Hugging Face's logo

mlfoundations-dev
/
hp_ablations_qwen_lr2e-6_dcftv1.2

Text Generation
Transformers
Safetensors
qwen2
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Model card Files
xet
Community
1
sedrickkeh commited on
Commit
22044af
·
verified ·
1 Parent(s): 40e11d5

Training in progress, epoch 1

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 +35 -0
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dd6ef2c8b7cde217709129a4882e9b89673d53b261a23bdbb5abf7167a7bd78d
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f986ae453a496481387a6021383b9aab71356256ca952db85a7446e0f8de722
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a166141e72b0bed44813946194d332d33c831d2f6c53d60f76c20b0dc3c64b7c
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb69f036064b5a5b88d72a49d14950e225c758b3e64ad50610b41dec03ba1c7f
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d1a3682ff2f91ab2f2f01f9ab9b88899ba9dbe9d3162d184401aaa2da1bf4bc5
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab4a51b39ab8a0a8403be253a3869e209ab73d2b3cf074c93286b92432239647
3
  size 4330865200
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bc22f5fd8b0e29702720fe8230b4b38358861a9ce1d8a1778dbdd1de43687500
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9c9a52d6f1a492f887bd2c852daf4c9dd2800fb6cf19fd3c6747e0d9572a241
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -33,3 +33,38 @@
33
  {"current_steps": 330, "total_steps": 1023, "loss": 0.6514, "learning_rate": 2e-06, "epoch": 0.9656181419166057, "percentage": 32.26, "elapsed_time": "4:48:38", "remaining_time": "10:06:08"}
34
  {"current_steps": 340, "total_steps": 1023, "loss": 0.6474, "learning_rate": 2e-06, "epoch": 0.9948792977322605, "percentage": 33.24, "elapsed_time": "4:57:22", "remaining_time": "9:57:23"}
35
  {"current_steps": 341, "total_steps": 1023, "eval_loss": 0.652036190032959, "epoch": 0.9978054133138259, "percentage": 33.33, "elapsed_time": "5:04:18", "remaining_time": "10:08:36"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
33
  {"current_steps": 330, "total_steps": 1023, "loss": 0.6514, "learning_rate": 2e-06, "epoch": 0.9656181419166057, "percentage": 32.26, "elapsed_time": "4:48:38", "remaining_time": "10:06:08"}
34
  {"current_steps": 340, "total_steps": 1023, "loss": 0.6474, "learning_rate": 2e-06, "epoch": 0.9948792977322605, "percentage": 33.24, "elapsed_time": "4:57:22", "remaining_time": "9:57:23"}
35
  {"current_steps": 341, "total_steps": 1023, "eval_loss": 0.652036190032959, "epoch": 0.9978054133138259, "percentage": 33.33, "elapsed_time": "5:04:18", "remaining_time": "10:08:36"}
36
+ {"current_steps": 350, "total_steps": 1023, "loss": 0.6779, "learning_rate": 2e-06, "epoch": 1.025237746891002, "percentage": 34.21, "elapsed_time": "5:12:55", "remaining_time": "10:01:41"}
37
+ {"current_steps": 360, "total_steps": 1023, "loss": 0.634, "learning_rate": 2e-06, "epoch": 1.054498902706657, "percentage": 35.19, "elapsed_time": "5:21:39", "remaining_time": "9:52:23"}
38
+ {"current_steps": 370, "total_steps": 1023, "loss": 0.6373, "learning_rate": 2e-06, "epoch": 1.0837600585223117, "percentage": 36.17, "elapsed_time": "5:30:25", "remaining_time": "9:43:08"}
