Hugging Face's logo

mlfoundations-dev
/
llama3-1_8b_oh_dcft_v1_wo_slim_orca_500k

Text Generation
Transformers
Safetensors
llama
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Model card Files Community
gsmyrnis commited on
Commit
ebd59b7
·
verified ·
1 Parent(s): ede30ec

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 +22 -0
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:24cc35f4b570dc63b6992e7c274740d6ce4c8de4282b110b2e9b8eba3d9aeaab
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ca3995a3e0e6ee8256af1190bf9cbdb6f4356e811606275d1eb9b7b52dfe188
3
  size 4976698672
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1a7f874592378edf7604f1d4cce127bd5062112b4bbbd3507b63fc92c530678c
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:611adfa13ef9f11b6420d6390623cabb5ea094f1d4468abdc59b9fc46ec0275e
3
  size 4999802720
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:82b34c05890ed7ef46e342f406099146fafb8c17a8a19930f168b449a28f4a80
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2efcde3b8779aedd8faec2a475b2a8fddd69355eb16eb439d26618e92f1aff4c
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:c31aa2555c13da8e4368bdc03e0d20e6c41adb9adfca38271eea8423455b7042
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99ef526607fd9f84bdeacf3c6c37c2aba87c709da8c620db2c34293f10a6ff67
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -22,3 +22,25 @@
22
  {"current_steps": 210, "total_steps": 630, "eval_loss": 0.44027426838874817, "epoch": 1.0, "percentage": 33.33, "elapsed_time": "0:22:10", "remaining_time": "0:44:21"}
23
  {"current_steps": 220, "total_steps": 630, "loss": 0.4177, "learning_rate": 5e-06, "epoch": 1.0476190476190477, "percentage": 34.92, "elapsed_time": "0:27:13", "remaining_time": "0:50:45"}
24
  {"current_steps": 230, "total_steps": 630, "loss": 0.4166, "learning_rate": 5e-06, "epoch": 1.0952380952380953, "percentage": 36.51, "elapsed_time": "0:28:16", "remaining_time": "0:49:10"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
22
  {"current_steps": 210, "total_steps": 630, "eval_loss": 0.44027426838874817, "epoch": 1.0, "percentage": 33.33, "elapsed_time": "0:22:10", "remaining_time": "0:44:21"}
23
  {"current_steps": 220, "total_steps": 630, "loss": 0.4177, "learning_rate": 5e-06, "epoch": 1.0476190476190477, "percentage": 34.92, "elapsed_time": "0:27:13", "remaining_time": "0:50:45"}
24
  {"current_steps": 230, "total_steps": 630, "loss": 0.4166, "learning_rate": 5e-06, "epoch": 1.0952380952380953, "percentage": 36.51, "elapsed_time": "0:28:16", "remaining_time": "0:49:10"}
25
+ {"current_steps": 240, "total_steps": 630, "loss": 0.4146, "learning_rate": 5e-06, "epoch": 1.1428571428571428, "percentage": 38.1, "elapsed_time": "0:29:18", "remaining_time": "0:47:38"}
26
+ {"current_steps": 250, "total_steps": 630, "loss": 0.41, "learning_rate": 5e-06, "epoch": 1.1904761904761905, "percentage": 39.68, "elapsed_time": "0:30:21", "remaining_time": "0:46:08"}
27
+ {"current_steps": 260, "total_steps": 630, "loss": 0.4092, "learning_rate": 5e-06, "epoch": 1.2380952380952381, "percentage": 41.27, "elapsed_time": "0:31:23", "remaining_time": "0:44:40"}
28
+ {"current_steps": 270, "total_steps": 630, "loss": 0.4117, "learning_rate": 5e-06, "epoch": 1.2857142857142856, "percentage": 42.86, "elapsed_time": "0:32:26", "remaining_time": "0:43:14"}
29
