Hugging Face's logo

hariniiiiiiiiii
/
finetuned-tamil-text-summarization

Summarization
Transformers
PyTorch
TensorBoard
mt5
text2text-generation
generated_from_trainer
Inference Endpoints
text-generation-inference
Model card Files Metrics Community
2
hariniiiiiiiiii commited on
Commit
a1ed687
•
1 Parent(s): 1f849b2

Upload last-checkpoint with huggingface_hub

Browse files
Files changed (12) hide show
  1. last-checkpoint/config.json +36 -0
  2. last-checkpoint/generation_config.json +11 -0
  3. last-checkpoint/optimizer.pt +3 -0
  4. last-checkpoint/pytorch_model.bin +3 -0
  5. last-checkpoint/rng_state.pth +3 -0
  6. last-checkpoint/scheduler.pt +3 -0
  7. last-checkpoint/special_tokens_map.json +5 -0
  8. last-checkpoint/spiece.model +3 -0
  9. last-checkpoint/tokenizer.json +3 -0
  10. last-checkpoint/tokenizer_config.json +12 -0
  11. last-checkpoint/trainer_state.json +3616 -0
  12. last-checkpoint/training_args.bin +3 -0
last-checkpoint/config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/mt5-base",
3
+ "architectures": [
4
+ "MT5ForConditionalGeneration"
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
+ "length_penalty": 0.6,
19
+ "max_length": 128,
20
+ "model_type": "mt5",
21
+ "no_repeat_ngram_size": 2,
22
+ "num_beams": 15,
23
+ "num_decoder_layers": 12,
24
+ "num_heads": 12,
25
+ "num_layers": 12,
26
+ "output_past": true,
27
+ "pad_token_id": 0,
28
+ "relative_attention_max_distance": 128,
29
+ "relative_attention_num_buckets": 32,
30
+ "tie_word_embeddings": false,
31
+ "tokenizer_class": "T5Tokenizer",
32
+ "torch_dtype": "float32",
33
+ "transformers_version": "4.26.1",
34
+ "use_cache": true,
35
+ "vocab_size": 250112
36
+ }
last-checkpoint/generation_config.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "decoder_start_token_id": 0,
4
+ "eos_token_id": 1,
5
+ "length_penalty": 0.6,
6
+ "max_length": 128,
7
+ "no_repeat_ngram_size": 2,
8
+ "num_beams": 15,
9
+ "pad_token_id": 0,
10
+ "transformers_version": "4.26.1"
11
+ }
last-checkpoint/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:35d81815d2717de634f2a36953a7237bebc0aed6d6f05bf4b444356bcd0bbcf5
3
+ size 4115013
last-checkpoint/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c87f4fb413b45320b3f6b962097316ca8762605322043e16b3d8b94d7c09674a
3
+ size 2329702453
last-checkpoint/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0d39dfe3569fd98eb88e2a2c2eaaf8e508e20a76576f7fbb2655866ff3eba6b
3
+ size 14575
last-checkpoint/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6982685cb2f1f3ac97aedb27d2a37d776ee4b9327cce88693a07d917b95ae056
3
+ size 627
last-checkpoint/special_tokens_map.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "eos_token": "</s>",
3
+ "pad_token": "<pad>",
4
+ "unk_token": "<unk>"
5
+ }
last-checkpoint/spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef78f86560d809067d12bac6c09f19a462cb3af3f54d2b8acbba26e1433125d6
3
+ size 4309802
last-checkpoint/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:faaa6405f5f79c9e788c7980874a9a3b5b0aea07b53bd9243bf1abb8f5c49c81
3
+ size 16330467
last-checkpoint/tokenizer_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": null,
3
+ "eos_token": "</s>",
4
+ "extra_ids": 0,
5
+ "model_max_length": 1000000000000000019884624838656,
6
+ "name_or_path": "google/mt5-base",
7
+ "pad_token": "<pad>",
8
+ "sp_model_kwargs": {},
9
+ "special_tokens_map_file": "/home/patrick/.cache/torch/transformers/685ac0ca8568ec593a48b61b0a3c272beee9bc194a3c7241d15dcadb5f875e53.f76030f3ec1b96a8199b2593390c610e76ca8028ef3d24680000619ffb646276",
10
+ "tokenizer_class": "T5Tokenizer",
11
+ "unk_token": "<unk>"
12
+ }
last-checkpoint/trainer_state.json ADDED
@@ -0,0 +1,3616 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 9.879792873874985,
5
+ "global_step": 5000,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.02,
12
+ "learning_rate": 5.555555555555555e-05,
13
+ "loss": 13.7427,
14
+ "step": 10
15
+ },
16
+ {
17
+ "epoch": 0.04,
18
+ "learning_rate": 0.0001111111111111111,
19
+ "loss": 8.8821,
20
+ "step": 20
21
+ },
22
+ {
23
+ "epoch": 0.06,
24
+ "learning_rate": 0.00016666666666666666,
25
+ "loss": 2.5857,
26
+ "step": 30
27
+ },
28
+ {
29
+ "epoch": 0.08,
30
+ "learning_rate": 0.0002222222222222222,
31
+ "loss": 1.3518,
32
+ "step": 40
33
+ },
34
+ {
35
+ "epoch": 0.1,
36
+ "learning_rate": 0.0002777777777777778,
37
+ "loss": 1.0054,
38
+ "step": 50
39
+ },
40
+ {
41
+ "epoch": 0.12,
42
+ "learning_rate": 0.0003333333333333333,
43
+ "loss": 0.864,
44
+ "step": 60
45
+ },
46
+ {
47
+ "epoch": 0.14,
48
+ "learning_rate": 0.0003888888888888889,
49
+ "loss": 0.8669,
50
+ "step": 70
51
+ },
52
+ {
53
+ "epoch": 0.16,
54
+ "learning_rate": 0.0004444444444444444,
55
+ "loss": 0.9395,
56
+ "step": 80
57
+ },
58
+ {
59
+ "epoch": 0.18,
60
+ "learning_rate": 0.0005,
61
+ "loss": 1.0424,
62
+ "step": 90
63
+ },
64
+ {
65
+ "epoch": 0.2,
66
+ "learning_rate": 0.0004985515643105447,
67
+ "loss": 0.6298,
68
+ "step": 100
69
+ },
70
+ {
71
+ "epoch": 0.2,
72
+ "eval_loss": 1.61441171169281,
73
+ "eval_rouge1": 0.07727272727272727,
74
+ "eval_rouge2": 0.061111111111111116,
75
+ "eval_rougeL": 0.06893939393939394,
76
+ "eval_rougeLsum": 0.08333333333333333,
77
+ "eval_runtime": 91.9317,
78
+ "eval_samples_per_second": 0.218,
79
+ "eval_steps_per_second": 0.218,
80
+ "step": 100
81
+ },
82
+ {
83
+ "epoch": 0.22,
84
+ "learning_rate": 0.0004971031286210893,
85
+ "loss": 0.5699,
86
+ "step": 110
87
+ },
88
+ {
89
+ "epoch": 0.24,
90
+ "learning_rate": 0.0004956546929316338,
91
+ "loss": 0.6074,
92
+ "step": 120
93
+ },
94
+ {
95
+ "epoch": 0.26,
96
+ "learning_rate": 0.0004942062572421785,
97
+ "loss": 0.6291,
98
+ "step": 130
99
+ },
100
+ {
101
+ "epoch": 0.28,
102
+ "learning_rate": 0.0004927578215527231,
103
+ "loss": 0.5098,
104
+ "step": 140
105
+ },
106
+ {
107
+ "epoch": 0.3,
108
+ "learning_rate": 0.0004913093858632677,
109
+ "loss": 0.4448,
110
+ "step": 150
111
+ },
112
+ {
113
+ "epoch": 0.32,
114
+ "learning_rate": 0.0004898609501738123,
115
+ "loss": 0.4508,
116
+ "step": 160
117
+ },
118
+ {
119
+ "epoch": 0.34,
120
+ "learning_rate": 0.0004884125144843569,
121
+ "loss": 0.4255,
122
+ "step": 170
123
+ },
124
+ {
125
+ "epoch": 0.36,
126
+ "learning_rate": 0.00048696407879490153,
127
+ "loss": 0.3705,
128
+ "step": 180
129
+ },
130
+ {
131
+ "epoch": 0.37,
132
+ "learning_rate": 0.0004855156431054461,
133
+ "loss": 0.4009,
134
+ "step": 190
135
+ },
136
+ {
137
+ "epoch": 0.39,
138
+ "learning_rate": 0.00048406720741599077,
139
+ "loss": 0.4317,
140
+ "step": 200
141
+ },
142
+ {
143
+ "epoch": 0.39,
144
+ "eval_loss": 1.176011323928833,
145
+ "eval_rouge1": 0.16153846153846152,
146
+ "eval_rouge2": 0.06988636363636364,
147
+ "eval_rougeL": 0.15999999999999998,
148
+ "eval_rougeLsum": 0.15999999999999998,
149
+ "eval_runtime": 88.2692,
150
+ "eval_samples_per_second": 0.227,
151
+ "eval_steps_per_second": 0.227,
152
+ "step": 200
153
+ },
154
+ {
155
+ "epoch": 0.41,
156
+ "learning_rate": 0.00048261877172653536,
157
+ "loss": 0.3679,
158
+ "step": 210
159
+ },
160
+ {
161
+ "epoch": 0.43,
162
+ "learning_rate": 0.00048117033603707995,
163
+ "loss": 0.3252,
164
+ "step": 220
165
+ },
166
+ {
167
+ "epoch": 0.45,
168
+ "learning_rate": 0.0004797219003476246,
169
+ "loss": 0.3707,
170
+ "step": 230
171
+ },
172
+ {
173
+ "epoch": 0.47,
174
+ "learning_rate": 0.0004782734646581692,
175
+ "loss": 0.3543,
176
+ "step": 240
177
+ },
178
+ {
179
+ "epoch": 0.49,
180
+ "learning_rate": 0.0004768250289687138,
181
+ "loss": 0.3434,
182
+ "step": 250
183
+ },
184
+ {
185
+ "epoch": 0.51,
186
+ "learning_rate": 0.0004753765932792584,
187
+ "loss": 0.4007,
188
+ "step": 260
189
+ },
190
+ {
191
+ "epoch": 0.53,
192
+ "learning_rate": 0.000473928157589803,
193
+ "loss": 0.3552,
194
+ "step": 270
195
+ },
196
+ {
197
+ "epoch": 0.55,
198
+ "learning_rate": 0.00047247972190034765,
199
+ "loss": 0.388,
200
+ "step": 280
201
+ },
202
+ {
203
+ "epoch": 0.57,
204
+ "learning_rate": 0.00047103128621089224,
205
+ "loss": 0.307,
206
+ "step": 290
207
+ },
208
+ {
209
+ "epoch": 0.59,
210
+ "learning_rate": 0.0004695828505214368,
211
+ "loss": 0.2588,
212
+ "step": 300
213
+ },
214
+ {
215
+ "epoch": 0.59,
216
+ "eval_loss": 1.0633952617645264,
217
+ "eval_rouge1": 0.08,
218
+ "eval_rouge2": 0.05555555555555556,
219
+ "eval_rougeL": 0.08414141414141416,
220
+ "eval_rougeLsum": 0.08383838383838385,
221
+ "eval_runtime": 88.5138,
222
+ "eval_samples_per_second": 0.226,
223
+ "eval_steps_per_second": 0.226,
224
+ "step": 300
225
+ },
226
+ {
227
+ "epoch": 0.61,
228
+ "learning_rate": 0.00046813441483198147,
229
+ "loss": 0.2965,
230
+ "step": 310
231
+ },
232
+ {
233
+ "epoch": 0.63,
234
+ "learning_rate": 0.00046668597914252606,
235
+ "loss": 0.3096,
236
+ "step": 320
237
+ },
238
+ {
239
+ "epoch": 0.65,
240
+ "learning_rate": 0.0004652375434530707,
241
+ "loss": 0.301,
242
+ "step": 330
243
+ },
244
+ {
245
+ "epoch": 0.67,
246
+ "learning_rate": 0.00046378910776361535,
247
+ "loss": 0.3153,
248
+ "step": 340
249
+ },
250
+ {
251
+ "epoch": 0.69,
252
+ "learning_rate": 0.00046234067207415994,
253
+ "loss": 0.3549,
254
+ "step": 350
255
+ },
256
+ {
257
+ "epoch": 0.71,
258
+ "learning_rate": 0.0004608922363847045,
259
+ "loss": 0.356,
260
+ "step": 360
261
+ },
262
+ {
263
+ "epoch": 0.73,
264
+ "learning_rate": 0.00045944380069524917,
265
+ "loss": 0.3278,
266
+ "step": 370
267
+ },
268
+ {
269
+ "epoch": 0.75,
270
+ "learning_rate": 0.00045799536500579376,
271
+ "loss": 0.2985,
272
+ "step": 380
273
+ },
274
+ {
275
+ "epoch": 0.77,
276
+ "learning_rate": 0.00045654692931633835,
277
+ "loss": 0.3152,
278
+ "step": 390
279
+ },
280
+ {
281
+ "epoch": 0.79,
282
+ "learning_rate": 0.000455098493626883,
283
+ "loss": 0.2665,
284
+ "step": 400
285
+ },
286
+ {
287
+ "epoch": 0.79,
288
+ "eval_loss": 1.044259786605835,
289
+ "eval_rouge1": 0.06307692307692307,
290
+ "eval_rouge2": 0.021590909090909088,
291
+ "eval_rougeL": 0.06307692307692307,
292
+ "eval_rougeLsum": 0.06307692307692307,
293
+ "eval_runtime": 80.5878,
294
+ "eval_samples_per_second": 0.248,
295
+ "eval_steps_per_second": 0.248,
296
+ "step": 400
297
+ },
298
+ {
299
+ "epoch": 0.81,
300
+ "learning_rate": 0.0004536500579374276,
301
+ "loss": 0.2323,
302
+ "step": 410
303
+ },
304
+ {
305
+ "epoch": 0.83,
306
+ "learning_rate": 0.00045220162224797217,
307
+ "loss": 0.2222,
308
+ "step": 420
309
+ },
310
+ {
311
+ "epoch": 0.85,
312
+ "learning_rate": 0.0004507531865585168,
313
+ "loss": 0.2516,
314
+ "step": 430
315
+ },
316
+ {
317
+ "epoch": 0.87,
318
+ "learning_rate": 0.0004493047508690614,
319
+ "loss": 0.2851,
320
+ "step": 440
321
+ },
322
+ {
323
+ "epoch": 0.89,
324
+ "learning_rate": 0.000447856315179606,
325
+ "loss": 0.2677,
326
+ "step": 450
327
+ },
328
+ {
329
+ "epoch": 0.91,
330
+ "learning_rate": 0.00044640787949015064,
331
+ "loss": 0.2447,
332
+ "step": 460
333
+ },
334
+ {
335
+ "epoch": 0.93,
336
