Commit
•
59a004f
1
Parent(s):
a13772e
Upload 8 files
Browse files- .gitattributes +1 -0
- config.json +32 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +5 -0
- spiece.model +3 -0
- tokenizer.json +3 -0
- tokenizer_config.json +12 -0
- trainer_state.json +1716 -0
- training_args.bin +3 -0
.gitattributes
CHANGED
|
@@ -32,3 +32,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 32 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 33 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 32 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 33 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 35 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
config.json
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "bigscience/mt0-large",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"MT5ForConditionalGeneration"
|
| 5 |
+
],
|
| 6 |
+
"d_ff": 2816,
|
| 7 |
+
"d_kv": 64,
|
| 8 |
+
"d_model": 1024,
|
| 9 |
+
"decoder_start_token_id": 0,
|
| 10 |
+
"dense_act_fn": "gelu_new",
|
| 11 |
+
"dropout_rate": 0.1,
|
| 12 |
+
"eos_token_id": 1,
|
| 13 |
+
"feed_forward_proj": "gated-gelu",
|
| 14 |
+
"initializer_factor": 1.0,
|
| 15 |
+
"is_encoder_decoder": true,
|
| 16 |
+
"is_gated_act": true,
|
| 17 |
+
"layer_norm_epsilon": 1e-06,
|
| 18 |
+
"model_type": "mt5",
|
| 19 |
+
"num_decoder_layers": 24,
|
| 20 |
+
"num_heads": 16,
|
| 21 |
+
"num_layers": 24,
|
| 22 |
+
"output_past": true,
|
| 23 |
+
"pad_token_id": 0,
|
| 24 |
+
"relative_attention_max_distance": 128,
|
| 25 |
+
"relative_attention_num_buckets": 32,
|
| 26 |
+
"tie_word_embeddings": false,
|
| 27 |
+
"tokenizer_class": "T5Tokenizer",
|
| 28 |
+
"torch_dtype": "float16",
|
| 29 |
+
"transformers_version": "4.25.1",
|
| 30 |
+
"use_cache": true,
|
| 31 |
+
"vocab_size": 250112
|
| 32 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c60c9ae72fd6881459a29a78081a6fe74bb9daa049db046407128cdca9b1eb4a
|
| 3 |
+
size 2459242663
|
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 sha256:6502d07619068a98aa2d3bb531332a694ffe108ca6c6fe62a467ccfe98d666b9
|
| 3 |
+
size 16315219
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": null,
|
| 3 |
+
"eos_token": "</s>",
|
| 4 |
+
"extra_ids": 0,
|
| 5 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 6 |
+
"name_or_path": "bigscience/mt0-large",
|
| 7 |
+
"pad_token": "<pad>",
|
| 8 |
+
"sp_model_kwargs": {},
|
| 9 |
+
"special_tokens_map_file": "/home/patrick/.cache/torch/transformers/685ac0ca8568ec593a48b61b0a3c272beee9bc194a3c7241d15dcadb5f875e53.f76030f3ec1b96a8199b2593390c610e76ca8028ef3d24680000619ffb646276",
|
| 10 |
+
"tokenizer_class": "T5Tokenizer",
|
| 11 |
+
"unk_token": "<unk>"
|
| 12 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1716 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 19.83629191321499,
|
| 5 |
+
"global_step": 2500,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.08,
|
| 12 |
+
"learning_rate": 6.2827061767850974e-06,
|
| 13 |
+
"loss": 3.8041,
|
| 14 |
+
"step": 10
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.16,
|
| 18 |
+
"learning_rate": 9.721930086076435e-06,
|
| 19 |
+
"loss": 3.5706,
|
| 20 |
+
"step": 20
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.24,
|
| 24 |
+
"learning_rate": 1.1424336578396131e-05,
|
| 25 |
+
"loss": 3.2293,
|
| 26 |
+
"step": 30
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.32,
|
| 30 |
+
"learning_rate": 1.2565412353570195e-05,
|
| 31 |
+
"loss": 2.8198,
|
| 32 |
+
"step": 40
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.39,
|
| 36 |
+
"learning_rate": 1.3424920790724471e-05,
|
| 37 |
+
"loss": 2.6382,
|
| 38 |
+
"step": 50
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.47,
|
| 42 |
+
"learning_rate": 1.4114674634318977e-05,
|
| 43 |
+
"loss": 2.5852,
|
| 44 |
+
"step": 60
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.55,
|
| 48 |
+
"learning_rate": 1.4690794260273606e-05,
|
| 49 |
+
"loss": 2.4718,
|
| 50 |
+
"step": 70
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.63,
|
| 54 |
+
"learning_rate": 1.5185478617142983e-05,
|
| 55 |
+
"loss": 2.3908,
|
| 56 |
+
"step": 80
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.71,
|
| 60 |
+
"learning_rate": 1.561892416495773e-05,
|
| 61 |
+
"loss": 2.3321,
|
| 62 |
+
"step": 90
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.79,
|
| 66 |
+
"learning_rate": 1.600463626286153e-05,
|
| 67 |
+
"loss": 2.3622,
|
| 68 |
+
"step": 100
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.79,
|
| 72 |
+
"eval_loss": 2.0142996311187744,
|
| 73 |
+
"eval_runtime": 13.3285,
|
| 74 |
+
"eval_samples_per_second": 92.958,
|
| 75 |
+
"eval_steps_per_second": 18.607,
|
| 76 |
+
"step": 100
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"epoch": 0.87,
|
| 80 |
+
"learning_rate": 1.6352093070986755e-05,
|
| 81 |
+
"loss": 2.2679,
|
| 82 |
+
"step": 110
|
| 83 |
+
},
|
| 84 |
+
{
|
| 85 |
+
"epoch": 0.95,
|
| 86 |
+
"learning_rate": 1.666820294156779e-05,
|
| 87 |
+
"loss": 2.2493,
|
| 88 |
+
"step": 120
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 1.03,
|
| 92 |
+
"learning_rate": 1.6958156901812732e-05,
|
| 93 |
+
"loss": 2.3766,
|
| 94 |
+
"step": 130
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 1.11,
|
| 98 |
+
"learning_rate": 1.7225954557575116e-05,
|
| 99 |
+
"loss": 2.1449,
|
| 100 |
+
"step": 140
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 1.19,
|
| 104 |
+
"learning_rate": 1.747474292314672e-05,
|
| 105 |
+
"loss": 2.1136,
|
| 106 |
+
"step": 150
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 1.27,
|
| 110 |
+
"learning_rate": 1.770704275518123e-05,
|
| 111 |
+
"loss": 2.107,
|
| 112 |
+
"step": 160
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"epoch": 1.35,
|
| 116 |
+
"learning_rate": 1.7924904433402933e-05,
|
| 117 |
+
"loss": 2.1469,
|
| 118 |
+
"step": 170
|
| 119 |
+
},
|
| 120 |
+
{
|
| 121 |
+
"epoch": 1.43,
|
| 122 |
+
"learning_rate": 1.8130018169564944e-05,
|
| 123 |
+
"loss": 2.1229,
|
| 124 |
+
"step": 180
|
| 125 |
+
},
|
| 126 |
+
{
|
| 127 |
+
"epoch": 1.5,
|
| 128 |
+
"learning_rate": 1.832379371735486e-05,
|
| 129 |
+
"loss": 2.0893,
|
| 130 |
+
"step": 190
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 1.58,
|
| 134 |
+
"learning_rate": 1.8507419182561513e-05,
|
| 135 |
+
"loss": 2.0836,
|
| 136 |
+
"step": 200
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 1.58,
|
| 140 |
