Hugging Face's logo

mlfoundations-dev
/
llama3-1_8b_oh_v3.1_wo_evolinstruct

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
05e881d
·
verified ·
1 Parent(s): bf7236f

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 +40 -0
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7cb8ff72458bfea52a29719b126a314513c3f3379f049afa92692d10ee0e5516
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff7ef0f3c7f0fd3b0c92bc2e8d51ed993adab4df25b3c18a48c873cd3eb5b9c1
3
  size 4976698672
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:959e1464a41b436009ef9bb1be60d03751c6632508d735c89cf4b4c4d6d30e32
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a76bbca7a01b137d3244b227bdaeaf0d7ccb69109eb4cb300324cd18c1f721ae
3
  size 4999802720
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4d229d6e6df0a720ed478a2bd126e6b5bfdf6d738025b9565fdac5ac8fd324f4
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d7a012d84cc51ca4336748f137daaf53eb6eeed595cba05803356e9485e3917
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:e83831a979c8dd77b82ad13d1be824a897c71dcb5df8f14df6934cd50a9ac132
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:36c0205f7172e2f54b6a7f421177695f17aa6b9a2a2c66bd2cd31d5313efa081
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -40,3 +40,43 @@
40
  {"current_steps": 391, "total_steps": 1173, "eval_loss": 0.6434539556503296, "epoch": 1.0, "percentage": 33.33, "elapsed_time": "0:39:10", "remaining_time": "1:18:20"}
41
  {"current_steps": 400, "total_steps": 1173, "loss": 0.6099, "learning_rate": 5e-06, "epoch": 1.0230179028132993, "percentage": 34.1, "elapsed_time": "0:41:31", "remaining_time": "1:20:14"}
42
  {"current_steps": 410, "total_steps": 1173, "loss": 0.6049, "learning_rate": 5e-06, "epoch": 1.0485933503836318, "percentage": 34.95, "elapsed_time": "0:42:29", "remaining_time": "1:19:05"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
40
  {"current_steps": 391, "total_steps": 1173, "eval_loss": 0.6434539556503296, "epoch": 1.0, "percentage": 33.33, "elapsed_time": "0:39:10", "remaining_time": "1:18:20"}
41
  {"current_steps": 400, "total_steps": 1173, "loss": 0.6099, "learning_rate": 5e-06, "epoch": 1.0230179028132993, "percentage": 34.1, "elapsed_time": "0:41:31", "remaining_time": "1:20:14"}
42
  {"current_steps": 410, "total_steps": 1173, "loss": 0.6049, "learning_rate": 5e-06, "epoch": 1.0485933503836318, "percentage": 34.95, "elapsed_time": "0:42:29", "remaining_time": "1:19:05"}
43
+ {"current_steps": 420, "total_steps": 1173, "loss": 0.6013, "learning_rate": 5e-06, "epoch": 1.0741687979539642, "percentage": 35.81, "elapsed_time": "0:43:28", "remaining_time": "1:17:56"}
44
+ {"current_steps": 430, "total_steps": 1173, "loss": 0.5995, "learning_rate": 5e-06, "epoch": 1.0997442455242967, "percentage": 36.66, "elapsed_time": "0:44:27", "remaining_time": "1:16:49"}
45
+ {"current_steps": 440, "total_steps": 1173, "loss": 0.6027, "learning_rate": 5e-06, "epoch": 1.1253196930946292, "percentage": 37.51, "elapsed_time": "0:45:27", "remaining_time": "1:15:43"}
46
+ {"current_steps": 450, "total_steps": 1173, "loss": 0.6103, "learning_rate": 5e-06, "epoch": 1.1508951406649617, "percentage": 38.36, "elapsed_time": "0:46:26", "remaining_time": "1:14:36"}
47
+ {"current_steps": 460, "total_steps": 1173, "loss": 0.5999, "learning_rate": 5e-06, "epoch": 1.1764705882352942, "percentage": 39.22, "elapsed_time": "0:47:25", "remaining_time": "1:13:30"}
