heruberuto
commited on
Commit
•
bb0764d
1
Parent(s):
195fe53
Upload folder using huggingface_hub
Browse files- .gitattributes +1 -0
- config.json +33 -0
- generation_config.json +7 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +5 -0
- spiece.model +3 -0
- tokenizer.json +3 -0
- tokenizer_config.json +12 -0
- trainer_state.json +3136 -0
- training_args.bin +3 -0
.gitattributes
CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
config.json
ADDED
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "google/mt5-large",
|
3 |
+
"architectures": [
|
4 |
+
"MT5ForConditionalGeneration"
|
5 |
+
],
|
6 |
+
"classifier_dropout": 0.0,
|
7 |
+
"d_ff": 2816,
|
8 |
+
"d_kv": 64,
|
9 |
+
"d_model": 1024,
|
10 |
+
"decoder_start_token_id": 0,
|
11 |
+
"dense_act_fn": "gelu_new",
|
12 |
+
"dropout_rate": 0.1,
|
13 |
+
"eos_token_id": 1,
|
14 |
+
"feed_forward_proj": "gated-gelu",
|
15 |
+
"initializer_factor": 1.0,
|
16 |
+
"is_encoder_decoder": true,
|
17 |
+
"is_gated_act": true,
|
18 |
+
"layer_norm_epsilon": 1e-06,
|
19 |
+
"model_type": "mt5",
|
20 |
+
"num_decoder_layers": 24,
|
21 |
+
"num_heads": 16,
|
22 |
+
"num_layers": 24,
|
23 |
+
"output_past": true,
|
24 |
+
"pad_token_id": 0,
|
25 |
+
"relative_attention_max_distance": 128,
|
26 |
+
"relative_attention_num_buckets": 32,
|
27 |
+
"tie_word_embeddings": false,
|
28 |
+
"tokenizer_class": "T5Tokenizer",
|
29 |
+
"torch_dtype": "float32",
|
30 |
+
"transformers_version": "4.32.0.dev0",
|
31 |
+
"use_cache": true,
|
32 |
+
"vocab_size": 250112
|
33 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"decoder_start_token_id": 0,
|
4 |
+
"eos_token_id": 1,
|
5 |
+
"pad_token_id": 0,
|
6 |
+
"transformers_version": "4.32.0.dev0"
|
7 |
+
}
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9372c507142c3a715cd7ad9c08a60acfc046a387e76711cf3e9910d3b19c7d00
|
3 |
+
size 9837129287
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:70c2afa27e8cb70375984e0386acb4a4db1f2444c37b89c518735897e547ef8a
|
3 |
+
size 4918515513
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9cb0bf7b8fd4c288d24b9af1964ebcd7feffc487c50147ab2b0821e93ff44b21
|
3 |
+
size 14503
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7444ac309071b55f60227ce1cde0285bfad82efa4b2802948625b4abb3cad5e4
|
3 |
+
size 623
|
special_tokens_map.json
ADDED
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"eos_token": "</s>",
|
3 |
+
"pad_token": "<pad>",
|
4 |
+
"unk_token": "<unk>"
|
5 |
+
}
|
spiece.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ef78f86560d809067d12bac6c09f19a462cb3af3f54d2b8acbba26e1433125d6
|
3 |
+
size 4309802
|
tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:93c3578052e1605d8332eb961bc08d72e246071974e4cc54aa6991826b802aa5
|
3 |
+
size 16330369
|
tokenizer_config.json
ADDED
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": null,
|
3 |
+
"clean_up_tokenization_spaces": true,
|
4 |
+
"eos_token": "</s>",
|
5 |
+
"extra_ids": 0,
|
6 |
+
"legacy": true,
|
7 |
+
"model_max_length": 1000000000000000019884624838656,
|
8 |
+
"pad_token": "<pad>",
|
9 |
+
"sp_model_kwargs": {},
|
10 |
+
"tokenizer_class": "T5Tokenizer",
|
11 |
+
"unk_token": "<unk>"
|
12 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,3136 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 2.141591787338257,
|
3 |
+
"best_model_checkpoint": "experiments/qa2d/google/mt5-large_all/checkpoint-156000",
|
4 |
+
"epoch": 2.569593147751606,
|
5 |
+
"global_step": 156000,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.01,
|
12 |
+
"learning_rate": 3e-05,
|
13 |
+
"loss": 11.6929,
|
14 |
+
"step": 500
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.02,
|
18 |
+
"learning_rate": 2.9975354434553247e-05,
|
19 |
+
"loss": 3.2221,
|
20 |
+
"step": 1000
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 0.02,
|
24 |
+
"eval_loss": 2.6418206691741943,
|
25 |
+
"eval_runtime": 1565.2313,
|
26 |
+
"eval_samples_per_second": 25.555,
|
27 |
+
"eval_steps_per_second": 25.555,
|
28 |
+
"step": 1000
|
29 |
+
},
|
30 |
+
{
|
31 |
+
"epoch": 0.02,
|
32 |
+
"learning_rate": 2.9950708869106497e-05,
|
33 |
+
"loss": 2.8153,
|
34 |
+
"step": 1500
|
35 |
+
},
|
36 |
+
{
|
37 |
+
"epoch": 0.03,
|
38 |
+
"learning_rate": 2.9926063303659743e-05,
|
39 |
+
"loss": 2.6697,
|
40 |
+
"step": 2000
|
41 |
+
},
|
42 |
+
{
|
43 |
+
"epoch": 0.03,
|
44 |
+
"eval_loss": 2.4854109287261963,
|
45 |
+
"eval_runtime": 1558.2706,
|
46 |
+
"eval_samples_per_second": 25.669,
|
47 |
+
"eval_steps_per_second": 25.669,
|
48 |
+
"step": 2000
|
49 |
+
},
|
50 |
+
{
|
51 |
+
"epoch": 0.04,
|
52 |
+
"learning_rate": 2.990141773821299e-05,
|
53 |
+
"loss": 2.6416,
|
54 |
+
"step": 2500
|
55 |
+
},
|
56 |
+
{
|
57 |
+
"epoch": 0.05,
|
58 |
+
"learning_rate": 2.987677217276624e-05,
|
59 |
+
"loss": 2.6305,
|
60 |
+
"step": 3000
|
61 |
+
},
|
62 |
+
{
|
63 |
+
"epoch": 0.05,
|
64 |
+
"eval_loss": 2.4116737842559814,
|
65 |
+
"eval_runtime": 1557.0077,
|
66 |
+
"eval_samples_per_second": 25.69,
|
67 |
+
"eval_steps_per_second": 25.69,
|
68 |
+
"step": 3000
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 0.06,
|
72 |
+
"learning_rate": 2.9852126607319485e-05,
|
73 |
+
"loss": 2.5755,
|
74 |
+
"step": 3500
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"epoch": 0.07,
|
78 |
+
"learning_rate": 2.9827481041872735e-05,
|
79 |
+
"loss": 2.5568,
|
80 |
+
"step": 4000
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 0.07,
|
84 |
+
"eval_loss": 2.395322561264038,
|
85 |
+
"eval_runtime": 1559.3248,
|
86 |
+
"eval_samples_per_second": 25.652,
|
87 |
+
"eval_steps_per_second": 25.652,
|
88 |
+
"step": 4000
|
89 |
+
},
|
90 |
+
{
|
91 |
+
"epoch": 0.07,
|
92 |
+
"learning_rate": 2.980283547642598e-05,
|
93 |
+
"loss": 2.5352,
|
94 |
+
"step": 4500
|
95 |
+
},
|
96 |
+
{
|
97 |
+
"epoch": 0.08,
|
98 |
+
"learning_rate": 2.977818991097923e-05,
|
99 |
+
"loss": 2.501,
|
100 |
+
"step": 5000
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 0.08,
|
104 |
+
"eval_loss": 2.3722634315490723,
|
105 |
+
"eval_runtime": 1560.8236,
|
106 |
+
"eval_samples_per_second": 25.627,
|
107 |
+
"eval_steps_per_second": 25.627,
|
108 |
+
"step": 5000
|
109 |
+
},
|
110 |
+
{
|
111 |
+
"epoch": 0.09,
|
112 |
+
"learning_rate": 2.9753544345532477e-05,
|
113 |
+
"loss": 2.5226,
|
114 |
+
"step": 5500
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.1,
|
118 |
+
"learning_rate": 2.9728898780085723e-05,
|
119 |
+
"loss": 2.5234,
|
120 |
+
"step": 6000
|
121 |
+
},
|
122 |
+
{
|
123 |
+
"epoch": 0.1,
|
124 |
+
"eval_loss": 2.3681018352508545,
|
125 |
+
"eval_runtime": 1556.6002,
|
126 |
+
"eval_samples_per_second": 25.697,
|
127 |
+
"eval_steps_per_second": 25.697,
|
128 |
+
"step": 6000
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.11,
|
132 |
+
"learning_rate": 2.9704253214638973e-05,
|
133 |
+
"loss": 2.4771,
|
134 |
+
"step": 6500
|
135 |
+
},
|
136 |
+
{
|
137 |
+
"epoch": 0.12,
|
138 |
+
"learning_rate": 2.967960764919222e-05,
|
139 |
+
"loss": 2.461,
|
140 |
+
"step": 7000
|
141 |
+
},
|
142 |
+
{
|
143 |
+
"epoch": 0.12,
|
144 |
+
"eval_loss": 2.3373661041259766,
|
145 |
+
"eval_runtime": 1557.5651,
|
146 |
+
"eval_samples_per_second": 25.681,
|
147 |
+
"eval_steps_per_second": 25.681,
|
148 |
+
"step": 7000
|
149 |
+
},
|
150 |
+
{
|
151 |
+
"epoch": 0.12,
|
152 |
+
"learning_rate": 2.9654962083745466e-05,
|
153 |
+
"loss": 2.4578,
|
154 |
+
"step": 7500
|
155 |
+
},
|
156 |
+
{
|
157 |
+
"epoch": 0.13,
|
158 |
+
"learning_rate": 2.9630316518298715e-05,
|
159 |
+
"loss": 2.4421,
|
160 |
+
"step": 8000
|
161 |
+
},
|
162 |
+
{
|
163 |
+
"epoch": 0.13,
|
164 |
+
"eval_loss": 2.3323025703430176,
|
165 |
+
"eval_runtime": 1562.2934,
|
166 |
+
"eval_samples_per_second": 25.603,
|
167 |
+
"eval_steps_per_second": 25.603,
|
168 |
+
"step": 8000
|
169 |
+
},
|
170 |
+
{
|
171 |
+
"epoch": 0.14,
|
172 |
+
"learning_rate": 2.960567095285196e-05,
|
173 |
+
"loss": 2.4323,
|
174 |
+
"step": 8500
|
175 |
+
},
|
176 |
+
{
|
177 |
+
"epoch": 0.15,
|
178 |
+
"learning_rate": 2.9581025387405208e-05,
|
179 |
+
"loss": 2.4347,
|
180 |
+
"step": 9000
|
181 |
+
},
|
182 |
+
{
|
183 |
+
"epoch": 0.15,
|
184 |
+
"eval_loss": 2.3352105617523193,
|
185 |
+
"eval_runtime": 1554.7815,
|
186 |
+
"eval_samples_per_second": 25.727,
|
187 |
+
"eval_steps_per_second": 25.727,
|
188 |
+
"step": 9000
|
189 |
+
},
|
190 |
+
{
|
191 |
+
"epoch": 0.16,
|
192 |
+
"learning_rate": 2.9556379821958458e-05,
|
193 |
+
"loss": 2.4114,
|
194 |
+
"step": 9500
|
195 |
+
},
|
196 |
+
{
|
197 |
+
"epoch": 0.16,
|
198 |
+
"learning_rate": 2.9531734256511704e-05,
|
199 |
+
"loss": 2.4128,
|
200 |
+
"step": 10000
|
201 |
+
},
|
202 |
+
{
|
203 |
+
"epoch": 0.16,
|
204 |
+
"eval_loss": 2.310478448867798,
|
205 |
+
"eval_runtime": 1531.4425,
|
206 |
+
"eval_samples_per_second": 26.119,
|
207 |
+
"eval_steps_per_second": 26.119,
|
208 |
+
"step": 10000
|
209 |
+
},
|
210 |
+
{
|
211 |
+
"epoch": 0.17,
|
212 |
+
"learning_rate": 2.9507088691064954e-05,
|
213 |
+
"loss": 2.4011,
|
214 |
+
"step": 10500
|
215 |
+
},
|
216 |
+
{
|
217 |
+
"epoch": 0.18,
|
218 |
+
"learning_rate": 2.9482443125618203e-05,
|
219 |
+
"loss": 2.4146,
|
220 |
+
"step": 11000
|
221 |
+
},
|
222 |
+
{
|
223 |
+
"epoch": 0.18,
|
224 |
+
"eval_loss": 2.299036979675293,
|
225 |
+
"eval_runtime": 1528.7138,
|
226 |
+
"eval_samples_per_second": 26.166,
|
227 |
+
"eval_steps_per_second": 26.166,
|
228 |
+
"step": 11000
|
229 |
+
},
|
230 |
+
{
|
231 |
+
"epoch": 0.19,
|
232 |
+
"learning_rate": 2.945779756017145e-05,
|
233 |
+
"loss": 2.3943,
|
234 |
+
"step": 11500
|
235 |
+
},
|
236 |
+
{
|
237 |
+
"epoch": 0.2,
|
238 |
+
"learning_rate": 2.9433151994724696e-05,
|
239 |
+
"loss": 2.4149,
|
240 |
+
"step": 12000
|
241 |
+
},
|
242 |
+
{
|
243 |
+
"epoch": 0.2,
|
244 |
+
"eval_loss": 2.2903053760528564,
|
245 |
+
"eval_runtime": 1529.473,
|
246 |
+
"eval_samples_per_second": 26.153,
|
247 |
+
"eval_steps_per_second": 26.153,
|
248 |
+
"step": 12000
|
249 |
+
},
|
250 |
+
{
|
251 |
+
"epoch": 0.21,
|
252 |
+
"learning_rate": 2.9408506429277945e-05,
|
253 |
+
"loss": 2.3832,
|
254 |
+
"step": 12500
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 0.21,
|
258 |
+
"learning_rate": 2.9383860863831192e-05,
|
259 |
+
"loss": 2.4014,
|
260 |
+
"step": 13000
|
261 |
+
},
|
262 |
+
{
|
263 |
+
"epoch": 0.21,
|
264 |
+
"eval_loss": 2.2913293838500977,
|
265 |
+
"eval_runtime": 1532.1216,
|
266 |
+
"eval_samples_per_second": 26.108,
|
267 |
+
"eval_steps_per_second": 26.108,
|
268 |
+
"step": 13000
|
269 |
+
},
|
270 |
+
{
|
271 |
+
"epoch": 0.22,
|
272 |
+
"learning_rate": 2.9359215298384438e-05,
|
273 |
+
"loss": 2.3717,
|
274 |
+
"step": 13500
|
275 |
+
},
|
276 |
+
{
|
277 |
+
"epoch": 0.23,
|
278 |
+
"learning_rate": 2.9334569732937684e-05,
|
279 |
+
"loss": 2.4076,
|
280 |
+
"step": 14000
|
281 |
+
},
|
282 |
+
{
|
283 |
+
"epoch": 0.23,
|
284 |
+
"eval_loss": 2.2880167961120605,
|
285 |
+
"eval_runtime": 1529.4251,
|
286 |
+
"eval_samples_per_second": 26.154,
|
287 |
+
"eval_steps_per_second": 26.154,
|
288 |
+
"step": 14000
|
289 |
+
},
|
290 |
+
{
|
291 |
+
"epoch": 0.24,
|
292 |
+
"learning_rate": 2.9309924167490934e-05,
|
293 |
+
"loss": 2.3883,
|
294 |
+
"step": 14500
|
295 |
+
},
|
296 |
+
{
|
297 |
+
"epoch": 0.25,
|
298 |
+
"learning_rate": 2.928527860204418e-05,
|
299 |
+
"loss": 2.3683,
|
300 |
+
"step": 15000
