Upload folder using huggingface_hub
Browse files- added_tokens.json +24 -0
- config.json +29 -0
- generation_config.json +7 -0
- merges.txt +0 -0
- model-00001-of-00004.safetensors +3 -0
- model-00002-of-00004.safetensors +3 -0
- model-00003-of-00004.safetensors +3 -0
- model-00004-of-00004.safetensors +3 -0
- model.safetensors.index.json +346 -0
- special_tokens_map.json +31 -0
- tokenizer.json +0 -0
- tokenizer_config.json +207 -0
- trainer_state.json +2706 -0
- training_args.bin +3 -0
- vocab.json +0 -0
added_tokens.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"</tool_call>": 151658,
|
3 |
+
"<tool_call>": 151657,
|
4 |
+
"<|box_end|>": 151649,
|
5 |
+
"<|box_start|>": 151648,
|
6 |
+
"<|endoftext|>": 151643,
|
7 |
+
"<|file_sep|>": 151664,
|
8 |
+
"<|fim_middle|>": 151660,
|
9 |
+
"<|fim_pad|>": 151662,
|
10 |
+
"<|fim_prefix|>": 151659,
|
11 |
+
"<|fim_suffix|>": 151661,
|
12 |
+
"<|im_end|>": 151645,
|
13 |
+
"<|im_start|>": 151644,
|
14 |
+
"<|image_pad|>": 151655,
|
15 |
+
"<|object_ref_end|>": 151647,
|
16 |
+
"<|object_ref_start|>": 151646,
|
17 |
+
"<|quad_end|>": 151651,
|
18 |
+
"<|quad_start|>": 151650,
|
19 |
+
"<|repo_name|>": 151663,
|
20 |
+
"<|video_pad|>": 151656,
|
21 |
+
"<|vision_end|>": 151653,
|
22 |
+
"<|vision_pad|>": 151654,
|
23 |
+
"<|vision_start|>": 151652
|
24 |
+
}
|
config.json
ADDED
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "Qwen/Qwen2.5-7B",
|
3 |
+
"architectures": [
|
4 |
+
"Qwen2ForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_dropout": 0.0,
|
7 |
+
"eos_token_id": 151643,
|
8 |
+
"hidden_act": "silu",
|
9 |
+
"hidden_size": 3584,
|
10 |
+
"initializer_range": 0.02,
|
11 |
+
"intermediate_size": 18944,
|
12 |
+
"max_position_embeddings": 131072,
|
13 |
+
"max_window_layers": 28,
|
14 |
+
"model_type": "qwen2",
|
15 |
+
"num_attention_heads": 28,
|
16 |
+
"num_hidden_layers": 28,
|
17 |
+
"num_key_value_heads": 4,
|
18 |
+
"rms_norm_eps": 1e-06,
|
19 |
+
"rope_scaling": null,
|
20 |
+
"rope_theta": 1000000.0,
|
21 |
+
"sliding_window": null,
|
22 |
+
"tie_word_embeddings": false,
|
23 |
+
"torch_dtype": "bfloat16",
|
24 |
+
"transformers_version": "4.45.1",
|
25 |
+
"use_cache": false,
|
26 |
+
"use_mrope": false,
|
27 |
+
"use_sliding_window": false,
|
28 |
+
"vocab_size": 152064
|
29 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token_id": 151643,
|
3 |
+
"do_sample": true,
|
4 |
+
"eos_token_id": 151643,
|
5 |
+
"max_new_tokens": 2048,
|
6 |
+
"transformers_version": "4.45.1"
|
7 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
model-00001-of-00004.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c76fa96a7451ac044ab0bbfec547783bde3a1aca86cb1357d390149c29ea2527
|
3 |
+
size 4877660776
|
model-00002-of-00004.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a3991f71374e83952e55049260e2933a6c78c337e78790ac798528b5a9d49834
|
3 |
+
size 4932751008
|
model-00003-of-00004.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a9cfb2a1a963db89a6841e6d3415b766076e4f59ae068d788fcdb3bcd713ecc4
|
3 |
+
size 4330865200
|
model-00004-of-00004.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b8aa26a04efea407b900b2ccd8c14eaaa71adb68cbf77a28fe6678e39014a68d
|
3 |
+
size 1089994880
|
model.safetensors.index.json
ADDED
@@ -0,0 +1,346 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"metadata": {
|
3 |
+
"total_size": 15231233024
|
4 |
+
},
|
5 |
+
"weight_map": {
|
6 |
+
"lm_head.weight": "model-00004-of-00004.safetensors",
|
7 |
+
"model.embed_tokens.weight": "model-00001-of-00004.safetensors",
|
8 |
+
"model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
9 |
+
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
10 |
+
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
11 |
+
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
12 |
+
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
13 |
+
"model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
14 |
+
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
15 |
+
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
16 |
+
"model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
17 |
+
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
18 |
+
"model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
19 |
+
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
20 |
+
"model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
21 |
+
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
22 |
+
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
23 |
+
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
24 |
+
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
25 |
+
"model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
26 |
+
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
27 |
+
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
28 |
+
"model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
29 |
+
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
30 |
+
"model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
31 |
+
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
32 |
+
"model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
33 |
+
"model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
34 |
+
"model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
35 |
+
"model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
36 |
+
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
37 |
+
"model.layers.10.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
38 |
+
"model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
39 |
+
"model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
40 |
+
"model.layers.10.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
41 |
+
"model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
42 |
+
"model.layers.10.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
43 |
+
"model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
44 |
+
"model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
45 |
+
"model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
46 |
+
"model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
47 |
+
"model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
48 |
+
"model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
49 |
+
"model.layers.11.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
50 |
+
"model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
51 |
+
"model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
52 |
+
"model.layers.11.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
53 |
+
"model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
54 |
+
"model.layers.11.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
55 |
+
"model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
56 |
+
"model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
57 |
+
"model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
58 |
+
"model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
59 |
+
"model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
60 |
+
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
61 |
+
"model.layers.12.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
62 |
+
"model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
63 |
+
"model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
64 |
+
"model.layers.12.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
65 |
+
"model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
66 |
+
"model.layers.12.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
67 |
+
"model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
68 |
+
"model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
69 |
+
"model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
70 |
+
"model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
71 |
+
"model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
72 |
+
"model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
73 |
+
"model.layers.13.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
74 |
+
"model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
75 |
+
"model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
76 |
+
"model.layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
77 |
+
"model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
78 |
+
"model.layers.13.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
79 |
+
"model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
80 |
+
"model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
81 |
+
"model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
82 |
+
"model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
83 |
+
"model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
84 |
+
"model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
85 |
+
"model.layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
86 |
+
"model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
87 |
+
"model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
88 |
+
"model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
89 |
+
"model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
90 |
+
"model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
91 |
+
"model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
92 |
+
"model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
93 |
+
"model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
94 |
+
"model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
95 |
+
"model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
96 |
+
"model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
97 |
+
"model.layers.15.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
98 |
+
"model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
99 |
+
"model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
100 |
+
"model.layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
101 |
+
"model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
102 |
+
"model.layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
103 |
+
"model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
104 |
+
"model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
105 |
+
"model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
106 |
+
"model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
107 |
+
"model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
108 |
+
"model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
109 |
+
"model.layers.16.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
110 |
+
"model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
111 |
+
"model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
112 |
+
"model.layers.16.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
113 |
+
"model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
114 |
+
"model.layers.16.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
115 |
+
"model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
116 |
+
"model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
117 |
+
"model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
118 |
+
"model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
119 |
+
"model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
120 |
+
"model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
121 |
+
"model.layers.17.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
122 |
+
"model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
123 |
+
"model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
124 |
+
"model.layers.17.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
125 |
+
"model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
126 |
+
"model.layers.17.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
127 |
+
"model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
128 |
+
"model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
129 |
+
"model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
130 |
+
"model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
131 |
+
"model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
132 |
+
"model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
133 |
+
"model.layers.18.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
134 |
+
"model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
135 |
+
"model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
136 |
+
"model.layers.18.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
137 |
+
"model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
138 |
+
"model.layers.18.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
139 |
+
"model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
140 |
+
"model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
141 |
+
"model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
142 |
+
"model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
143 |
+
"model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
144 |
+
"model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
145 |
+
"model.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
146 |
+
"model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
147 |
+
"model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
148 |
+
"model.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
149 |
+
"model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
150 |
+
"model.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
151 |
+
"model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
152 |
+
"model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
153 |
+
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
154 |
+
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
155 |
+
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
156 |
+
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
157 |
+
"model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
158 |
+
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
159 |
+
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
160 |
+
"model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
161 |
+
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
162 |
+
"model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
163 |
+
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
164 |
+
"model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
165 |
+
