Upload 10 files
Browse files- .gitattributes +1 -0
- config.json +38 -0
- generation_config.json +7 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +6 -0
- tokenizer.json +3 -0
- tokenizer_config.json +12 -0
- trainer_state.json +956 -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 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "bigscience/bloom-560m",
|
| 3 |
+
"apply_residual_connection_post_layernorm": false,
|
| 4 |
+
"architectures": [
|
| 5 |
+
"BloomForCausalLM"
|
| 6 |
+
],
|
| 7 |
+
"attention_dropout": 0.0,
|
| 8 |
+
"attention_softmax_in_fp32": true,
|
| 9 |
+
"bias_dropout_fusion": true,
|
| 10 |
+
"bos_token_id": 1,
|
| 11 |
+
"do_sample": true,
|
| 12 |
+
"early_stopping": true,
|
| 13 |
+
"eos_token_id": 2,
|
| 14 |
+
"hidden_dropout": 0.0,
|
| 15 |
+
"hidden_size": 1024,
|
| 16 |
+
"initializer_range": 0.02,
|
| 17 |
+
"layer_norm_epsilon": 1e-05,
|
| 18 |
+
"length_penalty": 2.0,
|
| 19 |
+
"masked_softmax_fusion": true,
|
| 20 |
+
"model_type": "bloom",
|
| 21 |
+
"n_head": 16,
|
| 22 |
+
"n_inner": null,
|
| 23 |
+
"n_layer": 24,
|
| 24 |
+
"no_repeat_ngram_size": 3,
|
| 25 |
+
"offset_alibi": 100,
|
| 26 |
+
"pad_token_id": 3,
|
| 27 |
+
"pretraining_tp": 1,
|
| 28 |
+
"skip_bias_add": true,
|
| 29 |
+
"skip_bias_add_qkv": false,
|
| 30 |
+
"slow_but_exact": false,
|
| 31 |
+
"top_k": 60,
|
| 32 |
+
"top_p": 0.92,
|
| 33 |
+
"torch_dtype": "float32",
|
| 34 |
+
"transformers_version": "4.26.1",
|
| 35 |
+
"unk_token_id": 0,
|
| 36 |
+
"use_cache": true,
|
| 37 |
+
"vocab_size": 250880
|
| 38 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 1,
|
| 4 |
+
"eos_token_id": 2,
|
| 5 |
+
"pad_token_id": 3,
|
| 6 |
+
"transformers_version": "4.26.1"
|
| 7 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:91bfd981abb614805d588fc35c031d7f3aaa15ed9a1cee8a58351d3e80bd723e
|
| 3 |
+
size 2236957537
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:81d6b47129952371ab2fd8446c1e2725d81d6a761188904442cf49d1ae386ab7
|
| 3 |
+
size 14575
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0d85754066ede50281fc6fc51ae29a32b98a31679cb9cde5042e99e296028f46
|
| 3 |
+
size 627
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<s>",
|
| 3 |
+
"eos_token": "</s>",
|
| 4 |
+
"pad_token": "<pad>",
|
| 5 |
+
"unk_token": "<unk>"
|
| 6 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0550bef7146d515c4bb17a0149fc321f69c623bdb5ae5e090c039d505c066a56
|
| 3 |
+
size 14500542
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"bos_token": "<s>",
|
| 4 |
+
"eos_token": "</s>",
|
| 5 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 6 |
+
"name_or_path": "bigscience/bloom-560m",
|
| 7 |
+
"pad_token": "<pad>",
|
| 8 |
+
"padding_side": "left",
|
| 9 |
+
"special_tokens_map_file": null,
|
| 10 |
+
"tokenizer_class": "BloomTokenizer",
|
| 11 |
+
"unk_token": "<unk>"
|
| 12 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,956 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 5.0,
|
| 5 |
+
"global_step": 75115,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.03,
|
| 12 |
+
"learning_rate": 1.9866870798109567e-05,
|
| 13 |
+
"loss": 1.968,
|
| 14 |
+
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.07,
|
| 18 |
+
"learning_rate": 1.9733741596219132e-05,
|
| 19 |
+
"loss": 1.7712,
|
| 20 |
+
"step": 1000
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.1,
|
| 24 |
+
"learning_rate": 1.9600612394328697e-05,
|
| 25 |
+
"loss": 1.7087,
|
| 26 |
+
"step": 1500
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.13,
|
| 30 |
+
"learning_rate": 1.9467483192438262e-05,
|
| 31 |
+
"loss": 1.6706,
|
| 32 |
+
"step": 2000
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.17,