48
+ {"current_steps": 470, "total_steps": 1173, "loss": 0.6058, "learning_rate": 5e-06, "epoch": 1.2020460358056266, "percentage": 40.07, "elapsed_time": "0:48:25", "remaining_time": "1:12:25"}
49
+ {"current_steps": 480, "total_steps": 1173, "loss": 0.6013, "learning_rate": 5e-06, "epoch": 1.227621483375959, "percentage": 40.92, "elapsed_time": "0:49:24", "remaining_time": "1:11:20"}
50
+ {"current_steps": 490, "total_steps": 1173, "loss": 0.5985, "learning_rate": 5e-06, "epoch": 1.2531969309462916, "percentage": 41.77, "elapsed_time": "0:50:23", "remaining_time": "1:10:14"}
51
+ {"current_steps": 500, "total_steps": 1173, "loss": 0.5971, "learning_rate": 5e-06, "epoch": 1.278772378516624, "percentage": 42.63, "elapsed_time": "0:51:23", "remaining_time": "1:09:10"}
52
+ {"current_steps": 510, "total_steps": 1173, "loss": 0.6043, "learning_rate": 5e-06, "epoch": 1.3043478260869565, "percentage": 43.48, "elapsed_time": "0:52:21", "remaining_time": "1:08:04"}
53
+ {"current_steps": 520, "total_steps": 1173, "loss": 0.6089, "learning_rate": 5e-06, "epoch": 1.329923273657289, "percentage": 44.33, "elapsed_time": "0:53:21", "remaining_time": "1:06:59"}
54
+ {"current_steps": 530, "total_steps": 1173, "loss": 0.6016, "learning_rate": 5e-06, "epoch": 1.3554987212276215, "percentage": 45.18, "elapsed_time": "0:54:20", "remaining_time": "1:05:55"}
55
+ {"current_steps": 540, "total_steps": 1173, "loss": 0.5987, "learning_rate": 5e-06, "epoch": 1.381074168797954, "percentage": 46.04, "elapsed_time": "0:55:19", "remaining_time": "1:04:51"}
56
+ {"current_steps": 550, "total_steps": 1173, "loss": 0.6009, "learning_rate": 5e-06, "epoch": 1.4066496163682864, "percentage": 46.89, "elapsed_time": "0:56:18", "remaining_time": "1:03:46"}
57
+ {"current_steps": 560, "total_steps": 1173, "loss": 0.5974, "learning_rate": 5e-06, "epoch": 1.432225063938619, "percentage": 47.74, "elapsed_time": "0:57:16", "remaining_time": "1:02:41"}
58
+ {"current_steps": 570, "total_steps": 1173, "loss": 0.6009, "learning_rate": 5e-06, "epoch": 1.4578005115089514, "percentage": 48.59, "elapsed_time": "0:58:15", "remaining_time": "1:01:37"}
59
+ {"current_steps": 580, "total_steps": 1173, "loss": 0.5994, "learning_rate": 5e-06, "epoch": 1.4833759590792839, "percentage": 49.45, "elapsed_time": "0:59:13", "remaining_time": "1:00:33"}
60
+ {"current_steps": 590, "total_steps": 1173, "loss": 0.5948, "learning_rate": 5e-06, "epoch": 1.5089514066496164, "percentage": 50.3, "elapsed_time": "1:00:12", "remaining_time": "0:59:29"}
61
+ {"current_steps": 600, "total_steps": 1173, "loss": 0.6072, "learning_rate": 5e-06, "epoch": 1.5345268542199488, "percentage": 51.15, "elapsed_time": "1:01:10", "remaining_time": "0:58:25"}
62
+ {"current_steps": 610, "total_steps": 1173, "loss": 0.5915, "learning_rate": 5e-06, "epoch": 1.5601023017902813, "percentage": 52.0, "elapsed_time": "1:02:09", "remaining_time": "0:57:21"}
63
+ {"current_steps": 620, "total_steps": 1173, "loss": 0.5879, "learning_rate": 5e-06, "epoch": 1.5856777493606138, "percentage": 52.86, "elapsed_time": "1:03:08", "remaining_time": "0:56:19"}
64
+ {"current_steps": 630, "total_steps": 1173, "loss": 0.6002, "learning_rate": 5e-06, "epoch": 1.6112531969309463, "percentage": 53.71, "elapsed_time": "1:04:07", "remaining_time": "0:55:16"}
65
