Commit
β’
0c60668
1
Parent(s):
a2a6b42
Training in progress, step 1200
Browse files- {checkpoint-800 β checkpoint-1200}/config.json +0 -0
- {checkpoint-800 β checkpoint-1200}/generation_config.json +0 -0
- {checkpoint-800/global_step800 β checkpoint-1200/global_step1200}/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +1 -1
- {checkpoint-800/global_step800 β checkpoint-1200/global_step1200}/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +1 -1
- {checkpoint-800/global_step800 β checkpoint-1200/global_step1200}/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +1 -1
- {checkpoint-800/global_step800 β checkpoint-1200/global_step1200}/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +1 -1
- {checkpoint-800/global_step800 β checkpoint-1200/global_step1200}/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt +1 -1
- {checkpoint-800/global_step800 β checkpoint-1200/global_step1200}/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt +1 -1
- {checkpoint-800/global_step800 β checkpoint-1200/global_step1200}/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt +1 -1
- {checkpoint-800/global_step800 β checkpoint-1200/global_step1200}/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt +1 -1
- {checkpoint-800/global_step800 β checkpoint-1200/global_step1200}/zero_pp_rank_0_mp_rank_00_model_states.pt +1 -1
- {checkpoint-800/global_step800 β checkpoint-1200/global_step1200}/zero_pp_rank_1_mp_rank_00_model_states.pt +1 -1
- {checkpoint-800/global_step800 β checkpoint-1200/global_step1200}/zero_pp_rank_2_mp_rank_00_model_states.pt +1 -1
- {checkpoint-800/global_step800 β checkpoint-1200/global_step1200}/zero_pp_rank_3_mp_rank_00_model_states.pt +1 -1
- {checkpoint-800/global_step800 β checkpoint-1200/global_step1200}/zero_pp_rank_4_mp_rank_00_model_states.pt +1 -1
- {checkpoint-800/global_step800 β checkpoint-1200/global_step1200}/zero_pp_rank_5_mp_rank_00_model_states.pt +1 -1
- {checkpoint-800/global_step800 β checkpoint-1200/global_step1200}/zero_pp_rank_6_mp_rank_00_model_states.pt +1 -1
- {checkpoint-800/global_step800 β checkpoint-1200/global_step1200}/zero_pp_rank_7_mp_rank_00_model_states.pt +1 -1
- checkpoint-1200/latest +1 -0
- {checkpoint-800 β checkpoint-1200}/model-00001-of-00002.safetensors +1 -1
- {checkpoint-800 β checkpoint-1200}/model-00002-of-00002.safetensors +1 -1
- {checkpoint-800 β checkpoint-1200}/model.safetensors.index.json +0 -0
- {checkpoint-800 β checkpoint-1200}/rng_state_0.pth +0 -0
- {checkpoint-800 β checkpoint-1200}/rng_state_1.pth +0 -0
- {checkpoint-800 β checkpoint-1200}/rng_state_2.pth +0 -0
- {checkpoint-800 β checkpoint-1200}/rng_state_3.pth +0 -0
- {checkpoint-800 β checkpoint-1200}/rng_state_4.pth +0 -0
- {checkpoint-800 β checkpoint-1200}/rng_state_5.pth +0 -0
- {checkpoint-800 β checkpoint-1200}/rng_state_6.pth +0 -0
- {checkpoint-800 β checkpoint-1200}/rng_state_7.pth +0 -0
- {checkpoint-800 β checkpoint-1200}/special_tokens_map.json +0 -0
- {checkpoint-800 β checkpoint-1200}/tokenizer.json +0 -0
