Commit
·
e650eeb
1
Parent(s):
ac2c922
Pievienoju apmācīto mT5-large modeli
Browse filesApmācītais mT5-large modelis latviešu valodas medicīnisko tekstu normalizācijai.
Pielietots batch-size=4 un learning-rate = 2,0e-5
Labākais validation-loss pie 4 epohām (checkpoint 64668)
Precizitāte uz testa datu kopu 85,25 %
- large-1/checkpoint-113169/config.json +32 -0
- large-1/checkpoint-113169/generation_config.json +7 -0
- large-1/checkpoint-113169/optimizer.pt +3 -0
- large-1/checkpoint-113169/pytorch_model.bin +3 -0
- large-1/checkpoint-113169/rng_state.pth +3 -0
- large-1/checkpoint-113169/scheduler.pt +3 -0
- large-1/checkpoint-113169/trainer_state.json +1428 -0
- large-1/checkpoint-113169/training_args.bin +3 -0
- large-1/checkpoint-64668/config.json +32 -0
- large-1/checkpoint-64668/generation_config.json +7 -0
- large-1/checkpoint-64668/optimizer.pt +3 -0
- large-1/checkpoint-64668/pytorch_model.bin +3 -0
- large-1/checkpoint-64668/rng_state.pth +3 -0
- large-1/checkpoint-64668/scheduler.pt +3 -0
- large-1/checkpoint-64668/trainer_state.json +822 -0
- large-1/checkpoint-64668/training_args.bin +3 -0
- large-1/checkpoint-97002/config.json +32 -0
- large-1/checkpoint-97002/generation_config.json +7 -0
- large-1/checkpoint-97002/optimizer.pt +3 -0
- large-1/checkpoint-97002/pytorch_model.bin +3 -0
- large-1/checkpoint-97002/rng_state.pth +3 -0
- large-1/checkpoint-97002/scheduler.pt +3 -0
- large-1/checkpoint-97002/trainer_state.json +1228 -0
- large-1/checkpoint-97002/training_args.bin +3 -0
- large-1/config.json +32 -0
- large-1/generation_config.json +7 -0
- large-1/output.txt +234 -0
- large-1/pytorch_model.bin +3 -0
- large-1/training_args.bin +3 -0
large-1/checkpoint-113169/config.json
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "google/mt5-large",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"MT5ForConditionalGeneration"
|
| 5 |
+
],
|
| 6 |
+
"d_ff": 2816,
|
| 7 |
+
"d_kv": 64,
|
| 8 |
+
"d_model": 1024,
|
| 9 |
+
"decoder_start_token_id": 0,
|
| 10 |
+
"dense_act_fn": "gelu_new",
|
| 11 |
+
"dropout_rate": 0.1,
|
| 12 |
+
"eos_token_id": 1,
|
| 13 |
+
"feed_forward_proj": "gated-gelu",
|
| 14 |
+
"initializer_factor": 1.0,
|
| 15 |
+
"is_encoder_decoder": true,
|
| 16 |
+
"is_gated_act": true,
|
| 17 |
+
"layer_norm_epsilon": 1e-06,
|
| 18 |
+
"model_type": "mt5",
|
| 19 |
+
"num_decoder_layers": 24,
|
| 20 |
+
"num_heads": 16,
|
| 21 |
+
"num_layers": 24,
|
| 22 |
+
"output_past": true,
|
| 23 |
+
"pad_token_id": 0,
|
| 24 |
+
"relative_attention_max_distance": 128,
|
| 25 |
+
"relative_attention_num_buckets": 32,
|
| 26 |
+
"tie_word_embeddings": false,
|
| 27 |
+
"tokenizer_class": "T5Tokenizer",
|
| 28 |
+
"torch_dtype": "float32",
|
| 29 |
+
"transformers_version": "4.29.1",
|
| 30 |
+
"use_cache": true,
|
| 31 |
+
"vocab_size": 250112
|
| 32 |
+
}
|
large-1/checkpoint-113169/generation_config.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"decoder_start_token_id": 0,
|
| 4 |
+
"eos_token_id": 1,
|
| 5 |
+
"pad_token_id": 0,
|
| 6 |
+
"transformers_version": "4.29.1"
|
| 7 |
+
}
|
large-1/checkpoint-113169/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:495a6f1710cb3b4637790f8b758fa7e774b39ed3007413febe0b3148f84cd23b
|
| 3 |
+
size 9836995421
|
large-1/checkpoint-113169/pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:82c4b201cb4725c6930172987e1f3ee1bec3c2ad5ddcbcc1da3ed2901842ce80
|
| 3 |
+
size 4918519065
|
large-1/checkpoint-113169/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:25ac25aa24033b4b0ad58405db1859faacf014776497dec2b3821ad206f0a4f1
|
| 3 |
+
size 14575
|
large-1/checkpoint-113169/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ca55b8d64cc5639e647c8de40ee849c3076eb426af50cf864894f8d7c4be676b
|
| 3 |
+
size 627
|
large-1/checkpoint-113169/trainer_state.json
ADDED
|
@@ -0,0 +1,1428 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.004835214000195265,
|
| 3 |
+
"best_model_checkpoint": "./results/large-1/checkpoint-64668",
|
| 4 |
+
"epoch": 7.0,
|
| 5 |
+
"global_step": 113169,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.03,
|
| 12 |
+
"learning_rate": 1e-05,
|
| 13 |
+
"loss": 29.3333,
|
| 14 |
+
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.06,
|
| 18 |
+
"learning_rate": 2e-05,
|
| 19 |
+
"loss": 12.5737,
|
| 20 |
+
"step": 1000
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.09,
|
| 24 |
+
"learning_rate": 1.9968976856735126e-05,
|
| 25 |
+
"loss": 2.3813,
|
| 26 |
+
"step": 1500
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.12,
|
| 30 |
+
"learning_rate": 1.993795371347025e-05,
|
| 31 |
+
"loss": 0.2316,
|
| 32 |
+
"step": 2000
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.15,
|
| 36 |
+
"learning_rate": 1.9906930570205375e-05,
|
| 37 |
+
"loss": 0.099,
|
| 38 |
+
"step": 2500
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.19,
|
| 42 |
+
"learning_rate": 1.98759074269405e-05,
|
| 43 |
+
"loss": 0.0608,
|
| 44 |
+
"step": 3000
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.22,
|
| 48 |
+
"learning_rate": 1.9844884283675623e-05,
|
| 49 |
+
"loss": 0.0565,
|
| 50 |
+
"step": 3500
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.25,
|
| 54 |
+
"learning_rate": 1.9813861140410748e-05,
|
| 55 |
+
"loss": 0.0435,
|
| 56 |
+
"step": 4000
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.28,
|
| 60 |
+
"learning_rate": 1.9782837997145872e-05,
|
| 61 |
+
"loss": 0.0354,
|
| 62 |
+
"step": 4500
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.31,
|
| 66 |
+
"learning_rate": 1.9751814853880996e-05,
|
| 67 |
+
"loss": 0.0339,
|
| 68 |
+
"step": 5000
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.34,
|
| 72 |
+
"learning_rate": 1.972079171061612e-05,
|
| 73 |
+
"loss": 0.0294,
|
| 74 |
+
"step": 5500
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.37,
|
| 78 |
+
"learning_rate": 1.9689768567351245e-05,
|
| 79 |
+
"loss": 0.035,
|
| 80 |
+
"step": 6000
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.4,
|
| 84 |
+
"learning_rate": 1.965874542408637e-05,
|
| 85 |
+
"loss": 0.0515,
|
| 86 |
+
"step": 6500
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.43,
|
| 90 |
+
"learning_rate": 1.9627722280821494e-05,
|
| 91 |
+
"loss": 0.0232,
|
| 92 |
+
"step": 7000
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.46,
|
| 96 |
+
"learning_rate": 1.9596699137556618e-05,
|
| 97 |
+
"loss": 0.0349,
|
| 98 |
+
"step": 7500
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.49,
|
| 102 |
+
"learning_rate": 1.9565675994291742e-05,
|
| 103 |
+
"loss": 0.0226,
|
| 104 |
+
"step": 8000
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.53,
|
| 108 |
+
"learning_rate": 1.9534652851026867e-05,
|
| 109 |
+
"loss": 0.0215,
|
| 110 |
+
"step": 8500
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 0.56,
|
| 114 |
+
"learning_rate": 1.9503629707761994e-05,
|
| 115 |
+
"loss": 0.0204,
|
| 116 |
+
"step": 9000
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.59,
|
| 120 |
+
"learning_rate": 1.9472606564497115e-05,
|
| 121 |
+
"loss": 0.0192,
|
| 122 |
+
"step": 9500
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.62,
|
| 126 |
+
"learning_rate": 1.9441583421232243e-05,
|
| 127 |
+
"loss": 0.0194,
|
| 128 |
+
"step": 10000
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.65,
|
| 132 |
+
"learning_rate": 1.9410560277967364e-05,
|
| 133 |
+
"loss": 0.0179,
|
| 134 |
+
"step": 10500
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 0.68,
|
| 138 |
+
"learning_rate": 1.937953713470249e-05,
|
| 139 |
+
"loss": 0.017,
|
| 140 |
+
"step": 11000
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 0.71,
|
| 144 |
+
"learning_rate": 1.9348513991437613e-05,
|
| 145 |
+
"loss": 0.0226,
|
| 146 |
+
"step": 11500
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 0.74,
|
| 150 |
+
"learning_rate": 1.9317490848172737e-05,
|
| 151 |
+
"loss": 0.016,
|
| 152 |
+
"step": 12000
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 0.77,
|
| 156 |
+
"learning_rate": 1.928646770490786e-05,
|
| 157 |
+
"loss": 0.0154,
|
| 158 |
+
"step": 12500
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 0.8,
|
| 162 |
+
"learning_rate": 1.9255444561642986e-05,
|
| 163 |
+
"loss": 0.0157,
|
| 164 |
+
"step": 13000
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.84,
|
| 168 |
+
"learning_rate": 1.9224421418378113e-05,
|
| 169 |
+
"loss": 0.0139,
|
| 170 |
+
"step": 13500
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.87,
|
| 174 |
+
"learning_rate": 1.9193398275113234e-05,
|
| 175 |
+
"loss": 0.0129,
|
| 176 |
+
"step": 14000
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 0.9,
|
| 180 |
+
"learning_rate": 1.9162375131848362e-05,
|
| 181 |
+
"loss": 0.0134,
|
| 182 |
+
"step": 14500
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 0.93,
|
| 186 |
+
"learning_rate": 1.9131351988583483e-05,
|
| 187 |
+
"loss": 0.0134,
|
| 188 |
+
"step": 15000
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 0.96,
|
| 192 |
+
"learning_rate": 1.910032884531861e-05,
|
| 193 |
+
"loss": 0.0133,
|
| 194 |
+
"step": 15500
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 0.99,
|
| 198 |
+
"learning_rate": 1.9069305702053732e-05,
|
| 199 |
+
"loss": 0.0133,
|
| 200 |
+
"step": 16000
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 1.0,
|
| 204 |
+
"eval_loss": 0.007159320637583733,
|
| 205 |
+
"eval_runtime": 63.5558,
|
| 206 |
+
"eval_samples_per_second": 113.05,
|
| 207 |
+
"eval_steps_per_second": 7.08,
|
| 208 |
+
"step": 16167
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 1.02,
|
| 212 |
+
"learning_rate": 1.903828255878886e-05,
|
| 213 |
+
"loss": 0.0118,
|
| 214 |
+
"step": 16500
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"epoch": 1.05,
|
| 218 |
+
"learning_rate": 1.900725941552398e-05,
|
| 219 |
+
"loss": 0.0114,
|
| 220 |
+
"step": 17000
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 1.08,
|
| 224 |
+
"learning_rate": 1.8976236272259108e-05,
|
| 225 |
+
"loss": 0.0115,
|
| 226 |
+
"step": 17500
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 1.11,
|
| 230 |
+
"learning_rate": 1.8945213128994233e-05,
|
| 231 |
+
"loss": 0.0115,
|
| 232 |
+
"step": 18000
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"epoch": 1.14,
|
| 236 |
+
"learning_rate": 1.8914189985729357e-05,
|
| 237 |
+
"loss": 0.0118,
|
| 238 |
+
"step": 18500
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"epoch": 1.18,
|
| 242 |
+
"learning_rate": 1.888316684246448e-05,
|
| 243 |
+
"loss": 0.0119,
|
| 244 |
+
"step": 19000
|
| 245 |
+
},
|
| 246 |
+
{
|
| 247 |
+
"epoch": 1.21,
|
| 248 |
+
"learning_rate": 1.8852143699199606e-05,
|
| 249 |
+
"loss": 0.0117,
|
| 250 |
+
"step": 19500
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 1.24,
|
| 254 |
+
"learning_rate": 1.882112055593473e-05,
|
| 255 |
+
"loss": 0.0113,
|
| 256 |
+
"step": 20000
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 1.27,
|
| 260 |
+
"learning_rate": 1.8790097412669854e-05,
|
| 261 |
+
"loss": 0.0102,
|
| 262 |
+
"step": 20500
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 1.3,
|
| 266 |
+
"learning_rate": 1.875907426940498e-05,
|
| 267 |
+
"loss": 0.0109,
|
| 268 |
+
"step": 21000
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 1.33,
|
| 272 |
+
"learning_rate": 1.87280511261401e-05,
|
| 273 |
+
"loss": 0.0096,
|
| 274 |
+
"step": 21500
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 1.36,
|
| 278 |
+
"learning_rate": 1.8697027982875227e-05,
|
| 279 |
+
"loss": 0.0105,
|
| 280 |
+
"step": 22000
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 1.39,
|
| 284 |
+
"learning_rate": 1.866600483961035e-05,
|
| 285 |
+
"loss": 0.0093,
|
| 286 |
+
"step": 22500
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 1.42,
|
| 290 |
+
"learning_rate": 1.8634981696345476e-05,
|
| 291 |
+
"loss": 0.0096,
|
| 292 |
+
"step": 23000
|
| 293 |
+
},
|
| 294 |
+
{
|
| 295 |
+
"epoch": 1.45,
|
| 296 |
+
"learning_rate": 1.86039585530806e-05,
|
| 297 |
+
"loss": 0.0091,
|
| 298 |
+
"step": 23500
|
| 299 |
+
},
|
| 300 |
+
{
|
| 301 |
+
"epoch": 1.48,
|
| 302 |
+
"learning_rate": 1.8572935409815725e-05,
|
| 303 |
+
"loss": 0.0099,
|
| 304 |
+
"step": 24000
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 1.52,
|
| 308 |
+
"learning_rate": 1.854191226655085e-05,
|
| 309 |
+
"loss": 0.009,
|
| 310 |
+
"step": 24500
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 1.55,
|
| 314 |
+
"learning_rate": 1.8510889123285973e-05,
|
| 315 |
+
"loss": 0.0097,
|
| 316 |
+
"step": 25000
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 1.58,
|
| 320 |
+
"learning_rate": 1.8479865980021098e-05,
|
| 321 |
+
"loss": 0.0089,
|
| 322 |
+
"step": 25500
|
| 323 |
+
},
|
| 324 |
+
{
|
| 325 |
+
"epoch": 1.61,
|
| 326 |
+
"learning_rate": 1.8448842836756222e-05,
|
| 327 |
+
"loss": 0.0097,
|
| 328 |
+
"step": 26000
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"epoch": 1.64,
|
| 332 |
+
"learning_rate": 1.8417819693491346e-05,
|
| 333 |
+
"loss": 0.0099,
|
| 334 |
+
"step": 26500
|
| 335 |
+
},
|
| 336 |
+
{
|
| 337 |
+
"epoch": 1.67,
|
| 338 |
+
"learning_rate": 1.838679655022647e-05,
|
| 339 |
+
"loss": 0.0092,
|
| 340 |
+
"step": 27000
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"epoch": 1.7,
|
| 344 |
+
"learning_rate": 1.8355773406961595e-05,
|
| 345 |
+
"loss": 0.0094,
|
| 346 |
+
"step": 27500
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 1.73,
|
| 350 |
+
"learning_rate": 1.832475026369672e-05,
|
| 351 |
+
"loss": 0.0087,
|
| 352 |
+
"step": 28000
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 1.76,
|
| 356 |
+
"learning_rate": 1.8293727120431844e-05,
|
| 357 |
+
"loss": 0.0091,
|
| 358 |
+
"step": 28500
|
| 359 |
+
},
|
| 360 |
+
{
|
| 361 |
+
"epoch": 1.79,
|
| 362 |
+
"learning_rate": 1.8262703977166968e-05,
|
| 363 |
+
"loss": 0.0098,
|
| 364 |
+
"step": 29000
|
| 365 |
+
},
|
| 366 |
+
{
|
| 367 |
+
"epoch": 1.82,
|
| 368 |
+
"learning_rate": 1.8231680833902092e-05,
|
| 369 |
+
"loss": 0.0093,
|
| 370 |
+
"step": 29500
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 1.86,
|
| 374 |
+
"learning_rate": 1.8200657690637217e-05,
|
| 375 |
+
"loss": 0.0088,
|
| 376 |
+
"step": 30000
|
| 377 |
+
},
|
| 378 |
+
{
|
| 379 |
+
"epoch": 1.89,
|
| 380 |
+
"learning_rate": 1.816963454737234e-05,
|
| 381 |
+
"loss": 0.008,
|
| 382 |
+
"step": 30500
|
| 383 |
+
},
|
| 384 |
+
{
|
| 385 |
+
"epoch": 1.92,
|
| 386 |
+
"learning_rate": 1.8138611404107465e-05,
|
| 387 |
+
"loss": 0.0088,
|
| 388 |
+
"step": 31000
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 1.95,
|
| 392 |
+
"learning_rate": 1.810758826084259e-05,
|
| 393 |
+
"loss": 0.0084,
|
| 394 |
+
"step": 31500
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 1.98,
|
| 398 |
+
"learning_rate": 1.8076565117577714e-05,
|
| 399 |
+
"loss": 0.0087,
|
| 400 |
+
"step": 32000
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"epoch": 2.0,
|
| 404 |
+
"eval_loss": 0.005626102443784475,
|
| 405 |
+
"eval_runtime": 63.5514,
|
| 406 |
+
"eval_samples_per_second": 113.058,
|
| 407 |
+
"eval_steps_per_second": 7.081,
|
| 408 |
+
"step": 32334
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 2.01,
|
| 412 |
+
"learning_rate": 1.804554197431284e-05,
|
| 413 |
+
"loss": 0.0081,
|
| 414 |
+
"step": 32500
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 2.04,
|
| 418 |
+
"learning_rate": 1.8014518831047963e-05,
|
| 419 |
+
"loss": 0.007,
|
| 420 |
+
"step": 33000
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 2.07,
|
| 424 |
+
"learning_rate": 1.7983495687783087e-05,
|
| 425 |
+
"loss": 0.0072,
|
| 426 |
+
"step": 33500
|
| 427 |
+
},
|
| 428 |
+
{
|
| 429 |
+
"epoch": 2.1,
|
| 430 |
+
"learning_rate": 1.795247254451821e-05,
|
| 431 |
+
"loss": 0.0069,
|
| 432 |
+
"step": 34000
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 2.13,
|
| 436 |
+
"learning_rate": 1.7921449401253336e-05,
|
| 437 |
+
"loss": 0.0072,
|
| 438 |
+
"step": 34500
