Upload folder using huggingface_hub
Browse files- .gitattributes +1 -0
- config.json +33 -0
- generation_config.json +6 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state_0.pth +3 -0
- rng_state_1.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +23 -0
- spiece.model +3 -0
- tokenizer.json +3 -0
- tokenizer_config.json +39 -0
- trainer_state.json +1138 -0
- training_args.bin +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 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
config.json
ADDED
|
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "google/mt5-base",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"MT5ForConditionalGeneration"
|
| 5 |
+
],
|
| 6 |
+
"classifier_dropout": 0.0,
|
| 7 |
+
"d_ff": 2048,
|
| 8 |
+
"d_kv": 64,
|
| 9 |
+
"d_model": 768,
|
| 10 |
+
"decoder_start_token_id": 0,
|
| 11 |
+
"dense_act_fn": "gelu_new",
|
| 12 |
+
"dropout_rate": 0.1,
|
| 13 |
+
"eos_token_id": 1,
|
| 14 |
+
"feed_forward_proj": "gated-gelu",
|
| 15 |
+
"initializer_factor": 1.0,
|
| 16 |
+
"is_encoder_decoder": true,
|
| 17 |
+
"is_gated_act": true,
|
| 18 |
+
"layer_norm_epsilon": 1e-06,
|
| 19 |
+
"model_type": "mt5",
|
| 20 |
+
"num_decoder_layers": 12,
|
| 21 |
+
"num_heads": 12,
|
| 22 |
+
"num_layers": 12,
|
| 23 |
+
"output_past": true,
|
| 24 |
+
"pad_token_id": 0,
|
| 25 |
+
"relative_attention_max_distance": 128,
|
| 26 |
+
"relative_attention_num_buckets": 32,
|
| 27 |
+
"tie_word_embeddings": false,
|
| 28 |
+
"tokenizer_class": "T5Tokenizer",
|
| 29 |
+
"torch_dtype": "float32",
|
| 30 |
+
"transformers_version": "4.40.2",
|
| 31 |
+
"use_cache": true,
|
| 32 |
+
"vocab_size": 250112
|
| 33 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"decoder_start_token_id": 0,
|
| 3 |
+
"eos_token_id": 1,
|
| 4 |
+
"pad_token_id": 0,
|
| 5 |
+
"transformers_version": "4.40.2"
|
| 6 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e36e69864ca2dd7ab198529e09bf6ae29f703b9ac678067a4030e4734dca5d1b
|
| 3 |
+
size 2329638768
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c4af40543f3f4737138013cd8dfef60ff96f5f0db4b82571e8ff153b5209c382
|
| 3 |
+
size 4115322
|
rng_state_0.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:09dc913f8390f905c4bfee7072c2421292d8f99fba33681bf427cde3f4699045
|
| 3 |
+
size 14512
|
rng_state_1.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8fa721b6778b7011e9e69e01915c0edb4d3c2abc253bd9d5a7d2d2c20437ad4e
|
| 3 |
+
size 14512
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ff142e42ad4bbcf8518b6a439ef30c14478e4470306df3a76115a5239a55c910
|
| 3 |
+
size 1000
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"eos_token": {
|
| 3 |
+
"content": "</s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"pad_token": {
|
| 10 |
+
"content": "<pad>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"unk_token": {
|
| 17 |
+
"content": "<unk>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
}
|
| 23 |
+
}
|
spiece.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ef78f86560d809067d12bac6c09f19a462cb3af3f54d2b8acbba26e1433125d6
|
| 3 |
+
size 4309802
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ddb1b00035edffde435e24e69011b7f552691405237455cb7c3a59c890682807
|
| 3 |
+
size 16330540
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": true,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"0": {
|
| 5 |
+
"content": "<pad>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": false,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"1": {
|
| 13 |
+
"content": "</s>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": false,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"2": {
|
| 21 |
+
"content": "<unk>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": false,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": true
|
| 27 |
+
}
|
| 28 |
+
},
|
| 29 |
+
"additional_special_tokens": [],
|
| 30 |
+
"clean_up_tokenization_spaces": true,
|
| 31 |
+
"eos_token": "</s>",
|
| 32 |
+
"extra_ids": 0,
|
| 33 |
+
"legacy": true,
|
| 34 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 35 |
+
"pad_token": "<pad>",
|
| 36 |
+
"sp_model_kwargs": {},
|
| 37 |
+
"tokenizer_class": "T5Tokenizer",
|
| 38 |
+
"unk_token": "<unk>"
|
| 39 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1138 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 3.5637874603271484,
|
| 3 |
+
"best_model_checkpoint": "checkpoints/mt5-base/checkpoint-37386",
|
| 4 |
+
"epoch": 13.501625135427952,
|
| 5 |
+
"eval_steps": 2077,
|
| 6 |
+
"global_step": 37386,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.14987360057782592,
|
| 13 |
+
"eval_g2l_cer": 286.0084,
|
| 14 |
+
"eval_g2l_gen_len": 8.1826,
|
| 15 |
+
"eval_g2l_rouge1": 5.5622,
|
| 16 |
+
"eval_g2l_rouge2": 1.1913,
|
| 17 |
+
"eval_g2l_rougeL": 5.4996,
|
| 18 |
+
"eval_g2l_rougeLsum": 5.5114,
|
| 19 |
+
"eval_l2ex_cer": 86.6247,
|
| 20 |
+
"eval_l2ex_gen_len": 7.9383,
|
| 21 |
+
"eval_l2ex_rouge1": 16.8571,
|
| 22 |
+
"eval_l2ex_rouge2": 5.0595,
|
| 23 |
+
"eval_l2ex_rougeL": 15.4605,
|
| 24 |
+
"eval_l2ex_rougeLsum": 15.4778,
|
| 25 |
+
"eval_l2g_cer": 87.9265,
|
| 26 |
+
"eval_l2g_gen_len": 5.5834,
|
| 27 |
+
"eval_l2g_rouge1": 12.3664,
|
| 28 |
+
"eval_l2g_rouge2": 1.6791,
|
| 29 |
+
"eval_l2g_rougeL": 11.57,
|
| 30 |
+
"eval_l2g_rougeLsum": 11.5871,
|
| 31 |
+
"eval_loss": 8.359071731567383,
|
| 32 |
+
"eval_runtime": 145.7254,
|
| 33 |
+
"eval_samples_per_second": 68.08,
|
| 34 |
+
"eval_steps_per_second": 2.134,
|
| 35 |
+
"step": 415
