Upload folder using huggingface_hub
Browse files- added_tokens.json +6 -0
- config.json +93 -0
- generation_config.json +6 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +21 -0
- tokenizer_config.json +52 -0
- trainer_state.json +540 -0
- training_args.bin +3 -0
- vocab.json +0 -0
added_tokens.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<|endoftext|>": 151643,
|
| 3 |
+
"<|extra_0|>": 151646,
|
| 4 |
+
"<|im_end|>": 151645,
|
| 5 |
+
"<|im_start|>": 151644
|
| 6 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,93 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "./checkpoints/ft-llava-qwen1.5-0.5b-vista_llava-merged-2ep",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"MoELLaVAQwen1_5ForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 151643,
|
| 8 |
+
"eos_token_id": 151643,
|
| 9 |
+
"freeze_mm_mlp_adapter": false,
|
| 10 |
+
"hidden_act": "silu",
|
| 11 |
+
"hidden_size": 1024,
|
| 12 |
+
"image_aspect_ratio": "pad",
|
| 13 |
+
"image_projector_type": "mlp2x_gelu",
|
| 14 |
+
"initializer_range": 0.02,
|
| 15 |
+
"intermediate_size": 2816,
|
| 16 |
+
"lora": {},
|
| 17 |
+
"max_position_embeddings": 32768,
|
| 18 |
+
"max_window_layers": 21,
|
| 19 |
+
"mm_hidden_size": 768,
|
| 20 |
+
"mm_image_tower": "google/siglip-base-patch16-256-multilingual",
|
| 21 |
+
"mm_projector_lr": null,
|
| 22 |
+
"mm_use_im_patch_token": false,
|
| 23 |
+
"mm_use_im_start_end": false,
|
| 24 |
+
"mm_video_tower": null,
|
| 25 |
+
"mm_vision_select_feature": "patch",
|
| 26 |
+
"mm_vision_select_layer": -2,
|
| 27 |
+
"model_type": "moe_llava_qwen1_5",
|
| 28 |
+
"moe": {
|
| 29 |
+
"capacity_factor": 1.5,
|
| 30 |
+
"ep_size": 1,
|
| 31 |
+
"eval_capacity_factor": 2.0,
|
| 32 |
+
"min_capacity": 0,
|
| 33 |
+
"moe_enable": true,
|
| 34 |
+
"moe_layers_idx": [
|
| 35 |
+
0,
|
| 36 |
+
2,
|
| 37 |
+
4,
|
| 38 |
+
6,
|
| 39 |
+
8,
|
| 40 |
+
10,
|
| 41 |
+
12,
|
| 42 |
+
14,
|
| 43 |
+
16,
|
| 44 |
+
18,
|
| 45 |
+
20,
|
| 46 |
+
22
|
| 47 |
+
],
|
| 48 |
+
"moe_mode": "sparse",
|
| 49 |
+
"num_experts": [
|
| 50 |
+
4,
|
| 51 |
+
4,
|
| 52 |
+
4,
|
| 53 |
+
4,
|
| 54 |
+
4,
|
| 55 |
+
4,
|
| 56 |
+
4,
|
| 57 |
+
4,
|
| 58 |
+
4,
|
| 59 |
+
4,
|
| 60 |
+
4,
|
| 61 |
+
4
|
| 62 |
+
],
|
| 63 |
+
"router_aux_loss_coef": 0.01,
|
| 64 |
+
"top_k_experts": 2,
|
| 65 |
+
"train_modules": [
|
| 66 |
+
"mlp.gate_proj",
|
| 67 |
+
"mlp.up_proj",
|
| 68 |
+
"mlp.down_proj",
|
| 69 |
+
"wg"
|
| 70 |
+
],
|
| 71 |
+
"use_residual": false
|
| 72 |
+
},
|
| 73 |
+
"num_attention_heads": 16,
|
| 74 |
+
"num_hidden_layers": 24,
|
| 75 |
+
"num_key_value_heads": 16,
|
| 76 |
+
"pad_token_id": 151643,
|
| 77 |
+
"rms_norm_eps": 1e-06,
|
| 78 |
+
"rope_theta": 1000000.0,
|
| 79 |
+
"sliding_window": 32768,
|
| 80 |
+
"tie_word_embeddings": true,
|
| 81 |
+
"tokenizer_padding_side": "right",
|
| 82 |
+
"torch_dtype": "bfloat16",
|
| 83 |
+
"transformers_version": "4.37.0",
|
| 84 |
+
"tune_mm_mlp_adapter": false,
|
| 85 |
+
"use_cache": true,
|
| 86 |
+
"use_mm_proj": true,
|
| 87 |
+
"use_sliding_window": false,
|
| 88 |
+
"video_global_proj": false,
|
| 89 |
+
"video_projector_type": "linear",
|
| 90 |
+
"video_spatial_proj": false,
|
| 91 |
+
"video_temproal_proj": false,
|
| 92 |
+
"vocab_size": 151646
|
| 93 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 151643,
|
| 3 |
+
"eos_token_id": 151643,
|
| 4 |
+
"max_new_tokens": 2048,
|
| 5 |
+
"transformers_version": "4.37.0"