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 2.16,
|
| 442 |
+
"learning_rate": 1.789042625798846e-05,
|
| 443 |
+
"loss": 0.0067,
|
| 444 |
+
"step": 35000
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 2.2,
|
| 448 |
+
"learning_rate": 1.7859403114723584e-05,
|
| 449 |
+
"loss": 0.007,
|
| 450 |
+
"step": 35500
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 2.23,
|
| 454 |
+
"learning_rate": 1.782837997145871e-05,
|
| 455 |
+
"loss": 0.0072,
|
| 456 |
+
"step": 36000
|
| 457 |
+
},
|
| 458 |
+
{
|
| 459 |
+
"epoch": 2.26,
|
| 460 |
+
"learning_rate": 1.7797356828193833e-05,
|
| 461 |
+
"loss": 0.0074,
|
| 462 |
+
"step": 36500
|
| 463 |
+
},
|
| 464 |
+
{
|
| 465 |
+
"epoch": 2.29,
|
| 466 |
+
"learning_rate": 1.7766333684928957e-05,
|
| 467 |
+
"loss": 0.0075,
|
| 468 |
+
"step": 37000
|
| 469 |
+
},
|
| 470 |
+
{
|
| 471 |
+
"epoch": 2.32,
|
| 472 |
+
"learning_rate": 1.7735310541664085e-05,
|
| 473 |
+
"loss": 0.0072,
|
| 474 |
+
"step": 37500
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 2.35,
|
| 478 |
+
"learning_rate": 1.7704287398399206e-05,
|
| 479 |
+
"loss": 0.0061,
|
| 480 |
+
"step": 38000
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 2.38,
|
| 484 |
+
"learning_rate": 1.7673264255134334e-05,
|
| 485 |
+
"loss": 0.0071,
|
| 486 |
+
"step": 38500
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 2.41,
|
| 490 |
+
"learning_rate": 1.7642241111869455e-05,
|
| 491 |
+
"loss": 0.0074,
|
| 492 |
+
"step": 39000
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 2.44,
|
| 496 |
+
"learning_rate": 1.7611217968604582e-05,
|
| 497 |
+
"loss": 0.0072,
|
| 498 |
+
"step": 39500
|
| 499 |
+
},
|
| 500 |
+
{
|
| 501 |
+
"epoch": 2.47,
|
| 502 |
+
"learning_rate": 1.7580194825339703e-05,
|
| 503 |
+
"loss": 0.0072,
|
| 504 |
+
"step": 40000
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 2.51,
|
| 508 |
+
"learning_rate": 1.754917168207483e-05,
|
| 509 |
+
"loss": 0.0075,
|
| 510 |
+
"step": 40500
|
| 511 |
+
},
|
| 512 |
+
{
|
| 513 |
+
"epoch": 2.54,
|
| 514 |
+
"learning_rate": 1.7518148538809952e-05,
|
| 515 |
+
"loss": 0.0069,
|
| 516 |
+
"step": 41000
|
| 517 |
+
},
|
| 518 |
+
{
|
| 519 |
+
"epoch": 2.57,
|
| 520 |
+
"learning_rate": 1.7487125395545076e-05,
|
| 521 |
+
"loss": 0.007,
|
| 522 |
+
"step": 41500
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 2.6,
|
| 526 |
+
"learning_rate": 1.7456102252280204e-05,
|
| 527 |
+
"loss": 0.0058,
|
| 528 |
+
"step": 42000
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 2.63,
|
| 532 |
+
"learning_rate": 1.7425079109015325e-05,
|
| 533 |
+
"loss": 0.0064,
|
| 534 |
+
"step": 42500
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 2.66,
|
| 538 |
+
"learning_rate": 1.7394055965750453e-05,
|
| 539 |
+
"loss": 0.0067,
|
| 540 |
+
"step": 43000
|
| 541 |
+
},
|
| 542 |
+
{
|
| 543 |
+
"epoch": 2.69,
|
| 544 |
+
"learning_rate": 1.7363032822485574e-05,
|
| 545 |
+
"loss": 0.0062,
|
| 546 |
+
"step": 43500
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 2.72,
|
| 550 |
+
"learning_rate": 1.73320096792207e-05,
|
| 551 |
+
"loss": 0.0066,
|
| 552 |
+
"step": 44000
|
| 553 |
+
},
|
| 554 |
+
{
|
| 555 |
+
"epoch": 2.75,
|
| 556 |
+
"learning_rate": 1.7300986535955822e-05,
|
| 557 |
+
"loss": 0.0066,
|
| 558 |
+
"step": 44500
|
| 559 |
+
},
|
| 560 |
+
{
|
| 561 |
+
"epoch": 2.78,
|
| 562 |
+
"learning_rate": 1.726996339269095e-05,
|
| 563 |
+
"loss": 0.0071,
|
| 564 |
+
"step": 45000
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 2.81,
|
| 568 |
+
"learning_rate": 1.723894024942607e-05,
|
| 569 |
+
"loss": 0.0065,
|
| 570 |
+
"step": 45500
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 2.85,
|
| 574 |
+
"learning_rate": 1.72079171061612e-05,
|
| 575 |
+
"loss": 0.0065,
|
| 576 |
+
"step": 46000
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 2.88,
|
| 580 |
+
"learning_rate": 1.7176893962896323e-05,
|
| 581 |
+
"loss": 0.0065,
|
| 582 |
+
"step": 46500
|
| 583 |
+
},
|
| 584 |
+
{
|
| 585 |
+
"epoch": 2.91,
|
| 586 |
+
"learning_rate": 1.7145870819631448e-05,
|
| 587 |
+
"loss": 0.0062,
|
| 588 |
+
"step": 47000
|
| 589 |
+
},
|
| 590 |
+
{
|
| 591 |
+
"epoch": 2.94,
|
| 592 |
+
"learning_rate": 1.7114847676366572e-05,
|
| 593 |
+
"loss": 0.0075,
|
| 594 |
+
"step": 47500
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 2.97,
|
| 598 |
+
"learning_rate": 1.7083824533101696e-05,
|
| 599 |
+
"loss": 0.0064,
|
| 600 |
+
"step": 48000
|
| 601 |
+
},
|
| 602 |
+
{
|
| 603 |
+
"epoch": 3.0,
|
| 604 |
+
"learning_rate": 1.705280138983682e-05,
|
| 605 |
+
"loss": 0.0063,
|
| 606 |
+
"step": 48500
|
| 607 |
+
},
|
| 608 |
+
{
|
| 609 |
+
"epoch": 3.0,
|
| 610 |
+
"eval_loss": 0.005162048153579235,
|
| 611 |
+
"eval_runtime": 63.5102,
|
| 612 |
+
"eval_samples_per_second": 113.132,
|
| 613 |
+
"eval_steps_per_second": 7.085,
|
| 614 |
+
"step": 48501
|
| 615 |
+
},
|
| 616 |
+
{
|
| 617 |
+
"epoch": 3.03,
|
| 618 |
+
"learning_rate": 1.7021778246571945e-05,
|
| 619 |
+
"loss": 0.0055,
|
| 620 |
+
"step": 49000
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 3.06,
|
| 624 |
+
"learning_rate": 1.699075510330707e-05,
|
| 625 |
+
"loss": 0.0055,
|
| 626 |
+
"step": 49500
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 3.09,
|
| 630 |
+
"learning_rate": 1.6959731960042194e-05,
|
| 631 |
+
"loss": 0.0059,
|
| 632 |
+
"step": 50000
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 3.12,
|
| 636 |
+
"learning_rate": 1.6928708816777318e-05,
|
| 637 |
+
"loss": 0.0052,
|
| 638 |
+
"step": 50500
|
| 639 |
+
},
|
| 640 |
+
{
|
| 641 |
+
"epoch": 3.15,
|
| 642 |
+
"learning_rate": 1.6897685673512442e-05,
|
| 643 |
+
"loss": 0.0053,
|
| 644 |
+
"step": 51000
|
| 645 |
+
},
|
| 646 |
+
{
|
| 647 |
+
"epoch": 3.19,
|
| 648 |
+
"learning_rate": 1.6866662530247567e-05,
|
| 649 |
+
"loss": 0.005,
|
| 650 |
+
"step": 51500
|
| 651 |
+
},
|
| 652 |
+
{
|
| 653 |
+
"epoch": 3.22,
|
| 654 |
+
"learning_rate": 1.683563938698269e-05,
|
| 655 |
+
"loss": 0.0056,
|
| 656 |
+
"step": 52000
|
| 657 |
+
},
|
| 658 |
+
{
|
| 659 |
+
"epoch": 3.25,
|
| 660 |
+
"learning_rate": 1.6804616243717815e-05,
|
| 661 |
+
"loss": 0.0051,
|
| 662 |
+
"step": 52500
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 3.28,
|
| 666 |
+
"learning_rate": 1.677359310045294e-05,
|
| 667 |
+
"loss": 0.0053,
|
| 668 |
+
"step": 53000
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 3.31,
|
| 672 |
+
"learning_rate": 1.6742569957188064e-05,
|
| 673 |
+
"loss": 0.0053,
|
| 674 |
+
"step": 53500
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 3.34,
|
| 678 |
+
"learning_rate": 1.6711546813923188e-05,
|
| 679 |
+
"loss": 0.0051,
|
| 680 |
+
"step": 54000
|
| 681 |
+
},
|
| 682 |
+
{
|
| 683 |
+
"epoch": 3.37,
|
| 684 |
+
"learning_rate": 1.6680523670658313e-05,
|
| 685 |
+
"loss": 0.0056,
|
| 686 |
+
"step": 54500
|
| 687 |
+
},
|
| 688 |
+
{
|
| 689 |
+
"epoch": 3.4,
|
| 690 |
+
"learning_rate": 1.6649500527393437e-05,
|
| 691 |
+
"loss": 0.0068,
|
| 692 |
+
"step": 55000
|
| 693 |
+
},
|
| 694 |
+
{
|
| 695 |
+
"epoch": 3.43,
|
| 696 |
+
"learning_rate": 1.661847738412856e-05,
|
| 697 |
+
"loss": 0.0054,
|
| 698 |
+
"step": 55500
|
| 699 |
+
},
|
| 700 |
+
{
|
| 701 |
+
"epoch": 3.46,
|
| 702 |
+
"learning_rate": 1.6587454240863686e-05,
|
| 703 |
+
"loss": 0.0055,
|
| 704 |
+
"step": 56000
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 3.49,
|
| 708 |
+
"learning_rate": 1.655643109759881e-05,
|
| 709 |
+
"loss": 0.0056,
|
| 710 |
+
"step": 56500
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 3.53,
|
| 714 |
+
"learning_rate": 1.6525407954333934e-05,
|
| 715 |
+
"loss": 0.0053,
|
| 716 |
+
"step": 57000
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 3.56,
|
| 720 |
+
"learning_rate": 1.649438481106906e-05,
|
| 721 |
+
"loss": 0.0051,
|
| 722 |
+
"step": 57500
|
| 723 |
+
},
|
| 724 |
+
{
|
| 725 |
+
"epoch": 3.59,
|
| 726 |
+
"learning_rate": 1.6463361667804183e-05,
|
| 727 |
+
"loss": 0.005,
|
| 728 |
+
"step": 58000
|
| 729 |
+
},
|
| 730 |
+
{
|
| 731 |
+
"epoch": 3.62,
|
| 732 |
+
"learning_rate": 1.6432338524539307e-05,
|
| 733 |
+
"loss": 0.0055,
|
| 734 |
+
"step": 58500
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 3.65,
|
| 738 |
+
"learning_rate": 1.640131538127443e-05,
|
| 739 |
+
"loss": 0.0048,
|
| 740 |
+
"step": 59000
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 3.68,
|
| 744 |
+
"learning_rate": 1.6370292238009556e-05,
|
| 745 |
+
"loss": 0.0052,
|
| 746 |
+
"step": 59500
|
| 747 |
+
},
|
| 748 |
+
{
|
| 749 |
+
"epoch": 3.71,
|
| 750 |
+
"learning_rate": 1.633926909474468e-05,
|
| 751 |
+
"loss": 0.0048,
|
| 752 |
+
"step": 60000
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 3.74,
|
| 756 |
+
"learning_rate": 1.6308245951479805e-05,
|
| 757 |
+
"loss": 0.0049,
|
| 758 |
+
"step": 60500
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 3.77,
|
| 762 |
+
"learning_rate": 1.627722280821493e-05,
|
| 763 |
+
"loss": 0.0054,
|
| 764 |
+
"step": 61000
|
| 765 |
+
},
|
| 766 |
+
{
|
| 767 |
+
"epoch": 3.8,
|
| 768 |
+
"learning_rate": 1.6246199664950053e-05,
|
| 769 |
+
"loss": 0.0052,
|
| 770 |
+
"step": 61500
|
| 771 |
+
},
|
| 772 |
+
{
|
| 773 |
+
"epoch": 3.83,
|
| 774 |
+
"learning_rate": 1.6215176521685178e-05,
|
| 775 |
+
"loss": 0.0053,
|
| 776 |
+
"step": 62000
|
| 777 |
+
},
|
| 778 |
+
{
|
| 779 |
+
"epoch": 3.87,
|
| 780 |
+
"learning_rate": 1.6184153378420302e-05,
|
| 781 |
+
"loss": 0.0052,
|
| 782 |
+
"step": 62500
|
| 783 |
+
},
|
| 784 |
+
{
|
| 785 |
+
"epoch": 3.9,
|
| 786 |
+
"learning_rate": 1.6153130235155426e-05,
|
| 787 |
+
"loss": 0.0053,
|
| 788 |
+
"step": 63000
|
| 789 |
+
},
|
| 790 |
+
{
|
| 791 |
+
"epoch": 3.93,
|
| 792 |
+
"learning_rate": 1.612210709189055e-05,
|
| 793 |
+
"loss": 0.0052,
|
| 794 |
+
"step": 63500
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 3.96,
|
| 798 |
+
"learning_rate": 1.6091083948625675e-05,
|
| 799 |
+
"loss": 0.0052,
|
| 800 |
+
"step": 64000
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 3.99,
|
| 804 |
+
"learning_rate": 1.60600608053608e-05,
|
| 805 |
+
"loss": 0.0054,
|
| 806 |
+
"step": 64500
|
| 807 |
+
},
|
| 808 |
+
{
|
| 809 |
+
"epoch": 4.0,
|
| 810 |
+
"eval_loss": 0.004835214000195265,
|
| 811 |
+
"eval_runtime": 63.5993,
|
| 812 |
+
"eval_samples_per_second": 112.973,
|
| 813 |
+
"eval_steps_per_second": 7.076,
|
| 814 |
+
"step": 64668
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 4.02,
|
| 818 |
+
"learning_rate": 1.6029037662095924e-05,
|
| 819 |
+
"loss": 0.0042,
|
| 820 |
+
"step": 65000
|
| 821 |
+
},
|
| 822 |
+
{
|
| 823 |
+
"epoch": 4.05,
|
| 824 |
+
"learning_rate": 1.5998014518831048e-05,
|
| 825 |
+
"loss": 0.0044,
|
| 826 |
+
"step": 65500
|
| 827 |
+
},
|
| 828 |
+
{
|
| 829 |
+
"epoch": 4.08,
|
| 830 |
+
"learning_rate": 1.5966991375566176e-05,
|
| 831 |
+
"loss": 0.0041,
|
| 832 |
+
"step": 66000
|
| 833 |
+
},
|
| 834 |
+
{
|
| 835 |
+
"epoch": 4.11,
|
| 836 |
+
"learning_rate": 1.5935968232301297e-05,
|
| 837 |
+
"loss": 0.0046,
|
| 838 |
+
"step": 66500
|
| 839 |
+
},
|
| 840 |
+
{
|
| 841 |
+
"epoch": 4.14,
|
| 842 |
+
"learning_rate": 1.5904945089036424e-05,
|
| 843 |
+
"loss": 0.004,
|
| 844 |
+
"step": 67000
|
| 845 |
+
},
|
| 846 |
+
{
|
| 847 |
+
"epoch": 4.18,
|
| 848 |
+
"learning_rate": 1.5873921945771545e-05,
|
| 849 |
+
"loss": 0.0044,
|
| 850 |
+
"step": 67500
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 4.21,
|
| 854 |
+
"learning_rate": 1.5842898802506673e-05,
|
| 855 |
+
"loss": 0.0047,
|
| 856 |
+
"step": 68000
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 4.24,
|
| 860 |
+
"learning_rate": 1.5811875659241794e-05,
|
| 861 |
+
"loss": 0.0043,
|
| 862 |
+
"step": 68500
|
| 863 |
+
},
|
| 864 |
+
{
|
| 865 |
+
"epoch": 4.27,
|
| 866 |
+
"learning_rate": 1.5780852515976922e-05,
|
| 867 |
+
"loss": 0.004,
|
| 868 |
+
"step": 69000
|
| 869 |
+
},
|
| 870 |
+
{
|
| 871 |
+
"epoch": 4.3,
|
| 872 |
+
"learning_rate": 1.5749829372712043e-05,
|
| 873 |
+
"loss": 0.0043,
|
| 874 |
+
"step": 69500
|
| 875 |
+
},
|
| 876 |
+
{
|
| 877 |
+
"epoch": 4.33,
|
| 878 |
+
"learning_rate": 1.571880622944717e-05,
|
| 879 |
+
"loss": 0.0048,
|
| 880 |
+
"step": 70000
|
| 881 |
+
},
|
| 882 |
+
{
|
| 883 |
+
"epoch": 4.36,
|
| 884 |
+
"learning_rate": 1.5687783086182295e-05,
|
| 885 |
+
"loss": 0.0044,
|
| 886 |
+
"step": 70500
|
| 887 |
+
},
|
| 888 |
+
{
|
| 889 |
+
"epoch": 4.39,
|
| 890 |
+
"learning_rate": 1.5656759942917416e-05,
|
| 891 |
+
"loss": 0.0042,
|
| 892 |
+
"step": 71000
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 4.42,
|
| 896 |
+
"learning_rate": 1.5625736799652544e-05,
|
| 897 |
+
"loss": 0.0041,
|
| 898 |
+
"step": 71500
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 4.45,
|
| 902 |
+
"learning_rate": 1.5594713656387664e-05,
|
| 903 |
+
"loss": 0.0045,
|
| 904 |
+
"step": 72000
|
| 905 |
+
},
|
| 906 |
+
{
|
| 907 |
+
"epoch": 4.48,
|
| 908 |
+
"learning_rate": 1.5563690513122792e-05,
|
| 909 |
+
"loss": 0.0041,
|
| 910 |
+
"step": 72500
|
| 911 |
+
},
|
| 912 |
+
{
|
| 913 |
+
"epoch": 4.52,
|
| 914 |
+
"learning_rate": 1.5532667369857913e-05,
|
| 915 |
+
"loss": 0.0044,
|
| 916 |
+
"step": 73000
|
| 917 |
+
},
|
| 918 |
+
{
|
| 919 |
+
"epoch": 4.55,
|
| 920 |
+
"learning_rate": 1.550164422659304e-05,
|
| 921 |
+
"loss": 0.0039,
|
| 922 |
+
"step": 73500
|
| 923 |
+
},
|
| 924 |
+
{
|
| 925 |
+
"epoch": 4.58,
|
| 926 |
+
"learning_rate": 1.5470621083328162e-05,
|
| 927 |
+
"loss": 0.0045,
|
| 928 |
+
"step": 74000
|
| 929 |
+
},
|
| 930 |
+
{
|
| 931 |
+
"epoch": 4.61,
|
| 932 |
+
"learning_rate": 1.543959794006329e-05,
|
| 933 |
+
"loss": 0.0039,
|
| 934 |
+
"step": 74500
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 4.64,
|
| 938 |
+
"learning_rate": 1.5408574796798414e-05,
|
| 939 |
+
"loss": 0.0044,
|
| 940 |
+
"step": 75000
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 4.67,
|
| 944 |
+
"learning_rate": 1.5377551653533538e-05,
|
| 945 |
+
"loss": 0.004,
|
| 946 |
+
"step": 75500
|
| 947 |
+
},
|
| 948 |
+
{
|
| 949 |
+
"epoch": 4.7,
|
| 950 |
+
"learning_rate": 1.5346528510268663e-05,
|
| 951 |
+
"loss": 0.0048,
|
| 952 |
+
"step": 76000
|
| 953 |
+
},
|
| 954 |
+
{
|
| 955 |
+
"epoch": 4.73,
|
| 956 |
+
"learning_rate": 1.5315505367003787e-05,
|
| 957 |
+
"loss": 0.004,
|
| 958 |
+
"step": 76500
|
| 959 |
+
},
|
| 960 |
+
{
|
| 961 |
+
"epoch": 4.76,
|
| 962 |
+
"learning_rate": 1.528448222373891e-05,
|
| 963 |
+
"loss": 0.0046,
|
| 964 |
+
"step": 77000
|
| 965 |
+
},
|
| 966 |
+
{
|
| 967 |
+
"epoch": 4.79,
|
| 968 |
+
"learning_rate": 1.5253459080474036e-05,
|
| 969 |
+
"loss": 0.0043,
|
| 970 |
+
"step": 77500
|
| 971 |
+
},
|
| 972 |
+
{
|
| 973 |
+
"epoch": 4.82,
|
| 974 |
+
"learning_rate": 1.5222435937209158e-05,
|
| 975 |
+
"loss": 0.0043,
|
| 976 |
+
"step": 78000
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 4.86,
|
| 980 |
+
"learning_rate": 1.5191412793944284e-05,
|
| 981 |
+
"loss": 0.0042,
|
| 982 |
+
"step": 78500
|
| 983 |
+
},
|
| 984 |
+
{
|
| 985 |
+
"epoch": 4.89,
|
| 986 |
+
"learning_rate": 1.5160389650679409e-05,
|
| 987 |
+
"loss": 0.0045,
|
| 988 |
+
"step": 79000
|
| 989 |
+
},
|
| 990 |
+
{
|
| 991 |
+
"epoch": 4.92,
|
| 992 |
+
"learning_rate": 1.5129366507414533e-05,
|
| 993 |
+
"loss": 0.004,
|
| 994 |
+
"step": 79500
|
| 995 |
+
},
|
| 996 |
+
{
|
| 997 |
+
"epoch": 4.95,
|
| 998 |
+
"learning_rate": 1.5098343364149657e-05,
|
| 999 |
+
"loss": 0.0037,
|
| 1000 |
+
"step": 80000
|
| 1001 |
+
},
|
| 1002 |
+
{
|
| 1003 |
+
"epoch": 4.98,
|
| 1004 |
+
"learning_rate": 1.506732022088478e-05,
|
| 1005 |
+
"loss": 0.0045,
|
| 1006 |
+
"step": 80500
|
| 1007 |
+
},
|
| 1008 |
+
{
|
| 1009 |
+
"epoch": 5.0,
|
| 1010 |
+
"eval_loss": 0.004868941381573677,
|
| 1011 |
+
"eval_runtime": 63.5068,
|
| 1012 |
+
"eval_samples_per_second": 113.137,
|
| 1013 |
+
"eval_steps_per_second": 7.086,
|