- {checkpoint-800 β checkpoint-1200}/tokenizer.model +0 -0
- {checkpoint-800 β checkpoint-1200}/tokenizer_config.json +0 -0
- {checkpoint-800 β checkpoint-1200}/trainer_state.json +243 -3
- {checkpoint-800 β checkpoint-1200}/training_args.bin +0 -0
- {checkpoint-800 β checkpoint-1200}/zero_to_fp32.py +0 -0
- checkpoint-800/latest +0 -1
- runs/Aug22_18-42-03_ip-26-0-150-12/events.out.tfevents.1692729850.ip-26-0-150-12.2895584.0 +2 -2
{checkpoint-800 β checkpoint-1200}/config.json
RENAMED
File without changes
|
{checkpoint-800 β checkpoint-1200}/generation_config.json
RENAMED
File without changes
|
{checkpoint-800/global_step800 β checkpoint-1200/global_step1200}/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 sha256:4fb262812656b3c83b6881b1dd67c5767d8042011235ae6468454646240b5c07
|
3 |
size 10107626487
|
{checkpoint-800/global_step800 β checkpoint-1200/global_step1200}/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 sha256:7df89141b87c7b3401cf3dc6d0f0e35b07ee4007b03d264482fa67df22e6e386
|
3 |
size 10107626487
|
{checkpoint-800/global_step800 β checkpoint-1200/global_step1200}/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 sha256:304104b8210689a208414ce338a1a8170d07fd50ede690c06cc17f711af7d23b
|
3 |
size 10107626487
|
{checkpoint-800/global_step800 β checkpoint-1200/global_step1200}/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 sha256:11e7a70ad03df41c4584486b35cde5c60d0c66a22c3f5c4048017d438d1d7dd5
|
3 |
size 10107626487
|
{checkpoint-800/global_step800 β checkpoint-1200/global_step1200}/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 sha256:11e5c69f087a06dfa4218e7205637830d59e2eb6ab4496e20b6099fcccbc9b07
|
3 |
size 10107626487
|
{checkpoint-800/global_step800 β checkpoint-1200/global_step1200}/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 sha256:37dd48878dd48bb7d2a1f2ea052444d84a13e6f4cbab8f1d27904757ae116bd0
|
3 |
size 10107626487
|
{checkpoint-800/global_step800 β checkpoint-1200/global_step1200}/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 sha256:4d614936212979e10ebba5d41469df3f0f5d966c2da7d3029cfa1ec1e9dd897a
|
3 |
size 10107626487
|
{checkpoint-800/global_step800 β checkpoint-1200/global_step1200}/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 sha256:3266f649233e5304749c7c1f07769559935f00b03922e28bff0442991ec9388a
|
3 |
size 10107626487
|
{checkpoint-800/global_step800 β checkpoint-1200/global_step1200}/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:ee838bbe2d8ed873c80d9a5740fcb7f54c91e439e0f4bdde882b4456ea232c7c
|
3 |
size 168086
|
{checkpoint-800/global_step800 β checkpoint-1200/global_step1200}/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 sha256:4326e6a49ee2354fb513f4f301a33c21ffb84a9a51a4e3d0ed33bc12d02bd10b
|
3 |
size 168086
|
{checkpoint-800/global_step800 β checkpoint-1200/global_step1200}/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:d6c42d8a6eeae2786121f541dc5d4a06728de74fdd785c4e82bf7be14708e787
|
3 |
size 168086
|
