Commit
•
82f663f
1
Parent(s):
ea43ae1
Training in progress, step 1000, checkpoint
Browse files
last-checkpoint/model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 577789320
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8ce54e79e12252bae59725175488c3040706f1f2b3d873b46e5f7b8b4f2a94b7
|
3 |
size 577789320
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1155772233
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:daa35d4afe619e77f5e075540ee2f825ce0dd6443ebafffcbfc84cbf09c27f5f
|
3 |
size 1155772233
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14244
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:eead311c135878827beadbd3c4b2cc7fba012f606f4bb99598cadd7e7cbf63b8
|
3 |
size 14244
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1064
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8210f8e2249c280ac4965b4cc059199e79e619c33beb58bb250012029c0aaadf
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
-
"best_metric": 0.
|
3 |
-
"best_model_checkpoint": "mikhail_panzo/ceb_b64_le4_s8000/checkpoint-
|
4 |
-
"epoch":
|
5 |
"eval_steps": 500,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -85,6 +85,84 @@
|
|
85 |
"eval_samples_per_second": 24.011,
|
86 |
"eval_steps_per_second": 3.068,
|
87 |
"step": 500
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
88 |
}
|
89 |
],
|
90 |
"logging_steps": 50,
|
@@ -104,7 +182,7 @@
|
|
104 |
"attributes": {}
|
105 |
}
|
106 |
},
|
107 |
-
"total_flos":
|
108 |
"train_batch_size": 16,
|
109 |
"trial_name": null,
|
110 |
"trial_params": null
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.39941468834877014,
|
3 |
+
"best_model_checkpoint": "mikhail_panzo/ceb_b64_le4_s8000/checkpoint-1000",
|
4 |
+
"epoch": 39.603960396039604,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 1000,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
85 |
"eval_samples_per_second": 24.011,
|
86 |
"eval_steps_per_second": 3.068,
|
87 |
"step": 500
|
88 |
+
},
|
89 |
+
{
|
90 |
+
"epoch": 21.782178217821784,
|
91 |
+
"grad_norm": 1.0462185144424438,
|
92 |
+
"learning_rate": 2.7450000000000003e-05,
|
93 |
+
"loss": 0.4465,
|
94 |
+
"step": 550
|
95 |
+
},
|
96 |
+
{
|
97 |
+
"epoch": 23.762376237623762,
|
98 |
+
"grad_norm": 1.103574275970459,
|
99 |
+
"learning_rate": 2.995e-05,
|
100 |
+
"loss": 0.4453,
|
101 |
+
"step": 600
|
102 |
+
},
|
103 |
+
{
|
104 |
+
"epoch": 25.742574257425744,
|
105 |
+
"grad_norm": 3.00575590133667,
|
106 |
+
"learning_rate": 3.245e-05,
|
107 |
+
"loss": 0.447,
|
108 |
+
"step": 650
|
109 |
+
},
|
110 |
+
{
|
111 |
+
"epoch": 27.722772277227723,
|
112 |
+
"grad_norm": 1.786911129951477,
|
113 |
+
"learning_rate": 3.495e-05,
|
114 |
+
"loss": 0.4351,
|
115 |
+
"step": 700
|
116 |
+
},
|
117 |
+
{
|
118 |
+
"epoch": 29.702970297029704,
|
119 |
+
"grad_norm": 1.236941933631897,
|
120 |
+
"learning_rate": 3.745e-05,
|
121 |
+
"loss": 0.4347,
|
122 |
+
"step": 750
|
123 |
+
},
|
124 |
+
{
|
125 |
+
"epoch": 31.683168316831683,
|
126 |
+
"grad_norm": 1.3743062019348145,
|
127 |
+
"learning_rate": 3.995e-05,
|
128 |
+
"loss": 0.4319,
|
129 |
+
"step": 800
|
130 |
+
},
|
131 |
+
{
|
132 |
+
"epoch": 33.663366336633665,
|
133 |
+
"grad_norm": 2.7615420818328857,
|
134 |
+
"learning_rate": 4.245e-05,
|
135 |
+
"loss": 0.4358,
|
136 |
+
"step": 850
|
137 |
+
},
|
138 |
+
{
|
139 |
+
"epoch": 35.64356435643565,
|
140 |
+
"grad_norm": 1.662369966506958,
|
141 |
+
"learning_rate": 4.495e-05,
|
142 |
+
"loss": 0.4276,
|
143 |
+
"step": 900
|
144 |
+
},
|
145 |
+
{
|
146 |
+
"epoch": 37.62376237623762,
|
147 |
+
"grad_norm": 1.0967382192611694,
|
148 |
+
"learning_rate": 4.745e-05,
|
149 |
+
"loss": 0.4267,
|
150 |
+
"step": 950
|
151 |
+
},
|
152 |
+
{
|
153 |
+
"epoch": 39.603960396039604,
|
154 |
+
"grad_norm": 2.530874252319336,
|
155 |
+
"learning_rate": 4.995e-05,
|
156 |
+
"loss": 0.4179,
|
157 |
+
"step": 1000
|
158 |
+
},
|
159 |
+
{
|
160 |
+
"epoch": 39.603960396039604,
|
161 |
+
"eval_loss": 0.39941468834877014,
|
162 |
+
"eval_runtime": 7.4617,
|
163 |
+
"eval_samples_per_second": 24.123,
|
164 |
+
"eval_steps_per_second": 3.082,
|
165 |
+
"step": 1000
|
166 |
}
|
167 |
],
|
168 |
"logging_steps": 50,
|
|
|
182 |
"attributes": {}
|
183 |
}
|
184 |
},
|
185 |
+
"total_flos": 1.0803690034289064e+16,
|
186 |
"train_batch_size": 16,
|
187 |
"trial_name": null,
|
188 |
"trial_params": null
|