| 1014 |
+
"step": 80835
|
| 1015 |
+
},
|
| 1016 |
+
{
|
| 1017 |
+
"epoch": 5.01,
|
| 1018 |
+
"learning_rate": 1.5036297077619906e-05,
|
| 1019 |
+
"loss": 0.0038,
|
| 1020 |
+
"step": 81000
|
| 1021 |
+
},
|
| 1022 |
+
{
|
| 1023 |
+
"epoch": 5.04,
|
| 1024 |
+
"learning_rate": 1.5005273934355029e-05,
|
| 1025 |
+
"loss": 0.0035,
|
| 1026 |
+
"step": 81500
|
| 1027 |
+
},
|
| 1028 |
+
{
|
| 1029 |
+
"epoch": 5.07,
|
| 1030 |
+
"learning_rate": 1.4974250791090155e-05,
|
| 1031 |
+
"loss": 0.0035,
|
| 1032 |
+
"step": 82000
|
| 1033 |
+
},
|
| 1034 |
+
{
|
| 1035 |
+
"epoch": 5.1,
|
| 1036 |
+
"learning_rate": 1.4943227647825277e-05,
|
| 1037 |
+
"loss": 0.0037,
|
| 1038 |
+
"step": 82500
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"epoch": 5.13,
|
| 1042 |
+
"learning_rate": 1.4912204504560403e-05,
|
| 1043 |
+
"loss": 0.0031,
|
| 1044 |
+
"step": 83000
|
| 1045 |
+
},
|
| 1046 |
+
{
|
| 1047 |
+
"epoch": 5.16,
|
| 1048 |
+
"learning_rate": 1.4881181361295528e-05,
|
| 1049 |
+
"loss": 0.0035,
|
| 1050 |
+
"step": 83500
|
| 1051 |
+
},
|
| 1052 |
+
{
|
| 1053 |
+
"epoch": 5.2,
|
| 1054 |
+
"learning_rate": 1.4850158218030652e-05,
|
| 1055 |
+
"loss": 0.0037,
|
| 1056 |
+
"step": 84000
|
| 1057 |
+
},
|
| 1058 |
+
{
|
| 1059 |
+
"epoch": 5.23,
|
| 1060 |
+
"learning_rate": 1.4819135074765776e-05,
|
| 1061 |
+
"loss": 0.0033,
|
| 1062 |
+
"step": 84500
|
| 1063 |
+
},
|
| 1064 |
+
{
|
| 1065 |
+
"epoch": 5.26,
|
| 1066 |
+
"learning_rate": 1.47881119315009e-05,
|
| 1067 |
+
"loss": 0.0039,
|
| 1068 |
+
"step": 85000
|
| 1069 |
+
},
|
| 1070 |
+
{
|
| 1071 |
+
"epoch": 5.29,
|
| 1072 |
+
"learning_rate": 1.4757088788236025e-05,
|
| 1073 |
+
"loss": 0.0036,
|
| 1074 |
+
"step": 85500
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 5.32,
|
| 1078 |
+
"learning_rate": 1.4726065644971151e-05,
|
| 1079 |
+
"loss": 0.0039,
|
| 1080 |
+
"step": 86000
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 5.35,
|
| 1084 |
+
"learning_rate": 1.4695042501706274e-05,
|
| 1085 |
+
"loss": 0.0035,
|
| 1086 |
+
"step": 86500
|
| 1087 |
+
},
|
| 1088 |
+
{
|
| 1089 |
+
"epoch": 5.38,
|
| 1090 |
+
"learning_rate": 1.46640193584414e-05,
|
| 1091 |
+
"loss": 0.0034,
|
| 1092 |
+
"step": 87000
|
| 1093 |
+
},
|
| 1094 |
+
{
|
| 1095 |
+
"epoch": 5.41,
|
| 1096 |
+
"learning_rate": 1.4632996215176522e-05,
|
| 1097 |
+
"loss": 0.003,
|
| 1098 |
+
"step": 87500
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"epoch": 5.44,
|
| 1102 |
+
"learning_rate": 1.4601973071911648e-05,
|
| 1103 |
+
"loss": 0.0034,
|
| 1104 |
+
"step": 88000
|
| 1105 |
+
},
|
| 1106 |
+
{
|
| 1107 |
+
"epoch": 5.47,
|
| 1108 |
+
"learning_rate": 1.4570949928646771e-05,
|
| 1109 |
+
"loss": 0.0045,
|
| 1110 |
+
"step": 88500
|
| 1111 |
+
},
|
| 1112 |
+
{
|
| 1113 |
+
"epoch": 5.51,
|
| 1114 |
+
"learning_rate": 1.4539926785381897e-05,
|
| 1115 |
+
"loss": 0.0036,
|
| 1116 |
+
"step": 89000
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 5.54,
|
| 1120 |
+
"learning_rate": 1.450890364211702e-05,
|
| 1121 |
+
"loss": 0.0036,
|
| 1122 |
+
"step": 89500
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 5.57,
|
| 1126 |
+
"learning_rate": 1.4477880498852146e-05,
|
| 1127 |
+
"loss": 0.0037,
|
| 1128 |
+
"step": 90000
|
| 1129 |
+
},
|
| 1130 |
+
{
|
| 1131 |
+
"epoch": 5.6,
|
| 1132 |
+
"learning_rate": 1.444685735558727e-05,
|
| 1133 |
+
"loss": 0.0035,
|
| 1134 |
+
"step": 90500
|
| 1135 |
+
},
|
| 1136 |
+
{
|
| 1137 |
+
"epoch": 5.63,
|
| 1138 |
+
"learning_rate": 1.4415834212322393e-05,
|
| 1139 |
+
"loss": 0.0037,
|
| 1140 |
+
"step": 91000
|
| 1141 |
+
},
|
| 1142 |
+
{
|
| 1143 |
+
"epoch": 5.66,
|
| 1144 |
+
"learning_rate": 1.4384811069057519e-05,
|
| 1145 |
+
"loss": 0.0037,
|
| 1146 |
+
"step": 91500
|
| 1147 |
+
},
|
| 1148 |
+
{
|
| 1149 |
+
"epoch": 5.69,
|
| 1150 |
+
"learning_rate": 1.4353787925792641e-05,
|
| 1151 |
+
"loss": 0.0035,
|
| 1152 |
+
"step": 92000
|
| 1153 |
+
},
|
| 1154 |
+
{
|
| 1155 |
+
"epoch": 5.72,
|
| 1156 |
+
"learning_rate": 1.4322764782527767e-05,
|
| 1157 |
+
"loss": 0.0039,
|
| 1158 |
+
"step": 92500
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"epoch": 5.75,
|
| 1162 |
+
"learning_rate": 1.429174163926289e-05,
|
| 1163 |
+
"loss": 0.0038,
|
| 1164 |
+
"step": 93000
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 5.78,
|
| 1168 |
+
"learning_rate": 1.4260718495998016e-05,
|
| 1169 |
+
"loss": 0.003,
|
| 1170 |
+
"step": 93500
|
| 1171 |
+
},
|
| 1172 |
+
{
|
| 1173 |
+
"epoch": 5.81,
|
| 1174 |
+
"learning_rate": 1.4229695352733139e-05,
|
| 1175 |
+
"loss": 0.0033,
|
| 1176 |
+
"step": 94000
|
| 1177 |
+
},
|
| 1178 |
+
{
|
| 1179 |
+
"epoch": 5.85,
|
| 1180 |
+
"learning_rate": 1.4198672209468265e-05,
|
| 1181 |
+
"loss": 0.004,
|
| 1182 |
+
"step": 94500
|
| 1183 |
+
},
|
| 1184 |
+
{
|
| 1185 |
+
"epoch": 5.88,
|
| 1186 |
+
"learning_rate": 1.4167649066203389e-05,
|
| 1187 |
+
"loss": 0.0031,
|
| 1188 |
+
"step": 95000
|
| 1189 |
+
},
|
| 1190 |
+
{
|
| 1191 |
+
"epoch": 5.91,
|
| 1192 |
+
"learning_rate": 1.4136625922938513e-05,
|
| 1193 |
+
"loss": 0.0034,
|
| 1194 |
+
"step": 95500
|
| 1195 |
+
},
|
| 1196 |
+
{
|
| 1197 |
+
"epoch": 5.94,
|
| 1198 |
+
"learning_rate": 1.4105602779673638e-05,
|
| 1199 |
+
"loss": 0.0032,
|
| 1200 |
+
"step": 96000
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 5.97,
|
| 1204 |
+
"learning_rate": 1.4074579636408762e-05,
|
| 1205 |
+
"loss": 0.0036,
|
| 1206 |
+
"step": 96500
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"epoch": 6.0,
|
| 1210 |
+
"learning_rate": 1.4043556493143886e-05,
|
| 1211 |
+
"loss": 0.0035,
|
| 1212 |
+
"step": 97000
|
| 1213 |
+
},
|
| 1214 |
+
{
|
| 1215 |
+
"epoch": 6.0,
|
| 1216 |
+
"eval_loss": 0.004906239919364452,
|
| 1217 |
+
"eval_runtime": 63.3798,
|
| 1218 |
+
"eval_samples_per_second": 113.364,
|
| 1219 |
+
"eval_steps_per_second": 7.1,
|
| 1220 |
+
"step": 97002
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 6.03,
|
| 1224 |
+
"learning_rate": 1.4012533349879013e-05,
|
| 1225 |
+
"loss": 0.0029,
|
| 1226 |
+
"step": 97500
|
| 1227 |
+
},
|
| 1228 |
+
{
|
| 1229 |
+
"epoch": 6.06,
|
| 1230 |
+
"learning_rate": 1.3981510206614135e-05,
|
| 1231 |
+
"loss": 0.0028,
|
| 1232 |
+
"step": 98000
|
| 1233 |
+
},
|
| 1234 |
+
{
|
| 1235 |
+
"epoch": 6.09,
|
| 1236 |
+
"learning_rate": 1.3950487063349261e-05,
|
| 1237 |
+
"loss": 0.0026,
|
| 1238 |
+
"step": 98500
|
| 1239 |
+
},
|
| 1240 |
+
{
|
| 1241 |
+
"epoch": 6.12,
|
| 1242 |
+
"learning_rate": 1.3919463920084384e-05,
|
| 1243 |
+
"loss": 0.0028,
|
| 1244 |
+
"step": 99000
|
| 1245 |
+
},
|
| 1246 |
+
{
|
| 1247 |
+
"epoch": 6.15,
|
| 1248 |
+
"learning_rate": 1.388844077681951e-05,
|
| 1249 |
+
"loss": 0.0025,
|
| 1250 |
+
"step": 99500
|
| 1251 |
+
},
|
| 1252 |
+
{
|
| 1253 |
+
"epoch": 6.19,
|
| 1254 |
+
"learning_rate": 1.3857417633554633e-05,
|
| 1255 |
+
"loss": 0.0027,
|
| 1256 |
+
"step": 100000
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 6.22,
|
| 1260 |
+
"learning_rate": 1.3826394490289757e-05,
|
| 1261 |
+
"loss": 0.0029,
|
| 1262 |
+
"step": 100500
|
| 1263 |
+
},
|
| 1264 |
+
{
|
| 1265 |
+
"epoch": 6.25,
|
| 1266 |
+
"learning_rate": 1.3795371347024881e-05,
|
| 1267 |
+
"loss": 0.0029,
|
| 1268 |
+
"step": 101000
|
| 1269 |
+
},
|
| 1270 |
+
{
|
| 1271 |
+
"epoch": 6.28,
|
| 1272 |
+
"learning_rate": 1.3764348203760006e-05,
|
| 1273 |
+
"loss": 0.0027,
|
| 1274 |
+
"step": 101500
|
| 1275 |
+
},
|
| 1276 |
+
{
|
| 1277 |
+
"epoch": 6.31,
|
| 1278 |
+
"learning_rate": 1.373332506049513e-05,
|
| 1279 |
+
"loss": 0.0032,
|
| 1280 |
+
"step": 102000
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 6.34,
|
| 1284 |
+
"learning_rate": 1.3702301917230254e-05,
|
| 1285 |
+
"loss": 0.0031,
|
| 1286 |
+
"step": 102500
|
| 1287 |
+
},
|
| 1288 |
+
{
|
| 1289 |
+
"epoch": 6.37,
|
| 1290 |
+
"learning_rate": 1.367127877396538e-05,
|
| 1291 |
+
"loss": 0.0032,
|
| 1292 |
+
"step": 103000
|
| 1293 |
+
},
|
| 1294 |
+
{
|
| 1295 |
+
"epoch": 6.4,
|
| 1296 |
+
"learning_rate": 1.3640255630700503e-05,
|
| 1297 |
+
"loss": 0.0029,
|
| 1298 |
+
"step": 103500
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 6.43,
|
| 1302 |
+
"learning_rate": 1.3609232487435629e-05,
|
| 1303 |
+
"loss": 0.0031,
|
| 1304 |
+
"step": 104000
|
| 1305 |
+
},
|
| 1306 |
+
{
|
| 1307 |
+
"epoch": 6.46,
|
| 1308 |
+
"learning_rate": 1.3578209344170752e-05,
|
| 1309 |
+
"loss": 0.0029,
|
| 1310 |
+
"step": 104500
|
| 1311 |
+
},
|
| 1312 |
+
{
|
| 1313 |
+
"epoch": 6.49,
|
| 1314 |
+
"learning_rate": 1.3547186200905878e-05,
|
| 1315 |
+
"loss": 0.0031,
|
| 1316 |
+
"step": 105000
|
| 1317 |
+
},
|
| 1318 |
+
{
|
| 1319 |
+
"epoch": 6.53,
|
| 1320 |
+
"learning_rate": 1.3516163057641e-05,
|
| 1321 |
+
"loss": 0.003,
|
| 1322 |
+
"step": 105500
|
| 1323 |
+
},
|
| 1324 |
+
{
|
| 1325 |
+
"epoch": 6.56,
|
| 1326 |
+
"learning_rate": 1.3485139914376126e-05,
|
| 1327 |
+
"loss": 0.0033,
|
| 1328 |
+
"step": 106000
|
| 1329 |
+
},
|
| 1330 |
+
{
|
| 1331 |
+
"epoch": 6.59,
|
| 1332 |
+
"learning_rate": 1.3454116771111249e-05,
|
| 1333 |
+
"loss": 0.0028,
|
| 1334 |
+
"step": 106500
|
| 1335 |
+
},
|
| 1336 |
+
{
|
| 1337 |
+
"epoch": 6.62,
|
| 1338 |
+
"learning_rate": 1.3423093627846375e-05,
|
| 1339 |
+
"loss": 0.0029,
|
| 1340 |
+
"step": 107000
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"epoch": 6.65,
|
| 1344 |
+
"learning_rate": 1.33920704845815e-05,
|
| 1345 |
+
"loss": 0.003,
|
| 1346 |
+
"step": 107500
|
| 1347 |
+
},
|
| 1348 |
+
{
|
| 1349 |
+
"epoch": 6.68,
|
| 1350 |
+
"learning_rate": 1.3361047341316624e-05,
|
| 1351 |
+
"loss": 0.0027,
|
| 1352 |
+
"step": 108000
|
| 1353 |
+
},
|
| 1354 |
+
{
|
| 1355 |
+
"epoch": 6.71,
|
| 1356 |
+
"learning_rate": 1.3330024198051748e-05,
|
| 1357 |
+
"loss": 0.0029,
|
| 1358 |
+
"step": 108500
|
| 1359 |
+
},
|
| 1360 |
+
{
|
| 1361 |
+
"epoch": 6.74,
|
| 1362 |
+
"learning_rate": 1.3299001054786872e-05,
|
| 1363 |
+
"loss": 0.003,
|
| 1364 |
+
"step": 109000
|
| 1365 |
+
},
|
| 1366 |
+
{
|
| 1367 |
+
"epoch": 6.77,
|
| 1368 |
+
"learning_rate": 1.3267977911521997e-05,
|
| 1369 |
+
"loss": 0.003,
|
| 1370 |
+
"step": 109500
|
| 1371 |
+
},
|
| 1372 |
+
{
|
| 1373 |
+
"epoch": 6.8,
|
| 1374 |
+
"learning_rate": 1.3236954768257123e-05,
|
| 1375 |
+
"loss": 0.0031,
|
| 1376 |
+
"step": 110000
|
| 1377 |
+
},
|
| 1378 |
+
{
|
| 1379 |
+
"epoch": 6.83,
|
| 1380 |
+
"learning_rate": 1.3205931624992245e-05,
|
| 1381 |
+
"loss": 0.0027,
|
| 1382 |
+
"step": 110500
|
| 1383 |
+
},
|
| 1384 |
+
{
|
| 1385 |
+
"epoch": 6.87,
|
| 1386 |
+
"learning_rate": 1.3174908481727368e-05,
|
| 1387 |
+
"loss": 0.0034,
|
| 1388 |
+
"step": 111000
|
| 1389 |
+
},
|
| 1390 |
+
{
|
| 1391 |
+
"epoch": 6.9,
|
| 1392 |
+
"learning_rate": 1.3143885338462494e-05,
|
| 1393 |
+
"loss": 0.0029,
|
| 1394 |
+
"step": 111500
|
| 1395 |
+
},
|
| 1396 |
+
{
|
| 1397 |
+
"epoch": 6.93,
|
| 1398 |
+
"learning_rate": 1.3112862195197618e-05,
|
| 1399 |
+
"loss": 0.0028,
|
| 1400 |
+
"step": 112000
|
| 1401 |
+
},
|
| 1402 |
+
{
|
| 1403 |
+
"epoch": 6.96,
|
| 1404 |
+
"learning_rate": 1.3081839051932743e-05,
|
| 1405 |
+
"loss": 0.0027,
|
| 1406 |
+
"step": 112500
|
| 1407 |
+
},
|
| 1408 |
+
{
|
| 1409 |
+
"epoch": 6.99,
|
| 1410 |
+
"learning_rate": 1.3050815908667867e-05,
|
| 1411 |
+
"loss": 0.0032,
|
| 1412 |
+
"step": 113000
|
| 1413 |
+
},
|
| 1414 |
+
{
|
| 1415 |
+
"epoch": 7.0,
|
| 1416 |
+
"eval_loss": 0.005266720894724131,
|
| 1417 |
+
"eval_runtime": 63.4285,
|
| 1418 |
+
"eval_samples_per_second": 113.277,
|
| 1419 |
+
"eval_steps_per_second": 7.095,
|
| 1420 |
+
"step": 113169
|
| 1421 |
+
}
|
| 1422 |
+
],
|
| 1423 |
+
"max_steps": 323340,
|
| 1424 |
+
"num_train_epochs": 20,
|
| 1425 |
+
"total_flos": 3.38414646657024e+17,
|
| 1426 |
+
"trial_name": null,
|
| 1427 |
+
"trial_params": null
|
| 1428 |
+
}
|
large-1/checkpoint-113169/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a3edc56f0f0e1d7be1ce3265d43ba3e04b7d248bf3e6aeba8adfbe111cabeb09
|
| 3 |
+
size 4027
|
large-1/checkpoint-64668/config.json
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "google/mt5-large",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"MT5ForConditionalGeneration"
|
| 5 |
+
],
|
| 6 |
+
"d_ff": 2816,
|
| 7 |
+
"d_kv": 64,
|
| 8 |
+
"d_model": 1024,
|
| 9 |
+
"decoder_start_token_id": 0,
|
| 10 |
+
"dense_act_fn": "gelu_new",
|
| 11 |
+
"dropout_rate": 0.1,
|
| 12 |
+
"eos_token_id": 1,
|
| 13 |
+
"feed_forward_proj": "gated-gelu",
|
| 14 |
+
"initializer_factor": 1.0,
|
| 15 |
+
"is_encoder_decoder": true,
|
| 16 |
+
"is_gated_act": true,
|
| 17 |
+
"layer_norm_epsilon": 1e-06,
|
| 18 |
+
"model_type": "mt5",
|
| 19 |
+
"num_decoder_layers": 24,
|
| 20 |
+
"num_heads": 16,
|
| 21 |
+
"num_layers": 24,
|
| 22 |
+
"output_past": true,
|
| 23 |
+
"pad_token_id": 0,
|
| 24 |
+
"relative_attention_max_distance": 128,
|
| 25 |
+
"relative_attention_num_buckets": 32,
|
| 26 |
+
"tie_word_embeddings": false,
|
| 27 |
+
"tokenizer_class": "T5Tokenizer",
|
| 28 |
+
"torch_dtype": "float32",
|
| 29 |
+
"transformers_version": "4.29.1",
|
| 30 |
+
"use_cache": true,
|
| 31 |
+
"vocab_size": 250112
|
| 32 |
+
}
|
large-1/checkpoint-64668/generation_config.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"decoder_start_token_id": 0,
|
| 4 |
+
"eos_token_id": 1,
|
| 5 |
+
"pad_token_id": 0,
|
| 6 |
+
"transformers_version": "4.29.1"
|
| 7 |
+
}
|
large-1/checkpoint-64668/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d013a3d1cacdd0397c134b03717d26d5bf7ca0e632caccc018a7d883d85bdc14
|
| 3 |
+
size 9836994269
|
large-1/checkpoint-64668/pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:80f51a079ead19b7f0e9d82d46e113eee42e614b574c8b285b733727812a3be1
|
| 3 |
+
size 4918519065
|
large-1/checkpoint-64668/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:602ce66165617c434f695a1145e3f712d0699a10e357fbdc249db85bd503c117
|
| 3 |
+
size 14575
|
large-1/checkpoint-64668/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d1b0b5cad85af6807c555e0dff8fb82dfd97942c66e73906546fb2b06f96fc0e
|
| 3 |
+
size 627
|
large-1/checkpoint-64668/trainer_state.json
ADDED
|
@@ -0,0 +1,822 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.004835214000195265,
|
| 3 |
+
"best_model_checkpoint": "./results/large-1/checkpoint-64668",
|
| 4 |
+
"epoch": 4.0,
|
| 5 |
+
"global_step": 64668,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.03,
|
| 12 |
+
"learning_rate": 1e-05,
|
| 13 |
+
"loss": 29.3333,
|
| 14 |
+
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.06,
|
| 18 |
+
"learning_rate": 2e-05,
|
| 19 |
+
"loss": 12.5737,
|
| 20 |
+
"step": 1000
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.09,
|
| 24 |
+
"learning_rate": 1.9968976856735126e-05,
|
| 25 |
+
"loss": 2.3813,
|
| 26 |
+
"step": 1500
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.12,
|
| 30 |
+
"learning_rate": 1.993795371347025e-05,
|
| 31 |
+
"loss": 0.2316,
|
| 32 |
+
"step": 2000
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.15,
|
| 36 |
+
"learning_rate": 1.9906930570205375e-05,
|
| 37 |
+
"loss": 0.099,
|
| 38 |
+
"step": 2500
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.19,
|
| 42 |
+
"learning_rate": 1.98759074269405e-05,
|
| 43 |
+
"loss": 0.0608,
|
| 44 |
+
"step": 3000
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.22,
|
| 48 |
+
"learning_rate": 1.9844884283675623e-05,
|
| 49 |
+
"loss": 0.0565,
|
| 50 |
+
"step": 3500
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.25,
|
| 54 |
+
"learning_rate": 1.9813861140410748e-05,
|
| 55 |
+
"loss": 0.0435,
|
| 56 |
+
"step": 4000
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.28,
|
| 60 |
+
"learning_rate": 1.9782837997145872e-05,
|
| 61 |
+
"loss": 0.0354,
|
| 62 |
+
"step": 4500
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.31,
|
| 66 |
+
"learning_rate": 1.9751814853880996e-05,
|
| 67 |
+
"loss": 0.0339,
|
| 68 |
+
