Hugging Face's logo

ntnu-smil
/
phi4-mini-rag

TensorBoard
Safetensors
phi3
custom_code
Model card Files
xet
 Metrics Community
JacobLinCool howard9199 commited on
Commit
cb02cf4
·
verified ·
0 Parent(s):

Super-squash branch 'main' using huggingface_hub

Browse files

Co-authored-by: howard9199 <howard9199@users.noreply.huggingface.co>

Files changed (42) hide show
  1. .gitattributes +36 -0
  2. added_tokens.json +12 -0
  3. checkpoint-13293/config.json +143 -0
  4. checkpoint-13293/generation_config.json +10 -0
  5. checkpoint-13293/model-00001-of-00002.safetensors +3 -0
  6. checkpoint-13293/model-00002-of-00002.safetensors +3 -0
  7. checkpoint-13293/model.safetensors.index.json +201 -0
  8. checkpoint-13293/trainer_state.json +0 -0
  9. checkpoint-13293/training_args.bin +3 -0
  10. checkpoint-4431/config.json +143 -0
  11. checkpoint-4431/generation_config.json +10 -0
  12. checkpoint-4431/model-00001-of-00002.safetensors +3 -0
  13. checkpoint-4431/model-00002-of-00002.safetensors +3 -0
  14. checkpoint-4431/model.safetensors.index.json +201 -0
  15. checkpoint-4431/trainer_state.json +3135 -0
  16. checkpoint-4431/training_args.bin +3 -0
  17. checkpoint-8862/config.json +143 -0
  18. checkpoint-8862/generation_config.json +10 -0
  19. checkpoint-8862/model-00001-of-00002.safetensors +3 -0
  20. checkpoint-8862/model-00002-of-00002.safetensors +3 -0
  21. checkpoint-8862/model.safetensors.index.json +201 -0
  22. checkpoint-8862/trainer_state.json +0 -0
  23. checkpoint-8862/training_args.bin +3 -0
  24. config.json +143 -0
  25. generation_config.json +10 -0
  26. merges.txt +0 -0
  27. model-00001-of-00002.safetensors +3 -0
  28. model-00002-of-00002.safetensors +3 -0
  29. model.safetensors.index.json +201 -0
  30. runs/Apr01_13-43-26_f952690d2a16/events.out.tfevents.1743515006.f952690d2a16 +3 -0
  31. runs/Apr01_13-44-23_f952690d2a16/events.out.tfevents.1743515063.f952690d2a16 +3 -0
  32. runs/Apr01_13-46-10_f952690d2a16/events.out.tfevents.1743515171.f952690d2a16 +3 -0
  33. runs/Apr01_13-49-28_f952690d2a16/events.out.tfevents.1743515368.f952690d2a16 +3 -0
  34. runs/Apr01_13-50-10_f952690d2a16/events.out.tfevents.1743515410.f952690d2a16 +3 -0
  35. runs/Apr01_13-51-48_f952690d2a16/events.out.tfevents.1743515508.f952690d2a16 +3 -0
  36. runs/Apr01_14-12-59_f952690d2a16/events.out.tfevents.1743516780.f952690d2a16 +3 -0
  37. runs/Apr01_16-49-22_f952690d2a16/events.out.tfevents.1743526162.f952690d2a16 +3 -0
  38. special_tokens_map.json +30 -0
  39. tokenizer.json +3 -0
  40. tokenizer_config.json +112 -0
  41. training_args.bin +3 -0
  42. vocab.json +0 -0
.gitattributes ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ *.7z filter=lfs diff=lfs merge=lfs -text
2
+ *.arrow filter=lfs diff=lfs merge=lfs -text
3
+ *.bin filter=lfs diff=lfs merge=lfs -text
4
+ *.bz2 filter=lfs diff=lfs merge=lfs -text
5
+ *.ckpt filter=lfs diff=lfs merge=lfs -text
6
+ *.ftz filter=lfs diff=lfs merge=lfs -text
7
+ *.gz filter=lfs diff=lfs merge=lfs -text
8
+ *.h5 filter=lfs diff=lfs merge=lfs -text
9
+ *.joblib filter=lfs diff=lfs merge=lfs -text
10
+ *.lfs.* filter=lfs diff=lfs merge=lfs -text
11
+ *.mlmodel filter=lfs diff=lfs merge=lfs -text
12
+ *.model filter=lfs diff=lfs merge=lfs -text
13
+ *.msgpack filter=lfs diff=lfs merge=lfs -text
14
+ *.npy filter=lfs diff=lfs merge=lfs -text
15
+ *.npz filter=lfs diff=lfs merge=lfs -text
16
+ *.onnx filter=lfs diff=lfs merge=lfs -text
17
+ *.ot filter=lfs diff=lfs merge=lfs -text
18
+ *.parquet filter=lfs diff=lfs merge=lfs -text
19
+ *.pb filter=lfs diff=lfs merge=lfs -text
20
+ *.pickle filter=lfs diff=lfs merge=lfs -text
21
+ *.pkl filter=lfs diff=lfs merge=lfs -text
22
+ *.pt filter=lfs diff=lfs merge=lfs -text
23
+ *.pth filter=lfs diff=lfs merge=lfs -text
24
+ *.rar filter=lfs diff=lfs merge=lfs -text
25
+ *.safetensors filter=lfs diff=lfs merge=lfs -text
26
+ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
27
+ *.tar.* filter=lfs diff=lfs merge=lfs -text
28
+ *.tar filter=lfs diff=lfs merge=lfs -text
29
+ *.tflite filter=lfs diff=lfs merge=lfs -text
30
+ *.tgz filter=lfs diff=lfs merge=lfs -text
31
+ *.wasm filter=lfs diff=lfs merge=lfs -text
32
+ *.xz 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
added_tokens.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<|/tool_call|>": 200026,
3
+ "<|/tool|>": 200024,
4
+ "<|assistant|>": 200019,
5
+ "<|end|>": 200020,
6
+ "<|system|>": 200022,
7
+ "<|tag|>": 200028,
8
+ "<|tool_call|>": 200025,
9
+ "<|tool_response|>": 200027,
10
+ "<|tool|>": 200023,
11
+ "<|user|>": 200021
12
+ }
checkpoint-13293/config.json ADDED
@@ -0,0 +1,143 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Phi3ForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "auto_map": {
8
+ "AutoConfig": "microsoft/Phi-4-mini-instruct--configuration_phi3.Phi3Config",
9
+ "AutoModelForCausalLM": "microsoft/Phi-4-mini-instruct--modeling_phi3.Phi3ForCausalLM",
10
+ "AutoTokenizer": "microsoft/Phi-4-mini-instruct--Xenova/gpt-4o"
11
+ },
12
+ "bos_token_id": 199999,
13
+ "embd_pdrop": 0.0,
14
+ "eos_token_id": 199999,
15
+ "full_attn_mod": 1,
16
+ "hidden_act": "silu",
17
+ "hidden_size": 3072,
18
+ "initializer_range": 0.02,
19
+ "intermediate_size": 8192,
20
+ "interpolate_factor": 1,
21
+ "lm_head_bias": false,
22
+ "max_position_embeddings": 131072,
23
+ "mlp_bias": false,
24
+ "model_type": "phi3",
25
+ "num_attention_heads": 24,
26
+ "num_hidden_layers": 32,
27
+ "num_key_value_heads": 8,
28
+ "original_max_position_embeddings": 4096,
29
+ "pad_token_id": 199999,
30
+ "partial_rotary_factor": 0.75,
31
+ "resid_pdrop": 0.0,
32
+ "rms_norm_eps": 1e-05,
33
+ "rope_scaling": {
34
+ "long_factor": [
35
+ 1,
36
+ 1.118320672,
37
+ 1.250641126,
38
+ 1.398617824,
39
+ 1.564103225,
40
+ 1.74916897,
41
+ 1.956131817,
42
+ 2.187582649,
43
+ 2.446418898,
44
+ 2.735880826,
45
+ 3.059592084,
46
+ 3.421605075,
47
+ 3.826451687,
48
+ 4.279200023,
49
+ 4.785517845,
50
+ 5.351743533,
51
+ 5.984965424,
52
+ 6.693110555,
53
+ 7.485043894,
54
+ 8.370679318,
55
+ 9.36110372,
56
+ 10.4687158,
57
+ 11.70738129,
58
+ 13.09260651,
59
+ 14.64173252,
60
+ 16.37415215,
61
+ 18.31155283,
62
+ 20.47818807,
63
+ 22.90118105,
64
+ 25.61086418,
65
+ 28.64115884,
66
+ 32.03,
67
+ 32.1,
68
+ 32.13,
69
+ 32.23,
70
+ 32.6,
71
+ 32.61,
72
+ 32.64,
73
+ 32.66,
74
+ 32.7,
75
+ 32.71,
76
+ 32.93,
77
+ 32.97,
78
+ 33.28,
79
+ 33.49,
80
+ 33.5,
81
+ 44.16,
82
+ 47.77
83
+ ],
84
+ "short_factor": [
85
+ 1.0,
86
+ 1.0,
87
+ 1.0,
88
+ 1.0,
89
+ 1.0,
90
+ 1.0,
91
+ 1.0,
92
+ 1.0,
93
+ 1.0,
94
+ 1.0,
95
+ 1.0,
96
+ 1.0,
97
+ 1.0,
98
+ 1.0,
99
+ 1.0,
100
+ 1.0,
101
+ 1.0,
102
+ 1.0,
103
+ 1.0,
104
+ 1.0,
105
+ 1.0,
106
+ 1.0,
107
+ 1.0,
108
+ 1.0,
109
+ 1.0,
110
+ 1.0,
111
+ 1.0,
112
+ 1.0,
113
+ 1.0,
114
+ 1.0,
115
+ 1.0,
116
+ 1.0,
117
+ 1.0,
118
+ 1.0,
119
+ 1.0,
120
+ 1.0,
121
+ 1.0,
122
+ 1.0,
123
+ 1.0,
124
+ 1.0,
125
+ 1.0,
126
+ 1.0,
127
+ 1.0,
128
+ 1.0,
129
+ 1.0,
130
+ 1.0,
131
+ 1.0,
132
+ 1.0
133
+ ],
134
+ "type": "longrope"
135
+ },
136
+ "rope_theta": 10000.0,
137
+ "sliding_window": 262144,
138
+ "tie_word_embeddings": true,
139
+ "torch_dtype": "bfloat16",
140
+ "transformers_version": "4.50.3",
141
+ "use_cache": true,
142
+ "vocab_size": 200064
143
+ }
checkpoint-13293/generation_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 199999,
4
+ "eos_token_id": [
5
+ 200020,
6
+ 199999
7
+ ],
8
+ "pad_token_id": 199999,
9
+ "transformers_version": "4.50.3"
10
+ }
checkpoint-13293/model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a95f7cfd274cc1286e46a9d1713da4ddf9b90c02051478cc7a095e6a862b68b1
3
+ size 4903637712
checkpoint-13293/model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cdc26676eeb2fcb18b5e7aad475c8267d2a63be86e86b65f7e5b28f1a04742c6
3
+ size 2768428504
checkpoint-13293/model.safetensors.index.json ADDED
@@ -0,0 +1,201 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 7672043520
4
+ },
5
+ "weight_map": {
6
+ "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
7
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
8
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
9
+ "model.layers.0.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
10
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
11
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
12
+ "model.layers.0.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
13
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
14
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
15
+ "model.layers.1.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
16
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
17
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
18
+ "model.layers.1.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
19
+ "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
20
+ "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
21
+ "model.layers.10.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
22
+ "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
23
+ "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
24
+ "model.layers.10.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
25
+ "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
26
+ "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
27
+ "model.layers.11.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
28
+ "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
29
+ "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
30
+ "model.layers.11.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
31
+ "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
32
+ "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
33
+ "model.layers.12.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
34
+ "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
35
+ "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
36
+ "model.layers.12.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
37
+ "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
38
+ "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
39
+ "model.layers.13.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
40
+ "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
41
+ "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
42
+ "model.layers.13.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
43
+ "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
44
+ "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
45
+ "model.layers.14.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
46
+ "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
47
+ "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
48
+ "model.layers.14.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
49
+ "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
50
+ "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
51
+ "model.layers.15.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
52
+ "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
53
+ "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
54
+ "model.layers.15.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
55
+ "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
56
+ "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
57
+ "model.layers.16.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
58
+ "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
59
+ "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
60
+ "model.layers.16.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
61
+ "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
62
+ "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
63
+ "model.layers.17.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
64
+ "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
65
+ "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
66
+ "model.layers.17.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
67
+ "model.layers.18.input_layernorm.weight": "model-00002-of-00002.safetensors",
68
+ "model.layers.18.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
69
+ "model.layers.18.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
70
+ "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
71
+ "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
72
+ "model.layers.18.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
73
+ "model.layers.19.input_layernorm.weight": "model-00002-of-00002.safetensors",
74
+ "model.layers.19.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
75
+ "model.layers.19.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
76
+ "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
77
+ "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
78
+ "model.layers.19.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
79
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
80
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
81
+ "model.layers.2.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
82
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
83
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
84
+ "model.layers.2.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
85
+ "model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
86
+ "model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
87
+ "model.layers.20.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
88
+ "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
89
+ "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
90
+ "model.layers.20.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
91
+ "model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
92
+ "model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
93
+ "model.layers.21.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
94
+ "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
95
+ "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
96
+ "model.layers.21.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
97
+ "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
98
+ "model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
99
+ "model.layers.22.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
100
+ "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
101
+ "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
102
+ "model.layers.22.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
103
+ "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
104
+ "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
105
+ "model.layers.23.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
106
+ "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
107
+ "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
108
+ "model.layers.23.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
109
+ "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
110
+ "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
111
+ "model.layers.24.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
112
+ "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
113
+ "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
114
+ "model.layers.24.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
115
+ "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
116
+ "model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
117
+ "model.layers.25.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
118
+ "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
119
+ "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
120
+ "model.layers.25.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
121
+ "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
122
+ "model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
123
+ "model.layers.26.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
124
+ "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
125
+ "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
126
+ "model.layers.26.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
127
+ "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
128
+ "model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
129
+ "model.layers.27.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
130
+ "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
131
+ "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
132
+ "model.layers.27.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
133
+ "model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
134
+ "model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
135
+ "model.layers.28.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
136
+ "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
137
+ "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
138
+ "model.layers.28.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
139
+ "model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
140
+ "model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
141
+ "model.layers.29.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
142
+ "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
143
+ "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
144
+ "model.layers.29.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
145
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
146
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
147
+ "model.layers.3.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
148
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
149
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
150
+ "model.layers.3.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
151
+ "model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
152
+ "model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
153
+ "model.layers.30.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
154
+ "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
155
+ "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
156
+ "model.layers.30.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
157
+ "model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
158
+ "model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
159
+ "model.layers.31.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
160
+ "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
161
+ "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
162
+ "model.layers.31.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
163
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
164
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
165
+ "model.layers.4.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
166
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
167
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
168
+ "model.layers.4.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
169
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
170
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
171
+ "model.layers.5.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
172
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
173
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
174
+ "model.layers.5.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
175
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
176
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
177
+ "model.layers.6.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
178
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
