modellen
Browse files- config.json +32 -0
- generation_config.json +6 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +5 -0
- spiece.model +3 -0
- tokenizer_config.json +11 -0
- trainer_state.json +1158 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "north/t5_base_NCC_lm",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"T5ForConditionalGeneration"
|
| 5 |
+
],
|
| 6 |
+
"d_ff": 2048,
|
| 7 |
+
"d_kv": 64,
|
| 8 |
+
"d_model": 768,
|
| 9 |
+
"decoder_start_token_id": 0,
|
| 10 |
+
"dense_act_fn": "gelu_new",
|
| 11 |
+
"dropout_rate": 0.1,
|
| 12 |
+
"eos_token_id": 1,
|
| 13 |
+
"feed_forward_proj": "gated-gelu",
|
| 14 |
+
"initializer_factor": 1.0,
|
| 15 |
+
"is_encoder_decoder": true,
|
| 16 |
+
"is_gated_act": true,
|
| 17 |
+
"layer_norm_epsilon": 1e-06,
|
| 18 |
+
"model_type": "t5",
|
| 19 |
+
"num_decoder_layers": 12,
|
| 20 |
+
"num_heads": 12,
|
| 21 |
+
"num_layers": 12,
|
| 22 |
+
"output_past": true,
|
| 23 |
+
"pad_token_id": 0,
|
| 24 |
+
"relative_attention_max_distance": 128,
|
| 25 |
+
"relative_attention_num_buckets": 32,
|
| 26 |
+
"tie_word_embeddings": false,
|
| 27 |
+
"tokenizer_class": "T5Tokenizer",
|
| 28 |
+
"torch_dtype": "float32",
|
| 29 |
+
"transformers_version": "4.27.0.dev0",
|
| 30 |
+
"use_cache": true,
|
| 31 |
+
"vocab_size": 250112
|
| 32 |
+
}
|
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": "4.27.0.dev0"
|
| 6 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d72cc8af03371eaabcee9b4778bd0a5e1e398708e20ddddc82829d249dd732b9
|
| 3 |
+
size 2329702581
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"eos_token": "</s>",
|
| 3 |
+
"pad_token": "<pad>",
|
| 4 |
+
"unk_token": "<unk>"
|
| 5 |
+
}
|
spiece.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ef78f86560d809067d12bac6c09f19a462cb3af3f54d2b8acbba26e1433125d6
|
| 3 |
+
size 4309802
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": null,
|
| 3 |
+
"eos_token": "</s>",
|
| 4 |
+
"extra_ids": 0,
|
| 5 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 6 |
+
"pad_token": "<pad>",
|
| 7 |
+
"sp_model_kwargs": {},
|
| 8 |
+
"special_tokens_map_file": "/home/patrick/.cache/torch/transformers/685ac0ca8568ec593a48b61b0a3c272beee9bc194a3c7241d15dcadb5f875e53.f76030f3ec1b96a8199b2593390c610e76ca8028ef3d24680000619ffb646276",
|
| 9 |
+
"tokenizer_class": "T5Tokenizer",
|
| 10 |
+
"unk_token": "<unk>"
|
| 11 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1158 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 2.039487600326538,
|
| 3 |
+
"best_model_checkpoint": "t5-base-cnndaily/checkpoint-3680",
|
| 4 |
+
"epoch": 19.99728997289973,
|
| 5 |
+
"global_step": 3680,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.14,
|
| 12 |
+
"learning_rate": 4.9660326086956525e-05,
|
| 13 |
+
"loss": 4.2518,
|
| 14 |
+
"step": 25
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.27,
|
| 18 |
+
"learning_rate": 4.932065217391305e-05,
|
| 19 |
+
"loss": 3.2161,
|
| 20 |
+
"step": 50
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.41,
|
| 24 |
+
"learning_rate": 4.898097826086957e-05,
|
| 25 |
+
"loss": 2.9499,
|
| 26 |
+
"step": 75
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.54,
|
| 30 |
+
"learning_rate": 4.8641304347826086e-05,
|
| 31 |
+
"loss": 2.8424,
|
| 32 |
+
"step": 100
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.68,
|
| 36 |
+
"learning_rate": 4.8301630434782615e-05,
|
| 37 |
+
"loss": 2.7775,
|
| 38 |
+
"step": 125
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.81,
|
| 42 |
+
"learning_rate": 4.796195652173913e-05,
|
| 43 |
+
"loss": 2.7339,
|
| 44 |
+
"step": 150
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.95,
|
| 48 |
+
"learning_rate": 4.7622282608695654e-05,
|
| 49 |
+
"loss": 2.7173,
|
| 50 |
+
"step": 175
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 1.0,
|
| 54 |
+
"eval_gen_len": 68.36778372289496,
|
| 55 |
+
"eval_loss": 2.237959384918213,
|
| 56 |
+
"eval_rouge1": 26.4764,
|
| 57 |
+
"eval_rouge2": 9.4302,
|
| 58 |
+
"eval_rougeL": 19.7562,
|
| 59 |
+
"eval_rougeLsum": 24.4771,
|
| 60 |
+
"eval_runtime": 180.353,
|
| 61 |
+
"eval_samples_per_second": 19.689,
|
| 62 |
+
"eval_steps_per_second": 0.615,
|
| 63 |
+
"step": 184
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 1.09,
|
| 67 |
+
"learning_rate": 4.7282608695652177e-05,
|
| 68 |
+
"loss": 2.7233,
|
| 69 |
+
"step": 200
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 1.22,
|
| 73 |
+
"learning_rate": 4.69429347826087e-05,
|
| 74 |
+
"loss": 2.6398,
|
| 75 |
+