"step": 5000
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.34,
|
| 72 |
+
"learning_rate": 1.972079171061612e-05,
|
| 73 |
+
"loss": 0.0294,
|
| 74 |
+
"step": 5500
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.37,
|
| 78 |
+
"learning_rate": 1.9689768567351245e-05,
|
| 79 |
+
"loss": 0.035,
|
| 80 |
+
"step": 6000
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.4,
|
| 84 |
+
"learning_rate": 1.965874542408637e-05,
|
| 85 |
+
"loss": 0.0515,
|
| 86 |
+
"step": 6500
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.43,
|
| 90 |
+
"learning_rate": 1.9627722280821494e-05,
|
| 91 |
+
"loss": 0.0232,
|
| 92 |
+
"step": 7000
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.46,
|
| 96 |
+
"learning_rate": 1.9596699137556618e-05,
|
| 97 |
+
"loss": 0.0349,
|
| 98 |
+
"step": 7500
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.49,
|
| 102 |
+
"learning_rate": 1.9565675994291742e-05,
|
| 103 |
+
"loss": 0.0226,
|
| 104 |
+
"step": 8000
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.53,
|
| 108 |
+
"learning_rate": 1.9534652851026867e-05,
|
| 109 |
+
"loss": 0.0215,
|
| 110 |
+
"step": 8500
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 0.56,
|
| 114 |
+
"learning_rate": 1.9503629707761994e-05,
|
| 115 |
+
"loss": 0.0204,
|
| 116 |
+
"step": 9000
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.59,
|
| 120 |
+
"learning_rate": 1.9472606564497115e-05,
|
| 121 |
+
"loss": 0.0192,
|
| 122 |
+
"step": 9500
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.62,
|
| 126 |
+
"learning_rate": 1.9441583421232243e-05,
|
| 127 |
+
"loss": 0.0194,
|
| 128 |
+
"step": 10000
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.65,
|
| 132 |
+
"learning_rate": 1.9410560277967364e-05,
|
| 133 |
+
"loss": 0.0179,
|
| 134 |
+
"step": 10500
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 0.68,
|
| 138 |
+
"learning_rate": 1.937953713470249e-05,
|
| 139 |
+
"loss": 0.017,
|
| 140 |
+
"step": 11000
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 0.71,
|
| 144 |
+
"learning_rate": 1.9348513991437613e-05,
|
| 145 |
+
"loss": 0.0226,
|
| 146 |
+
"step": 11500
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 0.74,
|
| 150 |
+
"learning_rate": 1.9317490848172737e-05,
|
| 151 |
+
"loss": 0.016,
|
| 152 |
+
"step": 12000
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 0.77,
|
| 156 |
+
"learning_rate": 1.928646770490786e-05,
|
| 157 |
+
"loss": 0.0154,
|
| 158 |
+
"step": 12500
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 0.8,
|
| 162 |
+
"learning_rate": 1.9255444561642986e-05,
|
| 163 |
+
"loss": 0.0157,
|
| 164 |
+
"step": 13000
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.84,
|
| 168 |
+
"learning_rate": 1.9224421418378113e-05,
|
| 169 |
+
"loss": 0.0139,
|
| 170 |
+
"step": 13500
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.87,
|
| 174 |
+
"learning_rate": 1.9193398275113234e-05,
|
| 175 |
+
"loss": 0.0129,
|
| 176 |
+
"step": 14000
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 0.9,
|
| 180 |
+
"learning_rate": 1.9162375131848362e-05,
|
| 181 |
+
"loss": 0.0134,
|
| 182 |
+
"step": 14500
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 0.93,
|
| 186 |
+
"learning_rate": 1.9131351988583483e-05,
|
| 187 |
+
"loss": 0.0134,
|
| 188 |
+
"step": 15000
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 0.96,
|
| 192 |
+
"learning_rate": 1.910032884531861e-05,
|
| 193 |
+
"loss": 0.0133,
|
| 194 |
+
"step": 15500
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 0.99,
|
| 198 |
+
"learning_rate": 1.9069305702053732e-05,
|
| 199 |
+
"loss": 0.0133,
|
| 200 |
+
"step": 16000
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 1.0,
|
| 204 |
+
"eval_loss": 0.007159320637583733,
|
| 205 |
+
"eval_runtime": 63.5558,
|
| 206 |
+
"eval_samples_per_second": 113.05,
|
| 207 |
+
"eval_steps_per_second": 7.08,
|
| 208 |
+
"step": 16167
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 1.02,
|
| 212 |
+
"learning_rate": 1.903828255878886e-05,
|
| 213 |
+
"loss": 0.0118,
|
| 214 |
+
"step": 16500
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"epoch": 1.05,
|
| 218 |
+
"learning_rate": 1.900725941552398e-05,
|
| 219 |
+
"loss": 0.0114,
|
| 220 |
+
"step": 17000
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 1.08,
|
| 224 |
+
"learning_rate": 1.8976236272259108e-05,
|
| 225 |
+
"loss": 0.0115,
|
| 226 |
+
"step": 17500
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 1.11,
|
| 230 |
+
"learning_rate": 1.8945213128994233e-05,
|
| 231 |
+
"loss": 0.0115,
|
| 232 |
+
"step": 18000
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"epoch": 1.14,
|
| 236 |
+
"learning_rate": 1.8914189985729357e-05,
|
| 237 |
+
"loss": 0.0118,
|
| 238 |
+
"step": 18500
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"epoch": 1.18,
|
| 242 |
+
"learning_rate": 1.888316684246448e-05,
|
| 243 |
+
"loss": 0.0119,
|
| 244 |
+
"step": 19000
|
| 245 |
+
},
|
| 246 |
+
{
|
| 247 |
+
"epoch": 1.21,
|
| 248 |
+
"learning_rate": 1.8852143699199606e-05,
|
| 249 |
+
"loss": 0.0117,
|
| 250 |
+
"step": 19500
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 1.24,
|
| 254 |
+
"learning_rate": 1.882112055593473e-05,
|
| 255 |
+
"loss": 0.0113,
|
| 256 |
+
"step": 20000
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 1.27,
|
| 260 |
+
"learning_rate": 1.8790097412669854e-05,
|
| 261 |
+
"loss": 0.0102,
|
| 262 |
+
"step": 20500
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 1.3,
|
| 266 |
+
"learning_rate": 1.875907426940498e-05,
|
| 267 |
+
"loss": 0.0109,
|
| 268 |
+
"step": 21000
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 1.33,
|
| 272 |
+
"learning_rate": 1.87280511261401e-05,
|
| 273 |
+
"loss": 0.0096,
|
| 274 |
+
"step": 21500
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 1.36,
|
| 278 |
+
"learning_rate": 1.8697027982875227e-05,
|
| 279 |
+
"loss": 0.0105,
|
| 280 |
+
"step": 22000
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 1.39,
|
| 284 |
+
"learning_rate": 1.866600483961035e-05,
|
| 285 |
+
"loss": 0.0093,
|
| 286 |
+
"step": 22500
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 1.42,
|
| 290 |
+
"learning_rate": 1.8634981696345476e-05,
|
| 291 |
+
"loss": 0.0096,
|
| 292 |
+
"step": 23000
|
| 293 |
+
},
|
| 294 |
+
{
|
| 295 |
+
"epoch": 1.45,
|
| 296 |
+
"learning_rate": 1.86039585530806e-05,
|
| 297 |
+
"loss": 0.0091,
|
| 298 |
+
"step": 23500
|
| 299 |
+
},
|
| 300 |
+
{
|
| 301 |
+
"epoch": 1.48,
|
| 302 |
+
"learning_rate": 1.8572935409815725e-05,
|
| 303 |
+
"loss": 0.0099,
|
| 304 |
+
"step": 24000
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 1.52,
|
| 308 |
+
"learning_rate": 1.854191226655085e-05,
|
| 309 |
+
"loss": 0.009,
|
| 310 |
+
"step": 24500
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 1.55,
|
| 314 |
+
"learning_rate": 1.8510889123285973e-05,
|
| 315 |
+
"loss": 0.0097,
|
| 316 |
+
"step": 25000
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 1.58,
|
| 320 |
+
"learning_rate": 1.8479865980021098e-05,
|
| 321 |
+
"loss": 0.0089,
|
| 322 |
+
"step": 25500
|
| 323 |
+
},
|
| 324 |
+
{
|
| 325 |
+
"epoch": 1.61,
|
| 326 |
+
"learning_rate": 1.8448842836756222e-05,
|
| 327 |
+
"loss": 0.0097,
|
| 328 |
+
"step": 26000
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"epoch": 1.64,
|
| 332 |
+
"learning_rate": 1.8417819693491346e-05,
|
| 333 |
+
"loss": 0.0099,
|
| 334 |
+
"step": 26500
|
| 335 |
+
},
|
| 336 |
+
{
|
| 337 |
+
"epoch": 1.67,
|
| 338 |
+
"learning_rate": 1.838679655022647e-05,
|
| 339 |
+
"loss": 0.0092,
|
| 340 |
+
"step": 27000
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"epoch": 1.7,
|
| 344 |
+
"learning_rate": 1.8355773406961595e-05,
|
| 345 |
+
"loss": 0.0094,
|
| 346 |
+
"step": 27500
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 1.73,
|
| 350 |
+
"learning_rate": 1.832475026369672e-05,
|
| 351 |
+
"loss": 0.0087,
|
| 352 |
+
"step": 28000
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 1.76,
|
| 356 |
+
"learning_rate": 1.8293727120431844e-05,
|
| 357 |
+
"loss": 0.0091,
|
| 358 |
+
"step": 28500
|
| 359 |
+
},
|
| 360 |
+
{
|
| 361 |
+
"epoch": 1.79,
|
| 362 |
+
"learning_rate": 1.8262703977166968e-05,
|
| 363 |
+
"loss": 0.0098,
|
| 364 |
+
"step": 29000
|
| 365 |
+
},
|
| 366 |
+
{
|
| 367 |
+
"epoch": 1.82,
|
| 368 |
+
"learning_rate": 1.8231680833902092e-05,
|
| 369 |
+
"loss": 0.0093,
|
| 370 |
+
"step": 29500
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 1.86,
|
| 374 |
+
"learning_rate": 1.8200657690637217e-05,
|
| 375 |
+
"loss": 0.0088,
|
| 376 |
+
"step": 30000
|
| 377 |
+
},
|
| 378 |
+
{
|
| 379 |
+
"epoch": 1.89,
|
| 380 |
+
"learning_rate": 1.816963454737234e-05,
|
| 381 |
+
"loss": 0.008,
|
| 382 |
+
"step": 30500
|
| 383 |
+
},
|
| 384 |
+
{
|
| 385 |
+
"epoch": 1.92,
|
| 386 |
+
"learning_rate": 1.8138611404107465e-05,
|
| 387 |
+
"loss": 0.0088,
|
| 388 |
+
"step": 31000
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 1.95,
|
| 392 |
+
"learning_rate": 1.810758826084259e-05,
|
| 393 |
+
"loss": 0.0084,
|
| 394 |
+
"step": 31500
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 1.98,
|
| 398 |
+
"learning_rate": 1.8076565117577714e-05,
|
| 399 |
+
"loss": 0.0087,
|
| 400 |
+
"step": 32000
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"epoch": 2.0,
|
| 404 |
+
"eval_loss": 0.005626102443784475,
|
| 405 |
+
"eval_runtime": 63.5514,
|
| 406 |
+
"eval_samples_per_second": 113.058,
|
| 407 |
+
"eval_steps_per_second": 7.081,
|
| 408 |
+
"step": 32334
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 2.01,
|
| 412 |
+
"learning_rate": 1.804554197431284e-05,
|
| 413 |
+
"loss": 0.0081,
|
| 414 |
+
"step": 32500
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 2.04,
|
| 418 |
+
"learning_rate": 1.8014518831047963e-05,
|
| 419 |
+
"loss": 0.007,
|
| 420 |
+
"step": 33000
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 2.07,
|
| 424 |
+
"learning_rate": 1.7983495687783087e-05,
|
| 425 |
+
"loss": 0.0072,
|
| 426 |
+
"step": 33500
|
| 427 |
+
},
|
| 428 |
+
{
|
| 429 |
+
"epoch": 2.1,
|
| 430 |
+
"learning_rate": 1.795247254451821e-05,
|
| 431 |
+
"loss": 0.0069,
|
| 432 |
+
"step": 34000
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 2.13,
|
| 436 |
+
"learning_rate": 1.7921449401253336e-05,
|
| 437 |
+
"loss": 0.0072,
|
| 438 |
+
"step": 34500
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 2.16,
|
| 442 |
+
"learning_rate": 1.789042625798846e-05,
|
| 443 |
+
"loss": 0.0067,
|
| 444 |
+
"step": 35000
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 2.2,
|
| 448 |
+
"learning_rate": 1.7859403114723584e-05,
|
| 449 |
+
"loss": 0.007,
|
| 450 |
+
"step": 35500
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 2.23,
|
| 454 |
+
"learning_rate": 1.782837997145871e-05,
|
| 455 |
+
"loss": 0.0072,
|
| 456 |
+
"step": 36000
|
| 457 |
+
},
|
| 458 |
+
{
|
| 459 |
+
"epoch": 2.26,
|
| 460 |
+
"learning_rate": 1.7797356828193833e-05,
|
| 461 |
+
"loss": 0.0074,
|
| 462 |
+
"step": 36500
|
| 463 |
+
},
|
| 464 |
+
{
|
| 465 |
+
"epoch": 2.29,
|
| 466 |
+
"learning_rate": 1.7766333684928957e-05,
|
| 467 |
+
"loss": 0.0075,
|
| 468 |
+
"step": 37000
|
| 469 |
+
},
|
| 470 |
+
{
|
| 471 |
+
"epoch": 2.32,
|
| 472 |
+
"learning_rate": 1.7735310541664085e-05,
|
| 473 |
+
"loss": 0.0072,
|
| 474 |
+
"step": 37500
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 2.35,
|
| 478 |
+
"learning_rate": 1.7704287398399206e-05,
|
| 479 |
+
"loss": 0.0061,
|
| 480 |
+
"step": 38000
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 2.38,
|
| 484 |
+
"learning_rate": 1.7673264255134334e-05,
|
| 485 |
+
"loss": 0.0071,
|
| 486 |
+
"step": 38500
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 2.41,
|
| 490 |
+
"learning_rate": 1.7642241111869455e-05,
|
| 491 |
+
"loss": 0.0074,
|
| 492 |
+
"step": 39000
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 2.44,
|
| 496 |
+
"learning_rate": 1.7611217968604582e-05,
|
| 497 |
+
"loss": 0.0072,
|
| 498 |
+
"step": 39500
|
| 499 |
+
},
|
| 500 |
+
{
|
| 501 |
+
"epoch": 2.47,
|
| 502 |
+
"learning_rate": 1.7580194825339703e-05,
|
| 503 |
+
"loss": 0.0072,
|
| 504 |
+
"step": 40000
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 2.51,
|
| 508 |
+
"learning_rate": 1.754917168207483e-05,
|
| 509 |
+
"loss": 0.0075,
|
| 510 |
+
"step": 40500
|
| 511 |
+
},
|
| 512 |
+
{
|
| 513 |
+
"epoch": 2.54,
|
| 514 |
+
"learning_rate": 1.7518148538809952e-05,
|
| 515 |
+
"loss": 0.0069,
|
| 516 |
+
"step": 41000
|
| 517 |
+
},
|
| 518 |
+
{
|
| 519 |
+
"epoch": 2.57,
|
| 520 |
+
"learning_rate": 1.7487125395545076e-05,
|
| 521 |
+
"loss": 0.007,
|
| 522 |
+
"step": 41500
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 2.6,
|
| 526 |
+
"learning_rate": 1.7456102252280204e-05,
|
| 527 |
+
"loss": 0.0058,
|
| 528 |
+
"step": 42000
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 2.63,
|
| 532 |
+
"learning_rate": 1.7425079109015325e-05,
|
| 533 |
+
"loss": 0.0064,
|
| 534 |
+
"step": 42500
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 2.66,
|
| 538 |
+
"learning_rate": 1.7394055965750453e-05,
|
| 539 |
+
"loss": 0.0067,
|
| 540 |
+
"step": 43000
|
| 541 |
+
},
|
| 542 |
+
{
|
| 543 |
+
"epoch": 2.69,
|
| 544 |
+
"learning_rate": 1.7363032822485574e-05,
|
| 545 |
+
"loss": 0.0062,
|
| 546 |
+
"step": 43500
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 2.72,
|
| 550 |
+
"learning_rate": 1.73320096792207e-05,
|
| 551 |
+
"loss": 0.0066,
|
| 552 |
+
"step": 44000
|
| 553 |
+
},
|
| 554 |
+
{
|
| 555 |
+
"epoch": 2.75,
|
| 556 |
+
"learning_rate": 1.7300986535955822e-05,
|
| 557 |
+
"loss": 0.0066,
|
| 558 |
+
"step": 44500
|
| 559 |
+
},
|
| 560 |
+
{
|
| 561 |
+
"epoch": 2.78,
|
| 562 |
+
"learning_rate": 1.726996339269095e-05,
|
| 563 |
+
"loss": 0.0071,
|
| 564 |
+
"step": 45000
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 2.81,
|
| 568 |
+
"learning_rate": 1.723894024942607e-05,
|
| 569 |
+
"loss": 0.0065,
|
| 570 |
+
"step": 45500
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 2.85,
|
| 574 |
+
"learning_rate": 1.72079171061612e-05,
|
| 575 |
+
"loss": 0.0065,
|
| 576 |
+
"step": 46000
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 2.88,
|
| 580 |
+
"learning_rate": 1.7176893962896323e-05,
|
| 581 |
+
"loss": 0.0065,
|
| 582 |
+
"step": 46500
|
| 583 |
+
},
|
| 584 |
+
{
|
| 585 |
+
"epoch": 2.91,
|
| 586 |
+
"learning_rate": 1.7145870819631448e-05,
|
| 587 |
+
"loss": 0.0062,
|
| 588 |
+
"step": 47000
|
| 589 |
+
},
|
| 590 |
+
{
|
| 591 |
+
"epoch": 2.94,
|
| 592 |
+
"learning_rate": 1.7114847676366572e-05,
|
| 593 |
+
"loss": 0.0075,
|
| 594 |
+
"step": 47500
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 2.97,
|
| 598 |
+
"learning_rate": 1.7083824533101696e-05,
|
| 599 |
+
"loss": 0.0064,
|
| 600 |
+
"step": 48000
|
| 601 |
+
},
|
| 602 |
+
{
|
| 603 |
+
"epoch": 3.0,
|
| 604 |
+
"learning_rate": 1.705280138983682e-05,
|
| 605 |
+
"loss": 0.0063,
|
| 606 |
+
"step": 48500
|
| 607 |
+
},
|
| 608 |
+
{
|
| 609 |
+
"epoch": 3.0,
|
| 610 |
+
"eval_loss": 0.005162048153579235,
|
| 611 |
+
"eval_runtime": 63.5102,
|
| 612 |
+
"eval_samples_per_second": 113.132,
|
| 613 |
+
"eval_steps_per_second": 7.085,
|
| 614 |
+
"step": 48501
|
| 615 |
+
},
|
| 616 |
+
{
|
| 617 |
+
"epoch": 3.03,
|
| 618 |
+
"learning_rate": 1.7021778246571945e-05,
|
| 619 |
+
"loss": 0.0055,
|
| 620 |
+
"step": 49000
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 3.06,
|
| 624 |
+
"learning_rate": 1.699075510330707e-05,
|
| 625 |
+
"loss": 0.0055,
|
| 626 |
+
"step": 49500
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 3.09,
|
| 630 |
+
"learning_rate": 1.6959731960042194e-05,
|
| 631 |
+
"loss": 0.0059,
|
| 632 |
+
"step": 50000
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 3.12,
|
| 636 |
+
"learning_rate": 1.6928708816777318e-05,
|
| 637 |
+
"loss": 0.0052,
|
| 638 |
+
"step": 50500
|
| 639 |
+
},
|
| 640 |
+
{
|
| 641 |
