Initial upload of multiple checkpoints
Browse filesThis view is limited to 50 files because it contains too many changes. See raw diff
- .gitattributes +1 -0
- cc100-monolingual-crawled-data.csv +3 -0
- cc100-monolingual-crawled-data/cache-507101ac94bf52fe.arrow +3 -0
- cc100-monolingual-crawled-data/data-00000-of-00001.arrow +3 -0
- cc100-monolingual-crawled-data/dataset_info.json +63 -0
- cc100-monolingual-crawled-data/state.json +13 -0
- checkpoint-100000/config.json +26 -0
- checkpoint-100000/merges.txt +0 -0
- checkpoint-100000/model.safetensors +3 -0
- checkpoint-100000/optimizer.pt +3 -0
- checkpoint-100000/rng_state.pth +3 -0
- checkpoint-100000/scaler.pt +3 -0
- checkpoint-100000/scheduler.pt +3 -0
- checkpoint-100000/special_tokens_map.json +51 -0
- checkpoint-100000/tokenizer.json +0 -0
- checkpoint-100000/tokenizer_config.json +58 -0
- checkpoint-100000/trainer_state.json +1434 -0
- checkpoint-100000/training_args.bin +3 -0
- checkpoint-100000/vocab.json +0 -0
- checkpoint-120000/config.json +26 -0
- checkpoint-120000/merges.txt +0 -0
- checkpoint-120000/model.safetensors +3 -0
- checkpoint-120000/optimizer.pt +3 -0
- checkpoint-120000/rng_state.pth +3 -0
- checkpoint-120000/scaler.pt +3 -0
- checkpoint-120000/scheduler.pt +3 -0
- checkpoint-120000/special_tokens_map.json +51 -0
- checkpoint-120000/tokenizer.json +0 -0
- checkpoint-120000/tokenizer_config.json +58 -0
- checkpoint-120000/trainer_state.json +1714 -0
- checkpoint-120000/training_args.bin +3 -0
- checkpoint-120000/vocab.json +0 -0
- checkpoint-140000/config.json +26 -0
- checkpoint-140000/merges.txt +0 -0
- checkpoint-140000/model.safetensors +3 -0
- checkpoint-140000/optimizer.pt +3 -0
- checkpoint-140000/rng_state.pth +3 -0
- checkpoint-140000/scaler.pt +3 -0
- checkpoint-140000/scheduler.pt +3 -0
- checkpoint-140000/special_tokens_map.json +51 -0
- checkpoint-140000/tokenizer.json +0 -0
- checkpoint-140000/tokenizer_config.json +58 -0
- checkpoint-140000/trainer_state.json +1994 -0
- checkpoint-140000/training_args.bin +3 -0
- checkpoint-140000/vocab.json +0 -0
- checkpoint-160000/config.json +26 -0
- checkpoint-160000/merges.txt +0 -0
- checkpoint-160000/model.safetensors +3 -0
- checkpoint-160000/optimizer.pt +3 -0
- checkpoint-160000/rng_state.pth +3 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
cc100-monolingual-crawled-data.csv filter=lfs diff=lfs merge=lfs -text
|
cc100-monolingual-crawled-data.csv
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b0a95bd558af79db10bdb03f444c69fd133fa2bd01cab0e0b43e06a157312810
|
| 3 |
+
size 6104768433
|
cc100-monolingual-crawled-data/cache-507101ac94bf52fe.arrow
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:058a2df81c3a913fc165df756422e1eac15cf9f77e5a884a3b1e8b826508d708
|
| 3 |
+
size 407504
|
cc100-monolingual-crawled-data/data-00000-of-00001.arrow
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1add4a48977015deba328a45ea560ef4edc817fb59e8771f7570e0ed767f6b8b
|
| 3 |
+
size 7208080
|
cc100-monolingual-crawled-data/dataset_info.json
ADDED
|
@@ -0,0 +1,63 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"builder_name": "csv",
|
| 3 |
+
"citation": "",
|
| 4 |
+
"config_name": "default",
|
| 5 |
+
"dataset_name": "csv",
|
| 6 |
+
"dataset_size": 6378299418,
|
| 7 |
+
"description": "",
|
| 8 |
+
"download_checksums": {
|
| 9 |
+
"/l/users/daniil.orel/cc_kaz/cc100-monolingual-crawled-data.csv": {
|
| 10 |
+
"num_bytes": 6104768433,
|
| 11 |
+
"checksum": null
|
| 12 |
+
}
|
| 13 |
+
},
|
| 14 |
+
"download_size": 6104768433,
|
| 15 |
+
"features": {
|
| 16 |
+
"input_ids": {
|
| 17 |
+
"feature": {
|
| 18 |
+
"dtype": "int32",
|
| 19 |
+
"_type": "Value"
|
| 20 |
+
},
|
| 21 |
+
"_type": "Sequence"
|
| 22 |
+
},
|
| 23 |
+
"attention_mask": {
|
| 24 |
+
"feature": {
|
| 25 |
+
"dtype": "int8",
|
| 26 |
+
"_type": "Value"
|
| 27 |
+
},
|
| 28 |
+
"_type": "Sequence"
|
| 29 |
+
}
|
| 30 |
+
},
|
| 31 |
+
"homepage": "",
|
| 32 |
+
"license": "",
|
| 33 |
+
"size_in_bytes": 12483067851,
|
| 34 |
+
"splits": {
|
| 35 |
+
"train": {
|
| 36 |
+
"name": "train",
|
| 37 |
+
"num_bytes": 6378299418,
|
| 38 |
+
"num_examples": 19635580,
|
| 39 |
+
"shard_lengths": [
|
| 40 |
+
1610000,
|
| 41 |
+
1590000,
|
| 42 |
+
1560000,
|
| 43 |
+
1570000,
|
| 44 |
+
1560000,
|
| 45 |
+
1540000,
|
| 46 |
+
1540000,
|
| 47 |
+
1560000,
|
| 48 |
+
1520000,
|
| 49 |
+
1490000,
|
| 50 |
+
1510000,
|
| 51 |
+
1510000,
|
| 52 |
+
1075580
|
| 53 |
+
],
|
| 54 |
+
"dataset_name": "csv"
|
| 55 |
+
}
|
| 56 |
+
},
|
| 57 |
+
"version": {
|
| 58 |
+
"version_str": "0.0.0",
|
| 59 |
+
"major": 0,
|
| 60 |
+
"minor": 0,
|
| 61 |
+
"patch": 0
|
| 62 |
+
}
|
| 63 |
+
}
|
cc100-monolingual-crawled-data/state.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_data_files": [
|
| 3 |
+
{
|
| 4 |
+
"filename": "data-00000-of-00001.arrow"
|
| 5 |
+
}
|
| 6 |
+
],
|
| 7 |
+
"_fingerprint": "376818ebcb54d9a6",
|
| 8 |
+
"_format_columns": null,
|
| 9 |
+
"_format_kwargs": {},
|
| 10 |
+
"_format_type": null,
|
| 11 |
+
"_output_all_columns": false,
|
| 12 |
+
"_split": null
|
| 13 |
+
}
|
checkpoint-100000/config.json
ADDED
|
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"RobertaForMaskedLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_probs_dropout_prob": 0.1,
|
| 6 |
+
"bos_token_id": 0,
|
| 7 |
+
"classifier_dropout": null,
|
| 8 |
+
"eos_token_id": 2,
|
| 9 |
+
"hidden_act": "gelu",
|
| 10 |
+
"hidden_dropout_prob": 0.1,
|
| 11 |
+
"hidden_size": 768,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 3072,
|
| 14 |
+
"layer_norm_eps": 1e-12,
|
| 15 |
+
"max_position_embeddings": 514,
|
| 16 |
+
"model_type": "roberta",
|
| 17 |
+
"num_attention_heads": 12,
|
| 18 |
+
"num_hidden_layers": 6,
|
| 19 |
+
"pad_token_id": 1,
|
| 20 |
+
"position_embedding_type": "absolute",
|
| 21 |
+
"torch_dtype": "float32",
|
| 22 |
+
"transformers_version": "4.50.3",
|
| 23 |
+
"type_vocab_size": 1,
|
| 24 |
+
"use_cache": true,
|
| 25 |
+
"vocab_size": 52000
|
| 26 |
+
}
|
checkpoint-100000/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-100000/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4aa7a0cb4401de20adbaa2cfd3619c066aaea77fdadc62f773542702f95b1cb3
|
| 3 |
+
size 334030264
|
checkpoint-100000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:67ffff3fe3a34e8c2df6399ee2ceb3a474e7236dafe934051e5f0eb790e01f51
|
| 3 |
+
size 668124218
|
checkpoint-100000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b6bd9645b85acc9ee10413c41061eba3e66c0c53263150e6445469e04a5f3e7b
|
| 3 |
+
size 14244
|
checkpoint-100000/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7b2107c9ccf5e4ff51c754873fbc46e91719244bde8287739031fe890bdf9610
|
| 3 |
+
size 988
|
checkpoint-100000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7dff6fc1476d5cd4ea4cb1bbbd16bc05aca1e149df5d70699b79c60ce406b283
|
| 3 |
+
size 1064
|
checkpoint-100000/special_tokens_map.json
ADDED
|
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": true,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"cls_token": {
|
| 10 |
+
"content": "<s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": true,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"eos_token": {
|
| 17 |
+
"content": "</s>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": true,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"mask_token": {
|
| 24 |
+
"content": "<mask>",
|
| 25 |
+
"lstrip": true,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"pad_token": {
|
| 31 |
+
"content": "<pad>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": true,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
},
|
| 37 |
+
"sep_token": {
|
| 38 |
+
"content": "</s>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": true,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false
|
| 43 |
+
},
|
| 44 |
+
"unk_token": {
|
| 45 |
+
"content": "<unk>",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": true,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false
|
| 50 |
+
}
|
| 51 |
+
}
|
checkpoint-100000/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-100000/tokenizer_config.json
ADDED
|
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"0": {
|
| 5 |
+
"content": "<s>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": true,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"1": {
|
| 13 |
+
"content": "<pad>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": true,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"2": {
|
| 21 |
+
"content": "</s>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": true,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": true
|
| 27 |
+
},
|
| 28 |
+
"3": {
|
| 29 |
+
"content": "<unk>",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": true,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false,
|
| 34 |
+
"special": true
|
| 35 |
+
},
|
| 36 |
+
"4": {
|
| 37 |
+
"content": "<mask>",
|
| 38 |
+
"lstrip": true,
|
| 39 |
+
"normalized": false,
|
| 40 |
+
"rstrip": false,
|
| 41 |
+
"single_word": false,
|
| 42 |
+
"special": true
|
| 43 |
+
}
|
| 44 |
+
},
|
| 45 |
+
"bos_token": "<s>",
|
| 46 |
+
"clean_up_tokenization_spaces": false,
|
| 47 |
+
"cls_token": "<s>",
|
| 48 |
+
"eos_token": "</s>",
|
| 49 |
+
"errors": "replace",
|
| 50 |
+
"extra_special_tokens": {},
|
| 51 |
+
"mask_token": "<mask>",
|
| 52 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 53 |
+
"pad_token": "<pad>",
|
| 54 |
+
"sep_token": "</s>",
|
| 55 |
+
"tokenizer_class": "RobertaTokenizer",
|
| 56 |
+
"trim_offsets": true,
|
| 57 |
+
"unk_token": "<unk>"
|
| 58 |
+
}
|
checkpoint-100000/trainer_state.json
ADDED
|
@@ -0,0 +1,1434 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 63.97952655150352,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 100000,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.3198976327575176,
|
| 14 |
+
"grad_norm": 4.1601386070251465,
|
| 15 |
+
"learning_rate": 5e-06,
|
| 16 |
+
"loss": 10.3279,
|
| 17 |
+
"step": 500
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.6397952655150352,
|
| 21 |
+
"grad_norm": 4.366061687469482,
|
| 22 |
+
"learning_rate": 1e-05,
|
| 23 |
+
"loss": 9.3834,
|
| 24 |
+
"step": 1000
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.9596928982725528,
|
| 28 |
+
"grad_norm": 4.784337043762207,
|
| 29 |
+
"learning_rate": 1.5e-05,
|
| 30 |
+
"loss": 8.8888,
|
| 31 |
+
"step": 1500
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 1.2795905310300704,
|
| 35 |
+
"grad_norm": 3.9968652725219727,
|
| 36 |
+
"learning_rate": 2e-05,
|
| 37 |
+
"loss": 8.6568,
|
| 38 |
+
"step": 2000
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 1.599488163787588,
|
| 42 |
+
"grad_norm": 4.402552127838135,
|
| 43 |
+
"learning_rate": 2.5e-05,
|
| 44 |
+
"loss": 8.5473,
|
| 45 |
+
"step": 2500
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 1.9193857965451055,
|
| 49 |
+
"grad_norm": 4.639041423797607,
|
| 50 |
+
"learning_rate": 3e-05,
|
| 51 |
+
"loss": 8.4044,
|
| 52 |
+
"step": 3000
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 2.239283429302623,
|
| 56 |
+
"grad_norm": 5.651747226715088,
|
| 57 |
+
"learning_rate": 3.5e-05,
|
| 58 |
+
"loss": 8.2868,
|
| 59 |
+
"step": 3500
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 2.5591810620601407,
|
| 63 |
+
"grad_norm": 4.6999359130859375,
|
| 64 |
+
"learning_rate": 4e-05,
|
| 65 |
+
"loss": 8.1766,
|
| 66 |
+
"step": 4000
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 2.8790786948176583,
|
| 70 |
+
"grad_norm": 4.838181495666504,
|
| 71 |
+
"learning_rate": 4.499e-05,
|
| 72 |
+
"loss": 8.1118,
|
| 73 |
+
"step": 4500
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 3.198976327575176,
|
| 77 |
+
"grad_norm": 4.238831996917725,
|
| 78 |
+
"learning_rate": 4.999e-05,
|
| 79 |
+
"loss": 8.0038,
|
| 80 |
+
"step": 5000
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 3.5188739603326935,
|
| 84 |
+
"grad_norm": 4.455530643463135,
|
| 85 |
+
"learning_rate": 5.499000000000001e-05,
|
| 86 |
+
"loss": 7.9014,
|
| 87 |
+
"step": 5500
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 3.838771593090211,
|
| 91 |
+
"grad_norm": 5.811736583709717,
|
| 92 |
+
"learning_rate": 5.999e-05,
|
| 93 |
+
"loss": 7.8352,
|
| 94 |
+
"step": 6000
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 4.158669225847729,
|
| 98 |
+
"grad_norm": 4.998301982879639,
|
| 99 |
+
"learning_rate": 6.498e-05,
|
| 100 |
+
"loss": 7.7613,
|
| 101 |
+
"step": 6500
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 4.478566858605246,
|
| 105 |
+
"grad_norm": 5.011510848999023,
|
| 106 |
+
"learning_rate": 6.998e-05,
|
| 107 |
+
"loss": 7.6554,
|
| 108 |
+
"step": 7000
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 4.798464491362764,
|
| 112 |
+
"grad_norm": 4.750300884246826,
|
| 113 |
+
"learning_rate": 7.498e-05,
|
| 114 |
+
"loss": 7.6109,
|
| 115 |
+
"step": 7500
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 5.1183621241202815,
|
| 119 |
+
"grad_norm": 6.24017858505249,
|
| 120 |
+
"learning_rate": 7.998e-05,
|
| 121 |
+
"loss": 7.5186,
|
| 122 |
+
"step": 8000
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 5.438259756877799,
|
| 126 |
+
"grad_norm": 6.061458587646484,
|
| 127 |
+
"learning_rate": 8.497000000000001e-05,
|
| 128 |
+
"loss": 7.3966,
|
| 129 |
+
"step": 8500
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 5.758157389635317,
|
| 133 |
+
"grad_norm": 7.151447772979736,
|
| 134 |
+
"learning_rate": 8.997000000000001e-05,
|
| 135 |
+
"loss": 7.2877,
|
| 136 |
+
"step": 9000
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 6.078055022392834,
|
| 140 |
+
"grad_norm": 7.578985214233398,
|
| 141 |
+
"learning_rate": 9.497000000000001e-05,
|
| 142 |
+
"loss": 7.1542,
|
| 143 |
+
"step": 9500
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 6.397952655150352,
|
| 147 |
+
"grad_norm": 5.948920726776123,
|
| 148 |
+
"learning_rate": 9.997e-05,
|
| 149 |
+
"loss": 7.0008,
|
| 150 |
+
"step": 10000
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 6.717850287907869,
|
| 154 |
+
"grad_norm": 8.036959648132324,
|
| 155 |
+
"learning_rate": 9.982896551724137e-05,
|
| 156 |
+
"loss": 6.8966,
|
| 157 |
+
"step": 10500
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 7.037747920665387,
|
| 161 |
+
"grad_norm": 7.160433292388916,
|
| 162 |
+
"learning_rate": 9.965655172413794e-05,
|
| 163 |
+
"loss": 6.7509,
|
| 164 |
+
"step": 11000
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 7.357645553422905,
|
| 168 |
+
"grad_norm": 5.934999465942383,
|
| 169 |
+
"learning_rate": 9.948413793103449e-05,
|
| 170 |
+
"loss": 6.5833,
|
| 171 |
+
"step": 11500
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 7.677543186180422,
|
| 175 |
+
"grad_norm": 7.745622634887695,
|
| 176 |
+
"learning_rate": 9.931172413793104e-05,
|
| 177 |
+
"loss": 6.4975,
|
| 178 |
+
"step": 12000
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 7.99744081893794,
|
| 182 |
+
"grad_norm": 7.0418477058410645,
|
| 183 |
+
"learning_rate": 9.91393103448276e-05,
|
| 184 |
+
"loss": 6.4261,
|
| 185 |
+
"step": 12500
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 8.317338451695457,
|
| 189 |
+
"grad_norm": 6.101259708404541,
|
| 190 |
+
"learning_rate": 9.896689655172414e-05,
|
| 191 |
+
"loss": 6.2092,
|
| 192 |
+
"step": 13000
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 8.637236084452976,
|
| 196 |
+
"grad_norm": 7.289799213409424,
|
| 197 |
+
"learning_rate": 9.87944827586207e-05,
|
| 198 |
+
"loss": 6.1436,
|
| 199 |
+
"step": 13500
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 8.957133717210493,
|
| 203 |
+
"grad_norm": 8.126811027526855,
|
| 204 |
+
"learning_rate": 9.862206896551725e-05,
|
| 205 |
+
"loss": 6.0456,
|
| 206 |
+
"step": 14000
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 9.277031349968011,
|
| 210 |
+
"grad_norm": 8.221816062927246,
|
| 211 |
+
"learning_rate": 9.845000000000001e-05,
|
| 212 |
+
"loss": 5.9141,
|
| 213 |
+
"step": 14500
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 9.596928982725528,
|
| 217 |
+
"grad_norm": 7.361550331115723,
|
| 218 |
+
"learning_rate": 9.827793103448277e-05,
|
| 219 |
+
"loss": 5.8326,
|
| 220 |
+
"step": 15000
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 9.916826615483046,
|
| 224 |
+
"grad_norm": 7.1737775802612305,
|
| 225 |
+
"learning_rate": 9.810551724137932e-05,
|
| 226 |
+
"loss": 5.7974,
|
| 227 |
+
"step": 15500
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 10.236724248240563,
|
| 231 |
+
"grad_norm": 9.80185604095459,
|
| 232 |
+
"learning_rate": 9.793310344827586e-05,
|
| 233 |
+
"loss": 5.6282,
|
| 234 |
+
"step": 16000
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 10.556621880998081,
|
| 238 |
+
"grad_norm": 7.2062153816223145,
|
| 239 |
+
"learning_rate": 9.776068965517242e-05,
|
| 240 |
+
"loss": 5.5619,
|
| 241 |
+
"step": 16500
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 10.876519513755598,
|
| 245 |
+
"grad_norm": 10.801878929138184,
|
| 246 |
+
"learning_rate": 9.758827586206896e-05,
|
| 247 |
+
"loss": 5.5155,
|
| 248 |
+
"step": 17000
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 11.196417146513117,
|
| 252 |
+
"grad_norm": 8.48509693145752,
|
| 253 |
+
"learning_rate": 9.741586206896553e-05,
|
| 254 |
+
"loss": 5.4259,
|
| 255 |
+
"step": 17500
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 11.516314779270633,
|
| 259 |
+
"grad_norm": 8.47572135925293,
|
| 260 |
+
"learning_rate": 9.724344827586207e-05,
|
| 261 |
+
"loss": 5.3205,
|
| 262 |
+
"step": 18000
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 11.836212412028152,
|
| 266 |
+
"grad_norm": 6.122796535491943,
|
| 267 |
+
"learning_rate": 9.707103448275863e-05,
|
| 268 |
+
"loss": 5.3025,
|
| 269 |
+
"step": 18500
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 12.156110044785668,
|
| 273 |
+
"grad_norm": 8.210710525512695,
|
| 274 |
+
"learning_rate": 9.689896551724139e-05,
|
| 275 |
+
"loss": 5.2264,
|
| 276 |
+
"step": 19000
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 12.476007677543187,
|
| 280 |
+
"grad_norm": 7.857537746429443,
|
| 281 |
+
"learning_rate": 9.672655172413794e-05,
|
| 282 |
+
"loss": 5.1395,
|
| 283 |
+
"step": 19500
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 12.795905310300704,
|
| 287 |
+
"grad_norm": 7.743075370788574,
|
| 288 |
+
"learning_rate": 9.655413793103448e-05,
|
| 289 |
+
"loss": 5.1109,
|
| 290 |
+
"step": 20000
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 13.115802943058222,
|
| 294 |
+
"grad_norm": 10.574569702148438,
|
| 295 |
+
"learning_rate": 9.638172413793104e-05,
|
| 296 |
+
"loss": 5.0794,
|
| 297 |
+
"step": 20500
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 13.435700575815739,
|
| 301 |
+
"grad_norm": 8.313858985900879,
|
| 302 |
+
"learning_rate": 9.620931034482758e-05,
|
| 303 |
+
"loss": 4.921,
|
| 304 |
+
"step": 21000
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 13.755598208573257,
|
| 308 |
+
"grad_norm": 9.096057891845703,
|
| 309 |
+
"learning_rate": 9.603689655172414e-05,
|
| 310 |
+
"loss": 4.96,
|
| 311 |
+
"step": 21500
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 14.075495841330774,
|
| 315 |
+
"grad_norm": 8.402993202209473,
|
| 316 |
+
"learning_rate": 9.58644827586207e-05,
|
| 317 |
+
"loss": 4.9062,
|
| 318 |
+
"step": 22000
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 14.395393474088293,
|
| 322 |
+
"grad_norm": 8.110074996948242,
|
| 323 |
+
"learning_rate": 9.569206896551725e-05,
|
| 324 |
+
"loss": 4.8026,
|
| 325 |
+
"step": 22500
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 14.71529110684581,
|
| 329 |
+
"grad_norm": 7.908292293548584,
|
| 330 |
+
"learning_rate": 9.552000000000001e-05,
|
| 331 |
+
"loss": 4.82,
|
| 332 |
+
"step": 23000
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 15.035188739603328,
|
| 336 |
+
"grad_norm": 7.991878986358643,
|
| 337 |
+
"learning_rate": 9.534758620689655e-05,
|
| 338 |
+
"loss": 4.7397,
|
| 339 |
+
"step": 23500
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 15.355086372360844,
|
| 343 |
+
"grad_norm": 8.696029663085938,
|
| 344 |
+
"learning_rate": 9.517551724137932e-05,
|
| 345 |
+
"loss": 4.6656,
|
| 346 |
+
"step": 24000
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 15.674984005118363,
|
| 350 |
+
"grad_norm": 9.421612739562988,
|
| 351 |
+
"learning_rate": 9.500310344827586e-05,
|
| 352 |
+
"loss": 4.6412,
|
| 353 |
+
"step": 24500
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 15.99488163787588,
|
| 357 |
+
"grad_norm": 9.747482299804688,
|
| 358 |
+
"learning_rate": 9.483068965517242e-05,
|
| 359 |
+
"loss": 4.6048,
|
| 360 |
+
"step": 25000
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 16.314779270633398,
|
| 364 |
+
"grad_norm": 10.389492988586426,
|
| 365 |
+
"learning_rate": 9.465827586206897e-05,
|
| 366 |
+
"loss": 4.481,
|
| 367 |
+
"step": 25500
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 16.634676903390915,
|
| 371 |
+
"grad_norm": 8.661949157714844,
|
| 372 |
+
"learning_rate": 9.448586206896553e-05,
|
| 373 |
+
"loss": 4.4923,
|
| 374 |
+
"step": 26000
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 16.95457453614843,
|
| 378 |
+
"grad_norm": 12.681297302246094,
|
| 379 |
+
"learning_rate": 9.431344827586207e-05,
|
| 380 |
+
"loss": 4.4816,
|
| 381 |
+
"step": 26500
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 17.27447216890595,
|
| 385 |
+
"grad_norm": 8.993134498596191,
|
| 386 |
+
"learning_rate": 9.414103448275863e-05,
|
| 387 |
+
"loss": 4.3512,
|
| 388 |
+
"step": 27000
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 17.59436980166347,
|
| 392 |
+
"grad_norm": 10.020146369934082,
|
| 393 |
+
"learning_rate": 9.396862068965517e-05,
|
| 394 |
+
"loss": 4.3447,
|
| 395 |
+
"step": 27500
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 17.914267434420985,
|
| 399 |
+
"grad_norm": 9.514701843261719,
|
| 400 |
+
"learning_rate": 9.379655172413794e-05,
|
| 401 |
+
"loss": 4.3376,
|
| 402 |
+
"step": 28000
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 18.234165067178502,
|
| 406 |
+
"grad_norm": 10.324498176574707,
|
| 407 |
+
"learning_rate": 9.362413793103448e-05,
|
| 408 |
+
"loss": 4.2612,
|
| 409 |
+
"step": 28500
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 18.554062699936022,
|
| 413 |
+
"grad_norm": 10.682856559753418,
|
| 414 |
+
"learning_rate": 9.345172413793104e-05,
|
| 415 |
+
"loss": 4.226,
|
| 416 |
+
"step": 29000
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 18.87396033269354,
|
| 420 |
+
"grad_norm": 7.883260726928711,
|
| 421 |
+
"learning_rate": 9.327931034482758e-05,
|
| 422 |
+
"loss": 4.19,
|
| 423 |
+
"step": 29500
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 19.193857965451055,
|
| 427 |
+
"grad_norm": 12.470623016357422,
|
| 428 |
+
"learning_rate": 9.310724137931035e-05,
|
| 429 |
+
"loss": 4.1881,
|
| 430 |
+
"step": 30000
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 19.513755598208572,
|
| 434 |
+
"grad_norm": 9.932331085205078,
|
| 435 |
+
"learning_rate": 9.29348275862069e-05,
|
| 436 |
+
"loss": 4.0853,
|
| 437 |