179
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
180
+ "model.layers.6.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
181
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
182
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
183
+ "model.layers.7.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
184
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
185
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
186
+ "model.layers.7.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
187
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
188
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
189
+ "model.layers.8.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
190
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
191
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
192
+ "model.layers.8.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
193
+ "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
194
+ "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
195
+ "model.layers.9.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
196
+ "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
197
+ "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
198
+ "model.layers.9.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
199
+ "model.norm.weight": "model-00002-of-00002.safetensors"
200
+ }
201
+ }
checkpoint-13293/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-13293/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:796a84fa762533861d74178663d2c947fb1915fe6d6b1fc474c454eece28dda1
3
+ size 5432
checkpoint-4431/config.json ADDED
@@ -0,0 +1,143 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Phi3ForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "auto_map": {
8
+ "AutoConfig": "microsoft/Phi-4-mini-instruct--configuration_phi3.Phi3Config",
9
+ "AutoModelForCausalLM": "microsoft/Phi-4-mini-instruct--modeling_phi3.Phi3ForCausalLM",
10
+ "AutoTokenizer": "microsoft/Phi-4-mini-instruct--Xenova/gpt-4o"
11
+ },
12
+ "bos_token_id": 199999,
13
+ "embd_pdrop": 0.0,
14
+ "eos_token_id": 199999,
15
+ "full_attn_mod": 1,
16
+ "hidden_act": "silu",
17
+ "hidden_size": 3072,
18
+ "initializer_range": 0.02,
19
+ "intermediate_size": 8192,
20
+ "interpolate_factor": 1,
21
+ "lm_head_bias": false,
22
+ "max_position_embeddings": 131072,
23
+ "mlp_bias": false,
24
+ "model_type": "phi3",
25
+ "num_attention_heads": 24,
26
+ "num_hidden_layers": 32,
27
+ "num_key_value_heads": 8,
28
+ "original_max_position_embeddings": 4096,
29
+ "pad_token_id": 199999,
30
+ "partial_rotary_factor": 0.75,
31
+ "resid_pdrop": 0.0,
32
+ "rms_norm_eps": 1e-05,
33
+ "rope_scaling": {
34
+ "long_factor": [
35
+ 1,
36
+ 1.118320672,
37
+ 1.250641126,
38
+ 1.398617824,
39
+ 1.564103225,
40
+ 1.74916897,
41
+ 1.956131817,
42
+ 2.187582649,
43
+ 2.446418898,
44
+ 2.735880826,
45
+ 3.059592084,
46
+ 3.421605075,
47
+ 3.826451687,
48
+ 4.279200023,
49
+ 4.785517845,
50
+ 5.351743533,
51
+ 5.984965424,
52
+ 6.693110555,
53
+ 7.485043894,
54
+ 8.370679318,
55
+ 9.36110372,
56
+ 10.4687158,
57
+ 11.70738129,
58
+ 13.09260651,
59
+ 14.64173252,
60
+ 16.37415215,
61
+ 18.31155283,
62
+ 20.47818807,
63
+ 22.90118105,
64
+ 25.61086418,
65
+ 28.64115884,
66
+ 32.03,
67
+ 32.1,
68
+ 32.13,
69
+ 32.23,
70
+ 32.6,
71
+ 32.61,
72
+ 32.64,
73
+ 32.66,
74
+ 32.7,
75
+ 32.71,
76
+ 32.93,
77
+ 32.97,
78
+ 33.28,
79
+ 33.49,
80
+ 33.5,
81
+ 44.16,
82
+ 47.77
83
+ ],
84
+ "short_factor": [
85
+ 1.0,
86
+ 1.0,
87
+ 1.0,
88
+ 1.0,
89
+ 1.0,
90
+ 1.0,
91
+ 1.0,
92
+ 1.0,
93
+ 1.0,
94
+ 1.0,
95
+ 1.0,
96
+ 1.0,
97
+ 1.0,
98
+ 1.0,
99
+ 1.0,
100
+ 1.0,
101
+ 1.0,
102
+ 1.0,
103
+ 1.0,
104
+ 1.0,
105
+ 1.0,
106
+ 1.0,
107
+ 1.0,
108
+ 1.0,
109
+ 1.0,
110
+ 1.0,
111
+ 1.0,
112
+ 1.0,
113
+ 1.0,
114
+ 1.0,
115
+ 1.0,
116
+ 1.0,
117
+ 1.0,
118
+ 1.0,
119
+ 1.0,
120
+ 1.0,
121
+ 1.0,
122
+ 1.0,
123
+ 1.0,
124
+ 1.0,
125
+ 1.0,
126
+ 1.0,
127
+ 1.0,
128
+ 1.0,
129
+ 1.0,
130
+ 1.0,
131
+ 1.0,
132
+ 1.0
133
+ ],
134
+ "type": "longrope"
135
+ },
136
+ "rope_theta": 10000.0,
137
+ "sliding_window": 262144,
138
+ "tie_word_embeddings": true,
139
+ "torch_dtype": "bfloat16",
140
+ "transformers_version": "4.50.3",
141
+ "use_cache": true,
142
+ "vocab_size": 200064
143
+ }
checkpoint-4431/generation_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 199999,
4
+ "eos_token_id": [
5
+ 200020,
6
+ 199999
7
+ ],
8
+ "pad_token_id": 199999,
9
+ "transformers_version": "4.50.3"
10
+ }
checkpoint-4431/model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c808a7192fd5b4c19efbd6ce0f51e107982d44c1ecd2cc8cd7c388465ff8e87d
3
+ size 4903637712
checkpoint-4431/model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:31cca3df25611febcfc5d5d501e0a7fffd06d622c25f5354db06d5d2f3873d9b
3
+ size 2768428504
checkpoint-4431/model.safetensors.index.json ADDED
@@ -0,0 +1,201 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 7672043520
4
+ },
5
+ "weight_map": {
6
+ "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
7
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
8
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
9
+ "model.layers.0.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
10
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
11
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
12
+ "model.layers.0.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
13
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
14
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
15
+ "model.layers.1.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
16
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
17
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
18
+ "model.layers.1.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
19
+ "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
20
+ "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
21
+ "model.layers.10.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
22
+ "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
23
+ "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
24
+ "model.layers.10.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
25
+ "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
26
+ "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
27
+ "model.layers.11.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
28
+ "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
29
+ "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
30
+ "model.layers.11.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
31
+ "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
32
+ "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
33
+ "model.layers.12.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
34
+ "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
35
+ "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
36
+ "model.layers.12.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
37
+ "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
38
+ "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
39
+ "model.layers.13.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
40
+ "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
41
+ "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
42
+ "model.layers.13.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
43
+ "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
44
+ "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
45
+ "model.layers.14.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
46
+ "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
47
+ "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
48
+ "model.layers.14.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
49
+ "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
50
+ "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
51
+ "model.layers.15.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
52
+ "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
53
+ "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
54
+ "model.layers.15.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
55
+ "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
56
+ "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
57
+ "model.layers.16.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
58
+ "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
59
+ "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
60
+ "model.layers.16.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
61
+ "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
62
+ "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
63
+ "model.layers.17.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
64
+ "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
65
+ "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
66
+ "model.layers.17.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
67
+ "model.layers.18.input_layernorm.weight": "model-00002-of-00002.safetensors",
68
+ "model.layers.18.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
69
+ "model.layers.18.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
70
+ "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
71
+ "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
72
+ "model.layers.18.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
73
+ "model.layers.19.input_layernorm.weight": "model-00002-of-00002.safetensors",
74
+ "model.layers.19.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
75
+ "model.layers.19.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
76
+ "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
77
+ "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
78
+ "model.layers.19.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
79
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
80
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
81
+ "model.layers.2.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
82
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
83
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
84
+ "model.layers.2.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
85
+ "model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
86
+ "model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
87
+ "model.layers.20.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
88
+ "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
89
+ "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
90
+ "model.layers.20.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
91
+ "model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
92
+ "model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
93
+ "model.layers.21.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
94
+ "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
95
+ "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
96
+ "model.layers.21.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
97
+ "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
98
+ "model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
99
+ "model.layers.22.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
100
+ "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
101
+ "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
102
+ "model.layers.22.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
103
+ "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
104
+ "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
105
+ "model.layers.23.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
106
+ "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
107
+ "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
108
+ "model.layers.23.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
109
+ "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
110
+ "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
111
+ "model.layers.24.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
112
+ "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
113
+ "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
114
+ "model.layers.24.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
115
+ "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
116
+ "model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
117
+ "model.layers.25.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
118
+ "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
119
+ "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
120
+ "model.layers.25.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
121
+ "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
122
+ "model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
123
+ "model.layers.26.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
124
+ "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
125
+ "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
126
+ "model.layers.26.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
127
+ "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
128
+ "model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
129
+ "model.layers.27.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
130
+ "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
131
+ "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
132
+ "model.layers.27.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
133
+ "model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
134
+ "model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
135
+ "model.layers.28.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
136
+ "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
137
+ "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
138
+ "model.layers.28.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
139
+ "model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
140
+ "model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
141
+ "model.layers.29.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
142
+ "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
143
+ "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
144
+ "model.layers.29.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
145
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
146
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
147
+ "model.layers.3.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
148
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
149
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
150
+ "model.layers.3.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
151
+ "model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
152
+ "model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
153
+ "model.layers.30.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
154
+ "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
155
+ "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
156
+ "model.layers.30.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
157
+ "model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
158
+ "model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
159
+ "model.layers.31.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
160
+ "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
161
+ "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
162
+ "model.layers.31.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
163
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
164
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
165
+ "model.layers.4.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
166
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
167
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
168
+ "model.layers.4.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
169
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
170
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
171
+ "model.layers.5.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
172
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
173
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
174
+ "model.layers.5.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
175
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
176
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
177
+ "model.layers.6.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
178
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
179
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
180
+ "model.layers.6.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
181
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
182
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
183
+ "model.layers.7.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
184
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
185
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
186
+ "model.layers.7.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
187
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
188
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
189
+ "model.layers.8.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
190
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
191
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
192
+ "model.layers.8.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
193
+ "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
194
+ "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
195
+ "model.layers.9.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
196
+ "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
197
+ "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
198
+ "model.layers.9.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
199
+ "model.norm.weight": "model-00002-of-00002.safetensors"
200
+ }
201
+ }
checkpoint-4431/trainer_state.json ADDED
@@ -0,0 +1,3135 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 1.0,
6
+ "eval_steps": 500,
7
+ "global_step": 4431,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.0022568269013766643,
14
+ "grad_norm": 342.0,
15
+ "learning_rate": 2.0000000000000003e-06,
16
+ "loss": 6.6491,
17
+ "step": 10
18
+ },
19
+ {
20
+ "epoch": 0.0045136538027533285,
21
+ "grad_norm": 60.75,
22
+ "learning_rate": 4.000000000000001e-06,
23
+ "loss": 2.1305,
24
+ "step": 20
25
+ },
26
+ {
27
+ "epoch": 0.006770480704129994,
28
+ "grad_norm": 13.9375,
29
+ "learning_rate": 6e-06,
30
+ "loss": 0.2525,
31
+ "step": 30
32
+ },
33
+ {
34
+ "epoch": 0.009027307605506657,
35
+ "grad_norm": 100.0,
36
+ "learning_rate": 8.000000000000001e-06,
37
+ "loss": 0.2105,
38
+ "step": 40
39
+ },
40
+ {
41
+ "epoch": 0.011284134506883321,
42
+ "grad_norm": 84.5,
43
+ "learning_rate": 1e-05,
44
+ "loss": 0.0882,
45
+ "step": 50
46
+ },
47
+ {
48
+ "epoch": 0.013540961408259987,
49
+ "grad_norm": 0.06591796875,
50
+ "learning_rate": 9.992448840897079e-06,
51
+ "loss": 0.2672,
52
+ "step": 60
53
+ },
54
+ {
55
+ "epoch": 0.01579778830963665,
56
+ "grad_norm": 0.00982666015625,
57
+ "learning_rate": 9.984897681794156e-06,
58
+ "loss": 0.0005,
59
+ "step": 70
60
+ },
61
+ {
62
+ "epoch": 0.018054615211013314,
63
+ "grad_norm": 0.00927734375,
64
+ "learning_rate": 9.977346522691234e-06,
65
+ "loss": 0.0073,
66
+ "step": 80
67
+ },
68
+ {
69
+ "epoch": 0.020311442112389978,
70
+ "grad_norm": 0.0020751953125,
71
+ "learning_rate": 9.969795363588312e-06,
72
+ "loss": 0.0,
73
