AiAF commited on
Commit
ca3a016
·
verified ·
1 Parent(s): 7385171

Training in progress, step 50

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: google/gemma-2-2b-it
3
+ library_name: peft
4
+ pipeline_tag: text-generation
5
+ tags:
6
+ - axolotl
7
+ - base_model:adapter:google/gemma-2-2b-it
8
+ - lora
9
+ - transformers
10
+ ---
11
+ ### Framework versions
12
+
13
+ - PEFT 0.17.1
adapter_config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "google/gemma-2-2b-it",
5
+ "bias": "none",
6
+ "corda_config": null,
7
+ "eva_config": null,
8
+ "exclude_modules": null,
9
+ "fan_in_fan_out": null,
10
+ "inference_mode": true,
11
+ "init_lora_weights": true,
12
+ "layer_replication": null,
13
+ "layers_pattern": null,
14
+ "layers_to_transform": null,
15
+ "loftq_config": {},
16
+ "lora_alpha": 128,
17
+ "lora_bias": false,
18
+ "lora_dropout": 0.05,
19
+ "megatron_config": null,
20
+ "megatron_core": "megatron.core",
21
+ "modules_to_save": null,
22
+ "peft_type": "LORA",
23
+ "qalora_group_size": 16,
24
+ "r": 64,
25
+ "rank_pattern": {},
26
+ "revision": null,
27
+ "target_modules": [
28
+ "k_proj",
29
+ "o_proj",
30
+ "gate_proj",
31
+ "down_proj",
32
+ "q_proj",
33
+ "v_proj",
34
+ "up_proj"
35
+ ],
36
+ "target_parameters": [],
37
+ "task_type": "CAUSAL_LM",
38
+ "trainable_token_indices": null,
39
+ "use_dora": false,
40
+ "use_qalora": false,
41
+ "use_rslora": false
42
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f732f117c056d41c8b4043c91065e7c8dbd15fcd6f53c69b51bbbb395846336c
3
+ size 332316480
chat_template.jinja ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {{ bos_token }}{% if messages[0]['role'] == 'system' %}{{ raise_exception('System role not supported') }}{% endif %}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if (message['role'] == 'assistant') %}{% set role = 'model' %}{% else %}{% set role = message['role'] %}{% endif %}{{ '<start_of_turn>' + role + '
2
+ ' + message['content'] | trim + '<end_of_turn>
3
+ ' }}{% endfor %}{% if add_generation_prompt %}{{'<start_of_turn>model
4
+ '}}{% endif %}
config.json ADDED
@@ -0,0 +1,75 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Gemma2ForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "attn_logit_softcapping": 50.0,
8
+ "bos_token_id": 2,
9
+ "cache_implementation": "hybrid",
10
+ "dtype": "bfloat16",
11
+ "eos_token_id": 1,
12
+ "final_logit_softcapping": 30.0,
13
+ "head_dim": 256,
14
+ "hidden_act": "gelu_pytorch_tanh",
15
+ "hidden_activation": "gelu_pytorch_tanh",
16
+ "hidden_size": 2304,
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 9216,
19
+ "layer_types": [
20
+ "sliding_attention",
21
+ "full_attention",
22
+ "sliding_attention",
23
+ "full_attention",
24
+ "sliding_attention",
25
+ "full_attention",
26
+ "sliding_attention",
27
+ "full_attention",
28
+ "sliding_attention",
29
+ "full_attention",
30
+ "sliding_attention",
31
+ "full_attention",
32
+ "sliding_attention",
33
+ "full_attention",
34
+ "sliding_attention",
35
+ "full_attention",
36
+ "sliding_attention",
37
+ "full_attention",
38
+ "sliding_attention",
39
+ "full_attention",
40
+ "sliding_attention",
41
+ "full_attention",
42
+ "sliding_attention",
43
+ "full_attention",
44
+ "sliding_attention",
45
+ "full_attention"
46
+ ],
47
+ "max_position_embeddings": 8192,
48
+ "model_type": "gemma2",
49
+ "num_attention_heads": 8,
50
+ "num_hidden_layers": 26,
51
+ "num_key_value_heads": 4,
52
+ "pad_token_id": 0,
53
+ "quantization_config": {
54
+ "_load_in_4bit": true,
55
+ "_load_in_8bit": false,
56
+ "bnb_4bit_compute_dtype": "bfloat16",
57
+ "bnb_4bit_quant_storage": "bfloat16",
58
+ "bnb_4bit_quant_type": "nf4",
59
+ "bnb_4bit_use_double_quant": true,
60
+ "llm_int8_enable_fp32_cpu_offload": false,
61
+ "llm_int8_has_fp16_weight": false,
62
+ "llm_int8_skip_modules": null,
63
+ "llm_int8_threshold": 6.0,
64
+ "load_in_4bit": true,
65
+ "load_in_8bit": false,
66
+ "quant_method": "bitsandbytes"
67
+ },
68
+ "query_pre_attn_scalar": 256,
69
+ "rms_norm_eps": 1e-06,
70
+ "rope_theta": 10000.0,
71
+ "sliding_window": 4096,
72
+ "transformers_version": "4.57.0",
73
+ "use_cache": false,
74
+ "vocab_size": 256000
75
+ }
debug.log ADDED
@@ -0,0 +1,703 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
0
  0%| | 0/1000 [00:00<?, ?it/s][2025-10-18 19:02:46,619] [INFO] [axolotl.core.trainers.base.evaluate:376] [PID:42363] Running evaluation step...
 
 
 
 
 
 
 
1
  0%| | 0/179 [00:00<?, ?it/s]
 
2
  1%|▎ | 2/179 [00:00<00:21, 8.31it/s]
 
3
  2%|▍ | 3/179 [00:00<00:35, 4.96it/s]
 
4
  2%|▌ | 4/179 [00:00<00:42, 4.11it/s]
 
5
  3%|▋ | 5/179 [00:01<01:00, 2.89it/s]
 
6
  3%|▊ | 6/179 [00:01<00:56, 3.06it/s]
 
7
  4%|▉ | 7/179 [00:02<00:55, 3.07it/s]
 
8
  4%|█ | 8/179 [00:02<00:54, 3.11it/s]
 
9
  5%|█▏ | 9/179 [00:02<01:05, 2.59it/s]
 
10
  6%|█▏ | 10/179 [00:03<01:00, 2.80it/s]
 
11
  6%|█▎ | 11/179 [00:03<00:57, 2.90it/s]
 
12
  7%|█▍ | 12/179 [00:03<00:55, 2.99it/s]
 
13
  7%|█▌ | 13/179 [00:04<01:05, 2.55it/s]
 
14
  8%|█▋ | 14/179 [00:04<00:59, 2.78it/s]
 
15
  8%|█▊ | 15/179 [00:04<00:56, 2.89it/s]
 
16
  9%|█▉ | 16/179 [00:05<00:54, 2.97it/s]
 
17
  9%|██ | 17/179 [00:05<01:03, 2.54it/s]
 
18
  10%|██▏ | 18/179 [00:06<00:58, 2.77it/s]
 
19
  11%|██▎ | 19/179 [00:06<00:55, 2.89it/s]
 
20
  11%|██▍ | 20/179 [00:06<00:53, 2.97it/s]
 
21
  12%|██▌ | 21/179 [00:07<01:02, 2.55it/s]
 
22
  12%|██▋ | 22/179 [00:07<00:56, 2.77it/s]
 
23
  13%|██▊ | 23/179 [00:07<00:54, 2.89it/s]
 
24
  13%|██▉ | 24/179 [00:08<00:52, 2.97it/s]
 
25
  14%|███ | 25/179 [00:08<01:00, 2.54it/s]
 
26
  15%|███▏ | 26/179 [00:08<00:55, 2.77it/s]
 
27
  15%|███▎ | 27/179 [00:09<00:52, 2.88it/s]
 
28
  16%|███▍ | 28/179 [00:09<00:50, 2.96it/s]
 
29
  16%|███▌ | 29/179 [00:10<00:59, 2.54it/s]
 
30
  17%|███▋ | 30/179 [00:10<00:53, 2.77it/s]
 
31
  17%|███▊ | 31/179 [00:10<00:51, 2.87it/s]
 
32
  18%|███▉ | 32/179 [00:10<00:49, 2.96it/s]
 
33
  18%|████ | 33/179 [00:11<00:57, 2.52it/s]
 
34
  19%|████▏ | 34/179 [00:11<00:52, 2.75it/s]
 
35
  20%|████▎ | 35/179 [00:12<00:50, 2.87it/s]
 
36
  20%|████▍ | 36/179 [00:12<00:48, 2.96it/s]
 
37
  21%|████▌ | 37/179 [00:12<00:56, 2.53it/s]
 
38
  21%|████▋ | 38/179 [00:13<00:50, 2.77it/s]
 
39
  22%|████▊ | 39/179 [00:13<00:48, 2.88it/s]
 
40
  22%|████▉ | 40/179 [00:13<00:46, 2.97it/s]
 
41
  23%|█████ | 41/179 [00:14<00:54, 2.54it/s]
 
42
  23%|█████▏ | 42/179 [00:14<00:49, 2.78it/s]
 
43
  24%|█████▎ | 43/179 [00:14<00:46, 2.90it/s]
 
