alex-chiu commited on
Commit
d44a562
·
verified ·
1 Parent(s): 13be78b

Upload folder using huggingface_hub

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: other
4
+ base_model: Qwen/Qwen2.5-7B-Instruct
5
+ tags:
6
+ - llama-factory
7
+ - full
8
+ - generated_from_trainer
9
+ model-index:
10
+ - name: original
11
+ results: []
12
+ ---
13
+
14
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
15
+ should probably proofread and complete it, then remove this comment. -->
16
+
17
+ # original
18
+
19
+ This model is a fine-tuned version of [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) on the Sky-T1 dataset.
20
+
21
+ ## Model description
22
+
23
+ More information needed
24
+
25
+ ## Intended uses & limitations
26
+
27
+ More information needed
28
+
29
+ ## Training and evaluation data
30
+
31
+ More information needed
32
+
33
+ ## Training procedure
34
+
35
+ ### Training hyperparameters
36
+
37
+ The following hyperparameters were used during training:
38
+ - learning_rate: 2e-05
39
+ - train_batch_size: 1
40
+ - eval_batch_size: 8
41
+ - seed: 42
42
+ - distributed_type: multi-GPU
43
+ - num_devices: 8
44
+ - gradient_accumulation_steps: 12
45
+ - total_train_batch_size: 96
46
+ - total_eval_batch_size: 64
47
+ - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
48
+ - lr_scheduler_type: cosine
49
+ - lr_scheduler_warmup_ratio: 0.1
50
+ - num_epochs: 2.0
51
+
52
+ ### Training results
53
+
54
+
55
+
56
+ ### Framework versions
57
+
58
+ - Transformers 4.46.1
59
+ - Pytorch 2.4.0a0+f70bd71a48.nv24.06
60
+ - Datasets 3.1.0
61
+ - Tokenizers 0.20.3
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
+ }
all_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.991111111111111,
3
+ "total_flos": 185195202609152.0,
4
+ "train_loss": 0.65867241738098,
5
+ "train_runtime": 12992.6194,
6
+ "train_samples_per_second": 0.83,
7
+ "train_steps_per_second": 0.009
8
+ }
config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "Qwen/Qwen2.5-7B-Instruct",
3
+ "architectures": [
4
+ "Qwen2ForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 151643,
8
+ "eos_token_id": 151645,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 3584,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 18944,
13
+ "max_position_embeddings": 32768,
14
+ "max_window_layers": 28,
15
+ "model_type": "qwen2",
16
+ "num_attention_heads": 28,
17
+ "num_hidden_layers": 28,
18
+ "num_key_value_heads": 4,
19
+ "rms_norm_eps": 1e-06,
20
+ "rope_scaling": null,
21
+ "rope_theta": 1000000.0,
22
+ "sliding_window": null,
23
+ "tie_word_embeddings": false,
24
+ "torch_dtype": "bfloat16",
25
+ "transformers_version": "4.46.1",
26
+ "use_cache": false,
27
+ "use_sliding_window": false,
28
+ "vocab_size": 152064
29
+ }
generation_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 151645,
6
+ 151643
7
+ ],
8
+ "pad_token_id": 151643,
9
+ "repetition_penalty": 1.05,
10
+ "temperature": 0.7,
11
+ "top_k": 20,
12
+ "top_p": 0.8,
13
+ "transformers_version": "4.46.1"
14
+ }
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:b5bdd81d38d526fd624ec5b539329080d16aef574d2d8d7a8183fbdc6fafa676
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:aca3caccfc231cb4656f779878787c8f8629d69bdc83ec5ddb8b5317a76774ec
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:f3db292aa538da52c792b82583d7c8028d32bb8f22dcae1b446112ad7256a4b0
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:bca2036175c18ed020961b3d089a5e5aa512b4161b40df905ff7d071bb25bd6d
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
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
3
+ size 11421896
tokenizer_config.json ADDED
@@ -0,0 +1,208 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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 tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n {%- endif %}\n {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0]['role'] == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n {%- else %}\n {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
199
+ "clean_up_tokenization_spaces": false,
200
+ "eos_token": "<|endoftext|>",
201
+ "errors": "replace",
202
+ "model_max_length": 131072,
203
+ "pad_token": "<|endoftext|>",
204
+ "padding_side": "right",
205
+ "split_special_tokens": false,
206
+ "tokenizer_class": "Qwen2Tokenizer",
207
+ "unk_token": null
208
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.991111111111111,
3
+ "total_flos": 185195202609152.0,
4
+ "train_loss": 0.65867241738098,
5
+ "train_runtime": 12992.6194,
6
+ "train_samples_per_second": 0.83,
7
+ "train_steps_per_second": 0.009
8
+ }
trainer_log.jsonl ADDED
@@ -0,0 +1,113 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {"current_steps": 1, "total_steps": 112, "loss": 0.9993, "lr": 1.6666666666666667e-06, "epoch": 0.017777777777777778, "percentage": 0.89, "elapsed_time": "0:02:05", "remaining_time": "3:52:28"}
2
+ {"current_steps": 2, "total_steps": 112, "loss": 1.0111, "lr": 3.3333333333333333e-06, "epoch": 0.035555555555555556, "percentage": 1.79, "elapsed_time": "0:04:08", "remaining_time": "3:47:30"}
3
+ {"current_steps": 3, "total_steps": 112, "loss": 0.9858, "lr": 5e-06, "epoch": 0.05333333333333334, "percentage": 2.68, "elapsed_time": "0:05:54", "remaining_time": "3:34:27"}
4
+ {"current_steps": 4, "total_steps": 112, "loss": 0.9484, "lr": 6.666666666666667e-06, "epoch": 0.07111111111111111, "percentage": 3.57, "elapsed_time": "0:08:01", "remaining_time": "3:36:28"}
5
+ {"current_steps": 5, "total_steps": 112, "loss": 0.9376, "lr": 8.333333333333334e-06, "epoch": 0.08888888888888889, "percentage": 4.46, "elapsed_time": "0:09:54", "remaining_time": "3:31:57"}
6
+ {"current_steps": 6, "total_steps": 112, "loss": 0.9214, "lr": 1e-05, "epoch": 0.10666666666666667, "percentage": 5.36, "elapsed_time": "0:11:36", "remaining_time": "3:25:07"}
7
+ {"current_steps": 7, "total_steps": 112, "loss": 0.9122, "lr": 1.1666666666666668e-05, "epoch": 0.12444444444444444, "percentage": 6.25, "elapsed_time": "0:13:27", "remaining_time": "3:21:57"}