+ "step": 90
74
+ },
75
+ {
76
+ "epoch": 0.022568269013766643,
77
+ "grad_norm": 0.0023345947265625,
78
+ "learning_rate": 9.96224420448539e-06,
79
+ "loss": 0.0,
80
+ "step": 100
81
+ },
82
+ {
83
+ "epoch": 0.02482509591514331,
84
+ "grad_norm": 0.0027618408203125,
85
+ "learning_rate": 9.954693045382467e-06,
86
+ "loss": 0.0,
87
+ "step": 110
88
+ },
89
+ {
90
+ "epoch": 0.027081922816519974,
91
+ "grad_norm": 0.0198974609375,
92
+ "learning_rate": 9.947141886279545e-06,
93
+ "loss": 0.0001,
94
+ "step": 120
95
+ },
96
+ {
97
+ "epoch": 0.02933874971789664,
98
+ "grad_norm": 0.005035400390625,
99
+ "learning_rate": 9.939590727176623e-06,
100
+ "loss": 0.0,
101
+ "step": 130
102
+ },
103
+ {
104
+ "epoch": 0.0315955766192733,
105
+ "grad_norm": 0.0927734375,
106
+ "learning_rate": 9.9320395680737e-06,
107
+ "loss": 0.0,
108
+ "step": 140
109
+ },
110
+ {
111
+ "epoch": 0.033852403520649964,
112
+ "grad_norm": 0.0025177001953125,
113
+ "learning_rate": 9.924488408970778e-06,
114
+ "loss": 0.6798,
115
+ "step": 150
116
+ },
117
+ {
118
+ "epoch": 0.03610923042202663,
119
+ "grad_norm": 0.01239013671875,
120
+ "learning_rate": 9.916937249867854e-06,
121
+ "loss": 0.216,
122
+ "step": 160
123
+ },
124
+ {
125
+ "epoch": 0.03836605732340329,
126
+ "grad_norm": 0.00543212890625,
127
+ "learning_rate": 9.909386090764932e-06,
128
+ "loss": 0.0005,
129
+ "step": 170
130
+ },
131
+ {
132
+ "epoch": 0.040622884224779957,
133
+ "grad_norm": 0.006072998046875,
134
+ "learning_rate": 9.901834931662012e-06,
135
+ "loss": 0.4586,
136
+ "step": 180
137
+ },
138
+ {
139
+ "epoch": 0.04287971112615662,
140
+ "grad_norm": 0.00101470947265625,
141
+ "learning_rate": 9.89428377255909e-06,
142
+ "loss": 0.0,
143
+ "step": 190
144
+ },
145
+ {
146
+ "epoch": 0.045136538027533285,
147
+ "grad_norm": 0.000591278076171875,
148
+ "learning_rate": 9.886732613456166e-06,
149
+ "loss": 0.0001,
150
+ "step": 200
151
+ },
152
+ {
153
+ "epoch": 0.04739336492890995,
154
+ "grad_norm": 0.042236328125,
155
+ "learning_rate": 9.879181454353243e-06,
156
+ "loss": 0.4003,
157
+ "step": 210
158
+ },
159
+ {
160
+ "epoch": 0.04965019183028662,
161
+ "grad_norm": 0.00171661376953125,
162
+ "learning_rate": 9.871630295250321e-06,
163
+ "loss": 0.0001,
164
+ "step": 220
165
+ },
166
+ {
167
+ "epoch": 0.051907018731663285,
168
+ "grad_norm": 0.0009918212890625,
169
+ "learning_rate": 9.8640791361474e-06,
170
+ "loss": 0.38,
171
+ "step": 230
172
+ },
173
+ {
174
+ "epoch": 0.05416384563303995,
175
+ "grad_norm": 0.1376953125,
176
+ "learning_rate": 9.856527977044477e-06,
177
+ "loss": 0.6111,
178
+ "step": 240
179
+ },
180
+ {
181
+ "epoch": 0.05642067253441661,
182
+ "grad_norm": 0.0033721923828125,
183
+ "learning_rate": 9.848976817941554e-06,
184
+ "loss": 0.3474,
185
+ "step": 250
186
+ },
187
+ {
188
+ "epoch": 0.05867749943579328,
189
+ "grad_norm": 2.5,
190
+ "learning_rate": 9.841425658838632e-06,
191
+ "loss": 0.0004,
192
+ "step": 260
193
+ },
194
+ {
195
+ "epoch": 0.06093432633716994,
196
+ "grad_norm": 0.000698089599609375,
197
+ "learning_rate": 9.83387449973571e-06,
198
+ "loss": 0.0,
199
+ "step": 270
200
+ },
201
+ {
202
+ "epoch": 0.0631911532385466,
203
+ "grad_norm": 0.0159912109375,
204
+ "learning_rate": 9.82632334063279e-06,
205
+ "loss": 0.0001,
206
+ "step": 280
207
+ },
208
+ {
209
+ "epoch": 0.06544798013992327,
210
+ "grad_norm": 0.01904296875,
211
+ "learning_rate": 9.818772181529865e-06,
212
+ "loss": 0.0,
213
+ "step": 290
214
+ },
215
+ {
216
+ "epoch": 0.06770480704129993,
217
+ "grad_norm": 0.00119781494140625,
218
+ "learning_rate": 9.811221022426943e-06,
219
+ "loss": 0.0,
220
+ "step": 300
221
+ },
222
+ {
223
+ "epoch": 0.0699616339426766,
224
+ "grad_norm": 0.00106048583984375,
225
+ "learning_rate": 9.803669863324021e-06,
226
+ "loss": 0.0,
227
+ "step": 310
228
+ },
229
+ {
230
+ "epoch": 0.07221846084405326,
231
+ "grad_norm": 0.00186920166015625,
232
+ "learning_rate": 9.796118704221099e-06,
233
+ "loss": 0.2718,
234
+ "step": 320
235
+ },
236
+ {
237
+ "epoch": 0.07447528774542993,
238
+ "grad_norm": 17.25,
239
+ "learning_rate": 9.788567545118176e-06,
240
+ "loss": 0.0021,
241
+ "step": 330
242
+ },
243
+ {
244
+ "epoch": 0.07673211464680658,
245
+ "grad_norm": 0.16796875,
246
+ "learning_rate": 9.781016386015254e-06,
247
+ "loss": 0.3681,
248
+ "step": 340
249
+ },
250
+ {
251
+ "epoch": 0.07898894154818326,
252
+ "grad_norm": 0.041015625,
253
+ "learning_rate": 9.773465226912332e-06,
254
+ "loss": 0.2174,
255
+ "step": 350
256
+ },
257
+ {
258
+ "epoch": 0.08124576844955991,
259
+ "grad_norm": 0.005401611328125,
260
+ "learning_rate": 9.76591406780941e-06,
261
+ "loss": 0.0003,
262
+ "step": 360
263
+ },
264
+ {
265
+ "epoch": 0.08350259535093658,
266
+ "grad_norm": 0.0069580078125,
267
+ "learning_rate": 9.758362908706487e-06,
268
+ "loss": 0.0,
269
+ "step": 370
270
+ },
271
+ {
272
+ "epoch": 0.08575942225231324,
273
+ "grad_norm": 0.051513671875,
274
+ "learning_rate": 9.750811749603565e-06,
275
+ "loss": 0.0,
276
+ "step": 380
277
+ },
278
+ {
279
+ "epoch": 0.08801624915368991,
280
+ "grad_norm": 0.00099945068359375,
281
+ "learning_rate": 9.743260590500643e-06,
282
+ "loss": 0.0001,
283
+ "step": 390
284
+ },
285
+ {
286
+ "epoch": 0.09027307605506657,
287
+ "grad_norm": 69.0,
288
+ "learning_rate": 9.73570943139772e-06,
289
+ "loss": 0.3307,
290
+ "step": 400
291
+ },
292
+ {
293
+ "epoch": 0.09252990295644324,
294
+ "grad_norm": 0.047607421875,
295
+ "learning_rate": 9.728158272294797e-06,
296
+ "loss": 0.0001,
297
+ "step": 410
298
+ },
299
+ {
300
+ "epoch": 0.0947867298578199,
301
+ "grad_norm": 0.002288818359375,
302
+ "learning_rate": 9.720607113191876e-06,
303
+ "loss": 0.0,
304
+ "step": 420
305
+ },
306
+ {
307
+ "epoch": 0.09704355675919657,
308
+ "grad_norm": 0.00250244140625,
309
+ "learning_rate": 9.713055954088954e-06,
310
+ "loss": 0.0001,
311
+ "step": 430
312
+ },
313
+ {
314
+ "epoch": 0.09930038366057324,
315
+ "grad_norm": 0.00469970703125,
316
+ "learning_rate": 9.705504794986032e-06,
317
+ "loss": 0.0,
318
+ "step": 440
319
+ },
320
+ {
321
+ "epoch": 0.1015572105619499,
322
+ "grad_norm": 0.000396728515625,
323
+ "learning_rate": 9.697953635883108e-06,
324
+ "loss": 0.0001,
325
+ "step": 450
326
+ },
327
+ {
328
+ "epoch": 0.10381403746332657,
329
+ "grad_norm": 57.5,
330
+ "learning_rate": 9.690402476780186e-06,
331
+ "loss": 0.3762,
332
+ "step": 460
333
+ },
334
+ {
335
+ "epoch": 0.10607086436470323,
336
+ "grad_norm": 0.00113677978515625,
337
+ "learning_rate": 9.682851317677265e-06,
338
+ "loss": 0.0001,
339
+ "step": 470
340
+ },
341
+ {
342
+ "epoch": 0.1083276912660799,
343
+ "grad_norm": 0.000865936279296875,
344
+ "learning_rate": 9.675300158574343e-06,
345
+ "loss": 0.0,
346
+ "step": 480
347
+ },
348
+ {
349
+ "epoch": 0.11058451816745656,
350
+ "grad_norm": 0.0208740234375,
351
+ "learning_rate": 9.66774899947142e-06,
352
+ "loss": 0.3327,
353
+ "step": 490
354
+ },
355
+ {
356
+ "epoch": 0.11284134506883323,
357
+ "grad_norm": 0.00079345703125,
358
+ "learning_rate": 9.660197840368497e-06,
359
+ "loss": 0.0,
360
+ "step": 500
361
+ },
362
+ {
363
+ "epoch": 0.11509817197020988,
364
+ "grad_norm": 0.002532958984375,
365
+ "learning_rate": 9.652646681265574e-06,
366
+ "loss": 0.8702,
367
+ "step": 510
368
+ },
369
+ {
370
+ "epoch": 0.11735499887158655,
371
+ "grad_norm": 0.029541015625,
372
+ "learning_rate": 9.645095522162652e-06,
373
+ "loss": 0.0,
374
+ "step": 520
375
+ },
376
+ {
377
+ "epoch": 0.11961182577296321,
378
+ "grad_norm": 0.0025177001953125,
379
+ "learning_rate": 9.637544363059732e-06,
380
+ "loss": 0.1008,
381
+ "step": 530
382
+ },
383
+ {
384
+ "epoch": 0.12186865267433988,
385
+ "grad_norm": 0.00628662109375,
386
+ "learning_rate": 9.629993203956808e-06,
387
+ "loss": 0.0,
388
+ "step": 540
389
+ },
390
+ {
391
+ "epoch": 0.12412547957571654,
392
+ "grad_norm": 0.0291748046875,
393
+ "learning_rate": 9.622442044853885e-06,
394
+ "loss": 0.0002,
395
+ "step": 550
396
+ },
397
+ {
398
+ "epoch": 0.1263823064770932,
399
+ "grad_norm": 0.26171875,
400
+ "learning_rate": 9.614890885750963e-06,
401
+ "loss": 0.0001,
402
+ "step": 560
403
+ },
404
+ {
405
+ "epoch": 0.12863913337846988,
406
+ "grad_norm": 0.0028839111328125,
407
+ "learning_rate": 9.607339726648041e-06,
408
+ "loss": 0.0,
409
+ "step": 570
410
+ },
411
+ {
412
+ "epoch": 0.13089596027984654,
413
+ "grad_norm": 0.0004730224609375,
414
+ "learning_rate": 9.599788567545119e-06,
415
+ "loss": 0.0,
416
+ "step": 580
417
+ },
418
+ {
419
+ "epoch": 0.1331527871812232,
420
+ "grad_norm": 0.0004100799560546875,
421
+ "learning_rate": 9.592237408442197e-06,
422
+ "loss": 0.0,
423
+ "step": 590
424
+ },
425
+ {
426
+ "epoch": 0.13540961408259986,
427
+ "grad_norm": 0.0712890625,
428
+ "learning_rate": 9.584686249339274e-06,
429
+ "loss": 0.0,
430
+ "step": 600
431
+ },
432
+ {
433
+ "epoch": 0.13766644098397654,
434
+ "grad_norm": 0.0244140625,
435
+ "learning_rate": 9.577135090236352e-06,
436
+ "loss": 0.0198,
437
+ "step": 610
438
+ },
439
+ {
440
+ "epoch": 0.1399232678853532,
441
+ "grad_norm": 16.625,
442
+ "learning_rate": 9.56958393113343e-06,
443
+ "loss": 0.0008,
444
+ "step": 620
445
+ },
446
+ {
447
+ "epoch": 0.14218009478672985,
448
+ "grad_norm": 1.6796875,
449
+ "learning_rate": 9.562032772030508e-06,
450
+ "loss": 0.0001,
451
+ "step": 630
452
+ },
453
+ {
454
+ "epoch": 0.1444369216881065,
455
+ "grad_norm": 0.00055694580078125,
456
+ "learning_rate": 9.554481612927585e-06,
457
+ "loss": 0.0,
458
+ "step": 640
459
+ },
460
+ {
461
+ "epoch": 0.1466937485894832,
462
+ "grad_norm": 0.000457763671875,
463
+ "learning_rate": 9.546930453824663e-06,
464
+ "loss": 0.0,
465
+ "step": 650
466
+ },
467
+ {
468
+ "epoch": 0.14895057549085985,
469
+ "grad_norm": 0.001251220703125,
470
+ "learning_rate": 9.53937929472174e-06,
471
+ "loss": 0.0,
472
+ "step": 660
473
+ },
474
+ {
475
+ "epoch": 0.1512074023922365,
476
+ "grad_norm": 0.00077056884765625,
477
+ "learning_rate": 9.531828135618819e-06,
478
+ "loss": 0.3169,
479
+ "step": 670
480
+ },
481
+ {
482
+ "epoch": 0.15346422929361317,
483
+ "grad_norm": 0.00122833251953125,
484
+ "learning_rate": 9.524276976515896e-06,
485
+ "loss": 0.7091,
486
+ "step": 680
487
+ },
488
+ {
489
+ "epoch": 0.15572105619498985,
490
+ "grad_norm": 0.00067901611328125,
491
+ "learning_rate": 9.516725817412974e-06,
492
+ "loss": 0.0,
493
+ "step": 690
494
+ },
495
+ {
496
+ "epoch": 0.1579778830963665,
497
+ "grad_norm": 0.00445556640625,
498
+ "learning_rate": 9.50917465831005e-06,
499
+ "loss": 0.4241,
500
+ "step": 700
501
+ },
502
+ {
503
+ "epoch": 0.16023470999774317,
504
+ "grad_norm": 0.000370025634765625,
505
+ "learning_rate": 9.501623499207128e-06,
506
+ "loss": 0.0071,
507
+ "step": 710
508
+ },
509
+ {
510
+ "epoch": 0.16249153689911983,
511
+ "grad_norm": 0.0016326904296875,
512
+ "learning_rate": 9.494072340104207e-06,
513
+ "loss": 0.2712,
514
+ "step": 720
515
+ },
516
+ {
517
+ "epoch": 0.1647483638004965,
518
+ "grad_norm": 0.07470703125,
519
+ "learning_rate": 9.486521181001285e-06,
520
+ "loss": 0.0,
521
+ "step": 730
522
+ },
523
+ {
524
+ "epoch": 0.16700519070187317,
525
+ "grad_norm": 0.10302734375,
526
+ "learning_rate": 9.478970021898363e-06,
527
+ "loss": 0.3055,
528
+ "step": 740
529
+ },
530
+ {
531
+ "epoch": 0.16926201760324983,
532
+ "grad_norm": 0.032470703125,
533
+ "learning_rate": 9.471418862795439e-06,
534
+ "loss": 0.0,
535
+ "step": 750
536
+ },
537
+ {
538
+ "epoch": 0.17151884450462648,
539
+ "grad_norm": 0.0003681182861328125,
540
+ "learning_rate": 9.463867703692517e-06,
541
+ "loss": 0.0,
542
+ "step": 760
543
+ },
544
+ {
545
+ "epoch": 0.17377567140600317,
546
+ "grad_norm": 0.0004787445068359375,
547
+ "learning_rate": 9.456316544589596e-06,
548
+ "loss": 0.0,
549
+ "step": 770
550
+ },
551
+ {
552
+ "epoch": 0.17603249830737983,
553
+ "grad_norm": 0.0021514892578125,
554
+ "learning_rate": 9.448765385486674e-06,
555
+ "loss": 0.0003,
556
+ "step": 780
557
+ },
558
+ {
559
+ "epoch": 0.17828932520875648,
560
+ "grad_norm": 0.00040435791015625,
561
+ "learning_rate": 9.44121422638375e-06,
562
+ "loss": 0.0,
563
+ "step": 790
564
+ },
565
+ {
566
+ "epoch": 0.18054615211013314,
567
+ "grad_norm": 0.00135040283203125,
568
+ "learning_rate": 9.433663067280828e-06,
569
+ "loss": 0.0,
570
+ "step": 800
571
+ },
572
+ {
573
+ "epoch": 0.18280297901150983,
574
+ "grad_norm": 0.000331878662109375,
575
+ "learning_rate": 9.426111908177906e-06,
576
+ "loss": 0.0,
577
+ "step": 810
578
+ },
579
+ {
580
+ "epoch": 0.18505980591288648,
581
+ "grad_norm": 0.00049591064453125,
582
+ "learning_rate": 9.418560749074985e-06,
583
+ "loss": 0.0,
584
+ "step": 820
585
+ },
586
+ {
587
+ "epoch": 0.18731663281426314,
588
+ "grad_norm": 0.0003795623779296875,
589
+ "learning_rate": 9.411009589972061e-06,
590
+ "loss": 0.0,
591
+ "step": 830
592
+ },
593
+ {
594
+ "epoch": 0.1895734597156398,
595
+ "grad_norm": 0.000629425048828125,
596
+ "learning_rate": 9.403458430869139e-06,
597
+ "loss": 0.3432,
598
+ "step": 840
599
+ },
600
+ {
601
+ "epoch": 0.19183028661701648,
602
+ "grad_norm": 0.00048828125,
603
+ "learning_rate": 9.395907271766217e-06,
604
+ "loss": 0.0,
605
+ "step": 850
606
+ },
607
+ {
608
+ "epoch": 0.19408711351839314,
609
+ "grad_norm": 0.0004253387451171875,
610
+ "learning_rate": 9.388356112663294e-06,
611
+ "loss": 0.0,
612
+ "step": 860
613
+ },
614
+ {
615
+ "epoch": 0.1963439404197698,
616
+ "grad_norm": 0.000579833984375,
617
+ "learning_rate": 9.380804953560372e-06,
618
+ "loss": 0.0,
619
+ "step": 870
620
+ },
621
+ {
622
+ "epoch": 0.19860076732114648,
623
+ "grad_norm": 0.007232666015625,
624
+ "learning_rate": 9.37325379445745e-06,
625
+ "loss": 0.0,
626
+ "step": 880
627
+ },
628
+ {
629
+ "epoch": 0.20085759422252314,
630
+ "grad_norm": 0.003631591796875,
631
+ "learning_rate": 9.365702635354528e-06,
632
+ "loss": 0.1363,
633
+ "step": 890
634
+ },
635
+ {
636
+ "epoch": 0.2031144211238998,
637
+ "grad_norm": 0.003875732421875,
638
+ "learning_rate": 9.358151476251605e-06,
639
+ "loss": 0.0,
640
+ "step": 900
641
+ },
642
+ {
643
+ "epoch": 0.20537124802527645,
644
+ "grad_norm": 0.00830078125,
645
+ "learning_rate": 9.350600317148683e-06,
646
+ "loss": 0.0,
647
+ "step": 910
648
+ },
649
+ {
650
+ "epoch": 0.20762807492665314,
651
+ "grad_norm": 0.00213623046875,
652
+ "learning_rate": 9.343049158045761e-06,
653
+ "loss": 0.0,
654
+ "step": 920
655
+ },
656
+ {
657
+ "epoch": 0.2098849018280298,
658
+ "grad_norm": 0.0003643035888671875,
659
+ "learning_rate": 9.335497998942839e-06,
660
+ "loss": 0.0929,
661
+ "step": 930
662
+ },
663
+ {
664
+ "epoch": 0.21214172872940645,
665
+ "grad_norm": 0.67578125,
666
+ "learning_rate": 9.327946839839916e-06,
667
+ "loss": 0.6867,
668
+ "step": 940
669
+ },
670
+ {
671
+ "epoch": 0.2143985556307831,
672
+ "grad_norm": 0.0030975341796875,
673
+ "learning_rate": 9.320395680736994e-06,
674
+ "loss": 0.0005,
675
+ "step": 950
676
+ },
677
+ {
678
+ "epoch": 0.2166553825321598,
679
+ "grad_norm": 0.0011138916015625,
680
+ "learning_rate": 9.312844521634072e-06,
681
+ "loss": 0.3669,
682
+ "step": 960
683
+ },
684
+ {
685
+ "epoch": 0.21891220943353645,
686
+ "grad_norm": 71.5,
687
+ "learning_rate": 9.30529336253115e-06,
688
+ "loss": 0.2307,
689
+ "step": 970
690
+ },
691
+ {
692
+ "epoch": 0.2211690363349131,
693
+ "grad_norm": 0.0164794921875,
694
+ "learning_rate": 9.297742203428227e-06,
695
+ "loss": 0.0213,
696
+ "step": 980
697
+ },
698
+ {
699
+ "epoch": 0.22342586323628977,
700
+ "grad_norm": 0.003570556640625,
701
+ "learning_rate": 9.290191044325305e-06,
702
+ "loss": 0.0001,
703
+ "step": 990
704
+ },
705
+ {
706
+ "epoch": 0.22568269013766645,
707
+ "grad_norm": 0.000316619873046875,
708
+ "learning_rate": 9.282639885222381e-06,
709
+ "loss": 0.0002,
710
+ "step": 1000
711
+ },
712
+ {
713
+ "epoch": 0.2279395170390431,
714
+ "grad_norm": 0.0004711151123046875,
715
+ "learning_rate": 9.27508872611946e-06,
716
+ "loss": 0.0,
717
+ "step": 1010
718
+ },
719
+ {
720
+ "epoch": 0.23019634394041977,
721
+ "grad_norm": 0.00096893310546875,
722
+ "learning_rate": 9.267537567016539e-06,
723
+ "loss": 0.0007,
724
+ "step": 1020
725
+ },
726
+ {
727
+ "epoch": 0.23245317084179642,
728
+ "grad_norm": 0.005950927734375,
729
+ "learning_rate": 9.259986407913616e-06,
730
+ "loss": 0.4785,
731
+ "step": 1030
732
+ },
733
+ {
734
+ "epoch": 0.2347099977431731,
735
+ "grad_norm": 0.0087890625,
736
+ "learning_rate": 9.252435248810692e-06,
737
+ "loss": 0.2708,
738
+ "step": 1040
739
+ },
740
+ {
741
+ "epoch": 0.23696682464454977,
742
+ "grad_norm": 0.00506591796875,
743
+ "learning_rate": 9.24488408970777e-06,
744
+ "loss": 0.2259,
745
+ "step": 1050
746
+ },
747
+ {
748
+ "epoch": 0.23922365154592642,
749
+ "grad_norm": 0.001434326171875,
750
+ "learning_rate": 9.237332930604848e-06,
751
+ "loss": 0.0045,
752
+ "step": 1060
753
+ },
754
+ {
755
+ "epoch": 0.24148047844730308,
756
+ "grad_norm": 0.003143310546875,
757
+ "learning_rate": 9.229781771501927e-06,
758
+ "loss": 0.0,
759
+ "step": 1070
760
+ },
761
+ {
762
+ "epoch": 0.24373730534867977,
763
+ "grad_norm": 0.0025787353515625,
764
+ "learning_rate": 9.222230612399003e-06,
765
+ "loss": 0.0,
766
+ "step": 1080
767
+ },
768
+ {
769
+ "epoch": 0.24599413225005642,
770
+ "grad_norm": 0.0003833770751953125,
771
+ "learning_rate": 9.214679453296081e-06,
772
+ "loss": 0.0,
773
+ "step": 1090
774
+ },
775
+ {
776
+ "epoch": 0.24825095915143308,
777
+ "grad_norm": 0.00494384765625,
778
+ "learning_rate": 9.207128294193159e-06,
779
+ "loss": 0.0,
780
+ "step": 1100
781
+ },
782
+ {
783
+ "epoch": 0.25050778605280977,
784
+ "grad_norm": 0.0024566650390625,
785
+ "learning_rate": 9.199577135090237e-06,
786
+ "loss": 0.1667,
787
+ "step": 1110
788
+ },
789
+ {
790
+ "epoch": 0.2527646129541864,
791
+ "grad_norm": 0.00183868408203125,
792
+ "learning_rate": 9.192025975987314e-06,
793
+ "loss": 0.0001,
794
+ "step": 1120
795
+ },
796
+ {
797
+ "epoch": 0.2550214398555631,
798
+ "grad_norm": 0.00396728515625,
799
+ "learning_rate": 9.184474816884392e-06,
800
+ "loss": 0.0,
801
+ "step": 1130
802
+ },
803
+ {
804
+ "epoch": 0.25727826675693977,
805
+ "grad_norm": 0.0147705078125,
806
+ "learning_rate": 9.17692365778147e-06,
807
+ "loss": 0.0,
808
+ "step": 1140
809
+ },
810
+ {
811
+ "epoch": 0.2595350936583164,
812
+ "grad_norm": 0.00179290771484375,
813
+ "learning_rate": 9.169372498678548e-06,
814
+ "loss": 0.0,
815
+ "step": 1150
816
+ },
817
+ {
818
+ "epoch": 0.2617919205596931,
819
+ "grad_norm": 0.0025634765625,
820
+ "learning_rate": 9.161821339575625e-06,
821
+ "loss": 0.0,
822
+ "step": 1160
823
+ },
824
+ {
825
+ "epoch": 0.2640487474610697,
826
+ "grad_norm": 0.004486083984375,
827
+ "learning_rate": 9.154270180472703e-06,
828
+ "loss": 0.0,
829
+ "step": 1170
830
+ },
831
+ {
832
+ "epoch": 0.2663055743624464,
833
+ "grad_norm": 0.0001277923583984375,
834
+ "learning_rate": 9.146719021369781e-06,
835
+ "loss": 0.0,
836
+ "step": 1180
837
+ },
838
+ {
839
+ "epoch": 0.2685624012638231,
840
+ "grad_norm": 0.0001659393310546875,
841
+ "learning_rate": 9.139167862266859e-06,
842
+ "loss": 0.0,
843
+ "step": 1190
844
+ },
845
+ {
846
+ "epoch": 0.2708192281651997,
847
+ "grad_norm": 0.0002899169921875,
848
+ "learning_rate": 9.131616703163937e-06,
849
+ "loss": 0.0412,
850
+ "step": 1200