{checkpoint-800/global_step800 β checkpoint-1200/global_step1200}/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:ca8f493f0fa1429963ac77a6e815a9f189220490b4f4457f7be2b942cdc01726
|
3 |
size 168086
|
{checkpoint-800/global_step800 β checkpoint-1200/global_step1200}/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 sha256:7c1911bcfb001e09fe12e3ee69beaea09f5f021dc647d8b1040b0d66821cc448
|
3 |
size 168086
|
{checkpoint-800/global_step800 β checkpoint-1200/global_step1200}/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 sha256:6c7c6cda3f5f3d82146b47b1ad4b836ecfff16ca2e586ea073dd665626f8757e
|
3 |
size 168086
|
{checkpoint-800/global_step800 β checkpoint-1200/global_step1200}/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 sha256:23cb97ab9d849ada9216fd67b47e13c5ebfbeaeb019c59c09a9cb3298aa097e6
|
3 |
size 168086
|
{checkpoint-800/global_step800 β checkpoint-1200/global_step1200}/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 sha256:5bb17570ce5f68b67d4232815d8eb3b18765ca6071753b7ef99040ac8710b3ec
|
3 |
size 168086
|
checkpoint-1200/latest
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
global_step1200
|
{checkpoint-800 β checkpoint-1200}/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 sha256:050176f4baa1bd8c33427c5122e69e830566029acf7a4cca7415b3b41047fcbd
|
3 |
size 9976576392
|
{checkpoint-800 β checkpoint-1200}/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 sha256:30aa4a97478659826d8dbb57cb3e6ba545204647306edfcfec56c36a5b191c85
|
3 |
size 3500296504
|
{checkpoint-800 β checkpoint-1200}/model.safetensors.index.json
RENAMED
File without changes
|
{checkpoint-800 β checkpoint-1200}/rng_state_0.pth
RENAMED
File without changes
|
{checkpoint-800 β checkpoint-1200}/rng_state_1.pth
RENAMED
File without changes
|
{checkpoint-800 β checkpoint-1200}/rng_state_2.pth
RENAMED
File without changes
|
{checkpoint-800 β checkpoint-1200}/rng_state_3.pth
RENAMED
File without changes
|
{checkpoint-800 β checkpoint-1200}/rng_state_4.pth
RENAMED
File without changes
|
{checkpoint-800 β checkpoint-1200}/rng_state_5.pth
RENAMED
File without changes
|
{checkpoint-800 β checkpoint-1200}/rng_state_6.pth
RENAMED
File without changes
|
{checkpoint-800 β checkpoint-1200}/rng_state_7.pth
RENAMED
File without changes
|
{checkpoint-800 β checkpoint-1200}/special_tokens_map.json
RENAMED
File without changes
|
{checkpoint-800 β checkpoint-1200}/tokenizer.json
RENAMED
File without changes
|
{checkpoint-800 β checkpoint-1200}/tokenizer.model
RENAMED
File without changes
|
{checkpoint-800 β checkpoint-1200}/tokenizer_config.json
RENAMED
File without changes
|
{checkpoint-800 β checkpoint-1200}/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,
|
@@ -486,11 +486,251 @@
|
|
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":
|
494 |
"trial_name": null,
|
495 |
"trial_params": null
|
496 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.4,
|
5 |
+
"global_step": 1200,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
486 |
"learning_rate": 0.0003,
