Commit
•
fb70f38
1
Parent(s):
50e9a02
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 +2536 -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 sha256:0cb8b0c2ccf7503787401b77021b3e759fbd163436644225c5f7cada93e46cb7
|
| 3 |
+
size 9837132703
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ecb919a4b4b6328cd095095497fb4cd5a3939cbc4a030951ac802d6f3b56feef
|
| 3 |
+
size 4918519193
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3263ee99e9d98436b30959acd0d78c2473e4b93f48341eb6c5ea1d0c7411dea0
|
| 3 |
+
size 14575
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:53926e5aaff3807d06f802b0f5e91d31ea5a856628d982ba61d20df6a290d02d
|
| 3 |
+
size 627
|
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:faaa6405f5f79c9e788c7980874a9a3b5b0aea07b53bd9243bf1abb8f5c49c81
|
| 3 |
+
size 16330467
|
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 +1,2536 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 2.785961627960205,
|
| 3 |
+
"best_model_checkpoint": "experiments/qg/google/mt5-large_all/checkpoint-126000",
|
| 4 |
+
"epoch": 1.9977723341340248,
|
| 5 |
+
"global_step": 126000,
|
| 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": 8.8865,
|
| 14 |
+
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.02,
|
| 18 |
+
"learning_rate": 2.9976277372262774e-05,
|
| 19 |
+
"loss": 4.0325,
|
| 20 |
+
"step": 1000
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.02,
|
| 24 |
+
"eval_loss": 3.3621604442596436,
|
| 25 |
+
"eval_runtime": 444.6073,
|
| 26 |
+
"eval_samples_per_second": 89.967,
|
| 27 |
+
"eval_steps_per_second": 11.246,
|
| 28 |
+
"step": 1000
|
| 29 |
+
},
|
| 30 |
+
{
|
| 31 |
+
"epoch": 0.02,
|
| 32 |
+
"learning_rate": 2.9952554744525548e-05,
|
| 33 |
+
"loss": 3.6162,
|
| 34 |
+
"step": 1500
|
| 35 |
+
},
|
| 36 |
+
{
|
| 37 |
+
"epoch": 0.03,
|
| 38 |
+
"learning_rate": 2.992883211678832e-05,
|
| 39 |
+
"loss": 3.4961,
|
| 40 |
+
"step": 2000
|
| 41 |
+
},
|
| 42 |
+
{
|
| 43 |
+
"epoch": 0.03,
|
| 44 |
+
"eval_loss": 3.1849684715270996,
|
| 45 |
+
"eval_runtime": 443.8466,
|
| 46 |
+
"eval_samples_per_second": 90.121,
|
| 47 |
+
"eval_steps_per_second": 11.265,
|
| 48 |
+
"step": 2000
|
| 49 |
+
},
|
| 50 |
+
{
|
| 51 |
+
"epoch": 0.04,
|
| 52 |
+
"learning_rate": 2.9905109489051095e-05,
|
| 53 |
+
"loss": 3.4531,
|
| 54 |
+
"step": 2500
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 0.05,
|
| 58 |
+
"learning_rate": 2.988138686131387e-05,
|
| 59 |
+
"loss": 3.3883,
|
| 60 |
+
"step": 3000
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"epoch": 0.05,
|
| 64 |
+
"eval_loss": 3.0837316513061523,
|
| 65 |
+
"eval_runtime": 451.6674,
|
| 66 |
+
"eval_samples_per_second": 88.561,
|
| 67 |
+
"eval_steps_per_second": 11.07,
|
| 68 |
+
"step": 3000
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.06,
|
| 72 |
+
"learning_rate": 2.9857664233576645e-05,
|
| 73 |
+
"loss": 3.3483,
|
| 74 |
+
"step": 3500
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.06,
|
| 78 |
+
"learning_rate": 2.9833941605839416e-05,
|
| 79 |
+
"loss": 3.281,
|
| 80 |
+
"step": 4000
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.06,
|
| 84 |
+
"eval_loss": 3.053595781326294,
|
| 85 |
+
"eval_runtime": 451.6413,
|
| 86 |
+
"eval_samples_per_second": 88.566,
|
| 87 |
+
"eval_steps_per_second": 11.071,
|
| 88 |
+
"step": 4000
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 0.07,
|
| 92 |
+
"learning_rate": 2.9810218978102192e-05,
|
| 93 |
+
"loss": 3.2901,
|
| 94 |
+
"step": 4500
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.08,
|
| 98 |
+
"learning_rate": 2.9786496350364963e-05,
|
| 99 |
+
"loss": 3.2764,
|
| 100 |
+
"step": 5000
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.08,
|
| 104 |
+
"eval_loss": 3.045032262802124,
|
| 105 |
+
"eval_runtime": 450.7805,
|
| 106 |
+
"eval_samples_per_second": 88.735,
|
| 107 |
+
"eval_steps_per_second": 11.092,
|
| 108 |
+
"step": 5000
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.09,
|
| 112 |
+
"learning_rate": 2.9762773722627736e-05,
|
| 113 |
+
"loss": 3.255,
|
| 114 |
+
"step": 5500
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.1,
|
| 118 |
+
"learning_rate": 2.9739051094890513e-05,
|
| 119 |
+
"loss": 3.2352,
|
| 120 |
+
"step": 6000
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 0.1,
|
| 124 |
+
"eval_loss": 3.018794059753418,
|
| 125 |
+
"eval_runtime": 451.4803,
|
| 126 |
+
"eval_samples_per_second": 88.597,
|
| 127 |
+
"eval_steps_per_second": 11.075,
|
| 128 |
+
"step": 6000
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.1,
|
| 132 |
+
"learning_rate": 2.9715328467153283e-05,
|
| 133 |
+
"loss": 3.1954,
|
| 134 |
+
"step": 6500
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 0.11,
|
| 138 |
+
"learning_rate": 2.969160583941606e-05,
|
| 139 |
+
"loss": 3.1939,
|
| 140 |
+
"step": 7000
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 0.11,
|
| 144 |
+
"eval_loss": 3.000720500946045,
|
| 145 |
+
"eval_runtime": 450.9264,
|
| 146 |
+
"eval_samples_per_second": 88.706,
|
| 147 |
+
"eval_steps_per_second": 11.088,
|
| 148 |
+
"step": 7000
|
| 149 |
+
},
|
| 150 |
+
{
|
| 151 |
+
"epoch": 0.12,
|
| 152 |
+
"learning_rate": 2.966788321167883e-05,
|
| 153 |
+
"loss": 3.1893,
|
| 154 |
+
"step": 7500
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 0.13,
|
| 158 |
+
"learning_rate": 2.9644160583941607e-05,
|
| 159 |
+
"loss": 3.1936,
|
| 160 |
+
"step": 8000
|
| 161 |
+
},
|
| 162 |
+
{
|
| 163 |
+
"epoch": 0.13,
|
| 164 |
+
"eval_loss": 2.988145589828491,
|
| 165 |
+
"eval_runtime": 451.5214,
|
| 166 |
+
"eval_samples_per_second": 88.589,
|
| 167 |
+
"eval_steps_per_second": 11.074,
|
| 168 |
+
"step": 8000
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 0.13,
|
| 172 |
+
"learning_rate": 2.962043795620438e-05,
|
| 173 |
+
"loss": 3.1604,
|
| 174 |
+
"step": 8500
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 0.14,
|
| 178 |
+
"learning_rate": 2.9596715328467154e-05,
|
| 179 |
+
"loss": 3.1765,
|
| 180 |
+
"step": 9000
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 0.14,
|
| 184 |
+
"eval_loss": 2.9744112491607666,
|
| 185 |
+
"eval_runtime": 449.7283,
|
| 186 |
+
"eval_samples_per_second": 88.943,
|
| 187 |
+
"eval_steps_per_second": 11.118,
|
| 188 |
+
"step": 9000
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 0.15,
|
| 192 |
+
"learning_rate": 2.9572992700729928e-05,
|
| 193 |
+
"loss": 3.1478,
|
| 194 |
+
"step": 9500
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 0.16,
|
| 198 |
+
"learning_rate": 2.95492700729927e-05,
|
| 199 |
+
"loss": 3.1532,
|
| 200 |
+
"step": 10000
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 0.16,
|
| 204 |
+
"eval_loss": 2.960232734680176,
|
| 205 |
+
"eval_runtime": 450.2869,
|
| 206 |
+
"eval_samples_per_second": 88.832,
|
| 207 |
+
"eval_steps_per_second": 11.104,
|
| 208 |
+
"step": 10000
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 0.17,
|
| 212 |
+
"learning_rate": 2.9525547445255475e-05,
|
| 213 |
+
"loss": 3.1187,
|
| 214 |
+
"step": 10500
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"epoch": 0.17,
|
| 218 |
+
"learning_rate": 2.950182481751825e-05,
|
| 219 |
+
"loss": 3.1318,
|
| 220 |
+
"step": 11000
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.17,
|
| 224 |
+
"eval_loss": 2.956113338470459,
|
| 225 |
+
"eval_runtime": 450.2104,
|
| 226 |
+
"eval_samples_per_second": 88.847,
|
| 227 |
+
"eval_steps_per_second": 11.106,
|
| 228 |
+
"step": 11000
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"epoch": 0.18,
|
| 232 |
+
"learning_rate": 2.9478102189781022e-05,
|
| 233 |
+
"loss": 3.1086,
|
| 234 |
+
"step": 11500
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.19,
|
| 238 |
+
"learning_rate": 2.9454379562043796e-05,
|
| 239 |
+
"loss": 3.0946,
|
| 240 |
+
"step": 12000
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.19,
|
| 244 |
+
"eval_loss": 2.946828842163086,
|
| 245 |
+
"eval_runtime": 450.0294,
|
| 246 |
+
"eval_samples_per_second": 88.883,
|
| 247 |
+
"eval_steps_per_second": 11.11,
|
| 248 |
+
"step": 12000
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.2,
|
| 252 |
+
"learning_rate": 2.9430656934306573e-05,
|
| 253 |
+
"loss": 3.114,
|
| 254 |
+
"step": 12500
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.21,
|
| 258 |
+
"learning_rate": 2.9406934306569343e-05,
|
| 259 |
+
"loss": 3.0903,
|
| 260 |
+
"step": 13000
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 0.21,
|
| 264 |
+
"eval_loss": 2.936713457107544,
|
| 265 |
+
"eval_runtime": 449.1132,
|
| 266 |
+
"eval_samples_per_second": 89.064,
|
| 267 |
+
"eval_steps_per_second": 11.133,
|
| 268 |
+
"step": 13000
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.21,
|
| 272 |
+
"learning_rate": 2.938321167883212e-05,
|
| 273 |
+
"loss": 3.102,
|
| 274 |
+
"step": 13500
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 0.22,
|
| 278 |
+
"learning_rate": 2.935948905109489e-05,
|
| 279 |
+
"loss": 3.0916,
|
| 280 |
+
"step": 14000
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 0.22,
|
| 284 |
+
"eval_loss": 2.9305248260498047,
|
| 285 |
+
"eval_runtime": 449.5477,
|
| 286 |
+
"eval_samples_per_second": 88.978,
|
| 287 |
+
"eval_steps_per_second": 11.122,
|
| 288 |
+
"step": 14000
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 0.23,
|
| 292 |
+
"learning_rate": 2.9335766423357667e-05,
|
| 293 |
+
"loss": 3.0578,
|
| 294 |
+
"step": 14500
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 0.24,
|
| 298 |
+
"learning_rate": 2.931204379562044e-05,
|
| 299 |
+
"loss": 3.0754,
|
| 300 |
+
"step": 15000