|
| 6 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:71bce6d4b65d6963b4418f6c06d10f06c62db5ca8a568a30ff46d0edf057bc56
|
| 3 |
+
size 2050524576
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b7afffefa151565af2accc6f55fce87d588fba878113b291deff69fda11a2f42
|
| 3 |
+
size 1740053129
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|im_start|>",
|
| 4 |
+
"<|im_end|>"
|
| 5 |
+
],
|
| 6 |
+
"eos_token": {
|
| 7 |
+
"content": "<|endoftext|>",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": false,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false
|
| 12 |
+
},
|
| 13 |
+
"pad_token": "<|extra_0|>",
|
| 14 |
+
"unk_token": {
|
| 15 |
+
"content": "<|extra_0|>",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": false,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false
|
| 20 |
+
}
|
| 21 |
+
}
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,52 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"151643": {
|
| 5 |
+
"content": "<|endoftext|>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": false,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"151644": {
|
| 13 |
+
"content": "<|im_start|>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": false,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"151645": {
|
| 21 |
+
"content": "<|im_end|>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": false,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": true
|
| 27 |
+
},
|
| 28 |
+
"151646": {
|
| 29 |
+
"content": "<|extra_0|>",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": false,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false,
|
| 34 |
+
"special": true
|
| 35 |
+
}
|
| 36 |
+
},
|
| 37 |
+
"additional_special_tokens": [
|
| 38 |
+
"<|im_start|>",
|
| 39 |
+
"<|im_end|>"
|
| 40 |
+
],
|
| 41 |
+
"bos_token": null,
|
| 42 |
+
"chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
|
| 43 |
+
"clean_up_tokenization_spaces": false,
|
| 44 |
+
"eos_token": "<|endoftext|>",
|
| 45 |
+
"errors": "replace",
|
| 46 |
+
"model_max_length": 2048,
|
| 47 |
+
"pad_token": "<|extra_0|>",
|
| 48 |
+
"padding_side": "right",
|
| 49 |
+
"split_special_tokens": false,
|
| 50 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 51 |
+
"unk_token": "<|extra_0|>"
|
| 52 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,540 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 4283,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.01,
|
| 13 |
+
"learning_rate": 7.751937984496126e-06,
|
| 14 |
+
"loss": 2.7409,
|
| 15 |
+
"step": 50
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.02,
|
| 19 |
+
"learning_rate": 1.550387596899225e-05,
|
| 20 |
+
"loss": 2.4444,
|
| 21 |
+
"step": 100
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.04,
|
| 25 |
+
"learning_rate": 1.9998738851504623e-05,
|
| 26 |
+
"loss": 2.2444,
|
| 27 |
+
"step": 150
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.05,
|
| 31 |
+
"learning_rate": 1.9985587175059564e-05,
|
| 32 |
+
"loss": 2.1017,
|
| 33 |
+
"step": 200
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.06,
|
| 37 |
+
"learning_rate": 1.995815877254959e-05,
|
| 38 |
+
"loss": 2.0129,
|
| 39 |
+
"step": 250
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.07,
|
| 43 |
+
"learning_rate": 1.991649285927394e-05,
|
| 44 |
+
"loss": 1.9724,
|
| 45 |
+
"step": 300
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.08,
|
| 49 |
+