+ "learning_rate": 0.00044495944380069523,
337
+ "loss": 0.3186,
338
+ "step": 470
339
+ },
340
+ {
341
+ "epoch": 0.95,
342
+ "learning_rate": 0.0004435110081112398,
343
+ "loss": 0.3035,
344
+ "step": 480
345
+ },
346
+ {
347
+ "epoch": 0.97,
348
+ "learning_rate": 0.0004420625724217845,
349
+ "loss": 0.3036,
350
+ "step": 490
351
+ },
352
+ {
353
+ "epoch": 0.99,
354
+ "learning_rate": 0.0004406141367323291,
355
+ "loss": 0.1972,
356
+ "step": 500
357
+ },
358
+ {
359
+ "epoch": 0.99,
360
+ "eval_loss": 1.0465357303619385,
361
+ "eval_rouge1": 0.1908791208791209,
362
+ "eval_rouge2": 0.10681818181818181,
363
+ "eval_rougeL": 0.17934065934065935,
364
+ "eval_rougeLsum": 0.19159340659340657,
365
+ "eval_runtime": 84.3482,
366
+ "eval_samples_per_second": 0.237,
367
+ "eval_steps_per_second": 0.237,
368
+ "step": 500
369
+ },
370
+ {
371
+ "epoch": 1.01,
372
+ "learning_rate": 0.00043916570104287375,
373
+ "loss": 0.279,
374
+ "step": 510
375
+ },
376
+ {
377
+ "epoch": 1.03,
378
+ "learning_rate": 0.00043771726535341834,
379
+ "loss": 0.272,
380
+ "step": 520
381
+ },
382
+ {
383
+ "epoch": 1.05,
384
+ "learning_rate": 0.00043626882966396293,
385
+ "loss": 0.2272,
386
+ "step": 530
387
+ },
388
+ {
389
+ "epoch": 1.07,
390
+ "learning_rate": 0.0004348203939745076,
391
+ "loss": 0.2495,
392
+ "step": 540
393
+ },
394
+ {
395
+ "epoch": 1.09,
396
+ "learning_rate": 0.00043337195828505216,
397
+ "loss": 0.1965,
398
+ "step": 550
399
+ },
400
+ {
401
+ "epoch": 1.11,
402
+ "learning_rate": 0.00043192352259559675,
403
+ "loss": 0.2364,
404
+ "step": 560
405
+ },
406
+ {
407
+ "epoch": 1.13,
408
+ "learning_rate": 0.0004304750869061414,
409
+ "loss": 0.2478,
410
+ "step": 570
411
+ },
412
+ {
413
+ "epoch": 1.15,
414
+ "learning_rate": 0.000429026651216686,
415
+ "loss": 0.2046,
416
+ "step": 580
417
+ },
418
+ {
419
+ "epoch": 1.17,
420
+ "learning_rate": 0.0004275782155272306,
421
+ "loss": 0.2661,
422
+ "step": 590
423
+ },
424
+ {
425
+ "epoch": 1.19,
426
+ "learning_rate": 0.0004261297798377752,
427
+ "loss": 0.2041,
428
+ "step": 600
429
+ },
430
+ {
431
+ "epoch": 1.19,
432
+ "eval_loss": 0.9551488757133484,
433
+ "eval_rouge1": 0.09038461538461538,
434
+ "eval_rouge2": 0.05051948051948052,
435
+ "eval_rougeL": 0.09679487179487178,
436
+ "eval_rougeLsum": 0.09871794871794871,
437
+ "eval_runtime": 89.0139,
438
+ "eval_samples_per_second": 0.225,
439
+ "eval_steps_per_second": 0.225,
440
+ "step": 600
441
+ },
442
+ {
443
+ "epoch": 1.21,
444
+ "learning_rate": 0.0004246813441483198,
445
+ "loss": 0.2816,
446
+ "step": 610
447
+ },
448
+ {
449
+ "epoch": 1.22,
450
+ "learning_rate": 0.0004232329084588644,
451
+ "loss": 0.1904,
452
+ "step": 620
453
+ },
454
+ {
455
+ "epoch": 1.24,
456
+ "learning_rate": 0.00042178447276940904,
457
+ "loss": 0.21,
458
+ "step": 630
459
+ },
460
+ {
461
+ "epoch": 1.26,
462
+ "learning_rate": 0.0004203360370799537,
463
+ "loss": 0.1662,
464
+ "step": 640
465
+ },
466
+ {
467
+ "epoch": 1.28,
468
+ "learning_rate": 0.0004188876013904983,
469
+ "loss": 0.3052,
470
+ "step": 650
471
+ },
472
+ {
473
+ "epoch": 1.3,
474
+ "learning_rate": 0.0004174391657010429,
475
+ "loss": 0.1744,
476
+ "step": 660
477
+ },
478
+ {
479
+ "epoch": 1.32,
480
+ "learning_rate": 0.0004159907300115875,
481
+ "loss": 0.288,
482
+ "step": 670
483
+ },
484
+ {
485
+ "epoch": 1.34,
486
+ "learning_rate": 0.0004145422943221321,
487
+ "loss": 0.2303,
488
+ "step": 680
489
+ },
490
+ {
491
+ "epoch": 1.36,
492
+ "learning_rate": 0.00041309385863267674,
493
+ "loss": 0.2866,
494
+ "step": 690
495
+ },
496
+ {
497
+ "epoch": 1.38,
498
+ "learning_rate": 0.00041164542294322133,
499
+ "loss": 0.238,
500
+ "step": 700
501
+ },
502
+ {
503
+ "epoch": 1.38,
504
+ "eval_loss": 0.9423090219497681,
505
+ "eval_rouge1": 0.1,
506
+ "eval_rouge2": 0.07291666666666667,
507
+ "eval_rougeL": 0.1,
508
+ "eval_rougeLsum": 0.10333333333333335,
509
+ "eval_runtime": 88.0456,
510
+ "eval_samples_per_second": 0.227,
511
+ "eval_steps_per_second": 0.227,
512
+ "step": 700
513
+ },
514
+ {
515
+ "epoch": 1.4,
516
+ "learning_rate": 0.0004101969872537659,
517
+ "loss": 0.2342,
518
+ "step": 710
519
+ },
520
+ {
521
+ "epoch": 1.42,
522
+ "learning_rate": 0.00040874855156431057,
523
+ "loss": 0.2716,
524
+ "step": 720
525
+ },
526
+ {
527
+ "epoch": 1.44,
528
+ "learning_rate": 0.00040730011587485516,
529
+ "loss": 0.2453,
530
+ "step": 730
531
+ },
532
+ {
533
+ "epoch": 1.46,
534
+ "learning_rate": 0.00040585168018539974,
535
+ "loss": 0.2313,
536
+ "step": 740
537
+ },
538
+ {
539
+ "epoch": 1.48,
540
+ "learning_rate": 0.0004044032444959444,
541
+ "loss": 0.2306,
542
+ "step": 750
543
+ },
544
+ {
545
+ "epoch": 1.5,
546
+ "learning_rate": 0.000402954808806489,
547
+ "loss": 0.1773,
548
+ "step": 760
549
+ },
550
+ {
551
+ "epoch": 1.52,
552
+ "learning_rate": 0.00040150637311703357,
553
+ "loss": 0.1957,
554
+ "step": 770
555
+ },
556
+ {
557
+ "epoch": 1.54,
558
+ "learning_rate": 0.0004000579374275782,
559
+ "loss": 0.2758,
560
+ "step": 780
561
+ },
562
+ {
563
+ "epoch": 1.56,
564
+ "learning_rate": 0.0003986095017381228,
565
+ "loss": 0.2649,
566
+ "step": 790
567
+ },
568
+ {
569
+ "epoch": 1.58,
570
+ "learning_rate": 0.0003971610660486675,
571
+ "loss": 0.275,
572
+ "step": 800
573
+ },
574
+ {
575
+ "epoch": 1.58,
576
+ "eval_loss": 0.9273136258125305,
577
+ "eval_rouge1": 0.14666666666666667,
578
+ "eval_rouge2": 0.10977272727272727,
579
+ "eval_rougeL": 0.15038461538461537,
580
+ "eval_rougeLsum": 0.15153846153846154,
581
+ "eval_runtime": 87.8017,
582
+ "eval_samples_per_second": 0.228,
583
+ "eval_steps_per_second": 0.228,
584
+ "step": 800
585
+ },
586
+ {
587
+ "epoch": 1.6,
588
+ "learning_rate": 0.0003957126303592121,
589
+ "loss": 0.2102,
590
+ "step": 810
591
+ },
592
+ {
593
+ "epoch": 1.62,
594
+ "learning_rate": 0.0003942641946697567,
595
+ "loss": 0.2146,
596
+ "step": 820
597
+ },
598
+ {
599
+ "epoch": 1.64,
600
+ "learning_rate": 0.0003928157589803013,
601
+ "loss": 0.1918,
602
+ "step": 830
603
+ },
604
+ {
605
+ "epoch": 1.66,
606
+ "learning_rate": 0.0003913673232908459,
607
+ "loss": 0.2512,
608
+ "step": 840
609
+ },
610
+ {
611
+ "epoch": 1.68,
612
+ "learning_rate": 0.0003899188876013905,
613
+ "loss": 0.2499,
614
+ "step": 850
615
+ },
616
+ {
617
+ "epoch": 1.7,
618
+ "learning_rate": 0.00038847045191193515,
619
+ "loss": 0.228,
620
+ "step": 860
621
+ },
622
+ {
623
+ "epoch": 1.72,
624
+ "learning_rate": 0.00038702201622247974,
625
+ "loss": 0.2507,
626
+ "step": 870
627
+ },
628
+ {
629
+ "epoch": 1.74,
630
+ "learning_rate": 0.0003855735805330243,
631
+ "loss": 0.1735,
632
+ "step": 880
633
+ },
634
+ {
635
+ "epoch": 1.76,
636
+ "learning_rate": 0.00038412514484356897,
637
+ "loss": 0.2752,
638
+ "step": 890
639
+ },
640
+ {
641
+ "epoch": 1.78,
642
+ "learning_rate": 0.00038267670915411356,
643
+ "loss": 0.2379,
644
+ "step": 900
645
+ },
646
+ {
647
+ "epoch": 1.78,
648
+ "eval_loss": 0.9023244976997375,
649
+ "eval_rouge1": 0.1,
650
+ "eval_rouge2": 0.08333333333333333,
651
+ "eval_rougeL": 0.1,
652
+ "eval_rougeLsum": 0.1,
653
+ "eval_runtime": 80.7798,
654
+ "eval_samples_per_second": 0.248,
655
+ "eval_steps_per_second": 0.248,
656
+ "step": 900
657
+ },
658
+ {
659
+ "epoch": 1.8,
660
+ "learning_rate": 0.00038122827346465815,
661
+ "loss": 0.1993,
662
+ "step": 910
663
+ },
664
+ {
665
+ "epoch": 1.82,
666
+ "learning_rate": 0.0003797798377752028,
667
+ "loss": 0.2058,
668
+ "step": 920
669
+ },
670
+ {
671
+ "epoch": 1.84,
672
+ "learning_rate": 0.0003783314020857474,
673
+ "loss": 0.2675,
674
+ "step": 930
675
+ },
676
+ {
677
+ "epoch": 1.86,
678
+ "learning_rate": 0.00037688296639629197,
679
+ "loss": 0.1928,
680
+ "step": 940
681
+ },
682
+ {
683
+ "epoch": 1.88,
684
+ "learning_rate": 0.0003754345307068366,
685
+ "loss": 0.1903,
686
+ "step": 950
687
+ },
688
+ {
689
+ "epoch": 1.9,
690
+ "learning_rate": 0.00037398609501738126,
691
+ "loss": 0.1967,
692
+ "step": 960
693
+ },
694
+ {
695
+ "epoch": 1.92,
696
+ "learning_rate": 0.00037253765932792585,
697
+ "loss": 0.2044,
698
+ "step": 970
699
+ },
700
+ {
701
+ "epoch": 1.94,
702
+ "learning_rate": 0.0003710892236384705,
703
+ "loss": 0.2027,
704
+ "step": 980
705
+ },
706
+ {
707
+ "epoch": 1.95,
708
+ "learning_rate": 0.0003696407879490151,
709
+ "loss": 0.25,
710
+ "step": 990
711
+ },
712
+ {
713
+ "epoch": 1.97,
714
+ "learning_rate": 0.00036819235225955967,
715
+ "loss": 0.2896,
716
+ "step": 1000
717
+ },
718
+ {
719
+ "epoch": 1.97,
720
+ "eval_loss": 0.9184179306030273,
721
+ "eval_rouge1": 0.19,
722
+ "eval_rouge2": 0.1,
723
+ "eval_rougeL": 0.18893939393939393,
724
+ "eval_rougeLsum": 0.19848484848484846,
725
+ "eval_runtime": 81.9559,
726
+ "eval_samples_per_second": 0.244,
727
+ "eval_steps_per_second": 0.244,
728
+ "step": 1000
729
+ },
730
+ {
731
+ "epoch": 1.99,
732
+ "learning_rate": 0.0003667439165701043,
733
+ "loss": 0.1462,
734
+ "step": 1010
735
+ },
736
+ {
737
+ "epoch": 2.02,
738
+ "learning_rate": 0.0003652954808806489,
739
+ "loss": 0.1944,
740
+ "step": 1020
741
+ },
742
+ {
743
+ "epoch": 2.04,
744
+ "learning_rate": 0.0003638470451911935,
745
+ "loss": 0.2296,
746
+ "step": 1030
747
+ },
748
+ {
749
+ "epoch": 2.06,
750
+ "learning_rate": 0.00036239860950173814,
751
+ "loss": 0.2446,
752
+ "step": 1040
753
+ },
754
+ {
755
+ "epoch": 2.07,
756
+ "learning_rate": 0.00036095017381228273,
757
+ "loss": 0.1448,
758
+ "step": 1050
759
+ },
760
+ {
761
+ "epoch": 2.09,
762
+ "learning_rate": 0.0003595017381228273,
763
+ "loss": 0.1507,
764
+ "step": 1060
765
+ },
766
+ {
767
+ "epoch": 2.11,
768
+ "learning_rate": 0.00035805330243337196,
769
+ "loss": 0.1636,
770
+ "step": 1070
771
+ },
772
+ {
773
+ "epoch": 2.13,
774
+ "learning_rate": 0.00035660486674391655,
775
+ "loss": 0.1909,
776
+ "step": 1080
777
+ },
778
+ {
779
+ "epoch": 2.15,
780
+ "learning_rate": 0.0003551564310544612,
781
+ "loss": 0.1895,
782
+ "step": 1090
783
+ },
784
+ {
785
+ "epoch": 2.17,
786
+ "learning_rate": 0.0003537079953650058,
787
+ "loss": 0.2663,
788
+ "step": 1100
789
+ },
790
+ {
791
+ "epoch": 2.17,
792
+ "eval_loss": 0.9002671241760254,
793
+ "eval_rouge1": 0.07948717948717948,
794
+ "eval_rouge2": 0.06779220779220778,
795
+ "eval_rougeL": 0.08782051282051281,
796
+ "eval_rougeLsum": 0.08333333333333333,
797
+ "eval_runtime": 84.9078,
798
+ "eval_samples_per_second": 0.236,
799
+ "eval_steps_per_second": 0.236,
800
+ "step": 1100
801
+ },
802
+ {
803
+ "epoch": 2.19,
804
+ "learning_rate": 0.0003522595596755504,
805
+ "loss": 0.1672,
806
+ "step": 1110
807
+ },
808
+ {
809
+ "epoch": 2.21,
810
+ "learning_rate": 0.00035081112398609507,
811
+ "loss": 0.1909,
812
+ "step": 1120
813
+ },
814
+ {
815
+ "epoch": 2.23,
816
+ "learning_rate": 0.00034936268829663966,
817
+ "loss": 0.1675,
818
+ "step": 1130
819
+ },
820
+ {
821
+ "epoch": 2.25,
822
+ "learning_rate": 0.00034791425260718425,
823
+ "loss": 0.2636,
824
+ "step": 1140
825