8
+ {"current_steps": 8, "total_steps": 112, "loss": 0.8665, "lr": 1.3333333333333333e-05, "epoch": 0.14222222222222222, "percentage": 7.14, "elapsed_time": "0:15:25", "remaining_time": "3:20:29"}
9
+ {"current_steps": 9, "total_steps": 112, "loss": 0.8395, "lr": 1.5000000000000002e-05, "epoch": 0.16, "percentage": 8.04, "elapsed_time": "0:17:14", "remaining_time": "3:17:22"}
10
+ {"current_steps": 10, "total_steps": 112, "loss": 0.8198, "lr": 1.6666666666666667e-05, "epoch": 0.17777777777777778, "percentage": 8.93, "elapsed_time": "0:19:15", "remaining_time": "3:16:25"}
11
+ {"current_steps": 11, "total_steps": 112, "loss": 0.7984, "lr": 1.8333333333333333e-05, "epoch": 0.19555555555555557, "percentage": 9.82, "elapsed_time": "0:21:11", "remaining_time": "3:14:32"}
12
+ {"current_steps": 12, "total_steps": 112, "loss": 0.794, "lr": 2e-05, "epoch": 0.21333333333333335, "percentage": 10.71, "elapsed_time": "0:23:21", "remaining_time": "3:14:35"}
13
+ {"current_steps": 13, "total_steps": 112, "loss": 0.783, "lr": 1.9995065603657317e-05, "epoch": 0.2311111111111111, "percentage": 11.61, "elapsed_time": "0:25:25", "remaining_time": "3:13:40"}
14
+ {"current_steps": 14, "total_steps": 112, "loss": 0.7379, "lr": 1.9980267284282718e-05, "epoch": 0.24888888888888888, "percentage": 12.5, "elapsed_time": "0:27:25", "remaining_time": "3:11:58"}
15
+ {"current_steps": 15, "total_steps": 112, "loss": 0.7524, "lr": 1.99556196460308e-05, "epoch": 0.26666666666666666, "percentage": 13.39, "elapsed_time": "0:29:08", "remaining_time": "3:08:29"}
16
+ {"current_steps": 16, "total_steps": 112, "loss": 0.754, "lr": 1.9921147013144782e-05, "epoch": 0.28444444444444444, "percentage": 14.29, "elapsed_time": "0:30:51", "remaining_time": "3:05:07"}
17
+ {"current_steps": 17, "total_steps": 112, "loss": 0.7073, "lr": 1.9876883405951378e-05, "epoch": 0.3022222222222222, "percentage": 15.18, "elapsed_time": "0:32:35", "remaining_time": "3:02:05"}
18
+ {"current_steps": 18, "total_steps": 112, "loss": 0.7159, "lr": 1.982287250728689e-05, "epoch": 0.32, "percentage": 16.07, "elapsed_time": "0:34:36", "remaining_time": "3:00:42"}
19
+ {"current_steps": 19, "total_steps": 112, "loss": 0.7114, "lr": 1.9759167619387474e-05, "epoch": 0.3377777777777778, "percentage": 16.96, "elapsed_time": "0:36:33", "remaining_time": "2:58:58"}
20
+ {"current_steps": 20, "total_steps": 112, "loss": 0.7012, "lr": 1.9685831611286312e-05, "epoch": 0.35555555555555557, "percentage": 17.86, "elapsed_time": "0:38:17", "remaining_time": "2:56:07"}
21
+ {"current_steps": 21, "total_steps": 112, "loss": 0.6948, "lr": 1.9602936856769432e-05, "epoch": 0.37333333333333335, "percentage": 18.75, "elapsed_time": "0:40:00", "remaining_time": "2:53:21"}
22
+ {"current_steps": 22, "total_steps": 112, "loss": 0.7046, "lr": 1.9510565162951538e-05, "epoch": 0.39111111111111113, "percentage": 19.64, "elapsed_time": "0:42:05", "remaining_time": "2:52:12"}
23
+ {"current_steps": 23, "total_steps": 112, "loss": 0.7076, "lr": 1.9408807689542257e-05, "epoch": 0.4088888888888889, "percentage": 20.54, "elapsed_time": "0:44:00", "remaining_time": "2:50:16"}
24
+ {"current_steps": 24, "total_steps": 112, "loss": 0.6983, "lr": 1.9297764858882516e-05, "epoch": 0.4266666666666667, "percentage": 21.43, "elapsed_time": "0:45:52", "remaining_time": "2:48:13"}
25
+ {"current_steps": 25, "total_steps": 112, "loss": 0.6839, "lr": 1.9177546256839814e-05, "epoch": 0.4444444444444444, "percentage": 22.32, "elapsed_time": "0:47:44", "remaining_time": "2:46:06"}
26
+ {"current_steps": 26, "total_steps": 112, "loss": 0.6768, "lr": 1.9048270524660197e-05, "epoch": 0.4622222222222222, "percentage": 23.21, "elapsed_time": "0:49:47", "remaining_time": "2:44:40"}
27
+ {"current_steps": 27, "total_steps": 112, "loss": 0.6773, "lr": 1.891006524188368e-05, "epoch": 0.48, "percentage": 24.11, "elapsed_time": "0:51:44", "remaining_time": "2:42:54"}
28
+ {"current_steps": 28, "total_steps": 112, "loss": 0.6852, "lr": 1.8763066800438638e-05, "epoch": 0.49777777777777776, "percentage": 25.0, "elapsed_time": "0:53:44", "remaining_time": "2:41:14"}
29
+ {"current_steps": 29, "total_steps": 112, "loss": 0.6882, "lr": 1.860742027003944e-05, "epoch": 0.5155555555555555, "percentage": 25.89, "elapsed_time": "0:55:40", "remaining_time": "2:39:21"}
30
+ {"current_steps": 30, "total_steps": 112, "loss": 0.6677, "lr": 1.8443279255020153e-05, "epoch": 0.5333333333333333, "percentage": 26.79, "elapsed_time": "0:57:37", "remaining_time": "2:37:31"}
31
+ {"current_steps": 31, "total_steps": 112, "loss": 0.6696, "lr": 1.827080574274562e-05, "epoch": 0.5511111111111111, "percentage": 27.68, "elapsed_time": "0:59:44", "remaining_time": "2:36:05"}
32
+ {"current_steps": 32, "total_steps": 112, "loss": 0.6484, "lr": 1.8090169943749477e-05, "epoch": 0.5688888888888889, "percentage": 28.57, "elapsed_time": "1:01:48", "remaining_time": "2:34:32"}
33
+ {"current_steps": 33, "total_steps": 112, "loss": 0.6859, "lr": 1.7901550123756906e-05, "epoch": 0.5866666666666667, "percentage": 29.46, "elapsed_time": "1:03:34", "remaining_time": "2:32:12"}
34
+ {"current_steps": 34, "total_steps": 112, "loss": 0.6557, "lr": 1.7705132427757895e-05, "epoch": 0.6044444444444445, "percentage": 30.36, "elapsed_time": "1:05:24", "remaining_time": "2:30:02"}
35
+ {"current_steps": 35, "total_steps": 112, "loss": 0.6511, "lr": 1.7501110696304598e-05, "epoch": 0.6222222222222222, "percentage": 31.25, "elapsed_time": "1:07:17", "remaining_time": "2:28:01"}
36
+ {"current_steps": 36, "total_steps": 112, "loss": 0.6603, "lr": 1.7289686274214116e-05, "epoch": 0.64, "percentage": 32.14, "elapsed_time": "1:09:05", "remaining_time": "2:25:51"}
37
+ {"current_steps": 37, "total_steps": 112, "loss": 0.6674, "lr": 1.7071067811865477e-05, "epoch": 0.6577777777777778, "percentage": 33.04, "elapsed_time": "1:11:01", "remaining_time": "2:23:57"}
