Hugging Face's logo

mlfoundations-dev
/
llama3-1_8b_physics_500000_samples

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
b4f0b1f
·
verified ·
1 Parent(s): 1862ce8

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 +38 -0
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:66b4df9df67e251fa0827a95aa09d1309c67ae23d5937410090a28dedeeed7a5
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c235ec884cec4c782996b5b708c2282cff3bbad9c27f70731506279859c1b209
3
  size 4976698672
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2f631ec5e5f307d8887ce41f4e4f4d1433547ddb6b836b43204c636eda76b8b1
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8040884c71059fe42984aa33dc2759e4ecd66a0512016a63fec809e8d924264c
3
  size 4999802720
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:445ade241731986c77b85ee1c4354b04732648a39b41352a607b23a4329d686f
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab4705ab8d40f41bd0fe7678d033fba600ef603143a259bdff36153587097538
3
  size 4915916176
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1503ae59e8ffbb3a331b8357eb977bc9210b588eb17a1980c54f1be6810f35f9
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af5c950950af8cdf9d0a9161d76cef051b540f052314a78d5479f3630616f171
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -74,3 +74,41 @@
74
  {"current_steps": 730, "total_steps": 1134, "loss": 0.7451, "lr": 5e-06, "epoch": 1.9312169312169312, "percentage": 64.37, "elapsed_time": "1:14:12", "remaining_time": "0:41:04"}
75
  {"current_steps": 740, "total_steps": 1134, "loss": 0.7466, "lr": 5e-06, "epoch": 1.9576719576719577, "percentage": 65.26, "elapsed_time": "1:15:11", "remaining_time": "0:40:02"}
76
  {"current_steps": 750, "total_steps": 1134, "loss": 0.7445, "lr": 5e-06, "epoch": 1.9841269841269842, "percentage": 66.14, "elapsed_time": "1:16:11", "remaining_time": "0:39:00"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
74
  {"current_steps": 730, "total_steps": 1134, "loss": 0.7451, "lr": 5e-06, "epoch": 1.9312169312169312, "percentage": 64.37, "elapsed_time": "1:14:12", "remaining_time": "0:41:04"}
75
  {"current_steps": 740, "total_steps": 1134, "loss": 0.7466, "lr": 5e-06, "epoch": 1.9576719576719577, "percentage": 65.26, "elapsed_time": "1:15:11", "remaining_time": "0:40:02"}
76
  {"current_steps": 750, "total_steps": 1134, "loss": 0.7445, "lr": 5e-06, "epoch": 1.9841269841269842, "percentage": 66.14, "elapsed_time": "1:16:11", "remaining_time": "0:39:00"}
77
+ {"current_steps": 756, "total_steps": 1134, "eval_loss": 0.7725165486335754, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "1:17:23", "remaining_time": "0:38:41"}
78
+ {"current_steps": 760, "total_steps": 1134, "loss": 0.7322, "lr": 5e-06, "epoch": 2.0105820105820107, "percentage": 67.02, "elapsed_time": "1:19:21", "remaining_time": "0:39:03"}
79
+ {"current_steps": 770, "total_steps": 1134, "loss": 0.7091, "lr": 5e-06, "epoch": 2.037037037037037, "percentage": 67.9, "elapsed_time": "1:20:20", "remaining_time": "0:37:58"}
80
+ {"current_steps": 780, "total_steps": 1134, "loss": 0.711, "lr": 5e-06, "epoch": 2.0634920634920633, "percentage": 68.78, "elapsed_time": "1:21:19", "remaining_time": "0:36:54"}