+
"eval_loss": 1.813197135925293,
|
| 141 |
+
"eval_runtime": 13.3546,
|
| 142 |
+
"eval_samples_per_second": 92.777,
|
| 143 |
+
"eval_steps_per_second": 18.57,
|
| 144 |
+
"step": 200
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 1.66,
|
| 148 |
+
"learning_rate": 1.868190518296623e-05,
|
| 149 |
+
"loss": 2.0307,
|
| 150 |
+
"step": 210
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 1.74,
|
| 154 |
+
"learning_rate": 1.8848118530355293e-05,
|
| 155 |
+
"loss": 2.0025,
|
| 156 |
+
"step": 220
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 1.82,
|
| 160 |
+
"learning_rate": 1.9006808283301558e-05,
|
| 161 |
+
"loss": 2.0116,
|
| 162 |
+
"step": 230
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 1.9,
|
| 166 |
+
"learning_rate": 1.915862615484805e-05,
|
| 167 |
+
"loss": 2.0355,
|
| 168 |
+
"step": 240
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 1.98,
|
| 172 |
+
"learning_rate": 1.9304142682139013e-05,
|
| 173 |
+
"loss": 2.0056,
|
| 174 |
+
"step": 250
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 2.06,
|
| 178 |
+
"learning_rate": 1.945753054066002e-05,
|
| 179 |
+
"loss": 2.1508,
|
| 180 |
+
"step": 260
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 2.14,
|
| 184 |
+
"learning_rate": 1.959138057324679e-05,
|
| 185 |
+
"loss": 1.9203,
|
| 186 |
+
"step": 270
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 2.22,
|
| 190 |
+
"learning_rate": 1.9720308518695147e-05,
|
| 191 |
+
"loss": 1.9358,
|
| 192 |
+
"step": 280
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 2.3,
|
| 196 |
+
"learning_rate": 1.9844663575115566e-05,
|
| 197 |
+
"loss": 1.877,
|
| 198 |
+
"step": 290
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 2.38,
|
| 202 |
+
"learning_rate": 1.9964759049286476e-05,
|
| 203 |
+
"loss": 1.9239,
|
| 204 |
+
"step": 300
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 2.38,
|
| 208 |
+
"eval_loss": 1.726140022277832,
|
| 209 |
+
"eval_runtime": 13.3534,
|
| 210 |
+
"eval_samples_per_second": 92.785,
|
| 211 |
+
"eval_steps_per_second": 18.572,
|
| 212 |
+
"step": 300
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 2.46,
|
| 216 |
+
"learning_rate": 1.994594594594595e-05,
|
| 217 |
+
"loss": 1.9449,
|
| 218 |
+
"step": 310
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 2.54,
|
| 222 |
+
"learning_rate": 1.9855855855855857e-05,
|
| 223 |
+
"loss": 1.895,
|
| 224 |
+
"step": 320
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 2.62,
|
| 228 |
+
"learning_rate": 1.9765765765765768e-05,
|
| 229 |
+
"loss": 1.864,
|
| 230 |
+
"step": 330
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 2.69,
|
| 234 |
+
"learning_rate": 1.967567567567568e-05,
|
| 235 |
+
"loss": 1.8928,
|
| 236 |
+
"step": 340
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 2.77,
|
| 240 |
+
"learning_rate": 1.9585585585585586e-05,
|
| 241 |
+
"loss": 1.8801,
|
| 242 |
+
"step": 350
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 2.85,
|
| 246 |
+
"learning_rate": 1.9495495495495497e-05,
|
| 247 |
+
"loss": 1.911,
|
| 248 |
+
"step": 360
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 2.93,
|
| 252 |
+
"learning_rate": 1.9405405405405408e-05,
|
| 253 |
+
"loss": 1.8945,
|
| 254 |
+
"step": 370
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 3.02,
|
| 258 |
+
"learning_rate": 1.930630630630631e-05,
|
| 259 |
+
"loss": 1.9508,
|
| 260 |
+
"step": 380
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 3.09,
|
| 264 |
+
"learning_rate": 1.9216216216216216e-05,
|
| 265 |
+
"loss": 1.7709,
|
| 266 |
+
"step": 390
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 3.17,
|
| 270 |
+
"learning_rate": 1.9126126126126127e-05,
|
| 271 |
+
"loss": 1.7693,
|
| 272 |
+
"step": 400
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 3.17,
|
| 276 |
+
"eval_loss": 1.673058032989502,
|
| 277 |
+
"eval_runtime": 13.3468,
|
| 278 |
+
"eval_samples_per_second": 92.832,
|
| 279 |
+
"eval_steps_per_second": 18.581,
|
| 280 |
+
"step": 400
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 3.25,
|
| 284 |
+
"learning_rate": 1.9036036036036038e-05,
|
| 285 |
+
"loss": 1.7773,
|
| 286 |
+
"step": 410
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 3.33,
|
| 290 |
+
"learning_rate": 1.8945945945945945e-05,
|
| 291 |
+
"loss": 1.8198,
|
| 292 |
+
"step": 420
|
| 293 |
+
},
|
| 294 |
+
{
|
| 295 |
+
"epoch": 3.41,
|
| 296 |
+
"learning_rate": 1.8855855855855856e-05,
|
| 297 |
+
"loss": 1.7813,
|
| 298 |
+
"step": 430
|
| 299 |
+
},
|
| 300 |
+
{
|
| 301 |
+
"epoch": 3.49,
|
| 302 |
+
"learning_rate": 1.8765765765765767e-05,
|
| 303 |
+
"loss": 1.7736,
|
| 304 |
+
"step": 440
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 3.57,
|
| 308 |
+
"learning_rate": 1.8675675675675678e-05,
|
| 309 |
+
"loss": 1.8544,
|
| 310 |
+
"step": 450
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 3.65,
|
| 314 |
+
"learning_rate": 1.8585585585585585e-05,
|
| 315 |
+
"loss": 1.7672,
|
| 316 |
+
"step": 460
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 3.73,
|
| 320 |
+
"learning_rate": 1.8495495495495496e-05,
|
| 321 |
+
"loss": 1.8223,
|
| 322 |
+
"step": 470
|
| 323 |
+
},
|
| 324 |
+
{
|
| 325 |
+
"epoch": 3.8,
|
| 326 |
+
"learning_rate": 1.8405405405405407e-05,
|
| 327 |
+
"loss": 1.7832,
|
| 328 |
+
"step": 480
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"epoch": 3.88,
|
| 332 |
+
"learning_rate": 1.8315315315315318e-05,
|
| 333 |
+
"loss": 1.7937,
|
| 334 |
+
"step": 490
|
| 335 |
+
},
|
| 336 |
+
{
|
| 337 |
+
"epoch": 3.96,
|
| 338 |
+
"learning_rate": 1.822522522522523e-05,
|
| 339 |
+
"loss": 1.8078,
|
| 340 |
+
"step": 500
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"epoch": 3.96,
|
| 344 |
+
"eval_loss": 1.6267061233520508,
|
| 345 |
+
"eval_runtime": 13.3535,
|
| 346 |
+
"eval_samples_per_second": 92.784,
|
| 347 |
+
"eval_steps_per_second": 18.572,
|
| 348 |
+
"step": 500
|
| 349 |
+
},
|
| 350 |
+
{
|
| 351 |
+
"epoch": 4.05,
|
| 352 |
+
"learning_rate": 1.8126126126126127e-05,
|
| 353 |
+
"loss": 1.8374,
|
| 354 |
+
"step": 510
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 4.13,
|
| 358 |
+
"learning_rate": 1.8036036036036037e-05,
|
| 359 |
+
"loss": 1.7228,
|
| 360 |
+
"step": 520
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 4.21,
|
| 364 |
+
"learning_rate": 1.7945945945945948e-05,
|
| 365 |
+
"loss": 1.6986,
|
| 366 |
+
