Upload folder using huggingface_hub
Browse files- config.json +52 -0
- optimizer_scheduler.bin +3 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +24 -0
- tokenizer.model +3 -0
- tokenizer_config.json +44 -0
- trainer_state.bin +3 -0
- trainer_state.json +1800 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,52 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "microsoft/llava-med-v1.5-mistral-7b",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"LlavaMistralForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_bias": false,
|
| 7 |
+
"attention_dropout": 0.0,
|
| 8 |
+
"bos_token_id": 1,
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
+
"feature_outs": "encoder+decoder",
|
| 11 |
+
"freeze_mm_mlp_adapter": false,
|
| 12 |
+
"hidden_act": "silu",
|
| 13 |
+
"hidden_size": 4096,
|
| 14 |
+
"image_aspect_ratio": "square",
|
| 15 |
+
"img_size": 640,
|
| 16 |
+
"initializer_range": 0.02,
|
| 17 |
+
"intermediate_size": 14336,
|
| 18 |
+
"max_position_embeddings": 32768,
|
| 19 |
+
"mm_hidden_size": 1024,
|
| 20 |
+
"mm_patch_merge_type": "flat",
|
| 21 |
+
"mm_projector_lr": null,
|
| 22 |
+
"mm_projector_type": "mlp2x_gelu",
|
| 23 |
+
"mm_use_im_patch_token": false,
|
| 24 |
+
"mm_use_im_start_end": false,
|
| 25 |
+
"mm_vision_select_feature": "patch",
|
| 26 |
+
"mm_vision_select_layer": -2,
|
| 27 |
+
"mm_vision_tower": "openai/clip-vit-large-patch14-336",
|
| 28 |
+
"model_type": "llava_llama",
|
| 29 |
+
"num_attention_heads": 32,
|
| 30 |
+
"num_hidden_layers": 32,
|
| 31 |
+
"num_key_value_heads": 8,
|
| 32 |
+
"pretraining_tp": 1,
|
| 33 |
+
"proj_vis_to_txt_tokens": false,
|
| 34 |
+
"prompt_segtok_w_instruct": false,
|
| 35 |
+
"rms_norm_eps": 1e-05,
|
| 36 |
+
"rope_scaling": null,
|
| 37 |
+
"rope_theta": 1000000.0,
|
| 38 |
+
"segtok_posembed": "sincos",
|
| 39 |
+
"sliding_window": null,
|
| 40 |
+
"tie_word_embeddings": false,
|
| 41 |
+
"tokenizer_model_max_length": 2048,
|
| 42 |
+
"tokenizer_padding_side": "right",
|
| 43 |
+
"torch_dtype": "bfloat16",
|
| 44 |
+
"transformers_version": "4.37.2",
|
| 45 |
+
"tune_mm_mlp_adapter": true,
|
| 46 |
+
"tune_vision_tokenizer": "none",
|
| 47 |
+
"use_cache": true,
|
| 48 |
+
"use_mm_proj": true,
|
| 49 |
+
"vision_backbone": "convnextlarge",
|
| 50 |
+
"vision_tokenizer_lr": null,
|
| 51 |
+
"vocab_size": 32000
|
| 52 |
+
}
|
optimizer_scheduler.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d8c57e303635196d9c32fa0ea0409504341fe67ca3115d51bb85722823ec86c7
|
| 3 |
+
size 125882704
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:20c3ccd129498ca9ce9ae282dfc54d812820cecaf9029471b36d64362ec09225
|
| 3 |
+
size 15132745698
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "</s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": "<unk>",
|
| 17 |
+
"unk_token": {
|
| 18 |
+
"content": "<unk>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
}
|
| 24 |
+
}
|
tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
|
| 3 |
+
size 493443
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"0": {
|
| 6 |
+
"content": "<unk>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"1": {
|
| 14 |
+
"content": "<s>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"2": {
|
| 22 |
+
"content": "</s>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
}
|
| 29 |
+
},
|
| 30 |
+
"additional_special_tokens": [],
|
| 31 |
+
"bos_token": "<s>",
|
| 32 |
+
"chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token}}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
|
| 33 |
+
"clean_up_tokenization_spaces": false,
|
| 34 |
+
"eos_token": "</s>",
|
| 35 |
+
"legacy": true,
|
| 36 |
+
"model_max_length": 2048,
|
| 37 |
+
"pad_token": "<unk>",
|
| 38 |
+
"padding_side": "right",
|
| 39 |
+
"sp_model_kwargs": {},
|
| 40 |
+
"spaces_between_special_tokens": false,
|
| 41 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 42 |
+
"unk_token": "<unk>",
|
| 43 |
+
"use_default_system_prompt": false
|
| 44 |
+
}
|
trainer_state.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1a5f3ba7e6cf5eb82637918b92d392c98b35d6858bbdf573a8f8a668ef3bffb8
|
| 3 |
+
size 15132745762
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1800 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 5.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 295,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.02,
|
| 13 |
+
"learning_rate": 0.0001111111111111111,
|
| 14 |
+
"loss": 2.2793,
|
| 15 |
+
"step": 1
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.03,
|
| 19 |
+
"learning_rate": 0.0002222222222222222,
|
| 20 |
+
"loss": 2.2853,
|
| 21 |
+
"step": 2
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.05,
|
| 25 |
+
"learning_rate": 0.0003333333333333333,
|
| 26 |
+
"loss": 1.9982,
|
| 27 |
+
"step": 3
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.07,
|
| 31 |
+
"learning_rate": 0.0004444444444444444,
|
| 32 |
+
"loss": 1.7452,
|
| 33 |
+
"step": 4
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.08,
|
| 37 |
+
"learning_rate": 0.0005555555555555556,
|
| 38 |
+
"loss": 1.4194,
|
| 39 |
+
"step": 5
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.1,
|
| 43 |
+
"learning_rate": 0.0006666666666666666,
|
| 44 |
+
"loss": 1.3396,
|
| 45 |
+
"step": 6
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.12,
|
| 49 |
+
"learning_rate": 0.0007777777777777778,
|
| 50 |
+
"loss": 1.3332,
|
| 51 |
+
"step": 7
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.14,
|
| 55 |
+
"learning_rate": 0.0008888888888888888,
|
| 56 |
+
"loss": 1.2855,
|
| 57 |
+
"step": 8
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.15,
|
| 61 |
+
"learning_rate": 0.001,
|
| 62 |
+
"loss": 1.2143,
|
| 63 |
+
"step": 9
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.17,
|
| 67 |
+
"learning_rate": 0.0009999698350006063,
|
| 68 |
+
"loss": 1.087,
|
| 69 |
+
"step": 10
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.19,
|
| 73 |
+
"learning_rate": 0.000999879343642134,
|
| 74 |
+
"loss": 1.0377,
|
| 75 |
+
"step": 11
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.2,
|
| 79 |
+
"learning_rate": 0.0009997285368432702,
|
| 80 |
+
"loss": 1.2128,
|
| 81 |
+
"step": 12
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.22,
|
| 85 |
+
"learning_rate": 0.000999517432800363,
|
| 86 |
+
"loss": 1.0801,
|
| 87 |
+
"step": 13
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.24,
|
| 91 |
+
"learning_rate": 0.0009992460569852254,
|
| 92 |
+
"loss": 0.848,
|
| 93 |
+
"step": 14
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.25,
|
| 97 |
+
"learning_rate": 0.000998914442142063,
|
| 98 |
+
"loss": 0.8885,
|
| 99 |
+
"step": 15
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.27,