+
"epoch": 3.15,
|
| 642 |
+
"learning_rate": 1.6897685673512442e-05,
|
| 643 |
+
"loss": 0.0053,
|
| 644 |
+
"step": 51000
|
| 645 |
+
},
|
| 646 |
+
{
|
| 647 |
+
"epoch": 3.19,
|
| 648 |
+
"learning_rate": 1.6866662530247567e-05,
|
| 649 |
+
"loss": 0.005,
|
| 650 |
+
"step": 51500
|
| 651 |
+
},
|
| 652 |
+
{
|
| 653 |
+
"epoch": 3.22,
|
| 654 |
+
"learning_rate": 1.683563938698269e-05,
|
| 655 |
+
"loss": 0.0056,
|
| 656 |
+
"step": 52000
|
| 657 |
+
},
|
| 658 |
+
{
|
| 659 |
+
"epoch": 3.25,
|
| 660 |
+
"learning_rate": 1.6804616243717815e-05,
|
| 661 |
+
"loss": 0.0051,
|
| 662 |
+
"step": 52500
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 3.28,
|
| 666 |
+
"learning_rate": 1.677359310045294e-05,
|
| 667 |
+
"loss": 0.0053,
|
| 668 |
+
"step": 53000
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 3.31,
|
| 672 |
+
"learning_rate": 1.6742569957188064e-05,
|
| 673 |
+
"loss": 0.0053,
|
| 674 |
+
"step": 53500
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 3.34,
|
| 678 |
+
"learning_rate": 1.6711546813923188e-05,
|
| 679 |
+
"loss": 0.0051,
|
| 680 |
+
"step": 54000
|
| 681 |
+
},
|
| 682 |
+
{
|
| 683 |
+
"epoch": 3.37,
|
| 684 |
+
"learning_rate": 1.6680523670658313e-05,
|
| 685 |
+
"loss": 0.0056,
|
| 686 |
+
"step": 54500
|
| 687 |
+
},
|
| 688 |
+
{
|
| 689 |
+
"epoch": 3.4,
|
| 690 |
+
"learning_rate": 1.6649500527393437e-05,
|
| 691 |
+
"loss": 0.0068,
|
| 692 |
+
"step": 55000
|
| 693 |
+
},
|
| 694 |
+
{
|
| 695 |
+
"epoch": 3.43,
|
| 696 |
+
"learning_rate": 1.661847738412856e-05,
|
| 697 |
+
"loss": 0.0054,
|
| 698 |
+
"step": 55500
|
| 699 |
+
},
|
| 700 |
+
{
|
| 701 |
+
"epoch": 3.46,
|
| 702 |
+
"learning_rate": 1.6587454240863686e-05,
|
| 703 |
+
"loss": 0.0055,
|
| 704 |
+
"step": 56000
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 3.49,
|
| 708 |
+
"learning_rate": 1.655643109759881e-05,
|
| 709 |
+
"loss": 0.0056,
|
| 710 |
+
"step": 56500
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 3.53,
|
| 714 |
+
"learning_rate": 1.6525407954333934e-05,
|
| 715 |
+
"loss": 0.0053,
|
| 716 |
+
"step": 57000
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 3.56,
|
| 720 |
+
"learning_rate": 1.649438481106906e-05,
|
| 721 |
+
"loss": 0.0051,
|
| 722 |
+
"step": 57500
|
| 723 |
+
},
|
| 724 |
+
{
|
| 725 |
+
"epoch": 3.59,
|
| 726 |
+
"learning_rate": 1.6463361667804183e-05,
|
| 727 |
+
"loss": 0.005,
|
| 728 |
+
"step": 58000
|
| 729 |
+
},
|
| 730 |
+
{
|
| 731 |
+
"epoch": 3.62,
|
| 732 |
+
"learning_rate": 1.6432338524539307e-05,
|
| 733 |
+
"loss": 0.0055,
|
| 734 |
+
"step": 58500
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 3.65,
|
| 738 |
+
"learning_rate": 1.640131538127443e-05,
|
| 739 |
+
"loss": 0.0048,
|
| 740 |
+
"step": 59000
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 3.68,
|
| 744 |
+
"learning_rate": 1.6370292238009556e-05,
|
| 745 |
+
"loss": 0.0052,
|
| 746 |
+
"step": 59500
|
| 747 |
+
},
|
| 748 |
+
{
|
| 749 |
+
"epoch": 3.71,
|
| 750 |
+
"learning_rate": 1.633926909474468e-05,
|
| 751 |
+
"loss": 0.0048,
|
| 752 |
+
"step": 60000
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 3.74,
|
| 756 |
+
"learning_rate": 1.6308245951479805e-05,
|
| 757 |
+
"loss": 0.0049,
|
| 758 |
+
"step": 60500
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 3.77,
|
| 762 |
+
"learning_rate": 1.627722280821493e-05,
|
| 763 |
+
"loss": 0.0054,
|
| 764 |
+
"step": 61000
|
| 765 |
+
},
|
| 766 |
+
{
|
| 767 |
+
"epoch": 3.8,
|
| 768 |
+
"learning_rate": 1.6246199664950053e-05,
|
| 769 |
+
"loss": 0.0052,
|
| 770 |
+
"step": 61500
|
| 771 |
+
},
|
| 772 |
+
{
|
| 773 |
+
"epoch": 3.83,
|
| 774 |
+
"learning_rate": 1.6215176521685178e-05,
|
| 775 |
+
"loss": 0.0053,
|
| 776 |
+
"step": 62000
|
| 777 |
+
},
|
| 778 |
+
{
|
| 779 |
+
"epoch": 3.87,
|
| 780 |
+
"learning_rate": 1.6184153378420302e-05,
|
| 781 |
+
"loss": 0.0052,
|
| 782 |
+
"step": 62500
|
| 783 |
+
},
|
| 784 |
+
{
|
| 785 |
+
"epoch": 3.9,
|
| 786 |
+
"learning_rate": 1.6153130235155426e-05,
|
| 787 |
+
"loss": 0.0053,
|
| 788 |
+
"step": 63000
|
| 789 |
+
},
|
| 790 |
+
{
|
| 791 |
+
"epoch": 3.93,
|
| 792 |
+
"learning_rate": 1.612210709189055e-05,
|
| 793 |
+
"loss": 0.0052,
|
| 794 |
+
"step": 63500
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 3.96,
|
| 798 |
+
"learning_rate": 1.6091083948625675e-05,
|
| 799 |
+
"loss": 0.0052,
|
| 800 |
+
"step": 64000
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 3.99,
|
| 804 |
+
"learning_rate": 1.60600608053608e-05,
|
| 805 |
+
"loss": 0.0054,
|
| 806 |
+
"step": 64500
|
| 807 |
+
},
|
| 808 |
+
{
|
| 809 |
+
"epoch": 4.0,
|
| 810 |
+
"eval_loss": 0.004835214000195265,
|
| 811 |
+
"eval_runtime": 63.5993,
|
| 812 |
+
"eval_samples_per_second": 112.973,
|
| 813 |
+
"eval_steps_per_second": 7.076,
|
| 814 |
+
"step": 64668
|
| 815 |
+
}
|
| 816 |
+
],
|
| 817 |
+
"max_steps": 323340,
|
| 818 |
+
"num_train_epochs": 20,
|
| 819 |
+
"total_flos": 1.93379798089728e+17,
|
| 820 |
+
"trial_name": null,
|
| 821 |
+
"trial_params": null
|
| 822 |
+
}
|
large-1/checkpoint-64668/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a3edc56f0f0e1d7be1ce3265d43ba3e04b7d248bf3e6aeba8adfbe111cabeb09
|
| 3 |
+
size 4027
|
large-1/checkpoint-97002/config.json
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "google/mt5-large",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"MT5ForConditionalGeneration"
|
| 5 |
+
],
|
| 6 |
+
"d_ff": 2816,
|
| 7 |
+
"d_kv": 64,
|
| 8 |
+
"d_model": 1024,
|
| 9 |
+
"decoder_start_token_id": 0,
|
| 10 |
+
"dense_act_fn": "gelu_new",
|
| 11 |
+
"dropout_rate": 0.1,
|
| 12 |
+
"eos_token_id": 1,
|
| 13 |
+
"feed_forward_proj": "gated-gelu",
|
| 14 |
+
"initializer_factor": 1.0,
|
| 15 |
+
"is_encoder_decoder": true,
|
| 16 |
+
"is_gated_act": true,
|
| 17 |
+
"layer_norm_epsilon": 1e-06,
|
| 18 |
+
"model_type": "mt5",
|
| 19 |
+
"num_decoder_layers": 24,
|
| 20 |
+
"num_heads": 16,
|
| 21 |
+
"num_layers": 24,
|
| 22 |
+
"output_past": true,
|
| 23 |
+
"pad_token_id": 0,
|
| 24 |
+
"relative_attention_max_distance": 128,
|
| 25 |
+
"relative_attention_num_buckets": 32,
|
| 26 |
+
"tie_word_embeddings": false,
|
| 27 |
+
"tokenizer_class": "T5Tokenizer",
|
| 28 |
+
"torch_dtype": "float32",
|
| 29 |
+
"transformers_version": "4.29.1",
|
| 30 |
+
"use_cache": true,
|
| 31 |
+
"vocab_size": 250112
|
| 32 |
+
}
|
large-1/checkpoint-97002/generation_config.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"decoder_start_token_id": 0,
|
| 4 |
+
"eos_token_id": 1,
|
| 5 |
+
"pad_token_id": 0,
|
| 6 |
+
"transformers_version": "4.29.1"
|
| 7 |
+
}
|
large-1/checkpoint-97002/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:97bc9add4003432e4b73fbf5195365630a1e94653a8a6299f12887ab8f518f8f
|
| 3 |
+
size 9836995421
|
large-1/checkpoint-97002/pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bde965fc31b963bf99a38ce54b1ab687c2386e8b45f342fa07e82f61e2c2bf0d
|
| 3 |
+
size 4918519065
|
large-1/checkpoint-97002/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c6d2c3e848b2aa31b46401d9c34136b5d405f81068653c8c796ae9973715d12f
|
| 3 |
+
size 14575
|
large-1/checkpoint-97002/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4d549102eb8db911ba7a9c667c760cbf641146127e2cc87d0dbbf7e01a68f02d
|
| 3 |
+
size 627
|
large-1/checkpoint-97002/trainer_state.json
ADDED
|
@@ -0,0 +1,1228 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.004835214000195265,
|
| 3 |
+
"best_model_checkpoint": "./results/large-1/checkpoint-64668",
|
| 4 |
+
"epoch": 6.0,
|
| 5 |
+
"global_step": 97002,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.03,
|
| 12 |
+
"learning_rate": 1e-05,
|
| 13 |
+
"loss": 29.3333,
|
| 14 |
+
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.06,
|
| 18 |
+
"learning_rate": 2e-05,
|
| 19 |
+
"loss": 12.5737,
|
| 20 |
+
"step": 1000
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.09,
|
| 24 |
+
"learning_rate": 1.9968976856735126e-05,
|
| 25 |
+
"loss": 2.3813,
|
| 26 |
+
"step": 1500
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.12,
|
| 30 |
+
"learning_rate": 1.993795371347025e-05,
|
| 31 |
+
"loss": 0.2316,
|
| 32 |
+
"step": 2000
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.15,
|
| 36 |
+
"learning_rate": 1.9906930570205375e-05,
|
| 37 |
+
"loss": 0.099,
|
| 38 |
+
"step": 2500
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.19,
|
| 42 |
+
"learning_rate": 1.98759074269405e-05,
|
| 43 |
+
"loss": 0.0608,
|
| 44 |
+
"step": 3000
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.22,
|
| 48 |
+
"learning_rate": 1.9844884283675623e-05,
|
| 49 |
+
"loss": 0.0565,
|
| 50 |
+
"step": 3500
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.25,
|
| 54 |
+
"learning_rate": 1.9813861140410748e-05,
|
| 55 |
+
"loss": 0.0435,
|
| 56 |
+
"step": 4000
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.28,
|
| 60 |
+
"learning_rate": 1.9782837997145872e-05,
|
| 61 |
+
"loss": 0.0354,
|
| 62 |
+
"step": 4500
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.31,
|
| 66 |
+
"learning_rate": 1.9751814853880996e-05,
|
| 67 |
+
"loss": 0.0339,
|
| 68 |
+
"step": 5000
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.34,
|
| 72 |
+
"learning_rate": 1.972079171061612e-05,
|
| 73 |
+
"loss": 0.0294,
|
| 74 |
+
"step": 5500
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.37,
|
| 78 |
+
"learning_rate": 1.9689768567351245e-05,
|
| 79 |
+
"loss": 0.035,
|
| 80 |
+
"step": 6000
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.4,
|
| 84 |
+
"learning_rate": 1.965874542408637e-05,
|
| 85 |
+
"loss": 0.0515,
|
| 86 |
+
"step": 6500
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.43,
|
| 90 |
+
"learning_rate": 1.9627722280821494e-05,
|
| 91 |
+
"loss": 0.0232,
|
| 92 |
+
"step": 7000
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.46,
|
| 96 |
+
"learning_rate": 1.9596699137556618e-05,
|
| 97 |
+
"loss": 0.0349,
|
| 98 |
+
"step": 7500
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.49,
|
| 102 |
+
"learning_rate": 1.9565675994291742e-05,
|
| 103 |
+
"loss": 0.0226,
|
| 104 |
+
"step": 8000
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.53,
|
| 108 |
+
"learning_rate": 1.9534652851026867e-05,
|
| 109 |
+
"loss": 0.0215,
|
| 110 |
+
"step": 8500
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 0.56,
|
| 114 |
+
"learning_rate": 1.9503629707761994e-05,
|
| 115 |
+
"loss": 0.0204,
|
| 116 |
+
"step": 9000
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.59,
|
| 120 |
+
"learning_rate": 1.9472606564497115e-05,
|
| 121 |
+
"loss": 0.0192,
|
| 122 |
+
"step": 9500
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.62,
|
| 126 |
+
"learning_rate": 1.9441583421232243e-05,
|
| 127 |
+
"loss": 0.0194,
|
| 128 |
+
"step": 10000
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.65,
|
| 132 |
+
"learning_rate": 1.9410560277967364e-05,
|
| 133 |
+
"loss": 0.0179,
|
| 134 |
+
"step": 10500
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 0.68,
|
| 138 |
+
"learning_rate": 1.937953713470249e-05,
|
| 139 |
+
"loss": 0.017,
|
| 140 |
+
"step": 11000
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 0.71,
|
| 144 |
+
"learning_rate": 1.9348513991437613e-05,
|
| 145 |
+
"loss": 0.0226,
|
| 146 |
+
"step": 11500
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 0.74,
|
| 150 |
+
"learning_rate": 1.9317490848172737e-05,
|
| 151 |
+
"loss": 0.016,
|
| 152 |
+
"step": 12000
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 0.77,
|
| 156 |
+
"learning_rate": 1.928646770490786e-05,
|
| 157 |
+
"loss": 0.0154,
|
| 158 |
+
"step": 12500
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 0.8,
|
| 162 |
+
"learning_rate": 1.9255444561642986e-05,
|
| 163 |
+
"loss": 0.0157,
|
| 164 |
+
"step": 13000
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.84,
|
| 168 |
+
"learning_rate": 1.9224421418378113e-05,
|
| 169 |
+
"loss": 0.0139,
|
| 170 |
+
"step": 13500
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.87,
|
| 174 |
+
"learning_rate": 1.9193398275113234e-05,
|
| 175 |
+
"loss": 0.0129,
|
| 176 |
+
"step": 14000
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 0.9,
|
| 180 |
+
"learning_rate": 1.9162375131848362e-05,
|
| 181 |
+
"loss": 0.0134,
|
| 182 |
+
"step": 14500
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 0.93,
|
| 186 |
+
"learning_rate": 1.9131351988583483e-05,
|
| 187 |
+
"loss": 0.0134,
|
| 188 |
+
"step": 15000
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 0.96,
|
| 192 |
+
"learning_rate": 1.910032884531861e-05,
|
| 193 |
+
"loss": 0.0133,
|
| 194 |
+
"step": 15500
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 0.99,
|
| 198 |
+
"learning_rate": 1.9069305702053732e-05,
|
| 199 |
+
"loss": 0.0133,
|
| 200 |
+
"step": 16000
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 1.0,
|
| 204 |
+
"eval_loss": 0.007159320637583733,
|
| 205 |
+
"eval_runtime": 63.5558,
|
| 206 |
+
"eval_samples_per_second": 113.05,
|
| 207 |
+
"eval_steps_per_second": 7.08,
|
| 208 |
+
"step": 16167
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 1.02,
|
| 212 |
+
"learning_rate": 1.903828255878886e-05,
|
| 213 |
+
"loss": 0.0118,
|
| 214 |
+
"step": 16500
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"epoch": 1.05,
|
| 218 |
+
"learning_rate": 1.900725941552398e-05,
|
| 219 |
+
"loss": 0.0114,
|
| 220 |
+
"step": 17000
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 1.08,
|
| 224 |
+
"learning_rate": 1.8976236272259108e-05,
|
| 225 |
+
"loss": 0.0115,
|
| 226 |
+
"step": 17500
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 1.11,
|
| 230 |
+
"learning_rate": 1.8945213128994233e-05,
|
| 231 |
+
"loss": 0.0115,
|
| 232 |
+
"step": 18000
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"epoch": 1.14,
|
| 236 |
+
"learning_rate": 1.8914189985729357e-05,
|
| 237 |
+
"loss": 0.0118,
|
| 238 |
+
"step": 18500
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"epoch": 1.18,
|
| 242 |
+
"learning_rate": 1.888316684246448e-05,
|
| 243 |
+
"loss": 0.0119,
|
| 244 |
+
"step": 19000
|
| 245 |
+
},
|
| 246 |
+
{
|
| 247 |
+
"epoch": 1.21,
|
| 248 |
+
"learning_rate": 1.8852143699199606e-05,
|
| 249 |
+
"loss": 0.0117,
|
| 250 |
+
"step": 19500
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 1.24,
|
| 254 |
+
"learning_rate": 1.882112055593473e-05,
|
| 255 |
+
"loss": 0.0113,
|
| 256 |
+
"step": 20000
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 1.27,
|
| 260 |
+
"learning_rate": 1.8790097412669854e-05,
|
| 261 |
+
"loss": 0.0102,
|
| 262 |
+
"step": 20500
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 1.3,
|
| 266 |
+
"learning_rate": 1.875907426940498e-05,
|
| 267 |
+
"loss": 0.0109,
|
| 268 |
+
"step": 21000
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 1.33,
|
| 272 |
+
"learning_rate": 1.87280511261401e-05,
|
| 273 |
+
"loss": 0.0096,
|
| 274 |
+
"step": 21500
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 1.36,
|
| 278 |
+
"learning_rate": 1.8697027982875227e-05,
|
| 279 |
+
"loss": 0.0105,
|
| 280 |
+
"step": 22000
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 1.39,
|
| 284 |
+
"learning_rate": 1.866600483961035e-05,
|
| 285 |
+
"loss": 0.0093,
|
| 286 |
+
"step": 22500
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 1.42,
|
| 290 |
+
"learning_rate": 1.8634981696345476e-05,
|
| 291 |
+
"loss": 0.0096,
|
| 292 |
+
"step": 23000
|
| 293 |
+
},
|
| 294 |
+
{
|
| 295 |
+
"epoch": 1.45,
|
| 296 |
+
"learning_rate": 1.86039585530806e-05,
|
| 297 |
+
"loss": 0.0091,
|
| 298 |
+
"step": 23500
|
| 299 |
+
},
|
| 300 |
+
{
|
| 301 |
+
"epoch": 1.48,
|
| 302 |
+
"learning_rate": 1.8572935409815725e-05,
|
| 303 |
+
"loss": 0.0099,
|
| 304 |
+
"step": 24000
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 1.52,
|
| 308 |
+
"learning_rate": 1.854191226655085e-05,
|
| 309 |
+
"loss": 0.009,
|
| 310 |
+
"step": 24500
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 1.55,
|
