Hugging Face's logo

mlfoundations-dev
/
oh-dcft-v3.1-SN-405B-hacky

Text Generation
Transformers
Safetensors
llama
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
sedrickkeh commited on
Commit
a123f9c
·
verified ·
1 Parent(s): 724e767

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 +32 -0
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c6cae7b7e6d23241844502f99d65486fa208588ae4ec692514fc686db214850f
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87d5639a8fd991eb8c87e1880f459bf42ef8f2c076e43594208d0c5dc2b4a2c8
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:b0df3146f034e202c316a788aafaa835bcb94e37fc0be50062cb01479299910c
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37dae0822e5c7453cce322677fa722c98125010fb5c2483611cea03e68c8c192
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:a65b63a39c828383b0748ec8e0bb7dae7a24c3a97838168d67f1770e0db7547c
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:142b9cc50010d0fbbb6657afdbed154f526a26e8ef29454147cde800aa645a1b
3
  size 4915916176
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:65e21d6700cf1b979f5cdcadc8d40b3f996786a0271b6c27f0ba53390e8b0c31
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c420f6774fb2f15a04739be82b00fbe9b45b8ac0dc01c0accb8135e70b344752
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -64,3 +64,35 @@
64
  {"current_steps": 630, "total_steps": 960, "loss": 0.5522, "lr": 5e-06, "epoch": 1.9676034348165494, "percentage": 65.62, "elapsed_time": "10:12:44", "remaining_time": "5:20:57"}
65
  {"current_steps": 640, "total_steps": 960, "loss": 0.5596, "lr": 5e-06, "epoch": 1.9988290398126463, "percentage": 66.67, "elapsed_time": "10:22:21", "remaining_time": "5:11:10"}
66
  {"current_steps": 640, "total_steps": 960, "eval_loss": 0.6045193076133728, "epoch": 1.9988290398126463, "percentage": 66.67, "elapsed_time": "10:28:15", "remaining_time": "5:14:07"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
64
  {"current_steps": 630, "total_steps": 960, "loss": 0.5522, "lr": 5e-06, "epoch": 1.9676034348165494, "percentage": 65.62, "elapsed_time": "10:12:44", "remaining_time": "5:20:57"}
65
  {"current_steps": 640, "total_steps": 960, "loss": 0.5596, "lr": 5e-06, "epoch": 1.9988290398126463, "percentage": 66.67, "elapsed_time": "10:22:21", "remaining_time": "5:11:10"}
66
  {"current_steps": 640, "total_steps": 960, "eval_loss": 0.6045193076133728, "epoch": 1.9988290398126463, "percentage": 66.67, "elapsed_time": "10:28:15", "remaining_time": "5:14:07"}
67
+ {"current_steps": 650, "total_steps": 960, "loss": 0.5662, "lr": 5e-06, "epoch": 2.030444964871194, "percentage": 67.71, "elapsed_time": "10:38:54", "remaining_time": "5:04:42"}
68
+ {"current_steps": 660, "total_steps": 960, "loss": 0.5018, "lr": 5e-06, "epoch": 2.061670569867291, "percentage": 68.75, "elapsed_time": "10:48:31", "remaining_time": "4:54:47"}
69
+ {"current_steps": 670, "total_steps": 960, "loss": 0.5057, "lr": 5e-06, "epoch": 2.092896174863388, "percentage": 69.79, "elapsed_time": "10:58:09", "remaining_time": "4:44:52"}
70
+ {"current_steps": 680, "total_steps": 960, "loss": 0.5036, "lr": 5e-06, "epoch": 2.1241217798594847, "percentage": 70.83, "elapsed_time": "11:07:46", "remaining_time": "4:34:58"}
71
+ {"current_steps": 690, "total_steps": 960, "loss": 0.5066, "lr": 5e-06, "epoch": 2.1553473848555815, "percentage": 71.88, "elapsed_time": "11:17:23", "remaining_time": "4:25:04"}
72
+ {"current_steps": 700, "total_steps": 960, "loss": 0.5086, "lr": 5e-06, "epoch": 2.1865729898516784, "percentage": 72.92, "elapsed_time": "11:27:01", "remaining_time": "4:15:10"}
73
+ {"current_steps": 710, "total_steps": 960, "loss": 0.508, "lr": 5e-06, "epoch": 2.217798594847775, "percentage": 73.96, "elapsed_time": "11:36:39", "remaining_time": "4:05:18"}
74
+ {"current_steps": 720, "total_steps": 960, "loss": 0.5073, "lr": 5e-06, "epoch": 2.249024199843872, "percentage": 75.0, "elapsed_time": "11:46:17", "remaining_time": "3:55:25"}
75
+ {"current_steps": 730, "total_steps": 960, "loss": 0.5126, "lr": 5e-06, "epoch": 2.280249804839969, "percentage": 76.04, "elapsed_time": "11:55:53", "remaining_time": "3:45:33"}
76