|
| 103 |
+
"learning_rate": 0.0009985226282835215,
|
| 104 |
+
"loss": 0.8587,
|
| 105 |
+
"step": 16
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.29,
|
| 109 |
+
"learning_rate": 0.0009980706626858606,
|
| 110 |
+
"loss": 0.8086,
|
| 111 |
+
"step": 17
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 0.31,
|
| 115 |
+
"learning_rate": 0.0009975585998832478,
|
| 116 |
+
"loss": 0.8043,
|
| 117 |
+
"step": 18
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 0.32,
|
| 121 |
+
"learning_rate": 0.00099698650166118,
|
| 122 |
+
"loss": 0.7563,
|
| 123 |
+
"step": 19
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.34,
|
| 127 |
+
"learning_rate": 0.000996354437049027,
|
| 128 |
+
"loss": 0.723,
|
| 129 |
+
"step": 20
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.36,
|
| 133 |
+
"learning_rate": 0.0009956624823117036,
|
| 134 |
+
"loss": 0.7343,
|
| 135 |
+
"step": 21
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.37,
|
| 139 |
+
"learning_rate": 0.0009949107209404665,
|
| 140 |
+
"loss": 0.693,
|
| 141 |
+
"step": 22
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 0.39,
|
| 145 |
+
"learning_rate": 0.000994099243642841,
|
| 146 |
+
"loss": 0.6227,
|
| 147 |
+
"step": 23
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 0.41,
|
| 151 |
+
"learning_rate": 0.0009932281483316758,
|
| 152 |
+
"loss": 0.6093,
|
| 153 |
+
"step": 24
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 0.42,
|
| 157 |
+
"learning_rate": 0.0009922975401133291,
|
| 158 |
+
"loss": 0.6365,
|
| 159 |
+
"step": 25
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.44,
|
| 163 |
+
"learning_rate": 0.0009913075312749865,
|
| 164 |
+
"loss": 0.5727,
|
| 165 |
+
"step": 26
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 0.46,
|
| 169 |
+
"learning_rate": 0.000990258241271112,
|
| 170 |
+
"loss": 0.3922,
|
| 171 |
+
"step": 27
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.47,
|
| 175 |
+
"learning_rate": 0.0009891497967090344,
|
| 176 |
+
"loss": 0.5033,
|
| 177 |
+
"step": 28
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.49,
|
| 181 |
+
"learning_rate": 0.0009879823313336722,
|
| 182 |
+
"loss": 0.5103,
|
| 183 |
+
"step": 29
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 0.51,
|
| 187 |
+
"learning_rate": 0.000986755986011395,
|
| 188 |
+
"loss": 0.4317,
|
| 189 |
+
"step": 30
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 0.53,
|
| 193 |
+
"learning_rate": 0.000985470908713026,
|
| 194 |
+
"loss": 0.4054,
|
| 195 |
+
"step": 31
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 0.54,
|
| 199 |
+
"learning_rate": 0.0009841272544959892,
|
| 200 |
+
"loss": 0.361,
|
| 201 |
+
"step": 32
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 0.56,
|
| 205 |
+
"learning_rate": 0.0009827251854855992,
|
| 206 |
+
"loss": 0.4515,
|
| 207 |
+
"step": 33
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 0.58,
|
| 211 |
+
"learning_rate": 0.000981264870855499,
|
| 212 |
+
"loss": 0.3893,
|
| 213 |
+
"step": 34
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.59,
|
| 217 |
+
"learning_rate": 0.0009797464868072487,
|
| 218 |
+
"loss": 0.332,
|
| 219 |
+
"step": 35
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.61,
|
| 223 |
+
"learning_rate": 0.0009781702165490638,
|
| 224 |
+
"loss": 0.3706,
|
| 225 |
+
"step": 36
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 0.63,
|
| 229 |
+
"learning_rate": 0.0009765362502737097,
|
| 230 |
+
"loss": 0.3606,
|
| 231 |
+
"step": 37
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 0.64,
|
| 235 |
+
"learning_rate": 0.0009748447851355535,
|
| 236 |
+
"loss": 0.3067,
|
| 237 |
+
"step": 38
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 0.66,
|
| 241 |
+
"learning_rate": 0.0009730960252267743,
|
| 242 |
+
"loss": 0.2683,
|
| 243 |
+
"step": 39
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 0.68,
|
| 247 |
+
"learning_rate": 0.0009712901815527386,
|
| 248 |
+
"loss": 0.3499,
|
| 249 |
+
"step": 40
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 0.69,
|
| 253 |
+
"learning_rate": 0.0009694274720065399,
|
| 254 |
+
"loss": 0.3047,
|
| 255 |
+
"step": 41
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.71,
|
| 259 |
+
"learning_rate": 0.0009675081213427075,
|
| 260 |
+
"loss": 0.334,
|
| 261 |
+
"step": 42
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.73,
|
| 265 |
+
"learning_rate": 0.0009655323611500874,
|
| 266 |
+
"loss": 0.252,
|
| 267 |
+
"step": 43
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 0.75,
|
| 271 |
+
"learning_rate": 0.0009635004298239003,
|
| 272 |
+
"loss": 0.2929,
|
| 273 |
+
"step": 44
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 0.76,
|
| 277 |
+
"learning_rate": 0.0009614125725369747,
|
| 278 |
+
"loss": 0.2636,
|
| 279 |
+
"step": 45
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 0.78,
|
| 283 |
+
"learning_rate": 0.0009592690412101658,
|
| 284 |
+
"loss": 0.2265,
|
| 285 |
+
"step": 46
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 0.8,
|
| 289 |
+
"learning_rate": 0.0009570700944819584,
|
| 290 |
+
"loss": 0.2842,
|
| 291 |
+
"step": 47
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 0.81,
|
| 295 |
+
"learning_rate": 0.0009548159976772592,
|
| 296 |
+
"loss": 0.3006,
|
| 297 |
+
"step": 48
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.83,
|
| 301 |
+
"learning_rate": 0.0009525070227753834,
|
| 302 |
+
"loss": 0.2884,
|
| 303 |
+
"step": 49
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.85,
|
| 307 |
+
"learning_rate": 0.0009501434483772371,
|
| 308 |
+
"loss": 0.2627,
|
| 309 |
+
"step": 50
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 0.86,
|
| 313 |
+
"learning_rate": 0.0009477255596717012,
|
| 314 |
+
"loss": 0.2446,
|
| 315 |
+
"step": 51
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 0.88,
|
| 319 |
+
"learning_rate": 0.0009452536484012212,
|
| 320 |
+
"loss": 0.1926,
|
| 321 |
+
"step": 52
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 0.9,
|
| 325 |
+
"learning_rate": 0.0009427280128266049,
|
| 326 |
+
"loss": 0.2356,
|
| 327 |
+
"step": 53
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 0.92,
|
| 331 |
+
"learning_rate": 0.0009401489576910349,
|
| 332 |
+
"loss": 0.2356,
|
| 333 |
+
"step": 54
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 0.93,
|
| 337 |
+
"learning_rate": 0.0009375167941832973,
|
| 338 |
+
"loss": 0.2395,
|
| 339 |
+
"step": 55
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.95,
|
| 343 |
+
"learning_rate": 0.0009348318399002345,
|
| 344 |
+
"loss": 0.2681,
|
| 345 |
+
"step": 56
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.97,
|
| 349 |
+
