Hugging Face's logo

mlfoundations-dev
/
top_10_ranking_stackexchange

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
4a9c919
·
verified ·
1 Parent(s): 4638a01

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 +38 -0
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a43b392e5d2b32b2f72c9ebb256ec801dbd17c4e9bc89796d024a6cb2f98217e
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e64f889c919712fe83536853590c7f046f84ddfdcf5233deebf9f8245d1336d
3
  size 4976698672
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3bea87e8d760799ca522131efa5d4e4c622e715e04ef88153fc81773b527ece6
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:631122b613c021e963599fe69b4c66b4ba9110b81d5d3c960f9bf7ef2998121d
3
  size 4999802720
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3ba86719738465aa8c32072ec195dceb17993bddcab51ba339a2de0af8ee7a67
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d7ab7477ee75c799d1f0504d6a190399feccb676aac24ad6ef8724d95bff9346
3
  size 4915916176
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:49cc13e0e25eee327d76cd669d33584accb1d24bc2bc5106cafd182beb14575f
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b7d099da71419d3f38eb560e072b379c0ee97c0b62740124c2e4d00c83cff7e4
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -36,3 +36,41 @@
36
  {"current_steps": 360, "total_steps": 1119, "loss": 0.8019, "lr": 5e-06, "epoch": 0.964824120603015, "percentage": 32.17, "elapsed_time": "5:45:17", "remaining_time": "12:07:59"}
37
  {"current_steps": 370, "total_steps": 1119, "loss": 0.7989, "lr": 5e-06, "epoch": 0.9916247906197655, "percentage": 33.07, "elapsed_time": "5:54:52", "remaining_time": "11:58:22"}
38
  {"current_steps": 373, "total_steps": 1119, "eval_loss": 0.7980747222900391, "epoch": 0.9996649916247906, "percentage": 33.33, "elapsed_time": "6:04:28", "remaining_time": "12:08:56"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
36
  {"current_steps": 360, "total_steps": 1119, "loss": 0.8019, "lr": 5e-06, "epoch": 0.964824120603015, "percentage": 32.17, "elapsed_time": "5:45:17", "remaining_time": "12:07:59"}
37
  {"current_steps": 370, "total_steps": 1119, "loss": 0.7989, "lr": 5e-06, "epoch": 0.9916247906197655, "percentage": 33.07, "elapsed_time": "5:54:52", "remaining_time": "11:58:22"}
38
  {"current_steps": 373, "total_steps": 1119, "eval_loss": 0.7980747222900391, "epoch": 0.9996649916247906, "percentage": 33.33, "elapsed_time": "6:04:28", "remaining_time": "12:08:56"}
39
+ {"current_steps": 380, "total_steps": 1119, "loss": 0.846, "lr": 5e-06, "epoch": 1.018425460636516, "percentage": 33.96, "elapsed_time": "6:12:14", "remaining_time": "12:03:54"}
40
+ {"current_steps": 390, "total_steps": 1119, "loss": 0.7553, "lr": 5e-06, "epoch": 1.0452261306532664, "percentage": 34.85, "elapsed_time": "6:21:50", "remaining_time": "11:53:45"}
41
+ {"current_steps": 400, "total_steps": 1119, "loss": 0.7609, "lr": 5e-06, "epoch": 1.0720268006700167, "percentage": 35.75, "elapsed_time": "6:31:26", "remaining_time": "11:43:37"}
42
+ {"current_steps": 410, "total_steps": 1119, "loss": 0.7594, "lr": 5e-06, "epoch": 1.0988274706867671, "percentage": 36.64, "elapsed_time": "6:41:02", "remaining_time": "11:33:29"}