"step": 530
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 4.28,
|
| 370 |
+
"learning_rate": 1.7855855855855856e-05,
|
| 371 |
+
"loss": 1.6858,
|
| 372 |
+
"step": 540
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"epoch": 4.36,
|
| 376 |
+
"learning_rate": 1.7765765765765767e-05,
|
| 377 |
+
"loss": 1.7169,
|
| 378 |
+
"step": 550
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 4.44,
|
| 382 |
+
"learning_rate": 1.7675675675675677e-05,
|
| 383 |
+
"loss": 1.7069,
|
| 384 |
+
"step": 560
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 4.52,
|
| 388 |
+
"learning_rate": 1.7585585585585588e-05,
|
| 389 |
+
"loss": 1.6725,
|
| 390 |
+
"step": 570
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 4.6,
|
| 394 |
+
"learning_rate": 1.7495495495495496e-05,
|
| 395 |
+
"loss": 1.7052,
|
| 396 |
+
"step": 580
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 4.68,
|
| 400 |
+
"learning_rate": 1.7405405405405406e-05,
|
| 401 |
+
"loss": 1.6597,
|
| 402 |
+
"step": 590
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 4.76,
|
| 406 |
+
"learning_rate": 1.7315315315315317e-05,
|
| 407 |
+
"loss": 1.7565,
|
| 408 |
+
"step": 600
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 4.76,
|
| 412 |
+
"eval_loss": 1.5994915962219238,
|
| 413 |
+
"eval_runtime": 13.2972,
|
| 414 |
+
"eval_samples_per_second": 93.177,
|
| 415 |
+
"eval_steps_per_second": 18.651,
|
| 416 |
+
"step": 600
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 4.84,
|
| 420 |
+
"learning_rate": 1.7225225225225225e-05,
|
| 421 |
+
"loss": 1.723,
|
| 422 |
+
"step": 610
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 4.92,
|
| 426 |
+
"learning_rate": 1.7135135135135135e-05,
|
| 427 |
+
"loss": 1.6777,
|
| 428 |
+
"step": 620
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 4.99,
|
| 432 |
+
"learning_rate": 1.7045045045045046e-05,
|
| 433 |
+
"loss": 1.6943,
|
| 434 |
+
"step": 630
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 5.08,
|
| 438 |
+
"learning_rate": 1.6954954954954957e-05,
|
| 439 |
+
"loss": 1.7274,
|
| 440 |
+
"step": 640
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 5.16,
|
| 444 |
+
"learning_rate": 1.6864864864864868e-05,
|
| 445 |
+
"loss": 1.7062,
|
| 446 |
+
"step": 650
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 5.24,
|
| 450 |
+
"learning_rate": 1.6774774774774775e-05,
|
| 451 |
+
"loss": 1.6078,
|
| 452 |
+
"step": 660
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 5.32,
|
| 456 |
+
"learning_rate": 1.6684684684684686e-05,
|
| 457 |
+
"loss": 1.6484,
|
| 458 |
+
"step": 670
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 5.39,
|
| 462 |
+
"learning_rate": 1.6594594594594597e-05,
|
| 463 |
+
"loss": 1.6097,
|
| 464 |
+
"step": 680
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 5.47,
|
| 468 |
+
"learning_rate": 1.6504504504504508e-05,
|
| 469 |
+
"loss": 1.6255,
|
| 470 |
+
"step": 690
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 5.55,
|
| 474 |
+
"learning_rate": 1.641441441441442e-05,
|
| 475 |
+
"loss": 1.6188,
|
| 476 |
+
"step": 700
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 5.55,
|
| 480 |
+
"eval_loss": 1.5767285823822021,
|
| 481 |
+
"eval_runtime": 13.2952,
|
| 482 |
+
"eval_samples_per_second": 93.191,
|
| 483 |
+
"eval_steps_per_second": 18.653,
|
| 484 |
+
"step": 700
|
| 485 |
+
},
|
| 486 |
+
{
|
| 487 |
+
"epoch": 5.63,
|
| 488 |
+
"learning_rate": 1.6324324324324326e-05,
|
| 489 |
+
"loss": 1.68,
|
| 490 |
+
"step": 710
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 5.71,
|
| 494 |
+
"learning_rate": 1.6234234234234237e-05,
|
| 495 |
+
"loss": 1.618,
|
| 496 |
+
"step": 720
|
| 497 |
+
},
|
| 498 |
+
{
|
| 499 |
+
"epoch": 5.79,
|
| 500 |
+
"learning_rate": 1.6144144144144144e-05,
|
| 501 |
+
"loss": 1.5747,
|
| 502 |
+
"step": 730
|
| 503 |
+
},
|
| 504 |
+
{
|
| 505 |
+
"epoch": 5.87,
|
| 506 |
+
"learning_rate": 1.6054054054054055e-05,
|
| 507 |
+
"loss": 1.6617,
|
| 508 |
+
"step": 740
|
| 509 |
+
},
|
| 510 |
+
{
|
| 511 |
+
"epoch": 5.95,
|
| 512 |
+
"learning_rate": 1.5963963963963966e-05,
|
| 513 |
+
"loss": 1.6466,
|
| 514 |
+
"step": 750
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 6.03,
|
| 518 |
+
"learning_rate": 1.5864864864864867e-05,
|
| 519 |
+
"loss": 1.7621,
|
| 520 |
+
"step": 760
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 6.11,
|
| 524 |
+
"learning_rate": 1.5774774774774778e-05,
|
| 525 |
+
"loss": 1.5679,
|
| 526 |
+
"step": 770
|
| 527 |
+
},
|
| 528 |
+
{
|
| 529 |
+
"epoch": 6.19,
|
| 530 |
+
"learning_rate": 1.5684684684684685e-05,
|
| 531 |
+
"loss": 1.6356,
|
| 532 |
+
"step": 780
|
| 533 |
+
},
|
| 534 |
+
{
|
| 535 |
+
"epoch": 6.27,
|
| 536 |
+
"learning_rate": 1.5594594594594596e-05,
|
| 537 |
+
"loss": 1.5499,
|
| 538 |
+
"step": 790
|
| 539 |
+
},
|
| 540 |
+
{
|
| 541 |
+
"epoch": 6.35,
|
| 542 |
+
"learning_rate": 1.5504504504504504e-05,
|
| 543 |
+
"loss": 1.5783,
|
| 544 |
+
"step": 800
|
| 545 |
+
},
|
| 546 |
+
{
|
| 547 |
+
"epoch": 6.35,
|
| 548 |
+
"eval_loss": 1.5619192123413086,
|
| 549 |
+
"eval_runtime": 13.2986,
|
| 550 |
+
"eval_samples_per_second": 93.168,
|
| 551 |
+
"eval_steps_per_second": 18.649,
|
| 552 |
+
"step": 800
|
| 553 |
+
},
|
| 554 |
+
{
|
| 555 |
+
"epoch": 6.43,
|
| 556 |
+
"learning_rate": 1.5414414414414414e-05,
|
| 557 |
+
"loss": 1.5848,
|
| 558 |
+
"step": 810
|
| 559 |
+
},
|
| 560 |
+
{
|
| 561 |
+
"epoch": 6.5,
|
| 562 |
+
"learning_rate": 1.5324324324324325e-05,
|
| 563 |
+
"loss": 1.5019,
|
| 564 |
+
"step": 820
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 6.58,
|
| 568 |
+
"learning_rate": 1.5234234234234236e-05,
|
| 569 |
+
"loss": 1.6008,
|
| 570 |
+
"step": 830
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 6.66,
|
| 574 |
+
"learning_rate": 1.5144144144144147e-05,
|
| 575 |
+
"loss": 1.5757,
|
| 576 |
+
"step": 840
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 6.74,
|
| 580 |
+
"learning_rate": 1.5054054054054054e-05,
|
| 581 |
+
"loss": 1.5855,
|
| 582 |
+
"step": 850
|
| 583 |
+
},
|
| 584 |
+
{
|
| 585 |
+
"epoch": 6.82,
|
| 586 |
+
"learning_rate": 1.4963963963963965e-05,
|
| 587 |
+
"loss": 1.629,
|
| 588 |
+
"step": 860
|
| 589 |
+
},
|
| 590 |
+
{
|
| 591 |
+
"epoch": 6.9,
|
| 592 |
+
"learning_rate": 1.4873873873873874e-05,
|
| 593 |
+
"loss": 1.5948,
|
| 594 |
+
"step": 870
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 6.98,