|
301 |
+
},
|
302 |
+
{
|
303 |
+
"epoch": 0.25,
|
304 |
+
"eval_loss": 2.282928228378296,
|
305 |
+
"eval_runtime": 1530.4125,
|
306 |
+
"eval_samples_per_second": 26.137,
|
307 |
+
"eval_steps_per_second": 26.137,
|
308 |
+
"step": 15000
|
309 |
+
},
|
310 |
+
{
|
311 |
+
"epoch": 0.26,
|
312 |
+
"learning_rate": 2.9260633036597427e-05,
|
313 |
+
"loss": 2.3794,
|
314 |
+
"step": 15500
|
315 |
+
},
|
316 |
+
{
|
317 |
+
"epoch": 0.26,
|
318 |
+
"learning_rate": 2.9235987471150676e-05,
|
319 |
+
"loss": 2.3711,
|
320 |
+
"step": 16000
|
321 |
+
},
|
322 |
+
{
|
323 |
+
"epoch": 0.26,
|
324 |
+
"eval_loss": 2.2699029445648193,
|
325 |
+
"eval_runtime": 1529.1971,
|
326 |
+
"eval_samples_per_second": 26.158,
|
327 |
+
"eval_steps_per_second": 26.158,
|
328 |
+
"step": 16000
|
329 |
+
},
|
330 |
+
{
|
331 |
+
"epoch": 0.27,
|
332 |
+
"learning_rate": 2.9211341905703926e-05,
|
333 |
+
"loss": 2.3701,
|
334 |
+
"step": 16500
|
335 |
+
},
|
336 |
+
{
|
337 |
+
"epoch": 0.28,
|
338 |
+
"learning_rate": 2.9186696340257172e-05,
|
339 |
+
"loss": 2.348,
|
340 |
+
"step": 17000
|
341 |
+
},
|
342 |
+
{
|
343 |
+
"epoch": 0.28,
|
344 |
+
"eval_loss": 2.27140736579895,
|
345 |
+
"eval_runtime": 1529.6771,
|
346 |
+
"eval_samples_per_second": 26.149,
|
347 |
+
"eval_steps_per_second": 26.149,
|
348 |
+
"step": 17000
|
349 |
+
},
|
350 |
+
{
|
351 |
+
"epoch": 0.29,
|
352 |
+
"learning_rate": 2.9162050774810422e-05,
|
353 |
+
"loss": 2.3521,
|
354 |
+
"step": 17500
|
355 |
+
},
|
356 |
+
{
|
357 |
+
"epoch": 0.3,
|
358 |
+
"learning_rate": 2.9137405209363668e-05,
|
359 |
+
"loss": 2.3649,
|
360 |
+
"step": 18000
|
361 |
+
},
|
362 |
+
{
|
363 |
+
"epoch": 0.3,
|
364 |
+
"eval_loss": 2.2581582069396973,
|
365 |
+
"eval_runtime": 1528.5087,
|
366 |
+
"eval_samples_per_second": 26.169,
|
367 |
+
"eval_steps_per_second": 26.169,
|
368 |
+
"step": 18000
|
369 |
+
},
|
370 |
+
{
|
371 |
+
"epoch": 0.3,
|
372 |
+
"learning_rate": 2.9112759643916914e-05,
|
373 |
+
"loss": 2.3625,
|
374 |
+
"step": 18500
|
375 |
+
},
|
376 |
+
{
|
377 |
+
"epoch": 0.31,
|
378 |
+
"learning_rate": 2.9088114078470164e-05,
|
379 |
+
"loss": 2.3413,
|
380 |
+
"step": 19000
|
381 |
+
},
|
382 |
+
{
|
383 |
+
"epoch": 0.31,
|
384 |
+
"eval_loss": 2.2619144916534424,
|
385 |
+
"eval_runtime": 1529.952,
|
386 |
+
"eval_samples_per_second": 26.145,
|
387 |
+
"eval_steps_per_second": 26.145,
|
388 |
+
"step": 19000
|
389 |
+
},
|
390 |
+
{
|
391 |
+
"epoch": 0.32,
|
392 |
+
"learning_rate": 2.906346851302341e-05,
|
393 |
+
"loss": 2.3399,
|
394 |
+
"step": 19500
|
395 |
+
},
|
396 |
+
{
|
397 |
+
"epoch": 0.33,
|
398 |
+
"learning_rate": 2.9038822947576657e-05,
|
399 |
+
"loss": 2.3123,
|
400 |
+
"step": 20000
|
401 |
+
},
|
402 |
+
{
|
403 |
+
"epoch": 0.33,
|
404 |
+
"eval_loss": 2.249448299407959,
|
405 |
+
"eval_runtime": 1530.0932,
|
406 |
+
"eval_samples_per_second": 26.142,
|
407 |
+
"eval_steps_per_second": 26.142,
|
408 |
+
"step": 20000
|
409 |
+
},
|
410 |
+
{
|
411 |
+
"epoch": 0.34,
|
412 |
+
"learning_rate": 2.9014177382129903e-05,
|
413 |
+
"loss": 2.343,
|
414 |
+
"step": 20500
|
415 |
+
},
|
416 |
+
{
|
417 |
+
"epoch": 0.35,
|
418 |
+
"learning_rate": 2.8989531816683153e-05,
|
419 |
+
"loss": 2.3207,
|
420 |
+
"step": 21000
|
421 |
+
},
|
422 |
+
{
|
423 |
+
"epoch": 0.35,
|
424 |
+
"eval_loss": 2.2527272701263428,
|
425 |
+
"eval_runtime": 1529.3921,
|
426 |
+
"eval_samples_per_second": 26.154,
|
427 |
+
"eval_steps_per_second": 26.154,
|
428 |
+
"step": 21000
|
429 |
+
},
|
430 |
+
{
|
431 |
+
"epoch": 0.35,
|
432 |
+
"learning_rate": 2.89648862512364e-05,
|
433 |
+
"loss": 2.3328,
|
434 |
+
"step": 21500
|
435 |
+
},
|
436 |
+
{
|
437 |
+
"epoch": 0.36,
|
438 |
+
"learning_rate": 2.8940240685789645e-05,
|
439 |
+
"loss": 2.3277,
|
440 |
+
"step": 22000
|
441 |
+
},
|
442 |
+
{
|
443 |
+
"epoch": 0.36,
|
444 |
+
"eval_loss": 2.252654552459717,
|
445 |
+
"eval_runtime": 1529.3372,
|
446 |
+
"eval_samples_per_second": 26.155,
|
447 |
+
"eval_steps_per_second": 26.155,
|
448 |
+
"step": 22000
|
449 |
+
},
|
450 |
+
{
|
451 |
+
"epoch": 0.37,
|
452 |
+
"learning_rate": 2.8915595120342895e-05,
|
453 |
+
"loss": 2.3279,
|
454 |
+
"step": 22500
|
455 |
+
},
|
456 |
+
{
|
457 |
+
"epoch": 0.38,
|
458 |
+
"learning_rate": 2.8890949554896145e-05,
|
459 |
+
"loss": 2.3539,
|
460 |
+
"step": 23000
|
461 |
+
},
|
462 |
+
{
|
463 |
+
"epoch": 0.38,
|
464 |
+
"eval_loss": 2.2401123046875,
|
465 |
+
"eval_runtime": 1530.6138,
|
466 |
+
"eval_samples_per_second": 26.133,
|
467 |
+
"eval_steps_per_second": 26.133,
|
468 |
+
"step": 23000
|
469 |
+
},
|
470 |
+
{
|
471 |
+
"epoch": 0.39,
|
472 |
+
"learning_rate": 2.886630398944939e-05,
|
473 |
+
"loss": 2.3201,
|
474 |
+
"step": 23500
|
475 |
+
},
|
476 |
+
{
|
477 |
+
"epoch": 0.4,
|
478 |
+
"learning_rate": 2.884165842400264e-05,
|
479 |
+
"loss": 2.3245,
|
480 |
+
"step": 24000
|
481 |
+
},
|
482 |
+
{
|
483 |
+
"epoch": 0.4,
|
484 |
+
"eval_loss": 2.2426249980926514,
|
485 |
+
"eval_runtime": 1530.4589,
|
486 |
+
"eval_samples_per_second": 26.136,
|
487 |
+
"eval_steps_per_second": 26.136,
|
488 |
+
"step": 24000
|
489 |
+
},
|
490 |
+
{
|
491 |
+
"epoch": 0.4,
|
492 |
+
"learning_rate": 2.8817012858555887e-05,
|
493 |
+
"loss": 2.3039,
|
494 |
+
"step": 24500
|
495 |
+
},
|
496 |
+
{
|
497 |
+
"epoch": 0.41,
|
498 |
+
"learning_rate": 2.8792367293109133e-05,
|
499 |
+
"loss": 2.3077,
|
500 |
+
"step": 25000
|
501 |
+
},
|
502 |
+
{
|
503 |
+
"epoch": 0.41,
|
504 |
+
"eval_loss": 2.243065118789673,
|
505 |
+
"eval_runtime": 1532.734,
|
506 |
+
"eval_samples_per_second": 26.097,
|
507 |
+
"eval_steps_per_second": 26.097,
|
508 |
+
"step": 25000
|
509 |
+
},
|
510 |
+
{
|
511 |
+
"epoch": 0.42,
|
512 |
+
"learning_rate": 2.8767721727662383e-05,
|
513 |
+
"loss": 2.313,
|
514 |
+
"step": 25500
|
515 |
+
},
|
516 |
+
{
|
517 |
+
"epoch": 0.43,
|
518 |
+
"learning_rate": 2.874307616221563e-05,
|
519 |
+
"loss": 2.3275,
|
520 |
+
"step": 26000
|
521 |
+
},
|
522 |
+
{
|
523 |
+
"epoch": 0.43,
|
524 |
+
"eval_loss": 2.23547101020813,
|
525 |
+
"eval_runtime": 1532.1284,
|
526 |
+
"eval_samples_per_second": 26.107,
|
527 |
+
"eval_steps_per_second": 26.107,
|
528 |
+
"step": 26000
|
529 |
+
},
|
530 |
+
{
|
531 |
+
"epoch": 0.44,
|
532 |
+
"learning_rate": 2.8718430596768875e-05,
|
533 |
+
"loss": 2.3099,
|
534 |
+
"step": 26500
|
535 |
+
},
|
536 |
+
{
|
537 |
+
"epoch": 0.44,
|
538 |
+
"learning_rate": 2.869378503132212e-05,
|
539 |
+
"loss": 2.293,
|
540 |
+
"step": 27000
|
541 |
+
},
|
542 |
+
{
|
543 |
+
"epoch": 0.44,
|
544 |
+
"eval_loss": 2.2356772422790527,
|
545 |
+
"eval_runtime": 1529.3039,
|
546 |
+
"eval_samples_per_second": 26.156,
|
547 |
+
"eval_steps_per_second": 26.156,
|
548 |
+
"step": 27000
|
549 |
+
},
|
550 |
+
{
|
551 |
+
"epoch": 0.45,
|
552 |
+
"learning_rate": 2.866913946587537e-05,
|
553 |
+
"loss": 2.2986,
|
554 |
+
"step": 27500
|
555 |
+
},
|
556 |
+
{
|
557 |
+
"epoch": 0.46,
|
558 |
+
"learning_rate": 2.8644493900428618e-05,
|
559 |
+
"loss": 2.2894,
|
560 |
+
"step": 28000
|
561 |
+
},
|
562 |
+
{
|
563 |
+
"epoch": 0.46,
|
564 |
+
"eval_loss": 2.2366623878479004,
|
565 |
+
"eval_runtime": 1530.364,
|
566 |
+
"eval_samples_per_second": 26.138,
|
567 |
+
"eval_steps_per_second": 26.138,
|
568 |
+
"step": 28000
|
569 |
+
},
|
570 |
+
{
|
571 |
+
"epoch": 0.47,
|
572 |
+
"learning_rate": 2.8619848334981864e-05,
|
573 |
+
"loss": 2.3039,
|
574 |
+
"step": 28500
|
575 |
+
},
|
576 |
+
{
|
577 |
+
"epoch": 0.48,
|
578 |
+
"learning_rate": 2.8595202769535114e-05,
|
579 |
+
"loss": 2.291,
|
580 |
+
"step": 29000
|
581 |
+
},
|
582 |
+
{
|
583 |
+
"epoch": 0.48,
|
584 |
+
"eval_loss": 2.2369134426116943,
|
585 |
+
"eval_runtime": 1531.5039,
|
586 |
+
"eval_samples_per_second": 26.118,
|
587 |
+
"eval_steps_per_second": 26.118,
|
588 |
+
"step": 29000
|
589 |
+
},
|
590 |
+
{
|
591 |
+
"epoch": 0.49,
|
592 |
+
"learning_rate": 2.8570557204088363e-05,
|
593 |
+
"loss": 2.2991,
|
594 |
+
"step": 29500
|
595 |
+
},
|
596 |
+
{
|
597 |
+
"epoch": 0.49,
|
598 |
+
"learning_rate": 2.854591163864161e-05,
|
599 |
+
"loss": 2.3012,
|
600 |
+
"step": 30000
|
601 |
+
},
|
602 |
+
{
|
603 |
+
"epoch": 0.49,
|
604 |
+
"eval_loss": 2.2239012718200684,
|
605 |
+
"eval_runtime": 1541.2582,
|
606 |
+
"eval_samples_per_second": 25.953,
|
607 |
+
"eval_steps_per_second": 25.953,
|
608 |
+
"step": 30000
|
609 |
+
},
|
610 |
+
{
|
611 |
+
"epoch": 0.5,
|
612 |
+
"learning_rate": 2.852126607319486e-05,
|
613 |
+
"loss": 2.2986,
|
614 |
+
"step": 30500
|
615 |
+
},
|
616 |
+
{
|
617 |
+
"epoch": 0.51,
|
618 |
+
"learning_rate": 2.8496620507748105e-05,
|
619 |
+
"loss": 2.307,
|
620 |
+
"step": 31000
|
621 |
+
},
|
622 |
+
{
|
623 |
+
"epoch": 0.51,
|
624 |
+
"eval_loss": 2.22198748588562,
|
625 |
+
"eval_runtime": 1529.6638,
|
626 |
+
"eval_samples_per_second": 26.15,
|
627 |
+
"eval_steps_per_second": 26.15,
|
628 |
+
"step": 31000
|
629 |
+
},
|
630 |
+
{
|
631 |
+
"epoch": 0.52,
|
632 |
+
"learning_rate": 2.8471974942301352e-05,
|
633 |
+
"loss": 2.2983,
|
634 |
+
"step": 31500
|
635 |
+
},
|
636 |
+
{
|
637 |
+
"epoch": 0.53,
|
638 |
+
"learning_rate": 2.84473293768546e-05,
|
639 |
+
"loss": 2.292,
|
640 |
+
"step": 32000
|
641 |
+
},
|
642 |
+
{
|
643 |
+
"epoch": 0.53,
|
644 |
+
"eval_loss": 2.2306456565856934,
|
645 |
+
"eval_runtime": 1530.562,
|
646 |
+
"eval_samples_per_second": 26.134,
|
647 |
+
"eval_steps_per_second": 26.134,
|
648 |
+
"step": 32000
|
649 |
+
},
|
650 |
+
{
|
651 |
+
"epoch": 0.54,
|
652 |
+
"learning_rate": 2.8422683811407848e-05,
|
653 |
+
"loss": 2.3024,
|
654 |
+
"step": 32500
|
655 |
+
},
|
656 |
+
{
|
657 |
+
"epoch": 0.54,
|
658 |
+
"learning_rate": 2.8398038245961094e-05,
|
659 |
+
"loss": 2.3136,
|
660 |
+
"step": 33000
|
661 |
+
},
|
662 |
+
{
|
663 |
+
"epoch": 0.54,
|
664 |
+
"eval_loss": 2.2240662574768066,
|
665 |
+
"eval_runtime": 1528.9582,
|
666 |
+
"eval_samples_per_second": 26.162,
|
667 |
+
"eval_steps_per_second": 26.162,
|
668 |
+
"step": 33000
|
669 |
+
},
|
670 |
+
{
|
671 |
+
"epoch": 0.55,
|
672 |
+
"learning_rate": 2.8373392680514344e-05,
|
673 |
+
"loss": 2.2743,
|
674 |
+
"step": 33500
|
675 |
+
},
|
676 |
+
{
|
677 |
+
"epoch": 0.56,
|
678 |
+
"learning_rate": 2.834874711506759e-05,
|
679 |
+
"loss": 2.2795,
|
680 |
+
"step": 34000
|
681 |
+
},
|
682 |
+
{
|
683 |
+
"epoch": 0.56,
|
684 |
+
"eval_loss": 2.2316462993621826,
|
685 |
+
"eval_runtime": 1529.0092,
|
686 |
+
"eval_samples_per_second": 26.161,
|
687 |
+
"eval_steps_per_second": 26.161,
|
688 |
+
"step": 34000
|
689 |
+
},
|
690 |
+
{
|
691 |
+
"epoch": 0.57,
|
692 |
+
"learning_rate": 2.8324101549620836e-05,
|
693 |
+
"loss": 2.284,
|
694 |
+
"step": 34500
|
695 |
+
},
|
696 |
+
{
|
697 |
+
"epoch": 0.58,
|
698 |
+
"learning_rate": 2.8299455984174086e-05,
|
699 |
+
"loss": 2.267,
|
700 |
+
"step": 35000
|
701 |
+
},
|
702 |
+
{
|
703 |
+
"epoch": 0.58,
|
704 |
+
"eval_loss": 2.2221341133117676,
|
705 |
+
"eval_runtime": 1538.4633,
|
706 |
+
"eval_samples_per_second": 26.0,
|
707 |
+
"eval_steps_per_second": 26.0,
|
708 |
+
"step": 35000
|
709 |
+
},
|
710 |
+
{
|
711 |
+
"epoch": 0.58,
|
712 |
+
"learning_rate": 2.8274810418727336e-05,
|
713 |
+
"loss": 2.2607,
|
714 |
+
"step": 35500
|
715 |
+
},
|
716 |
+
{
|
717 |
+
"epoch": 0.59,
|
718 |
+
"learning_rate": 2.8250164853280582e-05,
|
