Commit
·
6b63bf5
1
Parent(s):
25db008
Add 10-epoch checkpoint
Browse files- config.json +57 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +1 -0
- spiece.model +3 -0
- tokenizer_config.json +1 -0
- trainer_state.json +2886 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "t5-base",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"T5ForConditionalGeneration"
|
| 5 |
+
],
|
| 6 |
+
"d_ff": 3072,
|
| 7 |
+
"d_kv": 64,
|
| 8 |
+
"d_model": 768,
|
| 9 |
+
"decoder_start_token_id": 0,
|
| 10 |
+
"dropout_rate": 0.1,
|
| 11 |
+
"eos_token_id": 1,
|
| 12 |
+
"feed_forward_proj": "relu",
|
| 13 |
+
"initializer_factor": 1.0,
|
| 14 |
+
"is_encoder_decoder": true,
|
| 15 |
+
"layer_norm_epsilon": 1e-06,
|
| 16 |
+
"model_type": "t5",
|
| 17 |
+
"n_positions": 512,
|
| 18 |
+
"num_decoder_layers": 12,
|
| 19 |
+
"num_heads": 12,
|
| 20 |
+
"num_layers": 12,
|
| 21 |
+
"output_past": true,
|
| 22 |
+
"pad_token_id": 0,
|
| 23 |
+
"relative_attention_num_buckets": 32,
|
| 24 |
+
"task_specific_params": {
|
| 25 |
+
"summarization": {
|
| 26 |
+
"early_stopping": true,
|
| 27 |
+
"length_penalty": 2.0,
|
| 28 |
+
"max_length": 200,
|
| 29 |
+
"min_length": 30,
|
| 30 |
+
"no_repeat_ngram_size": 3,
|
| 31 |
+
"num_beams": 4,
|
| 32 |
+
"prefix": "summarize: "
|
| 33 |
+
},
|
| 34 |
+
"translation_en_to_de": {
|
| 35 |
+
"early_stopping": true,
|
| 36 |
+
"max_length": 300,
|
| 37 |
+
"num_beams": 4,
|
| 38 |
+
"prefix": "translate English to German: "
|
| 39 |
+
},
|
| 40 |
+
"translation_en_to_fr": {
|
| 41 |
+
"early_stopping": true,
|
| 42 |
+
"max_length": 300,
|
| 43 |
+
"num_beams": 4,
|
| 44 |
+
"prefix": "translate English to French: "
|
| 45 |
+
},
|
| 46 |
+
"translation_en_to_ro": {
|
| 47 |
+
"early_stopping": true,
|
| 48 |
+
"max_length": 300,
|
| 49 |
+
"num_beams": 4,
|
| 50 |
+
"prefix": "translate English to Romanian: "
|
| 51 |
+
}
|
| 52 |
+
},
|
| 53 |
+
"torch_dtype": "float32",
|
| 54 |
+
"transformers_version": "4.17.0",
|
| 55 |
+
"use_cache": true,
|
| 56 |
+
"vocab_size": 32128
|
| 57 |
+
}
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ee0a36760ed8b6eacee176aa9c7538bc5927bb95219824db24682ffb6f2b88ef
|
| 3 |
+
size 1783379645
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:043c99d5e94ca69717ef2f1904069ccce43b49ead13d5b814ab75cd6731d1650
|
| 3 |
+
size 891730879
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4f96e02b6aff5298795569d351f698a92d6f54ab70bead3702f1692ec05d87ff
|
| 3 |
+
size 14503
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c2add7c32f967635a54a0baf19baeb5865b7d21187f87839aaba79ce6f3e8107
|
| 3 |
+
size 623
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "additional_special_tokens": ["<extra_id_0>", "<extra_id_1>", "<extra_id_2>", "<extra_id_3>", "<extra_id_4>", "<extra_id_5>", "<extra_id_6>", "<extra_id_7>", "<extra_id_8>", "<extra_id_9>", "<extra_id_10>", "<extra_id_11>", "<extra_id_12>", "<extra_id_13>", "<extra_id_14>", "<extra_id_15>", "<extra_id_16>", "<extra_id_17>", "<extra_id_18>", "<extra_id_19>", "<extra_id_20>", "<extra_id_21>", "<extra_id_22>", "<extra_id_23>", "<extra_id_24>", "<extra_id_25>", "<extra_id_26>", "<extra_id_27>", "<extra_id_28>", "<extra_id_29>", "<extra_id_30>", "<extra_id_31>", "<extra_id_32>", "<extra_id_33>", "<extra_id_34>", "<extra_id_35>", "<extra_id_36>", "<extra_id_37>", "<extra_id_38>", "<extra_id_39>", "<extra_id_40>", "<extra_id_41>", "<extra_id_42>", "<extra_id_43>", "<extra_id_44>", "<extra_id_45>", "<extra_id_46>", "<extra_id_47>", "<extra_id_48>", "<extra_id_49>", "<extra_id_50>", "<extra_id_51>", "<extra_id_52>", "<extra_id_53>", "<extra_id_54>", "<extra_id_55>", "<extra_id_56>", "<extra_id_57>", "<extra_id_58>", "<extra_id_59>", "<extra_id_60>", "<extra_id_61>", "<extra_id_62>", "<extra_id_63>", "<extra_id_64>", "<extra_id_65>", "<extra_id_66>", "<extra_id_67>", "<extra_id_68>", "<extra_id_69>", "<extra_id_70>", "<extra_id_71>", "<extra_id_72>", "<extra_id_73>", "<extra_id_74>", "<extra_id_75>", "<extra_id_76>", "<extra_id_77>", "<extra_id_78>", "<extra_id_79>", "<extra_id_80>", "<extra_id_81>", "<extra_id_82>", "<extra_id_83>", "<extra_id_84>", "<extra_id_85>", "<extra_id_86>", "<extra_id_87>", "<extra_id_88>", "<extra_id_89>", "<extra_id_90>", "<extra_id_91>", "<extra_id_92>", "<extra_id_93>", "<extra_id_94>", "<extra_id_95>", "<extra_id_96>", "<extra_id_97>", "<extra_id_98>", "<extra_id_99>"]}
|
spiece.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86
|
| 3 |
+
size 791656
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "extra_ids": 100, "additional_special_tokens": ["<extra_id_0>", "<extra_id_1>", "<extra_id_2>", "<extra_id_3>", "<extra_id_4>", "<extra_id_5>", "<extra_id_6>", "<extra_id_7>", "<extra_id_8>", "<extra_id_9>", "<extra_id_10>", "<extra_id_11>", "<extra_id_12>", "<extra_id_13>", "<extra_id_14>", "<extra_id_15>", "<extra_id_16>", "<extra_id_17>", "<extra_id_18>", "<extra_id_19>", "<extra_id_20>", "<extra_id_21>", "<extra_id_22>", "<extra_id_23>", "<extra_id_24>", "<extra_id_25>", "<extra_id_26>", "<extra_id_27>", "<extra_id_28>", "<extra_id_29>", "<extra_id_30>", "<extra_id_31>", "<extra_id_32>", "<extra_id_33>", "<extra_id_34>", "<extra_id_35>", "<extra_id_36>", "<extra_id_37>", "<extra_id_38>", "<extra_id_39>", "<extra_id_40>", "<extra_id_41>", "<extra_id_42>", "<extra_id_43>", "<extra_id_44>", "<extra_id_45>", "<extra_id_46>", "<extra_id_47>", "<extra_id_48>", "<extra_id_49>", "<extra_id_50>", "<extra_id_51>", "<extra_id_52>", "<extra_id_53>", "<extra_id_54>", "<extra_id_55>", "<extra_id_56>", "<extra_id_57>", "<extra_id_58>", "<extra_id_59>", "<extra_id_60>", "<extra_id_61>", "<extra_id_62>", "<extra_id_63>", "<extra_id_64>", "<extra_id_65>", "<extra_id_66>", "<extra_id_67>", "<extra_id_68>", "<extra_id_69>", "<extra_id_70>", "<extra_id_71>", "<extra_id_72>", "<extra_id_73>", "<extra_id_74>", "<extra_id_75>", "<extra_id_76>", "<extra_id_77>", "<extra_id_78>", "<extra_id_79>", "<extra_id_80>", "<extra_id_81>", "<extra_id_82>", "<extra_id_83>", "<extra_id_84>", "<extra_id_85>", "<extra_id_86>", "<extra_id_87>", "<extra_id_88>", "<extra_id_89>", "<extra_id_90>", "<extra_id_91>", "<extra_id_92>", "<extra_id_93>", "<extra_id_94>", "<extra_id_95>", "<extra_id_96>", "<extra_id_97>", "<extra_id_98>", "<extra_id_99>"], "sp_model_kwargs": {}, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "t5-base", "tokenizer_class": "T5Tokenizer"}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,2886 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 10.0,
|
| 5 |
+
"global_step": 102820,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.05,
|
| 12 |
+
"learning_rate": 0.0001,
|
| 13 |
+
"loss": 2.9981,
|
| 14 |
+
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.05,
|
| 18 |
+
"eval_loss": 0.7217285633087158,
|
| 19 |
+
"eval_runtime": 1.4105,
|
| 20 |
+
"eval_samples_per_second": 708.956,
|
| 21 |
+
"eval_steps_per_second": 22.687,
|
| 22 |
+
"step": 500
|
| 23 |
+
},
|
| 24 |
+
{
|
| 25 |
+
"epoch": 0.1,
|
| 26 |
+
"learning_rate": 9.95113369820172e-05,
|
| 27 |
+
"loss": 0.3596,
|
| 28 |
+
"step": 1000
|
| 29 |
+
},
|
| 30 |
+
{
|
| 31 |
+
"epoch": 0.1,
|
| 32 |
+
"eval_loss": 0.683592677116394,
|
| 33 |
+
"eval_runtime": 1.425,
|
| 34 |
+
"eval_samples_per_second": 701.743,
|
| 35 |
+
"eval_steps_per_second": 22.456,
|
| 36 |
+
"step": 1000
|
| 37 |
+
},
|
| 38 |
+
{
|
| 39 |
+
"epoch": 0.15,
|
| 40 |
+
"learning_rate": 9.90226739640344e-05,
|
| 41 |
+
"loss": 0.3481,
|
| 42 |
+
"step": 1500
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"epoch": 0.15,
|
| 46 |
+
"eval_loss": 0.6578707695007324,
|
| 47 |
+
"eval_runtime": 1.4239,
|
| 48 |
+
"eval_samples_per_second": 702.301,
|
| 49 |
+
"eval_steps_per_second": 22.474,
|
| 50 |
+
"step": 1500
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.19,
|
| 54 |
+
"learning_rate": 9.85340109460516e-05,
|
| 55 |
+
"loss": 0.3381,
|
| 56 |
+
"step": 2000
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.19,
|
| 60 |
+
"eval_loss": 0.6479542255401611,
|
| 61 |
+
"eval_runtime": 1.42,
|
| 62 |
+
"eval_samples_per_second": 704.242,
|
| 63 |
+
"eval_steps_per_second": 22.536,
|
| 64 |
+
"step": 2000
|
| 65 |
+
},
|
| 66 |
+
{
|
| 67 |
+
"epoch": 0.24,
|
| 68 |
+
"learning_rate": 9.80453479280688e-05,
|
| 69 |
+
"loss": 0.3289,
|
| 70 |
+
"step": 2500
|
| 71 |
+
},
|
| 72 |
+
{
|
| 73 |
+
"epoch": 0.24,
|
| 74 |
+
"eval_loss": 0.6387728452682495,
|
| 75 |
+
"eval_runtime": 1.4329,
|
| 76 |
+
"eval_samples_per_second": 697.89,
|
| 77 |
+
"eval_steps_per_second": 22.332,
|
| 78 |
+
"step": 2500
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"epoch": 0.29,
|
| 82 |
+
"learning_rate": 9.7556684910086e-05,
|
| 83 |
+
"loss": 0.3279,
|
| 84 |
+
"step": 3000
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 0.29,
|
| 88 |
+
"eval_loss": 0.6298181414604187,
|
| 89 |
+
"eval_runtime": 1.4061,
|
| 90 |
+
"eval_samples_per_second": 711.206,
|
| 91 |
+
"eval_steps_per_second": 22.759,
|
| 92 |
+
"step": 3000
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.34,
|
| 96 |
+
"learning_rate": 9.706802189210322e-05,
|
| 97 |
+
"loss": 0.3217,
|
| 98 |
+
"step": 3500
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.34,
|
| 102 |
+
"eval_loss": 0.62165367603302,
|
| 103 |
+
"eval_runtime": 1.421,
|
| 104 |
+
"eval_samples_per_second": 703.748,
|
| 105 |
+
"eval_steps_per_second": 22.52,
|
| 106 |
+
"step": 3500
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 0.39,
|
| 110 |
+
"learning_rate": 9.65793588741204e-05,
|
| 111 |
+
"loss": 0.3165,
|
| 112 |
+
"step": 4000
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"epoch": 0.39,
|
| 116 |
+
"eval_loss": 0.616775393486023,
|
| 117 |
+
"eval_runtime": 1.4244,
|
| 118 |
+
"eval_samples_per_second": 702.031,
|
| 119 |
+
"eval_steps_per_second": 22.465,
|
| 120 |
+
"step": 4000
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 0.44,
|
| 124 |
+
"learning_rate": 9.609069585613761e-05,
|
| 125 |
+
"loss": 0.3188,
|
| 126 |
+
"step": 4500
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 0.44,
|
| 130 |
+
"eval_loss": 0.6099900007247925,
|
| 131 |
+
"eval_runtime": 1.4195,
|
| 132 |
+
"eval_samples_per_second": 704.489,
|
| 133 |
+
"eval_steps_per_second": 22.544,
|
| 134 |
+
"step": 4500
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 0.49,
|
| 138 |
+
"learning_rate": 9.560203283815481e-05,
|
| 139 |
+
"loss": 0.3022,
|
| 140 |
+
"step": 5000
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 0.49,
|
| 144 |
+
"eval_loss": 0.6031085252761841,
|
| 145 |
+
"eval_runtime": 1.4165,
|
| 146 |
+
"eval_samples_per_second": 705.968,
|
| 147 |
+
"eval_steps_per_second": 22.591,
|
| 148 |
+
"step": 5000
|
| 149 |
+
},
|
| 150 |
+
{
|
| 151 |
+
"epoch": 0.53,
|
| 152 |
+
"learning_rate": 9.511336982017201e-05,
|
| 153 |
+
"loss": 0.3167,
|
| 154 |
+
"step": 5500
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 0.53,
|
| 158 |
+
"eval_loss": 0.5986317992210388,
|
| 159 |
+
"eval_runtime": 1.413,
|
| 160 |
+
"eval_samples_per_second": 707.704,
|
| 161 |
+
"eval_steps_per_second": 22.647,
|
| 162 |
+
"step": 5500
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 0.58,
|
| 166 |
+
"learning_rate": 9.462470680218921e-05,
|
| 167 |
+
"loss": 0.3123,
|
| 168 |
+
"step": 6000
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 0.58,
|
| 172 |
+
"eval_loss": 0.594712495803833,
|
| 173 |
+
"eval_runtime": 1.4076,
|
| 174 |
+
"eval_samples_per_second": 710.451,
|
| 175 |
+
"eval_steps_per_second": 22.734,
|
| 176 |
+
"step": 6000
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 0.63,
|
| 180 |
+
"learning_rate": 9.413604378420641e-05,
|
| 181 |
+
"loss": 0.3102,
|
| 182 |
+
"step": 6500
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 0.63,
|
| 186 |
+
"eval_loss": 0.589926540851593,
|
| 187 |
+
"eval_runtime": 1.4215,
|
| 188 |
+
