Hugging Face's logo

mlfoundations-dev
/
oh_v1.3_evol_instruct_x8

Text Generation
Transformers
Safetensors
llama
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Model card Files
xet
Community
sedrickkeh commited on
Commit
e784074
·
verified ·
1 Parent(s): b06b03a

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 +41 -0
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d9d81fc7f62612b0f55c0f73123489cd7736a1d04f87024efe84626740e659e7
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fdb19656907c5225a875be54b033aa66fec1b4d1ca18d173e688bbf44ae09312
3
  size 4976698672
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9a47e27aaddf734b59684fbd9c8e484e065a72e29c571ebd806c636be47fe71e
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:31a8b6df2460b8b85f343677be79a57fa1d4a800d2ce5cd8171ae76508a9ecf6
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:b23ed03479a4b528e8f7e8b8dc53817ce36145eceb3b3736c306dda20ff3d8f2
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6cac513412996112a59538d9d73489fbef049f67b3b8d5c2aec97347125c9de9
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:bdc2dc98394a579785f076cc998b6e454560bd54f8708ea79194152cd8e148d3
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff59925a65c5736d47057608839f0d5db18d085b1fef73b8d971103e83f7c7ce
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -39,3 +39,44 @@
39
  {"current_steps": 390, "total_steps": 1200, "loss": 0.8256, "lr": 5e-06, "epoch": 0.975, "percentage": 32.5, "elapsed_time": "3:31:46", "remaining_time": "7:19:50"}
40
  {"current_steps": 400, "total_steps": 1200, "loss": 0.8272, "lr": 5e-06, "epoch": 1.0, "percentage": 33.33, "elapsed_time": "3:37:12", "remaining_time": "7:14:24"}
41
  {"current_steps": 400, "total_steps": 1200, "eval_loss": 0.8262304067611694, "epoch": 1.0, "percentage": 33.33, "elapsed_time": "3:41:55", "remaining_time": "7:23:51"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
39
  {"current_steps": 390, "total_steps": 1200, "loss": 0.8256, "lr": 5e-06, "epoch": 0.975, "percentage": 32.5, "elapsed_time": "3:31:46", "remaining_time": "7:19:50"}
40
  {"current_steps": 400, "total_steps": 1200, "loss": 0.8272, "lr": 5e-06, "epoch": 1.0, "percentage": 33.33, "elapsed_time": "3:37:12", "remaining_time": "7:14:24"}
41
  {"current_steps": 400, "total_steps": 1200, "eval_loss": 0.8262304067611694, "epoch": 1.0, "percentage": 33.33, "elapsed_time": "3:41:55", "remaining_time": "7:23:51"}
42
+ {"current_steps": 410, "total_steps": 1200, "loss": 0.7842, "lr": 5e-06, "epoch": 1.025, "percentage": 34.17, "elapsed_time": "3:48:33", "remaining_time": "7:20:23"}
43
+ {"current_steps": 420, "total_steps": 1200, "loss": 0.7849, "lr": 5e-06, "epoch": 1.05, "percentage": 35.0, "elapsed_time": "3:53:59", "remaining_time": "7:14:33"}
44
+ {"current_steps": 430, "total_steps": 1200, "loss": 0.7849, "lr": 5e-06, "epoch": 1.075, "percentage": 35.83, "elapsed_time": "3:59:26", "remaining_time": "7:08:45"}
45
+ {"current_steps": 440, "total_steps": 1200, "loss": 0.779, "lr": 5e-06, "epoch": 1.1, "percentage": 36.67, "elapsed_time": "4:04:52", "remaining_time": "7:02:57"}
46