+ },
826
+ {
827
+ "epoch": 2.27,
828
+ "learning_rate": 0.0003464658169177289,
829
+ "loss": 0.2119,
830
+ "step": 1150
831
+ },
832
+ {
833
+ "epoch": 2.29,
834
+ "learning_rate": 0.0003450173812282735,
835
+ "loss": 0.2114,
836
+ "step": 1160
837
+ },
838
+ {
839
+ "epoch": 2.31,
840
+ "learning_rate": 0.0003435689455388181,
841
+ "loss": 0.1456,
842
+ "step": 1170
843
+ },
844
+ {
845
+ "epoch": 2.33,
846
+ "learning_rate": 0.0003421205098493627,
847
+ "loss": 0.1993,
848
+ "step": 1180
849
+ },
850
+ {
851
+ "epoch": 2.35,
852
+ "learning_rate": 0.0003406720741599073,
853
+ "loss": 0.1467,
854
+ "step": 1190
855
+ },
856
+ {
857
+ "epoch": 2.37,
858
+ "learning_rate": 0.0003392236384704519,
859
+ "loss": 0.237,
860
+ "step": 1200
861
+ },
862
+ {
863
+ "epoch": 2.37,
864
+ "eval_loss": 0.9139176607131958,
865
+ "eval_rouge1": 0.19904761904761903,
866
+ "eval_rouge2": 0.10285714285714284,
867
+ "eval_rougeL": 0.19511904761904764,
868
+ "eval_rougeLsum": 0.20619047619047615,
869
+ "eval_runtime": 85.9903,
870
+ "eval_samples_per_second": 0.233,
871
+ "eval_steps_per_second": 0.233,
872
+ "step": 1200
873
+ },
874
+ {
875
+ "epoch": 2.39,
876
+ "learning_rate": 0.00033777520278099654,
877
+ "loss": 0.1996,
878
+ "step": 1210
879
+ },
880
+ {
881
+ "epoch": 2.41,
882
+ "learning_rate": 0.00033632676709154113,
883
+ "loss": 0.1725,
884
+ "step": 1220
885
+ },
886
+ {
887
+ "epoch": 2.43,
888
+ "learning_rate": 0.0003348783314020857,
889
+ "loss": 0.2089,
890
+ "step": 1230
891
+ },
892
+ {
893
+ "epoch": 2.45,
894
+ "learning_rate": 0.00033342989571263036,
895
+ "loss": 0.183,
896
+ "step": 1240
897
+ },
898
+ {
899
+ "epoch": 2.47,
900
+ "learning_rate": 0.00033198146002317495,
901
+ "loss": 0.1631,
902
+ "step": 1250
903
+ },
904
+ {
905
+ "epoch": 2.49,
906
+ "learning_rate": 0.00033053302433371954,
907
+ "loss": 0.1889,
908
+ "step": 1260
909
+ },
910
+ {
911
+ "epoch": 2.51,
912
+ "learning_rate": 0.00032908458864426424,
913
+ "loss": 0.172,
914
+ "step": 1270
915
+ },
916
+ {
917
+ "epoch": 2.53,
918
+ "learning_rate": 0.00032763615295480883,
919
+ "loss": 0.1236,
920
+ "step": 1280
921
+ },
922
+ {
923
+ "epoch": 2.55,
924
+ "learning_rate": 0.0003261877172653534,
925
+ "loss": 0.1682,
926
+ "step": 1290
927
+ },
928
+ {
929
+ "epoch": 2.57,
930
+ "learning_rate": 0.00032473928157589806,
931
+ "loss": 0.2019,
932
+ "step": 1300
933
+ },
934
+ {
935
+ "epoch": 2.57,
936
+ "eval_loss": 0.920964241027832,
937
+ "eval_rouge1": 0.11282051282051282,
938
+ "eval_rouge2": 0.03636363636363636,
939
+ "eval_rougeL": 0.1128205128205128,
940
+ "eval_rougeLsum": 0.11607142857142858,
941
+ "eval_runtime": 82.9262,
942
+ "eval_samples_per_second": 0.241,
943
+ "eval_steps_per_second": 0.241,
944
+ "step": 1300
945
+ },
946
+ {
947
+ "epoch": 2.59,
948
+ "learning_rate": 0.00032329084588644265,
949
+ "loss": 0.1681,
950
+ "step": 1310
951
+ },
952
+ {
953
+ "epoch": 2.61,
954
+ "learning_rate": 0.00032184241019698724,
955
+ "loss": 0.2372,
956
+ "step": 1320
957
+ },
958
+ {
959
+ "epoch": 2.63,
960
+ "learning_rate": 0.0003203939745075319,
961
+ "loss": 0.1343,
962
+ "step": 1330
963
+ },
964
+ {
965
+ "epoch": 2.65,
966
+ "learning_rate": 0.0003189455388180765,
967
+ "loss": 0.2125,
968
+ "step": 1340
969
+ },
970
+ {
971
+ "epoch": 2.67,
972
+ "learning_rate": 0.0003174971031286211,
973
+ "loss": 0.2217,
974
+ "step": 1350
975
+ },
976
+ {
977
+ "epoch": 2.69,
978
+ "learning_rate": 0.0003160486674391657,
979
+ "loss": 0.1542,
980
+ "step": 1360
981
+ },
982
+ {
983
+ "epoch": 2.71,
984
+ "learning_rate": 0.0003146002317497103,
985
+ "loss": 0.171,
986
+ "step": 1370
987
+ },
988
+ {
989
+ "epoch": 2.73,
990
+ "learning_rate": 0.00031315179606025494,
991
+ "loss": 0.1808,
992
+ "step": 1380
993
+ },
994
+ {
995
+ "epoch": 2.75,
996
+ "learning_rate": 0.00031170336037079953,
997
+ "loss": 0.1423,
998
+ "step": 1390
999
+ },
1000
+ {
1001
+ "epoch": 2.77,
1002
+ "learning_rate": 0.0003102549246813441,
1003
+ "loss": 0.1794,
1004
+ "step": 1400
1005
+ },
1006
+ {
1007
+ "epoch": 2.77,
1008
+ "eval_loss": 0.9037507772445679,
1009
+ "eval_rouge1": 0.11666666666666667,
1010
+ "eval_rouge2": 0.08636363636363635,
1011
+ "eval_rougeL": 0.11833333333333333,
1012
+ "eval_rougeLsum": 0.12064102564102563,
1013
+ "eval_runtime": 84.5851,
1014
+ "eval_samples_per_second": 0.236,
1015
+ "eval_steps_per_second": 0.236,
1016
+ "step": 1400
1017
+ },
1018
+ {
1019
+ "epoch": 2.79,
1020
+ "learning_rate": 0.00030880648899188877,
1021
+ "loss": 0.2313,
1022
+ "step": 1410
1023
+ },
1024
+ {
1025
+ "epoch": 2.8,
1026
+ "learning_rate": 0.00030735805330243336,
1027
+ "loss": 0.1548,
1028
+ "step": 1420
1029
+ },
1030
+ {
1031
+ "epoch": 2.82,
1032
+ "learning_rate": 0.000305909617612978,
1033
+ "loss": 0.2318,
1034
+ "step": 1430
1035
+ },
1036
+ {
1037
+ "epoch": 2.84,
1038
+ "learning_rate": 0.00030446118192352264,
1039
+ "loss": 0.1959,
1040
+ "step": 1440
1041
+ },
1042
+ {
1043
+ "epoch": 2.86,
1044
+ "learning_rate": 0.00030301274623406723,
1045
+ "loss": 0.1438,
1046
+ "step": 1450
1047
+ },
1048
+ {
1049
+ "epoch": 2.88,
1050
+ "learning_rate": 0.0003015643105446118,
1051
+ "loss": 0.1953,
1052
+ "step": 1460
1053
+ },
1054
+ {
1055
+ "epoch": 2.9,
1056
+ "learning_rate": 0.00030011587485515647,
1057
+ "loss": 0.1542,
1058
+ "step": 1470
1059
+ },
1060
+ {
1061
+ "epoch": 2.92,
1062
+ "learning_rate": 0.00029866743916570106,
1063
+ "loss": 0.1693,
1064
+ "step": 1480
1065
+ },
1066
+ {
1067
+ "epoch": 2.94,
1068
+ "learning_rate": 0.00029721900347624565,
1069
+ "loss": 0.1836,
1070
+ "step": 1490
1071
+ },
1072
+ {
1073
+ "epoch": 2.96,
1074
+ "learning_rate": 0.0002957705677867903,
1075
+ "loss": 0.1847,
1076
+ "step": 1500
1077
+ },
1078
+ {
1079
+ "epoch": 2.96,
1080
+ "eval_loss": 0.8892697095870972,
1081
+ "eval_rouge1": 0.14335664335664336,
1082
+ "eval_rouge2": 0.13131313131313133,
1083
+ "eval_rougeL": 0.14375624375624377,
1084
+ "eval_rougeLsum": 0.14725274725274726,
1085
+ "eval_runtime": 86.985,
1086
+ "eval_samples_per_second": 0.23,
1087
+ "eval_steps_per_second": 0.23,
1088
+ "step": 1500
1089
+ },
1090
+ {
1091
+ "epoch": 2.98,
1092
+ "learning_rate": 0.0002943221320973349,
1093
+ "loss": 0.1245,
1094
+ "step": 1510
1095
+ },
1096
+ {
1097
+ "epoch": 3.0,
1098
+ "learning_rate": 0.00029287369640787947,
1099
+ "loss": 0.1917,
1100
+ "step": 1520
1101
+ },
1102
+ {
1103
+ "epoch": 3.02,
1104
+ "learning_rate": 0.0002914252607184241,
1105
+ "loss": 0.205,
1106
+ "step": 1530
1107
+ },
1108
+ {
1109
+ "epoch": 3.04,
1110
+ "learning_rate": 0.0002899768250289687,
1111
+ "loss": 0.1493,
1112
+ "step": 1540
1113
+ },
1114
+ {
1115
+ "epoch": 3.06,
1116
+ "learning_rate": 0.0002885283893395133,
1117
+ "loss": 0.1596,
1118
+ "step": 1550
1119
+ },
1120
+ {
1121
+ "epoch": 3.08,
1122
+ "learning_rate": 0.00028707995365005794,
1123
+ "loss": 0.1689,
1124
+ "step": 1560
1125
+ },
1126
+ {
1127
+ "epoch": 3.1,
1128
+ "learning_rate": 0.0002856315179606025,
1129
+ "loss": 0.1371,
1130
+ "step": 1570
1131
+ },
1132
+ {
1133
+ "epoch": 3.12,
1134
+ "learning_rate": 0.0002841830822711471,
1135
+ "loss": 0.1676,
1136
+ "step": 1580
1137
+ },
1138
+ {
1139
+ "epoch": 3.14,
1140
+ "learning_rate": 0.0002827346465816918,
1141
+ "loss": 0.1441,
1142
+ "step": 1590
1143
+ },
1144
+ {
1145
+ "epoch": 3.16,
1146
+ "learning_rate": 0.0002812862108922364,
1147
+ "loss": 0.1436,
1148
+ "step": 1600
1149
+ },
1150
+ {
1151
+ "epoch": 3.16,
1152
+ "eval_loss": 0.8872199058532715,
1153
+ "eval_rouge1": 0.16825396825396824,
1154
+ "eval_rouge2": 0.05833333333333333,
1155
+ "eval_rougeL": 0.1650793650793651,
1156
+ "eval_rougeLsum": 0.17285714285714288,
1157
+ "eval_runtime": 83.5131,
1158
+ "eval_samples_per_second": 0.239,
1159
+ "eval_steps_per_second": 0.239,
1160
+ "step": 1600
1161
+ },
1162
+ {
1163
+ "epoch": 3.18,
1164
+ "learning_rate": 0.000279837775202781,
1165
+ "loss": 0.2173,
1166
+ "step": 1610
1167
+ },
1168
+ {
1169
+ "epoch": 3.2,
1170
+ "learning_rate": 0.00027838933951332564,
1171
+ "loss": 0.1457,
1172
+ "step": 1620
1173
+ },
1174
+ {
1175
+ "epoch": 3.22,
1176
+ "learning_rate": 0.0002769409038238702,
1177
+ "loss": 0.1503,
1178
+ "step": 1630
1179
+ },
1180
+ {
1181
+ "epoch": 3.24,
1182
+ "learning_rate": 0.00027549246813441487,
1183
+ "loss": 0.1371,
1184
+ "step": 1640
1185
+ },
1186
+ {
1187
+ "epoch": 3.26,
1188
+ "learning_rate": 0.00027404403244495946,
1189
+ "loss": 0.1331,
1190
+ "step": 1650
1191
+ },
1192
+ {
1193
+ "epoch": 3.28,
1194
+ "learning_rate": 0.00027259559675550405,
1195
+ "loss": 0.2068,
1196
+ "step": 1660
1197
+ },
1198
+ {
1199
+ "epoch": 3.3,
1200
+ "learning_rate": 0.0002711471610660487,
1201
+ "loss": 0.2001,
1202
+ "step": 1670
1203
+ },
1204
+ {
1205
+ "epoch": 3.32,
1206
+ "learning_rate": 0.0002696987253765933,
1207
+ "loss": 0.177,
1208
+ "step": 1680
1209
+ },
1210
+ {
1211
+ "epoch": 3.34,
1212
+ "learning_rate": 0.00026825028968713787,
1213
+ "loss": 0.1772,
1214
+ "step": 1690
1215
+ },
1216
+ {
1217
+ "epoch": 3.36,
1218
+ "learning_rate": 0.0002668018539976825,
1219
+ "loss": 0.138,
1220
+ "step": 1700
1221
+ },
1222
+ {
1223
+ "epoch": 3.36,
1224
+ "eval_loss": 0.8929020762443542,
1225
+ "eval_rouge1": 0.22999999999999998,
1226
+ "eval_rouge2": 0.12491883116883117,
1227
+ "eval_rougeL": 0.22615384615384615,
1228
+ "eval_rougeLsum": 0.23115384615384618,
1229
+ "eval_runtime": 86.6494,
1230
+ "eval_samples_per_second": 0.231,
1231
+ "eval_steps_per_second": 0.231,
1232
+ "step": 1700
1233
+ },
1234
+ {
1235
+ "epoch": 3.38,
1236
+ "learning_rate": 0.0002653534183082271,
1237
+ "loss": 0.164,
1238
+ "step": 1710
1239
+ },
1240
+ {
1241
+ "epoch": 3.4,
1242
+ "learning_rate": 0.0002639049826187717,
1243
+ "loss": 0.1249,
1244
+ "step": 1720
1245
+ },
1246
+ {
1247
+ "epoch": 3.42,
1248
+ "learning_rate": 0.00026245654692931634,
1249
+ "loss": 0.1356,
1250
+ "step": 1730
1251
+ },
1252
+ {
1253
+ "epoch": 3.44,
1254
+ "learning_rate": 0.000261008111239861,
1255
+ "loss": 0.1374,
1256
+ "step": 1740
1257
+ },
1258
+ {
1259
+ "epoch": 3.46,
1260
+ "learning_rate": 0.00025955967555040557,
1261
+ "loss": 0.2013,
1262
+ "step": 1750
1263
+ },
1264
+ {
1265
+ "epoch": 3.48,
1266
+ "learning_rate": 0.0002581112398609502,
1267
+ "loss": 0.1337,
1268
+ "step": 1760
1269
+ },
1270
+ {
1271
+ "epoch": 3.5,
1272
+ "learning_rate": 0.0002566628041714948,
1273
+ "loss": 0.1226,
1274
+ "step": 1770
1275
+ },
1276
+ {
1277
+ "epoch": 3.52,
1278
+ "learning_rate": 0.0002552143684820394,
1279
+ "loss": 0.1166,
1280
+ "step": 1780
1281
+ },
1282
+ {
1283
+ "epoch": 3.54,
1284
+ "learning_rate": 0.00025376593279258404,
1285
+ "loss": 0.2308,
1286
+ "step": 1790
1287
+ },
1288
+ {
1289
+ "epoch": 3.56,
1290
+ "learning_rate": 0.00025231749710312863,
1291
+ "loss": 0.1265,
1292
+ "step": 1800
1293
+ },
1294
+ {
1295
+ "epoch": 3.56,
1296
+ "eval_loss": 0.9203845858573914,
1297
+ "eval_rouge1": 0.17454545454545453,