"learning_rate": 1.9860649006374456e-05,
|
| 50 |
+
"loss": 1.904,
|
| 51 |
+
"step": 350
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.09,
|
| 55 |
+
"learning_rate": 1.979070705566478e-05,
|
| 56 |
+
"loss": 1.8862,
|
| 57 |
+
"step": 400
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.11,
|
| 61 |
+
"learning_rate": 1.9706767005477825e-05,
|
| 62 |
+
"loss": 1.8507,
|
| 63 |
+
"step": 450
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.12,
|
| 67 |
+
"learning_rate": 1.960894886769486e-05,
|
| 68 |
+
"loss": 1.8229,
|
| 69 |
+
"step": 500
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.13,
|
| 73 |
+
"learning_rate": 1.949739249616051e-05,
|
| 74 |
+
"loss": 1.792,
|
| 75 |
+
"step": 550
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.14,
|
| 79 |
+
"learning_rate": 1.937225738672908e-05,
|
| 80 |
+
"loss": 1.7843,
|
| 81 |
+
"step": 600
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.15,
|
| 85 |
+
"learning_rate": 1.9233722449228015e-05,
|
| 86 |
+
"loss": 1.7632,
|
| 87 |
+
"step": 650
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.16,
|
| 91 |
+
"learning_rate": 1.9081985751664576e-05,
|
| 92 |
+
"loss": 1.7554,
|
| 93 |
+
"step": 700
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.18,
|
| 97 |
+
"learning_rate": 1.8917264237041433e-05,
|
| 98 |
+
"loss": 1.7359,
|
| 99 |
+
"step": 750
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.19,
|
| 103 |
+
"learning_rate": 1.873979341318602e-05,
|
| 104 |
+
"loss": 1.7323,
|
| 105 |
+
"step": 800
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.2,
|
| 109 |
+
"learning_rate": 1.8549827016037167e-05,
|
| 110 |
+
"loss": 1.7054,
|
| 111 |
+
"step": 850
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 0.21,
|
| 115 |
+
"learning_rate": 1.8347636646870404e-05,
|
| 116 |
+
"loss": 1.7018,
|
| 117 |
+
"step": 900
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 0.22,
|
| 121 |
+
"learning_rate": 1.813351138398058e-05,
|
| 122 |
+
"loss": 1.6967,
|
| 123 |
+
"step": 950
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.23,
|
| 127 |
+
"learning_rate": 1.7907757369376984e-05,
|
| 128 |
+
"loss": 1.6812,
|
| 129 |
+
"step": 1000
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.25,
|
| 133 |
+
"learning_rate": 1.767069737108199e-05,
|
| 134 |
+
"loss": 1.6623,
|
| 135 |
+
"step": 1050
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.26,
|
| 139 |
+
"learning_rate": 1.7422670321658813e-05,
|
| 140 |
+
"loss": 1.6476,
|
| 141 |
+
"step": 1100
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 0.27,
|
| 145 |
+
"learning_rate": 1.716403083362841e-05,
|
| 146 |
+
"loss": 1.655,
|
| 147 |
+
"step": 1150
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 0.28,
|
| 151 |
+
"learning_rate": 1.6895148692468128e-05,
|
| 152 |
+
"loss": 1.6471,
|
| 153 |
+
"step": 1200
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 0.29,
|
| 157 |
+
"learning_rate": 1.6616408327917138e-05,
|
| 158 |
+
"loss": 1.6354,
|
| 159 |
+
"step": 1250
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.3,
|
| 163 |
+
"learning_rate": 1.632820826434442e-05,
|
| 164 |
+
"loss": 1.6324,
|
| 165 |
+
"step": 1300
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 0.32,
|
| 169 |
+
"learning_rate": 1.6030960550965252e-05,
|
| 170 |
+
"loss": 1.6249,
|
| 171 |
+
"step": 1350
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.33,
|
| 175 |
+
"learning_rate": 1.572509017272072e-05,