"model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
166 |
+
"model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
167 |
+
"model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
168 |
+
"model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
169 |
+
"model.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
170 |
+
"model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
171 |
+
"model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
172 |
+
"model.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
173 |
+
"model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
174 |
+
"model.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
175 |
+
"model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
176 |
+
"model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
177 |
+
"model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
178 |
+
"model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
179 |
+
"model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
180 |
+
"model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
181 |
+
"model.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
182 |
+
"model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
183 |
+
"model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
184 |
+
"model.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
185 |
+
"model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
186 |
+
"model.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
187 |
+
"model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
188 |
+
"model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
189 |
+
"model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
190 |
+
"model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
191 |
+
"model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
192 |
+
"model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
193 |
+
"model.layers.22.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
194 |
+
"model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
195 |
+
"model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
196 |
+
"model.layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
197 |
+
"model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
198 |
+
"model.layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
199 |
+
"model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
200 |
+
"model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
201 |
+
"model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
202 |
+
"model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
203 |
+
"model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
204 |
+
"model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
205 |
+
"model.layers.23.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
206 |
+
"model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
207 |
+
"model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
208 |
+
"model.layers.23.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
209 |
+
"model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
210 |
+
"model.layers.23.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
211 |
+
"model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
212 |
+
"model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
213 |
+
"model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
214 |
+
"model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
215 |
+
"model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
216 |
+
"model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
217 |
+
"model.layers.24.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
218 |
+
"model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
219 |
+
"model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
220 |
+
"model.layers.24.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
221 |
+
"model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
222 |
+
"model.layers.24.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
223 |
+
"model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
224 |
+
"model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
225 |
+
"model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
226 |
+
"model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
227 |
+
"model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
228 |
+
"model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
229 |
+
"model.layers.25.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
230 |
+
"model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
231 |
+
"model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
232 |
+
"model.layers.25.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
233 |
+
"model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
234 |
+
"model.layers.25.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
235 |
+
"model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
236 |
+
"model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
237 |
+
"model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
238 |
+
"model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
239 |
+
"model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
240 |
+
"model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
241 |
+
"model.layers.26.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
242 |
+
"model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
243 |
+
"model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
244 |
+
"model.layers.26.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
245 |
+
"model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
246 |
+
"model.layers.26.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
247 |
+
"model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
248 |
+
"model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
249 |
+
"model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
250 |
+
"model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
251 |
+
"model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
252 |
+
"model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
253 |
+
"model.layers.27.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
254 |
+
"model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
255 |
+
"model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
256 |
+
"model.layers.27.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
257 |
+
"model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
258 |
+
"model.layers.27.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
259 |
+
"model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
260 |
+
"model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
261 |
+
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
262 |
+
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
263 |
+
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
264 |
+
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
265 |
+
"model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
266 |
+
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
267 |
+
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
268 |
+
"model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
269 |
+
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
270 |
+
"model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
271 |
+
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
272 |
+
"model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
273 |
+
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
274 |
+
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
275 |
+
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
276 |
+
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
277 |
+
"model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
278 |
+
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
279 |
+
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
280 |
+
"model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
281 |
+
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
282 |
+
"model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
283 |
+
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
284 |
+
"model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
285 |
+
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
286 |
+
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
287 |
+
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
288 |
+
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
289 |
+
"model.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
290 |
+
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
291 |
+
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
292 |
+
"model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
293 |
+
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
294 |
+
"model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
295 |
+
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
296 |
+
"model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
297 |
+
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
298 |
+
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
299 |
+
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
300 |
+
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
301 |
+
"model.layers.6.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
302 |
+
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
303 |
+
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
304 |
+
"model.layers.6.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
305 |
+
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
306 |
+
"model.layers.6.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
307 |
+
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
308 |
+
"model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
309 |
+
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
310 |
+
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
311 |
+
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
312 |
+
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
313 |
+
"model.layers.7.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
314 |
+
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
315 |
+
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
316 |
+
"model.layers.7.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
317 |
+
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
318 |
+
"model.layers.7.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
319 |
+
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
320 |
+
"model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
321 |
+
"model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
322 |
+
"model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
323 |
+
"model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
324 |
+
"model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
325 |
+
"model.layers.8.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
326 |
+
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
327 |
+
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
328 |
+
"model.layers.8.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
329 |
+
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
330 |
+
"model.layers.8.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
331 |
+
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
332 |
+
"model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
333 |
+
"model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
334 |
+
"model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
335 |
+
"model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
336 |
+
"model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
337 |
+
"model.layers.9.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
338 |
+
"model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
339 |
+
"model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
340 |
+
"model.layers.9.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
341 |
+
"model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
342 |
+
"model.layers.9.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
343 |
+
"model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
344 |
+
"model.norm.weight": "model-00003-of-00004.safetensors"
|
345 |
+
}
|
346 |
+
}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<|im_start|>",
|
4 |
+
"<|im_end|>",
|
5 |
+
"<|object_ref_start|>",
|
6 |
+
"<|object_ref_end|>",
|
7 |
+
"<|box_start|>",
|
8 |
+
"<|box_end|>",
|
9 |
+
"<|quad_start|>",
|
10 |
+
"<|quad_end|>",
|
11 |
+
"<|vision_start|>",
|
12 |
+
"<|vision_end|>",
|
13 |
+
"<|vision_pad|>",
|
14 |
+
"<|image_pad|>",
|
15 |
+
"<|video_pad|>"
|
16 |
+
],
|
17 |
+
"eos_token": {
|
18 |
+
"content": "<|endoftext|>",
|
19 |
+
"lstrip": false,
|
20 |
+
"normalized": false,
|
21 |
+
"rstrip": false,
|
22 |
+
"single_word": false
|
23 |
+
},
|
24 |
+
"pad_token": {
|
25 |
+
"content": "<|endoftext|>",
|
26 |
+
"lstrip": false,
|
27 |
+
"normalized": false,
|
28 |
+
"rstrip": false,
|
29 |
+
"single_word": false
|
30 |
+
}
|
31 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,207 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": false,
|
3 |
+
"add_prefix_space": false,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"151643": {
|
6 |
+
"content": "<|endoftext|>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
},
|
13 |
+
"151644": {
|
14 |
+
"content": "<|im_start|>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": false,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": true
|
20 |
+
},
|
21 |
+
"151645": {
|
22 |
+
"content": "<|im_end|>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": false,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false,
|
27 |
+
"special": true
|
28 |
+
},
|
29 |
+
"151646": {
|
30 |
+
"content": "<|object_ref_start|>",
|
31 |
+
"lstrip": false,
|
32 |
+
"normalized": false,
|
33 |
+
"rstrip": false,
|
34 |
+
"single_word": false,
|
35 |
+
"special": true
|
36 |
+
},
|
37 |
+
"151647": {
|
38 |
+
"content": "<|object_ref_end|>",
|
39 |
+
"lstrip": false,
|
40 |
+
"normalized": false,
|
41 |
+
"rstrip": false,
|
42 |
+
"single_word": false,
|
43 |
+
"special": true
|
44 |
+
},
|
45 |
+
"151648": {