44
  25%|█████▍ | 44/179 [00:15<00:45, 2.97it/s]
 
45
  25%|█████▌ | 45/179 [00:15<00:53, 2.53it/s]
 
46
  26%|█████▋ | 46/179 [00:16<00:48, 2.77it/s]
 
47
  26%|█████▊ | 47/179 [00:16<00:45, 2.89it/s]
 
48
  27%|█████▉ | 48/179 [00:16<00:44, 2.96it/s]
 
49
  27%|██████ | 49/179 [00:17<00:51, 2.53it/s]
 
50
  28%|██████▏ | 50/179 [00:17<00:46, 2.76it/s]
 
51
  28%|██████▎ | 51/179 [00:17<00:44, 2.87it/s]
 
52
  29%|██████▍ | 52/179 [00:18<00:42, 2.96it/s]
 
53
  30%|██████▌ | 53/179 [00:18<00:49, 2.52it/s]
 
54
  30%|██████▋ | 54/179 [00:19<00:45, 2.76it/s]
 
55
  31%|██████▊ | 55/179 [00:19<00:43, 2.88it/s]
 
56
  31%|██████▉ | 56/179 [00:19<00:41, 2.96it/s]
 
57
  32%|███████ | 57/179 [00:20<00:48, 2.54it/s]
 
58
  32%|███████▏ | 58/179 [00:20<00:43, 2.77it/s]
 
59
  33%|███████▎ | 59/179 [00:20<00:41, 2.87it/s]
 
60
  34%|███████▎ | 60/179 [00:21<00:40, 2.94it/s]
 
61
  34%|███████▍ | 61/179 [00:21<00:46, 2.52it/s]
 
62
  35%|███████▌ | 62/179 [00:21<00:42, 2.74it/s]
 
63
  35%|███████▋ | 63/179 [00:22<00:40, 2.86it/s]
 
64
  36%|███████▊ | 64/179 [00:22<00:39, 2.95it/s]
 
65
  36%|███████▉ | 65/179 [00:23<00:45, 2.52it/s]
 
66
  37%|████████ | 66/179 [00:23<00:41, 2.75it/s]
 
67
  37%|████████▏ | 67/179 [00:23<00:39, 2.85it/s]
 
68
  38%|████████▎ | 68/179 [00:23<00:37, 2.93it/s]
 
69
  39%|████████▍ | 69/179 [00:24<00:44, 2.50it/s]
 
70
  39%|████████▌ | 70/179 [00:24<00:39, 2.75it/s]
 
71
  40%|████████▋ | 71/179 [00:25<00:37, 2.85it/s]
 
72
  40%|████████▊ | 72/179 [00:25<00:36, 2.94it/s]
 
73
  41%|████████▉ | 73/179 [00:25<00:42, 2.51it/s]
 
74
  41%|█████████ | 74/179 [00:26<00:38, 2.74it/s]
 
75
  42%|█████████▏ | 75/179 [00:26<00:36, 2.87it/s]
 
76
  42%|█████████▎ | 76/179 [00:26<00:34, 2.94it/s]
 
77
  43%|█████████▍ | 77/179 [00:27<00:42, 2.38it/s]
 
78
  44%|█████████▌ | 78/179 [00:27<00:38, 2.63it/s]
 
79
  44%|█████████▋ | 79/179 [00:28<00:36, 2.75it/s]
 
80
  45%|█████████▊ | 80/179 [00:28<00:34, 2.85it/s]
 
81
  45%|█████████▉ | 81/179 [00:28<00:40, 2.43it/s]
 
82
  46%|██████████ | 82/179 [00:29<00:36, 2.68it/s]
 
83
  46%|██████████▏ | 83/179 [00:29<00:34, 2.80it/s]
 
84
  47%|██████████▎ | 84/179 [00:29<00:33, 2.88it/s]
 
85
  47%|██████████▍ | 85/179 [00:30<00:37, 2.49it/s]
 
86
  48%|██████████▌ | 86/179 [00:30<00:33, 2.74it/s]
 
87
  49%|██████████▋ | 87/179 [00:31<00:32, 2.86it/s]
 
88
  49%|██████████▊ | 88/179 [00:31<00:30, 2.95it/s]
 
89
  50%|██████████▉ | 89/179 [00:31<00:35, 2.53it/s]
 
90
  50%|███████████ | 90/179 [00:32<00:32, 2.76it/s]
 
91
  51%|███████████▏ | 91/179 [00:32<00:30, 2.87it/s]
 
92
  51%|███████████▎ | 92/179 [00:32<00:29, 2.95it/s]
 
93
  52%|███████████▍ | 93/179 [00:33<00:34, 2.52it/s]
 
94
  53%|███████████▌ | 94/179 [00:33<00:30, 2.76it/s]
 
95
  53%|███████████▋ | 95/179 [00:33<00:29, 2.88it/s]
 
96
  54%|███████████▊ | 96/179 [00:34<00:28, 2.96it/s]
 
97
  54%|███████████▉ | 97/179 [00:34<00:32, 2.53it/s]
 
98
  55%|████████████ | 98/179 [00:35<00:29, 2.77it/s]
 
99
  55%|████████████▏ | 99/179 [00:35<00:27, 2.88it/s]
 
100
  56%|███████████▋ | 100/179 [00:35<00:26, 2.94it/s]
 
101
  56%|███████████▊ | 101/179 [00:36<00:30, 2.52it/s]
 
102
  57%|███████████▉ | 102/179 [00:36<00:28, 2.75it/s]
 
103
  58%|████████████ | 103/179 [00:36<00:26, 2.86it/s]
 
104
  58%|████████████▏ | 104/179 [00:37<00:25, 2.94it/s]
 
105
  59%|████████████▎ | 105/179 [00:37<00:29, 2.51it/s]
 
106
  59%|████████████▍ | 106/179 [00:37<00:26, 2.75it/s]
 
107
  60%|████████████▌ | 107/179 [00:38<00:25, 2.84it/s]
 
108
  60%|████████████▋ | 108/179 [00:38<00:24, 2.93it/s]
 
109
  61%|████████████▊ | 109/179 [00:39<00:27, 2.51it/s]
 
110
  61%|████████████▉ | 110/179 [00:39<00:25, 2.72it/s]
 
111
  62%|█████████████ | 111/179 [00:39<00:23, 2.85it/s]
 
112
  63%|█████████████▏ | 112/179 [00:40<00:22, 2.92it/s]
 
113
  63%|█████████████▎ | 113/179 [00:40<00:26, 2.52it/s]
 
114
  64%|█████████████▎ | 114/179 [00:40<00:23, 2.74it/s]
 
115
  64%|█████████████▍ | 115/179 [00:41<00:22, 2.86it/s]
 
116
  65%|█████████████▌ | 116/179 [00:41<00:21, 2.93it/s]
 
117
  65%|█████████████▋ | 117/179 [00:42<00:24, 2.51it/s]
 
118
  66%|█████████████▊ | 118/179 [00:42<00:22, 2.74it/s]
 
119
  66%|█████████████▉ | 119/179 [00:42<00:21, 2.84it/s]
 
120
  67%|██████████████ | 120/179 [00:42<00:20, 2.94it/s]
 
121
  68%|██████████████▏ | 121/179 [00:43<00:23, 2.52it/s]
 
122
  68%|██████████████▎ | 122/179 [00:43<00:20, 2.75it/s]
 
123
  69%|██████████████▍ | 123/179 [00:44<00:19, 2.87it/s]
 
124
  69%|██████████████▌ | 124/179 [00:44<00:18, 2.95it/s]
 
125
  70%|██████████████▋ | 125/179 [00:44<00:21, 2.53it/s]
 
126
  70%|██████████████▊ | 126/179 [00:45<00:19, 2.76it/s]
 
127
  71%|██████████████▉ | 127/179 [00:45<00:18, 2.88it/s]
 
128
  72%|███████████████ | 128/179 [00:45<00:17, 2.95it/s]
 
129
  72%|███████████████▏ | 129/179 [00:46<00:19, 2.51it/s]
 
130
  73%|███████████████▎ | 130/179 [00:46<00:17, 2.73it/s]
 
131
  73%|███████████████▎ | 131/179 [00:46<00:16, 2.83it/s]
 
132
  74%|███████████████▍ | 132/179 [00:47<00:16, 2.91it/s]
 
133
  74%|███████████████▌ | 133/179 [00:47<00:18, 2.49it/s]
 
134
  75%|███████████████▋ | 134/179 [00:48<00:16, 2.72it/s]
 
135
  75%|███████████████▊ | 135/179 [00:48<00:15, 2.84it/s]
 
136
  76%|███████████████▉ | 136/179 [00:48<00:14, 2.93it/s]
 
137
  77%|████████████████ | 137/179 [00:49<00:16, 2.51it/s]
 
138
  77%|████████████████▏ | 138/179 [00:49<00:14, 2.75it/s]
 
139
  78%|████████████████▎ | 139/179 [00:49<00:14, 2.85it/s]
 
140
  78%|████████████████▍ | 140/179 [00:50<00:13, 2.93it/s]
 
141
  79%|████████████████▌ | 141/179 [00:50<00:15, 2.50it/s]
 
142
  79%|████████████████▋ | 142/179 [00:51<00:13, 2.74it/s]
 
