Commit
•
15b21db
1
Parent(s):
8c1a0a1
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:ff8cae616e41b6eeadfd895301ce06f02907c037312d6d128cbc6789ddc9b7f8
|
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:ec073b4caedc3cfb8350822a4965385a3c9d2c064db1caa88ca86be33b024ab7
|
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 sha256:45cef88be00665fc8a314476e14e0a14878c0d750e849e6b98a7e57eddf92a77
|
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 sha256:6080dc3c4f31046c753abd07ed5f1a8449e11695e9772af37e8337628bc01d7f
|
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_b128_le5_s4000/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": 28.171,
|
86 |
"eval_steps_per_second": 3.6,
|
87 |
"step": 500
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
88 |
}
|
89 |
],
|
90 |
"logging_steps": 50,
|
@@ -104,7 +182,7 @@
|
|
104 |
"attributes": {}
|
105 |
}
|
106 |
},
|
107 |
-
"total_flos":
|
108 |
"train_batch_size": 32,
|
109 |
"trial_name": null,
|
110 |
"trial_params": null
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.42202475666999817,
|
3 |
+
"best_model_checkpoint": "mikhail-panzo/ceb_b128_le5_s4000/checkpoint-1000",
|
4 |
+
"epoch": 78.43137254901961,
|
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": 28.171,
|
86 |
"eval_steps_per_second": 3.6,
|
87 |
"step": 500
|
88 |
+
},
|
89 |
+
{
|
90 |
+
"epoch": 43.13725490196079,
|
91 |
+
"grad_norm": 0.8968011736869812,
|
92 |
+
"learning_rate": 2.7450000000000004e-06,
|
93 |
+
"loss": 0.5121,
|
94 |
+
"step": 550
|
95 |
+
},
|
96 |
+
{
|
97 |
+
"epoch": 47.05882352941177,
|
98 |
+
"grad_norm": 1.1953343152999878,
|
99 |
+
"learning_rate": 2.995e-06,
|
100 |
+
"loss": 0.5047,
|
101 |
+
"step": 600
|
102 |
+
},
|
103 |
+
{
|
104 |
+
"epoch": 50.98039215686274,
|
105 |
+
"grad_norm": 0.8916338682174683,
|
106 |
+
"learning_rate": 3.2450000000000003e-06,
|
107 |
+
"loss": 0.5013,
|
108 |
+
"step": 650
|
109 |
+
},
|
110 |
+
{
|
111 |
+
"epoch": 54.90196078431372,
|
112 |
+
"grad_norm": 1.166737675666809,
|
113 |
+
"learning_rate": 3.495e-06,
|
114 |
+
"loss": 0.4847,
|
115 |
+
"step": 700
|
116 |
+
},
|
117 |
+
{
|
118 |
+
"epoch": 58.8235294117647,
|
119 |
+
"grad_norm": 0.9191999435424805,
|
120 |
+
"learning_rate": 3.745e-06,
|
121 |
+
"loss": 0.4849,
|
122 |
+
"step": 750
|
123 |
+
},
|
124 |
+
{
|
125 |
+
"epoch": 62.745098039215684,
|
126 |
+
"grad_norm": 1.0393210649490356,
|
127 |
+
"learning_rate": 3.995000000000001e-06,
|
128 |
+
"loss": 0.4827,
|
129 |
+
"step": 800
|
130 |
+
},
|
131 |
+
{
|
132 |
+
"epoch": 66.66666666666667,
|
133 |
+
"grad_norm": 0.764959454536438,
|
134 |
+
"learning_rate": 4.245e-06,
|
135 |
+
"loss": 0.483,
|
136 |
+
"step": 850
|
137 |
+
},
|
138 |
+
{
|
139 |
+
"epoch": 70.58823529411765,
|
140 |
+
"grad_norm": 1.0713616609573364,
|
141 |
+
"learning_rate": 4.495e-06,
|
142 |
+
"loss": 0.4762,
|
143 |
+
"step": 900
|
144 |
+
},
|
145 |
+
{
|
146 |
+
"epoch": 74.50980392156863,
|
147 |
+
"grad_norm": 0.8433477282524109,
|
148 |
+
"learning_rate": 4.745e-06,
|
149 |
+
"loss": 0.4702,
|
150 |
+
"step": 950
|
151 |
+
},
|
152 |
+
{
|
153 |
+
"epoch": 78.43137254901961,
|
154 |
+
"grad_norm": 0.6966288685798645,
|
155 |
+
"learning_rate": 4.9950000000000005e-06,
|
156 |
+
"loss": 0.4634,
|
157 |
+
"step": 1000
|
158 |
+
},
|
159 |
+
{
|
160 |
+
"epoch": 78.43137254901961,
|
161 |
+
"eval_loss": 0.42202475666999817,
|
162 |
+
"eval_runtime": 6.3604,
|
163 |
+
"eval_samples_per_second": 28.3,
|
164 |
+
"eval_steps_per_second": 3.616,
|
165 |
+
"step": 1000
|
166 |
}
|
167 |
],
|
168 |
"logging_steps": 50,
|
|
|
182 |
"attributes": {}
|
183 |
}
|
184 |
},
|
185 |
+
"total_flos": 2.176673010094044e+16,
|
186 |
"train_batch_size": 32,
|
187 |
"trial_name": null,
|
188 |
"trial_params": null
|