43
+ {"current_steps": 420, "total_steps": 1119, "loss": 0.7555, "lr": 5e-06, "epoch": 1.1256281407035176, "percentage": 37.53, "elapsed_time": "6:50:37", "remaining_time": "11:23:23"}
44
+ {"current_steps": 430, "total_steps": 1119, "loss": 0.7554, "lr": 5e-06, "epoch": 1.152428810720268, "percentage": 38.43, "elapsed_time": "7:00:13", "remaining_time": "11:13:19"}
45
+ {"current_steps": 440, "total_steps": 1119, "loss": 0.7592, "lr": 5e-06, "epoch": 1.1792294807370185, "percentage": 39.32, "elapsed_time": "7:09:49", "remaining_time": "11:03:18"}
46
+ {"current_steps": 450, "total_steps": 1119, "loss": 0.7569, "lr": 5e-06, "epoch": 1.2060301507537687, "percentage": 40.21, "elapsed_time": "7:19:25", "remaining_time": "10:53:16"}
47
+ {"current_steps": 460, "total_steps": 1119, "loss": 0.7545, "lr": 5e-06, "epoch": 1.2328308207705192, "percentage": 41.11, "elapsed_time": "7:29:00", "remaining_time": "10:43:14"}
48
+ {"current_steps": 470, "total_steps": 1119, "loss": 0.755, "lr": 5e-06, "epoch": 1.2596314907872697, "percentage": 42.0, "elapsed_time": "7:38:36", "remaining_time": "10:33:16"}
49
+ {"current_steps": 480, "total_steps": 1119, "loss": 0.7546, "lr": 5e-06, "epoch": 1.2864321608040201, "percentage": 42.9, "elapsed_time": "7:48:13", "remaining_time": "10:23:19"}
50
+ {"current_steps": 490, "total_steps": 1119, "loss": 0.7613, "lr": 5e-06, "epoch": 1.3132328308207706, "percentage": 43.79, "elapsed_time": "7:57:48", "remaining_time": "10:13:20"}
51
+ {"current_steps": 500, "total_steps": 1119, "loss": 0.7558, "lr": 5e-06, "epoch": 1.3400335008375208, "percentage": 44.68, "elapsed_time": "8:07:23", "remaining_time": "10:03:23"}
52
+ {"current_steps": 510, "total_steps": 1119, "loss": 0.7513, "lr": 5e-06, "epoch": 1.3668341708542713, "percentage": 45.58, "elapsed_time": "8:16:58", "remaining_time": "9:53:26"}
53
+ {"current_steps": 520, "total_steps": 1119, "loss": 0.757, "lr": 5e-06, "epoch": 1.3936348408710217, "percentage": 46.47, "elapsed_time": "8:26:34", "remaining_time": "9:43:31"}
54
+ {"current_steps": 530, "total_steps": 1119, "loss": 0.7549, "lr": 5e-06, "epoch": 1.4204355108877722, "percentage": 47.36, "elapsed_time": "8:36:10", "remaining_time": "9:33:37"}
55
+ {"current_steps": 540, "total_steps": 1119, "loss": 0.7546, "lr": 5e-06, "epoch": 1.4472361809045227, "percentage": 48.26, "elapsed_time": "8:45:45", "remaining_time": "9:23:43"}
56
+ {"current_steps": 550, "total_steps": 1119, "loss": 0.7483, "lr": 5e-06, "epoch": 1.474036850921273, "percentage": 49.15, "elapsed_time": "8:55:21", "remaining_time": "9:13:50"}
57
+ {"current_steps": 560, "total_steps": 1119, "loss": 0.7554, "lr": 5e-06, "epoch": 1.5008375209380236, "percentage": 50.04, "elapsed_time": "9:04:57", "remaining_time": "9:03:59"}
58
+ {"current_steps": 570, "total_steps": 1119, "loss": 0.747, "lr": 5e-06, "epoch": 1.5276381909547738, "percentage": 50.94, "elapsed_time": "9:14:34", "remaining_time": "8:54:08"}
59
+ {"current_steps": 580, "total_steps": 1119, "loss": 0.7563, "lr": 5e-06, "epoch": 1.5544388609715243, "percentage": 51.83, "elapsed_time": "9:24:08", "remaining_time": "8:44:15"}