719 |
+
"loss": 2.2925,
|
720 |
+
"step": 36000
|
721 |
+
},
|
722 |
+
{
|
723 |
+
"epoch": 0.59,
|
724 |
+
"eval_loss": 2.2153666019439697,
|
725 |
+
"eval_runtime": 1535.3695,
|
726 |
+
"eval_samples_per_second": 26.052,
|
727 |
+
"eval_steps_per_second": 26.052,
|
728 |
+
"step": 36000
|
729 |
+
},
|
730 |
+
{
|
731 |
+
"epoch": 0.6,
|
732 |
+
"learning_rate": 2.8225519287833828e-05,
|
733 |
+
"loss": 2.2807,
|
734 |
+
"step": 36500
|
735 |
+
},
|
736 |
+
{
|
737 |
+
"epoch": 0.61,
|
738 |
+
"learning_rate": 2.8200873722387078e-05,
|
739 |
+
"loss": 2.2668,
|
740 |
+
"step": 37000
|
741 |
+
},
|
742 |
+
{
|
743 |
+
"epoch": 0.61,
|
744 |
+
"eval_loss": 2.2268478870391846,
|
745 |
+
"eval_runtime": 1531.1735,
|
746 |
+
"eval_samples_per_second": 26.124,
|
747 |
+
"eval_steps_per_second": 26.124,
|
748 |
+
"step": 37000
|
749 |
+
},
|
750 |
+
{
|
751 |
+
"epoch": 0.62,
|
752 |
+
"learning_rate": 2.8176228156940324e-05,
|
753 |
+
"loss": 2.2737,
|
754 |
+
"step": 37500
|
755 |
+
},
|
756 |
+
{
|
757 |
+
"epoch": 0.63,
|
758 |
+
"learning_rate": 2.815158259149357e-05,
|
759 |
+
"loss": 2.2593,
|
760 |
+
"step": 38000
|
761 |
+
},
|
762 |
+
{
|
763 |
+
"epoch": 0.63,
|
764 |
+
"eval_loss": 2.210831642150879,
|
765 |
+
"eval_runtime": 1534.412,
|
766 |
+
"eval_samples_per_second": 26.069,
|
767 |
+
"eval_steps_per_second": 26.069,
|
768 |
+
"step": 38000
|
769 |
+
},
|
770 |
+
{
|
771 |
+
"epoch": 0.63,
|
772 |
+
"learning_rate": 2.812693702604682e-05,
|
773 |
+
"loss": 2.263,
|
774 |
+
"step": 38500
|
775 |
+
},
|
776 |
+
{
|
777 |
+
"epoch": 0.64,
|
778 |
+
"learning_rate": 2.8102291460600066e-05,
|
779 |
+
"loss": 2.2773,
|
780 |
+
"step": 39000
|
781 |
+
},
|
782 |
+
{
|
783 |
+
"epoch": 0.64,
|
784 |
+
"eval_loss": 2.2057864665985107,
|
785 |
+
"eval_runtime": 1540.629,
|
786 |
+
"eval_samples_per_second": 25.963,
|
787 |
+
"eval_steps_per_second": 25.963,
|
788 |
+
"step": 39000
|
789 |
+
},
|
790 |
+
{
|
791 |
+
"epoch": 0.65,
|
792 |
+
"learning_rate": 2.8077645895153313e-05,
|
793 |
+
"loss": 2.2744,
|
794 |
+
"step": 39500
|
795 |
+
},
|
796 |
+
{
|
797 |
+
"epoch": 0.66,
|
798 |
+
"learning_rate": 2.8053000329706562e-05,
|
799 |
+
"loss": 2.2523,
|
800 |
+
"step": 40000
|
801 |
+
},
|
802 |
+
{
|
803 |
+
"epoch": 0.66,
|
804 |
+
"eval_loss": 2.2129907608032227,
|
805 |
+
"eval_runtime": 1528.9572,
|
806 |
+
"eval_samples_per_second": 26.162,
|
807 |
+
"eval_steps_per_second": 26.162,
|
808 |
+
"step": 40000
|
809 |
+
},
|
810 |
+
{
|
811 |
+
"epoch": 0.67,
|
812 |
+
"learning_rate": 2.802835476425981e-05,
|
813 |
+
"loss": 2.2854,
|
814 |
+
"step": 40500
|
815 |
+
},
|
816 |
+
{
|
817 |
+
"epoch": 0.68,
|
818 |
+
"learning_rate": 2.8003709198813055e-05,
|
819 |
+
"loss": 2.2641,
|
820 |
+
"step": 41000
|
821 |
+
},
|
822 |
+
{
|
823 |
+
"epoch": 0.68,
|
824 |
+
"eval_loss": 2.211035966873169,
|
825 |
+
"eval_runtime": 1530.9184,
|
826 |
+
"eval_samples_per_second": 26.128,
|
827 |
+
"eval_steps_per_second": 26.128,
|
828 |
+
"step": 41000
|
829 |
+
},
|
830 |
+
{
|
831 |
+
"epoch": 0.68,
|
832 |
+
"learning_rate": 2.7979063633366305e-05,
|
833 |
+
"loss": 2.2852,
|
834 |
+
"step": 41500
|
835 |
+
},
|
836 |
+
{
|
837 |
+
"epoch": 0.69,
|
838 |
+
"learning_rate": 2.7954418067919554e-05,
|
839 |
+
"loss": 2.2677,
|
840 |
+
"step": 42000
|
841 |
+
},
|
842 |
+
{
|
843 |
+
"epoch": 0.69,
|
844 |
+
"eval_loss": 2.215862989425659,
|
845 |
+
"eval_runtime": 1532.4939,
|
846 |
+
"eval_samples_per_second": 26.101,
|
847 |
+
"eval_steps_per_second": 26.101,
|
848 |
+
"step": 42000
|
849 |
+
},
|
850 |
+
{
|
851 |
+
"epoch": 0.7,
|
852 |
+
"learning_rate": 2.79297725024728e-05,
|
853 |
+
"loss": 2.2726,
|
854 |
+
"step": 42500
|
855 |
+
},
|
856 |
+
{
|
857 |
+
"epoch": 0.71,
|
858 |
+
"learning_rate": 2.7905126937026047e-05,
|
859 |
+
"loss": 2.2552,
|
860 |
+
"step": 43000
|
861 |
+
},
|
862 |
+
{
|
863 |
+
"epoch": 0.71,
|
864 |
+
"eval_loss": 2.2060205936431885,
|
865 |
+
"eval_runtime": 1528.9721,
|
866 |
+
"eval_samples_per_second": 26.161,
|
867 |
+
"eval_steps_per_second": 26.161,
|
868 |
+
"step": 43000
|
869 |
+
},
|
870 |
+
{
|
871 |
+
"epoch": 0.72,
|
872 |
+
"learning_rate": 2.7880481371579296e-05,
|
873 |
+
"loss": 2.2636,
|
874 |
+
"step": 43500
|
875 |
+
},
|
876 |
+
{
|
877 |
+
"epoch": 0.72,
|
878 |
+
"learning_rate": 2.7855835806132543e-05,
|
879 |
+
"loss": 2.2523,
|
880 |
+
"step": 44000
|
881 |
+
},
|
882 |
+
{
|
883 |
+
"epoch": 0.72,
|
884 |
+
"eval_loss": 2.2027759552001953,
|
885 |
+
"eval_runtime": 1654.4814,
|
886 |
+
"eval_samples_per_second": 24.177,
|
887 |
+
"eval_steps_per_second": 24.177,
|
888 |
+
"step": 44000
|
889 |
+
},
|
890 |
+
{
|
891 |
+
"epoch": 0.73,
|
892 |
+
"learning_rate": 2.7831190240685792e-05,
|
893 |
+
"loss": 2.2571,
|
894 |
+
"step": 44500
|
895 |
+
},
|
896 |
+
{
|
897 |
+
"epoch": 0.74,
|
898 |
+
"learning_rate": 2.780654467523904e-05,
|
899 |
+
"loss": 2.2631,
|
900 |
+
"step": 45000
|
901 |
+
},
|
902 |
+
{
|
903 |
+
"epoch": 0.74,
|
904 |
+
"eval_loss": 2.203402042388916,
|
905 |
+
"eval_runtime": 1646.7085,
|
906 |
+
"eval_samples_per_second": 24.291,
|
907 |
+
"eval_steps_per_second": 24.291,
|
908 |
+
"step": 45000
|
909 |
+
},
|
910 |
+
{
|
911 |
+
"epoch": 0.75,
|
912 |
+
"learning_rate": 2.7781899109792285e-05,
|
913 |
+
"loss": 2.2625,
|
914 |
+
"step": 45500
|
915 |
+
},
|
916 |
+
{
|
917 |
+
"epoch": 0.76,
|
918 |
+
"learning_rate": 2.775725354434553e-05,
|
919 |
+
"loss": 2.2526,
|
920 |
+
"step": 46000
|
921 |
+
},
|
922 |
+
{
|
923 |
+
"epoch": 0.76,
|
924 |
+
"eval_loss": 2.2011003494262695,
|
925 |
+
"eval_runtime": 1646.5268,
|
926 |
+
"eval_samples_per_second": 24.294,
|
927 |
+
"eval_steps_per_second": 24.294,
|
928 |
+
"step": 46000
|
929 |
+
},
|
930 |
+
{
|
931 |
+
"epoch": 0.77,
|
932 |
+
"learning_rate": 2.773260797889878e-05,
|
933 |
+
"loss": 2.2292,
|
934 |
+
"step": 46500
|
935 |
+
},
|
936 |
+
{
|
937 |
+
"epoch": 0.77,
|
938 |
+
"learning_rate": 2.7707962413452027e-05,
|
939 |
+
"loss": 2.233,
|
940 |
+
"step": 47000
|
941 |
+
},
|
942 |
+
{
|
943 |
+
"epoch": 0.77,
|
944 |
+
"eval_loss": 2.195323944091797,
|
945 |
+
"eval_runtime": 1654.3578,
|
946 |
+
"eval_samples_per_second": 24.179,
|
947 |
+
"eval_steps_per_second": 24.179,
|
948 |
+
"step": 47000
|
949 |
+
},
|
950 |
+
{
|
951 |
+
"epoch": 0.78,
|
952 |
+
"learning_rate": 2.7683316848005273e-05,
|
953 |
+
"loss": 2.2354,
|
954 |
+
"step": 47500
|
955 |
+
},
|
956 |
+
{
|
957 |
+
"epoch": 0.79,
|
958 |
+
"learning_rate": 2.7658671282558523e-05,
|
959 |
+
"loss": 2.2694,
|
960 |
+
"step": 48000
|
961 |
+
},
|
962 |
+
{
|
963 |
+
"epoch": 0.79,
|
964 |
+
"eval_loss": 2.197169542312622,
|
965 |
+
"eval_runtime": 1644.6807,
|
966 |
+
"eval_samples_per_second": 24.321,
|
967 |
+
"eval_steps_per_second": 24.321,
|
968 |
+
"step": 48000
|
969 |
+
},
|
970 |
+
{
|
971 |
+
"epoch": 0.8,
|
972 |
+
"learning_rate": 2.7634025717111773e-05,
|
973 |
+
"loss": 2.2419,
|
974 |
+
"step": 48500
|
975 |
+
},
|
976 |
+
{
|
977 |
+
"epoch": 0.81,
|
978 |
+
"learning_rate": 2.760938015166502e-05,
|
979 |
+
"loss": 2.2524,
|
980 |
+
"step": 49000
|
981 |
+
},
|
982 |
+
{
|
983 |
+
"epoch": 0.81,
|
984 |
+
"eval_loss": 2.1981358528137207,
|
985 |
+
"eval_runtime": 1641.1537,
|
986 |
+
"eval_samples_per_second": 24.373,
|
987 |
+
"eval_steps_per_second": 24.373,
|
988 |
+
"step": 49000
|
989 |
+
},
|
990 |
+
{
|
991 |
+
"epoch": 0.82,
|
992 |
+
"learning_rate": 2.758473458621827e-05,
|
993 |
+
"loss": 2.2496,
|
994 |
+
"step": 49500
|
995 |
+
},
|
996 |
+
{
|
997 |
+
"epoch": 0.82,
|
998 |
+
"learning_rate": 2.7560089020771515e-05,
|
999 |
+
"loss": 2.2361,
|
1000 |
+
"step": 50000
|
1001 |
+
},
|
1002 |
+
{
|
1003 |
+
"epoch": 0.82,
|
1004 |
+
"eval_loss": 2.1948020458221436,
|
1005 |
+
"eval_runtime": 1641.8374,
|
1006 |
+
"eval_samples_per_second": 24.363,
|
1007 |
+
"eval_steps_per_second": 24.363,
|
1008 |
+
"step": 50000
|
1009 |
+
},
|
1010 |
+
{
|
1011 |
+
"epoch": 0.83,
|
1012 |
+
"learning_rate": 2.753544345532476e-05,
|
1013 |
+
"loss": 2.2394,
|
1014 |
+
"step": 50500
|
1015 |
+
},
|
1016 |
+
{
|
1017 |
+
"epoch": 0.84,
|
1018 |
+
"learning_rate": 2.751079788987801e-05,
|
1019 |
+
"loss": 2.2415,
|
1020 |
+
"step": 51000
|
1021 |
+
},
|
1022 |
+
{
|
1023 |
+
"epoch": 0.84,
|
1024 |
+
"eval_loss": 2.201873540878296,
|
1025 |
+
"eval_runtime": 1644.4006,
|
1026 |
+
"eval_samples_per_second": 24.325,
|
1027 |
+
"eval_steps_per_second": 24.325,
|
1028 |
+
"step": 51000
|
1029 |
+
},
|
1030 |
+
{
|
1031 |
+
"epoch": 0.85,
|
1032 |
+
"learning_rate": 2.7486152324431257e-05,
|
1033 |
+
"loss": 2.2422,
|
1034 |
+
"step": 51500
|
1035 |
+
},
|
1036 |
+
{
|
1037 |
+
"epoch": 0.86,
|
1038 |
+
"learning_rate": 2.7461506758984504e-05,
|
1039 |
+
"loss": 2.2319,
|
1040 |
+
"step": 52000
|
1041 |
+
},
|
1042 |
+
{
|
1043 |
+
"epoch": 0.86,
|
1044 |
+
"eval_loss": 2.1902756690979004,
|
1045 |
+
"eval_runtime": 1640.1219,
|
1046 |
+
"eval_samples_per_second": 24.388,
|
1047 |
+
"eval_steps_per_second": 24.388,
|
1048 |
+
"step": 52000
|
1049 |
+
},
|
1050 |
+
{
|
1051 |
+
"epoch": 0.86,
|
1052 |
+
"learning_rate": 2.743686119353775e-05,
|
1053 |
+
"loss": 2.2421,
|
1054 |
+
"step": 52500
|
1055 |
+
},
|
1056 |
+
{
|
1057 |
+
"epoch": 0.87,
|
1058 |
+
"learning_rate": 2.7412215628091e-05,
|
1059 |
+
"loss": 2.2425,
|
1060 |
+
"step": 53000
|
1061 |
+
},
|
1062 |
+
{
|
1063 |
+
"epoch": 0.87,
|
1064 |
+
"eval_loss": 2.193206787109375,
|
1065 |
+
"eval_runtime": 1645.0368,
|
1066 |
+
"eval_samples_per_second": 24.316,
|
1067 |
+
"eval_steps_per_second": 24.316,
|
1068 |
+
"step": 53000
|
1069 |
+
},
|
1070 |
+
{
|
1071 |
+
"epoch": 0.88,
|
1072 |
+
"learning_rate": 2.7387570062644246e-05,
|
1073 |
+
"loss": 2.2464,
|
1074 |
+
"step": 53500
|
1075 |
+
},
|
1076 |
+
{
|
1077 |
+
"epoch": 0.89,
|
1078 |
+
"learning_rate": 2.7362924497197492e-05,
|
1079 |
+
"loss": 2.2113,
|
1080 |
+
"step": 54000
|
1081 |
+
},
|
1082 |
+
{
|
1083 |
+
"epoch": 0.89,
|
1084 |
+
"eval_loss": 2.1928114891052246,
|
1085 |
+
"eval_runtime": 1645.7517,
|
1086 |
+
"eval_samples_per_second": 24.305,
|
1087 |
+
"eval_steps_per_second": 24.305,
|
1088 |
+
"step": 54000
|
1089 |
+
},
|
1090 |
+
{
|
1091 |
+
"epoch": 0.9,
|
1092 |
+
"learning_rate": 2.7338278931750745e-05,
|
1093 |
+
"loss": 2.2371,
|
1094 |
+
"step": 54500
|
1095 |
+
},
|
1096 |
+
{
|
1097 |
+
"epoch": 0.91,
|
1098 |
+
"learning_rate": 2.731363336630399e-05,
|
1099 |
+
"loss": 2.2384,
|
1100 |
+
"step": 55000
|
1101 |
+
},
|
1102 |
+
{
|
1103 |
+
"epoch": 0.91,
|
1104 |
+
"eval_loss": 2.1923627853393555,
|
1105 |
+
"eval_runtime": 1645.6809,
|
1106 |
+
"eval_samples_per_second": 24.306,
|
1107 |
+
"eval_steps_per_second": 24.306,
|
1108 |
+
"step": 55000
|
1109 |
+
},
|
1110 |
+
{
|
1111 |
+
"epoch": 0.91,
|
1112 |
+
"learning_rate": 2.7288987800857238e-05,
|
1113 |
+
"loss": 2.2285,
|
1114 |
+
"step": 55500
|
1115 |
+
},
|
1116 |
+
{
|
1117 |
+
"epoch": 0.92,
|
1118 |
+
"learning_rate": 2.7264342235410487e-05,
|
1119 |
+
"loss": 2.2246,
|
1120 |
+
"step": 56000
|
1121 |
+
},
|
1122 |
+
{
|
1123 |
+
"epoch": 0.92,
|
1124 |
+
"eval_loss": 2.1856086254119873,
|
1125 |
+
"eval_runtime": 1644.6784,
|
1126 |
+
"eval_samples_per_second": 24.321,
|
1127 |
+
"eval_steps_per_second": 24.321,
|
1128 |
+
"step": 56000
|
1129 |
+
},
|
1130 |
+
{
|
1131 |
+
"epoch": 0.93,
|
1132 |
+
