Commit
·
f462d40
1
Parent(s):
be65f84
Upload 10 files
Browse files- checkpoint-200/optimizer.pt +3 -0
- checkpoint-200/pytorch_model.bin +3 -0
- checkpoint-200/rng_state_0.pth +3 -0
- checkpoint-200/rng_state_1.pth +3 -0
- checkpoint-200/rng_state_2.pth +3 -0
- checkpoint-200/rng_state_3.pth +3 -0
- checkpoint-200/scaler.pt +3 -0
- checkpoint-200/scheduler.pt +3 -0
- checkpoint-200/trainer_state.json +144 -0
- checkpoint-200/training_args.bin +3 -0
checkpoint-200/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9a0846351178ed12389fabe5183bdbfbc0308ace53bba3eccbc7eca032fc8394
|
3 |
+
size 52562757
|
checkpoint-200/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7afe55724db878f1af13f12941f09d2aa1a17a8c634a0f72b05f6d5d7a520fe8
|
3 |
+
size 26271757
|
checkpoint-200/rng_state_0.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:819bbebd4638bc94da4de230bc6ce2f470d518a082e944aedd33a78f501377f9
|
3 |
+
size 17655
|
checkpoint-200/rng_state_1.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6fb1711896b18fae6b3b01415cfe8630f68197edc43417b873cad79e315270bd
|
3 |
+
size 17655
|
checkpoint-200/rng_state_2.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:87213c71bd5423f9e0ce464f07994f133bfb98c7344d36f4951e6665a01e0435
|
3 |
+
size 17655
|
checkpoint-200/rng_state_3.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:152127eb111c9847a65aeef6260b412925df7be5584ebe72e4c3f5f0ab72570d
|
3 |
+
size 17655
|
checkpoint-200/scaler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4fccf0f9be1bb8f24861e4393745b3e09cc2687125a69e3757955fb0f0925ea5
|
3 |
+
size 557
|
checkpoint-200/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4ff459945c9072ddb427be2c55fc1e9f0c4f9793c6d7e1604ab714244220f037
|
3 |
+
size 627
|
checkpoint-200/trainer_state.json
ADDED
@@ -0,0 +1,144 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.7602501511573792,
|
3 |
+
"best_model_checkpoint": "../outputs/13b_chat_lora_ar/checkpoint-200",
|
4 |
+
"epoch": 0.6389776357827476,
|
5 |
+
"global_step": 200,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.03,
|
12 |
+
"learning_rate": 2.9999999999999997e-05,
|
13 |
+
"loss": 1.8411,
|
14 |
+
"step": 10
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.06,
|
18 |
+
"learning_rate": 5.9999999999999995e-05,
|
19 |
+
"loss": 1.7918,
|
20 |
+
"step": 20
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 0.1,
|
24 |
+
"learning_rate": 8.999999999999999e-05,
|
25 |
+
"loss": 1.5909,
|
26 |
+
"step": 30
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 0.13,
|
30 |
+
"learning_rate": 0.00011999999999999999,
|
31 |
+
"loss": 1.2588,
|
32 |
+
"step": 40
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 0.16,
|
36 |
+
"learning_rate": 0.00015,
|
37 |
+
"loss": 1.0547,
|
38 |
+
"step": 50
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 0.19,
|
42 |
+
"learning_rate": 0.00017999999999999998,
|
43 |
+
"loss": 0.9741,
|
44 |
+
"step": 60
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.22,
|
48 |
+
"learning_rate": 0.00020999999999999998,
|
49 |
+
"loss": 0.9258,
|
50 |
+
"step": 70
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 0.26,
|
54 |
+
"learning_rate": 0.00023999999999999998,
|
55 |
+
"loss": 0.9079,
|
56 |
+
"step": 80
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 0.29,
|
60 |
+
"learning_rate": 0.00027,
|
61 |
+
"loss": 0.8687,
|
62 |
+
"step": 90
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 0.32,
|
66 |
+
"learning_rate": 0.0003,
|
67 |
+
"loss": 0.8257,
|
68 |
+
"step": 100
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 0.35,
|
72 |
+
"learning_rate": 0.00028591549295774643,
|
73 |
+
"loss": 0.8167,
|
74 |
+
"step": 110
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"epoch": 0.38,
|
78 |
+
"learning_rate": 0.00027183098591549294,
|
79 |
+
"loss": 0.797,
|
80 |
+
"step": 120
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 0.42,
|
84 |
+
"learning_rate": 0.0002577464788732394,
|
85 |
+
"loss": 0.7874,
|
86 |
+
"step": 130
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.45,
|
90 |
+
"learning_rate": 0.00024366197183098588,
|
91 |
+
"loss": 0.7834,
|
92 |
+
"step": 140
|
93 |
+
},
|
94 |
+
{
|
95 |
+
"epoch": 0.48,
|
96 |
+
"learning_rate": 0.0002295774647887324,
|
97 |
+
"loss": 0.7813,
|
98 |
+
"step": 150
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 0.51,
|
102 |
+
"learning_rate": 0.00021549295774647887,
|
103 |
+
"loss": 0.7717,
|
104 |
+
"step": 160
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 0.54,
|
108 |
+
"learning_rate": 0.00020140845070422533,
|
109 |
+
"loss": 0.7713,
|
110 |
+
"step": 170
|
111 |
+
},
|
112 |
+
{
|
113 |
+
"epoch": 0.58,
|
114 |
+
"learning_rate": 0.00018732394366197181,
|
115 |
+
"loss": 0.766,
|
116 |
+
"step": 180
|
117 |
+
},
|
118 |
+
{
|
119 |
+
"epoch": 0.61,
|
120 |
+
"learning_rate": 0.0001732394366197183,
|
121 |
+
"loss": 0.7621,
|
122 |
+
"step": 190
|
123 |
+
},
|
124 |
+
{
|
125 |
+
"epoch": 0.64,
|
126 |
+
"learning_rate": 0.00015915492957746478,
|
127 |
+
"loss": 0.7635,
|
128 |
+
"step": 200
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.64,
|
132 |
+
"eval_loss": 0.7602501511573792,
|
133 |
+
"eval_runtime": 39.349,
|
134 |
+
"eval_samples_per_second": 50.827,
|
135 |
+
"eval_steps_per_second": 1.601,
|
136 |
+
"step": 200
|
137 |
+
}
|
138 |
+
],
|
139 |
+
"max_steps": 313,
|
140 |
+
"num_train_epochs": 1,
|
141 |
+
"total_flos": 6.32024838701056e+17,
|
142 |
+
"trial_name": null,
|
143 |
+
"trial_params": null
|
144 |
+
}
|
checkpoint-200/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:97071ecd0635e01608ff31da20858e2f0b82e2c0040e6ae716e2f136658208c0
|
3 |
+
size 3899
|