Hugging Face's logo

mlfoundations-dev
/
s1_32B

Safetensors
qwen2
Model card Files
xet
Community
neginr commited on
Commit
a0cf138
·
verified ·
1 Parent(s): e9358aa

Training in progress, epoch 0

Browse files
Files changed (16) 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 +16 -20
  16. training_args.bin +1 -1
model-00001-of-00014.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6ac756545969d0d56260ae4d82f19b05b10717b9aadb81c5f41c813153fb4fa4
3
  size 4891730992
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f0569af1105bc64a7eba5df94b09a28dd1a741e7d8ada0b4ce1451d74020fc11
3
  size 4891730992
model-00002-of-00014.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2db1d891470ec63e9b689923525cb707db1b06f59ac29ce653e90a813bf71429
3
  size 4876059352
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f57336a2ed1720f249588f1251a9dfa424ab87b97ec17b47d0e795c723dcd76
3
  size 4876059352
model-00003-of-00014.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:07b7cc72769c338a378e118ad635d592933e78e761ea11bac1d43fb908933e75
3
  size 4876059384
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:84841ea454d8090d653181bb7973c5922d3bc942a191019615cf58f36cc0c008
3
  size 4876059384
model-00004-of-00014.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2a01a3a73959fbd601b6809fb8fd4fcb05ca072e1b76464e2c8ba007aae8da47
3
  size 4876059416
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e67aeaecec7a3f900b0968dcfeda9b0df774a0b2729989723f5d534bb946f1bc
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:ff65d94baa10cb2ca90b4d38a154658715c89d9bd87d716a1a2b4b861d2387db
3
  size 4876059416
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e1aae7c830f0d86469832b910d430f4a84fa900276ab6255f89994591451603
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:beede200dcd68a2eacb4effd9838dbfa36eac7ecfa4ac33c68ada10087413ae1
3
  size 4876059416
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:68007df1d11a99991ff77ccc99c57c3b5d4d6da08c97d63e8226313dcc1baa66
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:bcdb98ae0d0b8c3ba18c31b1955f190568b60d908b383601ab4101bdca4b88f8
3
  size 4876059416
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e6ac37eee3ccda0b3cf1f5beb1e31c95f512170d19c0e360c5d8bacd7adc58c
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:b7d84c47a22f767df82c77d54777740b66647b8f66e12cef88e5300f77accd8c
3
  size 4876059416
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff63d13492ddaab2387b3263a026b5d48bcdc5e2b192883739c300ae57a7a11d
3
  size 4876059416
model-00009-of-00014.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7ffb64942988c0b28a0cbc24a9a3e1967fa06fdc9402c084c4fadbb5a3f36c5d
3
  size 4876059416
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f3901ef9e5d9e830e5c2468279b2e7a8a503c1371bd74821e7a274e7cb25397
3
  size 4876059416
model-00010-of-00014.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:33db9a4ac1010f1287f92abb66cba172f2d0d627dfec10ec40989e5f45ea55b6
3
  size 4876059416
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:53f25810763b73a83f4df42af7a46565e55446a42113969c6763bbcebcaf2c57
3
  size 4876059416
model-00011-of-00014.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9b000ce06ed71377fccc04b3ac57905dd0621bca9476ea7410cbcfea1d5a1283
3
  size 4876059416
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e45a612c1e2d1eb9216bcb59c976a60edee1d227cd2c290d4203e06a2400cc6e
3
  size 4876059416
model-00012-of-00014.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:13ed129d96d05999ab0f186387e99c4425f4a358260cce229348eb611c478d8a
3
  size 4876059416
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e993d25bd631c4ee931eeeaf90b02a7d3ae052f8868a8d7d8cbbe482e7cb3f5
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:f094169463578e8688b93864bc77ff09c37fc757020a29fadfa7067524cb3e9f
3
  size 4876059416
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49a4ce9393469311f5adafbe934e11ca3afbfaa5bcf2b3f9ca26ca050ce0d24c
3
  size 4876059416