851
+ },
852
+ {
853
+ "epoch": 0.2730760550665764,
854
+ "grad_norm": 0.006134033203125,
855
+ "learning_rate": 9.124065544061014e-06,
856
+ "loss": 0.0,
857
+ "step": 1210
858
+ },
859
+ {
860
+ "epoch": 0.2753328819679531,
861
+ "grad_norm": 0.03759765625,
862
+ "learning_rate": 9.116514384958092e-06,
863
+ "loss": 0.2408,
864
+ "step": 1220
865
+ },
866
+ {
867
+ "epoch": 0.2775897088693297,
868
+ "grad_norm": 0.00067138671875,
869
+ "learning_rate": 9.10896322585517e-06,
870
+ "loss": 0.0,
871
+ "step": 1230
872
+ },
873
+ {
874
+ "epoch": 0.2798465357707064,
875
+ "grad_norm": 0.0007171630859375,
876
+ "learning_rate": 9.101412066752248e-06,
877
+ "loss": 0.0007,
878
+ "step": 1240
879
+ },
880
+ {
881
+ "epoch": 0.282103362672083,
882
+ "grad_norm": 0.004669189453125,
883
+ "learning_rate": 9.093860907649325e-06,
884
+ "loss": 0.3364,
885
+ "step": 1250
886
+ },
887
+ {
888
+ "epoch": 0.2843601895734597,
889
+ "grad_norm": 0.000713348388671875,
890
+ "learning_rate": 9.086309748546403e-06,
891
+ "loss": 0.0,
892
+ "step": 1260
893
+ },
894
+ {
895
+ "epoch": 0.2866170164748364,
896
+ "grad_norm": 0.0010223388671875,
897
+ "learning_rate": 9.078758589443481e-06,
898
+ "loss": 0.0,
899
+ "step": 1270
900
+ },
901
+ {
902
+ "epoch": 0.288873843376213,
903
+ "grad_norm": 0.002960205078125,
904
+ "learning_rate": 9.071207430340559e-06,
905
+ "loss": 0.0,
906
+ "step": 1280
907
+ },
908
+ {
909
+ "epoch": 0.2911306702775897,
910
+ "grad_norm": 0.00034332275390625,
911
+ "learning_rate": 9.063656271237635e-06,
912
+ "loss": 0.0,
913
+ "step": 1290
914
+ },
915
+ {
916
+ "epoch": 0.2933874971789664,
917
+ "grad_norm": 0.002349853515625,
918
+ "learning_rate": 9.056105112134712e-06,
919
+ "loss": 0.0,
920
+ "step": 1300
921
+ },
922
+ {
923
+ "epoch": 0.295644324080343,
924
+ "grad_norm": 0.00058746337890625,
925
+ "learning_rate": 9.048553953031792e-06,
926
+ "loss": 0.2488,
927
+ "step": 1310
928
+ },
929
+ {
930
+ "epoch": 0.2979011509817197,
931
+ "grad_norm": 0.00115966796875,
932
+ "learning_rate": 9.04100279392887e-06,
933
+ "loss": 0.0,
934
+ "step": 1320
935
+ },
936
+ {
937
+ "epoch": 0.3001579778830964,
938
+ "grad_norm": 0.004425048828125,
939
+ "learning_rate": 9.033451634825946e-06,
940
+ "loss": 0.2421,
941
+ "step": 1330
942
+ },
943
+ {
944
+ "epoch": 0.302414804784473,
945
+ "grad_norm": 0.000965118408203125,
946
+ "learning_rate": 9.025900475723023e-06,
947
+ "loss": 0.0244,
948
+ "step": 1340
949
+ },
950
+ {
951
+ "epoch": 0.3046716316858497,
952
+ "grad_norm": 0.0810546875,
953
+ "learning_rate": 9.018349316620101e-06,
954
+ "loss": 0.0,
955
+ "step": 1350
956
+ },
957
+ {
958
+ "epoch": 0.30692845858722634,
959
+ "grad_norm": 0.00732421875,
960
+ "learning_rate": 9.01079815751718e-06,
961
+ "loss": 0.0,
962
+ "step": 1360
963
+ },
964
+ {
965
+ "epoch": 0.309185285488603,
966
+ "grad_norm": 0.0010223388671875,
967
+ "learning_rate": 9.003246998414258e-06,
968
+ "loss": 0.0,
969
+ "step": 1370
970
+ },
971
+ {
972
+ "epoch": 0.3114421123899797,
973
+ "grad_norm": 0.00130462646484375,
974
+ "learning_rate": 8.995695839311335e-06,
975
+ "loss": 0.0,
976
+ "step": 1380
977
+ },
978
+ {
979
+ "epoch": 0.31369893929135634,
980
+ "grad_norm": 0.0004634857177734375,
981
+ "learning_rate": 8.988144680208412e-06,
982
+ "loss": 0.0,
983
+ "step": 1390
984
+ },
985
+ {
986
+ "epoch": 0.315955766192733,
987
+ "grad_norm": 0.0206298828125,
988
+ "learning_rate": 8.98059352110549e-06,
989
+ "loss": 0.2664,
990
+ "step": 1400
991
+ },
992
+ {
993
+ "epoch": 0.3182125930941097,
994
+ "grad_norm": 0.005218505859375,
995
+ "learning_rate": 8.973042362002568e-06,
996
+ "loss": 0.0,
997
+ "step": 1410
998
+ },
999
+ {
1000
+ "epoch": 0.32046941999548634,
1001
+ "grad_norm": 0.00154876708984375,
1002
+ "learning_rate": 8.965491202899646e-06,
1003
+ "loss": 0.1572,
1004
+ "step": 1420
1005
+ },
1006
+ {
1007
+ "epoch": 0.322726246896863,
1008
+ "grad_norm": 0.000640869140625,
1009
+ "learning_rate": 8.957940043796723e-06,
1010
+ "loss": 0.0003,
1011
+ "step": 1430
1012
+ },
1013
+ {
1014
+ "epoch": 0.32498307379823965,
1015
+ "grad_norm": 0.00119781494140625,
1016
+ "learning_rate": 8.950388884693801e-06,
1017
+ "loss": 0.0,
1018
+ "step": 1440
1019
+ },
1020
+ {
1021
+ "epoch": 0.32723990069961634,
1022
+ "grad_norm": 0.0245361328125,
1023
+ "learning_rate": 8.942837725590879e-06,
1024
+ "loss": 0.0,
1025
+ "step": 1450
1026
+ },
1027
+ {
1028
+ "epoch": 0.329496727600993,
1029
+ "grad_norm": 0.0004062652587890625,
1030
+ "learning_rate": 8.935286566487957e-06,
1031
+ "loss": 0.0,
1032
+ "step": 1460
1033
+ },
1034
+ {
1035
+ "epoch": 0.33175355450236965,
1036
+ "grad_norm": 0.000385284423828125,
1037
+ "learning_rate": 8.927735407385034e-06,
1038
+ "loss": 0.0,
1039
+ "step": 1470
1040
+ },
1041
+ {
1042
+ "epoch": 0.33401038140374634,
1043
+ "grad_norm": 0.00616455078125,
1044
+ "learning_rate": 8.920184248282112e-06,
1045
+ "loss": 0.0,
1046
+ "step": 1480
1047
+ },
1048
+ {
1049
+ "epoch": 0.336267208305123,
1050
+ "grad_norm": 0.002532958984375,
1051
+ "learning_rate": 8.91263308917919e-06,
1052
+ "loss": 0.0,
1053
+ "step": 1490
1054
+ },
1055
+ {
1056
+ "epoch": 0.33852403520649965,
1057
+ "grad_norm": 0.0011444091796875,
1058
+ "learning_rate": 8.905081930076268e-06,
1059
+ "loss": 0.0,
1060
+ "step": 1500
1061
+ },
1062
+ {
1063
+ "epoch": 0.34078086210787634,
1064
+ "grad_norm": 0.0004138946533203125,
1065
+ "learning_rate": 8.897530770973345e-06,
1066
+ "loss": 0.0,
1067
+ "step": 1510
1068
+ },
1069
+ {
1070
+ "epoch": 0.34303768900925297,
1071
+ "grad_norm": 0.000579833984375,
1072
+ "learning_rate": 8.889979611870423e-06,
1073
+ "loss": 0.3398,
1074
+ "step": 1520
1075
+ },
1076
+ {
1077
+ "epoch": 0.34529451591062965,
1078
+ "grad_norm": 0.0003948211669921875,
1079
+ "learning_rate": 8.882428452767501e-06,
1080
+ "loss": 0.0,
1081
+ "step": 1530
1082
+ },
1083
+ {
1084
+ "epoch": 0.34755134281200634,
1085
+ "grad_norm": 0.000247955322265625,
1086
+ "learning_rate": 8.874877293664577e-06,
1087
+ "loss": 0.0,
1088
+ "step": 1540
1089
+ },
1090
+ {
1091
+ "epoch": 0.34980816971338297,
1092
+ "grad_norm": 0.000255584716796875,
1093
+ "learning_rate": 8.867326134561656e-06,
1094
+ "loss": 0.2765,
1095
+ "step": 1550
1096
+ },
1097
+ {
1098
+ "epoch": 0.35206499661475965,
1099
+ "grad_norm": 0.0001964569091796875,
1100
+ "learning_rate": 8.859774975458734e-06,
1101
+ "loss": 0.0,
1102
+ "step": 1560
1103
+ },
1104
+ {
1105
+ "epoch": 0.35432182351613634,
1106
+ "grad_norm": 0.00037384033203125,
1107
+ "learning_rate": 8.852223816355812e-06,
1108
+ "loss": 0.0,
1109
+ "step": 1570
1110
+ },
1111
+ {
1112
+ "epoch": 0.35657865041751297,
1113
+ "grad_norm": 0.00052642822265625,
1114
+ "learning_rate": 8.84467265725289e-06,
1115
+ "loss": 0.0,
1116
+ "step": 1580
1117
+ },
1118
+ {
1119
+ "epoch": 0.35883547731888965,
1120
+ "grad_norm": 0.00023555755615234375,
1121
+ "learning_rate": 8.837121498149966e-06,
1122
+ "loss": 0.4111,
1123
+ "step": 1590
1124
+ },
1125
+ {
1126
+ "epoch": 0.3610923042202663,
1127
+ "grad_norm": 0.05419921875,
1128
+ "learning_rate": 8.829570339047044e-06,
1129
+ "loss": 0.0007,
1130
+ "step": 1600
1131
+ },
1132
+ {
1133
+ "epoch": 0.36334913112164297,
1134
+ "grad_norm": 0.00982666015625,
1135
+ "learning_rate": 8.822019179944123e-06,
1136
+ "loss": 0.0,
1137
+ "step": 1610
1138
+ },
1139
+ {
1140
+ "epoch": 0.36560595802301965,
1141
+ "grad_norm": 0.0007476806640625,
1142
+ "learning_rate": 8.8144680208412e-06,
1143
+ "loss": 0.0,
1144
+ "step": 1620
1145
+ },
1146
+ {
1147
+ "epoch": 0.3678627849243963,
1148
+ "grad_norm": 0.0030059814453125,
1149
+ "learning_rate": 8.806916861738277e-06,
1150
+ "loss": 0.0,
1151
+ "step": 1630
1152
+ },
1153
+ {
1154
+ "epoch": 0.37011961182577297,
1155
+ "grad_norm": 0.005889892578125,
1156
+ "learning_rate": 8.799365702635355e-06,
1157
+ "loss": 0.0,
1158
+ "step": 1640
1159
+ },
1160
+ {
1161
+ "epoch": 0.37237643872714965,
1162
+ "grad_norm": 0.006927490234375,
1163
+ "learning_rate": 8.791814543532432e-06,
1164
+ "loss": 0.0001,
1165
+ "step": 1650
1166
+ },
1167
+ {
1168
+ "epoch": 0.3746332656285263,
1169
+ "grad_norm": 0.00494384765625,
1170
+ "learning_rate": 8.784263384429512e-06,
1171
+ "loss": 0.0,
1172
+ "step": 1660
1173
+ },
1174
+ {
1175
+ "epoch": 0.37689009252990296,
1176
+ "grad_norm": 0.00799560546875,
1177
+ "learning_rate": 8.776712225326588e-06,
1178
+ "loss": 0.0,
1179
+ "step": 1670
1180
+ },
1181
+ {
1182
+ "epoch": 0.3791469194312796,
1183
+ "grad_norm": 0.0003604888916015625,
1184
+ "learning_rate": 8.769161066223666e-06,
1185
+ "loss": 0.0,
1186
+ "step": 1680
1187
+ },
1188
+ {
1189
+ "epoch": 0.3814037463326563,
1190
+ "grad_norm": 66.5,
1191
+ "learning_rate": 8.761609907120743e-06,
1192
+ "loss": 0.651,
1193
+ "step": 1690
1194
+ },
1195
+ {
1196
+ "epoch": 0.38366057323403296,
1197
+ "grad_norm": 0.005645751953125,
1198
+ "learning_rate": 8.754058748017821e-06,
1199
+ "loss": 0.0,
1200
+ "step": 1700
1201
+ },
1202
+ {
1203
+ "epoch": 0.3859174001354096,
1204
+ "grad_norm": 0.002105712890625,
1205
+ "learning_rate": 8.746507588914899e-06,
1206
+ "loss": 0.0,
1207
+ "step": 1710
1208
+ },
1209
+ {
1210
+ "epoch": 0.3881742270367863,
1211
+ "grad_norm": 0.0003948211669921875,
1212
+ "learning_rate": 8.738956429811977e-06,
1213
+ "loss": 0.0,
1214
+ "step": 1720
1215
+ },
1216
+ {
1217
+ "epoch": 0.39043105393816296,
1218
+ "grad_norm": 0.0014801025390625,
1219
+ "learning_rate": 8.731405270709054e-06,
1220
+ "loss": 0.0,
1221
+ "step": 1730
1222
+ },
1223
+ {
1224
+ "epoch": 0.3926878808395396,
1225
+ "grad_norm": 0.000560760498046875,
1226
+ "learning_rate": 8.723854111606132e-06,
1227
+ "loss": 0.0,
1228
+ "step": 1740
1229
+ },
1230
+ {
1231
+ "epoch": 0.3949447077409163,
1232
+ "grad_norm": 0.000659942626953125,
1233
+ "learning_rate": 8.71630295250321e-06,
1234
+ "loss": 0.0,
1235
+ "step": 1750
1236
+ },
1237
+ {
1238
+ "epoch": 0.39720153464229296,
1239
+ "grad_norm": 0.162109375,
1240
+ "learning_rate": 8.708751793400288e-06,
1241
+ "loss": 0.0,
1242
+ "step": 1760
1243
+ },
1244
+ {
1245
+ "epoch": 0.3994583615436696,
1246
+ "grad_norm": 0.000843048095703125,
1247
+ "learning_rate": 8.701200634297366e-06,
1248
+ "loss": 0.1511,
1249
+ "step": 1770
1250
+ },
1251
+ {
1252
+ "epoch": 0.4017151884450463,
1253
+ "grad_norm": 0.003631591796875,
1254
+ "learning_rate": 8.693649475194443e-06,
1255
+ "loss": 0.8574,
1256
+ "step": 1780
1257
+ },
1258
+ {
1259
+ "epoch": 0.4039720153464229,
1260
+ "grad_norm": 0.004425048828125,
1261
+ "learning_rate": 8.686098316091521e-06,
1262
+ "loss": 0.0013,
1263
+ "step": 1790
1264
+ },
1265
+ {
1266
+ "epoch": 0.4062288422477996,
1267
+ "grad_norm": 0.004486083984375,
1268
+ "learning_rate": 8.678547156988599e-06,
1269
+ "loss": 0.0002,
1270
+ "step": 1800
1271
+ },
1272
+ {
1273
+ "epoch": 0.4084856691491763,
1274
+ "grad_norm": 0.0019683837890625,
1275
+ "learning_rate": 8.670995997885677e-06,
1276
+ "loss": 0.4738,
1277
+ "step": 1810
1278
+ },
1279
+ {
1280
+ "epoch": 0.4107424960505529,
1281
+ "grad_norm": 0.01092529296875,
1282
+ "learning_rate": 8.663444838782754e-06,
1283
+ "loss": 0.0,
1284
+ "step": 1820
1285
+ },
1286
+ {
1287
+ "epoch": 0.4129993229519296,
1288
+ "grad_norm": 0.0013885498046875,
1289
+ "learning_rate": 8.655893679679832e-06,
1290
+ "loss": 0.0,
1291
+ "step": 1830
1292
+ },
1293
+ {
1294
+ "epoch": 0.4152561498533063,
1295
+ "grad_norm": 0.09326171875,
1296
+ "learning_rate": 8.648342520576908e-06,
1297
+ "loss": 0.0,
1298
+ "step": 1840
1299
+ },
1300
+ {
1301
+ "epoch": 0.4175129767546829,
1302
+ "grad_norm": 0.01409912109375,
1303
+ "learning_rate": 8.640791361473988e-06,
1304
+ "loss": 0.0001,
1305
+ "step": 1850
1306
+ },
1307
+ {
1308
+ "epoch": 0.4197698036560596,
1309
+ "grad_norm": 0.004119873046875,
1310
+ "learning_rate": 8.633240202371065e-06,
1311
+ "loss": 0.4574,
1312
+ "step": 1860
1313
+ },
1314
+ {
1315
+ "epoch": 0.4220266305574362,
1316
+ "grad_norm": 0.00121307373046875,
1317
+ "learning_rate": 8.625689043268143e-06,
1318
+ "loss": 0.0,
1319
+ "step": 1870
1320
+ },
1321
+ {
1322
+ "epoch": 0.4242834574588129,
1323
+ "grad_norm": 0.006103515625,
1324
+ "learning_rate": 8.61813788416522e-06,
1325
+ "loss": 0.0,
1326
+ "step": 1880
1327
+ },
1328
+ {
1329
+ "epoch": 0.4265402843601896,
1330
+ "grad_norm": 0.005157470703125,
1331
+ "learning_rate": 8.610586725062297e-06,
1332
+ "loss": 0.0,
1333
+ "step": 1890
1334
+ },
1335
+ {
1336
+ "epoch": 0.4287971112615662,
1337
+ "grad_norm": 0.00360107421875,
1338
+ "learning_rate": 8.603035565959376e-06,
1339
+ "loss": 0.715,
1340
+ "step": 1900
1341
+ },
1342
+ {
1343
+ "epoch": 0.4310539381629429,
1344
+ "grad_norm": 0.0028076171875,
1345
+ "learning_rate": 8.595484406856454e-06,
1346
+ "loss": 0.0,
1347
+ "step": 1910
1348
+ },
1349
+ {
1350
+ "epoch": 0.4333107650643196,
1351
+ "grad_norm": 0.00799560546875,
1352
+ "learning_rate": 8.58793324775353e-06,
1353
+ "loss": 0.0001,
1354
+ "step": 1920
1355
+ },
1356
+ {
1357
+ "epoch": 0.4355675919656962,
1358
+ "grad_norm": 0.003265380859375,
1359
+ "learning_rate": 8.580382088650608e-06,
1360
+ "loss": 0.2658,
1361
+ "step": 1930
1362
+ },
1363
+ {
1364
+ "epoch": 0.4378244188670729,
1365
+ "grad_norm": 0.00970458984375,
1366
+ "learning_rate": 8.572830929547686e-06,
1367
+ "loss": 0.0,
1368
+ "step": 1940
1369
+ },
1370
+ {
1371
+ "epoch": 0.44008124576844954,
1372
+ "grad_norm": 0.1376953125,
1373
+ "learning_rate": 8.565279770444764e-06,
1374
+ "loss": 0.0,
1375
+ "step": 1950
1376
+ },
1377
+ {
1378
+ "epoch": 0.4423380726698262,
1379
+ "grad_norm": 0.007568359375,
1380
+ "learning_rate": 8.557728611341841e-06,
1381
+ "loss": 0.0,
1382
+ "step": 1960
1383
+ },
1384
+ {
1385
+ "epoch": 0.4445948995712029,
1386
+ "grad_norm": 0.000518798828125,
1387
+ "learning_rate": 8.550177452238919e-06,
1388
+ "loss": 0.0,
1389
+ "step": 1970
1390
+ },
1391
+ {
1392
+ "epoch": 0.44685172647257954,
1393
+ "grad_norm": 0.0037841796875,
1394
+ "learning_rate": 8.542626293135997e-06,
1395
+ "loss": 0.0,
1396
+ "step": 1980
1397
+ },
1398
+ {
1399
+ "epoch": 0.4491085533739562,
1400
+ "grad_norm": 0.000659942626953125,
1401
+ "learning_rate": 8.535075134033075e-06,
1402
+ "loss": 0.0,
1403
+ "step": 1990
1404
+ },
1405
+ {
1406
+ "epoch": 0.4513653802753329,
1407
+ "grad_norm": 0.000308990478515625,
1408
+ "learning_rate": 8.527523974930152e-06,
1409
+ "loss": 0.0,
1410
+ "step": 2000
1411
+ },
1412
+ {
1413
+ "epoch": 0.45362220717670954,
1414
+ "grad_norm": 0.00167083740234375,
1415
+ "learning_rate": 8.51997281582723e-06,
1416
+ "loss": 0.187,
1417
+ "step": 2010
1418
+ },
1419
+ {
1420
+ "epoch": 0.4558790340780862,
1421
+ "grad_norm": 0.001251220703125,
1422
+ "learning_rate": 8.512421656724308e-06,
1423
+ "loss": 0.7379,
1424
+ "step": 2020
1425
+ },
1426
+ {
1427
+ "epoch": 0.45813586097946285,
1428
+ "grad_norm": 0.003753662109375,
1429
+ "learning_rate": 8.504870497621386e-06,
1430
+ "loss": 0.0,
1431
+ "step": 2030
1432
+ },
1433
+ {
1434
+ "epoch": 0.46039268788083954,
1435
+ "grad_norm": 0.00179290771484375,
1436
+ "learning_rate": 8.497319338518463e-06,
1437
+ "loss": 0.0,
1438
+ "step": 2040
1439
+ },
1440
+ {
1441
+ "epoch": 0.4626495147822162,
1442
+ "grad_norm": 0.00034332275390625,
1443
+ "learning_rate": 8.489768179415541e-06,
1444
+ "loss": 0.0,
1445
+ "step": 2050
1446
+ },
1447
+ {
1448
+ "epoch": 0.46490634168359285,
1449
+ "grad_norm": 0.0003948211669921875,
1450
+ "learning_rate": 8.482217020312619e-06,
1451
+ "loss": 0.0,
1452
+ "step": 2060
1453
+ },
1454
+ {
1455
+ "epoch": 0.46716316858496953,
1456
+ "grad_norm": 0.0012359619140625,
1457
+ "learning_rate": 8.474665861209697e-06,
1458
+ "loss": 0.0,
1459
+ "step": 2070
1460
+ },
1461
+ {
1462
+ "epoch": 0.4694199954863462,
1463
+ "grad_norm": 0.000896453857421875,
1464
+ "learning_rate": 8.467114702106774e-06,
1465
+ "loss": 0.0,
1466
+ "step": 2080
1467
+ },
1468
+ {
1469
+ "epoch": 0.47167682238772285,
1470
+ "grad_norm": 4.8125,
1471
+ "learning_rate": 8.459563543003852e-06,
1472
+ "loss": 0.0007,
1473
+ "step": 2090
1474
+ },
1475
+ {
1476
+ "epoch": 0.47393364928909953,
1477
+ "grad_norm": 0.00017452239990234375,
1478
+ "learning_rate": 8.45201238390093e-06,
1479
+ "loss": 0.0,
1480
+ "step": 2100
1481
+ },
1482
+ {
1483
+ "epoch": 0.47619047619047616,
1484
+ "grad_norm": 0.00037384033203125,
1485
+ "learning_rate": 8.444461224798008e-06,
1486
+ "loss": 0.0,
1487
+ "step": 2110
1488
+ },
1489
+ {
1490
+ "epoch": 0.47844730309185285,
1491
+ "grad_norm": 0.0001983642578125,
1492
+ "learning_rate": 8.436910065695085e-06,
1493
+ "loss": 0.0,
1494
+ "step": 2120
1495
+ },
1496
+ {
1497
+ "epoch": 0.48070412999322953,
1498
+ "grad_norm": 0.00189971923828125,
1499
+ "learning_rate": 8.429358906592162e-06,
1500
+ "loss": 0.0,
1501
+ "step": 2130
1502
+ },
1503
+ {
1504
+ "epoch": 0.48296095689460616,
1505
+ "grad_norm": 0.0002422332763671875,
1506
+ "learning_rate": 8.421807747489241e-06,
1507
+ "loss": 0.0,
1508
+ "step": 2140
1509
+ },
1510
+ {
1511
+ "epoch": 0.48521778379598285,
1512
+ "grad_norm": 0.000522613525390625,
1513
+ "learning_rate": 8.414256588386319e-06,
1514
+ "loss": 0.0,
1515
+ "step": 2150
1516
+ },
1517
+ {
1518
+ "epoch": 0.48747461069735953,
1519
+ "grad_norm": 0.00021266937255859375,
1520
+ "learning_rate": 8.406705429283396e-06,
1521
+ "loss": 0.0,
1522
+ "step": 2160
1523
+ },
1524
+ {
1525
+ "epoch": 0.48973143759873616,
1526
+ "grad_norm": 0.000537872314453125,
1527
+ "learning_rate": 8.399154270180473e-06,
1528
+ "loss": 0.0,
1529
+ "step": 2170
1530
+ },
1531
+ {
1532
+ "epoch": 0.49198826450011285,
1533
+ "grad_norm": 0.001617431640625,
1534
+ "learning_rate": 8.39160311107755e-06,
1535
+ "loss": 0.6385,
1536
+ "step": 2180
1537
+ },
1538
+ {
1539
+ "epoch": 0.4942450914014895,
1540
+ "grad_norm": 0.0020904541015625,
1541
+ "learning_rate": 8.384051951974628e-06,
1542
+ "loss": 0.0643,
1543
+ "step": 2190
1544
+ },
1545
+ {
1546
+ "epoch": 0.49650191830286616,
1547
+ "grad_norm": 0.0020904541015625,
1548
+ "learning_rate": 8.376500792871708e-06,
1549
+ "loss": 0.0,
1550
+ "step": 2200
1551
+ },
1552
+ {
1553
+ "epoch": 0.49875874520424285,
1554
+ "grad_norm": 0.25390625,
1555
+ "learning_rate": 8.368949633768784e-06,
1556
+ "loss": 0.0001,
1557
+ "step": 2210
1558
+ },
1559
+ {
1560
+ "epoch": 0.5010155721056195,
1561
+ "grad_norm": 0.018310546875,
1562
+ "learning_rate": 8.361398474665861e-06,
1563
+ "loss": 0.3428,
1564
+ "step": 2220
1565
+ },
1566
+ {
1567
+ "epoch": 0.5032723990069962,
1568
+ "grad_norm": 0.006622314453125,
1569
+ "learning_rate": 8.353847315562939e-06,
1570
+ "loss": 0.307,
1571
+ "step": 2230
1572
+ },
1573
+ {
1574
+ "epoch": 0.5055292259083728,
1575
+ "grad_norm": 0.03515625,
1576
+ "learning_rate": 8.346296156460017e-06,
1577
+ "loss": 0.0007,
1578
+ "step": 2240
1579
+ },
1580
+ {
1581
+ "epoch": 0.5077860528097495,
1582
+ "grad_norm": 0.0308837890625,
1583
+ "learning_rate": 8.338744997357096e-06,
1584
+ "loss": 0.0308,
1585
+ "step": 2250
1586
+ },
1587
+ {
1588
+ "epoch": 0.5100428797111262,
1589
+ "grad_norm": 0.006591796875,
1590
+ "learning_rate": 8.331193838254172e-06,
1591
+ "loss": 0.2879,
1592
+ "step": 2260
1593
+ },
1594
+ {
1595
+ "epoch": 0.5122997066125028,
1596
+ "grad_norm": 77.0,
1597
+ "learning_rate": 8.32364267915125e-06,
1598
+ "loss": 0.4258,
1599