|
| 36 |
+
},
|
| 37 |
+
{
|
| 38 |
+
"epoch": 0.15023474178403756,
|
| 39 |
+
"grad_norm": 1659.9119873046875,
|
| 40 |
+
"learning_rate": 2.0038535645472063e-05,
|
| 41 |
+
"loss": 15.088,
|
| 42 |
+
"step": 416
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"epoch": 0.3004694835680751,
|
| 46 |
+
"grad_norm": 8.369742393493652,
|
| 47 |
+
"learning_rate": 4.0077071290944125e-05,
|
| 48 |
+
"loss": 7.1403,
|
| 49 |
+
"step": 832
|
| 50 |
+
},
|
| 51 |
+
{
|
| 52 |
+
"epoch": 0.4507042253521127,
|
| 53 |
+
"grad_norm": 1.8832136392593384,
|
| 54 |
+
"learning_rate": 6.0115606936416195e-05,
|
| 55 |
+
"loss": 5.3841,
|
| 56 |
+
"step": 1248
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.6009389671361502,
|
| 60 |
+
"grad_norm": 23.656179428100586,
|
| 61 |
+
"learning_rate": 8.015414258188825e-05,
|
| 62 |
+
"loss": 4.9928,
|
| 63 |
+
"step": 1664
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.7500902853015529,
|
| 67 |
+
"eval_g2l_cer": 59.4485,
|
| 68 |
+
"eval_g2l_gen_len": 2.9556,
|
| 69 |
+
"eval_g2l_rouge1": 27.1975,
|
| 70 |
+
"eval_g2l_rouge2": 17.2281,
|
| 71 |
+
"eval_g2l_rougeL": 27.1916,
|
| 72 |
+
"eval_g2l_rougeLsum": 27.2117,
|
| 73 |
+
"eval_l2ex_cer": 95.5123,
|
| 74 |
+
"eval_l2ex_gen_len": 23.6742,
|
| 75 |
+
"eval_l2ex_rouge1": 25.7497,
|
| 76 |
+
"eval_l2ex_rouge2": 11.1192,
|
| 77 |
+
"eval_l2ex_rougeL": 22.9461,
|
| 78 |
+
"eval_l2ex_rougeLsum": 22.9441,
|
| 79 |
+
"eval_l2g_cer": 83.2502,
|
| 80 |
+
"eval_l2g_gen_len": 15.9711,
|
| 81 |
+
"eval_l2g_rouge1": 27.2934,
|
| 82 |
+
"eval_l2g_rouge2": 14.8195,
|
| 83 |
+
"eval_l2g_rougeL": 25.9582,
|
| 84 |
+
"eval_l2g_rougeLsum": 25.9617,
|
| 85 |
+
"eval_loss": 4.2178425788879395,
|
| 86 |
+
"eval_runtime": 203.8137,
|
| 87 |
+
"eval_samples_per_second": 48.677,
|
| 88 |
+
"eval_steps_per_second": 1.526,
|
| 89 |
+
"step": 2077
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 0.7511737089201878,
|
| 93 |
+
"grad_norm": 1.5714240074157715,
|
| 94 |
+
"learning_rate": 9.999999747638704e-05,
|
| 95 |
+
"loss": 4.7614,
|
| 96 |
+
"step": 2080
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 0.9014084507042254,
|
| 100 |
+
"grad_norm": 2.348027467727661,
|
| 101 |
+
"learning_rate": 9.997217976013284e-05,
|
| 102 |
+
"loss": 4.6037,
|
| 103 |
+
"step": 2496
|
| 104 |
+
},
|
| 105 |
+
{
|
| 106 |
+
"epoch": 1.051643192488263,
|
| 107 |
+
"grad_norm": 2.6275577545166016,
|
| 108 |
+
"learning_rate": 9.98898067640237e-05,
|
| 109 |
+
"loss": 4.5136,
|
| 110 |
+
"step": 2912
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 1.2018779342723005,
|
| 114 |
+
"grad_norm": 1.1122652292251587,
|
| 115 |
+
"learning_rate": 9.975296886788363e-05,
|
| 116 |
+
"loss": 4.4057,
|
| 117 |
+
"step": 3328
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 1.352112676056338,
|
| 121 |
+
"grad_norm": 1.2248876094818115,
|
| 122 |
+
"learning_rate": 9.956181621053908e-05,
|
| 123 |
+
"loss": 4.3513,
|
| 124 |
+
"step": 3744
|
| 125 |
+
},
|
| 126 |
+
{
|
| 127 |
+
"epoch": 1.500180570603106,
|
| 128 |
+
"eval_g2l_cer": 56.9353,
|
| 129 |
+
"eval_g2l_gen_len": 3.093,
|
| 130 |
+
"eval_g2l_rouge1": 32.8366,
|
| 131 |
+
"eval_g2l_rouge2": 24.3793,
|
| 132 |
+
"eval_g2l_rougeL": 32.7964,
|
| 133 |
+
"eval_g2l_rougeLsum": 32.7681,
|
| 134 |
+
"eval_l2ex_cer": 84.2827,
|
| 135 |
+
"eval_l2ex_gen_len": 20.4604,
|
| 136 |
+
"eval_l2ex_rouge1": 28.5353,
|
| 137 |
+
"eval_l2ex_rouge2": 12.5551,
|
| 138 |
+
"eval_l2ex_rougeL": 25.5058,
|
| 139 |
+
"eval_l2ex_rougeLsum": 25.5427,
|
| 140 |
+
"eval_l2g_cer": 81.1104,
|
| 141 |
+
"eval_l2g_gen_len": 18.0072,
|
| 142 |
+
"eval_l2g_rouge1": 32.688,
|
| 143 |
+
"eval_l2g_rouge2": 18.9467,
|
| 144 |
+
"eval_l2g_rougeL": 30.7295,
|
| 145 |
+
"eval_l2g_rougeLsum": 30.7676,
|
| 146 |
+
"eval_loss": 3.949233293533325,
|
| 147 |
+
"eval_runtime": 197.691,
|
| 148 |
+
"eval_samples_per_second": 50.184,
|
| 149 |
+
"eval_steps_per_second": 1.573,
|
| 150 |
+
"step": 4154
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 1.5023474178403755,
|
| 154 |
+
"grad_norm": 1.4981008768081665,
|
| 155 |
+
"learning_rate": 9.931655852508637e-05,
|
| 156 |
+
"loss": 4.3061,
|
| 157 |
+
"step": 4160
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 1.652582159624413,
|
| 161 |
+
"grad_norm": 1.050997018814087,
|
| 162 |
+
"learning_rate": 9.901746490877203e-05,
|
| 163 |
+
"loss": 4.2525,
|
| 164 |
+
"step": 4576
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 1.8028169014084507,
|
| 168 |
+
"grad_norm": 0.8377422094345093,
|
| 169 |
+
"learning_rate": 9.866486352773886e-05,
|
| 170 |
+
"loss": 4.2289,
|
| 171 |
+
"step": 4992
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 1.9530516431924883,
|
| 175 |
+
"grad_norm": 0.968815267086029,
|
| 176 |
+
"learning_rate": 9.82591412569612e-05,
|
| 177 |
+
"loss": 4.1958,
|
| 178 |
+
"step": 5408
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 2.103286384976526,
|
| 182 |
+
"grad_norm": 0.9952152967453003,
|
| 183 |
+
"learning_rate": 9.780074325576496e-05,
|
| 184 |
+
"loss": 4.1187,
|
| 185 |
+
"step": 5824
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 2.2502708559046587,
|
| 189 |
+
"eval_g2l_cer": 53.8806,
|
| 190 |
+
"eval_g2l_gen_len": 3.0548,
|
| 191 |
+
"eval_g2l_rouge1": 35.439,
|
| 192 |
+
"eval_g2l_rouge2": 27.2433,
|
| 193 |
+
"eval_g2l_rougeL": 35.4384,
|
| 194 |
+
"eval_g2l_rougeLsum": 35.3985,
|
| 195 |
+
"eval_l2ex_cer": 89.3431,
|
| 196 |
+
"eval_l2ex_gen_len": 23.4573,
|
| 197 |