"learning_rate": 2.7239696669963734e-05,
|
1133 |
+
"loss": 2.2268,
|
1134 |
+
"step": 56500
|
1135 |
+
},
|
1136 |
+
{
|
1137 |
+
"epoch": 0.94,
|
1138 |
+
"learning_rate": 2.721505110451698e-05,
|
1139 |
+
"loss": 2.2098,
|
1140 |
+
"step": 57000
|
1141 |
+
},
|
1142 |
+
{
|
1143 |
+
"epoch": 0.94,
|
1144 |
+
"eval_loss": 2.1881797313690186,
|
1145 |
+
"eval_runtime": 1649.0436,
|
1146 |
+
"eval_samples_per_second": 24.256,
|
1147 |
+
"eval_steps_per_second": 24.256,
|
1148 |
+
"step": 57000
|
1149 |
+
},
|
1150 |
+
{
|
1151 |
+
"epoch": 0.95,
|
1152 |
+
"learning_rate": 2.719040553907023e-05,
|
1153 |
+
"loss": 2.2294,
|
1154 |
+
"step": 57500
|
1155 |
+
},
|
1156 |
+
{
|
1157 |
+
"epoch": 0.96,
|
1158 |
+
"learning_rate": 2.7165759973623476e-05,
|
1159 |
+
"loss": 2.2166,
|
1160 |
+
"step": 58000
|
1161 |
+
},
|
1162 |
+
{
|
1163 |
+
"epoch": 0.96,
|
1164 |
+
"eval_loss": 2.1920626163482666,
|
1165 |
+
"eval_runtime": 1641.5349,
|
1166 |
+
"eval_samples_per_second": 24.367,
|
1167 |
+
"eval_steps_per_second": 24.367,
|
1168 |
+
"step": 58000
|
1169 |
+
},
|
1170 |
+
{
|
1171 |
+
"epoch": 0.96,
|
1172 |
+
"learning_rate": 2.7141114408176722e-05,
|
1173 |
+
"loss": 2.233,
|
1174 |
+
"step": 58500
|
1175 |
+
},
|
1176 |
+
{
|
1177 |
+
"epoch": 0.97,
|
1178 |
+
"learning_rate": 2.711646884272997e-05,
|
1179 |
+
"loss": 2.2292,
|
1180 |
+
"step": 59000
|
1181 |
+
},
|
1182 |
+
{
|
1183 |
+
"epoch": 0.97,
|
1184 |
+
"eval_loss": 2.182201862335205,
|
1185 |
+
"eval_runtime": 1643.6909,
|
1186 |
+
"eval_samples_per_second": 24.335,
|
1187 |
+
"eval_steps_per_second": 24.335,
|
1188 |
+
"step": 59000
|
1189 |
+
},
|
1190 |
+
{
|
1191 |
+
"epoch": 0.98,
|
1192 |
+
"learning_rate": 2.7091823277283218e-05,
|
1193 |
+
"loss": 2.2104,
|
1194 |
+
"step": 59500
|
1195 |
+
},
|
1196 |
+
{
|
1197 |
+
"epoch": 0.99,
|
1198 |
+
"learning_rate": 2.7067177711836464e-05,
|
1199 |
+
"loss": 2.2322,
|
1200 |
+
"step": 60000
|
1201 |
+
},
|
1202 |
+
{
|
1203 |
+
"epoch": 0.99,
|
1204 |
+
"eval_loss": 2.186232089996338,
|
1205 |
+
"eval_runtime": 1642.8864,
|
1206 |
+
"eval_samples_per_second": 24.347,
|
1207 |
+
"eval_steps_per_second": 24.347,
|
1208 |
+
"step": 60000
|
1209 |
+
},
|
1210 |
+
{
|
1211 |
+
"epoch": 1.0,
|
1212 |
+
"learning_rate": 2.704253214638971e-05,
|
1213 |
+
"loss": 2.2059,
|
1214 |
+
"step": 60500
|
1215 |
+
},
|
1216 |
+
{
|
1217 |
+
"epoch": 1.0,
|
1218 |
+
"learning_rate": 2.7017886580942964e-05,
|
1219 |
+
"loss": 2.1856,
|
1220 |
+
"step": 61000
|
1221 |
+
},
|
1222 |
+
{
|
1223 |
+
"epoch": 1.0,
|
1224 |
+
"eval_loss": 2.1843557357788086,
|
1225 |
+
"eval_runtime": 1645.6389,
|
1226 |
+
"eval_samples_per_second": 24.307,
|
1227 |
+
"eval_steps_per_second": 24.307,
|
1228 |
+
"step": 61000
|
1229 |
+
},
|
1230 |
+
{
|
1231 |
+
"epoch": 1.01,
|
1232 |
+
"learning_rate": 2.699324101549621e-05,
|
1233 |
+
"loss": 2.1659,
|
1234 |
+
"step": 61500
|
1235 |
+
},
|
1236 |
+
{
|
1237 |
+
"epoch": 1.02,
|
1238 |
+
"learning_rate": 2.6968595450049456e-05,
|
1239 |
+
"loss": 2.177,
|
1240 |
+
"step": 62000
|
1241 |
+
},
|
1242 |
+
{
|
1243 |
+
"epoch": 1.02,
|
1244 |
+
"eval_loss": 2.1830549240112305,
|
1245 |
+
"eval_runtime": 1640.3296,
|
1246 |
+
"eval_samples_per_second": 24.385,
|
1247 |
+
"eval_steps_per_second": 24.385,
|
1248 |
+
"step": 62000
|
1249 |
+
},
|
1250 |
+
{
|
1251 |
+
"epoch": 1.03,
|
1252 |
+
"learning_rate": 2.6943949884602706e-05,
|
1253 |
+
"loss": 2.1659,
|
1254 |
+
"step": 62500
|
1255 |
+
},
|
1256 |
+
{
|
1257 |
+
"epoch": 1.04,
|
1258 |
+
"learning_rate": 2.6919304319155952e-05,
|
1259 |
+
"loss": 2.1708,
|
1260 |
+
"step": 63000
|
1261 |
+
},
|
1262 |
+
{
|
1263 |
+
"epoch": 1.04,
|
1264 |
+
"eval_loss": 2.1878035068511963,
|
1265 |
+
"eval_runtime": 1647.1232,
|
1266 |
+
"eval_samples_per_second": 24.285,
|
1267 |
+
"eval_steps_per_second": 24.285,
|
1268 |
+
"step": 63000
|
1269 |
+
},
|
1270 |
+
{
|
1271 |
+
"epoch": 1.05,
|
1272 |
+
"learning_rate": 2.68946587537092e-05,
|
1273 |
+
"loss": 2.1672,
|
1274 |
+
"step": 63500
|
1275 |
+
},
|
1276 |
+
{
|
1277 |
+
"epoch": 1.05,
|
1278 |
+
"learning_rate": 2.6870013188262448e-05,
|
1279 |
+
"loss": 2.162,
|
1280 |
+
"step": 64000
|
1281 |
+
},
|
1282 |
+
{
|
1283 |
+
"epoch": 1.05,
|
1284 |
+
"eval_loss": 2.184495210647583,
|
1285 |
+
"eval_runtime": 1647.5833,
|
1286 |
+
"eval_samples_per_second": 24.278,
|
1287 |
+
"eval_steps_per_second": 24.278,
|
1288 |
+
"step": 64000
|
1289 |
+
},
|
1290 |
+
{
|
1291 |
+
"epoch": 1.06,
|
1292 |
+
"learning_rate": 2.6845367622815695e-05,
|
1293 |
+
"loss": 2.157,
|
1294 |
+
"step": 64500
|
1295 |
+
},
|
1296 |
+
{
|
1297 |
+
"epoch": 1.07,
|
1298 |
+
"learning_rate": 2.682072205736894e-05,
|
1299 |
+
"loss": 2.1928,
|
1300 |
+
"step": 65000
|
1301 |
+
},
|
1302 |
+
{
|
1303 |
+
"epoch": 1.07,
|
1304 |
+
"eval_loss": 2.177741050720215,
|
1305 |
+
"eval_runtime": 1681.8483,
|
1306 |
+
"eval_samples_per_second": 23.783,
|
1307 |
+
"eval_steps_per_second": 23.783,
|
1308 |
+
"step": 65000
|
1309 |
+
},
|
1310 |
+
{
|
1311 |
+
"epoch": 1.08,
|
1312 |
+
"learning_rate": 2.6796076491922187e-05,
|
1313 |
+
"loss": 2.1747,
|
1314 |
+
"step": 65500
|
1315 |
+
},
|
1316 |
+
{
|
1317 |
+
"epoch": 1.09,
|
1318 |
+
"learning_rate": 2.6771430926475437e-05,
|
1319 |
+
"loss": 2.1839,
|
1320 |
+
"step": 66000
|
1321 |
+
},
|
1322 |
+
{
|
1323 |
+
"epoch": 1.09,
|
1324 |
+
"eval_loss": 2.1771292686462402,
|
1325 |
+
"eval_runtime": 1698.416,
|
1326 |
+
"eval_samples_per_second": 23.551,
|
1327 |
+
"eval_steps_per_second": 23.551,
|
1328 |
+
"step": 66000
|
1329 |
+
},
|
1330 |
+
{
|
1331 |
+
"epoch": 1.1,
|
1332 |
+
"learning_rate": 2.6746785361028683e-05,
|
1333 |
+
"loss": 2.1704,
|
1334 |
+
"step": 66500
|
1335 |
+
},
|
1336 |
+
{
|
1337 |
+
"epoch": 1.1,
|
1338 |
+
"learning_rate": 2.6722139795581933e-05,
|
1339 |
+
"loss": 2.1627,
|
1340 |
+
"step": 67000
|
1341 |
+
},
|
1342 |
+
{
|
1343 |
+
"epoch": 1.1,
|
1344 |
+
"eval_loss": 2.176990509033203,
|
1345 |
+
"eval_runtime": 1663.2499,
|
1346 |
+
"eval_samples_per_second": 24.049,
|
1347 |
+
"eval_steps_per_second": 24.049,
|
1348 |
+
"step": 67000
|
1349 |
+
},
|
1350 |
+
{
|
1351 |
+
"epoch": 1.11,
|
1352 |
+
"learning_rate": 2.6697494230135182e-05,
|
1353 |
+
"loss": 2.1672,
|
1354 |
+
"step": 67500
|
1355 |
+
},
|
1356 |
+
{
|
1357 |
+
"epoch": 1.12,
|
1358 |
+
"learning_rate": 2.667284866468843e-05,
|
1359 |
+
"loss": 2.1613,
|
1360 |
+
"step": 68000
|
1361 |
+
},
|
1362 |
+
{
|
1363 |
+
"epoch": 1.12,
|
1364 |
+
"eval_loss": 2.178516387939453,
|
1365 |
+
"eval_runtime": 1655.5689,
|
1366 |
+
"eval_samples_per_second": 24.161,
|
1367 |
+
"eval_steps_per_second": 24.161,
|
1368 |
+
"step": 68000
|
1369 |
+
},
|
1370 |
+
{
|
1371 |
+
"epoch": 1.13,
|
1372 |
+
"learning_rate": 2.6648203099241675e-05,
|
1373 |
+
"loss": 2.1681,
|
1374 |
+
"step": 68500
|
1375 |
+
},
|
1376 |
+
{
|
1377 |
+
"epoch": 1.14,
|
1378 |
+
"learning_rate": 2.6623557533794925e-05,
|
1379 |
+
"loss": 2.1664,
|
1380 |
+
"step": 69000
|
1381 |
+
},
|
1382 |
+
{
|
1383 |
+
"epoch": 1.14,
|
1384 |
+
"eval_loss": 2.1790318489074707,
|
1385 |
+
"eval_runtime": 1664.8312,
|
1386 |
+
"eval_samples_per_second": 24.026,
|
1387 |
+
"eval_steps_per_second": 24.026,
|
1388 |
+
"step": 69000
|
1389 |
+
},
|
1390 |
+
{
|
1391 |
+
"epoch": 1.14,
|
1392 |
+
"learning_rate": 2.659891196834817e-05,
|
1393 |
+
"loss": 2.1627,
|
1394 |
+
"step": 69500
|
1395 |
+
},
|
1396 |
+
{
|
1397 |
+
"epoch": 1.15,
|
1398 |
+
"learning_rate": 2.6574266402901417e-05,
|
1399 |
+
"loss": 2.1651,
|
1400 |
+
"step": 70000
|
1401 |
+
},
|
1402 |
+
{
|
1403 |
+
"epoch": 1.15,
|
1404 |
+
"eval_loss": 2.1793885231018066,
|
1405 |
+
"eval_runtime": 1658.525,
|
1406 |
+
"eval_samples_per_second": 24.118,
|
1407 |
+
"eval_steps_per_second": 24.118,
|
1408 |
+
"step": 70000
|
1409 |
+
},
|
1410 |
+
{
|
1411 |
+
"epoch": 1.16,
|
1412 |
+
"learning_rate": 2.6549620837454667e-05,
|
1413 |
+
"loss": 2.1489,
|
1414 |
+
"step": 70500
|
1415 |
+
},
|
1416 |
+
{
|
1417 |
+
"epoch": 1.17,
|
1418 |
+
"learning_rate": 2.6524975272007913e-05,
|
1419 |
+
"loss": 2.1548,
|
1420 |
+
"step": 71000
|
1421 |
+
},
|
1422 |
+
{
|
1423 |
+
"epoch": 1.17,
|
1424 |
+
"eval_loss": 2.1826231479644775,
|
1425 |
+
"eval_runtime": 1662.4548,
|
1426 |
+
"eval_samples_per_second": 24.061,
|
1427 |
+
"eval_steps_per_second": 24.061,
|
1428 |
+
"step": 71000
|
1429 |
+
},
|
1430 |
+
{
|
1431 |
+
"epoch": 1.18,
|
1432 |
+
"learning_rate": 2.650032970656116e-05,
|
1433 |
+
"loss": 2.156,
|
1434 |
+
"step": 71500
|
1435 |
+
},
|
1436 |
+
{
|
1437 |
+
"epoch": 1.19,
|
1438 |
+
"learning_rate": 2.647568414111441e-05,
|
1439 |
+
"loss": 2.1651,
|
1440 |
+
"step": 72000
|
1441 |
+
},
|
1442 |
+
{
|
1443 |
+
"epoch": 1.19,
|
1444 |
+
"eval_loss": 2.1709914207458496,
|
1445 |
+
"eval_runtime": 1673.5968,
|
1446 |
+
"eval_samples_per_second": 23.901,
|
1447 |
+
"eval_steps_per_second": 23.901,
|
1448 |
+
"step": 72000
|
1449 |
+
},
|
1450 |
+
{
|
1451 |
+
"epoch": 1.19,
|
1452 |
+
"learning_rate": 2.6451038575667655e-05,
|
1453 |
+
"loss": 2.1621,
|
1454 |
+
"step": 72500
|
1455 |
+
},
|
1456 |
+
{
|
1457 |
+
"epoch": 1.2,
|
1458 |
+
"learning_rate": 2.6426393010220902e-05,
|
1459 |
+
"loss": 2.1837,
|
1460 |
+
"step": 73000
|
1461 |
+
},
|
1462 |
+
{
|
1463 |
+
"epoch": 1.2,
|
1464 |
+
"eval_loss": 2.176527261734009,
|
1465 |
+
"eval_runtime": 1669.4555,
|
1466 |
+
"eval_samples_per_second": 23.96,
|
1467 |
+
"eval_steps_per_second": 23.96,
|
1468 |
+
"step": 73000
|
1469 |
+
},
|
1470 |
+
{
|
1471 |
+
"epoch": 1.21,
|
1472 |
+
"learning_rate": 2.640174744477415e-05,
|
1473 |
+
"loss": 2.1728,
|
1474 |
+
"step": 73500
|
1475 |
+
},
|
1476 |
+
{
|
1477 |
+
"epoch": 1.22,
|
1478 |
+
"learning_rate": 2.63771018793274e-05,
|
1479 |
+
"loss": 2.1521,
|
1480 |
+
"step": 74000
|
1481 |
+
},
|
1482 |
+
{
|
1483 |
+
"epoch": 1.22,
|
1484 |
+
"eval_loss": 2.1770825386047363,
|
1485 |
+
"eval_runtime": 1646.6769,
|
1486 |
+
"eval_samples_per_second": 24.291,
|
1487 |
+
"eval_steps_per_second": 24.291,
|
1488 |
+
"step": 74000
|
1489 |
+
},
|
1490 |
+
{
|
1491 |
+
"epoch": 1.23,
|
1492 |
+
"learning_rate": 2.6352456313880647e-05,
|
1493 |
+
"loss": 2.1571,
|
1494 |
+
"step": 74500
|
1495 |
+
},
|
1496 |
+
{
|
1497 |
+
"epoch": 1.24,
|
1498 |
+
"learning_rate": 2.6327810748433894e-05,
|
1499 |
+
"loss": 2.1474,
|
1500 |
+
"step": 75000
|
1501 |
+
},
|
1502 |
+
{
|
1503 |
+
"epoch": 1.24,
|
1504 |
+
"eval_loss": 2.183932304382324,
|
1505 |
+
"eval_runtime": 1639.8623,
|
1506 |
+
"eval_samples_per_second": 24.392,
|
1507 |
+
"eval_steps_per_second": 24.392,
|
1508 |
+
"step": 75000
|
1509 |
+
},
|
1510 |
+
{
|
1511 |
+
"epoch": 1.24,
|
1512 |
+
"learning_rate": 2.6303165182987143e-05,
|
1513 |
+
"loss": 2.165,
|
1514 |
+
"step": 75500
|
1515 |
+
},
|
1516 |
+
{
|
1517 |
+
"epoch": 1.25,
|
1518 |
+
"learning_rate": 2.627851961754039e-05,
|
1519 |
+
"loss": 2.1581,
|
1520 |
+
"step": 76000
|
1521 |
+
},
|
1522 |
+
{
|
1523 |
+
"epoch": 1.25,
|
1524 |
+
"eval_loss": 2.1714603900909424,
|
1525 |
+
"eval_runtime": 1639.9709,
|
1526 |
+
"eval_samples_per_second": 24.391,
|
1527 |
+
"eval_steps_per_second": 24.391,
|
1528 |
+
"step": 76000
|
1529 |
+
},
|
1530 |
+
{
|
1531 |
+
"epoch": 1.26,
|
1532 |
+
"learning_rate": 2.625387405209364e-05,
|
1533 |
+
"loss": 2.1739,
|
1534 |
+
"step": 76500