+
"step": 30500
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 19.833653230966092,
|
| 441 |
+
"grad_norm": 8.153782844543457,
|
| 442 |
+
"learning_rate": 9.276241379310345e-05,
|
| 443 |
+
"loss": 4.1087,
|
| 444 |
+
"step": 31000
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 20.15355086372361,
|
| 448 |
+
"grad_norm": 8.214093208312988,
|
| 449 |
+
"learning_rate": 9.258999999999999e-05,
|
| 450 |
+
"loss": 4.0751,
|
| 451 |
+
"step": 31500
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 20.473448496481126,
|
| 455 |
+
"grad_norm": 11.927350044250488,
|
| 456 |
+
"learning_rate": 9.241758620689656e-05,
|
| 457 |
+
"loss": 3.9686,
|
| 458 |
+
"step": 32000
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 20.793346129238643,
|
| 462 |
+
"grad_norm": 9.67835807800293,
|
| 463 |
+
"learning_rate": 9.224551724137932e-05,
|
| 464 |
+
"loss": 3.9745,
|
| 465 |
+
"step": 32500
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 21.113243761996163,
|
| 469 |
+
"grad_norm": 9.911735534667969,
|
| 470 |
+
"learning_rate": 9.207310344827586e-05,
|
| 471 |
+
"loss": 3.9308,
|
| 472 |
+
"step": 33000
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 21.43314139475368,
|
| 476 |
+
"grad_norm": 9.05053424835205,
|
| 477 |
+
"learning_rate": 9.190068965517242e-05,
|
| 478 |
+
"loss": 3.8718,
|
| 479 |
+
"step": 33500
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 21.753039027511196,
|
| 483 |
+
"grad_norm": 9.588044166564941,
|
| 484 |
+
"learning_rate": 9.172827586206897e-05,
|
| 485 |
+
"loss": 3.8425,
|
| 486 |
+
"step": 34000
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 22.072936660268713,
|
| 490 |
+
"grad_norm": 8.788230895996094,
|
| 491 |
+
"learning_rate": 9.155620689655173e-05,
|
| 492 |
+
"loss": 3.8617,
|
| 493 |
+
"step": 34500
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 22.392834293026233,
|
| 497 |
+
"grad_norm": 9.435895919799805,
|
| 498 |
+
"learning_rate": 9.138379310344827e-05,
|
| 499 |
+
"loss": 3.7524,
|
| 500 |
+
"step": 35000
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 22.71273192578375,
|
| 504 |
+
"grad_norm": 9.870182037353516,
|
| 505 |
+
"learning_rate": 9.121137931034483e-05,
|
| 506 |
+
"loss": 3.7916,
|
| 507 |
+
"step": 35500
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 23.032629558541267,
|
| 511 |
+
"grad_norm": 9.612881660461426,
|
| 512 |
+
"learning_rate": 9.103896551724139e-05,
|
| 513 |
+
"loss": 3.8011,
|
| 514 |
+
"step": 36000
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 23.352527191298783,
|
| 518 |
+
"grad_norm": 9.643827438354492,
|
| 519 |
+
"learning_rate": 9.086689655172414e-05,
|
| 520 |
+
"loss": 3.6478,
|
| 521 |
+
"step": 36500
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 23.672424824056304,
|
| 525 |
+
"grad_norm": 14.105424880981445,
|
| 526 |
+
"learning_rate": 9.069448275862069e-05,
|
| 527 |
+
"loss": 3.6671,
|
| 528 |
+
"step": 37000
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 23.99232245681382,
|
| 532 |
+
"grad_norm": 10.427962303161621,
|
| 533 |
+
"learning_rate": 9.052206896551724e-05,
|
| 534 |
+
"loss": 3.6809,
|
| 535 |
+
"step": 37500
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 24.312220089571337,
|
| 539 |
+
"grad_norm": 11.505946159362793,
|
| 540 |
+
"learning_rate": 9.03496551724138e-05,
|
| 541 |
+
"loss": 3.553,
|
| 542 |
+
"step": 38000
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 24.632117722328854,
|
| 546 |
+
"grad_norm": 10.393635749816895,
|
| 547 |
+
"learning_rate": 9.017724137931035e-05,
|
| 548 |
+
"loss": 3.5408,
|
| 549 |
+
"step": 38500
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 24.952015355086374,
|
| 553 |
+
"grad_norm": 9.023842811584473,
|
| 554 |
+
"learning_rate": 9.00051724137931e-05,
|
| 555 |
+
"loss": 3.5915,
|
| 556 |
+
"step": 39000
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 25.27191298784389,
|
| 560 |
+
"grad_norm": 10.69048023223877,
|
| 561 |
+
"learning_rate": 8.983275862068967e-05,
|
| 562 |
+
"loss": 3.4896,
|
| 563 |
+
"step": 39500
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 25.591810620601407,
|
| 567 |
+
"grad_norm": 10.803936958312988,
|
| 568 |
+
"learning_rate": 8.966034482758621e-05,
|
| 569 |
+
"loss": 3.4854,
|
| 570 |
+
"step": 40000
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 25.911708253358924,
|
| 574 |
+
"grad_norm": 10.489801406860352,
|
| 575 |
+
"learning_rate": 8.948793103448276e-05,
|
| 576 |
+
"loss": 3.4871,
|
| 577 |
+
"step": 40500
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 26.231605886116444,
|
| 581 |
+
"grad_norm": 10.558309555053711,
|
| 582 |
+
"learning_rate": 8.931586206896552e-05,
|
| 583 |
+
"loss": 3.4186,
|
| 584 |
+
"step": 41000
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 26.55150351887396,
|
| 588 |
+
"grad_norm": 12.186748504638672,
|
| 589 |
+
"learning_rate": 8.914344827586208e-05,
|
| 590 |
+
"loss": 3.4027,
|
| 591 |
+
"step": 41500
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 26.871401151631478,
|
| 595 |
+
"grad_norm": 9.8623046875,
|
| 596 |
+
"learning_rate": 8.897103448275862e-05,
|
| 597 |
+
"loss": 3.4191,
|
| 598 |
+
"step": 42000
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 27.191298784388994,
|
| 602 |
+
"grad_norm": 11.407792091369629,
|
| 603 |
+
"learning_rate": 8.879862068965518e-05,
|
| 604 |
+
"loss": 3.341,
|
| 605 |
+
"step": 42500
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 27.511196417146515,
|
| 609 |
+
"grad_norm": 13.37617301940918,
|
| 610 |
+
"learning_rate": 8.862655172413794e-05,
|
| 611 |
+
"loss": 3.3137,
|
| 612 |
+
"step": 43000
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 27.83109404990403,
|
| 616 |
+
"grad_norm": 10.30826187133789,
|
| 617 |
+
"learning_rate": 8.845413793103449e-05,
|
| 618 |
+
"loss": 3.3036,
|
| 619 |
+
"step": 43500
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 28.150991682661548,
|
| 623 |
+
"grad_norm": 12.024778366088867,
|
| 624 |
+
"learning_rate": 8.828172413793105e-05,
|
| 625 |
+
"loss": 3.2678,
|
| 626 |
+
"step": 44000
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 28.470889315419065,
|
| 630 |
+
"grad_norm": 9.730340957641602,
|
| 631 |
+
"learning_rate": 8.810931034482759e-05,
|
| 632 |
+
"loss": 3.1949,
|
| 633 |
+
"step": 44500
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 28.790786948176585,
|
| 637 |
+
"grad_norm": 9.700602531433105,
|
| 638 |
+
"learning_rate": 8.793689655172414e-05,
|
| 639 |
+
"loss": 3.2541,
|
| 640 |
+
"step": 45000
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 29.1106845809341,
|
| 644 |
+
"grad_norm": 12.359143257141113,
|
| 645 |
+
"learning_rate": 8.77648275862069e-05,
|
| 646 |
+
"loss": 3.2456,
|
| 647 |
+
"step": 45500
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 29.43058221369162,
|
| 651 |
+
"grad_norm": 11.989018440246582,
|
| 652 |
+
"learning_rate": 8.759241379310346e-05,
|
| 653 |
+
"loss": 3.1154,
|
| 654 |
+
"step": 46000
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 29.750479846449135,
|
| 658 |
+
"grad_norm": 10.904190063476562,
|
| 659 |
+
"learning_rate": 8.742e-05,
|
| 660 |
+
"loss": 3.175,
|
| 661 |
+
"step": 46500
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 30.070377479206655,
|
| 665 |
+
"grad_norm": 11.253949165344238,
|
| 666 |
+
"learning_rate": 8.724758620689656e-05,
|
| 667 |
+
"loss": 3.1478,
|
| 668 |
+
"step": 47000
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 30.390275111964172,
|
| 672 |
+
"grad_norm": 12.229791641235352,
|
| 673 |
+
"learning_rate": 8.707517241379311e-05,
|
| 674 |
+
"loss": 3.0632,
|
| 675 |
+
"step": 47500
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 30.71017274472169,
|
| 679 |
+
"grad_norm": 9.516524314880371,
|
| 680 |
+
"learning_rate": 8.690275862068967e-05,
|
| 681 |
+
"loss": 3.0843,
|
| 682 |
+
"step": 48000
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 31.030070377479205,
|
| 686 |
+
"grad_norm": 13.730731010437012,
|
| 687 |
+
"learning_rate": 8.673034482758621e-05,
|
| 688 |
+
"loss": 3.098,
|
| 689 |
+
"step": 48500
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 31.349968010236726,
|
| 693 |
+
"grad_norm": 9.73539924621582,
|
| 694 |
+
"learning_rate": 8.655827586206897e-05,
|
| 695 |
+
"loss": 2.9611,
|
| 696 |
+
"step": 49000
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 31.669865642994242,
|
| 700 |
+
"grad_norm": 12.066815376281738,
|
| 701 |
+
"learning_rate": 8.638586206896552e-05,
|
| 702 |
+
"loss": 2.9943,
|
| 703 |
+
"step": 49500
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 31.98976327575176,
|
| 707 |
+
"grad_norm": 11.028585433959961,
|
| 708 |
+
"learning_rate": 8.621344827586208e-05,
|
| 709 |
+
"loss": 3.0424,
|
| 710 |
+
"step": 50000
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 32.30966090850928,
|
| 714 |
+
"grad_norm": 11.2380952835083,
|
| 715 |
+
"learning_rate": 8.604103448275862e-05,
|
| 716 |
+
"loss": 2.9023,
|
| 717 |
+
"step": 50500
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 32.629558541266796,
|
| 721 |
+
"grad_norm": 9.345772743225098,
|
| 722 |
+
"learning_rate": 8.586862068965518e-05,
|
| 723 |
+
"loss": 2.9586,
|
| 724 |
+
"step": 51000
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 32.94945617402431,
|
| 728 |
+
"grad_norm": 10.239849090576172,
|
| 729 |
+
"learning_rate": 8.569655172413793e-05,
|
| 730 |
+
"loss": 2.9461,
|
| 731 |
+
"step": 51500
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 33.26935380678183,
|
| 735 |
+
"grad_norm": 11.058523178100586,
|
| 736 |
+
"learning_rate": 8.552413793103449e-05,
|
| 737 |
+
"loss": 2.8453,
|
| 738 |
+
"step": 52000
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 33.589251439539346,
|
| 742 |
+
"grad_norm": 12.131317138671875,
|
| 743 |
+
"learning_rate": 8.535172413793105e-05,
|
| 744 |
+
"loss": 2.8603,
|
| 745 |
+
"step": 52500
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 33.90914907229686,
|
| 749 |
+
"grad_norm": 10.392476081848145,
|
| 750 |
+
"learning_rate": 8.517931034482759e-05,
|
| 751 |
+
"loss": 2.8817,
|
| 752 |
+
"step": 53000
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 34.22904670505438,
|
| 756 |
+
"grad_norm": 10.749021530151367,
|
| 757 |
+
"learning_rate": 8.500724137931036e-05,
|
| 758 |
+
"loss": 2.8073,
|
| 759 |
+
"step": 53500
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 34.5489443378119,
|
| 763 |
+
"grad_norm": 12.33171558380127,
|
| 764 |
+
"learning_rate": 8.48348275862069e-05,
|
| 765 |
+
"loss": 2.7793,
|
| 766 |
+
"step": 54000
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 34.86884197056942,
|
| 770 |
+
"grad_norm": 12.961758613586426,
|
| 771 |
+
"learning_rate": 8.466241379310346e-05,
|
| 772 |
+
"loss": 2.8066,
|
| 773 |
+
"step": 54500
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 35.18873960332694,
|
| 777 |
+
"grad_norm": 13.320075035095215,
|
| 778 |
+
"learning_rate": 8.449e-05,
|
| 779 |
+
"loss": 2.7459,
|
| 780 |
+
"step": 55000
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 35.50863723608445,
|
| 784 |
+
"grad_norm": 14.416489601135254,
|
| 785 |
+
"learning_rate": 8.431758620689655e-05,
|
| 786 |
+
"loss": 2.7321,
|
| 787 |
+
"step": 55500
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 35.82853486884197,
|
| 791 |
+
"grad_norm": 11.203073501586914,
|
| 792 |
+
"learning_rate": 8.414551724137931e-05,
|
| 793 |
+
"loss": 2.7486,
|
| 794 |
+
"step": 56000
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 36.14843250159949,
|
| 798 |
+
"grad_norm": 10.463476181030273,
|
| 799 |
+
"learning_rate": 8.397310344827587e-05,
|
| 800 |
+
"loss": 2.7086,
|
| 801 |
+
"step": 56500
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 36.468330134357004,
|
| 805 |
+
"grad_norm": 11.375761985778809,
|
| 806 |
+
"learning_rate": 8.380068965517241e-05,
|
| 807 |
+
"loss": 2.6387,
|
| 808 |
+
"step": 57000
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 36.78822776711452,
|
| 812 |
+
"grad_norm": 11.649105072021484,
|
| 813 |
+
"learning_rate": 8.362827586206897e-05,
|
| 814 |
+
"loss": 2.6746,
|
| 815 |
+
"step": 57500
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 37.108125399872044,
|
| 819 |
+
"grad_norm": 12.708244323730469,
|
| 820 |
+
"learning_rate": 8.345586206896552e-05,
|
| 821 |
+
"loss": 2.6454,
|
| 822 |
+
"step": 58000
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 37.42802303262956,
|
| 826 |
+
"grad_norm": 12.876201629638672,
|
| 827 |
+
"learning_rate": 8.328344827586208e-05,
|
| 828 |
+
"loss": 2.5798,
|
| 829 |
+
"step": 58500
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 37.74792066538708,
|
| 833 |
+
"grad_norm": 11.92346477508545,
|
| 834 |
+
"learning_rate": 8.311103448275862e-05,
|
| 835 |
+
"loss": 2.6589,
|
| 836 |
+
"step": 59000
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 38.067818298144594,
|
| 840 |
+
"grad_norm": 10.742238998413086,
|
| 841 |
+
"learning_rate": 8.293896551724138e-05,
|
| 842 |
+
"loss": 2.5868,
|
| 843 |
+
"step": 59500
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 38.38771593090211,
|
| 847 |
+
"grad_norm": 11.399048805236816,
|
| 848 |
+
"learning_rate": 8.276655172413793e-05,
|
| 849 |
+
"loss": 2.5124,
|
| 850 |
+
"step": 60000
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 38.70761356365963,
|
| 854 |
+
"grad_norm": 13.563875198364258,
|
| 855 |
+
"learning_rate": 8.259413793103449e-05,
|
| 856 |
+
"loss": 2.576,
|
| 857 |
+
"step": 60500
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 39.027511196417144,
|
| 861 |
+
"grad_norm": 11.297135353088379,
|
| 862 |
+
"learning_rate": 8.242172413793103e-05,
|
| 863 |
+
"loss": 2.5671,
|
| 864 |
+
"step": 61000
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 39.34740882917466,
|
| 868 |
+
"grad_norm": 11.336121559143066,
|
| 869 |
+
"learning_rate": 8.22496551724138e-05,
|
| 870 |
+
"loss": 2.4445,
|
| 871 |
+
"step": 61500
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 39.667306461932185,
|
| 875 |
+
"grad_norm": 9.477692604064941,
|
| 876 |
+
"learning_rate": 8.207724137931035e-05,
|
| 877 |
+
"loss": 2.4981,
|
| 878 |
+
"step": 62000
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 39.9872040946897,
|
| 882 |
+
"grad_norm": 11.597848892211914,
|
| 883 |
+
"learning_rate": 8.19048275862069e-05,
|
| 884 |
+
"loss": 2.5382,
|
| 885 |
+
"step": 62500
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 40.30710172744722,
|
| 889 |
+
"grad_norm": 14.910037994384766,
|
| 890 |
+
"learning_rate": 8.173241379310346e-05,
|
| 891 |
+
"loss": 2.4158,
|
| 892 |
+
"step": 63000
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 40.626999360204735,
|
| 896 |
+
"grad_norm": 11.870673179626465,
|
| 897 |
+
"learning_rate": 8.156e-05,
|
| 898 |
+
"loss": 2.4395,
|
| 899 |
+
"step": 63500
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 40.94689699296225,
|
| 903 |
+
"grad_norm": 15.279576301574707,
|
| 904 |
+
"learning_rate": 8.138758620689655e-05,
|
| 905 |
+
"loss": 2.4653,
|
| 906 |
+
"step": 64000
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 41.26679462571977,
|
| 910 |
+
"grad_norm": 11.710406303405762,
|
| 911 |
+
"learning_rate": 8.121551724137931e-05,
|
| 912 |
+
"loss": 2.3567,
|
| 913 |
+
"step": 64500
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 41.586692258477285,
|
| 917 |
+
"grad_norm": 10.663411140441895,
|
| 918 |
+
"learning_rate": 8.104310344827587e-05,
|
| 919 |
+
"loss": 2.3655,
|
| 920 |
+
"step": 65000
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 41.9065898912348,
|
| 924 |
+
"grad_norm": 13.946629524230957,
|
| 925 |
+
"learning_rate": 8.087068965517241e-05,
|
| 926 |
+
"loss": 2.4336,
|
| 927 |
+
"step": 65500
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 42.226487523992326,
|
| 931 |
+
"grad_norm": 13.782262802124023,
|
| 932 |
+
"learning_rate": 8.069827586206898e-05,
|
| 933 |
+
"loss": 2.3351,
|
| 934 |
+
"step": 66000
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 42.54638515674984,
|
| 938 |
+
"grad_norm": 11.177961349487305,
|
| 939 |
+
"learning_rate": 8.052586206896552e-05,
|
| 940 |
+
"loss": 2.359,
|
| 941 |
+
"step": 66500
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 42.86628278950736,
|
| 945 |
+
"grad_norm": 15.120301246643066,
|
| 946 |
+
"learning_rate": 8.035344827586208e-05,
|
| 947 |
+
"loss": 2.355,
|
| 948 |
+
"step": 67000
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 43.186180422264876,
|
| 952 |
+
"grad_norm": 10.805267333984375,
|
| 953 |
+
"learning_rate": 8.018103448275862e-05,
|
| 954 |
+
"loss": 2.2905,
|
| 955 |
+
"step": 67500
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 43.50607805502239,
|
| 959 |
+
"grad_norm": 11.777176856994629,
|
| 960 |
+
"learning_rate": 8.000862068965517e-05,
|
| 961 |
+
"loss": 2.2906,
|
| 962 |
+
"step": 68000
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 43.82597568777991,
|
| 966 |
+
"grad_norm": 15.457807540893555,
|
| 967 |
+
"learning_rate": 7.983689655172414e-05,
|
| 968 |
+
"loss": 2.3269,
|
| 969 |
+
"step": 68500
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 44.145873320537426,
|
| 973 |
+
"grad_norm": 11.639357566833496,
|
| 974 |
+
"learning_rate": 7.966448275862069e-05,
|
| 975 |
+
"loss": 2.2371,
|
| 976 |
+
"step": 69000
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 44.46577095329494,
|
| 980 |
+
"grad_norm": 11.710591316223145,
|
| 981 |
+
"learning_rate": 7.949206896551725e-05,
|
| 982 |
+
"loss": 2.2248,
|
| 983 |
+
"step": 69500
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 44.785668586052466,
|
| 987 |
+
"grad_norm": 12.675103187561035,
|
| 988 |
+
"learning_rate": 7.93196551724138e-05,
|
| 989 |
+
"loss": 2.2586,
|
| 990 |
+
"step": 70000
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 45.10556621880998,
|
| 994 |
+
"grad_norm": 12.752120971679688,
|
| 995 |
+
"learning_rate": 7.914724137931034e-05,
|
| 996 |
+
"loss": 2.2489,
|
| 997 |
+
"step": 70500
|
| 998 |
+
},
|
| 999 |
+
{
|
| 1000 |
+
"epoch": 45.4254638515675,
|
| 1001 |
+
"grad_norm": 11.379339218139648,
|
| 1002 |
+
"learning_rate": 7.89751724137931e-05,
|
| 1003 |
+
"loss": 2.1774,
|
| 1004 |
+
"step": 71000
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 45.74536148432502,
|
| 1008 |
+
"grad_norm": 12.76633358001709,
|
| 1009 |
+
"learning_rate": 7.880275862068966e-05,
|
| 1010 |
+
"loss": 2.2007,
|
| 1011 |
+
"step": 71500
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 46.06525911708253,
|
| 1015 |
+
"grad_norm": 11.421367645263672,
|
| 1016 |
+
"learning_rate": 7.863034482758621e-05,
|
| 1017 |
+
"loss": 2.2262,
|
| 1018 |
+
"step": 72000
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"epoch": 46.38515674984005,
|
| 1022 |
+
"grad_norm": 14.81748104095459,
|
| 1023 |
+
"learning_rate": 7.845793103448277e-05,
|
| 1024 |
+
"loss": 2.101,
|
| 1025 |
+
"step": 72500
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 46.70505438259757,
|
| 1029 |
+
"grad_norm": 12.902971267700195,
|
| 1030 |
+
"learning_rate": 7.828551724137931e-05,
|
| 1031 |
+
"loss": 2.1568,
|
| 1032 |
+
"step": 73000
|
| 1033 |
+
},
|
| 1034 |
+
{
|
| 1035 |
+
"epoch": 47.02495201535508,
|
| 1036 |
+
"grad_norm": 10.685113906860352,
|
| 1037 |
+
"learning_rate": 7.811310344827587e-05,
|
| 1038 |
+
"loss": 2.1655,
|
| 1039 |
+
"step": 73500
|
| 1040 |
+
},
|
| 1041 |
+
{
|
| 1042 |
+
"epoch": 47.34484964811261,
|
| 1043 |
+
"grad_norm": 15.892518043518066,
|
| 1044 |
+
"learning_rate": 7.794068965517242e-05,
|
| 1045 |
+
"loss": 2.0551,
|
| 1046 |
+
"step": 74000
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 47.664747280870124,
|
| 1050 |
+
"grad_norm": 13.730358123779297,
|
| 1051 |
+
"learning_rate": 7.776862068965518e-05,
|
| 1052 |
+
"loss": 2.1053,
|
| 1053 |
+
"step": 74500
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 47.98464491362764,
|
| 1057 |
+
"grad_norm": 13.635787963867188,
|
| 1058 |
+
"learning_rate": 7.759620689655172e-05,
|
| 1059 |
+
"loss": 2.1408,
|
| 1060 |
+
"step": 75000
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"epoch": 48.30454254638516,
|
| 1064 |
+
"grad_norm": 12.861611366271973,
|
| 1065 |
+
"learning_rate": 7.742379310344828e-05,
|
| 1066 |
+
"loss": 2.0104,
|
| 1067 |
+
"step": 75500
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"epoch": 48.624440179142674,
|
| 1071 |
+
"grad_norm": 11.84931468963623,
|
| 1072 |
+
"learning_rate": 7.725137931034483e-05,
|
| 1073 |
+
"loss": 2.0555,
|
| 1074 |
+
"step": 76000
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 48.94433781190019,
|
| 1078 |
+
"grad_norm": 15.812765121459961,
|
| 1079 |
+
"learning_rate": 7.70793103448276e-05,
|
| 1080 |
+
"loss": 2.1087,
|
| 1081 |
+
"step": 76500
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 49.26423544465771,
|
| 1085 |
+
"grad_norm": 14.233431816101074,
|
| 1086 |
+
"learning_rate": 7.690689655172414e-05,
|
| 1087 |
+
"loss": 1.9998,
|
| 1088 |
+
"step": 77000
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 49.584133077415224,
|
| 1092 |
+
"grad_norm": 14.329803466796875,
|
| 1093 |
+
"learning_rate": 7.673448275862069e-05,
|
| 1094 |
+
"loss": 2.0189,
|
| 1095 |
+
"step": 77500
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 49.90403071017275,
|
| 1099 |
+
"grad_norm": 11.00400161743164,
|
| 1100 |
+
"learning_rate": 7.656206896551725e-05,
|
| 1101 |
+
"loss": 2.059,
|
| 1102 |
+
"step": 78000
|
| 1103 |
+
},
|
| 1104 |
+
{
|
| 1105 |
+
"epoch": 50.223928342930265,
|
| 1106 |
+
"grad_norm": 13.582133293151855,
|
| 1107 |
+
"learning_rate": 7.63896551724138e-05,
|
| 1108 |
+
"loss": 1.9753,
|
| 1109 |
+
"step": 78500
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 50.54382597568778,
|
| 1113 |
+
"grad_norm": 12.560907363891602,
|
| 1114 |
+
"learning_rate": 7.621724137931034e-05,
|
| 1115 |
+
"loss": 1.9759,
|
| 1116 |
+
"step": 79000
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 50.8637236084453,
|
| 1120 |
+
"grad_norm": 12.169915199279785,
|
| 1121 |
+
"learning_rate": 7.60451724137931e-05,
|
| 1122 |
+
"loss": 1.9944,
|
| 1123 |
+
"step": 79500
|
| 1124 |
+
},
|
| 1125 |
+
{
|
| 1126 |
+
"epoch": 51.183621241202815,
|
| 1127 |
+
"grad_norm": 13.5604248046875,
|
| 1128 |
+
"learning_rate": 7.587275862068966e-05,
|
| 1129 |
+
"loss": 1.9323,
|
| 1130 |
+
"step": 80000
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 51.50351887396033,
|
| 1134 |
+
"grad_norm": 15.892741203308105,
|
| 1135 |
+
"learning_rate": 7.570034482758621e-05,
|
| 1136 |
+
"loss": 1.9095,
|
| 1137 |
+
"step": 80500
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 51.82341650671785,
|
| 1141 |
+
"grad_norm": 13.435209274291992,
|
| 1142 |
+
"learning_rate": 7.552793103448276e-05,
|
| 1143 |
+
"loss": 1.9508,
|
| 1144 |
+
"step": 81000
|
| 1145 |
+
},
|
| 1146 |
+
{
|
| 1147 |
+
"epoch": 52.143314139475365,
|
| 1148 |
+
"grad_norm": 11.180010795593262,
|
| 1149 |
+
"learning_rate": 7.535586206896551e-05,
|
| 1150 |
+
"loss": 1.9216,
|
| 1151 |
+
"step": 81500
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 52.46321177223289,
|
| 1155 |
+
"grad_norm": 12.792661666870117,
|
| 1156 |
+
"learning_rate": 7.518344827586207e-05,