|
46 |
+
"content": "<|box_start|>",
|
47 |
+
"lstrip": false,
|
48 |
+
"normalized": false,
|
49 |
+
"rstrip": false,
|
50 |
+
"single_word": false,
|
51 |
+
"special": true
|
52 |
+
},
|
53 |
+
"151649": {
|
54 |
+
"content": "<|box_end|>",
|
55 |
+
"lstrip": false,
|
56 |
+
"normalized": false,
|
57 |
+
"rstrip": false,
|
58 |
+
"single_word": false,
|
59 |
+
"special": true
|
60 |
+
},
|
61 |
+
"151650": {
|
62 |
+
"content": "<|quad_start|>",
|
63 |
+
"lstrip": false,
|
64 |
+
"normalized": false,
|
65 |
+
"rstrip": false,
|
66 |
+
"single_word": false,
|
67 |
+
"special": true
|
68 |
+
},
|
69 |
+
"151651": {
|
70 |
+
"content": "<|quad_end|>",
|
71 |
+
"lstrip": false,
|
72 |
+
"normalized": false,
|
73 |
+
"rstrip": false,
|
74 |
+
"single_word": false,
|
75 |
+
"special": true
|
76 |
+
},
|
77 |
+
"151652": {
|
78 |
+
"content": "<|vision_start|>",
|
79 |
+
"lstrip": false,
|
80 |
+
"normalized": false,
|
81 |
+
"rstrip": false,
|
82 |
+
"single_word": false,
|
83 |
+
"special": true
|
84 |
+
},
|
85 |
+
"151653": {
|
86 |
+
"content": "<|vision_end|>",
|
87 |
+
"lstrip": false,
|
88 |
+
"normalized": false,
|
89 |
+
"rstrip": false,
|
90 |
+
"single_word": false,
|
91 |
+
"special": true
|
92 |
+
},
|
93 |
+
"151654": {
|
94 |
+
"content": "<|vision_pad|>",
|
95 |
+
"lstrip": false,
|
96 |
+
"normalized": false,
|
97 |
+
"rstrip": false,
|
98 |
+
"single_word": false,
|
99 |
+
"special": true
|
100 |
+
},
|
101 |
+
"151655": {
|
102 |
+
"content": "<|image_pad|>",
|
103 |
+
"lstrip": false,
|
104 |
+
"normalized": false,
|
105 |
+
"rstrip": false,
|
106 |
+
"single_word": false,
|
107 |
+
"special": true
|
108 |
+
},
|
109 |
+
"151656": {
|
110 |
+
"content": "<|video_pad|>",
|
111 |
+
"lstrip": false,
|
112 |
+
"normalized": false,
|
113 |
+
"rstrip": false,
|
114 |
+
"single_word": false,
|
115 |
+
"special": true
|
116 |
+
},
|
117 |
+
"151657": {
|
118 |
+
"content": "<tool_call>",
|
119 |
+
"lstrip": false,
|
120 |
+
"normalized": false,
|
121 |
+
"rstrip": false,
|
122 |
+
"single_word": false,
|
123 |
+
"special": false
|
124 |
+
},
|
125 |
+
"151658": {
|
126 |
+
"content": "</tool_call>",
|
127 |
+
"lstrip": false,
|
128 |
+
"normalized": false,
|
129 |
+
"rstrip": false,
|
130 |
+
"single_word": false,
|
131 |
+
"special": false
|
132 |
+
},
|
133 |
+
"151659": {
|
134 |
+
"content": "<|fim_prefix|>",
|
135 |
+
"lstrip": false,
|
136 |
+
"normalized": false,
|
137 |
+
"rstrip": false,
|
138 |
+
"single_word": false,
|
139 |
+
"special": false
|
140 |
+
},
|
141 |
+
"151660": {
|
142 |
+
"content": "<|fim_middle|>",
|
143 |
+
"lstrip": false,
|
144 |
+
"normalized": false,
|
145 |
+
"rstrip": false,
|
146 |
+
"single_word": false,
|
147 |
+
"special": false
|
148 |
+
},
|
149 |
+
"151661": {
|
150 |
+
"content": "<|fim_suffix|>",
|
151 |
+
"lstrip": false,
|
152 |
+
"normalized": false,
|
153 |
+
"rstrip": false,
|
154 |
+
"single_word": false,
|
155 |
+
"special": false
|
156 |
+
},
|
157 |
+
"151662": {
|
158 |
+
"content": "<|fim_pad|>",
|
159 |
+
"lstrip": false,
|
160 |
+
"normalized": false,
|
161 |
+
"rstrip": false,
|
162 |
+
"single_word": false,
|
163 |
+
"special": false
|
164 |
+
},
|
165 |
+
"151663": {
|
166 |
+
"content": "<|repo_name|>",
|
167 |
+
"lstrip": false,
|
168 |
+
"normalized": false,
|
169 |
+
"rstrip": false,
|
170 |
+
"single_word": false,
|
171 |
+
"special": false
|
172 |
+
},
|
173 |
+
"151664": {
|
174 |
+
"content": "<|file_sep|>",
|
175 |
+
"lstrip": false,
|
176 |
+
"normalized": false,
|
177 |
+
"rstrip": false,
|
178 |
+
"single_word": false,
|
179 |
+
"special": false
|
180 |
+
}
|
181 |
+
},
|
182 |
+
"additional_special_tokens": [
|
183 |
+
"<|im_start|>",
|
184 |
+
"<|im_end|>",
|
185 |
+
"<|object_ref_start|>",
|
186 |
+
"<|object_ref_end|>",
|
187 |
+
"<|box_start|>",
|
188 |
+
"<|box_end|>",
|
189 |
+
"<|quad_start|>",
|
190 |
+
"<|quad_end|>",
|
191 |
+
"<|vision_start|>",
|
192 |
+
"<|vision_end|>",
|
193 |
+
"<|vision_pad|>",
|
194 |
+
"<|image_pad|>",
|
195 |
+
"<|video_pad|>"
|
196 |
+
],
|
197 |
+
"bos_token": null,
|
198 |
+
"chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
|
199 |
+
"clean_up_tokenization_spaces": false,
|
200 |
+
"eos_token": "<|endoftext|>",
|
201 |
+
"errors": "replace",
|
202 |
+
"model_max_length": 131072,
|
203 |
+
"pad_token": "<|endoftext|>",
|
204 |
+
"split_special_tokens": false,
|
205 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
206 |
+
"unk_token": null
|
207 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,2706 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.2539152223846315,
|
5 |
+
"eval_steps": 75,
|
6 |
+
"global_step": 375,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.003341687552213868,
|
13 |
+
"grad_norm": 9.422656730262974,
|
14 |
+
"learning_rate": 1.6666666666666667e-06,
|
15 |
+
"loss": 1.4155,
|
16 |
+
"step": 1
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.003341687552213868,
|
20 |
+
"eval_loss": 1.8004764318466187,
|
21 |
+
"eval_runtime": 49.231,
|
22 |
+
"eval_samples_per_second": 0.447,
|
23 |
+
"eval_steps_per_second": 0.122,
|
24 |
+
"step": 1
|
25 |
+
},
|
26 |
+
{
|
27 |
+
"epoch": 0.006683375104427736,
|
28 |
+
"grad_norm": 7.9592686195064655,
|
29 |
+
"learning_rate": 3.3333333333333333e-06,
|
30 |
+
"loss": 1.4836,
|
31 |
+
"step": 2
|
32 |
+
},
|
33 |
+
{
|
34 |
+
"epoch": 0.010025062656641603,
|
35 |
+
"grad_norm": 11.08227927061808,
|
36 |
+
"learning_rate": 5e-06,
|
37 |
+
"loss": 1.568,
|
38 |
+
"step": 3
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 0.013366750208855471,
|
42 |
+
"grad_norm": 9.054404458978134,
|
43 |
+
"learning_rate": 6.666666666666667e-06,
|
44 |
+
"loss": 1.4902,
|
45 |
+
"step": 4
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"epoch": 0.01670843776106934,
|
49 |
+
"grad_norm": 4.814739146640832,
|
50 |
+
"learning_rate": 8.333333333333334e-06,
|
51 |
+
"loss": 1.4581,
|
52 |
+
"step": 5
|
53 |
+
},
|
54 |
+
{
|
55 |
+
"epoch": 0.020050125313283207,
|
56 |
+
"grad_norm": 3.370760758247303,
|
57 |
+
"learning_rate": 1e-05,
|
58 |
+
"loss": 1.4943,
|
59 |
+
"step": 6
|
60 |
+
},
|
61 |
+
{
|
62 |
+
"epoch": 0.023391812865497075,
|
63 |
+
"grad_norm": 4.15650648864708,
|
64 |
+
"learning_rate": 1.1666666666666668e-05,
|
65 |
+
"loss": 1.3664,
|
66 |
+
"step": 7
|
67 |
+
},
|
68 |
+
{
|
69 |
+
"epoch": 0.026733500417710943,
|
70 |
+
"grad_norm": 4.168972921570349,
|
71 |
+
"learning_rate": 1.3333333333333333e-05,
|
72 |
+
"loss": 1.369,
|
73 |
+
"step": 8
|
74 |
+
},
|
75 |
+
{
|
76 |
+
"epoch": 0.03007518796992481,
|
77 |
+
"grad_norm": 2.5626426979817754,
|
78 |
+
"learning_rate": 1.5e-05,
|
79 |
+
"loss": 1.4485,
|
80 |
+
"step": 9
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 0.03341687552213868,
|
84 |
+
"grad_norm": 1266.5995492196223,
|
85 |
+
"learning_rate": 1.6666666666666667e-05,
|
86 |
+
"loss": 1.3401,
|
87 |
+
"step": 10
|
88 |
+
},
|
89 |
+
{
|
90 |
+
"epoch": 0.036758563074352546,
|
91 |
+
"grad_norm": 2.544199092180538,
|
92 |
+
"learning_rate": 1.8333333333333333e-05,
|
93 |
+
"loss": 1.3449,
|
94 |
+
"step": 11
|
95 |
+
},
|
96 |
+
{
|
97 |
+
"epoch": 0.040100250626566414,
|
98 |
+
"grad_norm": 2.2046489399946028,
|
99 |
+
"learning_rate": 2e-05,
|
100 |
+
"loss": 1.3165,
|
101 |
+
"step": 12
|
102 |
+
},
|
103 |
+
{
|
104 |
+
"epoch": 0.04344193817878028,
|
105 |
+
"grad_norm": 1.8293693281340389,
|
106 |
+
"learning_rate": 2.1666666666666667e-05,
|
107 |
+
"loss": 1.397,
|
108 |
+
"step": 13
|
109 |
+
},
|
110 |
+
{
|
111 |
+
"epoch": 0.04678362573099415,
|
112 |
+
"grad_norm": 2.149761301718473,
|
113 |
+
"learning_rate": 2.3333333333333336e-05,
|
114 |
+
"loss": 1.436,
|
115 |
+
"step": 14
|
116 |
+
},
|
117 |
+
{
|
118 |
+
"epoch": 0.05012531328320802,
|
119 |
+
"grad_norm": 2.1865938834852523,
|
120 |
+
"learning_rate": 2.5e-05,
|
121 |
+
"loss": 1.3629,
|
122 |
+
"step": 15
|
123 |
+
},
|
124 |
+
{
|
125 |
+
"epoch": 0.053467000835421885,
|
126 |
+
"grad_norm": 1.6718675362366882,
|
127 |
+
"learning_rate": 2.6666666666666667e-05,
|
128 |
+
"loss": 1.2787,
|
129 |
+
"step": 16
|
130 |
+
},
|
131 |
+
{
|
132 |
+
"epoch": 0.05680868838763575,
|
133 |
+
"grad_norm": 1.7469631110837789,
|
134 |
+
"learning_rate": 2.8333333333333335e-05,
|
135 |
+
"loss": 1.3666,
|
136 |
+
"step": 17
|
137 |
+
},
|
138 |
+
{
|
139 |
+
"epoch": 0.06015037593984962,
|
140 |
+
"grad_norm": 2.026182288959042,
|
141 |
+
"learning_rate": 3e-05,
|
142 |
+
"loss": 1.3905,
|
143 |
+
"step": 18
|
144 |
+
},
|
145 |
+
{
|
146 |
+
"epoch": 0.06349206349206349,
|
147 |
+
"grad_norm": 1.5601215827368777,
|
148 |
+
"learning_rate": 3.1666666666666666e-05,
|
149 |
+
"loss": 1.2615,
|
150 |
+
"step": 19
|
151 |
+
},
|
152 |
+
{
|
153 |
+
"epoch": 0.06683375104427736,
|
154 |
+
"grad_norm": 1.6239108972686256,
|
155 |
+
"learning_rate": 3.3333333333333335e-05,
|
156 |
+
"loss": 1.2865,
|
157 |
+
"step": 20
|
158 |
+
},
|
159 |
+
{
|
160 |
+
"epoch": 0.07017543859649122,
|
161 |
+
"grad_norm": 1.8043652555869882,
|
162 |
+
"learning_rate": 3.5e-05,
|
163 |
+
"loss": 1.3364,
|
164 |
+
"step": 21
|
165 |
+
},
|
166 |
+
{
|
167 |
+
"epoch": 0.07351712614870509,
|
168 |
+
"grad_norm": 1.418878317939115,
|
169 |
+
"learning_rate": 3.6666666666666666e-05,
|
170 |
+
"loss": 1.239,
|
171 |
+
"step": 22
|
172 |
+
},
|
173 |
+
{
|
174 |
+
"epoch": 0.07685881370091896,
|
175 |
+
"grad_norm": 1.641006294199728,
|
176 |
+
"learning_rate": 3.8333333333333334e-05,
|
177 |
+
"loss": 1.2206,
|
178 |
+
"step": 23
|
179 |
+
},
|
180 |
+
{
|
181 |
+
"epoch": 0.08020050125313283,
|
182 |
+
"grad_norm": 1.4565002852740556,
|
183 |
+
"learning_rate": 4e-05,
|
184 |
+
"loss": 1.3179,
|
185 |
+
"step": 24
|
186 |
+
},
|
187 |
+
{
|
188 |
+
"epoch": 0.0835421888053467,
|
189 |
+
"grad_norm": 1.2586337015066662,
|
190 |
+
"learning_rate": 4.166666666666667e-05,
|
191 |
+
"loss": 1.2097,
|
192 |
+
"step": 25
|
193 |
+
},
|
194 |
+
{
|
195 |
+
"epoch": 0.08688387635756056,
|
196 |
+
"grad_norm": 1.2904448628312173,
|
197 |
+
"learning_rate": 4.3333333333333334e-05,
|
198 |
+
"loss": 1.2804,
|
199 |
+
"step": 26
|
200 |
+
},
|
201 |
+
{
|
202 |
+
"epoch": 0.09022556390977443,
|
203 |
+
"grad_norm": 1.336149520030802,
|
204 |
+
"learning_rate": 4.5e-05,
|
205 |
+
"loss": 1.2905,
|
206 |
+
"step": 27
|
207 |
+
},
|
208 |
+
{
|
209 |
+
"epoch": 0.0935672514619883,
|
210 |
+
"grad_norm": 1.3805663163469717,
|
211 |
+
"learning_rate": 4.666666666666667e-05,
|
212 |
+
"loss": 1.2018,
|
213 |
+
"step": 28
|
214 |
+
},
|
215 |
+
{
|
216 |
+
"epoch": 0.09690893901420217,
|
217 |
+
"grad_norm": 1.3223829196481407,
|
218 |
+
"learning_rate": 4.8333333333333334e-05,
|
219 |
+
"loss": 1.3514,
|
220 |
+
"step": 29
|
221 |
+
},
|
222 |
+
{
|
223 |
+
"epoch": 0.10025062656641603,
|
224 |
+
"grad_norm": 1.117557068600307,
|
225 |
+
"learning_rate": 5e-05,
|
226 |
+
"loss": 1.3185,
|
227 |
+
"step": 30
|
228 |
+
},
|
229 |
+
{
|
230 |
+
"epoch": 0.1035923141186299,
|
231 |
+
"grad_norm": 1.3628329620488002,
|
232 |
+
"learning_rate": 4.999983587637969e-05,
|
233 |
+
"loss": 1.3184,
|
234 |
+
"step": 31
|
235 |
+
},
|
236 |
+
{
|
237 |
+
"epoch": 0.10693400167084377,
|
238 |
+
"grad_norm": 1.6900882409593405,
|
239 |
+
"learning_rate": 4.999934350767369e-05,
|
240 |
+
"loss": 1.2478,
|
241 |
+
"step": 32
|
242 |
+
},
|
243 |
+
{
|
244 |
+
"epoch": 0.11027568922305764,
|
245 |
+
"grad_norm": 1.1018164563546424,
|
246 |
+
"learning_rate": 4.999852290034673e-05,
|
247 |
+
"loss": 1.1818,
|
248 |
+
"step": 33
|
249 |
+
},
|
250 |
+
{
|
251 |
+
"epoch": 0.1136173767752715,
|
252 |
+
"grad_norm": 1.517905740455229,
|
253 |
+
"learning_rate": 4.9997374065173316e-05,
|
254 |
+
"loss": 1.241,
|
255 |
+
"step": 34
|
256 |
+
},
|
257 |
+
{
|
258 |
+
"epoch": 0.11695906432748537,
|
259 |
+
"grad_norm": 1.3462450662992849,
|
260 |
+
"learning_rate": 4.999589701723751e-05,
|
261 |
+
"loss": 1.4392,
|
262 |
+
"step": 35
|
263 |
+
},
|
264 |
+
{
|
265 |
+
"epoch": 0.12030075187969924,
|
266 |
+
"grad_norm": 1.332649775646042,
|
267 |
+
"learning_rate": 4.99940917759328e-05,
|
268 |
+
"loss": 1.3001,
|
269 |
+
"step": 36
|
270 |
+
},
|
271 |
+
{
|
272 |
+
"epoch": 0.12364243943191311,
|
273 |
+
"grad_norm": 1.3291037070625635,
|
274 |
+
"learning_rate": 4.9991958364961794e-05,
|
275 |
+
"loss": 1.2308,
|
276 |
+
"step": 37
|
277 |
+
},
|
278 |
+
{
|
279 |
+
"epoch": 0.12698412698412698,
|
280 |
+
"grad_norm": 1.42150501947453,
|
281 |
+
"learning_rate": 4.998949681233595e-05,
|
282 |
+
"loss": 1.2918,
|
283 |
+
"step": 38
|
284 |
+
},
|
285 |
+
{
|
286 |
+
"epoch": 0.13032581453634084,
|
287 |
+
"grad_norm": 1.074142668859534,
|
288 |
+
"learning_rate": 4.998670715037518e-05,
|
289 |
+
"loss": 1.278,
|
290 |
+
"step": 39
|
291 |
+
},
|
292 |
+
{
|
293 |
+
"epoch": 0.1336675020885547,
|
294 |
+
"grad_norm": 1.2920579933597587,
|
295 |
+
"learning_rate": 4.998358941570744e-05,
|
296 |
+
"loss": 1.3275,
|
297 |
+
"step": 40
|
298 |
+
},
|
299 |
+
{
|
300 |
+
"epoch": 0.13700918964076858,
|
301 |
+
"grad_norm": 1.237403262913235,
|
302 |
+
"learning_rate": 4.998014364926824e-05,
|
303 |
+
"loss": 1.2,
|
304 |
+
"step": 41
|
305 |
+
},
|
306 |
+
{
|
307 |
+
"epoch": 0.14035087719298245,
|
308 |
+
"grad_norm": 1.268092315378372,
|
309 |
+
"learning_rate": 4.997636989630011e-05,
|
310 |
+
"loss": 1.1777,
|
311 |
+
"step": 42
|
312 |
+
},
|
313 |
+
{
|
314 |
+
"epoch": 0.14369256474519632,
|
315 |
+
"grad_norm": 1.0207096180154704,
|
316 |
+
"learning_rate": 4.997226820635203e-05,
|
317 |
+
"loss": 1.2758,
|
318 |
+
"step": 43
|
319 |
+
},
|
320 |
+
{
|
321 |
+
"epoch": 0.14703425229741018,
|
322 |
+
"grad_norm": 1.3430934015213214,
|
323 |
+
"learning_rate": 4.99678386332787e-05,
|
324 |
+
"loss": 1.1911,
|
325 |
+
"step": 44
|
326 |
+
},
|
327 |
+
{
|
328 |
+
"epoch": 0.15037593984962405,
|
329 |
+
"grad_norm": 1.1541607076308344,
|
330 |
+
"learning_rate": 4.996308123523995e-05,
|
331 |
+
"loss": 1.2296,
|
332 |
+
"step": 45
|
333 |
+
},
|
334 |
+
{
|
335 |
+
"epoch": 0.15371762740183792,
|
336 |
+
"grad_norm": 1.2443113266651544,
|
337 |
+
"learning_rate": 4.9957996074699884e-05,
|
338 |
+
"loss": 1.2381,
|
339 |
+
"step": 46
|
340 |
+
},
|
341 |
+
{
|
342 |
+
"epoch": 0.1570593149540518,
|
343 |
+