"eval_samples_per_second": 703.5,
|
| 189 |
+
"eval_steps_per_second": 22.512,
|
| 190 |
+
"step": 6500
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 0.68,
|
| 194 |
+
"learning_rate": 9.364738076622361e-05,
|
| 195 |
+
"loss": 0.3029,
|
| 196 |
+
"step": 7000
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 0.68,
|
| 200 |
+
"eval_loss": 0.5852935910224915,
|
| 201 |
+
"eval_runtime": 1.4145,
|
| 202 |
+
"eval_samples_per_second": 706.961,
|
| 203 |
+
"eval_steps_per_second": 22.623,
|
| 204 |
+
"step": 7000
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 0.73,
|
| 208 |
+
"learning_rate": 9.315871774824082e-05,
|
| 209 |
+
"loss": 0.2999,
|
| 210 |
+
"step": 7500
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 0.73,
|
| 214 |
+
"eval_loss": 0.5810648798942566,
|
| 215 |
+
"eval_runtime": 1.4374,
|
| 216 |
+
"eval_samples_per_second": 695.724,
|
| 217 |
+
"eval_steps_per_second": 22.263,
|
| 218 |
+
"step": 7500
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 0.78,
|
| 222 |
+
"learning_rate": 9.267005473025801e-05,
|
| 223 |
+
"loss": 0.2898,
|
| 224 |
+
"step": 8000
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 0.78,
|
| 228 |
+
"eval_loss": 0.5774234533309937,
|
| 229 |
+
"eval_runtime": 1.422,
|
| 230 |
+
"eval_samples_per_second": 703.256,
|
| 231 |
+
"eval_steps_per_second": 22.504,
|
| 232 |
+
"step": 8000
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"epoch": 0.83,
|
| 236 |
+
"learning_rate": 9.218139171227522e-05,
|
| 237 |
+
"loss": 0.2924,
|
| 238 |
+
"step": 8500
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"epoch": 0.83,
|
| 242 |
+
"eval_loss": 0.5741690993309021,
|
| 243 |
+
"eval_runtime": 1.4369,
|
| 244 |
+
"eval_samples_per_second": 695.963,
|
| 245 |
+
"eval_steps_per_second": 22.271,
|
| 246 |
+
"step": 8500
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 0.88,
|
| 250 |
+
"learning_rate": 9.169272869429242e-05,
|
| 251 |
+
"loss": 0.2965,
|
| 252 |
+
"step": 9000
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 0.88,
|
| 256 |
+
"eval_loss": 0.5683675408363342,
|
| 257 |
+
"eval_runtime": 1.4175,
|
| 258 |
+
"eval_samples_per_second": 705.474,
|
| 259 |
+
"eval_steps_per_second": 22.575,
|
| 260 |
+
"step": 9000
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 0.92,
|
| 264 |
+
"learning_rate": 9.120406567630962e-05,
|
| 265 |
+
"loss": 0.3003,
|
| 266 |
+
"step": 9500
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 0.92,
|
| 270 |
+
"eval_loss": 0.5660465359687805,
|
| 271 |
+
"eval_runtime": 1.4225,
|
| 272 |
+
"eval_samples_per_second": 703.011,
|
| 273 |
+
"eval_steps_per_second": 22.496,
|
| 274 |
+
"step": 9500
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 0.97,
|
| 278 |
+
"learning_rate": 9.071540265832682e-05,
|
| 279 |
+
"loss": 0.2877,
|
| 280 |
+
"step": 10000
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 0.97,
|
| 284 |
+
"eval_loss": 0.5636941194534302,
|
| 285 |
+
"eval_runtime": 1.4249,
|
| 286 |
+
"eval_samples_per_second": 701.786,
|
| 287 |
+
"eval_steps_per_second": 22.457,
|
| 288 |
+
"step": 10000
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 1.02,
|
| 292 |
+
"learning_rate": 9.022673964034402e-05,
|
| 293 |
+
"loss": 0.28,
|
| 294 |
+
"step": 10500
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 1.02,
|
| 298 |
+
"eval_loss": 0.5614505410194397,
|
| 299 |
+
"eval_runtime": 1.418,
|
| 300 |
+
"eval_samples_per_second": 705.226,
|
| 301 |
+
"eval_steps_per_second": 22.567,
|
| 302 |
+
"step": 10500
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 1.07,
|
| 306 |
+
"learning_rate": 8.973807662236122e-05,
|
| 307 |
+
"loss": 0.2596,
|
| 308 |
+
"step": 11000
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 1.07,
|
| 312 |
+
"eval_loss": 0.560372531414032,
|
| 313 |
+
"eval_runtime": 1.419,
|
| 314 |
+
"eval_samples_per_second": 704.735,
|
| 315 |
+
"eval_steps_per_second": 22.552,
|
| 316 |
+
"step": 11000
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 1.12,
|
| 320 |
+
"learning_rate": 8.924941360437843e-05,
|
| 321 |
+
"loss": 0.2629,
|
| 322 |
+
"step": 11500
|
| 323 |
+
},
|
| 324 |
+
{
|
| 325 |
+
"epoch": 1.12,
|
| 326 |
+
"eval_loss": 0.5570399165153503,
|
| 327 |
+
"eval_runtime": 1.422,
|
| 328 |
+
"eval_samples_per_second": 703.254,
|
| 329 |
+
"eval_steps_per_second": 22.504,
|
| 330 |
+
"step": 11500
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 1.17,
|
| 334 |
+
"learning_rate": 8.876075058639562e-05,
|
| 335 |
+
"loss": 0.2588,
|
| 336 |
+
"step": 12000
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 1.17,
|
| 340 |
+
"eval_loss": 0.5555282831192017,
|
| 341 |
+
"eval_runtime": 1.4115,
|
| 342 |
+
"eval_samples_per_second": 708.456,
|
| 343 |
+
"eval_steps_per_second": 22.671,
|
| 344 |
+
"step": 12000
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 1.22,
|
| 348 |
+
"learning_rate": 8.827208756841283e-05,
|
| 349 |
+
"loss": 0.2623,
|
| 350 |
+
"step": 12500
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 1.22,
|
| 354 |
+
"eval_loss": 0.5514973402023315,
|
| 355 |
+
"eval_runtime": 1.4195,
|
| 356 |
+
"eval_samples_per_second": 704.486,
|
| 357 |
+
"eval_steps_per_second": 22.544,
|
| 358 |
+
"step": 12500
|
| 359 |
+
},
|
| 360 |
+
{
|
| 361 |
+
"epoch": 1.26,
|
| 362 |
+
"learning_rate": 8.778342455043003e-05,
|
| 363 |
+
"loss": 0.2553,
|
| 364 |
+
"step": 13000
|
| 365 |
+
},
|
| 366 |
+
{
|
| 367 |
+
"epoch": 1.26,
|
| 368 |
+
"eval_loss": 0.5486002564430237,
|
| 369 |
+
"eval_runtime": 1.42,
|
| 370 |
+
"eval_samples_per_second": 704.24,
|
| 371 |
+
"eval_steps_per_second": 22.536,
|
| 372 |
+
"step": 13000
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"epoch": 1.31,
|
| 376 |
+
"learning_rate": 8.729476153244723e-05,
|
| 377 |
+
"loss": 0.262,
|
| 378 |
+
"step": 13500
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 1.31,
|
| 382 |
+
"eval_loss": 0.5457084774971008,
|
| 383 |
+
"eval_runtime": 1.4135,
|
| 384 |
+
"eval_samples_per_second": 707.481,
|
| 385 |
+
"eval_steps_per_second": 22.639,
|
| 386 |
+
"step": 13500
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 1.36,
|
| 390 |
+
"learning_rate": 8.680609851446443e-05,
|
| 391 |
+
"loss": 0.2613,
|
| 392 |
+
"step": 14000
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 1.36,
|
| 396 |
+
"eval_loss": 0.5417377948760986,
|
| 397 |
+
"eval_runtime": 1.4156,
|
| 398 |
+
"eval_samples_per_second": 706.429,
|
| 399 |
+
"eval_steps_per_second": 22.606,
|
| 400 |
+
"step": 14000
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"epoch": 1.41,
|
| 404 |
+
"learning_rate": 8.631743549648163e-05,
|
| 405 |
+
"loss": 0.2679,
|
| 406 |
+
"step": 14500
|
| 407 |
+
},
|
| 408 |
+
{
|
| 409 |
+
"epoch": 1.41,
|
| 410 |
+
"eval_loss": 0.5402753949165344,
|
| 411 |
+
"eval_runtime": 1.4211,
|
| 412 |
+
"eval_samples_per_second": 703.665,
|
| 413 |
+
"eval_steps_per_second": 22.517,
|
| 414 |
+
"step": 14500
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 1.46,
|
| 418 |
+
"learning_rate": 8.582877247849883e-05,
|
| 419 |
+
"loss": 0.2537,
|
| 420 |
+
"step": 15000
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 1.46,
|
| 424 |
+
"eval_loss": 0.5380659699440002,
|
| 425 |
+
"eval_runtime": 1.4234,
|
| 426 |
+
"eval_samples_per_second": 702.521,
|
| 427 |
+
"eval_steps_per_second": 22.481,
|
| 428 |
+
"step": 15000
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 1.51,
|
| 432 |
+
"learning_rate": 8.534010946051603e-05,
|
| 433 |
+
"loss": 0.2502,
|
| 434 |
+
"step": 15500
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 1.51,
|
| 438 |
+
"eval_loss": 0.532864511013031,
|
| 439 |
+
"eval_runtime": 1.4508,
|
| 440 |
+
"eval_samples_per_second": 689.292,
|
| 441 |
+
"eval_steps_per_second": 22.057,
|
| 442 |
+
"step": 15500
|
| 443 |
+
},
|
| 444 |
+
{
|
| 445 |
+
"epoch": 1.56,
|
| 446 |
+
"learning_rate": 8.485144644253323e-05,
|
| 447 |
+
"loss": 0.2594,
|
| 448 |
+
"step": 16000
|
| 449 |
+
},
|
| 450 |
+
{
|
| 451 |
+
"epoch": 1.56,
|
| 452 |
+
"eval_loss": 0.5308486223220825,
|
| 453 |
+
"eval_runtime": 1.4175,
|
| 454 |
+
"eval_samples_per_second": 705.473,
|
| 455 |
+
"eval_steps_per_second": 22.575,
|
| 456 |
+
"step": 16000
|
| 457 |
+
},
|
| 458 |
+
{
|
| 459 |
+
"epoch": 1.6,
|
| 460 |
+
"learning_rate": 8.436278342455043e-05,
|
| 461 |
+
"loss": 0.2495,
|
| 462 |
+
"step": 16500
|
| 463 |
+
},
|
| 464 |
+
{
|
| 465 |
+
"epoch": 1.6,
|
| 466 |
+
"eval_loss": 0.5297316312789917,
|
| 467 |
+
"eval_runtime": 1.416,
|
| 468 |
+
"eval_samples_per_second": 706.219,
|
| 469 |
+
"eval_steps_per_second": 22.599,
|
| 470 |
+
"step": 16500
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 1.65,
|
| 474 |
+
"learning_rate": 8.387412040656764e-05,
|
| 475 |
+
"loss": 0.2499,
|
| 476 |
+
"step": 17000
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 1.65,
|
| 480 |
+
"eval_loss": 0.5281020402908325,
|
| 481 |
+
"eval_runtime": 1.4056,
|
| 482 |
+
"eval_samples_per_second": 711.457,
|
| 483 |
+
"eval_steps_per_second": 22.767,
|
| 484 |
+
"step": 17000
|
| 485 |
+
},
|
| 486 |
+
{
|
| 487 |
+
"epoch": 1.7,
|
| 488 |
+
"learning_rate": 8.338545738858483e-05,
|
| 489 |
+
"loss": 0.2578,
|
| 490 |
+
"step": 17500
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 1.7,
|
| 494 |
+
"eval_loss": 0.5247856378555298,
|
| 495 |
+
"eval_runtime": 1.4135,
|
| 496 |
+
"eval_samples_per_second": 707.459,
|
| 497 |
+
"eval_steps_per_second": 22.639,
|
| 498 |
+
"step": 17500
|
| 499 |
+
},
|
| 500 |
+
{
|
| 501 |
+
"epoch": 1.75,
|
| 502 |
+
"learning_rate": 8.289679437060204e-05,
|
| 503 |
+
"loss": 0.2497,
|
| 504 |
+
"step": 18000
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 1.75,
|
| 508 |
+
"eval_loss": 0.5230081677436829,
|
| 509 |
+
"eval_runtime": 1.4438,
|
| 510 |
+
"eval_samples_per_second": 692.611,
|
| 511 |
+
"eval_steps_per_second": 22.164,
|
| 512 |
+
"step": 18000
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 1.8,
|
| 516 |
+
"learning_rate": 8.240813135261924e-05,
|
| 517 |
+
"loss": 0.2565,
|
| 518 |
+
"step": 18500
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 1.8,
|
| 522 |
+
"eval_loss": 0.5200880765914917,
|
| 523 |
+
"eval_runtime": 1.4398,
|
| 524 |
+
"eval_samples_per_second": 694.522,
|
| 525 |
+
"eval_steps_per_second": 22.225,
|
| 526 |
+
"step": 18500
|
| 527 |
+
},
|
| 528 |
+
{
|
| 529 |
+
"epoch": 1.85,
|
| 530 |
+
"learning_rate": 8.191946833463644e-05,
|
| 531 |
+
"loss": 0.2523,
|
| 532 |
+
"step": 19000
|
| 533 |
+
},
|
| 534 |
+
{
|
| 535 |
+
"epoch": 1.85,
|
| 536 |
+
"eval_loss": 0.5170234441757202,
|
| 537 |
+
"eval_runtime": 1.4299,
|
| 538 |
+
"eval_samples_per_second": 699.349,
|
| 539 |
+
"eval_steps_per_second": 22.379,
|
| 540 |
+
"step": 19000
|
| 541 |
+
},
|
| 542 |
+
{
|
| 543 |
+
"epoch": 1.9,
|
| 544 |
+
"learning_rate": 8.143080531665364e-05,
|
| 545 |
+
"loss": 0.2501,
|
| 546 |
+
"step": 19500
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 1.9,
|
| 550 |
+
"eval_loss": 0.5144360065460205,
|
| 551 |
+
"eval_runtime": 1.4239,
|
| 552 |
+
"eval_samples_per_second": 702.275,
|
| 553 |
+
"eval_steps_per_second": 22.473,
|
| 554 |
+
"step": 19500
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 1.95,
|
| 558 |
+
"learning_rate": 8.094214229867084e-05,
|
| 559 |
+
"loss": 0.2488,
|
| 560 |
+
"step": 20000
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 1.95,
|
| 564 |
+
"eval_loss": 0.5127125382423401,
|
| 565 |
+
"eval_runtime": 1.4244,
|
| 566 |
+
"eval_samples_per_second": 702.027,
|
| 567 |
+
"eval_steps_per_second": 22.465,
|
| 568 |
+
"step": 20000
|
| 569 |
+
},
|
| 570 |
+
{
|
| 571 |
+
"epoch": 1.99,
|
| 572 |
+
"learning_rate": 8.045347928068804e-05,
|
| 573 |
+
"loss": 0.2465,
|
| 574 |
+
"step": 20500
|
| 575 |
+
},
|
| 576 |
+
{
|
| 577 |
+
"epoch": 1.99,
|
| 578 |
+
"eval_loss": 0.511444091796875,
|
| 579 |
+