"step": 225
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 1.36,
|
| 79 |
+
"learning_rate": 4.660326086956522e-05,
|
| 80 |
+
"loss": 2.6332,
|
| 81 |
+
"step": 250
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 1.49,
|
| 85 |
+
"learning_rate": 4.6263586956521744e-05,
|
| 86 |
+
"loss": 2.6027,
|
| 87 |
+
"step": 275
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 1.63,
|
| 91 |
+
"learning_rate": 4.592391304347826e-05,
|
| 92 |
+
"loss": 2.5922,
|
| 93 |
+
"step": 300
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 1.76,
|
| 97 |
+
"learning_rate": 4.558423913043478e-05,
|
| 98 |
+
"loss": 2.581,
|
| 99 |
+
"step": 325
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 1.9,
|
| 103 |
+
"learning_rate": 4.5244565217391305e-05,
|
| 104 |
+
"loss": 2.5683,
|
| 105 |
+
"step": 350
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 2.0,
|
| 109 |
+
"eval_gen_len": 70.79273444100254,
|
| 110 |
+
"eval_loss": 2.177700996398926,
|
| 111 |
+
"eval_rouge1": 26.9803,
|
| 112 |
+
"eval_rouge2": 9.711,
|
| 113 |
+
"eval_rougeL": 20.1842,
|
| 114 |
+
"eval_rougeLsum": 25.0146,
|
| 115 |
+
"eval_runtime": 180.5228,
|
| 116 |
+
"eval_samples_per_second": 19.671,
|
| 117 |
+
"eval_steps_per_second": 0.615,
|
| 118 |
+
"step": 368
|
| 119 |
+
},
|
| 120 |
+
{
|
| 121 |
+
"epoch": 2.04,
|
| 122 |
+
"learning_rate": 4.490489130434783e-05,
|
| 123 |
+
"loss": 2.5997,
|
| 124 |
+
"step": 375
|
| 125 |
+
},
|
| 126 |
+
{
|
| 127 |
+
"epoch": 2.17,
|
| 128 |
+
"learning_rate": 4.456521739130435e-05,
|
| 129 |
+
"loss": 2.5445,
|
| 130 |
+
"step": 400
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 2.31,
|
| 134 |
+
"learning_rate": 4.422554347826087e-05,
|
| 135 |
+
"loss": 2.5334,
|
| 136 |
+
"step": 425
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 2.44,
|
| 140 |
+
"learning_rate": 4.388586956521739e-05,
|
| 141 |
+
"loss": 2.504,
|
| 142 |
+
"step": 450
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 2.58,
|
| 146 |
+
"learning_rate": 4.354619565217392e-05,
|
| 147 |
+
"loss": 2.521,
|
| 148 |
+
"step": 475
|
| 149 |
+
},
|
| 150 |
+
{
|
| 151 |
+
"epoch": 2.72,
|
| 152 |
+
"learning_rate": 4.3206521739130434e-05,
|
| 153 |
+
"loss": 2.515,
|
| 154 |
+
"step": 500
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 2.85,
|
| 158 |
+
"learning_rate": 4.286684782608696e-05,
|
| 159 |
+
"loss": 2.499,
|
| 160 |
+
"step": 525
|
| 161 |
+
},
|
| 162 |
+
{
|
| 163 |
+
"epoch": 2.99,
|
| 164 |
+
"learning_rate": 4.252717391304348e-05,
|
| 165 |
+
"loss": 2.4764,
|
| 166 |
+
"step": 550
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 3.0,
|
| 170 |
+
"eval_gen_len": 70.5550549141087,
|
| 171 |
+
"eval_loss": 2.149622917175293,
|
| 172 |
+
"eval_rouge1": 27.4931,
|
| 173 |
+
"eval_rouge2": 9.9982,
|
| 174 |
+
"eval_rougeL": 20.4503,
|
| 175 |
+
"eval_rougeLsum": 25.5179,
|
| 176 |
+
"eval_runtime": 181.4064,
|
| 177 |
+
"eval_samples_per_second": 19.575,
|
| 178 |
+
"eval_steps_per_second": 0.612,
|
| 179 |
+
"step": 552
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 3.12,
|
| 183 |
+
"learning_rate": 4.21875e-05,
|
| 184 |
+
"loss": 2.5205,
|
| 185 |
+
"step": 575
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 3.26,
|
| 189 |
+
"learning_rate": 4.1847826086956525e-05,
|
| 190 |
+
"loss": 2.4676,
|
| 191 |
+
"step": 600
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 3.4,
|
| 195 |
+
"learning_rate": 4.150815217391305e-05,
|
| 196 |
+
"loss": 2.4766,
|
| 197 |
+
"step": 625
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 3.53,
|
| 201 |
+
"learning_rate": 4.116847826086957e-05,
|
| 202 |
+
"loss": 2.4496,
|
| 203 |
+
"step": 650
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 3.67,
|
| 207 |
+
"learning_rate": 4.0828804347826086e-05,
|
| 208 |
+
"loss": 2.4475,
|
| 209 |
+
"step": 675
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 3.8,
|
| 213 |
+
"learning_rate": 4.0489130434782615e-05,
|
| 214 |
+
"loss": 2.4433,
|
| 215 |
+
"step": 700
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 3.94,
|
| 219 |
+
"learning_rate": 4.014945652173913e-05,
|
| 220 |
+
"loss": 2.4365,
|
| 221 |
+
"step": 725
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 4.0,
|
| 225 |
+
"eval_gen_len": 70.99042523232892,
|
| 226 |
+
"eval_loss": 2.124873161315918,
|
| 227 |
+
"eval_rouge1": 27.8843,
|
| 228 |
+
"eval_rouge2": 10.2961,
|
| 229 |
+
"eval_rougeL": 20.7113,
|
| 230 |
+
"eval_rougeLsum": 25.8998,
|
| 231 |
+
"eval_runtime": 179.7697,
|
| 232 |
+
"eval_samples_per_second": 19.753,
