Hugging Face's logo

mlfoundations-dev
/
hp_ablations_mistral_epoch3

Text Generation
Transformers
Safetensors
mistral
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
sedrickkeh commited on
Commit
17c719b
•
1 Parent(s): de775ee

Training in progress, epoch 1

Browse files
Files changed (4) hide show
  1. model-00001-of-00003.safetensors +1 -1
  2. model-00002-of-00003.safetensors +1 -1
  3. model-00003-of-00003.safetensors +1 -1
  4. trainer_log.jsonl +51 -0
model-00001-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c0fb20f47e1304ed34cfcf6dc48062899793d4b95e2ff5ed344466c2d42ee458
3
  size 4943162336
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5dcd6652b36325640355d9dc807db656bbf5747d4b7fe72934eb3f68b7213916
3
  size 4943162336
model-00002-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:81bc917ea02e2a6b3efc4a56d41076a3d174e221698f78d97d84155e98565f94
3
  size 4999819336
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37028ddcc0eef174a6dbc0baaaf5fa1b113016a67b72b8b21872fc42074341d4
3
  size 4999819336
model-00003-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2e390965a2e60077507da2776588f9db7be8a9daba083ab9f46f02d5574b6993
3
  size 4540516344
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfb4b03c6e0fc0bec16e4f5154cf10e19c40c14f2211207b8a7c3ebf726271cc
3
  size 4540516344
trainer_log.jsonl CHANGED
@@ -48,3 +48,54 @@
48
  {"current_steps": 480, "total_steps": 1479, "loss": 0.5511, "lr": 5e-06, "epoch": 0.9721518987341772, "percentage": 32.45, "elapsed_time": "3:45:46", "remaining_time": "7:49:53"}
49
  {"current_steps": 490, "total_steps": 1479, "loss": 0.5475, "lr": 5e-06, "epoch": 0.9924050632911392, "percentage": 33.13, "elapsed_time": "3:50:28", "remaining_time": "7:45:11"}
50
  {"current_steps": 493, "total_steps": 1479, "eval_loss": 0.13758791983127594, "epoch": 0.9984810126582279, "percentage": 33.33, "elapsed_time": "3:56:21", "remaining_time": "7:52:42"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
48
  {"current_steps": 480, "total_steps": 1479, "loss": 0.5511, "lr": 5e-06, "epoch": 0.9721518987341772, "percentage": 32.45, "elapsed_time": "3:45:46", "remaining_time": "7:49:53"}
49
  {"current_steps": 490, "total_steps": 1479, "loss": 0.5475, "lr": 5e-06, "epoch": 0.9924050632911392, "percentage": 33.13, "elapsed_time": "3:50:28", "remaining_time": "7:45:11"}
50
  {"current_steps": 493, "total_steps": 1479, "eval_loss": 0.13758791983127594, "epoch": 0.9984810126582279, "percentage": 33.33, "elapsed_time": "3:56:21", "remaining_time": "7:52:42"}
51
+ {"current_steps": 500, "total_steps": 1479, "loss": 0.5044, "lr": 5e-06, "epoch": 1.0131645569620253, "percentage": 33.81, "elapsed_time": "4:00:16", "remaining_time": "7:50:27"}
52
+ {"current_steps": 510, "total_steps": 1479, "loss": 0.4698, "lr": 5e-06, "epoch": 1.0334177215189873, "percentage": 34.48, "elapsed_time": "4:04:58", "remaining_time": "7:45:27"}
53