+ "step": 2270
1600
+ },
1601
+ {
1602
+ "epoch": 0.5145565335138795,
1603
+ "grad_norm": 0.031005859375,
1604
+ "learning_rate": 8.316091520048328e-06,
1605
+ "loss": 0.0502,
1606
+ "step": 2280
1607
+ },
1608
+ {
1609
+ "epoch": 0.5168133604152562,
1610
+ "grad_norm": 0.515625,
1611
+ "learning_rate": 8.308540360945406e-06,
1612
+ "loss": 0.0001,
1613
+ "step": 2290
1614
+ },
1615
+ {
1616
+ "epoch": 0.5190701873166328,
1617
+ "grad_norm": 0.01007080078125,
1618
+ "learning_rate": 8.300989201842483e-06,
1619
+ "loss": 0.0,
1620
+ "step": 2300
1621
+ },
1622
+ {
1623
+ "epoch": 0.5213270142180095,
1624
+ "grad_norm": 0.01483154296875,
1625
+ "learning_rate": 8.293438042739561e-06,
1626
+ "loss": 0.3391,
1627
+ "step": 2310
1628
+ },
1629
+ {
1630
+ "epoch": 0.5235838411193862,
1631
+ "grad_norm": 0.150390625,
1632
+ "learning_rate": 8.285886883636639e-06,
1633
+ "loss": 0.0,
1634
+ "step": 2320
1635
+ },
1636
+ {
1637
+ "epoch": 0.5258406680207628,
1638
+ "grad_norm": 0.002288818359375,
1639
+ "learning_rate": 8.278335724533717e-06,
1640
+ "loss": 0.3255,
1641
+ "step": 2330
1642
+ },
1643
+ {
1644
+ "epoch": 0.5280974949221394,
1645
+ "grad_norm": 0.00347900390625,
1646
+ "learning_rate": 8.270784565430794e-06,
1647
+ "loss": 0.2631,
1648
+ "step": 2340
1649
+ },
1650
+ {
1651
+ "epoch": 0.5303543218235162,
1652
+ "grad_norm": 0.038330078125,
1653
+ "learning_rate": 8.263233406327872e-06,
1654
+ "loss": 0.0,
1655
+ "step": 2350
1656
+ },
1657
+ {
1658
+ "epoch": 0.5326111487248928,
1659
+ "grad_norm": 0.01055908203125,
1660
+ "learning_rate": 8.25568224722495e-06,
1661
+ "loss": 0.0001,
1662
+ "step": 2360
1663
+ },
1664
+ {
1665
+ "epoch": 0.5348679756262694,
1666
+ "grad_norm": 0.0040283203125,
1667
+ "learning_rate": 8.248131088122028e-06,
1668
+ "loss": 0.0,
1669
+ "step": 2370
1670
+ },
1671
+ {
1672
+ "epoch": 0.5371248025276462,
1673
+ "grad_norm": 0.00035858154296875,
1674
+ "learning_rate": 8.240579929019104e-06,
1675
+ "loss": 0.0,
1676
+ "step": 2380
1677
+ },
1678
+ {
1679
+ "epoch": 0.5393816294290228,
1680
+ "grad_norm": 0.001983642578125,
1681
+ "learning_rate": 8.233028769916183e-06,
1682
+ "loss": 0.0003,
1683
+ "step": 2390
1684
+ },
1685
+ {
1686
+ "epoch": 0.5416384563303994,
1687
+ "grad_norm": 0.0002651214599609375,
1688
+ "learning_rate": 8.225477610813261e-06,
1689
+ "loss": 0.0,
1690
+ "step": 2400
1691
+ },
1692
+ {
1693
+ "epoch": 0.5438952832317762,
1694
+ "grad_norm": 0.0009918212890625,
1695
+ "learning_rate": 8.217926451710339e-06,
1696
+ "loss": 0.0,
1697
+ "step": 2410
1698
+ },
1699
+ {
1700
+ "epoch": 0.5461521101331528,
1701
+ "grad_norm": 0.0009613037109375,
1702
+ "learning_rate": 8.210375292607415e-06,
1703
+ "loss": 0.0,
1704
+ "step": 2420
1705
+ },
1706
+ {
1707
+ "epoch": 0.5484089370345294,
1708
+ "grad_norm": 0.00107574462890625,
1709
+ "learning_rate": 8.202824133504493e-06,
1710
+ "loss": 0.0,
1711
+ "step": 2430
1712
+ },
1713
+ {
1714
+ "epoch": 0.5506657639359062,
1715
+ "grad_norm": 0.0032958984375,
1716
+ "learning_rate": 8.195272974401572e-06,
1717
+ "loss": 0.248,
1718
+ "step": 2440
1719
+ },
1720
+ {
1721
+ "epoch": 0.5529225908372828,
1722
+ "grad_norm": 0.0021209716796875,
1723
+ "learning_rate": 8.18772181529865e-06,
1724
+ "loss": 0.0,
1725
+ "step": 2450
1726
+ },
1727
+ {
1728
+ "epoch": 0.5551794177386594,
1729
+ "grad_norm": 51.75,
1730
+ "learning_rate": 8.180170656195728e-06,
1731
+ "loss": 0.4205,
1732
+ "step": 2460
1733
+ },
1734
+ {
1735
+ "epoch": 0.5574362446400362,
1736
+ "grad_norm": 0.005767822265625,
1737
+ "learning_rate": 8.172619497092804e-06,
1738
+ "loss": 0.0,
1739
+ "step": 2470
1740
+ },
1741
+ {
1742
+ "epoch": 0.5596930715414128,
1743
+ "grad_norm": 0.0185546875,
1744
+ "learning_rate": 8.165068337989881e-06,
1745
+ "loss": 0.0,
1746
+ "step": 2480
1747
+ },
1748
+ {
1749
+ "epoch": 0.5619498984427894,
1750
+ "grad_norm": 0.0118408203125,
1751
+ "learning_rate": 8.15751717888696e-06,
1752
+ "loss": 0.13,
1753
+ "step": 2490
1754
+ },
1755
+ {
1756
+ "epoch": 0.564206725344166,
1757
+ "grad_norm": 1.375,
1758
+ "learning_rate": 8.149966019784039e-06,
1759
+ "loss": 0.0002,
1760
+ "step": 2500
1761
+ },
1762
+ {
1763
+ "epoch": 0.5664635522455428,
1764
+ "grad_norm": 0.00433349609375,
1765
+ "learning_rate": 8.142414860681115e-06,
1766
+ "loss": 0.0,
1767
+ "step": 2510
1768
+ },
1769
+ {
1770
+ "epoch": 0.5687203791469194,
1771
+ "grad_norm": 0.0026702880859375,
1772
+ "learning_rate": 8.134863701578192e-06,
1773
+ "loss": 0.0,
1774
+ "step": 2520
1775
+ },
1776
+ {
1777
+ "epoch": 0.570977206048296,
1778
+ "grad_norm": 548.0,
1779
+ "learning_rate": 8.12731254247527e-06,
1780
+ "loss": 0.6147,
1781
+ "step": 2530
1782
+ },
1783
+ {
1784
+ "epoch": 0.5732340329496728,
1785
+ "grad_norm": 0.0020904541015625,
1786
+ "learning_rate": 8.119761383372348e-06,
1787
+ "loss": 0.0,
1788
+ "step": 2540
1789
+ },
1790
+ {
1791
+ "epoch": 0.5754908598510494,
1792
+ "grad_norm": 0.003387451171875,
1793
+ "learning_rate": 8.112210224269426e-06,
1794
+ "loss": 0.0,
1795
+ "step": 2550
1796
+ },
1797
+ {
1798
+ "epoch": 0.577747686752426,
1799
+ "grad_norm": 0.0002536773681640625,
1800
+ "learning_rate": 8.104659065166504e-06,
1801
+ "loss": 0.0,
1802
+ "step": 2560
1803
+ },
1804
+ {
1805
+ "epoch": 0.5800045136538028,
1806
+ "grad_norm": 0.0035552978515625,
1807
+ "learning_rate": 8.097107906063581e-06,
1808
+ "loss": 0.3707,
1809
+ "step": 2570
1810
+ },
1811
+ {
1812
+ "epoch": 0.5822613405551794,
1813
+ "grad_norm": 0.0018157958984375,
1814
+ "learning_rate": 8.089556746960659e-06,
1815
+ "loss": 0.3046,
1816
+ "step": 2580
1817
+ },
1818
+ {
1819
+ "epoch": 0.584518167456556,
1820
+ "grad_norm": 0.0078125,
1821
+ "learning_rate": 8.082005587857737e-06,
1822
+ "loss": 0.0,
1823
+ "step": 2590
1824
+ },
1825
+ {
1826
+ "epoch": 0.5867749943579328,
1827
+ "grad_norm": 0.0037078857421875,
1828
+ "learning_rate": 8.074454428754815e-06,
1829
+ "loss": 0.3055,
1830
+ "step": 2600
1831
+ },
1832
+ {
1833
+ "epoch": 0.5890318212593094,
1834
+ "grad_norm": 0.0150146484375,
1835
+ "learning_rate": 8.066903269651892e-06,
1836
+ "loss": 0.0,
1837
+ "step": 2610
1838
+ },
1839
+ {
1840
+ "epoch": 0.591288648160686,
1841
+ "grad_norm": 0.0250244140625,
1842
+ "learning_rate": 8.05935211054897e-06,
1843
+ "loss": 0.0001,
1844
+ "step": 2620
1845
+ },
1846
+ {
1847
+ "epoch": 0.5935454750620628,
1848
+ "grad_norm": 0.020751953125,
1849
+ "learning_rate": 8.051800951446048e-06,
1850
+ "loss": 0.0001,
1851
+ "step": 2630
1852
+ },
1853
+ {
1854
+ "epoch": 0.5958023019634394,
1855
+ "grad_norm": 0.00372314453125,
1856
+ "learning_rate": 8.044249792343126e-06,
1857
+ "loss": 0.2485,
1858
+ "step": 2640
1859
+ },
1860
+ {
1861
+ "epoch": 0.598059128864816,
1862
+ "grad_norm": 0.001800537109375,
1863
+ "learning_rate": 8.036698633240203e-06,
1864
+ "loss": 0.0,
1865
+ "step": 2650
1866
+ },
1867
+ {
1868
+ "epoch": 0.6003159557661928,
1869
+ "grad_norm": 83.0,
1870
+ "learning_rate": 8.029147474137281e-06,
1871
+ "loss": 0.3156,
1872
+ "step": 2660
1873
+ },
1874
+ {
1875
+ "epoch": 0.6025727826675694,
1876
+ "grad_norm": 0.007720947265625,
1877
+ "learning_rate": 8.021596315034359e-06,
1878
+ "loss": 0.0,
1879
+ "step": 2670
1880
+ },
1881
+ {
1882
+ "epoch": 0.604829609568946,
1883
+ "grad_norm": 0.001373291015625,
1884
+ "learning_rate": 8.014045155931437e-06,
1885
+ "loss": 0.0002,
1886
+ "step": 2680
1887
+ },
1888
+ {
1889
+ "epoch": 0.6070864364703227,
1890
+ "grad_norm": 0.0008087158203125,
1891
+ "learning_rate": 8.006493996828514e-06,
1892
+ "loss": 0.0,
1893
+ "step": 2690
1894
+ },
1895
+ {
1896
+ "epoch": 0.6093432633716994,
1897
+ "grad_norm": 0.0030059814453125,
1898
+ "learning_rate": 7.998942837725592e-06,
1899
+ "loss": 0.0,
1900
+ "step": 2700
1901
+ },
1902
+ {
1903
+ "epoch": 0.611600090273076,
1904
+ "grad_norm": 0.0016021728515625,
1905
+ "learning_rate": 7.99139167862267e-06,
1906
+ "loss": 0.0,
1907
+ "step": 2710
1908
+ },
1909
+ {
1910
+ "epoch": 0.6138569171744527,
1911
+ "grad_norm": 0.0036468505859375,
1912
+ "learning_rate": 7.983840519519746e-06,
1913
+ "loss": 0.0014,
1914
+ "step": 2720
1915
+ },
1916
+ {
1917
+ "epoch": 0.6161137440758294,
1918
+ "grad_norm": 0.0003185272216796875,
1919
+ "learning_rate": 7.976289360416824e-06,
1920
+ "loss": 0.0,
1921
+ "step": 2730
1922
+ },
1923
+ {
1924
+ "epoch": 0.618370570977206,
1925
+ "grad_norm": 0.008056640625,
1926
+ "learning_rate": 7.968738201313903e-06,
1927
+ "loss": 0.0,
1928
+ "step": 2740
1929
+ },
1930
+ {
1931
+ "epoch": 0.6206273978785827,
1932
+ "grad_norm": 0.00103759765625,
1933
+ "learning_rate": 7.961187042210981e-06,
1934
+ "loss": 0.0,
1935
+ "step": 2750
1936
+ },
1937
+ {
1938
+ "epoch": 0.6228842247799594,
1939
+ "grad_norm": 132.0,
1940
+ "learning_rate": 7.953635883108057e-06,
1941
+ "loss": 0.3156,
1942
+ "step": 2760
1943
+ },
1944
+ {
1945
+ "epoch": 0.625141051681336,
1946
+ "grad_norm": 0.024658203125,
1947
+ "learning_rate": 7.946084724005135e-06,
1948
+ "loss": 0.0,
1949
+ "step": 2770
1950
+ },
1951
+ {
1952
+ "epoch": 0.6273978785827127,
1953
+ "grad_norm": 0.000629425048828125,
1954
+ "learning_rate": 7.938533564902213e-06,
1955
+ "loss": 0.0,
1956
+ "step": 2780
1957
+ },
1958
+ {
1959
+ "epoch": 0.6296547054840894,
1960
+ "grad_norm": 0.00897216796875,
1961
+ "learning_rate": 7.930982405799292e-06,
1962
+ "loss": 0.0,
1963
+ "step": 2790
1964
+ },
1965
+ {
1966
+ "epoch": 0.631911532385466,
1967
+ "grad_norm": 0.007354736328125,
1968
+ "learning_rate": 7.923431246696368e-06,
1969
+ "loss": 0.0,
1970
+ "step": 2800
1971
+ },
1972
+ {
1973
+ "epoch": 0.6341683592868427,
1974
+ "grad_norm": 0.0037841796875,
1975
+ "learning_rate": 7.915880087593446e-06,
1976
+ "loss": 0.0001,
1977
+ "step": 2810
1978
+ },
1979
+ {
1980
+ "epoch": 0.6364251861882194,
1981
+ "grad_norm": 0.0036163330078125,
1982
+ "learning_rate": 7.908328928490524e-06,
1983
+ "loss": 0.0,
1984
+ "step": 2820
1985
+ },
1986
+ {
1987
+ "epoch": 0.638682013089596,
1988
+ "grad_norm": 0.00250244140625,
1989
+ "learning_rate": 7.900777769387601e-06,
1990
+ "loss": 0.0,
1991
+ "step": 2830
1992
+ },
1993
+ {
1994
+ "epoch": 0.6409388399909727,
1995
+ "grad_norm": 0.00173187255859375,
1996
+ "learning_rate": 7.893226610284679e-06,
1997
+ "loss": 0.0,
1998
+ "step": 2840
1999
+ },
2000
+ {
2001
+ "epoch": 0.6431956668923493,
2002
+ "grad_norm": 0.0004520416259765625,
2003
+ "learning_rate": 7.885675451181757e-06,
2004
+ "loss": 0.0,
2005
+ "step": 2850
2006
+ },
2007
+ {
2008
+ "epoch": 0.645452493793726,
2009
+ "grad_norm": 0.00021457672119140625,
2010
+ "learning_rate": 7.878124292078835e-06,
2011
+ "loss": 0.0,
2012
+ "step": 2860
2013
+ },
2014
+ {
2015
+ "epoch": 0.6477093206951027,
2016
+ "grad_norm": 0.0004405975341796875,
2017
+ "learning_rate": 7.870573132975912e-06,
2018
+ "loss": 0.0,
2019
+ "step": 2870
2020
+ },
2021
+ {
2022
+ "epoch": 0.6499661475964793,
2023
+ "grad_norm": 0.00045013427734375,
2024
+ "learning_rate": 7.86302197387299e-06,
2025
+ "loss": 0.0,
2026
+ "step": 2880
2027
+ },
2028
+ {
2029
+ "epoch": 0.652222974497856,
2030
+ "grad_norm": 0.000522613525390625,
2031
+ "learning_rate": 7.855470814770068e-06,
2032
+ "loss": 0.0,
2033
+ "step": 2890
2034
+ },
2035
+ {
2036
+ "epoch": 0.6544798013992327,
2037
+ "grad_norm": 0.00029754638671875,
2038
+ "learning_rate": 7.847919655667146e-06,
2039
+ "loss": 0.3409,
2040
+ "step": 2900
2041
+ },
2042
+ {
2043
+ "epoch": 0.6567366283006093,
2044
+ "grad_norm": 0.00372314453125,
2045
+ "learning_rate": 7.840368496564223e-06,
2046
+ "loss": 0.1273,
2047
+ "step": 2910
2048
+ },
2049
+ {
2050
+ "epoch": 0.658993455201986,
2051
+ "grad_norm": 0.005401611328125,
2052
+ "learning_rate": 7.832817337461301e-06,
2053
+ "loss": 0.2191,
2054
+ "step": 2920
2055
+ },
2056
+ {
2057
+ "epoch": 0.6612502821033627,
2058
+ "grad_norm": 47.25,
2059
+ "learning_rate": 7.825266178358379e-06,
2060
+ "loss": 0.2522,
2061
+ "step": 2930
2062
+ },
2063
+ {
2064
+ "epoch": 0.6635071090047393,
2065
+ "grad_norm": 0.018310546875,
2066
+ "learning_rate": 7.817715019255457e-06,
2067
+ "loss": 0.0982,
2068
+ "step": 2940
2069
+ },
2070
+ {
2071
+ "epoch": 0.665763935906116,
2072
+ "grad_norm": 0.001220703125,
2073
+ "learning_rate": 7.810163860152535e-06,
2074
+ "loss": 0.0001,
2075
+ "step": 2950
2076
+ },
2077
+ {
2078
+ "epoch": 0.6680207628074927,
2079
+ "grad_norm": 0.001495361328125,
2080
+ "learning_rate": 7.802612701049612e-06,
2081
+ "loss": 0.1024,
2082
+ "step": 2960
2083
+ },
2084
+ {
2085
+ "epoch": 0.6702775897088693,
2086
+ "grad_norm": 0.005401611328125,
2087
+ "learning_rate": 7.795061541946688e-06,
2088
+ "loss": 0.0001,
2089
+ "step": 2970
2090
+ },
2091
+ {
2092
+ "epoch": 0.672534416610246,
2093
+ "grad_norm": 0.0035858154296875,
2094
+ "learning_rate": 7.787510382843768e-06,
2095
+ "loss": 0.0,
2096
+ "step": 2980
2097
+ },
2098
+ {
2099
+ "epoch": 0.6747912435116227,
2100
+ "grad_norm": 0.0654296875,
2101
+ "learning_rate": 7.779959223740846e-06,
2102
+ "loss": 0.0,
2103
+ "step": 2990
2104
+ },
2105
+ {
2106
+ "epoch": 0.6770480704129993,
2107
+ "grad_norm": 0.002838134765625,
2108
+ "learning_rate": 7.772408064637923e-06,
2109
+ "loss": 0.0,
2110
+ "step": 3000
2111
+ },
2112
+ {
2113
+ "epoch": 0.6793048973143759,
2114
+ "grad_norm": 0.001068115234375,
2115
+ "learning_rate": 7.764856905535e-06,
2116
+ "loss": 0.1202,
2117
+ "step": 3010
2118
+ },
2119
+ {
2120
+ "epoch": 0.6815617242157527,
2121
+ "grad_norm": 0.0078125,
2122
+ "learning_rate": 7.757305746432077e-06,
2123
+ "loss": 0.2662,
2124
+ "step": 3020
2125
+ },
2126
+ {
2127
+ "epoch": 0.6838185511171293,
2128
+ "grad_norm": 0.002227783203125,
2129
+ "learning_rate": 7.749754587329157e-06,
2130
+ "loss": 0.3129,
2131
+ "step": 3030
2132
+ },
2133
+ {
2134
+ "epoch": 0.6860753780185059,
2135
+ "grad_norm": 0.00093841552734375,
2136
+ "learning_rate": 7.742203428226234e-06,
2137
+ "loss": 0.0,
2138
+ "step": 3040
2139
+ },
2140
+ {
2141
+ "epoch": 0.6883322049198827,
2142
+ "grad_norm": 0.00162506103515625,
2143
+ "learning_rate": 7.73465226912331e-06,
2144
+ "loss": 0.0,
2145
+ "step": 3050
2146
+ },
2147
+ {
2148
+ "epoch": 0.6905890318212593,
2149
+ "grad_norm": 0.0113525390625,
2150
+ "learning_rate": 7.727101110020388e-06,
2151
+ "loss": 0.0,
2152
+ "step": 3060
2153
+ },
2154
+ {
2155
+ "epoch": 0.6928458587226359,
2156
+ "grad_norm": 0.0042724609375,
2157
+ "learning_rate": 7.719549950917466e-06,
2158
+ "loss": 0.0,
2159
+ "step": 3070
2160
+ },
2161
+ {
2162
+ "epoch": 0.6951026856240127,
2163
+ "grad_norm": 0.00174713134765625,
2164
+ "learning_rate": 7.711998791814544e-06,
2165
+ "loss": 0.0001,
2166
+ "step": 3080
2167
+ },
2168
+ {
2169
+ "epoch": 0.6973595125253893,
2170
+ "grad_norm": 0.0021820068359375,
2171
+ "learning_rate": 7.704447632711621e-06,
2172
+ "loss": 0.0,
2173
+ "step": 3090
2174
+ },
2175
+ {
2176
+ "epoch": 0.6996163394267659,
2177
+ "grad_norm": 0.00016307830810546875,
2178
+ "learning_rate": 7.6968964736087e-06,
2179
+ "loss": 0.0,
2180
+ "step": 3100
2181
+ },
2182
+ {
2183
+ "epoch": 0.7018731663281427,
2184
+ "grad_norm": 0.0008544921875,
2185
+ "learning_rate": 7.689345314505777e-06,
2186
+ "loss": 0.0868,
2187
+ "step": 3110
2188
+ },
2189
+ {
2190
+ "epoch": 0.7041299932295193,
2191
+ "grad_norm": 0.00162506103515625,
2192
+ "learning_rate": 7.681794155402855e-06,
2193
+ "loss": 0.0,
2194
+ "step": 3120
2195
+ },
2196
+ {
2197
+ "epoch": 0.7063868201308959,
2198
+ "grad_norm": 0.83984375,
2199
+ "learning_rate": 7.674242996299933e-06,
2200
+ "loss": 0.0001,
2201
+ "step": 3130
2202
+ },
2203
+ {
2204
+ "epoch": 0.7086436470322727,
2205
+ "grad_norm": 0.00021266937255859375,
2206
+ "learning_rate": 7.66669183719701e-06,
2207
+ "loss": 0.0,
2208
+ "step": 3140
2209
+ },
2210
+ {
2211
+ "epoch": 0.7109004739336493,
2212
+ "grad_norm": 0.000926971435546875,
2213
+ "learning_rate": 7.659140678094088e-06,
2214
+ "loss": 0.0,
2215
+ "step": 3150
2216
+ },
2217
+ {
2218
+ "epoch": 0.7131573008350259,
2219
+ "grad_norm": 2.515625,
2220
+ "learning_rate": 7.651589518991166e-06,
2221
+ "loss": 0.0004,
2222
+ "step": 3160
2223
+ },
2224
+ {
2225
+ "epoch": 0.7154141277364027,
2226
+ "grad_norm": 0.0029144287109375,
2227
+ "learning_rate": 7.644038359888244e-06,
2228
+ "loss": 0.0,
2229
+ "step": 3170
2230
+ },
2231
+ {
2232
+ "epoch": 0.7176709546377793,
2233
+ "grad_norm": 62.5,
2234
+ "learning_rate": 7.636487200785321e-06,
2235
+ "loss": 0.3018,
2236
+ "step": 3180
2237
+ },
2238
+ {
2239
+ "epoch": 0.7199277815391559,
2240
+ "grad_norm": 0.0005950927734375,
2241
+ "learning_rate": 7.628936041682399e-06,
2242
+ "loss": 0.0,
2243
+ "step": 3190
2244
+ },
2245
+ {
2246
+ "epoch": 0.7221846084405326,
2247
+ "grad_norm": 0.00054168701171875,
2248
+ "learning_rate": 7.621384882579477e-06,
2249
+ "loss": 0.0,
2250
+ "step": 3200
2251
+ },
2252
+ {
2253
+ "epoch": 0.7244414353419093,
2254
+ "grad_norm": 0.00701904296875,
2255
+ "learning_rate": 7.613833723476555e-06,
2256
+ "loss": 0.0,
2257
+ "step": 3210
2258
+ },
2259
+ {
2260
+ "epoch": 0.7266982622432859,
2261
+ "grad_norm": 41.75,
2262
+ "learning_rate": 7.6062825643736315e-06,
2263
+ "loss": 0.2809,
2264
+ "step": 3220
2265
+ },
2266
+ {
2267
+ "epoch": 0.7289550891446626,
2268
+ "grad_norm": 0.0018463134765625,
2269
+ "learning_rate": 7.598731405270709e-06,
2270
+ "loss": 0.0,
2271
+ "step": 3230
2272
+ },
2273
+ {
2274
+ "epoch": 0.7312119160460393,
2275
+ "grad_norm": 0.0024261474609375,
2276
+ "learning_rate": 7.591180246167788e-06,
2277
+ "loss": 0.0,
2278
+ "step": 3240
2279
+ },
2280
+ {
2281
+ "epoch": 0.7334687429474159,
2282
+ "grad_norm": 0.0032501220703125,
2283
+ "learning_rate": 7.583629087064866e-06,
2284
+ "loss": 0.0,
2285
+ "step": 3250
2286
+ },
2287
+ {
2288
+ "epoch": 0.7357255698487926,
2289
+ "grad_norm": 0.0016326904296875,
2290
+ "learning_rate": 7.5760779279619426e-06,
2291
+ "loss": 0.0,
2292
+ "step": 3260
2293
+ },
2294
+ {
2295
+ "epoch": 0.7379823967501693,
2296
+ "grad_norm": 0.000629425048828125,
2297
+ "learning_rate": 7.56852676885902e-06,
2298
+ "loss": 0.0,
2299
+ "step": 3270
2300
+ },
2301
+ {
2302
+ "epoch": 0.7402392236515459,
2303
+ "grad_norm": 0.0022735595703125,
2304
+ "learning_rate": 7.560975609756098e-06,
2305
+ "loss": 0.0,
2306
+ "step": 3280
2307
+ },
2308
+ {
2309
+ "epoch": 0.7424960505529226,
2310
+ "grad_norm": 0.00193023681640625,
2311
+ "learning_rate": 7.553424450653176e-06,
2312
+ "loss": 0.0,
2313
+ "step": 3290
2314
+ },
2315
+ {
2316
+ "epoch": 0.7447528774542993,
2317
+ "grad_norm": 0.00144195556640625,
2318
+ "learning_rate": 7.545873291550253e-06,
2319
+ "loss": 0.4039,
2320
+ "step": 3300
2321
+ },
2322
+ {
2323
+ "epoch": 0.7470097043556759,
2324
+ "grad_norm": 0.006134033203125,
2325
+ "learning_rate": 7.538322132447331e-06,
2326
+ "loss": 0.0,
2327
+ "step": 3310
2328
+ },
2329
+ {
2330
+ "epoch": 0.7492665312570526,
2331
+ "grad_norm": 0.0037384033203125,
2332
+ "learning_rate": 7.530770973344409e-06,
2333
+ "loss": 0.0,
2334
+ "step": 3320
2335
+ },
2336
+ {
2337
+ "epoch": 0.7515233581584293,
2338
+ "grad_norm": 0.0028228759765625,
2339
+ "learning_rate": 7.523219814241487e-06,
2340
+ "loss": 0.0,
2341
+ "step": 3330
2342
+ },
2343
+ {
2344
+ "epoch": 0.7537801850598059,
2345
+ "grad_norm": 0.0038604736328125,
2346
+ "learning_rate": 7.515668655138565e-06,
2347
+ "loss": 0.0,
2348
+ "step": 3340