"eval_runtime": 1.422,
|
| 580 |
+
"eval_samples_per_second": 703.257,
|
| 581 |
+
"eval_steps_per_second": 22.504,
|
| 582 |
+
"step": 20500
|
| 583 |
+
},
|
| 584 |
+
{
|
| 585 |
+
"epoch": 2.04,
|
| 586 |
+
"learning_rate": 7.996481626270525e-05,
|
| 587 |
+
"loss": 0.2282,
|
| 588 |
+
"step": 21000
|
| 589 |
+
},
|
| 590 |
+
{
|
| 591 |
+
"epoch": 2.04,
|
| 592 |
+
"eval_loss": 0.512248158454895,
|
| 593 |
+
"eval_runtime": 1.419,
|
| 594 |
+
"eval_samples_per_second": 704.734,
|
| 595 |
+
"eval_steps_per_second": 22.551,
|
| 596 |
+
"step": 21000
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 2.09,
|
| 600 |
+
"learning_rate": 7.947615324472244e-05,
|
| 601 |
+
"loss": 0.2251,
|
| 602 |
+
"step": 21500
|
| 603 |
+
},
|
| 604 |
+
{
|
| 605 |
+
"epoch": 2.09,
|
| 606 |
+
"eval_loss": 0.5102840065956116,
|
| 607 |
+
"eval_runtime": 1.414,
|
| 608 |
+
"eval_samples_per_second": 707.209,
|
| 609 |
+
"eval_steps_per_second": 22.631,
|
| 610 |
+
"step": 21500
|
| 611 |
+
},
|
| 612 |
+
{
|
| 613 |
+
"epoch": 2.14,
|
| 614 |
+
"learning_rate": 7.898749022673965e-05,
|
| 615 |
+
"loss": 0.2172,
|
| 616 |
+
"step": 22000
|
| 617 |
+
},
|
| 618 |
+
{
|
| 619 |
+
"epoch": 2.14,
|
| 620 |
+
"eval_loss": 0.5100817680358887,
|
| 621 |
+
"eval_runtime": 1.4279,
|
| 622 |
+
"eval_samples_per_second": 700.321,
|
| 623 |
+
"eval_steps_per_second": 22.41,
|
| 624 |
+
"step": 22000
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 2.19,
|
| 628 |
+
"learning_rate": 7.849882720875685e-05,
|
| 629 |
+
"loss": 0.2143,
|
| 630 |
+
"step": 22500
|
| 631 |
+
},
|
| 632 |
+
{
|
| 633 |
+
"epoch": 2.19,
|
| 634 |
+
"eval_loss": 0.509198784828186,
|
| 635 |
+
"eval_runtime": 1.4398,
|
| 636 |
+
"eval_samples_per_second": 694.524,
|
| 637 |
+
"eval_steps_per_second": 22.225,
|
| 638 |
+
"step": 22500
|
| 639 |
+
},
|
| 640 |
+
{
|
| 641 |
+
"epoch": 2.24,
|
| 642 |
+
"learning_rate": 7.801016419077405e-05,
|
| 643 |
+
"loss": 0.2215,
|
| 644 |
+
"step": 23000
|
| 645 |
+
},
|
| 646 |
+
{
|
| 647 |
+
"epoch": 2.24,
|
| 648 |
+
"eval_loss": 0.5054255127906799,
|
| 649 |
+
"eval_runtime": 1.4289,
|
| 650 |
+
"eval_samples_per_second": 699.834,
|
| 651 |
+
"eval_steps_per_second": 22.395,
|
| 652 |
+
"step": 23000
|
| 653 |
+
},
|
| 654 |
+
{
|
| 655 |
+
"epoch": 2.29,
|
| 656 |
+
"learning_rate": 7.752150117279125e-05,
|
| 657 |
+
"loss": 0.2175,
|
| 658 |
+
"step": 23500
|
| 659 |
+
},
|
| 660 |
+
{
|
| 661 |
+
"epoch": 2.29,
|
| 662 |
+
"eval_loss": 0.5042800307273865,
|
| 663 |
+
"eval_runtime": 1.4234,
|
| 664 |
+
"eval_samples_per_second": 702.521,
|
| 665 |
+
"eval_steps_per_second": 22.481,
|
| 666 |
+
"step": 23500
|
| 667 |
+
},
|
| 668 |
+
{
|
| 669 |
+
"epoch": 2.33,
|
| 670 |
+
"learning_rate": 7.703283815480845e-05,
|
| 671 |
+
"loss": 0.2181,
|
| 672 |
+
"step": 24000
|
| 673 |
+
},
|
| 674 |
+
{
|
| 675 |
+
"epoch": 2.33,
|
| 676 |
+
"eval_loss": 0.5006986260414124,
|
| 677 |
+
"eval_runtime": 1.419,
|
| 678 |
+
"eval_samples_per_second": 704.732,
|
| 679 |
+
"eval_steps_per_second": 22.551,
|
| 680 |
+
"step": 24000
|
| 681 |
+
},
|
| 682 |
+
{
|
| 683 |
+
"epoch": 2.38,
|
| 684 |
+
"learning_rate": 7.654417513682565e-05,
|
| 685 |
+
"loss": 0.2229,
|
| 686 |
+
"step": 24500
|
| 687 |
+
},
|
| 688 |
+
{
|
| 689 |
+
"epoch": 2.38,
|
| 690 |
+
"eval_loss": 0.49812304973602295,
|
| 691 |
+
"eval_runtime": 1.4369,
|
| 692 |
+
"eval_samples_per_second": 695.962,
|
| 693 |
+
"eval_steps_per_second": 22.271,
|
| 694 |
+
"step": 24500
|
| 695 |
+
},
|
| 696 |
+
{
|
| 697 |
+
"epoch": 2.43,
|
| 698 |
+
"learning_rate": 7.605551211884286e-05,
|
| 699 |
+
"loss": 0.2103,
|
| 700 |
+
"step": 25000
|
| 701 |
+
},
|
| 702 |
+
{
|
| 703 |
+
"epoch": 2.43,
|
| 704 |
+
"eval_loss": 0.49662986397743225,
|
| 705 |
+
"eval_runtime": 1.4066,
|
| 706 |
+
"eval_samples_per_second": 710.955,
|
| 707 |
+
"eval_steps_per_second": 22.751,
|
| 708 |
+
"step": 25000
|
| 709 |
+
},
|
| 710 |
+
{
|
| 711 |
+
"epoch": 2.48,
|
| 712 |
+
"learning_rate": 7.556684910086005e-05,
|
| 713 |
+
"loss": 0.2195,
|
| 714 |
+
"step": 25500
|
| 715 |
+
},
|
| 716 |
+
{
|
| 717 |
+
"epoch": 2.48,
|
| 718 |
+
"eval_loss": 0.4949464499950409,
|
| 719 |
+
"eval_runtime": 1.4145,
|
| 720 |
+
"eval_samples_per_second": 706.961,
|
| 721 |
+
"eval_steps_per_second": 22.623,
|
| 722 |
+
"step": 25500
|
| 723 |
+
},
|
| 724 |
+
{
|
| 725 |
+
"epoch": 2.53,
|
| 726 |
+
"learning_rate": 7.507818608287726e-05,
|
| 727 |
+
"loss": 0.2197,
|
| 728 |
+
"step": 26000
|
| 729 |
+
},
|
| 730 |
+
{
|
| 731 |
+
"epoch": 2.53,
|
| 732 |
+
"eval_loss": 0.49265730381011963,
|
| 733 |
+
"eval_runtime": 1.4441,
|
| 734 |
+
"eval_samples_per_second": 692.484,
|
| 735 |
+
"eval_steps_per_second": 22.159,
|
| 736 |
+
"step": 26000
|
| 737 |
+
},
|
| 738 |
+
{
|
| 739 |
+
"epoch": 2.58,
|
| 740 |
+
"learning_rate": 7.458952306489444e-05,
|
| 741 |
+
"loss": 0.2163,
|
| 742 |
+
"step": 26500
|
| 743 |
+
},
|
| 744 |
+
{
|
| 745 |
+
"epoch": 2.58,
|
| 746 |
+
"eval_loss": 0.4933662414550781,
|
| 747 |
+
"eval_runtime": 1.4196,
|
| 748 |
+
"eval_samples_per_second": 704.41,
|
| 749 |
+
"eval_steps_per_second": 22.541,
|
| 750 |
+
"step": 26500
|
| 751 |
+
},
|
| 752 |
+
{
|
| 753 |
+
"epoch": 2.63,
|
| 754 |
+
"learning_rate": 7.410086004691166e-05,
|
| 755 |
+
"loss": 0.2203,
|
| 756 |
+
"step": 27000
|
| 757 |
+
},
|
| 758 |
+
{
|
| 759 |
+
"epoch": 2.63,
|
| 760 |
+
"eval_loss": 0.4912818670272827,
|
| 761 |
+
"eval_runtime": 1.4225,
|
| 762 |
+
"eval_samples_per_second": 703.011,
|
| 763 |
+
"eval_steps_per_second": 22.496,
|
| 764 |
+
"step": 27000
|
| 765 |
+
},
|
| 766 |
+
{
|
| 767 |
+
"epoch": 2.67,
|
| 768 |
+
"learning_rate": 7.361219702892886e-05,
|
| 769 |
+
"loss": 0.2131,
|
| 770 |
+
"step": 27500
|
| 771 |
+
},
|
| 772 |
+
{
|
| 773 |
+
"epoch": 2.67,
|
| 774 |
+
"eval_loss": 0.49019622802734375,
|
| 775 |
+
"eval_runtime": 1.4165,
|
| 776 |
+
"eval_samples_per_second": 705.97,
|
| 777 |
+
"eval_steps_per_second": 22.591,
|
| 778 |
+
"step": 27500
|
| 779 |
+
},
|
| 780 |
+
{
|
| 781 |
+
"epoch": 2.72,
|
| 782 |
+
"learning_rate": 7.312353401094606e-05,
|
| 783 |
+
"loss": 0.2192,
|
| 784 |
+
"step": 28000
|
| 785 |
+
},
|
| 786 |
+
{
|
| 787 |
+
"epoch": 2.72,
|
| 788 |
+
"eval_loss": 0.48748642206192017,
|
| 789 |
+
"eval_runtime": 1.419,
|
| 790 |
+
"eval_samples_per_second": 704.732,
|
| 791 |
+
"eval_steps_per_second": 22.551,
|
| 792 |
+
"step": 28000
|
| 793 |
+
},
|
| 794 |
+
{
|
| 795 |
+
"epoch": 2.77,
|
| 796 |
+
"learning_rate": 7.263487099296326e-05,
|
| 797 |
+
"loss": 0.216,
|
| 798 |
+
"step": 28500
|
| 799 |
+
},
|
| 800 |
+
{
|
| 801 |
+
"epoch": 2.77,
|
| 802 |
+
"eval_loss": 0.4867847263813019,
|
| 803 |
+
"eval_runtime": 1.4078,
|
| 804 |
+
"eval_samples_per_second": 710.341,
|
| 805 |
+
"eval_steps_per_second": 22.731,
|
| 806 |
+
"step": 28500
|
| 807 |
+
},
|
| 808 |
+
{
|
| 809 |
+
"epoch": 2.82,
|
| 810 |
+
"learning_rate": 7.214620797498047e-05,
|
| 811 |
+
"loss": 0.2151,
|
| 812 |
+
"step": 29000
|
| 813 |
+
},
|
| 814 |
+
{
|
| 815 |
+
"epoch": 2.82,
|
| 816 |
+
"eval_loss": 0.4847819209098816,
|
| 817 |
+
"eval_runtime": 1.4175,
|
| 818 |
+
"eval_samples_per_second": 705.473,
|
| 819 |
+
"eval_steps_per_second": 22.575,
|
| 820 |
+
"step": 29000
|
| 821 |
+
},
|
| 822 |
+
{
|
| 823 |
+
"epoch": 2.87,
|
| 824 |
+
"learning_rate": 7.165754495699765e-05,
|
| 825 |
+
"loss": 0.2134,
|
| 826 |
+
"step": 29500
|
| 827 |
+
},
|
| 828 |
+
{
|
| 829 |
+
"epoch": 2.87,
|
| 830 |
+
"eval_loss": 0.48309269547462463,
|
| 831 |
+
"eval_runtime": 1.4264,
|
| 832 |
+
"eval_samples_per_second": 701.053,
|
| 833 |
+
"eval_steps_per_second": 22.434,
|
| 834 |
+
"step": 29500
|
| 835 |
+
},
|
| 836 |
+
{
|
| 837 |
+
"epoch": 2.92,
|
| 838 |
+
"learning_rate": 7.116888193901487e-05,
|
| 839 |
+
"loss": 0.215,
|
| 840 |
+
"step": 30000
|
| 841 |
+
},
|
| 842 |
+
{
|
| 843 |
+
"epoch": 2.92,
|
| 844 |
+
"eval_loss": 0.4808345437049866,
|
| 845 |
+
"eval_runtime": 1.4354,
|
| 846 |
+
"eval_samples_per_second": 696.688,
|
| 847 |
+
"eval_steps_per_second": 22.294,
|
| 848 |
+
"step": 30000
|
| 849 |
+
},
|
| 850 |
+
{
|
| 851 |
+
"epoch": 2.97,
|
| 852 |
+
"learning_rate": 7.068021892103205e-05,
|
| 853 |
+
"loss": 0.2149,
|
| 854 |
+
"step": 30500
|
| 855 |
+
},
|
| 856 |
+
{
|
| 857 |
+
"epoch": 2.97,
|
| 858 |
+
"eval_loss": 0.48003917932510376,
|
| 859 |
+
"eval_runtime": 1.4294,
|
| 860 |
+
"eval_samples_per_second": 699.594,
|
| 861 |
+
"eval_steps_per_second": 22.387,
|
| 862 |
+
"step": 30500
|
| 863 |
+
},
|
| 864 |
+
{
|
| 865 |
+
"epoch": 3.01,
|
| 866 |
+
"learning_rate": 7.019155590304925e-05,
|
| 867 |
+
"loss": 0.2081,
|
| 868 |
+
"step": 31000
|
| 869 |
+
},
|
| 870 |
+
{
|
| 871 |
+
"epoch": 3.01,
|
| 872 |
+
"eval_loss": 0.4828941524028778,
|
| 873 |
+
"eval_runtime": 1.4264,
|
| 874 |
+
"eval_samples_per_second": 701.051,
|
| 875 |
+
"eval_steps_per_second": 22.434,
|
| 876 |
+
"step": 31000
|
| 877 |
+
},
|
| 878 |
+
{
|
| 879 |
+
"epoch": 3.06,
|
| 880 |
+
"learning_rate": 6.970289288506647e-05,
|
| 881 |
+
"loss": 0.1851,
|
| 882 |
+
"step": 31500
|
| 883 |
+
},
|
| 884 |
+
{
|
| 885 |
+
"epoch": 3.06,
|
| 886 |
+
"eval_loss": 0.48561614751815796,
|
| 887 |
+
"eval_runtime": 1.4155,
|
| 888 |
+
"eval_samples_per_second": 706.463,
|
| 889 |
+
"eval_steps_per_second": 22.607,
|
| 890 |
+
"step": 31500
|
| 891 |
+
},
|
| 892 |
+
{
|
| 893 |
+
"epoch": 3.11,
|
| 894 |
+
"learning_rate": 6.921422986708365e-05,
|
| 895 |
+
"loss": 0.1888,
|
| 896 |
+
"step": 32000
|
| 897 |
+
},
|
| 898 |
+
{
|
| 899 |
+
"epoch": 3.11,
|
| 900 |
+
"eval_loss": 0.48478779196739197,
|
| 901 |
+
"eval_runtime": 1.4155,
|
| 902 |
+
"eval_samples_per_second": 706.465,
|
| 903 |
+
"eval_steps_per_second": 22.607,
|
| 904 |
+
"step": 32000
|
| 905 |
+
},
|
| 906 |
+
{
|
| 907 |
+
"epoch": 3.16,
|
| 908 |
+
"learning_rate": 6.872556684910086e-05,
|
| 909 |
+
"loss": 0.1916,
|
| 910 |
+
"step": 32500
|
| 911 |
+
},
|
| 912 |
+
{
|
| 913 |
+
"epoch": 3.16,
|
| 914 |
+
"eval_loss": 0.4795476198196411,
|
| 915 |
+
"eval_runtime": 1.4239,
|
| 916 |
+
"eval_samples_per_second": 702.273,
|
| 917 |
+
"eval_steps_per_second": 22.473,
|
| 918 |
+
"step": 32500
|
| 919 |
+
},
|
| 920 |
+
{
|
| 921 |
+
"epoch": 3.21,
|
| 922 |
+
"learning_rate": 6.823690383111806e-05,
|
| 923 |
+
"loss": 0.1932,
|
| 924 |
+
"step": 33000
|
| 925 |
+
},
|
| 926 |
+
{
|
| 927 |
+
"epoch": 3.21,
|
| 928 |
+
"eval_loss": 0.47898271679878235,
|
| 929 |
+
"eval_runtime": 1.42,
|
| 930 |
+
"eval_samples_per_second": 704.241,
|
| 931 |
+
"eval_steps_per_second": 22.536,
|
| 932 |
+
"step": 33000
|
| 933 |
+
},
|
| 934 |
+
{
|
| 935 |
+
"epoch": 3.26,
|
| 936 |
+
"learning_rate": 6.774824081313526e-05,
|
| 937 |
+
"loss": 0.1882,
|
| 938 |
+
"step": 33500
|
| 939 |
+
},
|
| 940 |
+
{
|
| 941 |
+
"epoch": 3.26,
|
| 942 |
+
"eval_loss": 0.48221901059150696,
|
| 943 |
+
"eval_runtime": 1.4234,
|
| 944 |
+
"eval_samples_per_second": 702.521,
|
| 945 |
+
"eval_steps_per_second": 22.481,
|
| 946 |
+
"step": 33500
|
| 947 |
+
},
|
| 948 |
+
{
|
| 949 |
+
"epoch": 3.31,
|
| 950 |
+
"learning_rate": 6.725957779515246e-05,
|
| 951 |
+
"loss": 0.1845,
|
| 952 |
+
"step": 34000
|
| 953 |
+
},
|
| 954 |
+
{
|
| 955 |
+
"epoch": 3.31,
|
| 956 |
+
"eval_loss": 0.479130357503891,
|
| 957 |
+
"eval_runtime": 1.4215,
|
| 958 |
+
"eval_samples_per_second": 703.503,
|
| 959 |
+
"eval_steps_per_second": 22.512,
|
| 960 |
+
"step": 34000
|
| 961 |
+
},
|
| 962 |
+
{
|
| 963 |
+
"epoch": 3.36,
|
| 964 |
+
"learning_rate": 6.677091477716966e-05,
|
| 965 |
+
"loss": 0.1895,
|
| 966 |
+
"step": 34500
|
| 967 |
+
},
|
| 968 |
+
{
|
| 969 |
+
"epoch": 3.36,
|
| 970 |
+
"eval_loss": 0.4773789644241333,
|
| 971 |
+
"eval_runtime": 1.4294,
|
| 972 |
+
"eval_samples_per_second": 699.592,
|
| 973 |
+
"eval_steps_per_second": 22.387,
|
| 974 |