+
"eval_l2ex_rouge1": 27.8815,
|
| 198 |
+
"eval_l2ex_rouge2": 12.1568,
|
| 199 |
+
"eval_l2ex_rougeL": 24.5796,
|
| 200 |
+
"eval_l2ex_rougeLsum": 24.6286,
|
| 201 |
+
"eval_l2g_cer": 78.589,
|
| 202 |
+
"eval_l2g_gen_len": 17.4946,
|
| 203 |
+
"eval_l2g_rouge1": 35.6236,
|
| 204 |
+
"eval_l2g_rouge2": 22.8027,
|
| 205 |
+
"eval_l2g_rougeL": 33.8966,
|
| 206 |
+
"eval_l2g_rougeLsum": 33.9001,
|
| 207 |
+
"eval_loss": 3.8344309329986572,
|
| 208 |
+
"eval_runtime": 202.9852,
|
| 209 |
+
"eval_samples_per_second": 48.875,
|
| 210 |
+
"eval_steps_per_second": 1.532,
|
| 211 |
+
"step": 6231
|
| 212 |
+
},
|
| 213 |
+
{
|
| 214 |
+
"epoch": 2.2535211267605635,
|
| 215 |
+
"grad_norm": 24.567110061645508,
|
| 216 |
+
"learning_rate": 9.72901724793979e-05,
|
| 217 |
+
"loss": 4.0993,
|
| 218 |
+
"step": 6240
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 2.403755868544601,
|
| 222 |
+
"grad_norm": 0.9726364612579346,
|
| 223 |
+
"learning_rate": 9.672798912718604e-05,
|
| 224 |
+
"loss": 4.0734,
|
| 225 |
+
"step": 6656
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 2.5539906103286385,
|
| 229 |
+
"grad_norm": 0.9216151833534241,
|
| 230 |
+
"learning_rate": 9.611481002788184e-05,
|
| 231 |
+
"loss": 4.0584,
|
| 232 |
+
"step": 7072
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"epoch": 2.704225352112676,
|
| 236 |
+
"grad_norm": 0.7880883812904358,
|
| 237 |
+
"learning_rate": 9.545130796287832e-05,
|
| 238 |
+
"loss": 4.0312,
|
| 239 |
+
"step": 7488
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 2.8544600938967135,
|
| 243 |
+
"grad_norm": 0.9635422229766846,
|
| 244 |
+
"learning_rate": 9.473821092803199e-05,
|
| 245 |
+
"loss": 4.0046,
|
| 246 |
+
"step": 7904
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 3.0003611412062114,
|
| 250 |
+
"eval_g2l_cer": 52.062,
|
| 251 |
+
"eval_g2l_gen_len": 3.0702,
|
| 252 |
+
"eval_g2l_rouge1": 36.8811,
|
| 253 |
+
"eval_g2l_rouge2": 28.8156,
|
| 254 |
+
"eval_g2l_rougeL": 36.8925,
|
| 255 |
+
"eval_g2l_rougeLsum": 36.8317,
|
| 256 |
+
"eval_l2ex_cer": 90.1083,
|
| 257 |
+
"eval_l2ex_gen_len": 22.4645,
|
| 258 |
+
"eval_l2ex_rouge1": 27.5056,
|
| 259 |
+
"eval_l2ex_rouge2": 12.5248,
|
| 260 |
+
"eval_l2ex_rougeL": 24.4085,
|
| 261 |
+
"eval_l2ex_rougeLsum": 24.4463,
|
| 262 |
+
"eval_l2g_cer": 78.1779,
|
| 263 |
+
"eval_l2g_gen_len": 17.8095,
|
| 264 |
+
"eval_l2g_rouge1": 36.8332,
|
| 265 |
+
"eval_l2g_rouge2": 23.9422,
|
| 266 |
+
"eval_l2g_rougeL": 34.9672,
|
| 267 |
+
"eval_l2g_rougeLsum": 34.995,
|
| 268 |
+
"eval_loss": 3.7595808506011963,
|
| 269 |
+
"eval_runtime": 202.3409,
|
| 270 |
+
"eval_samples_per_second": 49.031,
|
| 271 |
+
"eval_steps_per_second": 1.537,
|
| 272 |
+
"step": 8308
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 3.004694835680751,
|
| 276 |
+
"grad_norm": 0.900855541229248,
|
| 277 |
+
"learning_rate": 9.397630133490413e-05,
|
| 278 |
+
"loss": 3.992,
|
| 279 |
+
"step": 8320
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 3.1549295774647885,
|
| 283 |
+
"grad_norm": 0.8881470561027527,
|
| 284 |
+
"learning_rate": 9.316641515229741e-05,
|
| 285 |
+
"loss": 3.9362,
|
| 286 |
+
"step": 8736
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 3.3051643192488265,
|
| 290 |
+
"grad_norm": 0.7969784140586853,
|
| 291 |
+
"learning_rate": 9.230944098902894e-05,
|
| 292 |
+
"loss": 3.9143,
|
| 293 |
+
"step": 9152
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 3.455399061032864,
|
| 297 |
+
"grad_norm": 0.8603357672691345,
|
| 298 |
+
"learning_rate": 9.1406319118947e-05,
|
| 299 |
+
"loss": 3.9162,
|
| 300 |
+
"step": 9568
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 3.6056338028169015,
|
| 304 |
+
"grad_norm": 0.9974511861801147,
|
| 305 |
+
"learning_rate": 9.045804044926044e-05,
|
| 306 |
+
"loss": 3.8987,
|
| 307 |
+
"step": 9984
|
| 308 |
+
},
|
| 309 |
+
{
|
| 310 |
+
"epoch": 3.7504514265077646,
|
| 311 |
+
"eval_g2l_cer": 50.7917,
|
| 312 |
+
"eval_g2l_gen_len": 3.0031,
|
| 313 |
+
"eval_g2l_rouge1": 37.7135,
|
| 314 |
+
"eval_g2l_rouge2": 29.9526,
|
| 315 |
+
"eval_g2l_rougeL": 37.7649,
|
| 316 |
+
"eval_g2l_rougeLsum": 37.7041,
|
| 317 |
+
"eval_l2ex_cer": 86.8671,
|
| 318 |
+
"eval_l2ex_gen_len": 22.2271,
|
| 319 |
+
"eval_l2ex_rouge1": 28.7692,
|
| 320 |
+
"eval_l2ex_rouge2": 12.8536,
|
| 321 |
+
"eval_l2ex_rougeL": 25.3768,
|
| 322 |
+
"eval_l2ex_rougeLsum": 25.4158,
|
| 323 |
+
"eval_l2g_cer": 73.3411,
|
| 324 |
+
"eval_l2g_gen_len": 15.6692,
|
| 325 |
+
"eval_l2g_rouge1": 37.5152,
|
| 326 |
+
"eval_l2g_rouge2": 24.5536,
|
| 327 |
+
"eval_l2g_rougeL": 35.5225,
|
| 328 |
+
"eval_l2g_rougeLsum": 35.5437,
|
| 329 |
+
"eval_loss": 3.7121169567108154,
|
| 330 |
+
"eval_runtime": 192.3527,
|
| 331 |
+
"eval_samples_per_second": 51.577,
|
| 332 |
+
"eval_steps_per_second": 1.617,
|
| 333 |
+
"step": 10385
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 3.755868544600939,
|
| 337 |
+
"grad_norm": 0.8458616733551025,
|
| 338 |
+
"learning_rate": 8.94656454333133e-05,
|
| 339 |
+
"loss": 3.8883,
|
| 340 |
+
"step": 10400
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"epoch": 3.9061032863849765,
|
| 344 |
+
"grad_norm": 3.1263327598571777,
|
| 345 |
+
"learning_rate": 8.843022292899726e-05,
|
| 346 |
+
"loss": 3.8775,
|
| 347 |
+
"step": 10816
|
| 348 |
+
},
|
| 349 |
+
{
|
| 350 |
+
"epoch": 4.056338028169014,
|
| 351 |
+
"grad_norm": 1.013489842414856,
|
| 352 |
+
"learning_rate": 8.735290900405437e-05,
|
| 353 |
+
"loss": 3.8514,
