Commit
β’
70719e2
1
Parent(s):
6fe8b34
Training in progress, step 800
Browse files- checkpoint-400/latest +0 -1
- {checkpoint-400 β checkpoint-800}/config.json +0 -0
- {checkpoint-400 β checkpoint-800}/generation_config.json +0 -0
- {checkpoint-400/global_step400 β checkpoint-800/global_step800}/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +1 -1
- {checkpoint-400/global_step400 β checkpoint-800/global_step800}/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +1 -1
- {checkpoint-400/global_step400 β checkpoint-800/global_step800}/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +1 -1
- {checkpoint-400/global_step400 β checkpoint-800/global_step800}/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +1 -1
- {checkpoint-400/global_step400 β checkpoint-800/global_step800}/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt +1 -1
- {checkpoint-400/global_step400 β checkpoint-800/global_step800}/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt +1 -1
- {checkpoint-400/global_step400 β checkpoint-800/global_step800}/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt +1 -1
- {checkpoint-400/global_step400 β checkpoint-800/global_step800}/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt +1 -1
- {checkpoint-400/global_step400 β checkpoint-800/global_step800}/zero_pp_rank_0_mp_rank_00_model_states.pt +1 -1
- {checkpoint-400/global_step400 β checkpoint-800/global_step800}/zero_pp_rank_1_mp_rank_00_model_states.pt +1 -1
- {checkpoint-400/global_step400 β checkpoint-800/global_step800}/zero_pp_rank_2_mp_rank_00_model_states.pt +1 -1
- {checkpoint-400/global_step400 β checkpoint-800/global_step800}/zero_pp_rank_3_mp_rank_00_model_states.pt +1 -1
- {checkpoint-400/global_step400 β checkpoint-800/global_step800}/zero_pp_rank_4_mp_rank_00_model_states.pt +1 -1
- {checkpoint-400/global_step400 β checkpoint-800/global_step800}/zero_pp_rank_5_mp_rank_00_model_states.pt +1 -1
- {checkpoint-400/global_step400 β checkpoint-800/global_step800}/zero_pp_rank_6_mp_rank_00_model_states.pt +1 -1
- {checkpoint-400/global_step400 β checkpoint-800/global_step800}/zero_pp_rank_7_mp_rank_00_model_states.pt +1 -1
- checkpoint-800/latest +1 -0
- {checkpoint-400 β checkpoint-800}/model-00001-of-00002.safetensors +1 -1
- {checkpoint-400 β checkpoint-800}/model-00002-of-00002.safetensors +1 -1
- {checkpoint-400 β checkpoint-800}/model.safetensors.index.json +0 -0
- {checkpoint-400 β checkpoint-800}/rng_state_0.pth +0 -0
- {checkpoint-400 β checkpoint-800}/rng_state_1.pth +0 -0
- {checkpoint-400 β checkpoint-800}/rng_state_2.pth +0 -0
- {checkpoint-400 β checkpoint-800}/rng_state_3.pth +0 -0
- {checkpoint-400 β checkpoint-800}/rng_state_4.pth +0 -0
- {checkpoint-400 β checkpoint-800}/rng_state_5.pth +0 -0
- {checkpoint-400 β checkpoint-800}/rng_state_6.pth +0 -0
- {checkpoint-400 β checkpoint-800}/rng_state_7.pth +0 -0
- {checkpoint-400 β checkpoint-800}/special_tokens_map.json +0 -0
- {checkpoint-400 β checkpoint-800}/tokenizer.json +0 -0
- {checkpoint-400 β checkpoint-800}/tokenizer.model +0 -0
- {checkpoint-400 β checkpoint-800}/tokenizer_config.json +0 -0
- {checkpoint-400 β checkpoint-800}/trainer_state.json +243 -3
- {checkpoint-400 β checkpoint-800}/training_args.bin +0 -0
- {checkpoint-400 β checkpoint-800}/zero_to_fp32.py +0 -0
- runs/Aug22_18-42-03_ip-26-0-150-12/events.out.tfevents.1692729850.ip-26-0-150-12.2895584.0 +2 -2
checkpoint-400/latest
DELETED
@@ -1 +0,0 @@
|