2349
+ },
2350
+ {
2351
+ "epoch": 0.7560370119611826,
2352
+ "grad_norm": 0.00151824951171875,
2353
+ "learning_rate": 7.5081174960356416e-06,
2354
+ "loss": 0.0,
2355
+ "step": 3350
2356
+ },
2357
+ {
2358
+ "epoch": 0.7582938388625592,
2359
+ "grad_norm": 0.0002689361572265625,
2360
+ "learning_rate": 7.500566336932719e-06,
2361
+ "loss": 0.0,
2362
+ "step": 3360
2363
+ },
2364
+ {
2365
+ "epoch": 0.7605506657639359,
2366
+ "grad_norm": 0.000316619873046875,
2367
+ "learning_rate": 7.493015177829798e-06,
2368
+ "loss": 0.0,
2369
+ "step": 3370
2370
+ },
2371
+ {
2372
+ "epoch": 0.7628074926653126,
2373
+ "grad_norm": 0.00106048583984375,
2374
+ "learning_rate": 7.485464018726876e-06,
2375
+ "loss": 0.0,
2376
+ "step": 3380
2377
+ },
2378
+ {
2379
+ "epoch": 0.7650643195666892,
2380
+ "grad_norm": 0.00186920166015625,
2381
+ "learning_rate": 7.477912859623953e-06,
2382
+ "loss": 0.0,
2383
+ "step": 3390
2384
+ },
2385
+ {
2386
+ "epoch": 0.7673211464680659,
2387
+ "grad_norm": 0.00110626220703125,
2388
+ "learning_rate": 7.47036170052103e-06,
2389
+ "loss": 0.0,
2390
+ "step": 3400
2391
+ },
2392
+ {
2393
+ "epoch": 0.7695779733694426,
2394
+ "grad_norm": 0.0007781982421875,
2395
+ "learning_rate": 7.462810541418108e-06,
2396
+ "loss": 0.0,
2397
+ "step": 3410
2398
+ },
2399
+ {
2400
+ "epoch": 0.7718348002708192,
2401
+ "grad_norm": 0.000652313232421875,
2402
+ "learning_rate": 7.455259382315187e-06,
2403
+ "loss": 0.4836,
2404
+ "step": 3420
2405
+ },
2406
+ {
2407
+ "epoch": 0.7740916271721959,
2408
+ "grad_norm": 0.002777099609375,
2409
+ "learning_rate": 7.447708223212264e-06,
2410
+ "loss": 0.0,
2411
+ "step": 3430
2412
+ },
2413
+ {
2414
+ "epoch": 0.7763484540735726,
2415
+ "grad_norm": 0.002410888671875,
2416
+ "learning_rate": 7.440157064109341e-06,
2417
+ "loss": 0.0,
2418
+ "step": 3440
2419
+ },
2420
+ {
2421
+ "epoch": 0.7786052809749492,
2422
+ "grad_norm": 0.0023345947265625,
2423
+ "learning_rate": 7.432605905006419e-06,
2424
+ "loss": 0.0,
2425
+ "step": 3450
2426
+ },
2427
+ {
2428
+ "epoch": 0.7808621078763259,
2429
+ "grad_norm": 0.000885009765625,
2430
+ "learning_rate": 7.425054745903497e-06,
2431
+ "loss": 0.0,
2432
+ "step": 3460
2433
+ },
2434
+ {
2435
+ "epoch": 0.7831189347777026,
2436
+ "grad_norm": 0.001190185546875,
2437
+ "learning_rate": 7.417503586800574e-06,
2438
+ "loss": 0.0,
2439
+ "step": 3470
2440
+ },
2441
+ {
2442
+ "epoch": 0.7853757616790792,
2443
+ "grad_norm": 0.00164794921875,
2444
+ "learning_rate": 7.409952427697652e-06,
2445
+ "loss": 0.3779,
2446
+ "step": 3480
2447
+ },
2448
+ {
2449
+ "epoch": 0.7876325885804559,
2450
+ "grad_norm": 0.0024871826171875,
2451
+ "learning_rate": 7.40240126859473e-06,
2452
+ "loss": 0.3797,
2453
+ "step": 3490
2454
+ },
2455
+ {
2456
+ "epoch": 0.7898894154818326,
2457
+ "grad_norm": 0.0009002685546875,
2458
+ "learning_rate": 7.394850109491808e-06,
2459
+ "loss": 0.0,
2460
+ "step": 3500
2461
+ },
2462
+ {
2463
+ "epoch": 0.7921462423832092,
2464
+ "grad_norm": 0.00145721435546875,
2465
+ "learning_rate": 7.387298950388885e-06,
2466
+ "loss": 0.0,
2467
+ "step": 3510
2468
+ },
2469
+ {
2470
+ "epoch": 0.7944030692845859,
2471
+ "grad_norm": 0.00035858154296875,
2472
+ "learning_rate": 7.379747791285963e-06,
2473
+ "loss": 0.3298,
2474
+ "step": 3520
2475
+ },
2476
+ {
2477
+ "epoch": 0.7966598961859626,
2478
+ "grad_norm": 0.000583648681640625,
2479
+ "learning_rate": 7.37219663218304e-06,
2480
+ "loss": 0.0,
2481
+ "step": 3530
2482
+ },
2483
+ {
2484
+ "epoch": 0.7989167230873392,
2485
+ "grad_norm": 0.0028228759765625,
2486
+ "learning_rate": 7.364645473080119e-06,
2487
+ "loss": 0.187,
2488
+ "step": 3540
2489
+ },
2490
+ {
2491
+ "epoch": 0.8011735499887158,
2492
+ "grad_norm": 0.01263427734375,
2493
+ "learning_rate": 7.357094313977197e-06,
2494
+ "loss": 0.2544,
2495
+ "step": 3550
2496
+ },
2497
+ {
2498
+ "epoch": 0.8034303768900926,
2499
+ "grad_norm": 0.01226806640625,
2500
+ "learning_rate": 7.349543154874274e-06,
2501
+ "loss": 0.0001,
2502
+ "step": 3560
2503
+ },
2504
+ {
2505
+ "epoch": 0.8056872037914692,
2506
+ "grad_norm": 0.00079345703125,
2507
+ "learning_rate": 7.3419919957713514e-06,
2508
+ "loss": 0.0,
2509
+ "step": 3570
2510
+ },
2511
+ {
2512
+ "epoch": 0.8079440306928458,
2513
+ "grad_norm": 0.291015625,
2514
+ "learning_rate": 7.334440836668429e-06,
2515
+ "loss": 0.0001,
2516
+ "step": 3580
2517
+ },
2518
+ {
2519
+ "epoch": 0.8102008575942226,
2520
+ "grad_norm": 0.0021514892578125,
2521
+ "learning_rate": 7.326889677565508e-06,
2522
+ "loss": 0.0,
2523
+ "step": 3590
2524
+ },
2525
+ {
2526
+ "epoch": 0.8124576844955992,
2527
+ "grad_norm": 0.0004634857177734375,
2528
+ "learning_rate": 7.319338518462584e-06,
2529
+ "loss": 0.0,
2530
+ "step": 3600
2531
+ },
2532
+ {
2533
+ "epoch": 0.8147145113969758,
2534
+ "grad_norm": 0.001800537109375,
2535
+ "learning_rate": 7.3117873593596625e-06,
2536
+ "loss": 0.0,
2537
+ "step": 3610
2538
+ },
2539
+ {
2540
+ "epoch": 0.8169713382983526,
2541
+ "grad_norm": 0.0024871826171875,
2542
+ "learning_rate": 7.30423620025674e-06,
2543
+ "loss": 0.0,
2544
+ "step": 3620
2545
+ },
2546
+ {
2547
+ "epoch": 0.8192281651997292,
2548
+ "grad_norm": 0.00119781494140625,
2549
+ "learning_rate": 7.296685041153818e-06,
2550
+ "loss": 0.0,
2551
+ "step": 3630
2552
+ },
2553
+ {
2554
+ "epoch": 0.8214849921011058,
2555
+ "grad_norm": 0.000629425048828125,
2556
+ "learning_rate": 7.289133882050895e-06,
2557
+ "loss": 0.0,
2558
+ "step": 3640
2559
+ },
2560
+ {
2561
+ "epoch": 0.8237418190024826,
2562
+ "grad_norm": 0.000797271728515625,
2563
+ "learning_rate": 7.281582722947973e-06,
2564
+ "loss": 0.3255,
2565
+ "step": 3650
2566
+ },
2567
+ {
2568
+ "epoch": 0.8259986459038592,
2569
+ "grad_norm": 0.0008392333984375,
2570
+ "learning_rate": 7.274031563845051e-06,
2571
+ "loss": 0.0036,
2572
+ "step": 3660
2573
+ },
2574
+ {
2575
+ "epoch": 0.8282554728052358,
2576
+ "grad_norm": 0.00164794921875,
2577
+ "learning_rate": 7.266480404742129e-06,
2578
+ "loss": 0.0,
2579
+ "step": 3670
2580
+ },
2581
+ {
2582
+ "epoch": 0.8305122997066126,
2583
+ "grad_norm": 0.00012874603271484375,
2584
+ "learning_rate": 7.258929245639206e-06,
2585
+ "loss": 0.0,
2586
+ "step": 3680
2587
+ },
2588
+ {
2589
+ "epoch": 0.8327691266079892,
2590
+ "grad_norm": 0.000461578369140625,
2591
+ "learning_rate": 7.251378086536284e-06,
2592
+ "loss": 0.3065,
2593
+ "step": 3690
2594
+ },
2595
+ {
2596
+ "epoch": 0.8350259535093658,
2597
+ "grad_norm": 57.75,
2598
+ "learning_rate": 7.2438269274333615e-06,
2599
+ "loss": 0.3243,
2600
+ "step": 3700
2601
+ },
2602
+ {
2603
+ "epoch": 0.8372827804107424,
2604
+ "grad_norm": 0.0020599365234375,
2605
+ "learning_rate": 7.236275768330439e-06,
2606
+ "loss": 0.0,
2607
+ "step": 3710
2608
+ },
2609
+ {
2610
+ "epoch": 0.8395396073121192,
2611
+ "grad_norm": 0.0155029296875,
2612
+ "learning_rate": 7.228724609227516e-06,
2613
+ "loss": 0.0,
2614
+ "step": 3720
2615
+ },
2616
+ {
2617
+ "epoch": 0.8417964342134958,
2618
+ "grad_norm": 0.005401611328125,
2619
+ "learning_rate": 7.221173450124595e-06,
2620
+ "loss": 0.0,
2621
+ "step": 3730
2622
+ },
2623
+ {
2624
+ "epoch": 0.8440532611148724,
2625
+ "grad_norm": 0.0025634765625,
2626
+ "learning_rate": 7.2136222910216725e-06,
2627
+ "loss": 0.0,
2628
+ "step": 3740
2629
+ },
2630
+ {
2631
+ "epoch": 0.8463100880162492,
2632
+ "grad_norm": 0.003143310546875,
2633
+ "learning_rate": 7.20607113191875e-06,
2634
+ "loss": 0.0,
2635
+ "step": 3750
2636
+ },
2637
+ {
2638
+ "epoch": 0.8485669149176258,
2639
+ "grad_norm": 0.00994873046875,
2640
+ "learning_rate": 7.198519972815828e-06,
2641
+ "loss": 0.0,
2642
+ "step": 3760
2643
+ },
2644
+ {
2645
+ "epoch": 0.8508237418190024,
2646
+ "grad_norm": 0.0191650390625,
2647
+ "learning_rate": 7.190968813712905e-06,
2648
+ "loss": 0.0,
2649
+ "step": 3770
2650
+ },
2651
+ {
2652
+ "epoch": 0.8530805687203792,
2653
+ "grad_norm": 0.00024318695068359375,
2654
+ "learning_rate": 7.1834176546099836e-06,
2655
+ "loss": 0.0001,
2656
+ "step": 3780
2657
+ },
2658
+ {
2659
+ "epoch": 0.8553373956217558,
2660
+ "grad_norm": 0.0035247802734375,
2661
+ "learning_rate": 7.175866495507061e-06,
2662
+ "loss": 0.208,
2663
+ "step": 3790
2664
+ },
2665
+ {
2666
+ "epoch": 0.8575942225231324,
2667
+ "grad_norm": 0.0002269744873046875,
2668
+ "learning_rate": 7.168315336404139e-06,
2669
+ "loss": 0.0,
2670
+ "step": 3800
2671
+ },
2672
+ {
2673
+ "epoch": 0.8598510494245092,
2674
+ "grad_norm": 0.00250244140625,
2675
+ "learning_rate": 7.160764177301216e-06,
2676
+ "loss": 0.3297,
2677
+ "step": 3810
2678
+ },
2679
+ {
2680
+ "epoch": 0.8621078763258858,
2681
+ "grad_norm": 0.00150299072265625,
2682
+ "learning_rate": 7.153213018198294e-06,
2683
+ "loss": 0.0,
2684
+ "step": 3820
2685
+ },
2686
+ {
2687
+ "epoch": 0.8643647032272624,
2688
+ "grad_norm": 0.00274658203125,
2689
+ "learning_rate": 7.1456618590953715e-06,
2690
+ "loss": 0.0,
2691
+ "step": 3830
2692
+ },
2693
+ {
2694
+ "epoch": 0.8666215301286392,
2695
+ "grad_norm": 0.00262451171875,
2696
+ "learning_rate": 7.13811069999245e-06,
2697
+ "loss": 0.0033,
2698
+ "step": 3840
2699
+ },
2700
+ {
2701
+ "epoch": 0.8688783570300158,
2702
+ "grad_norm": 0.002197265625,
2703
+ "learning_rate": 7.130559540889527e-06,
2704
+ "loss": 0.0441,
2705
+ "step": 3850
2706
+ },
2707
+ {
2708
+ "epoch": 0.8711351839313924,
2709
+ "grad_norm": 0.031982421875,
2710
+ "learning_rate": 7.123008381786605e-06,
2711
+ "loss": 0.0,
2712
+ "step": 3860
2713
+ },
2714
+ {
2715
+ "epoch": 0.8733920108327691,
2716
+ "grad_norm": 0.00469970703125,
2717
+ "learning_rate": 7.1154572226836826e-06,
2718
+ "loss": 0.0,
2719
+ "step": 3870
2720
+ },
2721
+ {
2722
+ "epoch": 0.8756488377341458,
2723
+ "grad_norm": 0.00164794921875,
2724
+ "learning_rate": 7.10790606358076e-06,
2725
+ "loss": 0.0,
2726
+ "step": 3880
2727
+ },
2728
+ {
2729
+ "epoch": 0.8779056646355224,
2730
+ "grad_norm": 0.00125885009765625,
2731
+ "learning_rate": 7.100354904477837e-06,
2732
+ "loss": 0.0,
2733
+ "step": 3890
2734
+ },
2735
+ {
2736
+ "epoch": 0.8801624915368991,
2737
+ "grad_norm": 0.003814697265625,
2738
+ "learning_rate": 7.092803745374916e-06,
2739
+ "loss": 0.0,
2740
+ "step": 3900
2741
+ },
2742
+ {
2743
+ "epoch": 0.8824193184382758,
2744
+ "grad_norm": 0.01007080078125,
2745
+ "learning_rate": 7.085252586271994e-06,
2746
+ "loss": 0.0,
2747
+ "step": 3910
2748
+ },
2749
+ {
2750
+ "epoch": 0.8846761453396524,
2751
+ "grad_norm": 0.000579833984375,
2752
+ "learning_rate": 7.077701427169071e-06,
2753
+ "loss": 0.0,
2754
+ "step": 3920
2755
+ },
2756
+ {
2757
+ "epoch": 0.8869329722410291,
2758
+ "grad_norm": 0.00848388671875,
2759
+ "learning_rate": 7.070150268066148e-06,
2760
+ "loss": 0.0,
2761
+ "step": 3930
2762
+ },
2763
+ {
2764
+ "epoch": 0.8891897991424058,
2765
+ "grad_norm": 0.00054931640625,
2766
+ "learning_rate": 7.062599108963226e-06,
2767
+ "loss": 0.0,
2768
+ "step": 3940
2769
+ },
2770
+ {
2771
+ "epoch": 0.8914466260437824,
2772
+ "grad_norm": 0.000835418701171875,
2773
+ "learning_rate": 7.055047949860304e-06,
2774
+ "loss": 0.0,
2775
+ "step": 3950
2776
+ },
2777
+ {
2778
+ "epoch": 0.8937034529451591,
2779
+ "grad_norm": 0.00048828125,
2780
+ "learning_rate": 7.047496790757382e-06,
2781
+ "loss": 0.0,
2782
+ "step": 3960
2783
+ },
2784
+ {
2785
+ "epoch": 0.8959602798465358,
2786
+ "grad_norm": 0.00023365020751953125,
2787
+ "learning_rate": 7.039945631654459e-06,
2788
+ "loss": 0.0,
2789
+ "step": 3970
2790
+ },
2791
+ {
2792
+ "epoch": 0.8982171067479124,
2793
+ "grad_norm": 0.00335693359375,
2794
+ "learning_rate": 7.032394472551537e-06,
2795
+ "loss": 0.0,
2796
+ "step": 3980
2797
+ },
2798
+ {
2799
+ "epoch": 0.9004739336492891,
2800
+ "grad_norm": 0.00014400482177734375,
2801
+ "learning_rate": 7.024843313448615e-06,
2802
+ "loss": 0.0,
2803
+ "step": 3990
2804
+ },
2805
+ {
2806
+ "epoch": 0.9027307605506658,
2807
+ "grad_norm": 0.0002613067626953125,
2808
+ "learning_rate": 7.017292154345693e-06,
2809
+ "loss": 0.0,
2810
+ "step": 4000
2811
+ },
2812
+ {
2813
+ "epoch": 0.9049875874520424,
2814
+ "grad_norm": 0.00043487548828125,
2815
+ "learning_rate": 7.009740995242771e-06,
2816
+ "loss": 0.0,
2817
+ "step": 4010
2818
+ },
2819
+ {
2820
+ "epoch": 0.9072444143534191,
2821
+ "grad_norm": 0.318359375,
2822
+ "learning_rate": 7.002189836139847e-06,
2823
+ "loss": 0.0,
2824
+ "step": 4020
2825
+ },
2826
+ {
2827
+ "epoch": 0.9095012412547958,
2828
+ "grad_norm": 0.00089263916015625,
2829
+ "learning_rate": 6.994638677036926e-06,
2830
+ "loss": 0.0,
2831
+ "step": 4030
2832
+ },
2833
+ {
2834
+ "epoch": 0.9117580681561724,
2835
+ "grad_norm": 0.000247955322265625,
2836
+ "learning_rate": 6.987087517934004e-06,
2837
+ "loss": 0.0,
2838
+ "step": 4040
2839
+ },
2840
+ {
2841
+ "epoch": 0.9140148950575491,
2842
+ "grad_norm": 0.00011873245239257812,
2843
+ "learning_rate": 6.979536358831081e-06,
2844
+ "loss": 0.0,
2845
+ "step": 4050
2846
+ },
2847
+ {
2848
+ "epoch": 0.9162717219589257,
2849
+ "grad_norm": 0.00018978118896484375,
2850
+ "learning_rate": 6.971985199728158e-06,
2851
+ "loss": 0.0,
2852
+ "step": 4060
2853
+ },
2854
+ {
2855
+ "epoch": 0.9185285488603024,
2856
+ "grad_norm": 0.0001049041748046875,
2857
+ "learning_rate": 6.964434040625236e-06,
2858
+ "loss": 0.3925,
2859
+ "step": 4070
2860
+ },
2861
+ {
2862
+ "epoch": 0.9207853757616791,
2863
+ "grad_norm": 0.0002918243408203125,
2864
+ "learning_rate": 6.956882881522315e-06,
2865
+ "loss": 0.0,
2866
+ "step": 4080
2867
+ },
2868
+ {
2869
+ "epoch": 0.9230422026630557,
2870
+ "grad_norm": 0.000255584716796875,
2871
+ "learning_rate": 6.9493317224193925e-06,
2872
+ "loss": 0.0,
2873
+ "step": 4090
2874
+ },
2875
+ {
2876
+ "epoch": 0.9252990295644324,
2877
+ "grad_norm": 0.0001773834228515625,
2878
+ "learning_rate": 6.941780563316469e-06,
2879
+ "loss": 0.0,
2880
+ "step": 4100
2881
+ },
2882
+ {
2883
+ "epoch": 0.9275558564658091,
2884
+ "grad_norm": 0.0087890625,
2885
+ "learning_rate": 6.934229404213547e-06,
2886
+ "loss": 0.3115,
2887
+ "step": 4110
2888
+ },
2889
+ {
2890
+ "epoch": 0.9298126833671857,
2891
+ "grad_norm": 0.00093841552734375,
2892
+ "learning_rate": 6.926678245110625e-06,
2893
+ "loss": 0.086,
2894
+ "step": 4120
2895
+ },
2896
+ {
2897
+ "epoch": 0.9320695102685624,
2898
+ "grad_norm": 0.000865936279296875,
2899
+ "learning_rate": 6.9191270860077035e-06,
2900
+ "loss": 0.0488,
2901
+ "step": 4130
2902
+ },
2903
+ {
2904
+ "epoch": 0.9343263371699391,
2905
+ "grad_norm": 0.00144195556640625,
2906
+ "learning_rate": 6.9115759269047796e-06,
2907
+ "loss": 0.0,
2908
+ "step": 4140
2909
+ },
2910
+ {
2911
+ "epoch": 0.9365831640713157,
2912
+ "grad_norm": 0.00823974609375,
2913
+ "learning_rate": 6.904024767801858e-06,
2914
+ "loss": 0.0,
2915
+ "step": 4150
2916
+ },
2917
+ {
2918
+ "epoch": 0.9388399909726924,
2919
+ "grad_norm": 0.001922607421875,
2920
+ "learning_rate": 6.896473608698936e-06,
2921
+ "loss": 0.0,
2922
+ "step": 4160
2923
+ },
2924
+ {
2925
+ "epoch": 0.9410968178740691,
2926
+ "grad_norm": 0.00102996826171875,
2927
+ "learning_rate": 6.888922449596014e-06,
2928
+ "loss": 0.0,
2929
+ "step": 4170
2930
+ },
2931
+ {
2932
+ "epoch": 0.9433536447754457,
2933
+ "grad_norm": 0.000972747802734375,
2934
+ "learning_rate": 6.881371290493091e-06,
2935
+ "loss": 0.0,
2936
+ "step": 4180
2937
+ },
2938
+ {
2939
+ "epoch": 0.9456104716768224,
2940
+ "grad_norm": 53.5,
2941
+ "learning_rate": 6.873820131390168e-06,
2942
+ "loss": 0.1112,
2943
+ "step": 4190
2944
+ },
2945
+ {
2946
+ "epoch": 0.9478672985781991,
2947
+ "grad_norm": 0.00390625,
2948
+ "learning_rate": 6.866268972287247e-06,
2949
+ "loss": 0.4043,
2950
+ "step": 4200
2951
+ },
2952
+ {
2953
+ "epoch": 0.9501241254795757,
2954
+ "grad_norm": 0.0021514892578125,
2955
+ "learning_rate": 6.858717813184325e-06,
2956
+ "loss": 0.0001,
2957
+ "step": 4210
2958
+ },
2959
+ {
2960
+ "epoch": 0.9523809523809523,
2961
+ "grad_norm": 0.00074005126953125,
2962
+ "learning_rate": 6.8511666540814025e-06,
2963
+ "loss": 0.3612,
2964
+ "step": 4220
2965
+ },
2966
+ {
2967
+ "epoch": 0.9546377792823291,
2968
+ "grad_norm": 0.002044677734375,
2969
+ "learning_rate": 6.843615494978479e-06,
2970
+ "loss": 0.0,
2971
+ "step": 4230
2972
+ },
2973
+ {
2974
+ "epoch": 0.9568946061837057,
2975
+ "grad_norm": 0.0120849609375,
2976
+ "learning_rate": 6.836064335875557e-06,
2977
+ "loss": 0.2291,
2978
+ "step": 4240
2979
+ },
2980
+ {
2981
+ "epoch": 0.9591514330850823,
2982
+ "grad_norm": 0.004669189453125,
2983
+ "learning_rate": 6.828513176772635e-06,
2984
+ "loss": 0.0,
2985
+ "step": 4250
2986
+ },
2987
+ {
2988
+ "epoch": 0.9614082599864591,
2989
+ "grad_norm": 0.00494384765625,
2990
+ "learning_rate": 6.8209620176697136e-06,
2991
+ "loss": 0.0,
2992
+ "step": 4260
2993
+ },
2994
+ {
2995
+ "epoch": 0.9636650868878357,
2996
+ "grad_norm": 0.00072479248046875,
2997
+ "learning_rate": 6.8134108585667905e-06,
2998
+ "loss": 0.0,
2999
+ "step": 4270
3000
+ },
3001
+ {
3002
+ "epoch": 0.9659219137892123,
3003
+ "grad_norm": 0.005584716796875,
3004
+ "learning_rate": 6.805859699463868e-06,
3005
+ "loss": 0.0,
3006
+ "step": 4280
3007
+ },
3008
+ {
3009
+ "epoch": 0.9681787406905891,
3010
+ "grad_norm": 0.0017242431640625,
3011
+ "learning_rate": 6.798308540360946e-06,
3012
+ "loss": 0.0,
3013
+ "step": 4290
3014
+ },
3015
+ {
3016
+ "epoch": 0.9704355675919657,
3017
+ "grad_norm": 0.005035400390625,
3018
+ "learning_rate": 6.790757381258024e-06,
3019
+ "loss": 0.0,
3020
+ "step": 4300
3021
+ },
3022
+ {
3023
+ "epoch": 0.9726923944933423,
3024
+ "grad_norm": 0.001739501953125,
3025
+ "learning_rate": 6.783206222155101e-06,
3026
+ "loss": 0.2294,
3027
+ "step": 4310
3028
+ },
3029
+ {
3030
+ "epoch": 0.9749492213947191,
3031
+ "grad_norm": 0.000492095947265625,
3032
+ "learning_rate": 6.775655063052179e-06,
3033
+ "loss": 0.0,
3034
+ "step": 4320
3035
+ },
3036
+ {
3037
+ "epoch": 0.9772060482960957,
3038
+ "grad_norm": 0.004486083984375,
3039
+ "learning_rate": 6.768103903949257e-06,
3040
+ "loss": 0.0,
3041
+ "step": 4330
3042
+ },
3043
+ {
3044
+ "epoch": 0.9794628751974723,
3045
+ "grad_norm": 0.000896453857421875,
3046
+ "learning_rate": 6.760552744846335e-06,
3047
+ "loss": 0.0,
3048
+ "step": 4340
3049
+ },
3050
+ {
3051
+ "epoch": 0.9817197020988491,
3052
+ "grad_norm": 0.01055908203125,
3053
+ "learning_rate": 6.753001585743412e-06,
3054
+ "loss": 0.0,
3055
+ "step": 4350
3056
+ },
3057
+ {
3058
+ "epoch": 0.9839765290002257,
3059
+ "grad_norm": 0.00104522705078125,
3060
+ "learning_rate": 6.7454504266404895e-06,
3061
+ "loss": 0.1874,
3062
+ "step": 4360
3063
+ },
3064
+ {
3065
+ "epoch": 0.9862333559016023,
3066
+ "grad_norm": 0.00069427490234375,
3067
+ "learning_rate": 6.737899267537567e-06,
3068
+ "loss": 0.0005,
3069
+ "step": 4370
3070
+ },
3071
+ {
3072
+ "epoch": 0.988490182802979,
3073
+ "grad_norm": 0.030517578125,
3074
+ "learning_rate": 6.730348108434646e-06,
3075
+ "loss": 0.0,
3076
+ "step": 4380
3077
+ },
3078
+ {
3079
+ "epoch": 0.9907470097043557,
3080
+ "grad_norm": 0.028076171875,
3081
+ "learning_rate": 6.722796949331723e-06,
3082
+ "loss": 0.0001,
3083
+ "step": 4390
3084
+ },
3085
+ {
3086
+ "epoch": 0.9930038366057323,
3087
+ "grad_norm": 0.007171630859375,
3088
+ "learning_rate": 6.7152457902288005e-06,
3089
+ "loss": 0.0,
3090
+ "step": 4400
3091
+ },
3092
