Hugging Face's logo

mlfoundations-dev
/
oh_v1.3_evol_instruct_x4

Text Generation
Transformers
Safetensors
llama
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Model card Files
xet
Community
sedrickkeh commited on
Commit
2910f76
·
verified ·
1 Parent(s): c84107e

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 +41 -0
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:81ced73bab632c2cdd65333159528c8e6e8ca3909ca9ba2fa7d6362ba1bf928b
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4fbc9025a3c36aa92270726707bcb364b8974cac8eae9e9b8b7a4516efadccce
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:b7b4391df1f3a883fa3c0ee577464803fd2a51cccf3320b6b3392e19a1df34ac
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b83c4b96c07e6b1cf5c74b9b677d2843f7e477a95aff4a76df643e3c56577738
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:a789b3aa64201e336df959028e2683c117515fcfb4298791abd27490b0510563
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63a0cbeb36c7832a9e5d62b9b719576e9d19cb0a9c70a319353ebca727df8d47
3
  size 4915916176
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5dcea4cc9dffac4639c33ec4dac7d850e98297bcd8b201ef29e9c268cc433cc2
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b2cbab2687c53cce2bfa947024e837002c8db0a0d57f85d9545e92e4c65da4b0
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -39,3 +39,44 @@
39
  {"current_steps": 390, "total_steps": 1197, "loss": 0.7876, "lr": 5e-06, "epoch": 0.9762202753441802, "percentage": 32.58, "elapsed_time": "3:26:08", "remaining_time": "7:06:33"}
40
  {"current_steps": 399, "total_steps": 1197, "eval_loss": 0.7894856929779053, "epoch": 0.9987484355444305, "percentage": 33.33, "elapsed_time": "3:35:34", "remaining_time": "7:11:09"}
41
  {"current_steps": 400, "total_steps": 1197, "loss": 0.8446, "lr": 5e-06, "epoch": 1.0018773466833542, "percentage": 33.42, "elapsed_time": "3:37:09", "remaining_time": "7:12:41"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
39
  {"current_steps": 390, "total_steps": 1197, "loss": 0.7876, "lr": 5e-06, "epoch": 0.9762202753441802, "percentage": 32.58, "elapsed_time": "3:26:08", "remaining_time": "7:06:33"}
40
  {"current_steps": 399, "total_steps": 1197, "eval_loss": 0.7894856929779053, "epoch": 0.9987484355444305, "percentage": 33.33, "elapsed_time": "3:35:34", "remaining_time": "7:11:09"}
41
  {"current_steps": 400, "total_steps": 1197, "loss": 0.8446, "lr": 5e-06, "epoch": 1.0018773466833542, "percentage": 33.42, "elapsed_time": "3:37:09", "remaining_time": "7:12:41"}
42
+ {"current_steps": 410, "total_steps": 1197, "loss": 0.7458, "lr": 5e-06, "epoch": 1.0269086357947435, "percentage": 34.25, "elapsed_time": "3:42:27", "remaining_time": "7:07:00"}
43
+ {"current_steps": 420, "total_steps": 1197, "loss": 0.7468, "lr": 5e-06, "epoch": 1.0519399249061328, "percentage": 35.09, "elapsed_time": "3:47:44", "remaining_time": "7:01:19"}
44
+ {"current_steps": 430, "total_steps": 1197, "loss": 0.7482, "lr": 5e-06, "epoch": 1.0769712140175218, "percentage": 35.92, "elapsed_time": "3:53:02", "remaining_time": "6:55:41"}
45
+ {"current_steps": 440, "total_steps": 1197, "loss": 0.7462, "lr": 5e-06, "epoch": 1.1020025031289111, "percentage": 36.76, "elapsed_time": "3:58:20", "remaining_time": "6:50:02"}
46
