Hugging Face's logo

raffelm
/
bloomz-simulmask-en-fr

PyTorch
bloom
Model card Files
xet
Community
raffelm commited on
Commit
8f00ea1
·
verified ·
1 Parent(s): f754e5c

Upload 10 files

Browse files
Files changed (3) hide show
  1. pytorch_model.bin +1 -1
  2. trainer_state.json +35 -35
  3. training_args.bin +1 -1
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a3a736720d95ba8bd0a30613ae46c36a84cd21335d44c6ebd7ec5bbad305e4de
3
  size 1118121246
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c66a7a5ac362812ec8bf77fac363f364326766289cf1db92c1078e4313a8329a
3
  size 1118121246
trainer_state.json CHANGED
@@ -11,99 +11,99 @@
11
  {
12
  "epoch": 0.27,
13
  "learning_rate": 0.00011454256850621083,
14
- "loss": 1.5582,
15
  "step": 1000
16
  },
17
  {
18
  "epoch": 0.27,
19
- "eval_loss": 2.1084280014038086,
20
- "eval_runtime": 3.7072,
21
- "eval_samples_per_second": 240.072,
22
- "eval_steps_per_second": 30.211,
23
  "step": 1000
24
  },
25
  {
26
  "epoch": 0.55,
27
  "learning_rate": 8.099382692526634e-05,
28
- "loss": 1.2078,
29
  "step": 2000
30
  },
31
  {
32
  "epoch": 0.55,
33
- "eval_loss": 1.7273415327072144,
34
- "eval_runtime": 3.6878,
35
- "eval_samples_per_second": 241.334,
36
- "eval_steps_per_second": 30.37,
37
  "step": 2000
38
  },
39
  {
40
  "epoch": 0.82,
41
  "learning_rate": 6.613118276073197e-05,
42
- "loss": 1.0718,
43
  "step": 3000
44
  },
45
  {
46
  "epoch": 0.82,
47
- "eval_loss": 1.6304664611816406,
48
- "eval_runtime": 3.687,
49
- "eval_samples_per_second": 241.39,
50
- "eval_steps_per_second": 30.377,
51
  "step": 3000
52
  },
53
  {
54
  "epoch": 1.1,
55
  "learning_rate": 5.7271284253105416e-05,
56
- "loss": 0.9125,
57
  "step": 4000
58
  },
59
  {
60
  "epoch": 1.1,
61
- "eval_loss": 1.5620102882385254,
62
- "eval_runtime": 3.6964,
63
- "eval_samples_per_second": 240.774,
64
- "eval_steps_per_second": 30.3,
65
  "step": 4000
66
  },
67
  {
68
  "epoch": 1.37,
69
  "learning_rate": 5.1224993899462795e-05,
70
- "loss": 0.7192,
71
  "step": 5000
72
  },
73
  {
74
  "epoch": 1.37,
75
- "eval_loss": 1.5576059818267822,
76
- "eval_runtime": 3.6938,
77
- "eval_samples_per_second": 240.945,
78
- "eval_steps_per_second": 30.321,
79
  "step": 5000
80
  },
81
  {
82
  "epoch": 1.65,
83
  "learning_rate": 4.676180777800049e-05,
84
- "loss": 0.7183,
85
  "step": 6000
86
  },
87
  {
88
  "epoch": 1.65,
89
- "eval_loss": 1.5256845951080322,
90
- "eval_runtime": 3.6978,
91
- "eval_samples_per_second": 240.681,
92
- "eval_steps_per_second": 30.288,
93
  "step": 6000
94
  },
95
  {
96
  "epoch": 1.92,
97
  "learning_rate": 4.329302154257329e-05,
98
- "loss": 0.716,
99
  "step": 7000
100
  },
101
  {
102
  "epoch": 1.92,
103
- "eval_loss": 1.530071496963501,
104
- "eval_runtime": 3.6992,
105
- "eval_samples_per_second": 240.591,
106
- "eval_steps_per_second": 30.277,
107
  "step": 7000
108
  }
109
  ],
 
11
  {
12
  "epoch": 0.27,
13
  "learning_rate": 0.00011454256850621083,
14
+ "loss": 1.5046,
15
  "step": 1000
16
  },
17
  {
18
  "epoch": 0.27,
19
+ "eval_loss": 2.7397329807281494,
20
+ "eval_runtime": 3.8318,
21
+ "eval_samples_per_second": 232.268,
22
+ "eval_steps_per_second": 29.229,
23
  "step": 1000
24
  },
25
  {
26
  "epoch": 0.55,
27
  "learning_rate": 8.099382692526634e-05,
28
+ "loss": 1.1958,
29
  "step": 2000
30
  },
31
  {
32
  "epoch": 0.55,
33
+ "eval_loss": 2.4763500690460205,
34
+ "eval_runtime": 3.7761,
35
+ "eval_samples_per_second": 235.692,
36
+ "eval_steps_per_second": 29.66,
37
  "step": 2000
38
  },
39
  {
40
  "epoch": 0.82,
41
  "learning_rate": 6.613118276073197e-05,
42
+ "loss": 1.0733,
43
  "step": 3000
44
  },
45
  {
46
  "epoch": 0.82,
47
+ "eval_loss": 2.391991138458252,
48
+ "eval_runtime": 3.7954,
49
+ "eval_samples_per_second": 234.495,
50
+ "eval_steps_per_second": 29.51,
51
  "step": 3000
52
  },
53
  {
54
  "epoch": 1.1,
55
  "learning_rate": 5.7271284253105416e-05,
56
+ "loss": 0.9219,
57
  "step": 4000
58
  },
59
  {
60
  "epoch": 1.1,
61
+ "eval_loss": 2.3582706451416016,
62
+ "eval_runtime": 3.7454,
63
+ "eval_samples_per_second": 237.627,
64
+ "eval_steps_per_second": 29.904,
65
  "step": 4000
66
  },
67
  {
68
  "epoch": 1.37,
69
  "learning_rate": 5.1224993899462795e-05,
70
+ "loss": 0.7324,
71
  "step": 5000
72
  },
73
  {
74
  "epoch": 1.37,
75
+ "eval_loss": 2.3552770614624023,
76
+ "eval_runtime": 3.775,
77
+ "eval_samples_per_second": 235.76,
78
+ "eval_steps_per_second": 29.669,
79
  "step": 5000
80
  },
81
  {
82
  "epoch": 1.65,
83
  "learning_rate": 4.676180777800049e-05,
84
+ "loss": 0.7311,
85
  "step": 6000
86
  },
87
  {
88
  "epoch": 1.65,
89
+ "eval_loss": 2.318331003189087,
90
+ "eval_runtime": 3.7693,
91
+ "eval_samples_per_second": 236.117,
92
+ "eval_steps_per_second": 29.714,
93
  "step": 6000
94
  },
95
  {
96
  "epoch": 1.92,
97
  "learning_rate": 4.329302154257329e-05,
98
+ "loss": 0.7289,
99
  "step": 7000
100
  },
101
  {
102
  "epoch": 1.92,
103
+ "eval_loss": 2.3413245677948,
104
+ "eval_runtime": 3.7689,
105
+ "eval_samples_per_second": 236.14,
106
+ "eval_steps_per_second": 29.717,
107
  "step": 7000
108
  }
109
  ],
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:84a305c08093b6e784a8914dca2025b0771beaeb7f5a9755194979837345471f
3
  size 4600
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96c3dd11f8c11339c2aea1f3d87d9c4f9426241acd4630ac2b3063a1841d5949
3
  size 4600