| 314 |
+
"learning_rate": 1.8510889123285973e-05,
|
| 315 |
+
"loss": 0.0097,
|
| 316 |
+
"step": 25000
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 1.58,
|
| 320 |
+
"learning_rate": 1.8479865980021098e-05,
|
| 321 |
+
"loss": 0.0089,
|
| 322 |
+
"step": 25500
|
| 323 |
+
},
|
| 324 |
+
{
|
| 325 |
+
"epoch": 1.61,
|
| 326 |
+
"learning_rate": 1.8448842836756222e-05,
|
| 327 |
+
"loss": 0.0097,
|
| 328 |
+
"step": 26000
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"epoch": 1.64,
|
| 332 |
+
"learning_rate": 1.8417819693491346e-05,
|
| 333 |
+
"loss": 0.0099,
|
| 334 |
+
"step": 26500
|
| 335 |
+
},
|
| 336 |
+
{
|
| 337 |
+
"epoch": 1.67,
|
| 338 |
+
"learning_rate": 1.838679655022647e-05,
|
| 339 |
+
"loss": 0.0092,
|
| 340 |
+
"step": 27000
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"epoch": 1.7,
|
| 344 |
+
"learning_rate": 1.8355773406961595e-05,
|
| 345 |
+
"loss": 0.0094,
|
| 346 |
+
"step": 27500
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 1.73,
|
| 350 |
+
"learning_rate": 1.832475026369672e-05,
|
| 351 |
+
"loss": 0.0087,
|
| 352 |
+
"step": 28000
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 1.76,
|
| 356 |
+
"learning_rate": 1.8293727120431844e-05,
|
| 357 |
+
"loss": 0.0091,
|
| 358 |
+
"step": 28500
|
| 359 |
+
},
|
| 360 |
+
{
|
| 361 |
+
"epoch": 1.79,
|
| 362 |
+
"learning_rate": 1.8262703977166968e-05,
|
| 363 |
+
"loss": 0.0098,
|
| 364 |
+
"step": 29000
|
| 365 |
+
},
|
| 366 |
+
{
|
| 367 |
+
"epoch": 1.82,
|
| 368 |
+
"learning_rate": 1.8231680833902092e-05,
|
| 369 |
+
"loss": 0.0093,
|
| 370 |
+
"step": 29500
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 1.86,
|
| 374 |
+
"learning_rate": 1.8200657690637217e-05,
|
| 375 |
+
"loss": 0.0088,
|
| 376 |
+
"step": 30000
|
| 377 |
+
},
|
| 378 |
+
{
|
| 379 |
+
"epoch": 1.89,
|
| 380 |
+
"learning_rate": 1.816963454737234e-05,
|
| 381 |
+
"loss": 0.008,
|
| 382 |
+
"step": 30500
|
| 383 |
+
},
|
| 384 |
+
{
|
| 385 |
+
"epoch": 1.92,
|
| 386 |
+
"learning_rate": 1.8138611404107465e-05,
|
| 387 |
+
"loss": 0.0088,
|
| 388 |
+
"step": 31000
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 1.95,
|
| 392 |
+
"learning_rate": 1.810758826084259e-05,
|
| 393 |
+
"loss": 0.0084,
|
| 394 |
+
"step": 31500
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 1.98,
|
| 398 |
+
"learning_rate": 1.8076565117577714e-05,
|
| 399 |
+
"loss": 0.0087,
|
| 400 |
+
"step": 32000
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"epoch": 2.0,
|
| 404 |
+
"eval_loss": 0.005626102443784475,
|
| 405 |
+
"eval_runtime": 63.5514,
|
| 406 |
+
"eval_samples_per_second": 113.058,
|
| 407 |
+
"eval_steps_per_second": 7.081,
|
| 408 |
+
"step": 32334
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 2.01,
|
| 412 |
+
"learning_rate": 1.804554197431284e-05,
|
| 413 |
+
"loss": 0.0081,
|
| 414 |
+
"step": 32500
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 2.04,
|
| 418 |
+
"learning_rate": 1.8014518831047963e-05,
|
| 419 |
+
"loss": 0.007,
|
| 420 |
+
"step": 33000
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 2.07,
|
| 424 |
+
"learning_rate": 1.7983495687783087e-05,
|
| 425 |
+
"loss": 0.0072,
|
| 426 |
+
"step": 33500
|
| 427 |
+
},
|
| 428 |
+
{
|
| 429 |
+
"epoch": 2.1,
|
| 430 |
+
"learning_rate": 1.795247254451821e-05,
|
| 431 |
+
"loss": 0.0069,
|
| 432 |
+
"step": 34000
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 2.13,
|
| 436 |
+
"learning_rate": 1.7921449401253336e-05,
|
| 437 |
+
"loss": 0.0072,
|
| 438 |
+
"step": 34500
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 2.16,
|
| 442 |
+
"learning_rate": 1.789042625798846e-05,
|
| 443 |
+
"loss": 0.0067,
|
| 444 |
+
"step": 35000
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 2.2,
|
| 448 |
+
"learning_rate": 1.7859403114723584e-05,
|
| 449 |
+
"loss": 0.007,
|
| 450 |
+
"step": 35500
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 2.23,
|
| 454 |
+
"learning_rate": 1.782837997145871e-05,
|
| 455 |
+
"loss": 0.0072,
|
| 456 |
+
"step": 36000
|
| 457 |
+
},
|
| 458 |
+
{
|
| 459 |
+
"epoch": 2.26,
|
| 460 |
+
"learning_rate": 1.7797356828193833e-05,
|
| 461 |
+
"loss": 0.0074,
|
| 462 |
+
"step": 36500
|
| 463 |
+
},
|
| 464 |
+
{
|
| 465 |
+
"epoch": 2.29,
|
| 466 |
+
"learning_rate": 1.7766333684928957e-05,
|
| 467 |
+
"loss": 0.0075,
|
| 468 |
+
"step": 37000
|
| 469 |
+
},
|
| 470 |
+
{
|
| 471 |
+
"epoch": 2.32,
|
| 472 |
+
"learning_rate": 1.7735310541664085e-05,
|
| 473 |
+
"loss": 0.0072,
|
| 474 |
+
"step": 37500
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 2.35,
|
| 478 |
+
"learning_rate": 1.7704287398399206e-05,
|
| 479 |
+
"loss": 0.0061,
|
| 480 |
+
"step": 38000
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 2.38,
|
| 484 |
+
"learning_rate": 1.7673264255134334e-05,
|
| 485 |
+
"loss": 0.0071,
|
| 486 |
+
"step": 38500
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 2.41,
|
| 490 |
+
"learning_rate": 1.7642241111869455e-05,
|
| 491 |
+
"loss": 0.0074,
|
| 492 |
+
"step": 39000
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 2.44,
|
| 496 |
+
"learning_rate": 1.7611217968604582e-05,
|
| 497 |
+
"loss": 0.0072,
|
| 498 |
+
"step": 39500
|
| 499 |
+
},
|
| 500 |
+
{
|
| 501 |
+
"epoch": 2.47,
|
| 502 |
+
"learning_rate": 1.7580194825339703e-05,
|
| 503 |
+
"loss": 0.0072,
|
| 504 |
+
"step": 40000
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 2.51,
|
| 508 |
+
"learning_rate": 1.754917168207483e-05,
|
| 509 |
+
"loss": 0.0075,
|
| 510 |
+
"step": 40500
|
| 511 |
+
},
|
| 512 |
+
{
|
| 513 |
+
"epoch": 2.54,
|
| 514 |
+
"learning_rate": 1.7518148538809952e-05,
|
| 515 |
+
"loss": 0.0069,
|
| 516 |
+
"step": 41000
|
| 517 |
+
},
|
| 518 |
+
{
|
| 519 |
+
"epoch": 2.57,
|
| 520 |
+
"learning_rate": 1.7487125395545076e-05,
|
| 521 |
+
"loss": 0.007,
|
| 522 |
+
"step": 41500
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 2.6,
|
| 526 |
+
"learning_rate": 1.7456102252280204e-05,
|
| 527 |
+
"loss": 0.0058,
|
| 528 |
+
"step": 42000
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 2.63,
|
| 532 |
+
"learning_rate": 1.7425079109015325e-05,
|
| 533 |
+
"loss": 0.0064,
|
| 534 |
+
"step": 42500
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 2.66,
|
| 538 |
+
"learning_rate": 1.7394055965750453e-05,
|
| 539 |
+
"loss": 0.0067,
|
| 540 |
+
"step": 43000
|
| 541 |
+
},
|
| 542 |
+
{
|
| 543 |
+
"epoch": 2.69,
|
| 544 |
+
"learning_rate": 1.7363032822485574e-05,
|
| 545 |
+
"loss": 0.0062,
|
| 546 |
+
"step": 43500
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 2.72,
|
| 550 |
+
"learning_rate": 1.73320096792207e-05,
|
| 551 |
+
"loss": 0.0066,
|
| 552 |
+
"step": 44000
|
| 553 |
+
},
|
| 554 |
+
{
|
| 555 |
+
"epoch": 2.75,
|
| 556 |
+
"learning_rate": 1.7300986535955822e-05,
|
| 557 |
+
"loss": 0.0066,
|
| 558 |
+
"step": 44500
|
| 559 |
+
},
|
| 560 |
+
{
|
| 561 |
+
"epoch": 2.78,
|
| 562 |
+
"learning_rate": 1.726996339269095e-05,
|
| 563 |
+
"loss": 0.0071,
|
| 564 |
+
"step": 45000
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 2.81,
|
| 568 |
+
"learning_rate": 1.723894024942607e-05,
|
| 569 |
+
"loss": 0.0065,
|
| 570 |
+
"step": 45500
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 2.85,
|
| 574 |
+
"learning_rate": 1.72079171061612e-05,
|
| 575 |
+
"loss": 0.0065,
|
| 576 |
+
"step": 46000
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 2.88,
|
| 580 |
+
"learning_rate": 1.7176893962896323e-05,
|
| 581 |
+
"loss": 0.0065,
|
| 582 |
+
"step": 46500
|
| 583 |
+
},
|
| 584 |
+
{
|
| 585 |
+
"epoch": 2.91,
|
| 586 |
+
"learning_rate": 1.7145870819631448e-05,
|
| 587 |
+
"loss": 0.0062,
|
| 588 |
+
"step": 47000
|
| 589 |
+
},
|
| 590 |
+
{
|
| 591 |
+
"epoch": 2.94,
|
| 592 |
+
"learning_rate": 1.7114847676366572e-05,
|
| 593 |
+
"loss": 0.0075,
|
| 594 |
+
"step": 47500
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 2.97,
|
| 598 |
+
"learning_rate": 1.7083824533101696e-05,
|
| 599 |
+
"loss": 0.0064,
|
| 600 |
+
"step": 48000
|
| 601 |
+
},
|
| 602 |
+
{
|
| 603 |
+
"epoch": 3.0,
|
| 604 |
+
"learning_rate": 1.705280138983682e-05,
|
| 605 |
+
"loss": 0.0063,
|
| 606 |
+
"step": 48500
|
| 607 |
+
},
|
| 608 |
+
{
|
| 609 |
+
"epoch": 3.0,
|
| 610 |
+
"eval_loss": 0.005162048153579235,
|
| 611 |
+
"eval_runtime": 63.5102,
|
| 612 |
+
"eval_samples_per_second": 113.132,
|
| 613 |
+
"eval_steps_per_second": 7.085,
|
| 614 |
+
"step": 48501
|
| 615 |
+
},
|
| 616 |
+
{
|
| 617 |
+
"epoch": 3.03,
|
| 618 |
+
"learning_rate": 1.7021778246571945e-05,
|
| 619 |
+
"loss": 0.0055,
|
| 620 |
+
"step": 49000
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 3.06,
|
| 624 |
+
"learning_rate": 1.699075510330707e-05,
|
| 625 |
+
"loss": 0.0055,
|
| 626 |
+
"step": 49500
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 3.09,
|
| 630 |
+
"learning_rate": 1.6959731960042194e-05,
|
| 631 |
+
"loss": 0.0059,
|
| 632 |
+
"step": 50000
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 3.12,
|
| 636 |
+
"learning_rate": 1.6928708816777318e-05,
|
| 637 |
+
"loss": 0.0052,
|
| 638 |
+
"step": 50500
|
| 639 |
+
},
|
| 640 |
+
{
|
| 641 |
+
"epoch": 3.15,
|
| 642 |
+
"learning_rate": 1.6897685673512442e-05,
|
| 643 |
+
"loss": 0.0053,
|
| 644 |
+
"step": 51000
|
| 645 |
+
},
|
| 646 |
+
{
|
| 647 |
+
"epoch": 3.19,
|
| 648 |
+
"learning_rate": 1.6866662530247567e-05,
|
| 649 |
+
"loss": 0.005,
|
| 650 |
+
"step": 51500
|
| 651 |
+
},
|
| 652 |
+
{
|
| 653 |
+
"epoch": 3.22,
|
| 654 |
+
"learning_rate": 1.683563938698269e-05,
|
| 655 |
+
"loss": 0.0056,
|
| 656 |
+
"step": 52000
|
| 657 |
+
},
|
| 658 |
+
{
|
| 659 |
+
"epoch": 3.25,
|
| 660 |
+
"learning_rate": 1.6804616243717815e-05,
|
| 661 |
+
"loss": 0.0051,
|
| 662 |
+
"step": 52500
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 3.28,
|
| 666 |
+
"learning_rate": 1.677359310045294e-05,
|
| 667 |
+
"loss": 0.0053,
|
| 668 |
+
"step": 53000
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 3.31,
|
| 672 |
+
"learning_rate": 1.6742569957188064e-05,
|
| 673 |
+
"loss": 0.0053,
|
| 674 |
+
"step": 53500
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 3.34,
|
| 678 |
+
"learning_rate": 1.6711546813923188e-05,
|
| 679 |
+
"loss": 0.0051,
|
| 680 |
+
"step": 54000
|
| 681 |
+
},
|
| 682 |
+
{
|
| 683 |
+
"epoch": 3.37,
|
| 684 |
+
"learning_rate": 1.6680523670658313e-05,
|
| 685 |
+
"loss": 0.0056,
|
| 686 |
+
"step": 54500
|
| 687 |
+
},
|
| 688 |
+
{
|
| 689 |
+
"epoch": 3.4,
|
| 690 |
+
"learning_rate": 1.6649500527393437e-05,
|
| 691 |
+
"loss": 0.0068,
|
| 692 |
+
"step": 55000
|
| 693 |
+
},
|
| 694 |
+
{
|
| 695 |
+
"epoch": 3.43,
|
| 696 |
+
"learning_rate": 1.661847738412856e-05,
|
| 697 |
+
"loss": 0.0054,
|
| 698 |
+
"step": 55500
|
| 699 |
+
},
|
| 700 |
+
{
|
| 701 |
+
"epoch": 3.46,
|
| 702 |
+
"learning_rate": 1.6587454240863686e-05,
|
| 703 |
+
"loss": 0.0055,
|
| 704 |
+
"step": 56000
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 3.49,
|
| 708 |
+
"learning_rate": 1.655643109759881e-05,
|
| 709 |
+
"loss": 0.0056,
|
| 710 |
+
"step": 56500
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 3.53,
|
| 714 |
+
"learning_rate": 1.6525407954333934e-05,
|
| 715 |
+
"loss": 0.0053,
|
| 716 |
+
"step": 57000
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 3.56,
|
| 720 |
+
"learning_rate": 1.649438481106906e-05,
|
| 721 |
+
"loss": 0.0051,
|
| 722 |
+
"step": 57500
|
| 723 |
+
},
|
| 724 |
+
{
|
| 725 |
+
"epoch": 3.59,
|
| 726 |
+
"learning_rate": 1.6463361667804183e-05,
|
| 727 |
+
"loss": 0.005,
|
| 728 |
+
"step": 58000
|
| 729 |
+
},
|
| 730 |
+
{
|
| 731 |
+
"epoch": 3.62,
|
| 732 |
+
"learning_rate": 1.6432338524539307e-05,
|
| 733 |
+
"loss": 0.0055,
|
| 734 |
+
"step": 58500
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 3.65,
|
| 738 |
+
"learning_rate": 1.640131538127443e-05,
|
| 739 |
+
"loss": 0.0048,
|
| 740 |
+
"step": 59000
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 3.68,
|
| 744 |
+
"learning_rate": 1.6370292238009556e-05,
|
| 745 |
+
"loss": 0.0052,
|
| 746 |
+
"step": 59500
|
| 747 |
+
},
|
| 748 |
+
{
|
| 749 |
+
"epoch": 3.71,
|
| 750 |
+
"learning_rate": 1.633926909474468e-05,
|
| 751 |
+
"loss": 0.0048,
|
| 752 |
+
"step": 60000
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 3.74,
|
| 756 |
+
"learning_rate": 1.6308245951479805e-05,
|
| 757 |
+
"loss": 0.0049,
|
| 758 |
+
"step": 60500
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 3.77,
|
| 762 |
+
"learning_rate": 1.627722280821493e-05,
|
| 763 |
+
"loss": 0.0054,
|
| 764 |
+
"step": 61000
|
| 765 |
+
},
|
| 766 |
+
{
|
| 767 |
+
"epoch": 3.8,
|
| 768 |
+
"learning_rate": 1.6246199664950053e-05,
|
| 769 |
+
"loss": 0.0052,
|
| 770 |
+
"step": 61500
|
| 771 |
+
},
|
| 772 |
+
{
|
| 773 |
+
"epoch": 3.83,
|
| 774 |
+
"learning_rate": 1.6215176521685178e-05,
|
| 775 |
+
"loss": 0.0053,
|
| 776 |
+
"step": 62000
|
| 777 |
+
},
|
| 778 |
+
{
|
| 779 |
+
"epoch": 3.87,
|
| 780 |
+
"learning_rate": 1.6184153378420302e-05,
|
| 781 |
+
"loss": 0.0052,
|
| 782 |
+
"step": 62500
|
| 783 |
+
},
|
| 784 |
+
{
|
| 785 |
+
"epoch": 3.9,
|
| 786 |
+
"learning_rate": 1.6153130235155426e-05,
|
| 787 |
+
"loss": 0.0053,
|
| 788 |
+
"step": 63000
|
| 789 |
+
},
|
| 790 |
+
{
|
| 791 |
+
"epoch": 3.93,
|
| 792 |
+
"learning_rate": 1.612210709189055e-05,
|
| 793 |
+
"loss": 0.0052,
|
| 794 |
+
"step": 63500
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 3.96,
|
| 798 |
+
"learning_rate": 1.6091083948625675e-05,
|
| 799 |
+
"loss": 0.0052,
|
| 800 |
+
"step": 64000
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 3.99,
|
| 804 |
+
"learning_rate": 1.60600608053608e-05,
|
| 805 |
+
"loss": 0.0054,
|
| 806 |
+
"step": 64500
|
| 807 |
+
},
|
| 808 |
+
{
|
| 809 |
+
"epoch": 4.0,
|
| 810 |
+
"eval_loss": 0.004835214000195265,
|
| 811 |
+
"eval_runtime": 63.5993,
|
| 812 |
+
"eval_samples_per_second": 112.973,
|
| 813 |
+
"eval_steps_per_second": 7.076,
|
| 814 |
+
"step": 64668
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 4.02,
|
| 818 |
+
"learning_rate": 1.6029037662095924e-05,
|
| 819 |
+
"loss": 0.0042,
|
| 820 |
+
"step": 65000
|
| 821 |
+
},
|
| 822 |
+
{
|
| 823 |
+
"epoch": 4.05,
|
| 824 |
+
"learning_rate": 1.5998014518831048e-05,
|
| 825 |
+
"loss": 0.0044,
|
| 826 |
+
"step": 65500
|
| 827 |
+
},
|
| 828 |
+
{
|
| 829 |
+
"epoch": 4.08,
|
| 830 |
+
"learning_rate": 1.5966991375566176e-05,
|
| 831 |
+
"loss": 0.0041,
|
| 832 |
+
"step": 66000
|
| 833 |
+
},
|
| 834 |
+
{
|
| 835 |
+
"epoch": 4.11,
|
| 836 |
+
"learning_rate": 1.5935968232301297e-05,
|
| 837 |
+
"loss": 0.0046,
|
| 838 |
+
"step": 66500
|
| 839 |
+
},
|
| 840 |
+
{
|
| 841 |
+
"epoch": 4.14,
|
| 842 |
+
"learning_rate": 1.5904945089036424e-05,
|
| 843 |
+
"loss": 0.004,
|
| 844 |
+
"step": 67000
|
| 845 |
+
},
|
| 846 |
+
{
|
| 847 |
+
"epoch": 4.18,
|
| 848 |
+
"learning_rate": 1.5873921945771545e-05,
|
| 849 |
+
"loss": 0.0044,
|
| 850 |
+
"step": 67500
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 4.21,
|
| 854 |
+
"learning_rate": 1.5842898802506673e-05,
|
| 855 |
+
"loss": 0.0047,
|
| 856 |
+
"step": 68000
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 4.24,
|
| 860 |
+
"learning_rate": 1.5811875659241794e-05,
|
| 861 |
+
"loss": 0.0043,
|
| 862 |
+
"step": 68500
|
| 863 |
+
},
|
| 864 |
+
{
|
| 865 |
+
"epoch": 4.27,
|
| 866 |
+
"learning_rate": 1.5780852515976922e-05,
|
| 867 |
+
"loss": 0.004,
|
| 868 |
+
"step": 69000
|
| 869 |
+
},
|
| 870 |
+
{
|
| 871 |
+
"epoch": 4.3,
|
| 872 |
+
"learning_rate": 1.5749829372712043e-05,
|
| 873 |
+
"loss": 0.0043,
|
| 874 |
+
"step": 69500
|
| 875 |
+
},
|
| 876 |
+
{
|
| 877 |
+
"epoch": 4.33,
|
| 878 |
+
"learning_rate": 1.571880622944717e-05,
|
| 879 |
+
"loss": 0.0048,
|
| 880 |
+
"step": 70000
|
| 881 |
+
},
|
| 882 |
+
{
|
| 883 |
+
"epoch": 4.36,
|
| 884 |
+
"learning_rate": 1.5687783086182295e-05,
|
| 885 |
+
"loss": 0.0044,
|
| 886 |
+
"step": 70500
|