+ {"current_steps": 280, "total_steps": 630, "loss": 0.4088, "learning_rate": 5e-06, "epoch": 1.3333333333333333, "percentage": 44.44, "elapsed_time": "0:33:28", "remaining_time": "0:41:50"}
30
+ {"current_steps": 290, "total_steps": 630, "loss": 0.401, "learning_rate": 5e-06, "epoch": 1.380952380952381, "percentage": 46.03, "elapsed_time": "0:34:31", "remaining_time": "0:40:28"}
31
+ {"current_steps": 300, "total_steps": 630, "loss": 0.4018, "learning_rate": 5e-06, "epoch": 1.4285714285714286, "percentage": 47.62, "elapsed_time": "0:35:33", "remaining_time": "0:39:06"}
32
+ {"current_steps": 310, "total_steps": 630, "loss": 0.4043, "learning_rate": 5e-06, "epoch": 1.4761904761904763, "percentage": 49.21, "elapsed_time": "0:36:36", "remaining_time": "0:37:47"}
33
+ {"current_steps": 320, "total_steps": 630, "loss": 0.4048, "learning_rate": 5e-06, "epoch": 1.5238095238095237, "percentage": 50.79, "elapsed_time": "0:37:38", "remaining_time": "0:36:28"}
34
+ {"current_steps": 330, "total_steps": 630, "loss": 0.4025, "learning_rate": 5e-06, "epoch": 1.5714285714285714, "percentage": 52.38, "elapsed_time": "0:38:41", "remaining_time": "0:35:10"}
35
+ {"current_steps": 340, "total_steps": 630, "loss": 0.3983, "learning_rate": 5e-06, "epoch": 1.619047619047619, "percentage": 53.97, "elapsed_time": "0:39:43", "remaining_time": "0:33:52"}
36
+ {"current_steps": 350, "total_steps": 630, "loss": 0.398, "learning_rate": 5e-06, "epoch": 1.6666666666666665, "percentage": 55.56, "elapsed_time": "0:40:45", "remaining_time": "0:32:36"}
37
+ {"current_steps": 360, "total_steps": 630, "loss": 0.3966, "learning_rate": 5e-06, "epoch": 1.7142857142857144, "percentage": 57.14, "elapsed_time": "0:41:48", "remaining_time": "0:31:21"}
38
+ {"current_steps": 370, "total_steps": 630, "loss": 0.3966, "learning_rate": 5e-06, "epoch": 1.7619047619047619, "percentage": 58.73, "elapsed_time": "0:42:50", "remaining_time": "0:30:06"}
39
+ {"current_steps": 380, "total_steps": 630, "loss": 0.3991, "learning_rate": 5e-06, "epoch": 1.8095238095238095, "percentage": 60.32, "elapsed_time": "0:43:53", "remaining_time": "0:28:52"}
40
+ {"current_steps": 390, "total_steps": 630, "loss": 0.3923, "learning_rate": 5e-06, "epoch": 1.8571428571428572, "percentage": 61.9, "elapsed_time": "0:44:55", "remaining_time": "0:27:38"}
41
+ {"current_steps": 400, "total_steps": 630, "loss": 0.3927, "learning_rate": 5e-06, "epoch": 1.9047619047619047, "percentage": 63.49, "elapsed_time": "0:45:58", "remaining_time": "0:26:26"}
42
+ {"current_steps": 410, "total_steps": 630, "loss": 0.3899, "learning_rate": 5e-06, "epoch": 1.9523809523809523, "percentage": 65.08, "elapsed_time": "0:47:00", "remaining_time": "0:25:13"}
43
+ {"current_steps": 420, "total_steps": 630, "loss": 0.3876, "learning_rate": 5e-06, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "0:48:03", "remaining_time": "0:24:01"}
44
+ {"current_steps": 420, "total_steps": 630, "eval_loss": 0.40606528520584106, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "0:48:22", "remaining_time": "0:24:11"}
45
+ {"current_steps": 430, "total_steps": 630, "loss": 0.3631, "learning_rate": 5e-06, "epoch": 2.0476190476190474, "percentage": 68.25, "elapsed_time": "0:53:25", "remaining_time": "0:24:50"}
46
+ {"current_steps": 440, "total_steps": 630, "loss": 0.361, "learning_rate": 5e-06, "epoch": 2.0952380952380953, "percentage": 69.84, "elapsed_time": "0:54:27", "remaining_time": "0:23:30"}