|
| 1157 |
+
"loss": 1.8817,
|
| 1158 |
+
"step": 82000
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"epoch": 52.783109404990405,
|
| 1162 |
+
"grad_norm": 11.785886764526367,
|
| 1163 |
+
"learning_rate": 7.501103448275863e-05,
|
| 1164 |
+
"loss": 1.9121,
|
| 1165 |
+
"step": 82500
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"epoch": 53.10300703774792,
|
| 1169 |
+
"grad_norm": 10.568120002746582,
|
| 1170 |
+
"learning_rate": 7.483862068965518e-05,
|
| 1171 |
+
"loss": 1.8885,
|
| 1172 |
+
"step": 83000
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 53.42290467050544,
|
| 1176 |
+
"grad_norm": 14.641459465026855,
|
| 1177 |
+
"learning_rate": 7.466620689655172e-05,
|
| 1178 |
+
"loss": 1.8357,
|
| 1179 |
+
"step": 83500
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 53.742802303262955,
|
| 1183 |
+
"grad_norm": 13.5363187789917,
|
| 1184 |
+
"learning_rate": 7.449379310344828e-05,
|
| 1185 |
+
"loss": 1.8515,
|
| 1186 |
+
"step": 84000
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 54.06269993602047,
|
| 1190 |
+
"grad_norm": 12.997908592224121,
|
| 1191 |
+
"learning_rate": 7.432172413793104e-05,
|
| 1192 |
+
"loss": 1.8681,
|
| 1193 |
+
"step": 84500
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 54.38259756877799,
|
| 1197 |
+
"grad_norm": 12.53503131866455,
|
| 1198 |
+
"learning_rate": 7.414931034482759e-05,
|
| 1199 |
+
"loss": 1.7785,
|
| 1200 |
+
"step": 85000
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 54.702495201535505,
|
| 1204 |
+
"grad_norm": 11.986194610595703,
|
| 1205 |
+
"learning_rate": 7.397689655172413e-05,
|
| 1206 |
+
"loss": 1.8507,
|
| 1207 |
+
"step": 85500
|
| 1208 |
+
},
|
| 1209 |
+
{
|
| 1210 |
+
"epoch": 55.02239283429303,
|
| 1211 |
+
"grad_norm": 12.089723587036133,
|
| 1212 |
+
"learning_rate": 7.380448275862069e-05,
|
| 1213 |
+
"loss": 1.8537,
|
| 1214 |
+
"step": 86000
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 55.342290467050546,
|
| 1218 |
+
"grad_norm": 13.552453994750977,
|
| 1219 |
+
"learning_rate": 7.363206896551725e-05,
|
| 1220 |
+
"loss": 1.7622,
|
| 1221 |
+
"step": 86500
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 55.66218809980806,
|
| 1225 |
+
"grad_norm": 12.03878116607666,
|
| 1226 |
+
"learning_rate": 7.346e-05,
|
| 1227 |
+
"loss": 1.8076,
|
| 1228 |
+
"step": 87000
|
| 1229 |
+
},
|
| 1230 |
+
{
|
| 1231 |
+
"epoch": 55.98208573256558,
|
| 1232 |
+
"grad_norm": 11.187782287597656,
|
| 1233 |
+
"learning_rate": 7.328758620689655e-05,
|
| 1234 |
+
"loss": 1.8241,
|
| 1235 |
+
"step": 87500
|
| 1236 |
+
},
|
| 1237 |
+
{
|
| 1238 |
+
"epoch": 56.301983365323096,
|
| 1239 |
+
"grad_norm": 14.924737930297852,
|
| 1240 |
+
"learning_rate": 7.311517241379312e-05,
|
| 1241 |
+
"loss": 1.7077,
|
| 1242 |
+
"step": 88000
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"epoch": 56.62188099808061,
|
| 1246 |
+
"grad_norm": 12.302467346191406,
|
| 1247 |
+
"learning_rate": 7.294275862068966e-05,
|
| 1248 |
+
"loss": 1.74,
|
| 1249 |
+
"step": 88500
|
| 1250 |
+
},
|
| 1251 |
+
{
|
| 1252 |
+
"epoch": 56.94177863083813,
|
| 1253 |
+
"grad_norm": 10.834394454956055,
|
| 1254 |
+
"learning_rate": 7.277034482758621e-05,
|
| 1255 |
+
"loss": 1.7827,
|
| 1256 |
+
"step": 89000
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 57.261676263595646,
|
| 1260 |
+
"grad_norm": 14.356012344360352,
|
| 1261 |
+
"learning_rate": 7.259793103448276e-05,
|
| 1262 |
+
"loss": 1.7082,
|
| 1263 |
+
"step": 89500
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 57.58157389635317,
|
| 1267 |
+
"grad_norm": 14.632678031921387,
|
| 1268 |
+
"learning_rate": 7.242551724137931e-05,
|
| 1269 |
+
"loss": 1.7045,
|
| 1270 |
+
"step": 90000
|
| 1271 |
+
},
|
| 1272 |
+
{
|
| 1273 |
+
"epoch": 57.90147152911069,
|
| 1274 |
+
"grad_norm": 13.501043319702148,
|
| 1275 |
+
"learning_rate": 7.225344827586207e-05,
|
| 1276 |
+
"loss": 1.7522,
|
| 1277 |
+
"step": 90500
|
| 1278 |
+
},
|
| 1279 |
+
{
|
| 1280 |
+
"epoch": 58.2213691618682,
|
| 1281 |
+
"grad_norm": 18.839614868164062,
|
| 1282 |
+
"learning_rate": 7.208103448275862e-05,
|
| 1283 |
+
"loss": 1.6801,
|
| 1284 |
+
"step": 91000
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 58.54126679462572,
|
| 1288 |
+
"grad_norm": 13.41618824005127,
|
| 1289 |
+
"learning_rate": 7.190862068965517e-05,
|
| 1290 |
+
"loss": 1.7005,
|
| 1291 |
+
"step": 91500
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 58.86116442738324,
|
| 1295 |
+
"grad_norm": 12.56169605255127,
|
| 1296 |
+
"learning_rate": 7.173620689655172e-05,
|
| 1297 |
+
"loss": 1.7018,
|
| 1298 |
+
"step": 92000
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 59.18106206014075,
|
| 1302 |
+
"grad_norm": 13.447467803955078,
|
| 1303 |
+
"learning_rate": 7.15641379310345e-05,
|
| 1304 |
+
"loss": 1.6691,
|
| 1305 |
+
"step": 92500
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 59.50095969289827,
|
| 1309 |
+
"grad_norm": 12.452493667602539,
|
| 1310 |
+
"learning_rate": 7.139172413793104e-05,
|
| 1311 |
+
"loss": 1.651,
|
| 1312 |
+
"step": 93000
|
| 1313 |
+
},
|
| 1314 |
+
{
|
| 1315 |
+
"epoch": 59.82085732565579,
|
| 1316 |
+
"grad_norm": 10.552214622497559,
|
| 1317 |
+
"learning_rate": 7.121931034482759e-05,
|
| 1318 |
+
"loss": 1.6916,
|
| 1319 |
+
"step": 93500
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 60.14075495841331,
|
| 1323 |
+
"grad_norm": 11.099422454833984,
|
| 1324 |
+
"learning_rate": 7.104689655172413e-05,
|
| 1325 |
+
"loss": 1.6716,
|
| 1326 |
+
"step": 94000
|
| 1327 |
+
},
|
| 1328 |
+
{
|
| 1329 |
+
"epoch": 60.46065259117083,
|
| 1330 |
+
"grad_norm": 13.663276672363281,
|
| 1331 |
+
"learning_rate": 7.08744827586207e-05,
|
| 1332 |
+
"loss": 1.6105,
|
| 1333 |
+
"step": 94500
|
| 1334 |
+
},
|
| 1335 |
+
{
|
| 1336 |
+
"epoch": 60.780550223928344,
|
| 1337 |
+
"grad_norm": 11.783934593200684,
|
| 1338 |
+
"learning_rate": 7.070206896551725e-05,
|
| 1339 |
+
"loss": 1.6399,
|
| 1340 |
+
"step": 95000
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"epoch": 61.10044785668586,
|
| 1344 |
+
"grad_norm": 12.881340026855469,
|
| 1345 |
+
"learning_rate": 7.053e-05,
|
| 1346 |
+
"loss": 1.6058,
|
| 1347 |
+
"step": 95500
|
| 1348 |
+
},
|
| 1349 |
+
{
|
| 1350 |
+
"epoch": 61.42034548944338,
|
| 1351 |
+
"grad_norm": 12.405476570129395,
|
| 1352 |
+
"learning_rate": 7.035758620689656e-05,
|
| 1353 |
+
"loss": 1.5703,
|
| 1354 |
+
"step": 96000
|
| 1355 |
+
},
|
| 1356 |
+
{
|
| 1357 |
+
"epoch": 61.740243122200894,
|
| 1358 |
+
"grad_norm": 11.660452842712402,
|
| 1359 |
+
"learning_rate": 7.018517241379311e-05,
|
| 1360 |
+
"loss": 1.6002,
|
| 1361 |
+
"step": 96500
|
| 1362 |
+
},
|
| 1363 |
+
{
|
| 1364 |
+
"epoch": 62.06014075495841,
|
| 1365 |
+
"grad_norm": 11.69723892211914,
|
| 1366 |
+
"learning_rate": 7.001275862068966e-05,
|
| 1367 |
+
"loss": 1.6186,
|
| 1368 |
+
"step": 97000
|
| 1369 |
+
},
|
| 1370 |
+
{
|
| 1371 |
+
"epoch": 62.38003838771593,
|
| 1372 |
+
"grad_norm": 16.210947036743164,
|
| 1373 |
+
"learning_rate": 6.984034482758621e-05,
|
| 1374 |
+
"loss": 1.5663,
|
| 1375 |
+
"step": 97500
|
| 1376 |
+
},
|
| 1377 |
+
{
|
| 1378 |
+
"epoch": 62.69993602047345,
|
| 1379 |
+
"grad_norm": 11.853803634643555,
|
| 1380 |
+
"learning_rate": 6.966827586206897e-05,
|
| 1381 |
+
"loss": 1.5744,
|
| 1382 |
+
"step": 98000
|
| 1383 |
+
},
|
| 1384 |
+
{
|
| 1385 |
+
"epoch": 63.01983365323097,
|
| 1386 |
+
"grad_norm": 10.565818786621094,
|
| 1387 |
+
"learning_rate": 6.949586206896553e-05,
|
| 1388 |
+
"loss": 1.5829,
|
| 1389 |
+
"step": 98500
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 63.339731285988485,
|
| 1393 |
+
"grad_norm": 11.621013641357422,
|
| 1394 |
+
"learning_rate": 6.932344827586207e-05,
|
| 1395 |
+
"loss": 1.5213,
|
| 1396 |
+
"step": 99000
|
| 1397 |
+
},
|
| 1398 |
+
{
|
| 1399 |
+
"epoch": 63.659628918746,
|
| 1400 |
+
"grad_norm": 10.182308197021484,
|
| 1401 |
+
"learning_rate": 6.915103448275862e-05,
|
| 1402 |
+
"loss": 1.5291,
|
| 1403 |
+
"step": 99500
|
| 1404 |
+
},
|
| 1405 |
+
{
|
| 1406 |
+
"epoch": 63.97952655150352,
|
| 1407 |
+
"grad_norm": 14.434243202209473,
|
| 1408 |
+
"learning_rate": 6.897862068965517e-05,
|
| 1409 |
+
"loss": 1.5612,
|
| 1410 |
+
"step": 100000
|
| 1411 |
+
}
|
| 1412 |
+
],
|
| 1413 |
+
"logging_steps": 500,
|
| 1414 |
+
"max_steps": 300000,
|
| 1415 |
+
"num_input_tokens_seen": 0,
|
| 1416 |
+
"num_train_epochs": 192,
|
| 1417 |
+
"save_steps": 20000,
|
| 1418 |
+
"stateful_callbacks": {
|
| 1419 |
+
"TrainerControl": {
|
| 1420 |
+
"args": {
|
| 1421 |
+
"should_epoch_stop": false,
|
| 1422 |
+
"should_evaluate": false,
|
| 1423 |
+
"should_log": false,
|
| 1424 |
+
"should_save": true,
|
| 1425 |
+
"should_training_stop": false
|
| 1426 |
+
},
|
| 1427 |
+
"attributes": {}
|
| 1428 |
+
}
|
| 1429 |
+
},
|
| 1430 |
+
"total_flos": 1.1230494563853926e+17,
|
| 1431 |
+
"train_batch_size": 32,
|
| 1432 |
+
"trial_name": null,
|
| 1433 |
+
"trial_params": null
|
| 1434 |
+
}
|
checkpoint-100000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6fad2530f3d27917fbdcc941e3023a8fce21992040aa6f8afe98d384d87efa35
|
| 3 |
+
size 5368
|
checkpoint-100000/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-120000/config.json
ADDED
|
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"RobertaForMaskedLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_probs_dropout_prob": 0.1,
|
| 6 |
+
"bos_token_id": 0,
|
| 7 |
+
"classifier_dropout": null,
|
| 8 |
+
"eos_token_id": 2,
|
| 9 |
+
"hidden_act": "gelu",
|
| 10 |
+
"hidden_dropout_prob": 0.1,
|
| 11 |
+
"hidden_size": 768,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 3072,
|
| 14 |
+
"layer_norm_eps": 1e-12,
|
| 15 |
+
"max_position_embeddings": 514,
|
| 16 |
+
"model_type": "roberta",
|
| 17 |
+
"num_attention_heads": 12,
|
| 18 |
+
"num_hidden_layers": 6,
|
| 19 |
+
"pad_token_id": 1,
|
| 20 |
+
"position_embedding_type": "absolute",
|
| 21 |
+
"torch_dtype": "float32",
|
| 22 |
+
"transformers_version": "4.50.3",
|
| 23 |
+
"type_vocab_size": 1,
|
| 24 |
+
"use_cache": true,
|
| 25 |
+
"vocab_size": 52000
|
| 26 |
+
}
|
checkpoint-120000/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-120000/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:435127ee2359afb6047afa6ea7b4e169def74842be56f56d582183f928b9ef24
|
| 3 |
+
size 334030264
|
checkpoint-120000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d30be37f6fd9fdf30ed89ed165149c2773233f954f3910ff09a8f5e5258e95bf
|
| 3 |
+
size 668124218
|
checkpoint-120000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c19cac2a8c745e1f0fcb2d7a076997b50e753141b3f389e79ed9ad3e5f9de31e
|
| 3 |
+
size 14244
|
checkpoint-120000/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b1dad5fe9d8b3e4a89e14315d73d680a551f504512fec5a6790559d7f81a2a3f
|
| 3 |
+
size 988
|
checkpoint-120000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ef863ff4deaa1d16147993672cbfacc7a439c6689087446dd74d9f72159fdf9e
|
| 3 |
+
size 1064
|
checkpoint-120000/special_tokens_map.json
ADDED
|
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": true,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"cls_token": {
|
| 10 |
+
"content": "<s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": true,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"eos_token": {
|
| 17 |
+
"content": "</s>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": true,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"mask_token": {
|
| 24 |
+
"content": "<mask>",
|
| 25 |
+
"lstrip": true,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"pad_token": {
|
| 31 |
+
"content": "<pad>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": true,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
},
|
| 37 |
+
"sep_token": {
|
| 38 |
+
"content": "</s>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": true,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false
|
| 43 |
+
},
|
| 44 |
+
"unk_token": {
|
| 45 |
+
"content": "<unk>",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": true,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false
|
| 50 |
+
}
|
| 51 |
+
}
|
checkpoint-120000/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-120000/tokenizer_config.json
ADDED
|
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"0": {
|
| 5 |
+
"content": "<s>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": true,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"1": {
|
| 13 |
+
"content": "<pad>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": true,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"2": {
|
| 21 |
+
"content": "</s>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": true,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": true
|
| 27 |
+
},
|
| 28 |
+
"3": {
|
| 29 |
+
"content": "<unk>",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": true,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false,
|
| 34 |
+
"special": true
|
| 35 |
+
},
|
| 36 |
+
"4": {
|
| 37 |
+
"content": "<mask>",
|
| 38 |
+
"lstrip": true,
|
| 39 |
+
"normalized": false,
|
| 40 |
+
"rstrip": false,
|
| 41 |
+
"single_word": false,
|
| 42 |
+
"special": true
|
| 43 |
+
}
|
| 44 |
+
},
|
| 45 |
+
"bos_token": "<s>",
|
| 46 |
+
"clean_up_tokenization_spaces": false,
|
| 47 |
+
"cls_token": "<s>",
|
| 48 |
+
"eos_token": "</s>",
|
| 49 |
+
"errors": "replace",
|
| 50 |
+
"extra_special_tokens": {},
|
| 51 |
+
"mask_token": "<mask>",
|
| 52 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 53 |
+
"pad_token": "<pad>",
|
| 54 |
+
"sep_token": "</s>",
|
| 55 |
+
"tokenizer_class": "RobertaTokenizer",
|
| 56 |
+
"trim_offsets": true,
|
| 57 |
+
"unk_token": "<unk>"
|
| 58 |
+
}
|
checkpoint-120000/trainer_state.json
ADDED
|
@@ -0,0 +1,1714 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 76.77543186180422,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 120000,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.3198976327575176,
|
| 14 |
+
"grad_norm": 4.1601386070251465,
|
| 15 |
+
"learning_rate": 5e-06,
|
| 16 |
+
"loss": 10.3279,
|
| 17 |
+
"step": 500
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.6397952655150352,
|
| 21 |
+
"grad_norm": 4.366061687469482,
|
| 22 |
+
"learning_rate": 1e-05,
|
| 23 |
+
"loss": 9.3834,
|
| 24 |
+
"step": 1000
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.9596928982725528,
|
| 28 |
+
"grad_norm": 4.784337043762207,
|
| 29 |
+
"learning_rate": 1.5e-05,
|
| 30 |
+
"loss": 8.8888,
|
| 31 |
+
"step": 1500
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 1.2795905310300704,
|
| 35 |
+
"grad_norm": 3.9968652725219727,
|
| 36 |
+
"learning_rate": 2e-05,
|
| 37 |
+
"loss": 8.6568,
|
| 38 |
+
"step": 2000
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 1.599488163787588,
|
| 42 |
+
"grad_norm": 4.402552127838135,
|
| 43 |
+
"learning_rate": 2.5e-05,
|
| 44 |
+
"loss": 8.5473,
|
| 45 |
+
"step": 2500
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 1.9193857965451055,
|
| 49 |
+
"grad_norm": 4.639041423797607,
|
| 50 |
+
"learning_rate": 3e-05,
|
| 51 |
+
"loss": 8.4044,
|
| 52 |
+
"step": 3000
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 2.239283429302623,
|
| 56 |
+
"grad_norm": 5.651747226715088,
|
| 57 |
+
"learning_rate": 3.5e-05,
|
| 58 |
+
"loss": 8.2868,
|
| 59 |
+
"step": 3500
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 2.5591810620601407,
|
| 63 |
+
"grad_norm": 4.6999359130859375,
|
| 64 |
+
"learning_rate": 4e-05,
|
| 65 |
+
"loss": 8.1766,
|
| 66 |
+
"step": 4000
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 2.8790786948176583,
|
| 70 |
+
"grad_norm": 4.838181495666504,
|
| 71 |
+
"learning_rate": 4.499e-05,
|
| 72 |
+
"loss": 8.1118,
|
| 73 |
+
"step": 4500
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 3.198976327575176,
|
| 77 |
+
"grad_norm": 4.238831996917725,
|
| 78 |
+
"learning_rate": 4.999e-05,
|
| 79 |
+
"loss": 8.0038,
|
| 80 |
+
"step": 5000
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 3.5188739603326935,
|
| 84 |
+
"grad_norm": 4.455530643463135,
|
| 85 |
+
"learning_rate": 5.499000000000001e-05,
|
| 86 |
+
"loss": 7.9014,
|
| 87 |
+
"step": 5500
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 3.838771593090211,
|
| 91 |
+
"grad_norm": 5.811736583709717,
|
| 92 |
+
"learning_rate": 5.999e-05,
|
| 93 |
+
"loss": 7.8352,
|
| 94 |
+
"step": 6000
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 4.158669225847729,
|
| 98 |
+
"grad_norm": 4.998301982879639,
|
| 99 |
+
"learning_rate": 6.498e-05,
|
| 100 |
+
"loss": 7.7613,
|
| 101 |
+
"step": 6500
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 4.478566858605246,
|
| 105 |
+
"grad_norm": 5.011510848999023,
|
| 106 |
+
"learning_rate": 6.998e-05,
|
| 107 |
+
"loss": 7.6554,
|
| 108 |
+
"step": 7000
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 4.798464491362764,
|
| 112 |
+
"grad_norm": 4.750300884246826,
|
| 113 |
+
"learning_rate": 7.498e-05,
|
| 114 |
+
"loss": 7.6109,
|
| 115 |
+
"step": 7500
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 5.1183621241202815,
|
| 119 |
+
"grad_norm": 6.24017858505249,
|
| 120 |
+
"learning_rate": 7.998e-05,
|
| 121 |
+
"loss": 7.5186,
|
| 122 |
+
"step": 8000
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 5.438259756877799,
|
| 126 |
+
"grad_norm": 6.061458587646484,
|
| 127 |
+
"learning_rate": 8.497000000000001e-05,
|
| 128 |
+
"loss": 7.3966,
|
| 129 |
+
"step": 8500
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 5.758157389635317,
|
| 133 |
+
"grad_norm": 7.151447772979736,
|
| 134 |
+
"learning_rate": 8.997000000000001e-05,
|
| 135 |
+
"loss": 7.2877,
|
| 136 |
+
"step": 9000
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 6.078055022392834,
|
| 140 |
+
"grad_norm": 7.578985214233398,
|
| 141 |
+
"learning_rate": 9.497000000000001e-05,
|
| 142 |
+
"loss": 7.1542,
|
| 143 |
+
"step": 9500
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 6.397952655150352,
|
| 147 |
+
"grad_norm": 5.948920726776123,
|
| 148 |
+
"learning_rate": 9.997e-05,
|
| 149 |
+
"loss": 7.0008,
|
| 150 |
+
"step": 10000
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 6.717850287907869,
|
| 154 |
+
"grad_norm": 8.036959648132324,
|
| 155 |
+
"learning_rate": 9.982896551724137e-05,
|
| 156 |
+
"loss": 6.8966,
|
| 157 |
+
"step": 10500
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 7.037747920665387,
|
| 161 |
+
"grad_norm": 7.160433292388916,
|
| 162 |
+
"learning_rate": 9.965655172413794e-05,
|
| 163 |
+
"loss": 6.7509,
|
| 164 |
+
"step": 11000
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 7.357645553422905,
|
| 168 |
+
"grad_norm": 5.934999465942383,
|
| 169 |
+
"learning_rate": 9.948413793103449e-05,
|
| 170 |
+
"loss": 6.5833,
|
| 171 |
+
"step": 11500
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 7.677543186180422,
|
| 175 |
+
"grad_norm": 7.745622634887695,
|
| 176 |
+
"learning_rate": 9.931172413793104e-05,
|
| 177 |
+
"loss": 6.4975,
|
| 178 |
+
"step": 12000
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 7.99744081893794,
|
| 182 |
+
"grad_norm": 7.0418477058410645,
|
| 183 |
+
"learning_rate": 9.91393103448276e-05,
|
| 184 |
+
"loss": 6.4261,
|
| 185 |
+
"step": 12500
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 8.317338451695457,
|
| 189 |
+
"grad_norm": 6.101259708404541,
|
| 190 |
+
"learning_rate": 9.896689655172414e-05,
|
| 191 |
+
"loss": 6.2092,
|
| 192 |
+
"step": 13000
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 8.637236084452976,
|
| 196 |
+
"grad_norm": 7.289799213409424,
|
| 197 |
+
"learning_rate": 9.87944827586207e-05,
|
| 198 |
+
"loss": 6.1436,
|
| 199 |
+
"step": 13500
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 8.957133717210493,
|
| 203 |
+
"grad_norm": 8.126811027526855,
|
| 204 |
+
"learning_rate": 9.862206896551725e-05,
|
| 205 |
+
"loss": 6.0456,
|
| 206 |
+
"step": 14000
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 9.277031349968011,
|
| 210 |
+
"grad_norm": 8.221816062927246,
|
| 211 |
+
"learning_rate": 9.845000000000001e-05,
|
| 212 |
+
"loss": 5.9141,
|
| 213 |
+
"step": 14500
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 9.596928982725528,
|
| 217 |
+
"grad_norm": 7.361550331115723,
|
| 218 |
+
"learning_rate": 9.827793103448277e-05,
|
| 219 |
+
"loss": 5.8326,
|
| 220 |
+
"step": 15000
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 9.916826615483046,
|
| 224 |
+
"grad_norm": 7.1737775802612305,
|
| 225 |
+
"learning_rate": 9.810551724137932e-05,
|
| 226 |
+
"loss": 5.7974,
|
| 227 |
+
"step": 15500
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 10.236724248240563,
|
| 231 |
+
"grad_norm": 9.80185604095459,
|
| 232 |
+
"learning_rate": 9.793310344827586e-05,
|
| 233 |
+
"loss": 5.6282,
|
| 234 |
+
"step": 16000
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 10.556621880998081,
|
| 238 |
+
"grad_norm": 7.2062153816223145,
|
| 239 |
+
"learning_rate": 9.776068965517242e-05,
|
| 240 |
+
"loss": 5.5619,
|
| 241 |
+
"step": 16500
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 10.876519513755598,
|
| 245 |
+
"grad_norm": 10.801878929138184,
|
| 246 |
+
"learning_rate": 9.758827586206896e-05,
|
| 247 |
+
"loss": 5.5155,
|
| 248 |
+
"step": 17000
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 11.196417146513117,
|
| 252 |
+
"grad_norm": 8.48509693145752,
|
| 253 |
+
"learning_rate": 9.741586206896553e-05,
|
| 254 |
+
"loss": 5.4259,
|
| 255 |
+
"step": 17500
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 11.516314779270633,
|
| 259 |
+
"grad_norm": 8.47572135925293,
|
| 260 |
+
"learning_rate": 9.724344827586207e-05,
|
| 261 |
+
"loss": 5.3205,
|
| 262 |
+
"step": 18000
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 11.836212412028152,
|
| 266 |
+
"grad_norm": 6.122796535491943,
|
| 267 |
+
"learning_rate": 9.707103448275863e-05,
|
| 268 |
+
"loss": 5.3025,
|
| 269 |
+
"step": 18500
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 12.156110044785668,
|
| 273 |
+
"grad_norm": 8.210710525512695,
|
| 274 |
+
"learning_rate": 9.689896551724139e-05,
|
| 275 |
+
"loss": 5.2264,
|
| 276 |
+
"step": 19000
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 12.476007677543187,
|
| 280 |
+
"grad_norm": 7.857537746429443,
|
| 281 |
+
"learning_rate": 9.672655172413794e-05,
|
| 282 |
+
"loss": 5.1395,
|
| 283 |
+
"step": 19500
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 12.795905310300704,
|
| 287 |
+
"grad_norm": 7.743075370788574,
|
| 288 |
+
"learning_rate": 9.655413793103448e-05,
|
| 289 |
+
"loss": 5.1109,
|
| 290 |
+
"step": 20000
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 13.115802943058222,
|
| 294 |
+
"grad_norm": 10.574569702148438,
|
| 295 |
+
"learning_rate": 9.638172413793104e-05,
|
| 296 |
+
"loss": 5.0794,
|
| 297 |
+
"step": 20500
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 13.435700575815739,
|
| 301 |
+
"grad_norm": 8.313858985900879,
|
| 302 |
+
"learning_rate": 9.620931034482758e-05,
|
| 303 |
+
"loss": 4.921,
|
| 304 |
+
"step": 21000
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 13.755598208573257,
|
| 308 |
+
