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
Inference Endpoints
Model card Files Community
gsmyrnis commited on
Commit
8fcdc60
·
verified ·
1 Parent(s): ebd59b7

Training in progress, epoch 3

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 +21 -0
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2ca3995a3e0e6ee8256af1190bf9cbdb6f4356e811606275d1eb9b7b52dfe188
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78529dbf20015c0f53d9c5fa283ec688b58cfba6e830da7d9735cc044a56b0a5
3
  size 4976698672
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:611adfa13ef9f11b6420d6390623cabb5ea094f1d4468abdc59b9fc46ec0275e
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a5ec7579c3b4623cf386b765dc0ba088e74c80aa22f4f3a14ae1678ec6a3369
3
  size 4999802720
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2efcde3b8779aedd8faec2a475b2a8fddd69355eb16eb439d26618e92f1aff4c
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99946b8f28d5216f2a9f08ce9202279beaac4745c00d1834e303b917838505c7
3
  size 4915916176
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:99ef526607fd9f84bdeacf3c6c37c2aba87c709da8c620db2c34293f10a6ff67
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c35f7f8225fb1349f2f9bb33b8b86e256e0a748b0fadda7ab04020578d61638
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -44,3 +44,24 @@
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"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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"}
47
+ {"current_steps": 450, "total_steps": 630, "loss": 0.3585, "learning_rate": 5e-06, "epoch": 2.142857142857143, "percentage": 71.43, "elapsed_time": "0:55:29", "remaining_time": "0:22:11"}
48
+ {"current_steps": 460, "total_steps": 630, "loss": 0.3595, "learning_rate": 5e-06, "epoch": 2.1904761904761907, "percentage": 73.02, "elapsed_time": "0:56:32", "remaining_time": "0:20:53"}
49
+ {"current_steps": 470, "total_steps": 630, "loss": 0.3583, "learning_rate": 5e-06, "epoch": 2.238095238095238, "percentage": 74.6, "elapsed_time": "0:57:34", "remaining_time": "0:19:36"}
50
+ {"current_steps": 480, "total_steps": 630, "loss": 0.3555, "learning_rate": 5e-06, "epoch": 2.2857142857142856, "percentage": 76.19, "elapsed_time": "0:58:37", "remaining_time": "0:18:19"}
51
+ {"current_steps": 490, "total_steps": 630, "loss": 0.359, "learning_rate": 5e-06, "epoch": 2.3333333333333335, "percentage": 77.78, "elapsed_time": "0:59:39", "remaining_time": "0:17:02"}
52
+ {"current_steps": 500, "total_steps": 630, "loss": 0.3603, "learning_rate": 5e-06, "epoch": 2.380952380952381, "percentage": 79.37, "elapsed_time": "1:00:42", "remaining_time": "0:15:46"}
53
+ {"current_steps": 510, "total_steps": 630, "loss": 0.3536, "learning_rate": 5e-06, "epoch": 2.4285714285714284, "percentage": 80.95, "elapsed_time": "1:01:44", "remaining_time": "0:14:31"}
54
+ {"current_steps": 520, "total_steps": 630, "loss": 0.3583, "learning_rate": 5e-06, "epoch": 2.4761904761904763, "percentage": 82.54, "elapsed_time": "1:02:46", "remaining_time": "0:13:16"}
55
+ {"current_steps": 530, "total_steps": 630, "loss": 0.3592, "learning_rate": 5e-06, "epoch": 2.5238095238095237, "percentage": 84.13, "elapsed_time": "1:03:49", "remaining_time": "0:12:02"}
56
+ {"current_steps": 540, "total_steps": 630, "loss": 0.3563, "learning_rate": 5e-06, "epoch": 2.571428571428571, "percentage": 85.71, "elapsed_time": "1:04:51", "remaining_time": "0:10:48"}
57
+ {"current_steps": 550, "total_steps": 630, "loss": 0.3549, "learning_rate": 5e-06, "epoch": 2.619047619047619, "percentage": 87.3, "elapsed_time": "1:05:54", "remaining_time": "0:09:35"}
58
+ {"current_steps": 560, "total_steps": 630, "loss": 0.3558, "learning_rate": 5e-06, "epoch": 2.6666666666666665, "percentage": 88.89, "elapsed_time": "1:06:56", "remaining_time": "0:08:22"}
59
+ {"current_steps": 570, "total_steps": 630, "loss": 0.3584, "learning_rate": 5e-06, "epoch": 2.7142857142857144, "percentage": 90.48, "elapsed_time": "1:07:59", "remaining_time": "0:07:09"}
60
+ {"current_steps": 580, "total_steps": 630, "loss": 0.3547, "learning_rate": 5e-06, "epoch": 2.761904761904762, "percentage": 92.06, "elapsed_time": "1:09:01", "remaining_time": "0:05:57"}
61
+ {"current_steps": 590, "total_steps": 630, "loss": 0.3581, "learning_rate": 5e-06, "epoch": 2.8095238095238093, "percentage": 93.65, "elapsed_time": "1:10:04", "remaining_time": "0:04:45"}
62
+ {"current_steps": 600, "total_steps": 630, "loss": 0.3521, "learning_rate": 5e-06, "epoch": 2.857142857142857, "percentage": 95.24, "elapsed_time": "1:11:06", "remaining_time": "0:03:33"}
63
+ {"current_steps": 610, "total_steps": 630, "loss": 0.353, "learning_rate": 5e-06, "epoch": 2.9047619047619047, "percentage": 96.83, "elapsed_time": "1:12:09", "remaining_time": "0:02:21"}
64
+ {"current_steps": 620, "total_steps": 630, "loss": 0.3546, "learning_rate": 5e-06, "epoch": 2.9523809523809526, "percentage": 98.41, "elapsed_time": "1:13:11", "remaining_time": "0:01:10"}
65
+ {"current_steps": 630, "total_steps": 630, "loss": 0.3529, "learning_rate": 5e-06, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "1:14:13", "remaining_time": "0:00:00"}
66
+ {"current_steps": 630, "total_steps": 630, "eval_loss": 0.39452776312828064, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "1:18:14", "remaining_time": "0:00:00"}
67
+ {"current_steps": 630, "total_steps": 630, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "1:21:35", "remaining_time": "0:00:00"}