|
| 598 |
+
"learning_rate": 1.4783783783783785e-05,
|
| 599 |
+
"loss": 1.5814,
|
| 600 |
+
"step": 880
|
| 601 |
+
},
|
| 602 |
+
{
|
| 603 |
+
"epoch": 7.06,
|
| 604 |
+
"learning_rate": 1.4684684684684686e-05,
|
| 605 |
+
"loss": 1.7112,
|
| 606 |
+
"step": 890
|
| 607 |
+
},
|
| 608 |
+
{
|
| 609 |
+
"epoch": 7.14,
|
| 610 |
+
"learning_rate": 1.4594594594594596e-05,
|
| 611 |
+
"loss": 1.4981,
|
| 612 |
+
"step": 900
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 7.14,
|
| 616 |
+
"eval_loss": 1.546679139137268,
|
| 617 |
+
"eval_runtime": 13.2814,
|
| 618 |
+
"eval_samples_per_second": 93.288,
|
| 619 |
+
"eval_steps_per_second": 18.673,
|
| 620 |
+
"step": 900
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 7.22,
|
| 624 |
+
"learning_rate": 1.4504504504504506e-05,
|
| 625 |
+
"loss": 1.5341,
|
| 626 |
+
"step": 910
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 7.3,
|
| 630 |
+
"learning_rate": 1.4414414414414416e-05,
|
| 631 |
+
"loss": 1.5301,
|
| 632 |
+
"step": 920
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 7.38,
|
| 636 |
+
"learning_rate": 1.4324324324324326e-05,
|
| 637 |
+
"loss": 1.5253,
|
| 638 |
+
"step": 930
|
| 639 |
+
},
|
| 640 |
+
{
|
| 641 |
+
"epoch": 7.46,
|
| 642 |
+
"learning_rate": 1.4234234234234234e-05,
|
| 643 |
+
"loss": 1.5697,
|
| 644 |
+
"step": 940
|
| 645 |
+
},
|
| 646 |
+
{
|
| 647 |
+
"epoch": 7.54,
|
| 648 |
+
"learning_rate": 1.4144144144144145e-05,
|
| 649 |
+
"loss": 1.5482,
|
| 650 |
+
"step": 950
|
| 651 |
+
},
|
| 652 |
+
{
|
| 653 |
+
"epoch": 7.62,
|
| 654 |
+
"learning_rate": 1.4054054054054055e-05,
|
| 655 |
+
"loss": 1.4849,
|
| 656 |
+
"step": 960
|
| 657 |
+
},
|
| 658 |
+
{
|
| 659 |
+
"epoch": 7.69,
|
| 660 |
+
"learning_rate": 1.3963963963963964e-05,
|
| 661 |
+
"loss": 1.536,
|
| 662 |
+
"step": 970
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 7.77,
|
| 666 |
+
"learning_rate": 1.3873873873873875e-05,
|
| 667 |
+
"loss": 1.5267,
|
| 668 |
+
"step": 980
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 7.85,
|
| 672 |
+
"learning_rate": 1.3783783783783784e-05,
|
| 673 |
+
"loss": 1.5003,
|
| 674 |
+
"step": 990
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 7.93,
|
| 678 |
+
"learning_rate": 1.3693693693693695e-05,
|
| 679 |
+
"loss": 1.5296,
|
| 680 |
+
"step": 1000
|
| 681 |
+
},
|
| 682 |
+
{
|
| 683 |
+
"epoch": 7.93,
|
| 684 |
+
"eval_loss": 1.5358564853668213,
|
| 685 |
+
"eval_runtime": 13.2903,
|
| 686 |
+
"eval_samples_per_second": 93.226,
|
| 687 |
+
"eval_steps_per_second": 18.66,
|
| 688 |
+
"step": 1000
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 8.02,
|
| 692 |
+
"learning_rate": 1.3594594594594597e-05,
|
| 693 |
+
"loss": 1.6728,
|
| 694 |
+
"step": 1010
|
| 695 |
+
},
|
| 696 |
+
{
|
| 697 |
+
"epoch": 8.09,
|
| 698 |
+
"learning_rate": 1.3504504504504506e-05,
|
| 699 |
+
"loss": 1.4944,
|
| 700 |
+
"step": 1020
|
| 701 |
+
},
|
| 702 |
+
{
|
| 703 |
+
"epoch": 8.17,
|
| 704 |
+
"learning_rate": 1.3414414414414417e-05,
|
| 705 |
+
"loss": 1.5016,
|
| 706 |
+
"step": 1030
|
| 707 |
+
},
|
| 708 |
+
{
|
| 709 |
+
"epoch": 8.25,
|
| 710 |
+
"learning_rate": 1.3324324324324324e-05,
|
| 711 |
+
"loss": 1.5407,
|
| 712 |
+
"step": 1040
|
| 713 |
+
},
|
| 714 |
+
{
|
| 715 |
+
"epoch": 8.33,
|
| 716 |
+
"learning_rate": 1.3234234234234235e-05,
|
| 717 |
+
"loss": 1.5129,
|
| 718 |
+
"step": 1050
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 8.41,
|
| 722 |
+
"learning_rate": 1.3144144144144144e-05,
|
| 723 |
+
"loss": 1.4774,
|
| 724 |
+
"step": 1060
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 8.49,
|
| 728 |
+
"learning_rate": 1.3054054054054055e-05,
|
| 729 |
+
"loss": 1.5181,
|
| 730 |
+
"step": 1070
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 8.57,
|
| 734 |
+
"learning_rate": 1.2963963963963966e-05,
|
| 735 |
+
"loss": 1.4897,
|
| 736 |
+
"step": 1080
|
| 737 |
+
},
|
| 738 |
+
{
|
| 739 |
+
"epoch": 8.65,
|
| 740 |
+
"learning_rate": 1.2873873873873875e-05,
|
| 741 |
+
"loss": 1.4918,
|
| 742 |
+
"step": 1090
|
| 743 |
+
},
|
| 744 |
+
{
|
| 745 |
+
"epoch": 8.73,
|
| 746 |
+
"learning_rate": 1.2783783783783785e-05,
|
| 747 |
+
"loss": 1.4734,
|
| 748 |
+
"step": 1100
|
| 749 |
+
},
|
| 750 |
+
{
|
| 751 |
+
"epoch": 8.73,
|
| 752 |
+
"eval_loss": 1.5299837589263916,
|
| 753 |
+
"eval_runtime": 13.3097,
|
| 754 |
+
"eval_samples_per_second": 93.09,
|
| 755 |
+
"eval_steps_per_second": 18.633,
|
| 756 |
+
"step": 1100
|
| 757 |
+
},
|
| 758 |
+
{
|
| 759 |
+
"epoch": 8.8,
|
| 760 |
+
"learning_rate": 1.2693693693693695e-05,
|
| 761 |
+
"loss": 1.4425,
|
| 762 |
+
"step": 1110
|
| 763 |
+
},
|
| 764 |
+
{
|
| 765 |
+
"epoch": 8.88,
|
| 766 |
+
"learning_rate": 1.2603603603603605e-05,
|
| 767 |
+
"loss": 1.5102,
|
| 768 |
+
"step": 1120
|
| 769 |
+
},
|
| 770 |
+
{
|
| 771 |
+
"epoch": 8.96,
|
| 772 |
+
"learning_rate": 1.2513513513513516e-05,
|
| 773 |
+
"loss": 1.4614,
|
| 774 |
+
"step": 1130
|
| 775 |
+
},
|
| 776 |
+
{
|
| 777 |
+
"epoch": 9.05,
|
| 778 |
+
"learning_rate": 1.2423423423423424e-05,
|
| 779 |
+
"loss": 1.5378,
|
| 780 |
+
"step": 1140
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 9.13,
|
| 784 |
+
"learning_rate": 1.2333333333333334e-05,
|
| 785 |
+
"loss": 1.5182,
|
| 786 |
+
"step": 1150
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 9.21,
|
| 790 |
+
"learning_rate": 1.2243243243243244e-05,
|
| 791 |
+
"loss": 1.4606,
|
| 792 |
+
"step": 1160
|
| 793 |
+
},
|
| 794 |
+
{
|
| 795 |
+
"epoch": 9.28,
|
| 796 |
+
"learning_rate": 1.2153153153153154e-05,
|
| 797 |
+
"loss": 1.4675,
|
| 798 |
+
"step": 1170
|
| 799 |
+
},
|
| 800 |
+
{
|
| 801 |
+
"epoch": 9.36,
|
| 802 |
+
"learning_rate": 1.2063063063063063e-05,
|
| 803 |
+
"loss": 1.5261,
|
| 804 |
+
"step": 1180
|
| 805 |
+
},
|
| 806 |
+
{
|
| 807 |
+
"epoch": 9.44,
|
| 808 |
+
"learning_rate": 1.1972972972972974e-05,
|
| 809 |
+
"loss": 1.4602,
|
| 810 |
+
"step": 1190
|
| 811 |
+
},
|
| 812 |
+
{
|
| 813 |
+
"epoch": 9.52,
|
| 814 |
+
"learning_rate": 1.1882882882882885e-05,
|
| 815 |
+
"loss": 1.4415,
|
| 816 |
+
"step": 1200
|
| 817 |
+
},
|
| 818 |
+
{
|
| 819 |
+
"epoch": 9.52,
|
| 820 |
+
"eval_loss": 1.521682620048523,
|
| 821 |
+
"eval_runtime": 13.2939,
|
| 822 |
+
"eval_samples_per_second": 93.2,
|
| 823 |
+
"eval_steps_per_second": 18.655,
|
| 824 |
+
"step": 1200
