Hugging Face's logo

mlfoundations-dev
/
oh-dcft-v1.2_no-curation_gpt-4o-mini

Text Generation
Transformers
Safetensors
llama
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
sedrickkeh commited on
Commit
e73b5f9
•
1 Parent(s): 859af18

Training in progress, epoch 1

Browse files
Files changed (6) 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 +36 -36
  6. training_args.bin +1 -1
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5460309525cf9ce579eadbf303486894f57d02c2bef68e5d4fec22a049330336
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd1ab7668b777c90ac006b3d2a37777959282e39caf68931f9c4188d9913b578
3
  size 4976698672
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:33af5c9660c777fae7f435b92c4f7a56ab65c237b812989c643221da1ba374b6
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:32b27f5ca180008f120726e147001f43b65765619359d71c777dbf589d16fd76
3
  size 4999802720
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:43af2f1562bfcc3e1dc3ee253cc121557bda2e03deb5693a4211ea4e89ed868c
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:376569465f563abc5c7f0a557a004f97ebe9de9e446506df9b44bd632047b18a
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:f9d5e03eb26a3109b9372e70158a557e5ff40de75e7b5ab8fb4dfdc26bacbc02
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4edc33fe7782949d973dceda437ddb3debc2896b0e9b07a44bccdd7895f9d6aa
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -1,37 +1,37 @@
1
- {"current_steps": 10, "total_steps": 987, "loss": 0.9277, "learning_rate": 5e-06, "epoch": 0.030395136778115502, "percentage": 1.01, "elapsed_time": "0:00:54", "remaining_time": "1:29:02"}
2
- {"current_steps": 20, "total_steps": 987, "loss": 0.8119, "learning_rate": 5e-06, "epoch": 0.060790273556231005, "percentage": 2.03, "elapsed_time": "0:01:39", "remaining_time": "1:20:06"}
3
- {"current_steps": 30, "total_steps": 987, "loss": 0.7777, "learning_rate": 5e-06, "epoch": 0.0911854103343465, "percentage": 3.04, "elapsed_time": "0:02:24", "remaining_time": "1:16:52"}
4
- {"current_steps": 40, "total_steps": 987, "loss": 0.7531, "learning_rate": 5e-06, "epoch": 0.12158054711246201, "percentage": 4.05, "elapsed_time": "0:03:09", "remaining_time": "1:14:53"}
5
- {"current_steps": 50, "total_steps": 987, "loss": 0.7355, "learning_rate": 5e-06, "epoch": 0.1519756838905775, "percentage": 5.07, "elapsed_time": "0:03:55", "remaining_time": "1:13:25"}
6
- {"current_steps": 60, "total_steps": 987, "loss": 0.7225, "learning_rate": 5e-06, "epoch": 0.182370820668693, "percentage": 6.08, "elapsed_time": "0:04:40", "remaining_time": "1:12:10"}
7
- {"current_steps": 70, "total_steps": 987, "loss": 0.7119, "learning_rate": 5e-06, "epoch": 0.2127659574468085, "percentage": 7.09, "elapsed_time": "0:05:25", "remaining_time": "1:11:06"}
8
- {"current_steps": 80, "total_steps": 987, "loss": 0.7019, "learning_rate": 5e-06, "epoch": 0.24316109422492402, "percentage": 8.11, "elapsed_time": "0:06:10", "remaining_time": "1:10:04"}
9
- {"current_steps": 90, "total_steps": 987, "loss": 0.6986, "learning_rate": 5e-06, "epoch": 0.2735562310030395, "percentage": 9.12, "elapsed_time": "0:06:55", "remaining_time": "1:09:05"}
10