|
| 176 |
+
"loss": 1.62,
|
| 177 |
+
"step": 1400
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.34,
|
| 181 |
+
"learning_rate": 1.5411034442662632e-05,
|
| 182 |
+
"loss": 1.6093,
|
| 183 |
+
"step": 1450
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 0.35,
|
| 187 |
+
"learning_rate": 1.508924237671248e-05,
|
| 188 |
+
"loss": 1.5981,
|
| 189 |
+
"step": 1500
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 0.36,
|
| 193 |
+
"learning_rate": 1.4760174051688485e-05,
|
| 194 |
+
"loss": 1.6053,
|
| 195 |
+
"step": 1550
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 0.37,
|
| 199 |
+
"learning_rate": 1.4424299947518423e-05,
|
| 200 |
+
"loss": 1.6095,
|
| 201 |
+
"step": 1600
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 0.39,
|
| 205 |
+
"learning_rate": 1.4082100274578854e-05,
|
| 206 |
+
"loss": 1.5971,
|
| 207 |
+
"step": 1650
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 0.4,
|
| 211 |
+
"learning_rate": 1.3734064287122381e-05,
|
| 212 |
+
"loss": 1.5827,
|
| 213 |
+
"step": 1700
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.41,
|
| 217 |
+
"learning_rate": 1.3380689583774554e-05,
|
| 218 |
+
"loss": 1.583,
|
| 219 |
+
"step": 1750
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.42,
|
| 223 |
+
"learning_rate": 1.3022481396100574e-05,
|
| 224 |
+
"loss": 1.5648,
|
| 225 |
+
"step": 1800
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 0.43,
|
| 229 |
+
"learning_rate": 1.265995186625894e-05,
|
| 230 |
+
"loss": 1.5692,
|
| 231 |
+
"step": 1850
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 0.44,
|
| 235 |
+
"learning_rate": 1.229361931477474e-05,
|
| 236 |
+
"loss": 1.5601,
|
| 237 |
+
"step": 1900
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 0.46,
|
| 241 |
+
"learning_rate": 1.1924007499479602e-05,
|
| 242 |
+
"loss": 1.5657,
|
| 243 |
+
"step": 1950
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 0.47,
|
| 247 |
+
"learning_rate": 1.1551644866677654e-05,
|
| 248 |
+
"loss": 1.5641,
|
| 249 |
+
"step": 2000
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 0.48,
|
| 253 |
+
"learning_rate": 1.1177063795608305e-05,
|
| 254 |
+
"loss": 1.5558,
|
| 255 |
+
"step": 2050
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.49,
|
| 259 |
+
"learning_rate": 1.0800799837285943e-05,
|
| 260 |
+
"loss": 1.5645,
|
| 261 |
+
"step": 2100
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.5,
|
| 265 |
+
"learning_rate": 1.0423390948804808e-05,
|
| 266 |
+
"loss": 1.5462,
|
| 267 |
+
"step": 2150
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 0.51,
|
| 271 |
+
"learning_rate": 1.0045376724203873e-05,
|
| 272 |
+
"loss": 1.5484,
|
| 273 |
+
"step": 2200
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 0.53,
|
| 277 |
+
"learning_rate": 9.667297622991301e-06,
|
| 278 |
+
"loss": 1.5371,
|
| 279 |
+
"step": 2250
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 0.54,
|
| 283 |
+
"learning_rate": 9.289694197431486e-06,
|
| 284 |
+
"loss": 1.5283,
|
| 285 |
+
"step": 2300
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 0.55,
|
| 289 |
+
"learning_rate": 8.913106319699537e-06,
|
| 290 |
+
"loss": 1.5323,
|
| 291 |
+
"step": 2350
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 0.56,
|
| 295 |
+
"learning_rate": 8.538072410008054e-06,
|
| 296 |
+
"loss": 1.5344,
|
| 297 |
+
"step": 2400
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.57,
|
| 301 |
+