"learning_rate": 0.0009320944188084242,
|
| 350 |
+
"loss": 0.2252,
|
| 351 |
+
"step": 57
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 0.98,
|
| 355 |
+
"learning_rate": 0.0009293048612050883,
|
| 356 |
+
"loss": 0.1862,
|
| 357 |
+
"step": 58
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 1.0,
|
| 361 |
+
"learning_rate": 0.0009264635036782405,
|
| 362 |
+
"loss": 0.2215,
|
| 363 |
+
"step": 59
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 1.02,
|
| 367 |
+
"learning_rate": 0.0009235706890660734,
|
| 368 |
+
"loss": 0.1712,
|
| 369 |
+
"step": 60
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 1.03,
|
| 373 |
+
"learning_rate": 0.0009206267664155906,
|
| 374 |
+
"loss": 0.2162,
|
| 375 |
+
"step": 61
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 1.05,
|
| 379 |
+
"learning_rate": 0.0009176320909404924,
|
| 380 |
+
"loss": 0.1684,
|
| 381 |
+
"step": 62
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 1.07,
|
| 385 |
+
"learning_rate": 0.0009145870239783141,
|
| 386 |
+
"loss": 0.1432,
|
| 387 |
+
"step": 63
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 1.08,
|
| 391 |
+
"learning_rate": 0.0009114919329468282,
|
| 392 |
+
"loss": 0.1798,
|
| 393 |
+
"step": 64
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 1.1,
|
| 397 |
+
"learning_rate": 0.0009083471912997109,
|
| 398 |
+
"loss": 0.1961,
|
| 399 |
+
"step": 65
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 1.12,
|
| 403 |
+
"learning_rate": 0.0009051531784814817,
|
| 404 |
+
"loss": 0.2043,
|
| 405 |
+
"step": 66
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 1.14,
|
| 409 |
+
"learning_rate": 0.0009019102798817196,
|
| 410 |
+
"loss": 0.1493,
|
| 411 |
+
"step": 67
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 1.15,
|
| 415 |
+
"learning_rate": 0.0008986188867885616,
|
| 416 |
+
"loss": 0.1943,
|
| 417 |
+
"step": 68
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 1.17,
|
| 421 |
+
"learning_rate": 0.0008952793963414907,
|
| 422 |
+
"loss": 0.1955,
|
| 423 |
+
"step": 69
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 1.19,
|
| 427 |
+
"learning_rate": 0.0008918922114834156,
|
| 428 |
+
"loss": 0.194,
|
| 429 |
+
"step": 70
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 1.2,
|
| 433 |
+
"learning_rate": 0.0008884577409120535,
|
| 434 |
+
"loss": 0.1765,
|
| 435 |
+
"step": 71
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 1.22,
|
| 439 |
+
"learning_rate": 0.0008849763990306152,
|
| 440 |
+
"loss": 0.1608,
|
| 441 |
+
"step": 72
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 1.24,
|
| 445 |
+
"learning_rate": 0.0008814486058978035,
|
| 446 |
+
"loss": 0.1596,
|
| 447 |
+
"step": 73
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 1.25,
|
| 451 |
+
"learning_rate": 0.0008778747871771292,
|
| 452 |
+
"loss": 0.1756,
|
| 453 |
+
"step": 74
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 1.27,
|
| 457 |
+
"learning_rate": 0.0008742553740855505,
|
| 458 |
+
"loss": 0.1507,
|
| 459 |
+
"step": 75
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 1.29,
|
| 463 |
+
"learning_rate": 0.0008705908033414425,
|
| 464 |
+
"loss": 0.1243,
|
| 465 |
+
"step": 76
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 1.31,
|
| 469 |
+
"learning_rate": 0.000866881517111902,
|
| 470 |
+
"loss": 0.1431,
|
| 471 |
+
"step": 77
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 1.32,
|
| 475 |
+
"learning_rate": 0.0008631279629593967,
|
| 476 |
+
"loss": 0.1358,
|
| 477 |
+
"step": 78
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 1.34,
|
| 481 |
+
"learning_rate": 0.0008593305937877613,
|
| 482 |
+
"loss": 0.1452,
|
| 483 |
+
"step": 79
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 1.36,
|
| 487 |
+
"learning_rate": 0.0008554898677875509,
|
| 488 |
+
"loss": 0.1239,
|
| 489 |
+
"step": 80
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 1.37,
|
| 493 |
+
"learning_rate": 0.0008516062483807555,
|
| 494 |
+
"loss": 0.1566,
|
| 495 |
+
"step": 81
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 1.39,
|
| 499 |
+
"learning_rate": 0.0008476802041648832,
|
| 500 |
+
"loss": 0.1353,
|
| 501 |
+
"step": 82
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 1.41,
|
| 505 |
+
"learning_rate": 0.0008437122088564197,
|
| 506 |
+
"loss": 0.1023,
|
| 507 |
+
"step": 83
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 1.42,
|
| 511 |
+
"learning_rate": 0.0008397027412336691,
|
| 512 |
+
"loss": 0.1386,
|
| 513 |
+
"step": 84
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 1.44,
|
| 517 |
+
"learning_rate": 0.0008356522850789851,
|
| 518 |
+
"loss": 0.1315,
|
| 519 |
+
"step": 85
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 1.46,
|
| 523 |
+
"learning_rate": 0.0008315613291203976,
|
| 524 |
+
"loss": 0.1285,
|
| 525 |
+
"step": 86
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 1.47,
|
| 529 |
+
"learning_rate": 0.0008274303669726426,
|
| 530 |
+
"loss": 0.1482,
|
| 531 |
+
"step": 87
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 1.49,
|
| 535 |
+
"learning_rate": 0.0008232598970776028,
|
| 536 |
+
"loss": 0.1012,
|
| 537 |
+
"step": 88
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 1.51,
|
| 541 |
+
"learning_rate": 0.0008190504226441654,
|
| 542 |
+
"loss": 0.1552,
|
| 543 |
+
"step": 89
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 1.53,
|
| 547 |
+
"learning_rate": 0.0008148024515875057,
|
| 548 |
+
"loss": 0.1133,
|
| 549 |
+
"step": 90
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 1.54,
|
| 553 |
+
"learning_rate": 0.0008105164964678008,
|
| 554 |
+
"loss": 0.1246,
|
| 555 |
+
"step": 91
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 1.56,
|
| 559 |
+
"learning_rate": 0.0008061930744283854,
|
| 560 |
+
"loss": 0.124,
|
| 561 |
+
"step": 92
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 1.58,
|
| 565 |
+
"learning_rate": 0.0008018327071333521,
|
| 566 |
+
"loss": 0.1149,
|
| 567 |
+
"step": 93
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 1.59,
|
| 571 |
+
"learning_rate": 0.000797435920704608,
|
| 572 |
+
"loss": 0.1231,
|
| 573 |
+
"step": 94
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 1.61,
|
| 577 |
+
"learning_rate": 0.0007930032456583931,
|
| 578 |
+
"loss": 0.1335,
|
| 579 |
+
"step": 95
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 1.63,
|
| 583 |
+
"learning_rate": 0.0007885352168412676,
|
| 584 |
+
"loss": 0.1132,
|
| 585 |
+
"step": 96
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 1.64,
|
| 589 |
+
"learning_rate": 0.0007840323733655779,
|
| 590 |
+
"loss": 0.1233,
|
| 591 |
+
"step": 97
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 1.66,
|
| 595 |
+