|
| 233 |
+
"eval_steps_per_second": 0.617,
|
| 234 |
+
"step": 736
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 4.08,
|
| 238 |
+
"learning_rate": 3.9809782608695654e-05,
|
| 239 |
+
"loss": 2.4847,
|
| 240 |
+
"step": 750
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 4.21,
|
| 244 |
+
"learning_rate": 3.9470108695652176e-05,
|
| 245 |
+
"loss": 2.4137,
|
| 246 |
+
"step": 775
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 4.35,
|
| 250 |
+
"learning_rate": 3.91304347826087e-05,
|
| 251 |
+
"loss": 2.4275,
|
| 252 |
+
"step": 800
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 4.48,
|
| 256 |
+
"learning_rate": 3.8790760869565215e-05,
|
| 257 |
+
"loss": 2.4068,
|
| 258 |
+
"step": 825
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 4.62,
|
| 262 |
+
"learning_rate": 3.8451086956521744e-05,
|
| 263 |
+
"loss": 2.4144,
|
| 264 |
+
"step": 850
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 4.75,
|
| 268 |
+
"learning_rate": 3.811141304347826e-05,
|
| 269 |
+
"loss": 2.4101,
|
| 270 |
+
"step": 875
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 4.89,
|
| 274 |
+
"learning_rate": 3.777173913043478e-05,
|
| 275 |
+
"loss": 2.3932,
|
| 276 |
+
"step": 900
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 5.0,
|
| 280 |
+
"eval_gen_len": 70.42692199380456,
|
| 281 |
+
"eval_loss": 2.1084039211273193,
|
| 282 |
+
"eval_rouge1": 28.2543,
|
| 283 |
+
"eval_rouge2": 10.433,
|
| 284 |
+
"eval_rougeL": 20.9026,
|
| 285 |
+
"eval_rougeLsum": 26.2599,
|
| 286 |
+
"eval_runtime": 178.1314,
|
| 287 |
+
"eval_samples_per_second": 19.935,
|
| 288 |
+
"eval_steps_per_second": 0.623,
|
| 289 |
+
"step": 920
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 5.03,
|
| 293 |
+
"learning_rate": 3.7432065217391305e-05,
|
| 294 |
+
"loss": 2.4457,
|
| 295 |
+
"step": 925
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 5.16,
|
| 299 |
+
"learning_rate": 3.709239130434783e-05,
|
| 300 |
+
"loss": 2.3702,
|
| 301 |
+
"step": 950
|
| 302 |
+
},
|
| 303 |
+
{
|
| 304 |
+
"epoch": 5.3,
|
| 305 |
+
"learning_rate": 3.675271739130435e-05,
|
| 306 |
+
"loss": 2.3941,
|
| 307 |
+
"step": 975
|
| 308 |
+
},
|
| 309 |
+
{
|
| 310 |
+
"epoch": 5.43,
|
| 311 |
+
"learning_rate": 3.641304347826087e-05,
|
| 312 |
+
"loss": 2.3999,
|
| 313 |
+
"step": 1000
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 5.57,
|
| 317 |
+
"learning_rate": 3.607336956521739e-05,
|
| 318 |
+
"loss": 2.3703,
|
| 319 |
+
"step": 1025
|
| 320 |
+
},
|
| 321 |
+
{
|
| 322 |
+
"epoch": 5.7,
|
| 323 |
+
"learning_rate": 3.573369565217392e-05,
|
| 324 |
+
"loss": 2.3707,
|
| 325 |
+
"step": 1050
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 5.84,
|
| 329 |
+
"learning_rate": 3.5394021739130434e-05,
|
| 330 |
+
"loss": 2.3716,
|
| 331 |
+
"step": 1075
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 5.98,
|
| 335 |
+
"learning_rate": 3.505434782608696e-05,
|
| 336 |
+
"loss": 2.3815,
|
| 337 |
+
"step": 1100
|
| 338 |
+
},
|
| 339 |
+
{
|
| 340 |
+
"epoch": 6.0,
|
| 341 |
+
"eval_gen_len": 70.43227259926782,
|
| 342 |
+
"eval_loss": 2.096766948699951,
|
| 343 |
+
"eval_rouge1": 28.4855,
|
| 344 |
+
"eval_rouge2": 10.5771,
|
| 345 |
+
"eval_rougeL": 21.0169,
|
| 346 |
+
"eval_rougeLsum": 26.4552,
|
| 347 |
+
"eval_runtime": 179.9467,
|
| 348 |
+
"eval_samples_per_second": 19.734,
|
| 349 |
+
"eval_steps_per_second": 0.617,
|
| 350 |
+
"step": 1104
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 6.11,
|
| 354 |
+
"learning_rate": 3.471467391304348e-05,
|
| 355 |
+
"loss": 2.391,
|
| 356 |
+
"step": 1125
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 6.25,
|
| 360 |
+
"learning_rate": 3.4375e-05,
|
| 361 |
+
"loss": 2.3547,
|
| 362 |
+
"step": 1150
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 6.38,
|
| 366 |
+
"learning_rate": 3.4035326086956525e-05,
|
| 367 |
+
"loss": 2.3611,
|
| 368 |
+
"step": 1175
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 6.52,
|
| 372 |
+
"learning_rate": 3.369565217391305e-05,
|
| 373 |
+
"loss": 2.3495,
|
| 374 |
+
"step": 1200
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 6.66,
|
| 378 |
+
"learning_rate": 3.335597826086957e-05,
|
| 379 |
+
"loss": 2.357,
|
| 380 |
+
"step": 1225
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 6.79,
|
| 384 |
+
"learning_rate": 3.3016304347826086e-05,
|
| 385 |
+
"loss": 2.3457,
|
| 386 |
+
"step": 1250
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 6.93,
|
| 390 |
+
"learning_rate": 3.2676630434782615e-05,