|
| 354 |
+
"step": 11232
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 4.206572769953052,
|
| 358 |
+
"grad_norm": 0.9674685001373291,
|
| 359 |
+
"learning_rate": 8.623488568958123e-05,
|
| 360 |
+
"loss": 3.7962,
|
| 361 |
+
"step": 11648
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 4.356807511737089,
|
| 365 |
+
"grad_norm": 1.0607421398162842,
|
| 366 |
+
"learning_rate": 8.507737968310197e-05,
|
| 367 |
+
"loss": 3.8043,
|
| 368 |
+
"step": 12064
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 4.500541711809317,
|
| 372 |
+
"eval_g2l_cer": 50.088,
|
| 373 |
+
"eval_g2l_gen_len": 3.0488,
|
| 374 |
+
"eval_g2l_rouge1": 38.7702,
|
| 375 |
+
"eval_g2l_rouge2": 30.6004,
|
| 376 |
+
"eval_g2l_rougeL": 38.7959,
|
| 377 |
+
"eval_g2l_rougeLsum": 38.7454,
|
| 378 |
+
"eval_l2ex_cer": 84.5143,
|
| 379 |
+
"eval_l2ex_gen_len": 20.52,
|
| 380 |
+
"eval_l2ex_rouge1": 28.9181,
|
| 381 |
+
"eval_l2ex_rouge2": 13.2853,
|
| 382 |
+
"eval_l2ex_rougeL": 25.6409,
|
| 383 |
+
"eval_l2ex_rougeLsum": 25.6588,
|
| 384 |
+
"eval_l2g_cer": 72.4949,
|
| 385 |
+
"eval_l2g_gen_len": 15.2432,
|
| 386 |
+
"eval_l2g_rouge1": 37.6479,
|
| 387 |
+
"eval_l2g_rouge2": 24.833,
|
| 388 |
+
"eval_l2g_rougeL": 35.7678,
|
| 389 |
+
"eval_l2g_rougeLsum": 35.776,
|
| 390 |
+
"eval_loss": 3.674677848815918,
|
| 391 |
+
"eval_runtime": 190.2532,
|
| 392 |
+
"eval_samples_per_second": 52.146,
|
| 393 |
+
"eval_steps_per_second": 1.635,
|
| 394 |
+
"step": 12462
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 4.507042253521127,
|
| 398 |
+
"grad_norm": 0.9242987632751465,
|
| 399 |
+
"learning_rate": 8.388166100263313e-05,
|
| 400 |
+
"loss": 3.804,
|
| 401 |
+
"step": 12480
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 4.657276995305164,
|
| 405 |
+
"grad_norm": 0.8233311772346497,
|
| 406 |
+
"learning_rate": 8.264904159321721e-05,
|
| 407 |
+
"loss": 3.7844,
|
| 408 |
+
"step": 12896
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 4.807511737089202,
|
| 412 |
+
"grad_norm": 1.918661117553711,
|
| 413 |
+
"learning_rate": 8.138087388745395e-05,
|
| 414 |
+
"loss": 3.7948,
|
| 415 |
+
"step": 13312
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 4.957746478873239,
|
| 419 |
+
"grad_norm": 0.8277648091316223,
|
| 420 |
+
"learning_rate": 8.00785493216083e-05,
|
| 421 |
+
"loss": 3.7951,
|
| 422 |
+
"step": 13728
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 5.107981220657277,
|
| 426 |
+
"grad_norm": 1.0518523454666138,
|
| 427 |
+
"learning_rate": 7.874349680892367e-05,
|
| 428 |
+
"loss": 3.7423,
|
| 429 |
+
"step": 14144
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 5.250631997110871,
|
| 433 |
+
"eval_g2l_cer": 49.743,
|
| 434 |
+
"eval_g2l_gen_len": 3.0201,
|
| 435 |
+
"eval_g2l_rouge1": 38.8263,
|
| 436 |
+
"eval_g2l_rouge2": 31.1673,
|
| 437 |
+
"eval_g2l_rougeL": 38.8286,
|
| 438 |
+
"eval_g2l_rougeLsum": 38.7898,
|
| 439 |
+
"eval_l2ex_cer": 86.565,
|
| 440 |
+
"eval_l2ex_gen_len": 21.7523,
|
| 441 |
+
"eval_l2ex_rouge1": 28.4984,
|
| 442 |
+
"eval_l2ex_rouge2": 13.072,
|
| 443 |
+
"eval_l2ex_rougeL": 25.2667,
|
| 444 |
+
"eval_l2ex_rougeLsum": 25.2757,
|
| 445 |
+
"eval_l2g_cer": 73.2917,
|
| 446 |
+
"eval_l2g_gen_len": 16.0011,
|
| 447 |
+
"eval_l2g_rouge1": 38.0438,
|
| 448 |
+
"eval_l2g_rouge2": 25.3209,
|
| 449 |
+
"eval_l2g_rougeL": 36.1091,
|
| 450 |
+
"eval_l2g_rougeLsum": 36.1243,
|
| 451 |
+
"eval_loss": 3.649608850479126,
|
| 452 |
+
"eval_runtime": 197.4229,
|
| 453 |
+
"eval_samples_per_second": 50.253,
|
| 454 |
+
"eval_steps_per_second": 1.575,
|
| 455 |
+
"step": 14539
|
| 456 |
+
},
|
| 457 |
+
{
|
| 458 |
+
"epoch": 5.258215962441315,
|
| 459 |
+
"grad_norm": 0.8540360331535339,
|
| 460 |
+
"learning_rate": 7.737718117181538e-05,
|
| 461 |
+
"loss": 3.7126,
|
| 462 |
+
"step": 14560
|
| 463 |
+
},
|
| 464 |
+
{
|
| 465 |
+
"epoch": 5.408450704225352,
|
| 466 |
+
"grad_norm": 0.9189392328262329,
|
| 467 |
+
"learning_rate": 7.598110153466441e-05,
|
| 468 |
+
"loss": 3.7223,
|
| 469 |
+
"step": 14976
|
| 470 |
+
},
|
| 471 |
+
{
|
| 472 |
+
"epoch": 5.55868544600939,
|
| 473 |
+
"grad_norm": 0.92618727684021,
|
| 474 |
+
"learning_rate": 7.45567896789749e-05,
|
| 475 |
+
"loss": 3.7139,
|
| 476 |
+
"step": 15392
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 5.708920187793427,
|
| 480 |
+
"grad_norm": 0.7882264852523804,
|
| 481 |
+
"learning_rate": 7.310580836270044e-05,
|
| 482 |
+
"loss": 3.7179,
|
| 483 |
+
"step": 15808
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 5.859154929577465,
|
| 487 |
+
"grad_norm": 0.8529959321022034,
|
| 488 |
+
"learning_rate": 7.162974960558259e-05,
|
| 489 |
+
"loss": 3.7121,
|
| 490 |
+
"step": 16224
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 6.000722282412423,
|
| 494 |
+
"eval_g2l_cer": 49.3934,
|
| 495 |
+
"eval_g2l_gen_len": 3.0096,
|
| 496 |
+
"eval_g2l_rouge1": 39.4408,
|
| 497 |
+
"eval_g2l_rouge2": 31.7057,
|
| 498 |
+
"eval_g2l_rougeL": 39.4639,
|
| 499 |
+
"eval_g2l_rougeLsum": 39.4161,
|
| 500 |
+
"eval_l2ex_cer": 86.119,
|
| 501 |
+
"eval_l2ex_gen_len": 20.7112,
|
| 502 |
+
"eval_l2ex_rouge1": 28.8739,
|
| 503 |
+
"eval_l2ex_rouge2": 13.2661,
|
| 504 |
+
"eval_l2ex_rougeL": 25.7042,
|
| 505 |
+
"eval_l2ex_rougeLsum": 25.7118,
|
| 506 |
+
"eval_l2g_cer": 73.625,
|
| 507 |
+
"eval_l2g_gen_len": 15.9897,
|
| 508 |
+
"eval_l2g_rouge1": 38.1171,
|
| 509 |
+
"eval_l2g_rouge2": 25.6405,
|
| 510 |
+
"eval_l2g_rougeL": 36.2592,
|
| 511 |
+