|
| 36 |
+
"learning_rate": 1.9334353990547827e-05,
|
| 37 |
+
"loss": 1.6431,
|
| 38 |
+
"step": 2500
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.2,
|
| 42 |
+
"learning_rate": 1.9201224788657392e-05,
|
| 43 |
+
"loss": 1.6151,
|
| 44 |
+
"step": 3000
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.23,
|
| 48 |
+
"learning_rate": 1.906809558676696e-05,
|
| 49 |
+
"loss": 1.6047,
|
| 50 |
+
"step": 3500
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.27,
|
| 54 |
+
"learning_rate": 1.8934966384876526e-05,
|
| 55 |
+
"loss": 1.5783,
|
| 56 |
+
"step": 4000
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.3,
|
| 60 |
+
"learning_rate": 1.8801837182986088e-05,
|
| 61 |
+
"loss": 1.5813,
|
| 62 |
+
"step": 4500
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.33,
|
| 66 |
+
"learning_rate": 1.8668707981095656e-05,
|
| 67 |
+
"loss": 1.5733,
|
| 68 |
+
"step": 5000
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.37,
|
| 72 |
+
"learning_rate": 1.853557877920522e-05,
|
| 73 |
+
"loss": 1.4983,
|
| 74 |
+
"step": 5500
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.4,
|
| 78 |
+
"learning_rate": 1.8402449577314786e-05,
|
| 79 |
+
"loss": 1.5354,
|
| 80 |
+
"step": 6000
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.43,
|
| 84 |
+
"learning_rate": 1.826932037542435e-05,
|
| 85 |
+
"loss": 1.5037,
|
| 86 |
+
"step": 6500
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.47,
|
| 90 |
+
"learning_rate": 1.8136191173533916e-05,
|
| 91 |
+
"loss": 1.5545,
|
| 92 |
+
"step": 7000
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.5,
|
| 96 |
+
"learning_rate": 1.800306197164348e-05,
|
| 97 |
+
"loss": 1.5555,
|
| 98 |
+
"step": 7500
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.53,
|
| 102 |
+
"learning_rate": 1.7869932769753047e-05,
|
| 103 |
+
"loss": 1.5364,
|
| 104 |
+
"step": 8000
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.57,
|
| 108 |
+
"learning_rate": 1.773680356786261e-05,
|
| 109 |
+
"loss": 1.5221,
|
| 110 |
+
"step": 8500
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 0.6,
|
| 114 |
+
"learning_rate": 1.7603674365972177e-05,
|
| 115 |
+
"loss": 1.4612,
|
| 116 |
+
"step": 9000
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.63,
|
| 120 |
+
"learning_rate": 1.7470545164081742e-05,
|
| 121 |
+
"loss": 1.4768,
|
| 122 |
+
"step": 9500
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.67,
|
| 126 |
+
"learning_rate": 1.7337415962191307e-05,
|
| 127 |
+
"loss": 1.4906,
|
| 128 |
+
"step": 10000
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.7,
|
| 132 |
+
"learning_rate": 1.7204286760300872e-05,
|
| 133 |
+
"loss": 1.4838,
|
| 134 |
+
"step": 10500
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 0.73,
|
| 138 |
+
"learning_rate": 1.7071157558410437e-05,
|
| 139 |
+
"loss": 1.4675,
|
| 140 |
+
"step": 11000
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 0.77,
|
| 144 |
+
"learning_rate": 1.6938028356520006e-05,
|
| 145 |
+
"loss": 1.4579,
|
| 146 |
+
"step": 11500
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 0.8,
|
| 150 |
+
"learning_rate": 1.680489915462957e-05,
|
| 151 |
+
"loss": 1.4626,
|
| 152 |
+
"step": 12000
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 0.83,
|
| 156 |
+
"learning_rate": 1.6671769952739136e-05,
|
| 157 |
+
"loss": 1.455,
|
| 158 |
+
"step": 12500
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 0.87,
|
| 162 |
+
"learning_rate": 1.65386407508487e-05,
|
| 163 |
+
"loss": 1.4327,
|
| 164 |
+
"step": 13000
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.9,
|
| 168 |
+
"learning_rate": 1.6405511548958266e-05,
|