38
+ {"current_steps": 38, "total_steps": 112, "loss": 0.6624, "lr": 1.684547105928689e-05, "epoch": 0.6755555555555556, "percentage": 33.93, "elapsed_time": "1:12:51", "remaining_time": "2:21:53"}
39
+ {"current_steps": 39, "total_steps": 112, "loss": 0.659, "lr": 1.661311865323652e-05, "epoch": 0.6933333333333334, "percentage": 34.82, "elapsed_time": "1:14:54", "remaining_time": "2:20:12"}
40
+ {"current_steps": 40, "total_steps": 112, "loss": 0.6403, "lr": 1.63742398974869e-05, "epoch": 0.7111111111111111, "percentage": 35.71, "elapsed_time": "1:16:42", "remaining_time": "2:18:03"}
41
+ {"current_steps": 41, "total_steps": 112, "loss": 0.6649, "lr": 1.6129070536529767e-05, "epoch": 0.7288888888888889, "percentage": 36.61, "elapsed_time": "1:18:39", "remaining_time": "2:16:13"}
42
+ {"current_steps": 42, "total_steps": 112, "loss": 0.6636, "lr": 1.5877852522924733e-05, "epoch": 0.7466666666666667, "percentage": 37.5, "elapsed_time": "1:20:30", "remaining_time": "2:14:10"}
43
+ {"current_steps": 43, "total_steps": 112, "loss": 0.6464, "lr": 1.5620833778521306e-05, "epoch": 0.7644444444444445, "percentage": 38.39, "elapsed_time": "1:22:22", "remaining_time": "2:12:10"}
44
+ {"current_steps": 44, "total_steps": 112, "loss": 0.6513, "lr": 1.5358267949789968e-05, "epoch": 0.7822222222222223, "percentage": 39.29, "elapsed_time": "1:24:26", "remaining_time": "2:10:30"}
45
+ {"current_steps": 45, "total_steps": 112, "loss": 0.6625, "lr": 1.5090414157503715e-05, "epoch": 0.8, "percentage": 40.18, "elapsed_time": "1:26:14", "remaining_time": "2:08:24"}
46
+ {"current_steps": 46, "total_steps": 112, "loss": 0.6471, "lr": 1.4817536741017153e-05, "epoch": 0.8177777777777778, "percentage": 41.07, "elapsed_time": "1:28:10", "remaining_time": "2:06:31"}
47
+ {"current_steps": 47, "total_steps": 112, "loss": 0.6625, "lr": 1.4539904997395468e-05, "epoch": 0.8355555555555556, "percentage": 41.96, "elapsed_time": "1:30:13", "remaining_time": "2:04:46"}
48
+ {"current_steps": 48, "total_steps": 112, "loss": 0.6374, "lr": 1.4257792915650728e-05, "epoch": 0.8533333333333334, "percentage": 42.86, "elapsed_time": "1:32:06", "remaining_time": "2:02:48"}
49
+ {"current_steps": 49, "total_steps": 112, "loss": 0.6431, "lr": 1.3971478906347806e-05, "epoch": 0.8711111111111111, "percentage": 43.75, "elapsed_time": "1:33:50", "remaining_time": "2:00:39"}
50
+ {"current_steps": 50, "total_steps": 112, "loss": 0.6381, "lr": 1.3681245526846782e-05, "epoch": 0.8888888888888888, "percentage": 44.64, "elapsed_time": "1:35:49", "remaining_time": "1:58:48"}
51
+ {"current_steps": 51, "total_steps": 112, "loss": 0.6338, "lr": 1.3387379202452917e-05, "epoch": 0.9066666666666666, "percentage": 45.54, "elapsed_time": "1:37:38", "remaining_time": "1:56:47"}
52
+ {"current_steps": 52, "total_steps": 112, "loss": 0.6502, "lr": 1.3090169943749475e-05, "epoch": 0.9244444444444444, "percentage": 46.43, "elapsed_time": "1:39:43", "remaining_time": "1:55:04"}
53
+ {"current_steps": 53, "total_steps": 112, "loss": 0.6449, "lr": 1.2789911060392295e-05, "epoch": 0.9422222222222222, "percentage": 47.32, "elapsed_time": "1:41:46", "remaining_time": "1:53:18"}
54
+ {"current_steps": 54, "total_steps": 112, "loss": 0.6511, "lr": 1.2486898871648552e-05, "epoch": 0.96, "percentage": 48.21, "elapsed_time": "1:43:36", "remaining_time": "1:51:17"}
55
+ {"current_steps": 55, "total_steps": 112, "loss": 0.6367, "lr": 1.2181432413965428e-05, "epoch": 0.9777777777777777, "percentage": 49.11, "elapsed_time": "1:45:27", "remaining_time": "1:49:17"}
56
+ {"current_steps": 56, "total_steps": 112, "loss": 0.6532, "lr": 1.187381314585725e-05, "epoch": 0.9955555555555555, "percentage": 50.0, "elapsed_time": "1:47:18", "remaining_time": "1:47:18"}
57
+ {"current_steps": 57, "total_steps": 112, "loss": 1.0796, "lr": 1.156434465040231e-05, "epoch": 1.0133333333333334, "percentage": 50.89, "elapsed_time": "1:49:09", "remaining_time": "1:45:19"}
58
+ {"current_steps": 58, "total_steps": 112, "loss": 0.634, "lr": 1.1253332335643043e-05, "epoch": 1.031111111111111, "percentage": 51.79, "elapsed_time": "1:51:06", "remaining_time": "1:43:27"}
59
+ {"current_steps": 59, "total_steps": 112, "loss": 0.6002, "lr": 1.0941083133185146e-05, "epoch": 1.048888888888889, "percentage": 52.68, "elapsed_time": "1:53:14", "remaining_time": "1:41:43"}
60
+ {"current_steps": 60, "total_steps": 112, "loss": 0.5628, "lr": 1.0627905195293135e-05, "epoch": 1.0666666666666667, "percentage": 53.57, "elapsed_time": "1:55:07", "remaining_time": "1:39:46"}
61
+ {"current_steps": 61, "total_steps": 112, "loss": 0.6532, "lr": 1.0314107590781284e-05, "epoch": 1.0844444444444445, "percentage": 54.46, "elapsed_time": "1:56:57", "remaining_time": "1:37:46"}
62
+ {"current_steps": 62, "total_steps": 112, "loss": 0.5744, "lr": 1e-05, "epoch": 1.1022222222222222, "percentage": 55.36, "elapsed_time": "1:59:02", "remaining_time": "1:35:59"}
63
+ {"current_steps": 63, "total_steps": 112, "loss": 0.5798, "lr": 9.685892409218718e-06, "epoch": 1.12, "percentage": 56.25, "elapsed_time": "2:00:52", "remaining_time": "1:34:00"}
64
+ {"current_steps": 64, "total_steps": 112, "loss": 0.567, "lr": 9.372094804706867e-06, "epoch": 1.1377777777777778, "percentage": 57.14, "elapsed_time": "2:02:53", "remaining_time": "1:32:10"}
65
+ {"current_steps": 65, "total_steps": 112, "loss": 0.6152, "lr": 9.058916866814857e-06, "epoch": 1.1555555555555554, "percentage": 58.04, "elapsed_time": "2:04:58", "remaining_time": "1:30:22"}
66
+ {"current_steps": 66, "total_steps": 112, "loss": 0.6099, "lr": 8.746667664356957e-06, "epoch": 1.1733333333333333, "percentage": 58.93, "elapsed_time": "2:06:55", "remaining_time": "1:28:27"}
67
+ {"current_steps": 67, "total_steps": 112, "loss": 0.5508, "lr": 8.43565534959769e-06, "epoch": 1.1911111111111112, "percentage": 59.82, "elapsed_time": "2:08:40", "remaining_time": "1:26:25"}