+ {"current_steps": 450, "total_steps": 1200, "loss": 0.7831, "lr": 5e-06, "epoch": 1.125, "percentage": 37.5, "elapsed_time": "4:10:19", "remaining_time": "6:57:12"}
47
+ {"current_steps": 460, "total_steps": 1200, "loss": 0.7818, "lr": 5e-06, "epoch": 1.15, "percentage": 38.33, "elapsed_time": "4:15:47", "remaining_time": "6:51:28"}
48
+ {"current_steps": 470, "total_steps": 1200, "loss": 0.7772, "lr": 5e-06, "epoch": 1.175, "percentage": 39.17, "elapsed_time": "4:21:14", "remaining_time": "6:45:46"}
49
+ {"current_steps": 480, "total_steps": 1200, "loss": 0.7813, "lr": 5e-06, "epoch": 1.2, "percentage": 40.0, "elapsed_time": "4:26:41", "remaining_time": "6:40:01"}
50
+ {"current_steps": 490, "total_steps": 1200, "loss": 0.7836, "lr": 5e-06, "epoch": 1.225, "percentage": 40.83, "elapsed_time": "4:32:07", "remaining_time": "6:34:18"}
51
+ {"current_steps": 500, "total_steps": 1200, "loss": 0.7801, "lr": 5e-06, "epoch": 1.25, "percentage": 41.67, "elapsed_time": "4:37:33", "remaining_time": "6:28:34"}
52
+ {"current_steps": 510, "total_steps": 1200, "loss": 0.7806, "lr": 5e-06, "epoch": 1.275, "percentage": 42.5, "elapsed_time": "4:42:59", "remaining_time": "6:22:51"}
53
+ {"current_steps": 520, "total_steps": 1200, "loss": 0.7776, "lr": 5e-06, "epoch": 1.3, "percentage": 43.33, "elapsed_time": "4:48:25", "remaining_time": "6:17:10"}
54
+ {"current_steps": 530, "total_steps": 1200, "loss": 0.7796, "lr": 5e-06, "epoch": 1.325, "percentage": 44.17, "elapsed_time": "4:53:52", "remaining_time": "6:11:29"}
55
+ {"current_steps": 540, "total_steps": 1200, "loss": 0.7823, "lr": 5e-06, "epoch": 1.35, "percentage": 45.0, "elapsed_time": "4:59:18", "remaining_time": "6:05:49"}
56
+ {"current_steps": 550, "total_steps": 1200, "loss": 0.7783, "lr": 5e-06, "epoch": 1.375, "percentage": 45.83, "elapsed_time": "5:04:43", "remaining_time": "6:00:08"}
57
+ {"current_steps": 560, "total_steps": 1200, "loss": 0.7755, "lr": 5e-06, "epoch": 1.4, "percentage": 46.67, "elapsed_time": "5:10:11", "remaining_time": "5:54:30"}
58
+ {"current_steps": 570, "total_steps": 1200, "loss": 0.7811, "lr": 5e-06, "epoch": 1.425, "percentage": 47.5, "elapsed_time": "5:15:38", "remaining_time": "5:48:52"}
59
+ {"current_steps": 580, "total_steps": 1200, "loss": 0.7783, "lr": 5e-06, "epoch": 1.45, "percentage": 48.33, "elapsed_time": "5:21:06", "remaining_time": "5:43:14"}
60
+ {"current_steps": 590, "total_steps": 1200, "loss": 0.7789, "lr": 5e-06, "epoch": 1.475, "percentage": 49.17, "elapsed_time": "5:26:31", "remaining_time": "5:37:35"}
61
+ {"current_steps": 600, "total_steps": 1200, "loss": 0.7732, "lr": 5e-06, "epoch": 1.5, "percentage": 50.0, "elapsed_time": "5:31:56", "remaining_time": "5:31:56"}
62
+ {"current_steps": 610, "total_steps": 1200, "loss": 0.7803, "lr": 5e-06, "epoch": 1.525, "percentage": 50.83, "elapsed_time": "5:37:22", "remaining_time": "5:26:19"}
63
+ {"current_steps": 620, "total_steps": 1200, "loss": 0.7771, "lr": 5e-06, "epoch": 1.55, "percentage": 51.67, "elapsed_time": "5:42:50", "remaining_time": "5:20:43"}
64
+ {"current_steps": 630, "total_steps": 1200, "loss": 0.7781, "lr": 5e-06, "epoch": 1.575, "percentage": 52.5, "elapsed_time": "5:48:16", "remaining_time": "5:15:06"}