60
+ {"current_steps": 590, "total_steps": 1119, "loss": 0.7597, "lr": 5e-06, "epoch": 1.5812395309882747, "percentage": 52.73, "elapsed_time": "9:33:43", "remaining_time": "8:34:24"}
61
+ {"current_steps": 600, "total_steps": 1119, "loss": 0.7538, "lr": 5e-06, "epoch": 1.608040201005025, "percentage": 53.62, "elapsed_time": "9:43:20", "remaining_time": "8:24:35"}
62
+ {"current_steps": 610, "total_steps": 1119, "loss": 0.7552, "lr": 5e-06, "epoch": 1.6348408710217757, "percentage": 54.51, "elapsed_time": "9:52:57", "remaining_time": "8:14:46"}
63
+ {"current_steps": 620, "total_steps": 1119, "loss": 0.7556, "lr": 5e-06, "epoch": 1.661641541038526, "percentage": 55.41, "elapsed_time": "10:02:34", "remaining_time": "8:04:58"}
64
+ {"current_steps": 630, "total_steps": 1119, "loss": 0.7523, "lr": 5e-06, "epoch": 1.6884422110552764, "percentage": 56.3, "elapsed_time": "10:12:11", "remaining_time": "7:55:10"}
65
+ {"current_steps": 640, "total_steps": 1119, "loss": 0.7548, "lr": 5e-06, "epoch": 1.7152428810720268, "percentage": 57.19, "elapsed_time": "10:21:48", "remaining_time": "7:45:23"}
66
+ {"current_steps": 650, "total_steps": 1119, "loss": 0.7506, "lr": 5e-06, "epoch": 1.742043551088777, "percentage": 58.09, "elapsed_time": "10:31:25", "remaining_time": "7:35:35"}
67
+ {"current_steps": 660, "total_steps": 1119, "loss": 0.7526, "lr": 5e-06, "epoch": 1.7688442211055277, "percentage": 58.98, "elapsed_time": "10:41:02", "remaining_time": "7:25:48"}
68
+ {"current_steps": 670, "total_steps": 1119, "loss": 0.756, "lr": 5e-06, "epoch": 1.795644891122278, "percentage": 59.87, "elapsed_time": "10:50:37", "remaining_time": "7:16:01"}
69
+ {"current_steps": 680, "total_steps": 1119, "loss": 0.7516, "lr": 5e-06, "epoch": 1.8224455611390284, "percentage": 60.77, "elapsed_time": "11:00:12", "remaining_time": "7:06:13"}
70
+ {"current_steps": 690, "total_steps": 1119, "loss": 0.7552, "lr": 5e-06, "epoch": 1.849246231155779, "percentage": 61.66, "elapsed_time": "11:09:49", "remaining_time": "6:56:27"}
71
+ {"current_steps": 700, "total_steps": 1119, "loss": 0.7506, "lr": 5e-06, "epoch": 1.8760469011725294, "percentage": 62.56, "elapsed_time": "11:19:24", "remaining_time": "6:46:40"}
72
+ {"current_steps": 710, "total_steps": 1119, "loss": 0.7512, "lr": 5e-06, "epoch": 1.9028475711892798, "percentage": 63.45, "elapsed_time": "11:29:00", "remaining_time": "6:36:54"}
73
+ {"current_steps": 720, "total_steps": 1119, "loss": 0.7523, "lr": 5e-06, "epoch": 1.92964824120603, "percentage": 64.34, "elapsed_time": "11:38:36", "remaining_time": "6:27:08"}
74
+ {"current_steps": 730, "total_steps": 1119, "loss": 0.7489, "lr": 5e-06, "epoch": 1.9564489112227805, "percentage": 65.24, "elapsed_time": "11:48:13", "remaining_time": "6:17:23"}
75
+ {"current_steps": 740, "total_steps": 1119, "loss": 0.7568, "lr": 5e-06, "epoch": 1.983249581239531, "percentage": 66.13, "elapsed_time": "11:57:50", "remaining_time": "6:07:38"}
76
+ {"current_steps": 746, "total_steps": 1119, "eval_loss": 0.7848142385482788, "epoch": 1.9993299832495812, "percentage": 66.67, "elapsed_time": "12:10:27", "remaining_time": "6:05:13"}