"eval_l2g_rougeLsum": 36.2666,
|
| 512 |
+
"eval_loss": 3.6273715496063232,
|
| 513 |
+
"eval_runtime": 193.9276,
|
| 514 |
+
"eval_samples_per_second": 51.158,
|
| 515 |
+
"eval_steps_per_second": 1.604,
|
| 516 |
+
"step": 16616
|
| 517 |
+
},
|
| 518 |
+
{
|
| 519 |
+
"epoch": 6.009389671361502,
|
| 520 |
+
"grad_norm": 0.7976297736167908,
|
| 521 |
+
"learning_rate": 7.013023294238368e-05,
|
| 522 |
+
"loss": 3.7191,
|
| 523 |
+
"step": 16640
|
| 524 |
+
},
|
| 525 |
+
{
|
| 526 |
+
"epoch": 6.15962441314554,
|
| 527 |
+
"grad_norm": 0.8516309261322021,
|
| 528 |
+
"learning_rate": 6.860890364592963e-05,
|
| 529 |
+
"loss": 3.6428,
|
| 530 |
+
"step": 17056
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 6.309859154929577,
|
| 534 |
+
"grad_norm": 0.9273515343666077,
|
| 535 |
+
"learning_rate": 6.706743092191335e-05,
|
| 536 |
+
"loss": 3.6566,
|
| 537 |
+
"step": 17472
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 6.460093896713615,
|
| 541 |
+
"grad_norm": 0.932829737663269,
|
| 542 |
+
"learning_rate": 6.550750607743873e-05,
|
| 543 |
+
"loss": 3.6627,
|
| 544 |
+
"step": 17888
|
| 545 |
+
},
|
| 546 |
+
{
|
| 547 |
+
"epoch": 6.610328638497653,
|
| 548 |
+
"grad_norm": 0.9968202114105225,
|
| 549 |
+
"learning_rate": 6.393084066531485e-05,
|
| 550 |
+
"loss": 3.6652,
|
| 551 |
+
"step": 18304
|
| 552 |
+
},
|
| 553 |
+
{
|
| 554 |
+
"epoch": 6.750812567713976,
|
| 555 |
+
"eval_g2l_cer": 49.5579,
|
| 556 |
+
"eval_g2l_gen_len": 2.9938,
|
| 557 |
+
"eval_g2l_rouge1": 39.6581,
|
| 558 |
+
"eval_g2l_rouge2": 32.026,
|
| 559 |
+
"eval_g2l_rougeL": 39.6932,
|
| 560 |
+
"eval_g2l_rougeLsum": 39.6518,
|
| 561 |
+
"eval_l2ex_cer": 88.4427,
|
| 562 |
+
"eval_l2ex_gen_len": 23.11,
|
| 563 |
+
"eval_l2ex_rouge1": 28.1485,
|
| 564 |
+
"eval_l2ex_rouge2": 12.4558,
|
| 565 |
+
"eval_l2ex_rougeL": 24.9414,
|
| 566 |
+
"eval_l2ex_rougeLsum": 24.9605,
|
| 567 |
+
"eval_l2g_cer": 73.3296,
|
| 568 |
+
"eval_l2g_gen_len": 16.3263,
|
| 569 |
+
"eval_l2g_rouge1": 38.4506,
|
| 570 |
+
"eval_l2g_rouge2": 25.7696,
|
| 571 |
+
"eval_l2g_rougeL": 36.5748,
|
| 572 |
+
"eval_l2g_rougeLsum": 36.6091,
|
| 573 |
+
"eval_loss": 3.6120047569274902,
|
| 574 |
+
"eval_runtime": 197.9501,
|
| 575 |
+
"eval_samples_per_second": 50.119,
|
| 576 |
+
"eval_steps_per_second": 1.571,
|
| 577 |
+
"step": 18693
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 6.76056338028169,
|
| 581 |
+
"grad_norm": 0.7791869640350342,
|
| 582 |
+
"learning_rate": 6.233916460613673e-05,
|
| 583 |
+
"loss": 3.6614,
|
| 584 |
+
"step": 18720
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 6.910798122065728,
|
| 588 |
+
"grad_norm": 0.9385781288146973,
|
| 589 |
+
"learning_rate": 6.0734224290212784e-05,
|
| 590 |
+
"loss": 3.6471,
|
| 591 |
+
"step": 19136
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 7.061032863849765,
|
| 595 |
+
"grad_norm": 0.8267916440963745,
|
| 596 |
+
"learning_rate": 5.9117780661421754e-05,
|
| 597 |
+
"loss": 3.6264,
|
| 598 |
+
"step": 19552
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 7.211267605633803,
|
| 602 |
+
"grad_norm": 0.794131875038147,
|
| 603 |
+
"learning_rate": 5.7491607285101345e-05,
|
| 604 |
+
"loss": 3.6015,
|
| 605 |
+
"step": 19968
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 7.36150234741784,
|
| 609 |
+
"grad_norm": 0.8748852610588074,
|
| 610 |
+
"learning_rate": 5.585748840208869e-05,
|
| 611 |
+
"loss": 3.5993,
|
| 612 |
+
"step": 20384
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 7.500902853015529,
|
| 616 |
+
"eval_g2l_cer": 50.088,
|
| 617 |
+
"eval_g2l_gen_len": 3.0582,
|
| 618 |
+
"eval_g2l_rouge1": 39.9874,
|
| 619 |
+
"eval_g2l_rouge2": 32.4432,
|
| 620 |
+
"eval_g2l_rougeL": 40.0195,
|
| 621 |
+
"eval_g2l_rougeLsum": 39.9365,
|
| 622 |
+
"eval_l2ex_cer": 87.6165,
|
| 623 |
+
"eval_l2ex_gen_len": 22.7133,
|
| 624 |
+
"eval_l2ex_rouge1": 28.1937,
|
| 625 |
+
"eval_l2ex_rouge2": 12.5673,
|
| 626 |
+
"eval_l2ex_rougeL": 24.9397,
|
| 627 |
+
"eval_l2ex_rougeLsum": 24.921,
|
| 628 |
+
"eval_l2g_cer": 72.7284,
|
| 629 |
+
"eval_l2g_gen_len": 15.6759,
|
| 630 |
+
"eval_l2g_rouge1": 38.4813,
|
| 631 |
+
"eval_l2g_rouge2": 25.936,
|
| 632 |
+
"eval_l2g_rougeL": 36.5693,
|
| 633 |
+
"eval_l2g_rougeLsum": 36.5729,
|
| 634 |
+
"eval_loss": 3.6013987064361572,
|
| 635 |
+
"eval_runtime": 195.438,
|
| 636 |
+
"eval_samples_per_second": 50.763,
|
| 637 |
+
"eval_steps_per_second": 1.591,
|
| 638 |
+
"step": 20770
|
| 639 |
+
},
|
| 640 |
+
{
|
| 641 |
+
"epoch": 7.511737089201878,
|
| 642 |
+
"grad_norm": 0.9019631743431091,
|
| 643 |
+
"learning_rate": 5.4217216971047445e-05,
|
| 644 |
+
"loss": 3.5978,
|
| 645 |
+
"step": 20800
|
| 646 |
+
},
|
| 647 |
+
{
|
| 648 |
+
"epoch": 7.661971830985916,
|
| 649 |
+
"grad_norm": 0.8872570395469666,
|
| 650 |
+
"learning_rate": 5.257259270122993e-05,
|
| 651 |
+
"loss": 3.6113,
|
| 652 |
+
"step": 21216
|
| 653 |
+
},
|
| 654 |
+
{
|
| 655 |
+
"epoch": 7.812206572769953,
|
| 656 |
+
"grad_norm": 0.7394893169403076,
|
| 657 |
+
"learning_rate": 5.0925420077832285e-05,
|
| 658 |
+
"loss": 3.593,
|
| 659 |
+
"step": 21632
|
| 660 |
+
},
|
| 661 |
+
{
|
| 662 |
+
"epoch": 7.962441314553991,
|
| 663 |
+
"grad_norm": 0.8534842133522034,
|
| 664 |
+
"learning_rate": 4.927750638210947e-05,
|
| 665 |
+
"loss": 3.5963,
|
| 666 |
+
"step": 22048
|
| 667 |
+
},
|
| 668 |
+
{
|
| 669 |
+
"epoch": 8.112676056338028,
|
| 670 |
+
"grad_norm": 0.9047814607620239,
|
| 671 |
+
"learning_rate": 4.7630659708422666e-05,