"grad_norm": 1.0652313229665111,
|
344 |
+
"learning_rate": 4.995258321842611e-05,
|
345 |
+
"loss": 1.1833,
|
346 |
+
"step": 47
|
347 |
+
},
|
348 |
+
{
|
349 |
+
"epoch": 0.16040100250626566,
|
350 |
+
"grad_norm": 1.1543672819429747,
|
351 |
+
"learning_rate": 4.9946842737488815e-05,
|
352 |
+
"loss": 1.2179,
|
353 |
+
"step": 48
|
354 |
+
},
|
355 |
+
{
|
356 |
+
"epoch": 0.16374269005847952,
|
357 |
+
"grad_norm": 1.1021407909957812,
|
358 |
+
"learning_rate": 4.994077470725989e-05,
|
359 |
+
"loss": 1.2463,
|
360 |
+
"step": 49
|
361 |
+
},
|
362 |
+
{
|
363 |
+
"epoch": 0.1670843776106934,
|
364 |
+
"grad_norm": 1.1322090567817211,
|
365 |
+
"learning_rate": 4.993437920741191e-05,
|
366 |
+
"loss": 1.1531,
|
367 |
+
"step": 50
|
368 |
+
},
|
369 |
+
{
|
370 |
+
"epoch": 0.17042606516290726,
|
371 |
+
"grad_norm": 1.272598115993271,
|
372 |
+
"learning_rate": 4.992765632191706e-05,
|
373 |
+
"loss": 1.2044,
|
374 |
+
"step": 51
|
375 |
+
},
|
376 |
+
{
|
377 |
+
"epoch": 0.17376775271512113,
|
378 |
+
"grad_norm": 1.2820610442976028,
|
379 |
+
"learning_rate": 4.992060613904611e-05,
|
380 |
+
"loss": 1.2833,
|
381 |
+
"step": 52
|
382 |
+
},
|
383 |
+
{
|
384 |
+
"epoch": 0.177109440267335,
|
385 |
+
"grad_norm": 1.03946480935167,
|
386 |
+
"learning_rate": 4.991322875136716e-05,
|
387 |
+
"loss": 1.2043,
|
388 |
+
"step": 53
|
389 |
+
},
|
390 |
+
{
|
391 |
+
"epoch": 0.18045112781954886,
|
392 |
+
"grad_norm": 1.4100014931322022,
|
393 |
+
"learning_rate": 4.990552425574452e-05,
|
394 |
+
"loss": 1.2572,
|
395 |
+
"step": 54
|
396 |
+
},
|
397 |
+
{
|
398 |
+
"epoch": 0.18379281537176273,
|
399 |
+
"grad_norm": 1.1044198987392109,
|
400 |
+
"learning_rate": 4.989749275333735e-05,
|
401 |
+
"loss": 1.173,
|
402 |
+
"step": 55
|
403 |
+
},
|
404 |
+
{
|
405 |
+
"epoch": 0.1871345029239766,
|
406 |
+
"grad_norm": 1.2029957139213148,
|
407 |
+
"learning_rate": 4.9889134349598384e-05,
|
408 |
+
"loss": 1.2086,
|
409 |
+
"step": 56
|
410 |
+
},
|
411 |
+
{
|
412 |
+
"epoch": 0.19047619047619047,
|
413 |
+
"grad_norm": 1.1209588633953635,
|
414 |
+
"learning_rate": 4.988044915427257e-05,
|
415 |
+
"loss": 1.2347,
|
416 |
+
"step": 57
|
417 |
+
},
|
418 |
+
{
|
419 |
+
"epoch": 0.19381787802840433,
|
420 |
+
"grad_norm": 1.1050690405175774,
|
421 |
+
"learning_rate": 4.9871437281395525e-05,
|
422 |
+
"loss": 1.2299,
|
423 |
+
"step": 58
|
424 |
+
},
|
425 |
+
{
|
426 |
+
"epoch": 0.1971595655806182,
|
427 |
+
"grad_norm": 1.121471860445537,
|
428 |
+
"learning_rate": 4.986209884929218e-05,
|
429 |
+
"loss": 1.1989,
|
430 |
+
"step": 59
|
431 |
+
},
|
432 |
+
{
|
433 |
+
"epoch": 0.20050125313283207,
|
434 |
+
"grad_norm": 1.1616230448507037,
|
435 |
+
"learning_rate": 4.98524339805751e-05,
|
436 |
+
"loss": 1.392,
|
437 |
+
"step": 60
|
438 |
+
},
|
439 |
+
{
|
440 |
+
"epoch": 0.20384294068504594,
|
441 |
+
"grad_norm": 1.091249962757003,
|
442 |
+
"learning_rate": 4.984244280214294e-05,
|
443 |
+
"loss": 1.2663,
|
444 |
+
"step": 61
|
445 |
+
},
|
446 |
+
{
|
447 |
+
"epoch": 0.2071846282372598,
|
448 |
+
"grad_norm": 1.1157809777653205,
|
449 |
+
"learning_rate": 4.983212544517878e-05,
|
450 |
+
"loss": 1.2751,
|
451 |
+
"step": 62
|
452 |
+
},
|
453 |
+
{
|
454 |
+
"epoch": 0.21052631578947367,
|
455 |
+
"grad_norm": 1.2254356056906608,
|
456 |
+
"learning_rate": 4.9821482045148375e-05,
|
457 |
+
"loss": 1.2468,
|
458 |
+
"step": 63
|
459 |
+
},
|
460 |
+
{
|
461 |
+
"epoch": 0.21386800334168754,
|
462 |
+
"grad_norm": 1.0405533895078984,
|
463 |
+
"learning_rate": 4.98105127417984e-05,
|
464 |
+
"loss": 1.1853,
|
465 |
+
"step": 64
|
466 |
+
},
|
467 |
+
{
|
468 |
+
"epoch": 0.2172096908939014,
|
469 |
+
"grad_norm": 1.1342961308693198,
|
470 |
+
"learning_rate": 4.9799217679154584e-05,
|
471 |
+
"loss": 1.2196,
|
472 |
+
"step": 65
|
473 |
+
},
|
474 |
+
{
|
475 |
+
"epoch": 0.22055137844611528,
|
476 |
+
"grad_norm": 1.1946061028510457,
|
477 |
+
"learning_rate": 4.978759700551986e-05,
|
478 |
+
"loss": 1.1807,
|
479 |
+
"step": 66
|
480 |
+
},
|
481 |
+
{
|
482 |
+
"epoch": 0.22389306599832914,
|
483 |
+
"grad_norm": 1.1751408913504486,
|
484 |
+
"learning_rate": 4.977565087347239e-05,
|
485 |
+
"loss": 1.2289,
|
486 |
+
"step": 67
|
487 |
+
},
|
488 |
+
{
|
489 |
+
"epoch": 0.227234753550543,
|
490 |
+
"grad_norm": 1.3191541216438447,
|
491 |
+
"learning_rate": 4.976337943986357e-05,
|
492 |
+
"loss": 1.214,
|
493 |
+
"step": 68
|
494 |
+
},
|
495 |
+
{
|
496 |
+
"epoch": 0.23057644110275688,
|
497 |
+
"grad_norm": 1.1444973785656187,
|
498 |
+
"learning_rate": 4.975078286581596e-05,
|
499 |
+
"loss": 1.2287,
|
500 |
+
"step": 69
|
501 |
+
},
|
502 |
+
{
|
503 |
+
"epoch": 0.23391812865497075,
|
504 |
+
"grad_norm": 1.2184149728817883,
|
505 |
+
"learning_rate": 4.97378613167212e-05,
|
506 |
+
"loss": 1.3791,
|
507 |
+
"step": 70
|
508 |
+
},
|
509 |
+
{
|
510 |
+
"epoch": 0.23725981620718462,
|
511 |
+
"grad_norm": 1.1647377307572258,
|
512 |
+
"learning_rate": 4.9724614962237803e-05,
|
513 |
+
"loss": 1.1693,
|
514 |
+
"step": 71
|
515 |
+
},
|
516 |
+
{
|
517 |
+
"epoch": 0.24060150375939848,
|
518 |
+
"grad_norm": 1.1110859065431626,
|
519 |
+
"learning_rate": 4.971104397628893e-05,
|
520 |
+
"loss": 1.2154,
|
521 |
+
"step": 72
|
522 |
+
},
|
523 |
+
{
|
524 |
+
"epoch": 0.24394319131161235,
|
525 |
+
"grad_norm": 1.2567000920579476,
|
526 |
+
"learning_rate": 4.9697148537060136e-05,
|
527 |
+
"loss": 1.1611,
|
528 |
+
"step": 73
|
529 |
+
},
|
530 |
+
{
|
531 |
+
"epoch": 0.24728487886382622,
|
532 |
+
"grad_norm": 1.1550950387887173,
|
533 |
+
"learning_rate": 4.9682928826997e-05,
|
534 |
+
"loss": 1.257,
|
535 |
+
"step": 74
|
536 |
+
},
|
537 |
+
{
|
538 |
+
"epoch": 0.2506265664160401,
|
539 |
+
"grad_norm": 1.0281075297368318,
|
540 |
+
"learning_rate": 4.966838503280275e-05,
|
541 |
+
"loss": 1.1868,
|
542 |
+
"step": 75
|
543 |
+
},
|
544 |
+
{
|
545 |
+
"epoch": 0.2506265664160401,
|
546 |
+
"eval_loss": 1.4157997369766235,
|
547 |
+
"eval_runtime": 48.5608,
|
548 |
+
"eval_samples_per_second": 0.453,
|
549 |
+
"eval_steps_per_second": 0.124,
|
550 |
+
"step": 75
|
551 |
+
},
|
552 |
+
{
|
553 |
+
"epoch": 0.25396825396825395,
|
554 |
+
"grad_norm": 1.1032178941225772,
|
555 |
+
"learning_rate": 4.96535173454358e-05,
|
556 |
+
"loss": 1.1861,
|
557 |
+
"step": 76
|
558 |
+
},
|
559 |
+
{
|
560 |
+
"epoch": 0.2573099415204678,
|
561 |
+
"grad_norm": 1.093369250778169,
|
562 |
+
"learning_rate": 4.9638325960107235e-05,
|
563 |
+
"loss": 1.2555,
|
564 |
+
"step": 77
|
565 |
+
},
|
566 |
+
{
|
567 |
+
"epoch": 0.2606516290726817,
|
568 |
+
"grad_norm": 1.1413869539274288,
|
569 |
+
"learning_rate": 4.962281107627828e-05,
|
570 |
+
"loss": 1.2892,
|
571 |
+
"step": 78
|
572 |
+
},
|
573 |
+
{
|
574 |
+
"epoch": 0.26399331662489556,
|
575 |
+
"grad_norm": 1.0532164721638475,
|
576 |
+
"learning_rate": 4.960697289765764e-05,
|
577 |
+
"loss": 1.2131,
|
578 |
+
"step": 79
|
579 |
+
},
|
580 |
+
{
|
581 |
+
"epoch": 0.2673350041771094,
|
582 |
+
"grad_norm": 1.0579041886059877,
|
583 |
+
"learning_rate": 4.959081163219885e-05,
|
584 |
+
"loss": 1.2693,
|
585 |
+
"step": 80
|
586 |
+
},
|
587 |
+
{
|
588 |
+
"epoch": 0.2706766917293233,
|
589 |
+
"grad_norm": 1.1312038750809115,
|
590 |
+
"learning_rate": 4.957432749209755e-05,
|
591 |
+
"loss": 1.2504,
|
592 |
+
"step": 81
|
593 |
+
},
|
594 |
+
{
|
595 |
+
"epoch": 0.27401837928153716,
|
596 |
+
"grad_norm": 1.0252412589334967,
|
597 |
+
"learning_rate": 4.955752069378867e-05,
|
598 |
+
"loss": 1.1226,
|
599 |
+
"step": 82
|
600 |
+
},
|
601 |
+
{
|
602 |
+
"epoch": 0.27736006683375103,
|
603 |
+
"grad_norm": 1.0668623234540449,
|
604 |
+
"learning_rate": 4.9540391457943626e-05,
|
605 |
+
"loss": 1.2471,
|
606 |
+
"step": 83
|
607 |
+
},
|
608 |
+
{
|
609 |
+
"epoch": 0.2807017543859649,
|
610 |
+
"grad_norm": 1.1247331389355435,
|
611 |
+
"learning_rate": 4.9522940009467385e-05,
|
612 |
+
"loss": 1.3092,
|
613 |
+
"step": 84
|
614 |
+
},
|
615 |
+
{
|
616 |
+
"epoch": 0.28404344193817876,
|
617 |
+
"grad_norm": 1.0404338917876472,
|
618 |
+
"learning_rate": 4.9505166577495546e-05,
|
619 |
+
"loss": 1.2724,
|
620 |
+
"step": 85
|
621 |
+
},
|
622 |
+
{
|
623 |
+
"epoch": 0.28738512949039263,
|
624 |
+
"grad_norm": 1.0666603820625944,
|
625 |
+
"learning_rate": 4.9487071395391304e-05,
|
626 |
+
"loss": 1.212,
|
627 |
+
"step": 86
|
628 |
+
},
|
629 |
+
{
|
630 |
+
"epoch": 0.2907268170426065,
|
631 |
+
"grad_norm": 1.028172195805746,
|
632 |
+
"learning_rate": 4.946865470074241e-05,
|
633 |
+
"loss": 1.2332,
|
634 |
+
"step": 87
|
635 |
+
},
|
636 |
+
{
|
637 |
+
"epoch": 0.29406850459482037,
|
638 |
+
"grad_norm": 1.086672162070916,
|
639 |
+
"learning_rate": 4.944991673535803e-05,
|
640 |
+
"loss": 1.2241,
|
641 |
+
"step": 88
|
642 |
+
},
|
643 |
+
{
|
644 |
+
"epoch": 0.29741019214703424,
|
645 |
+
"grad_norm": 1.0006701473196968,
|
646 |
+
"learning_rate": 4.943085774526557e-05,
|
647 |
+
"loss": 1.2506,
|
648 |
+
"step": 89
|
649 |
+
},
|
650 |
+
{
|
651 |
+
"epoch": 0.3007518796992481,
|
652 |
+
"grad_norm": 1.0581177814326124,
|
653 |
+
"learning_rate": 4.941147798070748e-05,
|
654 |
+
"loss": 1.1867,
|
655 |
+
"step": 90
|
656 |
+
},
|
657 |
+
{
|
658 |
+
"epoch": 0.30409356725146197,
|
659 |
+
"grad_norm": 1.1670838320424346,
|
660 |
+
"learning_rate": 4.939177769613793e-05,
|
661 |
+
"loss": 1.2656,
|
662 |
+
"step": 91
|
663 |
+
},
|
664 |
+
{
|
665 |
+
"epoch": 0.30743525480367584,
|
666 |
+
"grad_norm": 1.0708821933487631,
|
667 |
+
"learning_rate": 4.937175715021947e-05,
|
668 |
+
"loss": 1.2476,
|
669 |
+
"step": 92
|
670 |
+
},
|
671 |
+
{
|
672 |
+
"epoch": 0.3107769423558897,
|
673 |
+
"grad_norm": 1.2274131496276997,
|
674 |
+
"learning_rate": 4.935141660581967e-05,
|
675 |
+
"loss": 1.2109,
|
676 |
+
"step": 93
|
677 |
+
},
|
678 |
+
{
|
679 |
+
"epoch": 0.3141186299081036,
|
680 |
+
"grad_norm": 1.1219369001475894,
|
681 |
+
"learning_rate": 4.933075633000762e-05,
|
682 |
+
"loss": 1.1672,
|
683 |
+
"step": 94
|
684 |
+
},
|
685 |
+
{
|
686 |
+
"epoch": 0.31746031746031744,
|
687 |
+
"grad_norm": 1.3306757923587944,
|
688 |
+
"learning_rate": 4.9309776594050485e-05,
|
689 |
+
"loss": 1.2768,
|
690 |
+
"step": 95
|
691 |
+
},
|
692 |
+
{
|
693 |
+
"epoch": 0.3208020050125313,
|
694 |
+
"grad_norm": 1.2323559759209257,
|
695 |
+
"learning_rate": 4.928847767340985e-05,
|
696 |
+
"loss": 1.2487,
|
697 |
+
"step": 96
|
698 |
+
},
|
699 |
+
{
|
700 |
+
"epoch": 0.3241436925647452,
|
701 |
+
"grad_norm": 1.3365381410958403,
|
702 |
+
"learning_rate": 4.9266859847738216e-05,
|
703 |
+
"loss": 1.3815,
|
704 |
+
"step": 97
|
705 |
+
},
|
706 |
+
{
|
707 |
+
"epoch": 0.32748538011695905,
|
708 |
+
"grad_norm": 1.0365471654338871,
|
709 |
+
"learning_rate": 4.9244923400875245e-05,
|
710 |
+
"loss": 1.2593,
|
711 |
+
"step": 98
|
712 |
+
},
|
713 |
+
{
|
714 |
+
"epoch": 0.3308270676691729,
|
715 |
+
"grad_norm": 1.2743177210627519,
|
716 |
+
"learning_rate": 4.9222668620844045e-05,
|
717 |
+
"loss": 1.2763,
|
718 |
+
"step": 99
|
719 |
+
},
|
720 |
+
{
|
721 |
+
"epoch": 0.3341687552213868,
|
722 |
+
"grad_norm": 1.134125425689655,
|
723 |
+
"learning_rate": 4.920009579984745e-05,
|
724 |
+
"loss": 1.213,
|
725 |
+
"step": 100
|
726 |
+
},
|
727 |
+
{
|
728 |
+
"epoch": 0.33751044277360065,
|
729 |
+
"grad_norm": 1.09970050960468,
|
730 |
+
"learning_rate": 4.917720523426408e-05,
|
731 |
+
"loss": 1.124,
|
732 |
+
"step": 101
|
733 |
+
},
|
734 |
+
{
|
735 |
+
"epoch": 0.3408521303258145,
|
736 |
+
"grad_norm": 1.206078654647485,
|
737 |
+
"learning_rate": 4.915399722464455e-05,
|
738 |
+
"loss": 1.2306,
|
739 |
+
"step": 102
|
740 |
+
},
|
741 |
+
{
|
742 |
+
"epoch": 0.3441938178780284,
|
743 |
+
"grad_norm": 1.1159637768382946,
|
744 |
+
"learning_rate": 4.9130472075707476e-05,
|
745 |
+
"loss": 1.1426,
|
746 |
+
"step": 103
|
747 |
+
},
|
748 |
+
{
|
749 |
+
"epoch": 0.34753550543024225,
|
750 |
+
"grad_norm": 0.9446952904809814,
|
751 |
+
"learning_rate": 4.910663009633544e-05,
|
752 |
+
"loss": 1.1786,
|
753 |
+
"step": 104
|
754 |
+
},
|
755 |
+
{
|
756 |
+
"epoch": 0.3508771929824561,
|
757 |
+
"grad_norm": 1.1367001934835825,
|
758 |
+
"learning_rate": 4.9082471599571015e-05,
|
759 |
+
"loss": 1.2124,
|
760 |
+
"step": 105
|
761 |
+
},
|
762 |
+
{
|
763 |
+
"epoch": 0.35421888053467,
|
764 |
+
"grad_norm": 1.0634444839475792,
|
765 |
+
"learning_rate": 4.90579969026126e-05,
|
766 |
+
"loss": 1.2518,
|
767 |
+
"step": 106
|
768 |
+
},
|
769 |
+
{
|
770 |
+
"epoch": 0.35756056808688386,
|
771 |
+
"grad_norm": 1.0063586119274412,
|
772 |
+
"learning_rate": 4.9033206326810254e-05,
|
773 |
+
"loss": 1.1361,
|
774 |
+
"step": 107
|
775 |
+
},
|
776 |
+
{
|
777 |
+
"epoch": 0.3609022556390977,
|
778 |
+
"grad_norm": 0.9565419392852244,
|
779 |
+
"learning_rate": 4.900810019766151e-05,
|
780 |
+
"loss": 1.2128,
|
781 |
+
"step": 108
|
782 |
+
},
|
783 |
+
{
|
784 |
+
"epoch": 0.3642439431913116,
|
785 |
+
"grad_norm": 0.9787104337545581,
|
786 |
+
"learning_rate": 4.8982678844807074e-05,
|
787 |
+
"loss": 1.212,
|
788 |
+
"step": 109
|
789 |
+
},
|
790 |
+
{
|
791 |
+
"epoch": 0.36758563074352546,
|
792 |
+
"grad_norm": 0.9780003889680408,
|
793 |
+
"learning_rate": 4.895694260202649e-05,
|
794 |
+
"loss": 1.2376,
|
795 |
+
"step": 110
|
796 |
+
},
|
797 |
+
{
|
798 |
+
"epoch": 0.37092731829573933,
|
799 |
+
"grad_norm": 1.0138882081963447,
|
800 |
+
"learning_rate": 4.8930891807233794e-05,
|
801 |
+
"loss": 1.2159,
|
802 |
+
"step": 111
|
803 |
+
},
|
804 |
+
{
|
805 |
+
"epoch": 0.3742690058479532,
|
806 |
+
"grad_norm": 0.9274261672525066,
|
807 |
+
"learning_rate": 4.890452680247305e-05,
|
808 |
+
"loss": 1.1519,
|
809 |
+
"step": 112
|
810 |
+
},
|
811 |
+
{
|
812 |
+
"epoch": 0.37761069340016706,
|
813 |
+
"grad_norm": 1.0636922620211422,
|
814 |
+
"learning_rate": 4.887784793391386e-05,
|
815 |
+
"loss": 1.1895,
|
816 |
+
"step": 113
|
817 |
+
},
|
818 |
+
{
|
819 |
+
"epoch": 0.38095238095238093,
|
820 |
+
"grad_norm": 0.9764663835059763,
|
821 |
+
"learning_rate": 4.885085555184681e-05,
|
822 |
+
"loss": 1.1014,
|
823 |
+
"step": 114
|
824 |
+
},
|
825 |
+
{
|
826 |
+
"epoch": 0.3842940685045948,
|
827 |
+
"grad_norm": 1.0579986191441333,
|
828 |
+
"learning_rate": 4.882355001067892e-05,