"learning_rate": 8.16512866680985e-06,
|
| 302 |
+
"loss": 1.5305,
|
| 303 |
+
"step": 2450
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.58,
|
| 307 |
+
"learning_rate": 7.794808300177196e-06,
|
| 308 |
+
"loss": 1.5403,
|
| 309 |
+
"step": 2500
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 0.6,
|
| 313 |
+
"learning_rate": 7.427640769453647e-06,
|
| 314 |
+
"loss": 1.5241,
|
| 315 |
+
"step": 2550
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 0.61,
|
| 319 |
+
"learning_rate": 7.064151026268395e-06,
|
| 320 |
+
"loss": 1.5347,
|
| 321 |
+
"step": 2600
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 0.62,
|
| 325 |
+
"learning_rate": 6.704858763995493e-06,
|
| 326 |
+
"loss": 1.5308,
|
| 327 |
+
"step": 2650
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 0.63,
|
| 331 |
+
"learning_rate": 6.350277674730938e-06,
|
| 332 |
+
"loss": 1.525,
|
| 333 |
+
"step": 2700
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 0.64,
|
| 337 |
+
"learning_rate": 6.0009147148499936e-06,
|
| 338 |
+
"loss": 1.5206,
|
| 339 |
+
"step": 2750
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.65,
|
| 343 |
+
"learning_rate": 5.657269380194827e-06,
|
| 344 |
+
"loss": 1.5029,
|
| 345 |
+
"step": 2800
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.67,
|
| 349 |
+
"learning_rate": 5.319832991928664e-06,
|
| 350 |
+
"loss": 1.516,
|
| 351 |
+
"step": 2850
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 0.68,
|
| 355 |
+
"learning_rate": 4.989087994077596e-06,
|
| 356 |
+
"loss": 1.5273,
|
| 357 |
+
"step": 2900
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 0.69,
|
| 361 |
+
"learning_rate": 4.665507263764299e-06,
|
| 362 |
+
"loss": 1.5062,
|
| 363 |
+
"step": 2950
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 0.7,
|
| 367 |
+
"learning_rate": 4.349553435119907e-06,
|
| 368 |
+
"loss": 1.5154,
|
| 369 |
+
"step": 3000
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 0.71,
|
| 373 |
+
"learning_rate": 4.041678237840601e-06,
|
| 374 |
+
"loss": 1.5018,
|
| 375 |
+
"step": 3050
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 0.72,
|
| 379 |
+
"learning_rate": 3.742321851334625e-06,
|
| 380 |
+
"loss": 1.5079,
|
| 381 |
+
"step": 3100
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.74,
|
| 385 |
+
"learning_rate": 3.4519122753831635e-06,
|
| 386 |
+
"loss": 1.5034,
|
| 387 |
+
"step": 3150
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.75,
|
| 391 |
+
"learning_rate": 3.170864718214822e-06,
|
| 392 |
+
"loss": 1.4912,
|
| 393 |
+
"step": 3200
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 0.76,
|
| 397 |
+
"learning_rate": 2.8995810028685947e-06,
|
| 398 |
+
"loss": 1.507,
|
| 399 |
+
"step": 3250
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 0.77,
|
| 403 |
+
"learning_rate": 2.638448992694124e-06,
|
| 404 |
+
"loss": 1.5073,
|
| 405 |
+
"step": 3300
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 0.78,
|
| 409 |
+
"learning_rate": 2.3878420368105706e-06,
|
| 410 |
+
"loss": 1.5077,
|
| 411 |
+
"step": 3350
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 0.79,
|
| 415 |
+
"learning_rate": 2.148118436316944e-06,
|
| 416 |
+
"loss": 1.4956,
|
| 417 |
+
"step": 3400
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 0.81,
|
| 421 |
+
"learning_rate": 1.9196209320171176e-06,
|
| 422 |
+
"loss": 1.4851,
|
| 423 |
+
"step": 3450
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.82,
|
| 427 |