143
  80%|████████████████▊ | 143/179 [00:51<00:12, 2.85it/s]
 
144
  80%|████████████████▉ | 144/179 [00:51<00:11, 2.93it/s]
 
145
  81%|█████████████████ | 145/179 [00:52<00:13, 2.50it/s]
 
146
  82%|█████████████████▏ | 146/179 [00:52<00:12, 2.74it/s]
 
147
  82%|█████████████████▏ | 147/179 [00:52<00:11, 2.85it/s]
 
148
  83%|█████████████████▎ | 148/179 [00:53<00:10, 2.94it/s]
 
149
  83%|█████████████████▍ | 149/179 [00:53<00:11, 2.52it/s]
 
150
  84%|█████████████████▌ | 150/179 [00:53<00:10, 2.74it/s]
 
151
  84%|█████████████████▋ | 151/179 [00:54<00:09, 2.84it/s]
 
152
  85%|█████████████████▊ | 152/179 [00:54<00:09, 2.94it/s]
 
153
  85%|█████████████████▉ | 153/179 [00:55<00:10, 2.52it/s]
 
154
  86%|██████████████████ | 154/179 [00:55<00:09, 2.76it/s]
 
155
  87%|██████████████████▏ | 155/179 [00:55<00:08, 2.87it/s]
 
156
  87%|██████████████████▎ | 156/179 [00:56<00:07, 2.93it/s]
 
157
  88%|██████████████████▍ | 157/179 [00:56<00:08, 2.51it/s]
 
158
  88%|██████████████████▌ | 158/179 [00:56<00:07, 2.73it/s]
 
159
  89%|██████████████████▋ | 159/179 [00:57<00:07, 2.85it/s]
 
160
  89%|██████████████████▊ | 160/179 [00:57<00:06, 2.94it/s]
 
161
  90%|██████████████████▉ | 161/179 [00:58<00:07, 2.51it/s]
 
162
  91%|███████████████████ | 162/179 [00:58<00:06, 2.75it/s]
 
163
  91%|███████████████████ | 163/179 [00:58<00:05, 2.86it/s]
 
164
  92%|███████████████████▏ | 164/179 [00:58<00:05, 2.93it/s]
 
165
  92%|███████████████████▎ | 165/179 [00:59<00:05, 2.51it/s]
 
166
  93%|███████████████████▍ | 166/179 [00:59<00:04, 2.72it/s]
 
167
  93%|███████████████████▌ | 167/179 [01:00<00:04, 2.84it/s]
 
168
  94%|███████████████████▋ | 168/179 [01:00<00:03, 2.92it/s]
 
169
  94%|███████████████████▊ | 169/179 [01:00<00:03, 2.50it/s]
 
170
  95%|███████████████████▉ | 170/179 [01:01<00:03, 2.73it/s]
 
171
  96%|████████████████████ | 171/179 [01:01<00:02, 2.83it/s]
 
172
  96%|████████████████████▏| 172/179 [01:01<00:02, 2.91it/s]
 
173
  97%|████████████████████▎| 173/179 [01:02<00:02, 2.49it/s]
 
174
  97%|████████████████████▍| 174/179 [01:02<00:01, 2.72it/s]
 
175
  98%|████████████████████▌| 175/179 [01:03<00:01, 2.83it/s]
 
176
  98%|████████████████████▋| 176/179 [01:03<00:01, 2.91it/s]
 
177
  99%|████████████████████▊| 177/179 [01:03<00:00, 2.50it/s]
 
178
  99%|████████████████████▉| 178/179 [01:04<00:00, 2.72it/s]
 
179
 
 
180
 
 
181
  0%| | 0/1000 [01:14<?, ?it/s]
 
 
182
  [2025-10-18 19:04:31,800] [INFO] [axolotl.utils.data.wrappers.get_dataset_wrapper:87] [PID:42528] Loading dataset: AiAF/conversations with base_type: chat_template and prompt_style: None
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
183
  0%| | 1/1000 [35:40<594:06:42, 2140.94s/it]
184
 
 
185
  0%| | 1/1000 [35:40<594:06:42, 2140.94s/it]
186
  0%| | 2/1000 [35:48<245:35:41, 885.91s/it]
187
 
 
188
  0%| | 2/1000 [35:48<245:35:41, 885.91s/it]
189
  0%| | 3/1000 [35:55<134:15:37, 484.79s/it]
190
 
 
191
  0%| | 3/1000 [35:55<134:15:37, 484.79s/it]
192
  0%| | 4/1000 [36:03<81:59:23, 296.35s/it]
193
 
 
194
  0%| | 4/1000 [36:03<81:59:23, 296.35s/it]
195
  0%| | 5/1000 [36:10<53:07:06, 192.19s/it]
196
 
 
197
  0%| | 5/1000 [36:10<53:07:06, 192.19s/it]
198
  1%| | 6/1000 [36:18<35:43:34, 129.39s/it]
199
 
 
200
  1%| | 6/1000 [36:18<35:43:34, 129.39s/it]
201
  1%|▏ | 7/1000 [36:25<24:42:15, 89.56s/it]
202
 
 
203
  1%|▏ | 7/1000 [36:25<24:42:15, 89.56s/it]
204
  1%|▏ | 8/1000 [36:33<17:29:08, 63.46s/it]
205
 
 
206
  1%|▏ | 8/1000 [36:33<17:29:08, 63.46s/it]
207
  1%|▏ | 9/1000 [36:40<12:39:30, 45.98s/it]
208
 
 
209
  1%|▏ | 9/1000 [36:40<12:39:30, 45.98s/it]
210
  1%|▏ | 10/1000 [36:48<9:23:13, 34.13s/it]
211
 
 
212
  1%|▏ | 10/1000 [36:48<9:23:13, 34.13s/it]
213
  1%|▏ | 11/1000 [36:56<7:08:45, 26.01s/it]
214
 
 
215
  1%|▏ | 11/1000 [36:56<7:08:45, 26.01s/it]
216
  1%|▏ | 12/1000 [37:03<5:35:55, 20.40s/it]
217
 
 
218
  1%|▏ | 12/1000 [37:03<5:35:55, 20.40s/it]
219
  1%|▏ | 13/1000 [37:11<4:31:56, 16.53s/it]
220
 
 
221
  1%|▏ | 13/1000 [37:11<4:31:56, 16.53s/it]
222
  1%|▎ | 14/1000 [37:18<3:47:27, 13.84s/it]
223
 
 
224
  1%|▎ | 14/1000 [37:18<3:47:27, 13.84s/it]
225
  2%|▎ | 15/1000 [37:26<3:16:31, 11.97s/it]
226
 
 
227
  2%|▎ | 15/1000 [37:26<3:16:31, 11.97s/it]
228
  2%|▎ | 16/1000 [37:34<2:55:09, 10.68s/it]
229
 
 
230
  2%|▎ | 16/1000 [37:34<2:55:09, 10.68s/it]
231
  2%|▎ | 17/1000 [37:41<2:40:00, 9.77s/it]
232
 
 
233
  2%|▎ | 17/1000 [37:41<2:40:00, 9.77s/it]
234
  2%|▎ | 18/1000 [37:49<2:29:38, 9.14s/it]
235
 
 
236
  2%|▎ | 18/1000 [37:49<2:29:38, 9.14s/it]
237
  2%|▎ | 19/1000 [37:57<2:22:16, 8.70s/it]
238
 
 
239
  2%|▎ | 19/1000 [37:57<2:22:16, 8.70s/it]
240
  2%|▍ | 20/1000 [38:04<2:17:12, 8.40s/it]
241
 
 
242
  2%|▍ | 20/1000 [38:04<2:17:12, 8.40s/it]
243
  2%|▍ | 21/1000 [38:12<2:13:42, 8.19s/it]
244
 
 
245
  2%|▍ | 21/1000 [38:12<2:13:42, 8.19s/it]
246
  2%|▍ | 22/1000 [38:20<2:11:07, 8.04s/it]
247
 
 
248
  2%|▍ | 22/1000 [38:20<2:11:07, 8.04s/it]
249
  2%|▍ | 23/1000 [38:28<2:09:16, 7.94s/it]
250
 
 
251
  2%|▍ | 23/1000 [38:28<2:09:16, 7.94s/it]
252
  2%|▍ | 24/1000 [38:35<2:07:55, 7.86s/it]
253
 
 
254
  2%|▍ | 24/1000 [38:35<2:07:55, 7.86s/it]
255
  2%|▍ | 25/1000 [38:43<2:06:57, 7.81s/it]
256
 
 
257
  2%|▍ | 25/1000 [38:43<2:06:57, 7.81s/it]
258
  3%|▍ | 26/1000 [38:51<2:06:19, 7.78s/it]
259
 
 
260
  3%|▍ | 26/1000 [38:51<2:06:19, 7.78s/it]
261
  3%|▌ | 27/1000 [38:58<2:05:50, 7.76s/it]
262
 
 
263
  3%|▌ | 27/1000 [38:58<2:05:50, 7.76s/it]
264
  3%|▌ | 28/1000 [39:06<2:05:30, 7.75s/it]
265
 
 
266
  3%|▌ | 28/1000 [39:06<2:05:30, 7.75s/it]
267
  3%|▌ | 29/1000 [39:14<2:05:09, 7.73s/it]
268
 