|
829 |
+
"loss": 1.2347,
|
830 |
+
"step": 115
|
831 |
+
},
|
832 |
+
{
|
833 |
+
"epoch": 0.38763575605680867,
|
834 |
+
"grad_norm": 0.969263591488447,
|
835 |
+
"learning_rate": 4.8795931668928905e-05,
|
836 |
+
"loss": 1.1564,
|
837 |
+
"step": 116
|
838 |
+
},
|
839 |
+
{
|
840 |
+
"epoch": 0.39097744360902253,
|
841 |
+
"grad_norm": 0.9798160234272053,
|
842 |
+
"learning_rate": 4.8768000889222565e-05,
|
843 |
+
"loss": 1.1676,
|
844 |
+
"step": 117
|
845 |
+
},
|
846 |
+
{
|
847 |
+
"epoch": 0.3943191311612364,
|
848 |
+
"grad_norm": 1.0434982392991363,
|
849 |
+
"learning_rate": 4.8739758038287945e-05,
|
850 |
+
"loss": 1.2,
|
851 |
+
"step": 118
|
852 |
+
},
|
853 |
+
{
|
854 |
+
"epoch": 0.39766081871345027,
|
855 |
+
"grad_norm": 0.9650348846186049,
|
856 |
+
"learning_rate": 4.8711203486950565e-05,
|
857 |
+
"loss": 1.223,
|
858 |
+
"step": 119
|
859 |
+
},
|
860 |
+
{
|
861 |
+
"epoch": 0.40100250626566414,
|
862 |
+
"grad_norm": 0.9624246901303686,
|
863 |
+
"learning_rate": 4.8682337610128526e-05,
|
864 |
+
"loss": 1.1558,
|
865 |
+
"step": 120
|
866 |
+
},
|
867 |
+
{
|
868 |
+
"epoch": 0.404344193817878,
|
869 |
+
"grad_norm": 1.1488802443868404,
|
870 |
+
"learning_rate": 4.8653160786827615e-05,
|
871 |
+
"loss": 1.2288,
|
872 |
+
"step": 121
|
873 |
+
},
|
874 |
+
{
|
875 |
+
"epoch": 0.4076858813700919,
|
876 |
+
"grad_norm": 1.0238637619561288,
|
877 |
+
"learning_rate": 4.86236734001363e-05,
|
878 |
+
"loss": 1.2327,
|
879 |
+
"step": 122
|
880 |
+
},
|
881 |
+
{
|
882 |
+
"epoch": 0.41102756892230574,
|
883 |
+
"grad_norm": 1.11719239220642,
|
884 |
+
"learning_rate": 4.8593875837220695e-05,
|
885 |
+
"loss": 1.1635,
|
886 |
+
"step": 123
|
887 |
+
},
|
888 |
+
{
|
889 |
+
"epoch": 0.4143692564745196,
|
890 |
+
"grad_norm": 1.009353186551115,
|
891 |
+
"learning_rate": 4.8563768489319526e-05,
|
892 |
+
"loss": 1.1562,
|
893 |
+
"step": 124
|
894 |
+
},
|
895 |
+
{
|
896 |
+
"epoch": 0.4177109440267335,
|
897 |
+
"grad_norm": 0.977347992720917,
|
898 |
+
"learning_rate": 4.8533351751738953e-05,
|
899 |
+
"loss": 1.2481,
|
900 |
+
"step": 125
|
901 |
+
},
|
902 |
+
{
|
903 |
+
"epoch": 0.42105263157894735,
|
904 |
+
"grad_norm": 0.945296219380299,
|
905 |
+
"learning_rate": 4.8502626023847376e-05,
|
906 |
+
"loss": 1.2216,
|
907 |
+
"step": 126
|
908 |
+
},
|
909 |
+
{
|
910 |
+
"epoch": 0.4243943191311612,
|
911 |
+
"grad_norm": 1.0795727186569568,
|
912 |
+
"learning_rate": 4.847159170907022e-05,
|
913 |
+
"loss": 1.2282,
|
914 |
+
"step": 127
|
915 |
+
},
|
916 |
+
{
|
917 |
+
"epoch": 0.4277360066833751,
|
918 |
+
"grad_norm": 0.9860989054801752,
|
919 |
+
"learning_rate": 4.844024921488459e-05,
|
920 |
+
"loss": 1.1639,
|
921 |
+
"step": 128
|
922 |
+
},
|
923 |
+
{
|
924 |
+
"epoch": 0.43107769423558895,
|
925 |
+
"grad_norm": 1.1401469693168065,
|
926 |
+
"learning_rate": 4.8408598952814003e-05,
|
927 |
+
"loss": 1.2557,
|
928 |
+
"step": 129
|
929 |
+
},
|
930 |
+
{
|
931 |
+
"epoch": 0.4344193817878028,
|
932 |
+
"grad_norm": 0.9621929127805111,
|
933 |
+
"learning_rate": 4.837664133842289e-05,
|
934 |
+
"loss": 1.1059,
|
935 |
+
"step": 130
|
936 |
+
},
|
937 |
+
{
|
938 |
+
"epoch": 0.4377610693400167,
|
939 |
+
"grad_norm": 1.1183621390483012,
|
940 |
+
"learning_rate": 4.834437679131121e-05,
|
941 |
+
"loss": 1.1732,
|
942 |
+
"step": 131
|
943 |
+
},
|
944 |
+
{
|
945 |
+
"epoch": 0.44110275689223055,
|
946 |
+
"grad_norm": 1.0739625747121817,
|
947 |
+
"learning_rate": 4.8311805735108894e-05,
|
948 |
+
"loss": 1.247,
|
949 |
+
"step": 132
|
950 |
+
},
|
951 |
+
{
|
952 |
+
"epoch": 0.4444444444444444,
|
953 |
+
"grad_norm": 1.3490735034401256,
|
954 |
+
"learning_rate": 4.827892859747033e-05,
|
955 |
+
"loss": 1.2512,
|
956 |
+
"step": 133
|
957 |
+
},
|
958 |
+
{
|
959 |
+
"epoch": 0.4477861319966583,
|
960 |
+
"grad_norm": 1.087730861948047,
|
961 |
+
"learning_rate": 4.824574581006869e-05,
|
962 |
+
"loss": 1.3701,
|
963 |
+
"step": 134
|
964 |
+
},
|
965 |
+
{
|
966 |
+
"epoch": 0.45112781954887216,
|
967 |
+
"grad_norm": 0.9963500854374578,
|
968 |
+
"learning_rate": 4.821225780859032e-05,
|
969 |
+
"loss": 1.2301,
|
970 |
+
"step": 135
|
971 |
+
},
|
972 |
+
{
|
973 |
+
"epoch": 0.454469507101086,
|
974 |
+
"grad_norm": 1.0799658734382207,
|
975 |
+
"learning_rate": 4.817846503272898e-05,
|
976 |
+
"loss": 1.1723,
|
977 |
+
"step": 136
|
978 |
+
},
|
979 |
+
{
|
980 |
+
"epoch": 0.4578111946532999,
|
981 |
+
"grad_norm": 0.990853705689885,
|
982 |
+
"learning_rate": 4.814436792618008e-05,
|
983 |
+
"loss": 1.137,
|
984 |
+
"step": 137
|
985 |
+
},
|
986 |
+
{
|
987 |
+
"epoch": 0.46115288220551376,
|
988 |
+
"grad_norm": 1.1057038847113485,
|
989 |
+
"learning_rate": 4.810996693663489e-05,
|
990 |
+
"loss": 1.2275,
|
991 |
+
"step": 138
|
992 |
+
},
|
993 |
+
{
|
994 |
+
"epoch": 0.4644945697577276,
|
995 |
+
"grad_norm": 1.060021921008829,
|
996 |
+
"learning_rate": 4.807526251577458e-05,
|
997 |
+
"loss": 1.1548,
|
998 |
+
"step": 139
|
999 |
+
},
|
1000 |
+
{
|
1001 |
+
"epoch": 0.4678362573099415,
|
1002 |
+
"grad_norm": 1.0494665197923803,
|
1003 |
+
"learning_rate": 4.8040255119264365e-05,
|
1004 |
+
"loss": 1.1501,
|
1005 |
+
"step": 140
|
1006 |
+
},
|
1007 |
+
{
|
1008 |
+
"epoch": 0.47117794486215536,
|
1009 |
+
"grad_norm": 0.9677143325940332,
|
1010 |
+
"learning_rate": 4.8004945206747523e-05,
|
1011 |
+
"loss": 1.2043,
|
1012 |
+
"step": 141
|
1013 |
+
},
|
1014 |
+
{
|
1015 |
+
"epoch": 0.47451963241436923,
|
1016 |
+
"grad_norm": 1.1258991580511044,
|
1017 |
+
"learning_rate": 4.796933324183928e-05,
|
1018 |
+
"loss": 1.2874,
|
1019 |
+
"step": 142
|
1020 |
+
},
|
1021 |
+
{
|
1022 |
+
"epoch": 0.4778613199665831,
|
1023 |
+
"grad_norm": 1.0606416431046548,
|
1024 |
+
"learning_rate": 4.7933419692120816e-05,
|
1025 |
+
"loss": 1.2155,
|
1026 |
+
"step": 143
|
1027 |
+
},
|
1028 |
+
{
|
1029 |
+
"epoch": 0.48120300751879697,
|
1030 |
+
"grad_norm": 1.1260596252923112,
|
1031 |
+
"learning_rate": 4.789720502913309e-05,
|
1032 |
+
"loss": 1.2343,
|
1033 |
+
"step": 144
|
1034 |
+
},
|
1035 |
+
{
|
1036 |
+
"epoch": 0.48454469507101083,
|
1037 |
+
"grad_norm": 0.9662307671780914,
|
1038 |
+
"learning_rate": 4.78606897283706e-05,
|
1039 |
+
"loss": 1.3106,
|
1040 |
+
"step": 145
|
1041 |
+
},
|
1042 |
+
{
|
1043 |
+
"epoch": 0.4878863826232247,
|
1044 |
+
"grad_norm": 1.120463922826075,
|
1045 |
+
"learning_rate": 4.782387426927524e-05,
|
1046 |
+
"loss": 1.3122,
|
1047 |
+
"step": 146
|
1048 |
+
},
|
1049 |
+
{
|
1050 |
+
"epoch": 0.49122807017543857,
|
1051 |
+
"grad_norm": 0.9864203109388633,
|
1052 |
+
"learning_rate": 4.7786759135229903e-05,
|
1053 |
+
"loss": 1.2048,
|
1054 |
+
"step": 147
|
1055 |
+
},
|
1056 |
+
{
|
1057 |
+
"epoch": 0.49456975772765244,
|
1058 |
+
"grad_norm": 0.9891356625756446,
|
1059 |
+
"learning_rate": 4.774934481355222e-05,
|
1060 |
+
"loss": 1.2597,
|
1061 |
+
"step": 148
|
1062 |
+
},
|
1063 |
+
{
|
1064 |
+
"epoch": 0.4979114452798663,
|
1065 |
+
"grad_norm": 1.024223872892248,
|
1066 |
+
"learning_rate": 4.7711631795488096e-05,
|
1067 |
+
"loss": 1.1611,
|
1068 |
+
"step": 149
|
1069 |
+
},
|
1070 |
+
{
|
1071 |
+
"epoch": 0.5012531328320802,
|
1072 |
+
"grad_norm": 0.9945156162486835,
|
1073 |
+
"learning_rate": 4.7673620576205294e-05,
|
1074 |
+
"loss": 1.2275,
|
1075 |
+
"step": 150
|
1076 |
+
},
|
1077 |
+
{
|
1078 |
+
"epoch": 0.5012531328320802,
|
1079 |
+
"eval_loss": 1.3914530277252197,
|
1080 |
+
"eval_runtime": 51.6906,
|
1081 |
+
"eval_samples_per_second": 0.426,
|
1082 |
+
"eval_steps_per_second": 0.116,
|
1083 |
+
"step": 150
|
1084 |
+
},
|
1085 |
+
{
|
1086 |
+
"epoch": 0.504594820384294,
|
1087 |
+
"grad_norm": 0.9560597210744347,
|
1088 |
+
"learning_rate": 4.763531165478694e-05,
|
1089 |
+
"loss": 1.2391,
|
1090 |
+
"step": 151
|
1091 |
+
},
|
1092 |
+
{
|
1093 |
+
"epoch": 0.5079365079365079,
|
1094 |
+
"grad_norm": 0.948744365020844,
|
1095 |
+
"learning_rate": 4.759670553422493e-05,
|
1096 |
+
"loss": 1.1603,
|
1097 |
+
"step": 152
|
1098 |
+
},
|
1099 |
+
{
|
1100 |
+
"epoch": 0.5112781954887218,
|
1101 |
+
"grad_norm": 1.0551198879801713,
|
1102 |
+
"learning_rate": 4.755780272141338e-05,
|
1103 |
+
"loss": 1.2125,
|
1104 |
+
"step": 153
|
1105 |
+
},
|
1106 |
+
{
|
1107 |
+
"epoch": 0.5146198830409356,
|
1108 |
+
"grad_norm": 0.8750586318497058,
|
1109 |
+
"learning_rate": 4.751860372714191e-05,
|
1110 |
+
"loss": 1.1731,
|
1111 |
+
"step": 154
|
1112 |
+
},
|
1113 |
+
{
|
1114 |
+
"epoch": 0.5179615705931495,
|
1115 |
+
"grad_norm": 1.0142475214861557,
|
1116 |
+
"learning_rate": 4.7479109066089e-05,
|
1117 |
+
"loss": 1.2879,
|
1118 |
+
"step": 155
|
1119 |
+
},
|
1120 |
+
{
|
1121 |
+
"epoch": 0.5213032581453634,
|
1122 |
+
"grad_norm": 0.9748413470244546,
|
1123 |
+
"learning_rate": 4.743931925681519e-05,
|
1124 |
+
"loss": 1.268,
|
1125 |
+
"step": 156
|
1126 |
+
},
|
1127 |
+
{
|
1128 |
+
"epoch": 0.5246449456975772,
|
1129 |
+
"grad_norm": 1.0082053632672576,
|
1130 |
+
"learning_rate": 4.739923482175628e-05,
|
1131 |
+
"loss": 1.2415,
|
1132 |
+
"step": 157
|
1133 |
+
},
|
1134 |
+
{
|
1135 |
+
"epoch": 0.5279866332497911,
|
1136 |
+
"grad_norm": 0.9644430877325791,
|
1137 |
+
"learning_rate": 4.735885628721648e-05,
|
1138 |
+
"loss": 1.1902,
|
1139 |
+
"step": 158
|
1140 |
+
},
|
1141 |
+
{
|
1142 |
+
"epoch": 0.531328320802005,
|
1143 |
+
"grad_norm": 0.9511297910602282,
|
1144 |
+
"learning_rate": 4.73181841833615e-05,
|
1145 |
+
"loss": 1.3144,
|
1146 |
+
"step": 159
|
1147 |
+
},
|
1148 |
+
{
|
1149 |
+
"epoch": 0.5346700083542189,
|
1150 |
+
"grad_norm": 0.9441164162609572,
|
1151 |
+
"learning_rate": 4.7277219044211556e-05,
|
1152 |
+
"loss": 1.1854,
|
1153 |
+
"step": 160
|
1154 |
+
},
|
1155 |
+
{
|
1156 |
+
"epoch": 0.5380116959064327,
|
1157 |
+
"grad_norm": 0.8932457698431419,
|
1158 |
+
"learning_rate": 4.723596140763442e-05,
|
1159 |
+
"loss": 1.119,
|
1160 |
+
"step": 161
|
1161 |
+
},
|
1162 |
+
{
|
1163 |
+
"epoch": 0.5413533834586466,
|
1164 |
+
"grad_norm": 0.9849781123317826,
|
1165 |
+
"learning_rate": 4.71944118153383e-05,
|
1166 |
+
"loss": 1.1462,
|
1167 |
+
"step": 162
|
1168 |
+
},
|
1169 |
+
{
|
1170 |
+
"epoch": 0.5446950710108605,
|
1171 |
+
"grad_norm": 1.1331488120142974,
|
1172 |
+
"learning_rate": 4.7152570812864754e-05,
|
1173 |
+
"loss": 1.2394,
|
1174 |
+
"step": 163
|
1175 |
+
},
|
1176 |
+
{
|
1177 |
+
"epoch": 0.5480367585630743,
|
1178 |
+
"grad_norm": 0.9196323880752558,
|
1179 |
+
"learning_rate": 4.711043894958153e-05,
|
1180 |
+
"loss": 1.2024,
|
1181 |
+
"step": 164
|
1182 |
+
},
|
1183 |
+
{
|
1184 |
+
"epoch": 0.5513784461152882,
|
1185 |
+
"grad_norm": 1.0274558354445025,
|
1186 |
+
"learning_rate": 4.706801677867534e-05,
|
1187 |
+
"loss": 1.2215,
|
1188 |
+
"step": 165
|
1189 |
+
},
|
1190 |
+
{
|
1191 |
+
"epoch": 0.5547201336675021,
|
1192 |
+
"grad_norm": 0.9415019585312526,
|
1193 |
+
"learning_rate": 4.702530485714461e-05,
|
1194 |
+
"loss": 1.2155,
|
1195 |
+
"step": 166
|
1196 |
+
},
|
1197 |
+
{
|
1198 |
+
"epoch": 0.5580618212197159,
|
1199 |
+
"grad_norm": 0.8502808406712555,
|
1200 |
+
"learning_rate": 4.6982303745792155e-05,
|
1201 |
+
"loss": 1.1538,
|
1202 |
+
"step": 167
|
1203 |
+
},
|
1204 |
+
{
|
1205 |
+
"epoch": 0.5614035087719298,
|
1206 |
+
"grad_norm": 0.9941266995251048,
|
1207 |
+
"learning_rate": 4.6939014009217816e-05,
|
1208 |
+
"loss": 1.1087,
|
1209 |
+
"step": 168
|
1210 |
+
},
|
1211 |
+
{
|
1212 |
+
"epoch": 0.5647451963241437,
|
1213 |
+
"grad_norm": 0.9822704957931621,
|
1214 |
+
"learning_rate": 4.689543621581107e-05,
|
1215 |
+
"loss": 1.249,
|
1216 |
+
"step": 169
|
1217 |
+
},
|
1218 |
+
{
|
1219 |
+
"epoch": 0.5680868838763575,
|
1220 |
+
"grad_norm": 0.970176516153764,
|
1221 |
+
"learning_rate": 4.68515709377435e-05,
|
1222 |
+
"loss": 1.2191,
|
1223 |
+
"step": 170
|
1224 |
+
},
|
1225 |
+
{
|
1226 |
+
"epoch": 0.5714285714285714,
|
1227 |
+
"grad_norm": 0.9257237748439777,
|
1228 |
+
"learning_rate": 4.680741875096141e-05,
|
1229 |
+
"loss": 1.1665,
|
1230 |
+
"step": 171
|
1231 |
+
},
|
1232 |
+
{
|
1233 |
+
"epoch": 0.5747702589807853,
|
1234 |
+
"grad_norm": 0.9741770014363567,
|
1235 |
+
"learning_rate": 4.676298023517811e-05,
|
1236 |
+
"loss": 1.2693,
|
1237 |
+
"step": 172
|
1238 |
+
},
|
1239 |
+
{
|
1240 |
+
"epoch": 0.5781119465329991,
|
1241 |
+
"grad_norm": 0.9190281388578779,
|
1242 |
+
"learning_rate": 4.671825597386642e-05,
|
1243 |
+
"loss": 1.1128,
|
1244 |
+
"step": 173
|
1245 |
+
},
|
1246 |
+
{
|
1247 |
+
"epoch": 0.581453634085213,
|
1248 |
+
"grad_norm": 1.0223086002479052,
|
1249 |
+
"learning_rate": 4.6673246554250945e-05,
|
1250 |
+
"loss": 1.1661,
|
1251 |
+
"step": 174
|
1252 |
+
},
|
1253 |
+
{
|
1254 |
+
"epoch": 0.5847953216374269,
|
1255 |
+
"grad_norm": 1.0427490752652702,
|
1256 |
+
"learning_rate": 4.66279525673004e-05,
|
1257 |
+
"loss": 1.2023,
|
1258 |
+
"step": 175
|
1259 |
+
},
|
1260 |
+
{
|
1261 |
+
"epoch": 0.5881370091896407,
|
1262 |
+
"grad_norm": 0.9465248631048592,
|
1263 |
+
"learning_rate": 4.658237460771984e-05,
|
1264 |
+
"loss": 1.1683,
|
1265 |
+
"step": 176
|
1266 |
+
},
|
1267 |
+
{
|
1268 |
+
"epoch": 0.5914786967418546,
|
1269 |
+
"grad_norm": 1.1640631893552786,
|
1270 |
+
"learning_rate": 4.653651327394284e-05,
|
1271 |
+
"loss": 1.2079,
|
1272 |
+
"step": 177
|
1273 |
+
},
|
1274 |
+
{
|
1275 |
+
"epoch": 0.5948203842940685,
|
1276 |
+
"grad_norm": 0.9271984872996437,
|
1277 |
+
"learning_rate": 4.6490369168123646e-05,
|
1278 |
+
"loss": 1.1125,
|
1279 |
+
"step": 178
|
1280 |
+
},
|
1281 |
+
{
|
1282 |
+
"epoch": 0.5981620718462823,
|
1283 |
+
"grad_norm": 0.9641228986169222,
|
1284 |
+
"learning_rate": 4.644394289612928e-05,
|
1285 |
+
"loss": 1.1637,
|
1286 |
+
"step": 179
|
1287 |
+
},
|
1288 |
+
{
|
1289 |
+
"epoch": 0.6015037593984962,
|
1290 |
+
"grad_norm": 0.9782799741609496,
|
1291 |
+
"learning_rate": 4.6397235067531564e-05,
|
1292 |
+
"loss": 1.2689,
|
1293 |
+
"step": 180
|
1294 |
+
},
|
1295 |
+
{
|
1296 |
+
"epoch": 0.6048454469507101,
|
1297 |
+
"grad_norm": 1.0763810726777687,
|
1298 |
+
"learning_rate": 4.635024629559914e-05,
|
1299 |
+
"loss": 1.2241,
|
1300 |
+
"step": 181
|
1301 |
+
},
|
1302 |
+
{
|
1303 |
+
"epoch": 0.6081871345029239,
|
1304 |
+