|
| 672 |
+
"loss": 3.5722,
|
| 673 |
+
"step": 22464
|
| 674 |
+
},
|
| 675 |
+
{
|
| 676 |
+
"epoch": 8.250993138317082,
|
| 677 |
+
"eval_g2l_cer": 49.5716,
|
| 678 |
+
"eval_g2l_gen_len": 3.0388,
|
| 679 |
+
"eval_g2l_rouge1": 40.4088,
|
| 680 |
+
"eval_g2l_rouge2": 32.7272,
|
| 681 |
+
"eval_g2l_rougeL": 40.4374,
|
| 682 |
+
"eval_g2l_rougeLsum": 40.3677,
|
| 683 |
+
"eval_l2ex_cer": 83.5858,
|
| 684 |
+
"eval_l2ex_gen_len": 20.4851,
|
| 685 |
+
"eval_l2ex_rouge1": 29.084,
|
| 686 |
+
"eval_l2ex_rouge2": 12.9208,
|
| 687 |
+
"eval_l2ex_rougeL": 25.6832,
|
| 688 |
+
"eval_l2ex_rougeLsum": 25.7033,
|
| 689 |
+
"eval_l2g_cer": 72.1741,
|
| 690 |
+
"eval_l2g_gen_len": 15.6461,
|
| 691 |
+
"eval_l2g_rouge1": 38.8628,
|
| 692 |
+
"eval_l2g_rouge2": 26.1912,
|
| 693 |
+
"eval_l2g_rougeL": 36.9072,
|
| 694 |
+
"eval_l2g_rougeLsum": 36.9086,
|
| 695 |
+
"eval_loss": 3.5901942253112793,
|
| 696 |
+
"eval_runtime": 190.412,
|
| 697 |
+
"eval_samples_per_second": 52.103,
|
| 698 |
+
"eval_steps_per_second": 1.633,
|
| 699 |
+
"step": 22847
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 8.262910798122066,
|
| 703 |
+
"grad_norm": 0.8366677761077881,
|
| 704 |
+
"learning_rate": 4.598668698039414e-05,
|
| 705 |
+
"loss": 3.5641,
|
| 706 |
+
"step": 22880
|
| 707 |
+
},
|
| 708 |
+
{
|
| 709 |
+
"epoch": 8.413145539906104,
|
| 710 |
+
"grad_norm": 0.8628195524215698,
|
| 711 |
+
"learning_rate": 4.4347391968347015e-05,
|
| 712 |
+
"loss": 3.5702,
|
| 713 |
+
"step": 23296
|
| 714 |
+
},
|
| 715 |
+
{
|
| 716 |
+
"epoch": 8.56338028169014,
|
| 717 |
+
"grad_norm": 0.9060849547386169,
|
| 718 |
+
"learning_rate": 4.27145733102046e-05,
|
| 719 |
+
"loss": 3.5508,
|
| 720 |
+
"step": 23712
|
| 721 |
+
},
|
| 722 |
+
{
|
| 723 |
+
"epoch": 8.713615023474178,
|
| 724 |
+
"grad_norm": 0.8726539015769958,
|
| 725 |
+
"learning_rate": 4.109002253802116e-05,
|
| 726 |
+
"loss": 3.5637,
|
| 727 |
+
"step": 24128
|
| 728 |
+
},
|
| 729 |
+
{
|
| 730 |
+
"epoch": 8.863849765258216,
|
| 731 |
+
"grad_norm": 0.9154978394508362,
|
| 732 |
+
"learning_rate": 3.947552211230913e-05,
|
| 733 |
+
"loss": 3.5435,
|
| 734 |
+
"step": 24544
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 9.001083423618635,
|
| 738 |
+
"eval_g2l_cer": 48.6326,
|
| 739 |
+
"eval_g2l_gen_len": 3.008,
|
| 740 |
+
"eval_g2l_rouge1": 40.6427,
|
| 741 |
+
"eval_g2l_rouge2": 33.0447,
|
| 742 |
+
"eval_g2l_rougeL": 40.6651,
|
| 743 |
+
"eval_g2l_rougeLsum": 40.6197,
|
| 744 |
+
"eval_l2ex_cer": 85.6816,
|
| 745 |
+
"eval_l2ex_gen_len": 20.9753,
|
| 746 |
+
"eval_l2ex_rouge1": 28.5827,
|
| 747 |
+
"eval_l2ex_rouge2": 12.8213,
|
| 748 |
+
"eval_l2ex_rougeL": 25.352,
|
| 749 |
+
"eval_l2ex_rougeLsum": 25.3642,
|
| 750 |
+
"eval_l2g_cer": 72.7802,
|
| 751 |
+
"eval_l2g_gen_len": 15.8102,
|
| 752 |
+
"eval_l2g_rouge1": 38.814,
|
| 753 |
+
"eval_l2g_rouge2": 26.1373,
|
| 754 |
+
"eval_l2g_rougeL": 36.8943,
|
| 755 |
+
"eval_l2g_rougeLsum": 36.9272,
|
| 756 |
+
"eval_loss": 3.5814104080200195,
|
| 757 |
+
"eval_runtime": 193.5202,
|
| 758 |
+
"eval_samples_per_second": 51.266,
|
| 759 |
+
"eval_steps_per_second": 1.607,
|
| 760 |
+
"step": 24924
|
| 761 |
+
},
|
| 762 |
+
{
|
| 763 |
+
"epoch": 9.014084507042254,
|
| 764 |
+
"grad_norm": 0.9910312294960022,
|
| 765 |
+
"learning_rate": 3.7872843466319744e-05,
|
| 766 |
+
"loss": 3.5601,
|
| 767 |
+
"step": 24960
|
| 768 |
+
},
|
| 769 |
+
{
|
| 770 |
+
"epoch": 9.164319248826292,
|
| 771 |
+
"grad_norm": 0.913223922252655,
|
| 772 |
+
"learning_rate": 3.6283745062422726e-05,
|
| 773 |
+
"loss": 3.5156,
|
| 774 |
+
"step": 25376
|
| 775 |
+
},
|
| 776 |
+
{
|
| 777 |
+
"epoch": 9.314553990610328,
|
| 778 |
+
"grad_norm": 0.9026065468788147,
|
| 779 |
+
"learning_rate": 3.470997046271774e-05,
|
| 780 |
+
"loss": 3.5337,
|
| 781 |
+
"step": 25792
|
| 782 |
+
},
|
| 783 |
+
{
|
| 784 |
+
"epoch": 9.464788732394366,
|
| 785 |
+
"grad_norm": 0.9726517796516418,
|
| 786 |
+
"learning_rate": 3.315324641599434e-05,
|
| 787 |
+
"loss": 3.5294,
|
| 788 |
+
"step": 26208
|
| 789 |
+
},
|
| 790 |
+
{
|
| 791 |
+
"epoch": 9.615023474178404,
|
| 792 |
+
"grad_norm": 0.954593300819397,
|
| 793 |
+
"learning_rate": 3.161528096313964e-05,
|
| 794 |
+
"loss": 3.5242,
|
| 795 |
+
"step": 26624
|
| 796 |
+
},
|
| 797 |
+
{
|
| 798 |
+
"epoch": 9.751173708920188,
|
| 799 |
+
"eval_g2l_cer": 48.3196,
|
| 800 |
+
"eval_g2l_gen_len": 3.0196,
|
| 801 |
+
"eval_g2l_rouge1": 41.1733,
|
| 802 |
+
"eval_g2l_rouge2": 33.4761,
|
| 803 |
+
"eval_g2l_rougeL": 41.172,
|
| 804 |
+
"eval_g2l_rougeLsum": 41.1111,
|
| 805 |
+
"eval_l2ex_cer": 86.3469,
|
| 806 |
+
"eval_l2ex_gen_len": 21.333,
|
| 807 |
+
"eval_l2ex_rouge1": 28.6196,
|
| 808 |
+
"eval_l2ex_rouge2": 12.797,
|
| 809 |
+
"eval_l2ex_rougeL": 25.331,
|
| 810 |
+
"eval_l2ex_rougeLsum": 25.3251,
|
| 811 |
+
"eval_l2g_cer": 71.8519,
|
| 812 |
+
"eval_l2g_gen_len": 15.5771,
|
| 813 |
+
"eval_l2g_rouge1": 38.9877,
|
| 814 |
+
"eval_l2g_rouge2": 26.3016,
|
| 815 |
+
"eval_l2g_rougeL": 36.97,
|
| 816 |
+
"eval_l2g_rougeLsum": 37.0109,
|
| 817 |
+
"eval_loss": 3.5751187801361084,
|
| 818 |
+
"eval_runtime": 190.5769,
|
| 819 |
+
"eval_samples_per_second": 52.058,
|
| 820 |
+
"eval_steps_per_second": 1.632,
|
| 821 |
+
"step": 27001
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 9.765258215962442,
|
| 825 |
+
"grad_norm": 0.7817335724830627,
|
| 826 |
+
"learning_rate": 3.00977615630722e-05,
|
| 827 |
+
"loss": 3.5332,
|
| 828 |
+
"step": 27040