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 0.24,
|
| 304 |
+
"eval_loss": 2.92580246925354,
|
| 305 |
+
"eval_runtime": 449.9439,
|
| 306 |
+
"eval_samples_per_second": 88.9,
|
| 307 |
+
"eval_steps_per_second": 11.112,
|
| 308 |
+
"step": 15000
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 0.25,
|
| 312 |
+
"learning_rate": 2.928832116788321e-05,
|
| 313 |
+
"loss": 3.0673,
|
| 314 |
+
"step": 15500
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 0.25,
|
| 318 |
+
"learning_rate": 2.9264598540145987e-05,
|
| 319 |
+
"loss": 3.0606,
|
| 320 |
+
"step": 16000
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 0.25,
|
| 324 |
+
"eval_loss": 2.9198672771453857,
|
| 325 |
+
"eval_runtime": 450.1912,
|
| 326 |
+
"eval_samples_per_second": 88.851,
|
| 327 |
+
"eval_steps_per_second": 11.106,
|
| 328 |
+
"step": 16000
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"epoch": 0.26,
|
| 332 |
+
"learning_rate": 2.9240875912408757e-05,
|
| 333 |
+
"loss": 3.0472,
|
| 334 |
+
"step": 16500
|
| 335 |
+
},
|
| 336 |
+
{
|
| 337 |
+
"epoch": 0.27,
|
| 338 |
+
"learning_rate": 2.9217153284671534e-05,
|
| 339 |
+
"loss": 3.0598,
|
| 340 |
+
"step": 17000
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"epoch": 0.27,
|
| 344 |
+
"eval_loss": 2.91711163520813,
|
| 345 |
+
"eval_runtime": 449.4944,
|
| 346 |
+
"eval_samples_per_second": 88.989,
|
| 347 |
+
"eval_steps_per_second": 11.124,
|
| 348 |
+
"step": 17000
|
| 349 |
+
},
|
| 350 |
+
{
|
| 351 |
+
"epoch": 0.28,
|
| 352 |
+
"learning_rate": 2.9193430656934308e-05,
|
| 353 |
+
"loss": 3.0376,
|
| 354 |
+
"step": 17500
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 0.29,
|
| 358 |
+
"learning_rate": 2.916970802919708e-05,
|
| 359 |
+
"loss": 3.0369,
|
| 360 |
+
"step": 18000
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.29,
|
| 364 |
+
"eval_loss": 2.9090449810028076,
|
| 365 |
+
"eval_runtime": 450.1639,
|
| 366 |
+
"eval_samples_per_second": 88.857,
|
| 367 |
+
"eval_steps_per_second": 11.107,
|
| 368 |
+
"step": 18000
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 0.29,
|
| 372 |
+
"learning_rate": 2.9145985401459855e-05,
|
| 373 |
+
"loss": 3.0517,
|
| 374 |
+
"step": 18500
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.3,
|
| 378 |
+
"learning_rate": 2.912226277372263e-05,
|
| 379 |
+
"loss": 3.0312,
|
| 380 |
+
"step": 19000
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.3,
|
| 384 |
+
"eval_loss": 2.903899669647217,
|
| 385 |
+
"eval_runtime": 450.5358,
|
| 386 |
+
"eval_samples_per_second": 88.783,
|
| 387 |
+
"eval_steps_per_second": 11.098,
|
| 388 |
+
"step": 19000
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.31,
|
| 392 |
+
"learning_rate": 2.9098540145985402e-05,
|
| 393 |
+
"loss": 3.0135,
|
| 394 |
+
"step": 19500
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.32,
|
| 398 |
+
"learning_rate": 2.9074817518248176e-05,
|
| 399 |
+
"loss": 3.0304,
|
| 400 |
+
"step": 20000
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"epoch": 0.32,
|
| 404 |
+
"eval_loss": 2.8915276527404785,
|
| 405 |
+
"eval_runtime": 449.8834,
|
| 406 |
+
"eval_samples_per_second": 88.912,
|
| 407 |
+
"eval_steps_per_second": 11.114,
|
| 408 |
+
"step": 20000
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.33,
|
| 412 |
+
"learning_rate": 2.905109489051095e-05,
|
| 413 |
+
"loss": 3.0157,
|
| 414 |
+
"step": 20500
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 0.33,
|
| 418 |
+
"learning_rate": 2.9027372262773723e-05,
|
| 419 |
+
"loss": 3.008,
|
| 420 |
+
"step": 21000
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 0.33,
|
| 424 |
+
"eval_loss": 2.89363431930542,
|
| 425 |
+
"eval_runtime": 450.0699,
|
| 426 |
+
"eval_samples_per_second": 88.875,
|
| 427 |
+
"eval_steps_per_second": 11.109,
|
| 428 |
+
"step": 21000
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 0.34,
|
| 432 |
+
"learning_rate": 2.9003649635036496e-05,
|
| 433 |
+
"loss": 3.0125,
|
| 434 |
+
"step": 21500
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 0.35,
|
| 438 |
+
"learning_rate": 2.897992700729927e-05,
|
| 439 |
+
"loss": 3.0373,
|
| 440 |
+
"step": 22000
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 0.35,
|
| 444 |
+
"eval_loss": 2.8869340419769287,
|
| 445 |
+
"eval_runtime": 450.8527,
|
| 446 |
+
"eval_samples_per_second": 88.721,
|
| 447 |
+
"eval_steps_per_second": 11.09,
|
| 448 |
+
"step": 22000
|
| 449 |
+
},
|
| 450 |
+
{
|
| 451 |
+
"epoch": 0.36,
|
| 452 |
+
"learning_rate": 2.8956204379562047e-05,
|
| 453 |
+
"loss": 3.0246,
|
| 454 |
+
"step": 22500
|
| 455 |
+
},
|
| 456 |
+
{
|
| 457 |
+
"epoch": 0.36,
|
| 458 |
+
"learning_rate": 2.8932481751824817e-05,
|
| 459 |
+
"loss": 3.0107,
|
| 460 |
+
"step": 23000
|
| 461 |
+
},
|
| 462 |
+
{
|
| 463 |
+
"epoch": 0.36,
|
| 464 |
+
"eval_loss": 2.882735252380371,
|
| 465 |
+
"eval_runtime": 451.0618,
|
| 466 |
+
"eval_samples_per_second": 88.68,
|
| 467 |
+
"eval_steps_per_second": 11.085,
|
| 468 |
+
"step": 23000
|
| 469 |
+
},
|
| 470 |
+
{
|
| 471 |
+
"epoch": 0.37,
|
| 472 |
+
"learning_rate": 2.8908759124087594e-05,
|
| 473 |
+
"loss": 3.0006,
|
| 474 |
+
"step": 23500
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 0.38,
|
| 478 |
+
"learning_rate": 2.8885036496350364e-05,
|
| 479 |
+
"loss": 2.9781,
|
| 480 |
+
"step": 24000
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 0.38,
|
| 484 |
+
"eval_loss": 2.8770592212677,
|
| 485 |
+
"eval_runtime": 450.672,
|
| 486 |
+
"eval_samples_per_second": 88.756,
|
| 487 |
+
"eval_steps_per_second": 11.095,
|
| 488 |
+
"step": 24000
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 0.39,
|
| 492 |
+
"learning_rate": 2.886131386861314e-05,
|
| 493 |
+
"loss": 2.9744,
|
| 494 |
+
"step": 24500
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 0.4,
|
| 498 |
+
"learning_rate": 2.8837591240875914e-05,
|
| 499 |
+
"loss": 3.0146,
|
| 500 |
+
"step": 25000
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 0.4,
|
| 504 |
+
"eval_loss": 2.8825135231018066,
|
| 505 |
+
"eval_runtime": 450.4517,
|
| 506 |
+
"eval_samples_per_second": 88.8,
|
| 507 |
+
"eval_steps_per_second": 11.1,
|
| 508 |
+
"step": 25000
|
| 509 |
+
},
|
| 510 |
+
{
|
| 511 |
+
"epoch": 0.4,
|
| 512 |
+
"learning_rate": 2.8813868613138685e-05,
|
| 513 |
+
"loss": 2.997,
|
| 514 |
+
"step": 25500
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 0.41,
|
| 518 |
+
"learning_rate": 2.879014598540146e-05,
|
| 519 |
+
"loss": 2.9856,
|
| 520 |
+
"step": 26000
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 0.41,
|
| 524 |
+
"eval_loss": 2.8855531215667725,
|
| 525 |
+
"eval_runtime": 450.7359,
|
| 526 |
+
"eval_samples_per_second": 88.744,
|
| 527 |
+
"eval_steps_per_second": 11.093,
|
| 528 |
+
"step": 26000
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 0.42,
|
| 532 |
+
"learning_rate": 2.8766423357664232e-05,
|
| 533 |
+
"loss": 2.986,
|
| 534 |
+
"step": 26500
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.43,
|
| 538 |
+
"learning_rate": 2.874270072992701e-05,
|
| 539 |
+
"loss": 3.0001,
|
| 540 |
+
"step": 27000
|
| 541 |
+
},
|
| 542 |
+
{
|
| 543 |
+
"epoch": 0.43,
|
| 544 |
+
"eval_loss": 2.886821985244751,
|
| 545 |
+
"eval_runtime": 450.0432,
|
| 546 |
+
"eval_samples_per_second": 88.88,
|
| 547 |
+
"eval_steps_per_second": 11.11,
|
| 548 |
+
"step": 27000
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 0.44,
|
| 552 |
+
"learning_rate": 2.8718978102189782e-05,
|
| 553 |
+
"loss": 2.9924,
|
| 554 |
+
"step": 27500
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 0.44,
|
| 558 |
+
"learning_rate": 2.8695255474452556e-05,
|
| 559 |
+
"loss": 2.9633,
|
| 560 |
+
"step": 28000
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 0.44,
|
| 564 |
+
"eval_loss": 2.8713860511779785,
|
| 565 |
+
"eval_runtime": 450.4908,
|
| 566 |
+
"eval_samples_per_second": 88.792,
|
| 567 |
+
"eval_steps_per_second": 11.099,
|
| 568 |
+
"step": 28000
|
| 569 |
+
},
|
| 570 |
+
{
|
| 571 |
+
"epoch": 0.45,
|
| 572 |
+
"learning_rate": 2.867153284671533e-05,
|
| 573 |
+
"loss": 2.9684,
|
| 574 |
+
"step": 28500
|
| 575 |
+
},
|
| 576 |
+
{
|
| 577 |
+
"epoch": 0.46,
|
| 578 |
+
"learning_rate": 2.8647810218978103e-05,
|
| 579 |
+
"loss": 2.9563,
|
| 580 |
+
"step": 29000
|
| 581 |
+
},
|
| 582 |
+
{
|
| 583 |
+
"epoch": 0.46,
|
| 584 |
+
"eval_loss": 2.8724424839019775,
|
| 585 |
+
"eval_runtime": 450.9726,
|
| 586 |
+
"eval_samples_per_second": 88.697,
|
| 587 |
+
"eval_steps_per_second": 11.087,
|
| 588 |
+
"step": 29000
|
| 589 |
+
},
|
| 590 |
+
{
|
| 591 |
+
"epoch": 0.47,
|
| 592 |
+
"learning_rate": 2.8624087591240876e-05,
|
| 593 |
+
"loss": 2.9573,
|
| 594 |
+
"step": 29500
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 0.48,
|
| 598 |
+
"learning_rate": 2.860036496350365e-05,
|
| 599 |
+
"loss": 2.9812,
|
| 600 |
+
"step": 30000
|
| 601 |
+
},
|
| 602 |
+
{
|
| 603 |
+
"epoch": 0.48,
|
| 604 |
+
"eval_loss": 2.86970591545105,
|
| 605 |
+
"eval_runtime": 450.3055,
|
| 606 |
+
"eval_samples_per_second": 88.829,
|
| 607 |
+
"eval_steps_per_second": 11.104,
|
| 608 |
+
"step": 30000
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 0.48,
|
| 612 |
+
"learning_rate": 2.8576642335766423e-05,
|
| 613 |
+
"loss": 2.9677,
|
| 614 |
+
"step": 30500
|
| 615 |
+
},
|
| 616 |
+
{
|
| 617 |
+
"epoch": 0.49,
|
| 618 |
+
"learning_rate": 2.8552919708029197e-05,
|
| 619 |
+
"loss": 2.9773,
|
| 620 |
+
"step": 31000
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 0.49,
|
| 624 |
+
"eval_loss": 2.8727774620056152,
|
| 625 |
+
"eval_runtime": 449.455,
|
