Hugging Face's logo

wanderer2k1
/
base_LLM_433MB_chunk_and_concat_w_domain

TensorBoard
Safetensors
mpt
Model card Files Metrics Community
wanderer2k1 commited on
Commit
f0f003c
•
1 Parent(s): ed06358

Training in progress, step 1000

Browse files
Files changed (38) hide show
  1. config.json +33 -0
  2. model.safetensors +3 -0
  3. runs/Sep24_01-37-36_kao-dgxa-e10-u17/events.out.tfevents.1727141863.kao-dgxa-e10-u17.1357.0 +3 -0
  4. runs/Sep24_02-04-50_kao-dgxa-e10-u17/events.out.tfevents.1727143510.kao-dgxa-e10-u17.1357.1 +3 -0
  5. runs/Sep24_02-25-27_kao-dgxa-e10-u17/events.out.tfevents.1727144739.kao-dgxa-e10-u17.2488.0 +3 -0
  6. runs/Sep24_02-25-27_kao-dgxa-e10-u17/events.out.tfevents.1727144809.kao-dgxa-e10-u17.2488.1 +3 -0
  7. runs/Sep24_02-28-38_kao-dgxa-e10-u17/events.out.tfevents.1727144926.kao-dgxa-e10-u17.2963.0 +3 -0
  8. runs/Sep24_02-30-46_kao-dgxa-e10-u17/events.out.tfevents.1727145059.kao-dgxa-e10-u17.1688.0 +3 -0
  9. runs/Sep24_02-38-59_kao-dgxa-e10-u17/events.out.tfevents.1727145543.kao-dgxa-e10-u17.3952.0 +3 -0
  10. runs/Sep24_02-39-55_kao-dgxa-e10-u17/events.out.tfevents.1727145608.kao-dgxa-e10-u17.4404.0 +3 -0
  11. runs/Sep24_02-40-52_kao-dgxa-e10-u17/events.out.tfevents.1727145657.kao-dgxa-e10-u17.4825.0 +3 -0
  12. runs/Sep24_02-41-40_kao-dgxa-e10-u17/events.out.tfevents.1727145705.kao-dgxa-e10-u17.5249.0 +3 -0
  13. runs/Sep24_02-46-39_kao-dgxa-e10-u17/events.out.tfevents.1727146003.kao-dgxa-e10-u17.5673.0 +3 -0
  14. runs/Sep24_02-48-07_kao-dgxa-e10-u17/events.out.tfevents.1727146091.kao-dgxa-e10-u17.6096.0 +3 -0
  15. runs/Sep24_02-49-47_kao-dgxa-e10-u17/events.out.tfevents.1727146191.kao-dgxa-e10-u17.6521.0 +3 -0
  16. runs/Sep24_02-53-05_kao-dgxa-e10-u17/events.out.tfevents.1727146391.kao-dgxa-e10-u17.7093.0 +3 -0
  17. runs/Sep24_02-54-38_kao-dgxa-e10-u17/events.out.tfevents.1727146485.kao-dgxa-e10-u17.7709.0 +3 -0
  18. runs/Sep24_02-55-37_kao-dgxa-e10-u17/events.out.tfevents.1727146542.kao-dgxa-e10-u17.8151.0 +3 -0
  19. runs/Sep24_02-57-37_kao-dgxa-e10-u17/events.out.tfevents.1727146664.kao-dgxa-e10-u17.8599.0 +3 -0
  20. runs/Sep24_03-01-24_kao-dgxa-e10-u17/events.out.tfevents.1727146897.kao-dgxa-e10-u17.9081.0 +3 -0
  21. runs/Sep24_03-49-13_kao-dgxa-e10-u17/events.out.tfevents.1727149758.kao-dgxa-e10-u17.9499.0 +3 -0
  22. runs/Sep24_04-43-48_kao-dgxa-e10-u17/events.out.tfevents.1727153034.kao-dgxa-e10-u17.11528.0 +3 -0
  23. runs/Sep24_04-53-54_kao-dgxa-e10-u17/events.out.tfevents.1727153641.kao-dgxa-e10-u17.12774.0 +3 -0
  24. runs/Sep24_07-07-10_kao-dgxa-e10-u17/events.out.tfevents.1727161637.kao-dgxa-e10-u17.1118.0 +3 -0
  25. runs/Sep24_07-07-39_kao-dgxa-e10-u17/events.out.tfevents.1727161665.kao-dgxa-e10-u17.1134.0 +3 -0
  26. runs/Sep24_07-49-19_kao-dgxa-e10-u17/events.out.tfevents.1727164164.kao-dgxa-e10-u17.3283.0 +3 -0
  27. runs/Sep24_07-50-58_kao-dgxa-e10-u17/events.out.tfevents.1727164267.kao-dgxa-e10-u17.5428.0 +3 -0
  28. runs/Sep24_08-54-59_kao-dgxa-e10-u17/events.out.tfevents.1727168105.kao-dgxa-e10-u17.843.0 +3 -0
  29. runs/Sep24_08-55-44_kao-dgxa-e10-u17/events.out.tfevents.1727168149.kao-dgxa-e10-u17.1265.0 +3 -0
  30. runs/Sep24_08-57-49_kao-dgxa-e10-u17/events.out.tfevents.1727168273.kao-dgxa-e10-u17.841.0 +3 -0