"grad_norm": 9.096057891845703,
|
| 309 |
+
"learning_rate": 9.603689655172414e-05,
|
| 310 |
+
"loss": 4.96,
|
| 311 |
+
"step": 21500
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 14.075495841330774,
|
| 315 |
+
"grad_norm": 8.402993202209473,
|
| 316 |
+
"learning_rate": 9.58644827586207e-05,
|
| 317 |
+
"loss": 4.9062,
|
| 318 |
+
"step": 22000
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 14.395393474088293,
|
| 322 |
+
"grad_norm": 8.110074996948242,
|
| 323 |
+
"learning_rate": 9.569206896551725e-05,
|
| 324 |
+
"loss": 4.8026,
|
| 325 |
+
"step": 22500
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 14.71529110684581,
|
| 329 |
+
"grad_norm": 7.908292293548584,
|
| 330 |
+
"learning_rate": 9.552000000000001e-05,
|
| 331 |
+
"loss": 4.82,
|
| 332 |
+
"step": 23000
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 15.035188739603328,
|
| 336 |
+
"grad_norm": 7.991878986358643,
|
| 337 |
+
"learning_rate": 9.534758620689655e-05,
|
| 338 |
+
"loss": 4.7397,
|
| 339 |
+
"step": 23500
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 15.355086372360844,
|
| 343 |
+
"grad_norm": 8.696029663085938,
|
| 344 |
+
"learning_rate": 9.517551724137932e-05,
|
| 345 |
+
"loss": 4.6656,
|
| 346 |
+
"step": 24000
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 15.674984005118363,
|
| 350 |
+
"grad_norm": 9.421612739562988,
|
| 351 |
+
"learning_rate": 9.500310344827586e-05,
|
| 352 |
+
"loss": 4.6412,
|
| 353 |
+
"step": 24500
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 15.99488163787588,
|
| 357 |
+
"grad_norm": 9.747482299804688,
|
| 358 |
+
"learning_rate": 9.483068965517242e-05,
|
| 359 |
+
"loss": 4.6048,
|
| 360 |
+
"step": 25000
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 16.314779270633398,
|
| 364 |
+
"grad_norm": 10.389492988586426,
|
| 365 |
+
"learning_rate": 9.465827586206897e-05,
|
| 366 |
+
"loss": 4.481,
|
| 367 |
+
"step": 25500
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 16.634676903390915,
|
| 371 |
+
"grad_norm": 8.661949157714844,
|
| 372 |
+
"learning_rate": 9.448586206896553e-05,
|
| 373 |
+
"loss": 4.4923,
|
| 374 |
+
"step": 26000
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 16.95457453614843,
|
| 378 |
+
"grad_norm": 12.681297302246094,
|
| 379 |
+
"learning_rate": 9.431344827586207e-05,
|
| 380 |
+
"loss": 4.4816,
|
| 381 |
+
"step": 26500
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 17.27447216890595,
|
| 385 |
+
"grad_norm": 8.993134498596191,
|
| 386 |
+
"learning_rate": 9.414103448275863e-05,
|
| 387 |
+
"loss": 4.3512,
|
| 388 |
+
"step": 27000
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 17.59436980166347,
|
| 392 |
+
"grad_norm": 10.020146369934082,
|
| 393 |
+
"learning_rate": 9.396862068965517e-05,
|
| 394 |
+
"loss": 4.3447,
|
| 395 |
+
"step": 27500
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 17.914267434420985,
|
| 399 |
+
"grad_norm": 9.514701843261719,
|
| 400 |
+
"learning_rate": 9.379655172413794e-05,
|
| 401 |
+
"loss": 4.3376,
|
| 402 |
+
"step": 28000
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 18.234165067178502,
|
| 406 |
+
"grad_norm": 10.324498176574707,
|
| 407 |
+
"learning_rate": 9.362413793103448e-05,
|
| 408 |
+
"loss": 4.2612,
|
| 409 |
+
"step": 28500
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 18.554062699936022,
|
| 413 |
+
"grad_norm": 10.682856559753418,
|
| 414 |
+
"learning_rate": 9.345172413793104e-05,
|
| 415 |
+
"loss": 4.226,
|
| 416 |
+
"step": 29000
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 18.87396033269354,
|
| 420 |
+
"grad_norm": 7.883260726928711,
|
| 421 |
+
"learning_rate": 9.327931034482758e-05,
|
| 422 |
+
"loss": 4.19,
|
| 423 |
+
"step": 29500
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 19.193857965451055,
|
| 427 |
+
"grad_norm": 12.470623016357422,
|
| 428 |
+
"learning_rate": 9.310724137931035e-05,
|
| 429 |
+
"loss": 4.1881,
|
| 430 |
+
"step": 30000
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 19.513755598208572,
|
| 434 |
+
"grad_norm": 9.932331085205078,
|
| 435 |
+
"learning_rate": 9.29348275862069e-05,
|
| 436 |
+
"loss": 4.0853,
|
| 437 |
+
"step": 30500
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 19.833653230966092,
|
| 441 |
+
"grad_norm": 8.153782844543457,
|
| 442 |
+
"learning_rate": 9.276241379310345e-05,
|
| 443 |
+
"loss": 4.1087,
|
| 444 |
+
"step": 31000
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 20.15355086372361,
|
| 448 |
+
"grad_norm": 8.214093208312988,
|
| 449 |
+
"learning_rate": 9.258999999999999e-05,
|
| 450 |
+
"loss": 4.0751,
|
| 451 |
+
"step": 31500
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 20.473448496481126,
|
| 455 |
+
"grad_norm": 11.927350044250488,
|
| 456 |
+
"learning_rate": 9.241758620689656e-05,
|
| 457 |
+
"loss": 3.9686,
|
| 458 |
+
"step": 32000
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 20.793346129238643,
|
| 462 |
+
"grad_norm": 9.67835807800293,
|
| 463 |
+
"learning_rate": 9.224551724137932e-05,
|
| 464 |
+
"loss": 3.9745,
|
| 465 |
+
"step": 32500
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 21.113243761996163,
|
| 469 |
+
"grad_norm": 9.911735534667969,
|
| 470 |
+
"learning_rate": 9.207310344827586e-05,
|
| 471 |
+
"loss": 3.9308,
|
| 472 |
+
"step": 33000
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 21.43314139475368,
|
| 476 |
+
"grad_norm": 9.05053424835205,
|
| 477 |
+
"learning_rate": 9.190068965517242e-05,
|
| 478 |
+
"loss": 3.8718,
|
| 479 |
+
"step": 33500
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 21.753039027511196,
|
| 483 |
+
"grad_norm": 9.588044166564941,
|
| 484 |
+
"learning_rate": 9.172827586206897e-05,
|
| 485 |
+
"loss": 3.8425,
|
| 486 |
+
"step": 34000
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 22.072936660268713,
|
| 490 |
+
"grad_norm": 8.788230895996094,
|
| 491 |
+
"learning_rate": 9.155620689655173e-05,
|
| 492 |
+
"loss": 3.8617,
|
| 493 |
+
"step": 34500
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 22.392834293026233,
|
| 497 |
+
"grad_norm": 9.435895919799805,
|
| 498 |
+
"learning_rate": 9.138379310344827e-05,
|
| 499 |
+
"loss": 3.7524,
|
| 500 |
+
"step": 35000
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 22.71273192578375,
|
| 504 |
+
"grad_norm": 9.870182037353516,
|
| 505 |
+
"learning_rate": 9.121137931034483e-05,
|
| 506 |
+
"loss": 3.7916,
|
| 507 |
+
"step": 35500
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 23.032629558541267,
|
| 511 |
+
"grad_norm": 9.612881660461426,
|
| 512 |
+
"learning_rate": 9.103896551724139e-05,
|
| 513 |
+
"loss": 3.8011,
|
| 514 |
+
"step": 36000
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 23.352527191298783,
|
| 518 |
+
"grad_norm": 9.643827438354492,
|
| 519 |
+
"learning_rate": 9.086689655172414e-05,
|
| 520 |
+
"loss": 3.6478,
|
| 521 |
+
"step": 36500
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 23.672424824056304,
|
| 525 |
+
"grad_norm": 14.105424880981445,
|
| 526 |
+
"learning_rate": 9.069448275862069e-05,
|
| 527 |
+
"loss": 3.6671,
|
| 528 |
+
"step": 37000
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 23.99232245681382,
|
| 532 |
+
"grad_norm": 10.427962303161621,
|
| 533 |
+
"learning_rate": 9.052206896551724e-05,
|
| 534 |
+
"loss": 3.6809,
|
| 535 |
+
"step": 37500
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 24.312220089571337,
|
| 539 |
+
"grad_norm": 11.505946159362793,
|
| 540 |
+
"learning_rate": 9.03496551724138e-05,
|
| 541 |
+
"loss": 3.553,
|
| 542 |
+
"step": 38000
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 24.632117722328854,
|
| 546 |
+
"grad_norm": 10.393635749816895,
|
| 547 |
+
"learning_rate": 9.017724137931035e-05,
|
| 548 |
+
"loss": 3.5408,
|
| 549 |
+
"step": 38500
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 24.952015355086374,
|
| 553 |
+
"grad_norm": 9.023842811584473,
|
| 554 |
+
"learning_rate": 9.00051724137931e-05,
|
| 555 |
+
"loss": 3.5915,
|
| 556 |
+
"step": 39000
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 25.27191298784389,
|
| 560 |
+
"grad_norm": 10.69048023223877,
|
| 561 |
+
"learning_rate": 8.983275862068967e-05,
|
| 562 |
+
"loss": 3.4896,
|
| 563 |
+
"step": 39500
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 25.591810620601407,
|
| 567 |
+
"grad_norm": 10.803936958312988,
|
| 568 |
+
"learning_rate": 8.966034482758621e-05,
|
| 569 |
+
"loss": 3.4854,
|
| 570 |
+
"step": 40000
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 25.911708253358924,
|
| 574 |
+
"grad_norm": 10.489801406860352,
|
| 575 |
+
"learning_rate": 8.948793103448276e-05,
|
| 576 |
+
"loss": 3.4871,
|
| 577 |
+
"step": 40500
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 26.231605886116444,
|
| 581 |
+
"grad_norm": 10.558309555053711,
|
| 582 |
+
"learning_rate": 8.931586206896552e-05,
|
| 583 |
+
"loss": 3.4186,
|
| 584 |
+
"step": 41000
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 26.55150351887396,
|
| 588 |
+
"grad_norm": 12.186748504638672,
|
| 589 |
+
"learning_rate": 8.914344827586208e-05,
|
| 590 |
+
"loss": 3.4027,
|
| 591 |
+
"step": 41500
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 26.871401151631478,
|
| 595 |
+
"grad_norm": 9.8623046875,
|
| 596 |
+
"learning_rate": 8.897103448275862e-05,
|
| 597 |
+
"loss": 3.4191,
|
| 598 |
+
"step": 42000
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 27.191298784388994,
|
| 602 |
+
"grad_norm": 11.407792091369629,
|
| 603 |
+
"learning_rate": 8.879862068965518e-05,
|
| 604 |
+
"loss": 3.341,
|
| 605 |
+
"step": 42500
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 27.511196417146515,
|
| 609 |
+
"grad_norm": 13.37617301940918,
|
| 610 |
+
"learning_rate": 8.862655172413794e-05,
|
| 611 |
+
"loss": 3.3137,
|
| 612 |
+
"step": 43000
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 27.83109404990403,
|
| 616 |
+
"grad_norm": 10.30826187133789,
|
| 617 |
+
"learning_rate": 8.845413793103449e-05,
|
| 618 |
+
"loss": 3.3036,
|
| 619 |
+
"step": 43500
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 28.150991682661548,
|
| 623 |
+
"grad_norm": 12.024778366088867,
|
| 624 |
+
"learning_rate": 8.828172413793105e-05,
|
| 625 |
+
"loss": 3.2678,
|
| 626 |
+
"step": 44000
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 28.470889315419065,
|
| 630 |
+
"grad_norm": 9.730340957641602,
|
| 631 |
+
"learning_rate": 8.810931034482759e-05,
|
| 632 |
+
"loss": 3.1949,
|
| 633 |
+
"step": 44500
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 28.790786948176585,
|
| 637 |
+
"grad_norm": 9.700602531433105,
|
| 638 |
+
"learning_rate": 8.793689655172414e-05,
|
| 639 |
+
"loss": 3.2541,
|
| 640 |
+
"step": 45000
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 29.1106845809341,
|
| 644 |
+
"grad_norm": 12.359143257141113,
|
| 645 |
+
"learning_rate": 8.77648275862069e-05,
|
| 646 |
+
"loss": 3.2456,
|
| 647 |
+
"step": 45500
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 29.43058221369162,
|
| 651 |
+
"grad_norm": 11.989018440246582,
|
| 652 |
+
"learning_rate": 8.759241379310346e-05,
|
| 653 |
+
"loss": 3.1154,
|
| 654 |
+
"step": 46000
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 29.750479846449135,
|
| 658 |
+
"grad_norm": 10.904190063476562,
|
| 659 |
+
"learning_rate": 8.742e-05,
|
| 660 |
+
"loss": 3.175,
|
| 661 |
+
"step": 46500
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 30.070377479206655,
|
| 665 |
+
"grad_norm": 11.253949165344238,
|
| 666 |
+
"learning_rate": 8.724758620689656e-05,
|
| 667 |
+
"loss": 3.1478,
|
| 668 |
+
"step": 47000
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 30.390275111964172,
|
| 672 |
+
"grad_norm": 12.229791641235352,
|
| 673 |
+
"learning_rate": 8.707517241379311e-05,
|
| 674 |
+
"loss": 3.0632,
|
| 675 |
+
"step": 47500
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 30.71017274472169,
|
| 679 |
+
"grad_norm": 9.516524314880371,
|
| 680 |
+
"learning_rate": 8.690275862068967e-05,
|
| 681 |
+
"loss": 3.0843,
|
| 682 |
+
"step": 48000
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 31.030070377479205,
|
| 686 |
+
"grad_norm": 13.730731010437012,
|
| 687 |
+
"learning_rate": 8.673034482758621e-05,
|
| 688 |
+
"loss": 3.098,
|
| 689 |
+
"step": 48500
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 31.349968010236726,
|
| 693 |
+
"grad_norm": 9.73539924621582,
|
| 694 |
+
"learning_rate": 8.655827586206897e-05,
|
| 695 |
+
"loss": 2.9611,
|
| 696 |
+
"step": 49000
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 31.669865642994242,
|
| 700 |
+
"grad_norm": 12.066815376281738,
|
| 701 |
+
"learning_rate": 8.638586206896552e-05,
|
| 702 |
+
"loss": 2.9943,
|
| 703 |
+
"step": 49500
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 31.98976327575176,
|
| 707 |
+
"grad_norm": 11.028585433959961,
|
| 708 |
+
"learning_rate": 8.621344827586208e-05,
|
| 709 |
+
"loss": 3.0424,
|
| 710 |
+
"step": 50000
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 32.30966090850928,
|
| 714 |
+
"grad_norm": 11.2380952835083,
|
| 715 |
+
"learning_rate": 8.604103448275862e-05,
|
| 716 |
+
"loss": 2.9023,
|
| 717 |
+
"step": 50500
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 32.629558541266796,
|
| 721 |
+
"grad_norm": 9.345772743225098,
|
| 722 |
+
"learning_rate": 8.586862068965518e-05,
|
| 723 |
+
"loss": 2.9586,
|
| 724 |
+
"step": 51000
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 32.94945617402431,
|
| 728 |
+
"grad_norm": 10.239849090576172,
|
| 729 |
+
"learning_rate": 8.569655172413793e-05,
|
| 730 |
+
"loss": 2.9461,
|
| 731 |
+
"step": 51500
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 33.26935380678183,
|
| 735 |
+
"grad_norm": 11.058523178100586,
|
| 736 |
+
"learning_rate": 8.552413793103449e-05,
|
| 737 |
+
"loss": 2.8453,
|
| 738 |
+
"step": 52000
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 33.589251439539346,
|
| 742 |
+
"grad_norm": 12.131317138671875,
|
| 743 |
+
"learning_rate": 8.535172413793105e-05,
|
| 744 |
+
"loss": 2.8603,
|
| 745 |
+
"step": 52500
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 33.90914907229686,
|
| 749 |
+
"grad_norm": 10.392476081848145,
|
| 750 |
+
"learning_rate": 8.517931034482759e-05,
|
| 751 |
+
"loss": 2.8817,
|
| 752 |
+
"step": 53000
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 34.22904670505438,
|
| 756 |
+
"grad_norm": 10.749021530151367,
|
| 757 |
+
"learning_rate": 8.500724137931036e-05,
|
| 758 |
+
"loss": 2.8073,
|
| 759 |
+
"step": 53500
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 34.5489443378119,
|
| 763 |
+
"grad_norm": 12.33171558380127,
|
| 764 |
+
"learning_rate": 8.48348275862069e-05,
|
| 765 |
+
"loss": 2.7793,
|
| 766 |
+
"step": 54000
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 34.86884197056942,
|
| 770 |
+
"grad_norm": 12.961758613586426,
|
| 771 |
+
"learning_rate": 8.466241379310346e-05,
|
| 772 |
+
"loss": 2.8066,
|
| 773 |
+
"step": 54500
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 35.18873960332694,
|
| 777 |
+
"grad_norm": 13.320075035095215,
|
| 778 |
+
"learning_rate": 8.449e-05,
|
| 779 |
+
"loss": 2.7459,
|
| 780 |
+
"step": 55000
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 35.50863723608445,
|
| 784 |
+
"grad_norm": 14.416489601135254,
|
| 785 |
+
"learning_rate": 8.431758620689655e-05,
|
| 786 |
+
"loss": 2.7321,
|
| 787 |
+
"step": 55500
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 35.82853486884197,
|
| 791 |
+
"grad_norm": 11.203073501586914,
|
| 792 |
+
"learning_rate": 8.414551724137931e-05,
|
| 793 |
+
"loss": 2.7486,
|
| 794 |
+
"step": 56000
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 36.14843250159949,
|
| 798 |
+
"grad_norm": 10.463476181030273,
|
| 799 |
+
"learning_rate": 8.397310344827587e-05,
|
| 800 |
+
"loss": 2.7086,
|
| 801 |
+
"step": 56500
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 36.468330134357004,
|
| 805 |
+
"grad_norm": 11.375761985778809,
|
| 806 |
+
"learning_rate": 8.380068965517241e-05,
|
| 807 |
+
"loss": 2.6387,
|
| 808 |
+
"step": 57000
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 36.78822776711452,
|
| 812 |
+
"grad_norm": 11.649105072021484,
|
| 813 |
+
"learning_rate": 8.362827586206897e-05,
|
| 814 |
+
"loss": 2.6746,
|
| 815 |
+
"step": 57500
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 37.108125399872044,
|
| 819 |
+
"grad_norm": 12.708244323730469,
|
| 820 |
+
"learning_rate": 8.345586206896552e-05,
|
| 821 |
+
"loss": 2.6454,
|
| 822 |
+
"step": 58000
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 37.42802303262956,
|
| 826 |
+
"grad_norm": 12.876201629638672,
|
| 827 |
+
"learning_rate": 8.328344827586208e-05,
|
| 828 |
+
"loss": 2.5798,
|
| 829 |
+
"step": 58500
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 37.74792066538708,
|
| 833 |
+
"grad_norm": 11.92346477508545,
|
| 834 |
+
"learning_rate": 8.311103448275862e-05,
|
| 835 |
+
"loss": 2.6589,
|
| 836 |
+
"step": 59000
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 38.067818298144594,
|
| 840 |
+
"grad_norm": 10.742238998413086,
|
| 841 |
+
"learning_rate": 8.293896551724138e-05,
|
| 842 |
+
"loss": 2.5868,
|
| 843 |
+
"step": 59500
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 38.38771593090211,
|
| 847 |
+
"grad_norm": 11.399048805236816,
|
| 848 |
+
"learning_rate": 8.276655172413793e-05,
|
| 849 |
+
"loss": 2.5124,
|
| 850 |
+
"step": 60000
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 38.70761356365963,
|
| 854 |
+
"grad_norm": 13.563875198364258,
|
| 855 |
+
"learning_rate": 8.259413793103449e-05,
|
| 856 |
+
"loss": 2.576,
|
| 857 |
+
"step": 60500
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 39.027511196417144,
|
| 861 |
+
"grad_norm": 11.297135353088379,
|
| 862 |
+
"learning_rate": 8.242172413793103e-05,
|
| 863 |
+
"loss": 2.5671,
|
| 864 |
+
"step": 61000
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 39.34740882917466,
|
| 868 |
+
"grad_norm": 11.336121559143066,
|
| 869 |
+
"learning_rate": 8.22496551724138e-05,
|
| 870 |
+
"loss": 2.4445,
|
| 871 |
+
"step": 61500
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 39.667306461932185,
|
| 875 |
+
"grad_norm": 9.477692604064941,
|
| 876 |
+
"learning_rate": 8.207724137931035e-05,
|
| 877 |
+
"loss": 2.4981,
|
| 878 |
+
"step": 62000
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 39.9872040946897,
|
| 882 |
+
"grad_norm": 11.597848892211914,
|
| 883 |
+
"learning_rate": 8.19048275862069e-05,
|
| 884 |
+
"loss": 2.5382,
|
| 885 |
+
"step": 62500
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 40.30710172744722,
|
| 889 |
+
"grad_norm": 14.910037994384766,
|
| 890 |
+
"learning_rate": 8.173241379310346e-05,
|
| 891 |
+
"loss": 2.4158,
|
| 892 |
+
"step": 63000
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 40.626999360204735,
|
| 896 |
+
"grad_norm": 11.870673179626465,
|
| 897 |
+
"learning_rate": 8.156e-05,
|
| 898 |
+
"loss": 2.4395,
|
| 899 |
+
"step": 63500
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 40.94689699296225,
|
| 903 |
+
"grad_norm": 15.279576301574707,
|
| 904 |
+
"learning_rate": 8.138758620689655e-05,
|
| 905 |
+
"loss": 2.4653,
|
| 906 |
+
"step": 64000
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 41.26679462571977,
|
| 910 |
+
"grad_norm": 11.710406303405762,
|
| 911 |
+
"learning_rate": 8.121551724137931e-05,
|
| 912 |
+
"loss": 2.3567,
|
| 913 |
+
"step": 64500
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 41.586692258477285,
|
| 917 |
+
"grad_norm": 10.663411140441895,
|
| 918 |
+
"learning_rate": 8.104310344827587e-05,
|
| 919 |
+
"loss": 2.3655,
|
| 920 |
+
"step": 65000
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 41.9065898912348,
|
| 924 |
+
"grad_norm": 13.946629524230957,
|
| 925 |
+
"learning_rate": 8.087068965517241e-05,
|
| 926 |
+
"loss": 2.4336,
|
| 927 |
+
"step": 65500
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 42.226487523992326,
|
| 931 |
+
"grad_norm": 13.782262802124023,
|
| 932 |
+
"learning_rate": 8.069827586206898e-05,
|
| 933 |
+
"loss": 2.3351,
|
| 934 |
+
"step": 66000
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 42.54638515674984,
|
| 938 |
+
"grad_norm": 11.177961349487305,
|
| 939 |
+
"learning_rate": 8.052586206896552e-05,
|
| 940 |
+
"loss": 2.359,
|
| 941 |
+
"step": 66500
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 42.86628278950736,
|
| 945 |
+
"grad_norm": 15.120301246643066,
|
| 946 |
+
"learning_rate": 8.035344827586208e-05,
|
| 947 |
+
"loss": 2.355,
|
| 948 |
+
"step": 67000
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 43.186180422264876,
|
| 952 |
+
"grad_norm": 10.805267333984375,
|
| 953 |
+
"learning_rate": 8.018103448275862e-05,
|
| 954 |
+
"loss": 2.2905,
|
| 955 |
+
"step": 67500
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 43.50607805502239,
|
| 959 |
+
"grad_norm": 11.777176856994629,
|
| 960 |
+
"learning_rate": 8.000862068965517e-05,
|
| 961 |
+
"loss": 2.2906,
|
| 962 |
+
"step": 68000
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 43.82597568777991,
|
| 966 |
+
"grad_norm": 15.457807540893555,
|
| 967 |
+
"learning_rate": 7.983689655172414e-05,
|
| 968 |
+
"loss": 2.3269,
|
| 969 |
+
"step": 68500
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 44.145873320537426,
|
| 973 |
+
"grad_norm": 11.639357566833496,
|
| 974 |
+
"learning_rate": 7.966448275862069e-05,
|
| 975 |
+
"loss": 2.2371,
|
| 976 |
+
"step": 69000
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 44.46577095329494,
|
| 980 |
+
"grad_norm": 11.710591316223145,
|
| 981 |
+
"learning_rate": 7.949206896551725e-05,
|
| 982 |
+
"loss": 2.2248,
|
| 983 |
+
"step": 69500
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 44.785668586052466,
|
| 987 |
+
"grad_norm": 12.675103187561035,
|
| 988 |
+
"learning_rate": 7.93196551724138e-05,
|
| 989 |
+
"loss": 2.2586,
|
| 990 |
+
"step": 70000
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 45.10556621880998,
|
| 994 |
+
"grad_norm": 12.752120971679688,
|
| 995 |
+
"learning_rate": 7.914724137931034e-05,
|
| 996 |
+
"loss": 2.2489,
|
| 997 |
+
"step": 70500
|
| 998 |
+
},
|
| 999 |
+
{
|
| 1000 |
+
"epoch": 45.4254638515675,
|
| 1001 |
+
"grad_norm": 11.379339218139648,
|
| 1002 |
+
"learning_rate": 7.89751724137931e-05,
|
| 1003 |
+
"loss": 2.1774,
|
| 1004 |
+
"step": 71000
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 45.74536148432502,
|
| 1008 |
+
"grad_norm": 12.76633358001709,
|
| 1009 |
+
"learning_rate": 7.880275862068966e-05,
|
| 1010 |
+
"loss": 2.2007,
|
| 1011 |
+
"step": 71500
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 46.06525911708253,
|
| 1015 |
+
"grad_norm": 11.421367645263672,
|
| 1016 |
+
"learning_rate": 7.863034482758621e-05,
|
| 1017 |
+
"loss": 2.2262,
|
| 1018 |
+
"step": 72000
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"epoch": 46.38515674984005,
|
| 1022 |
+
"grad_norm": 14.81748104095459,
|
| 1023 |
+
"learning_rate": 7.845793103448277e-05,
|
| 1024 |
+
"loss": 2.101,
|
| 1025 |
+
"step": 72500
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 46.70505438259757,
|
| 1029 |
+
"grad_norm": 12.902971267700195,
|
| 1030 |
+