| 626 |
+
"eval_samples_per_second": 88.997,
|
| 627 |
+
"eval_steps_per_second": 11.125,
|
| 628 |
+
"step": 31000
|
| 629 |
+
},
|
| 630 |
+
{
|
| 631 |
+
"epoch": 0.5,
|
| 632 |
+
"learning_rate": 2.8529197080291974e-05,
|
| 633 |
+
"loss": 2.971,
|
| 634 |
+
"step": 31500
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 0.51,
|
| 638 |
+
"learning_rate": 2.8505474452554744e-05,
|
| 639 |
+
"loss": 2.9743,
|
| 640 |
+
"step": 32000
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 0.51,
|
| 644 |
+
"eval_loss": 2.8665173053741455,
|
| 645 |
+
"eval_runtime": 449.7846,
|
| 646 |
+
"eval_samples_per_second": 88.931,
|
| 647 |
+
"eval_steps_per_second": 11.116,
|
| 648 |
+
"step": 32000
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 0.52,
|
| 652 |
+
"learning_rate": 2.848175182481752e-05,
|
| 653 |
+
"loss": 2.9585,
|
| 654 |
+
"step": 32500
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 0.52,
|
| 658 |
+
"learning_rate": 2.845802919708029e-05,
|
| 659 |
+
"loss": 2.9428,
|
| 660 |
+
"step": 33000
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 0.52,
|
| 664 |
+
"eval_loss": 2.8613767623901367,
|
| 665 |
+
"eval_runtime": 450.8331,
|
| 666 |
+
"eval_samples_per_second": 88.725,
|
| 667 |
+
"eval_steps_per_second": 11.091,
|
| 668 |
+
"step": 33000
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 0.53,
|
| 672 |
+
"learning_rate": 2.8434306569343068e-05,
|
| 673 |
+
"loss": 2.9509,
|
| 674 |
+
"step": 33500
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 0.54,
|
| 678 |
+
"learning_rate": 2.841058394160584e-05,
|
| 679 |
+
"loss": 2.9683,
|
| 680 |
+
"step": 34000
|
| 681 |
+
},
|
| 682 |
+
{
|
| 683 |
+
"epoch": 0.54,
|
| 684 |
+
"eval_loss": 2.86824369430542,
|
| 685 |
+
"eval_runtime": 450.4958,
|
| 686 |
+
"eval_samples_per_second": 88.791,
|
| 687 |
+
"eval_steps_per_second": 11.099,
|
| 688 |
+
"step": 34000
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 0.55,
|
| 692 |
+
"learning_rate": 2.8386861313868612e-05,
|
| 693 |
+
"loss": 2.9332,
|
| 694 |
+
"step": 34500
|
| 695 |
+
},
|
| 696 |
+
{
|
| 697 |
+
"epoch": 0.55,
|
| 698 |
+
"learning_rate": 2.836313868613139e-05,
|
| 699 |
+
"loss": 2.9567,
|
| 700 |
+
"step": 35000
|
| 701 |
+
},
|
| 702 |
+
{
|
| 703 |
+
"epoch": 0.55,
|
| 704 |
+
"eval_loss": 2.854598045349121,
|
| 705 |
+
"eval_runtime": 450.2268,
|
| 706 |
+
"eval_samples_per_second": 88.844,
|
| 707 |
+
"eval_steps_per_second": 11.106,
|
| 708 |
+
"step": 35000
|
| 709 |
+
},
|
| 710 |
+
{
|
| 711 |
+
"epoch": 0.56,
|
| 712 |
+
"learning_rate": 2.833941605839416e-05,
|
| 713 |
+
"loss": 2.9529,
|
| 714 |
+
"step": 35500
|
| 715 |
+
},
|
| 716 |
+
{
|
| 717 |
+
"epoch": 0.57,
|
| 718 |
+
"learning_rate": 2.8315693430656936e-05,
|
| 719 |
+
"loss": 2.9515,
|
| 720 |
+
"step": 36000
|
| 721 |
+
},
|
| 722 |
+
{
|
| 723 |
+
"epoch": 0.57,
|
| 724 |
+
"eval_loss": 2.8551025390625,
|
| 725 |
+
"eval_runtime": 450.4445,
|
| 726 |
+
"eval_samples_per_second": 88.801,
|
| 727 |
+
"eval_steps_per_second": 11.1,
|
| 728 |
+
"step": 36000
|
| 729 |
+
},
|
| 730 |
+
{
|
| 731 |
+
"epoch": 0.58,
|
| 732 |
+
"learning_rate": 2.829197080291971e-05,
|
| 733 |
+
"loss": 2.9273,
|
| 734 |
+
"step": 36500
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 0.59,
|
| 738 |
+
"learning_rate": 2.8268248175182483e-05,
|
| 739 |
+
"loss": 2.965,
|
| 740 |
+
"step": 37000
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 0.59,
|
| 744 |
+
"eval_loss": 2.8546838760375977,
|
| 745 |
+
"eval_runtime": 450.6163,
|
| 746 |
+
"eval_samples_per_second": 88.767,
|
| 747 |
+
"eval_steps_per_second": 11.096,
|
| 748 |
+
"step": 37000
|
| 749 |
+
},
|
| 750 |
+
{
|
| 751 |
+
"epoch": 0.59,
|
| 752 |
+
"learning_rate": 2.8244525547445256e-05,
|
| 753 |
+
"loss": 2.9441,
|
| 754 |
+
"step": 37500
|
| 755 |
+
},
|
| 756 |
+
{
|
| 757 |
+
"epoch": 0.6,
|
| 758 |
+
"learning_rate": 2.822080291970803e-05,
|
| 759 |
+
"loss": 2.9326,
|
| 760 |
+
"step": 38000
|
| 761 |
+
},
|
| 762 |
+
{
|
| 763 |
+
"epoch": 0.6,
|
| 764 |
+
"eval_loss": 2.848287582397461,
|
| 765 |
+
"eval_runtime": 450.6373,
|
| 766 |
+
"eval_samples_per_second": 88.763,
|
| 767 |
+
"eval_steps_per_second": 11.095,
|
| 768 |
+
"step": 38000
|
| 769 |
+
},
|
| 770 |
+
{
|
| 771 |
+
"epoch": 0.61,
|
| 772 |
+
"learning_rate": 2.8197080291970803e-05,
|
| 773 |
+
"loss": 2.9547,
|
| 774 |
+
"step": 38500
|
| 775 |
+
},
|
| 776 |
+
{
|
| 777 |
+
"epoch": 0.62,
|
| 778 |
+
"learning_rate": 2.817335766423358e-05,
|
| 779 |
+
"loss": 2.9096,
|
| 780 |
+
"step": 39000
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 0.62,
|
| 784 |
+
"eval_loss": 2.8502256870269775,
|
| 785 |
+
"eval_runtime": 450.3731,
|
| 786 |
+
"eval_samples_per_second": 88.815,
|
| 787 |
+
"eval_steps_per_second": 11.102,
|
| 788 |
+
"step": 39000
|
| 789 |
+
},
|
| 790 |
+
{
|
| 791 |
+
"epoch": 0.63,
|
| 792 |
+
"learning_rate": 2.814963503649635e-05,
|
| 793 |
+
"loss": 2.9222,
|
| 794 |
+
"step": 39500
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 0.63,
|
| 798 |
+
"learning_rate": 2.8125912408759124e-05,
|
| 799 |
+
"loss": 2.9132,
|
| 800 |
+
"step": 40000
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 0.63,
|
| 804 |
+
"eval_loss": 2.8453314304351807,
|
| 805 |
+
"eval_runtime": 450.4787,
|
| 806 |
+
"eval_samples_per_second": 88.794,
|
| 807 |
+
"eval_steps_per_second": 11.099,
|
| 808 |
+
"step": 40000
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 0.64,
|
| 812 |
+
"learning_rate": 2.8102189781021898e-05,
|
| 813 |
+
"loss": 2.9172,
|
| 814 |
+
"step": 40500
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 0.65,
|
| 818 |
+
"learning_rate": 2.807846715328467e-05,
|
| 819 |
+
"loss": 2.9373,
|
| 820 |
+
"step": 41000
|
| 821 |
+
},
|
| 822 |
+
{
|
| 823 |
+
"epoch": 0.65,
|
| 824 |
+
"eval_loss": 2.8487000465393066,
|
| 825 |
+
"eval_runtime": 450.8104,
|
| 826 |
+
"eval_samples_per_second": 88.729,
|
| 827 |
+
"eval_steps_per_second": 11.091,
|
| 828 |
+
"step": 41000
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 0.66,
|
| 832 |
+
"learning_rate": 2.8054744525547448e-05,
|
| 833 |
+
"loss": 2.9451,
|
| 834 |
+
"step": 41500
|
| 835 |
+
},
|
| 836 |
+
{
|
| 837 |
+
"epoch": 0.67,
|
| 838 |
+
"learning_rate": 2.8031021897810218e-05,
|
| 839 |
+
"loss": 2.9333,
|
| 840 |
+
"step": 42000
|
| 841 |
+
},
|
| 842 |
+
{
|
| 843 |
+
"epoch": 0.67,
|
| 844 |
+
"eval_loss": 2.8426833152770996,
|
| 845 |
+
"eval_runtime": 449.7638,
|
| 846 |
+
"eval_samples_per_second": 88.936,
|
| 847 |
+
"eval_steps_per_second": 11.117,
|
| 848 |
+
"step": 42000
|
| 849 |
+
},
|
| 850 |
+
{
|
| 851 |
+
"epoch": 0.67,
|
| 852 |
+
"learning_rate": 2.8007299270072995e-05,
|
| 853 |
+
"loss": 2.9263,
|
| 854 |
+
"step": 42500
|
| 855 |
+
},
|
| 856 |
+
{
|
| 857 |
+
"epoch": 0.68,
|
| 858 |
+
"learning_rate": 2.7983576642335765e-05,
|
| 859 |
+
"loss": 2.9242,
|
| 860 |
+
"step": 43000
|
| 861 |
+
},
|
| 862 |
+
{
|
| 863 |
+
"epoch": 0.68,
|
| 864 |
+
"eval_loss": 2.8440945148468018,
|
| 865 |
+
"eval_runtime": 450.8592,
|
| 866 |
+
"eval_samples_per_second": 88.719,
|
| 867 |
+
"eval_steps_per_second": 11.09,
|
| 868 |
+
"step": 43000
|
| 869 |
+
},
|
| 870 |
+
{
|
| 871 |
+
"epoch": 0.69,
|
| 872 |
+
"learning_rate": 2.795985401459854e-05,
|
| 873 |
+
"loss": 2.9226,
|
| 874 |
+
"step": 43500
|
| 875 |
+
},
|
| 876 |
+
{
|
| 877 |
+
"epoch": 0.7,
|
| 878 |
+
"learning_rate": 2.7936131386861316e-05,
|
| 879 |
+
"loss": 2.9058,
|
| 880 |
+
"step": 44000
|
| 881 |
+
},
|
| 882 |
+
{
|
| 883 |
+
"epoch": 0.7,
|
| 884 |
+
"eval_loss": 2.8383543491363525,
|
| 885 |
+
"eval_runtime": 450.5891,
|
| 886 |
+
"eval_samples_per_second": 88.773,
|
| 887 |
+
"eval_steps_per_second": 11.097,
|
| 888 |
+
"step": 44000
|
| 889 |
+
},
|
| 890 |
+
{
|
| 891 |
+
"epoch": 0.71,
|
| 892 |
+
"learning_rate": 2.7912408759124086e-05,
|
| 893 |
+
"loss": 2.9113,
|
| 894 |
+
"step": 44500
|
| 895 |
+
},
|
| 896 |
+
{
|
| 897 |
+
"epoch": 0.71,
|
| 898 |
+
"learning_rate": 2.7888686131386863e-05,
|
| 899 |
+
"loss": 2.9237,
|
| 900 |
+
"step": 45000
|
| 901 |
+
},
|
| 902 |
+
{
|
| 903 |
+
"epoch": 0.71,
|
| 904 |
+
"eval_loss": 2.8444628715515137,
|
| 905 |
+
"eval_runtime": 450.7048,
|
| 906 |
+
"eval_samples_per_second": 88.75,
|
| 907 |
+
"eval_steps_per_second": 11.094,
|
| 908 |
+
"step": 45000
|
| 909 |
+
},
|
| 910 |
+
{
|
| 911 |
+
"epoch": 0.72,
|
| 912 |
+
"learning_rate": 2.7864963503649633e-05,
|
| 913 |
+
"loss": 2.904,
|
| 914 |
+
"step": 45500
|
| 915 |
+
},
|
| 916 |
+
{
|
| 917 |
+
"epoch": 0.73,
|
| 918 |
+
"learning_rate": 2.784124087591241e-05,
|
| 919 |
+
"loss": 2.9101,
|
| 920 |
+
"step": 46000
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 0.73,
|
| 924 |
+
"eval_loss": 2.8378028869628906,
|
| 925 |
+
"eval_runtime": 450.6185,
|
| 926 |
+
"eval_samples_per_second": 88.767,
|
| 927 |
+
"eval_steps_per_second": 11.096,
|
| 928 |
+
"step": 46000
|
| 929 |
+
},
|
| 930 |
+
{
|
| 931 |
+
"epoch": 0.74,
|
| 932 |
+
"learning_rate": 2.7817518248175184e-05,
|
| 933 |
+
"loss": 2.913,
|
| 934 |
+
"step": 46500
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 0.75,
|
| 938 |
+
"learning_rate": 2.7793795620437957e-05,
|
| 939 |
+
"loss": 2.9053,
|
| 940 |
+
"step": 47000
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 0.75,
|
| 944 |
+
"eval_loss": 2.840611219406128,
|
| 945 |
+
"eval_runtime": 448.4181,
|
| 946 |
+
"eval_samples_per_second": 89.202,
|
| 947 |
+
"eval_steps_per_second": 11.15,
|
| 948 |
+
"step": 47000
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 0.75,
|
| 952 |
+