+ {"current_steps": 450, "total_steps": 1197, "loss": 0.7451, "lr": 5e-06, "epoch": 1.1270337922403004, "percentage": 37.59, "elapsed_time": "4:03:37", "remaining_time": "6:44:24"}
47
+ {"current_steps": 460, "total_steps": 1197, "loss": 0.7455, "lr": 5e-06, "epoch": 1.1520650813516897, "percentage": 38.43, "elapsed_time": "4:08:55", "remaining_time": "6:38:48"}
48
+ {"current_steps": 470, "total_steps": 1197, "loss": 0.7464, "lr": 5e-06, "epoch": 1.1770963704630788, "percentage": 39.26, "elapsed_time": "4:14:12", "remaining_time": "6:33:12"}
49
+ {"current_steps": 480, "total_steps": 1197, "loss": 0.7467, "lr": 5e-06, "epoch": 1.202127659574468, "percentage": 40.1, "elapsed_time": "4:19:30", "remaining_time": "6:27:38"}
50
+ {"current_steps": 490, "total_steps": 1197, "loss": 0.7466, "lr": 5e-06, "epoch": 1.2271589486858574, "percentage": 40.94, "elapsed_time": "4:24:48", "remaining_time": "6:22:05"}
51
+ {"current_steps": 500, "total_steps": 1197, "loss": 0.7472, "lr": 5e-06, "epoch": 1.2521902377972465, "percentage": 41.77, "elapsed_time": "4:30:06", "remaining_time": "6:16:32"}
52
+ {"current_steps": 510, "total_steps": 1197, "loss": 0.7483, "lr": 5e-06, "epoch": 1.2772215269086358, "percentage": 42.61, "elapsed_time": "4:35:24", "remaining_time": "6:10:59"}
53
+ {"current_steps": 520, "total_steps": 1197, "loss": 0.7435, "lr": 5e-06, "epoch": 1.302252816020025, "percentage": 43.44, "elapsed_time": "4:40:42", "remaining_time": "6:05:27"}
54
+ {"current_steps": 530, "total_steps": 1197, "loss": 0.7466, "lr": 5e-06, "epoch": 1.3272841051314144, "percentage": 44.28, "elapsed_time": "4:45:58", "remaining_time": "5:59:53"}
55
+ {"current_steps": 540, "total_steps": 1197, "loss": 0.7448, "lr": 5e-06, "epoch": 1.3523153942428034, "percentage": 45.11, "elapsed_time": "4:51:16", "remaining_time": "5:54:22"}
56
+ {"current_steps": 550, "total_steps": 1197, "loss": 0.744, "lr": 5e-06, "epoch": 1.3773466833541927, "percentage": 45.95, "elapsed_time": "4:56:33", "remaining_time": "5:48:52"}
57
+ {"current_steps": 560, "total_steps": 1197, "loss": 0.7478, "lr": 5e-06, "epoch": 1.402377972465582, "percentage": 46.78, "elapsed_time": "5:01:51", "remaining_time": "5:43:21"}
58
+ {"current_steps": 570, "total_steps": 1197, "loss": 0.7439, "lr": 5e-06, "epoch": 1.4274092615769711, "percentage": 47.62, "elapsed_time": "5:07:09", "remaining_time": "5:37:52"}
59
+ {"current_steps": 580, "total_steps": 1197, "loss": 0.7409, "lr": 5e-06, "epoch": 1.4524405506883604, "percentage": 48.45, "elapsed_time": "5:12:26", "remaining_time": "5:32:22"}
60
+ {"current_steps": 590, "total_steps": 1197, "loss": 0.7426, "lr": 5e-06, "epoch": 1.4774718397997497, "percentage": 49.29, "elapsed_time": "5:17:45", "remaining_time": "5:26:54"}
61
+ {"current_steps": 600, "total_steps": 1197, "loss": 0.7411, "lr": 5e-06, "epoch": 1.502503128911139, "percentage": 50.13, "elapsed_time": "5:23:03", "remaining_time": "5:21:27"}
62
+ {"current_steps": 610, "total_steps": 1197, "loss": 0.7443, "lr": 5e-06, "epoch": 1.5275344180225283, "percentage": 50.96, "elapsed_time": "5:28:21", "remaining_time": "5:15:59"}
63
+ {"current_steps": 620, "total_steps": 1197, "loss": 0.745, "lr": 5e-06, "epoch": 1.5525657071339174, "percentage": 51.8, "elapsed_time": "5:33:40", "remaining_time": "5:10:31"}
64
+ {"current_steps": 630, "total_steps": 1197, "loss": 0.7431, "lr": 5e-06, "epoch": 1.5775969962453065, "percentage": 52.63, "elapsed_time": "5:38:58", "remaining_time": "5:05:04"}