68
+ {"current_steps": 68, "total_steps": 112, "loss": 0.625, "lr": 8.126186854142752e-06, "epoch": 1.208888888888889, "percentage": 60.71, "elapsed_time": "2:10:45", "remaining_time": "1:24:36"}
69
+ {"current_steps": 69, "total_steps": 112, "loss": 0.5666, "lr": 7.818567586034578e-06, "epoch": 1.2266666666666666, "percentage": 61.61, "elapsed_time": "2:12:40", "remaining_time": "1:22:41"}
70
+ {"current_steps": 70, "total_steps": 112, "loss": 0.6, "lr": 7.513101128351454e-06, "epoch": 1.2444444444444445, "percentage": 62.5, "elapsed_time": "2:14:28", "remaining_time": "1:20:41"}
71
+ {"current_steps": 71, "total_steps": 112, "loss": 0.5466, "lr": 7.210088939607709e-06, "epoch": 1.2622222222222224, "percentage": 63.39, "elapsed_time": "2:16:26", "remaining_time": "1:18:47"}
72
+ {"current_steps": 72, "total_steps": 112, "loss": 0.6297, "lr": 6.909830056250527e-06, "epoch": 1.28, "percentage": 64.29, "elapsed_time": "2:18:22", "remaining_time": "1:16:52"}
73
+ {"current_steps": 73, "total_steps": 112, "loss": 0.5333, "lr": 6.612620797547087e-06, "epoch": 1.2977777777777777, "percentage": 65.18, "elapsed_time": "2:20:11", "remaining_time": "1:14:53"}
74
+ {"current_steps": 74, "total_steps": 112, "loss": 0.6132, "lr": 6.318754473153221e-06, "epoch": 1.3155555555555556, "percentage": 66.07, "elapsed_time": "2:22:20", "remaining_time": "1:13:05"}
75
+ {"current_steps": 75, "total_steps": 112, "loss": 0.5587, "lr": 6.028521093652195e-06, "epoch": 1.3333333333333333, "percentage": 66.96, "elapsed_time": "2:24:15", "remaining_time": "1:11:10"}
76
+ {"current_steps": 76, "total_steps": 112, "loss": 0.6111, "lr": 5.742207084349274e-06, "epoch": 1.3511111111111112, "percentage": 67.86, "elapsed_time": "2:26:23", "remaining_time": "1:09:20"}
77
+ {"current_steps": 77, "total_steps": 112, "loss": 0.5848, "lr": 5.460095002604533e-06, "epoch": 1.3688888888888888, "percentage": 68.75, "elapsed_time": "2:28:19", "remaining_time": "1:07:25"}
78
+ {"current_steps": 78, "total_steps": 112, "loss": 0.6158, "lr": 5.1824632589828465e-06, "epoch": 1.3866666666666667, "percentage": 69.64, "elapsed_time": "2:30:17", "remaining_time": "1:05:30"}
79
+ {"current_steps": 79, "total_steps": 112, "loss": 0.5424, "lr": 4.909585842496287e-06, "epoch": 1.4044444444444444, "percentage": 70.54, "elapsed_time": "2:32:12", "remaining_time": "1:03:34"}
80
+ {"current_steps": 80, "total_steps": 112, "loss": 0.5793, "lr": 4.641732050210032e-06, "epoch": 1.4222222222222223, "percentage": 71.43, "elapsed_time": "2:34:06", "remaining_time": "1:01:38"}
81
+ {"current_steps": 81, "total_steps": 112, "loss": 0.5984, "lr": 4.379166221478697e-06, "epoch": 1.44, "percentage": 72.32, "elapsed_time": "2:35:58", "remaining_time": "0:59:41"}
82
+ {"current_steps": 82, "total_steps": 112, "loss": 0.621, "lr": 4.12214747707527e-06, "epoch": 1.4577777777777778, "percentage": 73.21, "elapsed_time": "2:37:56", "remaining_time": "0:57:46"}
83
+ {"current_steps": 83, "total_steps": 112, "loss": 0.5242, "lr": 3.8709294634702374e-06, "epoch": 1.4755555555555555, "percentage": 74.11, "elapsed_time": "2:39:42", "remaining_time": "0:55:48"}
84
+ {"current_steps": 84, "total_steps": 112, "loss": 0.563, "lr": 3.625760102513103e-06, "epoch": 1.4933333333333334, "percentage": 75.0, "elapsed_time": "2:41:28", "remaining_time": "0:53:49"}
85
+ {"current_steps": 85, "total_steps": 112, "loss": 0.6099, "lr": 3.3868813467634833e-06, "epoch": 1.511111111111111, "percentage": 75.89, "elapsed_time": "2:43:20", "remaining_time": "0:51:53"}
86
+ {"current_steps": 86, "total_steps": 112, "loss": 0.5765, "lr": 3.1545289407131128e-06, "epoch": 1.528888888888889, "percentage": 76.79, "elapsed_time": "2:45:06", "remaining_time": "0:49:55"}
87
+ {"current_steps": 87, "total_steps": 112, "loss": 0.5988, "lr": 2.9289321881345257e-06, "epoch": 1.5466666666666666, "percentage": 77.68, "elapsed_time": "2:46:56", "remaining_time": "0:47:58"}
88
+ {"current_steps": 88, "total_steps": 112, "loss": 0.5901, "lr": 2.7103137257858867e-06, "epoch": 1.5644444444444443, "percentage": 78.57, "elapsed_time": "2:48:42", "remaining_time": "0:46:00"}
89
+ {"current_steps": 89, "total_steps": 112, "loss": 0.5578, "lr": 2.4988893036954045e-06, "epoch": 1.5822222222222222, "percentage": 79.46, "elapsed_time": "2:50:35", "remaining_time": "0:44:05"}
90
+ {"current_steps": 90, "total_steps": 112, "loss": 0.5952, "lr": 2.2948675722421086e-06, "epoch": 1.6, "percentage": 80.36, "elapsed_time": "2:52:22", "remaining_time": "0:42:08"}
91
+ {"current_steps": 91, "total_steps": 112, "loss": 0.5729, "lr": 2.098449876243096e-06, "epoch": 1.6177777777777778, "percentage": 81.25, "elapsed_time": "2:54:29", "remaining_time": "0:40:16"}
92
+ {"current_steps": 92, "total_steps": 112, "loss": 0.6167, "lr": 1.9098300562505266e-06, "epoch": 1.6355555555555554, "percentage": 82.14, "elapsed_time": "2:56:37", "remaining_time": "0:38:23"}
93
+ {"current_steps": 93, "total_steps": 112, "loss": 0.558, "lr": 1.7291942572543806e-06, "epoch": 1.6533333333333333, "percentage": 83.04, "elapsed_time": "2:58:23", "remaining_time": "0:36:26"}
94
+ {"current_steps": 94, "total_steps": 112, "loss": 0.5948, "lr": 1.5567207449798517e-06, "epoch": 1.6711111111111112, "percentage": 83.93, "elapsed_time": "3:00:25", "remaining_time": "0:34:32"}
95
+ {"current_steps": 95, "total_steps": 112, "loss": 0.5715, "lr": 1.3925797299605649e-06, "epoch": 1.6888888888888889, "percentage": 84.82, "elapsed_time": "3:02:16", "remaining_time": "0:32:36"}
96
+ {"current_steps": 96, "total_steps": 112, "loss": 0.5936, "lr": 1.2369331995613664e-06, "epoch": 1.7066666666666666, "percentage": 85.71, "elapsed_time": "3:04:05", "remaining_time": "0:30:40"}
97
+ {"current_steps": 97, "total_steps": 112, "loss": 0.5924, "lr": 1.0899347581163222e-06, "epoch": 1.7244444444444444, "percentage": 86.61, "elapsed_time": "3:06:09", "remaining_time": "0:28:47"}
98