"grad_norm": 0.9048533754587863,
|
1305 |
+
"learning_rate": 4.630297719728939e-05,
|
1306 |
+
"loss": 1.1508,
|
1307 |
+
"step": 182
|
1308 |
+
},
|
1309 |
+
{
|
1310 |
+
"epoch": 0.6115288220551378,
|
1311 |
+
"grad_norm": 1.0817329026988984,
|
1312 |
+
"learning_rate": 4.625542839324036e-05,
|
1313 |
+
"loss": 1.2484,
|
1314 |
+
"step": 183
|
1315 |
+
},
|
1316 |
+
{
|
1317 |
+
"epoch": 0.6148705096073517,
|
1318 |
+
"grad_norm": 0.9479340425567955,
|
1319 |
+
"learning_rate": 4.6207600507762595e-05,
|
1320 |
+
"loss": 1.1593,
|
1321 |
+
"step": 184
|
1322 |
+
},
|
1323 |
+
{
|
1324 |
+
"epoch": 0.6182121971595655,
|
1325 |
+
"grad_norm": 0.9468319510477629,
|
1326 |
+
"learning_rate": 4.615949416883096e-05,
|
1327 |
+
"loss": 1.1732,
|
1328 |
+
"step": 185
|
1329 |
+
},
|
1330 |
+
{
|
1331 |
+
"epoch": 0.6215538847117794,
|
1332 |
+
"grad_norm": 1.10744893638066,
|
1333 |
+
"learning_rate": 4.611111000807637e-05,
|
1334 |
+
"loss": 1.2359,
|
1335 |
+
"step": 186
|
1336 |
+
},
|
1337 |
+
{
|
1338 |
+
"epoch": 0.6248955722639933,
|
1339 |
+
"grad_norm": 1.0229761924680858,
|
1340 |
+
"learning_rate": 4.6062448660777517e-05,
|
1341 |
+
"loss": 1.1828,
|
1342 |
+
"step": 187
|
1343 |
+
},
|
1344 |
+
{
|
1345 |
+
"epoch": 0.6282372598162071,
|
1346 |
+
"grad_norm": 0.921578652654033,
|
1347 |
+
"learning_rate": 4.601351076585253e-05,
|
1348 |
+
"loss": 1.1131,
|
1349 |
+
"step": 188
|
1350 |
+
},
|
1351 |
+
{
|
1352 |
+
"epoch": 0.631578947368421,
|
1353 |
+
"grad_norm": 0.9644681681801379,
|
1354 |
+
"learning_rate": 4.596429696585054e-05,
|
1355 |
+
"loss": 1.2319,
|
1356 |
+
"step": 189
|
1357 |
+
},
|
1358 |
+
{
|
1359 |
+
"epoch": 0.6349206349206349,
|
1360 |
+
"grad_norm": 1.0152012900492065,
|
1361 |
+
"learning_rate": 4.591480790694334e-05,
|
1362 |
+
"loss": 1.229,
|
1363 |
+
"step": 190
|
1364 |
+
},
|
1365 |
+
{
|
1366 |
+
"epoch": 0.6382623224728488,
|
1367 |
+
"grad_norm": 1.0332684046723948,
|
1368 |
+
"learning_rate": 4.5865044238916785e-05,
|
1369 |
+
"loss": 1.2663,
|
1370 |
+
"step": 191
|
1371 |
+
},
|
1372 |
+
{
|
1373 |
+
"epoch": 0.6416040100250626,
|
1374 |
+
"grad_norm": 0.9861329165286253,
|
1375 |
+
"learning_rate": 4.581500661516237e-05,
|
1376 |
+
"loss": 1.2411,
|
1377 |
+
"step": 192
|
1378 |
+
},
|
1379 |
+
{
|
1380 |
+
"epoch": 0.6449456975772765,
|
1381 |
+
"grad_norm": 1.008947869019847,
|
1382 |
+
"learning_rate": 4.576469569266856e-05,
|
1383 |
+
"loss": 1.1937,
|
1384 |
+
"step": 193
|
1385 |
+
},
|
1386 |
+
{
|
1387 |
+
"epoch": 0.6482873851294904,
|
1388 |
+
"grad_norm": 1.0351378349442564,
|
1389 |
+
"learning_rate": 4.57141121320122e-05,
|
1390 |
+
"loss": 1.2424,
|
1391 |
+
"step": 194
|
1392 |
+
},
|
1393 |
+
{
|
1394 |
+
"epoch": 0.6516290726817042,
|
1395 |
+
"grad_norm": 1.1292027980790191,
|
1396 |
+
"learning_rate": 4.5663256597349874e-05,
|
1397 |
+
"loss": 1.1868,
|
1398 |
+
"step": 195
|
1399 |
+
},
|
1400 |
+
{
|
1401 |
+
"epoch": 0.6549707602339181,
|
1402 |
+
"grad_norm": 1.1325783369030435,
|
1403 |
+
"learning_rate": 4.561212975640914e-05,
|
1404 |
+
"loss": 1.1521,
|
1405 |
+
"step": 196
|
1406 |
+
},
|
1407 |
+
{
|
1408 |
+
"epoch": 0.658312447786132,
|
1409 |
+
"grad_norm": 1.0325656509927605,
|
1410 |
+
"learning_rate": 4.556073228047977e-05,
|
1411 |
+
"loss": 1.178,
|
1412 |
+
"step": 197
|
1413 |
+
},
|
1414 |
+
{
|
1415 |
+
"epoch": 0.6616541353383458,
|
1416 |
+
"grad_norm": 1.1093263598080985,
|
1417 |
+
"learning_rate": 4.550906484440495e-05,
|
1418 |
+
"loss": 1.1982,
|
1419 |
+
"step": 198
|
1420 |
+
},
|
1421 |
+
{
|
1422 |
+
"epoch": 0.6649958228905597,
|
1423 |
+
"grad_norm": 1.114711642213788,
|
1424 |
+
"learning_rate": 4.5457128126572423e-05,
|
1425 |
+
"loss": 1.1487,
|
1426 |
+
"step": 199
|
1427 |
+
},
|
1428 |
+
{
|
1429 |
+
"epoch": 0.6683375104427736,
|
1430 |
+
"grad_norm": 0.9847883166674106,
|
1431 |
+
"learning_rate": 4.540492280890555e-05,
|
1432 |
+
"loss": 1.2062,
|
1433 |
+
"step": 200
|
1434 |
+
},
|
1435 |
+
{
|
1436 |
+
"epoch": 0.6716791979949874,
|
1437 |
+
"grad_norm": 1.1686727604239142,
|
1438 |
+
"learning_rate": 4.5352449576854384e-05,
|
1439 |
+
"loss": 1.278,
|
1440 |
+
"step": 201
|
1441 |
+
},
|
1442 |
+
{
|
1443 |
+
"epoch": 0.6750208855472013,
|
1444 |
+
"grad_norm": 1.017923076403849,
|
1445 |
+
"learning_rate": 4.529970911938669e-05,
|
1446 |
+
"loss": 1.1474,
|
1447 |
+
"step": 202
|
1448 |
+
},
|
1449 |
+
{
|
1450 |
+
"epoch": 0.6783625730994152,
|
1451 |
+
"grad_norm": 1.040704866427295,
|
1452 |
+
"learning_rate": 4.524670212897884e-05,
|
1453 |
+
"loss": 1.076,
|
1454 |
+
"step": 203
|
1455 |
+
},
|
1456 |
+
{
|
1457 |
+
"epoch": 0.681704260651629,
|
1458 |
+
"grad_norm": 1.0235899496431877,
|
1459 |
+
"learning_rate": 4.519342930160677e-05,
|
1460 |
+
"loss": 1.2,
|
1461 |
+
"step": 204
|
1462 |
+
},
|
1463 |
+
{
|
1464 |
+
"epoch": 0.6850459482038429,
|
1465 |
+
"grad_norm": 1.0833283292346052,
|
1466 |
+
"learning_rate": 4.5139891336736817e-05,
|
1467 |
+
"loss": 1.2234,
|
1468 |
+
"step": 205
|
1469 |
+
},
|
1470 |
+
{
|
1471 |
+
"epoch": 0.6883876357560568,
|
1472 |
+
"grad_norm": 1.0293109987669598,
|
1473 |
+
"learning_rate": 4.5086088937316565e-05,
|
1474 |
+
"loss": 1.1714,
|
1475 |
+
"step": 206
|
1476 |
+
},
|
1477 |
+
{
|
1478 |
+
"epoch": 0.6917293233082706,
|
1479 |
+
"grad_norm": 0.931945516283699,
|
1480 |
+
"learning_rate": 4.503202280976557e-05,
|
1481 |
+
"loss": 1.1223,
|
1482 |
+
"step": 207
|
1483 |
+
},
|
1484 |
+
{
|
1485 |
+
"epoch": 0.6950710108604845,
|
1486 |
+
"grad_norm": 1.0662949673683302,
|
1487 |
+
"learning_rate": 4.4977693663966124e-05,
|
1488 |
+
"loss": 1.1281,
|
1489 |
+
"step": 208
|
1490 |
+
},
|
1491 |
+
{
|
1492 |
+
"epoch": 0.6984126984126984,
|
1493 |
+
"grad_norm": 0.9541479357274659,
|
1494 |
+
"learning_rate": 4.492310221325391e-05,
|
1495 |
+
"loss": 1.1739,
|
1496 |
+
"step": 209
|
1497 |
+
},
|
1498 |
+
{
|
1499 |
+
"epoch": 0.7017543859649122,
|
1500 |
+
"grad_norm": 2.071821186380696,
|
1501 |
+
"learning_rate": 4.486824917440865e-05,
|
1502 |
+
"loss": 1.1923,
|
1503 |
+
"step": 210
|
1504 |
+
},
|
1505 |
+
{
|
1506 |
+
"epoch": 0.7050960735171261,
|
1507 |
+
"grad_norm": 0.946134090841913,
|
1508 |
+
"learning_rate": 4.4813135267644693e-05,
|
1509 |
+
"loss": 1.1303,
|
1510 |
+
"step": 211
|
1511 |
+
},
|
1512 |
+
{
|
1513 |
+
"epoch": 0.70843776106934,
|
1514 |
+
"grad_norm": 0.9842294673980075,
|
1515 |
+
"learning_rate": 4.475776121660156e-05,
|
1516 |
+
"loss": 1.1622,
|
1517 |
+
"step": 212
|
1518 |
+
},
|
1519 |
+
{
|
1520 |
+
"epoch": 0.7117794486215538,
|
1521 |
+
"grad_norm": 1.0173127525141705,
|
1522 |
+
"learning_rate": 4.4702127748334406e-05,
|
1523 |
+
"loss": 1.2342,
|
1524 |
+
"step": 213
|
1525 |
+
},
|
1526 |
+
{
|
1527 |
+
"epoch": 0.7151211361737677,
|
1528 |
+
"grad_norm": 1.0630978432447922,
|
1529 |
+
"learning_rate": 4.464623559330454e-05,
|
1530 |
+
"loss": 1.2226,
|
1531 |
+
"step": 214
|
1532 |
+
},
|
1533 |
+
{
|
1534 |
+
"epoch": 0.7184628237259816,
|
1535 |
+
"grad_norm": 0.8998677964481709,
|
1536 |
+
"learning_rate": 4.4590085485369805e-05,
|
1537 |
+
"loss": 1.1362,
|
1538 |
+
"step": 215
|
1539 |
+
},
|
1540 |
+
{
|
1541 |
+
"epoch": 0.7218045112781954,
|
1542 |
+
"grad_norm": 0.9647726772859397,
|
1543 |
+
"learning_rate": 4.4533678161774894e-05,
|
1544 |
+
"loss": 1.2361,
|
1545 |
+
"step": 216
|
1546 |
+
},
|
1547 |
+
{
|
1548 |
+
"epoch": 0.7251461988304093,
|
1549 |
+
"grad_norm": 0.9048508500249858,
|
1550 |
+
"learning_rate": 4.447701436314176e-05,
|
1551 |
+
"loss": 1.2976,
|
1552 |
+
"step": 217
|
1553 |
+
},
|
1554 |
+
{
|
1555 |
+
"epoch": 0.7284878863826232,
|
1556 |
+
"grad_norm": 1.080255188574221,
|
1557 |
+
"learning_rate": 4.4420094833459816e-05,
|
1558 |
+
"loss": 1.2975,
|
1559 |
+
"step": 218
|
1560 |
+
},
|
1561 |
+
{
|
1562 |
+
"epoch": 0.731829573934837,
|
1563 |
+
"grad_norm": 0.9486611908437018,
|
1564 |
+
"learning_rate": 4.4362920320076203e-05,
|
1565 |
+
"loss": 1.1322,
|
1566 |
+
"step": 219
|
1567 |
+
},
|
1568 |
+
{
|
1569 |
+
"epoch": 0.7351712614870509,
|
1570 |
+
"grad_norm": 0.89345410355984,
|
1571 |
+
"learning_rate": 4.430549157368598e-05,
|
1572 |
+
"loss": 1.1604,
|
1573 |
+
"step": 220
|
1574 |
+
},
|
1575 |
+
{
|
1576 |
+
"epoch": 0.7385129490392648,
|
1577 |
+
"grad_norm": 0.925519861323049,
|
1578 |
+
"learning_rate": 4.424780934832223e-05,
|
1579 |
+
"loss": 1.1733,
|
1580 |
+
"step": 221
|
1581 |
+
},
|
1582 |
+
{
|
1583 |
+
"epoch": 0.7418546365914787,
|
1584 |
+
"grad_norm": 0.9646295572099951,
|
1585 |
+
"learning_rate": 4.418987440134623e-05,
|
1586 |
+
"loss": 1.2468,
|
1587 |
+
"step": 222
|
1588 |
+
},
|
1589 |
+
{
|
1590 |
+
"epoch": 0.7451963241436925,
|
1591 |
+
"grad_norm": 1.0732651206685428,
|
1592 |
+
"learning_rate": 4.4131687493437425e-05,
|
1593 |
+
"loss": 1.3618,
|
1594 |
+
"step": 223
|
1595 |
+
},
|
1596 |
+
{
|
1597 |
+
"epoch": 0.7485380116959064,
|
1598 |
+
"grad_norm": 0.9938198279222078,
|
1599 |
+
"learning_rate": 4.407324938858349e-05,
|
1600 |
+
"loss": 1.186,
|
1601 |
+
"step": 224
|
1602 |
+
},
|
1603 |
+
{
|
1604 |
+
"epoch": 0.7518796992481203,
|
1605 |
+
"grad_norm": 0.8479511606829426,
|
1606 |
+
"learning_rate": 4.4014560854070294e-05,
|
1607 |
+
"loss": 1.1178,
|
1608 |
+
"step": 225
|
1609 |
+
},
|
1610 |
+
{
|
1611 |
+
"epoch": 0.7518796992481203,
|
1612 |
+
"eval_loss": 1.3396790027618408,
|
1613 |
+
"eval_runtime": 51.706,
|
1614 |
+
"eval_samples_per_second": 0.425,
|
1615 |
+
"eval_steps_per_second": 0.116,
|
1616 |
+
"step": 225
|
1617 |
+
},
|
1618 |
+
{
|
1619 |
+
"epoch": 0.7552213868003341,
|
1620 |
+
"grad_norm": 1.0263232831005216,
|
1621 |
+
"learning_rate": 4.395562266047182e-05,
|
1622 |
+
"loss": 1.1985,
|
1623 |
+
"step": 226
|
1624 |
+
},
|
1625 |
+
{
|
1626 |
+
"epoch": 0.758563074352548,
|
1627 |
+
"grad_norm": 0.8840382430386312,
|
1628 |
+
"learning_rate": 4.389643558164005e-05,
|
1629 |
+
"loss": 1.2017,
|
1630 |
+
"step": 227
|
1631 |
+
},
|
1632 |
+
{
|
1633 |
+
"epoch": 0.7619047619047619,
|
1634 |
+
"grad_norm": 0.9118616467182596,
|
1635 |
+
"learning_rate": 4.3837000394694796e-05,
|
1636 |
+
"loss": 1.192,
|
1637 |
+
"step": 228
|
1638 |
+
},
|
1639 |
+
{
|
1640 |
+
"epoch": 0.7652464494569757,
|
1641 |
+
"grad_norm": 0.89293130650277,
|
1642 |
+
"learning_rate": 4.377731788001349e-05,
|
1643 |
+
"loss": 1.1352,
|
1644 |
+
"step": 229
|
1645 |
+
},
|
1646 |
+
{
|
1647 |
+
"epoch": 0.7685881370091896,
|
1648 |
+
"grad_norm": 0.9807040646828536,
|
1649 |
+
"learning_rate": 4.371738882122096e-05,
|
1650 |
+
"loss": 1.1844,
|
1651 |
+
"step": 230
|
1652 |
+
},
|
1653 |
+
{
|
1654 |
+
"epoch": 0.7719298245614035,
|
1655 |
+
"grad_norm": 0.9931440422332504,
|
1656 |
+
"learning_rate": 4.365721400517916e-05,
|
1657 |
+
"loss": 1.15,
|
1658 |
+
"step": 231
|
1659 |
+
},
|
1660 |
+
{
|
1661 |
+
"epoch": 0.7752715121136173,
|
1662 |
+
"grad_norm": 1.0024474435465867,
|
1663 |
+
"learning_rate": 4.3596794221976754e-05,
|
1664 |
+
"loss": 1.2061,
|
1665 |
+
"step": 232
|
1666 |
+
},
|
1667 |
+
{
|
1668 |
+
"epoch": 0.7786131996658312,
|
1669 |
+
"grad_norm": 1.0199022805752922,
|
1670 |
+
"learning_rate": 4.353613026491884e-05,
|
1671 |
+
"loss": 1.2361,
|
1672 |
+
"step": 233
|
1673 |
+
},
|
1674 |
+
{
|
1675 |
+
"epoch": 0.7819548872180451,
|
1676 |
+
"grad_norm": 1.0050111475791503,
|
1677 |
+
"learning_rate": 4.347522293051648e-05,
|
1678 |
+
"loss": 1.1731,
|
1679 |
+
"step": 234
|
1680 |
+
},
|
1681 |
+
{
|
1682 |
+
"epoch": 0.7852965747702589,
|
1683 |
+
"grad_norm": 0.9751355856732374,
|
1684 |
+
"learning_rate": 4.341407301847625e-05,
|
1685 |
+
"loss": 1.0678,
|
1686 |
+
"step": 235
|
1687 |
+
},
|
1688 |
+
{
|
1689 |
+
"epoch": 0.7886382623224728,
|
1690 |
+
"grad_norm": 0.9149580750612679,
|
1691 |
+
"learning_rate": 4.335268133168974e-05,
|
1692 |
+
"loss": 1.039,
|
1693 |
+
"step": 236
|
1694 |
+
},
|
1695 |
+
{
|
1696 |
+
"epoch": 0.7919799498746867,
|
1697 |
+
"grad_norm": 0.96847442090601,
|
1698 |
+
"learning_rate": 4.329104867622302e-05,
|
1699 |
+
"loss": 1.241,
|
1700 |
+
"step": 237
|
1701 |
+
},
|
1702 |
+
{
|
1703 |
+
"epoch": 0.7953216374269005,
|
1704 |
+
"grad_norm": 0.9528602038954359,
|
1705 |
+
"learning_rate": 4.322917586130607e-05,
|
1706 |
+
"loss": 1.1732,
|
1707 |
+
"step": 238
|
1708 |
+
},
|
1709 |
+
{
|
1710 |
+
"epoch": 0.7986633249791144,
|
1711 |
+
"grad_norm": 0.9877273980590553,
|
1712 |
+
"learning_rate": 4.3167063699322105e-05,
|
1713 |
+
"loss": 1.1754,
|
1714 |
+
"step": 239
|
1715 |
+
},
|
1716 |
+
{
|
1717 |
+
"epoch": 0.8020050125313283,
|
1718 |
+
"grad_norm": 0.8682490913678883,
|
1719 |
+
"learning_rate": 4.310471300579697e-05,
|
1720 |
+
"loss": 1.1168,
|
1721 |
+
"step": 240
|
1722 |
+
},
|
1723 |
+
{
|
1724 |
+
"epoch": 0.8053467000835421,
|
1725 |
+
"grad_norm": 0.9028917199681886,
|
1726 |
+
"learning_rate": 4.304212459938837e-05,
|
1727 |
+
"loss": 1.1157,
|
1728 |
+
"step": 241
|
1729 |
+
},
|
1730 |
+
{
|
1731 |
+
"epoch": 0.808688387635756,
|
1732 |
+
"grad_norm": 0.9101708543226708,
|
1733 |
+
"learning_rate": 4.2979299301875184e-05,
|
1734 |
+
"loss": 1.1691,
|
1735 |
+
"step": 242
|
1736 |
+
},
|
1737 |
+
{
|
1738 |
+
"epoch": 0.8120300751879699,
|
1739 |
+
"grad_norm": 0.941286833245439,
|
1740 |
+
"learning_rate": 4.291623793814663e-05,
|
1741 |
+
"loss": 1.0917,
|
1742 |
+
"step": 243
|
1743 |
+
},
|
1744 |
+
{
|
1745 |
+
"epoch": 0.8153717627401837,
|
1746 |
+
"grad_norm": 0.9423441770657718,
|
1747 |
+
"learning_rate": 4.2852941336191466e-05,
|
1748 |
+
"loss": 1.1437,
|
1749 |
+
"step": 244
|
1750 |
+
},
|
1751 |
+
{
|
1752 |
+
"epoch": 0.8187134502923976,
|
1753 |
+
"grad_norm": 1.0019357611904858,
|
1754 |
+
"learning_rate": 4.278941032708707e-05,
|
1755 |
+
"loss": 1.2297,
|
1756 |
+
"step": 245
|
1757 |
+
},
|
1758 |
+
{
|
1759 |
+
"epoch": 0.8220551378446115,
|
1760 |
+
"grad_norm": 0.9134116880628933,
|
1761 |
+
"learning_rate": 4.27256457449886e-05,
|
1762 |
+
"loss": 1.1763,
|
1763 |
+
"step": 246
|
1764 |
+
},
|
1765 |
+
{
|
1766 |
+
"epoch": 0.8253968253968254,
|
1767 |
+
"grad_norm": 0.8593707359603224,
|
1768 |
+
"learning_rate": 4.266164842711796e-05,
|
1769 |
+
"loss": 1.097,
|
1770 |
+
"step": 247
|
1771 |
+
},
|
1772 |
+
{
|
1773 |
+
"epoch": 0.8287385129490392,
|