|
| 391 |
+
"loss": 2.35,
|
| 392 |
+
"step": 1275
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 7.0,
|
| 396 |
+
"eval_gen_len": 69.14080540692763,
|
| 397 |
+
"eval_loss": 2.0887129306793213,
|
| 398 |
+
"eval_rouge1": 28.7887,
|
| 399 |
+
"eval_rouge2": 10.6794,
|
| 400 |
+
"eval_rougeL": 21.2061,
|
| 401 |
+
"eval_rougeLsum": 26.7346,
|
| 402 |
+
"eval_runtime": 179.9375,
|
| 403 |
+
"eval_samples_per_second": 19.735,
|
| 404 |
+
"eval_steps_per_second": 0.617,
|
| 405 |
+
"step": 1288
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 7.07,
|
| 409 |
+
"learning_rate": 3.233695652173913e-05,
|
| 410 |
+
"loss": 2.3907,
|
| 411 |
+
"step": 1300
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 7.2,
|
| 415 |
+
"learning_rate": 3.1997282608695654e-05,
|
| 416 |
+
"loss": 2.329,
|
| 417 |
+
"step": 1325
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 7.34,
|
| 421 |
+
"learning_rate": 3.1657608695652176e-05,
|
| 422 |
+
"loss": 2.3296,
|
| 423 |
+
"step": 1350
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 7.47,
|
| 427 |
+
"learning_rate": 3.13179347826087e-05,
|
| 428 |
+
"loss": 2.3408,
|
| 429 |
+
"step": 1375
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 7.61,
|
| 433 |
+
"learning_rate": 3.0978260869565215e-05,
|
| 434 |
+
"loss": 2.3199,
|
| 435 |
+
"step": 1400
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 7.74,
|
| 439 |
+
"learning_rate": 3.0638586956521744e-05,
|
| 440 |
+
"loss": 2.3183,
|
| 441 |
+
"step": 1425
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 7.88,
|
| 445 |
+
"learning_rate": 3.029891304347826e-05,
|
| 446 |
+
"loss": 2.3331,
|
| 447 |
+
"step": 1450
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 8.0,
|
| 451 |
+
"eval_gen_len": 69.29850746268657,
|
| 452 |
+
"eval_loss": 2.0796895027160645,
|
| 453 |
+
"eval_rouge1": 28.8309,
|
| 454 |
+
"eval_rouge2": 10.7142,
|
| 455 |
+
"eval_rougeL": 21.2091,
|
| 456 |
+
"eval_rougeLsum": 26.791,
|
| 457 |
+
"eval_runtime": 178.7689,
|
| 458 |
+
"eval_samples_per_second": 19.864,
|
| 459 |
+
"eval_steps_per_second": 0.621,
|
| 460 |
+
"step": 1472
|
| 461 |
+
},
|
| 462 |
+
{
|
| 463 |
+
"epoch": 8.02,
|
| 464 |
+
"learning_rate": 2.9959239130434786e-05,
|
| 465 |
+
"loss": 2.3675,
|
| 466 |
+
"step": 1475
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 8.15,
|
| 470 |
+
"learning_rate": 2.9619565217391305e-05,
|
| 471 |
+
"loss": 2.3262,
|
| 472 |
+
"step": 1500
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 8.29,
|
| 476 |
+
"learning_rate": 2.9279891304347828e-05,
|
| 477 |
+
"loss": 2.3138,
|
| 478 |
+
"step": 1525
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 8.42,
|
| 482 |
+
"learning_rate": 2.8940217391304347e-05,
|
| 483 |
+
"loss": 2.3079,
|
| 484 |
+
"step": 1550
|
| 485 |
+
},
|
| 486 |
+
{
|
| 487 |
+
"epoch": 8.56,
|
| 488 |
+
"learning_rate": 2.8600543478260873e-05,
|
| 489 |
+
"loss": 2.3094,
|
| 490 |
+
"step": 1575
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 8.69,
|
| 494 |
+
"learning_rate": 2.826086956521739e-05,
|
| 495 |
+
"loss": 2.3081,
|
| 496 |
+
"step": 1600
|
| 497 |
+
},
|
| 498 |
+
{
|
| 499 |
+
"epoch": 8.83,
|
| 500 |
+
"learning_rate": 2.7921195652173915e-05,
|
| 501 |
+
"loss": 2.2917,
|
| 502 |
+
"step": 1625
|
| 503 |
+
},
|
| 504 |
+
{
|
| 505 |
+
"epoch": 8.96,
|
| 506 |
+
"learning_rate": 2.7581521739130434e-05,
|
| 507 |
+
"loss": 2.3139,
|
| 508 |
+
"step": 1650
|
| 509 |
+
},
|
| 510 |
+
{
|
| 511 |
+
"epoch": 9.0,
|
| 512 |
+
"eval_gen_len": 69.51900872993522,
|
| 513 |
+
"eval_loss": 2.071018934249878,
|
| 514 |
+
"eval_rouge1": 29.1251,
|
| 515 |
+
"eval_rouge2": 10.8789,
|
| 516 |
+
"eval_rougeL": 21.4693,
|
| 517 |
+
"eval_rougeLsum": 27.0652,
|
| 518 |
+
"eval_runtime": 178.038,
|
| 519 |
+
"eval_samples_per_second": 19.945,
|
| 520 |
+
"eval_steps_per_second": 0.623,
|
| 521 |
+
"step": 1656
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 9.1,
|
| 525 |
+
"learning_rate": 2.7241847826086957e-05,
|
| 526 |
+
"loss": 2.3485,
|
| 527 |
+
"step": 1675
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 9.24,
|
| 531 |
+
"learning_rate": 2.6902173913043476e-05,
|
| 532 |
+
"loss": 2.302,
|
| 533 |
+
"step": 1700
|
| 534 |
+
},
|
| 535 |
+
{
|
| 536 |
+
"epoch": 9.37,
|
| 537 |
+
"learning_rate": 2.6562500000000002e-05,
|
| 538 |
+
"loss": 2.3095,
|
| 539 |
+
"step": 1725
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 9.51,
|
| 543 |
+
"learning_rate": 2.6222826086956525e-05,
|
| 544 |
+
"loss": 2.2841,
|