+ {"current_steps": 98, "total_steps": 112, "loss": 0.575, "lr": 9.517294753398066e-07, "epoch": 1.7422222222222223, "percentage": 87.5, "elapsed_time": "3:08:11", "remaining_time": "0:26:53"}
99
+ {"current_steps": 99, "total_steps": 112, "loss": 0.5367, "lr": 8.224537431601886e-07, "epoch": 1.76, "percentage": 88.39, "elapsed_time": "3:10:04", "remaining_time": "0:24:57"}
100
+ {"current_steps": 100, "total_steps": 112, "loss": 0.5957, "lr": 7.022351411174866e-07, "epoch": 1.7777777777777777, "percentage": 89.29, "elapsed_time": "3:11:55", "remaining_time": "0:23:01"}
101
+ {"current_steps": 101, "total_steps": 112, "loss": 0.5824, "lr": 5.911923104577455e-07, "epoch": 1.7955555555555556, "percentage": 90.18, "elapsed_time": "3:14:59", "remaining_time": "0:21:14"}
102
+ {"current_steps": 102, "total_steps": 112, "loss": 0.561, "lr": 4.894348370484648e-07, "epoch": 1.8133333333333335, "percentage": 91.07, "elapsed_time": "3:16:57", "remaining_time": "0:19:18"}
103
+ {"current_steps": 103, "total_steps": 112, "loss": 0.5761, "lr": 3.9706314323056936e-07, "epoch": 1.8311111111111111, "percentage": 91.96, "elapsed_time": "3:18:45", "remaining_time": "0:17:22"}
104
+ {"current_steps": 104, "total_steps": 112, "loss": 0.5536, "lr": 3.1416838871368925e-07, "epoch": 1.8488888888888888, "percentage": 92.86, "elapsed_time": "3:20:15", "remaining_time": "0:15:24"}
105
+ {"current_steps": 105, "total_steps": 112, "loss": 0.6234, "lr": 2.4083238061252565e-07, "epoch": 1.8666666666666667, "percentage": 93.75, "elapsed_time": "3:22:02", "remaining_time": "0:13:28"}
106
+ {"current_steps": 106, "total_steps": 112, "loss": 0.5415, "lr": 1.7712749271311392e-07, "epoch": 1.8844444444444446, "percentage": 94.64, "elapsed_time": "3:23:46", "remaining_time": "0:11:32"}
107
+ {"current_steps": 107, "total_steps": 112, "loss": 0.5611, "lr": 1.231165940486234e-07, "epoch": 1.9022222222222223, "percentage": 95.54, "elapsed_time": "3:25:45", "remaining_time": "0:09:36"}
108
+ {"current_steps": 108, "total_steps": 112, "loss": 0.5628, "lr": 7.885298685522235e-08, "epoch": 1.92, "percentage": 96.43, "elapsed_time": "3:27:25", "remaining_time": "0:07:40"}
109
+ {"current_steps": 109, "total_steps": 112, "loss": 0.5907, "lr": 4.438035396920004e-08, "epoch": 1.9377777777777778, "percentage": 97.32, "elapsed_time": "3:29:17", "remaining_time": "0:05:45"}
110
+ {"current_steps": 110, "total_steps": 112, "loss": 0.6009, "lr": 1.973271571728441e-08, "epoch": 1.9555555555555557, "percentage": 98.21, "elapsed_time": "3:31:29", "remaining_time": "0:03:50"}
111
+ {"current_steps": 111, "total_steps": 112, "loss": 0.5773, "lr": 4.9343963426840006e-09, "epoch": 1.9733333333333334, "percentage": 99.11, "elapsed_time": "3:33:37", "remaining_time": "0:01:55"}
112
+ {"current_steps": 112, "total_steps": 112, "loss": 0.5963, "lr": 0.0, "epoch": 1.991111111111111, "percentage": 100.0, "elapsed_time": "3:35:29", "remaining_time": "0:00:00"}
113
+ {"current_steps": 112, "total_steps": 112, "epoch": 1.991111111111111, "percentage": 100.0, "elapsed_time": "3:36:31", "remaining_time": "0:00:00"}
trainer_state.json ADDED
@@ -0,0 +1,826 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.991111111111111,
5
+ "eval_steps": 500,
6
+ "global_step": 112,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.017777777777777778,
13
+ "grad_norm": 6.02266263961792,
14
+ "learning_rate": 1.6666666666666667e-06,
15
+ "loss": 0.9993,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.035555555555555556,
20
+ "grad_norm": 6.143394947052002,
21
+ "learning_rate": 3.3333333333333333e-06,
22
+ "loss": 1.0111,
23
+ "step": 2
24
+ },
25
+ {
26
+ "epoch": 0.05333333333333334,
27
+ "grad_norm": 5.803601264953613,
28
+ "learning_rate": 5e-06,
29
+ "loss": 0.9858,
30
+ "step": 3
31
+ },
32
+ {
33
+ "epoch": 0.07111111111111111,
34
+ "grad_norm": 4.266067028045654,
35
+ "learning_rate": 6.666666666666667e-06,
36
+ "loss": 0.9484,
37
+ "step": 4
38
+ },
39
+ {
40
+ "epoch": 0.08888888888888889,
41
+ "grad_norm": 2.9427103996276855,
42
+ "learning_rate": 8.333333333333334e-06,
43
+ "loss": 0.9376,
44
+ "step": 5
45
+ },
46
+ {
47
+ "epoch": 0.10666666666666667,
48
+ "grad_norm": 4.489638805389404,
49
+ "learning_rate": 1e-05,
50
+ "loss": 0.9214,
51
+ "step": 6
52
+ },
53
+ {
54
+ "epoch": 0.12444444444444444,
55
+ "grad_norm": 4.621401786804199,
56
+ "learning_rate": 1.1666666666666668e-05,
57
+ "loss": 0.9122,
58
+ "step": 7
59
+ },
60
+ {
61
+ "epoch": 0.14222222222222222,
62
+ "grad_norm": 3.9608113765716553,
63
+ "learning_rate": 1.3333333333333333e-05,
64
+ "loss": 0.8665,
65
+ "step": 8
66
+ },
67
+ {
68
+ "epoch": 0.16,
69
+ "grad_norm": 3.7279064655303955,
70
+ "learning_rate": 1.5000000000000002e-05,
71
+ "loss": 0.8395,
72
+ "step": 9
73
+ },
74
+ {
75
+ "epoch": 0.17777777777777778,
76
+ "grad_norm": 2.407290458679199,
77
+ "learning_rate": 1.6666666666666667e-05,
78
+ "loss": 0.8198,
79
+ "step": 10
80
+ },
81
+ {
82
+ "epoch": 0.19555555555555557,
83
+ "grad_norm": 2.280531644821167,
84
+ "learning_rate": 1.8333333333333333e-05,
85
+ "loss": 0.7984,
86
+ "step": 11
87
+ },
88
+ {
89
+ "epoch": 0.21333333333333335,
90
+ "grad_norm": 2.6176528930664062,
91
+ "learning_rate": 2e-05,
92
+ "loss": 0.794,
93
+ "step": 12
94
+ },
95
+ {
96
+ "epoch": 0.2311111111111111,
97
+ "grad_norm": 1.707384467124939,
98
+ "learning_rate": 1.9995065603657317e-05,
99
+ "loss": 0.783,
100
+ "step": 13
101
+ },
102
+ {
103
+ "epoch": 0.24888888888888888,
104
+ "grad_norm": 1.9082920551300049,
105
+ "learning_rate": 1.9980267284282718e-05,
106
+ "loss": 0.7379,
107
+ "step": 14
108
+ },
109
+ {
110
+ "epoch": 0.26666666666666666,
111
+ "grad_norm": 1.7811676263809204,
112
+ "learning_rate": 1.99556196460308e-05,
113
+ "loss": 0.7524,
114
+ "step": 15
115
+ },
116
+ {
117
+ "epoch": 0.28444444444444444,
118
+ "grad_norm": 1.3555017709732056,
119
+ "learning_rate": 1.9921147013144782e-05,
120
+ "loss": 0.754,
121
+ "step": 16
122
