Hugging Face's logo

mlfoundations-dev
/
top_9_ranking_stackexchange

Text Generation
Transformers
Safetensors
llama
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Model card Files Community
sedrickkeh commited on
Commit
567ee5f
·
verified ·
1 Parent(s): 122954d

Training in progress, epoch 2

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:d6913fc5d8d847585d181b5a3f22a70a91c3e5929019caad583186089f4fa806
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f64b1950e068f0c3edbf728b7a60b95ee33c5ec8c92234d7c8f323cf7f2a37c
3
  size 4976698672
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:61f9faec26611239f34343bc81f7cc6f2bfa07e671e86699e422cca1385fa65f
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:679f61b0a9ee6e52252ffdedf73b72fc538f12c54eed45a7da515d8494bc5294
3
  size 4999802720
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8c95dffb73451b8e7d7b45a00ee1063390ee57396f1ca0597a56381546596c65
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4188a20a94ecf0df3c7cf47ffa9a5fee8bed1e44006f286178b51f768f7133fe
3
  size 4915916176
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9e715a9d9723d572355bec49a7f78c59f35135d7d0f9ec043aa93bae99535397
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:83e1d53f4798b57728ad5493471c7d8bb7a41685eb92fd8a2e8df5f541fd14cf
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -32,3 +32,38 @@
32
  {"current_steps": 320, "total_steps": 1005, "loss": 0.7876, "lr": 5e-06, "epoch": 0.9552238805970149, "percentage": 31.84, "elapsed_time": "5:07:17", "remaining_time": "10:57:47"}
33
  {"current_steps": 330, "total_steps": 1005, "loss": 0.788, "lr": 5e-06, "epoch": 0.9850746268656716, "percentage": 32.84, "elapsed_time": "5:16:53", "remaining_time": "10:48:11"}
34
  {"current_steps": 335, "total_steps": 1005, "eval_loss": 0.7820407152175903, "epoch": 1.0, "percentage": 33.33, "elapsed_time": "5:27:37", "remaining_time": "10:55:14"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
32
  {"current_steps": 320, "total_steps": 1005, "loss": 0.7876, "lr": 5e-06, "epoch": 0.9552238805970149, "percentage": 31.84, "elapsed_time": "5:07:17", "remaining_time": "10:57:47"}
33
  {"current_steps": 330, "total_steps": 1005, "loss": 0.788, "lr": 5e-06, "epoch": 0.9850746268656716, "percentage": 32.84, "elapsed_time": "5:16:53", "remaining_time": "10:48:11"}
34
  {"current_steps": 335, "total_steps": 1005, "eval_loss": 0.7820407152175903, "epoch": 1.0, "percentage": 33.33, "elapsed_time": "5:27:37", "remaining_time": "10:55:14"}
35
+ {"current_steps": 340, "total_steps": 1005, "loss": 0.7615, "lr": 5e-06, "epoch": 1.0149253731343284, "percentage": 33.83, "elapsed_time": "5:33:32", "remaining_time": "10:52:21"}
36
+ {"current_steps": 350, "total_steps": 1005, "loss": 0.7459, "lr": 5e-06, "epoch": 1.044776119402985, "percentage": 34.83, "elapsed_time": "5:43:09", "remaining_time": "10:42:11"}
37
+ {"current_steps": 360, "total_steps": 1005, "loss": 0.7394, "lr": 5e-06, "epoch": 1.0746268656716418, "percentage": 35.82, "elapsed_time": "5:52:45", "remaining_time": "10:32:01"}
38
+ {"current_steps": 370, "total_steps": 1005, "loss": 0.741, "lr": 5e-06, "epoch": 1.1044776119402986, "percentage": 36.82, "elapsed_time": "6:02:21", "remaining_time": "10:21:52"}
39
+ {"current_steps": 380, "total_steps": 1005, "loss": 0.7369, "lr": 5e-06, "epoch": 1.1343283582089552, "percentage": 37.81, "elapsed_time": "6:11:56", "remaining_time": "10:11:45"}
40
+ {"current_steps": 390, "total_steps": 1005, "loss": 0.7418, "lr": 5e-06, "epoch": 1.164179104477612, "percentage": 38.81, "elapsed_time": "6:21:34", "remaining_time": "10:01:42"}
41
+ {"current_steps": 400, "total_steps": 1005, "loss": 0.7414, "lr": 5e-06, "epoch": 1.1940298507462686, "percentage": 39.8, "elapsed_time": "6:31:10", "remaining_time": "9:51:39"}
42
+ {"current_steps": 410, "total_steps": 1005, "loss": 0.7457, "lr": 5e-06, "epoch": 1.2238805970149254, "percentage": 40.8, "elapsed_time": "6:40:47", "remaining_time": "9:41:38"}
43
+ {"current_steps": 420, "total_steps": 1005, "loss": 0.74, "lr": 5e-06, "epoch": 1.2537313432835822, "percentage": 41.79, "elapsed_time": "6:50:25", "remaining_time": "9:31:39"}
44
+ {"current_steps": 430, "total_steps": 1005, "loss": 0.7485, "lr": 5e-06, "epoch": 1.2835820895522387, "percentage": 42.79, "elapsed_time": "7:00:03", "remaining_time": "9:21:42"}
45
+ {"current_steps": 440, "total_steps": 1005, "loss": 0.7448, "lr": 5e-06, "epoch": 1.3134328358208955, "percentage": 43.78, "elapsed_time": "7:09:42", "remaining_time": "9:11:46"}