65
+ {"current_steps": 640, "total_steps": 1197, "loss": 0.745, "lr": 5e-06, "epoch": 1.6026282853566958, "percentage": 53.47, "elapsed_time": "5:44:13", "remaining_time": "4:59:34"}
66
+ {"current_steps": 650, "total_steps": 1197, "loss": 0.745, "lr": 5e-06, "epoch": 1.627659574468085, "percentage": 54.3, "elapsed_time": "5:49:30", "remaining_time": "4:54:07"}
67
+ {"current_steps": 660, "total_steps": 1197, "loss": 0.7413, "lr": 5e-06, "epoch": 1.6526908635794744, "percentage": 55.14, "elapsed_time": "5:54:47", "remaining_time": "4:48:40"}
68
+ {"current_steps": 670, "total_steps": 1197, "loss": 0.746, "lr": 5e-06, "epoch": 1.6777221526908637, "percentage": 55.97, "elapsed_time": "6:00:03", "remaining_time": "4:43:12"}
69
+ {"current_steps": 680, "total_steps": 1197, "loss": 0.7434, "lr": 5e-06, "epoch": 1.702753441802253, "percentage": 56.81, "elapsed_time": "6:05:21", "remaining_time": "4:37:46"}
70
+ {"current_steps": 690, "total_steps": 1197, "loss": 0.7426, "lr": 5e-06, "epoch": 1.727784730913642, "percentage": 57.64, "elapsed_time": "6:10:39", "remaining_time": "4:32:21"}
71
+ {"current_steps": 700, "total_steps": 1197, "loss": 0.7397, "lr": 5e-06, "epoch": 1.7528160200250313, "percentage": 58.48, "elapsed_time": "6:15:55", "remaining_time": "4:26:54"}
72
+ {"current_steps": 710, "total_steps": 1197, "loss": 0.7425, "lr": 5e-06, "epoch": 1.7778473091364204, "percentage": 59.31, "elapsed_time": "6:21:14", "remaining_time": "4:21:29"}
73
+ {"current_steps": 720, "total_steps": 1197, "loss": 0.7415, "lr": 5e-06, "epoch": 1.8028785982478097, "percentage": 60.15, "elapsed_time": "6:26:31", "remaining_time": "4:16:04"}
74
+ {"current_steps": 730, "total_steps": 1197, "loss": 0.7409, "lr": 5e-06, "epoch": 1.827909887359199, "percentage": 60.99, "elapsed_time": "6:31:48", "remaining_time": "4:10:39"}
75
+ {"current_steps": 740, "total_steps": 1197, "loss": 0.741, "lr": 5e-06, "epoch": 1.8529411764705883, "percentage": 61.82, "elapsed_time": "6:37:06", "remaining_time": "4:05:14"}
76
+ {"current_steps": 750, "total_steps": 1197, "loss": 0.7398, "lr": 5e-06, "epoch": 1.8779724655819776, "percentage": 62.66, "elapsed_time": "6:42:24", "remaining_time": "3:59:49"}
77
+ {"current_steps": 760, "total_steps": 1197, "loss": 0.7375, "lr": 5e-06, "epoch": 1.9030037546933667, "percentage": 63.49, "elapsed_time": "6:47:42", "remaining_time": "3:54:25"}
78
+ {"current_steps": 770, "total_steps": 1197, "loss": 0.7398, "lr": 5e-06, "epoch": 1.928035043804756, "percentage": 64.33, "elapsed_time": "6:52:59", "remaining_time": "3:49:01"}
79
+ {"current_steps": 780, "total_steps": 1197, "loss": 0.738, "lr": 5e-06, "epoch": 1.953066332916145, "percentage": 65.16, "elapsed_time": "6:58:15", "remaining_time": "3:43:36"}
80
+ {"current_steps": 790, "total_steps": 1197, "loss": 0.7419, "lr": 5e-06, "epoch": 1.9780976220275344, "percentage": 66.0, "elapsed_time": "7:03:29", "remaining_time": "3:38:10"}
81
+ {"current_steps": 798, "total_steps": 1197, "eval_loss": 0.7726743817329407, "epoch": 1.9981226533166458, "percentage": 66.67, "elapsed_time": "7:12:37", "remaining_time": "3:36:18"}
82
+ {"current_steps": 800, "total_steps": 1197, "loss": 0.7865, "lr": 5e-06, "epoch": 2.0037546933667083, "percentage": 66.83, "elapsed_time": "7:14:45", "remaining_time": "3:35:44"}