"learning_rate": 2.777007299270073e-05,
|
| 953 |
+
"loss": 2.8649,
|
| 954 |
+
"step": 47500
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 0.76,
|
| 958 |
+
"learning_rate": 2.7746350364963504e-05,
|
| 959 |
+
"loss": 2.9016,
|
| 960 |
+
"step": 48000
|
| 961 |
+
},
|
| 962 |
+
{
|
| 963 |
+
"epoch": 0.76,
|
| 964 |
+
"eval_loss": 2.832401752471924,
|
| 965 |
+
"eval_runtime": 448.5723,
|
| 966 |
+
"eval_samples_per_second": 89.172,
|
| 967 |
+
"eval_steps_per_second": 11.146,
|
| 968 |
+
"step": 48000
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 0.77,
|
| 972 |
+
"learning_rate": 2.7722627737226278e-05,
|
| 973 |
+
"loss": 2.9178,
|
| 974 |
+
"step": 48500
|
| 975 |
+
},
|
| 976 |
+
{
|
| 977 |
+
"epoch": 0.78,
|
| 978 |
+
"learning_rate": 2.769890510948905e-05,
|
| 979 |
+
"loss": 2.8928,
|
| 980 |
+
"step": 49000
|
| 981 |
+
},
|
| 982 |
+
{
|
| 983 |
+
"epoch": 0.78,
|
| 984 |
+
"eval_loss": 2.8320999145507812,
|
| 985 |
+
"eval_runtime": 449.0119,
|
| 986 |
+
"eval_samples_per_second": 89.084,
|
| 987 |
+
"eval_steps_per_second": 11.136,
|
| 988 |
+
"step": 49000
|
| 989 |
+
},
|
| 990 |
+
{
|
| 991 |
+
"epoch": 0.78,
|
| 992 |
+
"learning_rate": 2.7675182481751825e-05,
|
| 993 |
+
"loss": 2.903,
|
| 994 |
+
"step": 49500
|
| 995 |
+
},
|
| 996 |
+
{
|
| 997 |
+
"epoch": 0.79,
|
| 998 |
+
"learning_rate": 2.76514598540146e-05,
|
| 999 |
+
"loss": 2.8792,
|
| 1000 |
+
"step": 50000
|
| 1001 |
+
},
|
| 1002 |
+
{
|
| 1003 |
+
"epoch": 0.79,
|
| 1004 |
+
"eval_loss": 2.836050033569336,
|
| 1005 |
+
"eval_runtime": 447.2366,
|
| 1006 |
+
"eval_samples_per_second": 89.438,
|
| 1007 |
+
"eval_steps_per_second": 11.18,
|
| 1008 |
+
"step": 50000
|
| 1009 |
+
},
|
| 1010 |
+
{
|
| 1011 |
+
"epoch": 0.8,
|
| 1012 |
+
"learning_rate": 2.7627737226277375e-05,
|
| 1013 |
+
"loss": 2.8807,
|
| 1014 |
+
"step": 50500
|
| 1015 |
+
},
|
| 1016 |
+
{
|
| 1017 |
+
"epoch": 0.81,
|
| 1018 |
+
"learning_rate": 2.7604014598540145e-05,
|
| 1019 |
+
"loss": 2.896,
|
| 1020 |
+
"step": 51000
|
| 1021 |
+
},
|
| 1022 |
+
{
|
| 1023 |
+
"epoch": 0.81,
|
| 1024 |
+
"eval_loss": 2.8326449394226074,
|
| 1025 |
+
"eval_runtime": 447.8025,
|
| 1026 |
+
"eval_samples_per_second": 89.325,
|
| 1027 |
+
"eval_steps_per_second": 11.166,
|
| 1028 |
+
"step": 51000
|
| 1029 |
+
},
|
| 1030 |
+
{
|
| 1031 |
+
"epoch": 0.82,
|
| 1032 |
+
"learning_rate": 2.7580291970802922e-05,
|
| 1033 |
+
"loss": 2.8805,
|
| 1034 |
+
"step": 51500
|
| 1035 |
+
},
|
| 1036 |
+
{
|
| 1037 |
+
"epoch": 0.82,
|
| 1038 |
+
"learning_rate": 2.7556569343065692e-05,
|
| 1039 |
+
"loss": 2.8708,
|
| 1040 |
+
"step": 52000
|
| 1041 |
+
},
|
| 1042 |
+
{
|
| 1043 |
+
"epoch": 0.82,
|
| 1044 |
+
"eval_loss": 2.830998420715332,
|
| 1045 |
+
"eval_runtime": 441.655,
|
| 1046 |
+
"eval_samples_per_second": 90.568,
|
| 1047 |
+
"eval_steps_per_second": 11.321,
|
| 1048 |
+
"step": 52000
|
| 1049 |
+
},
|
| 1050 |
+
{
|
| 1051 |
+
"epoch": 0.83,
|
| 1052 |
+
"learning_rate": 2.753284671532847e-05,
|
| 1053 |
+
"loss": 2.8656,
|
| 1054 |
+
"step": 52500
|
| 1055 |
+
},
|
| 1056 |
+
{
|
| 1057 |
+
"epoch": 0.84,
|
| 1058 |
+
"learning_rate": 2.7509124087591243e-05,
|
| 1059 |
+
"loss": 2.8882,
|
| 1060 |
+
"step": 53000
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"epoch": 0.84,
|
| 1064 |
+
"eval_loss": 2.8259706497192383,
|
| 1065 |
+
"eval_runtime": 442.0896,
|
| 1066 |
+
"eval_samples_per_second": 90.479,
|
| 1067 |
+
"eval_steps_per_second": 11.31,
|
| 1068 |
+
"step": 53000
|
| 1069 |
+
},
|
| 1070 |
+
{
|
| 1071 |
+
"epoch": 0.85,
|
| 1072 |
+
"learning_rate": 2.7485401459854017e-05,
|
| 1073 |
+
"loss": 2.8818,
|
| 1074 |
+
"step": 53500
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 0.86,
|
| 1078 |
+
"learning_rate": 2.746167883211679e-05,
|
| 1079 |
+
"loss": 2.8682,
|
| 1080 |
+
"step": 54000
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 0.86,
|
| 1084 |
+
"eval_loss": 2.8257410526275635,
|
| 1085 |
+
"eval_runtime": 441.6514,
|
| 1086 |
+
"eval_samples_per_second": 90.569,
|
| 1087 |
+
"eval_steps_per_second": 11.321,
|
| 1088 |
+
"step": 54000
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 0.86,
|
| 1092 |
+
"learning_rate": 2.743795620437956e-05,
|
| 1093 |
+
"loss": 2.8765,
|
| 1094 |
+
"step": 54500
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 0.87,
|
| 1098 |
+
"learning_rate": 2.7414233576642337e-05,
|
| 1099 |
+
"loss": 2.8843,
|
| 1100 |
+
"step": 55000
|
| 1101 |
+
},
|
| 1102 |
+
{
|
| 1103 |
+
"epoch": 0.87,
|
| 1104 |
+
"eval_loss": 2.8210554122924805,
|
| 1105 |
+
"eval_runtime": 441.9171,
|
| 1106 |
+
"eval_samples_per_second": 90.515,
|
| 1107 |
+
"eval_steps_per_second": 11.314,
|
| 1108 |
+
"step": 55000
|
| 1109 |
+
},
|
| 1110 |
+
{
|
| 1111 |
+
"epoch": 0.88,
|
| 1112 |
+
"learning_rate": 2.739051094890511e-05,
|
| 1113 |
+
"loss": 2.8785,
|
| 1114 |
+
"step": 55500
|
| 1115 |
+
},
|
| 1116 |
+
{
|
| 1117 |
+
"epoch": 0.89,
|
| 1118 |
+
"learning_rate": 2.7366788321167884e-05,
|
| 1119 |
+
"loss": 2.8631,
|
| 1120 |
+
"step": 56000
|
| 1121 |
+
},
|
| 1122 |
+
{
|
| 1123 |
+
"epoch": 0.89,
|
| 1124 |
+
"eval_loss": 2.825152635574341,
|
| 1125 |
+
"eval_runtime": 442.1075,
|
| 1126 |
+
"eval_samples_per_second": 90.476,
|
| 1127 |
+
"eval_steps_per_second": 11.309,
|
| 1128 |
+
"step": 56000
|
| 1129 |
+
},
|
| 1130 |
+
{
|
| 1131 |
+
"epoch": 0.9,
|
| 1132 |
+
"learning_rate": 2.7343065693430658e-05,
|
| 1133 |
+
"loss": 2.8557,
|
| 1134 |
+
"step": 56500
|
| 1135 |
+
},
|
| 1136 |
+
{
|
| 1137 |
+
"epoch": 0.9,
|
| 1138 |
+
"learning_rate": 2.731934306569343e-05,
|
| 1139 |
+
"loss": 2.8643,
|
| 1140 |
+
"step": 57000
|
| 1141 |
+
},
|
| 1142 |
+
{
|
| 1143 |
+
"epoch": 0.9,
|
| 1144 |
+
"eval_loss": 2.8247392177581787,
|
| 1145 |
+
"eval_runtime": 441.9526,
|
| 1146 |
+
"eval_samples_per_second": 90.507,
|
| 1147 |
+
"eval_steps_per_second": 11.313,
|
| 1148 |
+
"step": 57000
|
| 1149 |
+
},
|
| 1150 |
+
{
|
| 1151 |
+
"epoch": 0.91,
|
| 1152 |
+
"learning_rate": 2.7295620437956205e-05,
|
| 1153 |
+
"loss": 2.8976,
|
| 1154 |
+
"step": 57500
|
| 1155 |
+
},
|
| 1156 |
+
{
|
| 1157 |
+
"epoch": 0.92,
|
| 1158 |
+
"learning_rate": 2.727189781021898e-05,
|
| 1159 |
+
"loss": 2.8658,
|
| 1160 |
+
"step": 58000
|
| 1161 |
+
},
|
| 1162 |
+
{
|
| 1163 |
+
"epoch": 0.92,
|
| 1164 |
+
"eval_loss": 2.8236825466156006,
|
| 1165 |
+
"eval_runtime": 441.9598,
|
| 1166 |
+
"eval_samples_per_second": 90.506,
|
| 1167 |
+
"eval_steps_per_second": 11.313,
|
| 1168 |
+
"step": 58000
|
| 1169 |
+
},
|
| 1170 |
+
{
|
| 1171 |
+
"epoch": 0.93,
|
| 1172 |
+
"learning_rate": 2.7248175182481752e-05,
|
| 1173 |
+
"loss": 2.8608,
|
| 1174 |
+
"step": 58500
|
| 1175 |
+
},
|
| 1176 |
+
{
|
| 1177 |
+
"epoch": 0.94,
|
| 1178 |
+
"learning_rate": 2.7224452554744525e-05,
|
| 1179 |
+
"loss": 2.875,
|
| 1180 |
+
"step": 59000
|
| 1181 |
+
},
|
| 1182 |
+
{
|
| 1183 |
+
"epoch": 0.94,
|
| 1184 |
+
"eval_loss": 2.820819139480591,
|
| 1185 |
+
"eval_runtime": 442.0566,
|
| 1186 |
+
"eval_samples_per_second": 90.486,
|
| 1187 |
+
"eval_steps_per_second": 11.311,
|
| 1188 |
+
"step": 59000
|
| 1189 |
+
},
|
| 1190 |
+
{
|
| 1191 |
+
"epoch": 0.94,
|
| 1192 |
+
"learning_rate": 2.72007299270073e-05,
|
| 1193 |
+
"loss": 2.8704,
|
| 1194 |
+
"step": 59500
|
| 1195 |
+
},
|
| 1196 |
+
{
|
| 1197 |
+
"epoch": 0.95,
|
| 1198 |
+
"learning_rate": 2.7177007299270073e-05,
|
| 1199 |
+
"loss": 2.8531,
|
| 1200 |
+
"step": 60000
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 0.95,
|
| 1204 |
+
"eval_loss": 2.821174144744873,
|
| 1205 |
+
"eval_runtime": 442.2056,
|
| 1206 |
+
"eval_samples_per_second": 90.456,
|
| 1207 |
+
"eval_steps_per_second": 11.307,
|
| 1208 |
+
"step": 60000
|
| 1209 |
+
},
|
| 1210 |
+
{
|
| 1211 |
+
"epoch": 0.96,
|
| 1212 |
+
"learning_rate": 2.715328467153285e-05,
|
| 1213 |
+
"loss": 2.8748,
|
| 1214 |
+
"step": 60500
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 0.97,
|
| 1218 |
+
"learning_rate": 2.712956204379562e-05,
|
| 1219 |
+
"loss": 2.8654,
|
| 1220 |
+
"step": 61000
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 0.97,
|
| 1224 |
+
"eval_loss": 2.825101613998413,
|
| 1225 |
+
"eval_runtime": 442.0952,
|
| 1226 |
+
"eval_samples_per_second": 90.478,
|
| 1227 |
+
"eval_steps_per_second": 11.31,
|
| 1228 |
+
"step": 61000
|
| 1229 |
+
},
|
| 1230 |
+
{
|
| 1231 |
+
"epoch": 0.98,
|
| 1232 |
+
"learning_rate": 2.7105839416058397e-05,
|
| 1233 |
+
"loss": 2.8515,
|
| 1234 |
+
"step": 61500
|
| 1235 |
+
},
|
| 1236 |
+
{
|
| 1237 |
+
"epoch": 0.98,
|
| 1238 |
+
"learning_rate": 2.7082116788321167e-05,
|
| 1239 |
+
"loss": 2.8432,
|
| 1240 |
+
"step": 62000
|
| 1241 |
+
},
|
| 1242 |
+
{
|
| 1243 |
+
"epoch": 0.98,
|
| 1244 |
+
"eval_loss": 2.819878101348877,
|
| 1245 |
+
"eval_runtime": 441.9364,
|
| 1246 |
+
"eval_samples_per_second": 90.511,
|
| 1247 |
+
"eval_steps_per_second": 11.314,
|
| 1248 |
+
"step": 62000
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 0.99,
|
| 1252 |
+
"learning_rate": 2.7058394160583944e-05,
|
| 1253 |
+
"loss": 2.8591,
|
| 1254 |
+
"step": 62500
|
| 1255 |
+
},
|
| 1256 |
+
{
|
| 1257 |
+
"epoch": 1.0,
|
| 1258 |
+
"learning_rate": 2.7034671532846717e-05,
|
| 1259 |
+
"loss": 2.8871,
|
| 1260 |
+
"step": 63000
|
| 1261 |
+
},
|
| 1262 |
+
{
|
| 1263 |
+
"epoch": 1.0,
|
| 1264 |
+
"eval_loss": 2.8195338249206543,
|
| 1265 |
+
"eval_runtime": 442.0595,
|
| 1266 |
+
"eval_samples_per_second": 90.486,
|
| 1267 |
+
"eval_steps_per_second": 11.311,
|
| 1268 |
+
"step": 63000
|
| 1269 |
+
},
|
| 1270 |
+
{
|
| 1271 |
+