46
+ {"current_steps": 450, "total_steps": 1005, "loss": 0.736, "lr": 5e-06, "epoch": 1.3432835820895521, "percentage": 44.78, "elapsed_time": "7:19:18", "remaining_time": "9:01:48"}
47
+ {"current_steps": 460, "total_steps": 1005, "loss": 0.7411, "lr": 5e-06, "epoch": 1.373134328358209, "percentage": 45.77, "elapsed_time": "7:28:56", "remaining_time": "8:51:54"}
48
+ {"current_steps": 470, "total_steps": 1005, "loss": 0.7418, "lr": 5e-06, "epoch": 1.4029850746268657, "percentage": 46.77, "elapsed_time": "7:38:34", "remaining_time": "8:41:59"}
49
+ {"current_steps": 480, "total_steps": 1005, "loss": 0.7363, "lr": 5e-06, "epoch": 1.4328358208955223, "percentage": 47.76, "elapsed_time": "7:48:11", "remaining_time": "8:32:05"}
50
+ {"current_steps": 490, "total_steps": 1005, "loss": 0.744, "lr": 5e-06, "epoch": 1.462686567164179, "percentage": 48.76, "elapsed_time": "7:57:46", "remaining_time": "8:22:08"}
51
+ {"current_steps": 500, "total_steps": 1005, "loss": 0.7404, "lr": 5e-06, "epoch": 1.4925373134328357, "percentage": 49.75, "elapsed_time": "8:07:21", "remaining_time": "8:12:14"}
52
+ {"current_steps": 510, "total_steps": 1005, "loss": 0.7414, "lr": 5e-06, "epoch": 1.5223880597014925, "percentage": 50.75, "elapsed_time": "8:16:59", "remaining_time": "8:02:22"}
53
+ {"current_steps": 520, "total_steps": 1005, "loss": 0.7374, "lr": 5e-06, "epoch": 1.5522388059701493, "percentage": 51.74, "elapsed_time": "8:26:35", "remaining_time": "7:52:29"}
54
+ {"current_steps": 530, "total_steps": 1005, "loss": 0.7414, "lr": 5e-06, "epoch": 1.582089552238806, "percentage": 52.74, "elapsed_time": "8:36:10", "remaining_time": "7:42:36"}
55
+ {"current_steps": 540, "total_steps": 1005, "loss": 0.7354, "lr": 5e-06, "epoch": 1.6119402985074627, "percentage": 53.73, "elapsed_time": "8:45:45", "remaining_time": "7:32:44"}
56
+ {"current_steps": 550, "total_steps": 1005, "loss": 0.7422, "lr": 5e-06, "epoch": 1.6417910447761193, "percentage": 54.73, "elapsed_time": "8:55:21", "remaining_time": "7:22:53"}
57
+ {"current_steps": 560, "total_steps": 1005, "loss": 0.7359, "lr": 5e-06, "epoch": 1.671641791044776, "percentage": 55.72, "elapsed_time": "9:04:57", "remaining_time": "7:13:02"}
58
+ {"current_steps": 570, "total_steps": 1005, "loss": 0.7387, "lr": 5e-06, "epoch": 1.7014925373134329, "percentage": 56.72, "elapsed_time": "9:14:33", "remaining_time": "7:03:13"}
59
+ {"current_steps": 580, "total_steps": 1005, "loss": 0.7428, "lr": 5e-06, "epoch": 1.7313432835820897, "percentage": 57.71, "elapsed_time": "9:24:10", "remaining_time": "6:53:24"}
60
+ {"current_steps": 590, "total_steps": 1005, "loss": 0.7421, "lr": 5e-06, "epoch": 1.7611940298507462, "percentage": 58.71, "elapsed_time": "9:33:46", "remaining_time": "6:43:35"}
61
+ {"current_steps": 600, "total_steps": 1005, "loss": 0.7387, "lr": 5e-06, "epoch": 1.7910447761194028, "percentage": 59.7, "elapsed_time": "9:43:23", "remaining_time": "6:33:47"}
62
+ {"current_steps": 610, "total_steps": 1005, "loss": 0.7357, "lr": 5e-06, "epoch": 1.8208955223880596, "percentage": 60.7, "elapsed_time": "9:53:00", "remaining_time": "6:23:59"}
63
+ {"current_steps": 620, "total_steps": 1005, "loss": 0.7359, "lr": 5e-06, "epoch": 1.8507462686567164, "percentage": 61.69, "elapsed_time": "10:02:37", "remaining_time": "6:14:12"}
64
+ {"current_steps": 630, "total_steps": 1005, "loss": 0.7382, "lr": 5e-06, "epoch": 1.8805970149253732, "percentage": 62.69, "elapsed_time": "10:12:14", "remaining_time": "6:04:26"}
65
+ {"current_steps": 640, "total_steps": 1005, "loss": 0.7374, "lr": 5e-06, "epoch": 1.9104477611940298, "percentage": 63.68, "elapsed_time": "10:21:53", "remaining_time": "5:54:40"}
66
+ {"current_steps": 650, "total_steps": 1005, "loss": 0.7383, "lr": 5e-06, "epoch": 1.9402985074626866, "percentage": 64.68, "elapsed_time": "10:31:32", "remaining_time": "5:44:54"}
67
+ {"current_steps": 660, "total_steps": 1005, "loss": 0.7386, "lr": 5e-06, "epoch": 1.9701492537313432, "percentage": 65.67, "elapsed_time": "10:41:09", "remaining_time": "5:35:09"}
68
+ {"current_steps": 670, "total_steps": 1005, "loss": 0.7335, "lr": 5e-06, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "10:50:44", "remaining_time": "5:25:22"}
69
+ {"current_steps": 670, "total_steps": 1005, "eval_loss": 0.7694990634918213, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "10:56:42", "remaining_time": "5:28:21"}