"learning_rate": 0.0007794952585444068,
|
| 596 |
+
"loss": 0.1224,
|
| 597 |
+
"step": 98
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 1.68,
|
| 601 |
+
"learning_rate": 0.0007749244198260175,
|
| 602 |
+
"loss": 0.1014,
|
| 603 |
+
"step": 99
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 1.69,
|
| 607 |
+
"learning_rate": 0.0007703204087277988,
|
| 608 |
+
"loss": 0.1046,
|
| 609 |
+
"step": 100
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 1.71,
|
| 613 |
+
"learning_rate": 0.0007656837807697187,
|
| 614 |
+
"loss": 0.1291,
|
| 615 |
+
"step": 101
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 1.73,
|
| 619 |
+
"learning_rate": 0.0007610150954072952,
|
| 620 |
+
"loss": 0.1085,
|
| 621 |
+
"step": 102
|
| 622 |
+
},
|
| 623 |
+
{
|
| 624 |
+
"epoch": 1.75,
|
| 625 |
+
"learning_rate": 0.0007563149159640929,
|
| 626 |
+
"loss": 0.0982,
|
| 627 |
+
"step": 103
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 1.76,
|
| 631 |
+
"learning_rate": 0.000751583809563752,
|
| 632 |
+
"loss": 0.1024,
|
| 633 |
+
"step": 104
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 1.78,
|
| 637 |
+
"learning_rate": 0.0007468223470615592,
|
| 638 |
+
"loss": 0.1017,
|
| 639 |
+
"step": 105
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 1.8,
|
| 643 |
+
"learning_rate": 0.0007420311029755687,
|
| 644 |
+
"loss": 0.0854,
|
| 645 |
+
"step": 106
|
| 646 |
+
},
|
| 647 |
+
{
|
| 648 |
+
"epoch": 1.81,
|
| 649 |
+
"learning_rate": 0.0007372106554172802,
|
| 650 |
+
"loss": 0.1233,
|
| 651 |
+
"step": 107
|
| 652 |
+
},
|
| 653 |
+
{
|
| 654 |
+
"epoch": 1.83,
|
| 655 |
+
"learning_rate": 0.0007323615860218843,
|
| 656 |
+
"loss": 0.1052,
|
| 657 |
+
"step": 108
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"epoch": 1.85,
|
| 661 |
+
"learning_rate": 0.0007274844798780825,
|
| 662 |
+
"loss": 0.1145,
|
| 663 |
+
"step": 109
|
| 664 |
+
},
|
| 665 |
+
{
|
| 666 |
+
"epoch": 1.86,
|
| 667 |
+
"learning_rate": 0.0007225799254574904,
|
| 668 |
+
"loss": 0.0964,
|
| 669 |
+
"step": 110
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 1.88,
|
| 673 |
+
"learning_rate": 0.0007176485145436324,
|
| 674 |
+
"loss": 0.1058,
|
| 675 |
+
"step": 111
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 1.9,
|
| 679 |
+
"learning_rate": 0.0007126908421605375,
|
| 680 |
+
"loss": 0.1114,
|
| 681 |
+
"step": 112
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 1.92,
|
| 685 |
+
"learning_rate": 0.0007077075065009433,
|
| 686 |
+
"loss": 0.1143,
|
| 687 |
+
"step": 113
|
| 688 |
+
},
|
| 689 |
+
{
|
| 690 |
+
"epoch": 1.93,
|
| 691 |
+
"learning_rate": 0.0007026991088541184,
|
| 692 |
+
"loss": 0.0994,
|
| 693 |
+
"step": 114
|
| 694 |
+
},
|
| 695 |
+
{
|
| 696 |
+
"epoch": 1.95,
|
| 697 |
+
"learning_rate": 0.0006976662535333107,
|
| 698 |
+
"loss": 0.0954,
|
| 699 |
+
"step": 115
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 1.97,
|
| 703 |
+
"learning_rate": 0.0006926095478028312,
|
| 704 |
+
"loss": 0.0941,
|
| 705 |
+
"step": 116
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 1.98,
|
| 709 |
+
"learning_rate": 0.000687529601804781,
|
| 710 |
+
"loss": 0.1026,
|
| 711 |
+
"step": 117
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 2.0,
|
| 715 |
+
"learning_rate": 0.0006824270284854318,
|
| 716 |
+
"loss": 0.0884,
|
| 717 |
+
"step": 118
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 2.02,
|
| 721 |
+
"learning_rate": 0.0006773024435212678,
|
| 722 |
+
"loss": 0.0958,
|
| 723 |
+
"step": 119
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 2.03,
|
| 727 |
+
"learning_rate": 0.0006721564652446986,
|
| 728 |
+
"loss": 0.0869,
|
| 729 |
+
"step": 120
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 2.05,
|
| 733 |
+
"learning_rate": 0.0006669897145694507,
|
| 734 |
+
"loss": 0.0929,
|
| 735 |
+
"step": 121
|
| 736 |
+
},
|
| 737 |
+
{
|
| 738 |
+
"epoch": 2.07,
|
| 739 |
+
"learning_rate": 0.0006618028149156478,
|
| 740 |
+
"loss": 0.0858,
|
| 741 |
+
"step": 122
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 2.08,
|
| 745 |
+
"learning_rate": 0.0006565963921345895,
|
| 746 |
+
"loss": 0.0833,
|
| 747 |
+
"step": 123
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 2.1,
|
| 751 |
+
"learning_rate": 0.000651371074433236,
|
| 752 |
+
"loss": 0.093,
|
| 753 |
+
"step": 124
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 2.12,
|
| 757 |
+
"learning_rate": 0.0006461274922984087,
|
| 758 |
+
"loss": 0.0954,
|
| 759 |
+
"step": 125
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 2.14,
|
| 763 |
+
"learning_rate": 0.0006408662784207149,
|
| 764 |
+
"loss": 0.079,
|
| 765 |
+
"step": 126
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 2.15,
|
| 769 |
+
"learning_rate": 0.0006355880676182085,
|
| 770 |
+
"loss": 0.0794,
|
| 771 |
+
"step": 127
|
| 772 |
+
},
|
| 773 |
+
{
|
| 774 |
+
"epoch": 2.17,
|
| 775 |
+
"learning_rate": 0.0006302934967597922,
|
| 776 |
+
"loss": 0.0765,
|
| 777 |
+
"step": 128
|
| 778 |
+
},
|
| 779 |
+
{
|
| 780 |
+
"epoch": 2.19,
|
| 781 |
+
"learning_rate": 0.0006249832046883729,
|
| 782 |
+
"loss": 0.0811,
|
| 783 |
+
"step": 129
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 2.2,
|
| 787 |
+
"learning_rate": 0.0006196578321437789,
|
| 788 |
+
"loss": 0.077,
|
| 789 |
+
"step": 130
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 2.22,
|
| 793 |
+
"learning_rate": 0.0006143180216854487,
|
| 794 |
+
"loss": 0.0825,
|
| 795 |
+
"step": 131
|
| 796 |
+
},
|
| 797 |
+
{
|
| 798 |
+
"epoch": 2.24,
|
| 799 |
+
"learning_rate": 0.0006089644176148992,
|
| 800 |
+
"loss": 0.0878,
|
| 801 |
+
"step": 132
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 2.25,
|
| 805 |
+
"learning_rate": 0.0006035976658979846,
|
| 806 |
+
"loss": 0.089,
|
| 807 |
+
"step": 133
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 2.27,
|
| 811 |
+
"learning_rate": 0.0005982184140869538,
|
| 812 |
+
"loss": 0.0748,
|
| 813 |
+
"step": 134
|
| 814 |
+
},
|
| 815 |
+
{
|
| 816 |
+
"epoch": 2.29,
|
| 817 |
+
"learning_rate": 0.0005928273112423177,
|
| 818 |
+
"loss": 0.0811,
|
| 819 |
+
"step": 135
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"epoch": 2.31,
|
| 823 |
+
"learning_rate": 0.0005874250078545323,
|
| 824 |
+
"loss": 0.0825,
|
| 825 |
+
"step": 136
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 2.32,
|
| 829 |
+
"learning_rate": 0.000582012155765511,
|
| 830 |
+
"loss": 0.0866,
|
| 831 |
+
"step": 137
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 2.34,
|
| 835 |
+
"learning_rate": 0.000576589408089974,
|
| 836 |
+
"loss": 0.0818,
|
| 837 |
+
"step": 138
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 2.36,
|
| 841 |
+