"epoch": 1.01,
|
| 1272 |
+
"learning_rate": 2.7010948905109487e-05,
|
| 1273 |
+
"loss": 2.7957,
|
| 1274 |
+
"step": 63500
|
| 1275 |
+
},
|
| 1276 |
+
{
|
| 1277 |
+
"epoch": 1.01,
|
| 1278 |
+
"learning_rate": 2.6987226277372264e-05,
|
| 1279 |
+
"loss": 2.7854,
|
| 1280 |
+
"step": 64000
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 1.01,
|
| 1284 |
+
"eval_loss": 2.817440986633301,
|
| 1285 |
+
"eval_runtime": 442.0252,
|
| 1286 |
+
"eval_samples_per_second": 90.493,
|
| 1287 |
+
"eval_steps_per_second": 11.312,
|
| 1288 |
+
"step": 64000
|
| 1289 |
+
},
|
| 1290 |
+
{
|
| 1291 |
+
"epoch": 1.02,
|
| 1292 |
+
"learning_rate": 2.6963503649635034e-05,
|
| 1293 |
+
"loss": 2.7874,
|
| 1294 |
+
"step": 64500
|
| 1295 |
+
},
|
| 1296 |
+
{
|
| 1297 |
+
"epoch": 1.03,
|
| 1298 |
+
"learning_rate": 2.693978102189781e-05,
|
| 1299 |
+
"loss": 2.7703,
|
| 1300 |
+
"step": 65000
|
| 1301 |
+
},
|
| 1302 |
+
{
|
| 1303 |
+
"epoch": 1.03,
|
| 1304 |
+
"eval_loss": 2.8208272457122803,
|
| 1305 |
+
"eval_runtime": 442.1489,
|
| 1306 |
+
"eval_samples_per_second": 90.467,
|
| 1307 |
+
"eval_steps_per_second": 11.308,
|
| 1308 |
+
"step": 65000
|
| 1309 |
+
},
|
| 1310 |
+
{
|
| 1311 |
+
"epoch": 1.04,
|
| 1312 |
+
"learning_rate": 2.6916058394160585e-05,
|
| 1313 |
+
"loss": 2.7773,
|
| 1314 |
+
"step": 65500
|
| 1315 |
+
},
|
| 1316 |
+
{
|
| 1317 |
+
"epoch": 1.05,
|
| 1318 |
+
"learning_rate": 2.689233576642336e-05,
|
| 1319 |
+
"loss": 2.7764,
|
| 1320 |
+
"step": 66000
|
| 1321 |
+
},
|
| 1322 |
+
{
|
| 1323 |
+
"epoch": 1.05,
|
| 1324 |
+
"eval_loss": 2.8173325061798096,
|
| 1325 |
+
"eval_runtime": 443.1184,
|
| 1326 |
+
"eval_samples_per_second": 90.269,
|
| 1327 |
+
"eval_steps_per_second": 11.284,
|
| 1328 |
+
"step": 66000
|
| 1329 |
+
},
|
| 1330 |
+
{
|
| 1331 |
+
"epoch": 1.05,
|
| 1332 |
+
"learning_rate": 2.6868613138686132e-05,
|
| 1333 |
+
"loss": 2.7838,
|
| 1334 |
+
"step": 66500
|
| 1335 |
+
},
|
| 1336 |
+
{
|
| 1337 |
+
"epoch": 1.06,
|
| 1338 |
+
"learning_rate": 2.6844890510948906e-05,
|
| 1339 |
+
"loss": 2.7734,
|
| 1340 |
+
"step": 67000
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"epoch": 1.06,
|
| 1344 |
+
"eval_loss": 2.812627077102661,
|
| 1345 |
+
"eval_runtime": 443.0624,
|
| 1346 |
+
"eval_samples_per_second": 90.281,
|
| 1347 |
+
"eval_steps_per_second": 11.285,
|
| 1348 |
+
"step": 67000
|
| 1349 |
+
},
|
| 1350 |
+
{
|
| 1351 |
+
"epoch": 1.07,
|
| 1352 |
+
"learning_rate": 2.682116788321168e-05,
|
| 1353 |
+
"loss": 2.7541,
|
| 1354 |
+
"step": 67500
|
| 1355 |
+
},
|
| 1356 |
+
{
|
| 1357 |
+
"epoch": 1.08,
|
| 1358 |
+
"learning_rate": 2.6797445255474456e-05,
|
| 1359 |
+
"loss": 2.7637,
|
| 1360 |
+
"step": 68000
|
| 1361 |
+
},
|
| 1362 |
+
{
|
| 1363 |
+
"epoch": 1.08,
|
| 1364 |
+
"eval_loss": 2.817030668258667,
|
| 1365 |
+
"eval_runtime": 443.2279,
|
| 1366 |
+
"eval_samples_per_second": 90.247,
|
| 1367 |
+
"eval_steps_per_second": 11.281,
|
| 1368 |
+
"step": 68000
|
| 1369 |
+
},
|
| 1370 |
+
{
|
| 1371 |
+
"epoch": 1.09,
|
| 1372 |
+
"learning_rate": 2.6773722627737226e-05,
|
| 1373 |
+
"loss": 2.7809,
|
| 1374 |
+
"step": 68500
|
| 1375 |
+
},
|
| 1376 |
+
{
|
| 1377 |
+
"epoch": 1.09,
|
| 1378 |
+
"learning_rate": 2.675e-05,
|
| 1379 |
+
"loss": 2.775,
|
| 1380 |
+
"step": 69000
|
| 1381 |
+
},
|
| 1382 |
+
{
|
| 1383 |
+
"epoch": 1.09,
|
| 1384 |
+
"eval_loss": 2.819810628890991,
|
| 1385 |
+
"eval_runtime": 442.8797,
|
| 1386 |
+
"eval_samples_per_second": 90.318,
|
| 1387 |
+
"eval_steps_per_second": 11.29,
|
| 1388 |
+
"step": 69000
|
| 1389 |
+
},
|
| 1390 |
+
{
|
| 1391 |
+
"epoch": 1.1,
|
| 1392 |
+
"learning_rate": 2.6726277372262777e-05,
|
| 1393 |
+
"loss": 2.786,
|
| 1394 |
+
"step": 69500
|
| 1395 |
+
},
|
| 1396 |
+
{
|
| 1397 |
+
"epoch": 1.11,
|
| 1398 |
+
"learning_rate": 2.6702554744525547e-05,
|
| 1399 |
+
"loss": 2.747,
|
| 1400 |
+
"step": 70000
|
| 1401 |
+
},
|
| 1402 |
+
{
|
| 1403 |
+
"epoch": 1.11,
|
| 1404 |
+
"eval_loss": 2.820467233657837,
|
| 1405 |
+
"eval_runtime": 443.0381,
|
| 1406 |
+
"eval_samples_per_second": 90.286,
|
| 1407 |
+
"eval_steps_per_second": 11.286,
|
| 1408 |
+
"step": 70000
|
| 1409 |
+
},
|
| 1410 |
+
{
|
| 1411 |
+
"epoch": 1.12,
|
| 1412 |
+
"learning_rate": 2.6678832116788324e-05,
|
| 1413 |
+
"loss": 2.801,
|
| 1414 |
+
"step": 70500
|
| 1415 |
+
},
|
| 1416 |
+
{
|
| 1417 |
+
"epoch": 1.13,
|
| 1418 |
+
"learning_rate": 2.6655109489051094e-05,
|
| 1419 |
+
"loss": 2.7589,
|
| 1420 |
+
"step": 71000
|
| 1421 |
+
},
|
| 1422 |
+
{
|
| 1423 |
+
"epoch": 1.13,
|
| 1424 |
+
"eval_loss": 2.8193023204803467,
|
| 1425 |
+
"eval_runtime": 443.2053,
|
| 1426 |
+
"eval_samples_per_second": 90.252,
|
| 1427 |
+
"eval_steps_per_second": 11.281,
|
| 1428 |
+
"step": 71000
|
| 1429 |
+
},
|
| 1430 |
+
{
|
| 1431 |
+
"epoch": 1.13,
|
| 1432 |
+
"learning_rate": 2.663138686131387e-05,
|
| 1433 |
+
"loss": 2.7801,
|
| 1434 |
+
"step": 71500
|
| 1435 |
+
},
|
| 1436 |
+
{
|
| 1437 |
+
"epoch": 1.14,
|
| 1438 |
+
"learning_rate": 2.6607664233576644e-05,
|
| 1439 |
+
"loss": 2.7521,
|
| 1440 |
+
"step": 72000
|
| 1441 |
+
},
|
| 1442 |
+
{
|
| 1443 |
+
"epoch": 1.14,
|
| 1444 |
+
"eval_loss": 2.813857078552246,
|
| 1445 |
+
"eval_runtime": 443.2947,
|
| 1446 |
+
"eval_samples_per_second": 90.233,
|
| 1447 |
+
"eval_steps_per_second": 11.279,
|
| 1448 |
+
"step": 72000
|
| 1449 |
+
},
|
| 1450 |
+
{
|
| 1451 |
+
"epoch": 1.15,
|
| 1452 |
+
"learning_rate": 2.6583941605839414e-05,
|
| 1453 |
+
"loss": 2.7876,
|
| 1454 |
+
"step": 72500
|
| 1455 |
+
},
|
| 1456 |
+
{
|
| 1457 |
+
"epoch": 1.16,
|
| 1458 |
+
"learning_rate": 2.656021897810219e-05,
|
| 1459 |
+
"loss": 2.772,
|
| 1460 |
+
"step": 73000
|
| 1461 |
+
},
|
| 1462 |
+
{
|
| 1463 |
+
"epoch": 1.16,
|
| 1464 |
+
"eval_loss": 2.814068555831909,
|
| 1465 |
+
"eval_runtime": 443.3415,
|
| 1466 |
+
"eval_samples_per_second": 90.224,
|
| 1467 |
+
"eval_steps_per_second": 11.278,
|
| 1468 |
+
"step": 73000
|
| 1469 |
+
},
|
| 1470 |
+
{
|
| 1471 |
+
"epoch": 1.17,
|
| 1472 |
+
"learning_rate": 2.653649635036496e-05,
|
| 1473 |
+
"loss": 2.7618,
|
| 1474 |
+
"step": 73500
|
| 1475 |
+
},
|
| 1476 |
+
{
|
| 1477 |
+
"epoch": 1.17,
|
| 1478 |
+
"learning_rate": 2.651277372262774e-05,
|
| 1479 |
+
"loss": 2.785,
|
| 1480 |
+
"step": 74000
|
| 1481 |
+
},
|
| 1482 |
+
{
|
| 1483 |
+
"epoch": 1.17,
|
| 1484 |
+
"eval_loss": 2.8143815994262695,
|
| 1485 |
+
"eval_runtime": 443.2942,
|
| 1486 |
+
"eval_samples_per_second": 90.234,
|
| 1487 |
+
"eval_steps_per_second": 11.279,
|
| 1488 |
+
"step": 74000
|
| 1489 |
+
},
|
| 1490 |
+
{
|
| 1491 |
+
"epoch": 1.18,
|
| 1492 |
+
"learning_rate": 2.6489051094890512e-05,
|
| 1493 |
+
"loss": 2.7878,
|
| 1494 |
+
"step": 74500
|
| 1495 |
+
},
|
| 1496 |
+
{
|
| 1497 |
+
"epoch": 1.19,
|
| 1498 |
+
"learning_rate": 2.6465328467153286e-05,
|
| 1499 |
+
"loss": 2.743,
|
| 1500 |
+
"step": 75000
|
| 1501 |
+
},
|
| 1502 |
+
{
|
| 1503 |
+
"epoch": 1.19,
|
| 1504 |
+
"eval_loss": 2.8167881965637207,
|
| 1505 |
+
"eval_runtime": 443.0056,
|
| 1506 |
+
"eval_samples_per_second": 90.292,
|
| 1507 |
+
"eval_steps_per_second": 11.287,
|
| 1508 |
+
"step": 75000
|
| 1509 |
+
},
|
| 1510 |
+
{
|
| 1511 |
+
"epoch": 1.2,
|
| 1512 |
+
"learning_rate": 2.644160583941606e-05,
|
| 1513 |
+
"loss": 2.7564,
|
| 1514 |
+
"step": 75500
|
| 1515 |
+
},
|
| 1516 |
+
{
|
| 1517 |
+
"epoch": 1.21,
|
| 1518 |
+
"learning_rate": 2.6417883211678833e-05,
|
| 1519 |
+
"loss": 2.7694,
|
| 1520 |
+
"step": 76000
|
| 1521 |
+
},
|
| 1522 |
+
{
|
| 1523 |
+
"epoch": 1.21,
|
| 1524 |
+
"eval_loss": 2.8128414154052734,
|
| 1525 |
+
"eval_runtime": 443.1543,
|
| 1526 |
+
"eval_samples_per_second": 90.262,
|
| 1527 |
+
"eval_steps_per_second": 11.283,
|
| 1528 |
+
"step": 76000
|
| 1529 |
+
},
|
| 1530 |
+
{
|
| 1531 |
+
"epoch": 1.21,
|
| 1532 |
+
"learning_rate": 2.6394160583941606e-05,
|
| 1533 |
+
"loss": 2.7583,
|
| 1534 |
+
"step": 76500
|
| 1535 |
+
},
|
| 1536 |
+
{
|
| 1537 |
+
"epoch": 1.22,
|
| 1538 |
+
"learning_rate": 2.6370437956204383e-05,
|
| 1539 |
+
"loss": 2.7769,
|
| 1540 |
+
"step": 77000
|
| 1541 |
+
},
|
| 1542 |
+
{
|
| 1543 |
+
"epoch": 1.22,
|
| 1544 |
+
"eval_loss": 2.8131983280181885,
|
| 1545 |
+
"eval_runtime": 443.0764,
|
| 1546 |
+
"eval_samples_per_second": 90.278,
|
| 1547 |
+
"eval_steps_per_second": 11.285,
|
| 1548 |
+
"step": 77000
|
| 1549 |
+
},
|
| 1550 |
+
{
|
| 1551 |
+
"epoch": 1.23,
|
| 1552 |
+
"learning_rate": 2.6346715328467153e-05,
|
| 1553 |
+
"loss": 2.7623,
|
| 1554 |
+
"step": 77500
|
| 1555 |
+
},
|
| 1556 |
+
{
|
| 1557 |
+
"epoch": 1.24,
|
| 1558 |
+
"learning_rate": 2.6322992700729927e-05,
|
| 1559 |
+
"loss": 2.7523,
|
| 1560 |
+
"step": 78000
|
| 1561 |
+
},
|
| 1562 |
+
{
|
| 1563 |
+
"epoch": 1.24,
|
| 1564 |
+
"eval_loss": 2.813045024871826,
|
| 1565 |
+
"eval_runtime": 443.0803,
|
| 1566 |
+
"eval_samples_per_second": 90.277,
|
| 1567 |
+
"eval_steps_per_second": 11.285,
|
| 1568 |
+
"step": 78000
|
| 1569 |
+
},
|
| 1570 |
+
{
|
| 1571 |
+
"epoch": 1.24,
|
| 1572 |
+
"learning_rate": 2.62992700729927e-05,
|
| 1573 |
+
"loss": 2.7569,
|
| 1574 |
+
"step": 78500
|
| 1575 |
+
},
|
| 1576 |
+
{
|
| 1577 |
+
"epoch": 1.25,
|
| 1578 |
+
"learning_rate": 2.6275547445255474e-05,
|
| 1579 |
+
"loss": 2.7572,
|
| 1580 |
+
"step": 79000
|
| 1581 |
+
},
|
| 1582 |
+
{
|
| 1583 |
+
"epoch": 1.25,
|
| 1584 |
+
"eval_loss": 2.8214099407196045,
|
| 1585 |
+
"eval_runtime": 442.9545,
|
| 1586 |
+
"eval_samples_per_second": 90.303,
|
| 1587 |
+
"eval_steps_per_second": 11.288,
|
| 1588 |
+