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 9.915492957746478,
|
| 832 |
+
"grad_norm": 0.8576836585998535,
|
| 833 |
+
"learning_rate": 2.8602353241258667e-05,
|
| 834 |
+
"loss": 3.5247,
|
| 835 |
+
"step": 27456
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 10.065727699530516,
|
| 839 |
+
"grad_norm": 0.924045741558075,
|
| 840 |
+
"learning_rate": 2.7130696762844198e-05,
|
| 841 |
+
"loss": 3.5171,
|
| 842 |
+
"step": 27872
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 10.215962441314554,
|
| 846 |
+
"grad_norm": 0.9701129198074341,
|
| 847 |
+
"learning_rate": 2.568440683240166e-05,
|
| 848 |
+
"loss": 3.4886,
|
| 849 |
+
"step": 28288
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 10.366197183098592,
|
| 853 |
+
"grad_norm": 0.8473976850509644,
|
| 854 |
+
"learning_rate": 2.426507032227427e-05,
|
| 855 |
+
"loss": 3.5134,
|
| 856 |
+
"step": 28704
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 10.501263994221741,
|
| 860 |
+
"eval_g2l_cer": 48.8336,
|
| 861 |
+
"eval_g2l_gen_len": 3.0502,
|
| 862 |
+
"eval_g2l_rouge1": 41.0241,
|
| 863 |
+
"eval_g2l_rouge2": 33.2994,
|
| 864 |
+
"eval_g2l_rougeL": 41.0374,
|
| 865 |
+
"eval_g2l_rougeLsum": 40.9554,
|
| 866 |
+
"eval_l2ex_cer": 85.2795,
|
| 867 |
+
"eval_l2ex_gen_len": 21.6999,
|
| 868 |
+
"eval_l2ex_rouge1": 28.6576,
|
| 869 |
+
"eval_l2ex_rouge2": 12.5848,
|
| 870 |
+
"eval_l2ex_rougeL": 25.1057,
|
| 871 |
+
"eval_l2ex_rougeLsum": 25.1478,
|
| 872 |
+
"eval_l2g_cer": 71.5555,
|
| 873 |
+
"eval_l2g_gen_len": 15.5923,
|
| 874 |
+
"eval_l2g_rouge1": 39.111,
|
| 875 |
+
"eval_l2g_rouge2": 26.3632,
|
| 876 |
+
"eval_l2g_rougeL": 37.134,
|
| 877 |
+
"eval_l2g_rougeLsum": 37.1562,
|
| 878 |
+
"eval_loss": 3.5716097354888916,
|
| 879 |
+
"eval_runtime": 190.1354,
|
| 880 |
+
"eval_samples_per_second": 52.179,
|
| 881 |
+
"eval_steps_per_second": 1.636,
|
| 882 |
+
"step": 29078
|
| 883 |
+
},
|
| 884 |
+
{
|
| 885 |
+
"epoch": 10.51643192488263,
|
| 886 |
+
"grad_norm": 0.9222161769866943,
|
| 887 |
+
"learning_rate": 2.2874244531456016e-05,
|
| 888 |
+
"loss": 3.4995,
|
| 889 |
+
"step": 29120
|
| 890 |
+
},
|
| 891 |
+
{
|
| 892 |
+
"epoch": 10.666666666666666,
|
| 893 |
+
"grad_norm": 0.8834406137466431,
|
| 894 |
+
"learning_rate": 2.1513455476919875e-05,
|
| 895 |
+
"loss": 3.5005,
|
| 896 |
+
"step": 29536
|
| 897 |
+
},
|
| 898 |
+
{
|
| 899 |
+
"epoch": 10.816901408450704,
|
| 900 |
+
"grad_norm": 1.2534151077270508,
|
| 901 |
+
"learning_rate": 2.0184196219268805e-05,
|
| 902 |
+
"loss": 3.4956,
|
| 903 |
+
"step": 29952
|
| 904 |
+
},
|
| 905 |
+
{
|
| 906 |
+
"epoch": 10.967136150234742,
|
| 907 |
+
"grad_norm": 1.0579476356506348,
|
| 908 |
+
"learning_rate": 1.8887925224546575e-05,
|
| 909 |
+
"loss": 3.4984,
|
| 910 |
+
"step": 30368
|
| 911 |
+
},
|
| 912 |
+
{
|
| 913 |
+
"epoch": 11.11737089201878,
|
| 914 |
+
"grad_norm": 0.9352797269821167,
|
| 915 |
+
"learning_rate": 1.7626064764005655e-05,
|
| 916 |
+
"loss": 3.4891,
|
| 917 |
+
"step": 30784
|
| 918 |
+
},
|
| 919 |
+
{
|
| 920 |
+
"epoch": 11.251354279523294,
|
| 921 |
+
"eval_g2l_cer": 48.1779,
|
| 922 |
+
"eval_g2l_gen_len": 3.0241,
|
| 923 |
+
"eval_g2l_rouge1": 41.3076,
|
| 924 |
+
"eval_g2l_rouge2": 33.5874,
|
| 925 |
+
"eval_g2l_rougeL": 41.3381,
|
| 926 |
+
"eval_g2l_rougeLsum": 41.2834,
|
| 927 |
+
"eval_l2ex_cer": 86.303,
|
| 928 |
+
"eval_l2ex_gen_len": 21.6927,
|
| 929 |
+
"eval_l2ex_rouge1": 28.5306,
|
| 930 |
+
"eval_l2ex_rouge2": 12.66,
|
| 931 |
+
"eval_l2ex_rougeL": 25.107,
|
| 932 |
+
"eval_l2ex_rougeLsum": 25.1229,
|
| 933 |
+
"eval_l2g_cer": 71.7607,
|
| 934 |
+
"eval_l2g_gen_len": 15.6002,
|
| 935 |
+
"eval_l2g_rouge1": 39.1998,
|
| 936 |
+
"eval_l2g_rouge2": 26.5146,
|
| 937 |
+
"eval_l2g_rougeL": 37.2299,
|
| 938 |
+
"eval_l2g_rougeLsum": 37.2583,
|
| 939 |
+
"eval_loss": 3.5692920684814453,
|
| 940 |
+
"eval_runtime": 191.2935,
|
| 941 |
+
"eval_samples_per_second": 51.863,
|
| 942 |
+
"eval_steps_per_second": 1.626,
|
| 943 |
+
"step": 31155
|
| 944 |
+
},
|
| 945 |
+
{
|
| 946 |
+
"epoch": 11.267605633802816,
|
| 947 |
+
"grad_norm": 0.8403520584106445,
|
| 948 |
+
"learning_rate": 1.6399999353588347e-05,
|
| 949 |
+
"loss": 3.4762,
|
| 950 |
+
"step": 31200
|
| 951 |
+
},
|
| 952 |
+
{
|
| 953 |
+
"epoch": 11.417840375586854,
|
| 954 |
+
"grad_norm": 0.8685266375541687,
|
| 955 |
+
"learning_rate": 1.5211074234832911e-05,
|
| 956 |
+
"loss": 3.491,
|
| 957 |
+
"step": 31616
|
| 958 |
+
},
|
| 959 |
+
{
|
| 960 |
+
"epoch": 11.568075117370892,
|
| 961 |
+
"grad_norm": 0.8662200570106506,
|
| 962 |
+
"learning_rate": 1.4060593898871712e-05,
|
| 963 |
+
"loss": 3.4818,
|
| 964 |
+
"step": 32032
|
| 965 |
+
},
|
| 966 |
+
{
|
| 967 |
+
"epoch": 11.71830985915493,
|
| 968 |
+
"grad_norm": 0.915972888469696,
|
| 969 |
+
"learning_rate": 1.2949820655140888e-05,
|
| 970 |
+
"loss": 3.4729,
|
| 971 |
+
"step": 32448
|
| 972 |
+
},
|
| 973 |
+
{
|
| 974 |
+
"epoch": 11.868544600938968,
|
| 975 |
+
"grad_norm": 0.9427916407585144,
|
| 976 |
+
"learning_rate": 1.187997324637174e-05,
|
| 977 |
+
"loss": 3.4837,
|
| 978 |
+
"step": 32864
|
| 979 |
+
},
|
| 980 |
+
{
|
| 981 |
+
"epoch": 12.001444564824846,
|
| 982 |
+
"eval_g2l_cer": 48.4635,
|
| 983 |
+
"eval_g2l_gen_len": 3.0374,
|
| 984 |
+
"eval_g2l_rouge1": 41.42,
|
| 985 |
+
"eval_g2l_rouge2": 33.7871,
|
| 986 |
+
"eval_g2l_rougeL": 41.41,
|
| 987 |
+
"eval_g2l_rougeLsum": 41.3653,
|
| 988 |
+
"eval_l2ex_cer": 84.6873,
|
| 989 |
+