| 887 |
+
},
|
| 888 |
+
{
|
| 889 |
+
"epoch": 4.39,
|
| 890 |
+
"learning_rate": 1.5656759942917416e-05,
|
| 891 |
+
"loss": 0.0042,
|
| 892 |
+
"step": 71000
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 4.42,
|
| 896 |
+
"learning_rate": 1.5625736799652544e-05,
|
| 897 |
+
"loss": 0.0041,
|
| 898 |
+
"step": 71500
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 4.45,
|
| 902 |
+
"learning_rate": 1.5594713656387664e-05,
|
| 903 |
+
"loss": 0.0045,
|
| 904 |
+
"step": 72000
|
| 905 |
+
},
|
| 906 |
+
{
|
| 907 |
+
"epoch": 4.48,
|
| 908 |
+
"learning_rate": 1.5563690513122792e-05,
|
| 909 |
+
"loss": 0.0041,
|
| 910 |
+
"step": 72500
|
| 911 |
+
},
|
| 912 |
+
{
|
| 913 |
+
"epoch": 4.52,
|
| 914 |
+
"learning_rate": 1.5532667369857913e-05,
|
| 915 |
+
"loss": 0.0044,
|
| 916 |
+
"step": 73000
|
| 917 |
+
},
|
| 918 |
+
{
|
| 919 |
+
"epoch": 4.55,
|
| 920 |
+
"learning_rate": 1.550164422659304e-05,
|
| 921 |
+
"loss": 0.0039,
|
| 922 |
+
"step": 73500
|
| 923 |
+
},
|
| 924 |
+
{
|
| 925 |
+
"epoch": 4.58,
|
| 926 |
+
"learning_rate": 1.5470621083328162e-05,
|
| 927 |
+
"loss": 0.0045,
|
| 928 |
+
"step": 74000
|
| 929 |
+
},
|
| 930 |
+
{
|
| 931 |
+
"epoch": 4.61,
|
| 932 |
+
"learning_rate": 1.543959794006329e-05,
|
| 933 |
+
"loss": 0.0039,
|
| 934 |
+
"step": 74500
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 4.64,
|
| 938 |
+
"learning_rate": 1.5408574796798414e-05,
|
| 939 |
+
"loss": 0.0044,
|
| 940 |
+
"step": 75000
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 4.67,
|
| 944 |
+
"learning_rate": 1.5377551653533538e-05,
|
| 945 |
+
"loss": 0.004,
|
| 946 |
+
"step": 75500
|
| 947 |
+
},
|
| 948 |
+
{
|
| 949 |
+
"epoch": 4.7,
|
| 950 |
+
"learning_rate": 1.5346528510268663e-05,
|
| 951 |
+
"loss": 0.0048,
|
| 952 |
+
"step": 76000
|
| 953 |
+
},
|
| 954 |
+
{
|
| 955 |
+
"epoch": 4.73,
|
| 956 |
+
"learning_rate": 1.5315505367003787e-05,
|
| 957 |
+
"loss": 0.004,
|
| 958 |
+
"step": 76500
|
| 959 |
+
},
|
| 960 |
+
{
|
| 961 |
+
"epoch": 4.76,
|
| 962 |
+
"learning_rate": 1.528448222373891e-05,
|
| 963 |
+
"loss": 0.0046,
|
| 964 |
+
"step": 77000
|
| 965 |
+
},
|
| 966 |
+
{
|
| 967 |
+
"epoch": 4.79,
|
| 968 |
+
"learning_rate": 1.5253459080474036e-05,
|
| 969 |
+
"loss": 0.0043,
|
| 970 |
+
"step": 77500
|
| 971 |
+
},
|
| 972 |
+
{
|
| 973 |
+
"epoch": 4.82,
|
| 974 |
+
"learning_rate": 1.5222435937209158e-05,
|
| 975 |
+
"loss": 0.0043,
|
| 976 |
+
"step": 78000
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 4.86,
|
| 980 |
+
"learning_rate": 1.5191412793944284e-05,
|
| 981 |
+
"loss": 0.0042,
|
| 982 |
+
"step": 78500
|
| 983 |
+
},
|
| 984 |
+
{
|
| 985 |
+
"epoch": 4.89,
|
| 986 |
+
"learning_rate": 1.5160389650679409e-05,
|
| 987 |
+
"loss": 0.0045,
|
| 988 |
+
"step": 79000
|
| 989 |
+
},
|
| 990 |
+
{
|
| 991 |
+
"epoch": 4.92,
|
| 992 |
+
"learning_rate": 1.5129366507414533e-05,
|
| 993 |
+
"loss": 0.004,
|
| 994 |
+
"step": 79500
|
| 995 |
+
},
|
| 996 |
+
{
|
| 997 |
+
"epoch": 4.95,
|
| 998 |
+
"learning_rate": 1.5098343364149657e-05,
|
| 999 |
+
"loss": 0.0037,
|
| 1000 |
+
"step": 80000
|
| 1001 |
+
},
|
| 1002 |
+
{
|
| 1003 |
+
"epoch": 4.98,
|
| 1004 |
+
"learning_rate": 1.506732022088478e-05,
|
| 1005 |
+
"loss": 0.0045,
|
| 1006 |
+
"step": 80500
|
| 1007 |
+
},
|
| 1008 |
+
{
|
| 1009 |
+
"epoch": 5.0,
|
| 1010 |
+
"eval_loss": 0.004868941381573677,
|
| 1011 |
+
"eval_runtime": 63.5068,
|
| 1012 |
+
"eval_samples_per_second": 113.137,
|
| 1013 |
+
"eval_steps_per_second": 7.086,
|
| 1014 |
+
"step": 80835
|
| 1015 |
+
},
|
| 1016 |
+
{
|
| 1017 |
+
"epoch": 5.01,
|
| 1018 |
+
"learning_rate": 1.5036297077619906e-05,
|
| 1019 |
+
"loss": 0.0038,
|
| 1020 |
+
"step": 81000
|
| 1021 |
+
},
|
| 1022 |
+
{
|
| 1023 |
+
"epoch": 5.04,
|
| 1024 |
+
"learning_rate": 1.5005273934355029e-05,
|
| 1025 |
+
"loss": 0.0035,
|
| 1026 |
+
"step": 81500
|
| 1027 |
+
},
|
| 1028 |
+
{
|
| 1029 |
+
"epoch": 5.07,
|
| 1030 |
+
"learning_rate": 1.4974250791090155e-05,
|
| 1031 |
+
"loss": 0.0035,
|
| 1032 |
+
"step": 82000
|
| 1033 |
+
},
|
| 1034 |
+
{
|
| 1035 |
+
"epoch": 5.1,
|
| 1036 |
+
"learning_rate": 1.4943227647825277e-05,
|
| 1037 |
+
"loss": 0.0037,
|
| 1038 |
+
"step": 82500
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"epoch": 5.13,
|
| 1042 |
+
"learning_rate": 1.4912204504560403e-05,
|
| 1043 |
+
"loss": 0.0031,
|
| 1044 |
+
"step": 83000
|
| 1045 |
+
},
|
| 1046 |
+
{
|
| 1047 |
+
"epoch": 5.16,
|
| 1048 |
+
"learning_rate": 1.4881181361295528e-05,
|
| 1049 |
+
"loss": 0.0035,
|
| 1050 |
+
"step": 83500
|
| 1051 |
+
},
|
| 1052 |
+
{
|
| 1053 |
+
"epoch": 5.2,
|
| 1054 |
+
"learning_rate": 1.4850158218030652e-05,
|
| 1055 |
+
"loss": 0.0037,
|
| 1056 |
+
"step": 84000
|
| 1057 |
+
},
|
| 1058 |
+
{
|
| 1059 |
+
"epoch": 5.23,
|
| 1060 |
+
"learning_rate": 1.4819135074765776e-05,
|
| 1061 |
+
"loss": 0.0033,
|
| 1062 |
+
"step": 84500
|
| 1063 |
+
},
|
| 1064 |
+
{
|
| 1065 |
+
"epoch": 5.26,
|
| 1066 |
+
"learning_rate": 1.47881119315009e-05,
|
| 1067 |
+
"loss": 0.0039,
|
| 1068 |
+
"step": 85000
|
| 1069 |
+
},
|
| 1070 |
+
{
|
| 1071 |
+
"epoch": 5.29,
|
| 1072 |
+
"learning_rate": 1.4757088788236025e-05,
|
| 1073 |
+
"loss": 0.0036,
|
| 1074 |
+
"step": 85500
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 5.32,
|
| 1078 |
+
"learning_rate": 1.4726065644971151e-05,
|
| 1079 |
+
"loss": 0.0039,
|
| 1080 |
+
"step": 86000
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 5.35,
|
| 1084 |
+
"learning_rate": 1.4695042501706274e-05,
|
| 1085 |
+
"loss": 0.0035,
|
| 1086 |
+
"step": 86500
|
| 1087 |
+
},
|
| 1088 |
+
{
|
| 1089 |
+
"epoch": 5.38,
|
| 1090 |
+
"learning_rate": 1.46640193584414e-05,
|
| 1091 |
+
"loss": 0.0034,
|
| 1092 |
+
"step": 87000
|
| 1093 |
+
},
|
| 1094 |
+
{
|
| 1095 |
+
"epoch": 5.41,
|
| 1096 |
+
"learning_rate": 1.4632996215176522e-05,
|
| 1097 |
+
"loss": 0.003,
|
| 1098 |
+
"step": 87500
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"epoch": 5.44,
|
| 1102 |
+
"learning_rate": 1.4601973071911648e-05,
|
| 1103 |
+
"loss": 0.0034,
|
| 1104 |
+
"step": 88000
|
| 1105 |
+
},
|
| 1106 |
+
{
|
| 1107 |
+
"epoch": 5.47,
|
| 1108 |
+
"learning_rate": 1.4570949928646771e-05,
|
| 1109 |
+
"loss": 0.0045,
|
| 1110 |
+
"step": 88500
|
| 1111 |
+
},
|
| 1112 |
+
{
|
| 1113 |
+
"epoch": 5.51,
|
| 1114 |
+
"learning_rate": 1.4539926785381897e-05,
|
| 1115 |
+
"loss": 0.0036,
|
| 1116 |
+
"step": 89000
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 5.54,
|
| 1120 |
+
"learning_rate": 1.450890364211702e-05,
|
| 1121 |
+
"loss": 0.0036,
|
| 1122 |
+
"step": 89500
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 5.57,
|
| 1126 |
+
"learning_rate": 1.4477880498852146e-05,
|
| 1127 |
+
"loss": 0.0037,
|
| 1128 |
+
"step": 90000
|
| 1129 |
+
},
|
| 1130 |
+
{
|
| 1131 |
+
"epoch": 5.6,
|
| 1132 |
+
"learning_rate": 1.444685735558727e-05,
|
| 1133 |
+
"loss": 0.0035,
|
| 1134 |
+
"step": 90500
|
| 1135 |
+
},
|
| 1136 |
+
{
|
| 1137 |
+
"epoch": 5.63,
|
| 1138 |
+
"learning_rate": 1.4415834212322393e-05,
|
| 1139 |
+
"loss": 0.0037,
|
| 1140 |
+
"step": 91000
|
| 1141 |
+
},
|
| 1142 |
+
{
|
| 1143 |
+
"epoch": 5.66,
|
| 1144 |
+
"learning_rate": 1.4384811069057519e-05,
|
| 1145 |
+
"loss": 0.0037,
|
| 1146 |
+
"step": 91500
|
| 1147 |
+
},
|
| 1148 |
+
{
|
| 1149 |
+
"epoch": 5.69,
|
| 1150 |
+
"learning_rate": 1.4353787925792641e-05,
|
| 1151 |
+
"loss": 0.0035,
|
| 1152 |
+
"step": 92000
|
| 1153 |
+
},
|
| 1154 |
+
{
|
| 1155 |
+
"epoch": 5.72,
|
| 1156 |
+
"learning_rate": 1.4322764782527767e-05,
|
| 1157 |
+
"loss": 0.0039,
|
| 1158 |
+
"step": 92500
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"epoch": 5.75,
|
| 1162 |
+
"learning_rate": 1.429174163926289e-05,
|
| 1163 |
+
"loss": 0.0038,
|
| 1164 |
+
"step": 93000
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 5.78,
|
| 1168 |
+
"learning_rate": 1.4260718495998016e-05,
|
| 1169 |
+
"loss": 0.003,
|
| 1170 |
+
"step": 93500
|
| 1171 |
+
},
|
| 1172 |
+
{
|
| 1173 |
+
"epoch": 5.81,
|
| 1174 |
+
"learning_rate": 1.4229695352733139e-05,
|
| 1175 |
+
"loss": 0.0033,
|
| 1176 |
+
"step": 94000
|
| 1177 |
+
},
|
| 1178 |
+
{
|
| 1179 |
+
"epoch": 5.85,
|
| 1180 |
+
"learning_rate": 1.4198672209468265e-05,
|
| 1181 |
+
"loss": 0.004,
|
| 1182 |
+
"step": 94500
|
| 1183 |
+
},
|
| 1184 |
+
{
|
| 1185 |
+
"epoch": 5.88,
|
| 1186 |
+
"learning_rate": 1.4167649066203389e-05,
|
| 1187 |
+
"loss": 0.0031,
|
| 1188 |
+
"step": 95000
|
| 1189 |
+
},
|
| 1190 |
+
{
|
| 1191 |
+
"epoch": 5.91,
|
| 1192 |
+
"learning_rate": 1.4136625922938513e-05,
|
| 1193 |
+
"loss": 0.0034,
|
| 1194 |
+
"step": 95500
|
| 1195 |
+
},
|
| 1196 |
+
{
|
| 1197 |
+
"epoch": 5.94,
|
| 1198 |
+
"learning_rate": 1.4105602779673638e-05,
|
| 1199 |
+
"loss": 0.0032,
|
| 1200 |
+
"step": 96000
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 5.97,
|
| 1204 |
+
"learning_rate": 1.4074579636408762e-05,
|
| 1205 |
+
"loss": 0.0036,
|
| 1206 |
+
"step": 96500
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"epoch": 6.0,
|
| 1210 |
+
"learning_rate": 1.4043556493143886e-05,
|
| 1211 |
+
"loss": 0.0035,
|
| 1212 |
+
"step": 97000
|
| 1213 |
+
},
|
| 1214 |
+
{
|
| 1215 |
+
"epoch": 6.0,
|
| 1216 |
+
"eval_loss": 0.004906239919364452,
|
| 1217 |
+
"eval_runtime": 63.3798,
|
| 1218 |
+
"eval_samples_per_second": 113.364,
|
| 1219 |
+
"eval_steps_per_second": 7.1,
|
| 1220 |
+
"step": 97002
|
| 1221 |
+
}
|
| 1222 |
+
],
|
| 1223 |
+
"max_steps": 323340,
|
| 1224 |
+
"num_train_epochs": 20,
|
| 1225 |
+
"total_flos": 2.90069697134592e+17,
|
| 1226 |
+
"trial_name": null,
|
| 1227 |
+
"trial_params": null
|
| 1228 |
+
}
|
large-1/checkpoint-97002/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a3edc56f0f0e1d7be1ce3265d43ba3e04b7d248bf3e6aeba8adfbe111cabeb09
|
| 3 |
+
size 4027
|
large-1/config.json
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "google/mt5-large",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"MT5ForConditionalGeneration"
|
| 5 |
+
],
|
| 6 |
+
"d_ff": 2816,
|
| 7 |
+
"d_kv": 64,
|
| 8 |
+
"d_model": 1024,
|
| 9 |
+
"decoder_start_token_id": 0,
|
| 10 |
+
"dense_act_fn": "gelu_new",
|
| 11 |
+
"dropout_rate": 0.1,
|
| 12 |
+
"eos_token_id": 1,
|
| 13 |
+
"feed_forward_proj": "gated-gelu",
|
| 14 |
+
"initializer_factor": 1.0,
|
| 15 |
+
"is_encoder_decoder": true,
|
| 16 |
+
"is_gated_act": true,
|
| 17 |
+
"layer_norm_epsilon": 1e-06,
|
| 18 |
+
"model_type": "mt5",
|
| 19 |
+
"num_decoder_layers": 24,
|
| 20 |
+
"num_heads": 16,
|
| 21 |
+
"num_layers": 24,
|
| 22 |
+
"output_past": true,
|
| 23 |
+
"pad_token_id": 0,
|
| 24 |
+
"relative_attention_max_distance": 128,
|
| 25 |
+
"relative_attention_num_buckets": 32,
|
| 26 |
+
"tie_word_embeddings": false,
|
| 27 |
+
"tokenizer_class": "T5Tokenizer",
|
| 28 |
+
"torch_dtype": "float32",
|
| 29 |
+
"transformers_version": "4.29.1",
|
| 30 |
+
"use_cache": true,
|
| 31 |
+
"vocab_size": 250112
|
| 32 |
+
}
|
large-1/generation_config.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"decoder_start_token_id": 0,
|
| 4 |
+
"eos_token_id": 1,
|
| 5 |
+
"pad_token_id": 0,
|
| 6 |
+
"transformers_version": "4.29.1"
|
| 7 |
+
}
|
large-1/output.txt
ADDED
|
@@ -0,0 +1,234 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{'loss': 29.3333, 'learning_rate': 1e-05, 'epoch': 0.03}
|
| 2 |
+
{'loss': 12.5737, 'learning_rate': 2e-05, 'epoch': 0.06}
|
| 3 |
+
{'loss': 2.3813, 'learning_rate': 1.9968976856735126e-05, 'epoch': 0.09}
|
| 4 |
+
{'loss': 0.2316, 'learning_rate': 1.993795371347025e-05, 'epoch': 0.12}
|
| 5 |
+
{'loss': 0.099, 'learning_rate': 1.9906930570205375e-05, 'epoch': 0.15}
|
| 6 |
+
{'loss': 0.0608, 'learning_rate': 1.98759074269405e-05, 'epoch': 0.19}
|
| 7 |
+
{'loss': 0.0565, 'learning_rate': 1.9844884283675623e-05, 'epoch': 0.22}
|
| 8 |
+
{'loss': 0.0435, 'learning_rate': 1.9813861140410748e-05, 'epoch': 0.25}
|
| 9 |
+
{'loss': 0.0354, 'learning_rate': 1.9782837997145872e-05, 'epoch': 0.28}
|
| 10 |
+
{'loss': 0.0339, 'learning_rate': 1.9751814853880996e-05, 'epoch': 0.31}
|
| 11 |
+
{'loss': 0.0294, 'learning_rate': 1.972079171061612e-05, 'epoch': 0.34}
|
| 12 |
+
{'loss': 0.035, 'learning_rate': 1.9689768567351245e-05, 'epoch': 0.37}
|
| 13 |
+
{'loss': 0.0515, 'learning_rate': 1.965874542408637e-05, 'epoch': 0.4}
|
| 14 |
+
{'loss': 0.0232, 'learning_rate': 1.9627722280821494e-05, 'epoch': 0.43}
|
| 15 |
+
{'loss': 0.0349, 'learning_rate': 1.9596699137556618e-05, 'epoch': 0.46}
|
| 16 |
+
{'loss': 0.0226, 'learning_rate': 1.9565675994291742e-05, 'epoch': 0.49}
|
| 17 |
+
{'loss': 0.0215, 'learning_rate': 1.9534652851026867e-05, 'epoch': 0.53}
|
| 18 |
+
{'loss': 0.0204, 'learning_rate': 1.9503629707761994e-05, 'epoch': 0.56}
|
| 19 |
+
{'loss': 0.0192, 'learning_rate': 1.9472606564497115e-05, 'epoch': 0.59}
|
| 20 |
+
{'loss': 0.0194, 'learning_rate': 1.9441583421232243e-05, 'epoch': 0.62}
|
| 21 |
+
{'loss': 0.0179, 'learning_rate': 1.9410560277967364e-05, 'epoch': 0.65}
|
| 22 |
+
{'loss': 0.017, 'learning_rate': 1.937953713470249e-05, 'epoch': 0.68}
|
| 23 |
+
{'loss': 0.0226, 'learning_rate': 1.9348513991437613e-05, 'epoch': 0.71}
|
| 24 |
+
{'loss': 0.016, 'learning_rate': 1.9317490848172737e-05, 'epoch': 0.74}
|
| 25 |
+
{'loss': 0.0154, 'learning_rate': 1.928646770490786e-05, 'epoch': 0.77}
|
| 26 |
+
{'loss': 0.0157, 'learning_rate': 1.9255444561642986e-05, 'epoch': 0.8}
|
| 27 |
+
{'loss': 0.0139, 'learning_rate': 1.9224421418378113e-05, 'epoch': 0.84}
|
| 28 |
+
{'loss': 0.0129, 'learning_rate': 1.9193398275113234e-05, 'epoch': 0.87}
|
| 29 |
+
{'loss': 0.0134, 'learning_rate': 1.9162375131848362e-05, 'epoch': 0.9}
|
| 30 |
+
{'loss': 0.0134, 'learning_rate': 1.9131351988583483e-05, 'epoch': 0.93}
|
| 31 |
+
{'loss': 0.0133, 'learning_rate': 1.910032884531861e-05, 'epoch': 0.96}
|
| 32 |
+
{'loss': 0.0133, 'learning_rate': 1.9069305702053732e-05, 'epoch': 0.99}
|
| 33 |
+
{'eval_loss': 0.007159320637583733, 'eval_runtime': 63.5558, 'eval_samples_per_second': 113.05, 'eval_steps_per_second': 7.08, 'epoch': 1.0}
|
| 34 |
+
{'loss': 0.0118, 'learning_rate': 1.903828255878886e-05, 'epoch': 1.02}
|
| 35 |
+
{'loss': 0.0114, 'learning_rate': 1.900725941552398e-05, 'epoch': 1.05}
|
| 36 |
+
{'loss': 0.0115, 'learning_rate': 1.8976236272259108e-05, 'epoch': 1.08}
|
| 37 |
+
{'loss': 0.0115, 'learning_rate': 1.8945213128994233e-05, 'epoch': 1.11}
|
| 38 |
+
{'loss': 0.0118, 'learning_rate': 1.8914189985729357e-05, 'epoch': 1.14}
|
| 39 |
+
{'loss': 0.0119, 'learning_rate': 1.888316684246448e-05, 'epoch': 1.18}
|
| 40 |
+
{'loss': 0.0117, 'learning_rate': 1.8852143699199606e-05, 'epoch': 1.21}
|
| 41 |
+
{'loss': 0.0113, 'learning_rate': 1.882112055593473e-05, 'epoch': 1.24}
|
| 42 |
+
{'loss': 0.0102, 'learning_rate': 1.8790097412669854e-05, 'epoch': 1.27}
|
| 43 |
+
{'loss': 0.0109, 'learning_rate': 1.875907426940498e-05, 'epoch': 1.3}
|
| 44 |
+
{'loss': 0.0096, 'learning_rate': 1.87280511261401e-05, 'epoch': 1.33}
|
| 45 |
+
{'loss': 0.0105, 'learning_rate': 1.8697027982875227e-05, 'epoch': 1.36}
|
| 46 |
+
{'loss': 0.0093, 'learning_rate': 1.866600483961035e-05, 'epoch': 1.39}
|
| 47 |
+
{'loss': 0.0096, 'learning_rate': 1.8634981696345476e-05, 'epoch': 1.42}
|
| 48 |
+
{'loss': 0.0091, 'learning_rate': 1.86039585530806e-05, 'epoch': 1.45}
|
| 49 |
+
{'loss': 0.0099, 'learning_rate': 1.8572935409815725e-05, 'epoch': 1.48}
|
| 50 |
+
{'loss': 0.009, 'learning_rate': 1.854191226655085e-05, 'epoch': 1.52}
|
| 51 |
+
{'loss': 0.0097, 'learning_rate': 1.8510889123285973e-05, 'epoch': 1.55}
|
| 52 |
+
{'loss': 0.0089, 'learning_rate': 1.8479865980021098e-05, 'epoch': 1.58}
|
| 53 |
+
{'loss': 0.0097, 'learning_rate': 1.8448842836756222e-05, 'epoch': 1.61}
|
| 54 |
+
{'loss': 0.0099, 'learning_rate': 1.8417819693491346e-05, 'epoch': 1.64}
|
| 55 |
+
{'loss': 0.0092, 'learning_rate': 1.838679655022647e-05, 'epoch': 1.67}
|
| 56 |
+