| 169 |
+
"loss": 1.4114,
|
| 170 |
+
"step": 13500
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.93,
|
| 174 |
+
"learning_rate": 1.627238234706783e-05,
|
| 175 |
+
"loss": 1.4188,
|
| 176 |
+
"step": 14000
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 0.97,
|
| 180 |
+
"learning_rate": 1.6139253145177396e-05,
|
| 181 |
+
"loss": 1.4114,
|
| 182 |
+
"step": 14500
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 1.0,
|
| 186 |
+
"learning_rate": 1.600612394328696e-05,
|
| 187 |
+
"loss": 1.4332,
|
| 188 |
+
"step": 15000
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 1.0,
|
| 192 |
+
"eval_loss": 1.412462830543518,
|
| 193 |
+
"eval_runtime": 72.1932,
|
| 194 |
+
"eval_samples_per_second": 23.132,
|
| 195 |
+
"eval_steps_per_second": 23.132,
|
| 196 |
+
"step": 15023
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 1.03,
|
| 200 |
+
"learning_rate": 1.5872994741396526e-05,
|
| 201 |
+
"loss": 1.1332,
|
| 202 |
+
"step": 15500
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 1.07,
|
| 206 |
+
"learning_rate": 1.573986553950609e-05,
|
| 207 |
+
"loss": 1.109,
|
| 208 |
+
"step": 16000
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 1.1,
|
| 212 |
+
"learning_rate": 1.5606736337615657e-05,
|
| 213 |
+
"loss": 1.1059,
|
| 214 |
+
"step": 16500
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"epoch": 1.13,
|
| 218 |
+
"learning_rate": 1.547360713572522e-05,
|
| 219 |
+
"loss": 1.1183,
|
| 220 |
+
"step": 17000
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 1.16,
|
| 224 |
+
"learning_rate": 1.5340477933834787e-05,
|
| 225 |
+
"loss": 1.1313,
|
| 226 |
+
"step": 17500
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 1.2,
|
| 230 |
+
"learning_rate": 1.5207348731944354e-05,
|
| 231 |
+
"loss": 1.1148,
|
| 232 |
+
"step": 18000
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"epoch": 1.23,
|
| 236 |
+
"learning_rate": 1.507421953005392e-05,
|
| 237 |
+
"loss": 1.0957,
|
| 238 |
+
"step": 18500
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"epoch": 1.26,
|
| 242 |
+
"learning_rate": 1.4941090328163484e-05,
|
| 243 |
+
"loss": 1.1238,
|
| 244 |
+
"step": 19000
|
| 245 |
+
},
|
| 246 |
+
{
|
| 247 |
+
"epoch": 1.3,
|
| 248 |
+
"learning_rate": 1.4807961126273049e-05,
|
| 249 |
+
"loss": 1.142,
|
| 250 |
+
"step": 19500
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 1.33,
|
| 254 |
+
"learning_rate": 1.4674831924382616e-05,
|
| 255 |
+
"loss": 1.1324,
|
| 256 |
+
"step": 20000
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 1.36,
|
| 260 |
+
"learning_rate": 1.4541702722492179e-05,
|
| 261 |
+
"loss": 1.1169,
|
| 262 |
+
"step": 20500
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 1.4,
|
| 266 |
+
"learning_rate": 1.4408573520601746e-05,
|
| 267 |
+
"loss": 1.1449,
|
| 268 |
+
"step": 21000
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 1.43,
|
| 272 |
+
"learning_rate": 1.4275444318711311e-05,
|
| 273 |
+
"loss": 1.1185,
|
| 274 |
+
"step": 21500
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 1.46,
|
| 278 |
+
"learning_rate": 1.4142315116820874e-05,
|
| 279 |
+
"loss": 1.1091,
|
| 280 |
+
"step": 22000
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 1.5,
|
| 284 |
+
"learning_rate": 1.4009185914930441e-05,
|
| 285 |
+
"loss": 1.107,
|
| 286 |
+
"step": 22500
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 1.53,
|
| 290 |
+
"learning_rate": 1.3876056713040006e-05,
|
| 291 |
+
"loss": 1.1264,
|
| 292 |
+
"step": 23000
|
| 293 |
+
},
|
| 294 |
+
{
|
| 295 |
+
"epoch": 1.56,
|
| 296 |
+
"learning_rate": 1.3742927511149571e-05,
|
| 297 |
+
"loss": 1.1408,
|
| 298 |
+
"step": 23500
|
| 299 |
