epoch": 4.926108374384237, "percentage": 99.2, "elapsed_time": "6:48:29", "remaining_time": "0:03:17"}
125
+ {"current_steps": 125, "total_steps": 125, "loss": 0.3278, "lr": 0.0, "epoch": 4.9655172413793105, "percentage": 100.0, "elapsed_time": "6:51:39", "remaining_time": "0:00:00"}
126
+ {"current_steps": 125, "total_steps": 125, "epoch": 4.9655172413793105, "percentage": 100.0, "elapsed_time": "6:56:37", "remaining_time": "0:00:00"}