|
1535 |
+
},
|
1536 |
+
{
|
1537 |
+
"epoch": 1.27,
|
1538 |
+
"learning_rate": 2.6229228486646886e-05,
|
1539 |
+
"loss": 2.1539,
|
1540 |
+
"step": 77000
|
1541 |
+
},
|
1542 |
+
{
|
1543 |
+
"epoch": 1.27,
|
1544 |
+
"eval_loss": 2.1725363731384277,
|
1545 |
+
"eval_runtime": 1638.1954,
|
1546 |
+
"eval_samples_per_second": 24.417,
|
1547 |
+
"eval_steps_per_second": 24.417,
|
1548 |
+
"step": 77000
|
1549 |
+
},
|
1550 |
+
{
|
1551 |
+
"epoch": 1.28,
|
1552 |
+
"learning_rate": 2.6204582921200132e-05,
|
1553 |
+
"loss": 2.1458,
|
1554 |
+
"step": 77500
|
1555 |
+
},
|
1556 |
+
{
|
1557 |
+
"epoch": 1.28,
|
1558 |
+
"learning_rate": 2.6179937355753378e-05,
|
1559 |
+
"loss": 2.1755,
|
1560 |
+
"step": 78000
|
1561 |
+
},
|
1562 |
+
{
|
1563 |
+
"epoch": 1.28,
|
1564 |
+
"eval_loss": 2.176203727722168,
|
1565 |
+
"eval_runtime": 1640.2646,
|
1566 |
+
"eval_samples_per_second": 24.386,
|
1567 |
+
"eval_steps_per_second": 24.386,
|
1568 |
+
"step": 78000
|
1569 |
+
},
|
1570 |
+
{
|
1571 |
+
"epoch": 1.29,
|
1572 |
+
"learning_rate": 2.6155291790306628e-05,
|
1573 |
+
"loss": 2.1372,
|
1574 |
+
"step": 78500
|
1575 |
+
},
|
1576 |
+
{
|
1577 |
+
"epoch": 1.3,
|
1578 |
+
"learning_rate": 2.6130646224859874e-05,
|
1579 |
+
"loss": 2.1556,
|
1580 |
+
"step": 79000
|
1581 |
+
},
|
1582 |
+
{
|
1583 |
+
"epoch": 1.3,
|
1584 |
+
"eval_loss": 2.1716091632843018,
|
1585 |
+
"eval_runtime": 1640.0168,
|
1586 |
+
"eval_samples_per_second": 24.39,
|
1587 |
+
"eval_steps_per_second": 24.39,
|
1588 |
+
"step": 79000
|
1589 |
+
},
|
1590 |
+
{
|
1591 |
+
"epoch": 1.31,
|
1592 |
+
"learning_rate": 2.610600065941312e-05,
|
1593 |
+
"loss": 2.1467,
|
1594 |
+
"step": 79500
|
1595 |
+
},
|
1596 |
+
{
|
1597 |
+
"epoch": 1.32,
|
1598 |
+
"learning_rate": 2.6081355093966373e-05,
|
1599 |
+
"loss": 2.1613,
|
1600 |
+
"step": 80000
|
1601 |
+
},
|
1602 |
+
{
|
1603 |
+
"epoch": 1.32,
|
1604 |
+
"eval_loss": 2.1746010780334473,
|
1605 |
+
"eval_runtime": 1640.7934,
|
1606 |
+
"eval_samples_per_second": 24.378,
|
1607 |
+
"eval_steps_per_second": 24.378,
|
1608 |
+
"step": 80000
|
1609 |
+
},
|
1610 |
+
{
|
1611 |
+
"epoch": 1.33,
|
1612 |
+
"learning_rate": 2.605670952851962e-05,
|
1613 |
+
"loss": 2.1964,
|
1614 |
+
"step": 80500
|
1615 |
+
},
|
1616 |
+
{
|
1617 |
+
"epoch": 1.33,
|
1618 |
+
"learning_rate": 2.6032063963072866e-05,
|
1619 |
+
"loss": 2.16,
|
1620 |
+
"step": 81000
|
1621 |
+
},
|
1622 |
+
{
|
1623 |
+
"epoch": 1.33,
|
1624 |
+
"eval_loss": 2.170952558517456,
|
1625 |
+
"eval_runtime": 1636.9866,
|
1626 |
+
"eval_samples_per_second": 24.435,
|
1627 |
+
"eval_steps_per_second": 24.435,
|
1628 |
+
"step": 81000
|
1629 |
+
},
|
1630 |
+
{
|
1631 |
+
"epoch": 1.34,
|
1632 |
+
"learning_rate": 2.6007418397626112e-05,
|
1633 |
+
"loss": 2.1573,
|
1634 |
+
"step": 81500
|
1635 |
+
},
|
1636 |
+
{
|
1637 |
+
"epoch": 1.35,
|
1638 |
+
"learning_rate": 2.5982772832179362e-05,
|
1639 |
+
"loss": 2.1615,
|
1640 |
+
"step": 82000
|
1641 |
+
},
|
1642 |
+
{
|
1643 |
+
"epoch": 1.35,
|
1644 |
+
"eval_loss": 2.1753742694854736,
|
1645 |
+
"eval_runtime": 1641.4118,
|
1646 |
+
"eval_samples_per_second": 24.369,
|
1647 |
+
"eval_steps_per_second": 24.369,
|
1648 |
+
"step": 82000
|
1649 |
+
},
|
1650 |
+
{
|
1651 |
+
"epoch": 1.36,
|
1652 |
+
"learning_rate": 2.5958127266732608e-05,
|
1653 |
+
"loss": 2.1389,
|
1654 |
+
"step": 82500
|
1655 |
+
},
|
1656 |
+
{
|
1657 |
+
"epoch": 1.37,
|
1658 |
+
"learning_rate": 2.5933481701285858e-05,
|
1659 |
+
"loss": 2.162,
|
1660 |
+
"step": 83000
|
1661 |
+
},
|
1662 |
+
{
|
1663 |
+
"epoch": 1.37,
|
1664 |
+
"eval_loss": 2.1643452644348145,
|
1665 |
+
"eval_runtime": 1631.9127,
|
1666 |
+
"eval_samples_per_second": 24.511,
|
1667 |
+
"eval_steps_per_second": 24.511,
|
1668 |
+
"step": 83000
|
1669 |
+
},
|
1670 |
+
{
|
1671 |
+
"epoch": 1.38,
|
1672 |
+
"learning_rate": 2.5908836135839104e-05,
|
1673 |
+
"loss": 2.1261,
|
1674 |
+
"step": 83500
|
1675 |
+
},
|
1676 |
+
{
|
1677 |
+
"epoch": 1.38,
|
1678 |
+
"learning_rate": 2.588419057039235e-05,
|
1679 |
+
"loss": 2.1397,
|
1680 |
+
"step": 84000
|
1681 |
+
},
|
1682 |
+
{
|
1683 |
+
"epoch": 1.38,
|
1684 |
+
"eval_loss": 2.16678786277771,
|
1685 |
+
"eval_runtime": 1670.9426,
|
1686 |
+
"eval_samples_per_second": 23.939,
|
1687 |
+
"eval_steps_per_second": 23.939,
|
1688 |
+
"step": 84000
|
1689 |
+
},
|
1690 |
+
{
|
1691 |
+
"epoch": 1.39,
|
1692 |
+
"learning_rate": 2.5859545004945597e-05,
|
1693 |
+
"loss": 2.1437,
|
1694 |
+
"step": 84500
|
1695 |
+
},
|
1696 |
+
{
|
1697 |
+
"epoch": 1.4,
|
1698 |
+
"learning_rate": 2.5834899439498846e-05,
|
1699 |
+
"loss": 2.1385,
|
1700 |
+
"step": 85000
|
1701 |
+
},
|
1702 |
+
{
|
1703 |
+
"epoch": 1.4,
|
1704 |
+
"eval_loss": 2.1743927001953125,
|
1705 |
+
"eval_runtime": 1630.9596,
|
1706 |
+
"eval_samples_per_second": 24.525,
|
1707 |
+
"eval_steps_per_second": 24.525,
|
1708 |
+
"step": 85000
|
1709 |
+
},
|
1710 |
+
{
|
1711 |
+
"epoch": 1.41,
|
1712 |
+
"learning_rate": 2.5810253874052093e-05,
|
1713 |
+
"loss": 2.131,
|
1714 |
+
"step": 85500
|
1715 |
+
},
|
1716 |
+
{
|
1717 |
+
"epoch": 1.42,
|
1718 |
+
"learning_rate": 2.578560830860534e-05,
|
1719 |
+
"loss": 2.1457,
|
1720 |
+
"step": 86000
|
1721 |
+
},
|
1722 |
+
{
|
1723 |
+
"epoch": 1.42,
|
1724 |
+
"eval_loss": 2.1709821224212646,
|
1725 |
+
"eval_runtime": 1641.5418,
|
1726 |
+
"eval_samples_per_second": 24.367,
|
1727 |
+
"eval_steps_per_second": 24.367,
|
1728 |
+
"step": 86000
|
1729 |
+
},
|
1730 |
+
{
|
1731 |
+
"epoch": 1.42,
|
1732 |
+
"learning_rate": 2.5760962743158592e-05,
|
1733 |
+
"loss": 2.1115,
|
1734 |
+
"step": 86500
|
1735 |
+
},
|
1736 |
+
{
|
1737 |
+
"epoch": 1.43,
|
1738 |
+
"learning_rate": 2.573631717771184e-05,
|
1739 |
+
"loss": 2.1394,
|
1740 |
+
"step": 87000
|
1741 |
+
},
|
1742 |
+
{
|
1743 |
+
"epoch": 1.43,
|
1744 |
+
"eval_loss": 2.169813871383667,
|
1745 |
+
"eval_runtime": 1633.6854,
|
1746 |
+
"eval_samples_per_second": 24.485,
|
1747 |
+
"eval_steps_per_second": 24.485,
|
1748 |
+
"step": 87000
|
1749 |
+
},
|
1750 |
+
{
|
1751 |
+
"epoch": 1.44,
|
1752 |
+
"learning_rate": 2.5711671612265085e-05,
|
1753 |
+
"loss": 2.1397,
|
1754 |
+
"step": 87500
|
1755 |
+
},
|
1756 |
+
{
|
1757 |
+
"epoch": 1.45,
|
1758 |
+
"learning_rate": 2.568702604681833e-05,
|
1759 |
+
"loss": 2.1359,
|
1760 |
+
"step": 88000
|
1761 |
+
},
|
1762 |
+
{
|
1763 |
+
"epoch": 1.45,
|
1764 |
+
"eval_loss": 2.1732752323150635,
|
1765 |
+
"eval_runtime": 1802.3943,
|
1766 |
+
"eval_samples_per_second": 22.193,
|
1767 |
+
"eval_steps_per_second": 22.193,
|
1768 |
+
"step": 88000
|
1769 |
+
},
|
1770 |
+
{
|
1771 |
+
"epoch": 1.46,
|
1772 |
+
"learning_rate": 2.566238048137158e-05,
|
1773 |
+
"loss": 2.1412,
|
1774 |
+
"step": 88500
|
1775 |
+
},
|
1776 |
+
{
|
1777 |
+
"epoch": 1.47,
|
1778 |
+
"learning_rate": 2.5637734915924827e-05,
|
1779 |
+
"loss": 2.1248,
|
1780 |
+
"step": 89000
|
1781 |
+
},
|
1782 |
+
{
|
1783 |
+
"epoch": 1.47,
|
1784 |
+
"eval_loss": 2.1696412563323975,
|
1785 |
+
"eval_runtime": 1651.1875,
|
1786 |
+
"eval_samples_per_second": 24.225,
|
1787 |
+
"eval_steps_per_second": 24.225,
|
1788 |
+
"step": 89000
|
1789 |
+
},
|
1790 |
+
{
|
1791 |
+
"epoch": 1.47,
|
1792 |
+
"learning_rate": 2.5613089350478077e-05,
|
1793 |
+
"loss": 2.1184,
|
1794 |
+
"step": 89500
|
1795 |
+
},
|
1796 |
+
{
|
1797 |
+
"epoch": 1.48,
|
1798 |
+
"learning_rate": 2.5588443785031323e-05,
|
1799 |
+
"loss": 2.1352,
|
1800 |
+
"step": 90000
|
1801 |
+
},
|
1802 |
+
{
|
1803 |
+
"epoch": 1.48,
|
1804 |
+
"eval_loss": 2.1655664443969727,
|
1805 |
+
"eval_runtime": 1639.9406,
|
1806 |
+
"eval_samples_per_second": 24.391,
|
1807 |
+
"eval_steps_per_second": 24.391,
|
1808 |
+
"step": 90000
|
1809 |
+
},
|
1810 |
+
{
|
1811 |
+
"epoch": 1.49,
|
1812 |
+
"learning_rate": 2.556379821958457e-05,
|
1813 |
+
"loss": 2.1329,
|
1814 |
+
"step": 90500
|
1815 |
+
},
|
1816 |
+
{
|
1817 |
+
"epoch": 1.5,
|
1818 |
+
"learning_rate": 2.5539152654137815e-05,
|
1819 |
+
"loss": 2.1304,
|
1820 |
+
"step": 91000
|
1821 |
+
},
|
1822 |
+
{
|
1823 |
+
"epoch": 1.5,
|
1824 |
+
"eval_loss": 2.171034574508667,
|
1825 |
+
"eval_runtime": 1644.883,
|
1826 |
+
"eval_samples_per_second": 24.318,
|
1827 |
+
"eval_steps_per_second": 24.318,
|
1828 |
+
"step": 91000
|
1829 |
+
},
|
1830 |
+
{
|
1831 |
+
"epoch": 1.51,
|
1832 |
+
"learning_rate": 2.5514507088691065e-05,
|
1833 |
+
"loss": 2.134,
|
1834 |
+
"step": 91500
|
1835 |
+
},
|
1836 |
+
{
|
1837 |
+
"epoch": 1.52,
|
1838 |
+
"learning_rate": 2.548986152324431e-05,
|
1839 |
+
"loss": 2.1417,
|
1840 |
+
"step": 92000
|
1841 |
+
},
|
1842 |
+
{
|
1843 |
+
"epoch": 1.52,
|
1844 |
+
"eval_loss": 2.164717674255371,
|
1845 |
+
"eval_runtime": 1627.0004,
|
1846 |
+
"eval_samples_per_second": 24.585,
|
1847 |
+
"eval_steps_per_second": 24.585,
|
1848 |
+
"step": 92000
|
1849 |
+
},
|
1850 |
+
{
|
1851 |
+
"epoch": 1.52,
|
1852 |
+
"learning_rate": 2.546521595779756e-05,
|
1853 |
+
"loss": 2.1519,
|
1854 |
+
"step": 92500
|
1855 |
+
},
|
1856 |
+
{
|
1857 |
+
"epoch": 1.53,
|
1858 |
+
"learning_rate": 2.544057039235081e-05,
|
1859 |
+
"loss": 2.1321,
|
1860 |
+
"step": 93000
|
1861 |
+
},
|
1862 |
+
{
|
1863 |
+
"epoch": 1.53,
|
1864 |
+
"eval_loss": 2.164560317993164,
|
1865 |
+
"eval_runtime": 1620.161,
|
1866 |
+
"eval_samples_per_second": 24.689,
|
1867 |
+
"eval_steps_per_second": 24.689,
|
1868 |
+
"step": 93000
|
1869 |
+
},
|
1870 |
+
{
|
1871 |
+
"epoch": 1.54,
|
1872 |
+
"learning_rate": 2.5415924826904057e-05,
|
1873 |
+
"loss": 2.1395,
|
1874 |
+
"step": 93500
|
1875 |
+
},
|
1876 |
+
{
|
1877 |
+
"epoch": 1.55,
|
1878 |
+
"learning_rate": 2.5391279261457303e-05,
|
1879 |
+
"loss": 2.1364,
|
1880 |
+
"step": 94000
|
1881 |
+
},
|
1882 |
+
{
|
1883 |
+
"epoch": 1.55,
|
1884 |
+
"eval_loss": 2.1626968383789062,
|
1885 |
+
"eval_runtime": 1698.7469,
|
1886 |
+
"eval_samples_per_second": 23.547,
|
1887 |
+
"eval_steps_per_second": 23.547,
|
1888 |
+
"step": 94000
|
1889 |
+
},
|
1890 |
+
{
|
1891 |
+
"epoch": 1.56,
|
1892 |
+
"learning_rate": 2.5366633696010553e-05,
|
1893 |
+
"loss": 2.1361,
|
1894 |
+
"step": 94500
|
1895 |
+
},
|
1896 |
+
{
|
1897 |
+
"epoch": 1.56,
|
1898 |
+
"learning_rate": 2.53419881305638e-05,
|
1899 |
+
"loss": 2.1207,
|
1900 |
+
"step": 95000
|
1901 |
+
},
|
1902 |
+
{
|
1903 |
+
"epoch": 1.56,
|
1904 |
+
"eval_loss": 2.169800281524658,
|
1905 |
+
"eval_runtime": 1698.1462,
|
1906 |
+
"eval_samples_per_second": 23.555,
|
1907 |
+
"eval_steps_per_second": 23.555,
|
1908 |
+
"step": 95000
|
1909 |
+
},
|
1910 |
+
{
|
1911 |
+
"epoch": 1.57,
|
1912 |
+
"learning_rate": 2.5317342565117046e-05,
|
1913 |
+
"loss": 2.1177,
|
1914 |
+
"step": 95500
|
1915 |
+
},
|
1916 |
+
{
|
1917 |
+
"epoch": 1.58,
|
1918 |
+
"learning_rate": 2.5292696999670295e-05,
|
1919 |
+
"loss": 2.1159,
|
1920 |
+
"step": 96000
|
1921 |
+
},
|
1922 |
+
{
|
1923 |
+
"epoch": 1.58,
|
1924 |
+
"eval_loss": 2.1711175441741943,
|
1925 |
+
"eval_runtime": 1693.0388,
|
1926 |
+
"eval_samples_per_second": 23.626,
|
1927 |
+
"eval_steps_per_second": 23.626,
|
1928 |
+
"step": 96000
|
1929 |
+
},
|
1930 |
+
{
|
1931 |
+
"epoch": 1.59,
|
1932 |
+
"learning_rate": 2.526805143422354e-05,
|
1933 |
+
"loss": 2.132,
|
1934 |
+
"step": 96500
|
1935 |
+
},
|
1936 |
+
{
|
1937 |
+
"epoch": 1.6,
|
1938 |
+
"learning_rate": 2.5243405868776788e-05,
