Hugging Face's logo

OpenGVLab
/
cllm_td_opt

Text Generation
Transformers
PyTorch
opt
text-generation-inference
Model card Files
xet
 Community
1
zyliu commited on
Commit
0c2be7f
·
1 Parent(s): 77b89d9

update model

Browse files
Files changed (2) hide show
  1. pytorch_model.bin +1 -1
  2. trainer_state.json +10 -10
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e8e503d2a6e9e148d20417c2f5a1801a3e1cc30ad9003ea9f29a7e63ead0f6f7
3
  size 5303326905
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c4cac0338ea8d029ea576c1de0c1aaf04929e5493e23af567730887a3eb69a8
3
  size 5303326905
trainer_state.json CHANGED
@@ -10,19 +10,19 @@
10
  {
11
  "epoch": 0.78,
12
  "learning_rate": 1.793975255513717e-05,
13
- "loss": 0.0242,
14
  "step": 500
15
  },
16
  {
17
  "epoch": 1.56,
18
  "learning_rate": 1.5250134480903713e-05,
19
- "loss": 0.002,
20
  "step": 1000
21
  },
22
  {
23
  "epoch": 2.35,
24
  "learning_rate": 1.2560516406670254e-05,
25
- "loss": 0.0013,
26
  "step": 1500
27
  },
28
  {
@@ -34,7 +34,7 @@
34
  {
35
  "epoch": 3.91,
36
  "learning_rate": 7.181280258203336e-06,
37
- "loss": 0.0009,
38
  "step": 2500
39
  },
40
  {
@@ -52,16 +52,16 @@
52
  {
53
  "epoch": 6.0,
54
  "step": 3834,
55
- "total_flos": 2401267745816576.0,
56
- "train_loss": 0.0040198439031637265,
57
- "train_runtime": 24850.8432,
58
- "train_samples_per_second": 19.743,
59
- "train_steps_per_second": 0.154
60
  }
61
  ],
62
  "max_steps": 3834,
63
  "num_train_epochs": 6,
64
- "total_flos": 2401267745816576.0,
65
  "trial_name": null,
66
  "trial_params": null
67
  }
 
10
  {
11
  "epoch": 0.78,
12
  "learning_rate": 1.793975255513717e-05,
13
+ "loss": 0.0241,
14
  "step": 500
15
  },
16
  {
17
  "epoch": 1.56,
18
  "learning_rate": 1.5250134480903713e-05,
19
+ "loss": 0.0021,
20
  "step": 1000
21
  },
22
  {
23
  "epoch": 2.35,
24
  "learning_rate": 1.2560516406670254e-05,
25
+ "loss": 0.0014,
26
  "step": 1500
27
  },
28
  {
 
34
  {
35
  "epoch": 3.91,
36
  "learning_rate": 7.181280258203336e-06,
37
+ "loss": 0.0008,
38
  "step": 2500
39
  },
40
  {
 
52
  {
53
  "epoch": 6.0,
54
  "step": 3834,
55
+ "total_flos": 2403004334473216.0,
56
+ "train_loss": 0.0040491660264984795,
57
+ "train_runtime": 24808.6685,
58
+ "train_samples_per_second": 19.777,
59
+ "train_steps_per_second": 0.155
60
  }
61
  ],
62
  "max_steps": 3834,
63
  "num_train_epochs": 6,
64
+ "total_flos": 2403004334473216.0,
65
  "trial_name": null,
66
  "trial_params": null
67
  }