Training in progress, step 20000
Browse files- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/pytorch_model.bin +1 -1
- last-checkpoint/rng_state_0.pth +1 -1
- last-checkpoint/rng_state_1.pth +2 -2
- last-checkpoint/rng_state_2.pth +2 -2
- last-checkpoint/rng_state_3.pth +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +77 -3
- pytorch_model.bin +1 -1
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 893438545
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:25a7851a76774c9d24610e8c4b64407ceaf0cba09a83e925a33fb41a03307ed7
|
3 |
size 893438545
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 449471589
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d0d795304e92a242fb3daabda286fa8f94b1ee38faba8dda70081c35bf054d0f
|
3 |
size 449471589
|
last-checkpoint/rng_state_0.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14503
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3d483ecbfd7c4ae648878217616c66bacf030cae7b2ded7d170987d76a2250ac
|
3 |
size 14503
|
last-checkpoint/rng_state_1.pth
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 sha256:044ec9788542bc63cbbb94478363f427bd5fb7e95aea2357c2a84029d6027b74
|
3 |
+
size 14503
|
last-checkpoint/rng_state_2.pth
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 sha256:8cf0219f03126c61d6fe702f807db15414297e302e582e7db754139585c455cc
|
3 |
+
size 14439
|
last-checkpoint/rng_state_3.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14503
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:000f13089b5059ffd9098e2fa284df7971e249ea2a6dfce01fab8815f9fa26de
|
3 |
size 14503
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 623
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5ca250cf2344e8df6eed15e28ea548564b75ef302cf69c48962d23fb49df8b25
|
3 |
size 623
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,8 +1,8 @@
|
|
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,
|
@@ -80,11 +80,85 @@
|
|
80 |
"eval_samples_per_second": 879.066,
|
81 |
"eval_steps_per_second": 14.065,
|
82 |
"step": 10000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
83 |
}
|
84 |
],
|
85 |
"max_steps": 1000000,
|
86 |
"num_train_epochs": 16,
|
87 |
-
"total_flos":
|
88 |
"trial_name": null,
|
89 |
"trial_params": null
|
90 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.30540412600974237,
|
5 |
+
"global_step": 20000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
80 |
"eval_samples_per_second": 879.066,
|
81 |
"eval_steps_per_second": 14.065,
|
82 |
"step": 10000
|
83 |
+
},
|
84 |
+
{
|
85 |
+
"epoch": 0.17,
|
86 |
+
"learning_rate": 3.2999999999999996e-05,
|
87 |
+
"loss": 0.7148,
|
88 |
+
"step": 11000
|
89 |
+
},
|
90 |
+
{
|
91 |
+
"epoch": 0.18,
|
92 |
+
"learning_rate": 3.5999999999999994e-05,
|
93 |
+
"loss": 0.6963,
|
94 |
+
"step": 12000
|
95 |
+
},
|
96 |
+
{
|
97 |
+
"epoch": 0.2,
|
98 |
+
"learning_rate": 3.9e-05,
|
99 |
+
"loss": 0.6755,
|
100 |
+
"step": 13000
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 0.21,
|
104 |
+
"learning_rate": 4.2e-05,
|
105 |
+
"loss": 0.6516,
|
106 |
+
"step": 14000
|
107 |
+
},
|
108 |
+
{
|
109 |
+
"epoch": 0.23,
|
110 |
+
"learning_rate": 4.4999999999999996e-05,
|
111 |
+
"loss": 0.6412,
|
112 |
+
"step": 15000
|
113 |
+
},
|
114 |
+
{
|
115 |
+
"epoch": 0.23,
|
116 |
+
"eval_runtime": 1.1689,
|
117 |
+
"eval_samples_per_second": 855.472,
|
118 |
+
"eval_steps_per_second": 13.688,
|
119 |
+
"step": 15000
|
120 |
+
},
|
121 |
+
{
|
122 |
+
"epoch": 0.24,
|
123 |
+
"learning_rate": 4.7999999999999994e-05,
|
124 |
+
"loss": 0.6348,
|
125 |
+
"step": 16000
|
126 |
+
},
|
127 |
+
{
|
128 |
+
"epoch": 0.26,
|
129 |
+
"learning_rate": 5.1e-05,
|
130 |
+
"loss": 0.6295,
|
131 |
+
"step": 17000
|
132 |
+
},
|
133 |
+
{
|
134 |
+
"epoch": 0.27,
|
135 |
+
"learning_rate": 5.399999999999999e-05,
|
136 |
+
"loss": 0.6224,
|
137 |
+
"step": 18000
|
138 |
+
},
|
139 |
+
{
|
140 |
+
"epoch": 0.29,
|
141 |
+
"learning_rate": 5.6999999999999996e-05,
|
142 |
+
"loss": 0.6169,
|
143 |
+
"step": 19000
|
144 |
+
},
|
145 |
+
{
|
146 |
+
"epoch": 0.31,
|
147 |
+
"learning_rate": 5.9999999999999995e-05,
|
148 |
+
"loss": 0.6113,
|
149 |
+
"step": 20000
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 0.31,
|
153 |
+
"eval_runtime": 1.0179,
|
154 |
+
"eval_samples_per_second": 982.441,
|
155 |
+
"eval_steps_per_second": 15.719,
|
156 |
+
"step": 20000
|
157 |
}
|
158 |
],
|
159 |
"max_steps": 1000000,
|
160 |
"num_train_epochs": 16,
|
161 |
+
"total_flos": 1.402005220606943e+21,
|
162 |
"trial_name": null,
|
163 |
"trial_params": null
|
164 |
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 449471589
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d0d795304e92a242fb3daabda286fa8f94b1ee38faba8dda70081c35bf054d0f
|
3 |
size 449471589
|