model-00014-of-00014.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7a98239c1c417cf0a8b79d84b8c001d66b72479a4144bfdcab34531f5272d0a3
3
  size 2123397800
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:26c84ea5731aba855ddfdf002b1f865718a7bfcf5882c35ceb703638a7778ee7
3
  size 2123397800
trainer_log.jsonl CHANGED
@@ -1,20 +1,16 @@
1
- {"current_steps": 1, "total_steps": 70, "loss": 1.0886, "lr": 2.8571428571428573e-06, "epoch": 0.09375, "percentage": 1.43, "elapsed_time": "0:01:06", "remaining_time": "1:16:21"}
2
- {"current_steps": 2, "total_steps": 70, "loss": 1.0553, "lr": 5.7142857142857145e-06, "epoch": 0.1875, "percentage": 2.86, "elapsed_time": "0:02:07", "remaining_time": "1:12:02"}
3
- {"current_steps": 3, "total_steps": 70, "loss": 1.1395, "lr": 8.571428571428571e-06, "epoch": 0.28125, "percentage": 4.29, "elapsed_time": "0:03:06", "remaining_time": "1:09:34"}
4
- {"current_steps": 4, "total_steps": 70, "loss": 1.0206, "lr": 1.1428571428571429e-05, "epoch": 0.375, "percentage": 5.71, "elapsed_time": "0:04:10", "remaining_time": "1:08:50"}
5
- {"current_steps": 5, "total_steps": 70, "loss": 1.0315, "lr": 1.4285714285714287e-05, "epoch": 0.46875, "percentage": 7.14, "elapsed_time": "0:05:12", "remaining_time": "1:07:44"}
6
- {"current_steps": 6, "total_steps": 70, "loss": 1.0318, "lr": 1.7142857142857142e-05, "epoch": 0.5625, "percentage": 8.57, "elapsed_time": "0:06:13", "remaining_time": "1:06:25"}
7
- {"current_steps": 7, "total_steps": 70, "loss": 0.9626, "lr": 2e-05, "epoch": 0.65625, "percentage": 10.0, "elapsed_time": "0:07:18", "remaining_time": "1:05:43"}
8
- {"current_steps": 8, "total_steps": 70, "loss": 0.9187, "lr": 1.9987569212189224e-05, "epoch": 0.75, "percentage": 11.43, "elapsed_time": "0:08:23", "remaining_time": "1:04:58"}
9
- {"current_steps": 9, "total_steps": 70, "loss": 0.8968, "lr": 1.9950307753654016e-05, "epoch": 0.84375, "percentage": 12.86, "elapsed_time": "0:09:26", "remaining_time": "1:04:02"}
10
- {"current_steps": 10, "total_steps": 70, "loss": 0.8653, "lr": 1.9888308262251286e-05, "epoch": 0.9375, "percentage": 14.29, "elapsed_time": "0:10:25", "remaining_time": "1:02:33"}
11
- {"current_steps": 11, "total_steps": 70, "loss": 0.8784, "lr": 1.9801724878485438e-05, "epoch": 1.0625, "percentage": 15.71, "elapsed_time": "0:21:12", "remaining_time": "1:53:46"}
12
- {"current_steps": 12, "total_steps": 70, "loss": 0.8623, "lr": 1.969077286229078e-05, "epoch": 1.15625, "percentage": 17.14, "elapsed_time": "0:22:17", "remaining_time": "1:47:45"}
13
- {"current_steps": 13, "total_steps": 70, "loss": 0.847, "lr": 1.955572805786141e-05, "epoch": 1.25, "percentage": 18.57, "elapsed_time": "0:23:18", "remaining_time": "1:42:13"}
14
- {"current_steps": 14, "total_steps": 70, "loss": 0.8363, "lr": 1.9396926207859085e-05, "epoch": 1.34375, "percentage": 20.0, "elapsed_time": "0:24:20", "remaining_time": "1:37:23"}
15
- {"current_steps": 15, "total_steps": 70, "loss": 0.8276, "lr": 1.921476211870408e-05, "epoch": 1.4375, "percentage": 21.43, "elapsed_time": "0:25:23", "remaining_time": "1:33:06"}
16
- {"current_steps": 16, "total_steps": 70, "loss": 0.8409, "lr": 1.900968867902419e-05, "epoch": 1.53125, "percentage": 22.86, "elapsed_time": "0:26:25", "remaining_time": "1:29:10"}
17
- {"current_steps": 17, "total_steps": 70, "loss": 0.8399, "lr": 1.8782215733702286e-05, "epoch": 1.625, "percentage": 24.29, "elapsed_time": "0:27:28", "remaining_time": "1:25:40"}
18
- {"current_steps": 18, "total_steps": 70, "loss": 0.8647, "lr": 1.8532908816321557e-05, "epoch": 1.71875, "percentage": 25.71, "elapsed_time": "0:28:31", "remaining_time": "1:22:25"}
19
- {"current_steps": 19, "total_steps": 70, "loss": 0.7787, "lr": 1.826238774315995e-05, "epoch": 1.8125, "percentage": 27.14, "elapsed_time": "0:29:28", "remaining_time": "1:19:07"}
20
- {"current_steps": 20, "total_steps": 70, "loss": 0.817, "lr": 1.7971325072229227e-05, "epoch": 1.90625, "percentage": 28.57, "elapsed_time": "0:30:26", "remaining_time": "1:16:06"}
 