+
},
|
| 300 |
+
{
|
| 301 |
+
"epoch": 1.6,
|
| 302 |
+
"learning_rate": 1.3609798309259136e-05,
|
| 303 |
+
"loss": 1.1363,
|
| 304 |
+
"step": 24000
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 1.63,
|
| 308 |
+
"learning_rate": 1.3476669107368703e-05,
|
| 309 |
+
"loss": 1.1575,
|
| 310 |
+
"step": 24500
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 1.66,
|
| 314 |
+
"learning_rate": 1.3343539905478268e-05,
|
| 315 |
+
"loss": 1.1315,
|
| 316 |
+
"step": 25000
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 1.7,
|
| 320 |
+
"learning_rate": 1.3210410703587833e-05,
|
| 321 |
+
"loss": 1.1345,
|
| 322 |
+
"step": 25500
|
| 323 |
+
},
|
| 324 |
+
{
|
| 325 |
+
"epoch": 1.73,
|
| 326 |
+
"learning_rate": 1.3077281501697398e-05,
|
| 327 |
+
"loss": 1.1212,
|
| 328 |
+
"step": 26000
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"epoch": 1.76,
|
| 332 |
+
"learning_rate": 1.2944152299806965e-05,
|
| 333 |
+
"loss": 1.1461,
|
| 334 |
+
"step": 26500
|
| 335 |
+
},
|
| 336 |
+
{
|
| 337 |
+
"epoch": 1.8,
|
| 338 |
+
"learning_rate": 1.2811023097916529e-05,
|
| 339 |
+
"loss": 1.1087,
|
| 340 |
+
"step": 27000
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"epoch": 1.83,
|
| 344 |
+
"learning_rate": 1.2677893896026094e-05,
|
| 345 |
+
"loss": 1.1313,
|
| 346 |
+
"step": 27500
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 1.86,
|
| 350 |
+
"learning_rate": 1.254476469413566e-05,
|
| 351 |
+
"loss": 1.0995,
|
| 352 |
+
"step": 28000
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 1.9,
|
| 356 |
+
"learning_rate": 1.2411635492245224e-05,
|
| 357 |
+
"loss": 1.1351,
|
| 358 |
+
"step": 28500
|
| 359 |
+
},
|
| 360 |
+
{
|
| 361 |
+
"epoch": 1.93,
|
| 362 |
+
"learning_rate": 1.227850629035479e-05,
|
| 363 |
+
"loss": 1.1288,
|
| 364 |
+
"step": 29000
|
| 365 |
+
},
|
| 366 |
+
{
|
| 367 |
+
"epoch": 1.96,
|
| 368 |
+
"learning_rate": 1.2145377088464356e-05,
|
| 369 |
+
"loss": 1.1376,
|
| 370 |
+
"step": 29500
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 2.0,
|
| 374 |
+
"learning_rate": 1.201224788657392e-05,
|
| 375 |
+
"loss": 1.1405,
|
| 376 |
+
"step": 30000
|
| 377 |
+
},
|
| 378 |
+
{
|
| 379 |
+
"epoch": 2.0,
|
| 380 |
+
"eval_loss": 1.3536027669906616,
|
| 381 |
+
"eval_runtime": 72.2307,
|
| 382 |
+
"eval_samples_per_second": 23.12,
|
| 383 |
+
"eval_steps_per_second": 23.12,
|
| 384 |
+
"step": 30046
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 2.03,
|
| 388 |
+
"learning_rate": 1.1879118684683486e-05,
|
| 389 |
+
"loss": 0.8064,
|
| 390 |
+
"step": 30500
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 2.06,
|
| 394 |
+
"learning_rate": 1.1745989482793053e-05,
|
| 395 |
+
"loss": 0.775,
|
| 396 |
+
"step": 31000
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 2.1,
|
| 400 |
+
"learning_rate": 1.1612860280902616e-05,
|
| 401 |
+
"loss": 0.7799,
|
| 402 |
+
"step": 31500
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 2.13,
|
| 406 |
+
"learning_rate": 1.1479731079012181e-05,
|
| 407 |
+
"loss": 0.775,
|
| 408 |
+
"step": 32000
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 2.16,
|
| 412 |
+
"learning_rate": 1.1346601877121748e-05,
|
| 413 |
+
"loss": 0.7728,
|
| 414 |
+
"step": 32500
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 2.2,
|
| 418 |
+
"learning_rate": 1.1213472675231313e-05,
|
| 419 |
+
"loss": 0.777,
|
| 420 |
+
"step": 33000
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 2.23,
|
| 424 |
+
"learning_rate": 1.1080343473340878e-05,
|
| 425 |
+
"loss": 0.7864,
|
| 426 |
+
"step": 33500
|
| 427 |
+
},
|
| 428 |
+
{
|
| 429 |
+
"epoch": 2.26,
|
| 430 |
+
"learning_rate": 1.0947214271450443e-05,