"eval_l2ex_gen_len": 21.5406,
|
| 990 |
+
"eval_l2ex_rouge1": 28.7533,
|
| 991 |
+
"eval_l2ex_rouge2": 12.7721,
|
| 992 |
+
"eval_l2ex_rougeL": 25.3715,
|
| 993 |
+
"eval_l2ex_rougeLsum": 25.3817,
|
| 994 |
+
"eval_l2g_cer": 71.4847,
|
| 995 |
+
"eval_l2g_gen_len": 15.5437,
|
| 996 |
+
"eval_l2g_rouge1": 39.2147,
|
| 997 |
+
"eval_l2g_rouge2": 26.5099,
|
| 998 |
+
"eval_l2g_rougeL": 37.2362,
|
| 999 |
+
"eval_l2g_rougeLsum": 37.2641,
|
| 1000 |
+
"eval_loss": 3.5653076171875,
|
| 1001 |
+
"eval_runtime": 189.8727,
|
| 1002 |
+
"eval_samples_per_second": 52.251,
|
| 1003 |
+
"eval_steps_per_second": 1.638,
|
| 1004 |
+
"step": 33232
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 12.018779342723004,
|
| 1008 |
+
"grad_norm": 0.8259687423706055,
|
| 1009 |
+
"learning_rate": 1.0852225511383663e-05,
|
| 1010 |
+
"loss": 3.4764,
|
| 1011 |
+
"step": 33280
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 12.169014084507042,
|
| 1015 |
+
"grad_norm": 0.904097855091095,
|
| 1016 |
+
"learning_rate": 9.86770509714574e-06,
|
| 1017 |
+
"loss": 3.4791,
|
| 1018 |
+
"step": 33696
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"epoch": 12.31924882629108,
|
| 1022 |
+
"grad_norm": 0.9662612080574036,
|
| 1023 |
+
"learning_rate": 8.927492221520133e-06,
|
| 1024 |
+
"loss": 3.4593,
|
| 1025 |
+
"step": 34112
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 12.469483568075118,
|
| 1029 |
+
"grad_norm": 0.9324942231178284,
|
| 1030 |
+
"learning_rate": 8.032618488044715e-06,
|
| 1031 |
+
"loss": 3.4564,
|
| 1032 |
+
"step": 34528
|
| 1033 |
+
},
|
| 1034 |
+
{
|
| 1035 |
+
"epoch": 12.619718309859154,
|
| 1036 |
+
"grad_norm": 0.9966897964477539,
|
| 1037 |
+
"learning_rate": 7.184065754055608e-06,
|
| 1038 |
+
"loss": 3.4576,
|
| 1039 |
+
"step": 34944
|
| 1040 |
+
},
|
| 1041 |
+
{
|
| 1042 |
+
"epoch": 12.751534850126399,
|
| 1043 |
+
"eval_g2l_cer": 47.8718,
|
| 1044 |
+
"eval_g2l_gen_len": 3.0243,
|
| 1045 |
+
"eval_g2l_rouge1": 41.399,
|
| 1046 |
+
"eval_g2l_rouge2": 33.8189,
|
| 1047 |
+
"eval_g2l_rougeL": 41.4105,
|
| 1048 |
+
"eval_g2l_rougeLsum": 41.3515,
|
| 1049 |
+
"eval_l2ex_cer": 84.0524,
|
| 1050 |
+
"eval_l2ex_gen_len": 21.0206,
|
| 1051 |
+
"eval_l2ex_rouge1": 28.7814,
|
| 1052 |
+
"eval_l2ex_rouge2": 12.7663,
|
| 1053 |
+
"eval_l2ex_rougeL": 25.3724,
|
| 1054 |
+
"eval_l2ex_rougeLsum": 25.3895,
|
| 1055 |
+
"eval_l2g_cer": 71.6622,
|
| 1056 |
+
"eval_l2g_gen_len": 15.563,
|
| 1057 |
+
"eval_l2g_rouge1": 39.1666,
|
| 1058 |
+
"eval_l2g_rouge2": 26.5275,
|
| 1059 |
+
"eval_l2g_rougeL": 37.1881,
|
| 1060 |
+
"eval_l2g_rougeLsum": 37.2249,
|
| 1061 |
+
"eval_loss": 3.564103841781616,
|
| 1062 |
+
"eval_runtime": 190.2806,
|
| 1063 |
+
"eval_samples_per_second": 52.139,
|
| 1064 |
+
"eval_steps_per_second": 1.634,
|
| 1065 |
+
"step": 35309
|
| 1066 |
+
},
|
| 1067 |
+
{
|
| 1068 |
+
"epoch": 12.769953051643192,
|
| 1069 |
+
"grad_norm": 1.0099953413009644,
|
| 1070 |
+
"learning_rate": 6.382765053391182e-06,
|
| 1071 |
+
"loss": 3.4757,
|
| 1072 |
+
"step": 35360
|
| 1073 |
+
},
|
| 1074 |
+
{
|
| 1075 |
+
"epoch": 12.92018779342723,
|
| 1076 |
+
"grad_norm": 0.8347458243370056,
|
| 1077 |
+
"learning_rate": 5.629595574859816e-06,
|
| 1078 |
+
"loss": 3.4814,
|
| 1079 |
+
"step": 35776
|
| 1080 |
+
},
|
| 1081 |
+
{
|
| 1082 |
+
"epoch": 13.070422535211268,
|
| 1083 |
+
"grad_norm": 0.8532468676567078,
|
| 1084 |
+
"learning_rate": 4.925383697592043e-06,
|
| 1085 |
+
"loss": 3.4667,
|
| 1086 |
+
"step": 36192
|
| 1087 |
+
},
|
| 1088 |
+
{
|
| 1089 |
+
"epoch": 13.220657276995306,
|
| 1090 |
+
"grad_norm": 0.8852038383483887,
|
| 1091 |
+
"learning_rate": 4.2709020843357075e-06,
|
| 1092 |
+
"loss": 3.4512,
|
| 1093 |
+
"step": 36608
|
| 1094 |
+
},
|
| 1095 |
+
{
|
| 1096 |
+
"epoch": 13.370892018779342,
|
| 1097 |
+
"grad_norm": 1.058424472808838,
|
| 1098 |
+
"learning_rate": 3.666868833688726e-06,
|
| 1099 |
+
"loss": 3.4616,
|
| 1100 |
+
"step": 37024
|
| 1101 |
+
},
|
| 1102 |
+
{
|
| 1103 |
+
"epoch": 13.501625135427952,
|
| 1104 |
+
"eval_g2l_cer": 47.8581,
|
| 1105 |
+
"eval_g2l_gen_len": 3.0221,
|
| 1106 |
+
"eval_g2l_rouge1": 41.4693,
|
| 1107 |
+
"eval_g2l_rouge2": 33.7773,
|
| 1108 |
+
"eval_g2l_rougeL": 41.4822,
|
| 1109 |
+
"eval_g2l_rougeLsum": 41.4356,
|
| 1110 |
+
"eval_l2ex_cer": 84.3083,
|
| 1111 |
+
"eval_l2ex_gen_len": 21.0319,
|
| 1112 |
+
"eval_l2ex_rouge1": 28.654,
|
| 1113 |
+
"eval_l2ex_rouge2": 12.8413,
|
| 1114 |
+
"eval_l2ex_rougeL": 25.3941,
|
| 1115 |
+
"eval_l2ex_rougeLsum": 25.4326,
|
| 1116 |
+
"eval_l2g_cer": 71.0018,
|
| 1117 |
+
"eval_l2g_gen_len": 15.3407,
|
| 1118 |
+
"eval_l2g_rouge1": 39.2009,
|
| 1119 |
+
"eval_l2g_rouge2": 26.5422,
|
| 1120 |
+
"eval_l2g_rougeL": 37.2433,
|
| 1121 |
+
"eval_l2g_rougeLsum": 37.2693,
|
| 1122 |
+
"eval_loss": 3.5637874603271484,
|
| 1123 |
+
"eval_runtime": 187.7571,
|
| 1124 |
+
"eval_samples_per_second": 52.84,
|
| 1125 |
+
"eval_steps_per_second": 1.656,
|
| 1126 |
+
"step": 37386
|
| 1127 |
+
}
|
| 1128 |
+
],
|
| 1129 |
+
"logging_steps": 416,
|
| 1130 |
+
"max_steps": 41535,
|
| 1131 |
+
"num_input_tokens_seen": 0,
|
| 1132 |
+
"num_train_epochs": 15,
|
| 1133 |
+
"save_steps": 2077,
|
| 1134 |
+
"total_flos": 7.17240637379838e+17,
|
| 1135 |
+
"train_batch_size": 16,
|
| 1136 |
+
"trial_name": null,
|
| 1137 |
+
"trial_params": null
|
| 1138 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4d7cd326d002fd124e7b2f63ea7ced82382a90306e419db899b4d3a0d83186bf
|
| 3 |
+
size 5176
|