+ },
123
+ {
124
+ "epoch": 0.3022222222222222,
125
+ "grad_norm": 1.3673418760299683,
126
+ "learning_rate": 1.9876883405951378e-05,
127
+ "loss": 0.7073,
128
+ "step": 17
129
+ },
130
+ {
131
+ "epoch": 0.32,
132
+ "grad_norm": 1.4924910068511963,
133
+ "learning_rate": 1.982287250728689e-05,
134
+ "loss": 0.7159,
135
+ "step": 18
136
+ },
137
+ {
138
+ "epoch": 0.3377777777777778,
139
+ "grad_norm": 1.6850374937057495,
140
+ "learning_rate": 1.9759167619387474e-05,
141
+ "loss": 0.7114,
142
+ "step": 19
143
+ },
144
+ {
145
+ "epoch": 0.35555555555555557,
146
+ "grad_norm": 1.511631727218628,
147
+ "learning_rate": 1.9685831611286312e-05,
148
+ "loss": 0.7012,
149
+ "step": 20
150
+ },
151
+ {
152
+ "epoch": 0.37333333333333335,
153
+ "grad_norm": 1.2830287218093872,
154
+ "learning_rate": 1.9602936856769432e-05,
155
+ "loss": 0.6948,
156
+ "step": 21
157
+ },
158
+ {
159
+ "epoch": 0.39111111111111113,
160
+ "grad_norm": 1.2557350397109985,
161
+ "learning_rate": 1.9510565162951538e-05,
162
+ "loss": 0.7046,
163
+ "step": 22
164
+ },
165
+ {
166
+ "epoch": 0.4088888888888889,
167
+ "grad_norm": 0.9395996928215027,
168
+ "learning_rate": 1.9408807689542257e-05,
169
+ "loss": 0.7076,
170
+ "step": 23
171
+ },
172
+ {
173
+ "epoch": 0.4266666666666667,
174
+ "grad_norm": 1.0723974704742432,
175
+ "learning_rate": 1.9297764858882516e-05,
176
+ "loss": 0.6983,
177
+ "step": 24
178
+ },
179
+ {
180
+ "epoch": 0.4444444444444444,
181
+ "grad_norm": 1.0539971590042114,
182
+ "learning_rate": 1.9177546256839814e-05,
183
+ "loss": 0.6839,
184
+ "step": 25
185
+ },
186
+ {
187
+ "epoch": 0.4622222222222222,
188
+ "grad_norm": 0.9047765135765076,
189
+ "learning_rate": 1.9048270524660197e-05,
190
+ "loss": 0.6768,
191
+ "step": 26
192
+ },
193
+ {
194
+ "epoch": 0.48,
195
+ "grad_norm": 0.9144095182418823,
196
+ "learning_rate": 1.891006524188368e-05,
197
+ "loss": 0.6773,
198
+ "step": 27
199
+ },
200
+ {
201
+ "epoch": 0.49777777777777776,
202
+ "grad_norm": 0.8761118054389954,
203
+ "learning_rate": 1.8763066800438638e-05,
204
+ "loss": 0.6852,
205
+ "step": 28
206
+ },
207
+ {
208
+ "epoch": 0.5155555555555555,
209
+ "grad_norm": 0.9473320841789246,
210
+ "learning_rate": 1.860742027003944e-05,
211
+ "loss": 0.6882,
212
+ "step": 29
213
+ },
214
+ {
215
+ "epoch": 0.5333333333333333,
216
+ "grad_norm": 1.0702017545700073,
217
+ "learning_rate": 1.8443279255020153e-05,
218
+ "loss": 0.6677,
219
+ "step": 30
220
+ },
221
+ {
222
+ "epoch": 0.5511111111111111,
223
+ "grad_norm": 0.7134117484092712,
224
+ "learning_rate": 1.827080574274562e-05,
225
+ "loss": 0.6696,
226
+ "step": 31
227
+ },
228
+ {
229
+ "epoch": 0.5688888888888889,
230
+ "grad_norm": 0.8997704386711121,
231
+ "learning_rate": 1.8090169943749477e-05,
232
+ "loss": 0.6484,
233
+ "step": 32
234
+ },
235
+ {
236
+ "epoch": 0.5866666666666667,
237
+ "grad_norm": 0.7318180203437805,
238
+ "learning_rate": 1.7901550123756906e-05,
239
+ "loss": 0.6859,
240
+ "step": 33
241
+ },
242
+ {
243
+ "epoch": 0.6044444444444445,
244
+ "grad_norm": 0.8574209213256836,
245
+ "learning_rate": 1.7705132427757895e-05,
246
+ "loss": 0.6557,
247
+ "step": 34
248
+ },
249
+ {
250
+ "epoch": 0.6222222222222222,
251
+ "grad_norm": 0.7167562246322632,
252
+ "learning_rate": 1.7501110696304598e-05,
253
+ "loss": 0.6511,
254
+ "step": 35
255
+ },
256
+ {
257
+ "epoch": 0.64,
258
+ "grad_norm": 0.701689600944519,
259
+ "learning_rate": 1.7289686274214116e-05,
260
+ "loss": 0.6603,
261
+ "step": 36
262
+ },
263
+ {
264
+ "epoch": 0.6577777777777778,
265
+ "grad_norm": 0.6708585023880005,
266
+ "learning_rate": 1.7071067811865477e-05,
267
+ "loss": 0.6674,
268
+ "step": 37
269
+ },
270
+ {
271
+ "epoch": 0.6755555555555556,
272
+ "grad_norm": 0.7055069208145142,
273
+ "learning_rate": 1.684547105928689e-05,
274
+ "loss": 0.6624,
275
+ "step": 38
276
+ },
277
+ {
278
+ "epoch": 0.6933333333333334,
279
+ "grad_norm": 0.6366652250289917,
280
+ "learning_rate": 1.661311865323652e-05,
281
+ "loss": 0.659,
282
+ "step": 39
283
+ },
284
+ {
285
+ "epoch": 0.7111111111111111,
286
+ "grad_norm": 0.7192656397819519,
287
+ "learning_rate": 1.63742398974869e-05,
288
+ "loss": 0.6403,
289
+ "step": 40
290
+ },
291
+ {
292
+ "epoch": 0.7288888888888889,
293
+ "grad_norm": 0.7419708967208862,
294
+ "learning_rate": 1.6129070536529767e-05,
295
+ "loss": 0.6649,
296
+ "step": 41
297
+ },
298
+ {
299
+ "epoch": 0.7466666666666667,
300
+ "grad_norm": 0.6875132918357849,
301
+ "learning_rate": 1.5877852522924733e-05,
302
+ "loss": 0.6636,
303
+ "step": 42
304
+ },
305
+ {
306
+ "epoch": 0.7644444444444445,
307
+ "grad_norm": 0.7200429439544678,
308
+ "learning_rate": 1.5620833778521306e-05,
309
+ "loss": 0.6464,
310
+ "step": 43
311
+ },
312
+ {
313
+ "epoch": 0.7822222222222223,
314
+ "grad_norm": 0.6726692318916321,
315
+ "learning_rate": 1.5358267949789968e-05,
316
+ "loss": 0.6513,
317
+ "step": 44
318
+ },
319
+ {
320
+ "epoch": 0.8,
321
+ "grad_norm": 0.6832252740859985,
322
+ "learning_rate": 1.5090414157503715e-05,
323
+ "loss": 0.6625,
324
+ "step": 45
325
+ },
326
+ {
327
+ "epoch": 0.8177777777777778,
328
+ "grad_norm": 0.7112930417060852,
329
+ "learning_rate": 1.4817536741017153e-05,
330
+ "loss": 0.6471,
331
+ "step": 46
332
+ },
333
+ {
334
+ "epoch": 0.8355555555555556,
335
+ "grad_norm": 0.671824038028717,
336
+ "learning_rate": 1.4539904997395468e-05,
337
+ "loss": 0.6625,
338
+ "step": 47
339
+ },
340
+ {
341
+ "epoch": 0.8533333333333334,
342
+ "grad_norm": 0.6902845501899719,
343
+ "learning_rate": 1.4257792915650728e-05,
344
+ "loss": 0.6374,
345
+ "step": 48
346
+ },
347
+ {
348
+ "epoch": 0.8711111111111111,
349
+ "grad_norm": 0.5699530243873596,
350
+ "learning_rate": 1.3971478906347806e-05,
351
+ "loss": 0.6431,
352
+ "step": 49
353
+ },
354
+ {
355
+ "epoch": 0.8888888888888888,
356
+ "grad_norm": 0.6002618670463562,
357
+ "learning_rate": 1.3681245526846782e-05,
358
+ "loss": 0.6381,
359