"learning_rate": 7.828551724137931e-05,
|
| 1031 |
+
"loss": 2.1568,
|
| 1032 |
+
"step": 73000
|
| 1033 |
+
},
|
| 1034 |
+
{
|
| 1035 |
+
"epoch": 47.02495201535508,
|
| 1036 |
+
"grad_norm": 10.685113906860352,
|
| 1037 |
+
"learning_rate": 7.811310344827587e-05,
|
| 1038 |
+
"loss": 2.1655,
|
| 1039 |
+
"step": 73500
|
| 1040 |
+
},
|
| 1041 |
+
{
|
| 1042 |
+
"epoch": 47.34484964811261,
|
| 1043 |
+
"grad_norm": 15.892518043518066,
|
| 1044 |
+
"learning_rate": 7.794068965517242e-05,
|
| 1045 |
+
"loss": 2.0551,
|
| 1046 |
+
"step": 74000
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 47.664747280870124,
|
| 1050 |
+
"grad_norm": 13.730358123779297,
|
| 1051 |
+
"learning_rate": 7.776862068965518e-05,
|
| 1052 |
+
"loss": 2.1053,
|
| 1053 |
+
"step": 74500
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 47.98464491362764,
|
| 1057 |
+
"grad_norm": 13.635787963867188,
|
| 1058 |
+
"learning_rate": 7.759620689655172e-05,
|
| 1059 |
+
"loss": 2.1408,
|
| 1060 |
+
"step": 75000
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"epoch": 48.30454254638516,
|
| 1064 |
+
"grad_norm": 12.861611366271973,
|
| 1065 |
+
"learning_rate": 7.742379310344828e-05,
|
| 1066 |
+
"loss": 2.0104,
|
| 1067 |
+
"step": 75500
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"epoch": 48.624440179142674,
|
| 1071 |
+
"grad_norm": 11.84931468963623,
|
| 1072 |
+
"learning_rate": 7.725137931034483e-05,
|
| 1073 |
+
"loss": 2.0555,
|
| 1074 |
+
"step": 76000
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 48.94433781190019,
|
| 1078 |
+
"grad_norm": 15.812765121459961,
|
| 1079 |
+
"learning_rate": 7.70793103448276e-05,
|
| 1080 |
+
"loss": 2.1087,
|
| 1081 |
+
"step": 76500
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 49.26423544465771,
|
| 1085 |
+
"grad_norm": 14.233431816101074,
|
| 1086 |
+
"learning_rate": 7.690689655172414e-05,
|
| 1087 |
+
"loss": 1.9998,
|
| 1088 |
+
"step": 77000
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 49.584133077415224,
|
| 1092 |
+
"grad_norm": 14.329803466796875,
|
| 1093 |
+
"learning_rate": 7.673448275862069e-05,
|
| 1094 |
+
"loss": 2.0189,
|
| 1095 |
+
"step": 77500
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 49.90403071017275,
|
| 1099 |
+
"grad_norm": 11.00400161743164,
|
| 1100 |
+
"learning_rate": 7.656206896551725e-05,
|
| 1101 |
+
"loss": 2.059,
|
| 1102 |
+
"step": 78000
|
| 1103 |
+
},
|
| 1104 |
+
{
|
| 1105 |
+
"epoch": 50.223928342930265,
|
| 1106 |
+
"grad_norm": 13.582133293151855,
|
| 1107 |
+
"learning_rate": 7.63896551724138e-05,
|
| 1108 |
+
"loss": 1.9753,
|
| 1109 |
+
"step": 78500
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 50.54382597568778,
|
| 1113 |
+
"grad_norm": 12.560907363891602,
|
| 1114 |
+
"learning_rate": 7.621724137931034e-05,
|
| 1115 |
+
"loss": 1.9759,
|
| 1116 |
+
"step": 79000
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 50.8637236084453,
|
| 1120 |
+
"grad_norm": 12.169915199279785,
|
| 1121 |
+
"learning_rate": 7.60451724137931e-05,
|
| 1122 |
+
"loss": 1.9944,
|
| 1123 |
+
"step": 79500
|
| 1124 |
+
},
|
| 1125 |
+
{
|
| 1126 |
+
"epoch": 51.183621241202815,
|
| 1127 |
+
"grad_norm": 13.5604248046875,
|
| 1128 |
+
"learning_rate": 7.587275862068966e-05,
|
| 1129 |
+
"loss": 1.9323,
|
| 1130 |
+
"step": 80000
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 51.50351887396033,
|
| 1134 |
+
"grad_norm": 15.892741203308105,
|
| 1135 |
+
"learning_rate": 7.570034482758621e-05,
|
| 1136 |
+
"loss": 1.9095,
|
| 1137 |
+
"step": 80500
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 51.82341650671785,
|
| 1141 |
+
"grad_norm": 13.435209274291992,
|
| 1142 |
+
"learning_rate": 7.552793103448276e-05,
|
| 1143 |
+
"loss": 1.9508,
|
| 1144 |
+
"step": 81000
|
| 1145 |
+
},
|
| 1146 |
+
{
|
| 1147 |
+
"epoch": 52.143314139475365,
|
| 1148 |
+
"grad_norm": 11.180010795593262,
|
| 1149 |
+
"learning_rate": 7.535586206896551e-05,
|
| 1150 |
+
"loss": 1.9216,
|
| 1151 |
+
"step": 81500
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 52.46321177223289,
|
| 1155 |
+
"grad_norm": 12.792661666870117,
|
| 1156 |
+
"learning_rate": 7.518344827586207e-05,
|
| 1157 |
+
"loss": 1.8817,
|
| 1158 |
+
"step": 82000
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"epoch": 52.783109404990405,
|
| 1162 |
+
"grad_norm": 11.785886764526367,
|
| 1163 |
+
"learning_rate": 7.501103448275863e-05,
|
| 1164 |
+
"loss": 1.9121,
|
| 1165 |
+
"step": 82500
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"epoch": 53.10300703774792,
|
| 1169 |
+
"grad_norm": 10.568120002746582,
|
| 1170 |
+
"learning_rate": 7.483862068965518e-05,
|
| 1171 |
+
"loss": 1.8885,
|
| 1172 |
+
"step": 83000
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 53.42290467050544,
|
| 1176 |
+
"grad_norm": 14.641459465026855,
|
| 1177 |
+
"learning_rate": 7.466620689655172e-05,
|
| 1178 |
+
"loss": 1.8357,
|
| 1179 |
+
"step": 83500
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 53.742802303262955,
|
| 1183 |
+
"grad_norm": 13.5363187789917,
|
| 1184 |
+
"learning_rate": 7.449379310344828e-05,
|
| 1185 |
+
"loss": 1.8515,
|
| 1186 |
+
"step": 84000
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 54.06269993602047,
|
| 1190 |
+
"grad_norm": 12.997908592224121,
|
| 1191 |
+
"learning_rate": 7.432172413793104e-05,
|
| 1192 |
+
"loss": 1.8681,
|
| 1193 |
+
"step": 84500
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 54.38259756877799,
|
| 1197 |
+
"grad_norm": 12.53503131866455,
|
| 1198 |
+
"learning_rate": 7.414931034482759e-05,
|
| 1199 |
+
"loss": 1.7785,
|
| 1200 |
+
"step": 85000
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 54.702495201535505,
|
| 1204 |
+
"grad_norm": 11.986194610595703,
|
| 1205 |
+
"learning_rate": 7.397689655172413e-05,
|
| 1206 |
+
"loss": 1.8507,
|
| 1207 |
+
"step": 85500
|
| 1208 |
+
},
|
| 1209 |
+
{
|
| 1210 |
+
"epoch": 55.02239283429303,
|
| 1211 |
+
"grad_norm": 12.089723587036133,
|
| 1212 |
+
"learning_rate": 7.380448275862069e-05,
|
| 1213 |
+
"loss": 1.8537,
|
| 1214 |
+
"step": 86000
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 55.342290467050546,
|
| 1218 |
+
"grad_norm": 13.552453994750977,
|
| 1219 |
+
"learning_rate": 7.363206896551725e-05,
|
| 1220 |
+
"loss": 1.7622,
|
| 1221 |
+
"step": 86500
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 55.66218809980806,
|
| 1225 |
+
"grad_norm": 12.03878116607666,
|
| 1226 |
+
"learning_rate": 7.346e-05,
|
| 1227 |
+
"loss": 1.8076,
|
| 1228 |
+
"step": 87000
|
| 1229 |
+
},
|
| 1230 |
+
{
|
| 1231 |
+
"epoch": 55.98208573256558,
|
| 1232 |
+
"grad_norm": 11.187782287597656,
|
| 1233 |
+
"learning_rate": 7.328758620689655e-05,
|
| 1234 |
+
"loss": 1.8241,
|
| 1235 |
+
"step": 87500
|
| 1236 |
+
},
|
| 1237 |
+
{
|
| 1238 |
+
"epoch": 56.301983365323096,
|
| 1239 |
+
"grad_norm": 14.924737930297852,
|
| 1240 |
+
"learning_rate": 7.311517241379312e-05,
|
| 1241 |
+
"loss": 1.7077,
|
| 1242 |
+
"step": 88000
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"epoch": 56.62188099808061,
|
| 1246 |
+
"grad_norm": 12.302467346191406,
|
| 1247 |
+
"learning_rate": 7.294275862068966e-05,
|
| 1248 |
+
"loss": 1.74,
|
| 1249 |
+
"step": 88500
|
| 1250 |
+
},
|
| 1251 |
+
{
|
| 1252 |
+
"epoch": 56.94177863083813,
|
| 1253 |
+
"grad_norm": 10.834394454956055,
|
| 1254 |
+
"learning_rate": 7.277034482758621e-05,
|
| 1255 |
+
"loss": 1.7827,
|
| 1256 |
+
"step": 89000
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 57.261676263595646,
|
| 1260 |
+
"grad_norm": 14.356012344360352,
|
| 1261 |
+
"learning_rate": 7.259793103448276e-05,
|
| 1262 |
+
"loss": 1.7082,
|
| 1263 |
+
"step": 89500
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 57.58157389635317,
|
| 1267 |
+
"grad_norm": 14.632678031921387,
|
| 1268 |
+
"learning_rate": 7.242551724137931e-05,
|
| 1269 |
+
"loss": 1.7045,
|
| 1270 |
+
"step": 90000
|
| 1271 |
+
},
|
| 1272 |
+
{
|
| 1273 |
+
"epoch": 57.90147152911069,
|
| 1274 |
+
"grad_norm": 13.501043319702148,
|
| 1275 |
+
"learning_rate": 7.225344827586207e-05,
|
| 1276 |
+
"loss": 1.7522,
|
| 1277 |
+
"step": 90500
|
| 1278 |
+
},
|
| 1279 |
+
{
|
| 1280 |
+
"epoch": 58.2213691618682,
|
| 1281 |
+
"grad_norm": 18.839614868164062,
|
| 1282 |
+
"learning_rate": 7.208103448275862e-05,
|
| 1283 |
+
"loss": 1.6801,
|
| 1284 |
+
"step": 91000
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 58.54126679462572,
|
| 1288 |
+
"grad_norm": 13.41618824005127,
|
| 1289 |
+
"learning_rate": 7.190862068965517e-05,
|
| 1290 |
+
"loss": 1.7005,
|
| 1291 |
+
"step": 91500
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 58.86116442738324,
|
| 1295 |
+
"grad_norm": 12.56169605255127,
|
| 1296 |
+
"learning_rate": 7.173620689655172e-05,
|
| 1297 |
+
"loss": 1.7018,
|
| 1298 |
+
"step": 92000
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 59.18106206014075,
|
| 1302 |
+
"grad_norm": 13.447467803955078,
|
| 1303 |
+
"learning_rate": 7.15641379310345e-05,
|
| 1304 |
+
"loss": 1.6691,
|
| 1305 |
+
"step": 92500
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 59.50095969289827,
|
| 1309 |
+
"grad_norm": 12.452493667602539,
|
| 1310 |
+
"learning_rate": 7.139172413793104e-05,
|
| 1311 |
+
"loss": 1.651,
|
| 1312 |
+
"step": 93000
|
| 1313 |
+
},
|
| 1314 |
+
{
|
| 1315 |
+
"epoch": 59.82085732565579,
|
| 1316 |
+
"grad_norm": 10.552214622497559,
|
| 1317 |
+
"learning_rate": 7.121931034482759e-05,
|
| 1318 |
+
"loss": 1.6916,
|
| 1319 |
+
"step": 93500
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 60.14075495841331,
|
| 1323 |
+
"grad_norm": 11.099422454833984,
|
| 1324 |
+
"learning_rate": 7.104689655172413e-05,
|
| 1325 |
+
"loss": 1.6716,
|
| 1326 |
+
"step": 94000
|
| 1327 |
+
},
|
| 1328 |
+
{
|
| 1329 |
+
"epoch": 60.46065259117083,
|
| 1330 |
+
"grad_norm": 13.663276672363281,
|
| 1331 |
+
"learning_rate": 7.08744827586207e-05,
|
| 1332 |
+
"loss": 1.6105,
|
| 1333 |
+
"step": 94500
|
| 1334 |
+
},
|
| 1335 |
+
{
|
| 1336 |
+
"epoch": 60.780550223928344,
|
| 1337 |
+
"grad_norm": 11.783934593200684,
|
| 1338 |
+
"learning_rate": 7.070206896551725e-05,
|
| 1339 |
+
"loss": 1.6399,
|
| 1340 |
+
"step": 95000
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"epoch": 61.10044785668586,
|
| 1344 |
+
"grad_norm": 12.881340026855469,
|
| 1345 |
+
"learning_rate": 7.053e-05,
|
| 1346 |
+
"loss": 1.6058,
|
| 1347 |
+
"step": 95500
|
| 1348 |
+
},
|
| 1349 |
+
{
|
| 1350 |
+
"epoch": 61.42034548944338,
|
| 1351 |
+
"grad_norm": 12.405476570129395,
|
| 1352 |
+
"learning_rate": 7.035758620689656e-05,
|
| 1353 |
+
"loss": 1.5703,
|
| 1354 |
+
"step": 96000
|
| 1355 |
+
},
|
| 1356 |
+
{
|
| 1357 |
+
"epoch": 61.740243122200894,
|
| 1358 |
+
"grad_norm": 11.660452842712402,
|
| 1359 |
+
"learning_rate": 7.018517241379311e-05,
|
| 1360 |
+
"loss": 1.6002,
|
| 1361 |
+
"step": 96500
|
| 1362 |
+
},
|
| 1363 |
+
{
|
| 1364 |
+
"epoch": 62.06014075495841,
|
| 1365 |
+
"grad_norm": 11.69723892211914,
|
| 1366 |
+
"learning_rate": 7.001275862068966e-05,
|
| 1367 |
+
"loss": 1.6186,
|
| 1368 |
+
"step": 97000
|
| 1369 |
+
},
|
| 1370 |
+
{
|
| 1371 |
+
"epoch": 62.38003838771593,
|
| 1372 |
+
"grad_norm": 16.210947036743164,
|
| 1373 |
+
"learning_rate": 6.984034482758621e-05,
|
| 1374 |
+
"loss": 1.5663,
|
| 1375 |
+
"step": 97500
|
| 1376 |
+
},
|
| 1377 |
+
{
|
| 1378 |
+
"epoch": 62.69993602047345,
|
| 1379 |
+
"grad_norm": 11.853803634643555,
|
| 1380 |
+
"learning_rate": 6.966827586206897e-05,
|
| 1381 |
+
"loss": 1.5744,
|
| 1382 |
+
"step": 98000
|
| 1383 |
+
},
|
| 1384 |
+
{
|
| 1385 |
+
"epoch": 63.01983365323097,
|
| 1386 |
+
"grad_norm": 10.565818786621094,
|
| 1387 |
+
"learning_rate": 6.949586206896553e-05,
|
| 1388 |
+
"loss": 1.5829,
|
| 1389 |
+
"step": 98500
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 63.339731285988485,
|
| 1393 |
+
"grad_norm": 11.621013641357422,
|
| 1394 |
+
"learning_rate": 6.932344827586207e-05,
|
| 1395 |
+
"loss": 1.5213,
|
| 1396 |
+
"step": 99000
|
| 1397 |
+
},
|
| 1398 |
+
{
|
| 1399 |
+
"epoch": 63.659628918746,
|
| 1400 |
+
"grad_norm": 10.182308197021484,
|
| 1401 |
+
"learning_rate": 6.915103448275862e-05,
|
| 1402 |
+
"loss": 1.5291,
|
| 1403 |
+
"step": 99500
|
| 1404 |
+
},
|
| 1405 |
+
{
|
| 1406 |
+
"epoch": 63.97952655150352,
|
| 1407 |
+
"grad_norm": 14.434243202209473,
|
| 1408 |
+
"learning_rate": 6.897862068965517e-05,
|
| 1409 |
+
"loss": 1.5612,
|
| 1410 |
+
"step": 100000
|
| 1411 |
+
},
|
| 1412 |
+
{
|
| 1413 |
+
"epoch": 64.29942418426104,
|
| 1414 |
+
"grad_norm": 12.513864517211914,
|
| 1415 |
+
"learning_rate": 6.880655172413794e-05,
|
| 1416 |
+
"loss": 1.5041,
|
| 1417 |
+
"step": 100500
|
| 1418 |
+
},
|
| 1419 |
+
{
|
| 1420 |
+
"epoch": 64.61932181701856,
|
| 1421 |
+
"grad_norm": 13.189037322998047,
|
| 1422 |
+
"learning_rate": 6.863413793103448e-05,
|
| 1423 |
+
"loss": 1.5097,
|
| 1424 |
+
"step": 101000
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 64.93921944977608,
|
| 1428 |
+
"grad_norm": 11.867232322692871,
|
| 1429 |
+
"learning_rate": 6.846172413793104e-05,
|
| 1430 |
+
"loss": 1.5401,
|
| 1431 |
+
"step": 101500
|
| 1432 |
+
},
|
| 1433 |
+
{
|
| 1434 |
+
"epoch": 65.25911708253359,
|
| 1435 |
+
"grad_norm": 13.00894832611084,
|
| 1436 |
+
"learning_rate": 6.828931034482758e-05,
|
| 1437 |
+
"loss": 1.4581,
|
| 1438 |
+
"step": 102000
|
| 1439 |
+
},
|
| 1440 |
+
{
|
| 1441 |
+
"epoch": 65.57901471529111,
|
| 1442 |
+
"grad_norm": 11.719345092773438,
|
| 1443 |
+
"learning_rate": 6.811689655172415e-05,
|
| 1444 |
+
"loss": 1.4807,
|
| 1445 |
+
"step": 102500
|
| 1446 |
+
},
|
| 1447 |
+
{
|
| 1448 |
+
"epoch": 65.89891234804863,
|
| 1449 |
+
"grad_norm": 11.355063438415527,
|
| 1450 |
+
"learning_rate": 6.79444827586207e-05,
|
| 1451 |
+
"loss": 1.4892,
|
| 1452 |
+
"step": 103000
|
| 1453 |
+
},
|
| 1454 |
+
{
|
| 1455 |
+
"epoch": 66.21880998080614,
|
| 1456 |
+
"grad_norm": 13.351948738098145,
|
| 1457 |
+
"learning_rate": 6.777241379310345e-05,
|
| 1458 |
+
"loss": 1.4636,
|
| 1459 |
+
"step": 103500
|
| 1460 |
+
},
|
| 1461 |
+
{
|
| 1462 |
+
"epoch": 66.53870761356366,
|
| 1463 |
+
"grad_norm": 15.406342506408691,
|
| 1464 |
+
"learning_rate": 6.76e-05,
|
| 1465 |
+
"loss": 1.4678,
|
| 1466 |
+
"step": 104000
|
| 1467 |
+
},
|
| 1468 |
+
{
|
| 1469 |
+
"epoch": 66.85860524632118,
|
| 1470 |
+
"grad_norm": 14.357329368591309,
|
| 1471 |
+
"learning_rate": 6.742758620689656e-05,
|
| 1472 |
+
"loss": 1.4936,
|
| 1473 |
+
"step": 104500
|
| 1474 |
+
},
|
| 1475 |
+
{
|
| 1476 |
+
"epoch": 67.17850287907869,
|
| 1477 |
+
"grad_norm": 12.275686264038086,
|
| 1478 |
+
"learning_rate": 6.725517241379311e-05,
|
| 1479 |
+
"loss": 1.4566,
|
| 1480 |
+
"step": 105000
|
| 1481 |
+
},
|
| 1482 |
+
{
|
| 1483 |
+
"epoch": 67.49840051183621,
|
| 1484 |
+
"grad_norm": 13.198380470275879,
|
| 1485 |
+
"learning_rate": 6.708310344827586e-05,
|
| 1486 |
+
"loss": 1.4326,
|
| 1487 |
+
"step": 105500
|
| 1488 |
+
},
|
| 1489 |
+
{
|
| 1490 |
+
"epoch": 67.81829814459373,
|
| 1491 |
+
"grad_norm": 13.365631103515625,
|
| 1492 |
+
"learning_rate": 6.691068965517242e-05,
|
| 1493 |
+
"loss": 1.426,
|
| 1494 |
+
"step": 106000
|
| 1495 |
+
},
|
| 1496 |
+
{
|
| 1497 |
+
"epoch": 68.13819577735124,
|
| 1498 |
+
"grad_norm": 14.106985092163086,
|
| 1499 |
+
"learning_rate": 6.673827586206897e-05,
|
| 1500 |
+
"loss": 1.4289,
|
| 1501 |
+
"step": 106500
|
| 1502 |
+
},
|
| 1503 |
+
{
|
| 1504 |
+
"epoch": 68.45809341010876,
|
| 1505 |
+
"grad_norm": 10.076281547546387,
|
| 1506 |
+
"learning_rate": 6.656586206896553e-05,
|
| 1507 |
+
"loss": 1.396,
|
| 1508 |
+
"step": 107000
|
| 1509 |
+
},
|
| 1510 |
+
{
|
| 1511 |
+
"epoch": 68.77799104286628,
|
| 1512 |
+
"grad_norm": 14.63807201385498,
|
| 1513 |
+
"learning_rate": 6.639344827586207e-05,
|
| 1514 |
+
"loss": 1.3979,
|
| 1515 |
+
"step": 107500
|
| 1516 |
+
},
|
| 1517 |
+
{
|
| 1518 |
+
"epoch": 69.0978886756238,
|
| 1519 |
+
"grad_norm": 13.643959045410156,
|
| 1520 |
+
"learning_rate": 6.622137931034483e-05,
|
| 1521 |
+
"loss": 1.4274,
|
| 1522 |
+
"step": 108000
|
| 1523 |
+
},
|
| 1524 |
+
{
|
| 1525 |
+
"epoch": 69.41778630838132,
|
| 1526 |
+
"grad_norm": 11.819470405578613,
|
| 1527 |
+
"learning_rate": 6.604896551724138e-05,
|
| 1528 |
+
"loss": 1.3769,
|
| 1529 |
+
"step": 108500
|
| 1530 |
+
},
|
| 1531 |
+
{
|
| 1532 |
+
"epoch": 69.73768394113884,
|
| 1533 |
+
"grad_norm": 14.33261775970459,
|
| 1534 |
+
"learning_rate": 6.587655172413794e-05,
|
| 1535 |
+
"loss": 1.3825,
|
| 1536 |
+
"step": 109000
|
| 1537 |
+
},
|
| 1538 |
+
{
|
| 1539 |
+
"epoch": 70.05758157389636,
|
| 1540 |
+
"grad_norm": 10.918536186218262,
|
| 1541 |
+
"learning_rate": 6.570413793103448e-05,
|
| 1542 |
+
"loss": 1.3913,
|
| 1543 |
+
"step": 109500
|
| 1544 |
+
},
|
| 1545 |
+
{
|
| 1546 |
+
"epoch": 70.37747920665387,
|
| 1547 |
+
"grad_norm": 13.519926071166992,
|
| 1548 |
+
"learning_rate": 6.553172413793104e-05,
|
| 1549 |
+
"loss": 1.3341,
|
| 1550 |
+
"step": 110000
|
| 1551 |
+
},
|
| 1552 |
+
{
|
| 1553 |
+
"epoch": 70.69737683941139,
|
| 1554 |
+
"grad_norm": 12.5425386428833,
|
| 1555 |
+
"learning_rate": 6.535931034482759e-05,
|
| 1556 |
+
"loss": 1.3828,
|
| 1557 |
+
"step": 110500
|
| 1558 |
+
},
|
| 1559 |
+
{
|
| 1560 |
+
"epoch": 71.0172744721689,
|
| 1561 |
+
"grad_norm": 11.435805320739746,
|
| 1562 |
+
"learning_rate": 6.518724137931035e-05,
|
| 1563 |
+
"loss": 1.3821,
|
| 1564 |
+
"step": 111000
|
| 1565 |
+
},
|
| 1566 |
+
{
|
| 1567 |
+
"epoch": 71.33717210492642,
|
| 1568 |
+
"grad_norm": 12.65505313873291,
|
| 1569 |
+
"learning_rate": 6.501482758620689e-05,
|
| 1570 |
+
"loss": 1.3083,
|
| 1571 |
+
"step": 111500
|
| 1572 |
+
},
|
| 1573 |
+
{
|
| 1574 |
+
"epoch": 71.65706973768394,
|
| 1575 |
+
"grad_norm": 15.489115715026855,
|
| 1576 |
+
"learning_rate": 6.484241379310345e-05,
|
| 1577 |
+
"loss": 1.341,
|
| 1578 |
+
"step": 112000
|
| 1579 |
+
},
|
| 1580 |
+
{
|
| 1581 |
+
"epoch": 71.97696737044146,
|
| 1582 |
+
"grad_norm": 14.14395809173584,
|
| 1583 |
+
"learning_rate": 6.467e-05,
|
| 1584 |
+
"loss": 1.3579,
|
| 1585 |
+
"step": 112500
|
| 1586 |
+
},
|
| 1587 |
+
{
|
| 1588 |
+
"epoch": 72.29686500319897,
|
| 1589 |
+
"grad_norm": 13.708014488220215,
|
| 1590 |
+
"learning_rate": 6.449758620689656e-05,
|
| 1591 |
+
"loss": 1.3032,
|
| 1592 |
+
"step": 113000
|
| 1593 |
+
},
|
| 1594 |
+
{
|
| 1595 |
+
"epoch": 72.61676263595649,
|
| 1596 |
+
"grad_norm": 10.75635814666748,
|
| 1597 |
+
"learning_rate": 6.432551724137932e-05,
|
| 1598 |
+
"loss": 1.3045,
|
| 1599 |
+
"step": 113500
|
| 1600 |
+
},
|
| 1601 |
+
{
|
| 1602 |
+
"epoch": 72.93666026871401,
|
| 1603 |
+
"grad_norm": 12.12192440032959,
|
| 1604 |
+
"learning_rate": 6.415310344827586e-05,
|
| 1605 |
+
"loss": 1.3248,
|
| 1606 |
+
"step": 114000
|
| 1607 |
+
},
|
| 1608 |
+
{
|
| 1609 |
+
"epoch": 73.25655790147152,
|
| 1610 |
+
"grad_norm": 13.368456840515137,
|
| 1611 |
+
"learning_rate": 6.398068965517241e-05,
|
| 1612 |
+
"loss": 1.287,
|
| 1613 |
+
"step": 114500
|
| 1614 |
+
},
|
| 1615 |
+
{
|
| 1616 |
+
"epoch": 73.57645553422904,
|
| 1617 |
+
"grad_norm": 12.584633827209473,
|
| 1618 |
+
"learning_rate": 6.380827586206897e-05,
|
| 1619 |
+
"loss": 1.3015,
|
| 1620 |
+
"step": 115000
|
| 1621 |
+
},
|
| 1622 |
+
{
|
| 1623 |
+
"epoch": 73.89635316698656,
|
| 1624 |
+
"grad_norm": 13.863194465637207,
|
| 1625 |
+
"learning_rate": 6.363620689655173e-05,
|
| 1626 |
+
"loss": 1.2898,
|
| 1627 |
+
"step": 115500
|
| 1628 |
+
},
|
| 1629 |
+
{
|
| 1630 |
+
"epoch": 74.21625079974409,
|
| 1631 |
+
"grad_norm": 12.937112808227539,
|
| 1632 |
+
"learning_rate": 6.346379310344827e-05,
|
| 1633 |
+
"loss": 1.2456,
|
| 1634 |
+
"step": 116000
|
| 1635 |
+
},
|
| 1636 |
+
{
|
| 1637 |
+
"epoch": 74.5361484325016,
|
| 1638 |
+
"grad_norm": 11.274981498718262,
|
| 1639 |
+
"learning_rate": 6.329137931034484e-05,
|
| 1640 |
+
"loss": 1.2689,
|
| 1641 |
+
"step": 116500
|
| 1642 |
+
},
|
| 1643 |
+
{
|
| 1644 |
+
"epoch": 74.85604606525912,
|
| 1645 |
+
"grad_norm": 14.425061225891113,
|
| 1646 |
+
"learning_rate": 6.311896551724138e-05,
|
| 1647 |
+
"loss": 1.2752,
|
| 1648 |
+
"step": 117000
|
| 1649 |
+
},
|
| 1650 |
+
{
|
| 1651 |
+
"epoch": 75.17594369801664,
|
| 1652 |
+
"grad_norm": 11.654635429382324,
|
| 1653 |
+
"learning_rate": 6.294655172413794e-05,
|
| 1654 |
+
"loss": 1.2442,
|
| 1655 |
+
"step": 117500
|
| 1656 |
+
},
|
| 1657 |
+
{
|
| 1658 |
+
"epoch": 75.49584133077416,
|
| 1659 |
+
"grad_norm": 10.00129222869873,
|
| 1660 |
+
"learning_rate": 6.277413793103448e-05,
|
| 1661 |
+
"loss": 1.2506,
|
| 1662 |
+
"step": 118000
|
| 1663 |
+
},
|
| 1664 |
+
{
|
| 1665 |
+
"epoch": 75.81573896353167,
|
| 1666 |
+
"grad_norm": 11.665295600891113,
|
| 1667 |
+
"learning_rate": 6.260206896551725e-05,
|
| 1668 |
+
"loss": 1.2541,
|
| 1669 |
+
"step": 118500
|
| 1670 |
+
},
|
| 1671 |
+
{
|
| 1672 |
+
"epoch": 76.13563659628919,
|
| 1673 |
+
"grad_norm": 10.555766105651855,
|
| 1674 |
+
"learning_rate": 6.24296551724138e-05,
|
| 1675 |
+
"loss": 1.2486,
|
| 1676 |
+
"step": 119000
|
| 1677 |
+
},
|
| 1678 |
+
{
|
| 1679 |
+
"epoch": 76.4555342290467,
|
| 1680 |
+
"grad_norm": 14.879280090332031,
|
| 1681 |
+
"learning_rate": 6.225724137931035e-05,
|
| 1682 |
+
"loss": 1.2124,
|
| 1683 |
+
"step": 119500
|
| 1684 |
+
},
|
| 1685 |
+
{
|
| 1686 |
+
"epoch": 76.77543186180422,
|
| 1687 |
+
"grad_norm": 15.131136894226074,
|
| 1688 |
+
"learning_rate": 6.208482758620689e-05,
|
| 1689 |
+
"loss": 1.2549,
|
| 1690 |
+
"step": 120000
|
| 1691 |
+
}
|
| 1692 |
+
],
|
| 1693 |
+
"logging_steps": 500,
|
| 1694 |
+
"max_steps": 300000,
|
| 1695 |
+
"num_input_tokens_seen": 0,
|
| 1696 |
+
"num_train_epochs": 192,
|
| 1697 |
+
"save_steps": 20000,
|
| 1698 |
+
"stateful_callbacks": {
|
| 1699 |
+
"TrainerControl": {
|
| 1700 |
+
"args": {
|
| 1701 |
+
"should_epoch_stop": false,
|
| 1702 |
+
"should_evaluate": false,
|
| 1703 |
+
"should_log": false,
|
| 1704 |
+
"should_save": true,
|
| 1705 |
+
"should_training_stop": false
|
| 1706 |
+
},
|
| 1707 |
+
"attributes": {}
|
| 1708 |
+
}
|
| 1709 |
+
},
|
| 1710 |
+
"total_flos": 1.3473428330011853e+17,
|
| 1711 |
+
"train_batch_size": 32,
|
| 1712 |
+
"trial_name": null,
|
| 1713 |
+
"trial_params": null
|
| 1714 |
+
}
|
checkpoint-120000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6fad2530f3d27917fbdcc941e3023a8fce21992040aa6f8afe98d384d87efa35
|
| 3 |
+
size 5368
|
checkpoint-120000/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-140000/config.json
ADDED
|
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"RobertaForMaskedLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_probs_dropout_prob": 0.1,
|
| 6 |
+
"bos_token_id": 0,
|
| 7 |
+
"classifier_dropout": null,
|
| 8 |
+
"eos_token_id": 2,
|
| 9 |
+
"hidden_act": "gelu",
|
| 10 |
+
"hidden_dropout_prob": 0.1,
|
| 11 |
+
"hidden_size": 768,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 3072,
|
| 14 |
+
"layer_norm_eps": 1e-12,
|
| 15 |
+
"max_position_embeddings": 514,
|
| 16 |
+
"model_type": "roberta",
|
| 17 |
+
"num_attention_heads": 12,
|
| 18 |
+
"num_hidden_layers": 6,
|
| 19 |
+
"pad_token_id": 1,