+ {
3093
+ "epoch": 0.995260663507109,
3094
+ "grad_norm": 0.00023746490478515625,
3095
+ "learning_rate": 6.707694631125878e-06,
3096
+ "loss": 0.0,
3097
+ "step": 4410
3098
+ },
3099
+ {
3100
+ "epoch": 0.9975174904084857,
3101
+ "grad_norm": 0.00061798095703125,
3102
+ "learning_rate": 6.700143472022956e-06,
3103
+ "loss": 0.0,
3104
+ "step": 4420
3105
+ },
3106
+ {
3107
+ "epoch": 0.9997743173098623,
3108
+ "grad_norm": 0.01312255859375,
3109
+ "learning_rate": 6.692592312920035e-06,
3110
+ "loss": 0.0,
3111
+ "step": 4430
3112
+ }
3113
+ ],
3114
+ "logging_steps": 10,
3115
+ "max_steps": 13293,
3116
+ "num_input_tokens_seen": 0,
3117
+ "num_train_epochs": 3,
3118
+ "save_steps": 500,
3119
+ "stateful_callbacks": {
3120
+ "TrainerControl": {
3121
+ "args": {
3122
+ "should_epoch_stop": false,
3123
+ "should_evaluate": false,
3124
+ "should_log": false,
3125
+ "should_save": true,
3126
+ "should_training_stop": false
3127
+ },
3128
+ "attributes": {}
3129
+ }
3130
+ },
3131
+ "total_flos": 1.6972535855683584e+16,
3132
+ "train_batch_size": 1,
3133
+ "trial_name": null,
3134
+ "trial_params": null
3135
+ }
checkpoint-4431/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:796a84fa762533861d74178663d2c947fb1915fe6d6b1fc474c454eece28dda1
3
+ size 5432
checkpoint-8862/config.json ADDED
@@ -0,0 +1,143 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Phi3ForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "auto_map": {
8
+ "AutoConfig": "microsoft/Phi-4-mini-instruct--configuration_phi3.Phi3Config",
9
+ "AutoModelForCausalLM": "microsoft/Phi-4-mini-instruct--modeling_phi3.Phi3ForCausalLM",
10
+ "AutoTokenizer": "microsoft/Phi-4-mini-instruct--Xenova/gpt-4o"
11
+ },
12
+ "bos_token_id": 199999,
13
+ "embd_pdrop": 0.0,
14
+ "eos_token_id": 199999,
15
+ "full_attn_mod": 1,
16
+ "hidden_act": "silu",
17
+ "hidden_size": 3072,
18
+ "initializer_range": 0.02,
19
+ "intermediate_size": 8192,
20
+ "interpolate_factor": 1,
21
+ "lm_head_bias": false,
22
+ "max_position_embeddings": 131072,
23
+ "mlp_bias": false,
24
+ "model_type": "phi3",
25
+ "num_attention_heads": 24,
26
+ "num_hidden_layers": 32,
27
+ "num_key_value_heads": 8,
28
+ "original_max_position_embeddings": 4096,
29
+ "pad_token_id": 199999,
30
+ "partial_rotary_factor": 0.75,
31
+ "resid_pdrop": 0.0,
32
+ "rms_norm_eps": 1e-05,
33
+ "rope_scaling": {
34
+ "long_factor": [
35
+ 1,
36
+ 1.118320672,
37
+ 1.250641126,
38
+ 1.398617824,
39
+ 1.564103225,
40
+ 1.74916897,
41
+ 1.956131817,
42
+ 2.187582649,
43
+ 2.446418898,
44
+ 2.735880826,
45
+ 3.059592084,
46
+ 3.421605075,
47
+ 3.826451687,
48
+ 4.279200023,
49
+ 4.785517845,
50
+ 5.351743533,
51
+ 5.984965424,
52
+ 6.693110555,
53
+ 7.485043894,
54
+ 8.370679318,
55
+ 9.36110372,
56
+ 10.4687158,
57
+ 11.70738129,
58
+ 13.09260651,
59
+ 14.64173252,
60
+ 16.37415215,
61
+ 18.31155283,
62
+ 20.47818807,
63
+ 22.90118105,
64
+ 25.61086418,
65
+ 28.64115884,
66
+ 32.03,
67
+ 32.1,
68
+ 32.13,
69
+ 32.23,
70
+ 32.6,
71
+ 32.61,
72
+ 32.64,
73
+ 32.66,
74
+ 32.7,
75
+ 32.71,
76
+ 32.93,
77
+ 32.97,
78
+ 33.28,
79
+ 33.49,
80
+ 33.5,
81
+ 44.16,
82
+ 47.77
83
+ ],
84
+ "short_factor": [
85
+ 1.0,
86
+ 1.0,
87
+ 1.0,
88
+ 1.0,
89
+ 1.0,
90
+ 1.0,
91
+ 1.0,
92
+ 1.0,
93
+ 1.0,
94
+ 1.0,
95
+ 1.0,
96
+ 1.0,
97
+ 1.0,
98
+ 1.0,
99
+ 1.0,
100
+ 1.0,
101
+ 1.0,
102
+ 1.0,
103
+ 1.0,
104
+ 1.0,
105
+ 1.0,
106
+ 1.0,
107
+ 1.0,
108
+ 1.0,
109
+ 1.0,
110
+ 1.0,
111
+ 1.0,
112
+ 1.0,
113
+ 1.0,
114
+ 1.0,
115
+ 1.0,
116
+ 1.0,
117
+ 1.0,
118
+ 1.0,
119
+ 1.0,
120
+ 1.0,
121
+ 1.0,
122
+ 1.0,
123
+ 1.0,
124
+ 1.0,
125
+ 1.0,
126
+ 1.0,
127
+ 1.0,
128
+ 1.0,
129
+ 1.0,
130
+ 1.0,
131
+ 1.0,
132
+ 1.0
133
+ ],
134
+ "type": "longrope"
135
+ },
136
+ "rope_theta": 10000.0,
137
+ "sliding_window": 262144,
138
+ "tie_word_embeddings": true,
139
+ "torch_dtype": "bfloat16",
140
+ "transformers_version": "4.50.3",
141
+ "use_cache": true,
142
+ "vocab_size": 200064
143
+ }
checkpoint-8862/generation_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 199999,
4
+ "eos_token_id": [
5
+ 200020,
6
+ 199999
7
+ ],
8
+ "pad_token_id": 199999,
9
+ "transformers_version": "4.50.3"
10
+ }
checkpoint-8862/model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1a6804823fdc84def31c7d9d2a60c886bf340a48e43efda825b4678bdcc71d3
3
+ size 4903637712
checkpoint-8862/model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:475fb050a7dc94e91a93458888bf3a126a0b68cf81379f5d3df3c9bc6408a1e9
3
+ size 2768428504
checkpoint-8862/model.safetensors.index.json ADDED
@@ -0,0 +1,201 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 7672043520
4
+ },
5
+ "weight_map": {
6
+ "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
7
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
8
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
9
+ "model.layers.0.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
10
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
11
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
12
+ "model.layers.0.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
13
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
14
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
15
+ "model.layers.1.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
16
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
17
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
18
+ "model.layers.1.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
19
+ "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
20
+ "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
21
+ "model.layers.10.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
22
+ "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
23
+ "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
24
+ "model.layers.10.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
25
+ "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
26
+ "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
27
+ "model.layers.11.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
28
+ "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
29
+ "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
30
+ "model.layers.11.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
31
+ "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
32
+ "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
33
+ "model.layers.12.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
34
+ "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
35
+ "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
36
+ "model.layers.12.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
37
+ "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
38
+ "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
39
+ "model.layers.13.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
40
+ "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
41
+ "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
42
+ "model.layers.13.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
43
+ "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
44
+ "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
45
+ "model.layers.14.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
46
+ "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
47
+ "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
48
+ "model.layers.14.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
49
+ "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
50
+ "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
51
+ "model.layers.15.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
52
+ "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
53
+ "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
54
+ "model.layers.15.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
55
+ "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
56
+ "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
57
+ "model.layers.16.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
58
+ "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
59
+ "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
60
+ "model.layers.16.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
61
+ "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
62
+ "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
63
+ "model.layers.17.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
64
+ "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
65
+ "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
66
+ "model.layers.17.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
67
+ "model.layers.18.input_layernorm.weight": "model-00002-of-00002.safetensors",
68
+ "model.layers.18.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
69
+ "model.layers.18.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
70
+ "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
71
+ "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
72
+ "model.layers.18.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
73
+ "model.layers.19.input_layernorm.weight": "model-00002-of-00002.safetensors",
74
+ "model.layers.19.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
75
+ "model.layers.19.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
76
+ "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
77
+ "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
78
+ "model.layers.19.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
79
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
80
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
81
+ "model.layers.2.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
82
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
83
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
84
+ "model.layers.2.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
85
+ "model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
86
+ "model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
87
+ "model.layers.20.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
88
+ "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
89
+ "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
90
+ "model.layers.20.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
91
+ "model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
92
+ "model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
93
+ "model.layers.21.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
94
+ "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
95
+ "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
96
+ "model.layers.21.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
97
+ "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
98
+ "model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
99
+ "model.layers.22.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
100
+ "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
101
+ "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
102
+ "model.layers.22.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
103
+ "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
104
+ "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
105
+ "model.layers.23.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
106
+ "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
107
+ "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
108
+ "model.layers.23.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
109
+ "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
110
+ "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
111
+ "model.layers.24.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
112
+ "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
113
+ "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
114
+ "model.layers.24.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
115
+ "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
116
+ "model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
117
+ "model.layers.25.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
118
+ "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
119
+ "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
120
+ "model.layers.25.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
121
+ "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
122
+ "model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
123
+ "model.layers.26.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
124
+ "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
125
+ "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
126
+ "model.layers.26.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
127
+ "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
128
+ "model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
129
+ "model.layers.27.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
130
+ "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
131
+ "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
132
+ "model.layers.27.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
133
+ "model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
134
+ "model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
135
+ "model.layers.28.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
136
+ "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
137
+ "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
138
+ "model.layers.28.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
139
+ "model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
140
+ "model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
141
+ "model.layers.29.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
142
+ "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
143
+ "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
144
+ "model.layers.29.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
145
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
146
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
147
+ "model.layers.3.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
148
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
149
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
150
+ "model.layers.3.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
151
+ "model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
152
+ "model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
153
+ "model.layers.30.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
154
+ "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
155
+ "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
156
+ "model.layers.30.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
157
+ "model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
158
+ "model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
159
+ "model.layers.31.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
160
+ "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
161
+ "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
162
+ "model.layers.31.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
163
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
164
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
165
+ "model.layers.4.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
166
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
167
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
168
+ "model.layers.4.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
169
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
170
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
171
+ "model.layers.5.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
172
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
173
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
174
+ "model.layers.5.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
175
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
176
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
177
+ "model.layers.6.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
178
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
179
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
180
+ "model.layers.6.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
181
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
182
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
183
+ "model.layers.7.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
184
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
185
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
186
+ "model.layers.7.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
187
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
188
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
189
+ "model.layers.8.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
190
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
191
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
192
+ "model.layers.8.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
193
+ "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
194
+ "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
195
+ "model.layers.9.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
196
+ "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
197
+ "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
198
+ "model.layers.9.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
199
+ "model.norm.weight": "model-00002-of-00002.safetensors"
200
+ }
201
+ }
checkpoint-8862/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-8862/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:796a84fa762533861d74178663d2c947fb1915fe6d6b1fc474c454eece28dda1
3
+ size 5432
config.json ADDED
@@ -0,0 +1,143 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Phi3ForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "auto_map": {
8
+ "AutoConfig": "microsoft/Phi-4-mini-instruct--configuration_phi3.Phi3Config",
9
+ "AutoModelForCausalLM": "microsoft/Phi-4-mini-instruct--modeling_phi3.Phi3ForCausalLM",
10
+ "AutoTokenizer": "microsoft/Phi-4-mini-instruct--Xenova/gpt-4o"
11
+ },
12
+ "bos_token_id": 199999,
13
+ "embd_pdrop": 0.0,
14
+ "eos_token_id": 199999,
15
+ "full_attn_mod": 1,
16
+ "hidden_act": "silu",
17
+ "hidden_size": 3072,
18
+ "initializer_range": 0.02,
19
+ "intermediate_size": 8192,
20
+ "interpolate_factor": 1,
21
+ "lm_head_bias": false,
22
+ "max_position_embeddings": 131072,
23
+ "mlp_bias": false,
24
+ "model_type": "phi3",
25
+ "num_attention_heads": 24,
26
+ "num_hidden_layers": 32,
27
+ "num_key_value_heads": 8,
28
+ "original_max_position_embeddings": 4096,
29
+ "pad_token_id": 199999,
30
+ "partial_rotary_factor": 0.75,
31
+ "resid_pdrop": 0.0,
32
+ "rms_norm_eps": 1e-05,
33
+ "rope_scaling": {
34
+ "long_factor": [
35
+ 1,
36
+ 1.118320672,
37
+ 1.250641126,
38
+ 1.398617824,
39
+ 1.564103225,
40
+ 1.74916897,
41
+ 1.956131817,
42
+ 2.187582649,
43
+ 2.446418898,
44
+ 2.735880826,
45
+ 3.059592084,
46
+ 3.421605075,
47
+ 3.826451687,
48
+ 4.279200023,
49
+ 4.785517845,
50
+ 5.351743533,
51
+ 5.984965424,
52
+ 6.693110555,
53
+ 7.485043894,
54
+ 8.370679318,
55
+ 9.36110372,
56
+ 10.4687158,
57
+ 11.70738129,
58
+ 13.09260651,
59
+ 14.64173252,
60
+ 16.37415215,
61
+ 18.31155283,
62
+ 20.47818807,
63
+ 22.90118105,
64
+ 25.61086418,
65
+ 28.64115884,
66
+ 32.03,
67
+ 32.1,
68
+ 32.13,
69
+ 32.23,
70
+ 32.6,
71
+ 32.61,
72
+ 32.64,