|
1 |
-
global_step400
|
|
|
|
{checkpoint-400 β checkpoint-800}/config.json
RENAMED
File without changes
|
{checkpoint-400 β checkpoint-800}/generation_config.json
RENAMED
File without changes
|
{checkpoint-400/global_step400 β checkpoint-800/global_step800}/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt
RENAMED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 10107626487
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0233dc4a8194f3bef960787af2ec91f0e31a083f8d374af882f6450af5e55451
|
3 |
size 10107626487
|
{checkpoint-400/global_step400 β checkpoint-800/global_step800}/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt
RENAMED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 10107626487
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:381c023978239b23cc247f99fe963167a8628446b44e933551317dfe31264784
|
3 |
size 10107626487
|
{checkpoint-400/global_step400 β checkpoint-800/global_step800}/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt
RENAMED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 10107626487
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:768eeaca4fb869b895451ff1734b628eb698e54a8670ec4887523af22d518950
|
3 |
size 10107626487
|
{checkpoint-400/global_step400 β checkpoint-800/global_step800}/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt
RENAMED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 10107626487
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d0935cff42c9223a77c2953c7ff69a5cccd7b8230277cec7f703f5025371df9f
|
3 |
size 10107626487
|
{checkpoint-400/global_step400 β checkpoint-800/global_step800}/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt
RENAMED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 10107626487
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d119d36fcfb5bdf735763ac754c7164bf5861667ed232ff2ee1f521df9cf46ce
|
3 |
size 10107626487
|
{checkpoint-400/global_step400 β checkpoint-800/global_step800}/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt
RENAMED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 10107626487
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:72ba38f38dc3469211188737f44ee539df6f0d2f1113e8c9808bd498a97ba56e
|
3 |
size 10107626487
|
{checkpoint-400/global_step400 β checkpoint-800/global_step800}/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt
RENAMED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 10107626487
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bc9ad0aa2d656102bbfe892890bc18b332901104947c2e8a0cc11e68d656bb54
|
3 |
size 10107626487
|
{checkpoint-400/global_step400 β checkpoint-800/global_step800}/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt
RENAMED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 10107626487
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2ac9f429f41b6690c59415bdc4643bc040c204301bf6d9dc7f032d741bf2975f
|
3 |
size 10107626487
|
{checkpoint-400/global_step400 β checkpoint-800/global_step800}/zero_pp_rank_0_mp_rank_00_model_states.pt
RENAMED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 168086
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:233d3f4e42ae90fa4994c8c0b577e9fb31018d32bc58244df6cd4e57a5bc314a
|
3 |
size 168086
|
{checkpoint-400/global_step400 β checkpoint-800/global_step800}/zero_pp_rank_1_mp_rank_00_model_states.pt
RENAMED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 168086
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f8e6e08c9fbe96968cef4593a608fa7f32d2a76db208b81ed1cd4a8b64b512d6