1298
+ "eval_rouge2": 0.07291666666666667,
1299
+ "eval_rougeL": 0.16999999999999998,
1300
+ "eval_rougeLsum": 0.17727272727272728,
1301
+ "eval_runtime": 87.9704,
1302
+ "eval_samples_per_second": 0.227,
1303
+ "eval_steps_per_second": 0.227,
1304
+ "step": 1800
1305
+ },
1306
+ {
1307
+ "epoch": 3.58,
1308
+ "learning_rate": 0.0002508690614136732,
1309
+ "loss": 0.1526,
1310
+ "step": 1810
1311
+ },
1312
+ {
1313
+ "epoch": 3.6,
1314
+ "learning_rate": 0.00024942062572421786,
1315
+ "loss": 0.2201,
1316
+ "step": 1820
1317
+ },
1318
+ {
1319
+ "epoch": 3.62,
1320
+ "learning_rate": 0.00024797219003476245,
1321
+ "loss": 0.1271,
1322
+ "step": 1830
1323
+ },
1324
+ {
1325
+ "epoch": 3.64,
1326
+ "learning_rate": 0.0002465237543453071,
1327
+ "loss": 0.1749,
1328
+ "step": 1840
1329
+ },
1330
+ {
1331
+ "epoch": 3.65,
1332
+ "learning_rate": 0.0002450753186558517,
1333
+ "loss": 0.133,
1334
+ "step": 1850
1335
+ },
1336
+ {
1337
+ "epoch": 3.67,
1338
+ "learning_rate": 0.0002436268829663963,
1339
+ "loss": 0.2259,
1340
+ "step": 1860
1341
+ },
1342
+ {
1343
+ "epoch": 3.69,
1344
+ "learning_rate": 0.00024217844727694092,
1345
+ "loss": 0.1549,
1346
+ "step": 1870
1347
+ },
1348
+ {
1349
+ "epoch": 3.71,
1350
+ "learning_rate": 0.00024073001158748554,
1351
+ "loss": 0.1173,
1352
+ "step": 1880
1353
+ },
1354
+ {
1355
+ "epoch": 3.73,
1356
+ "learning_rate": 0.00023928157589803013,
1357
+ "loss": 0.1337,
1358
+ "step": 1890
1359
+ },
1360
+ {
1361
+ "epoch": 3.75,
1362
+ "learning_rate": 0.00023783314020857474,
1363
+ "loss": 0.1828,
1364
+ "step": 1900
1365
+ },
1366
+ {
1367
+ "epoch": 3.75,
1368
+ "eval_loss": 0.9094276428222656,
1369
+ "eval_rouge1": 0.18,
1370
+ "eval_rouge2": 0.14886363636363636,
1371
+ "eval_rougeL": 0.18,
1372
+ "eval_rougeLsum": 0.18615384615384614,
1373
+ "eval_runtime": 84.5106,
1374
+ "eval_samples_per_second": 0.237,
1375
+ "eval_steps_per_second": 0.237,
1376
+ "step": 1900
1377
+ },
1378
+ {
1379
+ "epoch": 3.77,
1380
+ "learning_rate": 0.00023638470451911936,
1381
+ "loss": 0.1821,
1382
+ "step": 1910
1383
+ },
1384
+ {
1385
+ "epoch": 3.79,
1386
+ "learning_rate": 0.00023493626882966395,
1387
+ "loss": 0.1257,
1388
+ "step": 1920
1389
+ },
1390
+ {
1391
+ "epoch": 3.81,
1392
+ "learning_rate": 0.00023348783314020857,
1393
+ "loss": 0.172,
1394
+ "step": 1930
1395
+ },
1396
+ {
1397
+ "epoch": 3.83,
1398
+ "learning_rate": 0.0002320393974507532,
1399
+ "loss": 0.1833,
1400
+ "step": 1940
1401
+ },
1402
+ {
1403
+ "epoch": 3.85,
1404
+ "learning_rate": 0.0002305909617612978,
1405
+ "loss": 0.1334,
1406
+ "step": 1950
1407
+ },
1408
+ {
1409
+ "epoch": 3.87,
1410
+ "learning_rate": 0.00022914252607184242,
1411
+ "loss": 0.1736,
1412
+ "step": 1960
1413
+ },
1414
+ {
1415
+ "epoch": 3.89,
1416
+ "learning_rate": 0.00022769409038238703,
1417
+ "loss": 0.1163,
1418
+ "step": 1970
1419
+ },
1420
+ {
1421
+ "epoch": 3.91,
1422
+ "learning_rate": 0.00022624565469293165,
1423
+ "loss": 0.1844,
1424
+ "step": 1980
1425
+ },
1426
+ {
1427
+ "epoch": 3.93,
1428
+ "learning_rate": 0.00022479721900347624,
1429
+ "loss": 0.1358,
1430
+ "step": 1990
1431
+ },
1432
+ {
1433
+ "epoch": 3.95,
1434
+ "learning_rate": 0.00022334878331402086,
1435
+ "loss": 0.1447,
1436
+ "step": 2000
1437
+ },
1438
+ {
1439
+ "epoch": 3.95,
1440
+ "eval_loss": 0.89415442943573,
1441
+ "eval_rouge1": 0.19,
1442
+ "eval_rouge2": 0.09886363636363635,
1443
+ "eval_rougeL": 0.18615384615384617,
1444
+ "eval_rougeLsum": 0.19615384615384615,
1445
+ "eval_runtime": 84.0506,
1446
+ "eval_samples_per_second": 0.238,
1447
+ "eval_steps_per_second": 0.238,
1448
+ "step": 2000
1449
+ },
1450
+ {
1451
+ "epoch": 3.97,
1452
+ "learning_rate": 0.00022190034762456547,
1453
+ "loss": 0.1566,
1454
+ "step": 2010
1455
+ },
1456
+ {
1457
+ "epoch": 3.99,
1458
+ "learning_rate": 0.0002204519119351101,
1459
+ "loss": 0.1132,
1460
+ "step": 2020
1461
+ },
1462
+ {
1463
+ "epoch": 4.01,
1464
+ "learning_rate": 0.0002190034762456547,
1465
+ "loss": 0.1013,
1466
+ "step": 2030
1467
+ },
1468
+ {
1469
+ "epoch": 4.03,
1470
+ "learning_rate": 0.00021755504055619932,
1471
+ "loss": 0.1554,
1472
+ "step": 2040
1473
+ },
1474
+ {
1475
+ "epoch": 4.05,
1476
+ "learning_rate": 0.0002161066048667439,
1477
+ "loss": 0.1405,
1478
+ "step": 2050
1479
+ },
1480
+ {
1481
+ "epoch": 4.07,
1482
+ "learning_rate": 0.00021465816917728853,
1483
+ "loss": 0.152,
1484
+ "step": 2060
1485
+ },
1486
+ {
1487
+ "epoch": 4.09,
1488
+ "learning_rate": 0.00021320973348783315,
1489
+ "loss": 0.1591,
1490
+ "step": 2070
1491
+ },
1492
+ {
1493
+ "epoch": 4.11,
1494
+ "learning_rate": 0.00021176129779837773,
1495
+ "loss": 0.152,
1496
+ "step": 2080
1497
+ },
1498
+ {
1499
+ "epoch": 4.13,
1500
+ "learning_rate": 0.00021031286210892235,
1501
+ "loss": 0.1059,
1502
+ "step": 2090
1503
+ },
1504
+ {
1505
+ "epoch": 4.15,
1506
+ "learning_rate": 0.000208864426419467,
1507
+ "loss": 0.099,
1508
+ "step": 2100
1509
+ },
1510
+ {
1511
+ "epoch": 4.15,
1512
+ "eval_loss": 0.9297454953193665,
1513
+ "eval_rouge1": 0.23864468864468863,
1514
+ "eval_rouge2": 0.15,
1515
+ "eval_rougeL": 0.23516483516483513,
1516
+ "eval_rougeLsum": 0.24514652014652014,
1517
+ "eval_runtime": 85.7086,
1518
+ "eval_samples_per_second": 0.233,
1519
+ "eval_steps_per_second": 0.233,
1520
+ "step": 2100
1521
+ },
1522
+ {
1523
+ "epoch": 4.17,
1524
+ "learning_rate": 0.0002074159907300116,
1525
+ "loss": 0.0916,
1526
+ "step": 2110
1527
+ },
1528
+ {
1529
+ "epoch": 4.19,
1530
+ "learning_rate": 0.0002059675550405562,
1531
+ "loss": 0.2006,
1532
+ "step": 2120
1533
+ },
1534
+ {
1535
+ "epoch": 4.21,
1536
+ "learning_rate": 0.00020451911935110082,
1537
+ "loss": 0.144,
1538
+ "step": 2130
1539
+ },
1540
+ {
1541
+ "epoch": 4.23,
1542
+ "learning_rate": 0.00020307068366164544,
1543
+ "loss": 0.1893,
1544
+ "step": 2140
1545
+ },
1546
+ {
1547
+ "epoch": 4.25,
1548
+ "learning_rate": 0.00020162224797219002,
1549
+ "loss": 0.1697,
1550
+ "step": 2150
1551
+ },
1552
+ {
1553
+ "epoch": 4.27,
1554
+ "learning_rate": 0.00020017381228273464,
1555
+ "loss": 0.1101,
1556
+ "step": 2160
1557
+ },
1558
+ {
1559
+ "epoch": 4.29,
1560
+ "learning_rate": 0.00019872537659327929,
1561
+ "loss": 0.1539,
1562
+ "step": 2170
1563
+ },
1564
+ {
1565
+ "epoch": 4.31,
1566
+ "learning_rate": 0.00019727694090382387,
1567
+ "loss": 0.1038,
1568
+ "step": 2180
1569
+ },
1570
+ {
1571
+ "epoch": 4.33,
1572
+ "learning_rate": 0.0001958285052143685,
1573
+ "loss": 0.1466,
1574
+ "step": 2190
1575
+ },
1576
+ {
1577
+ "epoch": 4.35,
1578
+ "learning_rate": 0.0001943800695249131,
1579
+ "loss": 0.1366,
1580
+ "step": 2200
1581
+ },
1582
+ {
1583
+ "epoch": 4.35,
1584
+ "eval_loss": 0.9124263525009155,
1585
+ "eval_rouge1": 0.12,
1586
+ "eval_rouge2": 0.07291666666666667,
1587
+ "eval_rougeL": 0.12,
1588
+ "eval_rougeLsum": 0.12454545454545454,
1589
+ "eval_runtime": 91.5173,
1590
+ "eval_samples_per_second": 0.219,
1591
+ "eval_steps_per_second": 0.219,
1592
+ "step": 2200
1593
+ },
1594
+ {
1595
+ "epoch": 4.37,
1596
+ "learning_rate": 0.0001929316338354577,
1597
+ "loss": 0.1298,
1598
+ "step": 2210
1599
+ },
1600
+ {
1601
+ "epoch": 4.39,
1602
+ "learning_rate": 0.00019148319814600231,
1603
+ "loss": 0.1886,
1604
+ "step": 2220
1605
+ },
1606
+ {
1607
+ "epoch": 4.41,
1608
+ "learning_rate": 0.00019003476245654693,
1609
+ "loss": 0.1579,
1610
+ "step": 2230
1611
+ },
1612
+ {
1613
+ "epoch": 4.43,
1614
+ "learning_rate": 0.00018858632676709152,
1615
+ "loss": 0.1078,
1616
+ "step": 2240
1617
+ },
1618
+ {
1619
+ "epoch": 4.45,
1620
+ "learning_rate": 0.00018713789107763616,
1621
+ "loss": 0.1509,
1622
+ "step": 2250
1623
+ },
1624
+ {
1625
+ "epoch": 4.47,
1626
+ "learning_rate": 0.00018568945538818078,
1627
+ "loss": 0.108,
1628
+ "step": 2260
1629
+ },
1630
+ {
1631
+ "epoch": 4.49,
1632
+ "learning_rate": 0.0001842410196987254,
1633
+ "loss": 0.1305,
1634
+ "step": 2270
1635
+ },
1636
+ {
1637
+ "epoch": 4.5,
1638
+ "learning_rate": 0.00018279258400927,
1639
+ "loss": 0.1257,
1640
+ "step": 2280
1641
+ },
1642
+ {
1643
+ "epoch": 4.52,
1644
+ "learning_rate": 0.0001813441483198146,
1645
+ "loss": 0.117,
1646
+ "step": 2290
1647
+ },
1648
+ {
1649
+ "epoch": 4.54,
1650
+ "learning_rate": 0.00017989571263035922,
1651
+ "loss": 0.1519,
1652
+ "step": 2300
1653
+ },
1654
+ {
1655
+ "epoch": 4.54,
1656
+ "eval_loss": 0.9040172696113586,
1657
+ "eval_rouge1": 0.18727272727272726,
1658
+ "eval_rouge2": 0.09861111111111112,
1659
+ "eval_rougeL": 0.18333333333333332,
1660
+ "eval_rougeLsum": 0.1906060606060606,
1661
+ "eval_runtime": 82.9032,
1662
+ "eval_samples_per_second": 0.241,
1663
+ "eval_steps_per_second": 0.241,
1664
+ "step": 2300
1665
+ },
1666
+ {
1667
+ "epoch": 4.56,
1668
+ "learning_rate": 0.0001784472769409038,
1669
+ "loss": 0.1536,
1670
+ "step": 2310
1671
+ },
1672
+ {
1673
+ "epoch": 4.58,
1674
+ "learning_rate": 0.00017699884125144843,
1675
+ "loss": 0.1159,
1676
+ "step": 2320
1677
+ },
1678
+ {
1679
+ "epoch": 4.6,
1680
+ "learning_rate": 0.00017555040556199307,
1681
+ "loss": 0.1257,
1682
+ "step": 2330
1683
+ },
1684
+ {
1685
+ "epoch": 4.62,
1686
+ "learning_rate": 0.00017410196987253766,
1687
+ "loss": 0.1698,
1688
+ "step": 2340
1689
+ },
1690
+ {
1691
+ "epoch": 4.64,
1692
+ "learning_rate": 0.00017265353418308228,
1693
+ "loss": 0.1369,
1694
+ "step": 2350
1695
+ },
1696
+ {
1697
+ "epoch": 4.66,
1698
+ "learning_rate": 0.0001712050984936269,
1699
+ "loss": 0.0809,
1700
+ "step": 2360
1701
+ },
1702
+ {
1703
+ "epoch": 4.68,
1704
+ "learning_rate": 0.00016975666280417148,
1705
+ "loss": 0.1003,
1706
+ "step": 2370
1707
+ },
1708
+ {
1709
+ "epoch": 4.7,
1710
+ "learning_rate": 0.0001683082271147161,
1711
+ "loss": 0.1066,
1712
+ "step": 2380
1713
+ },
1714
+ {
1715
+ "epoch": 4.72,
1716
+ "learning_rate": 0.00016685979142526072,
1717
+ "loss": 0.1621,
1718
+ "step": 2390
1719
+ },
1720
+ {
1721
+ "epoch": 4.74,
1722
+ "learning_rate": 0.00016541135573580533,
1723
+ "loss": 0.119,
1724
+ "step": 2400
1725
+ },
1726
+ {
1727
+ "epoch": 4.74,
1728
+ "eval_loss": 0.9120545387268066,
1729
+ "eval_rouge1": 0.12,
1730
+ "eval_rouge2": 0.04583333333333333,
1731
+ "eval_rougeL": 0.11285714285714285,
1732
+ "eval_rougeLsum": 0.12285714285714286,
1733
+ "eval_runtime": 84.1673,
1734
+ "eval_samples_per_second": 0.238,
1735
+ "eval_steps_per_second": 0.238,
1736
+ "step": 2400
1737
+ },
1738
+ {
1739
+ "epoch": 4.76,
1740
+ "learning_rate": 0.00016396292004634995,
1741
+ "loss": 0.1185,
1742
+ "step": 2410
1743
+ },
1744
+ {
1745
+ "epoch": 4.78,
1746
+ "learning_rate": 0.00016251448435689457,
1747
+ "loss": 0.1657,
1748
+ "step": 2420
1749
+ },
1750
+ {
1751
+ "epoch": 4.8,
1752
+ "learning_rate": 0.00016106604866743918,
1753
+ "loss": 0.1233,
1754
+ "step": 2430
1755
+ },
1756
+ {
1757
+ "epoch": 4.82,
1758
+ "learning_rate": 0.00015961761297798377,
1759
+ "loss": 0.1611,
1760
+ "step": 2440
1761
+ },
1762
+ {
1763
+ "epoch": 4.84,