- {"current_steps": 100, "total_steps": 987, "loss": 0.6867, "learning_rate": 5e-06, "epoch": 0.303951367781155, "percentage": 10.13, "elapsed_time": "0:07:41", "remaining_time": "1:08:11"}
11
- {"current_steps": 110, "total_steps": 987, "loss": 0.6908, "learning_rate": 5e-06, "epoch": 0.3343465045592705, "percentage": 11.14, "elapsed_time": "0:08:26", "remaining_time": "1:07:18"}
12
- {"current_steps": 120, "total_steps": 987, "loss": 0.6825, "learning_rate": 5e-06, "epoch": 0.364741641337386, "percentage": 12.16, "elapsed_time": "0:09:11", "remaining_time": "1:06:27"}
13
- {"current_steps": 130, "total_steps": 987, "loss": 0.6882, "learning_rate": 5e-06, "epoch": 0.3951367781155015, "percentage": 13.17, "elapsed_time": "0:09:57", "remaining_time": "1:05:36"}
14
- {"current_steps": 140, "total_steps": 987, "loss": 0.6826, "learning_rate": 5e-06, "epoch": 0.425531914893617, "percentage": 14.18, "elapsed_time": "0:10:42", "remaining_time": "1:04:46"}
15
- {"current_steps": 150, "total_steps": 987, "loss": 0.6787, "learning_rate": 5e-06, "epoch": 0.45592705167173253, "percentage": 15.2, "elapsed_time": "0:11:27", "remaining_time": "1:03:55"}
16
- {"current_steps": 160, "total_steps": 987, "loss": 0.6858, "learning_rate": 5e-06, "epoch": 0.48632218844984804, "percentage": 16.21, "elapsed_time": "0:12:12", "remaining_time": "1:03:05"}
17
- {"current_steps": 170, "total_steps": 987, "loss": 0.677, "learning_rate": 5e-06, "epoch": 0.5167173252279635, "percentage": 17.22, "elapsed_time": "0:12:57", "remaining_time": "1:02:15"}
18
- {"current_steps": 180, "total_steps": 987, "loss": 0.6853, "learning_rate": 5e-06, "epoch": 0.547112462006079, "percentage": 18.24, "elapsed_time": "0:13:42", "remaining_time": "1:01:26"}
19
- {"current_steps": 190, "total_steps": 987, "loss": 0.6717, "learning_rate": 5e-06, "epoch": 0.5775075987841946, "percentage": 19.25, "elapsed_time": "0:14:27", "remaining_time": "1:00:40"}
20
- {"current_steps": 200, "total_steps": 987, "loss": 0.6726, "learning_rate": 5e-06, "epoch": 0.60790273556231, "percentage": 20.26, "elapsed_time": "0:15:13", "remaining_time": "0:59:52"}
21
- {"current_steps": 210, "total_steps": 987, "loss": 0.6747, "learning_rate": 5e-06, "epoch": 0.6382978723404256, "percentage": 21.28, "elapsed_time": "0:15:58", "remaining_time": "0:59:05"}
22
- {"current_steps": 220, "total_steps": 987, "loss": 0.6731, "learning_rate": 5e-06, "epoch": 0.668693009118541, "percentage": 22.29, "elapsed_time": "0:16:43", "remaining_time": "0:58:17"}
23
- {"current_steps": 230, "total_steps": 987, "loss": 0.6701, "learning_rate": 5e-06, "epoch": 0.6990881458966566, "percentage": 23.3, "elapsed_time": "0:17:28", "remaining_time": "0:57:29"}
24
- {"current_steps": 240, "total_steps": 987, "loss": 0.6699, "learning_rate": 5e-06, "epoch": 0.729483282674772, "percentage": 24.32, "elapsed_time": "0:18:12", "remaining_time": "0:56:41"}
25
- {"current_steps": 250, "total_steps": 987, "loss": 0.6649, "learning_rate": 5e-06, "epoch": 0.7598784194528876, "percentage": 25.33, "elapsed_time": "0:18:57", "remaining_time": "0:55:54"}
26
- {"current_steps": 260, "total_steps": 987, "loss": 0.6697, "learning_rate": 5e-06, "epoch": 0.790273556231003, "percentage": 26.34, "elapsed_time": "0:19:42", "remaining_time": "0:55:06"}