+
"step": 34500
|
| 975 |
+
},
|
| 976 |
+
{
|
| 977 |
+
"epoch": 3.4,
|
| 978 |
+
"learning_rate": 6.628225175918686e-05,
|
| 979 |
+
"loss": 0.1909,
|
| 980 |
+
"step": 35000
|
| 981 |
+
},
|
| 982 |
+
{
|
| 983 |
+
"epoch": 3.4,
|
| 984 |
+
"eval_loss": 0.4763247072696686,
|
| 985 |
+
"eval_runtime": 1.409,
|
| 986 |
+
"eval_samples_per_second": 709.702,
|
| 987 |
+
"eval_steps_per_second": 22.71,
|
| 988 |
+
"step": 35000
|
| 989 |
+
},
|
| 990 |
+
{
|
| 991 |
+
"epoch": 3.45,
|
| 992 |
+
"learning_rate": 6.579358874120408e-05,
|
| 993 |
+
"loss": 0.1841,
|
| 994 |
+
"step": 35500
|
| 995 |
+
},
|
| 996 |
+
{
|
| 997 |
+
"epoch": 3.45,
|
| 998 |
+
"eval_loss": 0.4759540259838104,
|
| 999 |
+
"eval_runtime": 1.421,
|
| 1000 |
+
"eval_samples_per_second": 703.747,
|
| 1001 |
+
"eval_steps_per_second": 22.52,
|
| 1002 |
+
"step": 35500
|
| 1003 |
+
},
|
| 1004 |
+
{
|
| 1005 |
+
"epoch": 3.5,
|
| 1006 |
+
"learning_rate": 6.530492572322126e-05,
|
| 1007 |
+
"loss": 0.1882,
|
| 1008 |
+
"step": 36000
|
| 1009 |
+
},
|
| 1010 |
+
{
|
| 1011 |
+
"epoch": 3.5,
|
| 1012 |
+
"eval_loss": 0.4739590585231781,
|
| 1013 |
+
"eval_runtime": 1.417,
|
| 1014 |
+
"eval_samples_per_second": 705.724,
|
| 1015 |
+
"eval_steps_per_second": 22.583,
|
| 1016 |
+
"step": 36000
|
| 1017 |
+
},
|
| 1018 |
+
{
|
| 1019 |
+
"epoch": 3.55,
|
| 1020 |
+
"learning_rate": 6.481626270523847e-05,
|
| 1021 |
+
"loss": 0.1902,
|
| 1022 |
+
"step": 36500
|
| 1023 |
+
},
|
| 1024 |
+
{
|
| 1025 |
+
"epoch": 3.55,
|
| 1026 |
+
"eval_loss": 0.47059980034828186,
|
| 1027 |
+
"eval_runtime": 1.4215,
|
| 1028 |
+
"eval_samples_per_second": 703.504,
|
| 1029 |
+
"eval_steps_per_second": 22.512,
|
| 1030 |
+
"step": 36500
|
| 1031 |
+
},
|
| 1032 |
+
{
|
| 1033 |
+
"epoch": 3.6,
|
| 1034 |
+
"learning_rate": 6.432759968725567e-05,
|
| 1035 |
+
"loss": 0.1924,
|
| 1036 |
+
"step": 37000
|
| 1037 |
+
},
|
| 1038 |
+
{
|
| 1039 |
+
"epoch": 3.6,
|
| 1040 |
+
"eval_loss": 0.46917036175727844,
|
| 1041 |
+
"eval_runtime": 1.4388,
|
| 1042 |
+
"eval_samples_per_second": 695.005,
|
| 1043 |
+
"eval_steps_per_second": 22.24,
|
| 1044 |
+
"step": 37000
|
| 1045 |
+
},
|
| 1046 |
+
{
|
| 1047 |
+
"epoch": 3.65,
|
| 1048 |
+
"learning_rate": 6.383893666927287e-05,
|
| 1049 |
+
"loss": 0.1845,
|
| 1050 |
+
"step": 37500
|
| 1051 |
+
},
|
| 1052 |
+
{
|
| 1053 |
+
"epoch": 3.65,
|
| 1054 |
+
"eval_loss": 0.46856725215911865,
|
| 1055 |
+
"eval_runtime": 1.4135,
|
| 1056 |
+
"eval_samples_per_second": 707.458,
|
| 1057 |
+
"eval_steps_per_second": 22.639,
|
| 1058 |
+
"step": 37500
|
| 1059 |
+
},
|
| 1060 |
+
{
|
| 1061 |
+
"epoch": 3.7,
|
| 1062 |
+
"learning_rate": 6.335027365129007e-05,
|
| 1063 |
+
"loss": 0.1892,
|
| 1064 |
+
"step": 38000
|
| 1065 |
+
},
|
| 1066 |
+
{
|
| 1067 |
+
"epoch": 3.7,
|
| 1068 |
+
"eval_loss": 0.46638262271881104,
|
| 1069 |
+
"eval_runtime": 1.4632,
|
| 1070 |
+
"eval_samples_per_second": 683.445,
|
| 1071 |
+
"eval_steps_per_second": 21.87,
|
| 1072 |
+
"step": 38000
|
| 1073 |
+
},
|
| 1074 |
+
{
|
| 1075 |
+
"epoch": 3.74,
|
| 1076 |
+
"learning_rate": 6.286161063330727e-05,
|
| 1077 |
+
"loss": 0.1849,
|
| 1078 |
+
"step": 38500
|
| 1079 |
+
},
|
| 1080 |
+
{
|
| 1081 |
+
"epoch": 3.74,
|
| 1082 |
+
"eval_loss": 0.46737831830978394,
|
| 1083 |
+
"eval_runtime": 1.4319,
|
| 1084 |
+
"eval_samples_per_second": 698.377,
|
| 1085 |
+
"eval_steps_per_second": 22.348,
|
| 1086 |
+
"step": 38500
|
| 1087 |
+
},
|
| 1088 |
+
{
|
| 1089 |
+
"epoch": 3.79,
|
| 1090 |
+
"learning_rate": 6.237294761532447e-05,
|
| 1091 |
+
"loss": 0.1883,
|
| 1092 |
+
"step": 39000
|
| 1093 |
+
},
|
| 1094 |
+
{
|
| 1095 |
+
"epoch": 3.79,
|
| 1096 |
+
"eval_loss": 0.46423232555389404,
|
| 1097 |
+
"eval_runtime": 1.4249,
|
| 1098 |
+
"eval_samples_per_second": 701.787,
|
| 1099 |
+
"eval_steps_per_second": 22.457,
|
| 1100 |
+
"step": 39000
|
| 1101 |
+
},
|
| 1102 |
+
{
|
| 1103 |
+
"epoch": 3.84,
|
| 1104 |
+
"learning_rate": 6.188428459734168e-05,
|
| 1105 |
+
"loss": 0.1821,
|
| 1106 |
+
"step": 39500
|
| 1107 |
+
},
|
| 1108 |
+
{
|
| 1109 |
+
"epoch": 3.84,
|
| 1110 |
+
"eval_loss": 0.4651487171649933,
|
| 1111 |
+
"eval_runtime": 1.4135,
|
| 1112 |
+
"eval_samples_per_second": 707.454,
|
| 1113 |
+
"eval_steps_per_second": 22.639,
|
| 1114 |
+
"step": 39500
|
| 1115 |
+
},
|
| 1116 |
+
{
|
| 1117 |
+
"epoch": 3.89,
|
| 1118 |
+
"learning_rate": 6.139562157935887e-05,
|
| 1119 |
+
"loss": 0.1905,
|
| 1120 |
+
"step": 40000
|
| 1121 |
+
},
|
| 1122 |
+
{
|
| 1123 |
+
"epoch": 3.89,
|
| 1124 |
+
"eval_loss": 0.462035208940506,
|
| 1125 |
+
"eval_runtime": 1.417,
|
| 1126 |
+
"eval_samples_per_second": 705.722,
|
| 1127 |
+
"eval_steps_per_second": 22.583,
|
| 1128 |
+
"step": 40000
|
| 1129 |
+
},
|
| 1130 |
+
{
|
| 1131 |
+
"epoch": 3.94,
|
| 1132 |
+
"learning_rate": 6.090695856137608e-05,
|
| 1133 |
+
"loss": 0.185,
|
| 1134 |
+
"step": 40500
|
| 1135 |
+
},
|
| 1136 |
+
{
|
| 1137 |
+
"epoch": 3.94,
|
| 1138 |
+
"eval_loss": 0.4627071022987366,
|
| 1139 |
+
"eval_runtime": 1.4179,
|
| 1140 |
+
"eval_samples_per_second": 705.261,
|
| 1141 |
+
"eval_steps_per_second": 22.568,
|
| 1142 |
+
"step": 40500
|
| 1143 |
+
},
|
| 1144 |
+
{
|
| 1145 |
+
"epoch": 3.99,
|
| 1146 |
+
"learning_rate": 6.0418295543393276e-05,
|
| 1147 |
+
"loss": 0.19,
|
| 1148 |
+
"step": 41000
|
| 1149 |
+
},
|
| 1150 |
+
{
|
| 1151 |
+
"epoch": 3.99,
|
| 1152 |
+
"eval_loss": 0.4600967466831207,
|
| 1153 |
+
"eval_runtime": 1.422,
|
| 1154 |
+
"eval_samples_per_second": 703.255,
|
| 1155 |
+
"eval_steps_per_second": 22.504,
|
| 1156 |
+
"step": 41000
|
| 1157 |
+
},
|
| 1158 |
+
{
|
| 1159 |
+
"epoch": 4.04,
|
| 1160 |
+
"learning_rate": 5.992963252541048e-05,
|
| 1161 |
+
"loss": 0.1734,
|
| 1162 |
+
"step": 41500
|
| 1163 |
+
},
|
| 1164 |
+
{
|
| 1165 |
+
"epoch": 4.04,
|
| 1166 |
+
"eval_loss": 0.46835413575172424,
|
| 1167 |
+
"eval_runtime": 1.4105,
|
| 1168 |
+
"eval_samples_per_second": 708.959,
|
| 1169 |
+
"eval_steps_per_second": 22.687,
|
| 1170 |
+
"step": 41500
|
| 1171 |
+
},
|
| 1172 |
+
{
|
| 1173 |
+
"epoch": 4.08,
|
| 1174 |
+
"learning_rate": 5.944096950742768e-05,
|
| 1175 |
+
"loss": 0.1665,
|
| 1176 |
+
"step": 42000
|
| 1177 |
+
},
|
| 1178 |
+
{
|
| 1179 |
+
"epoch": 4.08,
|
| 1180 |
+
"eval_loss": 0.4674428403377533,
|
| 1181 |
+
"eval_runtime": 1.4224,
|
| 1182 |
+
"eval_samples_per_second": 703.013,
|
| 1183 |
+
"eval_steps_per_second": 22.496,
|
| 1184 |
+
"step": 42000
|
| 1185 |
+
},
|
| 1186 |
+
{
|
| 1187 |
+
"epoch": 4.13,
|
| 1188 |
+
"learning_rate": 5.895230648944489e-05,
|
| 1189 |
+
"loss": 0.1621,
|
| 1190 |
+
"step": 42500
|
| 1191 |
+
},
|
| 1192 |
+
{
|
| 1193 |
+
"epoch": 4.13,
|
| 1194 |
+
"eval_loss": 0.46939995884895325,
|
| 1195 |
+
"eval_runtime": 1.418,
|
| 1196 |
+
"eval_samples_per_second": 705.227,
|
| 1197 |
+
"eval_steps_per_second": 22.567,
|
| 1198 |
+
"step": 42500
|
| 1199 |
+
},
|
| 1200 |
+
{
|
| 1201 |
+
"epoch": 4.18,
|
| 1202 |
+
"learning_rate": 5.846364347146208e-05,
|
| 1203 |
+
"loss": 0.1633,
|
| 1204 |
+
"step": 43000
|
| 1205 |
+
},
|
| 1206 |
+
{
|
| 1207 |
+
"epoch": 4.18,
|
| 1208 |
+
"eval_loss": 0.4672936499118805,
|
| 1209 |
+
"eval_runtime": 1.4229,
|
| 1210 |
+
"eval_samples_per_second": 702.769,
|
| 1211 |
+
"eval_steps_per_second": 22.489,
|
| 1212 |
+
"step": 43000
|
| 1213 |
+
},
|
| 1214 |
+
{
|
| 1215 |
+
"epoch": 4.23,
|
| 1216 |
+
"learning_rate": 5.797498045347929e-05,
|
| 1217 |
+
"loss": 0.1612,
|
| 1218 |
+
"step": 43500
|
| 1219 |
+
},
|
| 1220 |
+
{
|
| 1221 |
+
"epoch": 4.23,
|
| 1222 |
+
"eval_loss": 0.4673324525356293,
|
| 1223 |
+
"eval_runtime": 1.42,
|
| 1224 |
+
"eval_samples_per_second": 704.241,
|
| 1225 |
+
"eval_steps_per_second": 22.536,
|
| 1226 |
+
"step": 43500
|
| 1227 |
+
},
|
| 1228 |
+
{
|
| 1229 |
+
"epoch": 4.28,
|
| 1230 |
+
"learning_rate": 5.7486317435496486e-05,
|
| 1231 |
+
"loss": 0.1644,
|
| 1232 |
+
"step": 44000
|
| 1233 |
+
},
|
| 1234 |
+
{
|
| 1235 |
+
"epoch": 4.28,
|
| 1236 |
+
"eval_loss": 0.4646117091178894,
|
| 1237 |
+
"eval_runtime": 1.4244,
|
| 1238 |
+
"eval_samples_per_second": 702.031,
|
| 1239 |
+
"eval_steps_per_second": 22.465,
|
| 1240 |
+
"step": 44000
|
| 1241 |
+
},
|
| 1242 |
+
{
|
| 1243 |
+
"epoch": 4.33,
|
| 1244 |
+
"learning_rate": 5.699765441751369e-05,
|
| 1245 |
+
"loss": 0.1655,
|
| 1246 |
+
"step": 44500
|
| 1247 |
+
},
|
| 1248 |
+
{
|
| 1249 |
+
"epoch": 4.33,
|
| 1250 |
+
"eval_loss": 0.46449655294418335,
|
| 1251 |
+
"eval_runtime": 1.4359,
|
| 1252 |
+
"eval_samples_per_second": 696.446,
|
| 1253 |
+
"eval_steps_per_second": 22.286,
|
| 1254 |
+
"step": 44500
|
| 1255 |
+
},
|
| 1256 |
+
{
|
| 1257 |
+
"epoch": 4.38,
|
| 1258 |
+
"learning_rate": 5.6508991399530885e-05,
|
| 1259 |
+
"loss": 0.1627,
|
| 1260 |
+
"step": 45000
|
| 1261 |
+
},
|
| 1262 |
+
{
|
| 1263 |
+
"epoch": 4.38,
|
| 1264 |
+
"eval_loss": 0.4624975025653839,
|
| 1265 |
+
"eval_runtime": 1.4244,
|
| 1266 |
+
"eval_samples_per_second": 702.032,
|
| 1267 |
+
"eval_steps_per_second": 22.465,
|
| 1268 |
+
"step": 45000
|
| 1269 |
+
},
|
| 1270 |
+
{
|
| 1271 |
+
"epoch": 4.43,
|
| 1272 |
+
"learning_rate": 5.6020328381548085e-05,
|
| 1273 |
+
"loss": 0.1675,
|
| 1274 |
+
"step": 45500
|
| 1275 |
+
},
|
| 1276 |
+
{
|
| 1277 |
+
"epoch": 4.43,
|
| 1278 |
+
"eval_loss": 0.46210145950317383,
|
| 1279 |
+
"eval_runtime": 1.4274,
|
| 1280 |
+
"eval_samples_per_second": 700.566,
|
| 1281 |
+
"eval_steps_per_second": 22.418,
|
| 1282 |
+
"step": 45500
|
| 1283 |
+
},
|
| 1284 |
+
{
|
| 1285 |
+
"epoch": 4.47,
|
| 1286 |
+
"learning_rate": 5.553166536356529e-05,
|
| 1287 |
+
"loss": 0.1648,
|
| 1288 |
+
"step": 46000
|
| 1289 |
+
},
|
| 1290 |
+
{
|
| 1291 |
+
"epoch": 4.47,
|
| 1292 |
+
"eval_loss": 0.4633449614048004,
|
| 1293 |
+
"eval_runtime": 1.4487,
|
| 1294 |
+
"eval_samples_per_second": 690.281,
|
| 1295 |
+
"eval_steps_per_second": 22.089,
|
| 1296 |
+
"step": 46000
|
| 1297 |
+
},
|
| 1298 |
+
{
|
| 1299 |
+
"epoch": 4.52,
|
| 1300 |
+
"learning_rate": 5.5043002345582483e-05,
|
| 1301 |
+
"loss": 0.1691,
|
| 1302 |
+
"step": 46500
|
| 1303 |
+
},
|
| 1304 |
+
{
|
| 1305 |
+
"epoch": 4.52,
|
| 1306 |
+
"eval_loss": 0.4609707295894623,
|
| 1307 |
+
"eval_runtime": 1.4403,
|
| 1308 |
+
"eval_samples_per_second": 694.283,
|
| 1309 |
+
"eval_steps_per_second": 22.217,
|
| 1310 |
+
"step": 46500
|
| 1311 |
+
},
|
| 1312 |
+
{
|
| 1313 |
+
"epoch": 4.57,
|
| 1314 |
+
"learning_rate": 5.455433932759969e-05,
|
| 1315 |
+
"loss": 0.1642,
|
| 1316 |
+
"step": 47000
|
| 1317 |
+
},
|
| 1318 |
+
{
|
| 1319 |
+
"epoch": 4.57,
|
| 1320 |
+
"eval_loss": 0.46095407009124756,
|
| 1321 |
+
"eval_runtime": 1.4319,
|
| 1322 |
+
"eval_samples_per_second": 698.378,
|
| 1323 |
+
"eval_steps_per_second": 22.348,
|
| 1324 |
+
"step": 47000
|
| 1325 |
+
},
|
| 1326 |
+
{
|
| 1327 |
+
"epoch": 4.62,
|
| 1328 |
+
"learning_rate": 5.406567630961689e-05,
|
| 1329 |
+
"loss": 0.1666,
|
| 1330 |
+
"step": 47500
|
| 1331 |
+
},
|
| 1332 |
+
{
|
| 1333 |
+
"epoch": 4.62,
|
| 1334 |
+
"eval_loss": 0.46066999435424805,
|
| 1335 |
+
"eval_runtime": 1.4264,
|
| 1336 |
+
"eval_samples_per_second": 701.053,
|
| 1337 |
+
"eval_steps_per_second": 22.434,
|
| 1338 |
+
"step": 47500
|
| 1339 |
+
},
|
| 1340 |
+
{
|
| 1341 |
+
"epoch": 4.67,
|
| 1342 |
+
"learning_rate": 5.3577013291634095e-05,
|
| 1343 |
+
"loss": 0.167,
|
| 1344 |
+
"step": 48000
|
| 1345 |
+
},
|
| 1346 |
+
{
|
| 1347 |
+
"epoch": 4.67,
|
| 1348 |
+
"eval_loss": 0.45587822794914246,
|
| 1349 |
+
"eval_runtime": 1.4344,
|
| 1350 |
+
"eval_samples_per_second": 697.169,
|
| 1351 |
+
"eval_steps_per_second": 22.309,
|
| 1352 |
+
"step": 48000
|
| 1353 |
+
},
|
| 1354 |
+
{
|
| 1355 |
+
"epoch": 4.72,
|
| 1356 |
+
"learning_rate": 5.308835027365129e-05,
|
| 1357 |
+
"loss": 0.1691,
|
| 1358 |
+
"step": 48500
|