73
+ 32.66,
74
+ 32.7,
75
+ 32.71,
76
+ 32.93,
77
+ 32.97,
78
+ 33.28,
79
+ 33.49,
80
+ 33.5,
81
+ 44.16,
82
+ 47.77
83
+ ],
84
+ "short_factor": [
85
+ 1.0,
86
+ 1.0,
87
+ 1.0,
88
+ 1.0,
89
+ 1.0,
90
+ 1.0,
91
+ 1.0,
92
+ 1.0,
93
+ 1.0,
94
+ 1.0,
95
+ 1.0,
96
+ 1.0,
97
+ 1.0,
98
+ 1.0,
99
+ 1.0,
100
+ 1.0,
101
+ 1.0,
102
+ 1.0,
103
+ 1.0,
104
+ 1.0,
105
+ 1.0,
106
+ 1.0,
107
+ 1.0,
108
+ 1.0,
109
+ 1.0,
110
+ 1.0,
111
+ 1.0,
112
+ 1.0,
113
+ 1.0,
114
+ 1.0,
115
+ 1.0,
116
+ 1.0,
117
+ 1.0,
118
+ 1.0,
119
+ 1.0,
120
+ 1.0,
121
+ 1.0,
122
+ 1.0,
123
+ 1.0,
124
+ 1.0,
125
+ 1.0,
126
+ 1.0,
127
+ 1.0,
128
+ 1.0,
129
+ 1.0,
130
+ 1.0,
131
+ 1.0,
132
+ 1.0
133
+ ],
134
+ "type": "longrope"
135
+ },
136
+ "rope_theta": 10000.0,
137
+ "sliding_window": 262144,
138
+ "tie_word_embeddings": true,
139
+ "torch_dtype": "bfloat16",
140
+ "transformers_version": "4.50.3",
141
+ "use_cache": true,
142
+ "vocab_size": 200064
143
+ }
generation_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 199999,
4
+ "eos_token_id": [
5
+ 200020,
6
+ 199999
7
+ ],
8
+ "pad_token_id": 199999,
9
+ "transformers_version": "4.50.3"
10
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a95f7cfd274cc1286e46a9d1713da4ddf9b90c02051478cc7a095e6a862b68b1
3
+ size 4903637712
model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cdc26676eeb2fcb18b5e7aad475c8267d2a63be86e86b65f7e5b28f1a04742c6
3
+ size 2768428504
model.safetensors.index.json ADDED
@@ -0,0 +1,201 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 7672043520
4
+ },
5
+ "weight_map": {
6
+ "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
7
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
8
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
9
+ "model.layers.0.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
10
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
11
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
12
+ "model.layers.0.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
13
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
14
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
15
+ "model.layers.1.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
16
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
17
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
18
+ "model.layers.1.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
19
+ "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
20
+ "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
21
+ "model.layers.10.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
22
+ "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
23
+ "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
24
+ "model.layers.10.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
25
+ "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
26
+ "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
27
+ "model.layers.11.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
28
+ "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
29
+ "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
30
+ "model.layers.11.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
31
+ "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
32
+ "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
33
+ "model.layers.12.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
34
+ "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
35
+ "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
36
+ "model.layers.12.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
37
+ "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
38
+ "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
39
+ "model.layers.13.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
40
+ "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
41
+ "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
42
+ "model.layers.13.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
43
+ "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
44
+ "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
45
+ "model.layers.14.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
46
+ "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
47
+ "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
48
+ "model.layers.14.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
49
+ "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
50
+ "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
51
+ "model.layers.15.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
52
+ "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
53
+ "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
54
+ "model.layers.15.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
55
+ "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
56
+ "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
57
+ "model.layers.16.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
58
+ "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
59
+ "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
60
+ "model.layers.16.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
61
+ "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
62
+ "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
63
+ "model.layers.17.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
64
+ "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
65
+ "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
66
+ "model.layers.17.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
67
+ "model.layers.18.input_layernorm.weight": "model-00002-of-00002.safetensors",
68
+ "model.layers.18.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
69
+ "model.layers.18.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
70
+ "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
71
+ "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
72
+ "model.layers.18.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
73
+ "model.layers.19.input_layernorm.weight": "model-00002-of-00002.safetensors",
74
+ "model.layers.19.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
75
+ "model.layers.19.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
76
+ "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
77
+ "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
78
+ "model.layers.19.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
79
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
80
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
81
+ "model.layers.2.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
82
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
83
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
84
+ "model.layers.2.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
85
+ "model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
86
+ "model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
87
+ "model.layers.20.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
88
+ "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
89
+ "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
90
+ "model.layers.20.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
91
+ "model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
92
+ "model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
93
+ "model.layers.21.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
94
+ "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
95
+ "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
96
+ "model.layers.21.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
97
+ "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
98
+ "model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
99
+ "model.layers.22.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
100
+ "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
101
+ "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
102
+ "model.layers.22.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
103
+ "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
104
+ "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
105
+ "model.layers.23.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
106
+ "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
107
+ "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
108
+ "model.layers.23.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
109
+ "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
110
+ "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
111
+ "model.layers.24.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
112
+ "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
113
+ "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
114
+ "model.layers.24.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
115
+ "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
116
+ "model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
117
+ "model.layers.25.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
118
+ "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
119
+ "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
120
+ "model.layers.25.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
121
+ "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
122
+ "model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
123
+ "model.layers.26.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
124
+ "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
125
+ "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
126
+ "model.layers.26.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
127
+ "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
128
+ "model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
129
+ "model.layers.27.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
130
+ "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
131
+ "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
132
+ "model.layers.27.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
133
+ "model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
134
+ "model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
135
+ "model.layers.28.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
136
+ "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
137
+ "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
138
+ "model.layers.28.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
139
+ "model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
140
+ "model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
141
+ "model.layers.29.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
142
+ "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
143
+ "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
144
+ "model.layers.29.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
145
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
146
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
147
+ "model.layers.3.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
148
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
149
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
150
+ "model.layers.3.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
151
+ "model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
152
+ "model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
153
+ "model.layers.30.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
154
+ "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
155
+ "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
156
+ "model.layers.30.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
157
+ "model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
158
+ "model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
159
+ "model.layers.31.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
160
+ "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
161
+ "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
162
+ "model.layers.31.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
163
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
164
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
165
+ "model.layers.4.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
166
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
167
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
168
+ "model.layers.4.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
169
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
170
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
171
+ "model.layers.5.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
172
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
173
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
174
+ "model.layers.5.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
175
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
176
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
177
+ "model.layers.6.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
178
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
179
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
180
+ "model.layers.6.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
181
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
182
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
183
+ "model.layers.7.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
184
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
185
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
186
+ "model.layers.7.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
187
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
188
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
189
+ "model.layers.8.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
190
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
191
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
192
+ "model.layers.8.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
193
+ "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
194
+ "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
195
+ "model.layers.9.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
196
+ "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
197
+ "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
198
+ "model.layers.9.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
199
+ "model.norm.weight": "model-00002-of-00002.safetensors"
200
+ }
201
+ }
runs/Apr01_13-43-26_f952690d2a16/events.out.tfevents.1743515006.f952690d2a16 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d09a29762515c8994be02c5ae41f02b6f8681d274f769db93947272c71bd09d
3
+ size 7012
runs/Apr01_13-44-23_f952690d2a16/events.out.tfevents.1743515063.f952690d2a16 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:207b031dcdd6fa6daf9da37b8ad8250c6a25456bacbdd8ec4b262f277358aec5
3
+ size 7012
runs/Apr01_13-46-10_f952690d2a16/events.out.tfevents.1743515171.f952690d2a16 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d63596c1d0c5a80f8055560400da8a12d3121ba415b70f0cb3f8894d6bee463
3
+ size 7012
runs/Apr01_13-49-28_f952690d2a16/events.out.tfevents.1743515368.f952690d2a16 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dde4011baf09a123ff1ad6e2fb750ef706e22723fdc70714c150770e9744f3c3
3
+ size 7012
runs/Apr01_13-50-10_f952690d2a16/events.out.tfevents.1743515410.f952690d2a16 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6085bfb7715bc5cc623fc4e1237aa5596ef326d4c063f96259f3b6dd92c3e590
3
+ size 7012
runs/Apr01_13-51-48_f952690d2a16/events.out.tfevents.1743515508.f952690d2a16 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:30851a41d54c8b930e7aacb138ed7c63725010cba5e8d18ee708b6347bad41b0
3
+ size 7634
runs/Apr01_14-12-59_f952690d2a16/events.out.tfevents.1743516780.f952690d2a16 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58cc608fa4f77290bd633c29d0ea8ab3952478c91f387509b72ffc6abe57f6a0
3
+ size 287738
runs/Apr01_16-49-22_f952690d2a16/events.out.tfevents.1743526162.f952690d2a16 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:83e689e78440c6fc5089e76f75e8a3f3b4c19d2086551406d6eb29ba34a1186e
3
+ size 7013
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|endoftext|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|endoftext|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<|endoftext|>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:382cc235b56c725945e149cc25f191da667c836655efd0857b004320e90e91ea
3
+ size 15524095
tokenizer_config.json ADDED
@@ -0,0 +1,112 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": false,
5
+ "added_tokens_decoder": {
6
+ "199999": {
7
+ "content": "<|endoftext|>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "200018": {
15
+ "content": "<|endofprompt|>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "200019": {
23
+ "content": "<|assistant|>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": true,
27
+ "single_word": false,
28
+ "special": true
29
+ },
30
+ "200020": {
31
+ "content": "<|end|>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": true,
35
+ "single_word": false,
36
+ "special": true
37
+ },
38
+ "200021": {
39
+ "content": "<|user|>",
40
+ "lstrip": false,
41
+ "normalized": false,
42
+ "rstrip": true,
43
+ "single_word": false,
44
+ "special": true
45
+ },
46
+ "200022": {
47
+ "content": "<|system|>",
48
+ "lstrip": false,
49
+ "normalized": false,
50
+ "rstrip": true,
51
+ "single_word": false,
52
+ "special": true
53
+ },
54
+ "200023": {
55
+ "content": "<|tool|>",
56
+ "lstrip": false,
57
+ "normalized": false,
58
+ "rstrip": true,
59
+ "single_word": false,
60
+ "special": false
61
+ },
62
+ "200024": {
63
+ "content": "<|/tool|>",
64
+ "lstrip": false,
65
+ "normalized": false,
66
+ "rstrip": true,
67
+ "single_word": false,
68
+ "special": false
69
+ },
70
+ "200025": {
71
+ "content": "<|tool_call|>",
72
+ "lstrip": false,
73
+ "normalized": false,
74
+ "rstrip": true,
75
+ "single_word": false,
76
+ "special": false
77
+ },
78
+ "200026": {
79
+ "content": "<|/tool_call|>",
80
+ "lstrip": false,
81
+ "normalized": false,
82
+ "rstrip": true,
83
+ "single_word": false,
84
+ "special": false
85
+ },
86
+ "200027": {
87
+ "content": "<|tool_response|>",
88
+ "lstrip": false,
89
+ "normalized": false,
90
+ "rstrip": true,
91
+ "single_word": false,
92
+ "special": false
93
+ },
94
+ "200028": {
95
+ "content": "<|tag|>",
96
+ "lstrip": false,
97
+ "normalized": false,
98
+ "rstrip": true,
99
+ "single_word": false,
100
+ "special": true
101
+ }
102
+ },
103
+ "bos_token": "<|endoftext|>",
104
+ "chat_template": "{% for message in messages %}{% if message['role'] == 'system' and 'tools' in message and message['tools'] is not none %}{{ '<|' + message['role'] + '|>' + message['content'] + '<|tool|>' + message['tools'] + '<|/tool|>' + '<|end|>' }}{% else %}{{ '<|' + message['role'] + '|>' + message['content'] + '<|end|>' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>' }}{% else %}{{ eos_token }}{% endif %}",
105
+ "clean_up_tokenization_spaces": false,
106
+ "eos_token": "<|endoftext|>",
107
+ "extra_special_tokens": {},
108
+ "model_max_length": 131072,
109
+ "pad_token": "<|endoftext|>",
110
+ "tokenizer_class": "GPT2Tokenizer",
111
+ "unk_token": "<|endoftext|>"
112
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:796a84fa762533861d74178663d2c947fb1915fe6d6b1fc474c454eece28dda1
3
+ size 5432
vocab.json ADDED
The diff for this file is too large to render. See raw diff