81
+ {"current_steps": 790, "total_steps": 1134, "loss": 0.7113, "lr": 5e-06, "epoch": 2.0899470899470898, "percentage": 69.66, "elapsed_time": "1:22:19", "remaining_time": "0:35:50"}
82
+ {"current_steps": 800, "total_steps": 1134, "loss": 0.7109, "lr": 5e-06, "epoch": 2.1164021164021163, "percentage": 70.55, "elapsed_time": "1:23:18", "remaining_time": "0:34:46"}
83
+ {"current_steps": 810, "total_steps": 1134, "loss": 0.7126, "lr": 5e-06, "epoch": 2.142857142857143, "percentage": 71.43, "elapsed_time": "1:24:17", "remaining_time": "0:33:42"}
84
+ {"current_steps": 820, "total_steps": 1134, "loss": 0.7124, "lr": 5e-06, "epoch": 2.1693121693121693, "percentage": 72.31, "elapsed_time": "1:25:16", "remaining_time": "0:32:39"}
85
+ {"current_steps": 830, "total_steps": 1134, "loss": 0.7123, "lr": 5e-06, "epoch": 2.195767195767196, "percentage": 73.19, "elapsed_time": "1:26:16", "remaining_time": "0:31:35"}
86
+ {"current_steps": 840, "total_steps": 1134, "loss": 0.7123, "lr": 5e-06, "epoch": 2.2222222222222223, "percentage": 74.07, "elapsed_time": "1:27:15", "remaining_time": "0:30:32"}
87
+ {"current_steps": 850, "total_steps": 1134, "loss": 0.7139, "lr": 5e-06, "epoch": 2.248677248677249, "percentage": 74.96, "elapsed_time": "1:28:14", "remaining_time": "0:29:28"}
88
+ {"current_steps": 860, "total_steps": 1134, "loss": 0.7164, "lr": 5e-06, "epoch": 2.2751322751322753, "percentage": 75.84, "elapsed_time": "1:29:13", "remaining_time": "0:28:25"}
89
+ {"current_steps": 870, "total_steps": 1134, "loss": 0.7141, "lr": 5e-06, "epoch": 2.3015873015873014, "percentage": 76.72, "elapsed_time": "1:30:13", "remaining_time": "0:27:22"}
90
+ {"current_steps": 880, "total_steps": 1134, "loss": 0.7189, "lr": 5e-06, "epoch": 2.328042328042328, "percentage": 77.6, "elapsed_time": "1:31:12", "remaining_time": "0:26:19"}
91
+ {"current_steps": 890, "total_steps": 1134, "loss": 0.7159, "lr": 5e-06, "epoch": 2.3544973544973544, "percentage": 78.48, "elapsed_time": "1:32:11", "remaining_time": "0:25:16"}
92
+ {"current_steps": 900, "total_steps": 1134, "loss": 0.717, "lr": 5e-06, "epoch": 2.380952380952381, "percentage": 79.37, "elapsed_time": "1:33:11", "remaining_time": "0:24:13"}
93
+ {"current_steps": 910, "total_steps": 1134, "loss": 0.7176, "lr": 5e-06, "epoch": 2.4074074074074074, "percentage": 80.25, "elapsed_time": "1:34:10", "remaining_time": "0:23:10"}
94
+ {"current_steps": 920, "total_steps": 1134, "loss": 0.7141, "lr": 5e-06, "epoch": 2.433862433862434, "percentage": 81.13, "elapsed_time": "1:35:09", "remaining_time": "0:22:08"}
95
+ {"current_steps": 930, "total_steps": 1134, "loss": 0.7147, "lr": 5e-06, "epoch": 2.4603174603174605, "percentage": 82.01, "elapsed_time": "1:36:08", "remaining_time": "0:21:05"}
96
+ {"current_steps": 940, "total_steps": 1134, "loss": 0.7126, "lr": 5e-06, "epoch": 2.4867724867724865, "percentage": 82.89, "elapsed_time": "1:37:07", "remaining_time": "0:20:02"}
97
+ {"current_steps": 950, "total_steps": 1134, "loss": 0.7171, "lr": 5e-06, "epoch": 2.5132275132275135, "percentage": 83.77, "elapsed_time": "1:38:07", "remaining_time": "0:19:00"}