|
| 20 |
+
"position_embedding_type": "absolute",
|
| 21 |
+
"torch_dtype": "float32",
|
| 22 |
+
"transformers_version": "4.50.3",
|
| 23 |
+
"type_vocab_size": 1,
|
| 24 |
+
"use_cache": true,
|
| 25 |
+
"vocab_size": 52000
|
| 26 |
+
}
|
checkpoint-140000/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-140000/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:053cd37a0b66921f66dfb546940f1fd65d7b75f9a70bcb8ec1b398091eee2303
|
| 3 |
+
size 334030264
|
checkpoint-140000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3019a72214ee97b0527ed585a82523923fe41a67a047c0cc5ccf15cf2c276486
|
| 3 |
+
size 668124218
|
checkpoint-140000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f15a681a1fc0bf27ccd1c987c61c529d5880fb8db9277c23d5ab555b4f1e8f9a
|
| 3 |
+
size 14244
|
checkpoint-140000/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6d1593f8f97b7a399d40d89a97e8065052942a27a9ea22f1fa955b45052c200b
|
| 3 |
+
size 988
|
checkpoint-140000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4dc21f50f60469db568ea6b9ea271f8a3ca309ab34bdd6f53bf4ea97e76846a4
|
| 3 |
+
size 1064
|
checkpoint-140000/special_tokens_map.json
ADDED
|
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": true,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"cls_token": {
|
| 10 |
+
"content": "<s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": true,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"eos_token": {
|
| 17 |
+
"content": "</s>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": true,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"mask_token": {
|
| 24 |
+
"content": "<mask>",
|
| 25 |
+
"lstrip": true,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"pad_token": {
|
| 31 |
+
"content": "<pad>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": true,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
},
|
| 37 |
+
"sep_token": {
|
| 38 |
+
"content": "</s>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": true,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false
|
| 43 |
+
},
|
| 44 |
+
"unk_token": {
|
| 45 |
+
"content": "<unk>",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": true,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false
|
| 50 |
+
}
|
| 51 |
+
}
|
checkpoint-140000/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-140000/tokenizer_config.json
ADDED
|
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"0": {
|
| 5 |
+
"content": "<s>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": true,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"1": {
|
| 13 |
+
"content": "<pad>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": true,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"2": {
|
| 21 |
+
"content": "</s>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": true,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": true
|
| 27 |
+
},
|
| 28 |
+
"3": {
|
| 29 |
+
"content": "<unk>",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": true,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false,
|
| 34 |
+
"special": true
|
| 35 |
+
},
|
| 36 |
+
"4": {
|
| 37 |
+
"content": "<mask>",
|
| 38 |
+
"lstrip": true,
|
| 39 |
+
"normalized": false,
|
| 40 |
+
"rstrip": false,
|
| 41 |
+
"single_word": false,
|
| 42 |
+
"special": true
|
| 43 |
+
}
|
| 44 |
+
},
|
| 45 |
+
"bos_token": "<s>",
|
| 46 |
+
"clean_up_tokenization_spaces": false,
|
| 47 |
+
"cls_token": "<s>",
|
| 48 |
+
"eos_token": "</s>",
|
| 49 |
+
"errors": "replace",
|
| 50 |
+
"extra_special_tokens": {},
|
| 51 |
+
"mask_token": "<mask>",
|
| 52 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 53 |
+
"pad_token": "<pad>",
|
| 54 |
+
"sep_token": "</s>",
|
| 55 |
+
"tokenizer_class": "RobertaTokenizer",
|
| 56 |
+
"trim_offsets": true,
|
| 57 |
+
"unk_token": "<unk>"
|
| 58 |
+
}
|
checkpoint-140000/trainer_state.json
ADDED
|
@@ -0,0 +1,1994 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 89.57133717210493,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 140000,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.3198976327575176,
|
| 14 |
+
"grad_norm": 4.1601386070251465,
|
| 15 |
+
"learning_rate": 5e-06,
|
| 16 |
+
"loss": 10.3279,
|
| 17 |
+
"step": 500
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.6397952655150352,
|
| 21 |
+
"grad_norm": 4.366061687469482,
|
| 22 |
+
"learning_rate": 1e-05,
|
| 23 |
+
"loss": 9.3834,
|
| 24 |
+
"step": 1000
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.9596928982725528,
|
| 28 |
+
"grad_norm": 4.784337043762207,
|
| 29 |
+
"learning_rate": 1.5e-05,
|
| 30 |
+
"loss": 8.8888,
|
| 31 |
+
"step": 1500
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 1.2795905310300704,
|
| 35 |
+
"grad_norm": 3.9968652725219727,
|
| 36 |
+
"learning_rate": 2e-05,
|
| 37 |
+
"loss": 8.6568,
|
| 38 |
+
"step": 2000
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 1.599488163787588,
|
| 42 |
+
"grad_norm": 4.402552127838135,
|
| 43 |
+
"learning_rate": 2.5e-05,
|
| 44 |
+
"loss": 8.5473,
|
| 45 |
+
"step": 2500
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 1.9193857965451055,
|
| 49 |
+
"grad_norm": 4.639041423797607,
|
| 50 |
+
"learning_rate": 3e-05,
|
| 51 |
+
"loss": 8.4044,
|
| 52 |
+
"step": 3000
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 2.239283429302623,
|
| 56 |
+
"grad_norm": 5.651747226715088,
|
| 57 |
+
"learning_rate": 3.5e-05,
|
| 58 |
+
"loss": 8.2868,
|
| 59 |
+
"step": 3500
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 2.5591810620601407,
|
| 63 |
+
"grad_norm": 4.6999359130859375,
|
| 64 |
+
"learning_rate": 4e-05,
|
| 65 |
+
"loss": 8.1766,
|
| 66 |
+
"step": 4000
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 2.8790786948176583,
|
| 70 |
+
"grad_norm": 4.838181495666504,
|
| 71 |
+
"learning_rate": 4.499e-05,
|
| 72 |
+
"loss": 8.1118,
|
| 73 |
+
"step": 4500
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 3.198976327575176,
|
| 77 |
+
"grad_norm": 4.238831996917725,
|
| 78 |
+
"learning_rate": 4.999e-05,
|
| 79 |
+
"loss": 8.0038,
|
| 80 |
+
"step": 5000
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 3.5188739603326935,
|
| 84 |
+
"grad_norm": 4.455530643463135,
|
| 85 |
+
"learning_rate": 5.499000000000001e-05,
|
| 86 |
+
"loss": 7.9014,
|
| 87 |
+
"step": 5500
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 3.838771593090211,
|
| 91 |
+
"grad_norm": 5.811736583709717,
|
| 92 |
+
"learning_rate": 5.999e-05,
|
| 93 |
+
"loss": 7.8352,
|
| 94 |
+
"step": 6000
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 4.158669225847729,
|
| 98 |
+
"grad_norm": 4.998301982879639,
|
| 99 |
+
"learning_rate": 6.498e-05,
|
| 100 |
+
"loss": 7.7613,
|
| 101 |
+
"step": 6500
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 4.478566858605246,
|
| 105 |
+
"grad_norm": 5.011510848999023,
|
| 106 |
+
"learning_rate": 6.998e-05,
|
| 107 |
+
"loss": 7.6554,
|
| 108 |
+
"step": 7000
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 4.798464491362764,
|
| 112 |
+
"grad_norm": 4.750300884246826,
|
| 113 |
+
"learning_rate": 7.498e-05,
|
| 114 |
+
"loss": 7.6109,
|
| 115 |
+
"step": 7500
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 5.1183621241202815,
|
| 119 |
+
"grad_norm": 6.24017858505249,
|
| 120 |
+
"learning_rate": 7.998e-05,
|
| 121 |
+
"loss": 7.5186,
|
| 122 |
+
"step": 8000
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 5.438259756877799,
|
| 126 |
+
"grad_norm": 6.061458587646484,
|
| 127 |
+
"learning_rate": 8.497000000000001e-05,
|
| 128 |
+
"loss": 7.3966,
|
| 129 |
+
"step": 8500
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 5.758157389635317,
|
| 133 |
+
"grad_norm": 7.151447772979736,
|
| 134 |
+
"learning_rate": 8.997000000000001e-05,
|
| 135 |
+
"loss": 7.2877,
|
| 136 |
+
"step": 9000
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 6.078055022392834,
|
| 140 |
+
"grad_norm": 7.578985214233398,
|
| 141 |
+
"learning_rate": 9.497000000000001e-05,
|
| 142 |
+
"loss": 7.1542,
|
| 143 |
+
"step": 9500
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 6.397952655150352,
|
| 147 |
+
"grad_norm": 5.948920726776123,
|
| 148 |
+
"learning_rate": 9.997e-05,
|
| 149 |
+
"loss": 7.0008,
|
| 150 |
+
"step": 10000
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 6.717850287907869,
|
| 154 |
+
"grad_norm": 8.036959648132324,
|
| 155 |
+
"learning_rate": 9.982896551724137e-05,
|
| 156 |
+
"loss": 6.8966,
|
| 157 |
+
"step": 10500
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 7.037747920665387,
|
| 161 |
+
"grad_norm": 7.160433292388916,
|
| 162 |
+
"learning_rate": 9.965655172413794e-05,
|
| 163 |
+
"loss": 6.7509,
|
| 164 |
+
"step": 11000
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 7.357645553422905,
|
| 168 |
+
"grad_norm": 5.934999465942383,
|
| 169 |
+
"learning_rate": 9.948413793103449e-05,
|
| 170 |
+
"loss": 6.5833,
|
| 171 |
+
"step": 11500
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 7.677543186180422,
|
| 175 |
+
"grad_norm": 7.745622634887695,
|
| 176 |
+
"learning_rate": 9.931172413793104e-05,
|
| 177 |
+
"loss": 6.4975,
|
| 178 |
+
"step": 12000
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 7.99744081893794,
|
| 182 |
+
"grad_norm": 7.0418477058410645,
|
| 183 |
+
"learning_rate": 9.91393103448276e-05,
|
| 184 |
+
"loss": 6.4261,
|
| 185 |
+
"step": 12500
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 8.317338451695457,
|
| 189 |
+
"grad_norm": 6.101259708404541,
|
| 190 |
+
"learning_rate": 9.896689655172414e-05,
|
| 191 |
+
"loss": 6.2092,
|
| 192 |
+
"step": 13000
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 8.637236084452976,
|
| 196 |
+
"grad_norm": 7.289799213409424,
|
| 197 |
+
"learning_rate": 9.87944827586207e-05,
|
| 198 |
+
"loss": 6.1436,
|
| 199 |
+
"step": 13500
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 8.957133717210493,
|
| 203 |
+
"grad_norm": 8.126811027526855,
|
| 204 |
+
"learning_rate": 9.862206896551725e-05,
|
| 205 |
+
"loss": 6.0456,
|
| 206 |
+
"step": 14000
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 9.277031349968011,
|
| 210 |
+
"grad_norm": 8.221816062927246,
|
| 211 |
+
"learning_rate": 9.845000000000001e-05,
|
| 212 |
+
"loss": 5.9141,
|
| 213 |
+
"step": 14500
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 9.596928982725528,
|
| 217 |
+
"grad_norm": 7.361550331115723,
|
| 218 |
+
"learning_rate": 9.827793103448277e-05,
|
| 219 |
+
"loss": 5.8326,
|
| 220 |
+
"step": 15000
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 9.916826615483046,
|
| 224 |
+
"grad_norm": 7.1737775802612305,
|
| 225 |
+
"learning_rate": 9.810551724137932e-05,
|
| 226 |
+
"loss": 5.7974,
|
| 227 |
+
"step": 15500
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 10.236724248240563,
|
| 231 |
+
"grad_norm": 9.80185604095459,
|
| 232 |
+
"learning_rate": 9.793310344827586e-05,
|
| 233 |
+
"loss": 5.6282,
|
| 234 |
+
"step": 16000
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 10.556621880998081,
|
| 238 |
+
"grad_norm": 7.2062153816223145,
|
| 239 |
+
"learning_rate": 9.776068965517242e-05,
|
| 240 |
+
"loss": 5.5619,
|
| 241 |
+
"step": 16500
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 10.876519513755598,
|
| 245 |
+
"grad_norm": 10.801878929138184,
|
| 246 |
+
"learning_rate": 9.758827586206896e-05,
|
| 247 |
+
"loss": 5.5155,
|
| 248 |
+
"step": 17000
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 11.196417146513117,
|
| 252 |
+
"grad_norm": 8.48509693145752,
|
| 253 |
+
"learning_rate": 9.741586206896553e-05,
|
| 254 |
+
"loss": 5.4259,
|
| 255 |
+
"step": 17500
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 11.516314779270633,
|
| 259 |
+
"grad_norm": 8.47572135925293,
|
| 260 |
+
"learning_rate": 9.724344827586207e-05,
|
| 261 |
+
"loss": 5.3205,
|
| 262 |
+
"step": 18000
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 11.836212412028152,
|
| 266 |
+
"grad_norm": 6.122796535491943,
|
| 267 |
+
"learning_rate": 9.707103448275863e-05,
|
| 268 |
+
"loss": 5.3025,
|
| 269 |
+
"step": 18500
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 12.156110044785668,
|
| 273 |
+
"grad_norm": 8.210710525512695,
|
| 274 |
+
"learning_rate": 9.689896551724139e-05,
|
| 275 |
+
"loss": 5.2264,
|
| 276 |
+
"step": 19000
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 12.476007677543187,
|
| 280 |
+
"grad_norm": 7.857537746429443,
|
| 281 |
+
"learning_rate": 9.672655172413794e-05,
|
| 282 |
+
"loss": 5.1395,
|
| 283 |
+
"step": 19500
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 12.795905310300704,
|
| 287 |
+
"grad_norm": 7.743075370788574,
|
| 288 |
+
"learning_rate": 9.655413793103448e-05,
|
| 289 |
+
"loss": 5.1109,
|
| 290 |
+
"step": 20000
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 13.115802943058222,
|
| 294 |
+
"grad_norm": 10.574569702148438,
|
| 295 |
+
"learning_rate": 9.638172413793104e-05,
|
| 296 |
+
"loss": 5.0794,
|
| 297 |
+
"step": 20500
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 13.435700575815739,
|
| 301 |
+
"grad_norm": 8.313858985900879,
|
| 302 |
+
"learning_rate": 9.620931034482758e-05,
|
| 303 |
+
"loss": 4.921,
|
| 304 |
+
"step": 21000
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 13.755598208573257,
|
| 308 |
+
"grad_norm": 9.096057891845703,
|
| 309 |
+
"learning_rate": 9.603689655172414e-05,
|
| 310 |
+
"loss": 4.96,
|
| 311 |
+
"step": 21500
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 14.075495841330774,
|
| 315 |
+
"grad_norm": 8.402993202209473,
|
| 316 |
+
"learning_rate": 9.58644827586207e-05,
|
| 317 |
+
"loss": 4.9062,
|
| 318 |
+
"step": 22000
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 14.395393474088293,
|
| 322 |
+
"grad_norm": 8.110074996948242,
|
| 323 |
+
"learning_rate": 9.569206896551725e-05,
|
| 324 |
+
"loss": 4.8026,
|
| 325 |
+
"step": 22500
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 14.71529110684581,
|
| 329 |
+
"grad_norm": 7.908292293548584,
|
| 330 |
+
"learning_rate": 9.552000000000001e-05,
|
| 331 |
+
"loss": 4.82,
|
| 332 |
+
"step": 23000
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 15.035188739603328,
|
| 336 |
+
"grad_norm": 7.991878986358643,
|
| 337 |
+
"learning_rate": 9.534758620689655e-05,
|
| 338 |
+
"loss": 4.7397,
|
| 339 |
+
"step": 23500
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 15.355086372360844,
|
| 343 |
+
"grad_norm": 8.696029663085938,
|
| 344 |
+
"learning_rate": 9.517551724137932e-05,
|
| 345 |
+
"loss": 4.6656,
|
| 346 |
+
"step": 24000
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 15.674984005118363,
|
| 350 |
+
"grad_norm": 9.421612739562988,
|
| 351 |
+
"learning_rate": 9.500310344827586e-05,
|
| 352 |
+
"loss": 4.6412,
|
| 353 |
+
"step": 24500
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 15.99488163787588,
|
| 357 |
+
"grad_norm": 9.747482299804688,
|
| 358 |
+
"learning_rate": 9.483068965517242e-05,
|
| 359 |
+
"loss": 4.6048,
|
| 360 |
+
"step": 25000
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 16.314779270633398,
|
| 364 |
+
"grad_norm": 10.389492988586426,
|
| 365 |
+
"learning_rate": 9.465827586206897e-05,
|
| 366 |
+
"loss": 4.481,
|
| 367 |
+
"step": 25500
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 16.634676903390915,
|
| 371 |
+
"grad_norm": 8.661949157714844,
|
| 372 |
+
"learning_rate": 9.448586206896553e-05,
|
| 373 |
+
"loss": 4.4923,
|
| 374 |
+
"step": 26000
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 16.95457453614843,
|
| 378 |
+
"grad_norm": 12.681297302246094,
|
| 379 |
+
"learning_rate": 9.431344827586207e-05,
|
| 380 |
+
"loss": 4.4816,
|
| 381 |
+
"step": 26500
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 17.27447216890595,
|
| 385 |
+
"grad_norm": 8.993134498596191,
|
| 386 |
+
"learning_rate": 9.414103448275863e-05,
|
| 387 |
+
"loss": 4.3512,
|
| 388 |
+
"step": 27000
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 17.59436980166347,
|
| 392 |
+
"grad_norm": 10.020146369934082,
|
| 393 |
+
"learning_rate": 9.396862068965517e-05,
|
| 394 |
+
"loss": 4.3447,
|
| 395 |
+
"step": 27500
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 17.914267434420985,
|
| 399 |
+
"grad_norm": 9.514701843261719,
|
| 400 |
+
"learning_rate": 9.379655172413794e-05,
|
| 401 |
+
"loss": 4.3376,
|
| 402 |
+
"step": 28000
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 18.234165067178502,
|
| 406 |
+
"grad_norm": 10.324498176574707,
|
| 407 |
+
"learning_rate": 9.362413793103448e-05,
|
| 408 |
+
"loss": 4.2612,
|
| 409 |
+
"step": 28500
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 18.554062699936022,
|
| 413 |
+
"grad_norm": 10.682856559753418,
|
| 414 |
+
"learning_rate": 9.345172413793104e-05,
|
| 415 |
+
"loss": 4.226,
|
| 416 |
+
"step": 29000
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 18.87396033269354,
|
| 420 |
+
"grad_norm": 7.883260726928711,
|
| 421 |
+
"learning_rate": 9.327931034482758e-05,
|
| 422 |
+
"loss": 4.19,
|
| 423 |
+
"step": 29500
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 19.193857965451055,
|
| 427 |
+
"grad_norm": 12.470623016357422,
|
| 428 |
+
"learning_rate": 9.310724137931035e-05,
|
| 429 |
+
"loss": 4.1881,
|
| 430 |
+
"step": 30000
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 19.513755598208572,
|
| 434 |
+
"grad_norm": 9.932331085205078,
|
| 435 |
+
"learning_rate": 9.29348275862069e-05,
|
| 436 |
+
"loss": 4.0853,
|
| 437 |
+
"step": 30500
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 19.833653230966092,
|
| 441 |
+
"grad_norm": 8.153782844543457,
|
| 442 |
+
"learning_rate": 9.276241379310345e-05,
|
| 443 |
+
"loss": 4.1087,
|
| 444 |
+
"step": 31000
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 20.15355086372361,
|
| 448 |
+
"grad_norm": 8.214093208312988,
|
| 449 |
+
"learning_rate": 9.258999999999999e-05,
|
| 450 |
+
"loss": 4.0751,
|
| 451 |
+
"step": 31500
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 20.473448496481126,
|
| 455 |
+
"grad_norm": 11.927350044250488,
|
| 456 |
+
"learning_rate": 9.241758620689656e-05,
|
| 457 |
+
"loss": 3.9686,
|
| 458 |
+
"step": 32000
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 20.793346129238643,
|
| 462 |
+
"grad_norm": 9.67835807800293,
|
| 463 |
+
"learning_rate": 9.224551724137932e-05,
|
| 464 |
+
"loss": 3.9745,
|
| 465 |
+
"step": 32500
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 21.113243761996163,
|
| 469 |
+
"grad_norm": 9.911735534667969,
|
| 470 |
+
"learning_rate": 9.207310344827586e-05,
|
| 471 |
+
"loss": 3.9308,
|
| 472 |
+
"step": 33000
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 21.43314139475368,
|
| 476 |
+
"grad_norm": 9.05053424835205,
|
| 477 |
+
"learning_rate": 9.190068965517242e-05,
|
| 478 |
+
"loss": 3.8718,
|
| 479 |
+
"step": 33500
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 21.753039027511196,
|
| 483 |
+
"grad_norm": 9.588044166564941,
|
| 484 |
+
"learning_rate": 9.172827586206897e-05,
|
| 485 |
+
"loss": 3.8425,
|
| 486 |
+
"step": 34000
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 22.072936660268713,
|
| 490 |
+
"grad_norm": 8.788230895996094,
|
| 491 |
+
"learning_rate": 9.155620689655173e-05,
|
| 492 |
+
"loss": 3.8617,
|
| 493 |
+
"step": 34500
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 22.392834293026233,
|
| 497 |
+
"grad_norm": 9.435895919799805,
|
| 498 |
+
"learning_rate": 9.138379310344827e-05,
|
| 499 |
+
"loss": 3.7524,
|
| 500 |
+
"step": 35000
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 22.71273192578375,
|
| 504 |
+
"grad_norm": 9.870182037353516,
|
| 505 |
+
"learning_rate": 9.121137931034483e-05,
|
| 506 |
+
"loss": 3.7916,
|
| 507 |
+
"step": 35500
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 23.032629558541267,
|
| 511 |
+
"grad_norm": 9.612881660461426,
|
| 512 |
+
"learning_rate": 9.103896551724139e-05,
|
| 513 |
+
"loss": 3.8011,
|
| 514 |
+
"step": 36000
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 23.352527191298783,
|
| 518 |
+
"grad_norm": 9.643827438354492,
|
| 519 |
+
"learning_rate": 9.086689655172414e-05,
|
| 520 |
+
"loss": 3.6478,
|
| 521 |
+
"step": 36500
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 23.672424824056304,
|
| 525 |
+
"grad_norm": 14.105424880981445,
|
| 526 |
+
"learning_rate": 9.069448275862069e-05,
|
| 527 |
+
"loss": 3.6671,
|
| 528 |
+
"step": 37000
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 23.99232245681382,
|
| 532 |
+
"grad_norm": 10.427962303161621,
|
| 533 |
+
"learning_rate": 9.052206896551724e-05,
|
| 534 |
+
"loss": 3.6809,
|
| 535 |
+
"step": 37500
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 24.312220089571337,
|
| 539 |
+
"grad_norm": 11.505946159362793,
|
| 540 |
+
"learning_rate": 9.03496551724138e-05,
|
| 541 |
+
"loss": 3.553,
|
| 542 |
+
"step": 38000
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 24.632117722328854,
|
| 546 |
+
"grad_norm": 10.393635749816895,
|
| 547 |
+
"learning_rate": 9.017724137931035e-05,
|
| 548 |
+
"loss": 3.5408,
|
| 549 |
+
"step": 38500
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 24.952015355086374,
|
| 553 |
+
"grad_norm": 9.023842811584473,
|
| 554 |
+
"learning_rate": 9.00051724137931e-05,
|
| 555 |
+
"loss": 3.5915,
|
| 556 |
+
"step": 39000
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 25.27191298784389,
|
| 560 |
+
"grad_norm": 10.69048023223877,
|
| 561 |
+
"learning_rate": 8.983275862068967e-05,
|
| 562 |
+
"loss": 3.4896,
|
| 563 |
+
"step": 39500
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 25.591810620601407,
|
| 567 |
+
"grad_norm": 10.803936958312988,
|
| 568 |
+
"learning_rate": 8.966034482758621e-05,
|
| 569 |
+
"loss": 3.4854,
|
| 570 |
+
"step": 40000
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 25.911708253358924,
|
| 574 |
+
"grad_norm": 10.489801406860352,
|
| 575 |
+
"learning_rate": 8.948793103448276e-05,
|
| 576 |
+
"loss": 3.4871,
|
| 577 |
+
"step": 40500
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 26.231605886116444,
|
| 581 |
+
"grad_norm": 10.558309555053711,
|
| 582 |
+
"learning_rate": 8.931586206896552e-05,
|
| 583 |
+
"loss": 3.4186,
|
| 584 |
+
"step": 41000
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 26.55150351887396,
|
| 588 |
+
"grad_norm": 12.186748504638672,
|
| 589 |
+
"learning_rate": 8.914344827586208e-05,
|
| 590 |
+
"loss": 3.4027,
|
| 591 |
+
"step": 41500
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 26.871401151631478,
|
| 595 |
+
"grad_norm": 9.8623046875,
|
| 596 |
+
"learning_rate": 8.897103448275862e-05,
|
| 597 |
+
"loss": 3.4191,
|
| 598 |
+
"step": 42000
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 27.191298784388994,
|
| 602 |
+
"grad_norm": 11.407792091369629,
|
| 603 |
+
"learning_rate": 8.879862068965518e-05,
|
| 604 |
+
"loss": 3.341,
|
| 605 |
+
"step": 42500
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 27.511196417146515,
|
| 609 |
+
"grad_norm": 13.37617301940918,
|
| 610 |
+
"learning_rate": 8.862655172413794e-05,
|
| 611 |
+
"loss": 3.3137,
|
| 612 |
+
"step": 43000
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 27.83109404990403,
|
| 616 |
+
"grad_norm": 10.30826187133789,
|
| 617 |
+