| 1359 |
+
},
|
| 1360 |
+
{
|
| 1361 |
+
"epoch": 4.72,
|
| 1362 |
+
"eval_loss": 0.45380640029907227,
|
| 1363 |
+
"eval_runtime": 1.4344,
|
| 1364 |
+
"eval_samples_per_second": 697.166,
|
| 1365 |
+
"eval_steps_per_second": 22.309,
|
| 1366 |
+
"step": 48500
|
| 1367 |
+
},
|
| 1368 |
+
{
|
| 1369 |
+
"epoch": 4.77,
|
| 1370 |
+
"learning_rate": 5.2599687255668494e-05,
|
| 1371 |
+
"loss": 0.1674,
|
| 1372 |
+
"step": 49000
|
| 1373 |
+
},
|
| 1374 |
+
{
|
| 1375 |
+
"epoch": 4.77,
|
| 1376 |
+
"eval_loss": 0.45414891839027405,
|
| 1377 |
+
"eval_runtime": 1.4319,
|
| 1378 |
+
"eval_samples_per_second": 698.38,
|
| 1379 |
+
"eval_steps_per_second": 22.348,
|
| 1380 |
+
"step": 49000
|
| 1381 |
+
},
|
| 1382 |
+
{
|
| 1383 |
+
"epoch": 4.81,
|
| 1384 |
+
"learning_rate": 5.2111024237685694e-05,
|
| 1385 |
+
"loss": 0.1613,
|
| 1386 |
+
"step": 49500
|
| 1387 |
+
},
|
| 1388 |
+
{
|
| 1389 |
+
"epoch": 4.81,
|
| 1390 |
+
"eval_loss": 0.45553380250930786,
|
| 1391 |
+
"eval_runtime": 1.4458,
|
| 1392 |
+
"eval_samples_per_second": 691.661,
|
| 1393 |
+
"eval_steps_per_second": 22.133,
|
| 1394 |
+
"step": 49500
|
| 1395 |
+
},
|
| 1396 |
+
{
|
| 1397 |
+
"epoch": 4.86,
|
| 1398 |
+
"learning_rate": 5.16223612197029e-05,
|
| 1399 |
+
"loss": 0.1613,
|
| 1400 |
+
"step": 50000
|
| 1401 |
+
},
|
| 1402 |
+
{
|
| 1403 |
+
"epoch": 4.86,
|
| 1404 |
+
"eval_loss": 0.4527079463005066,
|
| 1405 |
+
"eval_runtime": 1.4195,
|
| 1406 |
+
"eval_samples_per_second": 704.487,
|
| 1407 |
+
"eval_steps_per_second": 22.544,
|
| 1408 |
+
"step": 50000
|
| 1409 |
+
},
|
| 1410 |
+
{
|
| 1411 |
+
"epoch": 4.91,
|
| 1412 |
+
"learning_rate": 5.113369820172009e-05,
|
| 1413 |
+
"loss": 0.1639,
|
| 1414 |
+
"step": 50500
|
| 1415 |
+
},
|
| 1416 |
+
{
|
| 1417 |
+
"epoch": 4.91,
|
| 1418 |
+
"eval_loss": 0.44933873414993286,
|
| 1419 |
+
"eval_runtime": 1.416,
|
| 1420 |
+
"eval_samples_per_second": 706.217,
|
| 1421 |
+
"eval_steps_per_second": 22.599,
|
| 1422 |
+
"step": 50500
|
| 1423 |
+
},
|
| 1424 |
+
{
|
| 1425 |
+
"epoch": 4.96,
|
| 1426 |
+
"learning_rate": 5.06450351837373e-05,
|
| 1427 |
+
"loss": 0.1685,
|
| 1428 |
+
"step": 51000
|
| 1429 |
+
},
|
| 1430 |
+
{
|
| 1431 |
+
"epoch": 4.96,
|
| 1432 |
+
"eval_loss": 0.44989633560180664,
|
| 1433 |
+
"eval_runtime": 1.4289,
|
| 1434 |
+
"eval_samples_per_second": 699.837,
|
| 1435 |
+
"eval_steps_per_second": 22.395,
|
| 1436 |
+
"step": 51000
|
| 1437 |
+
},
|
| 1438 |
+
{
|
| 1439 |
+
"epoch": 5.01,
|
| 1440 |
+
"learning_rate": 5.01563721657545e-05,
|
| 1441 |
+
"loss": 0.1629,
|
| 1442 |
+
"step": 51500
|
| 1443 |
+
},
|
| 1444 |
+
{
|
| 1445 |
+
"epoch": 5.01,
|
| 1446 |
+
"eval_loss": 0.45488646626472473,
|
| 1447 |
+
"eval_runtime": 1.4239,
|
| 1448 |
+
"eval_samples_per_second": 702.276,
|
| 1449 |
+
"eval_steps_per_second": 22.473,
|
| 1450 |
+
"step": 51500
|
| 1451 |
+
},
|
| 1452 |
+
{
|
| 1453 |
+
"epoch": 5.06,
|
| 1454 |
+
"learning_rate": 4.9667709147771705e-05,
|
| 1455 |
+
"loss": 0.1484,
|
| 1456 |
+
"step": 52000
|
| 1457 |
+
},
|
| 1458 |
+
{
|
| 1459 |
+
"epoch": 5.06,
|
| 1460 |
+
"eval_loss": 0.4580441415309906,
|
| 1461 |
+
"eval_runtime": 1.416,
|
| 1462 |
+
"eval_samples_per_second": 706.223,
|
| 1463 |
+
"eval_steps_per_second": 22.599,
|
| 1464 |
+
"step": 52000
|
| 1465 |
+
},
|
| 1466 |
+
{
|
| 1467 |
+
"epoch": 5.11,
|
| 1468 |
+
"learning_rate": 4.9179046129788904e-05,
|
| 1469 |
+
"loss": 0.1468,
|
| 1470 |
+
"step": 52500
|
| 1471 |
+
},
|
| 1472 |
+
{
|
| 1473 |
+
"epoch": 5.11,
|
| 1474 |
+
"eval_loss": 0.4577222168445587,
|
| 1475 |
+
"eval_runtime": 1.4304,
|
| 1476 |
+
"eval_samples_per_second": 699.106,
|
| 1477 |
+
"eval_steps_per_second": 22.371,
|
| 1478 |
+
"step": 52500
|
| 1479 |
+
},
|
| 1480 |
+
{
|
| 1481 |
+
"epoch": 5.15,
|
| 1482 |
+
"learning_rate": 4.86903831118061e-05,
|
| 1483 |
+
"loss": 0.147,
|
| 1484 |
+
"step": 53000
|
| 1485 |
+
},
|
| 1486 |
+
{
|
| 1487 |
+
"epoch": 5.15,
|
| 1488 |
+
"eval_loss": 0.4562654197216034,
|
| 1489 |
+
"eval_runtime": 1.4284,
|
| 1490 |
+
"eval_samples_per_second": 700.079,
|
| 1491 |
+
"eval_steps_per_second": 22.403,
|
| 1492 |
+
"step": 53000
|
| 1493 |
+
},
|
| 1494 |
+
{
|
| 1495 |
+
"epoch": 5.2,
|
| 1496 |
+
"learning_rate": 4.8201720093823296e-05,
|
| 1497 |
+
"loss": 0.1486,
|
| 1498 |
+
"step": 53500
|
| 1499 |
+
},
|
| 1500 |
+
{
|
| 1501 |
+
"epoch": 5.2,
|
| 1502 |
+
"eval_loss": 0.4565419852733612,
|
| 1503 |
+
"eval_runtime": 1.4264,
|
| 1504 |
+
"eval_samples_per_second": 701.053,
|
| 1505 |
+
"eval_steps_per_second": 22.434,
|
| 1506 |
+
"step": 53500
|
| 1507 |
+
},
|
| 1508 |
+
{
|
| 1509 |
+
"epoch": 5.25,
|
| 1510 |
+
"learning_rate": 4.77130570758405e-05,
|
| 1511 |
+
"loss": 0.1461,
|
| 1512 |
+
"step": 54000
|
| 1513 |
+
},
|
| 1514 |
+
{
|
| 1515 |
+
"epoch": 5.25,
|
| 1516 |
+
"eval_loss": 0.45437780022621155,
|
| 1517 |
+
"eval_runtime": 1.4279,
|
| 1518 |
+
"eval_samples_per_second": 700.322,
|
| 1519 |
+
"eval_steps_per_second": 22.41,
|
| 1520 |
+
"step": 54000
|
| 1521 |
+
},
|
| 1522 |
+
{
|
| 1523 |
+
"epoch": 5.3,
|
| 1524 |
+
"learning_rate": 4.72243940578577e-05,
|
| 1525 |
+
"loss": 0.1435,
|
| 1526 |
+
"step": 54500
|
| 1527 |
+
},
|
| 1528 |
+
{
|
| 1529 |
+
"epoch": 5.3,
|
| 1530 |
+
"eval_loss": 0.4550324082374573,
|
| 1531 |
+
"eval_runtime": 1.4289,
|
| 1532 |
+
"eval_samples_per_second": 699.835,
|
| 1533 |
+
"eval_steps_per_second": 22.395,
|
| 1534 |
+
"step": 54500
|
| 1535 |
+
},
|
| 1536 |
+
{
|
| 1537 |
+
"epoch": 5.35,
|
| 1538 |
+
"learning_rate": 4.67357310398749e-05,
|
| 1539 |
+
"loss": 0.1463,
|
| 1540 |
+
"step": 55000
|
| 1541 |
+
},
|
| 1542 |
+
{
|
| 1543 |
+
"epoch": 5.35,
|
| 1544 |
+
"eval_loss": 0.4553817808628082,
|
| 1545 |
+
"eval_runtime": 1.4304,
|
| 1546 |
+
"eval_samples_per_second": 699.106,
|
| 1547 |
+
"eval_steps_per_second": 22.371,
|
| 1548 |
+
"step": 55000
|
| 1549 |
+
},
|
| 1550 |
+
{
|
| 1551 |
+
"epoch": 5.4,
|
| 1552 |
+
"learning_rate": 4.62470680218921e-05,
|
| 1553 |
+
"loss": 0.1495,
|
| 1554 |
+
"step": 55500
|
| 1555 |
+
},
|
| 1556 |
+
{
|
| 1557 |
+
"epoch": 5.4,
|
| 1558 |
+
"eval_loss": 0.45491766929626465,
|
| 1559 |
+
"eval_runtime": 1.4195,
|
| 1560 |
+
"eval_samples_per_second": 704.489,
|
| 1561 |
+
"eval_steps_per_second": 22.544,
|
| 1562 |
+
"step": 55500
|
| 1563 |
+
},
|
| 1564 |
+
{
|
| 1565 |
+
"epoch": 5.45,
|
| 1566 |
+
"learning_rate": 4.575840500390931e-05,
|
| 1567 |
+
"loss": 0.143,
|
| 1568 |
+
"step": 56000
|
| 1569 |
+
},
|
| 1570 |
+
{
|
| 1571 |
+
"epoch": 5.45,
|
| 1572 |
+
"eval_loss": 0.45461103320121765,
|
| 1573 |
+
"eval_runtime": 1.4225,
|
| 1574 |
+
"eval_samples_per_second": 703.01,
|
| 1575 |
+
"eval_steps_per_second": 22.496,
|
| 1576 |
+
"step": 56000
|
| 1577 |
+
},
|
| 1578 |
+
{
|
| 1579 |
+
"epoch": 5.5,
|
| 1580 |
+
"learning_rate": 4.5269741985926506e-05,
|
| 1581 |
+
"loss": 0.1473,
|
| 1582 |
+
"step": 56500
|
| 1583 |
+
},
|
| 1584 |
+
{
|
| 1585 |
+
"epoch": 5.5,
|
| 1586 |
+
"eval_loss": 0.4515800178050995,
|
| 1587 |
+
"eval_runtime": 1.4373,
|
| 1588 |
+
"eval_samples_per_second": 695.726,
|
| 1589 |
+
"eval_steps_per_second": 22.263,
|
| 1590 |
+
"step": 56500
|
| 1591 |
+
},
|
| 1592 |
+
{
|
| 1593 |
+
"epoch": 5.54,
|
| 1594 |
+
"learning_rate": 4.4781078967943706e-05,
|
| 1595 |
+
"loss": 0.1481,
|
| 1596 |
+
"step": 57000
|
| 1597 |
+
},
|
| 1598 |
+
{
|
| 1599 |
+
"epoch": 5.54,
|
| 1600 |
+
"eval_loss": 0.45015862584114075,
|
| 1601 |
+
"eval_runtime": 1.4259,
|
| 1602 |
+
"eval_samples_per_second": 701.296,
|
| 1603 |
+
"eval_steps_per_second": 22.441,
|
| 1604 |
+
"step": 57000
|
| 1605 |
+
},
|
| 1606 |
+
{
|
| 1607 |
+
"epoch": 5.59,
|
| 1608 |
+
"learning_rate": 4.4292415949960905e-05,
|
| 1609 |
+
"loss": 0.1494,
|
| 1610 |
+
"step": 57500
|
| 1611 |
+
},
|
| 1612 |
+
{
|
| 1613 |
+
"epoch": 5.59,
|
| 1614 |
+
"eval_loss": 0.4483198821544647,
|
| 1615 |
+
"eval_runtime": 1.4359,
|
| 1616 |
+
"eval_samples_per_second": 696.444,
|
| 1617 |
+
"eval_steps_per_second": 22.286,
|
| 1618 |
+
"step": 57500
|
| 1619 |
+
},
|
| 1620 |
+
{
|
| 1621 |
+
"epoch": 5.64,
|
| 1622 |
+
"learning_rate": 4.380375293197811e-05,
|
| 1623 |
+
"loss": 0.1413,
|
| 1624 |
+
"step": 58000
|
| 1625 |
+
},
|
| 1626 |
+
{
|
| 1627 |
+
"epoch": 5.64,
|
| 1628 |
+
"eval_loss": 0.4498542249202728,
|
| 1629 |
+
"eval_runtime": 1.4473,
|
| 1630 |
+
"eval_samples_per_second": 690.949,
|
| 1631 |
+
"eval_steps_per_second": 22.11,
|
| 1632 |
+
"step": 58000
|
| 1633 |
+
},
|
| 1634 |
+
{
|
| 1635 |
+
"epoch": 5.69,
|
| 1636 |
+
"learning_rate": 4.331508991399531e-05,
|
| 1637 |
+
"loss": 0.1498,
|
| 1638 |
+
"step": 58500
|
| 1639 |
+
},
|
| 1640 |
+
{
|
| 1641 |
+
"epoch": 5.69,
|
| 1642 |
+
"eval_loss": 0.447781503200531,
|
| 1643 |
+
"eval_runtime": 1.4225,
|
| 1644 |
+
"eval_samples_per_second": 703.012,
|
| 1645 |
+
"eval_steps_per_second": 22.496,
|
| 1646 |
+
"step": 58500
|
| 1647 |
+
},
|
| 1648 |
+
{
|
| 1649 |
+
"epoch": 5.74,
|
| 1650 |
+
"learning_rate": 4.282642689601251e-05,
|
| 1651 |
+
"loss": 0.146,
|
| 1652 |
+
"step": 59000
|
| 1653 |
+
},
|
| 1654 |
+
{
|
| 1655 |
+
"epoch": 5.74,
|
| 1656 |
+
"eval_loss": 0.4458942115306854,
|
| 1657 |
+
"eval_runtime": 1.413,
|
| 1658 |
+
"eval_samples_per_second": 707.707,
|
| 1659 |
+
"eval_steps_per_second": 22.647,
|
| 1660 |
+
"step": 59000
|
| 1661 |
+
},
|
| 1662 |
+
{
|
| 1663 |
+
"epoch": 5.79,
|
| 1664 |
+
"learning_rate": 4.233776387802971e-05,
|
| 1665 |
+
"loss": 0.1455,
|
| 1666 |
+
"step": 59500
|
| 1667 |
+
},
|
| 1668 |
+
{
|
| 1669 |
+
"epoch": 5.79,
|
| 1670 |
+
"eval_loss": 0.44468608498573303,
|
| 1671 |
+
"eval_runtime": 1.4239,
|
| 1672 |
+
"eval_samples_per_second": 702.274,
|
| 1673 |
+
"eval_steps_per_second": 22.473,
|
| 1674 |
+
"step": 59500
|
| 1675 |
+
},
|
| 1676 |
+
{
|
| 1677 |
+
"epoch": 5.84,
|
| 1678 |
+
"learning_rate": 4.1849100860046916e-05,
|
| 1679 |
+
"loss": 0.1439,
|
| 1680 |
+
"step": 60000
|
| 1681 |
+
},
|
| 1682 |
+
{
|
| 1683 |
+
"epoch": 5.84,
|
| 1684 |
+
"eval_loss": 0.446806401014328,
|
| 1685 |
+
"eval_runtime": 1.4224,
|
| 1686 |
+
"eval_samples_per_second": 703.012,
|
| 1687 |
+
"eval_steps_per_second": 22.496,
|
| 1688 |
+
"step": 60000
|
| 1689 |
+
},
|
| 1690 |
+
{
|
| 1691 |
+
"epoch": 5.88,
|
| 1692 |
+
"learning_rate": 4.1360437842064116e-05,
|
| 1693 |
+
"loss": 0.1472,
|
| 1694 |
+
"step": 60500
|
| 1695 |
+
},
|
| 1696 |
+
{
|
| 1697 |
+
"epoch": 5.88,
|
| 1698 |
+
"eval_loss": 0.44735094904899597,
|
| 1699 |
+
"eval_runtime": 1.4315,
|
| 1700 |
+
"eval_samples_per_second": 698.575,
|
| 1701 |
+
"eval_steps_per_second": 22.354,
|
| 1702 |
+
"step": 60500
|
| 1703 |
+
},
|
| 1704 |
+
{
|
| 1705 |
+
"epoch": 5.93,
|
| 1706 |
+
"learning_rate": 4.0871774824081315e-05,
|
| 1707 |
+
"loss": 0.1481,
|
| 1708 |
+
"step": 61000
|
| 1709 |
+
},
|
| 1710 |
+
{
|
| 1711 |
+
"epoch": 5.93,
|
| 1712 |
+
"eval_loss": 0.4440445303916931,
|
| 1713 |
+
"eval_runtime": 1.4374,
|
| 1714 |
+
"eval_samples_per_second": 695.724,
|
| 1715 |
+
"eval_steps_per_second": 22.263,
|
| 1716 |
+
"step": 61000
|
| 1717 |
+
},
|
| 1718 |
+
{
|
| 1719 |
+
"epoch": 5.98,
|
| 1720 |
+
"learning_rate": 4.0383111806098515e-05,
|
| 1721 |
+
"loss": 0.1462,
|
| 1722 |
+
"step": 61500
|
| 1723 |
+
},
|
| 1724 |
+
{
|
| 1725 |
+
"epoch": 5.98,
|
| 1726 |
+
"eval_loss": 0.44478389620780945,
|
| 1727 |
+
"eval_runtime": 1.4258,
|
| 1728 |
+
"eval_samples_per_second": 701.358,
|
| 1729 |
+
"eval_steps_per_second": 22.443,
|
| 1730 |
+
"step": 61500
|
| 1731 |
+
},
|
| 1732 |
+
{
|
| 1733 |
+
"epoch": 6.03,
|
| 1734 |
+
"learning_rate": 3.989444878811572e-05,
|
| 1735 |
+
"loss": 0.1335,
|
| 1736 |
+
"step": 62000
|
| 1737 |
+
},
|
| 1738 |
+
{
|
| 1739 |
+
"epoch": 6.03,
|
| 1740 |
+
"eval_loss": 0.450600266456604,
|
| 1741 |
+
"eval_runtime": 1.4249,
|
| 1742 |
+