|
| 431 |
+
"loss": 0.7762,
|
| 432 |
+
"step": 34000
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 2.3,
|
| 436 |
+
"learning_rate": 1.081408506956001e-05,
|
| 437 |
+
"loss": 0.7831,
|
| 438 |
+
"step": 34500
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 2.33,
|
| 442 |
+
"learning_rate": 1.0680955867669574e-05,
|
| 443 |
+
"loss": 0.8028,
|
| 444 |
+
"step": 35000
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 2.36,
|
| 448 |
+
"learning_rate": 1.0547826665779139e-05,
|
| 449 |
+
"loss": 0.7768,
|
| 450 |
+
"step": 35500
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 2.4,
|
| 454 |
+
"learning_rate": 1.0414697463888705e-05,
|
| 455 |
+
"loss": 0.7954,
|
| 456 |
+
"step": 36000
|
| 457 |
+
},
|
| 458 |
+
{
|
| 459 |
+
"epoch": 2.43,
|
| 460 |
+
"learning_rate": 1.0281568261998269e-05,
|
| 461 |
+
"loss": 0.784,
|
| 462 |
+
"step": 36500
|
| 463 |
+
},
|
| 464 |
+
{
|
| 465 |
+
"epoch": 2.46,
|
| 466 |
+
"learning_rate": 1.0148439060107836e-05,
|
| 467 |
+
"loss": 0.7873,
|
| 468 |
+
"step": 37000
|
| 469 |
+
},
|
| 470 |
+
{
|
| 471 |
+
"epoch": 2.5,
|
| 472 |
+
"learning_rate": 1.00153098582174e-05,
|
| 473 |
+
"loss": 0.795,
|
| 474 |
+
"step": 37500
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 2.53,
|
| 478 |
+
"learning_rate": 9.882180656326966e-06,
|
| 479 |
+
"loss": 0.7861,
|
| 480 |
+
"step": 38000
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 2.56,
|
| 484 |
+
"learning_rate": 9.749051454436531e-06,
|
| 485 |
+
"loss": 0.7789,
|
| 486 |
+
"step": 38500
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 2.6,
|
| 490 |
+
"learning_rate": 9.615922252546098e-06,
|
| 491 |
+
"loss": 0.7747,
|
| 492 |
+
"step": 39000
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 2.63,
|
| 496 |
+
"learning_rate": 9.482793050655663e-06,
|
| 497 |
+
"loss": 0.7668,
|
| 498 |
+
"step": 39500
|
| 499 |
+
},
|
| 500 |
+
{
|
| 501 |
+
"epoch": 2.66,
|
| 502 |
+
"learning_rate": 9.349663848765226e-06,
|
| 503 |
+
"loss": 0.789,
|
| 504 |
+
"step": 40000
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 2.7,
|
| 508 |
+
"learning_rate": 9.216534646874793e-06,
|
| 509 |
+
"loss": 0.796,
|
| 510 |
+
"step": 40500
|
| 511 |
+
},
|
| 512 |
+
{
|
| 513 |
+
"epoch": 2.73,
|
| 514 |
+
"learning_rate": 9.083405444984358e-06,
|
| 515 |
+
"loss": 0.7821,
|
| 516 |
+
"step": 41000
|
| 517 |
+
},
|
| 518 |
+
{
|
| 519 |
+
"epoch": 2.76,
|
| 520 |
+
"learning_rate": 8.950276243093923e-06,
|
| 521 |
+
"loss": 0.7798,
|
| 522 |
+
"step": 41500
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 2.8,
|
| 526 |
+
"learning_rate": 8.817147041203488e-06,
|
| 527 |
+
"loss": 0.7994,
|
| 528 |
+
"step": 42000
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 2.83,
|
| 532 |
+
"learning_rate": 8.684017839313053e-06,
|
| 533 |
+
"loss": 0.8004,
|
| 534 |
+
"step": 42500
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 2.86,
|
| 538 |
+
"learning_rate": 8.55088863742262e-06,
|
| 539 |
+
"loss": 0.8001,
|
| 540 |
+
"step": 43000
|
| 541 |
+
},
|
| 542 |
+
{
|
| 543 |
+
"epoch": 2.9,
|
| 544 |
+
"learning_rate": 8.417759435532185e-06,
|
| 545 |
+
"loss": 0.8043,
|
| 546 |
+
"step": 43500
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 2.93,
|
| 550 |
+
"learning_rate": 8.284630233641749e-06,
|
| 551 |
+
"loss": 0.8109,
|
| 552 |
+
"step": 44000
|
| 553 |
+
},
|
| 554 |
+
{
|
| 555 |
+
"epoch": 2.96,
|
| 556 |
+
"learning_rate": 8.151501031751316e-06,
|
| 557 |
+
"loss": 0.7883,
|
| 558 |
+
"step": 44500
|
| 559 |
+
},
|
| 560 |
+
{
|
| 561 |
+
"epoch": 3.0,
|
| 562 |
+
"learning_rate": 8.01837182986088e-06,
|
| 563 |
+
"loss": 0.7896,
|
| 564 |