39
+ {"current_steps": 380, "total_steps": 1023, "loss": 0.6345, "learning_rate": 2e-06, "epoch": 1.1130212143379663, "percentage": 37.15, "elapsed_time": "5:39:09", "remaining_time": "9:33:52"}
40
+ {"current_steps": 390, "total_steps": 1023, "loss": 0.6396, "learning_rate": 2e-06, "epoch": 1.142282370153621, "percentage": 38.12, "elapsed_time": "5:47:53", "remaining_time": "9:24:40"}
41
+ {"current_steps": 400, "total_steps": 1023, "loss": 0.641, "learning_rate": 2e-06, "epoch": 1.1715435259692757, "percentage": 39.1, "elapsed_time": "5:56:39", "remaining_time": "9:15:29"}
42
+ {"current_steps": 410, "total_steps": 1023, "loss": 0.6406, "learning_rate": 2e-06, "epoch": 1.2008046817849305, "percentage": 40.08, "elapsed_time": "6:05:24", "remaining_time": "9:06:20"}
43
+ {"current_steps": 420, "total_steps": 1023, "loss": 0.628, "learning_rate": 2e-06, "epoch": 1.2300658376005853, "percentage": 41.06, "elapsed_time": "6:14:09", "remaining_time": "8:57:11"}
44
+ {"current_steps": 430, "total_steps": 1023, "loss": 0.6383, "learning_rate": 2e-06, "epoch": 1.2593269934162399, "percentage": 42.03, "elapsed_time": "6:22:55", "remaining_time": "8:48:04"}
45
+ {"current_steps": 440, "total_steps": 1023, "loss": 0.6303, "learning_rate": 2e-06, "epoch": 1.2885881492318947, "percentage": 43.01, "elapsed_time": "6:31:39", "remaining_time": "8:38:56"}
46
+ {"current_steps": 450, "total_steps": 1023, "loss": 0.634, "learning_rate": 2e-06, "epoch": 1.3178493050475493, "percentage": 43.99, "elapsed_time": "6:40:24", "remaining_time": "8:29:51"}
47
+ {"current_steps": 460, "total_steps": 1023, "loss": 0.6314, "learning_rate": 2e-06, "epoch": 1.347110460863204, "percentage": 44.97, "elapsed_time": "6:49:08", "remaining_time": "8:20:45"}
48
+ {"current_steps": 470, "total_steps": 1023, "loss": 0.6284, "learning_rate": 2e-06, "epoch": 1.3763716166788589, "percentage": 45.94, "elapsed_time": "6:57:53", "remaining_time": "8:11:41"}
49
+ {"current_steps": 480, "total_steps": 1023, "loss": 0.6293, "learning_rate": 2e-06, "epoch": 1.4056327724945135, "percentage": 46.92, "elapsed_time": "7:06:37", "remaining_time": "8:02:37"}
50
+ {"current_steps": 490, "total_steps": 1023, "loss": 0.6358, "learning_rate": 2e-06, "epoch": 1.4348939283101683, "percentage": 47.9, "elapsed_time": "7:15:22", "remaining_time": "7:53:35"}
51
+ {"current_steps": 500, "total_steps": 1023, "loss": 0.6236, "learning_rate": 2e-06, "epoch": 1.464155084125823, "percentage": 48.88, "elapsed_time": "7:24:07", "remaining_time": "7:44:33"}
52
+ {"current_steps": 510, "total_steps": 1023, "loss": 0.6317, "learning_rate": 2e-06, "epoch": 1.4934162399414777, "percentage": 49.85, "elapsed_time": "7:32:52", "remaining_time": "7:35:32"}
53
+ {"current_steps": 520, "total_steps": 1023, "loss": 0.6341, "learning_rate": 2e-06, "epoch": 1.5226773957571325, "percentage": 50.83, "elapsed_time": "7:41:39", "remaining_time": "7:26:33"}
54
+ {"current_steps": 530, "total_steps": 1023, "loss": 0.6326, "learning_rate": 2e-06, "epoch": 1.5519385515727873, "percentage": 51.81, "elapsed_time": "7:50:24", "remaining_time": "7:17:34"}