"step": 79000
|
| 1589 |
+
},
|
| 1590 |
+
{
|
| 1591 |
+
"epoch": 1.26,
|
| 1592 |
+
"learning_rate": 2.625182481751825e-05,
|
| 1593 |
+
"loss": 2.7564,
|
| 1594 |
+
"step": 79500
|
| 1595 |
+
},
|
| 1596 |
+
{
|
| 1597 |
+
"epoch": 1.27,
|
| 1598 |
+
"learning_rate": 2.622810218978102e-05,
|
| 1599 |
+
"loss": 2.7573,
|
| 1600 |
+
"step": 80000
|
| 1601 |
+
},
|
| 1602 |
+
{
|
| 1603 |
+
"epoch": 1.27,
|
| 1604 |
+
"eval_loss": 2.811310052871704,
|
| 1605 |
+
"eval_runtime": 442.9337,
|
| 1606 |
+
"eval_samples_per_second": 90.307,
|
| 1607 |
+
"eval_steps_per_second": 11.288,
|
| 1608 |
+
"step": 80000
|
| 1609 |
+
},
|
| 1610 |
+
{
|
| 1611 |
+
"epoch": 1.28,
|
| 1612 |
+
"learning_rate": 2.6204379562043798e-05,
|
| 1613 |
+
"loss": 2.7635,
|
| 1614 |
+
"step": 80500
|
| 1615 |
+
},
|
| 1616 |
+
{
|
| 1617 |
+
"epoch": 1.28,
|
| 1618 |
+
"learning_rate": 2.6180656934306568e-05,
|
| 1619 |
+
"loss": 2.7514,
|
| 1620 |
+
"step": 81000
|
| 1621 |
+
},
|
| 1622 |
+
{
|
| 1623 |
+
"epoch": 1.28,
|
| 1624 |
+
"eval_loss": 2.8111774921417236,
|
| 1625 |
+
"eval_runtime": 442.9468,
|
| 1626 |
+
"eval_samples_per_second": 90.304,
|
| 1627 |
+
"eval_steps_per_second": 11.288,
|
| 1628 |
+
"step": 81000
|
| 1629 |
+
},
|
| 1630 |
+
{
|
| 1631 |
+
"epoch": 1.29,
|
| 1632 |
+
"learning_rate": 2.615693430656934e-05,
|
| 1633 |
+
"loss": 2.7534,
|
| 1634 |
+
"step": 81500
|
| 1635 |
+
},
|
| 1636 |
+
{
|
| 1637 |
+
"epoch": 1.3,
|
| 1638 |
+
"learning_rate": 2.613321167883212e-05,
|
| 1639 |
+
"loss": 2.7676,
|
| 1640 |
+
"step": 82000
|
| 1641 |
+
},
|
| 1642 |
+
{
|
| 1643 |
+
"epoch": 1.3,
|
| 1644 |
+
"eval_loss": 2.8070504665374756,
|
| 1645 |
+
"eval_runtime": 442.7918,
|
| 1646 |
+
"eval_samples_per_second": 90.336,
|
| 1647 |
+
"eval_steps_per_second": 11.292,
|
| 1648 |
+
"step": 82000
|
| 1649 |
+
},
|
| 1650 |
+
{
|
| 1651 |
+
"epoch": 1.31,
|
| 1652 |
+
"learning_rate": 2.6109489051094892e-05,
|
| 1653 |
+
"loss": 2.7212,
|
| 1654 |
+
"step": 82500
|
| 1655 |
+
},
|
| 1656 |
+
{
|
| 1657 |
+
"epoch": 1.32,
|
| 1658 |
+
"learning_rate": 2.6085766423357666e-05,
|
| 1659 |
+
"loss": 2.7044,
|
| 1660 |
+
"step": 83000
|
| 1661 |
+
},
|
| 1662 |
+
{
|
| 1663 |
+
"epoch": 1.32,
|
| 1664 |
+
"eval_loss": 2.8113818168640137,
|
| 1665 |
+
"eval_runtime": 440.1567,
|
| 1666 |
+
"eval_samples_per_second": 90.877,
|
| 1667 |
+
"eval_steps_per_second": 11.36,
|
| 1668 |
+
"step": 83000
|
| 1669 |
+
},
|
| 1670 |
+
{
|
| 1671 |
+
"epoch": 1.32,
|
| 1672 |
+
"learning_rate": 2.6062043795620436e-05,
|
| 1673 |
+
"loss": 2.742,
|
| 1674 |
+
"step": 83500
|
| 1675 |
+
},
|
| 1676 |
+
{
|
| 1677 |
+
"epoch": 1.33,
|
| 1678 |
+
"learning_rate": 2.6038321167883213e-05,
|
| 1679 |
+
"loss": 2.7205,
|
| 1680 |
+
"step": 84000
|
| 1681 |
+
},
|
| 1682 |
+
{
|
| 1683 |
+
"epoch": 1.33,
|
| 1684 |
+
"eval_loss": 2.810499906539917,
|
| 1685 |
+
"eval_runtime": 440.19,
|
| 1686 |
+
"eval_samples_per_second": 90.87,
|
| 1687 |
+
"eval_steps_per_second": 11.359,
|
| 1688 |
+
"step": 84000
|
| 1689 |
+
},
|
| 1690 |
+
{
|
| 1691 |
+
"epoch": 1.34,
|
| 1692 |
+
"learning_rate": 2.6014598540145986e-05,
|
| 1693 |
+
"loss": 2.7065,
|
| 1694 |
+
"step": 84500
|
| 1695 |
+
},
|
| 1696 |
+
{
|
| 1697 |
+
"epoch": 1.35,
|
| 1698 |
+
"learning_rate": 2.599087591240876e-05,
|
| 1699 |
+
"loss": 2.7168,
|
| 1700 |
+
"step": 85000
|
| 1701 |
+
},
|
| 1702 |
+
{
|
| 1703 |
+
"epoch": 1.35,
|
| 1704 |
+
"eval_loss": 2.813863754272461,
|
| 1705 |
+
"eval_runtime": 440.1828,
|
| 1706 |
+
"eval_samples_per_second": 90.871,
|
| 1707 |
+
"eval_steps_per_second": 11.359,
|
| 1708 |
+
"step": 85000
|
| 1709 |
+
},
|
| 1710 |
+
{
|
| 1711 |
+
"epoch": 1.36,
|
| 1712 |
+
"learning_rate": 2.5967153284671533e-05,
|
| 1713 |
+
"loss": 2.7367,
|
| 1714 |
+
"step": 85500
|
| 1715 |
+
},
|
| 1716 |
+
{
|
| 1717 |
+
"epoch": 1.36,
|
| 1718 |
+
"learning_rate": 2.5943430656934307e-05,
|
| 1719 |
+
"loss": 2.7337,
|
| 1720 |
+
"step": 86000
|
| 1721 |
+
},
|
| 1722 |
+
{
|
| 1723 |
+
"epoch": 1.36,
|
| 1724 |
+
"eval_loss": 2.80753231048584,
|
| 1725 |
+
"eval_runtime": 439.9369,
|
| 1726 |
+
"eval_samples_per_second": 90.922,
|
| 1727 |
+
"eval_steps_per_second": 11.365,
|
| 1728 |
+
"step": 86000
|
| 1729 |
+
},
|
| 1730 |
+
{
|
| 1731 |
+
"epoch": 1.37,
|
| 1732 |
+
"learning_rate": 2.591970802919708e-05,
|
| 1733 |
+
"loss": 2.718,
|
| 1734 |
+
"step": 86500
|
| 1735 |
+
},
|
| 1736 |
+
{
|
| 1737 |
+
"epoch": 1.38,
|
| 1738 |
+
"learning_rate": 2.5895985401459854e-05,
|
| 1739 |
+
"loss": 2.709,
|
| 1740 |
+
"step": 87000
|
| 1741 |
+
},
|
| 1742 |
+
{
|
| 1743 |
+
"epoch": 1.38,
|
| 1744 |
+
"eval_loss": 2.8110671043395996,
|
| 1745 |
+
"eval_runtime": 439.984,
|
| 1746 |
+
"eval_samples_per_second": 90.912,
|
| 1747 |
+
"eval_steps_per_second": 11.364,
|
| 1748 |
+
"step": 87000
|
| 1749 |
+
},
|
| 1750 |
+
{
|
| 1751 |
+
"epoch": 1.39,
|
| 1752 |
+
"learning_rate": 2.5872262773722628e-05,
|
| 1753 |
+
"loss": 2.7045,
|
| 1754 |
+
"step": 87500
|
| 1755 |
+
},
|
| 1756 |
+
{
|
| 1757 |
+
"epoch": 1.4,
|
| 1758 |
+
"learning_rate": 2.58485401459854e-05,
|
| 1759 |
+
"loss": 2.7449,
|
| 1760 |
+
"step": 88000
|
| 1761 |
+
},
|
| 1762 |
+
{
|
| 1763 |
+
"epoch": 1.4,
|
| 1764 |
+
"eval_loss": 2.806777238845825,
|
| 1765 |
+
"eval_runtime": 439.8672,
|
| 1766 |
+
"eval_samples_per_second": 90.937,
|
| 1767 |
+
"eval_steps_per_second": 11.367,
|
| 1768 |
+
"step": 88000
|
| 1769 |
+
},
|
| 1770 |
+
{
|
| 1771 |
+
"epoch": 1.4,
|
| 1772 |
+
"learning_rate": 2.5824817518248178e-05,
|
| 1773 |
+
"loss": 2.704,
|
| 1774 |
+
"step": 88500
|
| 1775 |
+
},
|
| 1776 |
+
{
|
| 1777 |
+
"epoch": 1.41,
|
| 1778 |
+
"learning_rate": 2.5801094890510948e-05,
|
| 1779 |
+
"loss": 2.7175,
|
| 1780 |
+
"step": 89000
|
| 1781 |
+
},
|
| 1782 |
+
{
|
| 1783 |
+
"epoch": 1.41,
|
| 1784 |
+
"eval_loss": 2.8058323860168457,
|
| 1785 |
+
"eval_runtime": 439.8993,
|
| 1786 |
+
"eval_samples_per_second": 90.93,
|
| 1787 |
+
"eval_steps_per_second": 11.366,
|
| 1788 |
+
"step": 89000
|
| 1789 |
+
},
|
| 1790 |
+
{
|
| 1791 |
+
"epoch": 1.42,
|
| 1792 |
+
"learning_rate": 2.5777372262773725e-05,
|
| 1793 |
+
"loss": 2.7292,
|
| 1794 |
+
"step": 89500
|
| 1795 |
+
},
|
| 1796 |
+
{
|
| 1797 |
+
"epoch": 1.43,
|
| 1798 |
+
"learning_rate": 2.5753649635036495e-05,
|
| 1799 |
+
"loss": 2.7096,
|
| 1800 |
+
"step": 90000
|
| 1801 |
+
},
|
| 1802 |
+
{
|
| 1803 |
+
"epoch": 1.43,
|
| 1804 |
+
"eval_loss": 2.808027744293213,
|
| 1805 |
+
"eval_runtime": 439.7855,
|
| 1806 |
+
"eval_samples_per_second": 90.953,
|
| 1807 |
+
"eval_steps_per_second": 11.369,
|
| 1808 |
+
"step": 90000
|
| 1809 |
+
},
|
| 1810 |
+
{
|
| 1811 |
+
"epoch": 1.43,
|
| 1812 |
+
"learning_rate": 2.572992700729927e-05,
|
| 1813 |
+
"loss": 2.7125,
|
| 1814 |
+
"step": 90500
|
| 1815 |
+
},
|
| 1816 |
+
{
|
| 1817 |
+
"epoch": 1.44,
|
| 1818 |
+
"learning_rate": 2.5706204379562046e-05,
|
| 1819 |
+
"loss": 2.7272,
|
| 1820 |
+
"step": 91000
|
| 1821 |
+
},
|
| 1822 |
+
{
|
| 1823 |
+
"epoch": 1.44,
|
| 1824 |
+
"eval_loss": 2.8089358806610107,
|
| 1825 |
+
"eval_runtime": 439.8804,
|
| 1826 |
+
"eval_samples_per_second": 90.934,
|
| 1827 |
+
"eval_steps_per_second": 11.367,
|
| 1828 |
+
"step": 91000
|
| 1829 |
+
},
|
| 1830 |
+
{
|
| 1831 |
+
"epoch": 1.45,
|
| 1832 |
+
"learning_rate": 2.568248175182482e-05,
|
| 1833 |
+
"loss": 2.719,
|
| 1834 |
+
"step": 91500
|
| 1835 |
+
},
|
| 1836 |
+
{
|
| 1837 |
+
"epoch": 1.46,
|
| 1838 |
+
"learning_rate": 2.5658759124087593e-05,
|
| 1839 |
+
"loss": 2.7092,
|
| 1840 |
+
"step": 92000
|
| 1841 |
+
},
|
| 1842 |
+
{
|
| 1843 |
+
"epoch": 1.46,
|
| 1844 |
+
"eval_loss": 2.806529998779297,
|
| 1845 |
+
"eval_runtime": 439.7422,
|
| 1846 |
+
"eval_samples_per_second": 90.962,
|
| 1847 |
+
"eval_steps_per_second": 11.37,
|
| 1848 |
+
"step": 92000
|
| 1849 |
+
},
|
| 1850 |
+
{
|
| 1851 |
+
"epoch": 1.47,
|
| 1852 |
+
"learning_rate": 2.5635036496350363e-05,
|
| 1853 |
+
"loss": 2.7121,
|
| 1854 |
+
"step": 92500
|
| 1855 |
+
},
|
| 1856 |
+
{
|
| 1857 |
+
"epoch": 1.47,
|
| 1858 |
+
"learning_rate": 2.561131386861314e-05,
|
| 1859 |
+
"loss": 2.6846,
|
| 1860 |
+
"step": 93000
|
| 1861 |
+
},
|
| 1862 |
+
{
|
| 1863 |
+
"epoch": 1.47,
|
| 1864 |
+
"eval_loss": 2.804901123046875,
|
| 1865 |
+
"eval_runtime": 440.0389,
|
| 1866 |
+
"eval_samples_per_second": 90.901,
|
| 1867 |
+
"eval_steps_per_second": 11.363,
|
| 1868 |
+
"step": 93000
|
| 1869 |
+
},
|
| 1870 |
+
{
|
| 1871 |
+
"epoch": 1.48,
|
| 1872 |
+
"learning_rate": 2.5587591240875913e-05,
|
| 1873 |
+
"loss": 2.7301,
|
| 1874 |
+
"step": 93500
|
| 1875 |
+
},
|
| 1876 |
+
{
|
| 1877 |
+
"epoch": 1.49,
|
| 1878 |
+
"learning_rate": 2.5563868613138687e-05,
|
| 1879 |
+
"loss": 2.6976,
|
| 1880 |
+
"step": 94000
|
| 1881 |
+
},
|
| 1882 |
+
{
|
| 1883 |
+
"epoch": 1.49,
|
| 1884 |
+
"eval_loss": 2.8061363697052,
|
| 1885 |
+
"eval_runtime": 439.8304,
|
| 1886 |
+
"eval_samples_per_second": 90.944,
|
| 1887 |
+
"eval_steps_per_second": 11.368,
|
| 1888 |
+
"step": 94000
|
| 1889 |
+
},
|
| 1890 |
+
{
|
| 1891 |
+
"epoch": 1.5,
|
| 1892 |
+
"learning_rate": 2.554014598540146e-05,
|
| 1893 |
+
"loss": 2.7008,
|
| 1894 |
+
"step": 94500
|
| 1895 |
+
},
|
| 1896 |
+
{
|
| 1897 |
+
"epoch": 1.51,
|
| 1898 |
+
"learning_rate": 2.5516423357664234e-05,
|
| 1899 |
+
"loss": 2.7057,
|
| 1900 |
+
"step": 95000
|
| 1901 |
+
},
|
| 1902 |
+
{
|
| 1903 |
+
"epoch": 1.51,
|
| 1904 |
+
"eval_loss": 2.815894603729248,
|
| 1905 |
+
"eval_runtime": 439.7552,
|
| 1906 |
+
"eval_samples_per_second": 90.96,
|
| 1907 |
+