"learning_rate": 0.0005711574191366427,
|
| 842 |
+
"loss": 0.0961,
|
| 843 |
+
"step": 139
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 2.37,
|
| 847 |
+
"learning_rate": 0.0005657168443292908,
|
| 848 |
+
"loss": 0.0767,
|
| 849 |
+
"step": 140
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 2.39,
|
| 853 |
+
"learning_rate": 0.0005602683401276614,
|
| 854 |
+
"loss": 0.0719,
|
| 855 |
+
"step": 141
|
| 856 |
+
},
|
| 857 |
+
{
|
| 858 |
+
"epoch": 2.41,
|
| 859 |
+
"learning_rate": 0.0005548125639482587,
|
| 860 |
+
"loss": 0.0747,
|
| 861 |
+
"step": 142
|
| 862 |
+
},
|
| 863 |
+
{
|
| 864 |
+
"epoch": 2.42,
|
| 865 |
+
"learning_rate": 0.0005493501740850228,
|
| 866 |
+
"loss": 0.0836,
|
| 867 |
+
"step": 143
|
| 868 |
+
},
|
| 869 |
+
{
|
| 870 |
+
"epoch": 2.44,
|
| 871 |
+
"learning_rate": 0.0005438818296299015,
|
| 872 |
+
"loss": 0.0823,
|
| 873 |
+
"step": 144
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 2.46,
|
| 877 |
+
"learning_rate": 0.0005384081903933235,
|
| 878 |
+
"loss": 0.0789,
|
| 879 |
+
"step": 145
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 2.47,
|
| 883 |
+
"learning_rate": 0.0005329299168245857,
|
| 884 |
+
"loss": 0.0788,
|
| 885 |
+
"step": 146
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 2.49,
|
| 889 |
+
"learning_rate": 0.0005274476699321638,
|
| 890 |
+
"loss": 0.0857,
|
| 891 |
+
"step": 147
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 2.51,
|
| 895 |
+
"learning_rate": 0.0005219621112039544,
|
| 896 |
+
"loss": 0.0828,
|
| 897 |
+
"step": 148
|
| 898 |
+
},
|
| 899 |
+
{
|
| 900 |
+
"epoch": 2.53,
|
| 901 |
+
"learning_rate": 0.0005164739025274604,
|
| 902 |
+
"loss": 0.083,
|
| 903 |
+
"step": 149
|
| 904 |
+
},
|
| 905 |
+
{
|
| 906 |
+
"epoch": 2.54,
|
| 907 |
+
"learning_rate": 0.0005109837061099274,
|
| 908 |
+
"loss": 0.0916,
|
| 909 |
+
"step": 150
|
| 910 |
+
},
|
| 911 |
+
{
|
| 912 |
+
"epoch": 2.56,
|
| 913 |
+
"learning_rate": 0.0005054921843984418,
|
| 914 |
+
"loss": 0.0813,
|
| 915 |
+
"step": 151
|
| 916 |
+
},
|
| 917 |
+
{
|
| 918 |
+
"epoch": 2.58,
|
| 919 |
+
"learning_rate": 0.0005,
|
| 920 |
+
"loss": 0.0714,
|
| 921 |
+
"step": 152
|
| 922 |
+
},
|
| 923 |
+
{
|
| 924 |
+
"epoch": 2.59,
|
| 925 |
+
"learning_rate": 0.0004945078156015581,
|
| 926 |
+
"loss": 0.0741,
|
| 927 |
+
"step": 153
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 2.61,
|
| 931 |
+
"learning_rate": 0.0004890162938900726,
|
| 932 |
+
"loss": 0.0839,
|
| 933 |
+
"step": 154
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 2.63,
|
| 937 |
+
"learning_rate": 0.00048352609747253966,
|
| 938 |
+
"loss": 0.0725,
|
| 939 |
+
"step": 155
|
| 940 |
+
},
|
| 941 |
+
{
|
| 942 |
+
"epoch": 2.64,
|
| 943 |
+
"learning_rate": 0.0004780378887960458,
|
| 944 |
+
"loss": 0.0843,
|
| 945 |
+
"step": 156
|
| 946 |
+
},
|
| 947 |
+
{
|
| 948 |
+
"epoch": 2.66,
|
| 949 |
+
"learning_rate": 0.0004725523300678363,
|
| 950 |
+
"loss": 0.106,
|
| 951 |
+
"step": 157
|
| 952 |
+
},
|
| 953 |
+
{
|
| 954 |
+
"epoch": 2.68,
|
| 955 |
+
"learning_rate": 0.00046707008317541446,
|
| 956 |
+
"loss": 0.0715,
|
| 957 |
+
"step": 158
|
| 958 |
+
},
|
| 959 |
+
{
|
| 960 |
+
"epoch": 2.69,
|
| 961 |
+
"learning_rate": 0.0004615918096066766,
|
| 962 |
+
"loss": 0.0787,
|
| 963 |
+
"step": 159
|
| 964 |
+
},
|
| 965 |
+
{
|
| 966 |
+
"epoch": 2.71,
|
| 967 |
+
"learning_rate": 0.00045611817037009855,
|
| 968 |
+
"loss": 0.0786,
|
| 969 |
+
"step": 160
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 2.73,
|
| 973 |
+
"learning_rate": 0.0004506498259149773,
|
| 974 |
+
"loss": 0.0752,
|
| 975 |
+
"step": 161
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 2.75,
|
| 979 |
+
"learning_rate": 0.0004451874360517413,
|
| 980 |
+
"loss": 0.0771,
|
| 981 |
+
"step": 162
|
| 982 |
+
},
|
| 983 |
+
{
|
| 984 |
+
"epoch": 2.76,
|
| 985 |
+
"learning_rate": 0.00043973165987233853,
|
| 986 |
+
"loss": 0.0704,
|
| 987 |
+
"step": 163
|
| 988 |
+
},
|
| 989 |
+
{
|
| 990 |
+
"epoch": 2.78,
|
| 991 |
+
"learning_rate": 0.0004342831556707093,
|
| 992 |
+
"loss": 0.0737,
|
| 993 |
+
"step": 164
|
| 994 |
+
},
|
| 995 |
+
{
|
| 996 |
+
"epoch": 2.8,
|
| 997 |
+
"learning_rate": 0.0004288425808633575,
|
| 998 |
+
"loss": 0.0711,
|
| 999 |
+
"step": 165
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 2.81,
|
| 1003 |
+
"learning_rate": 0.00042341059191002613,
|
| 1004 |
+
"loss": 0.0796,
|
| 1005 |
+
"step": 166
|
| 1006 |
+
},
|
| 1007 |
+
{
|
| 1008 |
+
"epoch": 2.83,
|
| 1009 |
+
"learning_rate": 0.0004179878442344892,
|
| 1010 |
+
"loss": 0.0753,
|
| 1011 |
+
"step": 167
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 2.85,
|
| 1015 |
+
"learning_rate": 0.0004125749921454679,
|
| 1016 |
+
"loss": 0.0787,
|
| 1017 |
+
"step": 168
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 2.86,
|
| 1021 |
+
"learning_rate": 0.00040717268875768226,
|
| 1022 |
+
"loss": 0.0765,
|
| 1023 |
+
"step": 169
|
| 1024 |
+
},
|
| 1025 |
+
{
|
| 1026 |
+
"epoch": 2.88,
|
| 1027 |
+
"learning_rate": 0.00040178158591304614,
|
| 1028 |
+
"loss": 0.074,
|
| 1029 |
+
"step": 170
|
| 1030 |
+
},
|
| 1031 |
+
{
|
| 1032 |
+
"epoch": 2.9,
|
| 1033 |
+
"learning_rate": 0.00039640233410201555,
|
| 1034 |
+
"loss": 0.0747,
|
| 1035 |
+
"step": 171
|
| 1036 |
+
},
|
| 1037 |
+
{
|
| 1038 |
+
"epoch": 2.92,
|
| 1039 |
+
"learning_rate": 0.00039103558238510084,
|
| 1040 |
+
"loss": 0.0779,
|
| 1041 |
+
"step": 172
|
| 1042 |
+
},
|
| 1043 |
+
{
|
| 1044 |
+
"epoch": 2.93,
|
| 1045 |
+
"learning_rate": 0.00038568197831455135,
|
| 1046 |
+
"loss": 0.0821,
|
| 1047 |
+
"step": 173
|
| 1048 |
+
},
|
| 1049 |
+
{
|
| 1050 |
+
"epoch": 2.95,
|
| 1051 |
+
"learning_rate": 0.00038034216785622126,
|
| 1052 |
+
"loss": 0.0796,
|
| 1053 |
+
"step": 174
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 2.97,
|
| 1057 |
+
"learning_rate": 0.0003750167953116272,
|
| 1058 |
+
"loss": 0.0661,
|
| 1059 |
+
"step": 175
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 2.98,
|
| 1063 |
+
"learning_rate": 0.00036970650324020783,
|
| 1064 |
+
"loss": 0.0725,
|
| 1065 |
+
"step": 176
|
| 1066 |
+
},
|
| 1067 |
+
{
|
| 1068 |
+
"epoch": 3.0,
|
| 1069 |
+
"learning_rate": 0.0003644119323817915,
|
| 1070 |
+
"loss": 0.0756,
|
| 1071 |
+
"step": 177
|
| 1072 |
+
},
|
| 1073 |
+
{
|
| 1074 |
+
"epoch": 3.02,
|
| 1075 |
+
"learning_rate": 0.0003591337215792851,
|
| 1076 |
+
"loss": 0.0635,
|
| 1077 |
+
"step": 178
|
| 1078 |
+
},
|
| 1079 |
+
{
|
| 1080 |
+
"epoch": 3.03,
|
| 1081 |
+
"learning_rate": 0.0003538725077015915,
|
| 1082 |
+
"loss": 0.0698,
|
| 1083 |
+
"step": 179
|
| 1084 |
+
},
|
| 1085 |
+
{
|
| 1086 |
+
"epoch": 3.05,
|
| 1087 |
+
