Training in progress, step 600
Browse files- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/pytorch_model.bin +1 -1
- last-checkpoint/rng_state.pth +1 -1
- last-checkpoint/scaler.pt +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +16 -144
- last-checkpoint/training_args.bin +2 -2
- pytorch_model.bin +1 -1
- runs/May10_05-23-50_beffab83ea5d/1683696283.5000205/events.out.tfevents.1683696283.beffab83ea5d.798.3 +3 -0
- runs/May10_05-23-50_beffab83ea5d/events.out.tfevents.1683696283.beffab83ea5d.798.2 +3 -0
- runs/May10_05-25-39_beffab83ea5d/1683696365.5629/events.out.tfevents.1683696365.beffab83ea5d.7168.1 +3 -0
- runs/May10_05-25-39_beffab83ea5d/events.out.tfevents.1683696365.beffab83ea5d.7168.0 +3 -0
- runs/May10_05-26-25_beffab83ea5d/1683696405.815436/events.out.tfevents.1683696405.beffab83ea5d.7168.3 +3 -0
- runs/May10_05-26-25_beffab83ea5d/events.out.tfevents.1683696405.beffab83ea5d.7168.2 +3 -0
- runs/May10_05-27-07_beffab83ea5d/1683696444.6674943/events.out.tfevents.1683696444.beffab83ea5d.7168.5 +3 -0
- runs/May10_05-27-07_beffab83ea5d/events.out.tfevents.1683696444.beffab83ea5d.7168.4 +3 -0
- runs/May10_05-28-48_beffab83ea5d/1683696547.3462582/events.out.tfevents.1683696547.beffab83ea5d.7168.7 +3 -0
- runs/May10_05-28-48_beffab83ea5d/events.out.tfevents.1683696547.beffab83ea5d.7168.6 +3 -0
- runs/May10_05-34-59_beffab83ea5d/1683696914.222446/events.out.tfevents.1683696914.beffab83ea5d.9415.1 +3 -0
- runs/May10_05-34-59_beffab83ea5d/1683696918.8552527/events.out.tfevents.1683696918.beffab83ea5d.9415.2 +3 -0
- runs/May10_05-34-59_beffab83ea5d/events.out.tfevents.1683696914.beffab83ea5d.9415.0 +3 -0
- runs/May10_05-43-13_beffab83ea5d/1683697416.1476538/events.out.tfevents.1683697416.beffab83ea5d.9415.4 +3 -0
- runs/May10_05-43-13_beffab83ea5d/events.out.tfevents.1683697416.beffab83ea5d.9415.3 +3 -0
- runs/May10_05-44-37_beffab83ea5d/1683697498.9784644/events.out.tfevents.1683697498.beffab83ea5d.9415.6 +3 -0
- runs/May10_05-44-37_beffab83ea5d/events.out.tfevents.1683697498.beffab83ea5d.9415.5 +3 -0
- runs/May10_05-47-52_beffab83ea5d/1683697688.3990335/events.out.tfevents.1683697688.beffab83ea5d.12842.1 +3 -0
- runs/May10_05-47-52_beffab83ea5d/events.out.tfevents.1683697688.beffab83ea5d.12842.0 +3 -0
- training_args.bin +2 -2
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 3871543575
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a70da9c307b89e0f6803e6b4d790724eaf22f16cf5a39b89e5be664b7c6ef817
|
3 |
size 3871543575
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1944201353
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9e2279d0b00eea02275f19b0918fc5caf16bc305821941ac3a1bfabdaec14495
|
3 |
size 1944201353
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14575
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9add67e0e7c64985d7f86ed3237947f4d8273983a833a5710b022a6a1bea08e2
|
3 |
size 14575
|
last-checkpoint/scaler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 557
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5dc9eacfeb00bd0bfeb98934a2309be01be65b288e0d747bbfc423b32679169f
|
3 |
size 557
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 627
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:753fb611d101de33818037c538ed00dd755c130ad830e2fc514a0dba409c9a50
|
3 |
size 627
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,160 +1,32 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch": 0
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
9 |
"log_history": [
|
10 |
{
|
11 |
-
"epoch":
|
12 |
-
"learning_rate": 3.