|
3 |
size 168086
|
{checkpoint-400/global_step400 β checkpoint-800/global_step800}/zero_pp_rank_2_mp_rank_00_model_states.pt
RENAMED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 168086
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:70f0a38b369c454c21cacfd4775ffd52d06a950af9007bb13eb599fb154fbd16
|
3 |
size 168086
|
{checkpoint-400/global_step400 β checkpoint-800/global_step800}/zero_pp_rank_3_mp_rank_00_model_states.pt
RENAMED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 168086
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:220292ca12becbd9ff5ee9e1cf8127dad0790ad867f8a9dc4b70a41a9328df3a
|
3 |
size 168086
|
{checkpoint-400/global_step400 β checkpoint-800/global_step800}/zero_pp_rank_4_mp_rank_00_model_states.pt
RENAMED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 168086
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5522cef3c853ba1a9d7d551d07427d3538f3363e964bd8c9926b829a7452f4f1
|
3 |
size 168086
|
{checkpoint-400/global_step400 β checkpoint-800/global_step800}/zero_pp_rank_5_mp_rank_00_model_states.pt
RENAMED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 168086
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4448f725283b27cf989c1c0dfd6702b9f83e6c23f68ce76d3e4ddf4b8760f6fa
|
3 |
size 168086
|
{checkpoint-400/global_step400 β checkpoint-800/global_step800}/zero_pp_rank_6_mp_rank_00_model_states.pt
RENAMED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 168086
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:84704b403c899d7143fd8224463da6540f81844bef520713bfccadc09e163505
|
3 |
size 168086
|
{checkpoint-400/global_step400 β checkpoint-800/global_step800}/zero_pp_rank_7_mp_rank_00_model_states.pt
RENAMED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 168086
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:713fcf20cfef9dfef3231bc5a8c499e8e943d47163a4393d8f733c8c8b664ad7
|
3 |
size 168086
|
checkpoint-800/latest
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
global_step800
|
{checkpoint-400 β checkpoint-800}/model-00001-of-00002.safetensors
RENAMED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 9976576392
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:072428d75e810d41d1cc6413f6e08761a39f896b97abd7cd47a986b9d58c1823
|
3 |
size 9976576392
|
{checkpoint-400 β checkpoint-800}/model-00002-of-00002.safetensors
RENAMED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 3500296504
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:33524383bb67b7cd8c24780afd4c26119fa1b45d6e6c9d7fa921ff3a85b3a78d
|
3 |
size 3500296504
|
{checkpoint-400 β checkpoint-800}/model.safetensors.index.json
RENAMED
File without changes
|
{checkpoint-400 β checkpoint-800}/rng_state_0.pth
RENAMED
File without changes
|
{checkpoint-400 β checkpoint-800}/rng_state_1.pth
RENAMED
File without changes
|
{checkpoint-400 β checkpoint-800}/rng_state_2.pth
RENAMED
File without changes
|
{checkpoint-400 β checkpoint-800}/rng_state_3.pth
RENAMED
File without changes
|
{checkpoint-400 β checkpoint-800}/rng_state_4.pth
RENAMED
File without changes
|
{checkpoint-400 β checkpoint-800}/rng_state_5.pth
RENAMED
File without changes
|
{checkpoint-400 β checkpoint-800}/rng_state_6.pth
RENAMED
File without changes
|
{checkpoint-400 β checkpoint-800}/rng_state_7.pth
RENAMED
File without changes
|
{checkpoint-400 β checkpoint-800}/special_tokens_map.json
RENAMED
File without changes
|