  31. runs/Sep24_08-58-09_kao-dgxa-e10-u17/events.out.tfevents.1727168307.kao-dgxa-e10-u17.857.0 +3 -0
  32. runs/Sep24_09-32-27_kao-dgxa-e10-u17/events.out.tfevents.1727170352.kao-dgxa-e10-u17.844.0 +3 -0
  33. runs/Sep24_09-34-26_kao-dgxa-e10-u17/events.out.tfevents.1727170472.kao-dgxa-e10-u17.3056.0 +3 -0
  34. runs/Sep25_04-19-41_kao-dgxa-e10-u17/events.out.tfevents.1727238091.kao-dgxa-e10-u17.3952.0 +3 -0
  35. runs/Sep25_04-23-35_kao-dgxa-e10-u17/events.out.tfevents.1727238221.kao-dgxa-e10-u17.4525.0 +3 -0
  36. runs/Sep25_04-31-21_kao-dgxa-e10-u17/events.out.tfevents.1727238817.kao-dgxa-e10-u17.5546.0 +3 -0
  37. runs/Sep25_04-33-36_kao-dgxa-e10-u17/events.out.tfevents.1727238820.kao-dgxa-e10-u17.5562.0 +3 -0
  38. training_args.bin +3 -0
config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "abili": false,
3
+ "architectures": [
4
+ "MptForCausalLM"
5
+ ],
6
+ "attn_config": {
7
+ "model_type": ""
8
+ },
9
+ "d_model": 1024,
10
+ "emb_pdrop": 0.0,
11
+ "embedding_fraction": 1.0,
12
+ "expansion_ratio": 4,
13
+ "init_device": "cpu",
14
+ "initializer_range": 0.02,
15
+ "layer_norm_epsilon": 1e-05,
16
+ "learned_pos_emb": true,
17
+ "logit_scale": null,
18
+ "max_seq_len": 8192,
19
+ "model_type": "mpt",
20
+ "n_heads": 16,
21
+ "n_layers": 24,
22
+ "no_bias": true,
23
+ "norm_type": "low_precision_layernorm",
24
+ "pad_token_id": 128009,
25
+ "resid_pdrop": 0.0,
26
+ "rope": true,
27
+ "rope_theta": 100000,
28
+ "torch_dtype": "float32",
29
+ "transformers_version": "4.40.0",
30
+ "use_cache": false,
31
+ "verbose": 0,
32
+ "vocab_size": 128256
33
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0bd35b88aa64719d14b449ef90af4d7bb3179175a2f8810acc9675c7c068c571
3
+ size 1733513312
runs/Sep24_01-37-36_kao-dgxa-e10-u17/events.out.tfevents.1727141863.kao-dgxa-e10-u17.1357.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:127263177b86e482f3a4b088bdd31017066a3601b5e3cf19031c0f458bef4968
3
+ size 104194
runs/Sep24_02-04-50_kao-dgxa-e10-u17/events.out.tfevents.1727143510.kao-dgxa-e10-u17.1357.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e56c1f1d5a963f8ce9e0858c3c6e3bbcdbbf6b25f18246f6961d0ab91a77c7c8
3
+ size 12099
runs/Sep24_02-25-27_kao-dgxa-e10-u17/events.out.tfevents.1727144739.kao-dgxa-e10-u17.2488.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:642e2bdaaf627a17ebbe83b6c492ac42c8115bc0c3b48da522776410512beaec
3
+ size 4771
runs/Sep24_02-25-27_kao-dgxa-e10-u17/events.out.tfevents.1727144809.kao-dgxa-e10-u17.2488.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1c27542fa232eea11460683891f2678ddc2897438ea0a7ca7d1a72ded5ce752
3
+ size 7876
runs/Sep24_02-28-38_kao-dgxa-e10-u17/events.out.tfevents.1727144926.kao-dgxa-e10-u17.2963.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f1dc7cb64e3bb78bd2f1320157eaec3e9e1294ba0bd92a20ed8ff2fdd41f1297
3
+ size 4979
runs/Sep24_02-30-46_kao-dgxa-e10-u17/events.out.tfevents.1727145059.kao-dgxa-e10-u17.1688.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2a98b37a2dc4759925c85a416fbd0df3df4c835c3b06e56a99760decd2c04cb
3
+ size 5607
runs/Sep24_02-38-59_kao-dgxa-e10-u17/events.out.tfevents.1727145543.kao-dgxa-e10-u17.3952.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3349bd3688bccace4a42d0b41d70a1de6dd023c705b356a73edeebe7694e9319