1774 |
+
"grad_norm": 0.9830714729124798,
|
1775 |
+
"learning_rate": 4.259741921375289e-05,
|
1776 |
+
"loss": 1.1476,
|
1777 |
+
"step": 248
|
1778 |
+
},
|
1779 |
+
{
|
1780 |
+
"epoch": 0.8320802005012531,
|
1781 |
+
"grad_norm": 1.0481652922328473,
|
1782 |
+
"learning_rate": 4.253295894821585e-05,
|
1783 |
+
"loss": 1.2401,
|
1784 |
+
"step": 249
|
1785 |
+
},
|
1786 |
+
{
|
1787 |
+
"epoch": 0.835421888053467,
|
1788 |
+
"grad_norm": 0.8568238111856314,
|
1789 |
+
"learning_rate": 4.246826847686303e-05,
|
1790 |
+
"loss": 1.1432,
|
1791 |
+
"step": 250
|
1792 |
+
},
|
1793 |
+
{
|
1794 |
+
"epoch": 0.8387635756056808,
|
1795 |
+
"grad_norm": 0.951730861839824,
|
1796 |
+
"learning_rate": 4.2403348649073174e-05,
|
1797 |
+
"loss": 1.115,
|
1798 |
+
"step": 251
|
1799 |
+
},
|
1800 |
+
{
|
1801 |
+
"epoch": 0.8421052631578947,
|
1802 |
+
"grad_norm": 1.1229791547441785,
|
1803 |
+
"learning_rate": 4.2338200317236445e-05,
|
1804 |
+
"loss": 1.2719,
|
1805 |
+
"step": 252
|
1806 |
+
},
|
1807 |
+
{
|
1808 |
+
"epoch": 0.8454469507101086,
|
1809 |
+
"grad_norm": 0.8979754621416325,
|
1810 |
+
"learning_rate": 4.2272824336743266e-05,
|
1811 |
+
"loss": 1.1643,
|
1812 |
+
"step": 253
|
1813 |
+
},
|
1814 |
+
{
|
1815 |
+
"epoch": 0.8487886382623224,
|
1816 |
+
"grad_norm": 1.1038784526628656,
|
1817 |
+
"learning_rate": 4.220722156597303e-05,
|
1818 |
+
"loss": 1.1755,
|
1819 |
+
"step": 254
|
1820 |
+
},
|
1821 |
+
{
|
1822 |
+
"epoch": 0.8521303258145363,
|
1823 |
+
"grad_norm": 0.8904169165772989,
|
1824 |
+
"learning_rate": 4.214139286628289e-05,
|
1825 |
+
"loss": 1.2078,
|
1826 |
+
"step": 255
|
1827 |
+
},
|
1828 |
+
{
|
1829 |
+
"epoch": 0.8554720133667502,
|
1830 |
+
"grad_norm": 1.0101893594108817,
|
1831 |
+
"learning_rate": 4.2075339101996394e-05,
|
1832 |
+
"loss": 1.188,
|
1833 |
+
"step": 256
|
1834 |
+
},
|
1835 |
+
{
|
1836 |
+
"epoch": 0.858813700918964,
|
1837 |
+
"grad_norm": 1.011947430714437,
|
1838 |
+
"learning_rate": 4.200906114039219e-05,
|
1839 |
+
"loss": 1.1815,
|
1840 |
+
"step": 257
|
1841 |
+
},
|
1842 |
+
{
|
1843 |
+
"epoch": 0.8621553884711779,
|
1844 |
+
"grad_norm": 1.0113920659899747,
|
1845 |
+
"learning_rate": 4.1942559851692586e-05,
|
1846 |
+
"loss": 1.1087,
|
1847 |
+
"step": 258
|
1848 |
+
},
|
1849 |
+
{
|
1850 |
+
"epoch": 0.8654970760233918,
|
1851 |
+
"grad_norm": 0.9436397647208052,
|
1852 |
+
"learning_rate": 4.1875836109052166e-05,
|
1853 |
+
"loss": 1.2688,
|
1854 |
+
"step": 259
|
1855 |
+
},
|
1856 |
+
{
|
1857 |
+
"epoch": 0.8688387635756056,
|
1858 |
+
"grad_norm": 0.9538949648911943,
|
1859 |
+
"learning_rate": 4.1808890788546316e-05,
|
1860 |
+
"loss": 1.1751,
|
1861 |
+
"step": 260
|
1862 |
+
},
|
1863 |
+
{
|
1864 |
+
"epoch": 0.8721804511278195,
|
1865 |
+
"grad_norm": 0.9935140809640558,
|
1866 |
+
"learning_rate": 4.17417247691597e-05,
|
1867 |
+
"loss": 1.1957,
|
1868 |
+
"step": 261
|
1869 |
+
},
|
1870 |
+
{
|
1871 |
+
"epoch": 0.8755221386800334,
|
1872 |
+
"grad_norm": 1.0792620651192726,
|
1873 |
+
"learning_rate": 4.1674338932774724e-05,
|
1874 |
+
"loss": 1.1847,
|
1875 |
+
"step": 262
|
1876 |
+
},
|
1877 |
+
{
|
1878 |
+
"epoch": 0.8788638262322472,
|
1879 |
+
"grad_norm": 1.1124795931921556,
|
1880 |
+
"learning_rate": 4.160673416416e-05,
|
1881 |
+
"loss": 1.1018,
|
1882 |
+
"step": 263
|
1883 |
+
},
|
1884 |
+
{
|
1885 |
+
"epoch": 0.8822055137844611,
|
1886 |
+
"grad_norm": 0.9002781532445973,
|
1887 |
+
"learning_rate": 4.153891135095866e-05,
|
1888 |
+
"loss": 1.2307,
|
1889 |
+
"step": 264
|
1890 |
+
},
|
1891 |
+
{
|
1892 |
+
"epoch": 0.885547201336675,
|
1893 |
+
"grad_norm": 0.9732414915209471,
|
1894 |
+
"learning_rate": 4.147087138367678e-05,
|
1895 |
+
"loss": 1.1941,
|
1896 |
+
"step": 265
|
1897 |
+
},
|
1898 |
+
{
|
1899 |
+
"epoch": 0.8888888888888888,
|
1900 |
+
"grad_norm": 1.0519997656823685,
|
1901 |
+
"learning_rate": 4.140261515567161e-05,
|
1902 |
+
"loss": 1.2149,
|
1903 |
+
"step": 266
|
1904 |
+
},
|
1905 |
+
{
|
1906 |
+
"epoch": 0.8922305764411027,
|
1907 |
+
"grad_norm": 0.9408286276236255,
|
1908 |
+
"learning_rate": 4.133414356313988e-05,
|
1909 |
+
"loss": 1.1152,
|
1910 |
+
"step": 267
|
1911 |
+
},
|
1912 |
+
{
|
1913 |
+
"epoch": 0.8955722639933166,
|
1914 |
+
"grad_norm": 0.852983888206745,
|
1915 |
+
"learning_rate": 4.126545750510605e-05,
|
1916 |
+
"loss": 1.1358,
|
1917 |
+
"step": 268
|
1918 |
+
},
|
1919 |
+
{
|
1920 |
+
"epoch": 0.8989139515455304,
|
1921 |
+
"grad_norm": 0.9108913540249899,
|
1922 |
+
"learning_rate": 4.119655788341049e-05,
|
1923 |
+
"loss": 1.0862,
|
1924 |
+
"step": 269
|
1925 |
+
},
|
1926 |
+
{
|
1927 |
+
"epoch": 0.9022556390977443,
|
1928 |
+
"grad_norm": 1.0060408412169828,
|
1929 |
+
"learning_rate": 4.112744560269761e-05,
|
1930 |
+
"loss": 1.1956,
|
1931 |
+
"step": 270
|
1932 |
+
},
|
1933 |
+
{
|
1934 |
+
"epoch": 0.9055973266499582,
|
1935 |
+
"grad_norm": 0.9488425518665664,
|
1936 |
+
"learning_rate": 4.105812157040404e-05,
|
1937 |
+
"loss": 1.1394,
|
1938 |
+
"step": 271
|
1939 |
+
},
|
1940 |
+
{
|
1941 |
+
"epoch": 0.908939014202172,
|
1942 |
+
"grad_norm": 0.9505931035562328,
|
1943 |
+
"learning_rate": 4.0988586696746674e-05,
|
1944 |
+
"loss": 1.293,
|
1945 |
+
"step": 272
|
1946 |
+
},
|
1947 |
+
{
|
1948 |
+
"epoch": 0.9122807017543859,
|
1949 |
+
"grad_norm": 0.9683900073885866,
|
1950 |
+
"learning_rate": 4.0918841894710715e-05,
|
1951 |
+
"loss": 1.2315,
|
1952 |
+
"step": 273
|
1953 |
+
},
|
1954 |
+
{
|
1955 |
+
"epoch": 0.9156223893065998,
|
1956 |
+
"grad_norm": 1.1528253800969626,
|
1957 |
+
"learning_rate": 4.084888808003773e-05,
|
1958 |
+
"loss": 1.2716,
|
1959 |
+
"step": 274
|
1960 |
+
},
|
1961 |
+
{
|
1962 |
+
"epoch": 0.9189640768588136,
|
1963 |
+
"grad_norm": 1.1069496791164177,
|
1964 |
+
"learning_rate": 4.0778726171213576e-05,
|
1965 |
+
"loss": 1.1983,
|
1966 |
+
"step": 275
|
1967 |
+
},
|
1968 |
+
{
|
1969 |
+
"epoch": 0.9223057644110275,
|
1970 |
+
"grad_norm": 0.8548083007702836,
|
1971 |
+
"learning_rate": 4.070835708945637e-05,
|
1972 |
+
"loss": 1.1328,
|
1973 |
+
"step": 276
|
1974 |
+
},
|
1975 |
+
{
|
1976 |
+
"epoch": 0.9256474519632414,
|
1977 |
+
"grad_norm": 0.9407270915469085,
|
1978 |
+
"learning_rate": 4.06377817587044e-05,
|
1979 |
+
"loss": 1.0841,
|
1980 |
+
"step": 277
|
1981 |
+
},
|
1982 |
+
{
|
1983 |
+
"epoch": 0.9289891395154553,
|
1984 |
+
"grad_norm": 0.8954694904440085,
|
1985 |
+
"learning_rate": 4.056700110560395e-05,
|
1986 |
+
"loss": 1.214,
|
1987 |
+
"step": 278
|
1988 |
+
},
|
1989 |
+
{
|
1990 |
+
"epoch": 0.9323308270676691,
|
1991 |
+
"grad_norm": 0.8961801390402134,
|
1992 |
+
"learning_rate": 4.0496016059497204e-05,
|
1993 |
+
"loss": 1.1721,
|
1994 |
+
"step": 279
|
1995 |
+
},
|
1996 |
+
{
|
1997 |
+
"epoch": 0.935672514619883,
|
1998 |
+
"grad_norm": 0.9760649547793313,
|
1999 |
+
"learning_rate": 4.042482755240997e-05,
|
2000 |
+
"loss": 1.2666,
|
2001 |
+
"step": 280
|
2002 |
+
},
|
2003 |
+
{
|
2004 |
+
"epoch": 0.9390142021720969,
|
2005 |
+
"grad_norm": 0.9643787134332955,
|
2006 |
+
"learning_rate": 4.035343651903949e-05,
|
2007 |
+
"loss": 1.1683,
|
2008 |
+
"step": 281
|
2009 |
+
},
|
2010 |
+
{
|
2011 |
+
"epoch": 0.9423558897243107,
|
2012 |
+
"grad_norm": 0.9626450895839377,
|
2013 |
+
"learning_rate": 4.0281843896742155e-05,
|
2014 |
+
"loss": 1.2133,
|
2015 |
+
"step": 282
|
2016 |
+
},
|
2017 |
+
{
|
2018 |
+
"epoch": 0.9456975772765246,
|
2019 |
+
"grad_norm": 1.2541266295867288,
|
2020 |
+
"learning_rate": 4.021005062552119e-05,
|
2021 |
+
"loss": 1.3502,
|
2022 |
+
"step": 283
|
2023 |
+
},
|
2024 |
+
{
|
2025 |
+
"epoch": 0.9490392648287385,
|
2026 |
+
"grad_norm": 1.0881131031114393,
|
2027 |
+
"learning_rate": 4.013805764801433e-05,
|
2028 |
+
"loss": 1.3208,
|
2029 |
+
"step": 284
|
2030 |
+
},
|
2031 |
+
{
|
2032 |
+
"epoch": 0.9523809523809523,
|
2033 |
+
"grad_norm": 0.8574920416716059,
|
2034 |
+
"learning_rate": 4.0065865909481417e-05,
|
2035 |
+
"loss": 1.1393,
|
2036 |
+
"step": 285
|
2037 |
+
},
|
2038 |
+
{
|
2039 |
+
"epoch": 0.9557226399331662,
|
2040 |
+
"grad_norm": 1.0510895540058778,
|
2041 |
+
"learning_rate": 3.9993476357792006e-05,
|
2042 |
+
"loss": 1.117,
|
2043 |
+
"step": 286
|
2044 |
+
},
|
2045 |
+
{
|
2046 |
+
"epoch": 0.9590643274853801,
|
2047 |
+
"grad_norm": 1.1533745861348077,
|
2048 |
+
"learning_rate": 3.992088994341292e-05,
|
2049 |
+
"loss": 1.2447,
|
2050 |
+
"step": 287
|
2051 |
+
},
|
2052 |
+
{
|
2053 |
+
"epoch": 0.9624060150375939,
|
2054 |
+
"grad_norm": 1.1105061332917363,
|
2055 |
+
"learning_rate": 3.984810761939578e-05,
|
2056 |
+
"loss": 1.216,
|
2057 |
+
"step": 288
|
2058 |
+
},
|
2059 |
+
{
|
2060 |
+
"epoch": 0.9657477025898078,
|
2061 |
+
"grad_norm": 0.9160630967149809,
|
2062 |
+
"learning_rate": 3.977513034136446e-05,
|
2063 |
+
"loss": 1.1986,
|
2064 |
+
"step": 289
|
2065 |
+
},
|
2066 |
+
{
|
2067 |
+
"epoch": 0.9690893901420217,
|
2068 |
+
"grad_norm": 0.8445853392627862,
|
2069 |
+
"learning_rate": 3.9701959067502564e-05,
|
2070 |
+
"loss": 1.1836,
|
2071 |
+
"step": 290
|
2072 |
+
},
|
2073 |
+
{
|
2074 |
+
"epoch": 0.9724310776942355,
|
2075 |
+
"grad_norm": 1.0668457057222869,
|
2076 |
+
"learning_rate": 3.9628594758540846e-05,
|
2077 |
+
"loss": 1.2284,
|
2078 |
+
"step": 291
|
2079 |
+
},
|
2080 |
+
{
|
2081 |
+
"epoch": 0.9757727652464494,
|
2082 |
+
"grad_norm": 0.9615370660038071,
|
2083 |
+
"learning_rate": 3.955503837774458e-05,
|
2084 |
+
"loss": 1.2016,
|
2085 |
+
"step": 292
|
2086 |
+
},
|
2087 |
+
{
|
2088 |
+
"epoch": 0.9791144527986633,
|
2089 |
+
"grad_norm": 0.9680542745347342,
|
2090 |
+
"learning_rate": 3.948129089090093e-05,
|
2091 |
+
"loss": 1.2164,
|
2092 |
+
"step": 293
|
2093 |
+
},
|
2094 |
+
{
|
2095 |
+
"epoch": 0.9824561403508771,
|
2096 |
+
"grad_norm": 0.9371176041766707,
|
2097 |
+
"learning_rate": 3.940735326630626e-05,
|
2098 |
+
"loss": 1.1087,
|
2099 |
+
"step": 294
|
2100 |
+
},
|
2101 |
+
{
|
2102 |
+
"epoch": 0.985797827903091,
|
2103 |
+
"grad_norm": 0.9053132575442242,
|
2104 |
+
"learning_rate": 3.933322647475342e-05,
|
2105 |
+
"loss": 1.0848,
|
2106 |
+
"step": 295
|
2107 |
+
},
|
2108 |
+
{
|
2109 |
+
"epoch": 0.9891395154553049,
|
2110 |
+
"grad_norm": 0.9933354429608345,
|
2111 |
+
"learning_rate": 3.925891148951899e-05,
|
2112 |
+
"loss": 1.2221,
|
2113 |
+
"step": 296
|
2114 |
+
},
|
2115 |
+
{
|
2116 |
+
"epoch": 0.9924812030075187,
|
2117 |
+
"grad_norm": 0.8955568637463743,
|
2118 |
+
"learning_rate": 3.9184409286350535e-05,
|
2119 |
+
"loss": 1.2599,
|
2120 |
+
"step": 297
|
2121 |
+
},
|
2122 |
+
{
|
2123 |
+
"epoch": 0.9958228905597326,
|
2124 |
+
"grad_norm": 0.8938226719609199,
|
2125 |
+
"learning_rate": 3.9109720843453756e-05,
|
2126 |
+
"loss": 1.0711,
|
2127 |
+
"step": 298
|
2128 |
+
},
|
2129 |
+
{
|
2130 |
+
"epoch": 0.9991645781119465,
|
2131 |
+
"grad_norm": 0.8770884720680571,
|
2132 |
+
"learning_rate": 3.903484714147967e-05,
|
2133 |
+
"loss": 1.1786,
|
2134 |
+
"step": 299
|
2135 |
+
},
|
2136 |
+
{
|
2137 |
+
"epoch": 1.0033409897682188,
|
2138 |
+
"grad_norm": 1.0959093164885338,
|
2139 |
+
"learning_rate": 3.895978916351172e-05,
|
2140 |
+
"loss": 0.8299,
|
2141 |
+
"step": 300
|
2142 |
+
},
|
2143 |
+
{
|
2144 |
+
"epoch": 1.0033409897682188,
|
2145 |
+
"eval_loss": 1.3238426446914673,
|
2146 |
+
"eval_runtime": 12.4782,
|
2147 |
+
"eval_samples_per_second": 1.763,
|
2148 |
+
"eval_steps_per_second": 0.481,
|
2149 |
+
"step": 300
|
2150 |
+
},
|
2151 |
+
{
|
2152 |
+
"epoch": 1.0066819795364377,
|
2153 |
+
"grad_norm": 0.9319113991503899,
|
2154 |
+
"learning_rate": 3.8884547895052856e-05,
|
2155 |
+
"loss": 0.873,
|
2156 |
+
"step": 301
|
2157 |
+
},
|
2158 |
+
{
|
2159 |
+
"epoch": 1.0100229693046565,
|
2160 |
+
"grad_norm": 1.009627278160726,
|
2161 |
+
"learning_rate": 3.880912432401265e-05,
|
2162 |
+
"loss": 0.8983,
|
2163 |
+
"step": 302
|
2164 |
+
},
|
2165 |
+
{
|
2166 |
+
"epoch": 1.0133639590728754,
|
2167 |
+
"grad_norm": 1.690445986414234,
|
2168 |
+
"learning_rate": 3.8733519440694244e-05,
|
2169 |
+
"loss": 0.8385,
|
2170 |
+
"step": 303
|
2171 |
+
},
|
2172 |
+
{
|
2173 |
+
"epoch": 1.0167049488410942,
|
2174 |
+
"grad_norm": 0.875475887556019,
|
2175 |
+
"learning_rate": 3.865773423778143e-05,
|
2176 |
+
"loss": 0.8192,
|
2177 |
+
"step": 304
|
2178 |
+
},
|
2179 |
+
{
|
2180 |
+
"epoch": 1.020045938609313,
|
2181 |
+
"grad_norm": 0.9324149051310555,
|
2182 |
+
"learning_rate": 3.858176971032555e-05,
|
2183 |
+
"loss": 0.8446,
|
2184 |
+
"step": 305
|
2185 |
+
},
|
2186 |
+
{
|
2187 |
+
"epoch": 1.0233869283775319,
|
2188 |
+
"grad_norm": 1.0045944824797584,
|
2189 |
+
"learning_rate": 3.850562685573246e-05,
|
2190 |
+
"loss": 0.803,
|
2191 |
+
"step": 306
|
2192 |
+
},
|
2193 |
+
{
|
2194 |
+
"epoch": 1.0267279181457507,
|
2195 |
+
"grad_norm": 1.0153805270432064,
|
2196 |
+
"learning_rate": 3.8429306673749445e-05,
|
2197 |
+
"loss": 0.8434,
|
2198 |
+
"step": 307
|
2199 |
+
},
|
2200 |
+
{
|
2201 |
+
"epoch": 1.0300689079139695,
|
2202 |
+
"grad_norm": 0.8791912191537664,
|
2203 |
+
"learning_rate": 3.835281016645206e-05,
|
2204 |
+
"loss": 0.8122,
|
2205 |
+
"step": 308
|
2206 |
+
},
|
2207 |
+
{
|
2208 |
+
"epoch": 1.0334098976821884,
|
2209 |
+
"grad_norm": 0.955967831714635,
|
2210 |
+
"learning_rate": 3.8276138338231005e-05,
|
2211 |
+
"loss": 0.7475,
|
2212 |
+
"step": 309
|
2213 |
+
},
|
2214 |
+
{
|
2215 |
+
"epoch": 1.0367508874504072,
|
2216 |
+
"grad_norm": 0.9944877643459474,
|
2217 |
+
"learning_rate": 3.819929219577894e-05,
|
2218 |
+
"loss": 0.8238,
|
2219 |
+
"step": 310
|
2220 |
+
},
|
2221 |
+
{
|
2222 |
+
"epoch": 1.040091877218626,
|
2223 |
+
"grad_norm": 0.9143180702052903,
|
2224 |
+
"learning_rate": 3.81222727480772e-05,
|
2225 |
+
"loss": 0.8181,
|
2226 |
+
"step": 311
|
2227 |
+
},
|
2228 |
+
{
|
2229 |
+
"epoch": 1.043432866986845,
|
2230 |
+
"grad_norm": 0.8888974597110828,
|
2231 |
+
"learning_rate": 3.8045081006382665e-05,
|
2232 |
+
"loss": 0.8252,
|
2233 |
+
"step": 312
|
2234 |
+
},
|
2235 |
+
{
|
2236 |
+
"epoch": 1.0467738567550637,
|
2237 |
+
"grad_norm": 0.8959954834332536,
|
2238 |
+
"learning_rate": 3.796771798421437e-05,
|
2239 |
+
"loss": 0.805,
|
2240 |
+
"step": 313
|
2241 |
+
},
|
2242 |
+
{
|
2243 |
+