 
269
  3%|▌ | 29/1000 [39:14<2:05:09, 7.73s/it]
270
  3%|▌ | 30/1000 [39:22<2:04:57, 7.73s/it]
271
 
 
272
  3%|▌ | 30/1000 [39:22<2:04:57, 7.73s/it]
273
  3%|▌ | 31/1000 [39:29<2:04:41, 7.72s/it]
274
 
 
275
  3%|▌ | 31/1000 [39:29<2:04:41, 7.72s/it]
276
  3%|▌ | 32/1000 [39:37<2:04:23, 7.71s/it]
277
 
 
278
  3%|▌ | 32/1000 [39:37<2:04:23, 7.71s/it]
279
  3%|▋ | 33/1000 [39:45<2:04:23, 7.72s/it]
280
 
 
281
  3%|▋ | 33/1000 [39:45<2:04:23, 7.72s/it]
282
  3%|▋ | 34/1000 [39:52<2:04:05, 7.71s/it]
283
 
 
284
  3%|▋ | 34/1000 [39:52<2:04:05, 7.71s/it]
285
  4%|▋ | 35/1000 [40:00<2:03:56, 7.71s/it]
286
 
 
287
  4%|▋ | 35/1000 [40:00<2:03:56, 7.71s/it]
288
  4%|▋ | 36/1000 [40:08<2:03:53, 7.71s/it]
289
 
 
290
  4%|▋ | 36/1000 [40:08<2:03:53, 7.71s/it]
291
  4%|▋ | 37/1000 [40:15<2:03:40, 7.71s/it]
292
 
 
293
  4%|▋ | 37/1000 [40:15<2:03:40, 7.71s/it]
294
  4%|▋ | 38/1000 [40:23<2:03:29, 7.70s/it]
295
 
 
296
  4%|▋ | 38/1000 [40:23<2:03:29, 7.70s/it]
297
  4%|▋ | 39/1000 [40:31<2:03:22, 7.70s/it]
298
 
 
299
  4%|▋ | 39/1000 [40:31<2:03:22, 7.70s/it]
300
  4%|▊ | 40/1000 [40:39<2:03:17, 7.71s/it]
301
 
 
302
  4%|▊ | 40/1000 [40:39<2:03:17, 7.71s/it]
303
  4%|▊ | 41/1000 [40:46<2:03:04, 7.70s/it]
304
 
 
305
  4%|▊ | 41/1000 [40:46<2:03:04, 7.70s/it]
306
  4%|▊ | 42/1000 [40:54<2:03:02, 7.71s/it]
307
 
 
308
  4%|▊ | 42/1000 [40:54<2:03:02, 7.71s/it]
309
  4%|▊ | 43/1000 [41:02<2:02:55, 7.71s/it]
310
 
 
311
  4%|▊ | 43/1000 [41:02<2:02:55, 7.71s/it]
312
  4%|▊ | 44/1000 [41:09<2:02:44, 7.70s/it]
313
 
 
314
  4%|▊ | 44/1000 [41:09<2:02:44, 7.70s/it]
315
  4%|▊ | 45/1000 [41:17<2:02:38, 7.71s/it]
316
 
 
317
  4%|▊ | 45/1000 [41:17<2:02:38, 7.71s/it]
318
  5%|▊ | 46/1000 [41:25<2:02:38, 7.71s/it]
319
 
 
320
  5%|▊ | 46/1000 [41:25<2:02:38, 7.71s/it]
321
  5%|▉ | 47/1000 [41:33<2:02:28, 7.71s/it]
322
 
 
323
  5%|▉ | 47/1000 [41:33<2:02:28, 7.71s/it]
324
  5%|▉ | 48/1000 [41:40<2:02:16, 7.71s/it]
325
 
 
326
  5%|▉ | 48/1000 [41:40<2:02:16, 7.71s/it]
327
  5%|▉ | 49/1000 [41:48<2:02:06, 7.70s/it]
328
 
 
329
  5%|▉ | 49/1000 [41:48<2:02:06, 7.70s/it]
330
  5%|▉ | 50/1000 [41:56<2:02:08, 7.71s/it]
331
 
 
332
  5%|▉ | 50/1000 [41:56<2:02:08, 7.71s/it][2025-10-18 19:44:42,774] [INFO] [axolotl.core.trainers.base.evaluate:376] [PID:42363] Running evaluation step...
 
 
 
 
 
 
 
333
  0%| | 0/179 [00:00<?, ?it/s]
 
334
  1%|▎ | 2/179 [00:00<00:28, 6.17it/s]
 
335
  2%|▍ | 3/179 [00:00<00:40, 4.35it/s]
 
336
  2%|▌ | 4/179 [00:00<00:46, 3.78it/s]
 
337
  3%|▋ | 5/179 [00:01<01:18, 2.21it/s]
 
338
  3%|▊ | 6/179 [00:02<01:09, 2.50it/s]
 
339
  4%|▉ | 7/179 [00:02<01:04, 2.66it/s]
 
340
  4%|█ | 8/179 [00:02<01:01, 2.78it/s]
 
341
  5%|█▏ | 9/179 [00:03<01:10, 2.42it/s]
 
342
  6%|█▏ | 10/179 [00:03<01:03, 2.65it/s]
 
343
  6%|█▎ | 11/179 [00:03<01:00, 2.77it/s]
 
344
  7%|█▍ | 12/179 [00:04<00:58, 2.87it/s]
 
345
  7%|█▌ | 13/179 [00:04<01:07, 2.46it/s]
 
346
  8%|█▋ | 14/179 [00:05<01:01, 2.69it/s]
 
347
  8%|█▊ | 15/179 [00:05<00:58, 2.80it/s]
 
348
  9%|█▉ | 16/179 [00:05<00:56, 2.87it/s]
 
349
  9%|██ | 17/179 [00:06<01:05, 2.46it/s]
 
350
  10%|██▏ | 18/179 [00:06<01:00, 2.68it/s]
 
351
  11%|██▎ | 19/179 [00:06<00:57, 2.78it/s]
 
352
  11%|██▍ | 20/179 [00:07<00:55, 2.86it/s]
 
353
  12%|██▌ | 21/179 [00:07<01:03, 2.47it/s]
 
354
  12%|██▋ | 22/179 [00:07<00:58, 2.68it/s]
 
355
  13%|██▊ | 23/179 [00:08<00:55, 2.80it/s]
 
356
  13%|██▉ | 24/179 [00:08<00:53, 2.87it/s]
 
357
  14%|███ | 25/179 [00:09<01:02, 2.47it/s]
 
358
  15%|███▏ | 26/179 [00:09<00:57, 2.68it/s]
 
359
  15%|███▎ | 27/179 [00:09<00:54, 2.79it/s]
 
360
  16%|███▍ | 28/179 [00:10<00:52, 2.87it/s]
 
361
  16%|███▌ | 29/179 [00:10<01:00, 2.46it/s]
 
362
  17%|███▋ | 30/179 [00:10<00:55, 2.68it/s]
 
363
  17%|███▊ | 31/179 [00:11<00:53, 2.79it/s]
 
364
  18%|██��▉ | 32/179 [00:11<00:51, 2.87it/s]
 
365
  18%|████ | 33/179 [00:12<00:59, 2.47it/s]
 
366
  19%|████▏ | 34/179 [00:12<00:54, 2.68it/s]
 
367
  20%|████▎ | 35/179 [00:12<00:51, 2.78it/s]
 
368
  20%|████▍ | 36/179 [00:13<00:50, 2.86it/s]
 
369
  21%|████▌ | 37/179 [00:13<00:57, 2.47it/s]
 
370
  21%|████▋ | 38/179 [00:13<00:52, 2.69it/s]
 
371
  22%|████▊ | 39/179 [00:14<00:49, 2.80it/s]
 
372
  22%|████▉ | 40/179 [00:14<00:48, 2.87it/s]
 
373
  23%|█████ | 41/179 [00:15<00:55, 2.47it/s]
 
374
  23%|█████▏ | 42/179 [00:15<00:50, 2.70it/s]
 
375
  24%|█████▎ | 43/179 [00:15<00:48, 2.79it/s]
 
376
  25%|█████▍ | 44/179 [00:16<00:47, 2.86it/s]
 
377
  25%|█████▌ | 45/179 [00:16<00:54, 2.47it/s]
 
378
  26%|█████▋ | 46/179 [00:16<00:49, 2.69it/s]
 
379
  26%|█████▊ | 47/179 [00:17<00:47, 2.80it/s]
 
380
  27%|█████▉ | 48/179 [00:17<00:45, 2.88it/s]
 
381
  27%|██████ | 49/179 [00:18<00:52, 2.48it/s]
 
382
  28%|██████▏ | 50/179 [00:18<00:47, 2.70it/s]
 
383
  28%|██████▎ | 51/179 [00:18<00:45, 2.80it/s]
 
384
  29%|██████▍ | 52/179 [00:19<00:44, 2.86it/s]
 
385
  30%|██████▌ | 53/179 [00:19<00:51, 2.46it/s]
 
386
  30%|██████▋ | 54/179 [00:19<00:46, 2.68it/s]
 
387
  31%|██████▊ | 55/179 [00:20<00:44, 2.78it/s]
 