1764
+ "learning_rate": 0.0001581691772885284,
1765
+ "loss": 0.1613,
1766
+ "step": 2450
1767
+ },
1768
+ {
1769
+ "epoch": 4.86,
1770
+ "learning_rate": 0.000156720741599073,
1771
+ "loss": 0.1107,
1772
+ "step": 2460
1773
+ },
1774
+ {
1775
+ "epoch": 4.88,
1776
+ "learning_rate": 0.0001552723059096176,
1777
+ "loss": 0.1436,
1778
+ "step": 2470
1779
+ },
1780
+ {
1781
+ "epoch": 4.9,
1782
+ "learning_rate": 0.00015382387022016221,
1783
+ "loss": 0.129,
1784
+ "step": 2480
1785
+ },
1786
+ {
1787
+ "epoch": 4.92,
1788
+ "learning_rate": 0.00015237543453070686,
1789
+ "loss": 0.1586,
1790
+ "step": 2490
1791
+ },
1792
+ {
1793
+ "epoch": 4.94,
1794
+ "learning_rate": 0.00015092699884125145,
1795
+ "loss": 0.1364,
1796
+ "step": 2500
1797
+ },
1798
+ {
1799
+ "epoch": 4.94,
1800
+ "eval_loss": 0.9120429754257202,
1801
+ "eval_rouge1": 0.20904761904761907,
1802
+ "eval_rouge2": 0.12583333333333332,
1803
+ "eval_rougeL": 0.20666666666666664,
1804
+ "eval_rougeLsum": 0.21904761904761902,
1805
+ "eval_runtime": 82.9463,
1806
+ "eval_samples_per_second": 0.241,
1807
+ "eval_steps_per_second": 0.241,
1808
+ "step": 2500
1809
+ },
1810
+ {
1811
+ "epoch": 4.96,
1812
+ "learning_rate": 0.00014947856315179606,
1813
+ "loss": 0.1688,
1814
+ "step": 2510
1815
+ },
1816
+ {
1817
+ "epoch": 4.98,
1818
+ "learning_rate": 0.00014803012746234068,
1819
+ "loss": 0.1385,
1820
+ "step": 2520
1821
+ },
1822
+ {
1823
+ "epoch": 5.0,
1824
+ "learning_rate": 0.0001465816917728853,
1825
+ "loss": 0.1592,
1826
+ "step": 2530
1827
+ },
1828
+ {
1829
+ "epoch": 5.02,
1830
+ "learning_rate": 0.0001451332560834299,
1831
+ "loss": 0.1014,
1832
+ "step": 2540
1833
+ },
1834
+ {
1835
+ "epoch": 5.04,
1836
+ "learning_rate": 0.0001436848203939745,
1837
+ "loss": 0.0796,
1838
+ "step": 2550
1839
+ },
1840
+ {
1841
+ "epoch": 5.06,
1842
+ "learning_rate": 0.00014223638470451912,
1843
+ "loss": 0.0981,
1844
+ "step": 2560
1845
+ },
1846
+ {
1847
+ "epoch": 5.08,
1848
+ "learning_rate": 0.00014078794901506374,
1849
+ "loss": 0.093,
1850
+ "step": 2570
1851
+ },
1852
+ {
1853
+ "epoch": 5.1,
1854
+ "learning_rate": 0.00013933951332560835,
1855
+ "loss": 0.1599,
1856
+ "step": 2580
1857
+ },
1858
+ {
1859
+ "epoch": 5.12,
1860
+ "learning_rate": 0.00013789107763615297,
1861
+ "loss": 0.1223,
1862
+ "step": 2590
1863
+ },
1864
+ {
1865
+ "epoch": 5.14,
1866
+ "learning_rate": 0.00013644264194669756,
1867
+ "loss": 0.1,
1868
+ "step": 2600
1869
+ },
1870
+ {
1871
+ "epoch": 5.14,
1872
+ "eval_loss": 0.9408878087997437,
1873
+ "eval_rouge1": 0.12507936507936507,
1874
+ "eval_rouge2": 0.08333333333333333,
1875
+ "eval_rougeL": 0.12396825396825398,
1876
+ "eval_rougeLsum": 0.13111111111111112,
1877
+ "eval_runtime": 96.2103,
1878
+ "eval_samples_per_second": 0.208,
1879
+ "eval_steps_per_second": 0.208,
1880
+ "step": 2600
1881
+ },
1882
+ {
1883
+ "epoch": 5.16,
1884
+ "learning_rate": 0.00013499420625724218,
1885
+ "loss": 0.1284,
1886
+ "step": 2610
1887
+ },
1888
+ {
1889
+ "epoch": 5.18,
1890
+ "learning_rate": 0.0001335457705677868,
1891
+ "loss": 0.1523,
1892
+ "step": 2620
1893
+ },
1894
+ {
1895
+ "epoch": 5.2,
1896
+ "learning_rate": 0.00013209733487833138,
1897
+ "loss": 0.1051,
1898
+ "step": 2630
1899
+ },
1900
+ {
1901
+ "epoch": 5.22,
1902
+ "learning_rate": 0.00013064889918887603,
1903
+ "loss": 0.1216,
1904
+ "step": 2640
1905
+ },
1906
+ {
1907
+ "epoch": 5.24,
1908
+ "learning_rate": 0.00012920046349942064,
1909
+ "loss": 0.1219,
1910
+ "step": 2650
1911
+ },
1912
+ {
1913
+ "epoch": 5.26,
1914
+ "learning_rate": 0.00012775202780996523,
1915
+ "loss": 0.1482,
1916
+ "step": 2660
1917
+ },
1918
+ {
1919
+ "epoch": 5.28,
1920
+ "learning_rate": 0.00012630359212050985,
1921
+ "loss": 0.1076,
1922
+ "step": 2670
1923
+ },
1924
+ {
1925
+ "epoch": 5.3,
1926
+ "learning_rate": 0.00012485515643105447,
1927
+ "loss": 0.121,
1928
+ "step": 2680
1929
+ },
1930
+ {
1931
+ "epoch": 5.32,
1932
+ "learning_rate": 0.00012340672074159908,
1933
+ "loss": 0.1448,
1934
+ "step": 2690
1935
+ },
1936
+ {
1937
+ "epoch": 5.34,
1938
+ "learning_rate": 0.0001219582850521437,
1939
+ "loss": 0.1683,
1940
+ "step": 2700
1941
+ },
1942
+ {
1943
+ "epoch": 5.34,
1944
+ "eval_loss": 0.9422550201416016,
1945
+ "eval_rouge1": 0.13818181818181818,
1946
+ "eval_rouge2": 0.0951010101010101,
1947
+ "eval_rougeL": 0.13713286713286715,
1948
+ "eval_rougeLsum": 0.14174825174825176,
1949
+ "eval_runtime": 96.365,
1950
+ "eval_samples_per_second": 0.208,
1951
+ "eval_steps_per_second": 0.208,
1952
+ "step": 2700
1953
+ },
1954
+ {
1955
+ "epoch": 5.36,
1956
+ "learning_rate": 0.0001205098493626883,
1957
+ "loss": 0.103,
1958
+ "step": 2710
1959
+ },
1960
+ {
1961
+ "epoch": 5.37,
1962
+ "learning_rate": 0.0001190614136732329,
1963
+ "loss": 0.1434,
1964
+ "step": 2720
1965
+ },
1966
+ {
1967
+ "epoch": 5.39,
1968
+ "learning_rate": 0.00011761297798377752,
1969
+ "loss": 0.1419,
1970
+ "step": 2730
1971
+ },
1972
+ {
1973
+ "epoch": 5.41,
1974
+ "learning_rate": 0.00011616454229432214,
1975
+ "loss": 0.1145,
1976
+ "step": 2740
1977
+ },
1978
+ {
1979
+ "epoch": 5.43,
1980
+ "learning_rate": 0.00011471610660486674,
1981
+ "loss": 0.1302,
1982
+ "step": 2750
1983
+ },
1984
+ {
1985
+ "epoch": 5.45,
1986
+ "learning_rate": 0.00011326767091541136,
1987
+ "loss": 0.0718,
1988
+ "step": 2760
1989
+ },
1990
+ {
1991
+ "epoch": 5.47,
1992
+ "learning_rate": 0.00011181923522595596,
1993
+ "loss": 0.1166,
1994
+ "step": 2770
1995
+ },
1996
+ {
1997
+ "epoch": 5.49,
1998
+ "learning_rate": 0.0001103707995365006,
1999
+ "loss": 0.1265,
2000
+ "step": 2780
2001
+ },
2002
+ {
2003
+ "epoch": 5.51,
2004
+ "learning_rate": 0.0001089223638470452,
2005
+ "loss": 0.0972,
2006
+ "step": 2790
2007
+ },
2008
+ {
2009
+ "epoch": 5.53,
2010
+ "learning_rate": 0.0001074739281575898,
2011
+ "loss": 0.1395,
2012
+ "step": 2800
2013
+ },
2014
+ {
2015
+ "epoch": 5.53,
2016
+ "eval_loss": 0.9336325526237488,
2017
+ "eval_rouge1": 0.16115384615384615,
2018
+ "eval_rouge2": 0.12329545454545454,
2019
+ "eval_rougeL": 0.15999999999999998,
2020
+ "eval_rougeLsum": 0.16307692307692306,
2021
+ "eval_runtime": 93.5346,
2022
+ "eval_samples_per_second": 0.214,
2023
+ "eval_steps_per_second": 0.214,
2024
+ "step": 2800
2025
+ },
2026
+ {
2027
+ "epoch": 5.55,
2028
+ "learning_rate": 0.00010602549246813442,
2029
+ "loss": 0.0808,
2030
+ "step": 2810
2031
+ },
2032
+ {
2033
+ "epoch": 5.57,
2034
+ "learning_rate": 0.00010457705677867903,
2035
+ "loss": 0.1205,
2036
+ "step": 2820
2037
+ },
2038
+ {
2039
+ "epoch": 5.59,
2040
+ "learning_rate": 0.00010312862108922364,
2041
+ "loss": 0.119,
2042
+ "step": 2830
2043
+ },
2044
+ {
2045
+ "epoch": 5.61,
2046
+ "learning_rate": 0.00010168018539976825,
2047
+ "loss": 0.1357,
2048
+ "step": 2840
2049
+ },
2050
+ {
2051
+ "epoch": 5.63,
2052
+ "learning_rate": 0.00010023174971031286,
2053
+ "loss": 0.1144,
2054
+ "step": 2850
2055
+ },
2056
+ {
2057
+ "epoch": 5.65,
2058
+ "learning_rate": 9.878331402085749e-05,
2059
+ "loss": 0.138,
2060
+ "step": 2860
2061
+ },
2062
+ {
2063
+ "epoch": 5.67,
2064
+ "learning_rate": 9.733487833140209e-05,
2065
+ "loss": 0.0998,
2066
+ "step": 2870
2067
+ },
2068
+ {
2069
+ "epoch": 5.69,
2070
+ "learning_rate": 9.588644264194669e-05,
2071
+ "loss": 0.1437,
2072
+ "step": 2880
2073
+ },
2074
+ {
2075
+ "epoch": 5.71,
2076
+ "learning_rate": 9.443800695249131e-05,
2077
+ "loss": 0.1053,
2078
+ "step": 2890
2079
+ },
2080
+ {
2081
+ "epoch": 5.73,
2082
+ "learning_rate": 9.298957126303593e-05,
2083
+ "loss": 0.1067,
2084
+ "step": 2900
2085
+ },
2086
+ {
2087
+ "epoch": 5.73,
2088
+ "eval_loss": 0.9290033578872681,
2089
+ "eval_rouge1": 0.2234265734265734,
2090
+ "eval_rouge2": 0.13156565656565655,
2091
+ "eval_rougeL": 0.21744755244755246,
2092
+ "eval_rougeLsum": 0.2169230769230769,
2093
+ "eval_runtime": 91.8958,
2094
+ "eval_samples_per_second": 0.218,
2095
+ "eval_steps_per_second": 0.218,
2096
+ "step": 2900
2097
+ },
2098
+ {
2099
+ "epoch": 5.75,
2100
+ "learning_rate": 9.154113557358054e-05,
2101
+ "loss": 0.1225,
2102
+ "step": 2910
2103
+ },
2104
+ {
2105
+ "epoch": 5.77,
2106
+ "learning_rate": 9.009269988412515e-05,
2107
+ "loss": 0.0867,
2108
+ "step": 2920
2109
+ },
2110
+ {
2111
+ "epoch": 5.79,
2112
+ "learning_rate": 8.864426419466975e-05,
2113
+ "loss": 0.1325,
2114
+ "step": 2930
2115
+ },
2116
+ {
2117
+ "epoch": 5.81,
2118
+ "learning_rate": 8.719582850521438e-05,
2119
+ "loss": 0.118,
2120
+ "step": 2940
2121
+ },
2122
+ {
2123
+ "epoch": 5.83,
2124
+ "learning_rate": 8.574739281575898e-05,
2125
+ "loss": 0.112,
2126
+ "step": 2950
2127
+ },
2128
+ {
2129
+ "epoch": 5.85,
2130
+ "learning_rate": 8.429895712630359e-05,
2131
+ "loss": 0.1326,
2132
+ "step": 2960
2133
+ },
2134
+ {
2135
+ "epoch": 5.87,
2136
+ "learning_rate": 8.28505214368482e-05,
2137
+ "loss": 0.1506,
2138
+ "step": 2970
2139
+ },
2140
+ {
2141
+ "epoch": 5.89,
2142
+ "learning_rate": 8.140208574739282e-05,
2143
+ "loss": 0.1499,
2144
+ "step": 2980
2145
+ },
2146
+ {
2147
+ "epoch": 5.91,
2148
+ "learning_rate": 7.995365005793744e-05,
2149
+ "loss": 0.1092,
2150
+ "step": 2990
2151
+ },
2152
+ {
2153
+ "epoch": 5.93,
2154
+ "learning_rate": 7.850521436848204e-05,
2155
+ "loss": 0.1104,
2156
+ "step": 3000
2157
+ },
2158
+ {
2159
+ "epoch": 5.93,
2160
+ "eval_loss": 0.9244877696037292,
2161
+ "eval_rouge1": 0.2,
2162
+ "eval_rouge2": 0.1,
2163
+ "eval_rougeL": 0.19153846153846155,
2164
+ "eval_rougeLsum": 0.19153846153846155,
2165
+ "eval_runtime": 93.7022,
2166
+ "eval_samples_per_second": 0.213,
2167
+ "eval_steps_per_second": 0.213,
2168
+ "step": 3000
2169
+ },
2170
+ {
2171
+ "epoch": 5.95,
2172
+ "learning_rate": 7.705677867902664e-05,
2173
+ "loss": 0.0824,
2174
+ "step": 3010
2175
+ },
2176
+ {
2177
+ "epoch": 5.97,
2178
+ "learning_rate": 7.560834298957127e-05,
2179
+ "loss": 0.1048,
2180
+ "step": 3020
2181
+ },
2182
+ {
2183
+ "epoch": 5.99,
2184
+ "learning_rate": 7.415990730011588e-05,
2185
+ "loss": 0.1295,
2186
+ "step": 3030
2187
+ },
2188
+ {
2189
+ "epoch": 6.01,
2190
+ "learning_rate": 7.271147161066048e-05,
2191
+ "loss": 0.1296,
2192
+ "step": 3040
2193
+ },
2194
+ {
2195
+ "epoch": 6.03,
2196
+ "learning_rate": 7.12630359212051e-05,
2197
+ "loss": 0.1146,
2198
+ "step": 3050
2199
+ },
2200
+ {
2201
+ "epoch": 6.05,
2202
+ "learning_rate": 6.981460023174971e-05,
2203
+ "loss": 0.1158,
2204
+ "step": 3060
2205
+ },
2206
+ {
2207
+ "epoch": 6.07,
2208
+ "learning_rate": 6.836616454229433e-05,
2209
+ "loss": 0.094,
2210
+ "step": 3070
2211
+ },
2212
+ {
2213
+ "epoch": 6.09,
2214
+ "learning_rate": 6.691772885283893e-05,
2215
+ "loss": 0.1141,
2216
+ "step": 3080
2217
+ },
2218
+ {
2219
+ "epoch": 6.11,
2220
+ "learning_rate": 6.546929316338354e-05,
2221
+ "loss": 0.1025,
2222
+ "step": 3090
2223
+ },
2224
+ {
2225
+ "epoch": 6.13,
2226
+ "learning_rate": 6.402085747392817e-05,
2227
+ "loss": 0.1474,
2228
+ "step": 3100
2229
+ },
2230