+ {"current_steps": 520, "total_steps": 1479, "loss": 0.4664, "lr": 5e-06, "epoch": 1.0536708860759494, "percentage": 35.16, "elapsed_time": "4:09:41", "remaining_time": "7:40:28"}
54
+ {"current_steps": 530, "total_steps": 1479, "loss": 0.4678, "lr": 5e-06, "epoch": 1.0739240506329113, "percentage": 35.84, "elapsed_time": "4:14:23", "remaining_time": "7:35:30"}
55
+ {"current_steps": 540, "total_steps": 1479, "loss": 0.4676, "lr": 5e-06, "epoch": 1.0941772151898734, "percentage": 36.51, "elapsed_time": "4:19:05", "remaining_time": "7:30:32"}
56
+ {"current_steps": 550, "total_steps": 1479, "loss": 0.4679, "lr": 5e-06, "epoch": 1.1144303797468353, "percentage": 37.19, "elapsed_time": "4:23:48", "remaining_time": "7:25:35"}
57
+ {"current_steps": 560, "total_steps": 1479, "loss": 0.4652, "lr": 5e-06, "epoch": 1.1346835443037975, "percentage": 37.86, "elapsed_time": "4:28:30", "remaining_time": "7:20:38"}
58
+ {"current_steps": 570, "total_steps": 1479, "loss": 0.4741, "lr": 5e-06, "epoch": 1.1549367088607596, "percentage": 38.54, "elapsed_time": "4:33:13", "remaining_time": "7:15:42"}
59
+ {"current_steps": 580, "total_steps": 1479, "loss": 0.4698, "lr": 5e-06, "epoch": 1.1751898734177215, "percentage": 39.22, "elapsed_time": "4:37:55", "remaining_time": "7:10:47"}
60
+ {"current_steps": 590, "total_steps": 1479, "loss": 0.4648, "lr": 5e-06, "epoch": 1.1954430379746834, "percentage": 39.89, "elapsed_time": "4:42:37", "remaining_time": "7:05:51"}
61
+ {"current_steps": 600, "total_steps": 1479, "loss": 0.4728, "lr": 5e-06, "epoch": 1.2156962025316456, "percentage": 40.57, "elapsed_time": "4:47:19", "remaining_time": "7:00:55"}
62
+ {"current_steps": 610, "total_steps": 1479, "loss": 0.4672, "lr": 5e-06, "epoch": 1.2359493670886077, "percentage": 41.24, "elapsed_time": "4:52:01", "remaining_time": "6:56:01"}
63
+ {"current_steps": 620, "total_steps": 1479, "loss": 0.4722, "lr": 5e-06, "epoch": 1.2562025316455696, "percentage": 41.92, "elapsed_time": "4:56:44", "remaining_time": "6:51:07"}
64
+ {"current_steps": 630, "total_steps": 1479, "loss": 0.4707, "lr": 5e-06, "epoch": 1.2764556962025315, "percentage": 42.6, "elapsed_time": "5:01:26", "remaining_time": "6:46:14"}
65
+ {"current_steps": 640, "total_steps": 1479, "loss": 0.4703, "lr": 5e-06, "epoch": 1.2967088607594937, "percentage": 43.27, "elapsed_time": "5:06:08", "remaining_time": "6:41:20"}
66
+ {"current_steps": 650, "total_steps": 1479, "loss": 0.4743, "lr": 5e-06, "epoch": 1.3169620253164558, "percentage": 43.95, "elapsed_time": "5:10:51", "remaining_time": "6:36:27"}
67
+ {"current_steps": 660, "total_steps": 1479, "loss": 0.4625, "lr": 5e-06, "epoch": 1.3372151898734177, "percentage": 44.62, "elapsed_time": "5:15:33", "remaining_time": "6:31:34"}
68
+ {"current_steps": 670, "total_steps": 1479, "loss": 0.4772, "lr": 5e-06, "epoch": 1.3574683544303796, "percentage": 45.3, "elapsed_time": "5:20:16", "remaining_time": "6:26:42"}
69
+ {"current_steps": 680, "total_steps": 1479, "loss": 0.4748, "lr": 5e-06, "epoch": 1.3777215189873417, "percentage": 45.98, "elapsed_time": "5:24:58", "remaining_time": "6:21:50"}