"learning_rate": 0.00034862892556676393,
|
| 1088 |
+
"loss": 0.0875,
|
| 1089 |
+
"step": 180
|
| 1090 |
+
},
|
| 1091 |
+
{
|
| 1092 |
+
"epoch": 3.07,
|
| 1093 |
+
"learning_rate": 0.0003434036078654106,
|
| 1094 |
+
"loss": 0.0675,
|
| 1095 |
+
"step": 181
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 3.08,
|
| 1099 |
+
"learning_rate": 0.0003381971850843523,
|
| 1100 |
+
"loss": 0.071,
|
| 1101 |
+
"step": 182
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 3.1,
|
| 1105 |
+
"learning_rate": 0.0003330102854305493,
|
| 1106 |
+
"loss": 0.0675,
|
| 1107 |
+
"step": 183
|
| 1108 |
+
},
|
| 1109 |
+
{
|
| 1110 |
+
"epoch": 3.12,
|
| 1111 |
+
"learning_rate": 0.00032784353475530137,
|
| 1112 |
+
"loss": 0.0689,
|
| 1113 |
+
"step": 184
|
| 1114 |
+
},
|
| 1115 |
+
{
|
| 1116 |
+
"epoch": 3.14,
|
| 1117 |
+
"learning_rate": 0.00032269755647873217,
|
| 1118 |
+
"loss": 0.0711,
|
| 1119 |
+
"step": 185
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 3.15,
|
| 1123 |
+
"learning_rate": 0.0003175729715145684,
|
| 1124 |
+
"loss": 0.0692,
|
| 1125 |
+
"step": 186
|
| 1126 |
+
},
|
| 1127 |
+
{
|
| 1128 |
+
"epoch": 3.17,
|
| 1129 |
+
"learning_rate": 0.00031247039819521906,
|
| 1130 |
+
"loss": 0.0718,
|
| 1131 |
+
"step": 187
|
| 1132 |
+
},
|
| 1133 |
+
{
|
| 1134 |
+
"epoch": 3.19,
|
| 1135 |
+
"learning_rate": 0.00030739045219716887,
|
| 1136 |
+
"loss": 0.0769,
|
| 1137 |
+
"step": 188
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 3.2,
|
| 1141 |
+
"learning_rate": 0.0003023337464666893,
|
| 1142 |
+
"loss": 0.0703,
|
| 1143 |
+
"step": 189
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 3.22,
|
| 1147 |
+
"learning_rate": 0.0002973008911458816,
|
| 1148 |
+
"loss": 0.0793,
|
| 1149 |
+
"step": 190
|
| 1150 |
+
},
|
| 1151 |
+
{
|
| 1152 |
+
"epoch": 3.24,
|
| 1153 |
+
"learning_rate": 0.0002922924934990568,
|
| 1154 |
+
"loss": 0.0681,
|
| 1155 |
+
"step": 191
|
| 1156 |
+
},
|
| 1157 |
+
{
|
| 1158 |
+
"epoch": 3.25,
|
| 1159 |
+
"learning_rate": 0.0002873091578394626,
|
| 1160 |
+
"loss": 0.07,
|
| 1161 |
+
"step": 192
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 3.27,
|
| 1165 |
+
"learning_rate": 0.0002823514854563677,
|
| 1166 |
+
"loss": 0.0667,
|
| 1167 |
+
"step": 193
|
| 1168 |
+
},
|
| 1169 |
+
{
|
| 1170 |
+
"epoch": 3.29,
|
| 1171 |
+
"learning_rate": 0.0002774200745425096,
|
| 1172 |
+
"loss": 0.0718,
|
| 1173 |
+
"step": 194
|
| 1174 |
+
},
|
| 1175 |
+
{
|
| 1176 |
+
"epoch": 3.31,
|
| 1177 |
+
"learning_rate": 0.0002725155201219176,
|
| 1178 |
+
"loss": 0.071,
|
| 1179 |
+
"step": 195
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 3.32,
|
| 1183 |
+
"learning_rate": 0.00026763841397811573,
|
| 1184 |
+
"loss": 0.0697,
|
| 1185 |
+
"step": 196
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 3.34,
|
| 1189 |
+
"learning_rate": 0.00026278934458272,
|
| 1190 |
+
"loss": 0.0633,
|
| 1191 |
+
"step": 197
|
| 1192 |
+
},
|
| 1193 |
+
{
|
| 1194 |
+
"epoch": 3.36,
|
| 1195 |
+
"learning_rate": 0.00025796889702443126,
|
| 1196 |
+
"loss": 0.0616,
|
| 1197 |
+
"step": 198
|
| 1198 |
+
},
|
| 1199 |
+
{
|
| 1200 |
+
"epoch": 3.37,
|
| 1201 |
+
"learning_rate": 0.0002531776529384407,
|
| 1202 |
+
"loss": 0.0653,
|
| 1203 |
+
"step": 199
|
| 1204 |
+
},
|
| 1205 |
+
{
|
| 1206 |
+
"epoch": 3.39,
|
| 1207 |
+
"learning_rate": 0.0002484161904362481,
|
| 1208 |
+
"loss": 0.0674,
|
| 1209 |
+
"step": 200
|
| 1210 |
+
},
|
| 1211 |
+
{
|
| 1212 |
+
"epoch": 3.41,
|
| 1213 |
+
"learning_rate": 0.00024368508403590727,
|
| 1214 |
+
"loss": 0.071,
|
| 1215 |
+
"step": 201
|
| 1216 |
+
},
|
| 1217 |
+
{
|
| 1218 |
+
"epoch": 3.42,
|
| 1219 |
+
"learning_rate": 0.0002389849045927049,
|
| 1220 |
+
"loss": 0.065,
|
| 1221 |
+
"step": 202
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 3.44,
|
| 1225 |
+
"learning_rate": 0.00023431621923028145,
|
| 1226 |
+
"loss": 0.0657,
|
| 1227 |
+
"step": 203
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 3.46,
|
| 1231 |
+
"learning_rate": 0.0002296795912722014,
|
| 1232 |
+
"loss": 0.0708,
|
| 1233 |
+
"step": 204
|
| 1234 |
+
},
|
| 1235 |
+
{
|
| 1236 |
+
"epoch": 3.47,
|
| 1237 |
+
"learning_rate": 0.0002250755801739826,
|
| 1238 |
+
"loss": 0.0666,
|
| 1239 |
+
"step": 205
|
| 1240 |
+
},
|
| 1241 |
+
{
|
| 1242 |
+
"epoch": 3.49,
|
| 1243 |
+
"learning_rate": 0.00022050474145559324,
|
| 1244 |
+
"loss": 0.0643,
|
| 1245 |
+
"step": 206
|
| 1246 |
+
},
|
| 1247 |
+
{
|
| 1248 |
+
"epoch": 3.51,
|
| 1249 |
+
"learning_rate": 0.00021596762663442215,
|
| 1250 |
+
"loss": 0.0622,
|
| 1251 |
+
"step": 207
|
| 1252 |
+
},
|
| 1253 |
+
{
|
| 1254 |
+
"epoch": 3.53,
|
| 1255 |
+
"learning_rate": 0.00021146478315873236,
|
| 1256 |
+
"loss": 0.0651,
|
| 1257 |
+
"step": 208
|
| 1258 |
+
},
|
| 1259 |
+
{
|
| 1260 |
+
"epoch": 3.54,
|
| 1261 |
+
"learning_rate": 0.00020699675434160698,
|
| 1262 |
+
"loss": 0.0712,
|
| 1263 |
+
"step": 209
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 3.56,
|
| 1267 |
+
"learning_rate": 0.000202564079295392,
|
| 1268 |
+
"loss": 0.0662,
|
| 1269 |
+
"step": 210
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 3.58,
|
| 1273 |
+
"learning_rate": 0.00019816729286664797,
|
| 1274 |
+
"loss": 0.0712,
|
| 1275 |
+
"step": 211
|
| 1276 |
+
},
|
| 1277 |
+
{
|
| 1278 |
+
"epoch": 3.59,
|
| 1279 |
+
"learning_rate": 0.0001938069255716145,
|
| 1280 |
+
"loss": 0.0688,
|
| 1281 |
+
"step": 212
|
| 1282 |
+
},
|
| 1283 |
+
{
|
| 1284 |
+
"epoch": 3.61,
|
| 1285 |
+
"learning_rate": 0.00018948350353219912,
|
| 1286 |
+
"loss": 0.0678,
|
| 1287 |
+
"step": 213
|
| 1288 |
+
},
|
| 1289 |
+
{
|
| 1290 |
+
"epoch": 3.63,
|
| 1291 |
+
"learning_rate": 0.0001851975484124944,
|
| 1292 |
+
"loss": 0.0685,
|
| 1293 |
+
"step": 214
|
| 1294 |
+
},
|
| 1295 |
+
{
|
| 1296 |
+
"epoch": 3.64,
|
| 1297 |
+
"learning_rate": 0.00018094957735583463,
|
| 1298 |
+
"loss": 0.0683,
|
| 1299 |
+
"step": 215
|
| 1300 |
+
},
|
| 1301 |
+
{
|
| 1302 |
+
"epoch": 3.66,
|
| 1303 |
+
"learning_rate": 0.00017674010292239746,
|
| 1304 |
+
"loss": 0.0704,
|
| 1305 |
+
"step": 216
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 3.68,
|
| 1309 |
+
"learning_rate": 0.0001725696330273575,
|
| 1310 |
+
"loss": 0.0665,
|
| 1311 |
+
"step": 217
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 3.69,
|
| 1315 |
+
"learning_rate": 0.00016843867087960252,
|
| 1316 |
+
"loss": 0.0662,
|
| 1317 |
+
"step": 218
|
| 1318 |
+
},
|
| 1319 |
+
{
|
| 1320 |
+
"epoch": 3.71,
|
| 1321 |
+
"learning_rate": 0.00016434771492101485,
|
| 1322 |
+
"loss": 0.0604,
|
| 1323 |
+
"step": 219
|
| 1324 |
+
},
|
| 1325 |
+
{
|
| 1326 |
+
"epoch": 3.73,
|
| 1327 |
+
"learning_rate": 0.00016029725876633085,