"epoch": 1.0501148465232826,
|
2244 |
+
"grad_norm": 0.9780665337855439,
|
2245 |
+
"learning_rate": 3.7890184697340245e-05,
|
2246 |
+
"loss": 0.7892,
|
2247 |
+
"step": 314
|
2248 |
+
},
|
2249 |
+
{
|
2250 |
+
"epoch": 1.0534558362915014,
|
2251 |
+
"grad_norm": 0.8280051777925341,
|
2252 |
+
"learning_rate": 3.781248216376381e-05,
|
2253 |
+
"loss": 0.7809,
|
2254 |
+
"step": 315
|
2255 |
+
},
|
2256 |
+
{
|
2257 |
+
"epoch": 1.0567968260597203,
|
2258 |
+
"grad_norm": 0.8113720404769008,
|
2259 |
+
"learning_rate": 3.773461140371074e-05,
|
2260 |
+
"loss": 0.7196,
|
2261 |
+
"step": 316
|
2262 |
+
},
|
2263 |
+
{
|
2264 |
+
"epoch": 1.060137815827939,
|
2265 |
+
"grad_norm": 0.9217003877136911,
|
2266 |
+
"learning_rate": 3.765657343961553e-05,
|
2267 |
+
"loss": 0.7653,
|
2268 |
+
"step": 317
|
2269 |
+
},
|
2270 |
+
{
|
2271 |
+
"epoch": 1.063478805596158,
|
2272 |
+
"grad_norm": 0.9202642653400472,
|
2273 |
+
"learning_rate": 3.757836929610803e-05,
|
2274 |
+
"loss": 0.7139,
|
2275 |
+
"step": 318
|
2276 |
+
},
|
2277 |
+
{
|
2278 |
+
"epoch": 1.0668197953643768,
|
2279 |
+
"grad_norm": 0.7884990227657028,
|
2280 |
+
"learning_rate": 3.7500000000000003e-05,
|
2281 |
+
"loss": 0.7358,
|
2282 |
+
"step": 319
|
2283 |
+
},
|
2284 |
+
{
|
2285 |
+
"epoch": 1.0701607851325956,
|
2286 |
+
"grad_norm": 0.873834596194201,
|
2287 |
+
"learning_rate": 3.742146658027167e-05,
|
2288 |
+
"loss": 0.8052,
|
2289 |
+
"step": 320
|
2290 |
+
},
|
2291 |
+
{
|
2292 |
+
"epoch": 1.0735017749008144,
|
2293 |
+
"grad_norm": 0.9067001826221809,
|
2294 |
+
"learning_rate": 3.7342770068058164e-05,
|
2295 |
+
"loss": 0.701,
|
2296 |
+
"step": 321
|
2297 |
+
},
|
2298 |
+
{
|
2299 |
+
"epoch": 1.0768427646690333,
|
2300 |
+
"grad_norm": 0.9066644745305507,
|
2301 |
+
"learning_rate": 3.7263911496636e-05,
|
2302 |
+
"loss": 0.8394,
|
2303 |
+
"step": 322
|
2304 |
+
},
|
2305 |
+
{
|
2306 |
+
"epoch": 1.0801837544372521,
|
2307 |
+
"grad_norm": 0.8415263526204737,
|
2308 |
+
"learning_rate": 3.7184891901409514e-05,
|
2309 |
+
"loss": 0.7271,
|
2310 |
+
"step": 323
|
2311 |
+
},
|
2312 |
+
{
|
2313 |
+
"epoch": 1.083524744205471,
|
2314 |
+
"grad_norm": 0.8351330407440325,
|
2315 |
+
"learning_rate": 3.7105712319897265e-05,
|
2316 |
+
"loss": 0.7699,
|
2317 |
+
"step": 324
|
2318 |
+
},
|
2319 |
+
{
|
2320 |
+
"epoch": 1.0868657339736898,
|
2321 |
+
"grad_norm": 0.9309652326420155,
|
2322 |
+
"learning_rate": 3.702637379171844e-05,
|
2323 |
+
"loss": 0.7845,
|
2324 |
+
"step": 325
|
2325 |
+
},
|
2326 |
+
{
|
2327 |
+
"epoch": 1.0902067237419086,
|
2328 |
+
"grad_norm": 0.8587868162529135,
|
2329 |
+
"learning_rate": 3.6946877358579134e-05,
|
2330 |
+
"loss": 0.6677,
|
2331 |
+
"step": 326
|
2332 |
+
},
|
2333 |
+
{
|
2334 |
+
"epoch": 1.0935477135101275,
|
2335 |
+
"grad_norm": 0.8257599053579875,
|
2336 |
+
"learning_rate": 3.6867224064258756e-05,
|
2337 |
+
"loss": 0.7815,
|
2338 |
+
"step": 327
|
2339 |
+
},
|
2340 |
+
{
|
2341 |
+
"epoch": 1.0968887032783463,
|
2342 |
+
"grad_norm": 0.9624273655367953,
|
2343 |
+
"learning_rate": 3.6787414954596256e-05,
|
2344 |
+
"loss": 0.7897,
|
2345 |
+
"step": 328
|
2346 |
+
},
|
2347 |
+
{
|
2348 |
+
"epoch": 1.1002296930465651,
|
2349 |
+
"grad_norm": 0.944493059699902,
|
2350 |
+
"learning_rate": 3.670745107747644e-05,
|
2351 |
+
"loss": 0.7673,
|
2352 |
+
"step": 329
|
2353 |
+
},
|
2354 |
+
{
|
2355 |
+
"epoch": 1.1035706828147838,
|
2356 |
+
"grad_norm": 0.929080034116846,
|
2357 |
+
"learning_rate": 3.662733348281619e-05,
|
2358 |
+
"loss": 0.7693,
|
2359 |
+
"step": 330
|
2360 |
+
},
|
2361 |
+
{
|
2362 |
+
"epoch": 1.1069116725830028,
|
2363 |
+
"grad_norm": 0.8423316920482857,
|
2364 |
+
"learning_rate": 3.6547063222550677e-05,
|
2365 |
+
"loss": 0.7417,
|
2366 |
+
"step": 331
|
2367 |
+
},
|
2368 |
+
{
|
2369 |
+
"epoch": 1.1102526623512214,
|
2370 |
+
"grad_norm": 0.8264975113942978,
|
2371 |
+
"learning_rate": 3.6466641350619564e-05,
|
2372 |
+
"loss": 0.7395,
|
2373 |
+
"step": 332
|
2374 |
+
},
|
2375 |
+
{
|
2376 |
+
"epoch": 1.1135936521194403,
|
2377 |
+
"grad_norm": 0.8707111741842398,
|
2378 |
+
"learning_rate": 3.638606892295315e-05,
|
2379 |
+
"loss": 0.7883,
|
2380 |
+
"step": 333
|
2381 |
+
},
|
2382 |
+
{
|
2383 |
+
"epoch": 1.1169346418876591,
|
2384 |
+
"grad_norm": 0.9052159861563299,
|
2385 |
+
"learning_rate": 3.6305346997458516e-05,
|
2386 |
+
"loss": 0.8919,
|
2387 |
+
"step": 334
|
2388 |
+
},
|
2389 |
+
{
|
2390 |
+
"epoch": 1.120275631655878,
|
2391 |
+
"grad_norm": 0.9463481966173595,
|
2392 |
+
"learning_rate": 3.622447663400563e-05,
|
2393 |
+
"loss": 0.8503,
|
2394 |
+
"step": 335
|
2395 |
+
},
|
2396 |
+
{
|
2397 |
+
"epoch": 1.1236166214240968,
|
2398 |
+
"grad_norm": 0.9451500816645809,
|
2399 |
+
"learning_rate": 3.6143458894413465e-05,
|
2400 |
+
"loss": 0.8774,
|
2401 |
+
"step": 336
|
2402 |
+
},
|
2403 |
+
{
|
2404 |
+
"epoch": 1.1269576111923156,
|
2405 |
+
"grad_norm": 0.8932849188786636,
|
2406 |
+
"learning_rate": 3.6062294842435956e-05,
|
2407 |
+
"loss": 0.7277,
|
2408 |
+
"step": 337
|
2409 |
+
},
|
2410 |
+
{
|
2411 |
+
"epoch": 1.1302986009605345,
|
2412 |
+
"grad_norm": 1.030017477004491,
|
2413 |
+
"learning_rate": 3.598098554374818e-05,
|
2414 |
+
"loss": 0.774,
|
2415 |
+
"step": 338
|
2416 |
+
},
|
2417 |
+
{
|
2418 |
+
"epoch": 1.1336395907287533,
|
2419 |
+
"grad_norm": 0.7852586071022029,
|
2420 |
+
"learning_rate": 3.5899532065932237e-05,
|
2421 |
+
"loss": 0.6738,
|
2422 |
+
"step": 339
|
2423 |
+
},
|
2424 |
+
{
|
2425 |
+
"epoch": 1.1369805804969721,
|
2426 |
+
"grad_norm": 0.944466415954939,
|
2427 |
+
"learning_rate": 3.58179354784633e-05,
|
2428 |
+
"loss": 0.6996,
|
2429 |
+
"step": 340
|
2430 |
+
},
|
2431 |
+
{
|
2432 |
+
"epoch": 1.140321570265191,
|
2433 |
+
"grad_norm": 0.8970982702078042,
|
2434 |
+
"learning_rate": 3.573619685269558e-05,
|
2435 |
+
"loss": 0.7989,
|
2436 |
+
"step": 341
|
2437 |
+
},
|
2438 |
+
{
|
2439 |
+
"epoch": 1.1436625600334098,
|
2440 |
+
"grad_norm": 0.8249224078826434,
|
2441 |
+
"learning_rate": 3.565431726184818e-05,
|
2442 |
+
"loss": 0.8146,
|
2443 |
+
"step": 342
|
2444 |
+
},
|
2445 |
+
{
|
2446 |
+
"epoch": 1.1470035498016287,
|
2447 |
+
"grad_norm": 0.8736887097571207,
|
2448 |
+
"learning_rate": 3.5572297780991106e-05,
|
2449 |
+
"loss": 0.6896,
|
2450 |
+
"step": 343
|
2451 |
+
},
|
2452 |
+
{
|
2453 |
+
"epoch": 1.1503445395698475,
|
2454 |
+
"grad_norm": 0.857438817771035,
|
2455 |
+
"learning_rate": 3.549013948703109e-05,
|
2456 |
+
"loss": 0.7344,
|
2457 |
+
"step": 344
|
2458 |
+
},
|
2459 |
+
{
|
2460 |
+
"epoch": 1.1536855293380663,
|
2461 |
+
"grad_norm": 0.8839080957163322,
|
2462 |
+
"learning_rate": 3.540784345869746e-05,
|
2463 |
+
"loss": 0.7072,
|
2464 |
+
"step": 345
|
2465 |
+
},
|
2466 |
+
{
|
2467 |
+
"epoch": 1.1570265191062852,
|
2468 |
+
"grad_norm": 0.8446516748750675,
|
2469 |
+
"learning_rate": 3.532541077652799e-05,
|
2470 |
+
"loss": 0.7722,
|
2471 |
+
"step": 346
|
2472 |
+
},
|
2473 |
+
{
|
2474 |
+
"epoch": 1.160367508874504,
|
2475 |
+
"grad_norm": 0.8988293368576468,
|
2476 |
+
"learning_rate": 3.5242842522854684e-05,
|
2477 |
+
"loss": 0.7905,
|
2478 |
+
"step": 347
|
2479 |
+
},
|
2480 |
+
{
|
2481 |
+
"epoch": 1.1637084986427229,
|
2482 |
+
"grad_norm": 0.8436031700001987,
|
2483 |
+
"learning_rate": 3.5160139781789613e-05,
|
2484 |
+
"loss": 0.8744,
|
2485 |
+
"step": 348
|
2486 |
+
},
|
2487 |
+
{
|
2488 |
+
"epoch": 1.1670494884109417,
|
2489 |
+
"grad_norm": 0.8742548462166777,
|
2490 |
+
"learning_rate": 3.5077303639210634e-05,
|
2491 |
+
"loss": 0.8624,
|
2492 |
+
"step": 349
|
2493 |
+
},
|
2494 |
+
{
|
2495 |
+
"epoch": 1.1703904781791605,
|
2496 |
+
"grad_norm": 0.8368319574075729,
|
2497 |
+
"learning_rate": 3.4994335182747156e-05,
|
2498 |
+
"loss": 0.8075,
|
2499 |
+
"step": 350
|
2500 |
+
},
|
2501 |
+
{
|
2502 |
+
"epoch": 1.1737314679473794,
|
2503 |
+
"grad_norm": 0.8431099635101353,
|
2504 |
+
"learning_rate": 3.491123550176586e-05,
|
2505 |
+
"loss": 0.7896,
|
2506 |
+
"step": 351
|
2507 |
+
},
|
2508 |
+
{
|
2509 |
+
"epoch": 1.1770724577155982,
|
2510 |
+
"grad_norm": 0.839463461544109,
|
2511 |
+
"learning_rate": 3.482800568735638e-05,
|
2512 |
+
"loss": 0.7758,
|
2513 |
+
"step": 352
|
2514 |
+
},
|
2515 |
+
{
|
2516 |
+
"epoch": 1.180413447483817,
|
2517 |
+
"grad_norm": 0.8166956510001087,
|
2518 |
+
"learning_rate": 3.474464683231698e-05,
|
2519 |
+
"loss": 0.7709,
|
2520 |
+
"step": 353
|
2521 |
+
},
|
2522 |
+
{
|
2523 |
+
"epoch": 1.1837544372520359,
|
2524 |
+
"grad_norm": 0.7527108106347021,
|
2525 |
+
"learning_rate": 3.4661160031140255e-05,
|
2526 |
+
"loss": 0.6954,
|
2527 |
+
"step": 354
|
2528 |
+
},
|
2529 |
+
{
|
2530 |
+
"epoch": 1.1870954270202547,
|
2531 |
+
"grad_norm": 0.8885535896061523,
|
2532 |
+
"learning_rate": 3.457754637999866e-05,
|
2533 |
+
"loss": 0.7933,
|
2534 |
+
"step": 355
|
2535 |
+
},
|
2536 |
+
{
|
2537 |
+
"epoch": 1.1904364167884736,
|
2538 |
+
"grad_norm": 0.7911211400323862,
|
2539 |
+
"learning_rate": 3.4493806976730234e-05,
|
2540 |
+
"loss": 0.7348,
|
2541 |
+
"step": 356
|
2542 |
+
},
|
2543 |
+
{
|
2544 |
+
"epoch": 1.1937774065566924,
|
2545 |
+
"grad_norm": 0.7941043129924138,
|
2546 |
+
"learning_rate": 3.440994292082408e-05,
|
2547 |
+
"loss": 0.7433,
|
2548 |
+
"step": 357
|
2549 |
+
},
|
2550 |
+
{
|
2551 |
+
"epoch": 1.1971183963249112,
|
2552 |
+
"grad_norm": 0.8629346749835708,
|
2553 |
+
"learning_rate": 3.432595531340599e-05,
|
2554 |
+
"loss": 0.7691,
|
2555 |
+
"step": 358
|
2556 |
+
},
|
2557 |
+
{
|
2558 |
+
"epoch": 1.20045938609313,
|
2559 |
+
"grad_norm": 0.8076399504870541,
|
2560 |
+
"learning_rate": 3.4241845257223995e-05,
|
2561 |
+
"loss": 0.8387,
|
2562 |
+
"step": 359
|
2563 |
+
},
|
2564 |
+
{
|
2565 |
+
"epoch": 1.203800375861349,
|
2566 |
+
"grad_norm": 0.8363534638021144,
|
2567 |
+
"learning_rate": 3.4157613856633844e-05,
|
2568 |
+
"loss": 0.7795,
|
2569 |
+
"step": 360
|
2570 |
+
},
|
2571 |
+
{
|
2572 |
+
"epoch": 1.2071413656295678,
|
2573 |
+
"grad_norm": 0.8323776244098587,
|
2574 |
+
"learning_rate": 3.4073262217584537e-05,
|
2575 |
+
"loss": 0.7621,
|
2576 |
+
"step": 361
|
2577 |
+
},
|
2578 |
+
{
|
2579 |
+
"epoch": 1.2104823553977866,
|
2580 |
+
"grad_norm": 0.8631318606885842,
|
2581 |
+
"learning_rate": 3.3988791447603764e-05,
|
2582 |
+
"loss": 0.7262,
|
2583 |
+
"step": 362
|
2584 |
+
},
|
2585 |
+
{
|
2586 |
+
"epoch": 1.2138233451660054,
|
2587 |
+
"grad_norm": 0.8650278683291232,
|
2588 |
+
"learning_rate": 3.390420265578342e-05,
|
2589 |
+
"loss": 0.7156,
|
2590 |
+
"step": 363
|
2591 |
+
},
|
2592 |
+
{
|
2593 |
+
"epoch": 1.2171643349342243,
|
2594 |
+
"grad_norm": 0.8210135985421421,
|
2595 |
+
"learning_rate": 3.381949695276502e-05,
|
2596 |
+
"loss": 0.8695,
|
2597 |
+
"step": 364
|
2598 |
+
},
|
2599 |
+
{
|
2600 |
+
"epoch": 1.220505324702443,
|
2601 |
+
"grad_norm": 0.9816959338758507,
|
2602 |
+
"learning_rate": 3.3734675450725075e-05,
|
2603 |
+
"loss": 0.8165,
|
2604 |
+
"step": 365
|
2605 |
+
},
|
2606 |
+
{
|
2607 |
+
"epoch": 1.223846314470662,
|
2608 |
+
"grad_norm": 0.8740711622449979,
|
2609 |
+
"learning_rate": 3.364973926336057e-05,
|
2610 |
+
"loss": 0.7659,
|
2611 |
+
"step": 366
|
2612 |
+
},
|
2613 |
+
{
|
2614 |
+
"epoch": 1.2271873042388808,
|
2615 |
+
"grad_norm": 0.7673070294593356,
|
2616 |
+
"learning_rate": 3.3564689505874236e-05,
|
2617 |
+
"loss": 0.7436,
|
2618 |
+
"step": 367
|
2619 |
+
},
|
2620 |
+
{
|
2621 |
+
"epoch": 1.2305282940070996,
|
2622 |
+
"grad_norm": 0.7912430037723751,
|
2623 |
+
"learning_rate": 3.347952729496003e-05,
|
2624 |
+
"loss": 0.6968,
|
2625 |
+
"step": 368
|
2626 |
+
},
|
2627 |
+
{
|
2628 |
+
"epoch": 1.2338692837753185,
|
2629 |
+
"grad_norm": 0.7941923934515878,
|
2630 |
+
"learning_rate": 3.3394253748788365e-05,
|
2631 |
+
"loss": 0.8381,
|
2632 |
+
"step": 369
|
2633 |
+
},
|
2634 |
+
{
|
2635 |
+
"epoch": 1.2372102735435373,
|
2636 |
+
"grad_norm": 0.814356027770181,
|
2637 |
+
"learning_rate": 3.330886998699149e-05,
|
2638 |
+
"loss": 0.7719,
|
2639 |
+
"step": 370
|
2640 |
+
},
|
2641 |
+
{
|
2642 |
+
"epoch": 1.2405512633117561,
|
2643 |
+
"grad_norm": 0.8646739914125222,
|
2644 |
+
"learning_rate": 3.322337713064879e-05,
|
2645 |
+
"loss": 0.7815,
|
2646 |
+
"step": 371
|
2647 |
+
},
|
2648 |
+
{
|
2649 |
+
"epoch": 1.243892253079975,
|
2650 |
+
"grad_norm": 0.8622517062146566,
|
2651 |
+
"learning_rate": 3.3137776302272016e-05,
|
2652 |
+
"loss": 0.8027,
|
2653 |
+
"step": 372
|
2654 |
+
},
|
2655 |
+
{
|
2656 |
+
"epoch": 1.2472332428481938,
|
2657 |
+
"grad_norm": 0.9524256434298602,
|
2658 |
+
"learning_rate": 3.3052068625790605e-05,
|
2659 |
+
"loss": 0.8201,
|
2660 |
+
"step": 373
|
2661 |
+
},
|
2662 |
+
{
|
2663 |
+
"epoch": 1.2505742326164127,
|
2664 |
+
"grad_norm": 0.8916856370400298,
|
2665 |
+
"learning_rate": 3.296625522653688e-05,
|
2666 |
+
"loss": 0.7923,
|
2667 |
+
"step": 374
|
2668 |
+
},
|
2669 |
+
{
|
2670 |
+
"epoch": 1.2539152223846315,
|
2671 |
+
"grad_norm": 0.8558222972029906,
|
2672 |
+
"learning_rate": 3.288033723123131e-05,
|
2673 |
+
"loss": 0.7559,
|
2674 |
+
"step": 375
|
2675 |
+
},
|
2676 |
+
{
|
2677 |
+
"epoch": 1.2539152223846315,
|
2678 |
+
"eval_loss": 1.369796633720398,
|
2679 |
+
"eval_runtime": 12.5778,
|
2680 |
+
"eval_samples_per_second": 1.749,
|
2681 |
+
"eval_steps_per_second": 0.477,
|
2682 |
+
"step": 375
|
2683 |
+
}
|
2684 |
+
],
|
2685 |
+
"logging_steps": 1,
|
2686 |
+
"max_steps": 897,
|
2687 |
+
"num_input_tokens_seen": 0,
|
2688 |
+
"num_train_epochs": 3,
|
2689 |
+
"save_steps": 75,
|
2690 |
+
"stateful_callbacks": {
|
2691 |
+
"TrainerControl": {
|
2692 |
+
"args": {
|
2693 |
+
"should_epoch_stop": false,
|
2694 |
+
"should_evaluate": false,
|
2695 |
+
"should_log": false,
|
2696 |
+
"should_save": true,
|
2697 |
+
"should_training_stop": false
|
2698 |
+
},
|
2699 |
+
"attributes": {}
|
2700 |
+
}
|
2701 |
+
},
|
2702 |
+
"total_flos": 1.507791558504612e+17,
|
2703 |
+
"train_batch_size": 1,
|
2704 |
+
"trial_name": null,
|
2705 |
+
"trial_params": null
|
2706 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6363c7fd4076c12a13237ed928a81c0f0e0926a93b924a6150ecfa586806eb92
|
3 |
+
size 7992
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|