| 545 |
+
"step": 1750
|
| 546 |
+
},
|
| 547 |
+
{
|
| 548 |
+
"epoch": 9.64,
|
| 549 |
+
"learning_rate": 2.5883152173913044e-05,
|
| 550 |
+
"loss": 2.3034,
|
| 551 |
+
"step": 1775
|
| 552 |
+
},
|
| 553 |
+
{
|
| 554 |
+
"epoch": 9.78,
|
| 555 |
+
"learning_rate": 2.554347826086957e-05,
|
| 556 |
+
"loss": 2.2753,
|
| 557 |
+
"step": 1800
|
| 558 |
+
},
|
| 559 |
+
{
|
| 560 |
+
"epoch": 9.92,
|
| 561 |
+
"learning_rate": 2.520380434782609e-05,
|
| 562 |
+
"loss": 2.2977,
|
| 563 |
+
"step": 1825
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 10.0,
|
| 567 |
+
"eval_gen_len": 69.72007885102788,
|
| 568 |
+
"eval_loss": 2.0674257278442383,
|
| 569 |
+
"eval_rouge1": 29.0481,
|
| 570 |
+
"eval_rouge2": 10.7896,
|
| 571 |
+
"eval_rougeL": 21.2985,
|
| 572 |
+
"eval_rougeLsum": 26.9968,
|
| 573 |
+
"eval_runtime": 179.3171,
|
| 574 |
+
"eval_samples_per_second": 19.803,
|
| 575 |
+
"eval_steps_per_second": 0.619,
|
| 576 |
+
"step": 1840
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 10.05,
|
| 580 |
+
"learning_rate": 2.4864130434782608e-05,
|
| 581 |
+
"loss": 2.3133,
|
| 582 |
+
"step": 1850
|
| 583 |
+
},
|
| 584 |
+
{
|
| 585 |
+
"epoch": 10.19,
|
| 586 |
+
"learning_rate": 2.452445652173913e-05,
|
| 587 |
+
"loss": 2.2748,
|
| 588 |
+
"step": 1875
|
| 589 |
+
},
|
| 590 |
+
{
|
| 591 |
+
"epoch": 10.33,
|
| 592 |
+
"learning_rate": 2.4184782608695653e-05,
|
| 593 |
+
"loss": 2.2849,
|
| 594 |
+
"step": 1900
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 10.46,
|
| 598 |
+
"learning_rate": 2.3845108695652173e-05,
|
| 599 |
+
"loss": 2.2777,
|
| 600 |
+
"step": 1925
|
| 601 |
+
},
|
| 602 |
+
{
|
| 603 |
+
"epoch": 10.6,
|
| 604 |
+
"learning_rate": 2.3505434782608695e-05,
|
| 605 |
+
"loss": 2.2862,
|
| 606 |
+
"step": 1950
|
| 607 |
+
},
|
| 608 |
+
{
|
| 609 |
+
"epoch": 10.73,
|
| 610 |
+
"learning_rate": 2.3165760869565218e-05,
|
| 611 |
+
"loss": 2.2779,
|
| 612 |
+
"step": 1975
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 10.87,
|
| 616 |
+
"learning_rate": 2.282608695652174e-05,
|
| 617 |
+
"loss": 2.2732,
|
| 618 |
+
"step": 2000
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 11.0,
|
| 622 |
+
"eval_gen_len": 69.99014362151506,
|
| 623 |
+
"eval_loss": 2.0569896697998047,
|
| 624 |
+
"eval_rouge1": 29.4623,
|
| 625 |
+
"eval_rouge2": 11.0479,
|
| 626 |
+
"eval_rougeL": 21.5714,
|
| 627 |
+
"eval_rougeLsum": 27.425,
|
| 628 |
+
"eval_runtime": 179.0446,
|
| 629 |
+
"eval_samples_per_second": 19.833,
|
| 630 |
+
"eval_steps_per_second": 0.62,
|
| 631 |
+
"step": 2024
|
| 632 |
+
},
|
| 633 |
+
{
|
| 634 |
+
"epoch": 11.01,
|
| 635 |
+
"learning_rate": 2.2486413043478263e-05,
|
| 636 |
+
"loss": 2.3298,
|
| 637 |
+
"step": 2025
|
| 638 |
+
},
|
| 639 |
+
{
|
| 640 |
+
"epoch": 11.14,
|
| 641 |
+
"learning_rate": 2.2146739130434786e-05,
|
| 642 |
+
"loss": 2.2779,
|
| 643 |
+
"step": 2050
|
| 644 |
+
},
|
| 645 |
+
{
|
| 646 |
+
"epoch": 11.28,
|
| 647 |
+
"learning_rate": 2.1807065217391305e-05,
|
| 648 |
+
"loss": 2.2701,
|
| 649 |
+
"step": 2075
|
| 650 |
+
},
|
| 651 |
+
{
|
| 652 |
+
"epoch": 11.41,
|
| 653 |
+
"learning_rate": 2.1467391304347828e-05,
|
| 654 |
+
"loss": 2.2635,
|
| 655 |
+
"step": 2100
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 11.55,
|
| 659 |
+
"learning_rate": 2.112771739130435e-05,
|
| 660 |
+
"loss": 2.2716,
|
| 661 |
+
"step": 2125
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 11.68,
|
| 665 |
+
"learning_rate": 2.0788043478260873e-05,
|
| 666 |
+
"loss": 2.2601,
|
| 667 |
+
"step": 2150
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 11.82,
|
| 671 |
+
"learning_rate": 2.0448369565217392e-05,
|
| 672 |
+
"loss": 2.2663,
|
| 673 |
+
"step": 2175
|
| 674 |
+
},
|
| 675 |
+
{
|
| 676 |
+
"epoch": 11.95,
|
| 677 |
+
"learning_rate": 2.0108695652173915e-05,
|
| 678 |
+
"loss": 2.2483,
|
| 679 |
+
"step": 2200
|
| 680 |
+
},
|
| 681 |
+
{
|
| 682 |
+
"epoch": 12.0,
|
| 683 |
+
"eval_gen_len": 70.79442410588567,
|
| 684 |
+
"eval_loss": 2.0552728176116943,
|
| 685 |
+
"eval_rouge1": 29.2723,
|
| 686 |
+
"eval_rouge2": 10.8919,
|
| 687 |
+
"eval_rougeL": 21.3793,
|
| 688 |
+
"eval_rougeLsum": 27.2419,
|
| 689 |
+
"eval_runtime": 179.2858,
|
| 690 |
+
"eval_samples_per_second": 19.806,
|
| 691 |
+
"eval_steps_per_second": 0.619,
|
| 692 |
+
"step": 2208
|
| 693 |
+
},
|
| 694 |
+
{
|
| 695 |
+
"epoch": 12.09,
|
| 696 |
+
"learning_rate": 1.9769021739130437e-05,
|
| 697 |
+
"loss": 2.3121,
|
| 698 |
+
"step": 2225
|
| 699 |
+
},
|
| 700 |
+