|
487 |
"loss": 1.118,
|
488 |
"step": 800
|
489 |
+
},
|
490 |
+
{
|
491 |
+
"epoch": 0.27,
|
492 |
+
"learning_rate": 0.0003,
|
493 |
+
"loss": 1.1228,
|
494 |
+
"step": 810
|
495 |
+
},
|
496 |
+
{
|
497 |
+
"epoch": 0.27,
|
498 |
+
"learning_rate": 0.0003,
|
499 |
+
"loss": 1.1339,
|
500 |
+
"step": 820
|
501 |
+
},
|
502 |
+
{
|
503 |
+
"epoch": 0.28,
|
504 |
+
"learning_rate": 0.0003,
|
505 |
+
"loss": 1.0853,
|
506 |
+
"step": 830
|
507 |
+
},
|
508 |
+
{
|
509 |
+
"epoch": 0.28,
|
510 |
+
"learning_rate": 0.0003,
|
511 |
+
"loss": 1.0676,
|
512 |
+
"step": 840
|
513 |
+
},
|
514 |
+
{
|
515 |
+
"epoch": 0.28,
|
516 |
+
"learning_rate": 0.0003,
|
517 |
+
"loss": 1.0905,
|
518 |
+
"step": 850
|
519 |
+
},
|
520 |
+
{
|
521 |
+
"epoch": 0.29,
|
522 |
+
"learning_rate": 0.0003,
|
523 |
+
"loss": 1.076,
|
524 |
+
"step": 860
|
525 |
+
},
|
526 |
+
{
|
527 |
+
"epoch": 0.29,
|
528 |
+
"learning_rate": 0.0003,
|
529 |
+
"loss": 1.0202,
|
530 |
+
"step": 870
|
531 |
+
},
|
532 |
+
{
|
533 |
+
"epoch": 0.29,
|
534 |
+
"learning_rate": 0.0003,
|
535 |
+
"loss": 1.0123,
|
536 |
+
"step": 880
|
537 |
+
},
|
538 |
+
{
|
539 |
+
"epoch": 0.3,
|
540 |
+
"learning_rate": 0.0003,
|
541 |
+
"loss": 0.9863,
|
542 |
+
"step": 890
|
543 |
+
},
|
544 |
+
{
|
545 |
+
"epoch": 0.3,
|
546 |
+
"learning_rate": 0.0003,
|
547 |
+
"loss": 0.9347,
|
548 |
+
"step": 900
|
549 |
+
},
|
550 |
+
{
|
551 |
+
"epoch": 0.3,
|
552 |
+
"learning_rate": 0.0003,
|
553 |
+
"loss": 0.9416,
|
554 |
+
"step": 910
|
555 |
+
},
|
556 |
+
{
|
557 |
+
"epoch": 0.31,
|
558 |
+
"learning_rate": 0.0003,
|
559 |
+
"loss": 0.9165,
|
560 |
+
"step": 920
|
561 |
+
},
|
562 |
+
{
|
563 |
+
"epoch": 0.31,
|
564 |
+
"learning_rate": 0.0003,
|
565 |
+
"loss": 0.8996,
|
566 |
+
"step": 930
|
567 |
+
},
|
568 |
+
{
|
569 |
+
"epoch": 0.31,
|
570 |
+
"learning_rate": 0.0003,
|
571 |
+
"loss": 0.8673,
|
572 |
+
"step": 940
|
573 |
+
},
|
574 |
+
{
|
575 |
+
"epoch": 0.32,
|
576 |
+
"learning_rate": 0.0003,
|
577 |
+
"loss": 0.8449,
|
578 |
+
"step": 950
|
579 |
+
},
|
580 |
+
{
|
581 |
+
"epoch": 0.32,
|
582 |
+
"learning_rate": 0.0003,
|
583 |
+
"loss": 0.8468,
|
584 |
+
"step": 960
|
585 |
+
},
|
586 |
+
{
|
587 |
+
"epoch": 0.32,
|
588 |
+
"learning_rate": 0.0003,
|
589 |
+
"loss": 0.817,
|
590 |
+
"step": 970
|
591 |
+
},
|
592 |
+
{
|
593 |
+
"epoch": 0.33,
|
594 |
+
"learning_rate": 0.0003,
|
595 |
+
"loss": 0.7947,
|
596 |
+
"step": 980
|
597 |
+
},
|
598 |
+
{
|
599 |
+
"epoch": 0.33,
|
600 |
+
"learning_rate": 0.0003,
|
601 |
+
"loss": 0.7706,
|
602 |
+
"step": 990
|
603 |
+
},
|
604 |
+
{
|
605 |
+
"epoch": 0.33,
|
606 |
+
"learning_rate": 0.0003,
|
607 |
+
"loss": 0.7357,
|
608 |
+
"step": 1000
|
609 |
+
},
|
610 |
+
{
|
611 |
+
"epoch": 0.34,
|
612 |
+
"learning_rate": 0.0003,
|
613 |
+
"loss": 0.6983,
|
614 |
+
"step": 1010
|
615 |
+
},
|
616 |
+
{
|
617 |
+
"epoch": 0.34,
|
618 |
+
"learning_rate": 0.0003,
|
619 |
+
"loss": 0.6989,
|
620 |
+
"step": 1020
|
621 |
+
},