+
"step": 45000
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 3.0,
|
| 568 |
+
"eval_loss": 1.4429526329040527,
|
| 569 |
+
"eval_runtime": 72.2054,
|
| 570 |
+
"eval_samples_per_second": 23.128,
|
| 571 |
+
"eval_steps_per_second": 23.128,
|
| 572 |
+
"step": 45069
|
| 573 |
+
},
|
| 574 |
+
{
|
| 575 |
+
"epoch": 3.03,
|
| 576 |
+
"learning_rate": 7.885242627970446e-06,
|
| 577 |
+
"loss": 0.5414,
|
| 578 |
+
"step": 45500
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 3.06,
|
| 582 |
+
"learning_rate": 7.75211342608001e-06,
|
| 583 |
+
"loss": 0.5111,
|
| 584 |
+
"step": 46000
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 3.1,
|
| 588 |
+
"learning_rate": 7.618984224189576e-06,
|
| 589 |
+
"loss": 0.5074,
|
| 590 |
+
"step": 46500
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 3.13,
|
| 594 |
+
"learning_rate": 7.485855022299142e-06,
|
| 595 |
+
"loss": 0.4974,
|
| 596 |
+
"step": 47000
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 3.16,
|
| 600 |
+
"learning_rate": 7.352725820408707e-06,
|
| 601 |
+
"loss": 0.5118,
|
| 602 |
+
"step": 47500
|
| 603 |
+
},
|
| 604 |
+
{
|
| 605 |
+
"epoch": 3.2,
|
| 606 |
+
"learning_rate": 7.219596618518273e-06,
|
| 607 |
+
"loss": 0.5211,
|
| 608 |
+
"step": 48000
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 3.23,
|
| 612 |
+
"learning_rate": 7.086467416627838e-06,
|
| 613 |
+
"loss": 0.5031,
|
| 614 |
+
"step": 48500
|
| 615 |
+
},
|
| 616 |
+
{
|
| 617 |
+
"epoch": 3.26,
|
| 618 |
+
"learning_rate": 6.953338214737403e-06,
|
| 619 |
+
"loss": 0.5106,
|
| 620 |
+
"step": 49000
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 3.29,
|
| 624 |
+
"learning_rate": 6.820209012846969e-06,
|
| 625 |
+
"loss": 0.5179,
|
| 626 |
+
"step": 49500
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 3.33,
|
| 630 |
+
"learning_rate": 6.687079810956534e-06,
|
| 631 |
+
"loss": 0.5159,
|
| 632 |
+
"step": 50000
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 3.36,
|
| 636 |
+
"learning_rate": 6.553950609066098e-06,
|
| 637 |
+
"loss": 0.5186,
|
| 638 |
+
"step": 50500
|
| 639 |
+
},
|
| 640 |
+
{
|
| 641 |
+
"epoch": 3.39,
|
| 642 |
+
"learning_rate": 6.420821407175664e-06,
|
| 643 |
+
"loss": 0.507,
|
| 644 |
+
"step": 51000
|
| 645 |
+
},
|
| 646 |
+
{
|
| 647 |
+
"epoch": 3.43,
|
| 648 |
+
"learning_rate": 6.287692205285229e-06,
|
| 649 |
+
"loss": 0.5058,
|
| 650 |
+
"step": 51500
|
| 651 |
+
},
|
| 652 |
+
{
|
| 653 |
+
"epoch": 3.46,
|
| 654 |
+
"learning_rate": 6.154563003394795e-06,
|
| 655 |
+
"loss": 0.5236,
|
| 656 |
+
"step": 52000
|
| 657 |
+
},
|
| 658 |
+
{
|
| 659 |
+
"epoch": 3.49,
|
| 660 |
+
"learning_rate": 6.0214338015043604e-06,
|
| 661 |
+
"loss": 0.5067,
|
| 662 |
+
"step": 52500
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 3.53,
|
| 666 |
+
"learning_rate": 5.8883045996139255e-06,
|
| 667 |
+
"loss": 0.5169,
|
| 668 |
+
"step": 53000
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 3.56,
|
| 672 |
+
"learning_rate": 5.7551753977234915e-06,
|
| 673 |
+
"loss": 0.5207,
|
| 674 |
+
"step": 53500
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 3.59,
|
| 678 |
+
"learning_rate": 5.6220461958330566e-06,
|
| 679 |
+
"loss": 0.4919,
|
| 680 |
+
"step": 54000
|
| 681 |
+
},
|
| 682 |
+
{
|
| 683 |
+
"epoch": 3.63,
|
| 684 |
+
"learning_rate": 5.488916993942621e-06,
|
| 685 |
+
"loss": 0.5258,
|
| 686 |
+
"step": 54500
|
| 687 |
+
},
|
| 688 |
+
{
|
| 689 |
+
"epoch": 3.66,
|
| 690 |
+
"learning_rate": 5.355787792052188e-06,
|
| 691 |
+
"loss": 0.5061,
|
| 692 |
+
"step": 55000
|
| 693 |
+
},
|
| 694 |
+
{
|
| 695 |
+
"epoch": 3.69,
|
| 696 |
+
"learning_rate": 5.222658590161752e-06,