|
13 |
-
"loss":
|
14 |
"step": 500
|
15 |
},
|
16 |
{
|
17 |
-
"epoch":
|
18 |
-
"
|
19 |
-
"
|
20 |
-
"
|
21 |
-
|
22 |
-
|
23 |
-
"
|
24 |
-
"
|
25 |
-
"loss": 1.1117,
|
26 |
-
"step": 1500
|
27 |
-
},
|
28 |
-
{
|
29 |
-
"epoch": 0.21,
|
30 |
-
"learning_rate": 3.775641735336502e-05,
|
31 |
-
"loss": 1.1636,
|
32 |
-
"step": 2000
|
33 |
-
},
|
34 |
-
{
|
35 |
-
"epoch": 0.26,
|
36 |
-
"learning_rate": 3.583764809409783e-05,
|
37 |
-
"loss": 1.1947,
|
38 |
-
"step": 2500
|
39 |
-
},
|
40 |
-
{
|
41 |
-
"epoch": 0.32,
|
42 |
-
"learning_rate": 3.34144538007923e-05,
|
43 |
-
"loss": 1.1979,
|
44 |
-
"step": 3000
|
45 |
-
},
|
46 |
-
{
|
47 |
-
"epoch": 0.37,
|
48 |
-
"learning_rate": 3.05640125908444e-05,
|
49 |
-
"loss": 1.4767,
|
50 |
-
"step": 3500
|
51 |
-
},
|
52 |
-
{
|
53 |
-
"epoch": 0.35,
|
54 |
-
"learning_rate": 3.1554332626816203e-05,
|
55 |
-
"loss": 0.9765,
|
56 |
-
"step": 4000
|
57 |
-
},
|
58 |
-
{
|
59 |
-
"epoch": 0.4,
|
60 |
-
"learning_rate": 2.9009680903546416e-05,
|
61 |
-
"loss": 1.4107,
|
62 |
-
"step": 4500
|
63 |
-
},
|
64 |
-
{
|
65 |
-
"epoch": 0.44,
|
66 |
-
"learning_rate": 2.6260730367115988e-05,
|
67 |
-
"loss": 1.5024,
|
68 |
-
"step": 5000
|
69 |
-
},
|
70 |
-
{
|
71 |
-
"epoch": 0.39,
|
72 |
-
"learning_rate": 2.9542651711125413e-05,
|
73 |
-
"loss": 0.975,
|
74 |
-
"step": 5500
|
75 |
-
},
|
76 |
-
{
|
77 |
-
"epoch": 0.42,
|
78 |
-
"learning_rate": 2.7394824453041223e-05,
|
79 |
-
"loss": 1.1808,
|
80 |
-
"step": 6000
|
81 |
-
},
|
82 |
-
{
|
83 |
-
"epoch": 0.46,
|
84 |
-
"learning_rate": 2.5133790365330005e-05,
|
85 |
-
"loss": 1.1449,
|
86 |
-
"step": 6500
|
87 |
-
},
|
88 |
-
{
|
89 |
-
"epoch": 0.49,
|
90 |
-
"learning_rate": 2.2799977645691646e-05,
|
91 |
-
"loss": 1.4763,
|
92 |
-
"step": 7000
|
93 |
-
},
|
94 |
-
{
|
95 |
-
"epoch": 0.53,
|
96 |
-
"learning_rate": 2.0426471341395805e-05,
|
97 |
-
"loss": 1.6014,
|
98 |
-
"step": 7500
|
99 |
-
},
|
100 |
-
{
|
101 |
-
"epoch": 0.56,
|
102 |
-
"learning_rate": 1.8046919211584273e-05,
|
103 |
-
"loss": 1.6065,
|
104 |
-
"step": 8000
|
105 |
-
},
|
106 |
-
{
|
107 |
-
"epoch": 0.6,
|
108 |
-
"learning_rate": 1.569505472339987e-05,
|
109 |
-
"loss": 1.6454,
|
110 |
-
"step": 8500
|
111 |
-
},
|
112 |
-
{
|
113 |
-
"epoch": 0.63,
|
114 |
-
"learning_rate": 1.3404218833084988e-05,
|
115 |
-
"loss": 1.6504,
|
116 |
-
"step": 9000
|
117 |
-
},
|
118 |
-
{
|
119 |
-
"epoch": 0.67,
|
120 |
-
"learning_rate": 1.1206887331469077e-05,
|
121 |
-
"loss": 1.6647,
|
122 |
-
"step": 9500
|
123 |
-
},
|
124 |
-
{
|
125 |
-
"epoch": 0.71,
|
126 |
-
"learning_rate": 9.134210454381382e-06,
|
127 |
-
"loss": 1.7032,
|
128 |
-
"step": 10000
|
129 |
-
},
|
130 |
-
{
|
131 |
-
"epoch": 0.74,
|
132 |
-
"learning_rate": 7.215571284652925e-06,
|
133 |
-
"loss": 1.6892,
|
134 |
-
"step": 10500
|
135 |
-
},
|
136 |
-
{
|
137 |
-
"epoch": 0.78,
|
138 |
-
"learning_rate": 5.478169205974455e-06,
|
139 |
-
"loss": 1.7176,
|
140 |
-
"step": 11000
|
141 |
-
},
|
142 |
-
{
|
143 |
-
"epoch": 0.81,
|
144 |
-
"learning_rate": 3.946634313732729e-06,
