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 +366 -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_reasoning-merged-4ep",
|
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": 151646,
|
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:edd31310b237533cc56559a926fc3e3f4db8e098f6d97bb7608f50953e0ce55b
|
3 |
+
size 2050524576
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:06739df7f61af3c0df008bff0dd27d1144a1083f6b3ae366c3352409942a3141
|
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 +1,366 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.9992900248491303,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 2816,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.04,
|
13 |
+
"learning_rate": 1.1764705882352942e-05,
|
14 |
+
"loss": 2.8037,
|
15 |
+
"step": 50
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 0.07,
|
19 |
+
"learning_rate": 1.999851133118102e-05,
|
20 |
+
"loss": 2.4343,
|
21 |
+
"step": 100
|
22 |
+
},
|
23 |
+
{
|
24 |
+
"epoch": 0.11,
|
25 |
+
"learning_rate": 1.9972058436024328e-05,
|
26 |
+
"loss": 2.233,
|
27 |
+
"step": 150
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 0.14,
|
31 |
+
"learning_rate": 1.9912624721856506e-05,
|
32 |
+
"loss": 2.1259,
|
33 |
+
"step": 200
|
34 |
+
},
|
35 |
+
{
|
36 |
+
"epoch": 0.18,
|
37 |
+
"learning_rate": 1.9820406755172106e-05,
|
38 |
+
"loss": 2.0545,
|
39 |
+
"step": 250
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 0.21,
|
43 |
+
"learning_rate": 1.9695709530580642e-05,
|
44 |
+
"loss": 1.9909,
|
45 |
+
"step": 300
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"epoch": 0.25,
|
49 |
+
"learning_rate": 1.9538945462090903e-05,
|
50 |
+
"loss": 1.9676,
|
51 |
+
"step": 350
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.28,
|
55 |
+
"learning_rate": 1.9350633019124565e-05,
|
56 |
+
"loss": 1.9318,
|
57 |
+
"step": 400
|
58 |
+
},
|
59 |
+
{
|
60 |
+
"epoch": 0.32,
|
61 |
+
"learning_rate": 1.913139501177033e-05,
|
62 |
+
"loss": 1.897,
|
63 |
+
"step": 450
|
64 |
+
},
|
65 |
+
{
|
66 |
+
"epoch": 0.35,
|
67 |
+
"learning_rate": 1.888195653094972e-05,
|
68 |
+
"loss": 1.8821,
|
69 |
+
"step": 500
|
70 |
+
},
|
71 |
+
{
|
72 |
+
"epoch": 0.39,
|
73 |
+
"learning_rate": 1.860314255030716e-05,
|
74 |
+
"loss": 1.8568,
|
75 |
+
"step": 550
|
76 |
+
},
|
77 |
+
{
|
78 |
+
"epoch": 0.43,
|
79 |
+
"learning_rate": 1.8295875197755593e-05,
|
80 |
+
"loss": 1.8416,
|
81 |
+
"step": 600
|
82 |
+
},
|
83 |
+
{
|
84 |
+
"epoch": 0.46,
|
85 |
+
"learning_rate": 1.796117070570155e-05,
|
86 |
+
"loss": 1.8278,
|
87 |
+
"step": 650
|
88 |
+
},
|
89 |
+
{
|
90 |
+
"epoch": 0.5,
|
91 |
+
"learning_rate": 1.7600136050036265e-05,
|
92 |
+
"loss": 1.8107,
|
93 |
+
"step": 700
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.53,
|
97 |
+
"learning_rate": 1.7213965289008755e-05,
|
98 |
+
"loss": 1.799,
|
99 |
+
"step": 750
|
100 |
+
},
|
101 |
+
{
|
102 |
+
"epoch": 0.57,
|
103 |
+
"learning_rate": 1.6803935614089426e-05,
|
104 |
+
"loss": 1.7788,
|
105 |
+
"step": 800
|
106 |
+
},
|
107 |
+
{
|
108 |
+
"epoch": 0.6,
|
109 |
+
"learning_rate": 1.637140312588523e-05,
|
110 |
+
"loss": 1.7629,
|
111 |
+
"step": 850
|
112 |
+
},
|
113 |
+
{
|
114 |
+
"epoch": 0.64,
|
115 |
+
"learning_rate": 1.5917798349076846e-05,
|