"eval_samples_per_second": 701.787,
|
| 1743 |
+
"eval_steps_per_second": 22.457,
|
| 1744 |
+
"step": 62000
|
| 1745 |
+
},
|
| 1746 |
+
{
|
| 1747 |
+
"epoch": 6.08,
|
| 1748 |
+
"learning_rate": 3.940578577013292e-05,
|
| 1749 |
+
"loss": 0.1279,
|
| 1750 |
+
"step": 62500
|
| 1751 |
+
},
|
| 1752 |
+
{
|
| 1753 |
+
"epoch": 6.08,
|
| 1754 |
+
"eval_loss": 0.45286017656326294,
|
| 1755 |
+
"eval_runtime": 1.4175,
|
| 1756 |
+
"eval_samples_per_second": 705.475,
|
| 1757 |
+
"eval_steps_per_second": 22.575,
|
| 1758 |
+
"step": 62500
|
| 1759 |
+
},
|
| 1760 |
+
{
|
| 1761 |
+
"epoch": 6.13,
|
| 1762 |
+
"learning_rate": 3.891712275215012e-05,
|
| 1763 |
+
"loss": 0.1318,
|
| 1764 |
+
"step": 63000
|
| 1765 |
+
},
|
| 1766 |
+
{
|
| 1767 |
+
"epoch": 6.13,
|
| 1768 |
+
"eval_loss": 0.4531707763671875,
|
| 1769 |
+
"eval_runtime": 1.4314,
|
| 1770 |
+
"eval_samples_per_second": 698.621,
|
| 1771 |
+
"eval_steps_per_second": 22.356,
|
| 1772 |
+
"step": 63000
|
| 1773 |
+
},
|
| 1774 |
+
{
|
| 1775 |
+
"epoch": 6.18,
|
| 1776 |
+
"learning_rate": 3.842845973416732e-05,
|
| 1777 |
+
"loss": 0.1297,
|
| 1778 |
+
"step": 63500
|
| 1779 |
+
},
|
| 1780 |
+
{
|
| 1781 |
+
"epoch": 6.18,
|
| 1782 |
+
"eval_loss": 0.4539336562156677,
|
| 1783 |
+
"eval_runtime": 1.422,
|
| 1784 |
+
"eval_samples_per_second": 703.255,
|
| 1785 |
+
"eval_steps_per_second": 22.504,
|
| 1786 |
+
"step": 63500
|
| 1787 |
+
},
|
| 1788 |
+
{
|
| 1789 |
+
"epoch": 6.22,
|
| 1790 |
+
"learning_rate": 3.7939796716184525e-05,
|
| 1791 |
+
"loss": 0.1314,
|
| 1792 |
+
"step": 64000
|
| 1793 |
+
},
|
| 1794 |
+
{
|
| 1795 |
+
"epoch": 6.22,
|
| 1796 |
+
"eval_loss": 0.4507242441177368,
|
| 1797 |
+
"eval_runtime": 1.4354,
|
| 1798 |
+
"eval_samples_per_second": 696.689,
|
| 1799 |
+
"eval_steps_per_second": 22.294,
|
| 1800 |
+
"step": 64000
|
| 1801 |
+
},
|
| 1802 |
+
{
|
| 1803 |
+
"epoch": 6.27,
|
| 1804 |
+
"learning_rate": 3.7451133698201725e-05,
|
| 1805 |
+
"loss": 0.1295,
|
| 1806 |
+
"step": 64500
|
| 1807 |
+
},
|
| 1808 |
+
{
|
| 1809 |
+
"epoch": 6.27,
|
| 1810 |
+
"eval_loss": 0.45251962542533875,
|
| 1811 |
+
"eval_runtime": 1.4215,
|
| 1812 |
+
"eval_samples_per_second": 703.503,
|
| 1813 |
+
"eval_steps_per_second": 22.512,
|
| 1814 |
+
"step": 64500
|
| 1815 |
+
},
|
| 1816 |
+
{
|
| 1817 |
+
"epoch": 6.32,
|
| 1818 |
+
"learning_rate": 3.6962470680218924e-05,
|
| 1819 |
+
"loss": 0.1311,
|
| 1820 |
+
"step": 65000
|
| 1821 |
+
},
|
| 1822 |
+
{
|
| 1823 |
+
"epoch": 6.32,
|
| 1824 |
+
"eval_loss": 0.45232245326042175,
|
| 1825 |
+
"eval_runtime": 1.4364,
|
| 1826 |
+
"eval_samples_per_second": 696.202,
|
| 1827 |
+
"eval_steps_per_second": 22.278,
|
| 1828 |
+
"step": 65000
|
| 1829 |
+
},
|
| 1830 |
+
{
|
| 1831 |
+
"epoch": 6.37,
|
| 1832 |
+
"learning_rate": 3.6473807662236124e-05,
|
| 1833 |
+
"loss": 0.1303,
|
| 1834 |
+
"step": 65500
|
| 1835 |
+
},
|
| 1836 |
+
{
|
| 1837 |
+
"epoch": 6.37,
|
| 1838 |
+
"eval_loss": 0.45104601979255676,
|
| 1839 |
+
"eval_runtime": 1.421,
|
| 1840 |
+
"eval_samples_per_second": 703.749,
|
| 1841 |
+
"eval_steps_per_second": 22.52,
|
| 1842 |
+
"step": 65500
|
| 1843 |
+
},
|
| 1844 |
+
{
|
| 1845 |
+
"epoch": 6.42,
|
| 1846 |
+
"learning_rate": 3.598514464425333e-05,
|
| 1847 |
+
"loss": 0.1289,
|
| 1848 |
+
"step": 66000
|
| 1849 |
+
},
|
| 1850 |
+
{
|
| 1851 |
+
"epoch": 6.42,
|
| 1852 |
+
"eval_loss": 0.44871556758880615,
|
| 1853 |
+
"eval_runtime": 1.4274,
|
| 1854 |
+
"eval_samples_per_second": 700.563,
|
| 1855 |
+
"eval_steps_per_second": 22.418,
|
| 1856 |
+
"step": 66000
|
| 1857 |
+
},
|
| 1858 |
+
{
|
| 1859 |
+
"epoch": 6.47,
|
| 1860 |
+
"learning_rate": 3.549648162627053e-05,
|
| 1861 |
+
"loss": 0.1375,
|
| 1862 |
+
"step": 66500
|
| 1863 |
+
},
|
| 1864 |
+
{
|
| 1865 |
+
"epoch": 6.47,
|
| 1866 |
+
"eval_loss": 0.4471152126789093,
|
| 1867 |
+
"eval_runtime": 1.4185,
|
| 1868 |
+
"eval_samples_per_second": 704.978,
|
| 1869 |
+
"eval_steps_per_second": 22.559,
|
| 1870 |
+
"step": 66500
|
| 1871 |
+
},
|
| 1872 |
+
{
|
| 1873 |
+
"epoch": 6.52,
|
| 1874 |
+
"learning_rate": 3.500781860828773e-05,
|
| 1875 |
+
"loss": 0.1295,
|
| 1876 |
+
"step": 67000
|
| 1877 |
+
},
|
| 1878 |
+
{
|
| 1879 |
+
"epoch": 6.52,
|
| 1880 |
+
"eval_loss": 0.44929370284080505,
|
| 1881 |
+
"eval_runtime": 1.414,
|
| 1882 |
+
"eval_samples_per_second": 707.208,
|
| 1883 |
+
"eval_steps_per_second": 22.631,
|
| 1884 |
+
"step": 67000
|
| 1885 |
+
},
|
| 1886 |
+
{
|
| 1887 |
+
"epoch": 6.56,
|
| 1888 |
+
"learning_rate": 3.451915559030492e-05,
|
| 1889 |
+
"loss": 0.1291,
|
| 1890 |
+
"step": 67500
|
| 1891 |
+
},
|
| 1892 |
+
{
|
| 1893 |
+
"epoch": 6.56,
|
| 1894 |
+
"eval_loss": 0.44738081097602844,
|
| 1895 |
+
"eval_runtime": 1.4095,
|
| 1896 |
+
"eval_samples_per_second": 709.453,
|
| 1897 |
+
"eval_steps_per_second": 22.703,
|
| 1898 |
+
"step": 67500
|
| 1899 |
+
},
|
| 1900 |
+
{
|
| 1901 |
+
"epoch": 6.61,
|
| 1902 |
+
"learning_rate": 3.403049257232213e-05,
|
| 1903 |
+
"loss": 0.1297,
|
| 1904 |
+
"step": 68000
|
| 1905 |
+
},
|
| 1906 |
+
{
|
| 1907 |
+
"epoch": 6.61,
|
| 1908 |
+
"eval_loss": 0.4483153820037842,
|
| 1909 |
+
"eval_runtime": 1.4314,
|
| 1910 |
+
"eval_samples_per_second": 698.622,
|
| 1911 |
+
"eval_steps_per_second": 22.356,
|
| 1912 |
+
"step": 68000
|
| 1913 |
+
},
|
| 1914 |
+
{
|
| 1915 |
+
"epoch": 6.66,
|
| 1916 |
+
"learning_rate": 3.354182955433933e-05,
|
| 1917 |
+
"loss": 0.1354,
|
| 1918 |
+
"step": 68500
|
| 1919 |
+
},
|
| 1920 |
+
{
|
| 1921 |
+
"epoch": 6.66,
|
| 1922 |
+
"eval_loss": 0.4452635943889618,
|
| 1923 |
+
"eval_runtime": 1.4074,
|
| 1924 |
+
"eval_samples_per_second": 710.532,
|
| 1925 |
+
"eval_steps_per_second": 22.737,
|
| 1926 |
+
"step": 68500
|
| 1927 |
+
},
|
| 1928 |
+
{
|
| 1929 |
+
"epoch": 6.71,
|
| 1930 |
+
"learning_rate": 3.305316653635653e-05,
|
| 1931 |
+
"loss": 0.1316,
|
| 1932 |
+
"step": 69000
|
| 1933 |
+
},
|
| 1934 |
+
{
|
| 1935 |
+
"epoch": 6.71,
|
| 1936 |
+
"eval_loss": 0.4459252953529358,
|
| 1937 |
+
"eval_runtime": 1.4149,
|
| 1938 |
+
"eval_samples_per_second": 706.773,
|
| 1939 |
+
"eval_steps_per_second": 22.617,
|
| 1940 |
+
"step": 69000
|
| 1941 |
+
},
|
| 1942 |
+
{
|
| 1943 |
+
"epoch": 6.76,
|
| 1944 |
+
"learning_rate": 3.2564503518373726e-05,
|
| 1945 |
+
"loss": 0.1303,
|
| 1946 |
+
"step": 69500
|
| 1947 |
+
},
|
| 1948 |
+
{
|
| 1949 |
+
"epoch": 6.76,
|
| 1950 |
+
"eval_loss": 0.4454708397388458,
|
| 1951 |
+
"eval_runtime": 1.4195,
|
| 1952 |
+
"eval_samples_per_second": 704.485,
|
| 1953 |
+
"eval_steps_per_second": 22.544,
|
| 1954 |
+
"step": 69500
|
| 1955 |
+
},
|
| 1956 |
+
{
|
| 1957 |
+
"epoch": 6.81,
|
| 1958 |
+
"learning_rate": 3.207584050039093e-05,
|
| 1959 |
+
"loss": 0.1352,
|
| 1960 |
+
"step": 70000
|
| 1961 |
+
},
|
| 1962 |
+
{
|
| 1963 |
+
"epoch": 6.81,
|
| 1964 |
+
"eval_loss": 0.4453655481338501,
|
| 1965 |
+
"eval_runtime": 1.4036,
|
| 1966 |
+
"eval_samples_per_second": 712.466,
|
| 1967 |
+
"eval_steps_per_second": 22.799,
|
| 1968 |
+
"step": 70000
|
| 1969 |
+
},
|
| 1970 |
+
{
|
| 1971 |
+
"epoch": 6.86,
|
| 1972 |
+
"learning_rate": 3.158717748240813e-05,
|
| 1973 |
+
"loss": 0.1278,
|
| 1974 |
+
"step": 70500
|
| 1975 |
+
},
|
| 1976 |
+
{
|
| 1977 |
+
"epoch": 6.86,
|
| 1978 |
+
"eval_loss": 0.44641512632369995,
|
| 1979 |
+
"eval_runtime": 1.4284,
|
| 1980 |
+
"eval_samples_per_second": 700.077,
|
| 1981 |
+
"eval_steps_per_second": 22.402,
|
| 1982 |
+
"step": 70500
|
| 1983 |
+
},
|
| 1984 |
+
{
|
| 1985 |
+
"epoch": 6.91,
|
| 1986 |
+
"learning_rate": 3.109851446442533e-05,
|
| 1987 |
+
"loss": 0.127,
|
| 1988 |
+
"step": 71000
|
| 1989 |
+
},
|
| 1990 |
+
{
|
| 1991 |
+
"epoch": 6.91,
|
| 1992 |
+
"eval_loss": 0.446814626455307,
|
| 1993 |
+
"eval_runtime": 1.4239,
|
| 1994 |
+
"eval_samples_per_second": 702.277,
|
| 1995 |
+
"eval_steps_per_second": 22.473,
|
| 1996 |
+
"step": 71000
|
| 1997 |
+
},
|
| 1998 |
+
{
|
| 1999 |
+
"epoch": 6.95,
|
| 2000 |
+
"learning_rate": 3.060985144644253e-05,
|
| 2001 |
+
"loss": 0.1337,
|
| 2002 |
+
"step": 71500
|
| 2003 |
+
},
|
| 2004 |
+
{
|
| 2005 |
+
"epoch": 6.95,
|
| 2006 |
+
"eval_loss": 0.44566431641578674,
|
| 2007 |
+
"eval_runtime": 1.421,
|
| 2008 |
+
"eval_samples_per_second": 703.749,
|
| 2009 |
+
"eval_steps_per_second": 22.52,
|
| 2010 |
+
"step": 71500
|
| 2011 |
+
},
|
| 2012 |
+
{
|
| 2013 |
+
"epoch": 7.0,
|
| 2014 |
+
"learning_rate": 3.0121188428459734e-05,
|
| 2015 |
+
"loss": 0.1322,
|
| 2016 |
+
"step": 72000
|
| 2017 |
+
},
|
| 2018 |
+
{
|
| 2019 |
+
"epoch": 7.0,
|
| 2020 |
+
"eval_loss": 0.4453600347042084,
|
| 2021 |
+
"eval_runtime": 1.3961,
|
| 2022 |
+
"eval_samples_per_second": 716.266,
|
| 2023 |
+
"eval_steps_per_second": 22.921,
|
| 2024 |
+
"step": 72000
|
| 2025 |
+
},
|
| 2026 |
+
{
|
| 2027 |
+
"epoch": 7.05,
|
| 2028 |
+
"learning_rate": 2.9632525410476936e-05,
|
| 2029 |
+
"loss": 0.1171,
|
| 2030 |
+
"step": 72500
|
| 2031 |
+
},
|
| 2032 |
+
{
|
| 2033 |
+
"epoch": 7.05,
|
| 2034 |
+
"eval_loss": 0.45082348585128784,
|
| 2035 |
+
"eval_runtime": 1.4021,
|
| 2036 |
+
"eval_samples_per_second": 713.223,
|
| 2037 |
+
"eval_steps_per_second": 22.823,
|
| 2038 |
+
"step": 72500
|
| 2039 |
+
},
|
| 2040 |
+
{
|
| 2041 |
+
"epoch": 7.1,
|
| 2042 |
+
"learning_rate": 2.9143862392494136e-05,
|
| 2043 |
+
"loss": 0.1201,
|
| 2044 |
+
"step": 73000
|
| 2045 |
+
},
|
| 2046 |
+
{
|
| 2047 |
+
"epoch": 7.1,
|
| 2048 |
+
"eval_loss": 0.45133039355278015,
|
| 2049 |
+
"eval_runtime": 1.4284,
|
| 2050 |
+
"eval_samples_per_second": 700.08,
|
| 2051 |
+
"eval_steps_per_second": 22.403,
|
| 2052 |
+
"step": 73000
|
| 2053 |
+
},
|
| 2054 |
+
{
|
| 2055 |
+
"epoch": 7.15,
|
| 2056 |
+
"learning_rate": 2.865519937451134e-05,
|
| 2057 |
+
"loss": 0.1119,
|
| 2058 |
+
"step": 73500
|
| 2059 |
+
},
|
| 2060 |
+
{
|
| 2061 |
+
"epoch": 7.15,
|
| 2062 |
+
"eval_loss": 0.4528238773345947,
|
| 2063 |
+
"eval_runtime": 1.4066,
|
| 2064 |
+
"eval_samples_per_second": 710.952,
|
| 2065 |
+
"eval_steps_per_second": 22.75,
|
| 2066 |
+
"step": 73500
|
| 2067 |
+
},
|
| 2068 |
+
{
|
| 2069 |
+
"epoch": 7.2,
|
| 2070 |
+
"learning_rate": 2.8166536356528538e-05,
|
| 2071 |
+
"loss": 0.1178,
|
| 2072 |
+
"step": 74000
|
| 2073 |
+
},
|
| 2074 |
+
{
|
| 2075 |
+
"epoch": 7.2,
|
| 2076 |
+
"eval_loss": 0.4517793655395508,
|
| 2077 |
+
"eval_runtime": 1.4279,
|
| 2078 |
+
"eval_samples_per_second": 700.319,
|
| 2079 |
+
"eval_steps_per_second": 22.41,
|
| 2080 |
+
"step": 74000
|
| 2081 |
+
},
|
| 2082 |
+
{
|
| 2083 |
+
"epoch": 7.25,
|
| 2084 |
+
"learning_rate": 2.767787333854574e-05,
|
| 2085 |
+
"loss": 0.1172,
|
| 2086 |
+
"step": 74500
|
| 2087 |
+
},
|
| 2088 |
+
{
|
| 2089 |
+
"epoch": 7.25,
|
| 2090 |
+
"eval_loss": 0.45097029209136963,
|
| 2091 |
+
"eval_runtime": 1.4105,
|
| 2092 |
+
"eval_samples_per_second": 708.955,
|
| 2093 |
+
"eval_steps_per_second": 22.687,
|
| 2094 |
+
"step": 74500
|
| 2095 |
+
},
|
| 2096 |
+
{
|
| 2097 |
+
"epoch": 7.29,
|
| 2098 |
+
"learning_rate": 2.718921032056294e-05,
|
| 2099 |
+
"loss": 0.1229,
|
| 2100 |
+
"step": 75000
|
| 2101 |
+
},
|
| 2102 |
+
{
|
| 2103 |
+
"epoch": 7.29,
|
| 2104 |
+
"eval_loss": 0.4481058418750763,
|
| 2105 |
+
"eval_runtime": 1.4051,
|
| 2106 |
+
"eval_samples_per_second": 711.694,
|
| 2107 |
+
"eval_steps_per_second": 22.774,
|
| 2108 |
+
"step": 75000
|
| 2109 |
+
},
|
| 2110 |
+
{
|
| 2111 |
+
"epoch": 7.34,
|
| 2112 |
+
"learning_rate": 2.6700547302580143e-05,
|
| 2113 |
+
"loss": 0.12,
|
| 2114 |
+
"step": 75500
|
| 2115 |
+
},
|
| 2116 |
+
{
|
| 2117 |
+
"epoch": 7.34,
|
| 2118 |
+
"eval_loss": 0.4482279419898987,
|
| 2119 |
+
"eval_runtime": 1.411,
|
| 2120 |
+
"eval_samples_per_second": 708.702,
|
| 2121 |
+
"eval_steps_per_second": 22.678,
|
| 2122 |
+
"step": 75500
|
| 2123 |
+
},
|
| 2124 |
+
{
|
| 2125 |
+
"epoch": 7.39,
|