|
| 1328 |
+
"loss": 0.0697,
|
| 1329 |
+
"step": 220
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 3.75,
|
| 1333 |
+
"learning_rate": 0.00015628779114358032,
|
| 1334 |
+
"loss": 0.0652,
|
| 1335 |
+
"step": 221
|
| 1336 |
+
},
|
| 1337 |
+
{
|
| 1338 |
+
"epoch": 3.76,
|
| 1339 |
+
"learning_rate": 0.00015231979583511668,
|
| 1340 |
+
"loss": 0.0712,
|
| 1341 |
+
"step": 222
|
| 1342 |
+
},
|
| 1343 |
+
{
|
| 1344 |
+
"epoch": 3.78,
|
| 1345 |
+
"learning_rate": 0.00014839375161924446,
|
| 1346 |
+
"loss": 0.0711,
|
| 1347 |
+
"step": 223
|
| 1348 |
+
},
|
| 1349 |
+
{
|
| 1350 |
+
"epoch": 3.8,
|
| 1351 |
+
"learning_rate": 0.00014451013221244914,
|
| 1352 |
+
"loss": 0.0693,
|
| 1353 |
+
"step": 224
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"epoch": 3.81,
|
| 1357 |
+
"learning_rate": 0.0001406694062122389,
|
| 1358 |
+
"loss": 0.07,
|
| 1359 |
+
"step": 225
|
| 1360 |
+
},
|
| 1361 |
+
{
|
| 1362 |
+
"epoch": 3.83,
|
| 1363 |
+
"learning_rate": 0.00013687203704060343,
|
| 1364 |
+
"loss": 0.0685,
|
| 1365 |
+
"step": 226
|
| 1366 |
+
},
|
| 1367 |
+
{
|
| 1368 |
+
"epoch": 3.85,
|
| 1369 |
+
"learning_rate": 0.00013311848288809813,
|
| 1370 |
+
"loss": 0.0705,
|
| 1371 |
+
"step": 227
|
| 1372 |
+
},
|
| 1373 |
+
{
|
| 1374 |
+
"epoch": 3.86,
|
| 1375 |
+
"learning_rate": 0.0001294091966585576,
|
| 1376 |
+
"loss": 0.0666,
|
| 1377 |
+
"step": 228
|
| 1378 |
+
},
|
| 1379 |
+
{
|
| 1380 |
+
"epoch": 3.88,
|
| 1381 |
+
"learning_rate": 0.0001257446259144494,
|
| 1382 |
+
"loss": 0.0625,
|
| 1383 |
+
"step": 229
|
| 1384 |
+
},
|
| 1385 |
+
{
|
| 1386 |
+
"epoch": 3.9,
|
| 1387 |
+
"learning_rate": 0.00012212521282287093,
|
| 1388 |
+
"loss": 0.0672,
|
| 1389 |
+
"step": 230
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 3.92,
|
| 1393 |
+
"learning_rate": 0.00011855139410219657,
|
| 1394 |
+
"loss": 0.0645,
|
| 1395 |
+
"step": 231
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"epoch": 3.93,
|
| 1399 |
+
"learning_rate": 0.00011502360096938485,
|
| 1400 |
+
"loss": 0.0684,
|
| 1401 |
+
"step": 232
|
| 1402 |
+
},
|
| 1403 |
+
{
|
| 1404 |
+
"epoch": 3.95,
|
| 1405 |
+
"learning_rate": 0.0001115422590879464,
|
| 1406 |
+
"loss": 0.0676,
|
| 1407 |
+
"step": 233
|
| 1408 |
+
},
|
| 1409 |
+
{
|
| 1410 |
+
"epoch": 3.97,
|
| 1411 |
+
"learning_rate": 0.00010810778851658437,
|
| 1412 |
+
"loss": 0.0694,
|
| 1413 |
+
"step": 234
|
| 1414 |
+
},
|
| 1415 |
+
{
|
| 1416 |
+
"epoch": 3.98,
|
| 1417 |
+
"learning_rate": 0.00010472060365850949,
|
| 1418 |
+
"loss": 0.0668,
|
| 1419 |
+
"step": 235
|
| 1420 |
+
},
|
| 1421 |
+
{
|
| 1422 |
+
"epoch": 4.0,
|
| 1423 |
+
"learning_rate": 0.00010138111321143839,
|
| 1424 |
+
"loss": 0.0642,
|
| 1425 |
+
"step": 236
|
| 1426 |
+
},
|
| 1427 |
+
{
|
| 1428 |
+
"epoch": 4.02,
|
| 1429 |
+
"learning_rate": 9.808972011828055e-05,
|
| 1430 |
+
"loss": 0.0594,
|
| 1431 |
+
"step": 237
|
| 1432 |
+
},
|
| 1433 |
+
{
|
| 1434 |
+
"epoch": 4.03,
|
| 1435 |
+
"learning_rate": 9.484682151851831e-05,
|
| 1436 |
+
"loss": 0.0644,
|
| 1437 |
+
"step": 238
|
| 1438 |
+
},
|
| 1439 |
+
{
|
| 1440 |
+
"epoch": 4.05,
|
| 1441 |
+
"learning_rate": 9.16528087002892e-05,
|
| 1442 |
+
"loss": 0.0641,
|
| 1443 |
+
"step": 239
|
| 1444 |
+
},
|
| 1445 |
+
{
|
| 1446 |
+
"epoch": 4.07,
|
| 1447 |
+
"learning_rate": 8.850806705317183e-05,
|
| 1448 |
+
"loss": 0.0642,
|
| 1449 |
+
"step": 240
|
| 1450 |
+
},
|
| 1451 |
+
{
|
| 1452 |
+
"epoch": 4.08,
|
| 1453 |
+
"learning_rate": 8.54129760216859e-05,
|
| 1454 |
+
"loss": 0.068,
|
| 1455 |
+
"step": 241
|
| 1456 |
+
},
|
| 1457 |
+
{
|
| 1458 |
+
"epoch": 4.1,
|
| 1459 |
+
"learning_rate": 8.236790905950763e-05,
|
| 1460 |
+
"loss": 0.0604,
|
| 1461 |
+
"step": 242
|
| 1462 |
+
},
|
| 1463 |
+
{
|
| 1464 |
+
"epoch": 4.12,
|
| 1465 |
+
"learning_rate": 7.937323358440934e-05,
|
| 1466 |
+
"loss": 0.0663,
|
| 1467 |
+
"step": 243
|
| 1468 |
+
},
|
| 1469 |
+
{
|
| 1470 |
+
"epoch": 4.14,
|
| 1471 |
+
"learning_rate": 7.642931093392674e-05,
|
| 1472 |
+
"loss": 0.0624,
|
| 1473 |
+
"step": 244
|
| 1474 |
+
},
|
| 1475 |
+
{
|
| 1476 |
+
"epoch": 4.15,
|
| 1477 |
+
"learning_rate": 7.353649632175957e-05,
|
| 1478 |
+
"loss": 0.0686,
|
| 1479 |
+
"step": 245
|
| 1480 |
+
},
|
| 1481 |
+
{
|
| 1482 |
+
"epoch": 4.17,
|
| 1483 |
+
"learning_rate": 7.069513879491179e-05,
|
| 1484 |
+
"loss": 0.0672,
|
| 1485 |
+
"step": 246
|
| 1486 |
+
},
|
| 1487 |
+
{
|
| 1488 |
+
"epoch": 4.19,
|
| 1489 |
+
"learning_rate": 6.790558119157597e-05,
|
| 1490 |
+
"loss": 0.0657,
|
| 1491 |
+
"step": 247
|
| 1492 |
+
},
|
| 1493 |
+
{
|
| 1494 |
+
"epoch": 4.2,
|
| 1495 |
+
"learning_rate": 6.516816009976557e-05,
|
| 1496 |
+
"loss": 0.0639,
|
| 1497 |
+
"step": 248
|
| 1498 |
+
},
|
| 1499 |
+
{
|
| 1500 |
+
"epoch": 4.22,
|
| 1501 |
+
"learning_rate": 6.248320581670281e-05,
|
| 1502 |
+
"loss": 0.0667,
|
| 1503 |
+
"step": 249
|
| 1504 |
+
},
|
| 1505 |
+
{
|
| 1506 |
+
"epoch": 4.24,
|
| 1507 |
+
"learning_rate": 5.9851042308965156e-05,
|
| 1508 |
+
"loss": 0.0658,
|
| 1509 |
+
"step": 250
|
| 1510 |
+
},
|
| 1511 |
+
{
|
| 1512 |
+
"epoch": 4.25,
|
| 1513 |
+
"learning_rate": 5.72719871733951e-05,
|
| 1514 |
+
"loss": 0.0663,
|
| 1515 |
+
"step": 251
|
| 1516 |
+
},
|
| 1517 |
+
{
|
| 1518 |
+
"epoch": 4.27,
|
| 1519 |
+
"learning_rate": 5.474635159877883e-05,
|
| 1520 |
+
"loss": 0.0677,
|
| 1521 |
+
"step": 252
|
| 1522 |
+
},
|
| 1523 |
+
{
|
| 1524 |
+
"epoch": 4.29,
|
| 1525 |
+
"learning_rate": 5.227444032829887e-05,
|
| 1526 |
+
"loss": 0.0681,
|
| 1527 |
+
"step": 253
|
| 1528 |
+
},
|
| 1529 |
+
{
|
| 1530 |
+
"epoch": 4.31,
|
| 1531 |
+
"learning_rate": 4.985655162276298e-05,
|
| 1532 |
+
"loss": 0.0822,
|
| 1533 |
+
"step": 254
|
| 1534 |
+
},
|
| 1535 |
+
{
|
| 1536 |
+
"epoch": 4.32,
|
| 1537 |
+
"learning_rate": 4.7492977224616595e-05,
|
| 1538 |
+
"loss": 0.0626,
|
| 1539 |
+
"step": 255
|
| 1540 |
+
},
|
| 1541 |
+
{
|
| 1542 |
+
"epoch": 4.34,
|
| 1543 |
+
"learning_rate": 4.518400232274078e-05,
|
| 1544 |
+
"loss": 0.0648,
|
| 1545 |
+
"step": 256
|
| 1546 |
+
},
|
| 1547 |
+
{
|
| 1548 |
+
"epoch": 4.36,
|
| 1549 |
+
"learning_rate": 4.292990551804171e-05,
|
| 1550 |
+
"loss": 0.0697,
|
| 1551 |
+
"step": 257
|
| 1552 |
+
},
|
| 1553 |
+
{
|
| 1554 |
+
"epoch": 4.37,
|
| 1555 |
+
"learning_rate": 4.0730958789834295e-05,
|
| 1556 |
+
"loss": 0.0661,
|
| 1557 |
+
"step": 258
|
| 1558 |
+
},
|
| 1559 |
+
{
|
| 1560 |
+
"epoch": 4.39,
|
| 1561 |
+
"learning_rate": 3.8587427463025346e-05,
|
| 1562 |
+
"loss": 0.0613,
|
| 1563 |
+
"step": 259
|
| 1564 |
+
},
|
| 1565 |
+
{
|
| 1566 |
+
"epoch": 4.41,
|
| 1567 |
+
"learning_rate": 3.6499570176099786e-05,