|
| 697 |
+
"loss": 0.4913,
|
| 698 |
+
"step": 55500
|
| 699 |
+
},
|
| 700 |
+
{
|
| 701 |
+
"epoch": 3.73,
|
| 702 |
+
"learning_rate": 5.089529388271318e-06,
|
| 703 |
+
"loss": 0.4932,
|
| 704 |
+
"step": 56000
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 3.76,
|
| 708 |
+
"learning_rate": 4.956400186380883e-06,
|
| 709 |
+
"loss": 0.4958,
|
| 710 |
+
"step": 56500
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 3.79,
|
| 714 |
+
"learning_rate": 4.823270984490449e-06,
|
| 715 |
+
"loss": 0.5071,
|
| 716 |
+
"step": 57000
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 3.83,
|
| 720 |
+
"learning_rate": 4.690141782600014e-06,
|
| 721 |
+
"loss": 0.505,
|
| 722 |
+
"step": 57500
|
| 723 |
+
},
|
| 724 |
+
{
|
| 725 |
+
"epoch": 3.86,
|
| 726 |
+
"learning_rate": 4.557012580709579e-06,
|
| 727 |
+
"loss": 0.5174,
|
| 728 |
+
"step": 58000
|
| 729 |
+
},
|
| 730 |
+
{
|
| 731 |
+
"epoch": 3.89,
|
| 732 |
+
"learning_rate": 4.423883378819144e-06,
|
| 733 |
+
"loss": 0.5126,
|
| 734 |
+
"step": 58500
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 3.93,
|
| 738 |
+
"learning_rate": 4.29075417692871e-06,
|
| 739 |
+
"loss": 0.4965,
|
| 740 |
+
"step": 59000
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 3.96,
|
| 744 |
+
"learning_rate": 4.157624975038275e-06,
|
| 745 |
+
"loss": 0.4889,
|
| 746 |
+
"step": 59500
|
| 747 |
+
},
|
| 748 |
+
{
|
| 749 |
+
"epoch": 3.99,
|
| 750 |
+
"learning_rate": 4.02449577314784e-06,
|
| 751 |
+
"loss": 0.5011,
|
| 752 |
+
"step": 60000
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 4.0,
|
| 756 |
+
"eval_loss": 1.6782159805297852,
|
| 757 |
+
"eval_runtime": 72.2227,
|
| 758 |
+
"eval_samples_per_second": 23.123,
|
| 759 |
+
"eval_steps_per_second": 23.123,
|
| 760 |
+
"step": 60092
|
| 761 |
+
},
|
| 762 |
+
{
|
| 763 |
+
"epoch": 4.03,
|
| 764 |
+
"learning_rate": 3.891366571257405e-06,
|
| 765 |
+
"loss": 0.3499,
|
| 766 |
+
"step": 60500
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 4.06,
|
| 770 |
+
"learning_rate": 3.758237369366971e-06,
|
| 771 |
+
"loss": 0.3204,
|
| 772 |
+
"step": 61000
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 4.09,
|
| 776 |
+
"learning_rate": 3.6251081674765364e-06,
|
| 777 |
+
"loss": 0.313,
|
| 778 |
+
"step": 61500
|
| 779 |
+
},
|
| 780 |
+
{
|
| 781 |
+
"epoch": 4.13,
|
| 782 |
+
"learning_rate": 3.4919789655861015e-06,
|
| 783 |
+
"loss": 0.3279,
|
| 784 |
+
"step": 62000
|
| 785 |
+
},
|
| 786 |
+
{
|
| 787 |
+
"epoch": 4.16,
|
| 788 |
+
"learning_rate": 3.358849763695667e-06,
|
| 789 |
+
"loss": 0.3198,
|
| 790 |
+
"step": 62500
|
| 791 |
+
},
|
| 792 |
+
{
|
| 793 |
+
"epoch": 4.19,
|
| 794 |
+
"learning_rate": 3.225720561805232e-06,
|
| 795 |
+
"loss": 0.3223,
|
| 796 |
+
"step": 63000
|
| 797 |
+
},
|
| 798 |
+
{
|
| 799 |
+
"epoch": 4.23,
|
| 800 |
+
"learning_rate": 3.0925913599147976e-06,
|
| 801 |
+
"loss": 0.3115,
|
| 802 |
+
"step": 63500
|
| 803 |
+
},
|
| 804 |
+
{
|
| 805 |
+
"epoch": 4.26,
|
| 806 |
+
"learning_rate": 2.9594621580243627e-06,
|
| 807 |
+
"loss": 0.3261,
|
| 808 |
+
"step": 64000
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 4.29,
|
| 812 |
+
"learning_rate": 2.8263329561339283e-06,
|
| 813 |
+
"loss": 0.3108,
|
| 814 |
+
"step": 64500
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 4.33,
|
| 818 |
+
"learning_rate": 2.6932037542434938e-06,
|
| 819 |
+
"loss": 0.3062,
|
| 820 |
+
"step": 65000
|
| 821 |
+
},
|
| 822 |
+
{
|
| 823 |
+
"epoch": 4.36,
|
| 824 |
+
"learning_rate": 2.560074552353059e-06,
|
| 825 |
+
"loss": 0.3057,
|
| 826 |
+
"step": 65500
|
| 827 |
+
},
|
| 828 |
+
{
|
| 829 |
+
"epoch": 4.39,