{checkpoint-400 β checkpoint-800}/tokenizer.json
RENAMED
File without changes
|
{checkpoint-400 β checkpoint-800}/tokenizer.model
RENAMED
File without changes
|
{checkpoint-400 β checkpoint-800}/tokenizer_config.json
RENAMED
File without changes
|
{checkpoint-400 β checkpoint-800}/trainer_state.json
RENAMED
@@ -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,
|
@@ -246,11 +246,251 @@
|
|
246 |
"learning_rate": 0.0003,
|
247 |
"loss": 4.4799,
|
248 |
"step": 400
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
249 |
}
|
250 |
],
|
251 |
"max_steps": 3000,
|
252 |
"num_train_epochs": 9223372036854775807,
|
253 |
-
"total_flos":
|
254 |
"trial_name": null,
|
255 |
"trial_params": null
|
256 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.26666666666666666,
|
5 |
+
"global_step": 800,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
246 |
"learning_rate": 0.0003,
|
247 |
"loss": 4.4799,
|
248 |
"step": 400
|
249 |
+
},
|
250 |
+
{
|
251 |
+
"epoch": 0.14,
|
252 |
+
"learning_rate": 0.0003,
|
253 |
+
"loss": 4.3733,
|
254 |
+
"step": 410
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 0.14,
|
258 |
+
"learning_rate": 0.0003,
|
259 |
+
"loss": 4.1788,
|
260 |
+
"step": 420
|
261 |
+
},
|
262 |
+
{
|
263 |
+
"epoch": 0.14,
|
264 |
+
"learning_rate": 0.0003,
|
265 |
+
"loss": 3.6706,
|
266 |
+
"step": 430
|
267 |
+
},
|
268 |
+
{
|
269 |
+
"epoch": 0.15,
|
270 |
+
"learning_rate": 0.0003,
|
271 |
+
"loss": 2.8767,
|
272 |
+
"step": 440
|
273 |
+
},
|
274 |
+
{
|
275 |
+
"epoch": 0.15,
|
276 |
+
"learning_rate": 0.0003,
|
277 |
+
"loss": 2.3927,
|
278 |
+
"step": 450
|
279 |
+
},
|
280 |
+
{
|
281 |
+
"epoch": 0.15,
|
282 |
+
"learning_rate": 0.0003,
|
283 |
+
"loss": 2.3062,
|
284 |
+
"step": 460
|
285 |
+
},
|
286 |
+
{
|
287 |
+
"epoch": 0.16,
|
288 |
+
"learning_rate": 0.0003,
|
289 |
+
"loss": 2.2299,
|
290 |
+
"step": 470
|
291 |
+
},
|
292 |
+
{
|
293 |
+
"epoch": 0.16,
|
294 |
+
"learning_rate": 0.0003,
|
295 |
+
"loss": 2.1739,
|
296 |
+
"step": 480
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 0.16,
|
300 |
+
"learning_rate": 0.0003,
|
301 |
+
"loss": 2.1303,
|
302 |
+
"step": 490
|
303 |
+
},
|
304 |
+
{
|
305 |
+
"epoch": 0.17,
|
306 |
+
"learning_rate": 0.0003,
|
307 |
+
"loss": 2.1092,
|
308 |
+
"step": 500
|
309 |
+
},
|
310 |
+
{
|
311 |
+
"epoch": 0.17,
|
312 |
+
"learning_rate": 0.0003,
|
313 |
+
"loss": 2.0715,
|
314 |
+
"step": 510
|
315 |
+
},
|
316 |
+
{
|
317 |
+
"epoch": 0.17,
|
318 |
+
"learning_rate": 0.0003,
|
319 |
+
"loss": 2.0473,
|
320 |
+
"step": 520
|
321 |
+
},
|
322 |
+
{
|
323 |
+
"epoch": 0.18,
|
324 |
+
"learning_rate": 0.0003,
|
325 |
+
"loss": 2.0566,
|
326 |
+
"step": 530
|
327 |
+
},
|
328 |
+
{
|
329 |
+
"epoch": 0.18,
|
330 |
+
"learning_rate": 0.0003,
|
331 |
+
"loss": 1.9818,
|
332 |
+
"step": 540
|
333 |
+
},
|
334 |
+
{
|
335 |
+
"epoch": 0.18,
|
336 |
+
"learning_rate": 0.0003,
|
337 |
+
"loss": 1.9592,
|
338 |
+
"step": 550
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 0.19,
|
342 |
+
"learning_rate": 0.0003,
|
343 |
+
"loss": 1.8939,
|
344 |
+
"step": 560
|
345 |
+
},
|
346 |
+
{
|
347 |
+
"epoch": 0.19,
|
348 |
+
"learning_rate": 0.0003,
|
349 |
+
"loss": 1.8441,
|
350 |
+
"step": 570
|
351 |
+
},
|
352 |
+
{
|
353 |
+
"epoch": 0.19,
|
354 |
+
"learning_rate": 0.0003,
|
355 |
+
"loss": 1.808,
|
356 |
+
"step": 580
|
357 |
+
},
|
358 |
+
{
|
359 |
+
"epoch": 0.2,
|
360 |
+
"learning_rate": 0.0003,