{'loss': 0.0094, 'learning_rate': 1.8355773406961595e-05, 'epoch': 1.7}
|
| 57 |
+
{'loss': 0.0087, 'learning_rate': 1.832475026369672e-05, 'epoch': 1.73}
|
| 58 |
+
{'loss': 0.0091, 'learning_rate': 1.8293727120431844e-05, 'epoch': 1.76}
|
| 59 |
+
{'loss': 0.0098, 'learning_rate': 1.8262703977166968e-05, 'epoch': 1.79}
|
| 60 |
+
{'loss': 0.0093, 'learning_rate': 1.8231680833902092e-05, 'epoch': 1.82}
|
| 61 |
+
{'loss': 0.0088, 'learning_rate': 1.8200657690637217e-05, 'epoch': 1.86}
|
| 62 |
+
{'loss': 0.008, 'learning_rate': 1.816963454737234e-05, 'epoch': 1.89}
|
| 63 |
+
{'loss': 0.0088, 'learning_rate': 1.8138611404107465e-05, 'epoch': 1.92}
|
| 64 |
+
{'loss': 0.0084, 'learning_rate': 1.810758826084259e-05, 'epoch': 1.95}
|
| 65 |
+
{'loss': 0.0087, 'learning_rate': 1.8076565117577714e-05, 'epoch': 1.98}
|
| 66 |
+
{'eval_loss': 0.005626102443784475, 'eval_runtime': 63.5514, 'eval_samples_per_second': 113.058, 'eval_steps_per_second': 7.081, 'epoch': 2.0}
|
| 67 |
+
{'loss': 0.0081, 'learning_rate': 1.804554197431284e-05, 'epoch': 2.01}
|
| 68 |
+
{'loss': 0.007, 'learning_rate': 1.8014518831047963e-05, 'epoch': 2.04}
|
| 69 |
+
{'loss': 0.0072, 'learning_rate': 1.7983495687783087e-05, 'epoch': 2.07}
|
| 70 |
+
{'loss': 0.0069, 'learning_rate': 1.795247254451821e-05, 'epoch': 2.1}
|
| 71 |
+
{'loss': 0.0072, 'learning_rate': 1.7921449401253336e-05, 'epoch': 2.13}
|
| 72 |
+
{'loss': 0.0067, 'learning_rate': 1.789042625798846e-05, 'epoch': 2.16}
|
| 73 |
+
{'loss': 0.007, 'learning_rate': 1.7859403114723584e-05, 'epoch': 2.2}
|
| 74 |
+
{'loss': 0.0072, 'learning_rate': 1.782837997145871e-05, 'epoch': 2.23}
|
| 75 |
+
{'loss': 0.0074, 'learning_rate': 1.7797356828193833e-05, 'epoch': 2.26}
|
| 76 |
+
{'loss': 0.0075, 'learning_rate': 1.7766333684928957e-05, 'epoch': 2.29}
|
| 77 |
+
{'loss': 0.0072, 'learning_rate': 1.7735310541664085e-05, 'epoch': 2.32}
|
| 78 |
+
{'loss': 0.0061, 'learning_rate': 1.7704287398399206e-05, 'epoch': 2.35}
|
| 79 |
+
{'loss': 0.0071, 'learning_rate': 1.7673264255134334e-05, 'epoch': 2.38}
|
| 80 |
+
{'loss': 0.0074, 'learning_rate': 1.7642241111869455e-05, 'epoch': 2.41}
|
| 81 |
+
{'loss': 0.0072, 'learning_rate': 1.7611217968604582e-05, 'epoch': 2.44}
|
| 82 |
+
{'loss': 0.0072, 'learning_rate': 1.7580194825339703e-05, 'epoch': 2.47}
|
| 83 |
+
{'loss': 0.0075, 'learning_rate': 1.754917168207483e-05, 'epoch': 2.51}
|
| 84 |
+
{'loss': 0.0069, 'learning_rate': 1.7518148538809952e-05, 'epoch': 2.54}
|
| 85 |
+
{'loss': 0.007, 'learning_rate': 1.7487125395545076e-05, 'epoch': 2.57}
|
| 86 |
+
{'loss': 0.0058, 'learning_rate': 1.7456102252280204e-05, 'epoch': 2.6}
|
| 87 |
+
{'loss': 0.0064, 'learning_rate': 1.7425079109015325e-05, 'epoch': 2.63}
|
| 88 |
+
{'loss': 0.0067, 'learning_rate': 1.7394055965750453e-05, 'epoch': 2.66}
|
| 89 |
+
{'loss': 0.0062, 'learning_rate': 1.7363032822485574e-05, 'epoch': 2.69}
|
| 90 |
+
{'loss': 0.0066, 'learning_rate': 1.73320096792207e-05, 'epoch': 2.72}
|
| 91 |
+
{'loss': 0.0066, 'learning_rate': 1.7300986535955822e-05, 'epoch': 2.75}
|
| 92 |
+
{'loss': 0.0071, 'learning_rate': 1.726996339269095e-05, 'epoch': 2.78}
|
| 93 |
+
{'loss': 0.0065, 'learning_rate': 1.723894024942607e-05, 'epoch': 2.81}
|
| 94 |
+
{'loss': 0.0065, 'learning_rate': 1.72079171061612e-05, 'epoch': 2.85}
|
| 95 |
+
{'loss': 0.0065, 'learning_rate': 1.7176893962896323e-05, 'epoch': 2.88}
|
| 96 |
+
{'loss': 0.0062, 'learning_rate': 1.7145870819631448e-05, 'epoch': 2.91}
|
| 97 |
+
{'loss': 0.0075, 'learning_rate': 1.7114847676366572e-05, 'epoch': 2.94}
|
| 98 |
+
{'loss': 0.0064, 'learning_rate': 1.7083824533101696e-05, 'epoch': 2.97}
|
| 99 |
+
{'loss': 0.0063, 'learning_rate': 1.705280138983682e-05, 'epoch': 3.0}
|
| 100 |
+
{'eval_loss': 0.005162048153579235, 'eval_runtime': 63.5102, 'eval_samples_per_second': 113.132, 'eval_steps_per_second': 7.085, 'epoch': 3.0}
|
| 101 |
+
{'loss': 0.0055, 'learning_rate': 1.7021778246571945e-05, 'epoch': 3.03}
|
| 102 |
+
{'loss': 0.0055, 'learning_rate': 1.699075510330707e-05, 'epoch': 3.06}
|
| 103 |
+
{'loss': 0.0059, 'learning_rate': 1.6959731960042194e-05, 'epoch': 3.09}
|
| 104 |
+
{'loss': 0.0052, 'learning_rate': 1.6928708816777318e-05, 'epoch': 3.12}
|
| 105 |
+
{'loss': 0.0053, 'learning_rate': 1.6897685673512442e-05, 'epoch': 3.15}
|
| 106 |
+
{'loss': 0.005, 'learning_rate': 1.6866662530247567e-05, 'epoch': 3.19}
|
| 107 |
+
{'loss': 0.0056, 'learning_rate': 1.683563938698269e-05, 'epoch': 3.22}
|
| 108 |
+
{'loss': 0.0051, 'learning_rate': 1.6804616243717815e-05, 'epoch': 3.25}
|
| 109 |
+
{'loss': 0.0053, 'learning_rate': 1.677359310045294e-05, 'epoch': 3.28}
|
| 110 |
+
{'loss': 0.0053, 'learning_rate': 1.6742569957188064e-05, 'epoch': 3.31}
|
| 111 |
+
{'loss': 0.0051, 'learning_rate': 1.6711546813923188e-05, 'epoch': 3.34}
|
| 112 |
+
{'loss': 0.0056, 'learning_rate': 1.6680523670658313e-05, 'epoch': 3.37}
|
| 113 |
+
{'loss': 0.0068, 'learning_rate': 1.6649500527393437e-05, 'epoch': 3.4}
|
| 114 |
+
{'loss': 0.0054, 'learning_rate': 1.661847738412856e-05, 'epoch': 3.43}
|
| 115 |
+
{'loss': 0.0055, 'learning_rate': 1.6587454240863686e-05, 'epoch': 3.46}
|
| 116 |
+
{'loss': 0.0056, 'learning_rate': 1.655643109759881e-05, 'epoch': 3.49}
|
| 117 |
+
{'loss': 0.0053, 'learning_rate': 1.6525407954333934e-05, 'epoch': 3.53}
|
| 118 |
+
{'loss': 0.0051, 'learning_rate': 1.649438481106906e-05, 'epoch': 3.56}
|
| 119 |
+
{'loss': 0.005, 'learning_rate': 1.6463361667804183e-05, 'epoch': 3.59}
|
| 120 |
+
{'loss': 0.0055, 'learning_rate': 1.6432338524539307e-05, 'epoch': 3.62}
|
| 121 |
+
{'loss': 0.0048, 'learning_rate': 1.640131538127443e-05, 'epoch': 3.65}
|
| 122 |
+
{'loss': 0.0052, 'learning_rate': 1.6370292238009556e-05, 'epoch': 3.68}
|
| 123 |
+
{'loss': 0.0048, 'learning_rate': 1.633926909474468e-05, 'epoch': 3.71}
|
| 124 |
+
{'loss': 0.0049, 'learning_rate': 1.6308245951479805e-05, 'epoch': 3.74}
|
| 125 |
+
{'loss': 0.0054, 'learning_rate': 1.627722280821493e-05, 'epoch': 3.77}
|
| 126 |
+
{'loss': 0.0052, 'learning_rate': 1.6246199664950053e-05, 'epoch': 3.8}
|
| 127 |
+
{'loss': 0.0053, 'learning_rate': 1.6215176521685178e-05, 'epoch': 3.83}
|
| 128 |
+
{'loss': 0.0052, 'learning_rate': 1.6184153378420302e-05, 'epoch': 3.87}
|
| 129 |
+
{'loss': 0.0053, 'learning_rate': 1.6153130235155426e-05, 'epoch': 3.9}
|
| 130 |
+
{'loss': 0.0052, 'learning_rate': 1.612210709189055e-05, 'epoch': 3.93}
|
| 131 |
+
{'loss': 0.0052, 'learning_rate': 1.6091083948625675e-05, 'epoch': 3.96}
|
| 132 |
+
{'loss': 0.0054, 'learning_rate': 1.60600608053608e-05, 'epoch': 3.99}
|
| 133 |
+
{'eval_loss': 0.004835214000195265, 'eval_runtime': 63.5993, 'eval_samples_per_second': 112.973, 'eval_steps_per_second': 7.076, 'epoch': 4.0}
|
| 134 |
+
{'loss': 0.0042, 'learning_rate': 1.6029037662095924e-05, 'epoch': 4.02}
|
| 135 |
+
{'loss': 0.0044, 'learning_rate': 1.5998014518831048e-05, 'epoch': 4.05}
|
| 136 |
+
{'loss': 0.0041, 'learning_rate': 1.5966991375566176e-05, 'epoch': 4.08}
|
| 137 |
+
{'loss': 0.0046, 'learning_rate': 1.5935968232301297e-05, 'epoch': 4.11}
|
| 138 |
+
{'loss': 0.004, 'learning_rate': 1.5904945089036424e-05, 'epoch': 4.14}
|
| 139 |
+
{'loss': 0.0044, 'learning_rate': 1.5873921945771545e-05, 'epoch': 4.18}
|
| 140 |
+
{'loss': 0.0047, 'learning_rate': 1.5842898802506673e-05, 'epoch': 4.21}
|
| 141 |
+
{'loss': 0.0043, 'learning_rate': 1.5811875659241794e-05, 'epoch': 4.24}
|
| 142 |
+
{'loss': 0.004, 'learning_rate': 1.5780852515976922e-05, 'epoch': 4.27}
|
| 143 |
+
{'loss': 0.0043, 'learning_rate': 1.5749829372712043e-05, 'epoch': 4.3}
|
| 144 |
+
{'loss': 0.0048, 'learning_rate': 1.571880622944717e-05, 'epoch': 4.33}
|
| 145 |
+
{'loss': 0.0044, 'learning_rate': 1.5687783086182295e-05, 'epoch': 4.36}
|
| 146 |
+
{'loss': 0.0042, 'learning_rate': 1.5656759942917416e-05, 'epoch': 4.39}
|
| 147 |
+
{'loss': 0.0041, 'learning_rate': 1.5625736799652544e-05, 'epoch': 4.42}
|
| 148 |
+
{'loss': 0.0045, 'learning_rate': 1.5594713656387664e-05, 'epoch': 4.45}
|
| 149 |
+
{'loss': 0.0041, 'learning_rate': 1.5563690513122792e-05, 'epoch': 4.48}
|
| 150 |
+
{'loss': 0.0044, 'learning_rate': 1.5532667369857913e-05, 'epoch': 4.52}
|
| 151 |
+
{'loss': 0.0039, 'learning_rate': 1.550164422659304e-05, 'epoch': 4.55}
|
| 152 |
+
{'loss': 0.0045, 'learning_rate': 1.5470621083328162e-05, 'epoch': 4.58}
|
| 153 |
+
{'loss': 0.0039, 'learning_rate': 1.543959794006329e-05, 'epoch': 4.61}
|
| 154 |
+
{'loss': 0.0044, 'learning_rate': 1.5408574796798414e-05, 'epoch': 4.64}
|
| 155 |
+
{'loss': 0.004, 'learning_rate': 1.5377551653533538e-05, 'epoch': 4.67}
|
| 156 |
+
{'loss': 0.0048, 'learning_rate': 1.5346528510268663e-05, 'epoch': 4.7}
|
| 157 |
+
{'loss': 0.004, 'learning_rate': 1.5315505367003787e-05, 'epoch': 4.73}
|
| 158 |
+
{'loss': 0.0046, 'learning_rate': 1.528448222373891e-05, 'epoch': 4.76}
|
| 159 |
+
{'loss': 0.0043, 'learning_rate': 1.5253459080474036e-05, 'epoch': 4.79}
|
| 160 |
+
{'loss': 0.0043, 'learning_rate': 1.5222435937209158e-05, 'epoch': 4.82}
|
| 161 |
+
{'loss': 0.0042, 'learning_rate': 1.5191412793944284e-05, 'epoch': 4.86}
|
| 162 |
+
{'loss': 0.0045, 'learning_rate': 1.5160389650679409e-05, 'epoch': 4.89}
|
| 163 |
+
{'loss': 0.004, 'learning_rate': 1.5129366507414533e-05, 'epoch': 4.92}
|
| 164 |
+
{'loss': 0.0037, 'learning_rate': 1.5098343364149657e-05, 'epoch': 4.95}
|
| 165 |
+
{'loss': 0.0045, 'learning_rate': 1.506732022088478e-05, 'epoch': 4.98}
|
| 166 |
+
{'eval_loss': 0.004868941381573677, 'eval_runtime': 63.5068, 'eval_samples_per_second': 113.137, 'eval_steps_per_second': 7.086, 'epoch': 5.0}
|
| 167 |
+
{'loss': 0.0038, 'learning_rate': 1.5036297077619906e-05, 'epoch': 5.01}
|
| 168 |
+
{'loss': 0.0035, 'learning_rate': 1.5005273934355029e-05, 'epoch': 5.04}
|
| 169 |
+
{'loss': 0.0035, 'learning_rate': 1.4974250791090155e-05, 'epoch': 5.07}
|
| 170 |
+
{'loss': 0.0037, 'learning_rate': 1.4943227647825277e-05, 'epoch': 5.1}
|
| 171 |
+
{'loss': 0.0031, 'learning_rate': 1.4912204504560403e-05, 'epoch': 5.13}
|
| 172 |
+
{'loss': 0.0035, 'learning_rate': 1.4881181361295528e-05, 'epoch': 5.16}
|
| 173 |
+
{'loss': 0.0037, 'learning_rate': 1.4850158218030652e-05, 'epoch': 5.2}
|
| 174 |
+
{'loss': 0.0033, 'learning_rate': 1.4819135074765776e-05, 'epoch': 5.23}
|
| 175 |
+
{'loss': 0.0039, 'learning_rate': 1.47881119315009e-05, 'epoch': 5.26}
|
| 176 |
+
{'loss': 0.0036, 'learning_rate': 1.4757088788236025e-05, 'epoch': 5.29}
|
| 177 |
+
{'loss': 0.0039, 'learning_rate': 1.4726065644971151e-05, 'epoch': 5.32}
|
| 178 |
+
{'loss': 0.0035, 'learning_rate': 1.4695042501706274e-05, 'epoch': 5.35}
|
| 179 |
+
{'loss': 0.0034, 'learning_rate': 1.46640193584414e-05, 'epoch': 5.38}
|
| 180 |
+
{'loss': 0.003, 'learning_rate': 1.4632996215176522e-05, 'epoch': 5.41}
|
| 181 |
+
{'loss': 0.0034, 'learning_rate': 1.4601973071911648e-05, 'epoch': 5.44}
|
| 182 |
+
{'loss': 0.0045, 'learning_rate': 1.4570949928646771e-05, 'epoch': 5.47}
|
| 183 |
+
{'loss': 0.0036, 'learning_rate': 1.4539926785381897e-05, 'epoch': 5.51}
|
| 184 |
+
{'loss': 0.0036, 'learning_rate': 1.450890364211702e-05, 'epoch': 5.54}
|
| 185 |
+
{'loss': 0.0037, 'learning_rate': 1.4477880498852146e-05, 'epoch': 5.57}
|
| 186 |
+
{'loss': 0.0035, 'learning_rate': 1.444685735558727e-05, 'epoch': 5.6}
|
| 187 |
+
{'loss': 0.0037, 'learning_rate': 1.4415834212322393e-05, 'epoch': 5.63}
|
| 188 |
+
{'loss': 0.0037, 'learning_rate': 1.4384811069057519e-05, 'epoch': 5.66}
|
| 189 |
+
{'loss': 0.0035, 'learning_rate': 1.4353787925792641e-05, 'epoch': 5.69}
|
| 190 |
+
{'loss': 0.0039, 'learning_rate': 1.4322764782527767e-05, 'epoch': 5.72}
|
| 191 |
+
{'loss': 0.0038, 'learning_rate': 1.429174163926289e-05, 'epoch': 5.75}
|
| 192 |
+
{'loss': 0.003, 'learning_rate': 1.4260718495998016e-05, 'epoch': 5.78}
|
| 193 |
+
{'loss': 0.0033, 'learning_rate': 1.4229695352733139e-05, 'epoch': 5.81}
|
| 194 |
+
{'loss': 0.004, 'learning_rate': 1.4198672209468265e-05, 'epoch': 5.85}
|
| 195 |
+
{'loss': 0.0031, 'learning_rate': 1.4167649066203389e-05, 'epoch': 5.88}
|
| 196 |
+
{'loss': 0.0034, 'learning_rate': 1.4136625922938513e-05, 'epoch': 5.91}
|
| 197 |
+
{'loss': 0.0032, 'learning_rate': 1.4105602779673638e-05, 'epoch': 5.94}
|
| 198 |
+
{'loss': 0.0036, 'learning_rate': 1.4074579636408762e-05, 'epoch': 5.97}
|
| 199 |
+
{'loss': 0.0035, 'learning_rate': 1.4043556493143886e-05, 'epoch': 6.0}
|
| 200 |
+
{'eval_loss': 0.004906239919364452, 'eval_runtime': 63.3798, 'eval_samples_per_second': 113.364, 'eval_steps_per_second': 7.1, 'epoch': 6.0}
|
| 201 |
+
{'loss': 0.0029, 'learning_rate': 1.4012533349879013e-05, 'epoch': 6.03}
|
| 202 |
+
{'loss': 0.0028, 'learning_rate': 1.3981510206614135e-05, 'epoch': 6.06}
|
| 203 |
+
{'loss': 0.0026, 'learning_rate': 1.3950487063349261e-05, 'epoch': 6.09}
|
| 204 |
+
{'loss': 0.0028, 'learning_rate': 1.3919463920084384e-05, 'epoch': 6.12}
|
| 205 |
+
{'loss': 0.0025, 'learning_rate': 1.388844077681951e-05, 'epoch': 6.15}
|
| 206 |
+
{'loss': 0.0027, 'learning_rate': 1.3857417633554633e-05, 'epoch': 6.19}
|
| 207 |
+
{'loss': 0.0029, 'learning_rate': 1.3826394490289757e-05, 'epoch': 6.22}
|
| 208 |
+
{'loss': 0.0029, 'learning_rate': 1.3795371347024881e-05, 'epoch': 6.25}
|
| 209 |
+
{'loss': 0.0027, 'learning_rate': 1.3764348203760006e-05, 'epoch': 6.28}
|
| 210 |
+
{'loss': 0.0032, 'learning_rate': 1.373332506049513e-05, 'epoch': 6.31}
|
| 211 |
+
{'loss': 0.0031, 'learning_rate': 1.3702301917230254e-05, 'epoch': 6.34}
|
| 212 |
+
{'loss': 0.0032, 'learning_rate': 1.367127877396538e-05, 'epoch': 6.37}
|
| 213 |
+
{'loss': 0.0029, 'learning_rate': 1.3640255630700503e-05, 'epoch': 6.4}
|
| 214 |
+
{'loss': 0.0031, 'learning_rate': 1.3609232487435629e-05, 'epoch': 6.43}
|
| 215 |
+
{'loss': 0.0029, 'learning_rate': 1.3578209344170752e-05, 'epoch': 6.46}
|
| 216 |
+
{'loss': 0.0031, 'learning_rate': 1.3547186200905878e-05, 'epoch': 6.49}
|
| 217 |
+
{'loss': 0.003, 'learning_rate': 1.3516163057641e-05, 'epoch': 6.53}
|
| 218 |
+
{'loss': 0.0033, 'learning_rate': 1.3485139914376126e-05, 'epoch': 6.56}
|
| 219 |
+
{'loss': 0.0028, 'learning_rate': 1.3454116771111249e-05, 'epoch': 6.59}
|
| 220 |
+
{'loss': 0.0029, 'learning_rate': 1.3423093627846375e-05, 'epoch': 6.62}
|
| 221 |
+
{'loss': 0.003, 'learning_rate': 1.33920704845815e-05, 'epoch': 6.65}
|
| 222 |
+
{'loss': 0.0027, 'learning_rate': 1.3361047341316624e-05, 'epoch': 6.68}
|
| 223 |
+
{'loss': 0.0029, 'learning_rate': 1.3330024198051748e-05, 'epoch': 6.71}
|
| 224 |
+
{'loss': 0.003, 'learning_rate': 1.3299001054786872e-05, 'epoch': 6.74}
|
| 225 |
+
{'loss': 0.003, 'learning_rate': 1.3267977911521997e-05, 'epoch': 6.77}
|
| 226 |
+
{'loss': 0.0031, 'learning_rate': 1.3236954768257123e-05, 'epoch': 6.8}
|
| 227 |
+
{'loss': 0.0027, 'learning_rate': 1.3205931624992245e-05, 'epoch': 6.83}
|
| 228 |
+
{'loss': 0.0034, 'learning_rate': 1.3174908481727368e-05, 'epoch': 6.87}
|
| 229 |
+
{'loss': 0.0029, 'learning_rate': 1.3143885338462494e-05, 'epoch': 6.9}
|
| 230 |
+
{'loss': 0.0028, 'learning_rate': 1.3112862195197618e-05, 'epoch': 6.93}
|
| 231 |
+
{'loss': 0.0027, 'learning_rate': 1.3081839051932743e-05, 'epoch': 6.96}
|
| 232 |
+
{'loss': 0.0032, 'learning_rate': 1.3050815908667867e-05, 'epoch': 6.99}
|
| 233 |
+
{'eval_loss': 0.005266720894724131, 'eval_runtime': 63.4285, 'eval_samples_per_second': 113.277, 'eval_steps_per_second': 7.095, 'epoch': 7.0}
|
| 234 |
+
{'train_runtime': 28268.4419, 'train_samples_per_second': 45.751, 'train_steps_per_second': 11.438, 'train_loss': 0.20489513011235258, 'epoch': 7.0}
|
large-1/pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:80f51a079ead19b7f0e9d82d46e113eee42e614b574c8b285b733727812a3be1
|
| 3 |
+
size 4918519065
|
large-1/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a3edc56f0f0e1d7be1ce3265d43ba3e04b7d248bf3e6aeba8adfbe111cabeb09
|
| 3 |
+
size 4027
|