70
+ {"current_steps": 690, "total_steps": 1479, "loss": 0.4737, "lr": 5e-06, "epoch": 1.3979746835443039, "percentage": 46.65, "elapsed_time": "5:29:40", "remaining_time": "6:16:58"}
71
+ {"current_steps": 700, "total_steps": 1479, "loss": 0.4706, "lr": 5e-06, "epoch": 1.4182278481012658, "percentage": 47.33, "elapsed_time": "5:34:23", "remaining_time": "6:12:07"}
72
+ {"current_steps": 710, "total_steps": 1479, "loss": 0.4766, "lr": 5e-06, "epoch": 1.438481012658228, "percentage": 48.01, "elapsed_time": "5:39:05", "remaining_time": "6:07:16"}
73
+ {"current_steps": 720, "total_steps": 1479, "loss": 0.4764, "lr": 5e-06, "epoch": 1.4587341772151898, "percentage": 48.68, "elapsed_time": "5:43:47", "remaining_time": "6:02:24"}
74
+ {"current_steps": 730, "total_steps": 1479, "loss": 0.4788, "lr": 5e-06, "epoch": 1.478987341772152, "percentage": 49.36, "elapsed_time": "5:48:29", "remaining_time": "5:57:33"}
75
+ {"current_steps": 740, "total_steps": 1479, "loss": 0.4729, "lr": 5e-06, "epoch": 1.4992405063291139, "percentage": 50.03, "elapsed_time": "5:53:11", "remaining_time": "5:52:43"}
76
+ {"current_steps": 750, "total_steps": 1479, "loss": 0.4752, "lr": 5e-06, "epoch": 1.5194936708860758, "percentage": 50.71, "elapsed_time": "5:57:54", "remaining_time": "5:47:53"}
77
+ {"current_steps": 760, "total_steps": 1479, "loss": 0.4751, "lr": 5e-06, "epoch": 1.539746835443038, "percentage": 51.39, "elapsed_time": "6:02:37", "remaining_time": "5:43:03"}
78
+ {"current_steps": 770, "total_steps": 1479, "loss": 0.4745, "lr": 5e-06, "epoch": 1.56, "percentage": 52.06, "elapsed_time": "6:07:19", "remaining_time": "5:38:13"}
79
+ {"current_steps": 780, "total_steps": 1479, "loss": 0.4744, "lr": 5e-06, "epoch": 1.5802531645569622, "percentage": 52.74, "elapsed_time": "6:12:01", "remaining_time": "5:33:23"}
80
+ {"current_steps": 790, "total_steps": 1479, "loss": 0.4778, "lr": 5e-06, "epoch": 1.600506329113924, "percentage": 53.41, "elapsed_time": "6:16:43", "remaining_time": "5:28:33"}
81
+ {"current_steps": 800, "total_steps": 1479, "loss": 0.4749, "lr": 5e-06, "epoch": 1.620759493670886, "percentage": 54.09, "elapsed_time": "6:21:25", "remaining_time": "5:23:44"}
82
+ {"current_steps": 810, "total_steps": 1479, "loss": 0.4668, "lr": 5e-06, "epoch": 1.6410126582278481, "percentage": 54.77, "elapsed_time": "6:26:08", "remaining_time": "5:18:55"}
83
+ {"current_steps": 820, "total_steps": 1479, "loss": 0.4755, "lr": 5e-06, "epoch": 1.6612658227848103, "percentage": 55.44, "elapsed_time": "6:30:50", "remaining_time": "5:14:06"}
84
+ {"current_steps": 830, "total_steps": 1479, "loss": 0.4709, "lr": 5e-06, "epoch": 1.6815189873417722, "percentage": 56.12, "elapsed_time": "6:35:33", "remaining_time": "5:09:17"}
85
+ {"current_steps": 840, "total_steps": 1479, "loss": 0.473, "lr": 5e-06, "epoch": 1.701772151898734, "percentage": 56.8, "elapsed_time": "6:40:15", "remaining_time": "5:04:29"}