|
1939 |
+
"loss": 2.1211,
|
1940 |
+
"step": 97000
|
1941 |
+
},
|
1942 |
+
{
|
1943 |
+
"epoch": 1.6,
|
1944 |
+
"eval_loss": 2.162254571914673,
|
1945 |
+
"eval_runtime": 1696.8798,
|
1946 |
+
"eval_samples_per_second": 23.573,
|
1947 |
+
"eval_steps_per_second": 23.573,
|
1948 |
+
"step": 97000
|
1949 |
+
},
|
1950 |
+
{
|
1951 |
+
"epoch": 1.61,
|
1952 |
+
"learning_rate": 2.5218760303330034e-05,
|
1953 |
+
"loss": 2.1106,
|
1954 |
+
"step": 97500
|
1955 |
+
},
|
1956 |
+
{
|
1957 |
+
"epoch": 1.61,
|
1958 |
+
"learning_rate": 2.5194114737883284e-05,
|
1959 |
+
"loss": 2.1324,
|
1960 |
+
"step": 98000
|
1961 |
+
},
|
1962 |
+
{
|
1963 |
+
"epoch": 1.61,
|
1964 |
+
"eval_loss": 2.160202980041504,
|
1965 |
+
"eval_runtime": 1693.2743,
|
1966 |
+
"eval_samples_per_second": 23.623,
|
1967 |
+
"eval_steps_per_second": 23.623,
|
1968 |
+
"step": 98000
|
1969 |
+
},
|
1970 |
+
{
|
1971 |
+
"epoch": 1.62,
|
1972 |
+
"learning_rate": 2.516946917243653e-05,
|
1973 |
+
"loss": 2.1137,
|
1974 |
+
"step": 98500
|
1975 |
+
},
|
1976 |
+
{
|
1977 |
+
"epoch": 1.63,
|
1978 |
+
"learning_rate": 2.5144823606989783e-05,
|
1979 |
+
"loss": 2.1332,
|
1980 |
+
"step": 99000
|
1981 |
+
},
|
1982 |
+
{
|
1983 |
+
"epoch": 1.63,
|
1984 |
+
"eval_loss": 2.1663293838500977,
|
1985 |
+
"eval_runtime": 1689.4982,
|
1986 |
+
"eval_samples_per_second": 23.676,
|
1987 |
+
"eval_steps_per_second": 23.676,
|
1988 |
+
"step": 99000
|
1989 |
+
},
|
1990 |
+
{
|
1991 |
+
"epoch": 1.64,
|
1992 |
+
"learning_rate": 2.512017804154303e-05,
|
1993 |
+
"loss": 2.1319,
|
1994 |
+
"step": 99500
|
1995 |
+
},
|
1996 |
+
{
|
1997 |
+
"epoch": 1.65,
|
1998 |
+
"learning_rate": 2.5095532476096276e-05,
|
1999 |
+
"loss": 2.1189,
|
2000 |
+
"step": 100000
|
2001 |
+
},
|
2002 |
+
{
|
2003 |
+
"epoch": 1.65,
|
2004 |
+
"eval_loss": 2.1696457862854004,
|
2005 |
+
"eval_runtime": 1699.5766,
|
2006 |
+
"eval_samples_per_second": 23.535,
|
2007 |
+
"eval_steps_per_second": 23.535,
|
2008 |
+
"step": 100000
|
2009 |
+
},
|
2010 |
+
{
|
2011 |
+
"epoch": 1.66,
|
2012 |
+
"learning_rate": 2.5070886910649522e-05,
|
2013 |
+
"loss": 2.1304,
|
2014 |
+
"step": 100500
|
2015 |
+
},
|
2016 |
+
{
|
2017 |
+
"epoch": 1.66,
|
2018 |
+
"learning_rate": 2.504624134520277e-05,
|
2019 |
+
"loss": 2.1117,
|
2020 |
+
"step": 101000
|
2021 |
+
},
|
2022 |
+
{
|
2023 |
+
"epoch": 1.66,
|
2024 |
+
"eval_loss": 2.1668128967285156,
|
2025 |
+
"eval_runtime": 1687.1022,
|
2026 |
+
"eval_samples_per_second": 23.709,
|
2027 |
+
"eval_steps_per_second": 23.709,
|
2028 |
+
"step": 101000
|
2029 |
+
},
|
2030 |
+
{
|
2031 |
+
"epoch": 1.67,
|
2032 |
+
"learning_rate": 2.5021595779756018e-05,
|
2033 |
+
"loss": 2.1354,
|
2034 |
+
"step": 101500
|
2035 |
+
},
|
2036 |
+
{
|
2037 |
+
"epoch": 1.68,
|
2038 |
+
"learning_rate": 2.4996950214309264e-05,
|
2039 |
+
"loss": 2.1229,
|
2040 |
+
"step": 102000
|
2041 |
+
},
|
2042 |
+
{
|
2043 |
+
"epoch": 1.68,
|
2044 |
+
"eval_loss": 2.1560218334198,
|
2045 |
+
"eval_runtime": 1690.1223,
|
2046 |
+
"eval_samples_per_second": 23.667,
|
2047 |
+
"eval_steps_per_second": 23.667,
|
2048 |
+
"step": 102000
|
2049 |
+
},
|
2050 |
+
{
|
2051 |
+
"epoch": 1.69,
|
2052 |
+
"learning_rate": 2.4972304648862514e-05,
|
2053 |
+
"loss": 2.1299,
|
2054 |
+
"step": 102500
|
2055 |
+
},
|
2056 |
+
{
|
2057 |
+
"epoch": 1.7,
|
2058 |
+
"learning_rate": 2.494765908341576e-05,
|
2059 |
+
"loss": 2.1263,
|
2060 |
+
"step": 103000
|
2061 |
+
},
|
2062 |
+
{
|
2063 |
+
"epoch": 1.7,
|
2064 |
+
"eval_loss": 2.1626064777374268,
|
2065 |
+
"eval_runtime": 1689.2429,
|
2066 |
+
"eval_samples_per_second": 23.679,
|
2067 |
+
"eval_steps_per_second": 23.679,
|
2068 |
+
"step": 103000
|
2069 |
+
},
|
2070 |
+
{
|
2071 |
+
"epoch": 1.7,
|
2072 |
+
"learning_rate": 2.4923013517969006e-05,
|
2073 |
+
"loss": 2.1201,
|
2074 |
+
"step": 103500
|
2075 |
+
},
|
2076 |
+
{
|
2077 |
+
"epoch": 1.71,
|
2078 |
+
"learning_rate": 2.4898367952522253e-05,
|
2079 |
+
"loss": 2.1187,
|
2080 |
+
"step": 104000
|
2081 |
+
},
|
2082 |
+
{
|
2083 |
+
"epoch": 1.71,
|
2084 |
+
"eval_loss": 2.1653449535369873,
|
2085 |
+
"eval_runtime": 1718.044,
|
2086 |
+
"eval_samples_per_second": 23.282,
|
2087 |
+
"eval_steps_per_second": 23.282,
|
2088 |
+
"step": 104000
|
2089 |
+
},
|
2090 |
+
{
|
2091 |
+
"epoch": 1.72,
|
2092 |
+
"learning_rate": 2.4873722387075502e-05,
|
2093 |
+
"loss": 2.1355,
|
2094 |
+
"step": 104500
|
2095 |
+
},
|
2096 |
+
{
|
2097 |
+
"epoch": 1.73,
|
2098 |
+
"learning_rate": 2.484907682162875e-05,
|
2099 |
+
"loss": 2.1306,
|
2100 |
+
"step": 105000
|
2101 |
+
},
|
2102 |
+
{
|
2103 |
+
"epoch": 1.73,
|
2104 |
+
"eval_loss": 2.161628007888794,
|
2105 |
+
"eval_runtime": 1732.448,
|
2106 |
+
"eval_samples_per_second": 23.089,
|
2107 |
+
"eval_steps_per_second": 23.089,
|
2108 |
+
"step": 105000
|
2109 |
+
},
|
2110 |
+
{
|
2111 |
+
"epoch": 1.74,
|
2112 |
+
"learning_rate": 2.4824431256182002e-05,
|
2113 |
+
"loss": 2.1256,
|
2114 |
+
"step": 105500
|
2115 |
+
},
|
2116 |
+
{
|
2117 |
+
"epoch": 1.75,
|
2118 |
+
"learning_rate": 2.4799785690735248e-05,
|
2119 |
+
"loss": 2.1253,
|
2120 |
+
"step": 106000
|
2121 |
+
},
|
2122 |
+
{
|
2123 |
+
"epoch": 1.75,
|
2124 |
+
"eval_loss": 2.162022113800049,
|
2125 |
+
"eval_runtime": 1750.94,
|
2126 |
+
"eval_samples_per_second": 22.845,
|
2127 |
+
"eval_steps_per_second": 22.845,
|
2128 |
+
"step": 106000
|
2129 |
+
},
|
2130 |
+
{
|
2131 |
+
"epoch": 1.75,
|
2132 |
+
"learning_rate": 2.4775140125288494e-05,
|
2133 |
+
"loss": 2.1164,
|
2134 |
+
"step": 106500
|
2135 |
+
},
|
2136 |
+
{
|
2137 |
+
"epoch": 1.76,
|
2138 |
+
"learning_rate": 2.475049455984174e-05,
|
2139 |
+
"loss": 2.1124,
|
2140 |
+
"step": 107000
|
2141 |
+
},
|
2142 |
+
{
|
2143 |
+
"epoch": 1.76,
|
2144 |
+
"eval_loss": 2.1629226207733154,
|
2145 |
+
"eval_runtime": 1747.2545,
|
2146 |
+
"eval_samples_per_second": 22.893,
|
2147 |
+
"eval_steps_per_second": 22.893,
|
2148 |
+
"step": 107000
|
2149 |
+
},
|
2150 |
+
{
|
2151 |
+
"epoch": 1.77,
|
2152 |
+
"learning_rate": 2.472584899439499e-05,
|
2153 |
+
"loss": 2.112,
|
2154 |
+
"step": 107500
|
2155 |
+
},
|
2156 |
+
{
|
2157 |
+
"epoch": 1.78,
|
2158 |
+
"learning_rate": 2.4701203428948237e-05,
|
2159 |
+
"loss": 2.1165,
|
2160 |
+
"step": 108000
|
2161 |
+
},
|
2162 |
+
{
|
2163 |
+
"epoch": 1.78,
|
2164 |
+
"eval_loss": 2.162862777709961,
|
2165 |
+
"eval_runtime": 1722.8861,
|
2166 |
+
"eval_samples_per_second": 23.217,
|
2167 |
+
"eval_steps_per_second": 23.217,
|
2168 |
+
"step": 108000
|
2169 |
+
},
|
2170 |
+
{
|
2171 |
+
"epoch": 1.79,
|
2172 |
+
"learning_rate": 2.4676557863501483e-05,
|
2173 |
+
"loss": 2.1258,
|
2174 |
+
"step": 108500
|
2175 |
+
},
|
2176 |
+
{
|
2177 |
+
"epoch": 1.8,
|
2178 |
+
"learning_rate": 2.4651912298054732e-05,
|
2179 |
+
"loss": 2.1283,
|
2180 |
+
"step": 109000
|
2181 |
+
},
|
2182 |
+
{
|
2183 |
+
"epoch": 1.8,
|
2184 |
+
"eval_loss": 2.1554527282714844,
|
2185 |
+
"eval_runtime": 1701.7426,
|
2186 |
+
"eval_samples_per_second": 23.505,
|
2187 |
+
"eval_steps_per_second": 23.505,
|
2188 |
+
"step": 109000
|
2189 |
+
},
|
2190 |
+
{
|
2191 |
+
"epoch": 1.8,
|
2192 |
+
"learning_rate": 2.462726673260798e-05,
|
2193 |
+
"loss": 2.1258,
|
2194 |
+
"step": 109500
|
2195 |
+
},
|
2196 |
+
{
|
2197 |
+
"epoch": 1.81,
|
2198 |
+
"learning_rate": 2.4602621167161225e-05,
|
2199 |
+
"loss": 2.1099,
|
2200 |
+
"step": 110000
|
2201 |
+
},
|
2202 |
+
{
|
2203 |
+
"epoch": 1.81,
|
2204 |
+
"eval_loss": 2.164123296737671,
|
2205 |
+
"eval_runtime": 1700.6722,
|
2206 |
+
"eval_samples_per_second": 23.52,
|
2207 |
+
"eval_steps_per_second": 23.52,
|
2208 |
+
"step": 110000
|
2209 |
+
},
|
2210 |
+
{
|
2211 |
+
"epoch": 1.82,
|
2212 |
+
"learning_rate": 2.457797560171447e-05,
|
2213 |
+
"loss": 2.1196,
|
2214 |
+
"step": 110500
|
2215 |
+
},
|
2216 |
+
{
|
2217 |
+
"epoch": 1.83,
|
2218 |
+
"learning_rate": 2.455333003626772e-05,
|
2219 |
+
"loss": 2.1165,
|
2220 |
+
"step": 111000
|
2221 |
+
},
|
2222 |
+
{
|
2223 |
+
"epoch": 1.83,
|
2224 |
+
"eval_loss": 2.1557888984680176,
|
2225 |
+
"eval_runtime": 1698.5145,
|
2226 |
+
"eval_samples_per_second": 23.55,
|
2227 |
+
"eval_steps_per_second": 23.55,
|
2228 |
+
"step": 111000
|
2229 |
+
},
|
2230 |
+
{
|
2231 |
+
"epoch": 1.84,
|
2232 |
+
"learning_rate": 2.4528684470820967e-05,
|
2233 |
+
"loss": 2.1125,
|
2234 |
+
"step": 111500
|
2235 |
+
},
|
2236 |
+
{
|
2237 |
+
"epoch": 1.84,
|
2238 |
+
"learning_rate": 2.450403890537422e-05,
|
2239 |
+
"loss": 2.1103,
|
2240 |
+
"step": 112000
|
2241 |
+
},
|
2242 |
+
{
|
2243 |
+
"epoch": 1.84,
|
2244 |
+
"eval_loss": 2.1602911949157715,
|
2245 |
+
"eval_runtime": 1693.809,
|
2246 |
+
"eval_samples_per_second": 23.615,
|
2247 |
+
"eval_steps_per_second": 23.615,
|
2248 |
+
"step": 112000
|
2249 |
+
},
|
2250 |
+
{
|
2251 |
+
"epoch": 1.85,
|
2252 |
+
"learning_rate": 2.4479393339927467e-05,
|
2253 |
+
"loss": 2.1217,
|
2254 |
+
"step": 112500
|
2255 |
+
},
|
2256 |
+
{
|
2257 |
+
"epoch": 1.86,
|
2258 |
+
"learning_rate": 2.4454747774480713e-05,
|
2259 |
+
"loss": 2.1136,
|
2260 |
+
"step": 113000
|
2261 |
+
},
|
2262 |
+
{
|
2263 |
+
"epoch": 1.86,
|
2264 |
+
"eval_loss": 2.159860134124756,
|
2265 |
+
"eval_runtime": 1688.1816,
|
2266 |
+
"eval_samples_per_second": 23.694,
|
2267 |
+
"eval_steps_per_second": 23.694,
|
2268 |
+
"step": 113000
|
2269 |
+
},
|
2270 |
+
{
|
2271 |
+
"epoch": 1.87,
|
2272 |
+
"learning_rate": 2.443010220903396e-05,
|
2273 |
+
"loss": 2.1218,
|
2274 |
+
"step": 113500
|
2275 |
+
},
|
2276 |
+
{
|
2277 |
+
"epoch": 1.88,
|
2278 |
+
"learning_rate": 2.440545664358721e-05,
|
2279 |
+
"loss": 2.101,
|
2280 |
+
"step": 114000
|
2281 |
+
},
|
2282 |
+
{
|
2283 |
+
"epoch": 1.88,
|
2284 |
+
"eval_loss": 2.161252498626709,
|
2285 |
+
"eval_runtime": 1707.6279,
|
2286 |
+
"eval_samples_per_second": 23.424,
|
2287 |
+
"eval_steps_per_second": 23.424,
|
2288 |
+
"step": 114000
|
2289 |
+
},
|
2290 |
+
{
|
2291 |
+
"epoch": 1.89,
|
2292 |
+
"learning_rate": 2.4380811078140455e-05,
|
2293 |
+
"loss": 2.0981,
|
2294 |
+
"step": 114500
|
2295 |
+
},
|
2296 |
+
{
|
2297 |
+
"epoch": 1.89,
|
2298 |
+
"learning_rate": 2.4356165512693705e-05,
|
2299 |
+
"loss": 2.1231,
|
2300 |
+
"step": 115000
|
2301 |
+
},
|
2302 |
+
{
|
2303 |
+
"epoch": 1.89,
|
2304 |
+
"eval_loss": 2.1558616161346436,
|
2305 |
+
"eval_runtime": 1696.8618,
|
2306 |
+
"eval_samples_per_second": 23.573,
|
2307 |
+
"eval_steps_per_second": 23.573,
|
2308 |
+
"step": 115000
|
2309 |
+
},
|
2310 |
+
{
|
2311 |
+
"epoch": 1.9,
|
2312 |
+
"learning_rate": 2.433151994724695e-05,
|
2313 |
+
"loss": 2.0957,
|
2314 |
+
"step": 115500
|
2315 |
+
},
|
2316 |
+
{
|
2317 |
+
"epoch": 1.91,
|
2318 |
+
"learning_rate": 2.4306874381800197e-05,
|
2319 |
+
"loss": 2.1368,
|
2320 |
+
"step": 116000
|
2321 |
+
},
|
2322 |
+
{
|
2323 |
+
"epoch": 1.91,
|
2324 |
+
"eval_loss": 2.154006242752075,
|
2325 |
+
"eval_runtime": 1697.1277,
|
2326 |
+
"eval_samples_per_second": 23.569,
|
2327 |
+
"eval_steps_per_second": 23.569,
|
2328 |
+
"step": 116000
|
2329 |
+
},
|
2330 |
+
{
|
2331 |
+
"epoch": 1.92,
|
2332 |
+
"learning_rate": 2.4282228816353444e-05,
|
2333 |
+
"loss": 2.1311,
|
2334 |
+
"step": 116500
|
2335 |
+
},
|
2336 |
+
{
|
2337 |
+
"epoch": 1.93,
|
2338 |
+
"learning_rate": 2.4257583250906693e-05,
|
2339 |
+
"loss": 2.1325,