27
- {"current_steps": 270, "total_steps": 987, "loss": 0.6639, "learning_rate": 5e-06, "epoch": 0.8206686930091185, "percentage": 27.36, "elapsed_time": "0:20:27", "remaining_time": "0:54:19"}
28
- {"current_steps": 280, "total_steps": 987, "loss": 0.6623, "learning_rate": 5e-06, "epoch": 0.851063829787234, "percentage": 28.37, "elapsed_time": "0:21:12", "remaining_time": "0:53:32"}
29
- {"current_steps": 290, "total_steps": 987, "loss": 0.6606, "learning_rate": 5e-06, "epoch": 0.8814589665653495, "percentage": 29.38, "elapsed_time": "0:21:57", "remaining_time": "0:52:45"}
30
  {"current_steps": 300, "total_steps": 987, "loss": 0.6632, "learning_rate": 5e-06, "epoch": 0.9118541033434651, "percentage": 30.4, "elapsed_time": "0:22:42", "remaining_time": "0:52:00"}
31
- {"current_steps": 310, "total_steps": 987, "loss": 0.6577, "learning_rate": 5e-06, "epoch": 0.9422492401215805, "percentage": 31.41, "elapsed_time": "0:23:27", "remaining_time": "0:51:14"}
32
- {"current_steps": 320, "total_steps": 987, "loss": 0.6591, "learning_rate": 5e-06, "epoch": 0.9726443768996961, "percentage": 32.42, "elapsed_time": "0:24:13", "remaining_time": "0:50:28"}
33
- {"current_steps": 329, "total_steps": 987, "eval_loss": 0.659148633480072, "epoch": 1.0, "percentage": 33.33, "elapsed_time": "0:25:24", "remaining_time": "0:50:49"}
34
- {"current_steps": 330, "total_steps": 987, "loss": 0.6601, "learning_rate": 5e-06, "epoch": 1.0030395136778116, "percentage": 33.43, "elapsed_time": "0:26:20", "remaining_time": "0:52:25"}
35
- {"current_steps": 340, "total_steps": 987, "loss": 0.622, "learning_rate": 5e-06, "epoch": 1.033434650455927, "percentage": 34.45, "elapsed_time": "0:27:04", "remaining_time": "0:51:32"}
36
- {"current_steps": 350, "total_steps": 987, "loss": 0.6146, "learning_rate": 5e-06, "epoch": 1.0638297872340425, "percentage": 35.46, "elapsed_time": "0:27:50", "remaining_time": "0:50:39"}
37
- {"current_steps": 360, "total_steps": 987, "loss": 0.6232, "learning_rate": 5e-06, "epoch": 1.094224924012158, "percentage": 36.47, "elapsed_time": "0:28:35", "remaining_time": "0:49:47"}
 
1
+ {"current_steps": 10, "total_steps": 987, "loss": 0.9277, "learning_rate": 5e-06, "epoch": 0.030395136778115502, "percentage": 1.01, "elapsed_time": "0:00:55", "remaining_time": "1:29:56"}
2
+ {"current_steps": 20, "total_steps": 987, "loss": 0.825, "learning_rate": 5e-06, "epoch": 0.060790273556231005, "percentage": 2.03, "elapsed_time": "0:01:39", "remaining_time": "1:20:33"}
3
+ {"current_steps": 30, "total_steps": 987, "loss": 0.7817, "learning_rate": 5e-06, "epoch": 0.0911854103343465, "percentage": 3.04, "elapsed_time": "0:02:24", "remaining_time": "1:16:54"}
4
+ {"current_steps": 40, "total_steps": 987, "loss": 0.7545, "learning_rate": 5e-06, "epoch": 0.12158054711246201, "percentage": 4.05, "elapsed_time": "0:03:09", "remaining_time": "1:14:52"}
5
+ {"current_steps": 50, "total_steps": 987, "loss": 0.7358, "learning_rate": 5e-06, "epoch": 0.1519756838905775, "percentage": 5.07, "elapsed_time": "0:03:54", "remaining_time": "1:13:20"}
6