|
622 |
+
{
|
623 |
+
"epoch": 0.34,
|
624 |
+
"learning_rate": 0.0003,
|
625 |
+
"loss": 0.6692,
|
626 |
+
"step": 1030
|
627 |
+
},
|
628 |
+
{
|
629 |
+
"epoch": 0.35,
|
630 |
+
"learning_rate": 0.0003,
|
631 |
+
"loss": 0.6553,
|
632 |
+
"step": 1040
|
633 |
+
},
|
634 |
+
{
|
635 |
+
"epoch": 0.35,
|
636 |
+
"learning_rate": 0.0003,
|
637 |
+
"loss": 0.6272,
|
638 |
+
"step": 1050
|
639 |
+
},
|
640 |
+
{
|
641 |
+
"epoch": 0.35,
|
642 |
+
"learning_rate": 0.0003,
|
643 |
+
"loss": 0.6092,
|
644 |
+
"step": 1060
|
645 |
+
},
|
646 |
+
{
|
647 |
+
"epoch": 0.36,
|
648 |
+
"learning_rate": 0.0003,
|
649 |
+
"loss": 0.604,
|
650 |
+
"step": 1070
|
651 |
+
},
|
652 |
+
{
|
653 |
+
"epoch": 0.36,
|
654 |
+
"learning_rate": 0.0003,
|
655 |
+
"loss": 0.6494,
|
656 |
+
"step": 1080
|
657 |
+
},
|
658 |
+
{
|
659 |
+
"epoch": 0.36,
|
660 |
+
"learning_rate": 0.0003,
|
661 |
+
"loss": 0.6155,
|
662 |
+
"step": 1090
|
663 |
+
},
|
664 |
+
{
|
665 |
+
"epoch": 0.37,
|
666 |
+
"learning_rate": 0.0003,
|
667 |
+
"loss": 0.5713,
|
668 |
+
"step": 1100
|
669 |
+
},
|
670 |
+
{
|
671 |
+
"epoch": 0.37,
|
672 |
+
"learning_rate": 0.0003,
|
673 |
+
"loss": 0.5358,
|
674 |
+
"step": 1110
|
675 |
+
},
|
676 |
+
{
|
677 |
+
"epoch": 0.37,
|
678 |
+
"learning_rate": 0.0003,
|
679 |
+
"loss": 0.5005,
|
680 |
+
"step": 1120
|
681 |
+
},
|
682 |
+
{
|
683 |
+
"epoch": 0.38,
|
684 |
+
"learning_rate": 0.0003,
|
685 |
+
"loss": 0.483,
|
686 |
+
"step": 1130
|
687 |
+
},
|
688 |
+
{
|
689 |
+
"epoch": 0.38,
|
690 |
+
"learning_rate": 0.0003,
|
691 |
+
"loss": 0.4736,
|
692 |
+
"step": 1140
|
693 |
+
},
|
694 |
+
{
|
695 |
+
"epoch": 0.38,
|
696 |
+
"learning_rate": 0.0003,
|
697 |
+
"loss": 0.4585,
|
698 |
+
"step": 1150
|
699 |
+
},
|
700 |
+
{
|
701 |
+
"epoch": 0.39,
|
702 |
+
"learning_rate": 0.0003,
|
703 |
+
"loss": 0.4442,
|
704 |
+
"step": 1160
|
705 |
+
},
|
706 |
+
{
|
707 |
+
"epoch": 0.39,
|
708 |
+
"learning_rate": 0.0003,
|
709 |
+
"loss": 0.4392,
|
710 |
+
"step": 1170
|
711 |
+
},
|
712 |
+
{
|
713 |
+
"epoch": 0.39,
|
714 |
+
"learning_rate": 0.0003,
|
715 |
+
"loss": 0.4084,
|
716 |
+
"step": 1180
|
717 |
+
},
|
718 |
+
{
|
719 |
+
"epoch": 0.4,
|
720 |
+
"learning_rate": 0.0003,
|
721 |
+
"loss": 0.4104,
|
722 |
+
"step": 1190
|
723 |
+
},
|
724 |
+
{
|
725 |
+
"epoch": 0.4,
|
726 |
+
"learning_rate": 0.0003,
|
727 |
+
"loss": 0.3855,
|
728 |
+
"step": 1200
|
729 |
}
|
730 |
],
|
731 |
"max_steps": 3000,
|
732 |
"num_train_epochs": 9223372036854775807,
|
733 |
+
"total_flos": 502511173632000.0,
|
734 |
"trial_name": null,
|
735 |
"trial_params": null
|
736 |
}
|
{checkpoint-800 β checkpoint-1200}/training_args.bin
RENAMED
File without changes
|
{checkpoint-800 β checkpoint-1200}/zero_to_fp32.py
RENAMED
File without changes
|
checkpoint-800/latest
DELETED
@@ -1 +0,0 @@
|
|
1 |
-
global_step800
|
|
|
|
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 sha256:80c6f49f860f2ea4ccc6f90490738df78763e614072a048d7839d11aebd11a94
|
3 |
+
size 22991
|