+ "step": 50
360
+ },
361
+ {
362
+ "epoch": 0.9066666666666666,
363
+ "grad_norm": 0.576767086982727,
364
+ "learning_rate": 1.3387379202452917e-05,
365
+ "loss": 0.6338,
366
+ "step": 51
367
+ },
368
+ {
369
+ "epoch": 0.9244444444444444,
370
+ "grad_norm": 0.6442639231681824,
371
+ "learning_rate": 1.3090169943749475e-05,
372
+ "loss": 0.6502,
373
+ "step": 52
374
+ },
375
+ {
376
+ "epoch": 0.9422222222222222,
377
+ "grad_norm": 0.651739776134491,
378
+ "learning_rate": 1.2789911060392295e-05,
379
+ "loss": 0.6449,
380
+ "step": 53
381
+ },
382
+ {
383
+ "epoch": 0.96,
384
+ "grad_norm": 0.8692764043807983,
385
+ "learning_rate": 1.2486898871648552e-05,
386
+ "loss": 0.6511,
387
+ "step": 54
388
+ },
389
+ {
390
+ "epoch": 0.9777777777777777,
391
+ "grad_norm": 0.6121811270713806,
392
+ "learning_rate": 1.2181432413965428e-05,
393
+ "loss": 0.6367,
394
+ "step": 55
395
+ },
396
+ {
397
+ "epoch": 0.9955555555555555,
398
+ "grad_norm": 0.8803330659866333,
399
+ "learning_rate": 1.187381314585725e-05,
400
+ "loss": 0.6532,
401
+ "step": 56
402
+ },
403
+ {
404
+ "epoch": 1.0133333333333334,
405
+ "grad_norm": 1.236048698425293,
406
+ "learning_rate": 1.156434465040231e-05,
407
+ "loss": 1.0796,
408
+ "step": 57
409
+ },
410
+ {
411
+ "epoch": 1.031111111111111,
412
+ "grad_norm": 0.899872362613678,
413
+ "learning_rate": 1.1253332335643043e-05,
414
+ "loss": 0.634,
415
+ "step": 58
416
+ },
417
+ {
418
+ "epoch": 1.048888888888889,
419
+ "grad_norm": 0.5719662308692932,
420
+ "learning_rate": 1.0941083133185146e-05,
421
+ "loss": 0.6002,
422
+ "step": 59
423
+ },
424
+ {
425
+ "epoch": 1.0666666666666667,
426
+ "grad_norm": 0.788408100605011,
427
+ "learning_rate": 1.0627905195293135e-05,
428
+ "loss": 0.5628,
429
+ "step": 60
430
+ },
431
+ {
432
+ "epoch": 1.0844444444444445,
433
+ "grad_norm": 0.7448046207427979,
434
+ "learning_rate": 1.0314107590781284e-05,
435
+ "loss": 0.6532,
436
+ "step": 61
437
+ },
438
+ {
439
+ "epoch": 1.1022222222222222,
440
+ "grad_norm": 0.8060784935951233,
441
+ "learning_rate": 1e-05,
442
+ "loss": 0.5744,
443
+ "step": 62
444
+ },
445
+ {
446
+ "epoch": 1.12,
447
+ "grad_norm": 0.7961754202842712,
448
+ "learning_rate": 9.685892409218718e-06,
449
+ "loss": 0.5798,
450
+ "step": 63
451
+ },
452
+ {
453
+ "epoch": 1.1377777777777778,
454
+ "grad_norm": 0.6215574145317078,
455
+ "learning_rate": 9.372094804706867e-06,
456
+ "loss": 0.567,
457
+ "step": 64
458
+ },
459
+ {
460
+ "epoch": 1.1555555555555554,
461
+ "grad_norm": 0.7157091498374939,
462
+ "learning_rate": 9.058916866814857e-06,
463
+ "loss": 0.6152,
464
+ "step": 65
465
+ },
466
+ {
467
+ "epoch": 1.1733333333333333,
468
+ "grad_norm": 0.6254159212112427,
469
+ "learning_rate": 8.746667664356957e-06,
470
+ "loss": 0.6099,
471
+ "step": 66
472
+ },
473
+ {
474
+ "epoch": 1.1911111111111112,
475
+ "grad_norm": 0.5155752897262573,
476
+ "learning_rate": 8.43565534959769e-06,
477
+ "loss": 0.5508,
478
+ "step": 67
479
+ },
480
+ {
481
+ "epoch": 1.208888888888889,
482
+ "grad_norm": 0.5491471886634827,
483
+ "learning_rate": 8.126186854142752e-06,
484
+ "loss": 0.625,
485
+ "step": 68
486
+ },
487
+ {
488
+ "epoch": 1.2266666666666666,
489
+ "grad_norm": 0.5200133919715881,
490
+ "learning_rate": 7.818567586034578e-06,
491
+ "loss": 0.5666,
492
+ "step": 69
493
+ },
494
+ {
495
+ "epoch": 1.2444444444444445,
496
+ "grad_norm": 0.5425897240638733,
497
+ "learning_rate": 7.513101128351454e-06,
498
+ "loss": 0.6,
499
+ "step": 70
500
+ },
501
+ {
502
+ "epoch": 1.2622222222222224,
503
+ "grad_norm": 0.420964777469635,
504
+ "learning_rate": 7.210088939607709e-06,
505
+ "loss": 0.5466,
506
+ "step": 71
507
+ },
508
+ {
509
+ "epoch": 1.28,
510
+ "grad_norm": 0.5204867124557495,
511
+ "learning_rate": 6.909830056250527e-06,
512
+ "loss": 0.6297,
513
+ "step": 72
514
+ },
515
+ {
516
+ "epoch": 1.2977777777777777,
517
+ "grad_norm": 0.491071879863739,
518
+ "learning_rate": 6.612620797547087e-06,
519
+ "loss": 0.5333,
520
+ "step": 73
521
+ },
522
+ {
523
+ "epoch": 1.3155555555555556,
524
+ "grad_norm": 0.4720323979854584,
525
+ "learning_rate": 6.318754473153221e-06,
526
+ "loss": 0.6132,
527
+ "step": 74
528
+ },
529
+ {
530
+ "epoch": 1.3333333333333333,
531
+ "grad_norm": 0.430493026971817,
532
+ "learning_rate": 6.028521093652195e-06,
533
+ "loss": 0.5587,
534
+ "step": 75
535
+ },
536
+ {
537
+ "epoch": 1.3511111111111112,
538
+ "grad_norm": 0.583470344543457,
539
+ "learning_rate": 5.742207084349274e-06,
540
+ "loss": 0.6111,
541
+ "step": 76
542
+ },
543
+ {
544
+ "epoch": 1.3688888888888888,
545
+ "grad_norm": 0.5109282732009888,
546
+ "learning_rate": 5.460095002604533e-06,
547
+ "loss": 0.5848,
548
+ "step": 77
549
+ },
550
+ {
551
+ "epoch": 1.3866666666666667,
552
+ "grad_norm": 0.5880340933799744,
553
+ "learning_rate": 5.1824632589828465e-06,
554
+ "loss": 0.6158,
555
+ "step": 78
556
+ },
557
+ {
558
+ "epoch": 1.4044444444444444,
559
+ "grad_norm": 0.5229690670967102,
560
+ "learning_rate": 4.909585842496287e-06,
561
+ "loss": 0.5424,
562
+ "step": 79
563
+ },
564
+ {
565
+ "epoch": 1.4222222222222223,
566
+ "grad_norm": 0.5499680638313293,
567
+ "learning_rate": 4.641732050210032e-06,
568
+ "loss": 0.5793,
569
+ "step": 80
570
+ },
571
+ {
572
+ "epoch": 1.44,
573
+ "grad_norm": 0.42541825771331787,
574
+ "learning_rate": 4.379166221478697e-06,
575
+ "loss": 0.5984,
576
+ "step": 81
577
+ },
578
+ {
579
+ "epoch": 1.4577777777777778,
580
+ "grad_norm": 0.46670961380004883,
581
+ "learning_rate": 4.12214747707527e-06,
582
+ "loss": 0.621,
583
+ "step": 82
584
+ },
585
+ {
586
+ "epoch": 1.4755555555555555,
587
+ "grad_norm": 0.4210701286792755,
588
+ "learning_rate": 3.8709294634702374e-06,
589
+ "loss": 0.5242,
590
+ "step": 83
591
+ },
592
+ {
593
+ "epoch": 1.4933333333333334,
594
+ "grad_norm": 0.4062272310256958,
595
+ "learning_rate": 3.625760102513103e-06,
596
+ "loss": 0.563,
597
+ "step": 84
598
+ },
599
+ {