|
| 830 |
+
"learning_rate": 2.4269453504626244e-06,
|
| 831 |
+
"loss": 0.3065,
|
| 832 |
+
"step": 66000
|
| 833 |
+
},
|
| 834 |
+
{
|
| 835 |
+
"epoch": 4.43,
|
| 836 |
+
"learning_rate": 2.2938161485721895e-06,
|
| 837 |
+
"loss": 0.3097,
|
| 838 |
+
"step": 66500
|
| 839 |
+
},
|
| 840 |
+
{
|
| 841 |
+
"epoch": 4.46,
|
| 842 |
+
"learning_rate": 2.160686946681755e-06,
|
| 843 |
+
"loss": 0.3092,
|
| 844 |
+
"step": 67000
|
| 845 |
+
},
|
| 846 |
+
{
|
| 847 |
+
"epoch": 4.49,
|
| 848 |
+
"learning_rate": 2.02755774479132e-06,
|
| 849 |
+
"loss": 0.3106,
|
| 850 |
+
"step": 67500
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 4.53,
|
| 854 |
+
"learning_rate": 1.8944285429008854e-06,
|
| 855 |
+
"loss": 0.3164,
|
| 856 |
+
"step": 68000
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 4.56,
|
| 860 |
+
"learning_rate": 1.761299341010451e-06,
|
| 861 |
+
"loss": 0.3091,
|
| 862 |
+
"step": 68500
|
| 863 |
+
},
|
| 864 |
+
{
|
| 865 |
+
"epoch": 4.59,
|
| 866 |
+
"learning_rate": 1.628170139120016e-06,
|
| 867 |
+
"loss": 0.312,
|
| 868 |
+
"step": 69000
|
| 869 |
+
},
|
| 870 |
+
{
|
| 871 |
+
"epoch": 4.63,
|
| 872 |
+
"learning_rate": 1.4950409372295815e-06,
|
| 873 |
+
"loss": 0.3055,
|
| 874 |
+
"step": 69500
|
| 875 |
+
},
|
| 876 |
+
{
|
| 877 |
+
"epoch": 4.66,
|
| 878 |
+
"learning_rate": 1.3619117353391466e-06,
|
| 879 |
+
"loss": 0.3138,
|
| 880 |
+
"step": 70000
|
| 881 |
+
},
|
| 882 |
+
{
|
| 883 |
+
"epoch": 4.69,
|
| 884 |
+
"learning_rate": 1.228782533448712e-06,
|
| 885 |
+
"loss": 0.3078,
|
| 886 |
+
"step": 70500
|
| 887 |
+
},
|
| 888 |
+
{
|
| 889 |
+
"epoch": 4.73,
|
| 890 |
+
"learning_rate": 1.0956533315582773e-06,
|
| 891 |
+
"loss": 0.3088,
|
| 892 |
+
"step": 71000
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 4.76,
|
| 896 |
+
"learning_rate": 9.625241296678428e-07,
|
| 897 |
+
"loss": 0.3036,
|
| 898 |
+
"step": 71500
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 4.79,
|
| 902 |
+
"learning_rate": 8.29394927777408e-07,
|
| 903 |
+
"loss": 0.3113,
|
| 904 |
+
"step": 72000
|
| 905 |
+
},
|
| 906 |
+
{
|
| 907 |
+
"epoch": 4.83,
|
| 908 |
+
"learning_rate": 6.962657258869733e-07,
|
| 909 |
+
"loss": 0.3,
|
| 910 |
+
"step": 72500
|
| 911 |
+
},
|
| 912 |
+
{
|
| 913 |
+
"epoch": 4.86,
|
| 914 |
+
"learning_rate": 5.631365239965387e-07,
|
| 915 |
+
"loss": 0.3071,
|
| 916 |
+
"step": 73000
|
| 917 |
+
},
|
| 918 |
+
{
|
| 919 |
+
"epoch": 4.89,
|
| 920 |
+
"learning_rate": 4.30007322106104e-07,
|
| 921 |
+
"loss": 0.3062,
|
| 922 |
+
"step": 73500
|
| 923 |
+
},
|
| 924 |
+
{
|
| 925 |
+
"epoch": 4.93,
|
| 926 |
+
"learning_rate": 2.968781202156693e-07,
|
| 927 |
+
"loss": 0.3108,
|
| 928 |
+
"step": 74000
|
| 929 |
+
},
|
| 930 |
+
{
|
| 931 |
+
"epoch": 4.96,
|
| 932 |
+
"learning_rate": 1.6374891832523464e-07,
|
| 933 |
+
"loss": 0.307,
|
| 934 |
+
"step": 74500
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 4.99,
|
| 938 |
+
"learning_rate": 3.061971643479997e-08,
|
| 939 |
+
"loss": 0.3092,
|
| 940 |
+
"step": 75000
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 5.0,
|
| 944 |
+
"eval_loss": 1.9851311445236206,
|
| 945 |
+
"eval_runtime": 72.2556,
|
| 946 |
+
"eval_samples_per_second": 23.112,
|
| 947 |
+
"eval_steps_per_second": 23.112,
|
| 948 |
+
"step": 75115
|
| 949 |
+
}
|
| 950 |
+
],
|
| 951 |
+
"max_steps": 75115,
|
| 952 |
+
"num_train_epochs": 5,
|
| 953 |
+
"total_flos": 5.581632376971264e+16,
|
| 954 |
+
"trial_name": null,
|
| 955 |
+
"trial_params": null
|
| 956 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:34182a231123b7e28eb808532432467dde60fdae5ca7d25a17cf1ebbb7c7a252
|
| 3 |
+
size 3451
|