|
2340 |
+
"step": 117000
|
2341 |
+
},
|
2342 |
+
{
|
2343 |
+
"epoch": 1.93,
|
2344 |
+
"eval_loss": 2.1554782390594482,
|
2345 |
+
"eval_runtime": 1697.9442,
|
2346 |
+
"eval_samples_per_second": 23.558,
|
2347 |
+
"eval_steps_per_second": 23.558,
|
2348 |
+
"step": 117000
|
2349 |
+
},
|
2350 |
+
{
|
2351 |
+
"epoch": 1.94,
|
2352 |
+
"learning_rate": 2.423293768545994e-05,
|
2353 |
+
"loss": 2.12,
|
2354 |
+
"step": 117500
|
2355 |
+
},
|
2356 |
+
{
|
2357 |
+
"epoch": 1.94,
|
2358 |
+
"learning_rate": 2.420829212001319e-05,
|
2359 |
+
"loss": 2.1017,
|
2360 |
+
"step": 118000
|
2361 |
+
},
|
2362 |
+
{
|
2363 |
+
"epoch": 1.94,
|
2364 |
+
"eval_loss": 2.1558518409729004,
|
2365 |
+
"eval_runtime": 1697.0901,
|
2366 |
+
"eval_samples_per_second": 23.57,
|
2367 |
+
"eval_steps_per_second": 23.57,
|
2368 |
+
"step": 118000
|
2369 |
+
},
|
2370 |
+
{
|
2371 |
+
"epoch": 1.95,
|
2372 |
+
"learning_rate": 2.418364655456644e-05,
|
2373 |
+
"loss": 2.1148,
|
2374 |
+
"step": 118500
|
2375 |
+
},
|
2376 |
+
{
|
2377 |
+
"epoch": 1.96,
|
2378 |
+
"learning_rate": 2.4159000989119685e-05,
|
2379 |
+
"loss": 2.1143,
|
2380 |
+
"step": 119000
|
2381 |
+
},
|
2382 |
+
{
|
2383 |
+
"epoch": 1.96,
|
2384 |
+
"eval_loss": 2.160183906555176,
|
2385 |
+
"eval_runtime": 1697.0904,
|
2386 |
+
"eval_samples_per_second": 23.57,
|
2387 |
+
"eval_steps_per_second": 23.57,
|
2388 |
+
"step": 119000
|
2389 |
+
},
|
2390 |
+
{
|
2391 |
+
"epoch": 1.97,
|
2392 |
+
"learning_rate": 2.413435542367293e-05,
|
2393 |
+
"loss": 2.1132,
|
2394 |
+
"step": 119500
|
2395 |
+
},
|
2396 |
+
{
|
2397 |
+
"epoch": 1.98,
|
2398 |
+
"learning_rate": 2.4109709858226178e-05,
|
2399 |
+
"loss": 2.0962,
|
2400 |
+
"step": 120000
|
2401 |
+
},
|
2402 |
+
{
|
2403 |
+
"epoch": 1.98,
|
2404 |
+
"eval_loss": 2.155602216720581,
|
2405 |
+
"eval_runtime": 1696.9463,
|
2406 |
+
"eval_samples_per_second": 23.572,
|
2407 |
+
"eval_steps_per_second": 23.572,
|
2408 |
+
"step": 120000
|
2409 |
+
},
|
2410 |
+
{
|
2411 |
+
"epoch": 1.98,
|
2412 |
+
"learning_rate": 2.4085064292779428e-05,
|
2413 |
+
"loss": 2.1274,
|
2414 |
+
"step": 120500
|
2415 |
+
},
|
2416 |
+
{
|
2417 |
+
"epoch": 1.99,
|
2418 |
+
"learning_rate": 2.4060418727332674e-05,
|
2419 |
+
"loss": 2.1103,
|
2420 |
+
"step": 121000
|
2421 |
+
},
|
2422 |
+
{
|
2423 |
+
"epoch": 1.99,
|
2424 |
+
"eval_loss": 2.1536872386932373,
|
2425 |
+
"eval_runtime": 1696.9858,
|
2426 |
+
"eval_samples_per_second": 23.571,
|
2427 |
+
"eval_steps_per_second": 23.571,
|
2428 |
+
"step": 121000
|
2429 |
+
},
|
2430 |
+
{
|
2431 |
+
"epoch": 2.0,
|
2432 |
+
"learning_rate": 2.4035773161885923e-05,
|
2433 |
+
"loss": 2.1002,
|
2434 |
+
"step": 121500
|
2435 |
+
},
|
2436 |
+
{
|
2437 |
+
"epoch": 2.01,
|
2438 |
+
"learning_rate": 2.401112759643917e-05,
|
2439 |
+
"loss": 2.0708,
|
2440 |
+
"step": 122000
|
2441 |
+
},
|
2442 |
+
{
|
2443 |
+
"epoch": 2.01,
|
2444 |
+
"eval_loss": 2.1589629650115967,
|
2445 |
+
"eval_runtime": 1700.1693,
|
2446 |
+
"eval_samples_per_second": 23.527,
|
2447 |
+
"eval_steps_per_second": 23.527,
|
2448 |
+
"step": 122000
|
2449 |
+
},
|
2450 |
+
{
|
2451 |
+
"epoch": 2.02,
|
2452 |
+
"learning_rate": 2.3986482030992416e-05,
|
2453 |
+
"loss": 2.0797,
|
2454 |
+
"step": 122500
|
2455 |
+
},
|
2456 |
+
{
|
2457 |
+
"epoch": 2.03,
|
2458 |
+
"learning_rate": 2.3961836465545662e-05,
|
2459 |
+
"loss": 2.072,
|
2460 |
+
"step": 123000
|
2461 |
+
},
|
2462 |
+
{
|
2463 |
+
"epoch": 2.03,
|
2464 |
+
"eval_loss": 2.157003402709961,
|
2465 |
+
"eval_runtime": 1683.9269,
|
2466 |
+
"eval_samples_per_second": 23.754,
|
2467 |
+
"eval_steps_per_second": 23.754,
|
2468 |
+
"step": 123000
|
2469 |
+
},
|
2470 |
+
{
|
2471 |
+
"epoch": 2.03,
|
2472 |
+
"learning_rate": 2.3937190900098912e-05,
|
2473 |
+
"loss": 2.1007,
|
2474 |
+
"step": 123500
|
2475 |
+
},
|
2476 |
+
{
|
2477 |
+
"epoch": 2.04,
|
2478 |
+
"learning_rate": 2.3912545334652158e-05,
|
2479 |
+
"loss": 2.0734,
|
2480 |
+
"step": 124000
|
2481 |
+
},
|
2482 |
+
{
|
2483 |
+
"epoch": 2.04,
|
2484 |
+
"eval_loss": 2.152344226837158,
|
2485 |
+
"eval_runtime": 1685.7847,
|
2486 |
+
"eval_samples_per_second": 23.728,
|
2487 |
+
"eval_steps_per_second": 23.728,
|
2488 |
+
"step": 124000
|
2489 |
+
},
|
2490 |
+
{
|
2491 |
+
"epoch": 2.05,
|
2492 |
+
"learning_rate": 2.3887899769205408e-05,
|
2493 |
+
"loss": 2.0679,
|
2494 |
+
"step": 124500
|
2495 |
+
},
|
2496 |
+
{
|
2497 |
+
"epoch": 2.06,
|
2498 |
+
"learning_rate": 2.3863254203758658e-05,
|
2499 |
+
"loss": 2.0927,
|
2500 |
+
"step": 125000
|
2501 |
+
},
|
2502 |
+
{
|
2503 |
+
"epoch": 2.06,
|
2504 |
+
"eval_loss": 2.1572160720825195,
|
2505 |
+
"eval_runtime": 1687.9536,
|
2506 |
+
"eval_samples_per_second": 23.697,
|
2507 |
+
"eval_steps_per_second": 23.697,
|
2508 |
+
"step": 125000
|
2509 |
+
},
|
2510 |
+
{
|
2511 |
+
"epoch": 2.07,
|
2512 |
+
"learning_rate": 2.3838608638311904e-05,
|
2513 |
+
"loss": 2.0667,
|
2514 |
+
"step": 125500
|
2515 |
+
},
|
2516 |
+
{
|
2517 |
+
"epoch": 2.08,
|
2518 |
+
"learning_rate": 2.381396307286515e-05,
|
2519 |
+
"loss": 2.0767,
|
2520 |
+
"step": 126000
|
2521 |
+
},
|
2522 |
+
{
|
2523 |
+
"epoch": 2.08,
|
2524 |
+
"eval_loss": 2.1578407287597656,
|
2525 |
+
"eval_runtime": 1683.6847,
|
2526 |
+
"eval_samples_per_second": 23.757,
|
2527 |
+
"eval_steps_per_second": 23.757,
|
2528 |
+
"step": 126000
|
2529 |
+
},
|
2530 |
+
{
|
2531 |
+
"epoch": 2.08,
|
2532 |
+
"learning_rate": 2.3789317507418396e-05,
|
2533 |
+
"loss": 2.0856,
|
2534 |
+
"step": 126500
|
2535 |
+
},
|
2536 |
+
{
|
2537 |
+
"epoch": 2.09,
|
2538 |
+
"learning_rate": 2.3764671941971646e-05,
|
2539 |
+
"loss": 2.087,
|
2540 |
+
"step": 127000
|
2541 |
+
},
|
2542 |
+
{
|
2543 |
+
"epoch": 2.09,
|
2544 |
+
"eval_loss": 2.1585898399353027,
|
2545 |
+
"eval_runtime": 1707.9519,
|
2546 |
+
"eval_samples_per_second": 23.42,
|
2547 |
+
"eval_steps_per_second": 23.42,
|
2548 |
+
"step": 127000
|
2549 |
+
},
|
2550 |
+
{
|
2551 |
+
"epoch": 2.1,
|
2552 |
+
"learning_rate": 2.3740026376524892e-05,
|
2553 |
+
"loss": 2.0583,
|
2554 |
+
"step": 127500
|
2555 |
+
},
|
2556 |
+
{
|
2557 |
+
"epoch": 2.11,
|
2558 |
+
"learning_rate": 2.3715380811078142e-05,
|
2559 |
+
"loss": 2.0817,
|
2560 |
+
"step": 128000
|
2561 |
+
},
|
2562 |
+
{
|
2563 |
+
"epoch": 2.11,
|
2564 |
+
"eval_loss": 2.1547696590423584,
|
2565 |
+
"eval_runtime": 1701.5775,
|
2566 |
+
"eval_samples_per_second": 23.508,
|
2567 |
+
"eval_steps_per_second": 23.508,
|
2568 |
+
"step": 128000
|
2569 |
+
},
|
2570 |
+
{
|
2571 |
+
"epoch": 2.12,
|
2572 |
+
"learning_rate": 2.369073524563139e-05,
|
2573 |
+
"loss": 2.091,
|
2574 |
+
"step": 128500
|
2575 |
+
},
|
2576 |
+
{
|
2577 |
+
"epoch": 2.12,
|
2578 |
+
"learning_rate": 2.3666089680184635e-05,
|
2579 |
+
"loss": 2.0842,
|
2580 |
+
"step": 129000
|
2581 |
+
},
|
2582 |
+
{
|
2583 |
+
"epoch": 2.12,
|
2584 |
+
"eval_loss": 2.159339427947998,
|
2585 |
+
"eval_runtime": 1702.707,
|
2586 |
+
"eval_samples_per_second": 23.492,
|
2587 |
+
"eval_steps_per_second": 23.492,
|
2588 |
+
"step": 129000
|
2589 |
+
},
|
2590 |
+
{
|
2591 |
+
"epoch": 2.13,
|
2592 |
+
"learning_rate": 2.364144411473788e-05,
|
2593 |
+
"loss": 2.0842,
|
2594 |
+
"step": 129500
|
2595 |
+
},
|
2596 |
+
{
|
2597 |
+
"epoch": 2.14,
|
2598 |
+
"learning_rate": 2.361679854929113e-05,
|
2599 |
+
"loss": 2.0801,
|
2600 |
+
"step": 130000
|
2601 |
+
},
|
2602 |
+
{
|
2603 |
+
"epoch": 2.14,
|
2604 |
+
"eval_loss": 2.1500117778778076,
|
2605 |
+
"eval_runtime": 1705.3521,
|
2606 |
+
"eval_samples_per_second": 23.456,
|
2607 |
+
"eval_steps_per_second": 23.456,
|
2608 |
+
"step": 130000
|
2609 |
+
},
|
2610 |
+
{
|
2611 |
+
"epoch": 2.15,
|
2612 |
+
"learning_rate": 2.3592152983844377e-05,
|
2613 |
+
"loss": 2.0596,
|
2614 |
+
"step": 130500
|
2615 |
+
},
|
2616 |
+
{
|
2617 |
+
"epoch": 2.16,
|
2618 |
+
"learning_rate": 2.356750741839763e-05,
|
2619 |
+
"loss": 2.0757,
|
2620 |
+
"step": 131000
|
2621 |
+
},
|
2622 |
+
{
|
2623 |
+
"epoch": 2.16,
|
2624 |
+
"eval_loss": 2.1629602909088135,
|
2625 |
+
"eval_runtime": 1695.1748,
|
2626 |
+
"eval_samples_per_second": 23.596,
|
2627 |
+
"eval_steps_per_second": 23.596,
|
2628 |
+
"step": 131000
|
2629 |
+
},
|
2630 |
+
{
|
2631 |
+
"epoch": 2.17,
|
2632 |
+
"learning_rate": 2.3542861852950876e-05,
|
2633 |
+
"loss": 2.0893,
|
2634 |
+
"step": 131500
|
2635 |
+
},
|
2636 |
+
{
|
2637 |
+
"epoch": 2.17,
|
2638 |
+
"learning_rate": 2.3518216287504123e-05,
|
2639 |
+
"loss": 2.0878,
|
2640 |
+
"step": 132000
|
2641 |
+
},
|
2642 |
+
{
|
2643 |
+
"epoch": 2.17,
|
2644 |
+
"eval_loss": 2.151366710662842,
|
2645 |
+
"eval_runtime": 1691.2631,
|
2646 |
+
"eval_samples_per_second": 23.651,
|
2647 |
+
"eval_steps_per_second": 23.651,
|
2648 |
+
"step": 132000
|
2649 |
+
},
|
2650 |
+
{
|
2651 |
+
"epoch": 2.18,
|
2652 |
+
"learning_rate": 2.349357072205737e-05,
|
2653 |
+
"loss": 2.0882,
|
2654 |
+
"step": 132500
|
2655 |
+
},
|
2656 |
+
{
|
2657 |
+
"epoch": 2.19,
|
2658 |
+
"learning_rate": 2.346892515661062e-05,
|
2659 |
+
"loss": 2.0758,
|
2660 |
+
"step": 133000
|
2661 |
+
},
|
2662 |
+
{
|
2663 |
+
"epoch": 2.19,
|
2664 |
+
"eval_loss": 2.1577887535095215,
|
2665 |
+
"eval_runtime": 1700.0595,
|
2666 |
+
"eval_samples_per_second": 23.529,
|
2667 |
+
"eval_steps_per_second": 23.529,
|
2668 |
+
"step": 133000
|
2669 |
+
},
|
2670 |
+
{
|
2671 |
+
"epoch": 2.2,
|
2672 |
+
"learning_rate": 2.3444279591163865e-05,
|
2673 |
+
"loss": 2.0691,
|
2674 |
+
"step": 133500
|
2675 |
+
},
|
2676 |
+
{
|
2677 |
+
"epoch": 2.21,
|
2678 |
+
"learning_rate": 2.341963402571711e-05,
|
2679 |
+
"loss": 2.0816,
|
2680 |
+
"step": 134000
|
2681 |
+
},
|
2682 |
+
{
|
2683 |
+
"epoch": 2.21,
|
2684 |
+
"eval_loss": 2.1542584896087646,
|
2685 |
+
"eval_runtime": 1689.3566,
|
2686 |
+
"eval_samples_per_second": 23.678,
|
2687 |
+
"eval_steps_per_second": 23.678,
|
2688 |
+
"step": 134000
|
2689 |
+
},
|
2690 |
+
{
|
2691 |
+
"epoch": 2.22,
|
2692 |
+
"learning_rate": 2.339498846027036e-05,
|
2693 |
+
"loss": 2.0819,
|
2694 |
+
"step": 134500
|
2695 |
+
},
|
2696 |
+
{
|
2697 |
+
"epoch": 2.22,
|
2698 |
+
"learning_rate": 2.3370342894823607e-05,
|
2699 |
+
"loss": 2.0853,
|
2700 |
+
"step": 135000
|
2701 |
+
},
|
2702 |
+
{
|
2703 |
+
"epoch": 2.22,
|
2704 |
+
"eval_loss": 2.152047634124756,
|
2705 |
+
"eval_runtime": 1696.0173,
|
2706 |
+
"eval_samples_per_second": 23.585,
|
2707 |
+
"eval_steps_per_second": 23.585,
|
2708 |
+
"step": 135000
|
2709 |
+
},
|
2710 |
+
{
|
2711 |
+
"epoch": 2.23,
|
2712 |
+
"learning_rate": 2.3345697329376853e-05,
|
2713 |
+
"loss": 2.0638,
|
2714 |
+
"step": 135500
|
2715 |
+
},
|
2716 |
+
{
|
2717 |
+
"epoch": 2.24,
|
2718 |
+
"learning_rate": 2.33210517639301e-05,
|
2719 |
+
"loss": 2.0759,
|
2720 |
+
"step": 136000
|
2721 |
+
},
|
2722 |
+
{
|
2723 |
+
"epoch": 2.24,
|
2724 |
+
"eval_loss": 2.1569483280181885,
|
2725 |
+
"eval_runtime": 1694.0839,
|
2726 |
+
"eval_samples_per_second": 23.612,
|
2727 |
+
"eval_steps_per_second": 23.612,
|
2728 |
+
"step": 136000
|
2729 |
+
},
|
2730 |
+
{
|
2731 |
+
"epoch": 2.25,
|
2732 |
+
"learning_rate": 2.329640619848335e-05,
|
2733 |
+
"loss": 2.089,
|
2734 |
+
"step": 136500
|
2735 |
+
},
|
2736 |
+
{
|
2737 |
+
"epoch": 2.26,
|
2738 |
+
"learning_rate": 2.32717606330366e-05,
|
2739 |
+
"loss": 2.0847,
|
2740 |
+
"step": 137000