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 9.6,
|
| 828 |
+
"learning_rate": 1.1792792792792792e-05,
|
| 829 |
+
"loss": 1.4601,
|
| 830 |
+
"step": 1210
|
| 831 |
+
},
|
| 832 |
+
{
|
| 833 |
+
"epoch": 9.68,
|
| 834 |
+
"learning_rate": 1.1702702702702703e-05,
|
| 835 |
+
"loss": 1.4676,
|
| 836 |
+
"step": 1220
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 9.76,
|
| 840 |
+
"learning_rate": 1.1612612612612612e-05,
|
| 841 |
+
"loss": 1.4213,
|
| 842 |
+
"step": 1230
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 9.84,
|
| 846 |
+
"learning_rate": 1.1522522522522523e-05,
|
| 847 |
+
"loss": 1.4096,
|
| 848 |
+
"step": 1240
|
| 849 |
+
},
|
| 850 |
+
{
|
| 851 |
+
"epoch": 9.92,
|
| 852 |
+
"learning_rate": 1.1432432432432434e-05,
|
| 853 |
+
"loss": 1.4475,
|
| 854 |
+
"step": 1250
|
| 855 |
+
},
|
| 856 |
+
{
|
| 857 |
+
"epoch": 9.99,
|
| 858 |
+
"learning_rate": 1.1342342342342343e-05,
|
| 859 |
+
"loss": 1.4477,
|
| 860 |
+
"step": 1260
|
| 861 |
+
},
|
| 862 |
+
{
|
| 863 |
+
"epoch": 10.08,
|
| 864 |
+
"learning_rate": 1.1243243243243245e-05,
|
| 865 |
+
"loss": 1.4979,
|
| 866 |
+
"step": 1270
|
| 867 |
+
},
|
| 868 |
+
{
|
| 869 |
+
"epoch": 10.16,
|
| 870 |
+
"learning_rate": 1.1153153153153154e-05,
|
| 871 |
+
"loss": 1.4436,
|
| 872 |
+
"step": 1280
|
| 873 |
+
},
|
| 874 |
+
{
|
| 875 |
+
"epoch": 10.24,
|
| 876 |
+
"learning_rate": 1.1063063063063065e-05,
|
| 877 |
+
"loss": 1.4913,
|
| 878 |
+
"step": 1290
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 10.32,
|
| 882 |
+
"learning_rate": 1.0972972972972974e-05,
|
| 883 |
+
"loss": 1.4513,
|
| 884 |
+
"step": 1300
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 10.32,
|
| 888 |
+
"eval_loss": 1.5171560049057007,
|
| 889 |
+
"eval_runtime": 13.2984,
|
| 890 |
+
"eval_samples_per_second": 93.169,
|
| 891 |
+
"eval_steps_per_second": 18.649,
|
| 892 |
+
"step": 1300
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 10.39,
|
| 896 |
+
"learning_rate": 1.0882882882882884e-05,
|
| 897 |
+
"loss": 1.4649,
|
| 898 |
+
"step": 1310
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 10.47,
|
| 902 |
+
"learning_rate": 1.0792792792792795e-05,
|
| 903 |
+
"loss": 1.4126,
|
| 904 |
+
"step": 1320
|
| 905 |
+
},
|
| 906 |
+
{
|
| 907 |
+
"epoch": 10.55,
|
| 908 |
+
"learning_rate": 1.0702702702702703e-05,
|
| 909 |
+
"loss": 1.3916,
|
| 910 |
+
"step": 1330
|
| 911 |
+
},
|
| 912 |
+
{
|
| 913 |
+
"epoch": 10.63,
|
| 914 |
+
"learning_rate": 1.0612612612612613e-05,
|
| 915 |
+
"loss": 1.393,
|
| 916 |
+
"step": 1340
|
| 917 |
+
},
|
| 918 |
+
{
|
| 919 |
+
"epoch": 10.71,
|
| 920 |
+
"learning_rate": 1.0522522522522523e-05,
|
| 921 |
+
"loss": 1.3972,
|
| 922 |
+
"step": 1350
|
| 923 |
+
},
|
| 924 |
+
{
|
| 925 |
+
"epoch": 10.79,
|
| 926 |
+
"learning_rate": 1.0432432432432433e-05,
|
| 927 |
+
"loss": 1.4867,
|
| 928 |
+
"step": 1360
|
| 929 |
+
},
|
| 930 |
+
{
|
| 931 |
+
"epoch": 10.87,
|
| 932 |
+
"learning_rate": 1.0342342342342344e-05,
|
| 933 |
+
"loss": 1.4109,
|
| 934 |
+
"step": 1370
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 10.95,
|
| 938 |
+
"learning_rate": 1.0252252252252253e-05,
|
| 939 |
+
"loss": 1.4215,
|
| 940 |
+
"step": 1380
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 11.03,
|
| 944 |
+
"learning_rate": 1.0153153153153155e-05,
|
| 945 |
+
"loss": 1.5288,
|
| 946 |
+
"step": 1390
|
| 947 |
+
},
|
| 948 |
+
{
|
| 949 |
+
"epoch": 11.11,
|
| 950 |
+
"learning_rate": 1.0063063063063064e-05,
|
| 951 |
+
"loss": 1.3782,
|
| 952 |
+
"step": 1400
|
| 953 |
+
},
|
| 954 |
+
{
|
| 955 |
+
"epoch": 11.11,
|
| 956 |
+
"eval_loss": 1.5077377557754517,
|
| 957 |
+
"eval_runtime": 13.2758,
|
| 958 |
+
"eval_samples_per_second": 93.328,
|
| 959 |
+
"eval_steps_per_second": 18.681,
|
| 960 |
+
"step": 1400
|
| 961 |
+
},
|
| 962 |
+
{
|
| 963 |
+
"epoch": 11.19,
|
| 964 |
+
"learning_rate": 9.972972972972975e-06,
|
| 965 |
+
"loss": 1.4292,
|
| 966 |
+
"step": 1410
|
| 967 |
+
},
|
| 968 |
+
{
|
| 969 |
+
"epoch": 11.27,
|
| 970 |
+
"learning_rate": 9.882882882882884e-06,
|
| 971 |
+
"loss": 1.4404,
|
| 972 |
+
"step": 1420
|
| 973 |
+
},
|
| 974 |
+
{
|
| 975 |
+
"epoch": 11.35,
|
| 976 |
+
"learning_rate": 9.792792792792793e-06,
|
| 977 |
+
"loss": 1.4192,
|
| 978 |
+
"step": 1430
|
| 979 |
+
},
|
| 980 |
+
{
|
| 981 |
+
"epoch": 11.43,
|
| 982 |
+
"learning_rate": 9.702702702702704e-06,
|
| 983 |
+
"loss": 1.324,
|
| 984 |
+
"step": 1440
|
| 985 |
+
},
|
| 986 |
+
{
|
| 987 |
+
"epoch": 11.5,
|
| 988 |
+
"learning_rate": 9.612612612612613e-06,
|
| 989 |
+
"loss": 1.4342,
|
| 990 |
+
"step": 1450
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 11.58,
|
| 994 |
+
"learning_rate": 9.522522522522524e-06,
|
| 995 |
+
"loss": 1.4233,
|
| 996 |
+
"step": 1460
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 11.66,
|
| 1000 |
+
"learning_rate": 9.432432432432433e-06,
|
| 1001 |
+
"loss": 1.3475,
|
| 1002 |
+
"step": 1470
|
| 1003 |
+
},
|
| 1004 |
+
{
|
| 1005 |
+
"epoch": 11.74,
|
| 1006 |
+
"learning_rate": 9.342342342342344e-06,
|
| 1007 |
+
"loss": 1.4178,
|
| 1008 |
+
"step": 1480
|
| 1009 |
+
},
|
| 1010 |
+
{
|
| 1011 |
+
"epoch": 11.82,
|
| 1012 |
+
"learning_rate": 9.252252252252253e-06,
|
| 1013 |
+
"loss": 1.3842,
|
| 1014 |
+
"step": 1490
|
| 1015 |
+
},
|
| 1016 |
+
{
|
| 1017 |
+
"epoch": 11.9,
|
| 1018 |
+
"learning_rate": 9.162162162162162e-06,
|
| 1019 |
+
"loss": 1.4103,
|
| 1020 |
+
"step": 1500
|
| 1021 |
+
},
|
| 1022 |
+
{
|
| 1023 |
+
"epoch": 11.9,
|
| 1024 |
+
"eval_loss": 1.507853388786316,
|
| 1025 |
+
"eval_runtime": 13.2911,
|
| 1026 |
+
"eval_samples_per_second": 93.22,
|
| 1027 |
+
"eval_steps_per_second": 18.659,
|
| 1028 |
+
"step": 1500
|
| 1029 |
+
},
|
| 1030 |
+
{
|
| 1031 |
+
"epoch": 11.98,
|
| 1032 |
+
"learning_rate": 9.072072072072073e-06,
|
| 1033 |
+
"loss": 1.3918,
|
| 1034 |
+
"step": 1510
|
| 1035 |
+
},
|
| 1036 |
+
{
|
| 1037 |
+
"epoch": 12.06,
|
| 1038 |
+
"learning_rate": 8.972972972972974e-06,
|
| 1039 |
+
"loss": 1.4841,
|
| 1040 |
+
"step": 1520
|
| 1041 |
+
},
|
| 1042 |
+
{
|
| 1043 |
+
"epoch": 12.14,
|
| 1044 |
+
"learning_rate": 8.882882882882883e-06,
|
| 1045 |
+
"loss": 1.3866,
|
| 1046 |
+
"step": 1530
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 12.22,
|
| 1050 |
+
"learning_rate": 8.792792792792794e-06,
|
| 1051 |
+
"loss": 1.3713,
|
| 1052 |
+
"step": 1540
