Training in progress, epoch 2, checkpoint
Browse files- last-checkpoint/README.md +0 -1
- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/rng_state.pth +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +100 -3
last-checkpoint/README.md
CHANGED
@@ -5,6 +5,5 @@ library_name: peft
|
|
5 |
|
6 |
### Framework versions
|
7 |
|
8 |
-
- PEFT 0.5.0
|
9 |
|
10 |
- PEFT 0.5.0
|
|
|
5 |
|
6 |
### Framework versions
|
7 |
|
|
|
8 |
|
9 |
- PEFT 0.5.0
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1256
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:538342ac688fb0a0d86aaedd7330737ae00e80eb8e093f459c58ce63d811fc33
|
3 |
size 1256
|
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 sha256:2ba8427ac6eea57ec5734699585fe0dd282eb1503ee998fdc4232e54bb7d6354
|
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 sha256:0bc60bce785072809819f1c1fc75a413381f48d7fd0b438c4400860ca72a7129
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": 2.2744693756103516,
|
3 |
"best_model_checkpoint": "dq158/pingusPongus/checkpoint-6323",
|
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,
|
@@ -98,13 +98,110 @@
|
|
98 |
"eval_steps_per_second": 0.895,
|
99 |
"eval_translation_length": 1439232,
|
100 |
"step": 6323
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
101 |
}
|
102 |
],
|
103 |
"logging_steps": 500,
|
104 |
"max_steps": 18969,
|
105 |
"num_train_epochs": 3,
|
106 |
"save_steps": 500,
|
107 |
-
"total_flos":
|
108 |
"trial_name": null,
|
109 |
"trial_params": null
|
110 |
}
|
|
|
1 |
{
|
2 |
"best_metric": 2.2744693756103516,
|
3 |
"best_model_checkpoint": "dq158/pingusPongus/checkpoint-6323",
|
4 |
+
"epoch": 2.0,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 12646,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
98 |
"eval_steps_per_second": 0.895,
|
99 |
"eval_translation_length": 1439232,
|
100 |
"step": 6323
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 1.03,
|
104 |
+
"learning_rate": 6.678034646037393e-05,
|
105 |
+
"loss": 2.3216,
|
106 |
+
"step": 6500
|
107 |
+
},
|
108 |
+
{
|
109 |
+
"epoch": 1.11,
|
110 |
+
"learning_rate": 6.343059707231406e-05,
|
111 |
+
"loss": 2.3675,
|
112 |
+
"step": 7000
|
113 |
+
},
|
114 |
+
{
|
115 |
+
"epoch": 1.19,
|
116 |
+
"learning_rate": 5.995319481960425e-05,
|
117 |
+
"loss": 2.3563,
|
118 |
+
"step": 7500
|
119 |
+
},
|
120 |
+
{
|
121 |
+
"epoch": 1.27,
|
122 |
+
"learning_rate": 5.6372224671242366e-05,
|
123 |
+
"loss": 2.4016,
|
124 |
+
"step": 8000
|
125 |
+
},
|
126 |
+
{
|
127 |
+
"epoch": 1.34,
|
128 |
+
"learning_rate": 5.2712488921797064e-05,
|
129 |
+
"loss": 2.3769,
|
130 |
+
"step": 8500
|
131 |
+
},
|
132 |
+
{
|
133 |
+
"epoch": 1.42,
|
134 |
+
"learning_rate": 4.899933540728503e-05,
|
135 |
+
"loss": 2.3531,
|
136 |
+
"step": 9000
|
137 |
+
},
|
138 |
+
{
|
139 |
+
"epoch": 1.5,
|
140 |
+
"learning_rate": 4.5258481942552583e-05,
|
141 |
+
"loss": 2.3503,
|
142 |
+
"step": 9500
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 1.58,
|
146 |
+
"learning_rate": 4.151583819613269e-05,
|
147 |
+
"loss": 2.3508,
|
148 |
+
"step": 10000
|
149 |
+
},
|
150 |
+
{
|
151 |
+
"epoch": 1.66,
|
152 |
+
"learning_rate": 3.779732623629695e-05,
|
153 |
+
"loss": 2.3509,
|
154 |
+
"step": 10500
|
155 |
+
},
|
156 |
+
{
|
157 |
+
"epoch": 1.74,
|
158 |
+
"learning_rate": 3.412870099122515e-05,
|
159 |
+
"loss": 2.3825,
|
160 |
+
"step": 11000
|
161 |
+
},
|
162 |
+
{
|
163 |
+
"epoch": 1.82,
|
164 |
+
"learning_rate": 3.0535371866810265e-05,
|
165 |
+
"loss": 2.3884,
|
166 |
+
"step": 11500
|
167 |
+
},
|
168 |
+
{
|
169 |
+
"epoch": 1.9,
|
170 |
+
"learning_rate": 2.704222675759866e-05,
|
171 |
+
"loss": 2.3531,
|
172 |
+
"step": 12000
|
173 |
+
},
|
174 |
+
{
|
175 |
+
"epoch": 1.98,
|
176 |
+
"learning_rate": 2.367345966978985e-05,
|
177 |
+
"loss": 2.3813,
|
178 |
+
"step": 12500
|
179 |
+
},
|
180 |
+
{
|
181 |
+
"epoch": 2.0,
|
182 |
+
"eval_bleu": 1.0,
|
183 |
+
"eval_brevity_penalty": 1.0,
|
184 |
+
"eval_length_ratio": 1.0,
|
185 |
+
"eval_loss": 2.2744693756103516,
|
186 |
+
"eval_precisions": [
|
187 |
+
1.0,
|
188 |
+
1.0,
|
189 |
+
1.0,
|
190 |
+
1.0
|
191 |
+
],
|
192 |
+
"eval_reference_length": 1439232,
|
193 |
+
"eval_runtime": 1567.8247,
|
194 |
+
"eval_samples_per_second": 1.793,
|
195 |
+
"eval_steps_per_second": 0.897,
|
196 |
+
"eval_translation_length": 1439232,
|
197 |
+
"step": 12646
|
198 |
}
|
199 |
],
|
200 |
"logging_steps": 500,
|
201 |
"max_steps": 18969,
|
202 |
"num_train_epochs": 3,
|
203 |
"save_steps": 500,
|
204 |
+
"total_flos": 4.3332645393373594e+17,
|
205 |
"trial_name": null,
|
206 |
"trial_params": null
|
207 |
}
|