|
2741 |
+
},
|
2742 |
+
{
|
2743 |
+
"epoch": 2.26,
|
2744 |
+
"eval_loss": 2.150604724884033,
|
2745 |
+
"eval_runtime": 1694.889,
|
2746 |
+
"eval_samples_per_second": 23.6,
|
2747 |
+
"eval_steps_per_second": 23.6,
|
2748 |
+
"step": 137000
|
2749 |
+
},
|
2750 |
+
{
|
2751 |
+
"epoch": 2.26,
|
2752 |
+
"learning_rate": 2.324711506758985e-05,
|
2753 |
+
"loss": 2.072,
|
2754 |
+
"step": 137500
|
2755 |
+
},
|
2756 |
+
{
|
2757 |
+
"epoch": 2.27,
|
2758 |
+
"learning_rate": 2.3222469502143095e-05,
|
2759 |
+
"loss": 2.0684,
|
2760 |
+
"step": 138000
|
2761 |
+
},
|
2762 |
+
{
|
2763 |
+
"epoch": 2.27,
|
2764 |
+
"eval_loss": 2.152568817138672,
|
2765 |
+
"eval_runtime": 1698.9537,
|
2766 |
+
"eval_samples_per_second": 23.544,
|
2767 |
+
"eval_steps_per_second": 23.544,
|
2768 |
+
"step": 138000
|
2769 |
+
},
|
2770 |
+
{
|
2771 |
+
"epoch": 2.28,
|
2772 |
+
"learning_rate": 2.319782393669634e-05,
|
2773 |
+
"loss": 2.0769,
|
2774 |
+
"step": 138500
|
2775 |
+
},
|
2776 |
+
{
|
2777 |
+
"epoch": 2.29,
|
2778 |
+
"learning_rate": 2.3173178371249587e-05,
|
2779 |
+
"loss": 2.0776,
|
2780 |
+
"step": 139000
|
2781 |
+
},
|
2782 |
+
{
|
2783 |
+
"epoch": 2.29,
|
2784 |
+
"eval_loss": 2.1548068523406982,
|
2785 |
+
"eval_runtime": 1697.8718,
|
2786 |
+
"eval_samples_per_second": 23.559,
|
2787 |
+
"eval_steps_per_second": 23.559,
|
2788 |
+
"step": 139000
|
2789 |
+
},
|
2790 |
+
{
|
2791 |
+
"epoch": 2.3,
|
2792 |
+
"learning_rate": 2.3148532805802837e-05,
|
2793 |
+
"loss": 2.0947,
|
2794 |
+
"step": 139500
|
2795 |
+
},
|
2796 |
+
{
|
2797 |
+
"epoch": 2.31,
|
2798 |
+
"learning_rate": 2.3123887240356083e-05,
|
2799 |
+
"loss": 2.0804,
|
2800 |
+
"step": 140000
|
2801 |
+
},
|
2802 |
+
{
|
2803 |
+
"epoch": 2.31,
|
2804 |
+
"eval_loss": 2.1525418758392334,
|
2805 |
+
"eval_runtime": 1696.6504,
|
2806 |
+
"eval_samples_per_second": 23.576,
|
2807 |
+
"eval_steps_per_second": 23.576,
|
2808 |
+
"step": 140000
|
2809 |
+
},
|
2810 |
+
{
|
2811 |
+
"epoch": 2.31,
|
2812 |
+
"learning_rate": 2.309924167490933e-05,
|
2813 |
+
"loss": 2.0667,
|
2814 |
+
"step": 140500
|
2815 |
+
},
|
2816 |
+
{
|
2817 |
+
"epoch": 2.32,
|
2818 |
+
"learning_rate": 2.307459610946258e-05,
|
2819 |
+
"loss": 2.0724,
|
2820 |
+
"step": 141000
|
2821 |
+
},
|
2822 |
+
{
|
2823 |
+
"epoch": 2.32,
|
2824 |
+
"eval_loss": 2.149521589279175,
|
2825 |
+
"eval_runtime": 1698.3371,
|
2826 |
+
"eval_samples_per_second": 23.552,
|
2827 |
+
"eval_steps_per_second": 23.552,
|
2828 |
+
"step": 141000
|
2829 |
+
},
|
2830 |
+
{
|
2831 |
+
"epoch": 2.33,
|
2832 |
+
"learning_rate": 2.3049950544015826e-05,
|
2833 |
+
"loss": 2.0728,
|
2834 |
+
"step": 141500
|
2835 |
+
},
|
2836 |
+
{
|
2837 |
+
"epoch": 2.34,
|
2838 |
+
"learning_rate": 2.3025304978569072e-05,
|
2839 |
+
"loss": 2.0699,
|
2840 |
+
"step": 142000
|
2841 |
+
},
|
2842 |
+
{
|
2843 |
+
"epoch": 2.34,
|
2844 |
+
"eval_loss": 2.1547553539276123,
|
2845 |
+
"eval_runtime": 1693.508,
|
2846 |
+
"eval_samples_per_second": 23.62,
|
2847 |
+
"eval_steps_per_second": 23.62,
|
2848 |
+
"step": 142000
|
2849 |
+
},
|
2850 |
+
{
|
2851 |
+
"epoch": 2.35,
|
2852 |
+
"learning_rate": 2.3000659413122318e-05,
|
2853 |
+
"loss": 2.0787,
|
2854 |
+
"step": 142500
|
2855 |
+
},
|
2856 |
+
{
|
2857 |
+
"epoch": 2.36,
|
2858 |
+
"learning_rate": 2.2976013847675568e-05,
|
2859 |
+
"loss": 2.0786,
|
2860 |
+
"step": 143000
|
2861 |
+
},
|
2862 |
+
{
|
2863 |
+
"epoch": 2.36,
|
2864 |
+
"eval_loss": 2.1501739025115967,
|
2865 |
+
"eval_runtime": 1698.296,
|
2866 |
+
"eval_samples_per_second": 23.553,
|
2867 |
+
"eval_steps_per_second": 23.553,
|
2868 |
+
"step": 143000
|
2869 |
+
},
|
2870 |
+
{
|
2871 |
+
"epoch": 2.36,
|
2872 |
+
"learning_rate": 2.2951368282228818e-05,
|
2873 |
+
"loss": 2.0667,
|
2874 |
+
"step": 143500
|
2875 |
+
},
|
2876 |
+
{
|
2877 |
+
"epoch": 2.37,
|
2878 |
+
"learning_rate": 2.2926722716782067e-05,
|
2879 |
+
"loss": 2.078,
|
2880 |
+
"step": 144000
|
2881 |
+
},
|
2882 |
+
{
|
2883 |
+
"epoch": 2.37,
|
2884 |
+
"eval_loss": 2.1527764797210693,
|
2885 |
+
"eval_runtime": 1691.4717,
|
2886 |
+
"eval_samples_per_second": 23.648,
|
2887 |
+
"eval_steps_per_second": 23.648,
|
2888 |
+
"step": 144000
|
2889 |
+
},
|
2890 |
+
{
|
2891 |
+
"epoch": 2.38,
|
2892 |
+
"learning_rate": 2.2902077151335314e-05,
|
2893 |
+
"loss": 2.0774,
|
2894 |
+
"step": 144500
|
2895 |
+
},
|
2896 |
+
{
|
2897 |
+
"epoch": 2.39,
|
2898 |
+
"learning_rate": 2.287743158588856e-05,
|
2899 |
+
"loss": 2.082,
|
2900 |
+
"step": 145000
|
2901 |
+
},
|
2902 |
+
{
|
2903 |
+
"epoch": 2.39,
|
2904 |
+
"eval_loss": 2.1524477005004883,
|
2905 |
+
"eval_runtime": 1702.729,
|
2906 |
+
"eval_samples_per_second": 23.492,
|
2907 |
+
"eval_steps_per_second": 23.492,
|
2908 |
+
"step": 145000
|
2909 |
+
},
|
2910 |
+
{
|
2911 |
+
"epoch": 2.4,
|
2912 |
+
"learning_rate": 2.2852786020441806e-05,
|
2913 |
+
"loss": 2.0654,
|
2914 |
+
"step": 145500
|
2915 |
+
},
|
2916 |
+
{
|
2917 |
+
"epoch": 2.4,
|
2918 |
+
"learning_rate": 2.2828140454995056e-05,
|
2919 |
+
"loss": 2.0641,
|
2920 |
+
"step": 146000
|
2921 |
+
},
|
2922 |
+
{
|
2923 |
+
"epoch": 2.4,
|
2924 |
+
"eval_loss": 2.1543331146240234,
|
2925 |
+
"eval_runtime": 1702.4222,
|
2926 |
+
"eval_samples_per_second": 23.496,
|
2927 |
+
"eval_steps_per_second": 23.496,
|
2928 |
+
"step": 146000
|
2929 |
+
},
|
2930 |
+
{
|
2931 |
+
"epoch": 2.41,
|
2932 |
+
"learning_rate": 2.2803494889548302e-05,
|
2933 |
+
"loss": 2.0681,
|
2934 |
+
"step": 146500
|
2935 |
+
},
|
2936 |
+
{
|
2937 |
+
"epoch": 2.42,
|
2938 |
+
"learning_rate": 2.2778849324101552e-05,
|
2939 |
+
"loss": 2.0676,
|
2940 |
+
"step": 147000
|
2941 |
+
},
|
2942 |
+
{
|
2943 |
+
"epoch": 2.42,
|
2944 |
+
"eval_loss": 2.148048162460327,
|
2945 |
+
"eval_runtime": 1691.5175,
|
2946 |
+
"eval_samples_per_second": 23.647,
|
2947 |
+
"eval_steps_per_second": 23.647,
|
2948 |
+
"step": 147000
|
2949 |
+
},
|
2950 |
+
{
|
2951 |
+
"epoch": 2.43,
|
2952 |
+
"learning_rate": 2.2754203758654798e-05,
|
2953 |
+
"loss": 2.0742,
|
2954 |
+
"step": 147500
|
2955 |
+
},
|
2956 |
+
{
|
2957 |
+
"epoch": 2.44,
|
2958 |
+
"learning_rate": 2.2729558193208044e-05,
|
2959 |
+
"loss": 2.0605,
|
2960 |
+
"step": 148000
|
2961 |
+
},
|
2962 |
+
{
|
2963 |
+
"epoch": 2.44,
|
2964 |
+
"eval_loss": 2.155611991882324,
|
2965 |
+
"eval_runtime": 1692.7049,
|
2966 |
+
"eval_samples_per_second": 23.631,
|
2967 |
+
"eval_steps_per_second": 23.631,
|
2968 |
+
"step": 148000
|
2969 |
+
},
|
2970 |
+
{
|
2971 |
+
"epoch": 2.45,
|
2972 |
+
"learning_rate": 2.270491262776129e-05,
|
2973 |
+
"loss": 2.0729,
|
2974 |
+
"step": 148500
|
2975 |
+
},
|
2976 |
+
{
|
2977 |
+
"epoch": 2.45,
|
2978 |
+
"learning_rate": 2.268026706231454e-05,
|
2979 |
+
"loss": 2.0763,
|
2980 |
+
"step": 149000
|
2981 |
+
},
|
2982 |
+
{
|
2983 |
+
"epoch": 2.45,
|
2984 |
+
"eval_loss": 2.1516194343566895,
|
2985 |
+
"eval_runtime": 1695.0008,
|
2986 |
+
"eval_samples_per_second": 23.599,
|
2987 |
+
"eval_steps_per_second": 23.599,
|
2988 |
+
"step": 149000
|
2989 |
+
},
|
2990 |
+
{
|
2991 |
+
"epoch": 2.46,
|
2992 |
+
"learning_rate": 2.2655621496867787e-05,
|
2993 |
+
"loss": 2.0678,
|
2994 |
+
"step": 149500
|
2995 |
+
},
|
2996 |
+
{
|
2997 |
+
"epoch": 2.47,
|
2998 |
+
"learning_rate": 2.2630975931421036e-05,
|
2999 |
+
"loss": 2.066,
|
3000 |
+
"step": 150000
|
3001 |
+
},
|
3002 |
+
{
|
3003 |
+
"epoch": 2.47,
|
3004 |
+
"eval_loss": 2.1532933712005615,
|
3005 |
+
"eval_runtime": 1693.3099,
|
3006 |
+
"eval_samples_per_second": 23.622,
|
3007 |
+
"eval_steps_per_second": 23.622,
|
3008 |
+
"step": 150000
|
3009 |
+
},
|
3010 |
+
{
|
3011 |
+
"epoch": 2.48,
|
3012 |
+
"learning_rate": 2.2606330365974286e-05,
|
3013 |
+
"loss": 2.0719,
|
3014 |
+
"step": 150500
|
3015 |
+
},
|
3016 |
+
{
|
3017 |
+
"epoch": 2.49,
|
3018 |
+
"learning_rate": 2.2581684800527532e-05,
|
3019 |
+
"loss": 2.0803,
|
3020 |
+
"step": 151000
|
3021 |
+
},
|
3022 |
+
{
|
3023 |
+
"epoch": 2.49,
|
3024 |
+
"eval_loss": 2.150263786315918,
|
3025 |
+
"eval_runtime": 1689.1882,
|
3026 |
+
"eval_samples_per_second": 23.68,
|
3027 |
+
"eval_steps_per_second": 23.68,
|
3028 |
+
"step": 151000
|
3029 |
+
},
|
3030 |
+
{
|
3031 |
+
"epoch": 2.5,
|
3032 |
+
"learning_rate": 2.255703923508078e-05,
|
3033 |
+
"loss": 2.0737,
|
3034 |
+
"step": 151500
|
3035 |
+
},
|
3036 |
+
{
|
3037 |
+
"epoch": 2.5,
|
3038 |
+
"learning_rate": 2.2532393669634025e-05,
|
3039 |
+
"loss": 2.0862,
|
3040 |
+
"step": 152000
|
3041 |
+
},
|
3042 |
+
{
|
3043 |
+
"epoch": 2.5,
|
3044 |
+
"eval_loss": 2.1463823318481445,
|
3045 |
+
"eval_runtime": 1693.5654,
|
3046 |
+
"eval_samples_per_second": 23.619,
|
3047 |
+
"eval_steps_per_second": 23.619,
|
3048 |
+
"step": 152000
|
3049 |
+
},
|
3050 |
+
{
|
3051 |
+
"epoch": 2.51,
|
3052 |
+
"learning_rate": 2.2507748104187274e-05,
|
3053 |
+
"loss": 2.0769,
|
3054 |
+
"step": 152500
|
3055 |
+
},
|
3056 |
+
{
|
3057 |
+
"epoch": 2.52,
|
3058 |
+
"learning_rate": 2.248310253874052e-05,
|
3059 |
+
"loss": 2.075,
|
3060 |
+
"step": 153000
|
3061 |
+
},
|
3062 |
+
{
|
3063 |
+
"epoch": 2.52,
|
3064 |
+
"eval_loss": 2.1545963287353516,
|
3065 |
+
"eval_runtime": 1697.0015,
|
3066 |
+
"eval_samples_per_second": 23.571,
|
3067 |
+
"eval_steps_per_second": 23.571,
|
3068 |
+
"step": 153000
|
3069 |
+
},
|
3070 |
+
{
|
3071 |
+
"epoch": 2.53,
|
3072 |
+
"learning_rate": 2.245845697329377e-05,
|
3073 |
+
"loss": 2.0745,
|
3074 |
+
"step": 153500
|
3075 |
+
},
|
3076 |
+
{
|
3077 |
+
"epoch": 2.54,
|
3078 |
+
"learning_rate": 2.2433811407847017e-05,
|
3079 |
+
"loss": 2.0801,
|
3080 |
+
"step": 154000
|
3081 |
+
},
|
3082 |
+
{
|
3083 |
+
"epoch": 2.54,
|
3084 |
+
"eval_loss": 2.146970748901367,
|
3085 |
+
"eval_runtime": 1700.75,
|
3086 |
+
"eval_samples_per_second": 23.519,
|
3087 |
+
"eval_steps_per_second": 23.519,
|
3088 |
+
"step": 154000
|
3089 |
+
},
|
3090 |
+
{
|
3091 |
+
"epoch": 2.54,
|
3092 |
+
"learning_rate": 2.2409165842400263e-05,
|
3093 |
+
"loss": 2.0755,
|
3094 |
+
"step": 154500
|
3095 |
+
},
|
3096 |
+
{
|
3097 |
+
"epoch": 2.55,
|
3098 |
+
"learning_rate": 2.238452027695351e-05,
|
3099 |
+
"loss": 2.0714,
|
3100 |
+
"step": 155000
|
3101 |
+
},
|
3102 |
+
{
|
3103 |
+
"epoch": 2.55,
|
3104 |
+
"eval_loss": 2.1499733924865723,
|
3105 |
+
"eval_runtime": 1700.6102,
|
3106 |
+
"eval_samples_per_second": 23.521,
|
3107 |
+
"eval_steps_per_second": 23.521,
|
3108 |
+
"step": 155000
|
3109 |
+
},
|
3110 |
+
{
|
3111 |
+
"epoch": 2.56,
|
3112 |
+
"learning_rate": 2.2359874711506756e-05,
|
3113 |
+
"loss": 2.0688,
|
3114 |
+
"step": 155500
|
3115 |
+
},
|
3116 |
+
{
|
3117 |
+
"epoch": 2.57,
|
3118 |
+
"learning_rate": 2.233522914606001e-05,
|
3119 |
+
"loss": 2.0764,
|
3120 |
+
"step": 156000
|
3121 |
+
},
|
3122 |
+
{
|
3123 |
+
"epoch": 2.57,
|
3124 |
+
"eval_loss": 2.141591787338257,
|
3125 |
+
"eval_runtime": 1694.1493,
|
3126 |
+
"eval_samples_per_second": 23.611,
|
3127 |
+
"eval_steps_per_second": 23.611,
|
3128 |
+
"step": 156000
|
3129 |
+
}
|
3130 |
+
],
|
3131 |
+
"max_steps": 607100,
|
3132 |
+
"num_train_epochs": 10,
|
3133 |
+
"total_flos": 1.115410746630144e+17,
|
3134 |
+
"trial_name": null,
|
3135 |
+
"trial_params": null
|
3136 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bbad09a8ea722e503e7503d03c1cea3d5b38b5384d494608b342d9ed528f23cc
|
3 |
+
size 4335
|