116 |
+
"loss": 1.7656,
|
117 |
+
"step": 900
|
118 |
+
},
|
119 |
+
{
|
120 |
+
"epoch": 0.67,
|
121 |
+
"learning_rate": 1.5444621501211386e-05,
|
122 |
+
"loss": 1.7521,
|
123 |
+
"step": 950
|
124 |
+
},
|
125 |
+
{
|
126 |
+
"epoch": 0.71,
|
127 |
+
"learning_rate": 1.4953437530998262e-05,
|
128 |
+
"loss": 1.738,
|
129 |
+
"step": 1000
|
130 |
+
},
|
131 |
+
{
|
132 |
+
"epoch": 0.75,
|
133 |
+
"learning_rate": 1.4445870942518226e-05,
|
134 |
+
"loss": 1.729,
|
135 |
+
"step": 1050
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.78,
|
139 |
+
"learning_rate": 1.3923600422463505e-05,
|
140 |
+
"loss": 1.7321,
|
141 |
+
"step": 1100
|
142 |
+
},
|
143 |
+
{
|
144 |
+
"epoch": 0.82,
|
145 |
+
"learning_rate": 1.3388353288178595e-05,
|
146 |
+
"loss": 1.7203,
|
147 |
+
"step": 1150
|
148 |
+
},
|
149 |
+
{
|
150 |
+
"epoch": 0.85,
|
151 |
+
"learning_rate": 1.284189977486371e-05,
|
152 |
+
"loss": 1.7134,
|
153 |
+
"step": 1200
|
154 |
+
},
|
155 |
+
{
|
156 |
+
"epoch": 0.89,
|
157 |
+
"learning_rate": 1.228604718083506e-05,
|
158 |
+
"loss": 1.7147,
|
159 |
+
"step": 1250
|
160 |
+
},
|
161 |
+
{
|
162 |
+
"epoch": 0.92,
|
163 |
+
"learning_rate": 1.1722633890205434e-05,
|
164 |
+
"loss": 1.6945,
|
165 |
+
"step": 1300
|
166 |
+
},
|
167 |
+
{
|
168 |
+
"epoch": 0.96,
|
169 |
+
"learning_rate": 1.1153523292753974e-05,
|
170 |
+
"loss": 1.6996,
|
171 |
+
"step": 1350
|
172 |
+
},
|
173 |
+
{
|
174 |
+
"epoch": 0.99,
|
175 |
+
"learning_rate": 1.0580597621094166e-05,
|
176 |
+
"loss": 1.6959,
|
177 |
+
"step": 1400
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 1.03,
|
181 |
+
"learning_rate": 1.0005751725522469e-05,
|
182 |
+
"loss": 1.6188,
|
183 |
+
"step": 1450
|
184 |
+
},
|
185 |
+
{
|
186 |
+
"epoch": 1.06,
|
187 |
+
"learning_rate": 9.430886807136206e-06,
|
188 |
+
"loss": 1.6012,
|
189 |
+
"step": 1500
|
190 |
+
},
|
191 |
+
{
|
192 |
+
"epoch": 1.1,
|
193 |
+
"learning_rate": 8.857904129947295e-06,
|
194 |
+
"loss": 1.6043,
|
195 |
+
"step": 1550
|
196 |
+
},
|
197 |
+
{
|
198 |
+
"epoch": 1.14,
|
199 |
+
"learning_rate": 8.288698732787898e-06,
|
200 |
+
"loss": 1.602,
|
201 |
+
"step": 1600
|
202 |
+
},
|
203 |
+
{
|
204 |
+
"epoch": 1.17,
|
205 |
+
"learning_rate": 7.725153161804767e-06,
|
206 |
+
"loss": 1.604,
|
207 |
+
"step": 1650
|
208 |
+
},
|
209 |
+
{
|
210 |
+
"epoch": 1.21,
|
211 |
+
"learning_rate": 7.169131244270906e-06,
|
212 |
+
"loss": 1.6012,
|
213 |
+
"step": 1700
|
214 |
+
},
|
215 |
+
{
|
216 |
+
"epoch": 1.24,
|
217 |
+
"learning_rate": 6.6224719243066386e-06,
|
218 |
+
"loss": 1.5921,
|
219 |
+
"step": 1750
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 1.28,
|
223 |
+
"learning_rate": 6.086983180897257e-06,
|
224 |
+
"loss": 1.6,
|
225 |
+
"step": 1800
|
226 |
+
},
|
227 |
+
{
|
228 |
+
"epoch": 1.31,
|
229 |
+
"learning_rate": 5.564436048322415e-06,
|
230 |
+
"loss": 1.5887,
|
231 |
+
"step": 1850
|
232 |
+
},
|
233 |
+
{
|
234 |
+
"epoch": 1.35,
|
235 |
+
"learning_rate": 5.056558758773566e-06,
|
236 |
+
"loss": 1.59,
|
237 |
+
"step": 1900
|
238 |
+
},
|
239 |
+
{
|
240 |
+
"epoch": 1.38,
|
241 |
+
"learning_rate": 4.56503102653177e-06,
|
242 |
+
"loss": 1.5835,
|
243 |
+
"step": 1950
|
244 |
+
},
|
245 |
+
{
|
246 |
+
"epoch": 1.42,
|
247 |
+
"learning_rate": 4.091478492609857e-06,