3
+ size 4184
runs/Sep24_02-39-55_kao-dgxa-e10-u17/events.out.tfevents.1727145608.kao-dgxa-e10-u17.4404.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ed081cb9ee8c0a6f97cd8d7cee6a8772b4e7c0e3093a4093efdc244a2b20b9f
3
+ size 4184
runs/Sep24_02-40-52_kao-dgxa-e10-u17/events.out.tfevents.1727145657.kao-dgxa-e10-u17.4825.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de8e0705b34abc911094854e91261a0b079133fcfaa44add9a87f1f6608f2377
3
+ size 4184
runs/Sep24_02-41-40_kao-dgxa-e10-u17/events.out.tfevents.1727145705.kao-dgxa-e10-u17.5249.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f5e7a835b976881fb67f8d2d13659cdefa07c5cec518f51383521c1524856b93
3
+ size 5165
runs/Sep24_02-46-39_kao-dgxa-e10-u17/events.out.tfevents.1727146003.kao-dgxa-e10-u17.5673.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a0e5b55b703f87d8ec217699c02c37f3dad9471a38bcedf03e754939ccc7ed1
3
+ size 4184
runs/Sep24_02-48-07_kao-dgxa-e10-u17/events.out.tfevents.1727146091.kao-dgxa-e10-u17.6096.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:186e45e2547ebcce8a29d3ebb7dee5e5db068c2854b9a6d8bf35589717ed9216
3
+ size 4184
runs/Sep24_02-49-47_kao-dgxa-e10-u17/events.out.tfevents.1727146191.kao-dgxa-e10-u17.6521.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b7075ecb0b2dc5e607459d5be40ede000404bbebae27bd4764d6b7cce88dca46
3
+ size 4773
runs/Sep24_02-53-05_kao-dgxa-e10-u17/events.out.tfevents.1727146391.kao-dgxa-e10-u17.7093.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:435a4d49a15f72bb0499ff4dfc13ca5d66afc8f3f66ce51d15e38f3aa608e0e9
3
+ size 4184
runs/Sep24_02-54-38_kao-dgxa-e10-u17/events.out.tfevents.1727146485.kao-dgxa-e10-u17.7709.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c092511a8c49b35ac90446e62b7dcd08ff21108c26471f58550d55c5f600687
3
+ size 4184
runs/Sep24_02-55-37_kao-dgxa-e10-u17/events.out.tfevents.1727146542.kao-dgxa-e10-u17.8151.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e3dde915f1d523900a0b7f2a9edbcbcf8a90b6d2d2695f09dc1d09a2cafe9c0
3
+ size 4184
runs/Sep24_02-57-37_kao-dgxa-e10-u17/events.out.tfevents.1727146664.kao-dgxa-e10-u17.8599.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:079d527ec21a827015b7ab8a716a1988e2e088323af07565a6e4ede7f4a87042
3
+ size 4774
runs/Sep24_03-01-24_kao-dgxa-e10-u17/events.out.tfevents.1727146897.kao-dgxa-e10-u17.9081.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:107bdf4ad6c7044dc2da52e4f4d2c50e59456f1379d38c7cc4dd9986a15459dd
3
+ size 5826
runs/Sep24_03-49-13_kao-dgxa-e10-u17/events.out.tfevents.1727149758.kao-dgxa-e10-u17.9499.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49b13d187e8a5931bfd9df55221ea30f85de6cadb24581ecb28c3047c164e5d8
3
+ size 14123
runs/Sep24_04-43-48_kao-dgxa-e10-u17/events.out.tfevents.1727153034.kao-dgxa-e10-u17.11528.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c658d2278e2607832d31c2a311189497dd9337a3b51fc3335851a6034fcd557
3
+ size 9202
runs/Sep24_04-53-54_kao-dgxa-e10-u17/events.out.tfevents.1727153641.kao-dgxa-e10-u17.12774.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3fd048c5ea6ab1ef69d9f5acefa8c518d8c101af91c7660be49ab5ccb18558d9
3
+ size 14898