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 12.3,
|
| 1056 |
+
"learning_rate": 8.702702702702703e-06,
|
| 1057 |
+
"loss": 1.3384,
|
| 1058 |
+
"step": 1550
|
| 1059 |
+
},
|
| 1060 |
+
{
|
| 1061 |
+
"epoch": 12.38,
|
| 1062 |
+
"learning_rate": 8.612612612612612e-06,
|
| 1063 |
+
"loss": 1.4079,
|
| 1064 |
+
"step": 1560
|
| 1065 |
+
},
|
| 1066 |
+
{
|
| 1067 |
+
"epoch": 12.46,
|
| 1068 |
+
"learning_rate": 8.522522522522523e-06,
|
| 1069 |
+
"loss": 1.3715,
|
| 1070 |
+
"step": 1570
|
| 1071 |
+
},
|
| 1072 |
+
{
|
| 1073 |
+
"epoch": 12.54,
|
| 1074 |
+
"learning_rate": 8.432432432432434e-06,
|
| 1075 |
+
"loss": 1.3541,
|
| 1076 |
+
"step": 1580
|
| 1077 |
+
},
|
| 1078 |
+
{
|
| 1079 |
+
"epoch": 12.62,
|
| 1080 |
+
"learning_rate": 8.342342342342343e-06,
|
| 1081 |
+
"loss": 1.3764,
|
| 1082 |
+
"step": 1590
|
| 1083 |
+
},
|
| 1084 |
+
{
|
| 1085 |
+
"epoch": 12.69,
|
| 1086 |
+
"learning_rate": 8.252252252252254e-06,
|
| 1087 |
+
"loss": 1.3907,
|
| 1088 |
+
"step": 1600
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 12.69,
|
| 1092 |
+
"eval_loss": 1.5033966302871704,
|
| 1093 |
+
"eval_runtime": 13.2864,
|
| 1094 |
+
"eval_samples_per_second": 93.254,
|
| 1095 |
+
"eval_steps_per_second": 18.666,
|
| 1096 |
+
"step": 1600
|
| 1097 |
+
},
|
| 1098 |
+
{
|
| 1099 |
+
"epoch": 12.77,
|
| 1100 |
+
"learning_rate": 8.162162162162163e-06,
|
| 1101 |
+
"loss": 1.3626,
|
| 1102 |
+
"step": 1610
|
| 1103 |
+
},
|
| 1104 |
+
{
|
| 1105 |
+
"epoch": 12.85,
|
| 1106 |
+
"learning_rate": 8.072072072072072e-06,
|
| 1107 |
+
"loss": 1.4094,
|
| 1108 |
+
"step": 1620
|
| 1109 |
+
},
|
| 1110 |
+
{
|
| 1111 |
+
"epoch": 12.93,
|
| 1112 |
+
"learning_rate": 7.981981981981983e-06,
|
| 1113 |
+
"loss": 1.3579,
|
| 1114 |
+
"step": 1630
|
| 1115 |
+
},
|
| 1116 |
+
{
|
| 1117 |
+
"epoch": 13.02,
|
| 1118 |
+
"learning_rate": 7.891891891891894e-06,
|
| 1119 |
+
"loss": 1.4517,
|
| 1120 |
+
"step": 1640
|
| 1121 |
+
},
|
| 1122 |
+
{
|
| 1123 |
+
"epoch": 13.09,
|
| 1124 |
+
"learning_rate": 7.801801801801803e-06,
|
| 1125 |
+
"loss": 1.301,
|
| 1126 |
+
"step": 1650
|
| 1127 |
+
},
|
| 1128 |
+
{
|
| 1129 |
+
"epoch": 13.17,
|
| 1130 |
+
"learning_rate": 7.711711711711712e-06,
|
| 1131 |
+
"loss": 1.3513,
|
| 1132 |
+
"step": 1660
|
| 1133 |
+
},
|
| 1134 |
+
{
|
| 1135 |
+
"epoch": 13.25,
|
| 1136 |
+
"learning_rate": 7.621621621621622e-06,
|
| 1137 |
+
"loss": 1.3487,
|
| 1138 |
+
"step": 1670
|
| 1139 |
+
},
|
| 1140 |
+
{
|
| 1141 |
+
"epoch": 13.33,
|
| 1142 |
+
"learning_rate": 7.531531531531532e-06,
|
| 1143 |
+
"loss": 1.3894,
|
| 1144 |
+
"step": 1680
|
| 1145 |
+
},
|
| 1146 |
+
{
|
| 1147 |
+
"epoch": 13.41,
|
| 1148 |
+
"learning_rate": 7.441441441441442e-06,
|
| 1149 |
+
"loss": 1.3619,
|
| 1150 |
+
"step": 1690
|
| 1151 |
+
},
|
| 1152 |
+
{
|
| 1153 |
+
"epoch": 13.49,
|
| 1154 |
+
"learning_rate": 7.3513513513513525e-06,
|
| 1155 |
+
"loss": 1.3663,
|
| 1156 |
+
"step": 1700
|
| 1157 |
+
},
|
| 1158 |
+
{
|
| 1159 |
+
"epoch": 13.49,
|
| 1160 |
+
"eval_loss": 1.501574993133545,
|
| 1161 |
+
"eval_runtime": 13.3092,
|
| 1162 |
+
"eval_samples_per_second": 93.094,
|
| 1163 |
+
"eval_steps_per_second": 18.634,
|
| 1164 |
+
"step": 1700
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 13.57,
|
| 1168 |
+
"learning_rate": 7.2612612612612625e-06,
|
| 1169 |
+
"loss": 1.3268,
|
| 1170 |
+
"step": 1710
|
| 1171 |
+
},
|
| 1172 |
+
{
|
| 1173 |
+
"epoch": 13.65,
|
| 1174 |
+
"learning_rate": 7.1711711711711716e-06,
|
| 1175 |
+
"loss": 1.3703,
|
| 1176 |
+
"step": 1720
|
| 1177 |
+
},
|
| 1178 |
+
{
|
| 1179 |
+
"epoch": 13.73,
|
| 1180 |
+
"learning_rate": 7.0810810810810815e-06,
|
| 1181 |
+
"loss": 1.4246,
|
| 1182 |
+
"step": 1730
|
| 1183 |
+
},
|
| 1184 |
+
{
|
| 1185 |
+
"epoch": 13.8,
|
| 1186 |
+
"learning_rate": 6.9909909909909915e-06,
|
| 1187 |
+
"loss": 1.3642,
|
| 1188 |
+
"step": 1740
|
| 1189 |
+
},
|
| 1190 |
+
{
|
| 1191 |
+
"epoch": 13.88,
|
| 1192 |
+
"learning_rate": 6.900900900900901e-06,
|
| 1193 |
+
"loss": 1.3467,
|
| 1194 |
+
"step": 1750
|
| 1195 |
+
},
|
| 1196 |
+
{
|
| 1197 |
+
"epoch": 13.96,
|
| 1198 |
+
"learning_rate": 6.810810810810811e-06,
|
| 1199 |
+
"loss": 1.3802,
|
| 1200 |
+
"step": 1760
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 14.05,
|
| 1204 |
+
"learning_rate": 6.711711711711713e-06,
|
| 1205 |
+
"loss": 1.4328,
|
| 1206 |
+
"step": 1770
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"epoch": 14.13,
|
| 1210 |
+
"learning_rate": 6.621621621621622e-06,
|
| 1211 |
+
"loss": 1.3316,
|
| 1212 |
+
"step": 1780
|
| 1213 |
+
},
|
| 1214 |
+
{
|
| 1215 |
+
"epoch": 14.21,
|
| 1216 |
+
"learning_rate": 6.531531531531532e-06,
|
| 1217 |
+
"loss": 1.3634,
|
| 1218 |
+
"step": 1790
|
| 1219 |
+
},
|
| 1220 |
+
{
|
| 1221 |
+
"epoch": 14.28,
|
| 1222 |
+
"learning_rate": 6.441441441441442e-06,
|
| 1223 |
+
"loss": 1.3565,
|
| 1224 |
+
"step": 1800
|
| 1225 |
+
},
|
| 1226 |
+
{
|
| 1227 |
+
"epoch": 14.28,
|
| 1228 |
+
"eval_loss": 1.4980181455612183,
|
| 1229 |
+
"eval_runtime": 13.2875,
|
| 1230 |
+
"eval_samples_per_second": 93.246,
|
| 1231 |
+
"eval_steps_per_second": 18.664,
|
| 1232 |
+
"step": 1800
|
| 1233 |
+
},
|
| 1234 |
+
{
|
| 1235 |
+
"epoch": 14.36,
|
| 1236 |
+
"learning_rate": 6.351351351351351e-06,
|
| 1237 |
+
"loss": 1.3217,
|
| 1238 |
+
"step": 1810
|
| 1239 |
+
},
|
| 1240 |
+
{
|
| 1241 |
+
"epoch": 14.44,
|
| 1242 |
+
"learning_rate": 6.261261261261262e-06,
|
| 1243 |
+
"loss": 1.33,
|
| 1244 |
+
"step": 1820
|
| 1245 |
+
},
|
| 1246 |
+
{
|
| 1247 |
+
"epoch": 14.52,
|
| 1248 |
+
"learning_rate": 6.171171171171172e-06,
|
| 1249 |
+
"loss": 1.3513,
|
| 1250 |
+
"step": 1830
|
| 1251 |
+
},
|
| 1252 |
+
{
|
| 1253 |
+
"epoch": 14.6,
|
| 1254 |
+
"learning_rate": 6.081081081081082e-06,
|
| 1255 |
+
"loss": 1.3649,
|
| 1256 |
+
"step": 1840
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 14.68,
|
| 1260 |
+
"learning_rate": 5.990990990990992e-06,
|
| 1261 |
+
"loss": 1.3462,
|
| 1262 |
+
"step": 1850
|
| 1263 |
+
},
|
| 1264 |
+
{
|
| 1265 |
+
"epoch": 14.76,
|
| 1266 |
+
"learning_rate": 5.900900900900901e-06,
|
| 1267 |
+
"loss": 1.3454,
|
| 1268 |
+
"step": 1860
|
| 1269 |
+
},
|
| 1270 |
+
{
|
| 1271 |
+
"epoch": 14.84,
|
| 1272 |
+
"learning_rate": 5.810810810810811e-06,
|
| 1273 |
+
"loss": 1.3316,
|
| 1274 |
+
"step": 1870
|
| 1275 |
+
},
|
| 1276 |
+