+ {"current_steps": 60, "total_steps": 987, "loss": 0.7226, "learning_rate": 5e-06, "epoch": 0.182370820668693, "percentage": 6.08, "elapsed_time": "0:04:39", "remaining_time": "1:12:04"}
7
+ {"current_steps": 70, "total_steps": 987, "loss": 0.7122, "learning_rate": 5e-06, "epoch": 0.2127659574468085, "percentage": 7.09, "elapsed_time": "0:05:24", "remaining_time": "1:10:57"}
8
+ {"current_steps": 80, "total_steps": 987, "loss": 0.7016, "learning_rate": 5e-06, "epoch": 0.24316109422492402, "percentage": 8.11, "elapsed_time": "0:06:09", "remaining_time": "1:09:54"}
9
+ {"current_steps": 90, "total_steps": 987, "loss": 0.6982, "learning_rate": 5e-06, "epoch": 0.2735562310030395, "percentage": 9.12, "elapsed_time": "0:06:54", "remaining_time": "1:08:55"}
10
+ {"current_steps": 100, "total_steps": 987, "loss": 0.6865, "learning_rate": 5e-06, "epoch": 0.303951367781155, "percentage": 10.13, "elapsed_time": "0:07:40", "remaining_time": "1:08:00"}
11
+ {"current_steps": 110, "total_steps": 987, "loss": 0.6907, "learning_rate": 5e-06, "epoch": 0.3343465045592705, "percentage": 11.14, "elapsed_time": "0:08:25", "remaining_time": "1:07:06"}
12
+ {"current_steps": 120, "total_steps": 987, "loss": 0.6824, "learning_rate": 5e-06, "epoch": 0.364741641337386, "percentage": 12.16, "elapsed_time": "0:09:10", "remaining_time": "1:06:17"}
13
+ {"current_steps": 130, "total_steps": 987, "loss": 0.6879, "learning_rate": 5e-06, "epoch": 0.3951367781155015, "percentage": 13.17, "elapsed_time": "0:09:55", "remaining_time": "1:05:28"}
14
+ {"current_steps": 140, "total_steps": 987, "loss": 0.6824, "learning_rate": 5e-06, "epoch": 0.425531914893617, "percentage": 14.18, "elapsed_time": "0:10:40", "remaining_time": "1:04:37"}
15
+ {"current_steps": 150, "total_steps": 987, "loss": 0.6785, "learning_rate": 5e-06, "epoch": 0.45592705167173253, "percentage": 15.2, "elapsed_time": "0:11:25", "remaining_time": "1:03:46"}
16
+ {"current_steps": 160, "total_steps": 987, "loss": 0.6857, "learning_rate": 5e-06, "epoch": 0.48632218844984804, "percentage": 16.21, "elapsed_time": "0:12:10", "remaining_time": "1:02:57"}
17
+ {"current_steps": 170, "total_steps": 987, "loss": 0.6769, "learning_rate": 5e-06, "epoch": 0.5167173252279635, "percentage": 17.22, "elapsed_time": "0:12:55", "remaining_time": "1:02:08"}
18
+ {"current_steps": 180, "total_steps": 987, "loss": 0.6853, "learning_rate": 5e-06, "epoch": 0.547112462006079, "percentage": 18.24, "elapsed_time": "0:13:41", "remaining_time": "1:01:21"}
19
+ {"current_steps": 190, "total_steps": 987, "loss": 0.6716, "learning_rate": 5e-06, "epoch": 0.5775075987841946, "percentage": 19.25, "elapsed_time": "0:14:26", "remaining_time": "1:00:34"}
20
+ {"current_steps": 200, "total_steps": 987, "loss": 0.6726, "learning_rate": 5e-06, "epoch": 0.60790273556231, "percentage": 20.26, "elapsed_time": "0:15:11", "remaining_time": "0:59:48"}
21
+ {"current_steps": 210, "total_steps": 987, "loss": 0.6747, "learning_rate": 5e-06, "epoch": 0.6382978723404256, "percentage": 21.28, "elapsed_time": "0:15:57", "remaining_time": "0:59:01"}
22
+ {"current_steps": 220, "total_steps": 987, "loss": 0.673, "learning_rate": 5e-06, "epoch": 0.668693009118541, "percentage": 22.29, "elapsed_time": "0:16:42", "remaining_time": "0:58:15"}