runs/Sep24_07-07-10_kao-dgxa-e10-u17/events.out.tfevents.1727161637.kao-dgxa-e10-u17.1118.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85865df66fbab41ebcab0cc765f082175b1e45d94c079da0e117aa69cc8a1f1c
3
+ size 4736
runs/Sep24_07-07-39_kao-dgxa-e10-u17/events.out.tfevents.1727161665.kao-dgxa-e10-u17.1134.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a50a1ab09aea65f7f8942d0faaa9dddfc3b6e74e6dd675ad6b73df26bee9357
3
+ size 4737
runs/Sep24_07-49-19_kao-dgxa-e10-u17/events.out.tfevents.1727164164.kao-dgxa-e10-u17.3283.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb1bf8ae5223ba499fbff3c952d3bf993bc36847f208e39167b7ef7ba3eaf097
3
+ size 6842
runs/Sep24_07-50-58_kao-dgxa-e10-u17/events.out.tfevents.1727164267.kao-dgxa-e10-u17.5428.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a665b6563ae5bfcfe5a8893ba67a12a3bf83189597a27422ba3f36015a44a41
3
+ size 5577
runs/Sep24_08-54-59_kao-dgxa-e10-u17/events.out.tfevents.1727168105.kao-dgxa-e10-u17.843.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:abefd108e24920b698e6778886f313ec583656213f43835c12fcb13ccbc38b72
3
+ size 28192
runs/Sep24_08-55-44_kao-dgxa-e10-u17/events.out.tfevents.1727168149.kao-dgxa-e10-u17.1265.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e3690c45866882dc870a34130fed1d8e0cd884db01c81268682632744197ab4
3
+ size 63888
runs/Sep24_08-57-49_kao-dgxa-e10-u17/events.out.tfevents.1727168273.kao-dgxa-e10-u17.841.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a935fb677808f9b9321153172c9dda8dbbf0a5aecaf21b2e9a81c2c15ecfc1e7
3
+ size 66215
runs/Sep24_08-58-09_kao-dgxa-e10-u17/events.out.tfevents.1727168307.kao-dgxa-e10-u17.857.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ff0129c20c253be78f8782221cf43bf7ce5223212a210e6a8ed8cc321631083
3
+ size 29209
runs/Sep24_09-32-27_kao-dgxa-e10-u17/events.out.tfevents.1727170352.kao-dgxa-e10-u17.844.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:288d08af46d259086e38e8a5ceafb464ede4a3ea3ce5a287d61319f33d5dbe00
3
+ size 144474
runs/Sep24_09-34-26_kao-dgxa-e10-u17/events.out.tfevents.1727170472.kao-dgxa-e10-u17.3056.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae394113f8ab32fcf191792a81b3ccc8c2a4e1e2cc901539a9f3e694adc980b6
3
+ size 4736
runs/Sep25_04-19-41_kao-dgxa-e10-u17/events.out.tfevents.1727238091.kao-dgxa-e10-u17.3952.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8120cb10852624fcb6af5c4c317c7a3462da0ccf83f7ae628a94252f6107a5c
3
+ size 4736
runs/Sep25_04-23-35_kao-dgxa-e10-u17/events.out.tfevents.1727238221.kao-dgxa-e10-u17.4525.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aeb5899b277c7fd0e4b00f58b775a7a39fd16179b3198ff0b06980b24135afee
3
+ size 4943
runs/Sep25_04-31-21_kao-dgxa-e10-u17/events.out.tfevents.1727238817.kao-dgxa-e10-u17.5546.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d72ff2fc379e702e3be1cff5bf55d6757ff1035429ccf11e5e2f0d46f875d5c3
3
+ size 10156
runs/Sep25_04-33-36_kao-dgxa-e10-u17/events.out.tfevents.1727238820.kao-dgxa-e10-u17.5562.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f789da0c4a04113903ea9752d3479ace5a03f1eeb4578768659dfde031fc182f
3
+ size 6842
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:387c7ff848f3982393f6903e47c4a0087704c4017bfc75a35f93e2372b91a0c1
3
+ size 5176