1
+ {"current_steps": 1, "total_steps": 70, "loss": 1.0886, "lr": 2.8571428571428573e-06, "epoch": 0.09523809523809523, "percentage": 1.43, "elapsed_time": "0:02:06", "remaining_time": "2:25:40"}
2
+ {"current_steps": 2, "total_steps": 70, "loss": 1.0553, "lr": 5.7142857142857145e-06, "epoch": 0.19047619047619047, "percentage": 2.86, "elapsed_time": "0:04:04", "remaining_time": "2:18:24"}
3
+ {"current_steps": 3, "total_steps": 70, "loss": 1.1396, "lr": 8.571428571428571e-06, "epoch": 0.2857142857142857, "percentage": 4.29, "elapsed_time": "0:05:57", "remaining_time": "2:13:04"}
4
+ {"current_steps": 4, "total_steps": 70, "loss": 1.0205, "lr": 1.1428571428571429e-05, "epoch": 0.38095238095238093, "percentage": 5.71, "elapsed_time": "0:07:44", "remaining_time": "2:07:42"}
5
+ {"current_steps": 5, "total_steps": 70, "loss": 1.0314, "lr": 1.4285714285714287e-05, "epoch": 0.47619047619047616, "percentage": 7.14, "elapsed_time": "0:09:38", "remaining_time": "2:05:20"}
6
+ {"current_steps": 6, "total_steps": 70, "loss": 1.0315, "lr": 1.7142857142857142e-05, "epoch": 0.5714285714285714, "percentage": 8.57, "elapsed_time": "0:11:27", "remaining_time": "2:02:18"}
7
+ {"current_steps": 7, "total_steps": 70, "loss": 0.962, "lr": 2e-05, "epoch": 0.6666666666666666, "percentage": 10.0, "elapsed_time": "0:13:18", "remaining_time": "1:59:50"}
8
+ {"current_steps": 8, "total_steps": 70, "loss": 0.9182, "lr": 1.9987569212189224e-05, "epoch": 0.7619047619047619, "percentage": 11.43, "elapsed_time": "0:15:24", "remaining_time": "1:59:28"}
9
+ {"current_steps": 9, "total_steps": 70, "loss": 0.8965, "lr": 1.9950307753654016e-05, "epoch": 0.8571428571428571, "percentage": 12.86, "elapsed_time": "0:17:17", "remaining_time": "1:57:14"}
10
+ {"current_steps": 10, "total_steps": 70, "loss": 0.8653, "lr": 1.9888308262251286e-05, "epoch": 0.9523809523809523, "percentage": 14.29, "elapsed_time": "0:19:08", "remaining_time": "1:54:50"}
11
+ {"current_steps": 11, "total_steps": 70, "loss": 0.8746, "lr": 1.9801724878485438e-05, "epoch": 1.0476190476190477, "percentage": 15.71, "elapsed_time": "0:32:19", "remaining_time": "2:53:21"}
12
+ {"current_steps": 12, "total_steps": 70, "loss": 0.8492, "lr": 1.969077286229078e-05, "epoch": 1.1428571428571428, "percentage": 17.14, "elapsed_time": "0:34:17", "remaining_time": "2:45:42"}
13
+ {"current_steps": 13, "total_steps": 70, "loss": 0.8375, "lr": 1.955572805786141e-05, "epoch": 1.2380952380952381, "percentage": 18.57, "elapsed_time": "0:36:19", "remaining_time": "2:39:16"}
14
+ {"current_steps": 14, "total_steps": 70, "loss": 0.8532, "lr": 1.9396926207859085e-05, "epoch": 1.3333333333333333, "percentage": 20.0, "elapsed_time": "0:38:11", "remaining_time": "2:32:45"}
15
+ {"current_steps": 15, "total_steps": 70, "loss": 0.8316, "lr": 1.921476211870408e-05, "epoch": 1.4285714285714286, "percentage": 21.43, "elapsed_time": "0:40:13", "remaining_time": "2:27:28"}
16
+ {"current_steps": 16, "total_steps": 70, "loss": 0.8317, "lr": 1.900968867902419e-05, "epoch": 1.5238095238095237, "percentage": 22.86, "elapsed_time": "0:42:02", "remaining_time": "2:21:53"}
 
 
 
 
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:510ff6a6e791536196c9abce411ddac8cd3c609e6242eb4768c79c1d42503446
3
  size 7224
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fbdb69ef5e771d54957083cd7d9fd132c6500d9d73a5b3bfaa8caa3abcf7c4e9
3
  size 7224