23
+ {"current_steps": 230, "total_steps": 987, "loss": 0.6701, "learning_rate": 5e-06, "epoch": 0.6990881458966566, "percentage": 23.3, "elapsed_time": "0:17:27", "remaining_time": "0:57:27"}
24
+ {"current_steps": 240, "total_steps": 987, "loss": 0.6699, "learning_rate": 5e-06, "epoch": 0.729483282674772, "percentage": 24.32, "elapsed_time": "0:18:12", "remaining_time": "0:56:40"}
25
+ {"current_steps": 250, "total_steps": 987, "loss": 0.6649, "learning_rate": 5e-06, "epoch": 0.7598784194528876, "percentage": 25.33, "elapsed_time": "0:18:57", "remaining_time": "0:55:53"}
26
+ {"current_steps": 260, "total_steps": 987, "loss": 0.6697, "learning_rate": 5e-06, "epoch": 0.790273556231003, "percentage": 26.34, "elapsed_time": "0:19:42", "remaining_time": "0:55:05"}
27
+ {"current_steps": 270, "total_steps": 987, "loss": 0.6639, "learning_rate": 5e-06, "epoch": 0.8206686930091185, "percentage": 27.36, "elapsed_time": "0:20:27", "remaining_time": "0:54:18"}
28
+ {"current_steps": 280, "total_steps": 987, "loss": 0.6624, "learning_rate": 5e-06, "epoch": 0.851063829787234, "percentage": 28.37, "elapsed_time": "0:21:12", "remaining_time": "0:53:32"}
29
+ {"current_steps": 290, "total_steps": 987, "loss": 0.6606, "learning_rate": 5e-06, "epoch": 0.8814589665653495, "percentage": 29.38, "elapsed_time": "0:21:57", "remaining_time": "0:52:46"}
30
  {"current_steps": 300, "total_steps": 987, "loss": 0.6632, "learning_rate": 5e-06, "epoch": 0.9118541033434651, "percentage": 30.4, "elapsed_time": "0:22:42", "remaining_time": "0:52:00"}
31
+ {"current_steps": 310, "total_steps": 987, "loss": 0.6576, "learning_rate": 5e-06, "epoch": 0.9422492401215805, "percentage": 31.41, "elapsed_time": "0:23:27", "remaining_time": "0:51:14"}
32
+ {"current_steps": 320, "total_steps": 987, "loss": 0.6591, "learning_rate": 5e-06, "epoch": 0.9726443768996961, "percentage": 32.42, "elapsed_time": "0:24:12", "remaining_time": "0:50:28"}
33
+ {"current_steps": 329, "total_steps": 987, "eval_loss": 0.6591953635215759, "epoch": 1.0, "percentage": 33.33, "elapsed_time": "0:25:24", "remaining_time": "0:50:48"}
34
+ {"current_steps": 330, "total_steps": 987, "loss": 0.6601, "learning_rate": 5e-06, "epoch": 1.0030395136778116, "percentage": 33.43, "elapsed_time": "0:26:19", "remaining_time": "0:52:23"}
35
+ {"current_steps": 340, "total_steps": 987, "loss": 0.6224, "learning_rate": 5e-06, "epoch": 1.033434650455927, "percentage": 34.45, "elapsed_time": "0:27:03", "remaining_time": "0:51:30"}
36
+ {"current_steps": 350, "total_steps": 987, "loss": 0.615, "learning_rate": 5e-06, "epoch": 1.0638297872340425, "percentage": 35.46, "elapsed_time": "0:27:48", "remaining_time": "0:50:37"}
37
+ {"current_steps": 360, "total_steps": 987, "loss": 0.6236, "learning_rate": 5e-06, "epoch": 1.094224924012158, "percentage": 36.47, "elapsed_time": "0:28:33", "remaining_time": "0:49:44"}
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0a22c23057161ce8caaf4753f5daa1dd9025e76ebc5269863ad39653fb970a67
3
  size 7224
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:54ac6424366eaeb9bb46e6e2b3f7103ee5b3693e18cb17196174ddad865b603f
3
  size 7224