+
"learning_rate": 1.7026762143919072e-06,
|
| 428 |
+
"loss": 1.5002,
|
| 429 |
+
"step": 3500
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.83,
|
| 433 |
+
"learning_rate": 1.4975944565188094e-06,
|
| 434 |
+
"loss": 1.4939,
|
| 435 |
+
"step": 3550
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 0.84,
|
| 439 |
+
"learning_rate": 1.3046688706072563e-06,
|
| 440 |
+
"loss": 1.4976,
|
| 441 |
+
"step": 3600
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 0.85,
|
| 445 |
+
"learning_rate": 1.1241752887833635e-06,
|
| 446 |
+
"loss": 1.4902,
|
| 447 |
+
"step": 3650
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 0.86,
|
| 451 |
+
"learning_rate": 9.563717687235586e-07,
|
| 452 |
+
"loss": 1.4959,
|
| 453 |
+
"step": 3700
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 0.88,
|
| 457 |
+
"learning_rate": 8.014982247009473e-07,
|
| 458 |
+
"loss": 1.4928,
|
| 459 |
+
"step": 3750
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 0.89,
|
| 463 |
+
"learning_rate": 6.597760845718881e-07,
|
| 464 |
+
"loss": 1.4905,
|
| 465 |
+
"step": 3800
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.9,
|
| 469 |
+
"learning_rate": 5.314079731932398e-07,
|
| 470 |
+
"loss": 1.5015,
|
| 471 |
+
"step": 3850
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.91,
|
| 475 |
+
"learning_rate": 4.165774227228492e-07,
|
| 476 |
+
"loss": 1.4831,
|
| 477 |
+
"step": 3900
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 0.92,
|
| 481 |
+
"learning_rate": 3.1544861021753137e-07,
|
| 482 |
+
"loss": 1.4946,
|
| 483 |
+
"step": 3950
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 0.93,
|
| 487 |
+
"learning_rate": 2.2816612290366358e-07,
|
| 488 |
+
"loss": 1.4841,
|
| 489 |
+
"step": 4000
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 0.95,
|
| 493 |
+
"learning_rate": 1.5485475145602614e-07,
|
| 494 |
+
"loss": 1.5016,
|
| 495 |
+
"step": 4050
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 0.96,
|
| 499 |
+
"learning_rate": 9.561931158041937e-08,
|
| 500 |
+
"loss": 1.4967,
|
| 501 |
+
"step": 4100
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 0.97,
|
| 505 |
+
"learning_rate": 5.0544494155169155e-08,
|
| 506 |
+
"loss": 1.4907,
|
| 507 |
+
"step": 4150
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.98,
|
| 511 |
+
"learning_rate": 1.9694744145755117e-08,
|
| 512 |
+
"loss": 1.4911,
|
| 513 |
+
"step": 4200
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.99,
|
| 517 |
+
"learning_rate": 3.1141684657065573e-09,
|
| 518 |
+
"loss": 1.4964,
|
| 519 |
+
"step": 4250
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 1.0,
|
| 523 |
+
"step": 4283,
|
| 524 |
+
"total_flos": 3.7850139050429645e+17,
|
| 525 |
+
"train_loss": 1.628265750483322,
|
| 526 |
+
"train_runtime": 14247.8723,
|
| 527 |
+
"train_samples_per_second": 14.428,
|
| 528 |
+
"train_steps_per_second": 0.301
|
| 529 |
+
}
|
| 530 |
+
],
|
| 531 |
+
"logging_steps": 50,
|
| 532 |
+
"max_steps": 4283,
|
| 533 |
+
"num_input_tokens_seen": 0,
|
| 534 |
+
"num_train_epochs": 1,
|
| 535 |
+
"save_steps": 24000,
|
| 536 |
+
"total_flos": 3.7850139050429645e+17,
|
| 537 |
+
"train_batch_size": 8,
|
| 538 |
+
"trial_name": null,
|
| 539 |
+
"trial_params": null
|
| 540 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2478cee026e3e556b7b13e44b58b2447acda78b50f44f993444297ed1a74b4cb
|
| 3 |
+
size 5947
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|