|
248 |
+
"loss": 1.5847,
|
249 |
+
"step": 2000
|
250 |
+
},
|
251 |
+
{
|
252 |
+
"epoch": 1.46,
|
253 |
+
"learning_rate": 3.637467348232414e-06,
|
254 |
+
"loss": 1.5934,
|
255 |
+
"step": 2050
|
256 |
+
},
|
257 |
+
{
|
258 |
+
"epoch": 1.49,
|
259 |
+
"learning_rate": 3.2044991549353832e-06,
|
260 |
+
"loss": 1.588,
|
261 |
+
"step": 2100
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 1.53,
|
265 |
+
"learning_rate": 2.7940058784169543e-06,
|
266 |
+
"loss": 1.5882,
|
267 |
+
"step": 2150
|
268 |
+
},
|
269 |
+
{
|
270 |
+
"epoch": 1.56,
|
271 |
+
"learning_rate": 2.4073451525643566e-06,
|
272 |
+
"loss": 1.5791,
|
273 |
+
"step": 2200
|
274 |
+
},
|
275 |
+
{
|
276 |
+
"epoch": 1.6,
|
277 |
+
"learning_rate": 2.045795789319962e-06,
|
278 |
+
"loss": 1.5802,
|
279 |
+
"step": 2250
|
280 |
+
},
|
281 |
+
{
|
282 |
+
"epoch": 1.63,
|
283 |
+
"learning_rate": 1.710553549237043e-06,
|
284 |
+
"loss": 1.5806,
|
285 |
+
"step": 2300
|
286 |
+
},
|
287 |
+
{
|
288 |
+
"epoch": 1.67,
|
289 |
+
"learning_rate": 1.402727186713303e-06,
|
290 |
+
"loss": 1.5816,
|
291 |
+
"step": 2350
|
292 |
+
},
|
293 |
+
{
|
294 |
+
"epoch": 1.7,
|
295 |
+
"learning_rate": 1.1233347829818563e-06,
|
296 |
+
"loss": 1.5822,
|
297 |
+
"step": 2400
|
298 |
+
},
|
299 |
+
{
|
300 |
+
"epoch": 1.74,
|
301 |
+
"learning_rate": 8.733003789876726e-07,
|
302 |
+
"loss": 1.5751,
|
303 |
+
"step": 2450
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"epoch": 1.77,
|
307 |
+
"learning_rate": 6.534509192856453e-07,
|
308 |
+
"loss": 1.5708,
|
309 |
+
"step": 2500
|
310 |
+
},
|
311 |
+
{
|
312 |
+
"epoch": 1.81,
|
313 |
+
"learning_rate": 4.645135170677595e-07,
|
314 |
+
"loss": 1.5777,
|
315 |
+
"step": 2550
|
316 |
+
},
|
317 |
+
{
|
318 |
+
"epoch": 1.85,
|
319 |
+
"learning_rate": 3.0711304936486664e-07,
|
320 |
+
"loss": 1.5673,
|
321 |
+
"step": 2600
|
322 |
+
},
|
323 |
+
{
|
324 |
+
"epoch": 1.88,
|
325 |
+
"learning_rate": 1.8177009037645633e-07,
|
326 |
+
"loss": 1.5766,
|
327 |
+
"step": 2650
|
328 |
+
},
|
329 |
+
{
|
330 |
+
"epoch": 1.92,
|
331 |
+
"learning_rate": 8.889918976358602e-08,
|
332 |
+
"loss": 1.5677,
|
333 |
+
"step": 2700
|
334 |
+
},
|
335 |
+
{
|
336 |
+
"epoch": 1.95,
|
337 |
+
"learning_rate": 2.8807501599226185e-08,
|
338 |
+
"loss": 1.5849,
|
339 |
+
"step": 2750
|
340 |
+
},
|
341 |
+
{
|
342 |
+
"epoch": 1.99,
|
343 |
+
"learning_rate": 1.6937685105011813e-09,
|
344 |
+
"loss": 1.5809,
|
345 |
+
"step": 2800
|
346 |
+
},
|
347 |
+
{
|
348 |
+
"epoch": 2.0,
|
349 |
+
"step": 2816,
|
350 |
+
"total_flos": 2.1906737398074573e+17,
|
351 |
+
"train_loss": 1.738261958414858,
|
352 |
+
"train_runtime": 14007.5678,
|
353 |
+
"train_samples_per_second": 16.084,
|
354 |
+
"train_steps_per_second": 0.201
|
355 |
+
}
|
356 |
+
],
|
357 |
+
"logging_steps": 50,
|
358 |
+
"max_steps": 2816,
|
359 |
+
"num_input_tokens_seen": 0,
|
360 |
+
"num_train_epochs": 2,
|
361 |
+
"save_steps": 24000,
|
362 |
+
"total_flos": 2.1906737398074573e+17,
|
363 |
+
"train_batch_size": 8,
|
364 |
+
"trial_name": null,
|
365 |
+
"trial_params": null
|
366 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ce6c87b0b3ba0cd7fb0d20932fa66e9ed29def2e45aa1e7458c852c456a54add
|
3 |
+
size 5947
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|