+ {"current_steps": 740, "total_steps": 960, "loss": 0.5098, "lr": 5e-06, "epoch": 2.3114754098360657, "percentage": 77.08, "elapsed_time": "12:05:31", "remaining_time": "3:35:41"}
77
+ {"current_steps": 750, "total_steps": 960, "loss": 0.5084, "lr": 5e-06, "epoch": 2.3427010148321625, "percentage": 78.12, "elapsed_time": "12:15:06", "remaining_time": "3:25:49"}
78
+ {"current_steps": 760, "total_steps": 960, "loss": 0.5097, "lr": 5e-06, "epoch": 2.3739266198282594, "percentage": 79.17, "elapsed_time": "12:24:44", "remaining_time": "3:15:59"}
79
+ {"current_steps": 770, "total_steps": 960, "loss": 0.5028, "lr": 5e-06, "epoch": 2.4051522248243558, "percentage": 80.21, "elapsed_time": "12:34:22", "remaining_time": "3:06:08"}
80
+ {"current_steps": 780, "total_steps": 960, "loss": 0.5102, "lr": 5e-06, "epoch": 2.4363778298204526, "percentage": 81.25, "elapsed_time": "12:43:59", "remaining_time": "2:56:18"}
81
+ {"current_steps": 790, "total_steps": 960, "loss": 0.5068, "lr": 5e-06, "epoch": 2.4676034348165494, "percentage": 82.29, "elapsed_time": "12:53:37", "remaining_time": "2:46:28"}
82
+ {"current_steps": 800, "total_steps": 960, "loss": 0.5141, "lr": 5e-06, "epoch": 2.4988290398126463, "percentage": 83.33, "elapsed_time": "13:03:14", "remaining_time": "2:36:38"}
83
+ {"current_steps": 810, "total_steps": 960, "loss": 0.5081, "lr": 5e-06, "epoch": 2.530054644808743, "percentage": 84.38, "elapsed_time": "13:12:52", "remaining_time": "2:26:49"}
84
+ {"current_steps": 820, "total_steps": 960, "loss": 0.5123, "lr": 5e-06, "epoch": 2.56128024980484, "percentage": 85.42, "elapsed_time": "13:22:30", "remaining_time": "2:17:00"}
85
+ {"current_steps": 830, "total_steps": 960, "loss": 0.5067, "lr": 5e-06, "epoch": 2.5925058548009368, "percentage": 86.46, "elapsed_time": "13:32:06", "remaining_time": "2:07:11"}
86
+ {"current_steps": 840, "total_steps": 960, "loss": 0.519, "lr": 5e-06, "epoch": 2.6237314597970336, "percentage": 87.5, "elapsed_time": "13:41:43", "remaining_time": "1:57:23"}
87
+ {"current_steps": 850, "total_steps": 960, "loss": 0.5048, "lr": 5e-06, "epoch": 2.6549570647931304, "percentage": 88.54, "elapsed_time": "13:51:21", "remaining_time": "1:47:35"}
88
+ {"current_steps": 860, "total_steps": 960, "loss": 0.5165, "lr": 5e-06, "epoch": 2.6861826697892273, "percentage": 89.58, "elapsed_time": "14:00:59", "remaining_time": "1:37:47"}
89
+ {"current_steps": 870, "total_steps": 960, "loss": 0.5154, "lr": 5e-06, "epoch": 2.717408274785324, "percentage": 90.62, "elapsed_time": "14:10:37", "remaining_time": "1:27:59"}
90
+ {"current_steps": 880, "total_steps": 960, "loss": 0.5091, "lr": 5e-06, "epoch": 2.748633879781421, "percentage": 91.67, "elapsed_time": "14:20:14", "remaining_time": "1:18:12"}
91
+ {"current_steps": 890, "total_steps": 960, "loss": 0.5112, "lr": 5e-06, "epoch": 2.7798594847775178, "percentage": 92.71, "elapsed_time": "14:29:52", "remaining_time": "1:08:25"}
92
+ {"current_steps": 900, "total_steps": 960, "loss": 0.5109, "lr": 5e-06, "epoch": 2.8110850897736146, "percentage": 93.75, "elapsed_time": "14:39:31", "remaining_time": "0:58:38"}
93
+ {"current_steps": 910, "total_steps": 960, "loss": 0.5166, "lr": 5e-06, "epoch": 2.8423106947697114, "percentage": 94.79, "elapsed_time": "14:49:07", "remaining_time": "0:48:51"}
94
+ {"current_steps": 920, "total_steps": 960, "loss": 0.519, "lr": 5e-06, "epoch": 2.873536299765808, "percentage": 95.83, "elapsed_time": "14:58:45", "remaining_time": "0:39:04"}
95
+ {"current_steps": 930, "total_steps": 960, "loss": 0.5181, "lr": 5e-06, "epoch": 2.9047619047619047, "percentage": 96.88, "elapsed_time": "15:08:22", "remaining_time": "0:29:18"}
96
+ {"current_steps": 940, "total_steps": 960, "loss": 0.5134, "lr": 5e-06, "epoch": 2.9359875097580015, "percentage": 97.92, "elapsed_time": "15:18:00", "remaining_time": "0:19:31"}
97
+ {"current_steps": 950, "total_steps": 960, "loss": 0.512, "lr": 5e-06, "epoch": 2.9672131147540983, "percentage": 98.96, "elapsed_time": "15:27:37", "remaining_time": "0:09:45"}
98
+ {"current_steps": 960, "total_steps": 960, "loss": 0.5083, "lr": 5e-06, "epoch": 2.998438719750195, "percentage": 100.0, "elapsed_time": "15:37:14", "remaining_time": "0:00:00"}