{
|
| 701 |
+
"epoch": 12.23,
|
| 702 |
+
"learning_rate": 1.9429347826086957e-05,
|
| 703 |
+
"loss": 2.2507,
|
| 704 |
+
"step": 2250
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 12.36,
|
| 708 |
+
"learning_rate": 1.908967391304348e-05,
|
| 709 |
+
"loss": 2.2494,
|
| 710 |
+
"step": 2275
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 12.5,
|
| 714 |
+
"learning_rate": 1.8750000000000002e-05,
|
| 715 |
+
"loss": 2.2538,
|
| 716 |
+
"step": 2300
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 12.63,
|
| 720 |
+
"learning_rate": 1.841032608695652e-05,
|
| 721 |
+
"loss": 2.2607,
|
| 722 |
+
"step": 2325
|
| 723 |
+
},
|
| 724 |
+
{
|
| 725 |
+
"epoch": 12.77,
|
| 726 |
+
"learning_rate": 1.8070652173913044e-05,
|
| 727 |
+
"loss": 2.264,
|
| 728 |
+
"step": 2350
|
| 729 |
+
},
|
| 730 |
+
{
|
| 731 |
+
"epoch": 12.91,
|
| 732 |
+
"learning_rate": 1.7730978260869566e-05,
|
| 733 |
+
"loss": 2.2468,
|
| 734 |
+
"step": 2375
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 13.0,
|
| 738 |
+
"eval_gen_len": 70.16896648831315,
|
| 739 |
+
"eval_loss": 2.048848867416382,
|
| 740 |
+
"eval_rouge1": 29.5015,
|
| 741 |
+
"eval_rouge2": 11.0234,
|
| 742 |
+
"eval_rougeL": 21.5698,
|
| 743 |
+
"eval_rougeLsum": 27.4697,
|
| 744 |
+
"eval_runtime": 178.4371,
|
| 745 |
+
"eval_samples_per_second": 19.901,
|
| 746 |
+
"eval_steps_per_second": 0.622,
|
| 747 |
+
"step": 2392
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 13.04,
|
| 751 |
+
"learning_rate": 1.739130434782609e-05,
|
| 752 |
+
"loss": 2.2379,
|
| 753 |
+
"step": 2400
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 13.18,
|
| 757 |
+
"learning_rate": 1.7051630434782608e-05,
|
| 758 |
+
"loss": 2.2511,
|
| 759 |
+
"step": 2425
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 13.31,
|
| 763 |
+
"learning_rate": 1.671195652173913e-05,
|
| 764 |
+
"loss": 2.2455,
|
| 765 |
+
"step": 2450
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 13.45,
|
| 769 |
+
"learning_rate": 1.6372282608695653e-05,
|
| 770 |
+
"loss": 2.2544,
|
| 771 |
+
"step": 2475
|
| 772 |
+
},
|
| 773 |
+
{
|
| 774 |
+
"epoch": 13.59,
|
| 775 |
+
"learning_rate": 1.6032608695652173e-05,
|
| 776 |
+
"loss": 2.2362,
|
| 777 |
+
"step": 2500
|
| 778 |
+
},
|
| 779 |
+
{
|
| 780 |
+
"epoch": 13.72,
|
| 781 |
+
"learning_rate": 1.5692934782608695e-05,
|
| 782 |
+
"loss": 2.2418,
|
| 783 |
+
"step": 2525
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 13.86,
|
| 787 |
+
"learning_rate": 1.5353260869565218e-05,
|
| 788 |
+
"loss": 2.2375,
|
| 789 |
+
"step": 2550
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 13.99,
|
| 793 |
+
"learning_rate": 1.5013586956521739e-05,
|
| 794 |
+
"loss": 2.2549,
|
| 795 |
+
"step": 2575
|
| 796 |
+
},
|
| 797 |
+
{
|
| 798 |
+
"epoch": 14.0,
|
| 799 |
+
"eval_gen_len": 70.30582934384681,
|
| 800 |
+
"eval_loss": 2.0479626655578613,
|
| 801 |
+
"eval_rouge1": 29.5076,
|
| 802 |
+
"eval_rouge2": 11.0717,
|
| 803 |
+
"eval_rougeL": 21.6358,
|
| 804 |
+
"eval_rougeLsum": 27.5399,
|
| 805 |
+
"eval_runtime": 177.5749,
|
| 806 |
+
"eval_samples_per_second": 19.997,
|
| 807 |
+
"eval_steps_per_second": 0.625,
|
| 808 |
+
"step": 2576
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 14.13,
|
| 812 |
+
"learning_rate": 1.4673913043478263e-05,
|
| 813 |
+
"loss": 2.293,
|
| 814 |
+
"step": 2600
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 14.27,
|
| 818 |
+
"learning_rate": 1.4334239130434784e-05,
|
| 819 |
+
"loss": 2.2487,
|
| 820 |
+
"step": 2625
|
| 821 |
+
},
|
| 822 |
+
{
|
| 823 |
+
"epoch": 14.4,
|
| 824 |
+
"learning_rate": 1.3994565217391307e-05,
|
| 825 |
+
"loss": 2.2404,
|
| 826 |
+
"step": 2650
|
| 827 |
+
},
|
| 828 |
+
{
|
| 829 |
+
"epoch": 14.54,
|
| 830 |
+
"learning_rate": 1.3654891304347827e-05,
|
| 831 |
+
"loss": 2.2404,
|
| 832 |
+
"step": 2675
|
| 833 |
+
},
|
| 834 |
+
{
|
| 835 |
+
"epoch": 14.67,
|
| 836 |
+
"learning_rate": 1.331521739130435e-05,
|
| 837 |
+
"loss": 2.234,
|
| 838 |
+
"step": 2700
|
| 839 |
+
},
|
| 840 |
+
{
|
| 841 |
+
"epoch": 14.81,
|
| 842 |
+
"learning_rate": 1.2975543478260871e-05,
|
| 843 |
+
"loss": 2.244,
|
| 844 |
+
"step": 2725
|
| 845 |
+
},
|
| 846 |
+
{
|
| 847 |
+
"epoch": 14.94,
|
| 848 |
+
"learning_rate": 1.2635869565217392e-05,
|
| 849 |
+
"loss": 2.2225,
|
| 850 |
+
"step": 2750
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 15.0,
|
| 854 |
+
"eval_gen_len": 70.256829062236,
|
| 855 |
+
"eval_loss": 2.044435977935791,
|
| 856 |
+
"eval_rouge1": 29.5289,