388
  31%|██████▉ | 56/179 [00:20<00:42, 2.87it/s]
 
389
  32%|███████ | 57/179 [00:21<00:49, 2.46it/s]
 
390
  32%|███████▏ | 58/179 [00:21<00:45, 2.68it/s]
 
391
  33%|███████▎ | 59/179 [00:21<00:43, 2.79it/s]
 
392
  34%|███████▎ | 60/179 [00:22<00:41, 2.86it/s]
 
393
  34%|███████▍ | 61/179 [00:22<00:47, 2.47it/s]
 
394
  35%|███████▌ | 62/179 [00:22<00:43, 2.68it/s]
 
395
  35%|███████▋ | 63/179 [00:23<00:41, 2.80it/s]
 
396
  36%|███████▊ | 64/179 [00:23<00:40, 2.87it/s]
 
397
  36%|███████▉ | 65/179 [00:24<00:46, 2.47it/s]
 
398
  37%|████████ | 66/179 [00:24<00:41, 2.70it/s]
 
399
  37%|████████▏ | 67/179 [00:24<00:40, 2.80it/s]
 
400
  38%|████████▎ | 68/179 [00:24<00:38, 2.87it/s]
 
401
  39%|████████▍ | 69/179 [00:25<00:44, 2.46it/s]
 
402
  39%|████████▌ | 70/179 [00:25<00:40, 2.69it/s]
 
403
  40%|████████▋ | 71/179 [00:26<00:38, 2.80it/s]
 
404
  40%|████████▊ | 72/179 [00:26<00:37, 2.87it/s]
 
405
  41%|████████▉ | 73/179 [00:26<00:42, 2.47it/s]
 
406
  41%|█████████ | 74/179 [00:27<00:38, 2.69it/s]
 
407
  42%|█████████▏ | 75/179 [00:27<00:37, 2.80it/s]
 
408
  42%|█████████▎ | 76/179 [00:27<00:35, 2.87it/s]
 
409
  43%|█████████▍ | 77/179 [00:28<00:41, 2.48it/s]
 
410
  44%|█████████▌ | 78/179 [00:28<00:37, 2.69it/s]
 
411
  44%|█████████▋ | 79/179 [00:29<00:35, 2.79it/s]
 
412
  45%|█████████▊ | 80/179 [00:29<00:34, 2.87it/s]
 
413
  45%|█████████▉ | 81/179 [00:29<00:39, 2.47it/s]
 
414
  46%|██████████ | 82/179 [00:30<00:36, 2.69it/s]
 
415
  46%|██████████▏ | 83/179 [00:30<00:34, 2.79it/s]
 
416
  47%|██████████▎ | 84/179 [00:30<00:33, 2.87it/s]
 
417
  47%|██████████▍ | 85/179 [00:31<00:38, 2.47it/s]
 
418
  48%|██████████▌ | 86/179 [00:31<00:34, 2.69it/s]
 
419
  49%|██████████▋ | 87/179 [00:32<00:32, 2.81it/s]
 
420
  49%|██████████▊ | 88/179 [00:32<00:31, 2.88it/s]
 
421
  50%|██████████▉ | 89/179 [00:32<00:36, 2.48it/s]
 
422
  50%|███████████ | 90/179 [00:33<00:32, 2.71it/s]
 
423
  51%|███████████▏ | 91/179 [00:33<00:31, 2.81it/s]
 
424
  51%|███████████▎ | 92/179 [00:33<00:30, 2.88it/s]
 
425
  52%|███████████▍ | 93/179 [00:34<00:34, 2.47it/s]
 
426
  53%|███████████▌ | 94/179 [00:34<00:31, 2.70it/s]
 
427
  53%|███████████▋ | 95/179 [00:35<00:30, 2.79it/s]
 
428
  54%|███████████▊ | 96/179 [00:35<00:28, 2.87it/s]
 
429
  54%|███████████▉ | 97/179 [00:35<00:33, 2.48it/s]
 
430
  55%|████████████ | 98/179 [00:36<00:30, 2.69it/s]
 
431
  55%|████████████▏ | 99/179 [00:36<00:28, 2.79it/s]
 
432
  56%|███████████▋ | 100/179 [00:36<00:27, 2.87it/s]
 
433
  56%|███████████▊ | 101/179 [00:37<00:31, 2.46it/s]
 
434
  57%|███████████▉ | 102/179 [00:37<00:28, 2.69it/s]
 
435
  58%|████████████ | 103/179 [00:37<00:27, 2.80it/s]
 
436
  58%|████████████▏ | 104/179 [00:38<00:26, 2.86it/s]
 
437
  59%|████████████▎ | 105/179 [00:38<00:30, 2.46it/s]
 
438
  59%|████████████▍ | 106/179 [00:39<00:27, 2.69it/s]
 
439
  60%|████████████▌ | 107/179 [00:39<00:25, 2.79it/s]
 
440
  60%|████████████▋ | 108/179 [00:39<00:24, 2.87it/s]
 
441
  61%|████████████▊ | 109/179 [00:40<00:28, 2.45it/s]
 
442
  61%|████████████▉ | 110/179 [00:40<00:25, 2.70it/s]
 
443
  62%|█████████████ | 111/179 [00:40<00:24, 2.81it/s]
 
444
  63%|█████████████▏ | 112/179 [00:41<00:23, 2.89it/s]
 
445
  63%|█████████████▎ | 113/179 [00:41<00:26, 2.46it/s]
 
446
  64%|█████████████▎ | 114/179 [00:42<00:24, 2.70it/s]
 
447
  64%|█████████████▍ | 115/179 [00:42<00:22, 2.81it/s]
 
448
  65%|█████████████▌ | 116/179 [00:42<00:21, 2.89it/s]
 
449
  65%|█████████████▋ | 117/179 [00:43<00:25, 2.47it/s]
 
450
  66%|█████████████▊ | 118/179 [00:43<00:22, 2.68it/s]
 
451
  66%|█████████████▉ | 119/179 [00:43<00:21, 2.78it/s]
 
452
  67%|██████████████ | 120/179 [00:44<00:20, 2.86it/s]
 
453
  68%|██████████████▏ | 121/179 [00:44<00:23, 2.47it/s]
 
454
  68%|██████████████▎ | 122/179 [00:45<00:21, 2.69it/s]
 
455
  69%|██████████████▍ | 123/179 [00:45<00:20, 2.79it/s]
 
456
  69%|██████████████▌ | 124/179 [00:45<00:19, 2.87it/s]
 
457
  70%|██████████████▋ | 125/179 [00:46<00:21, 2.47it/s]
 
458
  70%|██████████████▊ | 126/179 [00:46<00:19, 2.68it/s]
 
459
  71%|██████████████▉ | 127/179 [00:46<00:18, 2.80it/s]
 
460
  72%|███████████████ | 128/179 [00:47<00:17, 2.88it/s]
 
461
  72%|███████████████▏ | 129/179 [00:47<00:20, 2.46it/s]
 
462
  73%|███████████████▎ | 130/179 [00:48<00:18, 2.68it/s]
 
463
  73%|███████████████▎ | 131/179 [00:48<00:17, 2.78it/s]
 
464
  74%|███████████████▍ | 132/179 [00:48<00:16, 2.86it/s]
 
465
  74%|███████████████▌ | 133/179 [00:49<00:18, 2.46it/s]
 
466
  75%|███████████████▋ | 134/179 [00:49<00:16, 2.68it/s]
 
467
  75%|███████████████▊ | 135/179 [00:49<00:15, 2.79it/s]
 
468
  76%|███████████████▉ | 136/179 [00:50<00:14, 2.87it/s]
 
469
  77%|████████████████ | 137/179 [00:50<00:17, 2.46it/s]
 
470
  77%|████████████████▏ | 138/179 [00:51<00:15, 2.70it/s]
 
471
  78%|████████████████▎ | 139/179 [00:51<00:14, 2.79it/s]
 
472
  78%|████████████████▍ | 140/179 [00:51<00:13, 2.86it/s]
 
473
  79%|████████████████▌ | 141/179 [00:52<00:15, 2.44it/s]
 
474
  79%|████████████████▋ | 142/179 [00:52<00:13, 2.68it/s]
 
475
  80%|████████████████▊ | 143/179 [00:52<00:12, 2.78it/s]
 
476
  80%|████████████████▉ | 144/179 [00:53<00:12, 2.85it/s]
 
477
  81%|█████████████████ | 145/179 [00:53<00:13, 2.44it/s]
 
478
  82%|█████████████████▏ | 146/179 [00:54<00:12, 2.67it/s]
 
479
  82%|█████████████████▏ | 147/179 [00:54<00:11, 2.78it/s]
 
480
  83%|█████████████████▎ | 148/179 [00:54<00:10, 2.86it/s]
 
481
  83%|█████████████████▍ | 149/179 [00:55<00:12, 2.46it/s]
 
482
  84%|█████████████████▌ | 150/179 [00:55<00:10, 2.68it/s]
 
483
  84%|█████████████████▋ | 151/179 [00:55<00:10, 2.78it/s]
 
484
  85%|█████████████████▊ | 152/179 [00:56<00:09, 2.87it/s]
 
485
  85%|█████████████████▉ | 153/179 [00:56<00:10, 2.47it/s]
 
486
  86%|██████████████████ | 154/179 [00:56<00:09, 2.68it/s]
 