+ {
2231
+ "epoch": 6.13,
2232
+ "eval_loss": 0.9422538876533508,
2233
+ "eval_rouge1": 0.20069541569541566,
2234
+ "eval_rouge2": 0.10303030303030303,
2235
+ "eval_rougeL": 0.19625097125097124,
2236
+ "eval_rougeLsum": 0.19848096348096347,
2237
+ "eval_runtime": 94.7246,
2238
+ "eval_samples_per_second": 0.211,
2239
+ "eval_steps_per_second": 0.211,
2240
+ "step": 3100
2241
+ },
2242
+ {
2243
+ "epoch": 6.15,
2244
+ "learning_rate": 6.257242178447277e-05,
2245
+ "loss": 0.09,
2246
+ "step": 3110
2247
+ },
2248
+ {
2249
+ "epoch": 6.17,
2250
+ "learning_rate": 6.112398609501739e-05,
2251
+ "loss": 0.1235,
2252
+ "step": 3120
2253
+ },
2254
+ {
2255
+ "epoch": 6.19,
2256
+ "learning_rate": 5.9675550405561996e-05,
2257
+ "loss": 0.0733,
2258
+ "step": 3130
2259
+ },
2260
+ {
2261
+ "epoch": 6.21,
2262
+ "learning_rate": 5.822711471610661e-05,
2263
+ "loss": 0.1035,
2264
+ "step": 3140
2265
+ },
2266
+ {
2267
+ "epoch": 6.22,
2268
+ "learning_rate": 5.6778679026651216e-05,
2269
+ "loss": 0.1027,
2270
+ "step": 3150
2271
+ },
2272
+ {
2273
+ "epoch": 6.24,
2274
+ "learning_rate": 5.533024333719583e-05,
2275
+ "loss": 0.0863,
2276
+ "step": 3160
2277
+ },
2278
+ {
2279
+ "epoch": 6.26,
2280
+ "learning_rate": 5.388180764774044e-05,
2281
+ "loss": 0.095,
2282
+ "step": 3170
2283
+ },
2284
+ {
2285
+ "epoch": 6.28,
2286
+ "learning_rate": 5.243337195828506e-05,
2287
+ "loss": 0.1103,
2288
+ "step": 3180
2289
+ },
2290
+ {
2291
+ "epoch": 6.3,
2292
+ "learning_rate": 5.098493626882966e-05,
2293
+ "loss": 0.1325,
2294
+ "step": 3190
2295
+ },
2296
+ {
2297
+ "epoch": 6.32,
2298
+ "learning_rate": 4.953650057937428e-05,
2299
+ "loss": 0.1052,
2300
+ "step": 3200
2301
+ },
2302
+ {
2303
+ "epoch": 6.32,
2304
+ "eval_loss": 0.9328528642654419,
2305
+ "eval_rouge1": 0.2023076923076923,
2306
+ "eval_rouge2": 0.1102272727272727,
2307
+ "eval_rougeL": 0.19999999999999998,
2308
+ "eval_rougeLsum": 0.2,
2309
+ "eval_runtime": 92.8302,
2310
+ "eval_samples_per_second": 0.215,
2311
+ "eval_steps_per_second": 0.215,
2312
+ "step": 3200
2313
+ },
2314
+ {
2315
+ "epoch": 6.34,
2316
+ "learning_rate": 4.808806488991889e-05,
2317
+ "loss": 0.1293,
2318
+ "step": 3210
2319
+ },
2320
+ {
2321
+ "epoch": 6.36,
2322
+ "learning_rate": 4.6639629200463506e-05,
2323
+ "loss": 0.1301,
2324
+ "step": 3220
2325
+ },
2326
+ {
2327
+ "epoch": 6.38,
2328
+ "learning_rate": 4.519119351100811e-05,
2329
+ "loss": 0.0873,
2330
+ "step": 3230
2331
+ },
2332
+ {
2333
+ "epoch": 6.4,
2334
+ "learning_rate": 4.3742757821552725e-05,
2335
+ "loss": 0.1017,
2336
+ "step": 3240
2337
+ },
2338
+ {
2339
+ "epoch": 6.42,
2340
+ "learning_rate": 4.2294322132097335e-05,
2341
+ "loss": 0.0846,
2342
+ "step": 3250
2343
+ },
2344
+ {
2345
+ "epoch": 6.44,
2346
+ "learning_rate": 4.084588644264195e-05,
2347
+ "loss": 0.0898,
2348
+ "step": 3260
2349
+ },
2350
+ {
2351
+ "epoch": 6.46,
2352
+ "learning_rate": 3.9397450753186555e-05,
2353
+ "loss": 0.1494,
2354
+ "step": 3270
2355
+ },
2356
+ {
2357
+ "epoch": 6.48,
2358
+ "learning_rate": 3.794901506373117e-05,
2359
+ "loss": 0.0742,
2360
+ "step": 3280
2361
+ },
2362
+ {
2363
+ "epoch": 6.5,
2364
+ "learning_rate": 3.650057937427578e-05,
2365
+ "loss": 0.0793,
2366
+ "step": 3290
2367
+ },
2368
+ {
2369
+ "epoch": 6.52,
2370
+ "learning_rate": 3.50521436848204e-05,
2371
+ "loss": 0.1203,
2372
+ "step": 3300
2373
+ },
2374
+ {
2375
+ "epoch": 6.52,
2376
+ "eval_loss": 0.9380243420600891,
2377
+ "eval_rouge1": 0.2023076923076923,
2378
+ "eval_rouge2": 0.1102272727272727,
2379
+ "eval_rougeL": 0.19999999999999998,
2380
+ "eval_rougeLsum": 0.2,
2381
+ "eval_runtime": 94.5066,
2382
+ "eval_samples_per_second": 0.212,
2383
+ "eval_steps_per_second": 0.212,
2384
+ "step": 3300
2385
+ },
2386
+ {
2387
+ "epoch": 6.54,
2388
+ "learning_rate": 3.360370799536501e-05,
2389
+ "loss": 0.1257,
2390
+ "step": 3310
2391
+ },
2392
+ {
2393
+ "epoch": 6.56,
2394
+ "learning_rate": 3.215527230590962e-05,
2395
+ "loss": 0.1177,
2396
+ "step": 3320
2397
+ },
2398
+ {
2399
+ "epoch": 6.58,
2400
+ "learning_rate": 3.070683661645423e-05,
2401
+ "loss": 0.1359,
2402
+ "step": 3330
2403
+ },
2404
+ {
2405
+ "epoch": 6.6,
2406
+ "learning_rate": 2.9258400926998842e-05,
2407
+ "loss": 0.1303,
2408
+ "step": 3340
2409
+ },
2410
+ {
2411
+ "epoch": 6.62,
2412
+ "learning_rate": 2.7809965237543452e-05,
2413
+ "loss": 0.0968,
2414
+ "step": 3350
2415
+ },
2416
+ {
2417
+ "epoch": 6.64,
2418
+ "learning_rate": 2.6361529548088065e-05,
2419
+ "loss": 0.1061,
2420
+ "step": 3360
2421
+ },
2422
+ {
2423
+ "epoch": 6.66,
2424
+ "learning_rate": 2.4913093858632675e-05,
2425
+ "loss": 0.1307,
2426
+ "step": 3370
2427
+ },
2428
+ {
2429
+ "epoch": 6.68,
2430
+ "learning_rate": 2.346465816917729e-05,
2431
+ "loss": 0.0981,
2432
+ "step": 3380
2433
+ },
2434
+ {
2435
+ "epoch": 6.7,
2436
+ "learning_rate": 2.20162224797219e-05,
2437
+ "loss": 0.0901,
2438
+ "step": 3390
2439
+ },
2440
+ {
2441
+ "epoch": 6.72,
2442
+ "learning_rate": 2.0567786790266515e-05,
2443
+ "loss": 0.1125,
2444
+ "step": 3400
2445
+ },
2446
+ {
2447
+ "epoch": 6.72,
2448
+ "eval_loss": 0.9421626925468445,
2449
+ "eval_rouge1": 0.18958041958041955,
2450
+ "eval_rouge2": 0.0977272727272727,
2451
+ "eval_rougeL": 0.18615384615384614,
2452
+ "eval_rougeLsum": 0.19,
2453
+ "eval_runtime": 96.4239,
2454
+ "eval_samples_per_second": 0.207,
2455
+ "eval_steps_per_second": 0.207,
2456
+ "step": 3400
2457
+ },
2458
+ {
2459
+ "epoch": 6.74,
2460
+ "learning_rate": 1.9119351100811125e-05,
2461
+ "loss": 0.0823,
2462
+ "step": 3410
2463
+ },
2464
+ {
2465
+ "epoch": 6.76,
2466
+ "learning_rate": 1.767091541135574e-05,
2467
+ "loss": 0.1016,
2468
+ "step": 3420
2469
+ },
2470
+ {
2471
+ "epoch": 6.78,
2472
+ "learning_rate": 1.6222479721900348e-05,
2473
+ "loss": 0.1172,
2474
+ "step": 3430
2475
+ },
2476
+ {
2477
+ "epoch": 6.8,
2478
+ "learning_rate": 1.477404403244496e-05,
2479
+ "loss": 0.0959,
2480
+ "step": 3440
2481
+ },
2482
+ {
2483
+ "epoch": 6.82,
2484
+ "learning_rate": 1.3325608342989572e-05,
2485
+ "loss": 0.1534,
2486
+ "step": 3450
2487
+ },
2488
+ {
2489
+ "epoch": 6.84,
2490
+ "learning_rate": 1.1877172653534183e-05,
2491
+ "loss": 0.125,
2492
+ "step": 3460
2493
+ },
2494
+ {
2495
+ "epoch": 6.86,
2496
+ "learning_rate": 1.0428736964078795e-05,
2497
+ "loss": 0.1221,
2498
+ "step": 3470
2499
+ },
2500
+ {
2501
+ "epoch": 6.88,
2502
+ "learning_rate": 8.980301274623406e-06,
2503
+ "loss": 0.1391,
2504
+ "step": 3480
2505
+ },
2506
+ {
2507
+ "epoch": 6.9,
2508
+ "learning_rate": 7.531865585168019e-06,
2509
+ "loss": 0.0986,
2510
+ "step": 3490
2511
+ },
2512
+ {
2513
+ "epoch": 6.92,
2514
+ "learning_rate": 6.083429895712631e-06,
2515
+ "loss": 0.1323,
2516
+ "step": 3500
2517
+ },
2518
+ {
2519
+ "epoch": 6.92,
2520
+ "eval_loss": 0.9433181881904602,
2521
+ "eval_rouge1": 0.19,
2522
+ "eval_rouge2": 0.0977272727272727,
2523
+ "eval_rougeL": 0.18615384615384617,
2524
+ "eval_rougeLsum": 0.19,
2525
+ "eval_runtime": 94.6833,
2526
+ "eval_samples_per_second": 0.211,
2527
+ "eval_steps_per_second": 0.211,
2528
+ "step": 3500
2529
+ },
2530
+ {
2531
+ "epoch": 6.94,
2532
+ "learning_rate": 0.00015593561368209256,
2533
+ "loss": 0.1147,
2534
+ "step": 3510
2535
+ },
2536
+ {
2537
+ "epoch": 6.95,
2538
+ "learning_rate": 0.00015492957746478874,
2539
+ "loss": 0.0879,
2540
+ "step": 3520
2541
+ },
2542
+ {
2543
+ "epoch": 6.97,
2544
+ "learning_rate": 0.0001539235412474849,
2545
+ "loss": 0.095,
2546
+ "step": 3530
2547
+ },
2548
+ {
2549
+ "epoch": 6.99,
2550
+ "learning_rate": 0.00015291750503018109,
2551
+ "loss": 0.1277,
2552
+ "step": 3540
2553
+ },
2554
+ {
2555
+ "epoch": 7.02,
2556
+ "learning_rate": 0.00015191146881287726,
2557
+ "loss": 0.1332,
2558
+ "step": 3550
2559
+ },
2560
+ {
2561
+ "epoch": 7.04,
2562
+ "learning_rate": 0.00015090543259557344,
2563
+ "loss": 0.1055,
2564
+ "step": 3560
2565
+ },
2566
+ {
2567
+ "epoch": 7.06,
2568
+ "learning_rate": 0.00014989939637826964,
2569
+ "loss": 0.1114,
2570
+ "step": 3570
2571
+ },
2572
+ {
2573
+ "epoch": 7.07,
2574
+ "learning_rate": 0.00014889336016096582,
2575
+ "loss": 0.0983,
2576
+ "step": 3580
2577
+ },
2578
+ {
2579
+ "epoch": 7.09,
2580
+ "learning_rate": 0.00014788732394366196,
2581
+ "loss": 0.0823,
2582
+ "step": 3590
2583
+ },
2584
+ {
2585
+ "epoch": 7.11,
2586
+ "learning_rate": 0.00014688128772635814,
2587
+ "loss": 0.0949,
2588
+ "step": 3600
2589
+ },
2590
+ {
2591
+ "epoch": 7.11,
2592
+ "eval_loss": 0.9529324769973755,
2593
+ "eval_rouge1": 0.1603205128205128,
2594
+ "eval_rouge2": 0.09454545454545453,
2595
+ "eval_rougeL": 0.16115384615384615,
2596
+ "eval_rougeLsum": 0.15993589743589742,
2597
+ "eval_runtime": 96.2453,
2598
+ "eval_samples_per_second": 0.208,
2599
+ "eval_steps_per_second": 0.208,
2600
+ "step": 3600
2601
+ },
2602
+ {
2603
+ "epoch": 7.13,
2604
+ "learning_rate": 0.00014587525150905434,
2605
+ "loss": 0.0698,
2606
+ "step": 3610
2607
+ },
2608
+ {
2609
+ "epoch": 7.15,
2610
+ "learning_rate": 0.00014486921529175052,
2611
+ "loss": 0.0694,
2612
+ "step": 3620
2613
+ },
2614
+ {
2615
+ "epoch": 7.17,
2616
+ "learning_rate": 0.0001438631790744467,
2617
+ "loss": 0.1078,
2618
+ "step": 3630
2619
+ },
2620
+ {
2621
+ "epoch": 7.19,
2622
+ "learning_rate": 0.00014285714285714284,
2623
+ "loss": 0.1292,
2624
+ "step": 3640
2625
+ },
2626
+ {
2627
+ "epoch": 7.21,
2628
+ "learning_rate": 0.00014185110663983904,
2629
+ "loss": 0.1175,
2630
+ "step": 3650
2631
+ },
2632
+ {
2633
+ "epoch": 7.23,
2634
+ "learning_rate": 0.00014084507042253522,
2635
+ "loss": 0.1168,
2636
+ "step": 3660
2637
+ },
2638
+ {
2639
+ "epoch": 7.25,
2640
+ "learning_rate": 0.0001398390342052314,
2641
+ "loss": 0.0948,
2642
+ "step": 3670
2643
+ },
2644
+ {
2645
+ "epoch": 7.27,
2646
+ "learning_rate": 0.00013883299798792757,
2647
+ "loss": 0.1314,
2648
+ "step": 3680
2649
+ },
2650
+ {
2651
+ "epoch": 7.29,
2652
+ "learning_rate": 0.00013782696177062375,
2653
+ "loss": 0.1068,
2654
+ "step": 3690
2655
+ },
2656
+ {
2657
+ "epoch": 7.31,
2658
+ "learning_rate": 0.00013682092555331992,
2659
+ "loss": 0.1059,
2660
+ "step": 3700
2661
+ },
2662
+ {
2663
+ "epoch": 7.31,
2664
+ "eval_loss": 0.9520353078842163,
2665
+ "eval_rouge1": 0.13832167832167833,
2666
+ "eval_rouge2": 0.0977272727272727,
2667
+ "eval_rougeL": 0.14185314685314687,
2668
+ "eval_rougeLsum": 0.13999999999999999,
2669
+ "eval_runtime": 91.3536,
2670
+ "eval_samples_per_second": 0.219,
2671
+ "eval_steps_per_second": 0.219,
2672
+ "step": 3700
2673
+ },
2674
+ {
2675
+ "epoch": 7.33,
2676
+ "learning_rate": 0.0001358148893360161,
2677
+ "loss": 0.0945,
2678
+ "step": 3710
2679
+ },
2680
+ {
2681
+ "epoch": 7.35,
2682
+ "learning_rate": 0.00013480885311871227,
2683
+ "loss": 0.1298,
2684
+ "step": 3720
2685
+ },
2686
+ {
2687
+ "epoch": 7.37,
2688
+ "learning_rate": 0.00013380281690140845,
2689
+ "loss": 0.0972,
2690
+ "step": 3730
2691
+ },
2692
+ {
2693
+ "epoch": 7.39,