65
+ {"current_steps": 640, "total_steps": 1200, "loss": 0.7803, "lr": 5e-06, "epoch": 1.6, "percentage": 53.33, "elapsed_time": "5:53:43", "remaining_time": "5:09:30"}
66
+ {"current_steps": 650, "total_steps": 1200, "loss": 0.7755, "lr": 5e-06, "epoch": 1.625, "percentage": 54.17, "elapsed_time": "5:59:07", "remaining_time": "5:03:52"}
67
+ {"current_steps": 660, "total_steps": 1200, "loss": 0.7784, "lr": 5e-06, "epoch": 1.65, "percentage": 55.0, "elapsed_time": "6:04:34", "remaining_time": "4:58:17"}
68
+ {"current_steps": 670, "total_steps": 1200, "loss": 0.7798, "lr": 5e-06, "epoch": 1.675, "percentage": 55.83, "elapsed_time": "6:10:01", "remaining_time": "4:52:42"}
69
+ {"current_steps": 680, "total_steps": 1200, "loss": 0.7779, "lr": 5e-06, "epoch": 1.7, "percentage": 56.67, "elapsed_time": "6:15:28", "remaining_time": "4:47:07"}
70
+ {"current_steps": 690, "total_steps": 1200, "loss": 0.7743, "lr": 5e-06, "epoch": 1.725, "percentage": 57.5, "elapsed_time": "6:20:56", "remaining_time": "4:41:33"}
71
+ {"current_steps": 700, "total_steps": 1200, "loss": 0.7764, "lr": 5e-06, "epoch": 1.75, "percentage": 58.33, "elapsed_time": "6:26:23", "remaining_time": "4:35:59"}
72
+ {"current_steps": 710, "total_steps": 1200, "loss": 0.7743, "lr": 5e-06, "epoch": 1.775, "percentage": 59.17, "elapsed_time": "6:31:50", "remaining_time": "4:30:25"}
73
+ {"current_steps": 720, "total_steps": 1200, "loss": 0.7795, "lr": 5e-06, "epoch": 1.8, "percentage": 60.0, "elapsed_time": "6:37:17", "remaining_time": "4:24:51"}
74
+ {"current_steps": 730, "total_steps": 1200, "loss": 0.7727, "lr": 5e-06, "epoch": 1.825, "percentage": 60.83, "elapsed_time": "6:42:44", "remaining_time": "4:19:17"}
75
+ {"current_steps": 740, "total_steps": 1200, "loss": 0.7716, "lr": 5e-06, "epoch": 1.85, "percentage": 61.67, "elapsed_time": "6:48:11", "remaining_time": "4:13:44"}
76
+ {"current_steps": 750, "total_steps": 1200, "loss": 0.7759, "lr": 5e-06, "epoch": 1.875, "percentage": 62.5, "elapsed_time": "6:53:38", "remaining_time": "4:08:11"}
77
+ {"current_steps": 760, "total_steps": 1200, "loss": 0.7725, "lr": 5e-06, "epoch": 1.9, "percentage": 63.33, "elapsed_time": "6:59:03", "remaining_time": "4:02:36"}
78
+ {"current_steps": 770, "total_steps": 1200, "loss": 0.7746, "lr": 5e-06, "epoch": 1.925, "percentage": 64.17, "elapsed_time": "7:04:28", "remaining_time": "3:57:02"}
79
+ {"current_steps": 780, "total_steps": 1200, "loss": 0.7762, "lr": 5e-06, "epoch": 1.95, "percentage": 65.0, "elapsed_time": "7:09:54", "remaining_time": "3:51:29"}
80
+ {"current_steps": 790, "total_steps": 1200, "loss": 0.771, "lr": 5e-06, "epoch": 1.975, "percentage": 65.83, "elapsed_time": "7:15:21", "remaining_time": "3:45:56"}
81
+ {"current_steps": 800, "total_steps": 1200, "loss": 0.7753, "lr": 5e-06, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "7:20:47", "remaining_time": "3:40:23"}
82
+ {"current_steps": 800, "total_steps": 1200, "eval_loss": 0.8092445731163025, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "7:25:26", "remaining_time": "3:42:43"}