"eval_steps_per_second": 11.37,
|
| 1908 |
+
"step": 95000
|
| 1909 |
+
},
|
| 1910 |
+
{
|
| 1911 |
+
"epoch": 1.51,
|
| 1912 |
+
"learning_rate": 2.5492700729927008e-05,
|
| 1913 |
+
"loss": 2.724,
|
| 1914 |
+
"step": 95500
|
| 1915 |
+
},
|
| 1916 |
+
{
|
| 1917 |
+
"epoch": 1.52,
|
| 1918 |
+
"learning_rate": 2.546897810218978e-05,
|
| 1919 |
+
"loss": 2.6922,
|
| 1920 |
+
"step": 96000
|
| 1921 |
+
},
|
| 1922 |
+
{
|
| 1923 |
+
"epoch": 1.52,
|
| 1924 |
+
"eval_loss": 2.8022561073303223,
|
| 1925 |
+
"eval_runtime": 439.8096,
|
| 1926 |
+
"eval_samples_per_second": 90.948,
|
| 1927 |
+
"eval_steps_per_second": 11.369,
|
| 1928 |
+
"step": 96000
|
| 1929 |
+
},
|
| 1930 |
+
{
|
| 1931 |
+
"epoch": 1.53,
|
| 1932 |
+
"learning_rate": 2.5445255474452555e-05,
|
| 1933 |
+
"loss": 2.7095,
|
| 1934 |
+
"step": 96500
|
| 1935 |
+
},
|
| 1936 |
+
{
|
| 1937 |
+
"epoch": 1.54,
|
| 1938 |
+
"learning_rate": 2.542153284671533e-05,
|
| 1939 |
+
"loss": 2.7011,
|
| 1940 |
+
"step": 97000
|
| 1941 |
+
},
|
| 1942 |
+
{
|
| 1943 |
+
"epoch": 1.54,
|
| 1944 |
+
"eval_loss": 2.801751136779785,
|
| 1945 |
+
"eval_runtime": 439.7019,
|
| 1946 |
+
"eval_samples_per_second": 90.971,
|
| 1947 |
+
"eval_steps_per_second": 11.371,
|
| 1948 |
+
"step": 97000
|
| 1949 |
+
},
|
| 1950 |
+
{
|
| 1951 |
+
"epoch": 1.55,
|
| 1952 |
+
"learning_rate": 2.5397810218978102e-05,
|
| 1953 |
+
"loss": 2.7212,
|
| 1954 |
+
"step": 97500
|
| 1955 |
+
},
|
| 1956 |
+
{
|
| 1957 |
+
"epoch": 1.55,
|
| 1958 |
+
"learning_rate": 2.5374087591240875e-05,
|
| 1959 |
+
"loss": 2.7029,
|
| 1960 |
+
"step": 98000
|
| 1961 |
+
},
|
| 1962 |
+
{
|
| 1963 |
+
"epoch": 1.55,
|
| 1964 |
+
"eval_loss": 2.8029119968414307,
|
| 1965 |
+
"eval_runtime": 439.744,
|
| 1966 |
+
"eval_samples_per_second": 90.962,
|
| 1967 |
+
"eval_steps_per_second": 11.37,
|
| 1968 |
+
"step": 98000
|
| 1969 |
+
},
|
| 1970 |
+
{
|
| 1971 |
+
"epoch": 1.56,
|
| 1972 |
+
"learning_rate": 2.5350364963503652e-05,
|
| 1973 |
+
"loss": 2.7055,
|
| 1974 |
+
"step": 98500
|
| 1975 |
+
},
|
| 1976 |
+
{
|
| 1977 |
+
"epoch": 1.57,
|
| 1978 |
+
"learning_rate": 2.5326642335766422e-05,
|
| 1979 |
+
"loss": 2.701,
|
| 1980 |
+
"step": 99000
|
| 1981 |
+
},
|
| 1982 |
+
{
|
| 1983 |
+
"epoch": 1.57,
|
| 1984 |
+
"eval_loss": 2.800555944442749,
|
| 1985 |
+
"eval_runtime": 439.7759,
|
| 1986 |
+
"eval_samples_per_second": 90.955,
|
| 1987 |
+
"eval_steps_per_second": 11.369,
|
| 1988 |
+
"step": 99000
|
| 1989 |
+
},
|
| 1990 |
+
{
|
| 1991 |
+
"epoch": 1.58,
|
| 1992 |
+
"learning_rate": 2.53029197080292e-05,
|
| 1993 |
+
"loss": 2.7136,
|
| 1994 |
+
"step": 99500
|
| 1995 |
+
},
|
| 1996 |
+
{
|
| 1997 |
+
"epoch": 1.59,
|
| 1998 |
+
"learning_rate": 2.527919708029197e-05,
|
| 1999 |
+
"loss": 2.7044,
|
| 2000 |
+
"step": 100000
|
| 2001 |
+
},
|
| 2002 |
+
{
|
| 2003 |
+
"epoch": 1.59,
|
| 2004 |
+
"eval_loss": 2.8019235134124756,
|
| 2005 |
+
"eval_runtime": 439.7518,
|
| 2006 |
+
"eval_samples_per_second": 90.96,
|
| 2007 |
+
"eval_steps_per_second": 11.37,
|
| 2008 |
+
"step": 100000
|
| 2009 |
+
},
|
| 2010 |
+
{
|
| 2011 |
+
"epoch": 1.59,
|
| 2012 |
+
"learning_rate": 2.5255474452554746e-05,
|
| 2013 |
+
"loss": 2.7141,
|
| 2014 |
+
"step": 100500
|
| 2015 |
+
},
|
| 2016 |
+
{
|
| 2017 |
+
"epoch": 1.6,
|
| 2018 |
+
"learning_rate": 2.523175182481752e-05,
|
| 2019 |
+
"loss": 2.7311,
|
| 2020 |
+
"step": 101000
|
| 2021 |
+
},
|
| 2022 |
+
{
|
| 2023 |
+
"epoch": 1.6,
|
| 2024 |
+
"eval_loss": 2.8053483963012695,
|
| 2025 |
+
"eval_runtime": 439.6812,
|
| 2026 |
+
"eval_samples_per_second": 90.975,
|
| 2027 |
+
"eval_steps_per_second": 11.372,
|
| 2028 |
+
"step": 101000
|
| 2029 |
+
},
|
| 2030 |
+
{
|
| 2031 |
+
"epoch": 1.61,
|
| 2032 |
+
"learning_rate": 2.520802919708029e-05,
|
| 2033 |
+
"loss": 2.7107,
|
| 2034 |
+
"step": 101500
|
| 2035 |
+
},
|
| 2036 |
+
{
|
| 2037 |
+
"epoch": 1.62,
|
| 2038 |
+
"learning_rate": 2.5184306569343067e-05,
|
| 2039 |
+
"loss": 2.711,
|
| 2040 |
+
"step": 102000
|
| 2041 |
+
},
|
| 2042 |
+
{
|
| 2043 |
+
"epoch": 1.62,
|
| 2044 |
+
"eval_loss": 2.805739641189575,
|
| 2045 |
+
"eval_runtime": 439.6645,
|
| 2046 |
+
"eval_samples_per_second": 90.978,
|
| 2047 |
+
"eval_steps_per_second": 11.372,
|
| 2048 |
+
"step": 102000
|
| 2049 |
+
},
|
| 2050 |
+
{
|
| 2051 |
+
"epoch": 1.63,
|
| 2052 |
+
"learning_rate": 2.5160583941605837e-05,
|
| 2053 |
+
"loss": 2.7212,
|
| 2054 |
+
"step": 102500
|
| 2055 |
+
},
|
| 2056 |
+
{
|
| 2057 |
+
"epoch": 1.63,
|
| 2058 |
+
"learning_rate": 2.5136861313868614e-05,
|
| 2059 |
+
"loss": 2.7344,
|
| 2060 |
+
"step": 103000
|
| 2061 |
+
},
|
| 2062 |
+
{
|
| 2063 |
+
"epoch": 1.63,
|
| 2064 |
+
"eval_loss": 2.799654722213745,
|
| 2065 |
+
"eval_runtime": 439.7601,
|
| 2066 |
+
"eval_samples_per_second": 90.959,
|
| 2067 |
+
"eval_steps_per_second": 11.37,
|
| 2068 |
+
"step": 103000
|
| 2069 |
+
},
|
| 2070 |
+
{
|
| 2071 |
+
"epoch": 1.64,
|
| 2072 |
+
"learning_rate": 2.5113138686131388e-05,
|
| 2073 |
+
"loss": 2.7122,
|
| 2074 |
+
"step": 103500
|
| 2075 |
+
},
|
| 2076 |
+
{
|
| 2077 |
+
"epoch": 1.65,
|
| 2078 |
+
"learning_rate": 2.508941605839416e-05,
|
| 2079 |
+
"loss": 2.7236,
|
| 2080 |
+
"step": 104000
|
| 2081 |
+
},
|
| 2082 |
+
{
|
| 2083 |
+
"epoch": 1.65,
|
| 2084 |
+
"eval_loss": 2.803441047668457,
|
| 2085 |
+
"eval_runtime": 439.7253,
|
| 2086 |
+
"eval_samples_per_second": 90.966,
|
| 2087 |
+
"eval_steps_per_second": 11.371,
|
| 2088 |
+
"step": 104000
|
| 2089 |
+
},
|
| 2090 |
+
{
|
| 2091 |
+
"epoch": 1.66,
|
| 2092 |
+
"learning_rate": 2.5065693430656935e-05,
|
| 2093 |
+
"loss": 2.7226,
|
| 2094 |
+
"step": 104500
|
| 2095 |
+
},
|
| 2096 |
+
{
|
| 2097 |
+
"epoch": 1.66,
|
| 2098 |
+
"learning_rate": 2.5041970802919705e-05,
|
| 2099 |
+
"loss": 2.6879,
|
| 2100 |
+
"step": 105000
|
| 2101 |
+
},
|
| 2102 |
+
{
|
| 2103 |
+
"epoch": 1.66,
|
| 2104 |
+
"eval_loss": 2.801588773727417,
|
| 2105 |
+
"eval_runtime": 439.6315,
|
| 2106 |
+
"eval_samples_per_second": 90.985,
|
| 2107 |
+
"eval_steps_per_second": 11.373,
|
| 2108 |
+
"step": 105000
|
| 2109 |
+
},
|
| 2110 |
+
{
|
| 2111 |
+
"epoch": 1.67,
|
| 2112 |
+
"learning_rate": 2.5018248175182482e-05,
|
| 2113 |
+
"loss": 2.732,
|
| 2114 |
+
"step": 105500
|
| 2115 |
+
},
|
| 2116 |
+
{
|
| 2117 |
+
"epoch": 1.68,
|
| 2118 |
+
"learning_rate": 2.499452554744526e-05,
|
| 2119 |
+
"loss": 2.7188,
|
| 2120 |
+
"step": 106000
|
| 2121 |
+
},
|
| 2122 |
+
{
|
| 2123 |
+
"epoch": 1.68,
|
| 2124 |
+
"eval_loss": 2.7991223335266113,
|
| 2125 |
+
"eval_runtime": 439.7752,
|
| 2126 |
+
"eval_samples_per_second": 90.956,
|
| 2127 |
+
"eval_steps_per_second": 11.369,
|
| 2128 |
+
"step": 106000
|
| 2129 |
+
},
|
| 2130 |
+
{
|
| 2131 |
+
"epoch": 1.69,
|
| 2132 |
+
"learning_rate": 2.497080291970803e-05,
|
| 2133 |
+
"loss": 2.7164,
|
| 2134 |
+
"step": 106500
|
| 2135 |
+
},
|
| 2136 |
+
{
|
| 2137 |
+
"epoch": 1.7,
|
| 2138 |
+
"learning_rate": 2.4947080291970802e-05,
|
| 2139 |
+
"loss": 2.6994,
|
| 2140 |
+
"step": 107000
|
| 2141 |
+
},
|
| 2142 |
+
{
|
| 2143 |
+
"epoch": 1.7,
|
| 2144 |
+
"eval_loss": 2.8013699054718018,
|
| 2145 |
+
"eval_runtime": 439.7722,
|
| 2146 |
+
"eval_samples_per_second": 90.956,
|
| 2147 |
+
"eval_steps_per_second": 11.37,
|
| 2148 |
+
"step": 107000
|
| 2149 |
+
},
|
| 2150 |
+
{
|
| 2151 |
+
"epoch": 1.7,
|
| 2152 |
+
"learning_rate": 2.492335766423358e-05,
|
| 2153 |
+
"loss": 2.6989,
|
| 2154 |
+
"step": 107500
|
| 2155 |
+
},
|
| 2156 |
+
{
|
| 2157 |
+
"epoch": 1.71,
|
| 2158 |
+
"learning_rate": 2.489963503649635e-05,
|
| 2159 |
+
"loss": 2.7129,
|
| 2160 |
+
"step": 108000
|
| 2161 |
+
},
|
| 2162 |
+
{
|
| 2163 |
+
"epoch": 1.71,
|
| 2164 |
+
"eval_loss": 2.7973504066467285,
|
| 2165 |
+
"eval_runtime": 439.8695,
|
| 2166 |
+
"eval_samples_per_second": 90.936,
|
| 2167 |
+
"eval_steps_per_second": 11.367,
|
| 2168 |
+
"step": 108000
|
| 2169 |
+
},
|
| 2170 |
+
{
|
| 2171 |
+
"epoch": 1.72,
|
| 2172 |
+
"learning_rate": 2.4875912408759126e-05,
|
| 2173 |
+
"loss": 2.7056,
|
| 2174 |
+
"step": 108500
|
| 2175 |
+
},
|
| 2176 |
+
{
|
| 2177 |
+
"epoch": 1.73,
|
| 2178 |
+
"learning_rate": 2.4852189781021897e-05,
|
| 2179 |
+
"loss": 2.7095,
|
| 2180 |
+
"step": 109000
|
| 2181 |
+
},
|
| 2182 |
+
{
|
| 2183 |
+
"epoch": 1.73,
|
| 2184 |
+
"eval_loss": 2.8017683029174805,
|
| 2185 |
+
"eval_runtime": 439.7668,
|
| 2186 |
+
"eval_samples_per_second": 90.957,
|
| 2187 |
+
"eval_steps_per_second": 11.37,
|
| 2188 |
+
"step": 109000
|
| 2189 |
+
},
|
| 2190 |
+
{
|
| 2191 |
+
"epoch": 1.74,
|
| 2192 |
+
"learning_rate": 2.4828467153284674e-05,
|
| 2193 |
+
"loss": 2.7021,
|
| 2194 |
+
"step": 109500
|
| 2195 |
+
},
|
| 2196 |
+
{
|
| 2197 |
+
"epoch": 1.74,
|
| 2198 |
+
"learning_rate": 2.4804744525547447e-05,
|
| 2199 |
+
"loss": 2.7029,
|
| 2200 |
+
"step": 110000
|
| 2201 |
+
},
|
| 2202 |
+
{
|
| 2203 |
+
"epoch": 1.74,
|
| 2204 |
+
"eval_loss": 2.7975335121154785,
|
| 2205 |
+
"eval_runtime": 439.9718,
|
| 2206 |
+
"eval_samples_per_second": 90.915,
|
| 2207 |
+
"eval_steps_per_second": 11.364,
|
| 2208 |
+
"step": 110000
|
| 2209 |
+
},
|
| 2210 |
+
{
|
| 2211 |
+
"epoch": 1.75,
|
| 2212 |
+
"learning_rate": 2.4781021897810217e-05,
|
| 2213 |
+
"loss": 2.7046,
|
| 2214 |
+
"step": 110500
|
| 2215 |
+
},
|
| 2216 |
+
{
|
| 2217 |
+
"epoch": 1.76,
|
| 2218 |
+
"learning_rate": 2.4757299270072994e-05,
|
| 2219 |
+
"loss": 2.7042,
|
| 2220 |
+
"step": 111000
|
| 2221 |
+
},
|
| 2222 |
+
{
|
| 2223 |
+
"epoch": 1.76,
|
| 2224 |
+
"eval_loss": 2.7961161136627197,
|
| 2225 |
+