{
|
| 1277 |
+
"epoch": 14.92,
|
| 1278 |
+
"learning_rate": 5.720720720720722e-06,
|
| 1279 |
+
"loss": 1.3347,
|
| 1280 |
+
"step": 1880
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 14.99,
|
| 1284 |
+
"learning_rate": 5.6306306306306316e-06,
|
| 1285 |
+
"loss": 1.3039,
|
| 1286 |
+
"step": 1890
|
| 1287 |
+
},
|
| 1288 |
+
{
|
| 1289 |
+
"epoch": 15.08,
|
| 1290 |
+
"learning_rate": 5.531531531531532e-06,
|
| 1291 |
+
"loss": 1.4057,
|
| 1292 |
+
"step": 1900
|
| 1293 |
+
},
|
| 1294 |
+
{
|
| 1295 |
+
"epoch": 15.08,
|
| 1296 |
+
"eval_loss": 1.4985554218292236,
|
| 1297 |
+
"eval_runtime": 13.2747,
|
| 1298 |
+
"eval_samples_per_second": 93.335,
|
| 1299 |
+
"eval_steps_per_second": 18.682,
|
| 1300 |
+
"step": 1900
|
| 1301 |
+
},
|
| 1302 |
+
{
|
| 1303 |
+
"epoch": 15.16,
|
| 1304 |
+
"learning_rate": 5.441441441441442e-06,
|
| 1305 |
+
"loss": 1.3082,
|
| 1306 |
+
"step": 1910
|
| 1307 |
+
},
|
| 1308 |
+
{
|
| 1309 |
+
"epoch": 15.24,
|
| 1310 |
+
"learning_rate": 5.351351351351351e-06,
|
| 1311 |
+
"loss": 1.3589,
|
| 1312 |
+
"step": 1920
|
| 1313 |
+
},
|
| 1314 |
+
{
|
| 1315 |
+
"epoch": 15.32,
|
| 1316 |
+
"learning_rate": 5.261261261261261e-06,
|
| 1317 |
+
"loss": 1.3235,
|
| 1318 |
+
"step": 1930
|
| 1319 |
+
},
|
| 1320 |
+
{
|
| 1321 |
+
"epoch": 15.39,
|
| 1322 |
+
"learning_rate": 5.171171171171172e-06,
|
| 1323 |
+
"loss": 1.3153,
|
| 1324 |
+
"step": 1940
|
| 1325 |
+
},
|
| 1326 |
+
{
|
| 1327 |
+
"epoch": 15.47,
|
| 1328 |
+
"learning_rate": 5.081081081081082e-06,
|
| 1329 |
+
"loss": 1.3345,
|
| 1330 |
+
"step": 1950
|
| 1331 |
+
},
|
| 1332 |
+
{
|
| 1333 |
+
"epoch": 15.55,
|
| 1334 |
+
"learning_rate": 4.990990990990991e-06,
|
| 1335 |
+
"loss": 1.3824,
|
| 1336 |
+
"step": 1960
|
| 1337 |
+
},
|
| 1338 |
+
{
|
| 1339 |
+
"epoch": 15.63,
|
| 1340 |
+
"learning_rate": 4.900900900900901e-06,
|
| 1341 |
+
"loss": 1.291,
|
| 1342 |
+
"step": 1970
|
| 1343 |
+
},
|
| 1344 |
+
{
|
| 1345 |
+
"epoch": 15.71,
|
| 1346 |
+
"learning_rate": 4.810810810810811e-06,
|
| 1347 |
+
"loss": 1.3106,
|
| 1348 |
+
"step": 1980
|
| 1349 |
+
},
|
| 1350 |
+
{
|
| 1351 |
+
"epoch": 15.79,
|
| 1352 |
+
"learning_rate": 4.720720720720721e-06,
|
| 1353 |
+
"loss": 1.3559,
|
| 1354 |
+
"step": 1990
|
| 1355 |
+
},
|
| 1356 |
+
{
|
| 1357 |
+
"epoch": 15.87,
|
| 1358 |
+
"learning_rate": 4.630630630630631e-06,
|
| 1359 |
+
"loss": 1.3406,
|
| 1360 |
+
"step": 2000
|
| 1361 |
+
},
|
| 1362 |
+
{
|
| 1363 |
+
"epoch": 15.87,
|
| 1364 |
+
"eval_loss": 1.4952143430709839,
|
| 1365 |
+
"eval_runtime": 13.2782,
|
| 1366 |
+
"eval_samples_per_second": 93.31,
|
| 1367 |
+
"eval_steps_per_second": 18.677,
|
| 1368 |
+
"step": 2000
|
| 1369 |
+
},
|
| 1370 |
+
{
|
| 1371 |
+
"epoch": 15.95,
|
| 1372 |
+
"learning_rate": 4.540540540540541e-06,
|
| 1373 |
+
"loss": 1.328,
|
| 1374 |
+
"step": 2010
|
| 1375 |
+
},
|
| 1376 |
+
{
|
| 1377 |
+
"epoch": 16.03,
|
| 1378 |
+
"learning_rate": 4.441441441441442e-06,
|
| 1379 |
+
"loss": 1.4218,
|
| 1380 |
+
"step": 2020
|
| 1381 |
+
},
|
| 1382 |
+
{
|
| 1383 |
+
"epoch": 16.11,
|
| 1384 |
+
"learning_rate": 4.351351351351352e-06,
|
| 1385 |
+
"loss": 1.2962,
|
| 1386 |
+
"step": 2030
|
| 1387 |
+
},
|
| 1388 |
+
{
|
| 1389 |
+
"epoch": 16.19,
|
| 1390 |
+
"learning_rate": 4.2612612612612615e-06,
|
| 1391 |
+
"loss": 1.3122,
|
| 1392 |
+
"step": 2040
|
| 1393 |
+
},
|
| 1394 |
+
{
|
| 1395 |
+
"epoch": 16.27,
|
| 1396 |
+
"learning_rate": 4.1711711711711715e-06,
|
| 1397 |
+
"loss": 1.3641,
|
| 1398 |
+
"step": 2050
|
| 1399 |
+
},
|
| 1400 |
+
{
|
| 1401 |
+
"epoch": 16.35,
|
| 1402 |
+
"learning_rate": 4.0810810810810815e-06,
|
| 1403 |
+
"loss": 1.3058,
|
| 1404 |
+
"step": 2060
|
| 1405 |
+
},
|
| 1406 |
+
{
|
| 1407 |
+
"epoch": 16.43,
|
| 1408 |
+
"learning_rate": 3.990990990990991e-06,
|
| 1409 |
+
"loss": 1.2986,
|
| 1410 |
+
"step": 2070
|
| 1411 |
+
},
|
| 1412 |
+
{
|
| 1413 |
+
"epoch": 16.5,
|
| 1414 |
+
"learning_rate": 3.900900900900901e-06,
|
| 1415 |
+
"loss": 1.2902,
|
| 1416 |
+
"step": 2080
|
| 1417 |
+
},
|
| 1418 |
+
{
|
| 1419 |
+
"epoch": 16.58,
|
| 1420 |
+
"learning_rate": 3.810810810810811e-06,
|
| 1421 |
+
"loss": 1.3725,
|
| 1422 |
+
"step": 2090
|
| 1423 |
+
},
|
| 1424 |
+
{
|
| 1425 |
+
"epoch": 16.66,
|
| 1426 |
+
"learning_rate": 3.720720720720721e-06,
|
| 1427 |
+
"loss": 1.3031,
|
| 1428 |
+
"step": 2100
|
| 1429 |
+
},
|
| 1430 |
+
{
|
| 1431 |
+
"epoch": 16.66,
|
| 1432 |
+
"eval_loss": 1.495803713798523,
|
| 1433 |
+
"eval_runtime": 13.2846,
|
| 1434 |
+
"eval_samples_per_second": 93.266,
|
| 1435 |
+
"eval_steps_per_second": 18.668,
|
| 1436 |
+
"step": 2100
|
| 1437 |
+
},
|
| 1438 |
+
{
|
| 1439 |
+
"epoch": 16.74,
|
| 1440 |
+
"learning_rate": 3.6306306306306312e-06,
|
| 1441 |
+
"loss": 1.3091,
|
| 1442 |
+
"step": 2110
|
| 1443 |
+
},
|
| 1444 |
+
{
|
| 1445 |
+
"epoch": 16.82,
|
| 1446 |
+
"learning_rate": 3.5405405405405408e-06,
|
| 1447 |
+
"loss": 1.3003,
|
| 1448 |
+
"step": 2120
|
| 1449 |
+
},
|
| 1450 |
+
{
|
| 1451 |
+
"epoch": 16.9,
|
| 1452 |
+
"learning_rate": 3.4504504504504503e-06,
|
| 1453 |
+
"loss": 1.2694,
|
| 1454 |
+
"step": 2130
|
| 1455 |
+
},
|
| 1456 |
+
{
|
| 1457 |
+
"epoch": 16.98,
|
| 1458 |
+
"learning_rate": 3.3603603603603607e-06,
|
| 1459 |
+
"loss": 1.3349,
|
| 1460 |
+
"step": 2140
|
| 1461 |
+
},
|
| 1462 |
+
{
|
| 1463 |
+
"epoch": 17.06,
|
| 1464 |
+
"learning_rate": 3.2702702702702706e-06,
|
| 1465 |
+
"loss": 1.3553,
|
| 1466 |
+
"step": 2150
|
| 1467 |
+
},
|
| 1468 |
+
{
|
| 1469 |
+
"epoch": 17.14,
|
| 1470 |
+
"learning_rate": 3.1801801801801806e-06,
|
| 1471 |
+
"loss": 1.2844,
|
| 1472 |
+
"step": 2160
|
| 1473 |
+
},
|
| 1474 |
+
{
|
| 1475 |
+
"epoch": 17.22,
|
| 1476 |
+
"learning_rate": 3.0900900900900905e-06,
|
| 1477 |
+
"loss": 1.2815,
|
| 1478 |
+
"step": 2170
|
| 1479 |
+
},
|
| 1480 |
+
{
|
| 1481 |
+
"epoch": 17.3,
|
| 1482 |
+
"learning_rate": 3e-06,
|
| 1483 |
+
"loss": 1.2756,
|
| 1484 |
+
"step": 2180
|
| 1485 |
+
},
|
| 1486 |
+
{
|
| 1487 |
+
"epoch": 17.38,
|
| 1488 |
+
"learning_rate": 2.9099099099099105e-06,
|
| 1489 |
+
"loss": 1.33,
|
| 1490 |
+
"step": 2190
|
| 1491 |
+
},
|
| 1492 |
+
{
|
| 1493 |
+
"epoch": 17.46,
|
| 1494 |
+
"learning_rate": 2.81981981981982e-06,
|
| 1495 |
+
"loss": 1.31,
|
| 1496 |
+
"step": 2200
|
| 1497 |
+
},
|
| 1498 |
+
{
|
| 1499 |
+
"epoch": 17.46,
|
| 1500 |
+