| 2126 |
+
"learning_rate": 2.6211884284597343e-05,
|
| 2127 |
+
"loss": 0.1158,
|
| 2128 |
+
"step": 76000
|
| 2129 |
+
},
|
| 2130 |
+
{
|
| 2131 |
+
"epoch": 7.39,
|
| 2132 |
+
"eval_loss": 0.4505749046802521,
|
| 2133 |
+
"eval_runtime": 1.4021,
|
| 2134 |
+
"eval_samples_per_second": 713.221,
|
| 2135 |
+
"eval_steps_per_second": 22.823,
|
| 2136 |
+
"step": 76000
|
| 2137 |
+
},
|
| 2138 |
+
{
|
| 2139 |
+
"epoch": 7.44,
|
| 2140 |
+
"learning_rate": 2.5723221266614546e-05,
|
| 2141 |
+
"loss": 0.1212,
|
| 2142 |
+
"step": 76500
|
| 2143 |
+
},
|
| 2144 |
+
{
|
| 2145 |
+
"epoch": 7.44,
|
| 2146 |
+
"eval_loss": 0.4481782913208008,
|
| 2147 |
+
"eval_runtime": 1.4165,
|
| 2148 |
+
"eval_samples_per_second": 705.97,
|
| 2149 |
+
"eval_steps_per_second": 22.591,
|
| 2150 |
+
"step": 76500
|
| 2151 |
+
},
|
| 2152 |
+
{
|
| 2153 |
+
"epoch": 7.49,
|
| 2154 |
+
"learning_rate": 2.5234558248631745e-05,
|
| 2155 |
+
"loss": 0.1189,
|
| 2156 |
+
"step": 77000
|
| 2157 |
+
},
|
| 2158 |
+
{
|
| 2159 |
+
"epoch": 7.49,
|
| 2160 |
+
"eval_loss": 0.44906875491142273,
|
| 2161 |
+
"eval_runtime": 1.4185,
|
| 2162 |
+
"eval_samples_per_second": 704.978,
|
| 2163 |
+
"eval_steps_per_second": 22.559,
|
| 2164 |
+
"step": 77000
|
| 2165 |
+
},
|
| 2166 |
+
{
|
| 2167 |
+
"epoch": 7.54,
|
| 2168 |
+
"learning_rate": 2.4745895230648948e-05,
|
| 2169 |
+
"loss": 0.1225,
|
| 2170 |
+
"step": 77500
|
| 2171 |
+
},
|
| 2172 |
+
{
|
| 2173 |
+
"epoch": 7.54,
|
| 2174 |
+
"eval_loss": 0.4473673701286316,
|
| 2175 |
+
"eval_runtime": 1.408,
|
| 2176 |
+
"eval_samples_per_second": 710.203,
|
| 2177 |
+
"eval_steps_per_second": 22.727,
|
| 2178 |
+
"step": 77500
|
| 2179 |
+
},
|
| 2180 |
+
{
|
| 2181 |
+
"epoch": 7.59,
|
| 2182 |
+
"learning_rate": 2.4257232212666147e-05,
|
| 2183 |
+
"loss": 0.1206,
|
| 2184 |
+
"step": 78000
|
| 2185 |
+
},
|
| 2186 |
+
{
|
| 2187 |
+
"epoch": 7.59,
|
| 2188 |
+
"eval_loss": 0.4478332996368408,
|
| 2189 |
+
"eval_runtime": 1.4299,
|
| 2190 |
+
"eval_samples_per_second": 699.349,
|
| 2191 |
+
"eval_steps_per_second": 22.379,
|
| 2192 |
+
"step": 78000
|
| 2193 |
+
},
|
| 2194 |
+
{
|
| 2195 |
+
"epoch": 7.63,
|
| 2196 |
+
"learning_rate": 2.376856919468335e-05,
|
| 2197 |
+
"loss": 0.1205,
|
| 2198 |
+
"step": 78500
|
| 2199 |
+
},
|
| 2200 |
+
{
|
| 2201 |
+
"epoch": 7.63,
|
| 2202 |
+
"eval_loss": 0.4450225234031677,
|
| 2203 |
+
"eval_runtime": 1.4139,
|
| 2204 |
+
"eval_samples_per_second": 707.288,
|
| 2205 |
+
"eval_steps_per_second": 22.633,
|
| 2206 |
+
"step": 78500
|
| 2207 |
+
},
|
| 2208 |
+
{
|
| 2209 |
+
"epoch": 7.68,
|
| 2210 |
+
"learning_rate": 2.3279906176700546e-05,
|
| 2211 |
+
"loss": 0.1237,
|
| 2212 |
+
"step": 79000
|
| 2213 |
+
},
|
| 2214 |
+
{
|
| 2215 |
+
"epoch": 7.68,
|
| 2216 |
+
"eval_loss": 0.44548895955085754,
|
| 2217 |
+
"eval_runtime": 1.418,
|
| 2218 |
+
"eval_samples_per_second": 705.229,
|
| 2219 |
+
"eval_steps_per_second": 22.567,
|
| 2220 |
+
"step": 79000
|
| 2221 |
+
},
|
| 2222 |
+
{
|
| 2223 |
+
"epoch": 7.73,
|
| 2224 |
+
"learning_rate": 2.279124315871775e-05,
|
| 2225 |
+
"loss": 0.1211,
|
| 2226 |
+
"step": 79500
|
| 2227 |
+
},
|
| 2228 |
+
{
|
| 2229 |
+
"epoch": 7.73,
|
| 2230 |
+
"eval_loss": 0.4440496861934662,
|
| 2231 |
+
"eval_runtime": 1.4428,
|
| 2232 |
+
"eval_samples_per_second": 693.091,
|
| 2233 |
+
"eval_steps_per_second": 22.179,
|
| 2234 |
+
"step": 79500
|
| 2235 |
+
},
|
| 2236 |
+
{
|
| 2237 |
+
"epoch": 7.78,
|
| 2238 |
+
"learning_rate": 2.230258014073495e-05,
|
| 2239 |
+
"loss": 0.1167,
|
| 2240 |
+
"step": 80000
|
| 2241 |
+
},
|
| 2242 |
+
{
|
| 2243 |
+
"epoch": 7.78,
|
| 2244 |
+
"eval_loss": 0.44403979182243347,
|
| 2245 |
+
"eval_runtime": 1.415,
|
| 2246 |
+
"eval_samples_per_second": 706.709,
|
| 2247 |
+
"eval_steps_per_second": 22.615,
|
| 2248 |
+
"step": 80000
|
| 2249 |
+
},
|
| 2250 |
+
{
|
| 2251 |
+
"epoch": 7.83,
|
| 2252 |
+
"learning_rate": 2.181391712275215e-05,
|
| 2253 |
+
"loss": 0.1195,
|
| 2254 |
+
"step": 80500
|
| 2255 |
+
},
|
| 2256 |
+
{
|
| 2257 |
+
"epoch": 7.83,
|
| 2258 |
+
"eval_loss": 0.44386279582977295,
|
| 2259 |
+
"eval_runtime": 1.411,
|
| 2260 |
+
"eval_samples_per_second": 708.704,
|
| 2261 |
+
"eval_steps_per_second": 22.679,
|
| 2262 |
+
"step": 80500
|
| 2263 |
+
},
|
| 2264 |
+
{
|
| 2265 |
+
"epoch": 7.88,
|
| 2266 |
+
"learning_rate": 2.132525410476935e-05,
|
| 2267 |
+
"loss": 0.1236,
|
| 2268 |
+
"step": 81000
|
| 2269 |
+
},
|
| 2270 |
+
{
|
| 2271 |
+
"epoch": 7.88,
|
| 2272 |
+
"eval_loss": 0.4440469443798065,
|
| 2273 |
+
"eval_runtime": 1.413,
|
| 2274 |
+
"eval_samples_per_second": 707.702,
|
| 2275 |
+
"eval_steps_per_second": 22.646,
|
| 2276 |
+
"step": 81000
|
| 2277 |
+
},
|
| 2278 |
+
{
|
| 2279 |
+
"epoch": 7.93,
|
| 2280 |
+
"learning_rate": 2.0836591086786554e-05,
|
| 2281 |
+
"loss": 0.1196,
|
| 2282 |
+
"step": 81500
|
| 2283 |
+
},
|
| 2284 |
+
{
|
| 2285 |
+
"epoch": 7.93,
|
| 2286 |
+
"eval_loss": 0.4431215822696686,
|
| 2287 |
+
"eval_runtime": 1.4071,
|
| 2288 |
+
"eval_samples_per_second": 710.704,
|
| 2289 |
+
"eval_steps_per_second": 22.743,
|
| 2290 |
+
"step": 81500
|
| 2291 |
+
},
|
| 2292 |
+
{
|
| 2293 |
+
"epoch": 7.98,
|
| 2294 |
+
"learning_rate": 2.0347928068803753e-05,
|
| 2295 |
+
"loss": 0.1154,
|
| 2296 |
+
"step": 82000
|
| 2297 |
+
},
|
| 2298 |
+
{
|
| 2299 |
+
"epoch": 7.98,
|
| 2300 |
+
"eval_loss": 0.44494298100471497,
|
| 2301 |
+
"eval_runtime": 1.3991,
|
| 2302 |
+
"eval_samples_per_second": 714.74,
|
| 2303 |
+
"eval_steps_per_second": 22.872,
|
| 2304 |
+
"step": 82000
|
| 2305 |
+
},
|
| 2306 |
+
{
|
| 2307 |
+
"epoch": 8.02,
|
| 2308 |
+
"learning_rate": 1.9859265050820956e-05,
|
| 2309 |
+
"loss": 0.1146,
|
| 2310 |
+
"step": 82500
|
| 2311 |
+
},
|
| 2312 |
+
{
|
| 2313 |
+
"epoch": 8.02,
|
| 2314 |
+
"eval_loss": 0.44438567757606506,
|
| 2315 |
+
"eval_runtime": 1.4136,
|
| 2316 |
+
"eval_samples_per_second": 707.391,
|
| 2317 |
+
"eval_steps_per_second": 22.637,
|
| 2318 |
+
"step": 82500
|
| 2319 |
+
},
|
| 2320 |
+
{
|
| 2321 |
+
"epoch": 8.07,
|
| 2322 |
+
"learning_rate": 1.9370602032838155e-05,
|
| 2323 |
+
"loss": 0.111,
|
| 2324 |
+
"step": 83000
|
| 2325 |
+
},
|
| 2326 |
+
{
|
| 2327 |
+
"epoch": 8.07,
|
| 2328 |
+
"eval_loss": 0.4510573744773865,
|
| 2329 |
+
"eval_runtime": 1.4011,
|
| 2330 |
+
"eval_samples_per_second": 713.727,
|
| 2331 |
+
"eval_steps_per_second": 22.839,
|
| 2332 |
+
"step": 83000
|
| 2333 |
+
},
|
| 2334 |
+
{
|
| 2335 |
+
"epoch": 8.12,
|
| 2336 |
+
"learning_rate": 1.8881939014855358e-05,
|
| 2337 |
+
"loss": 0.1107,
|
| 2338 |
+
"step": 83500
|
| 2339 |
+
},
|
| 2340 |
+
{
|
| 2341 |
+
"epoch": 8.12,
|
| 2342 |
+
"eval_loss": 0.45002079010009766,
|
| 2343 |
+
"eval_runtime": 1.4195,
|
| 2344 |
+
"eval_samples_per_second": 704.487,
|
| 2345 |
+
"eval_steps_per_second": 22.544,
|
| 2346 |
+
"step": 83500
|
| 2347 |
+
},
|
| 2348 |
+
{
|
| 2349 |
+
"epoch": 8.17,
|
| 2350 |
+
"learning_rate": 1.8393275996872558e-05,
|
| 2351 |
+
"loss": 0.1069,
|
| 2352 |
+
"step": 84000
|
| 2353 |
+
},
|
| 2354 |
+
{
|
| 2355 |
+
"epoch": 8.17,
|
| 2356 |
+
"eval_loss": 0.4500637352466583,
|
| 2357 |
+
"eval_runtime": 1.4026,
|
| 2358 |
+
"eval_samples_per_second": 712.972,
|
| 2359 |
+
"eval_steps_per_second": 22.815,
|
| 2360 |
+
"step": 84000
|
| 2361 |
+
},
|
| 2362 |
+
{
|
| 2363 |
+
"epoch": 8.22,
|
| 2364 |
+
"learning_rate": 1.790461297888976e-05,
|
| 2365 |
+
"loss": 0.1091,
|
| 2366 |
+
"step": 84500
|
| 2367 |
+
},
|
| 2368 |
+
{
|
| 2369 |
+
"epoch": 8.22,
|
| 2370 |
+
"eval_loss": 0.450139582157135,
|
| 2371 |
+
"eval_runtime": 1.423,
|
| 2372 |
+
"eval_samples_per_second": 702.764,
|
| 2373 |
+
"eval_steps_per_second": 22.488,
|
| 2374 |
+
"step": 84500
|
| 2375 |
+
},
|
| 2376 |
+
{
|
| 2377 |
+
"epoch": 8.27,
|
| 2378 |
+
"learning_rate": 1.741594996090696e-05,
|
| 2379 |
+
"loss": 0.1107,
|
| 2380 |
+
"step": 85000
|
| 2381 |
+
},
|
| 2382 |
+
{
|
| 2383 |
+
"epoch": 8.27,
|
| 2384 |
+
"eval_loss": 0.4503149390220642,
|
| 2385 |
+
"eval_runtime": 1.407,
|
| 2386 |
+
"eval_samples_per_second": 710.707,
|
| 2387 |
+
"eval_steps_per_second": 22.743,
|
| 2388 |
+
"step": 85000
|
| 2389 |
+
},
|
| 2390 |
+
{
|
| 2391 |
+
"epoch": 8.32,
|
| 2392 |
+
"learning_rate": 1.6927286942924163e-05,
|
| 2393 |
+
"loss": 0.11,
|
| 2394 |
+
"step": 85500
|
| 2395 |
+
},
|
| 2396 |
+
{
|
| 2397 |
+
"epoch": 8.32,
|
| 2398 |
+
"eval_loss": 0.4499202370643616,
|
| 2399 |
+
"eval_runtime": 1.3956,
|
| 2400 |
+
"eval_samples_per_second": 716.522,
|
| 2401 |
+
"eval_steps_per_second": 22.929,
|
| 2402 |
+
"step": 85500
|
| 2403 |
+
},
|
| 2404 |
+
{
|
| 2405 |
+
"epoch": 8.36,
|
| 2406 |
+
"learning_rate": 1.6438623924941362e-05,
|
| 2407 |
+
"loss": 0.1084,
|
| 2408 |
+
"step": 86000
|
| 2409 |
+
},
|
| 2410 |
+
{
|
| 2411 |
+
"epoch": 8.36,
|
| 2412 |
+
"eval_loss": 0.4492938220500946,
|
| 2413 |
+
"eval_runtime": 1.4061,
|
| 2414 |
+
"eval_samples_per_second": 711.208,
|
| 2415 |
+
"eval_steps_per_second": 22.759,
|
| 2416 |
+
"step": 86000
|
| 2417 |
+
},
|
| 2418 |
+
{
|
| 2419 |
+
"epoch": 8.41,
|
| 2420 |
+
"learning_rate": 1.5949960906958562e-05,
|
| 2421 |
+
"loss": 0.1142,
|
| 2422 |
+
"step": 86500
|
| 2423 |
+
},
|
| 2424 |
+
{
|
| 2425 |
+
"epoch": 8.41,
|
| 2426 |
+
"eval_loss": 0.449333518743515,
|
| 2427 |
+
"eval_runtime": 1.417,
|
| 2428 |
+
"eval_samples_per_second": 705.721,
|
| 2429 |
+
"eval_steps_per_second": 22.583,
|
| 2430 |
+
"step": 86500
|
| 2431 |
+
},
|
| 2432 |
+
{
|
| 2433 |
+
"epoch": 8.46,
|
| 2434 |
+
"learning_rate": 1.546129788897576e-05,
|
| 2435 |
+
"loss": 0.1091,
|
| 2436 |
+
"step": 87000
|
| 2437 |
+
},
|
| 2438 |
+
{
|
| 2439 |
+
"epoch": 8.46,
|
| 2440 |
+
"eval_loss": 0.4506095051765442,
|
| 2441 |
+
"eval_runtime": 1.412,
|
| 2442 |
+
"eval_samples_per_second": 708.206,
|
| 2443 |
+
"eval_steps_per_second": 22.663,
|
| 2444 |
+
"step": 87000
|
| 2445 |
+
},
|
| 2446 |
+
{
|
| 2447 |
+
"epoch": 8.51,
|
| 2448 |
+
"learning_rate": 1.4972634870992962e-05,
|
| 2449 |
+
"loss": 0.1072,
|
| 2450 |
+
"step": 87500
|
| 2451 |
+
},
|
| 2452 |
+
{
|
| 2453 |
+
"epoch": 8.51,
|
| 2454 |
+
"eval_loss": 0.44918569922447205,
|
| 2455 |
+
"eval_runtime": 1.4021,
|
| 2456 |
+
"eval_samples_per_second": 713.221,
|
| 2457 |
+
"eval_steps_per_second": 22.823,
|
| 2458 |
+
"step": 87500
|
| 2459 |
+
},
|
| 2460 |
+
{
|
| 2461 |
+
"epoch": 8.56,
|
| 2462 |
+
"learning_rate": 1.4483971853010164e-05,
|
| 2463 |
+
"loss": 0.1128,
|
| 2464 |
+
"step": 88000
|
| 2465 |
+
},
|
| 2466 |
+
{
|
| 2467 |
+
"epoch": 8.56,
|
| 2468 |
+
"eval_loss": 0.44889140129089355,
|
| 2469 |
+
"eval_runtime": 1.414,
|
| 2470 |
+
"eval_samples_per_second": 707.21,
|
| 2471 |
+
"eval_steps_per_second": 22.631,
|
| 2472 |
+
"step": 88000
|
| 2473 |
+
},
|
| 2474 |
+
{
|
| 2475 |
+
"epoch": 8.61,
|
| 2476 |
+
"learning_rate": 1.3995308835027365e-05,
|
| 2477 |
+
"loss": 0.1123,
|
| 2478 |
+
"step": 88500
|
| 2479 |
+
},
|
| 2480 |
+
{
|
| 2481 |
+
"epoch": 8.61,
|
| 2482 |
+
"eval_loss": 0.44764241576194763,
|
| 2483 |
+
"eval_runtime": 1.4076,
|
| 2484 |
+
"eval_samples_per_second": 710.451,
|
| 2485 |
+
"eval_steps_per_second": 22.734,
|
| 2486 |
+
"step": 88500
|
| 2487 |
+
},
|
| 2488 |
+
{
|
| 2489 |
+
"epoch": 8.66,
|
| 2490 |
+
"learning_rate": 1.3506645817044566e-05,
|
| 2491 |
+
"loss": 0.1093,
|
| 2492 |
+
"step": 89000
|
| 2493 |
+
},
|
| 2494 |
+
{
|
| 2495 |
+
"epoch": 8.66,
|
| 2496 |
+
"eval_loss": 0.44862595200538635,
|
| 2497 |
+
"eval_runtime": 1.3991,
|
| 2498 |
+
"eval_samples_per_second": 714.742,
|
| 2499 |
+
"eval_steps_per_second": 22.872,
|
| 2500 |
+
"step": 89000
|
| 2501 |
+
},
|
| 2502 |
+
{
|
| 2503 |
+
"epoch": 8.7,
|
| 2504 |
+
"learning_rate": 1.3017982799061767e-05,
|
| 2505 |
+
"loss": 0.1111,
|
| 2506 |
+
"step": 89500
|
| 2507 |
+
},
|
| 2508 |
+
{
|
| 2509 |
+