55
+ {"current_steps": 540, "total_steps": 1023, "loss": 0.6392, "learning_rate": 2e-06, "epoch": 1.5811997073884418, "percentage": 52.79, "elapsed_time": "7:59:09", "remaining_time": "7:08:34"}
56
+ {"current_steps": 550, "total_steps": 1023, "loss": 0.6298, "learning_rate": 2e-06, "epoch": 1.6104608632040964, "percentage": 53.76, "elapsed_time": "8:07:56", "remaining_time": "6:59:37"}
57
+ {"current_steps": 560, "total_steps": 1023, "loss": 0.6313, "learning_rate": 2e-06, "epoch": 1.6397220190197512, "percentage": 54.74, "elapsed_time": "8:16:42", "remaining_time": "6:50:40"}
58
+ {"current_steps": 570, "total_steps": 1023, "loss": 0.6217, "learning_rate": 2e-06, "epoch": 1.668983174835406, "percentage": 55.72, "elapsed_time": "8:25:29", "remaining_time": "6:41:43"}
59
+ {"current_steps": 580, "total_steps": 1023, "loss": 0.6311, "learning_rate": 2e-06, "epoch": 1.6982443306510606, "percentage": 56.7, "elapsed_time": "8:34:15", "remaining_time": "6:32:47"}
60
+ {"current_steps": 590, "total_steps": 1023, "loss": 0.6311, "learning_rate": 2e-06, "epoch": 1.7275054864667154, "percentage": 57.67, "elapsed_time": "8:43:02", "remaining_time": "6:23:51"}
61
+ {"current_steps": 600, "total_steps": 1023, "loss": 0.6281, "learning_rate": 2e-06, "epoch": 1.7567666422823702, "percentage": 58.65, "elapsed_time": "8:51:48", "remaining_time": "6:14:55"}
62
+ {"current_steps": 610, "total_steps": 1023, "loss": 0.6305, "learning_rate": 2e-06, "epoch": 1.7860277980980248, "percentage": 59.63, "elapsed_time": "9:00:33", "remaining_time": "6:05:59"}
63
+ {"current_steps": 620, "total_steps": 1023, "loss": 0.6307, "learning_rate": 2e-06, "epoch": 1.8152889539136796, "percentage": 60.61, "elapsed_time": "9:09:19", "remaining_time": "5:57:03"}
64
+ {"current_steps": 630, "total_steps": 1023, "loss": 0.6297, "learning_rate": 2e-06, "epoch": 1.8445501097293344, "percentage": 61.58, "elapsed_time": "9:18:05", "remaining_time": "5:48:08"}
65
+ {"current_steps": 640, "total_steps": 1023, "loss": 0.6243, "learning_rate": 2e-06, "epoch": 1.873811265544989, "percentage": 62.56, "elapsed_time": "9:26:51", "remaining_time": "5:39:14"}
66
+ {"current_steps": 650, "total_steps": 1023, "loss": 0.6303, "learning_rate": 2e-06, "epoch": 1.9030724213606436, "percentage": 63.54, "elapsed_time": "9:35:38", "remaining_time": "5:30:19"}
67
+ {"current_steps": 660, "total_steps": 1023, "loss": 0.6304, "learning_rate": 2e-06, "epoch": 1.9323335771762986, "percentage": 64.52, "elapsed_time": "9:44:24", "remaining_time": "5:21:25"}
68
+ {"current_steps": 670, "total_steps": 1023, "loss": 0.619, "learning_rate": 2e-06, "epoch": 1.9615947329919532, "percentage": 65.49, "elapsed_time": "9:53:08", "remaining_time": "5:12:30"}
69
+ {"current_steps": 680, "total_steps": 1023, "loss": 0.6339, "learning_rate": 2e-06, "epoch": 1.9908558888076078, "percentage": 66.47, "elapsed_time": "10:01:52", "remaining_time": "5:03:35"}
70
+ {"current_steps": 682, "total_steps": 1023, "eval_loss": 0.6420042514801025, "epoch": 1.9967081199707388, "percentage": 66.67, "elapsed_time": "10:09:58", "remaining_time": "5:04:59"}