98
+ {"current_steps": 960, "total_steps": 1134, "loss": 0.7182, "lr": 5e-06, "epoch": 2.5396825396825395, "percentage": 84.66, "elapsed_time": "1:39:07", "remaining_time": "0:17:57"}
99
+ {"current_steps": 970, "total_steps": 1134, "loss": 0.7187, "lr": 5e-06, "epoch": 2.566137566137566, "percentage": 85.54, "elapsed_time": "1:40:05", "remaining_time": "0:16:55"}
100
+ {"current_steps": 980, "total_steps": 1134, "loss": 0.7164, "lr": 5e-06, "epoch": 2.5925925925925926, "percentage": 86.42, "elapsed_time": "1:41:05", "remaining_time": "0:15:53"}
101
+ {"current_steps": 990, "total_steps": 1134, "loss": 0.7157, "lr": 5e-06, "epoch": 2.619047619047619, "percentage": 87.3, "elapsed_time": "1:42:05", "remaining_time": "0:14:50"}
102
+ {"current_steps": 1000, "total_steps": 1134, "loss": 0.7175, "lr": 5e-06, "epoch": 2.6455026455026456, "percentage": 88.18, "elapsed_time": "1:43:04", "remaining_time": "0:13:48"}
103
+ {"current_steps": 1010, "total_steps": 1134, "loss": 0.715, "lr": 5e-06, "epoch": 2.671957671957672, "percentage": 89.07, "elapsed_time": "1:44:03", "remaining_time": "0:12:46"}
104
+ {"current_steps": 1020, "total_steps": 1134, "loss": 0.7208, "lr": 5e-06, "epoch": 2.6984126984126986, "percentage": 89.95, "elapsed_time": "1:45:02", "remaining_time": "0:11:44"}
105
+ {"current_steps": 1030, "total_steps": 1134, "loss": 0.7157, "lr": 5e-06, "epoch": 2.7248677248677247, "percentage": 90.83, "elapsed_time": "1:46:02", "remaining_time": "0:10:42"}
106
+ {"current_steps": 1040, "total_steps": 1134, "loss": 0.7119, "lr": 5e-06, "epoch": 2.751322751322751, "percentage": 91.71, "elapsed_time": "1:47:01", "remaining_time": "0:09:40"}
107
+ {"current_steps": 1050, "total_steps": 1134, "loss": 0.7159, "lr": 5e-06, "epoch": 2.7777777777777777, "percentage": 92.59, "elapsed_time": "1:47:59", "remaining_time": "0:08:38"}
108
+ {"current_steps": 1060, "total_steps": 1134, "loss": 0.7152, "lr": 5e-06, "epoch": 2.804232804232804, "percentage": 93.47, "elapsed_time": "1:48:59", "remaining_time": "0:07:36"}
109
+ {"current_steps": 1070, "total_steps": 1134, "loss": 0.7171, "lr": 5e-06, "epoch": 2.8306878306878307, "percentage": 94.36, "elapsed_time": "1:49:58", "remaining_time": "0:06:34"}
110
+ {"current_steps": 1080, "total_steps": 1134, "loss": 0.7154, "lr": 5e-06, "epoch": 2.857142857142857, "percentage": 95.24, "elapsed_time": "1:50:57", "remaining_time": "0:05:32"}
111
+ {"current_steps": 1090, "total_steps": 1134, "loss": 0.7152, "lr": 5e-06, "epoch": 2.8835978835978837, "percentage": 96.12, "elapsed_time": "1:51:57", "remaining_time": "0:04:31"}
112
+ {"current_steps": 1100, "total_steps": 1134, "loss": 0.7181, "lr": 5e-06, "epoch": 2.91005291005291, "percentage": 97.0, "elapsed_time": "1:52:56", "remaining_time": "0:03:29"}
113
+ {"current_steps": 1110, "total_steps": 1134, "loss": 0.7167, "lr": 5e-06, "epoch": 2.9365079365079367, "percentage": 97.88, "elapsed_time": "1:53:56", "remaining_time": "0:02:27"}
114
+ {"current_steps": 1120, "total_steps": 1134, "loss": 0.7146, "lr": 5e-06, "epoch": 2.962962962962963, "percentage": 98.77, "elapsed_time": "1:54:55", "remaining_time": "0:01:26"}