"learning_rate": 8.845413793103449e-05,
|
| 618 |
+
"loss": 3.3036,
|
| 619 |
+
"step": 43500
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 28.150991682661548,
|
| 623 |
+
"grad_norm": 12.024778366088867,
|
| 624 |
+
"learning_rate": 8.828172413793105e-05,
|
| 625 |
+
"loss": 3.2678,
|
| 626 |
+
"step": 44000
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 28.470889315419065,
|
| 630 |
+
"grad_norm": 9.730340957641602,
|
| 631 |
+
"learning_rate": 8.810931034482759e-05,
|
| 632 |
+
"loss": 3.1949,
|
| 633 |
+
"step": 44500
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 28.790786948176585,
|
| 637 |
+
"grad_norm": 9.700602531433105,
|
| 638 |
+
"learning_rate": 8.793689655172414e-05,
|
| 639 |
+
"loss": 3.2541,
|
| 640 |
+
"step": 45000
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 29.1106845809341,
|
| 644 |
+
"grad_norm": 12.359143257141113,
|
| 645 |
+
"learning_rate": 8.77648275862069e-05,
|
| 646 |
+
"loss": 3.2456,
|
| 647 |
+
"step": 45500
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 29.43058221369162,
|
| 651 |
+
"grad_norm": 11.989018440246582,
|
| 652 |
+
"learning_rate": 8.759241379310346e-05,
|
| 653 |
+
"loss": 3.1154,
|
| 654 |
+
"step": 46000
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 29.750479846449135,
|
| 658 |
+
"grad_norm": 10.904190063476562,
|
| 659 |
+
"learning_rate": 8.742e-05,
|
| 660 |
+
"loss": 3.175,
|
| 661 |
+
"step": 46500
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 30.070377479206655,
|
| 665 |
+
"grad_norm": 11.253949165344238,
|
| 666 |
+
"learning_rate": 8.724758620689656e-05,
|
| 667 |
+
"loss": 3.1478,
|
| 668 |
+
"step": 47000
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 30.390275111964172,
|
| 672 |
+
"grad_norm": 12.229791641235352,
|
| 673 |
+
"learning_rate": 8.707517241379311e-05,
|
| 674 |
+
"loss": 3.0632,
|
| 675 |
+
"step": 47500
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 30.71017274472169,
|
| 679 |
+
"grad_norm": 9.516524314880371,
|
| 680 |
+
"learning_rate": 8.690275862068967e-05,
|
| 681 |
+
"loss": 3.0843,
|
| 682 |
+
"step": 48000
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 31.030070377479205,
|
| 686 |
+
"grad_norm": 13.730731010437012,
|
| 687 |
+
"learning_rate": 8.673034482758621e-05,
|
| 688 |
+
"loss": 3.098,
|
| 689 |
+
"step": 48500
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 31.349968010236726,
|
| 693 |
+
"grad_norm": 9.73539924621582,
|
| 694 |
+
"learning_rate": 8.655827586206897e-05,
|
| 695 |
+
"loss": 2.9611,
|
| 696 |
+
"step": 49000
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 31.669865642994242,
|
| 700 |
+
"grad_norm": 12.066815376281738,
|
| 701 |
+
"learning_rate": 8.638586206896552e-05,
|
| 702 |
+
"loss": 2.9943,
|
| 703 |
+
"step": 49500
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 31.98976327575176,
|
| 707 |
+
"grad_norm": 11.028585433959961,
|
| 708 |
+
"learning_rate": 8.621344827586208e-05,
|
| 709 |
+
"loss": 3.0424,
|
| 710 |
+
"step": 50000
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 32.30966090850928,
|
| 714 |
+
"grad_norm": 11.2380952835083,
|
| 715 |
+
"learning_rate": 8.604103448275862e-05,
|
| 716 |
+
"loss": 2.9023,
|
| 717 |
+
"step": 50500
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 32.629558541266796,
|
| 721 |
+
"grad_norm": 9.345772743225098,
|
| 722 |
+
"learning_rate": 8.586862068965518e-05,
|
| 723 |
+
"loss": 2.9586,
|
| 724 |
+
"step": 51000
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 32.94945617402431,
|
| 728 |
+
"grad_norm": 10.239849090576172,
|
| 729 |
+
"learning_rate": 8.569655172413793e-05,
|
| 730 |
+
"loss": 2.9461,
|
| 731 |
+
"step": 51500
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 33.26935380678183,
|
| 735 |
+
"grad_norm": 11.058523178100586,
|
| 736 |
+
"learning_rate": 8.552413793103449e-05,
|
| 737 |
+
"loss": 2.8453,
|
| 738 |
+
"step": 52000
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 33.589251439539346,
|
| 742 |
+
"grad_norm": 12.131317138671875,
|
| 743 |
+
"learning_rate": 8.535172413793105e-05,
|
| 744 |
+
"loss": 2.8603,
|
| 745 |
+
"step": 52500
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 33.90914907229686,
|
| 749 |
+
"grad_norm": 10.392476081848145,
|
| 750 |
+
"learning_rate": 8.517931034482759e-05,
|
| 751 |
+
"loss": 2.8817,
|
| 752 |
+
"step": 53000
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 34.22904670505438,
|
| 756 |
+
"grad_norm": 10.749021530151367,
|
| 757 |
+
"learning_rate": 8.500724137931036e-05,
|
| 758 |
+
"loss": 2.8073,
|
| 759 |
+
"step": 53500
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 34.5489443378119,
|
| 763 |
+
"grad_norm": 12.33171558380127,
|
| 764 |
+
"learning_rate": 8.48348275862069e-05,
|
| 765 |
+
"loss": 2.7793,
|
| 766 |
+
"step": 54000
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 34.86884197056942,
|
| 770 |
+
"grad_norm": 12.961758613586426,
|
| 771 |
+
"learning_rate": 8.466241379310346e-05,
|
| 772 |
+
"loss": 2.8066,
|
| 773 |
+
"step": 54500
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 35.18873960332694,
|
| 777 |
+
"grad_norm": 13.320075035095215,
|
| 778 |
+
"learning_rate": 8.449e-05,
|
| 779 |
+
"loss": 2.7459,
|
| 780 |
+
"step": 55000
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 35.50863723608445,
|
| 784 |
+
"grad_norm": 14.416489601135254,
|
| 785 |
+
"learning_rate": 8.431758620689655e-05,
|
| 786 |
+
"loss": 2.7321,
|
| 787 |
+
"step": 55500
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 35.82853486884197,
|
| 791 |
+
"grad_norm": 11.203073501586914,
|
| 792 |
+
"learning_rate": 8.414551724137931e-05,
|
| 793 |
+
"loss": 2.7486,
|
| 794 |
+
"step": 56000
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 36.14843250159949,
|
| 798 |
+
"grad_norm": 10.463476181030273,
|
| 799 |
+
"learning_rate": 8.397310344827587e-05,
|
| 800 |
+
"loss": 2.7086,
|
| 801 |
+
"step": 56500
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 36.468330134357004,
|
| 805 |
+
"grad_norm": 11.375761985778809,
|
| 806 |
+
"learning_rate": 8.380068965517241e-05,
|
| 807 |
+
"loss": 2.6387,
|
| 808 |
+
"step": 57000
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 36.78822776711452,
|
| 812 |
+
"grad_norm": 11.649105072021484,
|
| 813 |
+
"learning_rate": 8.362827586206897e-05,
|
| 814 |
+
"loss": 2.6746,
|
| 815 |
+
"step": 57500
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 37.108125399872044,
|
| 819 |
+
"grad_norm": 12.708244323730469,
|
| 820 |
+
"learning_rate": 8.345586206896552e-05,
|
| 821 |
+
"loss": 2.6454,
|
| 822 |
+
"step": 58000
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 37.42802303262956,
|
| 826 |
+
"grad_norm": 12.876201629638672,
|
| 827 |
+
"learning_rate": 8.328344827586208e-05,
|
| 828 |
+
"loss": 2.5798,
|
| 829 |
+
"step": 58500
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 37.74792066538708,
|
| 833 |
+
"grad_norm": 11.92346477508545,
|
| 834 |
+
"learning_rate": 8.311103448275862e-05,
|
| 835 |
+
"loss": 2.6589,
|
| 836 |
+
"step": 59000
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 38.067818298144594,
|
| 840 |
+
"grad_norm": 10.742238998413086,
|
| 841 |
+
"learning_rate": 8.293896551724138e-05,
|
| 842 |
+
"loss": 2.5868,
|
| 843 |
+
"step": 59500
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 38.38771593090211,
|
| 847 |
+
"grad_norm": 11.399048805236816,
|
| 848 |
+
"learning_rate": 8.276655172413793e-05,
|
| 849 |
+
"loss": 2.5124,
|
| 850 |
+
"step": 60000
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 38.70761356365963,
|
| 854 |
+
"grad_norm": 13.563875198364258,
|
| 855 |
+
"learning_rate": 8.259413793103449e-05,
|
| 856 |
+
"loss": 2.576,
|
| 857 |
+
"step": 60500
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 39.027511196417144,
|
| 861 |
+
"grad_norm": 11.297135353088379,
|
| 862 |
+
"learning_rate": 8.242172413793103e-05,
|
| 863 |
+
"loss": 2.5671,
|
| 864 |
+
"step": 61000
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 39.34740882917466,
|
| 868 |
+
"grad_norm": 11.336121559143066,
|
| 869 |
+
"learning_rate": 8.22496551724138e-05,
|
| 870 |
+
"loss": 2.4445,
|
| 871 |
+
"step": 61500
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 39.667306461932185,
|
| 875 |
+
"grad_norm": 9.477692604064941,
|
| 876 |
+
"learning_rate": 8.207724137931035e-05,
|
| 877 |
+
"loss": 2.4981,
|
| 878 |
+
"step": 62000
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 39.9872040946897,
|
| 882 |
+
"grad_norm": 11.597848892211914,
|
| 883 |
+
"learning_rate": 8.19048275862069e-05,
|
| 884 |
+
"loss": 2.5382,
|
| 885 |
+
"step": 62500
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 40.30710172744722,
|
| 889 |
+
"grad_norm": 14.910037994384766,
|
| 890 |
+
"learning_rate": 8.173241379310346e-05,
|
| 891 |
+
"loss": 2.4158,
|
| 892 |
+
"step": 63000
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 40.626999360204735,
|
| 896 |
+
"grad_norm": 11.870673179626465,
|
| 897 |
+
"learning_rate": 8.156e-05,
|
| 898 |
+
"loss": 2.4395,
|
| 899 |
+
"step": 63500
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 40.94689699296225,
|
| 903 |
+
"grad_norm": 15.279576301574707,
|
| 904 |
+
"learning_rate": 8.138758620689655e-05,
|
| 905 |
+
"loss": 2.4653,
|
| 906 |
+
"step": 64000
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 41.26679462571977,
|
| 910 |
+
"grad_norm": 11.710406303405762,
|
| 911 |
+
"learning_rate": 8.121551724137931e-05,
|
| 912 |
+
"loss": 2.3567,
|
| 913 |
+
"step": 64500
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 41.586692258477285,
|
| 917 |
+
"grad_norm": 10.663411140441895,
|
| 918 |
+
"learning_rate": 8.104310344827587e-05,
|
| 919 |
+
"loss": 2.3655,
|
| 920 |
+
"step": 65000
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 41.9065898912348,
|
| 924 |
+
"grad_norm": 13.946629524230957,
|
| 925 |
+
"learning_rate": 8.087068965517241e-05,
|
| 926 |
+
"loss": 2.4336,
|
| 927 |
+
"step": 65500
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 42.226487523992326,
|
| 931 |
+
"grad_norm": 13.782262802124023,
|
| 932 |
+
"learning_rate": 8.069827586206898e-05,
|
| 933 |
+
"loss": 2.3351,
|
| 934 |
+
"step": 66000
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 42.54638515674984,
|
| 938 |
+
"grad_norm": 11.177961349487305,
|
| 939 |
+
"learning_rate": 8.052586206896552e-05,
|
| 940 |
+
"loss": 2.359,
|
| 941 |
+
"step": 66500
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 42.86628278950736,
|
| 945 |
+
"grad_norm": 15.120301246643066,
|
| 946 |
+
"learning_rate": 8.035344827586208e-05,
|
| 947 |
+
"loss": 2.355,
|
| 948 |
+
"step": 67000
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 43.186180422264876,
|
| 952 |
+
"grad_norm": 10.805267333984375,
|
| 953 |
+
"learning_rate": 8.018103448275862e-05,
|
| 954 |
+
"loss": 2.2905,
|
| 955 |
+
"step": 67500
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 43.50607805502239,
|
| 959 |
+
"grad_norm": 11.777176856994629,
|
| 960 |
+
"learning_rate": 8.000862068965517e-05,
|
| 961 |
+
"loss": 2.2906,
|
| 962 |
+
"step": 68000
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 43.82597568777991,
|
| 966 |
+
"grad_norm": 15.457807540893555,
|
| 967 |
+
"learning_rate": 7.983689655172414e-05,
|
| 968 |
+
"loss": 2.3269,
|
| 969 |
+
"step": 68500
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 44.145873320537426,
|
| 973 |
+
"grad_norm": 11.639357566833496,
|
| 974 |
+
"learning_rate": 7.966448275862069e-05,
|
| 975 |
+
"loss": 2.2371,
|
| 976 |
+
"step": 69000
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 44.46577095329494,
|
| 980 |
+
"grad_norm": 11.710591316223145,
|
| 981 |
+
"learning_rate": 7.949206896551725e-05,
|
| 982 |
+
"loss": 2.2248,
|
| 983 |
+
"step": 69500
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 44.785668586052466,
|
| 987 |
+
"grad_norm": 12.675103187561035,
|
| 988 |
+
"learning_rate": 7.93196551724138e-05,
|
| 989 |
+
"loss": 2.2586,
|
| 990 |
+
"step": 70000
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 45.10556621880998,
|
| 994 |
+
"grad_norm": 12.752120971679688,
|
| 995 |
+
"learning_rate": 7.914724137931034e-05,
|
| 996 |
+
"loss": 2.2489,
|
| 997 |
+
"step": 70500
|
| 998 |
+
},
|
| 999 |
+
{
|
| 1000 |
+
"epoch": 45.4254638515675,
|
| 1001 |
+
"grad_norm": 11.379339218139648,
|
| 1002 |
+
"learning_rate": 7.89751724137931e-05,
|
| 1003 |
+
"loss": 2.1774,
|
| 1004 |
+
"step": 71000
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 45.74536148432502,
|
| 1008 |
+
"grad_norm": 12.76633358001709,
|
| 1009 |
+
"learning_rate": 7.880275862068966e-05,
|
| 1010 |
+
"loss": 2.2007,
|
| 1011 |
+
"step": 71500
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 46.06525911708253,
|
| 1015 |
+
"grad_norm": 11.421367645263672,
|
| 1016 |
+
"learning_rate": 7.863034482758621e-05,
|
| 1017 |
+
"loss": 2.2262,
|
| 1018 |
+
"step": 72000
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"epoch": 46.38515674984005,
|
| 1022 |
+
"grad_norm": 14.81748104095459,
|
| 1023 |
+
"learning_rate": 7.845793103448277e-05,
|
| 1024 |
+
"loss": 2.101,
|
| 1025 |
+
"step": 72500
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 46.70505438259757,
|
| 1029 |
+
"grad_norm": 12.902971267700195,
|
| 1030 |
+
"learning_rate": 7.828551724137931e-05,
|
| 1031 |
+
"loss": 2.1568,
|
| 1032 |
+
"step": 73000
|
| 1033 |
+
},
|
| 1034 |
+
{
|
| 1035 |
+
"epoch": 47.02495201535508,
|
| 1036 |
+
"grad_norm": 10.685113906860352,
|
| 1037 |
+
"learning_rate": 7.811310344827587e-05,
|
| 1038 |
+
"loss": 2.1655,
|
| 1039 |
+
"step": 73500
|
| 1040 |
+
},
|
| 1041 |
+
{
|
| 1042 |
+
"epoch": 47.34484964811261,
|
| 1043 |
+
"grad_norm": 15.892518043518066,
|
| 1044 |
+
"learning_rate": 7.794068965517242e-05,
|
| 1045 |
+
"loss": 2.0551,
|
| 1046 |
+
"step": 74000
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 47.664747280870124,
|
| 1050 |
+
"grad_norm": 13.730358123779297,
|
| 1051 |
+
"learning_rate": 7.776862068965518e-05,
|
| 1052 |
+
"loss": 2.1053,
|
| 1053 |
+
"step": 74500
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 47.98464491362764,
|
| 1057 |
+
"grad_norm": 13.635787963867188,
|
| 1058 |
+
"learning_rate": 7.759620689655172e-05,
|
| 1059 |
+
"loss": 2.1408,
|
| 1060 |
+
"step": 75000
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"epoch": 48.30454254638516,
|
| 1064 |
+
"grad_norm": 12.861611366271973,
|
| 1065 |
+
"learning_rate": 7.742379310344828e-05,
|
| 1066 |
+
"loss": 2.0104,
|
| 1067 |
+
"step": 75500
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"epoch": 48.624440179142674,
|
| 1071 |
+
"grad_norm": 11.84931468963623,
|
| 1072 |
+
"learning_rate": 7.725137931034483e-05,
|
| 1073 |
+
"loss": 2.0555,
|
| 1074 |
+
"step": 76000
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 48.94433781190019,
|
| 1078 |
+
"grad_norm": 15.812765121459961,
|
| 1079 |
+
"learning_rate": 7.70793103448276e-05,
|
| 1080 |
+
"loss": 2.1087,
|
| 1081 |
+
"step": 76500
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 49.26423544465771,
|
| 1085 |
+
"grad_norm": 14.233431816101074,
|
| 1086 |
+
"learning_rate": 7.690689655172414e-05,
|
| 1087 |
+
"loss": 1.9998,
|
| 1088 |
+
"step": 77000
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 49.584133077415224,
|
| 1092 |
+
"grad_norm": 14.329803466796875,
|
| 1093 |
+
"learning_rate": 7.673448275862069e-05,
|
| 1094 |
+
"loss": 2.0189,
|
| 1095 |
+
"step": 77500
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 49.90403071017275,
|
| 1099 |
+
"grad_norm": 11.00400161743164,
|
| 1100 |
+
"learning_rate": 7.656206896551725e-05,
|
| 1101 |
+
"loss": 2.059,
|
| 1102 |
+
"step": 78000
|
| 1103 |
+
},
|
| 1104 |
+
{
|
| 1105 |
+
"epoch": 50.223928342930265,
|
| 1106 |
+
"grad_norm": 13.582133293151855,
|
| 1107 |
+
"learning_rate": 7.63896551724138e-05,
|
| 1108 |
+
"loss": 1.9753,
|
| 1109 |
+
"step": 78500
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 50.54382597568778,
|
| 1113 |
+
"grad_norm": 12.560907363891602,
|
| 1114 |
+
"learning_rate": 7.621724137931034e-05,
|
| 1115 |
+
"loss": 1.9759,
|
| 1116 |
+
"step": 79000
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 50.8637236084453,
|
| 1120 |
+
"grad_norm": 12.169915199279785,
|
| 1121 |
+
"learning_rate": 7.60451724137931e-05,
|
| 1122 |
+
"loss": 1.9944,
|
| 1123 |
+
"step": 79500
|
| 1124 |
+
},
|
| 1125 |
+
{
|
| 1126 |
+
"epoch": 51.183621241202815,
|
| 1127 |
+
"grad_norm": 13.5604248046875,
|
| 1128 |
+
"learning_rate": 7.587275862068966e-05,
|
| 1129 |
+
"loss": 1.9323,
|
| 1130 |
+
"step": 80000
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 51.50351887396033,
|
| 1134 |
+
"grad_norm": 15.892741203308105,
|
| 1135 |
+
"learning_rate": 7.570034482758621e-05,
|
| 1136 |
+
"loss": 1.9095,
|
| 1137 |
+
"step": 80500
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 51.82341650671785,
|
| 1141 |
+
"grad_norm": 13.435209274291992,
|
| 1142 |
+
"learning_rate": 7.552793103448276e-05,
|
| 1143 |
+
"loss": 1.9508,
|
| 1144 |
+
"step": 81000
|
| 1145 |
+
},
|
| 1146 |
+
{
|
| 1147 |
+
"epoch": 52.143314139475365,
|
| 1148 |
+
"grad_norm": 11.180010795593262,
|
| 1149 |
+
"learning_rate": 7.535586206896551e-05,
|
| 1150 |
+
"loss": 1.9216,
|
| 1151 |
+
"step": 81500
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 52.46321177223289,
|
| 1155 |
+
"grad_norm": 12.792661666870117,
|
| 1156 |
+
"learning_rate": 7.518344827586207e-05,
|
| 1157 |
+
"loss": 1.8817,
|
| 1158 |
+
"step": 82000
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"epoch": 52.783109404990405,
|
| 1162 |
+
"grad_norm": 11.785886764526367,
|
| 1163 |
+
"learning_rate": 7.501103448275863e-05,
|
| 1164 |
+
"loss": 1.9121,
|
| 1165 |
+
"step": 82500
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"epoch": 53.10300703774792,
|
| 1169 |
+
"grad_norm": 10.568120002746582,
|
| 1170 |
+
"learning_rate": 7.483862068965518e-05,
|
| 1171 |
+
"loss": 1.8885,
|
| 1172 |
+
"step": 83000
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 53.42290467050544,
|
| 1176 |
+
"grad_norm": 14.641459465026855,
|
| 1177 |
+
"learning_rate": 7.466620689655172e-05,
|
| 1178 |
+
"loss": 1.8357,
|
| 1179 |
+
"step": 83500
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 53.742802303262955,
|
| 1183 |
+
"grad_norm": 13.5363187789917,
|
| 1184 |
+
"learning_rate": 7.449379310344828e-05,
|
| 1185 |
+
"loss": 1.8515,
|
| 1186 |
+
"step": 84000
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 54.06269993602047,
|
| 1190 |
+
"grad_norm": 12.997908592224121,
|
| 1191 |
+
"learning_rate": 7.432172413793104e-05,
|
| 1192 |
+
"loss": 1.8681,
|
| 1193 |
+
"step": 84500
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 54.38259756877799,
|
| 1197 |
+
"grad_norm": 12.53503131866455,
|
| 1198 |
+
"learning_rate": 7.414931034482759e-05,
|
| 1199 |
+
"loss": 1.7785,
|
| 1200 |
+
"step": 85000
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 54.702495201535505,
|
| 1204 |
+
"grad_norm": 11.986194610595703,
|
| 1205 |
+
"learning_rate": 7.397689655172413e-05,
|
| 1206 |
+
"loss": 1.8507,
|
| 1207 |
+
"step": 85500
|
| 1208 |
+
},
|
| 1209 |
+
{
|
| 1210 |
+
"epoch": 55.02239283429303,
|
| 1211 |
+
"grad_norm": 12.089723587036133,
|
| 1212 |
+
"learning_rate": 7.380448275862069e-05,
|
| 1213 |
+
"loss": 1.8537,
|
| 1214 |
+
"step": 86000
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 55.342290467050546,
|
| 1218 |
+
"grad_norm": 13.552453994750977,
|
| 1219 |
+
"learning_rate": 7.363206896551725e-05,
|
| 1220 |
+
"loss": 1.7622,
|
| 1221 |
+
"step": 86500
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 55.66218809980806,
|
| 1225 |
+
"grad_norm": 12.03878116607666,
|
| 1226 |
+
"learning_rate": 7.346e-05,
|
| 1227 |
+
"loss": 1.8076,
|
| 1228 |
+
"step": 87000
|
| 1229 |
+
},
|
| 1230 |
+
{
|
| 1231 |
+
"epoch": 55.98208573256558,
|
| 1232 |
+
"grad_norm": 11.187782287597656,
|
| 1233 |
+
"learning_rate": 7.328758620689655e-05,
|
| 1234 |
+
"loss": 1.8241,
|
| 1235 |
+
"step": 87500
|
| 1236 |
+
},
|
| 1237 |
+
{
|
| 1238 |
+
"epoch": 56.301983365323096,
|
| 1239 |
+
"grad_norm": 14.924737930297852,
|
| 1240 |
+
"learning_rate": 7.311517241379312e-05,
|
| 1241 |
+
"loss": 1.7077,
|
| 1242 |
+
"step": 88000
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"epoch": 56.62188099808061,
|
| 1246 |
+
"grad_norm": 12.302467346191406,
|
| 1247 |
+
"learning_rate": 7.294275862068966e-05,
|
| 1248 |
+
"loss": 1.74,
|
| 1249 |
+
"step": 88500
|
| 1250 |
+
},
|
| 1251 |
+
{
|
| 1252 |
+
"epoch": 56.94177863083813,
|
| 1253 |
+
"grad_norm": 10.834394454956055,
|
| 1254 |
+
"learning_rate": 7.277034482758621e-05,
|
| 1255 |
+
"loss": 1.7827,
|
| 1256 |
+
"step": 89000
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 57.261676263595646,
|
| 1260 |
+
"grad_norm": 14.356012344360352,
|
| 1261 |
+
"learning_rate": 7.259793103448276e-05,
|
| 1262 |
+
"loss": 1.7082,
|
| 1263 |
+
"step": 89500
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 57.58157389635317,
|
| 1267 |
+
"grad_norm": 14.632678031921387,
|
| 1268 |
+
"learning_rate": 7.242551724137931e-05,
|
| 1269 |
+
"loss": 1.7045,
|
| 1270 |
+
"step": 90000
|
| 1271 |
+
},
|
| 1272 |
+
{
|
| 1273 |
+
"epoch": 57.90147152911069,
|
| 1274 |
+
"grad_norm": 13.501043319702148,
|
| 1275 |
+
"learning_rate": 7.225344827586207e-05,
|
| 1276 |
+
"loss": 1.7522,
|
| 1277 |
+
"step": 90500
|
| 1278 |
+
},
|
| 1279 |
+
{
|
| 1280 |
+
"epoch": 58.2213691618682,
|
| 1281 |
+
"grad_norm": 18.839614868164062,
|
| 1282 |
+
"learning_rate": 7.208103448275862e-05,
|
| 1283 |
+
"loss": 1.6801,
|
| 1284 |
+
"step": 91000
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 58.54126679462572,
|
| 1288 |
+
"grad_norm": 13.41618824005127,
|
| 1289 |
+
"learning_rate": 7.190862068965517e-05,
|
| 1290 |
+
"loss": 1.7005,
|
| 1291 |
+
"step": 91500
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 58.86116442738324,
|
| 1295 |
+
"grad_norm": 12.56169605255127,
|
| 1296 |
+
"learning_rate": 7.173620689655172e-05,
|
| 1297 |
+
"loss": 1.7018,
|
| 1298 |
+
"step": 92000
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 59.18106206014075,
|
| 1302 |
+
"grad_norm": 13.447467803955078,
|
| 1303 |
+
"learning_rate": 7.15641379310345e-05,
|
| 1304 |
+
"loss": 1.6691,
|
| 1305 |
+
"step": 92500
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 59.50095969289827,
|
| 1309 |
+
"grad_norm": 12.452493667602539,
|
| 1310 |
+
"learning_rate": 7.139172413793104e-05,
|
| 1311 |
+
"loss": 1.651,
|
| 1312 |
+
"step": 93000
|
| 1313 |
+
},
|
| 1314 |
+
{
|
| 1315 |
+
"epoch": 59.82085732565579,
|
| 1316 |
+
"grad_norm": 10.552214622497559,
|
| 1317 |
+
"learning_rate": 7.121931034482759e-05,
|
| 1318 |
+
"loss": 1.6916,
|
| 1319 |
+
"step": 93500
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 60.14075495841331,
|
| 1323 |
+
"grad_norm": 11.099422454833984,
|
| 1324 |
+
"learning_rate": 7.104689655172413e-05,
|
| 1325 |
+
"loss": 1.6716,
|
| 1326 |
+
"step": 94000
|
| 1327 |
+
},
|
| 1328 |
+
{
|
| 1329 |
+
"epoch": 60.46065259117083,
|
| 1330 |
+
"grad_norm": 13.663276672363281,
|
| 1331 |
+
"learning_rate": 7.08744827586207e-05,
|
| 1332 |
+
"loss": 1.6105,
|
| 1333 |
+