+ {"current_steps": 640, "total_steps": 1173, "loss": 0.5946, "learning_rate": 5e-06, "epoch": 1.6368286445012787, "percentage": 54.56, "elapsed_time": "1:05:07", "remaining_time": "0:54:14"}
66
+ {"current_steps": 650, "total_steps": 1173, "loss": 0.589, "learning_rate": 5e-06, "epoch": 1.6624040920716112, "percentage": 55.41, "elapsed_time": "1:06:06", "remaining_time": "0:53:11"}
67
+ {"current_steps": 660, "total_steps": 1173, "loss": 0.5994, "learning_rate": 5e-06, "epoch": 1.6879795396419437, "percentage": 56.27, "elapsed_time": "1:07:05", "remaining_time": "0:52:08"}
68
+ {"current_steps": 670, "total_steps": 1173, "loss": 0.6011, "learning_rate": 5e-06, "epoch": 1.7135549872122762, "percentage": 57.12, "elapsed_time": "1:08:05", "remaining_time": "0:51:06"}
69
+ {"current_steps": 680, "total_steps": 1173, "loss": 0.5943, "learning_rate": 5e-06, "epoch": 1.7391304347826086, "percentage": 57.97, "elapsed_time": "1:09:04", "remaining_time": "0:50:04"}
70
+ {"current_steps": 690, "total_steps": 1173, "loss": 0.597, "learning_rate": 5e-06, "epoch": 1.7647058823529411, "percentage": 58.82, "elapsed_time": "1:10:04", "remaining_time": "0:49:02"}
71
+ {"current_steps": 700, "total_steps": 1173, "loss": 0.6012, "learning_rate": 5e-06, "epoch": 1.7902813299232738, "percentage": 59.68, "elapsed_time": "1:11:02", "remaining_time": "0:48:00"}
72
+ {"current_steps": 710, "total_steps": 1173, "loss": 0.5996, "learning_rate": 5e-06, "epoch": 1.815856777493606, "percentage": 60.53, "elapsed_time": "1:12:02", "remaining_time": "0:46:58"}
73
+ {"current_steps": 720, "total_steps": 1173, "loss": 0.6001, "learning_rate": 5e-06, "epoch": 1.8414322250639388, "percentage": 61.38, "elapsed_time": "1:13:01", "remaining_time": "0:45:56"}
74
+ {"current_steps": 730, "total_steps": 1173, "loss": 0.5995, "learning_rate": 5e-06, "epoch": 1.867007672634271, "percentage": 62.23, "elapsed_time": "1:14:00", "remaining_time": "0:44:54"}
75
+ {"current_steps": 740, "total_steps": 1173, "loss": 0.5896, "learning_rate": 5e-06, "epoch": 1.8925831202046037, "percentage": 63.09, "elapsed_time": "1:15:00", "remaining_time": "0:43:53"}
76
+ {"current_steps": 750, "total_steps": 1173, "loss": 0.603, "learning_rate": 5e-06, "epoch": 1.918158567774936, "percentage": 63.94, "elapsed_time": "1:15:59", "remaining_time": "0:42:51"}
77
+ {"current_steps": 760, "total_steps": 1173, "loss": 0.6036, "learning_rate": 5e-06, "epoch": 1.9437340153452687, "percentage": 64.79, "elapsed_time": "1:16:59", "remaining_time": "0:41:50"}
78
+ {"current_steps": 770, "total_steps": 1173, "loss": 0.6086, "learning_rate": 5e-06, "epoch": 1.969309462915601, "percentage": 65.64, "elapsed_time": "1:17:58", "remaining_time": "0:40:48"}
79
+ {"current_steps": 780, "total_steps": 1173, "loss": 0.5983, "learning_rate": 5e-06, "epoch": 1.9948849104859336, "percentage": 66.5, "elapsed_time": "1:18:57", "remaining_time": "0:39:46"}
80
+ {"current_steps": 782, "total_steps": 1173, "eval_loss": 0.6335848569869995, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "1:19:47", "remaining_time": "0:39:53"}
81
+ {"current_steps": 790, "total_steps": 1173, "loss": 0.5672, "learning_rate": 5e-06, "epoch": 2.020460358056266, "percentage": 67.35, "elapsed_time": "1:22:06", "remaining_time": "0:39:48"}
82
+ {"current_steps": 800, "total_steps": 1173, "loss": 0.5592, "learning_rate": 5e-06, "epoch": 2.0460358056265986, "percentage": 68.2, "elapsed_time": "1:23:05", "remaining_time": "0:38:44"}