600
+ "epoch": 1.511111111111111,
601
+ "grad_norm": 0.42036882042884827,
602
+ "learning_rate": 3.3868813467634833e-06,
603
+ "loss": 0.6099,
604
+ "step": 85
605
+ },
606
+ {
607
+ "epoch": 1.528888888888889,
608
+ "grad_norm": 0.413107693195343,
609
+ "learning_rate": 3.1545289407131128e-06,
610
+ "loss": 0.5765,
611
+ "step": 86
612
+ },
613
+ {
614
+ "epoch": 1.5466666666666666,
615
+ "grad_norm": 0.4331943392753601,
616
+ "learning_rate": 2.9289321881345257e-06,
617
+ "loss": 0.5988,
618
+ "step": 87
619
+ },
620
+ {
621
+ "epoch": 1.5644444444444443,
622
+ "grad_norm": 0.4215940535068512,
623
+ "learning_rate": 2.7103137257858867e-06,
624
+ "loss": 0.5901,
625
+ "step": 88
626
+ },
627
+ {
628
+ "epoch": 1.5822222222222222,
629
+ "grad_norm": 0.3558850586414337,
630
+ "learning_rate": 2.4988893036954045e-06,
631
+ "loss": 0.5578,
632
+ "step": 89
633
+ },
634
+ {
635
+ "epoch": 1.6,
636
+ "grad_norm": 0.35593435168266296,
637
+ "learning_rate": 2.2948675722421086e-06,
638
+ "loss": 0.5952,
639
+ "step": 90
640
+ },
641
+ {
642
+ "epoch": 1.6177777777777778,
643
+ "grad_norm": 0.35841694474220276,
644
+ "learning_rate": 2.098449876243096e-06,
645
+ "loss": 0.5729,
646
+ "step": 91
647
+ },
648
+ {
649
+ "epoch": 1.6355555555555554,
650
+ "grad_norm": 0.36976689100265503,
651
+ "learning_rate": 1.9098300562505266e-06,
652
+ "loss": 0.6167,
653
+ "step": 92
654
+ },
655
+ {
656
+ "epoch": 1.6533333333333333,
657
+ "grad_norm": 0.34893473982810974,
658
+ "learning_rate": 1.7291942572543806e-06,
659
+ "loss": 0.558,
660
+ "step": 93
661
+ },
662
+ {
663
+ "epoch": 1.6711111111111112,
664
+ "grad_norm": 0.3704639673233032,
665
+ "learning_rate": 1.5567207449798517e-06,
666
+ "loss": 0.5948,
667
+ "step": 94
668
+ },
669
+ {
670
+ "epoch": 1.6888888888888889,
671
+ "grad_norm": 0.3578838109970093,
672
+ "learning_rate": 1.3925797299605649e-06,
673
+ "loss": 0.5715,
674
+ "step": 95
675
+ },
676
+ {
677
+ "epoch": 1.7066666666666666,
678
+ "grad_norm": 0.35762616991996765,
679
+ "learning_rate": 1.2369331995613664e-06,
680
+ "loss": 0.5936,
681
+ "step": 96
682
+ },
683
+ {
684
+ "epoch": 1.7244444444444444,
685
+ "grad_norm": 0.3288617730140686,
686
+ "learning_rate": 1.0899347581163222e-06,
687
+ "loss": 0.5924,
688
+ "step": 97
689
+ },
690
+ {
691
+ "epoch": 1.7422222222222223,
692
+ "grad_norm": 0.35121095180511475,
693
+ "learning_rate": 9.517294753398066e-07,
694
+ "loss": 0.575,
695
+ "step": 98
696
+ },
697
+ {
698
+ "epoch": 1.76,
699
+ "grad_norm": 0.32291051745414734,
700
+ "learning_rate": 8.224537431601886e-07,
701
+ "loss": 0.5367,
702
+ "step": 99
703
+ },
704
+ {
705
+ "epoch": 1.7777777777777777,
706
+ "grad_norm": 0.37526610493659973,
707
+ "learning_rate": 7.022351411174866e-07,
708
+ "loss": 0.5957,
709
+ "step": 100
710
+ },
711
+ {
712
+ "epoch": 1.7955555555555556,
713
+ "grad_norm": 0.34747347235679626,
714
+ "learning_rate": 5.911923104577455e-07,
715
+ "loss": 0.5824,
716
+ "step": 101
717
+ },
718
+ {
719
+ "epoch": 1.8133333333333335,
720
+ "grad_norm": 0.3201601803302765,
721
+ "learning_rate": 4.894348370484648e-07,
722
+ "loss": 0.561,
723
+ "step": 102
724
+ },
725
+ {
726
+ "epoch": 1.8311111111111111,
727
+ "grad_norm": 0.36945855617523193,
728
+ "learning_rate": 3.9706314323056936e-07,
729
+ "loss": 0.5761,
730
+ "step": 103
731
+ },
732
+ {
733
+ "epoch": 1.8488888888888888,
734
+ "grad_norm": 0.3337363600730896,
735
+ "learning_rate": 3.1416838871368925e-07,
736
+ "loss": 0.5536,
737
+ "step": 104
738
+ },
739
+ {
740
+ "epoch": 1.8666666666666667,
741
+ "grad_norm": 0.35673728585243225,
742
+ "learning_rate": 2.4083238061252565e-07,
743
+ "loss": 0.6234,
744
+ "step": 105
745
+ },
746
+ {
747
+ "epoch": 1.8844444444444446,
748
+ "grad_norm": 0.3251909613609314,
749
+ "learning_rate": 1.7712749271311392e-07,
750
+ "loss": 0.5415,
751
+ "step": 106
752
+ },
753
+ {
754
+ "epoch": 1.9022222222222223,
755
+ "grad_norm": 0.35213449597358704,
756
+ "learning_rate": 1.231165940486234e-07,
757
+ "loss": 0.5611,
758
+ "step": 107
759
+ },
760
+ {
761
+ "epoch": 1.92,
762
+ "grad_norm": 0.34044721722602844,
763
+ "learning_rate": 7.885298685522235e-08,
764
+ "loss": 0.5628,
765
+ "step": 108
766
+ },
767
+ {
768
+ "epoch": 1.9377777777777778,
769
+ "grad_norm": 0.34606897830963135,
770
+ "learning_rate": 4.438035396920004e-08,
771
+ "loss": 0.5907,
772
+ "step": 109
773
+ },
774
+ {
775
+ "epoch": 1.9555555555555557,
776
+ "grad_norm": 0.3360365629196167,
777
+ "learning_rate": 1.973271571728441e-08,
778
+ "loss": 0.6009,
779
+ "step": 110
780
+ },
781
+ {
782
+ "epoch": 1.9733333333333334,
783
+ "grad_norm": 0.3323586583137512,
784
+ "learning_rate": 4.9343963426840006e-09,
785
+ "loss": 0.5773,
786
+ "step": 111
787
+ },
788
+ {
789
+ "epoch": 1.991111111111111,
790
+ "grad_norm": 0.3478974997997284,
791
+ "learning_rate": 0.0,
792
+ "loss": 0.5963,
793
+ "step": 112
794
+ },
795
+ {
796
+ "epoch": 1.991111111111111,
797
+ "step": 112,
798
+ "total_flos": 185195202609152.0,
799
+ "train_loss": 0.65867241738098,
800
+ "train_runtime": 12992.6194,
801
+ "train_samples_per_second": 0.83,
802
+ "train_steps_per_second": 0.009
803
+ }
804
+ ],
805
+ "logging_steps": 1,
806
+ "max_steps": 112,
807
+ "num_input_tokens_seen": 0,
808
+ "num_train_epochs": 2,
809
+ "save_steps": 100,
810
+ "stateful_callbacks": {
811
+ "TrainerControl": {
812
+ "args": {
813
+ "should_epoch_stop": false,
814
+ "should_evaluate": false,
815
+ "should_log": false,
816
+ "should_save": true,
817
+ "should_training_stop": true
818
+ },
819
+ "attributes": {}
820
+ }
821
+ },
822
+ "total_flos": 185195202609152.0,
823
+ "train_batch_size": 1,
824
+ "trial_name": null,
825
+ "trial_params": null
826
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6add66dd5d153f621aa86f217739a1b5097adfcd09ff4887b181d9a284c89ba7
3
+ size 7416
training_loss.png ADDED
vocab.json ADDED
The diff for this file is too large to render. See raw diff