"step": 94500
|
| 1334 |
+
},
|
| 1335 |
+
{
|
| 1336 |
+
"epoch": 60.780550223928344,
|
| 1337 |
+
"grad_norm": 11.783934593200684,
|
| 1338 |
+
"learning_rate": 7.070206896551725e-05,
|
| 1339 |
+
"loss": 1.6399,
|
| 1340 |
+
"step": 95000
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"epoch": 61.10044785668586,
|
| 1344 |
+
"grad_norm": 12.881340026855469,
|
| 1345 |
+
"learning_rate": 7.053e-05,
|
| 1346 |
+
"loss": 1.6058,
|
| 1347 |
+
"step": 95500
|
| 1348 |
+
},
|
| 1349 |
+
{
|
| 1350 |
+
"epoch": 61.42034548944338,
|
| 1351 |
+
"grad_norm": 12.405476570129395,
|
| 1352 |
+
"learning_rate": 7.035758620689656e-05,
|
| 1353 |
+
"loss": 1.5703,
|
| 1354 |
+
"step": 96000
|
| 1355 |
+
},
|
| 1356 |
+
{
|
| 1357 |
+
"epoch": 61.740243122200894,
|
| 1358 |
+
"grad_norm": 11.660452842712402,
|
| 1359 |
+
"learning_rate": 7.018517241379311e-05,
|
| 1360 |
+
"loss": 1.6002,
|
| 1361 |
+
"step": 96500
|
| 1362 |
+
},
|
| 1363 |
+
{
|
| 1364 |
+
"epoch": 62.06014075495841,
|
| 1365 |
+
"grad_norm": 11.69723892211914,
|
| 1366 |
+
"learning_rate": 7.001275862068966e-05,
|
| 1367 |
+
"loss": 1.6186,
|
| 1368 |
+
"step": 97000
|
| 1369 |
+
},
|
| 1370 |
+
{
|
| 1371 |
+
"epoch": 62.38003838771593,
|
| 1372 |
+
"grad_norm": 16.210947036743164,
|
| 1373 |
+
"learning_rate": 6.984034482758621e-05,
|
| 1374 |
+
"loss": 1.5663,
|
| 1375 |
+
"step": 97500
|
| 1376 |
+
},
|
| 1377 |
+
{
|
| 1378 |
+
"epoch": 62.69993602047345,
|
| 1379 |
+
"grad_norm": 11.853803634643555,
|
| 1380 |
+
"learning_rate": 6.966827586206897e-05,
|
| 1381 |
+
"loss": 1.5744,
|
| 1382 |
+
"step": 98000
|
| 1383 |
+
},
|
| 1384 |
+
{
|
| 1385 |
+
"epoch": 63.01983365323097,
|
| 1386 |
+
"grad_norm": 10.565818786621094,
|
| 1387 |
+
"learning_rate": 6.949586206896553e-05,
|
| 1388 |
+
"loss": 1.5829,
|
| 1389 |
+
"step": 98500
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 63.339731285988485,
|
| 1393 |
+
"grad_norm": 11.621013641357422,
|
| 1394 |
+
"learning_rate": 6.932344827586207e-05,
|
| 1395 |
+
"loss": 1.5213,
|
| 1396 |
+
"step": 99000
|
| 1397 |
+
},
|
| 1398 |
+
{
|
| 1399 |
+
"epoch": 63.659628918746,
|
| 1400 |
+
"grad_norm": 10.182308197021484,
|
| 1401 |
+
"learning_rate": 6.915103448275862e-05,
|
| 1402 |
+
"loss": 1.5291,
|
| 1403 |
+
"step": 99500
|
| 1404 |
+
},
|
| 1405 |
+
{
|
| 1406 |
+
"epoch": 63.97952655150352,
|
| 1407 |
+
"grad_norm": 14.434243202209473,
|
| 1408 |
+
"learning_rate": 6.897862068965517e-05,
|
| 1409 |
+
"loss": 1.5612,
|
| 1410 |
+
"step": 100000
|
| 1411 |
+
},
|
| 1412 |
+
{
|
| 1413 |
+
"epoch": 64.29942418426104,
|
| 1414 |
+
"grad_norm": 12.513864517211914,
|
| 1415 |
+
"learning_rate": 6.880655172413794e-05,
|
| 1416 |
+
"loss": 1.5041,
|
| 1417 |
+
"step": 100500
|
| 1418 |
+
},
|
| 1419 |
+
{
|
| 1420 |
+
"epoch": 64.61932181701856,
|
| 1421 |
+
"grad_norm": 13.189037322998047,
|
| 1422 |
+
"learning_rate": 6.863413793103448e-05,
|
| 1423 |
+
"loss": 1.5097,
|
| 1424 |
+
"step": 101000
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 64.93921944977608,
|
| 1428 |
+
"grad_norm": 11.867232322692871,
|
| 1429 |
+
"learning_rate": 6.846172413793104e-05,
|
| 1430 |
+
"loss": 1.5401,
|
| 1431 |
+
"step": 101500
|
| 1432 |
+
},
|
| 1433 |
+
{
|
| 1434 |
+
"epoch": 65.25911708253359,
|
| 1435 |
+
"grad_norm": 13.00894832611084,
|
| 1436 |
+
"learning_rate": 6.828931034482758e-05,
|
| 1437 |
+
"loss": 1.4581,
|
| 1438 |
+
"step": 102000
|
| 1439 |
+
},
|
| 1440 |
+
{
|
| 1441 |
+
"epoch": 65.57901471529111,
|
| 1442 |
+
"grad_norm": 11.719345092773438,
|
| 1443 |
+
"learning_rate": 6.811689655172415e-05,
|
| 1444 |
+
"loss": 1.4807,
|
| 1445 |
+
"step": 102500
|
| 1446 |
+
},
|
| 1447 |
+
{
|
| 1448 |
+
"epoch": 65.89891234804863,
|
| 1449 |
+
"grad_norm": 11.355063438415527,
|
| 1450 |
+
"learning_rate": 6.79444827586207e-05,
|
| 1451 |
+
"loss": 1.4892,
|
| 1452 |
+
"step": 103000
|
| 1453 |
+
},
|
| 1454 |
+
{
|
| 1455 |
+
"epoch": 66.21880998080614,
|
| 1456 |
+
"grad_norm": 13.351948738098145,
|
| 1457 |
+
"learning_rate": 6.777241379310345e-05,
|
| 1458 |
+
"loss": 1.4636,
|
| 1459 |
+
"step": 103500
|
| 1460 |
+
},
|
| 1461 |
+
{
|
| 1462 |
+
"epoch": 66.53870761356366,
|
| 1463 |
+
"grad_norm": 15.406342506408691,
|
| 1464 |
+
"learning_rate": 6.76e-05,
|
| 1465 |
+
"loss": 1.4678,
|
| 1466 |
+
"step": 104000
|
| 1467 |
+
},
|
| 1468 |
+
{
|
| 1469 |
+
"epoch": 66.85860524632118,
|
| 1470 |
+
"grad_norm": 14.357329368591309,
|
| 1471 |
+
"learning_rate": 6.742758620689656e-05,
|
| 1472 |
+
"loss": 1.4936,
|
| 1473 |
+
"step": 104500
|
| 1474 |
+
},
|
| 1475 |
+
{
|
| 1476 |
+
"epoch": 67.17850287907869,
|
| 1477 |
+
"grad_norm": 12.275686264038086,
|
| 1478 |
+
"learning_rate": 6.725517241379311e-05,
|
| 1479 |
+
"loss": 1.4566,
|
| 1480 |
+
"step": 105000
|
| 1481 |
+
},
|
| 1482 |
+
{
|
| 1483 |
+
"epoch": 67.49840051183621,
|
| 1484 |
+
"grad_norm": 13.198380470275879,
|
| 1485 |
+
"learning_rate": 6.708310344827586e-05,
|
| 1486 |
+
"loss": 1.4326,
|
| 1487 |
+
"step": 105500
|
| 1488 |
+
},
|
| 1489 |
+
{
|
| 1490 |
+
"epoch": 67.81829814459373,
|
| 1491 |
+
"grad_norm": 13.365631103515625,
|
| 1492 |
+
"learning_rate": 6.691068965517242e-05,
|
| 1493 |
+
"loss": 1.426,
|
| 1494 |
+
"step": 106000
|
| 1495 |
+
},
|
| 1496 |
+
{
|
| 1497 |
+
"epoch": 68.13819577735124,
|
| 1498 |
+
"grad_norm": 14.106985092163086,
|
| 1499 |
+
"learning_rate": 6.673827586206897e-05,
|
| 1500 |
+
"loss": 1.4289,
|
| 1501 |
+
"step": 106500
|
| 1502 |
+
},
|
| 1503 |
+
{
|
| 1504 |
+
"epoch": 68.45809341010876,
|
| 1505 |
+
"grad_norm": 10.076281547546387,
|
| 1506 |
+
"learning_rate": 6.656586206896553e-05,
|
| 1507 |
+
"loss": 1.396,
|
| 1508 |
+
"step": 107000
|
| 1509 |
+
},
|
| 1510 |
+
{
|
| 1511 |
+
"epoch": 68.77799104286628,
|
| 1512 |
+
"grad_norm": 14.63807201385498,
|
| 1513 |
+
"learning_rate": 6.639344827586207e-05,
|
| 1514 |
+
"loss": 1.3979,
|
| 1515 |
+
"step": 107500
|
| 1516 |
+
},
|
| 1517 |
+
{
|
| 1518 |
+
"epoch": 69.0978886756238,
|
| 1519 |
+
"grad_norm": 13.643959045410156,
|
| 1520 |
+
"learning_rate": 6.622137931034483e-05,
|
| 1521 |
+
"loss": 1.4274,
|
| 1522 |
+
"step": 108000
|
| 1523 |
+
},
|
| 1524 |
+
{
|
| 1525 |
+
"epoch": 69.41778630838132,
|
| 1526 |
+
"grad_norm": 11.819470405578613,
|
| 1527 |
+
"learning_rate": 6.604896551724138e-05,
|
| 1528 |
+
"loss": 1.3769,
|
| 1529 |
+
"step": 108500
|
| 1530 |
+
},
|
| 1531 |
+
{
|
| 1532 |
+
"epoch": 69.73768394113884,
|
| 1533 |
+
"grad_norm": 14.33261775970459,
|
| 1534 |
+
"learning_rate": 6.587655172413794e-05,
|
| 1535 |
+
"loss": 1.3825,
|
| 1536 |
+
"step": 109000
|
| 1537 |
+
},
|
| 1538 |
+
{
|
| 1539 |
+
"epoch": 70.05758157389636,
|
| 1540 |
+
"grad_norm": 10.918536186218262,
|
| 1541 |
+
"learning_rate": 6.570413793103448e-05,
|
| 1542 |
+
"loss": 1.3913,
|
| 1543 |
+
"step": 109500
|
| 1544 |
+
},
|
| 1545 |
+
{
|
| 1546 |
+
"epoch": 70.37747920665387,
|
| 1547 |
+
"grad_norm": 13.519926071166992,
|
| 1548 |
+
"learning_rate": 6.553172413793104e-05,
|
| 1549 |
+
"loss": 1.3341,
|
| 1550 |
+
"step": 110000
|
| 1551 |
+
},
|
| 1552 |
+
{
|
| 1553 |
+
"epoch": 70.69737683941139,
|
| 1554 |
+
"grad_norm": 12.5425386428833,
|
| 1555 |
+
"learning_rate": 6.535931034482759e-05,
|
| 1556 |
+
"loss": 1.3828,
|
| 1557 |
+
"step": 110500
|
| 1558 |
+
},
|
| 1559 |
+
{
|
| 1560 |
+
"epoch": 71.0172744721689,
|
| 1561 |
+
"grad_norm": 11.435805320739746,
|
| 1562 |
+
"learning_rate": 6.518724137931035e-05,
|
| 1563 |
+
"loss": 1.3821,
|
| 1564 |
+
"step": 111000
|
| 1565 |
+
},
|
| 1566 |
+
{
|
| 1567 |
+
"epoch": 71.33717210492642,
|
| 1568 |
+
"grad_norm": 12.65505313873291,
|
| 1569 |
+
"learning_rate": 6.501482758620689e-05,
|
| 1570 |
+
"loss": 1.3083,
|
| 1571 |
+
"step": 111500
|
| 1572 |
+
},
|
| 1573 |
+
{
|
| 1574 |
+
"epoch": 71.65706973768394,
|
| 1575 |
+
"grad_norm": 15.489115715026855,
|
| 1576 |
+
"learning_rate": 6.484241379310345e-05,
|
| 1577 |
+
"loss": 1.341,
|
| 1578 |
+
"step": 112000
|
| 1579 |
+
},
|
| 1580 |
+
{
|
| 1581 |
+
"epoch": 71.97696737044146,
|
| 1582 |
+
"grad_norm": 14.14395809173584,
|
| 1583 |
+
"learning_rate": 6.467e-05,
|
| 1584 |
+
"loss": 1.3579,
|
| 1585 |
+
"step": 112500
|
| 1586 |
+
},
|
| 1587 |
+
{
|
| 1588 |
+
"epoch": 72.29686500319897,
|
| 1589 |
+
"grad_norm": 13.708014488220215,
|
| 1590 |
+
"learning_rate": 6.449758620689656e-05,
|
| 1591 |
+
"loss": 1.3032,
|
| 1592 |
+
"step": 113000
|
| 1593 |
+
},
|
| 1594 |
+
{
|
| 1595 |
+
"epoch": 72.61676263595649,
|
| 1596 |
+
"grad_norm": 10.75635814666748,
|
| 1597 |
+
"learning_rate": 6.432551724137932e-05,
|
| 1598 |
+
"loss": 1.3045,
|
| 1599 |
+
"step": 113500
|
| 1600 |
+
},
|
| 1601 |
+
{
|
| 1602 |
+
"epoch": 72.93666026871401,
|
| 1603 |
+
"grad_norm": 12.12192440032959,
|
| 1604 |
+
"learning_rate": 6.415310344827586e-05,
|
| 1605 |
+
"loss": 1.3248,
|
| 1606 |
+
"step": 114000
|
| 1607 |
+
},
|
| 1608 |
+
{
|
| 1609 |
+
"epoch": 73.25655790147152,
|
| 1610 |
+
"grad_norm": 13.368456840515137,
|
| 1611 |
+
"learning_rate": 6.398068965517241e-05,
|
| 1612 |
+
"loss": 1.287,
|
| 1613 |
+
"step": 114500
|
| 1614 |
+
},
|
| 1615 |
+
{
|
| 1616 |
+
"epoch": 73.57645553422904,
|
| 1617 |
+
"grad_norm": 12.584633827209473,
|
| 1618 |
+
"learning_rate": 6.380827586206897e-05,
|
| 1619 |
+
"loss": 1.3015,
|
| 1620 |
+
"step": 115000
|
| 1621 |
+
},
|
| 1622 |
+
{
|
| 1623 |
+
"epoch": 73.89635316698656,
|
| 1624 |
+
"grad_norm": 13.863194465637207,
|
| 1625 |
+
"learning_rate": 6.363620689655173e-05,
|
| 1626 |
+
"loss": 1.2898,
|
| 1627 |
+
"step": 115500
|
| 1628 |
+
},
|
| 1629 |
+
{
|
| 1630 |
+
"epoch": 74.21625079974409,
|
| 1631 |
+
"grad_norm": 12.937112808227539,
|
| 1632 |
+
"learning_rate": 6.346379310344827e-05,
|
| 1633 |
+
"loss": 1.2456,
|
| 1634 |
+
"step": 116000
|
| 1635 |
+
},
|
| 1636 |
+
{
|
| 1637 |
+
"epoch": 74.5361484325016,
|
| 1638 |
+
"grad_norm": 11.274981498718262,
|
| 1639 |
+
"learning_rate": 6.329137931034484e-05,
|
| 1640 |
+
"loss": 1.2689,
|
| 1641 |
+
"step": 116500
|
| 1642 |
+
},
|
| 1643 |
+
{
|
| 1644 |
+
"epoch": 74.85604606525912,
|
| 1645 |
+
"grad_norm": 14.425061225891113,
|
| 1646 |
+
"learning_rate": 6.311896551724138e-05,
|
| 1647 |
+
"loss": 1.2752,
|
| 1648 |
+
"step": 117000
|
| 1649 |
+
},
|
| 1650 |
+
{
|
| 1651 |
+
"epoch": 75.17594369801664,
|
| 1652 |
+
"grad_norm": 11.654635429382324,
|
| 1653 |
+
"learning_rate": 6.294655172413794e-05,
|
| 1654 |
+
"loss": 1.2442,
|
| 1655 |
+
"step": 117500
|
| 1656 |
+
},
|
| 1657 |
+
{
|
| 1658 |
+
"epoch": 75.49584133077416,
|
| 1659 |
+
"grad_norm": 10.00129222869873,
|
| 1660 |
+
"learning_rate": 6.277413793103448e-05,
|
| 1661 |
+
"loss": 1.2506,
|
| 1662 |
+
"step": 118000
|
| 1663 |
+
},
|
| 1664 |
+
{
|
| 1665 |
+
"epoch": 75.81573896353167,
|
| 1666 |
+
"grad_norm": 11.665295600891113,
|
| 1667 |
+
"learning_rate": 6.260206896551725e-05,
|
| 1668 |
+
"loss": 1.2541,
|
| 1669 |
+
"step": 118500
|
| 1670 |
+
},
|
| 1671 |
+
{
|
| 1672 |
+
"epoch": 76.13563659628919,
|
| 1673 |
+
"grad_norm": 10.555766105651855,
|
| 1674 |
+
"learning_rate": 6.24296551724138e-05,
|
| 1675 |
+
"loss": 1.2486,
|
| 1676 |
+
"step": 119000
|
| 1677 |
+
},
|
| 1678 |
+
{
|
| 1679 |
+
"epoch": 76.4555342290467,
|
| 1680 |
+
"grad_norm": 14.879280090332031,
|
| 1681 |
+
"learning_rate": 6.225724137931035e-05,
|
| 1682 |
+
"loss": 1.2124,
|
| 1683 |
+
"step": 119500
|
| 1684 |
+
},
|
| 1685 |
+
{
|
| 1686 |
+
"epoch": 76.77543186180422,
|
| 1687 |
+
"grad_norm": 15.131136894226074,
|
| 1688 |
+
"learning_rate": 6.208482758620689e-05,
|
| 1689 |
+
"loss": 1.2549,
|
| 1690 |
+
"step": 120000
|
| 1691 |
+
},
|
| 1692 |
+
{
|
| 1693 |
+
"epoch": 77.09532949456174,
|
| 1694 |
+
"grad_norm": 9.889472961425781,
|
| 1695 |
+
"learning_rate": 6.191241379310345e-05,
|
| 1696 |
+
"loss": 1.2376,
|
| 1697 |
+
"step": 120500
|
| 1698 |
+
},
|
| 1699 |
+
{
|
| 1700 |
+
"epoch": 77.41522712731926,
|
| 1701 |
+
"grad_norm": 11.307145118713379,
|
| 1702 |
+
"learning_rate": 6.174e-05,
|
| 1703 |
+
"loss": 1.1958,
|
| 1704 |
+
"step": 121000
|
| 1705 |
+
},
|
| 1706 |
+
{
|
| 1707 |
+
"epoch": 77.73512476007677,
|
| 1708 |
+
"grad_norm": 14.303799629211426,
|
| 1709 |
+
"learning_rate": 6.156758620689656e-05,
|
| 1710 |
+
"loss": 1.2009,
|
| 1711 |
+
"step": 121500
|
| 1712 |
+
},
|
| 1713 |
+
{
|
| 1714 |
+
"epoch": 78.05502239283429,
|
| 1715 |
+
"grad_norm": 11.318217277526855,
|
| 1716 |
+
"learning_rate": 6.139517241379311e-05,
|
| 1717 |
+
"loss": 1.2215,
|
| 1718 |
+
"step": 122000
|
| 1719 |
+
},
|
| 1720 |
+
{
|
| 1721 |
+
"epoch": 78.3749200255918,
|
| 1722 |
+
"grad_norm": 13.979291915893555,
|
| 1723 |
+
"learning_rate": 6.122310344827586e-05,
|
| 1724 |
+
"loss": 1.1713,
|
| 1725 |
+
"step": 122500
|
| 1726 |
+
},
|
| 1727 |
+
{
|
| 1728 |
+
"epoch": 78.69481765834932,
|
| 1729 |
+
"grad_norm": 12.78084945678711,
|
| 1730 |
+
"learning_rate": 6.105103448275863e-05,
|
| 1731 |
+
"loss": 1.1901,
|
| 1732 |
+
"step": 123000
|
| 1733 |
+
},
|
| 1734 |
+
{
|
| 1735 |
+
"epoch": 79.01471529110684,
|
| 1736 |
+
"grad_norm": 10.332459449768066,
|
| 1737 |
+
"learning_rate": 6.087862068965517e-05,
|
| 1738 |
+
"loss": 1.2141,
|
| 1739 |
+
"step": 123500
|
| 1740 |
+
},
|
| 1741 |
+
{
|
| 1742 |
+
"epoch": 79.33461292386437,
|
| 1743 |
+
"grad_norm": 11.179670333862305,
|
| 1744 |
+
"learning_rate": 6.0706206896551735e-05,
|
| 1745 |
+
"loss": 1.1641,
|
| 1746 |
+
"step": 124000
|
| 1747 |
+
},
|
| 1748 |
+
{
|
| 1749 |
+
"epoch": 79.65451055662189,
|
| 1750 |
+
"grad_norm": 12.706995964050293,
|
| 1751 |
+
"learning_rate": 6.053379310344828e-05,
|
| 1752 |
+
"loss": 1.1887,
|
| 1753 |
+
"step": 124500
|
| 1754 |
+
},
|
| 1755 |
+
{
|
| 1756 |
+
"epoch": 79.9744081893794,
|
| 1757 |
+
"grad_norm": 12.575511932373047,
|
| 1758 |
+
"learning_rate": 6.036137931034483e-05,
|
| 1759 |
+
"loss": 1.1994,
|
| 1760 |
+
"step": 125000
|
| 1761 |
+
},
|
| 1762 |
+
{
|
| 1763 |
+
"epoch": 80.29430582213692,
|
| 1764 |
+
"grad_norm": 11.299592971801758,
|
| 1765 |
+
"learning_rate": 6.0189310344827584e-05,
|
| 1766 |
+
"loss": 1.1535,
|
| 1767 |
+
"step": 125500
|
| 1768 |
+
},
|
| 1769 |
+
{
|
| 1770 |
+
"epoch": 80.61420345489444,
|
| 1771 |
+
"grad_norm": 9.741961479187012,
|
| 1772 |
+
"learning_rate": 6.0016896551724147e-05,
|
| 1773 |
+
"loss": 1.1508,
|
| 1774 |
+
"step": 126000
|
| 1775 |
+
},
|
| 1776 |
+
{
|
| 1777 |
+
"epoch": 80.93410108765195,
|
| 1778 |
+
"grad_norm": 13.86517333984375,
|
| 1779 |
+
"learning_rate": 5.984448275862069e-05,
|
| 1780 |
+
"loss": 1.1453,
|
| 1781 |
+
"step": 126500
|
| 1782 |
+
},
|
| 1783 |
+
{
|
| 1784 |
+
"epoch": 81.25399872040947,
|
| 1785 |
+
"grad_norm": 12.810471534729004,
|
| 1786 |
+
"learning_rate": 5.9672068965517244e-05,
|
| 1787 |
+
"loss": 1.131,
|
| 1788 |
+
"step": 127000
|
| 1789 |
+
},
|
| 1790 |
+
{
|
| 1791 |
+
"epoch": 81.57389635316699,
|
| 1792 |
+
"grad_norm": 11.828211784362793,
|
| 1793 |
+
"learning_rate": 5.949965517241379e-05,
|
| 1794 |
+
"loss": 1.1462,
|
| 1795 |
+
"step": 127500
|
| 1796 |
+
},
|
| 1797 |
+
{
|
| 1798 |
+
"epoch": 81.8937939859245,
|
| 1799 |
+
"grad_norm": 13.588178634643555,
|
| 1800 |
+
"learning_rate": 5.932724137931035e-05,
|
| 1801 |
+
"loss": 1.1519,
|
| 1802 |
+
"step": 128000
|
| 1803 |
+
},
|
| 1804 |
+
{
|
| 1805 |
+
"epoch": 82.21369161868202,
|
| 1806 |
+
"grad_norm": 13.903426170349121,
|
| 1807 |
+
"learning_rate": 5.91548275862069e-05,
|
| 1808 |
+
"loss": 1.1222,
|
| 1809 |
+
"step": 128500
|
| 1810 |
+
},
|
| 1811 |
+
{
|
| 1812 |
+
"epoch": 82.53358925143954,
|
| 1813 |
+
"grad_norm": 13.447443962097168,
|
| 1814 |
+
"learning_rate": 5.898275862068966e-05,
|
| 1815 |
+
"loss": 1.1173,
|
| 1816 |
+
"step": 129000
|
| 1817 |
+
},
|
| 1818 |
+
{
|
| 1819 |
+
"epoch": 82.85348688419705,
|
| 1820 |
+
"grad_norm": 12.132195472717285,
|
| 1821 |
+
"learning_rate": 5.8810344827586205e-05,
|
| 1822 |
+
"loss": 1.1262,
|
| 1823 |
+
"step": 129500
|
| 1824 |
+
},
|
| 1825 |
+
{
|
| 1826 |
+
"epoch": 83.17338451695457,
|
| 1827 |
+
"grad_norm": 11.170686721801758,
|
| 1828 |
+
"learning_rate": 5.863793103448276e-05,
|
| 1829 |
+
"loss": 1.0957,
|
| 1830 |
+
"step": 130000
|
| 1831 |
+
},
|
| 1832 |
+
{
|
| 1833 |
+
"epoch": 83.49328214971209,
|
| 1834 |
+
"grad_norm": 12.57539176940918,
|
| 1835 |
+
"learning_rate": 5.846551724137931e-05,
|
| 1836 |
+
"loss": 1.0862,
|
| 1837 |
+
"step": 130500
|
| 1838 |
+
},
|
| 1839 |
+
{
|
| 1840 |
+
"epoch": 83.8131797824696,
|
| 1841 |
+
"grad_norm": 14.212547302246094,
|
| 1842 |
+
"learning_rate": 5.8293448275862074e-05,
|
| 1843 |
+
"loss": 1.0929,
|
| 1844 |
+
"step": 131000
|
| 1845 |
+
},
|
| 1846 |
+
{
|
| 1847 |
+
"epoch": 84.13307741522712,
|
| 1848 |
+
"grad_norm": 14.803600311279297,
|
| 1849 |
+
"learning_rate": 5.8121034482758616e-05,
|
| 1850 |
+
"loss": 1.0948,
|
| 1851 |
+
"step": 131500
|
| 1852 |
+
},
|
| 1853 |
+
{
|
| 1854 |
+
"epoch": 84.45297504798465,
|
| 1855 |
+
"grad_norm": 19.55899429321289,
|
| 1856 |
+
"learning_rate": 5.794862068965518e-05,
|
| 1857 |
+
"loss": 1.0788,
|
| 1858 |
+
"step": 132000
|
| 1859 |
+
},
|
| 1860 |
+
{
|
| 1861 |
+
"epoch": 84.77287268074217,
|
| 1862 |
+
"grad_norm": 11.086203575134277,
|
| 1863 |
+
"learning_rate": 5.7776206896551734e-05,
|
| 1864 |
+
"loss": 1.098,
|
| 1865 |
+
"step": 132500
|
| 1866 |
+
},
|
| 1867 |
+
{
|
| 1868 |
+
"epoch": 85.09277031349968,
|
| 1869 |
+
"grad_norm": 10.74999713897705,
|
| 1870 |
+
"learning_rate": 5.7603793103448276e-05,
|
| 1871 |
+
"loss": 1.0649,
|
| 1872 |
+
"step": 133000
|
| 1873 |
+
},
|
| 1874 |
+
{
|
| 1875 |
+
"epoch": 85.4126679462572,
|
| 1876 |
+
"grad_norm": 14.409449577331543,
|
| 1877 |
+
"learning_rate": 5.743137931034484e-05,
|
| 1878 |
+
"loss": 1.0592,
|
| 1879 |
+
"step": 133500
|
| 1880 |
+
},
|
| 1881 |
+
{
|
| 1882 |
+
"epoch": 85.73256557901472,
|
| 1883 |
+
"grad_norm": 10.215742111206055,
|
| 1884 |
+
"learning_rate": 5.725931034482759e-05,
|
| 1885 |
+
"loss": 1.0765,
|
| 1886 |
+
"step": 134000
|
| 1887 |
+
},
|
| 1888 |
+
{
|
| 1889 |
+
"epoch": 86.05246321177223,
|
| 1890 |
+
"grad_norm": 12.911944389343262,
|
| 1891 |
+
"learning_rate": 5.7086896551724146e-05,
|
| 1892 |
+
"loss": 1.0504,
|
| 1893 |
+
"step": 134500
|
| 1894 |
+
},
|
| 1895 |
+
{
|
| 1896 |
+
"epoch": 86.37236084452975,
|
| 1897 |
+
"grad_norm": 14.987035751342773,
|
| 1898 |
+
"learning_rate": 5.691448275862069e-05,
|
| 1899 |
+
"loss": 1.0141,
|
| 1900 |
+
"step": 135000
|
| 1901 |
+
},
|
| 1902 |
+
{
|
| 1903 |
+
"epoch": 86.69225847728727,
|
| 1904 |
+
"grad_norm": 11.989995002746582,
|
| 1905 |
+
"learning_rate": 5.674206896551725e-05,
|
| 1906 |
+
"loss": 1.0431,
|
| 1907 |
+
"step": 135500
|
| 1908 |
+
},
|
| 1909 |
+
{
|
| 1910 |
+
"epoch": 87.01215611004478,
|
| 1911 |
+
"grad_norm": 12.771849632263184,
|
| 1912 |
+
"learning_rate": 5.657e-05,
|
| 1913 |
+
"loss": 1.054,
|
| 1914 |
+
"step": 136000
|
| 1915 |
+
},
|
| 1916 |
+
{
|
| 1917 |
+
"epoch": 87.3320537428023,
|
| 1918 |
+
"grad_norm": 13.398333549499512,
|
| 1919 |
+
"learning_rate": 5.639758620689656e-05,
|
| 1920 |
+
"loss": 0.9984,
|
| 1921 |
+
"step": 136500
|
| 1922 |
+
},
|
| 1923 |
+
{
|
| 1924 |
+
"epoch": 87.65195137555982,
|
| 1925 |
+
"grad_norm": 10.814030647277832,
|
| 1926 |
+
"learning_rate": 5.6225172413793106e-05,
|
| 1927 |
+
"loss": 1.0283,
|
| 1928 |
+
"step": 137000
|
| 1929 |
+
},
|
| 1930 |
+
{
|
| 1931 |
+
"epoch": 87.97184900831734,
|
| 1932 |
+
"grad_norm": 12.13095760345459,
|
| 1933 |
+
"learning_rate": 5.605275862068966e-05,
|
| 1934 |
+
"loss": 1.0414,
|
| 1935 |
+
"step": 137500
|
| 1936 |
+
},
|
| 1937 |
+
{
|
| 1938 |
+
"epoch": 88.29174664107485,
|
| 1939 |
+
"grad_norm": 12.733049392700195,
|
| 1940 |
+
"learning_rate": 5.5880344827586204e-05,
|
| 1941 |
+
"loss": 1.0087,
|
| 1942 |
+
"step": 138000
|
| 1943 |
+
},
|
| 1944 |
+
{
|
| 1945 |
+
"epoch": 88.61164427383237,
|
| 1946 |
+
"grad_norm": 16.555213928222656,
|
| 1947 |
+
"learning_rate": 5.570827586206897e-05,
|
| 1948 |
+
"loss": 1.0062,
|
| 1949 |
+
"step": 138500
|
| 1950 |
+
},
|
| 1951 |
+
{
|
| 1952 |
+
"epoch": 88.93154190658989,
|
| 1953 |
+
"grad_norm": 11.025595664978027,
|
| 1954 |
+
"learning_rate": 5.553586206896552e-05,
|
| 1955 |
+
"loss": 1.0212,
|
| 1956 |
+
"step": 139000
|
| 1957 |
+
},
|
| 1958 |
+
{
|
| 1959 |
+
"epoch": 89.2514395393474,
|
| 1960 |
+
"grad_norm": 9.93308162689209,
|
| 1961 |
+
"learning_rate": 5.5363448275862074e-05,
|
| 1962 |
+
"loss": 0.998,
|
| 1963 |
+
"step": 139500
|
| 1964 |
+
},
|
| 1965 |
+
{
|
| 1966 |
+
"epoch": 89.57133717210493,
|
| 1967 |
+
"grad_norm": 14.131500244140625,
|
| 1968 |
+
"learning_rate": 5.519103448275862e-05,
|
| 1969 |
+
"loss": 0.9797,
|
| 1970 |
+
"step": 140000
|
| 1971 |
+
}
|
| 1972 |
+
],
|
| 1973 |
+
"logging_steps": 500,
|
| 1974 |
+
"max_steps": 300000,
|
| 1975 |
+
"num_input_tokens_seen": 0,
|
| 1976 |
+
"num_train_epochs": 192,
|
| 1977 |
+
"save_steps": 20000,
|
| 1978 |
+
"stateful_callbacks": {
|
| 1979 |
+
"TrainerControl": {
|
| 1980 |
+
"args": {
|
| 1981 |
+
"should_epoch_stop": false,
|
| 1982 |
+
"should_evaluate": false,
|
| 1983 |
+
"should_log": false,
|
| 1984 |
+
"should_save": true,
|
| 1985 |
+
"should_training_stop": false
|
| 1986 |
+
},
|
| 1987 |
+
"attributes": {}
|
| 1988 |
+
}
|
| 1989 |
+
},
|
| 1990 |
+
"total_flos": 1.5720679109463245e+17,
|
| 1991 |
+
"train_batch_size": 32,
|
| 1992 |
+
"trial_name": null,
|
| 1993 |
+
"trial_params": null
|
| 1994 |
+
}
|
checkpoint-140000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6fad2530f3d27917fbdcc941e3023a8fce21992040aa6f8afe98d384d87efa35
|
| 3 |
+
size 5368
|
checkpoint-140000/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-160000/config.json
ADDED
|
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"RobertaForMaskedLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_probs_dropout_prob": 0.1,
|
| 6 |
+
"bos_token_id": 0,
|
| 7 |
+
"classifier_dropout": null,
|
| 8 |
+
"eos_token_id": 2,
|
| 9 |
+
"hidden_act": "gelu",
|
| 10 |
+
"hidden_dropout_prob": 0.1,
|
| 11 |
+
"hidden_size": 768,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 3072,
|
| 14 |
+
"layer_norm_eps": 1e-12,
|
| 15 |
+
"max_position_embeddings": 514,
|
| 16 |
+
"model_type": "roberta",
|
| 17 |
+
"num_attention_heads": 12,
|
| 18 |
+
"num_hidden_layers": 6,
|
| 19 |
+
"pad_token_id": 1,
|
| 20 |
+
"position_embedding_type": "absolute",
|
| 21 |
+
"torch_dtype": "float32",
|
| 22 |
+
"transformers_version": "4.50.3",
|
| 23 |
+
"type_vocab_size": 1,
|
| 24 |
+
"use_cache": true,
|
| 25 |
+
"vocab_size": 52000
|
| 26 |
+
}
|
checkpoint-160000/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-160000/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2f7ceb07e35284d34c79a6fc7cb4eb0e2ffae2c6dfffb33789d599c037883915
|
| 3 |
+
size 334030264
|
checkpoint-160000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:09dd0a9a0cb7d01cc321a8c37ec2adb632e97457a68889587af8e4354d81dc05
|
| 3 |
+
size 668124218
|
checkpoint-160000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ae8630f97881742aa9999bf3fe6d59dbd0d11a5493ceae5bf8e881196bb8bd9c
|
| 3 |
+
size 14244
|