"eval_runtime": 439.788,
|
| 2226 |
+
"eval_samples_per_second": 90.953,
|
| 2227 |
+
"eval_steps_per_second": 11.369,
|
| 2228 |
+
"step": 111000
|
| 2229 |
+
},
|
| 2230 |
+
{
|
| 2231 |
+
"epoch": 1.77,
|
| 2232 |
+
"learning_rate": 2.4733576642335768e-05,
|
| 2233 |
+
"loss": 2.7234,
|
| 2234 |
+
"step": 111500
|
| 2235 |
+
},
|
| 2236 |
+
{
|
| 2237 |
+
"epoch": 1.78,
|
| 2238 |
+
"learning_rate": 2.470985401459854e-05,
|
| 2239 |
+
"loss": 2.7134,
|
| 2240 |
+
"step": 112000
|
| 2241 |
+
},
|
| 2242 |
+
{
|
| 2243 |
+
"epoch": 1.78,
|
| 2244 |
+
"eval_loss": 2.795431613922119,
|
| 2245 |
+
"eval_runtime": 439.911,
|
| 2246 |
+
"eval_samples_per_second": 90.927,
|
| 2247 |
+
"eval_steps_per_second": 11.366,
|
| 2248 |
+
"step": 112000
|
| 2249 |
+
},
|
| 2250 |
+
{
|
| 2251 |
+
"epoch": 1.78,
|
| 2252 |
+
"learning_rate": 2.4686131386861315e-05,
|
| 2253 |
+
"loss": 2.6937,
|
| 2254 |
+
"step": 112500
|
| 2255 |
+
},
|
| 2256 |
+
{
|
| 2257 |
+
"epoch": 1.79,
|
| 2258 |
+
"learning_rate": 2.4662408759124088e-05,
|
| 2259 |
+
"loss": 2.6905,
|
| 2260 |
+
"step": 113000
|
| 2261 |
+
},
|
| 2262 |
+
{
|
| 2263 |
+
"epoch": 1.79,
|
| 2264 |
+
"eval_loss": 2.7966976165771484,
|
| 2265 |
+
"eval_runtime": 439.7831,
|
| 2266 |
+
"eval_samples_per_second": 90.954,
|
| 2267 |
+
"eval_steps_per_second": 11.369,
|
| 2268 |
+
"step": 113000
|
| 2269 |
+
},
|
| 2270 |
+
{
|
| 2271 |
+
"epoch": 1.8,
|
| 2272 |
+
"learning_rate": 2.4638686131386862e-05,
|
| 2273 |
+
"loss": 2.7027,
|
| 2274 |
+
"step": 113500
|
| 2275 |
+
},
|
| 2276 |
+
{
|
| 2277 |
+
"epoch": 1.81,
|
| 2278 |
+
"learning_rate": 2.4614963503649635e-05,
|
| 2279 |
+
"loss": 2.6871,
|
| 2280 |
+
"step": 114000
|
| 2281 |
+
},
|
| 2282 |
+
{
|
| 2283 |
+
"epoch": 1.81,
|
| 2284 |
+
"eval_loss": 2.7926506996154785,
|
| 2285 |
+
"eval_runtime": 440.0624,
|
| 2286 |
+
"eval_samples_per_second": 90.896,
|
| 2287 |
+
"eval_steps_per_second": 11.362,
|
| 2288 |
+
"step": 114000
|
| 2289 |
+
},
|
| 2290 |
+
{
|
| 2291 |
+
"epoch": 1.82,
|
| 2292 |
+
"learning_rate": 2.459124087591241e-05,
|
| 2293 |
+
"loss": 2.697,
|
| 2294 |
+
"step": 114500
|
| 2295 |
+
},
|
| 2296 |
+
{
|
| 2297 |
+
"epoch": 1.82,
|
| 2298 |
+
"learning_rate": 2.4567518248175186e-05,
|
| 2299 |
+
"loss": 2.6931,
|
| 2300 |
+
"step": 115000
|
| 2301 |
+
},
|
| 2302 |
+
{
|
| 2303 |
+
"epoch": 1.82,
|
| 2304 |
+
"eval_loss": 2.8011257648468018,
|
| 2305 |
+
"eval_runtime": 439.8116,
|
| 2306 |
+
"eval_samples_per_second": 90.948,
|
| 2307 |
+
"eval_steps_per_second": 11.369,
|
| 2308 |
+
"step": 115000
|
| 2309 |
+
},
|
| 2310 |
+
{
|
| 2311 |
+
"epoch": 1.83,
|
| 2312 |
+
"learning_rate": 2.4543795620437956e-05,
|
| 2313 |
+
"loss": 2.7136,
|
| 2314 |
+
"step": 115500
|
| 2315 |
+
},
|
| 2316 |
+
{
|
| 2317 |
+
"epoch": 1.84,
|
| 2318 |
+
"learning_rate": 2.452007299270073e-05,
|
| 2319 |
+
"loss": 2.702,
|
| 2320 |
+
"step": 116000
|
| 2321 |
+
},
|
| 2322 |
+
{
|
| 2323 |
+
"epoch": 1.84,
|
| 2324 |
+
"eval_loss": 2.7955451011657715,
|
| 2325 |
+
"eval_runtime": 439.914,
|
| 2326 |
+
"eval_samples_per_second": 90.927,
|
| 2327 |
+
"eval_steps_per_second": 11.366,
|
| 2328 |
+
"step": 116000
|
| 2329 |
+
},
|
| 2330 |
+
{
|
| 2331 |
+
"epoch": 1.85,
|
| 2332 |
+
"learning_rate": 2.4496350364963503e-05,
|
| 2333 |
+
"loss": 2.6859,
|
| 2334 |
+
"step": 116500
|
| 2335 |
+
},
|
| 2336 |
+
{
|
| 2337 |
+
"epoch": 1.86,
|
| 2338 |
+
"learning_rate": 2.4472627737226277e-05,
|
| 2339 |
+
"loss": 2.712,
|
| 2340 |
+
"step": 117000
|
| 2341 |
+
},
|
| 2342 |
+
{
|
| 2343 |
+
"epoch": 1.86,
|
| 2344 |
+
"eval_loss": 2.7944655418395996,
|
| 2345 |
+
"eval_runtime": 439.809,
|
| 2346 |
+
"eval_samples_per_second": 90.949,
|
| 2347 |
+
"eval_steps_per_second": 11.369,
|
| 2348 |
+
"step": 117000
|
| 2349 |
+
},
|
| 2350 |
+
{
|
| 2351 |
+
"epoch": 1.86,
|
| 2352 |
+
"learning_rate": 2.4448905109489054e-05,
|
| 2353 |
+
"loss": 2.6984,
|
| 2354 |
+
"step": 117500
|
| 2355 |
+
},
|
| 2356 |
+
{
|
| 2357 |
+
"epoch": 1.87,
|
| 2358 |
+
"learning_rate": 2.4425182481751824e-05,
|
| 2359 |
+
"loss": 2.7091,
|
| 2360 |
+
"step": 118000
|
| 2361 |
+
},
|
| 2362 |
+
{
|
| 2363 |
+
"epoch": 1.87,
|
| 2364 |
+
"eval_loss": 2.7959797382354736,
|
| 2365 |
+
"eval_runtime": 439.9158,
|
| 2366 |
+
"eval_samples_per_second": 90.926,
|
| 2367 |
+
"eval_steps_per_second": 11.366,
|
| 2368 |
+
"step": 118000
|
| 2369 |
+
},
|
| 2370 |
+
{
|
| 2371 |
+
"epoch": 1.88,
|
| 2372 |
+
"learning_rate": 2.44014598540146e-05,
|
| 2373 |
+
"loss": 2.6978,
|
| 2374 |
+
"step": 118500
|
| 2375 |
+
},
|
| 2376 |
+
{
|
| 2377 |
+
"epoch": 1.89,
|
| 2378 |
+
"learning_rate": 2.437773722627737e-05,
|
| 2379 |
+
"loss": 2.6913,
|
| 2380 |
+
"step": 119000
|
| 2381 |
+
},
|
| 2382 |
+
{
|
| 2383 |
+
"epoch": 1.89,
|
| 2384 |
+
"eval_loss": 2.79091739654541,
|
| 2385 |
+
"eval_runtime": 439.7923,
|
| 2386 |
+
"eval_samples_per_second": 90.952,
|
| 2387 |
+
"eval_steps_per_second": 11.369,
|
| 2388 |
+
"step": 119000
|
| 2389 |
+
},
|
| 2390 |
+
{
|
| 2391 |
+
"epoch": 1.89,
|
| 2392 |
+
"learning_rate": 2.4354014598540144e-05,
|
| 2393 |
+
"loss": 2.6964,
|
| 2394 |
+
"step": 119500
|
| 2395 |
+
},
|
| 2396 |
+
{
|
| 2397 |
+
"epoch": 1.9,
|
| 2398 |
+
"learning_rate": 2.433029197080292e-05,
|
| 2399 |
+
"loss": 2.7008,
|
| 2400 |
+
"step": 120000
|
| 2401 |
+
},
|
| 2402 |
+
{
|
| 2403 |
+
"epoch": 1.9,
|
| 2404 |
+
"eval_loss": 2.7938427925109863,
|
| 2405 |
+
"eval_runtime": 439.9595,
|
| 2406 |
+
"eval_samples_per_second": 90.917,
|
| 2407 |
+
"eval_steps_per_second": 11.365,
|
| 2408 |
+
"step": 120000
|
| 2409 |
+
},
|
| 2410 |
+
{
|
| 2411 |
+
"epoch": 1.91,
|
| 2412 |
+
"learning_rate": 2.4306569343065695e-05,
|
| 2413 |
+
"loss": 2.7015,
|
| 2414 |
+
"step": 120500
|
| 2415 |
+
},
|
| 2416 |
+
{
|
| 2417 |
+
"epoch": 1.92,
|
| 2418 |
+
"learning_rate": 2.428284671532847e-05,
|
| 2419 |
+
"loss": 2.6968,
|
| 2420 |
+
"step": 121000
|
| 2421 |
+
},
|
| 2422 |
+
{
|
| 2423 |
+
"epoch": 1.92,
|
| 2424 |
+
"eval_loss": 2.796417236328125,
|
| 2425 |
+
"eval_runtime": 439.8462,
|
| 2426 |
+
"eval_samples_per_second": 90.941,
|
| 2427 |
+
"eval_steps_per_second": 11.368,
|
| 2428 |
+
"step": 121000
|
| 2429 |
+
},
|
| 2430 |
+
{
|
| 2431 |
+
"epoch": 1.93,
|
| 2432 |
+
"learning_rate": 2.425912408759124e-05,
|
| 2433 |
+
"loss": 2.6936,
|
| 2434 |
+
"step": 121500
|
| 2435 |
+
},
|
| 2436 |
+
{
|
| 2437 |
+
"epoch": 1.93,
|
| 2438 |
+
"learning_rate": 2.4235401459854015e-05,
|
| 2439 |
+
"loss": 2.688,
|
| 2440 |
+
"step": 122000
|
| 2441 |
+
},
|
| 2442 |
+
{
|
| 2443 |
+
"epoch": 1.93,
|
| 2444 |
+
"eval_loss": 2.790297269821167,
|
| 2445 |
+
"eval_runtime": 439.89,
|
| 2446 |
+
"eval_samples_per_second": 90.932,
|
| 2447 |
+
"eval_steps_per_second": 11.366,
|
| 2448 |
+
"step": 122000
|
| 2449 |
+
},
|
| 2450 |
+
{
|
| 2451 |
+
"epoch": 1.94,
|
| 2452 |
+
"learning_rate": 2.421167883211679e-05,
|
| 2453 |
+
"loss": 2.6885,
|
| 2454 |
+
"step": 122500
|
| 2455 |
+
},
|
| 2456 |
+
{
|
| 2457 |
+
"epoch": 1.95,
|
| 2458 |
+
"learning_rate": 2.4187956204379563e-05,
|
| 2459 |
+
"loss": 2.7015,
|
| 2460 |
+
"step": 123000
|
| 2461 |
+
},
|
| 2462 |
+
{
|
| 2463 |
+
"epoch": 1.95,
|
| 2464 |
+
"eval_loss": 2.7968406677246094,
|
| 2465 |
+
"eval_runtime": 439.8161,
|
| 2466 |
+
"eval_samples_per_second": 90.947,
|
| 2467 |
+
"eval_steps_per_second": 11.368,
|
| 2468 |
+
"step": 123000
|
| 2469 |
+
},
|
| 2470 |
+
{
|
| 2471 |
+
"epoch": 1.96,
|
| 2472 |
+
"learning_rate": 2.4164233576642336e-05,
|
| 2473 |
+
"loss": 2.7095,
|
| 2474 |
+
"step": 123500
|
| 2475 |
+
},
|
| 2476 |
+
{
|
| 2477 |
+
"epoch": 1.97,
|
| 2478 |
+
"learning_rate": 2.414051094890511e-05,
|
| 2479 |
+
"loss": 2.7038,
|
| 2480 |
+
"step": 124000
|
| 2481 |
+
},
|
| 2482 |
+
{
|
| 2483 |
+
"epoch": 1.97,
|
| 2484 |
+
"eval_loss": 2.79244327545166,
|
| 2485 |
+
"eval_runtime": 439.8929,
|
| 2486 |
+
"eval_samples_per_second": 90.931,
|
| 2487 |
+
"eval_steps_per_second": 11.366,
|
| 2488 |
+
"step": 124000
|
| 2489 |
+
},
|
| 2490 |
+
{
|
| 2491 |
+
"epoch": 1.97,
|
| 2492 |
+
"learning_rate": 2.4116788321167883e-05,
|
| 2493 |
+
"loss": 2.6901,
|
| 2494 |
+
"step": 124500
|
| 2495 |
+
},
|
| 2496 |
+
{
|
| 2497 |
+
"epoch": 1.98,
|
| 2498 |
+
"learning_rate": 2.4093065693430657e-05,
|
| 2499 |
+
"loss": 2.6991,
|
| 2500 |
+
"step": 125000
|
| 2501 |
+
},
|
| 2502 |
+
{
|
| 2503 |
+
"epoch": 1.98,
|
| 2504 |
+
"eval_loss": 2.7943027019500732,
|
| 2505 |
+
"eval_runtime": 439.7901,
|
| 2506 |
+
"eval_samples_per_second": 90.952,
|
| 2507 |
+
"eval_steps_per_second": 11.369,
|
| 2508 |
+
"step": 125000
|
| 2509 |
+
},
|
| 2510 |
+
{
|
| 2511 |
+
"epoch": 1.99,
|
| 2512 |
+
"learning_rate": 2.406934306569343e-05,
|
| 2513 |
+
"loss": 2.6954,
|
| 2514 |
+
"step": 125500
|
| 2515 |
+
},
|
| 2516 |
+
{
|
| 2517 |
+
"epoch": 2.0,
|
| 2518 |
+
"learning_rate": 2.4045620437956207e-05,
|
| 2519 |
+
"loss": 2.6804,
|
| 2520 |
+
"step": 126000
|
| 2521 |
+
},
|
| 2522 |
+
{
|
| 2523 |
+
"epoch": 2.0,
|
| 2524 |
+
"eval_loss": 2.785961627960205,
|
| 2525 |
+
"eval_runtime": 440.0425,
|
| 2526 |
+
"eval_samples_per_second": 90.9,
|
| 2527 |
+
"eval_steps_per_second": 11.363,
|
| 2528 |
+
"step": 126000
|
| 2529 |
+
}
|
| 2530 |
+
],
|
| 2531 |
+
"max_steps": 630700,
|
| 2532 |
+
"num_train_epochs": 10,
|
| 2533 |
+
"total_flos": 8.47096165805568e+17,
|
| 2534 |
+
"trial_name": null,
|
| 2535 |
+
"trial_params": null
|
| 2536 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c0af4ae3f3aadb03321f57588b5566a66ddab049a401a7737dc0d44ea39ae2ee
|
| 3 |
+
size 4283
|