487
  87%|██████████████████▏ | 155/179 [00:57<00:08, 2.78it/s]
 
488
  87%|██████████████████▎ | 156/179 [00:57<00:08, 2.86it/s]
 
489
  88%|██████████████████▍ | 157/179 [00:58<00:08, 2.46it/s]
 
490
  88%|██████████████████▌ | 158/179 [00:58<00:07, 2.68it/s]
 
491
  89%|██████████████████▋ | 159/179 [00:58<00:07, 2.79it/s]
 
492
  89%|██████████████████▊ | 160/179 [00:59<00:06, 2.88it/s]
 
493
  90%|██████████████████▉ | 161/179 [00:59<00:07, 2.48it/s]
 
494
  91%|███████████████████ | 162/179 [00:59<00:06, 2.71it/s]
 
495
  91%|███████████████████ | 163/179 [01:00<00:05, 2.81it/s]
 
496
  92%|███████████████████▏ | 164/179 [01:00<00:05, 2.89it/s]
 
497
  92%|███████████████████▎ | 165/179 [01:01<00:05, 2.47it/s]
 
498
  93%|███████████████████▍ | 166/179 [01:01<00:04, 2.69it/s]
 
499
  93%|███████████████████▌ | 167/179 [01:01<00:04, 2.79it/s]
 
500
  94%|███████████████████▋ | 168/179 [01:02<00:03, 2.87it/s]
 
501
  94%|███████████████████▊ | 169/179 [01:02<00:04, 2.47it/s]
 
502
  95%|███████████████████▉ | 170/179 [01:02<00:03, 2.69it/s]
 
503
  96%|████████████████████ | 171/179 [01:03<00:02, 2.79it/s]
 
504
  96%|████████████████████▏| 172/179 [01:03<00:02, 2.87it/s]
 
505
  97%|████████████████████▎| 173/179 [01:04<00:02, 2.47it/s]
 
506
  97%|████████████████████▍| 174/179 [01:04<00:01, 2.69it/s]
 
507
  98%|████████████████████▌| 175/179 [01:04<00:01, 2.79it/s]
 
508
  98%|████████████████████▋| 176/179 [01:05<00:01, 2.86it/s]
 
509
  99%|████████████████████▊| 177/179 [01:05<00:00, 2.47it/s]
 
510
  99%|████████████████████▉| 178/179 [01:05<00:00, 2.69it/s]
 
511
 
 
512
 
 
513
  5%|▉ | 50/1000 [43:11<2:02:08, 7.71s/it]
 
 
514
  [2025-10-18 19:45:58,394] [INFO] [axolotl.core.trainers.base._save:664] [PID:42363] Saving model checkpoint to ./outputs/sft/gemma-2-2b-it-rp-sft-qlora/checkpoint-50
 
515
  5%|▉ | 51/1000 [43:21<8:12:20, 31.13s/it]
516
 
 
517
  5%|▉ | 51/1000 [43:21<8:12:20, 31.13s/it]
 