86
+ {"current_steps": 850, "total_steps": 1479, "loss": 0.4759, "lr": 5e-06, "epoch": 1.7220253164556962, "percentage": 57.47, "elapsed_time": "6:44:58", "remaining_time": "4:59:40"}
87
+ {"current_steps": 860, "total_steps": 1479, "loss": 0.4751, "lr": 5e-06, "epoch": 1.7422784810126584, "percentage": 58.15, "elapsed_time": "6:49:41", "remaining_time": "4:54:52"}
88
+ {"current_steps": 870, "total_steps": 1479, "loss": 0.476, "lr": 5e-06, "epoch": 1.7625316455696203, "percentage": 58.82, "elapsed_time": "6:54:23", "remaining_time": "4:50:04"}
89
+ {"current_steps": 880, "total_steps": 1479, "loss": 0.48, "lr": 5e-06, "epoch": 1.7827848101265822, "percentage": 59.5, "elapsed_time": "6:59:05", "remaining_time": "4:45:16"}
90
+ {"current_steps": 890, "total_steps": 1479, "loss": 0.477, "lr": 5e-06, "epoch": 1.8030379746835443, "percentage": 60.18, "elapsed_time": "7:03:48", "remaining_time": "4:40:28"}
91
+ {"current_steps": 900, "total_steps": 1479, "loss": 0.4753, "lr": 5e-06, "epoch": 1.8232911392405065, "percentage": 60.85, "elapsed_time": "7:08:30", "remaining_time": "4:35:40"}
92
+ {"current_steps": 910, "total_steps": 1479, "loss": 0.4771, "lr": 5e-06, "epoch": 1.8435443037974684, "percentage": 61.53, "elapsed_time": "7:13:13", "remaining_time": "4:30:52"}
93
+ {"current_steps": 920, "total_steps": 1479, "loss": 0.477, "lr": 5e-06, "epoch": 1.8637974683544303, "percentage": 62.2, "elapsed_time": "7:17:55", "remaining_time": "4:26:05"}
94
+ {"current_steps": 930, "total_steps": 1479, "loss": 0.4726, "lr": 5e-06, "epoch": 1.8840506329113924, "percentage": 62.88, "elapsed_time": "7:22:38", "remaining_time": "4:21:18"}
95
+ {"current_steps": 940, "total_steps": 1479, "loss": 0.4749, "lr": 5e-06, "epoch": 1.9043037974683545, "percentage": 63.56, "elapsed_time": "7:27:21", "remaining_time": "4:16:30"}
96
+ {"current_steps": 950, "total_steps": 1479, "loss": 0.4776, "lr": 5e-06, "epoch": 1.9245569620253165, "percentage": 64.23, "elapsed_time": "7:32:03", "remaining_time": "4:11:43"}
97
+ {"current_steps": 960, "total_steps": 1479, "loss": 0.4816, "lr": 5e-06, "epoch": 1.9448101265822784, "percentage": 64.91, "elapsed_time": "7:36:46", "remaining_time": "4:06:56"}
98
+ {"current_steps": 970, "total_steps": 1479, "loss": 0.4789, "lr": 5e-06, "epoch": 1.9650632911392405, "percentage": 65.58, "elapsed_time": "7:41:28", "remaining_time": "4:02:09"}
99
+ {"current_steps": 980, "total_steps": 1479, "loss": 0.4805, "lr": 5e-06, "epoch": 1.9853164556962026, "percentage": 66.26, "elapsed_time": "7:46:11", "remaining_time": "3:57:22"}
100
+ {"current_steps": 987, "total_steps": 1479, "eval_loss": 0.13782347738742828, "epoch": 1.999493670886076, "percentage": 66.73, "elapsed_time": "7:53:41", "remaining_time": "3:56:07"}
101
+ {"current_steps": 990, "total_steps": 1479, "loss": 0.4496, "lr": 5e-06, "epoch": 2.0060759493670886, "percentage": 66.94, "elapsed_time": "7:55:59", "remaining_time": "3:55:06"}