2694
+ "learning_rate": 0.00013279678068410465,
2695
+ "loss": 0.1007,
2696
+ "step": 3740
2697
+ },
2698
+ {
2699
+ "epoch": 7.41,
2700
+ "learning_rate": 0.0001317907444668008,
2701
+ "loss": 0.1194,
2702
+ "step": 3750
2703
+ },
2704
+ {
2705
+ "epoch": 7.43,
2706
+ "learning_rate": 0.00013078470824949697,
2707
+ "loss": 0.1416,
2708
+ "step": 3760
2709
+ },
2710
+ {
2711
+ "epoch": 7.45,
2712
+ "learning_rate": 0.00012977867203219315,
2713
+ "loss": 0.1112,
2714
+ "step": 3770
2715
+ },
2716
+ {
2717
+ "epoch": 7.47,
2718
+ "learning_rate": 0.00012877263581488935,
2719
+ "loss": 0.1232,
2720
+ "step": 3780
2721
+ },
2722
+ {
2723
+ "epoch": 7.49,
2724
+ "learning_rate": 0.00012776659959758553,
2725
+ "loss": 0.1053,
2726
+ "step": 3790
2727
+ },
2728
+ {
2729
+ "epoch": 7.51,
2730
+ "learning_rate": 0.0001267605633802817,
2731
+ "loss": 0.1482,
2732
+ "step": 3800
2733
+ },
2734
+ {
2735
+ "epoch": 7.51,
2736
+ "eval_loss": 0.9513714909553528,
2737
+ "eval_rouge1": 0.21115384615384616,
2738
+ "eval_rouge2": 0.12045454545454545,
2739
+ "eval_rougeL": 0.20999999999999996,
2740
+ "eval_rougeLsum": 0.20730769230769228,
2741
+ "eval_runtime": 90.7686,
2742
+ "eval_samples_per_second": 0.22,
2743
+ "eval_steps_per_second": 0.22,
2744
+ "step": 3800
2745
+ },
2746
+ {
2747
+ "epoch": 7.53,
2748
+ "learning_rate": 0.00012575452716297785,
2749
+ "loss": 0.1281,
2750
+ "step": 3810
2751
+ },
2752
+ {
2753
+ "epoch": 7.55,
2754
+ "learning_rate": 0.00012474849094567405,
2755
+ "loss": 0.1547,
2756
+ "step": 3820
2757
+ },
2758
+ {
2759
+ "epoch": 7.57,
2760
+ "learning_rate": 0.00012374245472837023,
2761
+ "loss": 0.1283,
2762
+ "step": 3830
2763
+ },
2764
+ {
2765
+ "epoch": 7.59,
2766
+ "learning_rate": 0.0001227364185110664,
2767
+ "loss": 0.174,
2768
+ "step": 3840
2769
+ },
2770
+ {
2771
+ "epoch": 7.61,
2772
+ "learning_rate": 0.00012173038229376258,
2773
+ "loss": 0.0827,
2774
+ "step": 3850
2775
+ },
2776
+ {
2777
+ "epoch": 7.63,
2778
+ "learning_rate": 0.00012072434607645876,
2779
+ "loss": 0.1174,
2780
+ "step": 3860
2781
+ },
2782
+ {
2783
+ "epoch": 7.65,
2784
+ "learning_rate": 0.00011971830985915493,
2785
+ "loss": 0.0914,
2786
+ "step": 3870
2787
+ },
2788
+ {
2789
+ "epoch": 7.67,
2790
+ "learning_rate": 0.0001187122736418511,
2791
+ "loss": 0.1205,
2792
+ "step": 3880
2793
+ },
2794
+ {
2795
+ "epoch": 7.69,
2796
+ "learning_rate": 0.00011770623742454728,
2797
+ "loss": 0.0821,
2798
+ "step": 3890
2799
+ },
2800
+ {
2801
+ "epoch": 7.71,
2802
+ "learning_rate": 0.00011670020120724347,
2803
+ "loss": 0.1268,
2804
+ "step": 3900
2805
+ },
2806
+ {
2807
+ "epoch": 7.71,
2808
+ "eval_loss": 0.938602089881897,
2809
+ "eval_rouge1": 0.20384615384615384,
2810
+ "eval_rouge2": 0.10909090909090909,
2811
+ "eval_rougeL": 0.20153846153846153,
2812
+ "eval_rougeLsum": 0.20076923076923076,
2813
+ "eval_runtime": 89.8217,
2814
+ "eval_samples_per_second": 0.223,
2815
+ "eval_steps_per_second": 0.223,
2816
+ "step": 3900
2817
+ },
2818
+ {
2819
+ "epoch": 7.73,
2820
+ "learning_rate": 0.00011569416498993963,
2821
+ "loss": 0.0964,
2822
+ "step": 3910
2823
+ },
2824
+ {
2825
+ "epoch": 7.75,
2826
+ "learning_rate": 0.00011468812877263582,
2827
+ "loss": 0.0878,
2828
+ "step": 3920
2829
+ },
2830
+ {
2831
+ "epoch": 7.77,
2832
+ "learning_rate": 0.00011368209255533198,
2833
+ "loss": 0.1205,
2834
+ "step": 3930
2835
+ },
2836
+ {
2837
+ "epoch": 7.79,
2838
+ "learning_rate": 0.00011267605633802817,
2839
+ "loss": 0.0916,
2840
+ "step": 3940
2841
+ },
2842
+ {
2843
+ "epoch": 7.8,
2844
+ "learning_rate": 0.00011167002012072435,
2845
+ "loss": 0.1021,
2846
+ "step": 3950
2847
+ },
2848
+ {
2849
+ "epoch": 7.82,
2850
+ "learning_rate": 0.00011066398390342052,
2851
+ "loss": 0.0843,
2852
+ "step": 3960
2853
+ },
2854
+ {
2855
+ "epoch": 7.84,
2856
+ "learning_rate": 0.0001096579476861167,
2857
+ "loss": 0.0947,
2858
+ "step": 3970
2859
+ },
2860
+ {
2861
+ "epoch": 7.86,
2862
+ "learning_rate": 0.00010865191146881289,
2863
+ "loss": 0.0884,
2864
+ "step": 3980
2865
+ },
2866
+ {
2867
+ "epoch": 7.88,
2868
+ "learning_rate": 0.00010764587525150905,
2869
+ "loss": 0.0943,
2870
+ "step": 3990
2871
+ },
2872
+ {
2873
+ "epoch": 7.9,
2874
+ "learning_rate": 0.00010663983903420524,
2875
+ "loss": 0.089,
2876
+ "step": 4000
2877
+ },
2878
+ {
2879
+ "epoch": 7.9,
2880
+ "eval_loss": 0.9426229596138,
2881
+ "eval_rouge1": 0.15076923076923077,
2882
+ "eval_rouge2": 0.1181818181818182,
2883
+ "eval_rougeL": 0.15615384615384614,
2884
+ "eval_rougeLsum": 0.15384615384615383,
2885
+ "eval_runtime": 90.9011,
2886
+ "eval_samples_per_second": 0.22,
2887
+ "eval_steps_per_second": 0.22,
2888
+ "step": 4000
2889
+ },
2890
+ {
2891
+ "epoch": 7.92,
2892
+ "learning_rate": 0.00010563380281690141,
2893
+ "loss": 0.1264,
2894
+ "step": 4010
2895
+ },
2896
+ {
2897
+ "epoch": 7.94,
2898
+ "learning_rate": 0.00010462776659959759,
2899
+ "loss": 0.1026,
2900
+ "step": 4020
2901
+ },
2902
+ {
2903
+ "epoch": 7.96,
2904
+ "learning_rate": 0.00010362173038229377,
2905
+ "loss": 0.1348,
2906
+ "step": 4030
2907
+ },
2908
+ {
2909
+ "epoch": 7.98,
2910
+ "learning_rate": 0.00010261569416498995,
2911
+ "loss": 0.1893,
2912
+ "step": 4040
2913
+ },
2914
+ {
2915
+ "epoch": 8.0,
2916
+ "learning_rate": 0.00010160965794768612,
2917
+ "loss": 0.1048,
2918
+ "step": 4050
2919
+ },
2920
+ {
2921
+ "epoch": 8.02,
2922
+ "learning_rate": 0.0001006036217303823,
2923
+ "loss": 0.1576,
2924
+ "step": 4060
2925
+ },
2926
+ {
2927
+ "epoch": 8.04,
2928
+ "learning_rate": 9.959758551307847e-05,
2929
+ "loss": 0.1084,
2930
+ "step": 4070
2931
+ },
2932
+ {
2933
+ "epoch": 8.06,
2934
+ "learning_rate": 9.859154929577464e-05,
2935
+ "loss": 0.089,
2936
+ "step": 4080
2937
+ },
2938
+ {
2939
+ "epoch": 8.08,
2940
+ "learning_rate": 9.758551307847083e-05,
2941
+ "loss": 0.0989,
2942
+ "step": 4090
2943
+ },
2944
+ {
2945
+ "epoch": 8.1,
2946
+ "learning_rate": 9.6579476861167e-05,
2947
+ "loss": 0.108,
2948
+ "step": 4100
2949
+ },
2950
+ {
2951
+ "epoch": 8.1,
2952
+ "eval_loss": 0.9726575016975403,
2953
+ "eval_rouge1": 0.1383333333333333,
2954
+ "eval_rouge2": 0.10340909090909092,
2955
+ "eval_rougeL": 0.14448717948717948,
2956
+ "eval_rougeLsum": 0.13666666666666666,
2957
+ "eval_runtime": 89.426,
2958
+ "eval_samples_per_second": 0.224,
2959
+ "eval_steps_per_second": 0.224,
2960
+ "step": 4100
2961
+ },
2962
+ {
2963
+ "epoch": 8.12,
2964
+ "learning_rate": 9.557344064386318e-05,
2965
+ "loss": 0.0576,
2966
+ "step": 4110
2967
+ },
2968
+ {
2969
+ "epoch": 8.14,
2970
+ "learning_rate": 9.456740442655936e-05,
2971
+ "loss": 0.0937,
2972
+ "step": 4120
2973
+ },
2974
+ {
2975
+ "epoch": 8.16,
2976
+ "learning_rate": 9.356136820925553e-05,
2977
+ "loss": 0.0814,
2978
+ "step": 4130
2979
+ },
2980
+ {
2981
+ "epoch": 8.18,
2982
+ "learning_rate": 9.255533199195171e-05,
2983
+ "loss": 0.0832,
2984
+ "step": 4140
2985
+ },
2986
+ {
2987
+ "epoch": 8.2,
2988
+ "learning_rate": 9.15492957746479e-05,
2989
+ "loss": 0.0881,
2990
+ "step": 4150
2991
+ },
2992
+ {
2993
+ "epoch": 8.22,
2994
+ "learning_rate": 9.054325955734406e-05,
2995
+ "loss": 0.0785,
2996
+ "step": 4160
2997
+ },
2998
+ {
2999
+ "epoch": 8.24,
3000
+ "learning_rate": 8.953722334004025e-05,
3001
+ "loss": 0.1046,
3002
+ "step": 4170
3003
+ },
3004
+ {
3005
+ "epoch": 8.26,
3006
+ "learning_rate": 8.853118712273642e-05,
3007
+ "loss": 0.1137,
3008
+ "step": 4180
3009
+ },
3010
+ {
3011
+ "epoch": 8.28,
3012
+ "learning_rate": 8.75251509054326e-05,
3013
+ "loss": 0.0966,
3014
+ "step": 4190
3015
+ },
3016
+ {
3017
+ "epoch": 8.3,
3018
+ "learning_rate": 8.651911468812877e-05,
3019
+ "loss": 0.1292,
3020
+ "step": 4200
3021
+ },
3022
+ {
3023
+ "epoch": 8.3,
3024
+ "eval_loss": 0.9639500379562378,
3025
+ "eval_rouge1": 0.21000000000000002,
3026
+ "eval_rouge2": 0.12563131313131312,
3027
+ "eval_rougeL": 0.2097902097902098,
3028
+ "eval_rougeLsum": 0.20979020979020976,
3029
+ "eval_runtime": 86.8779,
3030
+ "eval_samples_per_second": 0.23,
3031
+ "eval_steps_per_second": 0.23,
3032
+ "step": 4200
3033
+ },
3034
+ {
3035
+ "epoch": 8.32,
3036
+ "learning_rate": 8.551307847082495e-05,
3037
+ "loss": 0.099,
3038
+ "step": 4210
3039
+ },
3040
+ {
3041
+ "epoch": 8.34,
3042
+ "learning_rate": 8.450704225352113e-05,
3043
+ "loss": 0.082,
3044
+ "step": 4220
3045
+ },
3046
+ {
3047
+ "epoch": 8.36,
3048
+ "learning_rate": 8.350100603621731e-05,
3049
+ "loss": 0.1007,
3050
+ "step": 4230
3051
+ },
3052
+ {
3053
+ "epoch": 8.38,
3054
+ "learning_rate": 8.249496981891348e-05,
3055
+ "loss": 0.0826,
3056
+ "step": 4240
3057
+ },
3058
+ {
3059
+ "epoch": 8.4,
3060
+ "learning_rate": 8.148893360160967e-05,
3061
+ "loss": 0.0823,
3062
+ "step": 4250
3063
+ },
3064
+ {
3065
+ "epoch": 8.42,
3066
+ "learning_rate": 8.048289738430584e-05,
3067
+ "loss": 0.0863,
3068
+ "step": 4260
3069
+ },
3070
+ {
3071
+ "epoch": 8.44,
3072
+ "learning_rate": 7.9476861167002e-05,
3073
+ "loss": 0.1037,
3074
+ "step": 4270
3075
+ },
3076
+ {
3077
+ "epoch": 8.46,
3078
+ "learning_rate": 7.847082494969819e-05,
3079
+ "loss": 0.097,
3080
+ "step": 4280
3081
+ },
3082
+ {
3083
+ "epoch": 8.48,
3084
+ "learning_rate": 7.746478873239437e-05,
3085
+ "loss": 0.0589,
3086
+ "step": 4290
3087
+ },
3088
+ {
3089
+ "epoch": 8.5,
3090
+ "learning_rate": 7.645875251509054e-05,
3091
+ "loss": 0.0868,
3092
+ "step": 4300
3093
+ },
3094
+ {
3095
+ "epoch": 8.5,
3096
+ "eval_loss": 0.9618169069290161,
3097
+ "eval_rouge1": 0.15,
3098
+ "eval_rouge2": 0.09431818181818181,
3099
+ "eval_rougeL": 0.15076923076923077,
3100
+ "eval_rougeLsum": 0.1465384615384615,
3101
+ "eval_runtime": 86.2134,
3102
+ "eval_samples_per_second": 0.232,
3103
+ "eval_steps_per_second": 0.232,
3104
+ "step": 4300
3105
+ },
3106
+ {
3107
+ "epoch": 8.52,
3108
+ "learning_rate": 7.545271629778672e-05,
3109
+ "loss": 0.0964,
3110
+ "step": 4310
3111
+ },
3112
+ {
3113
+ "epoch": 8.54,
3114
+ "learning_rate": 7.444668008048291e-05,
3115
+ "loss": 0.1144,
3116
+ "step": 4320
3117
+ },
3118
+ {
3119
+ "epoch": 8.56,
3120
+ "learning_rate": 7.344064386317907e-05,
3121
+ "loss": 0.1029,
3122
+ "step": 4330
3123
+ },
3124
+ {
3125
+ "epoch": 8.58,
3126
+ "learning_rate": 7.243460764587526e-05,
3127
+ "loss": 0.0978,
3128
+ "step": 4340
3129
+ },
3130
+ {
3131
+ "epoch": 8.6,
3132
+ "learning_rate": 7.142857142857142e-05,
3133
+ "loss": 0.142,
3134
+ "step": 4350
3135
+ },
3136
+ {
3137
+ "epoch": 8.62,
3138
+ "learning_rate": 7.042253521126761e-05,
3139
+ "loss": 0.0957,
3140
+ "step": 4360
3141
+ },
3142
+ {
3143
+ "epoch": 8.64,
3144
+ "learning_rate": 6.941649899396378e-05,
3145
+ "loss": 0.0896,
3146
+ "step": 4370
3147
+ },
3148
+ {
3149
+ "epoch": 8.65,
3150
+ "learning_rate": 6.841046277665996e-05,
3151
+ "loss": 0.0998,
3152
+ "step": 4380
3153
+ },
3154
+ {
3155
+ "epoch": 8.67,
3156
+ "learning_rate": 6.740442655935614e-05,
3157
+ "loss": 0.0828,
3158
+ "step": 4390
3159
+ },
3160
+ {
3161