1
+ [2025-10-18 19:02:01,879] [DEBUG] [axolotl.utils.config.log_gpu_memory_usage:127] [PID:42363] baseline 0.000GB ()
2
+ [2025-10-18 19:02:01,880] [INFO] [axolotl.cli.config.load_cfg:248] [PID:42363] config:
3
+ {
4
+ "activation_offloading": false,
5
+ "adapter": "qlora",
6
+ "axolotl_config_path": "mrCuddle-stream.yaml",
7
+ "base_model": "google/gemma-2-2b-it",
8
+ "base_model_config": "google/gemma-2-2b-it",
9
+ "batch_size": 8,
10
+ "bf16": true,
11
+ "capabilities": {
12
+ "bf16": true,
13
+ "compute_capability": "sm_86",
14
+ "fp8": false,
15
+ "n_gpu": 1,
16
+ "n_node": 1
17
+ },
18
+ "context_parallel_size": 1,
19
+ "dataloader_num_workers": 1,
20
+ "dataloader_pin_memory": true,
21
+ "dataloader_prefetch_factor": 256,
22
+ "dataset_num_proc": 12,
23
+ "dataset_prepared_path": "last_run_prepared",
24
+ "datasets": [
25
+ {
26
+ "chat_template": "jinja",
27
+ "chat_template_jinja": "{{ bos_token }}\n{% for m in messages %}\n {% set role = 'model' if m['role']=='assistant' else 'user' %}\n {{ '<start_of_turn>' + role + '\\n' + m['content'] | trim + '<end_of_turn>\\n' }}\n{% endfor %}\n{% if add_generation_prompt %}\n{{ '<start_of_turn>model\\n' }}\n{% endif %}\n",
28
+ "data_files": "conversations_V3.jsonl",
29
+ "field_messages": "conversations",
30
+ "message_property_mappings": {
31
+ "content": "value",
32
+ "role": "from"
33
+ },
34
+ "path": "AiAF/conversations",
35
+ "roles_to_train": [
36
+ "assistant"
37
+ ],
38
+ "split": "train",
39
+ "train_on_eos": "turn",
40
+ "trust_remote_code": false,
41
+ "type": "chat_template"
42
+ }
43
+ ],
44
+ "ddp": false,
45
+ "device": "cuda:0",
46
+ "dion_rank_fraction": 1.0,
47
+ "dion_rank_multiple_of": 1,
48
+ "env_capabilities": {
49
+ "torch_version": "2.7.1"
50
+ },
51
+ "eot_tokens": [
52
+ "<end_of_turn>"
53
+ ],
54
+ "eval_batch_size": 2,
55
+ "eval_causal_lm_metrics": [
56
+ "sacrebleu",
57
+ "comet",
58
+ "ter",
59
+ "chrf"
60
+ ],
61
+ "eval_max_new_tokens": 128,
62
+ "eval_sample_packing": true,
63
+ "eval_steps": 50,
64
+ "eval_strategy": "steps",
65
+ "eval_table_size": 0,
66
+ "evaluation_strategy": "steps",
67
+ "experimental_skip_move_to_device": true,
68
+ "flash_attention": true,
69
+ "fp16": false,
70
+ "gradient_accumulation_steps": 4,
71
+ "gradient_checkpointing": true,
72
+ "gradient_checkpointing_kwargs": {
73
+ "use_reentrant": true
74
+ },
75
+ "hub_model_id": "AiAF/rp-2b",
76
+ "hub_strategy": "checkpoint",
77
+ "include_tkps": true,
78
+ "is_falcon_derived_model": false,
79
+ "is_llama_derived_model": false,
80
+ "is_mistral_derived_model": false,
81
+ "learning_rate": 0.0002,
82
+ "lisa_layers_attribute": "model.layers",
83
+ "load_best_model_at_end": false,
84
+ "load_in_4bit": true,
85
+ "load_in_8bit": false,
86
+ "local_rank": 0,
87
+ "logging_steps": 1,
88
+ "lora_alpha": 128,
89
+ "lora_dropout": 0.05,
90
+ "lora_r": 64,
91
+ "lora_target_linear": true,
92
+ "loraplus_lr_embedding": 1e-06,
93
+ "lr_scheduler": "cosine",
94
+ "max_steps": 1000,
95
+ "mean_resizing_embeddings": false,
96
+ "micro_batch_size": 2,
97
+ "model_config_type": "gemma2",
98
+ "num_epochs": 1.0,
99
+ "optimizer": "adamw_bnb_8bit",
100
+ "output_dir": "./outputs/sft/gemma-2-2b-it-rp-sft-qlora",
101
+ "pad_to_sequence_len": true,
102
+ "pretrain_multipack_attn": true,
103
+ "profiler_steps_start": 0,
104
+ "qlora_sharded_model_loading": false,
105
+ "ray_num_workers": 1,
106
+ "resources_per_worker": {
107
+ "GPU": 1
108
+ },
109
+ "sample_packing": true,
110
+ "sample_packing_bin_size": 200,
111
+ "sample_packing_group_size": 100000,
112
+ "save_only_model": false,
113
+ "save_safetensors": true,
114
+ "save_steps": 50,
115
+ "save_strategy": "steps",
116
+ "save_total_limit": 100,
117
+ "sequence_len": 2048,
118
+ "shuffle_before_merging_datasets": false,
119
+ "shuffle_merged_datasets": true,
120
+ "skip_prepare_dataset": false,
121
+ "special_tokens": {
122
+ "bos_token": "<bos>",
123
+ "eos_token": "<eos>",
124
+ "pad_token": "<pad>"
125
+ },
126
+ "streaming": true,
127
+ "streaming_multipack_buffer_size": 10000,
128
+ "strict": false,
129
+ "tensor_parallel_size": 1,
130
+ "test_datasets": [
131
+ {
132
+ "chat_template": "jinja",
133
+ "chat_template_jinja": "{{ bos_token }}\n{% for m in messages %}\n {% set role = 'model' if m['role']=='assistant' else 'user' %}\n {{ '<start_of_turn>' + role + '\\n' + m['content'] | trim + '<end_of_turn>\\n' }}\n{% endfor %}\n{% if add_generation_prompt %}\n{{ '<start_of_turn>model\\n' }}\n{% endif %}\n",
134
+ "data_files": "eval-datasets/shuf-1000_conversations_V2.jsonl",
135
+ "field_messages": "conversations",
136
+ "message_property_mappings": {
137
+ "content": "value",
138
+ "role": "from"
139
+ },
140
+ "name": "json",
141
+ "path": ".",
142
+ "roles_to_train": [
143
+ "assistant"
144
+ ],
145
+ "split": "train",
146
+ "trust_remote_code": false,
147
+ "type": "chat_template"
148
+ }
149
+ ],
150
+ "tf32": true,
151
+ "tiled_mlp_use_original_mlp": true,
152
+ "tokenizer_config": "google/gemma-2-2b-it",
153
+ "tokenizer_save_jinja_files": true,
154
+ "tokenizer_type": "AutoTokenizer",
155
+ "torch_dtype": "torch.bfloat16",
156
+ "train_on_inputs": false,
157
+ "trl": {
158
+ "log_completions": false,
159
+ "mask_truncated_completions": false,
160
+ "ref_model_mixup_alpha": 0.9,
161
+ "ref_model_sync_steps": 64,
162
+ "scale_rewards": true,
163
+ "sync_ref_model": false,
164
+ "use_vllm": false,
165
+ "vllm_server_host": "0.0.0.0",
166
+ "vllm_server_port": 8000
167
+ },
168
+ "type_of_model": "AutoModelForCausalLM",
169
+ "use_ray": false,
170
+ "use_wandb": true,
171
+ "val_set_size": 0.0,
172
+ "vllm": {
173
+ "device": "auto",
174
+ "dtype": "auto",
175
+ "gpu_memory_utilization": 0.9,
176
+ "host": "0.0.0.0",
177
+ "port": 8000
178
+ },
179
+ "wandb_log_model": "false",
180
+ "wandb_name": "gemma-2-2b-it-rp-sft-qlora",
181
+ "wandb_project": "rp-sft",
182
+ "wandb_run_id": "gemma-2-2b-it-rp-sft-qlora",
183
+ "weight_decay": 0.0,
184
+ "world_size": 1
185
+ }
186
+ [2025-10-18 19:02:03,610] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:278] [PID:42363] EOS: 1 / <eos>
187
+ [2025-10-18 19:02:03,610] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:279] [PID:42363] BOS: 2 / <bos>
188
+ [2025-10-18 19:02:03,610] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:280] [PID:42363] PAD: 0 / <pad>
189
+ [2025-10-18 19:02:03,610] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:281] [PID:42363] UNK: 3 / <unk>
190
+ [2025-10-18 19:02:17,503] [INFO] [axolotl.utils.data.shared.load_preprocessed_dataset:470] [PID:42363] Loading prepared dataset from disk at last_run_prepared/323978649404d0f4da7e1f3e2dc7b3de...
191
+ [2025-10-18 19:02:17,508] [DEBUG] [axolotl.train.setup_model_and_tokenizer:65] [PID:42363] Loading tokenizer... google/gemma-2-2b-it
192
+ [2025-10-18 19:02:18,978] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:278] [PID:42363] EOS: 1 / <eos>
193
+ [2025-10-18 19:02:18,978] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:279] [PID:42363] BOS: 2 / <bos>
194
+ [2025-10-18 19:02:18,978] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:280] [PID:42363] PAD: 0 / <pad>
195
+ [2025-10-18 19:02:18,979] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:281] [PID:42363] UNK: 3 / <unk>
196
+ [2025-10-18 19:02:18,979] [DEBUG] [axolotl.train.setup_model_and_tokenizer:74] [PID:42363] Loading model
197
+ [2025-10-18 19:02:19,156] [DEBUG] [axolotl.monkeypatch.transformers.trainer_loss_calc.patch_evaluation_loop:87] [PID:42363] Patched Trainer.evaluation_loop with nanmean loss calculation
198
+ [2025-10-18 19:02:19,159] [DEBUG] [axolotl.monkeypatch.transformers.trainer_loss_calc.patch_maybe_log_save_evaluate:138] [PID:42363] Patched Trainer._maybe_log_save_evaluate with nanmean loss calculation
199
+ [2025-10-18 19:02:19,160] [INFO] [axolotl.loaders.patch_manager._apply_multipack_patches:301] [PID:42363] Applying multipack dataloader patch for sample packing...
200
+
201
+ [2025-10-18 19:02:34,220] [INFO] [axolotl.loaders.model._prepare_model_for_quantization:863] [PID:42363] converting PEFT model w/ prepare_model_for_kbit_training
202
+ [2025-10-18 19:02:34,224] [INFO] [axolotl.loaders.model._configure_embedding_dtypes:345] [PID:42363] Converting modules to torch.bfloat16
203
+ [2025-10-18 19:02:34,227] [DEBUG] [axolotl.loaders.model.log_gpu_memory_usage:127] [PID:42363] Memory usage after model load 4.378GB (+4.378GB allocated, +4.486GB reserved)
204
+ [2025-10-18 19:02:34,228] [INFO] [axolotl.loaders.adapter.load_lora:80] [PID:42363] found linear modules: ['down_proj', 'gate_proj', 'k_proj', 'o_proj', 'q_proj', 'up_proj', 'v_proj']
205