"epoch": 8.7,
|
| 2510 |
+
"eval_loss": 0.4482482969760895,
|
| 2511 |
+
"eval_runtime": 1.3981,
|
| 2512 |
+
"eval_samples_per_second": 715.242,
|
| 2513 |
+
"eval_steps_per_second": 22.888,
|
| 2514 |
+
"step": 89500
|
| 2515 |
+
},
|
| 2516 |
+
{
|
| 2517 |
+
"epoch": 8.75,
|
| 2518 |
+
"learning_rate": 1.2529319781078968e-05,
|
| 2519 |
+
"loss": 0.1086,
|
| 2520 |
+
"step": 90000
|
| 2521 |
+
},
|
| 2522 |
+
{
|
| 2523 |
+
"epoch": 8.75,
|
| 2524 |
+
"eval_loss": 0.44752514362335205,
|
| 2525 |
+
"eval_runtime": 1.4036,
|
| 2526 |
+
"eval_samples_per_second": 712.46,
|
| 2527 |
+
"eval_steps_per_second": 22.799,
|
| 2528 |
+
"step": 90000
|
| 2529 |
+
},
|
| 2530 |
+
{
|
| 2531 |
+
"epoch": 8.8,
|
| 2532 |
+
"learning_rate": 1.204065676309617e-05,
|
| 2533 |
+
"loss": 0.11,
|
| 2534 |
+
"step": 90500
|
| 2535 |
+
},
|
| 2536 |
+
{
|
| 2537 |
+
"epoch": 8.8,
|
| 2538 |
+
"eval_loss": 0.44697925448417664,
|
| 2539 |
+
"eval_runtime": 1.401,
|
| 2540 |
+
"eval_samples_per_second": 713.773,
|
| 2541 |
+
"eval_steps_per_second": 22.841,
|
| 2542 |
+
"step": 90500
|
| 2543 |
+
},
|
| 2544 |
+
{
|
| 2545 |
+
"epoch": 8.85,
|
| 2546 |
+
"learning_rate": 1.155199374511337e-05,
|
| 2547 |
+
"loss": 0.1118,
|
| 2548 |
+
"step": 91000
|
| 2549 |
+
},
|
| 2550 |
+
{
|
| 2551 |
+
"epoch": 8.85,
|
| 2552 |
+
"eval_loss": 0.4479255974292755,
|
| 2553 |
+
"eval_runtime": 1.4107,
|
| 2554 |
+
"eval_samples_per_second": 708.879,
|
| 2555 |
+
"eval_steps_per_second": 22.684,
|
| 2556 |
+
"step": 91000
|
| 2557 |
+
},
|
| 2558 |
+
{
|
| 2559 |
+
"epoch": 8.9,
|
| 2560 |
+
"learning_rate": 1.1063330727130572e-05,
|
| 2561 |
+
"loss": 0.1078,
|
| 2562 |
+
"step": 91500
|
| 2563 |
+
},
|
| 2564 |
+
{
|
| 2565 |
+
"epoch": 8.9,
|
| 2566 |
+
"eval_loss": 0.4473107159137726,
|
| 2567 |
+
"eval_runtime": 1.4011,
|
| 2568 |
+
"eval_samples_per_second": 713.727,
|
| 2569 |
+
"eval_steps_per_second": 22.839,
|
| 2570 |
+
"step": 91500
|
| 2571 |
+
},
|
| 2572 |
+
{
|
| 2573 |
+
"epoch": 8.95,
|
| 2574 |
+
"learning_rate": 1.0574667709147771e-05,
|
| 2575 |
+
"loss": 0.1083,
|
| 2576 |
+
"step": 92000
|
| 2577 |
+
},
|
| 2578 |
+
{
|
| 2579 |
+
"epoch": 8.95,
|
| 2580 |
+
"eval_loss": 0.44750386476516724,
|
| 2581 |
+
"eval_runtime": 1.4056,
|
| 2582 |
+
"eval_samples_per_second": 711.457,
|
| 2583 |
+
"eval_steps_per_second": 22.767,
|
| 2584 |
+
"step": 92000
|
| 2585 |
+
},
|
| 2586 |
+
{
|
| 2587 |
+
"epoch": 9.0,
|
| 2588 |
+
"learning_rate": 1.0086004691164972e-05,
|
| 2589 |
+
"loss": 0.1127,
|
| 2590 |
+
"step": 92500
|
| 2591 |
+
},
|
| 2592 |
+
{
|
| 2593 |
+
"epoch": 9.0,
|
| 2594 |
+
"eval_loss": 0.4473421573638916,
|
| 2595 |
+
"eval_runtime": 1.4175,
|
| 2596 |
+
"eval_samples_per_second": 705.475,
|
| 2597 |
+
"eval_steps_per_second": 22.575,
|
| 2598 |
+
"step": 92500
|
| 2599 |
+
},
|
| 2600 |
+
{
|
| 2601 |
+
"epoch": 9.04,
|
| 2602 |
+
"learning_rate": 9.597341673182173e-06,
|
| 2603 |
+
"loss": 0.1034,
|
| 2604 |
+
"step": 93000
|
| 2605 |
+
},
|
| 2606 |
+
{
|
| 2607 |
+
"epoch": 9.04,
|
| 2608 |
+
"eval_loss": 0.4490604102611542,
|
| 2609 |
+
"eval_runtime": 1.4334,
|
| 2610 |
+
"eval_samples_per_second": 697.652,
|
| 2611 |
+
"eval_steps_per_second": 22.325,
|
| 2612 |
+
"step": 93000
|
| 2613 |
+
},
|
| 2614 |
+
{
|
| 2615 |
+
"epoch": 9.09,
|
| 2616 |
+
"learning_rate": 9.108678655199375e-06,
|
| 2617 |
+
"loss": 0.1022,
|
| 2618 |
+
"step": 93500
|
| 2619 |
+
},
|
| 2620 |
+
{
|
| 2621 |
+
"epoch": 9.09,
|
| 2622 |
+
"eval_loss": 0.45033252239227295,
|
| 2623 |
+
"eval_runtime": 1.4284,
|
| 2624 |
+
"eval_samples_per_second": 700.078,
|
| 2625 |
+
"eval_steps_per_second": 22.403,
|
| 2626 |
+
"step": 93500
|
| 2627 |
+
},
|
| 2628 |
+
{
|
| 2629 |
+
"epoch": 9.14,
|
| 2630 |
+
"learning_rate": 8.620015637216576e-06,
|
| 2631 |
+
"loss": 0.1048,
|
| 2632 |
+
"step": 94000
|
| 2633 |
+
},
|
| 2634 |
+
{
|
| 2635 |
+
"epoch": 9.14,
|
| 2636 |
+
"eval_loss": 0.45117974281311035,
|
| 2637 |
+
"eval_runtime": 1.412,
|
| 2638 |
+
"eval_samples_per_second": 708.205,
|
| 2639 |
+
"eval_steps_per_second": 22.663,
|
| 2640 |
+
"step": 94000
|
| 2641 |
+
},
|
| 2642 |
+
{
|
| 2643 |
+
"epoch": 9.19,
|
| 2644 |
+
"learning_rate": 8.131352619233777e-06,
|
| 2645 |
+
"loss": 0.1018,
|
| 2646 |
+
"step": 94500
|
| 2647 |
+
},
|
| 2648 |
+
{
|
| 2649 |
+
"epoch": 9.19,
|
| 2650 |
+
"eval_loss": 0.45118698477745056,
|
| 2651 |
+
"eval_runtime": 1.421,
|
| 2652 |
+
"eval_samples_per_second": 703.749,
|
| 2653 |
+
"eval_steps_per_second": 22.52,
|
| 2654 |
+
"step": 94500
|
| 2655 |
+
},
|
| 2656 |
+
{
|
| 2657 |
+
"epoch": 9.24,
|
| 2658 |
+
"learning_rate": 7.642689601250978e-06,
|
| 2659 |
+
"loss": 0.1064,
|
| 2660 |
+
"step": 95000
|
| 2661 |
+
},
|
| 2662 |
+
{
|
| 2663 |
+
"epoch": 9.24,
|
| 2664 |
+
"eval_loss": 0.4503132402896881,
|
| 2665 |
+
"eval_runtime": 1.4151,
|
| 2666 |
+
"eval_samples_per_second": 706.64,
|
| 2667 |
+
"eval_steps_per_second": 22.612,
|
| 2668 |
+
"step": 95000
|
| 2669 |
+
},
|
| 2670 |
+
{
|
| 2671 |
+
"epoch": 9.29,
|
| 2672 |
+
"learning_rate": 7.154026583268178e-06,
|
| 2673 |
+
"loss": 0.1055,
|
| 2674 |
+
"step": 95500
|
| 2675 |
+
},
|
| 2676 |
+
{
|
| 2677 |
+
"epoch": 9.29,
|
| 2678 |
+
"eval_loss": 0.4488275647163391,
|
| 2679 |
+
"eval_runtime": 1.417,
|
| 2680 |
+
"eval_samples_per_second": 705.722,
|
| 2681 |
+
"eval_steps_per_second": 22.583,
|
| 2682 |
+
"step": 95500
|
| 2683 |
+
},
|
| 2684 |
+
{
|
| 2685 |
+
"epoch": 9.34,
|
| 2686 |
+
"learning_rate": 6.665363565285379e-06,
|
| 2687 |
+
"loss": 0.1125,
|
| 2688 |
+
"step": 96000
|
| 2689 |
+
},
|
| 2690 |
+
{
|
| 2691 |
+
"epoch": 9.34,
|
| 2692 |
+
"eval_loss": 0.44890880584716797,
|
| 2693 |
+
"eval_runtime": 1.4006,
|
| 2694 |
+
"eval_samples_per_second": 713.983,
|
| 2695 |
+
"eval_steps_per_second": 22.847,
|
| 2696 |
+
"step": 96000
|
| 2697 |
+
},
|
| 2698 |
+
{
|
| 2699 |
+
"epoch": 9.39,
|
| 2700 |
+
"learning_rate": 6.1767005473025806e-06,
|
| 2701 |
+
"loss": 0.1002,
|
| 2702 |
+
"step": 96500
|
| 2703 |
+
},
|
| 2704 |
+
{
|
| 2705 |
+
"epoch": 9.39,
|
| 2706 |
+
"eval_loss": 0.44921454787254333,
|
| 2707 |
+
"eval_runtime": 1.4134,
|
| 2708 |
+
"eval_samples_per_second": 707.5,
|
| 2709 |
+
"eval_steps_per_second": 22.64,
|
| 2710 |
+
"step": 96500
|
| 2711 |
+
},
|
| 2712 |
+
{
|
| 2713 |
+
"epoch": 9.43,
|
| 2714 |
+
"learning_rate": 5.688037529319782e-06,
|
| 2715 |
+
"loss": 0.1043,
|
| 2716 |
+
"step": 97000
|
| 2717 |
+
},
|
| 2718 |
+
{
|
| 2719 |
+
"epoch": 9.43,
|
| 2720 |
+
"eval_loss": 0.4495786130428314,
|
| 2721 |
+
"eval_runtime": 1.408,
|
| 2722 |
+
"eval_samples_per_second": 710.206,
|
| 2723 |
+
"eval_steps_per_second": 22.727,
|
| 2724 |
+
"step": 97000
|
| 2725 |
+
},
|
| 2726 |
+
{
|
| 2727 |
+
"epoch": 9.48,
|
| 2728 |
+
"learning_rate": 5.199374511336982e-06,
|
| 2729 |
+
"loss": 0.102,
|
| 2730 |
+
"step": 97500
|
| 2731 |
+
},
|
| 2732 |
+
{
|
| 2733 |
+
"epoch": 9.48,
|
| 2734 |
+
"eval_loss": 0.44972699880599976,
|
| 2735 |
+
"eval_runtime": 1.4141,
|
| 2736 |
+
"eval_samples_per_second": 707.139,
|
| 2737 |
+
"eval_steps_per_second": 22.628,
|
| 2738 |
+
"step": 97500
|
| 2739 |
+
},
|
| 2740 |
+
{
|
| 2741 |
+
"epoch": 9.53,
|
| 2742 |
+
"learning_rate": 4.710711493354183e-06,
|
| 2743 |
+
"loss": 0.1059,
|
| 2744 |
+
"step": 98000
|
| 2745 |
+
},
|
| 2746 |
+
{
|
| 2747 |
+
"epoch": 9.53,
|
| 2748 |
+
"eval_loss": 0.44945281744003296,
|
| 2749 |
+
"eval_runtime": 1.4001,
|
| 2750 |
+
"eval_samples_per_second": 714.235,
|
| 2751 |
+
"eval_steps_per_second": 22.856,
|
| 2752 |
+
"step": 98000
|
| 2753 |
+
},
|
| 2754 |
+
{
|
| 2755 |
+
"epoch": 9.58,
|
| 2756 |
+
"learning_rate": 4.222048475371384e-06,
|
| 2757 |
+
"loss": 0.1012,
|
| 2758 |
+
"step": 98500
|
| 2759 |
+
},
|
| 2760 |
+
{
|
| 2761 |
+
"epoch": 9.58,
|
| 2762 |
+
"eval_loss": 0.44921252131462097,
|
| 2763 |
+
"eval_runtime": 1.4051,
|
| 2764 |
+
"eval_samples_per_second": 711.709,
|
| 2765 |
+
"eval_steps_per_second": 22.775,
|
| 2766 |
+
"step": 98500
|
| 2767 |
+
},
|
| 2768 |
+
{
|
| 2769 |
+
"epoch": 9.63,
|
| 2770 |
+
"learning_rate": 3.733385457388585e-06,
|
| 2771 |
+
"loss": 0.1066,
|
| 2772 |
+
"step": 99000
|
| 2773 |
+
},
|
| 2774 |
+
{
|
| 2775 |
+
"epoch": 9.63,
|
| 2776 |
+
"eval_loss": 0.44877171516418457,
|
| 2777 |
+
"eval_runtime": 1.42,
|
| 2778 |
+
"eval_samples_per_second": 704.241,
|
| 2779 |
+
"eval_steps_per_second": 22.536,
|
| 2780 |
+
"step": 99000
|
| 2781 |
+
},
|
| 2782 |
+
{
|
| 2783 |
+
"epoch": 9.68,
|
| 2784 |
+
"learning_rate": 3.244722439405786e-06,
|
| 2785 |
+
"loss": 0.1044,
|
| 2786 |
+
"step": 99500
|
| 2787 |
+
},
|
| 2788 |
+
{
|
| 2789 |
+
"epoch": 9.68,
|
| 2790 |
+
"eval_loss": 0.4489387273788452,
|
| 2791 |
+
"eval_runtime": 1.4031,
|
| 2792 |
+
"eval_samples_per_second": 712.712,
|
| 2793 |
+
"eval_steps_per_second": 22.807,
|
| 2794 |
+
"step": 99500
|
| 2795 |
+
},
|
| 2796 |
+
{
|
| 2797 |
+
"epoch": 9.73,
|
| 2798 |
+
"learning_rate": 2.756059421422987e-06,
|
| 2799 |
+
"loss": 0.1049,
|
| 2800 |
+
"step": 100000
|
| 2801 |
+
},
|
| 2802 |
+
{
|
| 2803 |
+
"epoch": 9.73,
|
| 2804 |
+
"eval_loss": 0.4488721191883087,
|
| 2805 |
+
"eval_runtime": 1.4041,
|
| 2806 |
+
"eval_samples_per_second": 712.211,
|
| 2807 |
+
"eval_steps_per_second": 22.791,
|
| 2808 |
+
"step": 100000
|
| 2809 |
+
},
|
| 2810 |
+
{
|
| 2811 |
+
"epoch": 9.77,
|
| 2812 |
+
"learning_rate": 2.2673964034401876e-06,
|
| 2813 |
+
"loss": 0.1038,
|
| 2814 |
+
"step": 100500
|
| 2815 |
+
},
|
| 2816 |
+
{
|
| 2817 |
+
"epoch": 9.77,
|
| 2818 |
+
"eval_loss": 0.44900763034820557,
|
| 2819 |
+
"eval_runtime": 1.4001,
|
| 2820 |
+
"eval_samples_per_second": 714.232,
|
| 2821 |
+
"eval_steps_per_second": 22.855,
|
| 2822 |
+
"step": 100500
|
| 2823 |
+
},
|
| 2824 |
+
{
|
| 2825 |
+
"epoch": 9.82,
|
| 2826 |
+
"learning_rate": 1.7787333854573888e-06,
|
| 2827 |
+
"loss": 0.1057,
|
| 2828 |
+
"step": 101000
|
| 2829 |
+
},
|
| 2830 |
+
{
|
| 2831 |
+
"epoch": 9.82,
|
| 2832 |
+
"eval_loss": 0.44878125190734863,
|
| 2833 |
+
"eval_runtime": 1.409,
|
| 2834 |
+
"eval_samples_per_second": 709.704,
|
| 2835 |
+
"eval_steps_per_second": 22.711,
|
| 2836 |
+
"step": 101000
|
| 2837 |
+
},
|
| 2838 |
+
{
|
| 2839 |
+
"epoch": 9.87,
|
| 2840 |
+
"learning_rate": 1.2900703674745897e-06,
|
| 2841 |
+
"loss": 0.1035,
|
| 2842 |
+
"step": 101500
|
| 2843 |
+
},
|
| 2844 |
+
{
|
| 2845 |
+
"epoch": 9.87,
|
| 2846 |
+
"eval_loss": 0.448639452457428,
|
| 2847 |
+
"eval_runtime": 1.4105,
|
| 2848 |
+
"eval_samples_per_second": 708.955,
|
| 2849 |
+
"eval_steps_per_second": 22.687,
|
| 2850 |
+
"step": 101500
|
| 2851 |
+
},
|
| 2852 |
+
{
|
| 2853 |
+
"epoch": 9.92,
|
| 2854 |
+
"learning_rate": 8.014073494917906e-07,
|
| 2855 |
+
"loss": 0.1058,
|
| 2856 |
+
"step": 102000
|
| 2857 |
+
},
|
| 2858 |
+
{
|
| 2859 |
+
"epoch": 9.92,
|
| 2860 |
+
"eval_loss": 0.4486231207847595,
|
| 2861 |
+
"eval_runtime": 1.3971,
|
| 2862 |
+
"eval_samples_per_second": 715.758,
|
| 2863 |
+
"eval_steps_per_second": 22.904,
|
| 2864 |
+
"step": 102000
|
| 2865 |
+
},
|
| 2866 |
+
{
|
| 2867 |
+
"epoch": 9.97,
|
| 2868 |
+
"learning_rate": 3.1274433150899144e-07,
|
| 2869 |
+
"loss": 0.1013,
|
| 2870 |
+
"step": 102500
|
| 2871 |
+
},
|
| 2872 |
+
{
|
| 2873 |
+
"epoch": 9.97,
|
| 2874 |
+
"eval_loss": 0.44872137904167175,
|
| 2875 |
+
"eval_runtime": 1.4115,
|
| 2876 |
+
"eval_samples_per_second": 708.454,
|
| 2877 |
+
"eval_steps_per_second": 22.671,
|
| 2878 |
+
"step": 102500
|
| 2879 |
+
}
|
| 2880 |
+
],
|
| 2881 |
+
"max_steps": 102820,
|
| 2882 |
+
"num_train_epochs": 10,
|
| 2883 |
+
"total_flos": 6.16302255744e+16,
|
| 2884 |
+
"trial_name": null,
|
| 2885 |
+
"trial_params": null
|
| 2886 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ee0fd7451e0c1843ce8da3602a36d98e13d48b4279052738b5dc4572db0664d4
|
| 3 |
+
size 3119
|