|
361 |
+
"loss": 1.765,
|
362 |
+
"step": 590
|
363 |
+
},
|
364 |
+
{
|
365 |
+
"epoch": 0.2,
|
366 |
+
"learning_rate": 0.0003,
|
367 |
+
"loss": 1.706,
|
368 |
+
"step": 600
|
369 |
+
},
|
370 |
+
{
|
371 |
+
"epoch": 0.2,
|
372 |
+
"learning_rate": 0.0003,
|
373 |
+
"loss": 1.6328,
|
374 |
+
"step": 610
|
375 |
+
},
|
376 |
+
{
|
377 |
+
"epoch": 0.21,
|
378 |
+
"learning_rate": 0.0003,
|
379 |
+
"loss": 1.6197,
|
380 |
+
"step": 620
|
381 |
+
},
|
382 |
+
{
|
383 |
+
"epoch": 0.21,
|
384 |
+
"learning_rate": 0.0003,
|
385 |
+
"loss": 1.6106,
|
386 |
+
"step": 630
|
387 |
+
},
|
388 |
+
{
|
389 |
+
"epoch": 0.21,
|
390 |
+
"learning_rate": 0.0003,
|
391 |
+
"loss": 1.5649,
|
392 |
+
"step": 640
|
393 |
+
},
|
394 |
+
{
|
395 |
+
"epoch": 0.22,
|
396 |
+
"learning_rate": 0.0003,
|
397 |
+
"loss": 1.5001,
|
398 |
+
"step": 650
|
399 |
+
},
|
400 |
+
{
|
401 |
+
"epoch": 0.22,
|
402 |
+
"learning_rate": 0.0003,
|
403 |
+
"loss": 1.4926,
|
404 |
+
"step": 660
|
405 |
+
},
|
406 |
+
{
|
407 |
+
"epoch": 0.22,
|
408 |
+
"learning_rate": 0.0003,
|
409 |
+
"loss": 1.4682,
|
410 |
+
"step": 670
|
411 |
+
},
|
412 |
+
{
|
413 |
+
"epoch": 0.23,
|
414 |
+
"learning_rate": 0.0003,
|
415 |
+
"loss": 1.442,
|
416 |
+
"step": 680
|
417 |
+
},
|
418 |
+
{
|
419 |
+
"epoch": 0.23,
|
420 |
+
"learning_rate": 0.0003,
|
421 |
+
"loss": 1.4117,
|
422 |
+
"step": 690
|
423 |
+
},
|
424 |
+
{
|
425 |
+
"epoch": 0.23,
|
426 |
+
"learning_rate": 0.0003,
|
427 |
+
"loss": 1.379,
|
428 |
+
"step": 700
|
429 |
+
},
|
430 |
+
{
|
431 |
+
"epoch": 0.24,
|
432 |
+
"learning_rate": 0.0003,
|
433 |
+
"loss": 1.3609,
|
434 |
+
"step": 710
|
435 |
+
},
|
436 |
+
{
|
437 |
+
"epoch": 0.24,
|
438 |
+
"learning_rate": 0.0003,
|
439 |
+
"loss": 1.3224,
|
440 |
+
"step": 720
|
441 |
+
},
|
442 |
+
{
|
443 |
+
"epoch": 0.24,
|
444 |
+
"learning_rate": 0.0003,
|
445 |
+
"loss": 1.2853,
|
446 |
+
"step": 730
|
447 |
+
},
|
448 |
+
{
|
449 |
+
"epoch": 0.25,
|
450 |
+
"learning_rate": 0.0003,
|
451 |
+
"loss": 1.2762,
|
452 |
+
"step": 740
|
453 |
+
},
|
454 |
+
{
|
455 |
+
"epoch": 0.25,
|
456 |
+
"learning_rate": 0.0003,
|
457 |
+
"loss": 1.2265,
|
458 |
+
"step": 750
|
459 |
+
},
|
460 |
+
{
|
461 |
+
"epoch": 0.25,
|
462 |
+
"learning_rate": 0.0003,
|
463 |
+
"loss": 1.2232,
|
464 |
+
"step": 760
|
465 |
+
},
|
466 |
+
{
|
467 |
+
"epoch": 0.26,
|
468 |
+
"learning_rate": 0.0003,
|
469 |
+
"loss": 1.2075,
|
470 |
+
"step": 770
|
471 |
+
},
|
472 |
+
{
|
473 |
+
"epoch": 0.26,
|
474 |
+
"learning_rate": 0.0003,
|
475 |
+
"loss": 1.168,
|
476 |
+
"step": 780
|
477 |
+
},
|
478 |
+
{
|
479 |
+
"epoch": 0.26,
|
480 |
+
"learning_rate": 0.0003,
|
481 |
+
"loss": 1.1472,
|
482 |
+
"step": 790
|
483 |
+
},
|
484 |
+
{
|
485 |
+
"epoch": 0.27,
|
486 |
+
"learning_rate": 0.0003,
|
487 |
+
"loss": 1.118,
|
488 |
+
"step": 800
|
489 |
}
|
490 |
],
|
491 |
"max_steps": 3000,
|
492 |
"num_train_epochs": 9223372036854775807,
|
493 |
+
"total_flos": 335007449088000.0,
|
494 |
"trial_name": null,
|
495 |
"trial_params": null
|
496 |
}
|
{checkpoint-400 β checkpoint-800}/training_args.bin
RENAMED
File without changes
|
{checkpoint-400 β checkpoint-800}/zero_to_fp32.py
RENAMED
File without changes
|
runs/Aug22_18-42-03_ip-26-0-150-12/events.out.tfevents.1692729850.ip-26-0-150-12.2895584.0
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:b518fc726384856248944d1be48f0582a8e8298752371b3b3f5437577456a8b7
|
3 |
+
size 16711
|