|
| 857 |
+
"eval_rouge2": 11.0401,
|
| 858 |
+
"eval_rougeL": 21.609,
|
| 859 |
+
"eval_rougeLsum": 27.5116,
|
| 860 |
+
"eval_runtime": 181.0716,
|
| 861 |
+
"eval_samples_per_second": 19.611,
|
| 862 |
+
"eval_steps_per_second": 0.613,
|
| 863 |
+
"step": 2760
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 15.08,
|
| 867 |
+
"learning_rate": 1.2296195652173915e-05,
|
| 868 |
+
"loss": 2.282,
|
| 869 |
+
"step": 2775
|
| 870 |
+
},
|
| 871 |
+
{
|
| 872 |
+
"epoch": 15.22,
|
| 873 |
+
"learning_rate": 1.1956521739130435e-05,
|
| 874 |
+
"loss": 2.2318,
|
| 875 |
+
"step": 2800
|
| 876 |
+
},
|
| 877 |
+
{
|
| 878 |
+
"epoch": 15.35,
|
| 879 |
+
"learning_rate": 1.1616847826086958e-05,
|
| 880 |
+
"loss": 2.239,
|
| 881 |
+
"step": 2825
|
| 882 |
+
},
|
| 883 |
+
{
|
| 884 |
+
"epoch": 15.49,
|
| 885 |
+
"learning_rate": 1.1277173913043479e-05,
|
| 886 |
+
"loss": 2.2285,
|
| 887 |
+
"step": 2850
|
| 888 |
+
},
|
| 889 |
+
{
|
| 890 |
+
"epoch": 15.62,
|
| 891 |
+
"learning_rate": 1.09375e-05,
|
| 892 |
+
"loss": 2.2364,
|
| 893 |
+
"step": 2875
|
| 894 |
+
},
|
| 895 |
+
{
|
| 896 |
+
"epoch": 15.76,
|
| 897 |
+
"learning_rate": 1.0597826086956523e-05,
|
| 898 |
+
"loss": 2.2213,
|
| 899 |
+
"step": 2900
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 15.89,
|
| 903 |
+
"learning_rate": 1.0258152173913043e-05,
|
| 904 |
+
"loss": 2.2351,
|
| 905 |
+
"step": 2925
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 16.0,
|
| 909 |
+
"eval_gen_len": 70.1554491692481,
|
| 910 |
+
"eval_loss": 2.042268991470337,
|
| 911 |
+
"eval_rouge1": 29.6463,
|
| 912 |
+
"eval_rouge2": 11.1162,
|
| 913 |
+
"eval_rougeL": 21.6627,
|
| 914 |
+
"eval_rougeLsum": 27.6332,
|
| 915 |
+
"eval_runtime": 180.5795,
|
| 916 |
+
"eval_samples_per_second": 19.664,
|
| 917 |
+
"eval_steps_per_second": 0.615,
|
| 918 |
+
"step": 2944
|
| 919 |
+
},
|
| 920 |
+
{
|
| 921 |
+
"epoch": 16.03,
|
| 922 |
+
"learning_rate": 9.918478260869566e-06,
|
| 923 |
+
"loss": 2.2698,
|
| 924 |
+
"step": 2950
|
| 925 |
+
},
|
| 926 |
+
{
|
| 927 |
+
"epoch": 16.17,
|
| 928 |
+
"learning_rate": 9.578804347826087e-06,
|
| 929 |
+
"loss": 2.2243,
|
| 930 |
+
"step": 2975
|
| 931 |
+
},
|
| 932 |
+
{
|
| 933 |
+
"epoch": 16.3,
|
| 934 |
+
"learning_rate": 9.239130434782608e-06,
|
| 935 |
+
"loss": 2.2397,
|
| 936 |
+
"step": 3000
|
| 937 |
+
},
|
| 938 |
+
{
|
| 939 |
+
"epoch": 16.44,
|
| 940 |
+
"learning_rate": 8.899456521739132e-06,
|
| 941 |
+
"loss": 2.2241,
|
| 942 |
+
"step": 3025
|
| 943 |
+
},
|
| 944 |
+
{
|
| 945 |
+
"epoch": 16.57,
|
| 946 |
+
"learning_rate": 8.559782608695653e-06,
|
| 947 |
+
"loss": 2.2186,
|
| 948 |
+
"step": 3050
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 16.71,
|
| 952 |
+
"learning_rate": 8.220108695652174e-06,
|
| 953 |
+
"loss": 2.2331,
|
| 954 |
+
"step": 3075
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 16.85,
|
| 958 |
+
"learning_rate": 7.880434782608697e-06,
|
| 959 |
+
"loss": 2.2231,
|
| 960 |
+
"step": 3100
|
| 961 |
+
},
|
| 962 |
+
{
|
| 963 |
+
"epoch": 16.98,
|
| 964 |
+
"learning_rate": 7.540760869565218e-06,
|
| 965 |
+
"loss": 2.2218,
|
| 966 |
+
"step": 3125
|
| 967 |
+
},
|
| 968 |
+
{
|
| 969 |
+
"epoch": 17.0,
|
| 970 |
+
"eval_gen_len": 69.79414249507181,
|
| 971 |
+
"eval_loss": 2.040226936340332,
|
| 972 |
+
"eval_rouge1": 29.7229,
|
| 973 |
+
"eval_rouge2": 11.1601,
|
| 974 |
+
"eval_rougeL": 21.7195,
|
| 975 |
+
"eval_rougeLsum": 27.6978,
|
| 976 |
+
"eval_runtime": 180.1107,
|
| 977 |
+
"eval_samples_per_second": 19.716,
|
| 978 |
+
"eval_steps_per_second": 0.616,
|
| 979 |
+
"step": 3128
|
| 980 |
+
},
|
| 981 |
+
{
|
| 982 |
+
"epoch": 17.12,
|
| 983 |
+
"learning_rate": 7.201086956521739e-06,
|
| 984 |
+
"loss": 2.2616,
|
| 985 |
+
"step": 3150
|
| 986 |
+
},
|
| 987 |
+
{
|
| 988 |
+
"epoch": 17.25,
|
| 989 |
+
"learning_rate": 6.861413043478261e-06,
|
| 990 |
+
"loss": 2.2188,
|
| 991 |
+
"step": 3175
|
| 992 |
+
},
|
| 993 |
+
{
|
| 994 |
+
"epoch": 17.39,
|
| 995 |
+
"learning_rate": 6.521739130434783e-06,
|
| 996 |
+
"loss": 2.2304,
|
| 997 |
+
"step": 3200
|
| 998 |
+
},
|
| 999 |
+
{
|
| 1000 |
+
"epoch": 17.53,
|
| 1001 |
+
"learning_rate": 6.182065217391305e-06,
|
| 1002 |
+
"loss": 2.2245,
|
| 1003 |
+
"step": 3225
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 17.66,
|
| 1007 |
+
"learning_rate": 5.842391304347826e-06,
|
| 1008 |
+
"loss": 2.2187,
|
| 1009 |
+
"step": 3250
|
| 1010 |
+
},
|
| 1011 |
+
{
|
| 1012 |
+
"epoch": 17.8,
|
| 1013 |
+