"eval_loss": 1.4959148168563843,
|
| 1501 |
+
"eval_runtime": 13.2926,
|
| 1502 |
+
"eval_samples_per_second": 93.21,
|
| 1503 |
+
"eval_steps_per_second": 18.657,
|
| 1504 |
+
"step": 2200
|
| 1505 |
+
},
|
| 1506 |
+
{
|
| 1507 |
+
"epoch": 17.54,
|
| 1508 |
+
"learning_rate": 2.72972972972973e-06,
|
| 1509 |
+
"loss": 1.3306,
|
| 1510 |
+
"step": 2210
|
| 1511 |
+
},
|
| 1512 |
+
{
|
| 1513 |
+
"epoch": 17.62,
|
| 1514 |
+
"learning_rate": 2.63963963963964e-06,
|
| 1515 |
+
"loss": 1.331,
|
| 1516 |
+
"step": 2220
|
| 1517 |
+
},
|
| 1518 |
+
{
|
| 1519 |
+
"epoch": 17.69,
|
| 1520 |
+
"learning_rate": 2.54954954954955e-06,
|
| 1521 |
+
"loss": 1.3347,
|
| 1522 |
+
"step": 2230
|
| 1523 |
+
},
|
| 1524 |
+
{
|
| 1525 |
+
"epoch": 17.77,
|
| 1526 |
+
"learning_rate": 2.45945945945946e-06,
|
| 1527 |
+
"loss": 1.3291,
|
| 1528 |
+
"step": 2240
|
| 1529 |
+
},
|
| 1530 |
+
{
|
| 1531 |
+
"epoch": 17.85,
|
| 1532 |
+
"learning_rate": 2.3693693693693693e-06,
|
| 1533 |
+
"loss": 1.2774,
|
| 1534 |
+
"step": 2250
|
| 1535 |
+
},
|
| 1536 |
+
{
|
| 1537 |
+
"epoch": 17.93,
|
| 1538 |
+
"learning_rate": 2.2792792792792793e-06,
|
| 1539 |
+
"loss": 1.3102,
|
| 1540 |
+
"step": 2260
|
| 1541 |
+
},
|
| 1542 |
+
{
|
| 1543 |
+
"epoch": 18.02,
|
| 1544 |
+
"learning_rate": 2.1801801801801804e-06,
|
| 1545 |
+
"loss": 1.4393,
|
| 1546 |
+
"step": 2270
|
| 1547 |
+
},
|
| 1548 |
+
{
|
| 1549 |
+
"epoch": 18.09,
|
| 1550 |
+
"learning_rate": 2.0900900900900904e-06,
|
| 1551 |
+
"loss": 1.2779,
|
| 1552 |
+
"step": 2280
|
| 1553 |
+
},
|
| 1554 |
+
{
|
| 1555 |
+
"epoch": 18.17,
|
| 1556 |
+
"learning_rate": 2.0000000000000003e-06,
|
| 1557 |
+
"loss": 1.2708,
|
| 1558 |
+
"step": 2290
|
| 1559 |
+
},
|
| 1560 |
+
{
|
| 1561 |
+
"epoch": 18.25,
|
| 1562 |
+
"learning_rate": 1.90990990990991e-06,
|
| 1563 |
+
"loss": 1.3565,
|
| 1564 |
+
"step": 2300
|
| 1565 |
+
},
|
| 1566 |
+
{
|
| 1567 |
+
"epoch": 18.25,
|
| 1568 |
+
"eval_loss": 1.494253396987915,
|
| 1569 |
+
"eval_runtime": 13.2974,
|
| 1570 |
+
"eval_samples_per_second": 93.176,
|
| 1571 |
+
"eval_steps_per_second": 18.65,
|
| 1572 |
+
"step": 2300
|
| 1573 |
+
},
|
| 1574 |
+
{
|
| 1575 |
+
"epoch": 18.33,
|
| 1576 |
+
"learning_rate": 1.81981981981982e-06,
|
| 1577 |
+
"loss": 1.2744,
|
| 1578 |
+
"step": 2310
|
| 1579 |
+
},
|
| 1580 |
+
{
|
| 1581 |
+
"epoch": 18.41,
|
| 1582 |
+
"learning_rate": 1.72972972972973e-06,
|
| 1583 |
+
"loss": 1.2697,
|
| 1584 |
+
"step": 2320
|
| 1585 |
+
},
|
| 1586 |
+
{
|
| 1587 |
+
"epoch": 18.49,
|
| 1588 |
+
"learning_rate": 1.6396396396396397e-06,
|
| 1589 |
+
"loss": 1.2921,
|
| 1590 |
+
"step": 2330
|
| 1591 |
+
},
|
| 1592 |
+
{
|
| 1593 |
+
"epoch": 18.57,
|
| 1594 |
+
"learning_rate": 1.5495495495495497e-06,
|
| 1595 |
+
"loss": 1.3096,
|
| 1596 |
+
"step": 2340
|
| 1597 |
+
},
|
| 1598 |
+
{
|
| 1599 |
+
"epoch": 18.65,
|
| 1600 |
+
"learning_rate": 1.4594594594594596e-06,
|
| 1601 |
+
"loss": 1.2971,
|
| 1602 |
+
"step": 2350
|
| 1603 |
+
},
|
| 1604 |
+
{
|
| 1605 |
+
"epoch": 18.73,
|
| 1606 |
+
"learning_rate": 1.3693693693693694e-06,
|
| 1607 |
+
"loss": 1.3132,
|
| 1608 |
+
"step": 2360
|
| 1609 |
+
},
|
| 1610 |
+
{
|
| 1611 |
+
"epoch": 18.8,
|
| 1612 |
+
"learning_rate": 1.2792792792792793e-06,
|
| 1613 |
+
"loss": 1.3367,
|
| 1614 |
+
"step": 2370
|
| 1615 |
+
},
|
| 1616 |
+
{
|
| 1617 |
+
"epoch": 18.88,
|
| 1618 |
+
"learning_rate": 1.1891891891891893e-06,
|
| 1619 |
+
"loss": 1.2648,
|
| 1620 |
+
"step": 2380
|
| 1621 |
+
},
|
| 1622 |
+
{
|
| 1623 |
+
"epoch": 18.96,
|
| 1624 |
+
"learning_rate": 1.0990990990990993e-06,
|
| 1625 |
+
"loss": 1.3025,
|
| 1626 |
+
"step": 2390
|
| 1627 |
+
},
|
| 1628 |
+
{
|
| 1629 |
+
"epoch": 19.05,
|
| 1630 |
+
"learning_rate": 1.0000000000000002e-06,
|
| 1631 |
+
"loss": 1.3732,
|
| 1632 |
+
"step": 2400
|
| 1633 |
+
},
|
| 1634 |
+
{
|
| 1635 |
+
"epoch": 19.05,
|
| 1636 |
+
"eval_loss": 1.4953521490097046,
|
| 1637 |
+
"eval_runtime": 13.2927,
|
| 1638 |
+
"eval_samples_per_second": 93.209,
|
| 1639 |
+
"eval_steps_per_second": 18.657,
|
| 1640 |
+
"step": 2400
|
| 1641 |
+
},
|
| 1642 |
+
{
|
| 1643 |
+
"epoch": 19.13,
|
| 1644 |
+
"learning_rate": 9.0990990990991e-07,
|
| 1645 |
+
"loss": 1.2938,
|
| 1646 |
+
"step": 2410
|
| 1647 |
+
},
|
| 1648 |
+
{
|
| 1649 |
+
"epoch": 19.21,
|
| 1650 |
+
"learning_rate": 8.198198198198199e-07,
|
| 1651 |
+
"loss": 1.3374,
|
| 1652 |
+
"step": 2420
|
| 1653 |
+
},
|
| 1654 |
+
{
|
| 1655 |
+
"epoch": 19.28,
|
| 1656 |
+
"learning_rate": 7.297297297297298e-07,
|
| 1657 |
+
"loss": 1.297,
|
| 1658 |
+
"step": 2430
|
| 1659 |
+
},
|
| 1660 |
+
{
|
| 1661 |
+
"epoch": 19.36,
|
| 1662 |
+
"learning_rate": 6.396396396396397e-07,
|
| 1663 |
+
"loss": 1.2748,
|
| 1664 |
+
"step": 2440
|
| 1665 |
+
},
|
| 1666 |
+
{
|
| 1667 |
+
"epoch": 19.44,
|
| 1668 |
+
"learning_rate": 5.495495495495496e-07,
|
| 1669 |
+
"loss": 1.3259,
|
| 1670 |
+
"step": 2450
|
| 1671 |
+
},
|
| 1672 |
+
{
|
| 1673 |
+
"epoch": 19.52,
|
| 1674 |
+
"learning_rate": 4.5945945945945953e-07,
|
| 1675 |
+
"loss": 1.3099,
|
| 1676 |
+
"step": 2460
|
| 1677 |
+
},
|
| 1678 |
+
{
|
| 1679 |
+
"epoch": 19.6,
|
| 1680 |
+
"learning_rate": 3.693693693693694e-07,
|
| 1681 |
+
"loss": 1.3277,
|
| 1682 |
+
"step": 2470
|
| 1683 |
+
},
|
| 1684 |
+
{
|
| 1685 |
+
"epoch": 19.68,
|
| 1686 |
+
"learning_rate": 2.792792792792793e-07,
|
| 1687 |
+
"loss": 1.2708,
|
| 1688 |
+
"step": 2480
|
| 1689 |
+
},
|
| 1690 |
+
{
|
| 1691 |
+
"epoch": 19.76,
|
| 1692 |
+
"learning_rate": 1.8918918918918921e-07,
|
| 1693 |
+
"loss": 1.2546,
|
| 1694 |
+
"step": 2490
|
| 1695 |
+
},
|
| 1696 |
+
{
|
| 1697 |
+
"epoch": 19.84,
|
| 1698 |
+
"learning_rate": 9.90990990990991e-08,
|
| 1699 |
+
"loss": 1.2705,
|
| 1700 |
+
"step": 2500
|
| 1701 |
+
},
|
| 1702 |
+
{
|
| 1703 |
+
"epoch": 19.84,
|
| 1704 |
+
"eval_loss": 1.494584560394287,
|
| 1705 |
+
"eval_runtime": 13.2864,
|
| 1706 |
+
"eval_samples_per_second": 93.253,
|
| 1707 |
+
"eval_steps_per_second": 18.666,
|
| 1708 |
+
"step": 2500
|
| 1709 |
+
}
|
| 1710 |
+
],
|
| 1711 |
+
"max_steps": 2520,
|
| 1712 |
+
"num_train_epochs": 20,
|
| 1713 |
+
"total_flos": 5.993865079244718e+17,
|
| 1714 |
+
"trial_name": null,
|
| 1715 |
+
"trial_params": null
|
| 1716 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:61115c5cf7ceefe0d455cb65f5dca284bb6e55117a5791159dac2fe0548e9c12
|
| 3 |
+
size 4591
|