+ "epoch": 8.69,
3162
+ "learning_rate": 6.639839034205232e-05,
3163
+ "loss": 0.1023,
3164
+ "step": 4400
3165
+ },
3166
+ {
3167
+ "epoch": 8.69,
3168
+ "eval_loss": 0.9609012603759766,
3169
+ "eval_rouge1": 0.18,
3170
+ "eval_rouge2": 0.075,
3171
+ "eval_rougeL": 0.18,
3172
+ "eval_rougeLsum": 0.18,
3173
+ "eval_runtime": 85.733,
3174
+ "eval_samples_per_second": 0.233,
3175
+ "eval_steps_per_second": 0.233,
3176
+ "step": 4400
3177
+ },
3178
+ {
3179
+ "epoch": 8.71,
3180
+ "learning_rate": 6.539235412474849e-05,
3181
+ "loss": 0.1324,
3182
+ "step": 4410
3183
+ },
3184
+ {
3185
+ "epoch": 8.73,
3186
+ "learning_rate": 6.438631790744468e-05,
3187
+ "loss": 0.1107,
3188
+ "step": 4420
3189
+ },
3190
+ {
3191
+ "epoch": 8.75,
3192
+ "learning_rate": 6.338028169014085e-05,
3193
+ "loss": 0.0756,
3194
+ "step": 4430
3195
+ },
3196
+ {
3197
+ "epoch": 8.77,
3198
+ "learning_rate": 6.237424547283703e-05,
3199
+ "loss": 0.1019,
3200
+ "step": 4440
3201
+ },
3202
+ {
3203
+ "epoch": 8.79,
3204
+ "learning_rate": 6.13682092555332e-05,
3205
+ "loss": 0.1232,
3206
+ "step": 4450
3207
+ },
3208
+ {
3209
+ "epoch": 8.81,
3210
+ "learning_rate": 6.036217303822938e-05,
3211
+ "loss": 0.1186,
3212
+ "step": 4460
3213
+ },
3214
+ {
3215
+ "epoch": 8.83,
3216
+ "learning_rate": 5.935613682092555e-05,
3217
+ "loss": 0.1093,
3218
+ "step": 4470
3219
+ },
3220
+ {
3221
+ "epoch": 8.85,
3222
+ "learning_rate": 5.8350100603621735e-05,
3223
+ "loss": 0.1009,
3224
+ "step": 4480
3225
+ },
3226
+ {
3227
+ "epoch": 8.87,
3228
+ "learning_rate": 5.734406438631791e-05,
3229
+ "loss": 0.0878,
3230
+ "step": 4490
3231
+ },
3232
+ {
3233
+ "epoch": 8.89,
3234
+ "learning_rate": 5.6338028169014086e-05,
3235
+ "loss": 0.1102,
3236
+ "step": 4500
3237
+ },
3238
+ {
3239
+ "epoch": 8.89,
3240
+ "eval_loss": 0.9644363522529602,
3241
+ "eval_rouge1": 0.14615384615384613,
3242
+ "eval_rouge2": 0.1,
3243
+ "eval_rougeL": 0.15115384615384614,
3244
+ "eval_rougeLsum": 0.145,
3245
+ "eval_runtime": 83.9759,
3246
+ "eval_samples_per_second": 0.238,
3247
+ "eval_steps_per_second": 0.238,
3248
+ "step": 4500
3249
+ },
3250
+ {
3251
+ "epoch": 8.91,
3252
+ "learning_rate": 5.533199195171026e-05,
3253
+ "loss": 0.1363,
3254
+ "step": 4510
3255
+ },
3256
+ {
3257
+ "epoch": 8.93,
3258
+ "learning_rate": 5.4325955734406444e-05,
3259
+ "loss": 0.0738,
3260
+ "step": 4520
3261
+ },
3262
+ {
3263
+ "epoch": 8.95,
3264
+ "learning_rate": 5.331991951710262e-05,
3265
+ "loss": 0.0649,
3266
+ "step": 4530
3267
+ },
3268
+ {
3269
+ "epoch": 8.97,
3270
+ "learning_rate": 5.2313883299798795e-05,
3271
+ "loss": 0.0971,
3272
+ "step": 4540
3273
+ },
3274
+ {
3275
+ "epoch": 8.99,
3276
+ "learning_rate": 5.130784708249498e-05,
3277
+ "loss": 0.0688,
3278
+ "step": 4550
3279
+ },
3280
+ {
3281
+ "epoch": 9.01,
3282
+ "learning_rate": 5.030181086519115e-05,
3283
+ "loss": 0.0837,
3284
+ "step": 4560
3285
+ },
3286
+ {
3287
+ "epoch": 9.03,
3288
+ "learning_rate": 4.929577464788732e-05,
3289
+ "loss": 0.0891,
3290
+ "step": 4570
3291
+ },
3292
+ {
3293
+ "epoch": 9.05,
3294
+ "learning_rate": 4.82897384305835e-05,
3295
+ "loss": 0.0744,
3296
+ "step": 4580
3297
+ },
3298
+ {
3299
+ "epoch": 9.07,
3300
+ "learning_rate": 4.728370221327968e-05,
3301
+ "loss": 0.0906,
3302
+ "step": 4590
3303
+ },
3304
+ {
3305
+ "epoch": 9.09,
3306
+ "learning_rate": 4.6277665995975854e-05,
3307
+ "loss": 0.1102,
3308
+ "step": 4600
3309
+ },
3310
+ {
3311
+ "epoch": 9.09,
3312
+ "eval_loss": 0.9806769490242004,
3313
+ "eval_rouge1": 0.12615384615384617,
3314
+ "eval_rouge2": 0.08636363636363635,
3315
+ "eval_rougeL": 0.13615384615384613,
3316
+ "eval_rougeLsum": 0.12615384615384617,
3317
+ "eval_runtime": 88.592,
3318
+ "eval_samples_per_second": 0.226,
3319
+ "eval_steps_per_second": 0.226,
3320
+ "step": 4600
3321
+ },
3322
+ {
3323
+ "epoch": 9.11,
3324
+ "learning_rate": 4.527162977867203e-05,
3325
+ "loss": 0.072,
3326
+ "step": 4610
3327
+ },
3328
+ {
3329
+ "epoch": 9.13,
3330
+ "learning_rate": 4.426559356136821e-05,
3331
+ "loss": 0.0729,
3332
+ "step": 4620
3333
+ },
3334
+ {
3335
+ "epoch": 9.15,
3336
+ "learning_rate": 4.325955734406439e-05,
3337
+ "loss": 0.0884,
3338
+ "step": 4630
3339
+ },
3340
+ {
3341
+ "epoch": 9.17,
3342
+ "learning_rate": 4.225352112676056e-05,
3343
+ "loss": 0.0782,
3344
+ "step": 4640
3345
+ },
3346
+ {
3347
+ "epoch": 9.19,
3348
+ "learning_rate": 4.124748490945674e-05,
3349
+ "loss": 0.0879,
3350
+ "step": 4650
3351
+ },
3352
+ {
3353
+ "epoch": 9.21,
3354
+ "learning_rate": 4.024144869215292e-05,
3355
+ "loss": 0.1,
3356
+ "step": 4660
3357
+ },
3358
+ {
3359
+ "epoch": 9.23,
3360
+ "learning_rate": 3.9235412474849096e-05,
3361
+ "loss": 0.0867,
3362
+ "step": 4670
3363
+ },
3364
+ {
3365
+ "epoch": 9.25,
3366
+ "learning_rate": 3.822937625754527e-05,
3367
+ "loss": 0.0881,
3368
+ "step": 4680
3369
+ },
3370
+ {
3371
+ "epoch": 9.27,
3372
+ "learning_rate": 3.7223340040241454e-05,
3373
+ "loss": 0.0903,
3374
+ "step": 4690
3375
+ },
3376
+ {
3377
+ "epoch": 9.29,
3378
+ "learning_rate": 3.621730382293763e-05,
3379
+ "loss": 0.0942,
3380
+ "step": 4700
3381
+ },
3382
+ {
3383
+ "epoch": 9.29,
3384
+ "eval_loss": 0.9865831136703491,
3385
+ "eval_rouge1": 0.13999999999999999,
3386
+ "eval_rouge2": 0.09772727272727272,
3387
+ "eval_rougeL": 0.14615384615384613,
3388
+ "eval_rougeLsum": 0.13999999999999999,
3389
+ "eval_runtime": 86.651,
3390
+ "eval_samples_per_second": 0.231,
3391
+ "eval_steps_per_second": 0.231,
3392
+ "step": 4700
3393
+ },
3394
+ {
3395
+ "epoch": 9.31,
3396
+ "learning_rate": 3.5211267605633805e-05,
3397
+ "loss": 0.1079,
3398
+ "step": 4710
3399
+ },
3400
+ {
3401
+ "epoch": 9.33,
3402
+ "learning_rate": 3.420523138832998e-05,
3403
+ "loss": 0.0807,
3404
+ "step": 4720
3405
+ },
3406
+ {
3407
+ "epoch": 9.35,
3408
+ "learning_rate": 3.319919517102616e-05,
3409
+ "loss": 0.105,
3410
+ "step": 4730
3411
+ },
3412
+ {
3413
+ "epoch": 9.37,
3414
+ "learning_rate": 3.219315895372234e-05,
3415
+ "loss": 0.095,
3416
+ "step": 4740
3417
+ },
3418
+ {
3419
+ "epoch": 9.39,
3420
+ "learning_rate": 3.118712273641851e-05,
3421
+ "loss": 0.0965,
3422
+ "step": 4750
3423
+ },
3424
+ {
3425
+ "epoch": 9.41,
3426
+ "learning_rate": 3.018108651911469e-05,
3427
+ "loss": 0.1001,
3428
+ "step": 4760
3429
+ },
3430
+ {
3431
+ "epoch": 9.43,
3432
+ "learning_rate": 2.9175050301810868e-05,
3433
+ "loss": 0.0782,
3434
+ "step": 4770
3435
+ },
3436
+ {
3437
+ "epoch": 9.45,
3438
+ "learning_rate": 2.8169014084507043e-05,
3439
+ "loss": 0.115,
3440
+ "step": 4780
3441
+ },
3442
+ {
3443
+ "epoch": 9.47,
3444
+ "learning_rate": 2.7162977867203222e-05,
3445
+ "loss": 0.071,
3446
+ "step": 4790
3447
+ },
3448
+ {
3449
+ "epoch": 9.49,
3450
+ "learning_rate": 2.6156941649899397e-05,
3451
+ "loss": 0.129,
3452
+ "step": 4800
3453
+ },
3454
+ {
3455
+ "epoch": 9.49,
3456
+ "eval_loss": 0.9853466153144836,
3457
+ "eval_rouge1": 0.12837606837606838,
3458
+ "eval_rouge2": 0.08636363636363635,
3459
+ "eval_rougeL": 0.13615384615384613,
3460
+ "eval_rougeLsum": 0.1294871794871795,
3461
+ "eval_runtime": 86.6444,
3462
+ "eval_samples_per_second": 0.231,
3463
+ "eval_steps_per_second": 0.231,
3464
+ "step": 4800
3465
+ },
3466
+ {
3467
+ "epoch": 9.5,
3468
+ "learning_rate": 2.5150905432595576e-05,
3469
+ "loss": 0.1285,
3470
+ "step": 4810
3471
+ },
3472
+ {
3473
+ "epoch": 9.52,
3474
+ "learning_rate": 2.414486921529175e-05,
3475
+ "loss": 0.0747,
3476
+ "step": 4820
3477
+ },
3478
+ {
3479
+ "epoch": 9.54,
3480
+ "learning_rate": 2.3138832997987927e-05,
3481
+ "loss": 0.0702,
3482
+ "step": 4830
3483
+ },
3484
+ {
3485
+ "epoch": 9.56,
3486
+ "learning_rate": 2.2132796780684106e-05,
3487
+ "loss": 0.1029,
3488
+ "step": 4840
3489
+ },
3490
+ {
3491
+ "epoch": 9.58,
3492
+ "learning_rate": 2.112676056338028e-05,
3493
+ "loss": 0.102,
3494
+ "step": 4850
3495
+ },
3496
+ {
3497
+ "epoch": 9.6,
3498
+ "learning_rate": 2.012072434607646e-05,
3499
+ "loss": 0.0909,
3500
+ "step": 4860
3501
+ },
3502
+ {
3503
+ "epoch": 9.62,
3504
+ "learning_rate": 1.9114688128772636e-05,
3505
+ "loss": 0.0849,
3506
+ "step": 4870
3507
+ },
3508
+ {
3509
+ "epoch": 9.64,
3510
+ "learning_rate": 1.8108651911468815e-05,
3511
+ "loss": 0.1216,
3512
+ "step": 4880
3513
+ },
3514
+ {
3515
+ "epoch": 9.66,
3516
+ "learning_rate": 1.710261569416499e-05,
3517
+ "loss": 0.1016,
3518
+ "step": 4890
3519
+ },
3520
+ {
3521
+ "epoch": 9.68,
3522
+ "learning_rate": 1.609657947686117e-05,
3523
+ "loss": 0.0949,
3524
+ "step": 4900
3525
+ },
3526
+ {
3527
+ "epoch": 9.68,
3528
+ "eval_loss": 0.9819391965866089,
3529
+ "eval_rouge1": 0.1911111111111111,
3530
+ "eval_rouge2": 0.09772727272727272,
3531
+ "eval_rougeL": 0.19615384615384612,
3532
+ "eval_rougeLsum": 0.1923076923076923,
3533
+ "eval_runtime": 87.241,
3534
+ "eval_samples_per_second": 0.229,
3535
+ "eval_steps_per_second": 0.229,
3536
+ "step": 4900
3537
+ },
3538
+ {
3539
+ "epoch": 9.7,
3540
+ "learning_rate": 1.5090543259557344e-05,
3541
+ "loss": 0.0692,
3542
+ "step": 4910
3543
+ },
3544
+ {
3545
+ "epoch": 9.72,
3546
+ "learning_rate": 1.4084507042253522e-05,
3547
+ "loss": 0.0653,
3548
+ "step": 4920
3549
+ },
3550
+ {
3551
+ "epoch": 9.74,
3552
+ "learning_rate": 1.3078470824949699e-05,
3553
+ "loss": 0.0797,
3554
+ "step": 4930
3555
+ },
3556
+ {
3557
+ "epoch": 9.76,
3558
+ "learning_rate": 1.2072434607645874e-05,
3559
+ "loss": 0.0905,
3560
+ "step": 4940
3561
+ },
3562
+ {
3563
+ "epoch": 9.78,
3564
+ "learning_rate": 1.1066398390342053e-05,
3565
+ "loss": 0.0868,
3566
+ "step": 4950
3567
+ },
3568
+ {
3569
+ "epoch": 9.8,
3570
+ "learning_rate": 1.006036217303823e-05,
3571
+ "loss": 0.0964,
3572
+ "step": 4960
3573
+ },
3574
+ {
3575
+ "epoch": 9.82,
3576
+ "learning_rate": 9.054325955734407e-06,
3577
+ "loss": 0.0913,
3578
+ "step": 4970
3579
+ },
3580
+ {
3581
+ "epoch": 9.84,
3582
+ "learning_rate": 8.048289738430584e-06,
3583
+ "loss": 0.0708,
3584
+ "step": 4980
3585
+ },
3586
+ {
3587
+ "epoch": 9.86,
3588
+ "learning_rate": 7.042253521126761e-06,
3589
+ "loss": 0.1102,
3590
+ "step": 4990
3591
+ },
3592
+ {
3593
+ "epoch": 9.88,
3594
+ "learning_rate": 6.036217303822937e-06,
3595
+ "loss": 0.0852,
3596
+ "step": 5000
3597
+ },
3598
+ {
3599
+ "epoch": 9.88,
3600
+ "eval_loss": 0.9852367639541626,
3601
+ "eval_rouge1": 0.12615384615384617,
3602
+ "eval_rouge2": 0.08636363636363635,
3603
+ "eval_rougeL": 0.13615384615384613,
3604
+ "eval_rougeLsum": 0.12615384615384617,
3605
+ "eval_runtime": 87.473,
3606
+ "eval_samples_per_second": 0.229,
3607
+ "eval_steps_per_second": 0.229,
3608
+ "step": 5000
3609
+ }
3610
+ ],
3611
+ "max_steps": 5060,
3612
+ "num_train_epochs": 10,
3613
+ "total_flos": 1.2175308798022656e+17,
3614
+ "trial_name": null,
3615
+ "trial_params": null
3616
+ }
last-checkpoint/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:77a4f7038b50ddc31edcc81a5b698eebafae24d0db54d6acae4be1a9f931706a
3
+ size 3643