Run 3. Outer Step 12. Inner Step 0.
Browse files- config.json +11 -16
- inner_optimizer.pt +2 -2
- model.safetensors +1 -1
config.json
CHANGED
@@ -154,13 +154,13 @@
|
|
154 |
"232": "NON_PARTICIPATING",
|
155 |
"233": "NON_PARTICIPATING",
|
156 |
"234": "NON_PARTICIPATING",
|
157 |
-
"235": "
|
158 |
"236": "NON_PARTICIPATING",
|
159 |
"237": "NON_PARTICIPATING",
|
160 |
"238": "NON_PARTICIPATING",
|
161 |
"239": "NON_PARTICIPATING",
|
162 |
"24": "NON_PARTICIPATING",
|
163 |
-
"240": "
|
164 |
"241": "NON_PARTICIPATING",
|
165 |
"242": "NON_PARTICIPATING",
|
166 |
"243": "NON_PARTICIPATING",
|
@@ -170,7 +170,7 @@
|
|
170 |
"247": "NON_PARTICIPATING",
|
171 |
"248": "NON_PARTICIPATING",
|
172 |
"249": "NON_PARTICIPATING",
|
173 |
-
"25": "
|
174 |
"250": "NON_PARTICIPATING",
|
175 |
"251": "NON_PARTICIPATING",
|
176 |
"252": "NON_PARTICIPATING",
|
@@ -212,7 +212,7 @@
|
|
212 |
"55": "NON_PARTICIPATING",
|
213 |
"56": "NON_PARTICIPATING",
|
214 |
"57": "NON_PARTICIPATING",
|
215 |
-
"58": "
|
216 |
"59": "NON_PARTICIPATING",
|
217 |
"6": "NON_PARTICIPATING",
|
218 |
"60": "NON_PARTICIPATING",
|
@@ -268,25 +268,20 @@
|
|
268 |
"AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
|
269 |
},
|
270 |
"block_list": [
|
271 |
-
|
272 |
-
|
273 |
-
|
274 |
-
|
275 |
-
|
276 |
-
5149443,
|
277 |
-
5149447,
|
278 |
-
5149451,
|
279 |
-
5149455,
|
280 |
-
5149459
|
281 |
],
|
282 |
"block_size": 1024,
|
283 |
"bos_token_id": 50256,
|
284 |
"embd_pdrop": 0.1,
|
285 |
"eos_token_id": 50256,
|
286 |
"initializer_range": 0.02,
|
287 |
-
"inner_step":
|
288 |
"inner_steps": 0,
|
289 |
-
"last_allreduce_block":
|
290 |
"layer_norm_epsilon": 1e-05,
|
291 |
"model_type": "gpt_optimized",
|
292 |
"n_embd": 1280,
|
|
|
154 |
"232": "NON_PARTICIPATING",
|
155 |
"233": "NON_PARTICIPATING",
|
156 |
"234": "NON_PARTICIPATING",
|
157 |
+
"235": "NON_PARTICIPATING",
|
158 |
"236": "NON_PARTICIPATING",
|
159 |
"237": "NON_PARTICIPATING",
|
160 |
"238": "NON_PARTICIPATING",
|
161 |
"239": "NON_PARTICIPATING",
|
162 |
"24": "NON_PARTICIPATING",
|
163 |
+
"240": "NON_PARTICIPATING",
|
164 |
"241": "NON_PARTICIPATING",
|
165 |
"242": "NON_PARTICIPATING",
|
166 |
"243": "NON_PARTICIPATING",
|
|
|
170 |
"247": "NON_PARTICIPATING",
|
171 |
"248": "NON_PARTICIPATING",
|
172 |
"249": "NON_PARTICIPATING",
|
173 |
+
"25": "NON_PARTICIPATING",
|
174 |
"250": "NON_PARTICIPATING",
|
175 |
"251": "NON_PARTICIPATING",
|
176 |
"252": "NON_PARTICIPATING",
|
|
|
212 |
"55": "NON_PARTICIPATING",
|
213 |
"56": "NON_PARTICIPATING",
|
214 |
"57": "NON_PARTICIPATING",
|
215 |
+
"58": "NON_PARTICIPATING",
|
216 |
"59": "NON_PARTICIPATING",
|
217 |
"6": "NON_PARTICIPATING",
|
218 |
"60": "NON_PARTICIPATING",
|
|
|
268 |
"AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
|
269 |
},
|
270 |
"block_list": [
|
271 |
+
5459667,
|
272 |
+
5459671,
|
273 |
+
5459676,
|
274 |
+
5459680,
|
275 |
+
5459684
|
|
|
|
|
|
|
|
|
|
|
276 |
],
|
277 |
"block_size": 1024,
|
278 |
"bos_token_id": 50256,
|
279 |
"embd_pdrop": 0.1,
|
280 |
"eos_token_id": 50256,
|
281 |
"initializer_range": 0.02,
|
282 |
+
"inner_step": 0,
|
283 |
"inner_steps": 0,
|
284 |
+
"last_allreduce_block": 5450451,
|
285 |
"layer_norm_epsilon": 1e-05,
|
286 |
"model_type": "gpt_optimized",
|
287 |
"n_embd": 1280,
|
inner_optimizer.pt
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 sha256:33e565b43e3a803cc0103fbe6dbdc5b644c1a180748c66e5e50343726a6184fb
|
3 |
+
size 8081782026
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4040701744
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:73efb0c1068249abe2eb6b6207f5e051b4312911446a9a1d544ec2cb71610cf7
|
3 |
size 4040701744
|