|
| 1568 |
+
"loss": 0.0645,
|
| 1569 |
+
"step": 260
|
| 1570 |
+
},
|
| 1571 |
+
{
|
| 1572 |
+
"epoch": 4.42,
|
| 1573 |
+
"learning_rate": 3.44676388499125e-05,
|
| 1574 |
+
"loss": 0.0586,
|
| 1575 |
+
"step": 261
|
| 1576 |
+
},
|
| 1577 |
+
{
|
| 1578 |
+
"epoch": 4.44,
|
| 1579 |
+
"learning_rate": 3.249187865729264e-05,
|
| 1580 |
+
"loss": 0.0631,
|
| 1581 |
+
"step": 262
|
| 1582 |
+
},
|
| 1583 |
+
{
|
| 1584 |
+
"epoch": 4.46,
|
| 1585 |
+
"learning_rate": 3.0572527993460054e-05,
|
| 1586 |
+
"loss": 0.0649,
|
| 1587 |
+
"step": 263
|
| 1588 |
+
},
|
| 1589 |
+
{
|
| 1590 |
+
"epoch": 4.47,
|
| 1591 |
+
"learning_rate": 2.8709818447261338e-05,
|
| 1592 |
+
"loss": 0.0657,
|
| 1593 |
+
"step": 264
|
| 1594 |
+
},
|
| 1595 |
+
{
|
| 1596 |
+
"epoch": 4.49,
|
| 1597 |
+
"learning_rate": 2.6903974773225702e-05,
|
| 1598 |
+
"loss": 0.0625,
|
| 1599 |
+
"step": 265
|
| 1600 |
+
},
|
| 1601 |
+
{
|
| 1602 |
+
"epoch": 4.51,
|
| 1603 |
+
"learning_rate": 2.5155214864446553e-05,
|
| 1604 |
+
"loss": 0.0648,
|
| 1605 |
+
"step": 266
|
| 1606 |
+
},
|
| 1607 |
+
{
|
| 1608 |
+
"epoch": 4.53,
|
| 1609 |
+
"learning_rate": 2.3463749726290285e-05,
|
| 1610 |
+
"loss": 0.0663,
|
| 1611 |
+
"step": 267
|
| 1612 |
+
},
|
| 1613 |
+
{
|
| 1614 |
+
"epoch": 4.54,
|
| 1615 |
+
"learning_rate": 2.182978345093628e-05,
|
| 1616 |
+
"loss": 0.0665,
|
| 1617 |
+
"step": 268
|
| 1618 |
+
},
|
| 1619 |
+
{
|
| 1620 |
+
"epoch": 4.56,
|
| 1621 |
+
"learning_rate": 2.025351319275137e-05,
|
| 1622 |
+
"loss": 0.0587,
|
| 1623 |
+
"step": 269
|
| 1624 |
+
},
|
| 1625 |
+
{
|
| 1626 |
+
"epoch": 4.58,
|
| 1627 |
+
"learning_rate": 1.8735129144501038e-05,
|
| 1628 |
+
"loss": 0.0608,
|
| 1629 |
+
"step": 270
|
| 1630 |
+
},
|
| 1631 |
+
{
|
| 1632 |
+
"epoch": 4.59,
|
| 1633 |
+
"learning_rate": 1.7274814514400992e-05,
|
| 1634 |
+
"loss": 0.0663,
|
| 1635 |
+
"step": 271
|
| 1636 |
+
},
|
| 1637 |
+
{
|
| 1638 |
+
"epoch": 4.61,
|
| 1639 |
+
"learning_rate": 1.58727455040108e-05,
|
| 1640 |
+
"loss": 0.0629,
|
| 1641 |
+
"step": 272
|
| 1642 |
+
},
|
| 1643 |
+
{
|
| 1644 |
+
"epoch": 4.63,
|
| 1645 |
+
"learning_rate": 1.4529091286973995e-05,
|
| 1646 |
+
"loss": 0.0585,
|
| 1647 |
+
"step": 273
|
| 1648 |
+
},
|
| 1649 |
+
{
|
| 1650 |
+
"epoch": 4.64,
|
| 1651 |
+
"learning_rate": 1.3244013988605087e-05,
|
| 1652 |
+
"loss": 0.0622,
|
| 1653 |
+
"step": 274
|
| 1654 |
+
},
|
| 1655 |
+
{
|
| 1656 |
+
"epoch": 4.66,
|
| 1657 |
+
"learning_rate": 1.2017668666327752e-05,
|
| 1658 |
+
"loss": 0.0603,
|
| 1659 |
+
"step": 275
|
| 1660 |
+
},
|
| 1661 |
+
{
|
| 1662 |
+
"epoch": 4.68,
|
| 1663 |
+
"learning_rate": 1.0850203290965699e-05,
|
| 1664 |
+
"loss": 0.0603,
|
| 1665 |
+
"step": 276
|
| 1666 |
+
},
|
| 1667 |
+
{
|
| 1668 |
+
"epoch": 4.69,
|
| 1669 |
+
"learning_rate": 9.741758728888216e-06,
|
| 1670 |
+
"loss": 0.0662,
|
| 1671 |
+
"step": 277
|
| 1672 |
+
},
|
| 1673 |
+
{
|
| 1674 |
+
"epoch": 4.71,
|
| 1675 |
+
"learning_rate": 8.692468725013448e-06,
|
| 1676 |
+
"loss": 0.065,
|
| 1677 |
+
"step": 278
|
| 1678 |
+
},
|
| 1679 |
+
{
|
| 1680 |
+
"epoch": 4.73,
|
| 1681 |
+
"learning_rate": 7.702459886670788e-06,
|
| 1682 |
+
"loss": 0.0653,
|
| 1683 |
+
"step": 279
|
| 1684 |
+
},
|
| 1685 |
+
{
|
| 1686 |
+
"epoch": 4.75,
|
| 1687 |
+
"learning_rate": 6.771851668324225e-06,
|
| 1688 |
+
"loss": 0.063,
|
| 1689 |
+
"step": 280
|
| 1690 |
+
},
|
| 1691 |
+
{
|
| 1692 |
+
"epoch": 4.76,
|
| 1693 |
+
"learning_rate": 5.9007563571591425e-06,
|
| 1694 |
+
"loss": 0.0653,
|
| 1695 |
+
"step": 281
|
| 1696 |
+
},
|
| 1697 |
+
{
|
| 1698 |
+
"epoch": 4.78,
|
| 1699 |
+
"learning_rate": 5.089279059533658e-06,
|
| 1700 |
+
"loss": 0.0638,
|
| 1701 |
+
"step": 282
|
| 1702 |
+
},
|
| 1703 |
+
{
|
| 1704 |
+
"epoch": 4.8,
|
| 1705 |
+
"learning_rate": 4.337517688296544e-06,
|
| 1706 |
+
"loss": 0.0631,
|
| 1707 |
+
"step": 283
|
| 1708 |
+
},
|
| 1709 |
+
{
|
| 1710 |
+
"epoch": 4.81,
|
| 1711 |
+
"learning_rate": 3.645562950973014e-06,
|
| 1712 |
+
"loss": 0.0607,
|
| 1713 |
+
"step": 284
|
| 1714 |
+
},
|
| 1715 |
+
{
|
| 1716 |
+
"epoch": 4.83,
|
| 1717 |
+
"learning_rate": 3.013498338820031e-06,
|
| 1718 |
+
"loss": 0.0668,
|
| 1719 |
+
"step": 285
|
| 1720 |
+
},
|
| 1721 |
+
{
|
| 1722 |
+
"epoch": 4.85,
|
| 1723 |
+
"learning_rate": 2.441400116752146e-06,
|
| 1724 |
+
"loss": 0.061,
|
| 1725 |
+
"step": 286
|
| 1726 |
+
},
|
| 1727 |
+
{
|
| 1728 |
+
"epoch": 4.86,
|
| 1729 |
+
"learning_rate": 1.9293373141394122e-06,
|
| 1730 |
+
"loss": 0.065,
|
| 1731 |
+
"step": 287
|
| 1732 |
+
},
|
| 1733 |
+
{
|
| 1734 |
+
"epoch": 4.88,
|
| 1735 |
+
"learning_rate": 1.4773717164784372e-06,
|
| 1736 |
+
"loss": 0.0671,
|
| 1737 |
+
"step": 288
|
| 1738 |
+
},
|
| 1739 |
+
{
|
| 1740 |
+
"epoch": 4.9,
|
| 1741 |
+
"learning_rate": 1.0855578579370695e-06,
|
| 1742 |
+
"loss": 0.0616,
|
| 1743 |
+
"step": 289
|
| 1744 |
+
},
|
| 1745 |
+
{
|
| 1746 |
+
"epoch": 4.92,
|
| 1747 |
+
"learning_rate": 7.539430147745497e-07,
|
| 1748 |
+
"loss": 0.0642,
|
| 1749 |
+
"step": 290
|
| 1750 |
+
},
|
| 1751 |
+
{
|
| 1752 |
+
"epoch": 4.93,
|
| 1753 |
+
"learning_rate": 4.825671996370185e-07,
|
| 1754 |
+
"loss": 0.0661,
|
| 1755 |
+
"step": 291
|
| 1756 |
+
},
|
| 1757 |
+
{
|
| 1758 |
+
"epoch": 4.95,
|
| 1759 |
+
"learning_rate": 2.714631567297121e-07,
|
| 1760 |
+
"loss": 0.0632,
|
| 1761 |
+
"step": 292
|
| 1762 |
+
},
|
| 1763 |
+
{
|
| 1764 |
+
"epoch": 4.97,
|
| 1765 |
+
"learning_rate": 1.2065635786595587e-07,
|
| 1766 |
+
"loss": 0.0671,
|
| 1767 |
+
"step": 293
|
| 1768 |
+
},
|
| 1769 |
+
{
|
| 1770 |
+
"epoch": 4.98,
|
| 1771 |
+
"learning_rate": 3.016499939367812e-08,
|
| 1772 |
+
"loss": 0.0615,
|
| 1773 |
+
"step": 294
|
| 1774 |
+
},
|
| 1775 |
+
{
|
| 1776 |
+
"epoch": 5.0,
|
| 1777 |
+
"learning_rate": 0.0,
|
| 1778 |
+
"loss": 0.0602,
|
| 1779 |
+
"step": 295
|
| 1780 |
+
},
|
| 1781 |
+
{
|
| 1782 |
+
"epoch": 5.0,
|
| 1783 |
+
"step": 295,
|
| 1784 |
+
"total_flos": 3.974264003126886e+16,
|
| 1785 |
+
"train_loss": 0.20217839560266268,
|
| 1786 |
+
"train_runtime": 961.6505,
|
| 1787 |
+
"train_samples_per_second": 19.363,
|
| 1788 |
+
"train_steps_per_second": 0.307
|
| 1789 |
+
}
|
| 1790 |
+
],
|
| 1791 |
+
"logging_steps": 1.0,
|
| 1792 |
+
"max_steps": 295,
|
| 1793 |
+
"num_input_tokens_seen": 0,
|
| 1794 |
+
"num_train_epochs": 5,
|
| 1795 |
+
"save_steps": 3000,
|
| 1796 |
+
"total_flos": 3.974264003126886e+16,
|
| 1797 |
+
"train_batch_size": 32,
|
| 1798 |
+
"trial_name": null,
|
| 1799 |
+
"trial_params": null
|
| 1800 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e3b3dbdec3ee7159450ff67c62b4f150708fc1383e0c3a0ca28d691124a59407
|
| 3 |
+
size 6200
|