|
145 |
-
"loss": 1.7457,
|
146 |
-
"step": 11500
|
147 |
-
},
|
148 |
-
{
|
149 |
-
"epoch": 0.85,
|
150 |
-
"learning_rate": 2.645046185968865e-06,
|
151 |
-
"loss": 1.7474,
|
152 |
-
"step": 12000
|
153 |
}
|
154 |
],
|
155 |
-
"max_steps":
|
156 |
-
"num_train_epochs":
|
157 |
-
"total_flos":
|
158 |
"trial_name": null,
|
159 |
"trial_params": null
|
160 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 20.0,
|
5 |
+
"global_step": 600,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
9 |
"log_history": [
|
10 |
{
|
11 |
+
"epoch": 16.67,
|
12 |
+
"learning_rate": 3.0977443609452007e-06,
|
13 |
+
"loss": 0.3114,
|
14 |
"step": 500
|
15 |
},
|
16 |
{
|
17 |
+
"epoch": 16.67,
|
18 |
+
"eval_bleu": 23.7507,
|
19 |
+
"eval_gen_len": 20.007,
|
20 |
+
"eval_loss": 2.0595486164093018,
|
21 |
+
"eval_runtime": 132.2443,
|
22 |
+
"eval_samples_per_second": 4.31,
|
23 |
+
"eval_steps_per_second": 0.484,
|
24 |
+
"step": 500
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
25 |
}
|
26 |
],
|
27 |
+
"max_steps": 600,
|
28 |
+
"num_train_epochs": 20,
|
29 |
+
"total_flos": 229044332888064.0,
|
30 |
"trial_name": null,
|
31 |
"trial_params": null
|
32 |
}
|
last-checkpoint/training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a6548a11b5bf41ca0d30d25ae762960cdd697b755d28048f063b6a4fe41abe08
|
3 |
+
size 3771
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1944201353
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9e2279d0b00eea02275f19b0918fc5caf16bc305821941ac3a1bfabdaec14495
|
3 |
size 1944201353
|
runs/May10_05-23-50_beffab83ea5d/1683696283.5000205/events.out.tfevents.1683696283.beffab83ea5d.798.3
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5f01e5e87bf0b6bf747b5309ff23c9480fe25b53f69a6bceac84dd4b1052a299
|
3 |
+
size 6187
|
runs/May10_05-23-50_beffab83ea5d/events.out.tfevents.1683696283.beffab83ea5d.798.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2e2dcad79710d03845a2e4987d82aeb4d9451c60c71735b707f716a8d4c929ae
|
3 |
+
size 4817
|
runs/May10_05-25-39_beffab83ea5d/1683696365.5629/events.out.tfevents.1683696365.beffab83ea5d.7168.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:efbbad9c17993e3f88ec52a6140d7249f7cdfa223aa96f95cd759b56fbadd070
|
3 |
+
size 6187
|
runs/May10_05-25-39_beffab83ea5d/events.out.tfevents.1683696365.beffab83ea5d.7168.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:64d3f7973d3020067ba1ee4ccf00dabe0150c73e6b84c80672f05c8c6ffd1496
|
3 |
+
size 4463
|
runs/May10_05-26-25_beffab83ea5d/1683696405.815436/events.out.tfevents.1683696405.beffab83ea5d.7168.3
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e34b010dbdcade1ed4195dc830014694bd7f5a3a6c391447b906985803c5d925
|
3 |
+
size 6187
|
runs/May10_05-26-25_beffab83ea5d/events.out.tfevents.1683696405.beffab83ea5d.7168.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d584ec19e4c2d7651dad0ea48871a102b5311607d20cb3845ed86449e2fefd28
|
3 |
+
size 4463
|