"learning_rate": 5.502717391304348e-06,
|
| 1014 |
+
"loss": 2.2147,
|
| 1015 |
+
"step": 3275
|
| 1016 |
+
},
|
| 1017 |
+
{
|
| 1018 |
+
"epoch": 17.93,
|
| 1019 |
+
"learning_rate": 5.16304347826087e-06,
|
| 1020 |
+
"loss": 2.2264,
|
| 1021 |
+
"step": 3300
|
| 1022 |
+
},
|
| 1023 |
+
{
|
| 1024 |
+
"epoch": 18.0,
|
| 1025 |
+
"eval_gen_len": 70.03801745987046,
|
| 1026 |
+
"eval_loss": 2.0398149490356445,
|
| 1027 |
+
"eval_rouge1": 29.6695,
|
| 1028 |
+
"eval_rouge2": 11.1279,
|
| 1029 |
+
"eval_rougeL": 21.6656,
|
| 1030 |
+
"eval_rougeLsum": 27.6246,
|
| 1031 |
+
"eval_runtime": 179.5984,
|
| 1032 |
+
"eval_samples_per_second": 19.772,
|
| 1033 |
+
"eval_steps_per_second": 0.618,
|
| 1034 |
+
"step": 3312
|
| 1035 |
+
},
|
| 1036 |
+
{
|
| 1037 |
+
"epoch": 18.07,
|
| 1038 |
+
"learning_rate": 4.823369565217392e-06,
|
| 1039 |
+
"loss": 2.2775,
|
| 1040 |
+
"step": 3325
|
| 1041 |
+
},
|
| 1042 |
+
{
|
| 1043 |
+
"epoch": 18.21,
|
| 1044 |
+
"learning_rate": 4.483695652173913e-06,
|
| 1045 |
+
"loss": 2.2251,
|
| 1046 |
+
"step": 3350
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 18.34,
|
| 1050 |
+
"learning_rate": 4.144021739130434e-06,
|
| 1051 |
+
"loss": 2.2135,
|
| 1052 |
+
"step": 3375
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 18.48,
|
| 1056 |
+
"learning_rate": 3.804347826086957e-06,
|
| 1057 |
+
"loss": 2.2338,
|
| 1058 |
+
"step": 3400
|
| 1059 |
+
},
|
| 1060 |
+
{
|
| 1061 |
+
"epoch": 18.61,
|
| 1062 |
+
"learning_rate": 3.4646739130434784e-06,
|
| 1063 |
+
"loss": 2.2216,
|
| 1064 |
+
"step": 3425
|
| 1065 |
+
},
|
| 1066 |
+
{
|
| 1067 |
+
"epoch": 18.75,
|
| 1068 |
+
"learning_rate": 3.125e-06,
|
| 1069 |
+
"loss": 2.2235,
|
| 1070 |
+
"step": 3450
|
| 1071 |
+
},
|
| 1072 |
+
{
|
| 1073 |
+
"epoch": 18.88,
|
| 1074 |
+
"learning_rate": 2.785326086956522e-06,
|
| 1075 |
+
"loss": 2.2104,
|
| 1076 |
+
"step": 3475
|
| 1077 |
+
},
|
| 1078 |
+
{
|
| 1079 |
+
"epoch": 19.0,
|
| 1080 |
+
"eval_gen_len": 70.22416220782878,
|
| 1081 |
+
"eval_loss": 2.0398826599121094,
|
| 1082 |
+
"eval_rouge1": 29.7001,
|
| 1083 |
+
"eval_rouge2": 11.1385,
|
| 1084 |
+
"eval_rougeL": 21.6634,
|
| 1085 |
+
"eval_rougeLsum": 27.635,
|
| 1086 |
+
"eval_runtime": 179.3733,
|
| 1087 |
+
"eval_samples_per_second": 19.797,
|
| 1088 |
+
"eval_steps_per_second": 0.619,
|
| 1089 |
+
"step": 3496
|
| 1090 |
+
},
|
| 1091 |
+
{
|
| 1092 |
+
"epoch": 19.02,
|
| 1093 |
+
"learning_rate": 2.4456521739130437e-06,
|
| 1094 |
+
"loss": 2.2583,
|
| 1095 |
+
"step": 3500
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 19.16,
|
| 1099 |
+
"learning_rate": 2.1059782608695655e-06,
|
| 1100 |
+
"loss": 2.2194,
|
| 1101 |
+
"step": 3525
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 19.29,
|
| 1105 |
+
"learning_rate": 1.7663043478260868e-06,
|
| 1106 |
+
"loss": 2.2273,
|
| 1107 |
+
"step": 3550
|
| 1108 |
+
},
|
| 1109 |
+
{
|
| 1110 |
+
"epoch": 19.43,
|
| 1111 |
+
"learning_rate": 1.4266304347826088e-06,
|
| 1112 |
+
"loss": 2.2196,
|
| 1113 |
+
"step": 3575
|
| 1114 |
+
},
|
| 1115 |
+
{
|
| 1116 |
+
"epoch": 19.56,
|
| 1117 |
+
"learning_rate": 1.0869565217391306e-06,
|
| 1118 |
+
"loss": 2.2192,
|
| 1119 |
+
"step": 3600
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 19.7,
|
| 1123 |
+
"learning_rate": 7.472826086956522e-07,
|
| 1124 |
+
"loss": 2.2073,
|
| 1125 |
+
"step": 3625
|
| 1126 |
+
},
|
| 1127 |
+
{
|
| 1128 |
+
"epoch": 19.83,
|
| 1129 |
+
"learning_rate": 4.0760869565217393e-07,
|
| 1130 |
+
"loss": 2.2106,
|
| 1131 |
+
"step": 3650
|
| 1132 |
+
},
|
| 1133 |
+
{
|
| 1134 |
+
"epoch": 19.97,
|
| 1135 |
+
"learning_rate": 6.793478260869566e-08,
|
| 1136 |
+
"loss": 2.2235,
|
| 1137 |
+
"step": 3675
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 20.0,
|
| 1141 |
+
"eval_gen_len": 70.12644325542101,
|
| 1142 |
+
"eval_loss": 2.039487600326538,
|
| 1143 |
+
"eval_rouge1": 29.6901,
|
| 1144 |
+
"eval_rouge2": 11.127,
|
| 1145 |
+
"eval_rougeL": 21.6809,
|
| 1146 |
+
"eval_rougeLsum": 27.6332,
|
| 1147 |
+
"eval_runtime": 179.8041,
|
| 1148 |
+
"eval_samples_per_second": 19.749,
|
| 1149 |
+
"eval_steps_per_second": 0.617,
|
| 1150 |
+
"step": 3680
|
| 1151 |
+
}
|
| 1152 |
+
],
|
| 1153 |
+
"max_steps": 3680,
|
| 1154 |
+
"num_train_epochs": 20,
|
| 1155 |
+
"total_flos": 1.1311399656530903e+18,
|
| 1156 |
+
"trial_name": null,
|
| 1157 |
+
"trial_params": null
|
| 1158 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:acae6994f57d4df8855f2e18d81e87edca75f2b0b3a9578bea546a24a4a2ba2b
|
| 3 |
+
size 3707
|