runs/May10_05-27-07_beffab83ea5d/1683696444.6674943/events.out.tfevents.1683696444.beffab83ea5d.7168.5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:90c10b098cf0ae3110a5cc6aa4802cccd12cb25e325e41a2bab4f4d66bf78549
|
3 |
+
size 6184
|
runs/May10_05-27-07_beffab83ea5d/events.out.tfevents.1683696444.beffab83ea5d.7168.4
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a6783a1d0f62b26035440740fa6aff489202b699d5331c747a8d00ce9a38694c
|
3 |
+
size 4459
|
runs/May10_05-28-48_beffab83ea5d/1683696547.3462582/events.out.tfevents.1683696547.beffab83ea5d.7168.7
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5efc32be3303686228f7f2b57be3ee7dcf13a066f1c471a2aa7d23a080bc8b50
|
3 |
+
size 6184
|
runs/May10_05-28-48_beffab83ea5d/events.out.tfevents.1683696547.beffab83ea5d.7168.6
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d3df2472ff9e93798e4c8b06a22257afcf5d1c13b653694827bd873b7a5d47a6
|
3 |
+
size 4458
|
runs/May10_05-34-59_beffab83ea5d/1683696914.222446/events.out.tfevents.1683696914.beffab83ea5d.9415.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:80854aeaaf56a3ecd7d14bc06089ae4e0888ab0ea0a95941489b208273efbaff
|
3 |
+
size 6184
|
runs/May10_05-34-59_beffab83ea5d/1683696918.8552527/events.out.tfevents.1683696918.beffab83ea5d.9415.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8a617ce3131d18144d4e5540b634aef77f29a0855701e2c50ebd14b78e47e699
|
3 |
+
size 6184
|
runs/May10_05-34-59_beffab83ea5d/events.out.tfevents.1683696914.beffab83ea5d.9415.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:604f8dec8a7e6d729b6c118c377ab31cb7a2e3f39ec9bdabffa6cb81633d2254
|
3 |
+
size 8828
|
runs/May10_05-43-13_beffab83ea5d/1683697416.1476538/events.out.tfevents.1683697416.beffab83ea5d.9415.4
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9f7d4d6c63629f3c4409e292cd48ddde75fc76668833d74de768a6d9dbf1ca74
|
3 |
+
size 6187
|
runs/May10_05-43-13_beffab83ea5d/events.out.tfevents.1683697416.beffab83ea5d.9415.3
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a039f0c1a57e6b0e47c2511ba8edb49b63636b06caab4cd99350e5d54efd07b8
|
3 |
+
size 4184
|
runs/May10_05-44-37_beffab83ea5d/1683697498.9784644/events.out.tfevents.1683697498.beffab83ea5d.9415.6
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a520a475c76f06745a08acd98e3ecd13dfe40aad3183affa4835654dbd6daf64
|
3 |
+
size 6190
|
runs/May10_05-44-37_beffab83ea5d/events.out.tfevents.1683697498.beffab83ea5d.9415.5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9a7409ccc21b6db26985dd9a9c87014b0354e00112bc8a49b9931d55c9b4fa82
|
3 |
+
size 4184
|
runs/May10_05-47-52_beffab83ea5d/1683697688.3990335/events.out.tfevents.1683697688.beffab83ea5d.12842.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:844f24ba42bd8c31e8a83f9e8d81635ea5e30fe03daaa2b280562859d12638c3
|
3 |
+
size 6190
|
runs/May10_05-47-52_beffab83ea5d/events.out.tfevents.1683697688.beffab83ea5d.12842.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:02843b4001406abec31e4ed18c77db8e05eda2bed214207d672cdd6b3a9a6804
|
3 |
+
size 4988
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a6548a11b5bf41ca0d30d25ae762960cdd697b755d28048f063b6a4fe41abe08
|
3 |
+
size 3771
|