+ trainable params: 83,066,880 || all params: 2,697,408,768 || trainable%: 3.0795
206
+ [2025-10-18 19:02:35,141] [DEBUG] [axolotl.loaders.model.log_gpu_memory_usage:127] [PID:42363] after adapters 2.438GB (+2.438GB allocated, +4.625GB reserved)
207
+ [2025-10-18 19:02:42,952] [INFO] [axolotl.train.save_initial_configs:398] [PID:42363] Pre-saving adapter config to ./outputs/sft/gemma-2-2b-it-rp-sft-qlora...
208
+ [2025-10-18 19:02:42,952] [INFO] [axolotl.train.save_initial_configs:402] [PID:42363] Pre-saving tokenizer to ./outputs/sft/gemma-2-2b-it-rp-sft-qlora...
209
+ [2025-10-18 19:02:43,482] [INFO] [axolotl.train.save_initial_configs:407] [PID:42363] Pre-saving model config to ./outputs/sft/gemma-2-2b-it-rp-sft-qlora...
210
+ [2025-10-18 19:02:43,494] [INFO] [axolotl.train.execute_training:196] [PID:42363] Starting trainer...
211
+ wandb: Currently logged in as: factoryaiart to https://api.wandb.ai. Use `wandb login --relogin` to force relogin
212
+ wandb: ⢿ Waiting for wandb.init()...
213
+
214
+
215
+ wandb: Run data is saved locally in /workspace/axolotl/wandb/run-20251018_190244-gemma-2-2b-it-rp-sft-qlora
216
+ wandb: Run `wandb offline` to turn off syncing.
217
+ wandb: Syncing run gemma-2-2b-it-rp-sft-qlora
218
+ wandb: ⭐️ View project at https://wandb.ai/factoryaiart/rp-sft
219
+ wandb: 🚀 View run at https://wandb.ai/factoryaiart/rp-sft/runs/gemma-2-2b-it-rp-sft-qlora
220
+ wandb: Detected [huggingface_hub.inference, openai] in use.
221
+ wandb: Use W&B Weave for improved LLM call tracing. Install Weave with `pip install weave` then add `import weave` to the top of your script.
222
+ wandb: For more information, check out the docs at: https://weave-docs.wandb.ai/
223
+ wandb: WARNING Saving files without folders. If you want to preserve subdirectories pass base_path to wandb.save, i.e. wandb.save("/mnt/folder/file.h5", base_path="/mnt")
224
+ [2025-10-18 19:02:46,605] [INFO] [axolotl.utils.callbacks.on_train_begin:757] [PID:42363] The Axolotl config has been saved to the WandB run under files.
225
+
226
  0%| | 0/1000 [00:00<?, ?it/s][2025-10-18 19:02:46,619] [INFO] [axolotl.core.trainers.base.evaluate:376] [PID:42363] Running evaluation step...
227
+ [2025-10-18 19:02:49,230] [DEBUG] [axolotl.utils.samplers.multipack.__len__:462] [PID:42363] generate_batches time: 1.221949577331543
228
+ [2025-10-18 19:02:50,452] [DEBUG] [axolotl.utils.samplers.multipack.__len__:462] [PID:42363] generate_batches time: 1.221228837966919
229
+ [2025-10-18 19:02:51,753] [DEBUG] [axolotl.utils.samplers.multipack.__len__:462] [PID:42363] generate_batches time: 1.3005599975585938
230
+ [2025-10-18 19:02:53,012] [DEBUG] [axolotl.utils.samplers.multipack.__len__:462] [PID:42363] generate_batches time: 1.258347511291504
231
+ [2025-10-18 19:02:53,012] [INFO] [axolotl.utils.samplers.multipack.calc_min_len:438] [PID:42363] gather_len_batches: [179]
232
+
233
+
234
  0%| | 0/179 [00:00<?, ?it/s]
235
+
236
  1%|▎ | 2/179 [00:00<00:21, 8.31it/s]
237
+
238
  2%|▍ | 3/179 [00:00<00:35, 4.96it/s]
239
+
240
  2%|▌ | 4/179 [00:00<00:42, 4.11it/s]
241
+
242
  3%|▋ | 5/179 [00:01<01:00, 2.89it/s]
243
+
244
  3%|▊ | 6/179 [00:01<00:56, 3.06it/s]
245
+
246
  4%|▉ | 7/179 [00:02<00:55, 3.07it/s]
247
+
248
  4%|█ | 8/179 [00:02<00:54, 3.11it/s]
249
+
250
  5%|█▏ | 9/179 [00:02<01:05, 2.59it/s]
251
+
252
  6%|█▏ | 10/179 [00:03<01:00, 2.80it/s]
253
+
254
  6%|█▎ | 11/179 [00:03<00:57, 2.90it/s]
255
+
256
  7%|█▍ | 12/179 [00:03<00:55, 2.99it/s]
257
+
258
  7%|█▌ | 13/179 [00:04<01:05, 2.55it/s]
259
+
260
  8%|█▋ | 14/179 [00:04<00:59, 2.78it/s]
261
+
262
  8%|█▊ | 15/179 [00:04<00:56, 2.89it/s]
263
+
264
  9%|█▉ | 16/179 [00:05<00:54, 2.97it/s]
265
+
266
  9%|██ | 17/179 [00:05<01:03, 2.54it/s]
267
+
268
  10%|██▏ | 18/179 [00:06<00:58, 2.77it/s]
269
+
270
  11%|██▎ | 19/179 [00:06<00:55, 2.89it/s]
271
+
272
  11%|██▍ | 20/179 [00:06<00:53, 2.97it/s]
273
+
274
  12%|██▌ | 21/179 [00:07<01:02, 2.55it/s]
275
+
276
  12%|██▋ | 22/179 [00:07<00:56, 2.77it/s]
277
+
278
  13%|██▊ | 23/179 [00:07<00:54, 2.89it/s]
279
+
280
  13%|██▉ | 24/179 [00:08<00:52, 2.97it/s]
281
+
282
  14%|███ | 25/179 [00:08<01:00, 2.54it/s]
283
+
284
  15%|███▏ | 26/179 [00:08<00:55, 2.77it/s]
285
+
286
  15%|███▎ | 27/179 [00:09<00:52, 2.88it/s]
287
+
288
  16%|███▍ | 28/179 [00:09<00:50, 2.96it/s]
289
+
290
  16%|███▌ | 29/179 [00:10<00:59, 2.54it/s]
291
+
292
  17%|███▋ | 30/179 [00:10<00:53, 2.77it/s]
293
+
294
  17%|███▊ | 31/179 [00:10<00:51, 2.87it/s]
295
+
296
  18%|███▉ | 32/179 [00:10<00:49, 2.96it/s]
297
+
298
  18%|████ | 33/179 [00:11<00:57, 2.52it/s]
299
+
300
  19%|████▏ | 34/179 [00:11<00:52, 2.75it/s]
301
+
302
  20%|████▎ | 35/179 [00:12<00:50, 2.87it/s]
303
+
304
  20%|████▍ | 36/179 [00:12<00:48, 2.96it/s]
305
+
306
  21%|████▌ | 37/179 [00:12<00:56, 2.53it/s]
307
+
308
  21%|████▋ | 38/179 [00:13<00:50, 2.77it/s]
309
+
310
  22%|████▊ | 39/179 [00:13<00:48, 2.88it/s]
311
+
312
  22%|████▉ | 40/179 [00:13<00:46, 2.97it/s]
313
+
314
  23%|█████ | 41/179 [00:14<00:54, 2.54it/s]
315
+
316
  23%|█████▏ | 42/179 [00:14<00:49, 2.78it/s]
317
+
318
  24%|█████▎ | 43/179 [00:14<00:46, 2.90it/s]
319
+
320
  25%|█████▍ | 44/179 [00:15<00:45, 2.97it/s]
321
+
322
  25%|█████▌ | 45/179 [00:15<00:53, 2.53it/s]
323
+
324
  26%|█████▋ | 46/179 [00:16<00:48, 2.77it/s]
325
+
326
  26%|█████▊ | 47/179 [00:16<00:45, 2.89it/s]
327
+
328
  27%|█████▉ | 48/179 [00:16<00:44, 2.96it/s]
329
+
330
  27%|██████ | 49/179 [00:17<00:51, 2.53it/s]
331
+
332
  28%|██████▏ | 50/179 [00:17<00:46, 2.76it/s]
333
+
334
  28%|██████▎ | 51/179 [00:17<00:44, 2.87it/s]
335
+
336
  29%|██████▍ | 52/179 [00:18<00:42, 2.96it/s]
337
+
338
  30%|██████▌ | 53/179 [00:18<00:49, 2.52it/s]
339
+
340
  30%|██████▋ | 54/179 [00:19<00:45, 2.76it/s]
341
+
342
  31%|██████▊ | 55/179 [00:19<00:43, 2.88it/s]
343
+
344
  31%|██████▉ | 56/179 [00:19<00:41, 2.96it/s]
345
+
346
  32%|███████ | 57/179 [00:20<00:48, 2.54it/s]
347
+
348
  32%|███████▏ | 58/179 [00:20<00:43, 2.77it/s]
349
+
350
  33%|███████▎ | 59/179 [00:20<00:41, 2.87it/s]
351
+
352
  34%|███████▎ | 60/179 [00:21<00:40, 2.94it/s]
353
+
354
  34%|███████▍ | 61/179 [00:21<00:46, 2.52it/s]
355
+
356
  35%|███████▌ | 62/179 [00:21<00:42, 2.74it/s]
357
+
358
  35%|███████▋ | 63/179 [00:22<00:40, 2.86it/s]
359
+
360
  36%|███████▊ | 64/179 [00:22<00:39, 2.95it/s]
361
+
362
  36%|███████▉ | 65/179 [00:23<00:45, 2.52it/s]
363
+
364
  37%|████████ | 66/179 [00:23<00:41, 2.75it/s]
365
+
366
  37%|████████▏ | 67/179 [00:23<00:39, 2.85it/s]
367
+
368
  38%|████████▎ | 68/179 [00:23<00:37, 2.93it/s]
369
+
370
  39%|████████▍ | 69/179 [00:24<00:44, 2.50it/s]
371
+
372
  39%|████████▌ | 70/179 [00:24<00:39, 2.75it/s]
373
+
374
  40%|████████▋ | 71/179 [00:25<00:37, 2.85it/s]
375
+
376
  40%|████████▊ | 72/179 [00:25<00:36, 2.94it/s]
377
+
378
  41%|████████▉ | 73/179 [00:25<00:42, 2.51it/s]
379
+
380
  41%|█████████ | 74/179 [00:26<00:38, 2.74it/s]
381
+
382
  42%|█████████▏ | 75/179 [00:26<00:36, 2.87it/s]
383
+
384
  42%|█████████▎ | 76/179 [00:26<00:34, 2.94it/s]
385
+
386
  43%|█████████▍ | 77/179 [00:27<00:42, 2.38it/s]
387
+
388
  44%|█████████▌ | 78/179 [00:27<00:38, 2.63it/s]
389
+
390
  44%|█████████▋ | 79/179 [00:28<00:36, 2.75it/s]
391
+
392
  45%|█████████▊ | 80/179 [00:28<00:34, 2.85it/s]
393
+
394
  45%|█████████▉ | 81/179 [00:28<00:40, 2.43it/s]
395
+
396
  46%|██████████ | 82/179 [00:29<00:36, 2.68it/s]
397
+
398
  46%|██████████▏ | 83/179 [00:29<00:34, 2.80it/s]
399
+
400
  47%|██████████▎ | 84/179 [00:29<00:33, 2.88it/s]
401
+
402
  47%|██████████▍ | 85/179 [00:30<00:37, 2.49it/s]
403
+
404
  48%|██████████▌ | 86/179 [00:30<00:33, 2.74it/s]
405
+
406
  49%|██████████▋ | 87/179 [00:31<00:32, 2.86it/s]
407
+
408
  49%|██████████▊ | 88/179 [00:31<00:30, 2.95it/s]
409
+
410
  50%|██████████▉ | 89/179 [00:31<00:35, 2.53it/s]
411
+
412
  50%|███████████ | 90/179 [00:32<00:32, 2.76it/s]
413
+
414
  51%|███████████▏ | 91/179 [00:32<00:30, 2.87it/s]
415
+
416
  51%|███████████▎ | 92/179 [00:32<00:29, 2.95it/s]
417
+
418
  52%|███████████▍ | 93/179 [00:33<00:34, 2.52it/s]
419
+
420
  53%|███████████▌ | 94/179 [00:33<00:30, 2.76it/s]
421
+
422
  53%|███████████▋ | 95/179 [00:33<00:29, 2.88it/s]
423
+
424
  54%|███████████▊ | 96/179 [00:34<00:28, 2.96it/s]
425
+
426
  54%|███████████▉ | 97/179 [00:34<00:32, 2.53it/s]
427
+
428
  55%|████████████ | 98/179 [00:35<00:29, 2.77it/s]
429
+
430
  55%|████████████▏ | 99/179 [00:35<00:27, 2.88it/s]
431
+
432
  56%|███████████▋ | 100/179 [00:35<00:26, 2.94it/s]
433
+
434
  56%|███████████▊ | 101/179 [00:36<00:30, 2.52it/s]
435
+
436
  57%|███████████▉ | 102/179 [00:36<00:28, 2.75it/s]
437
+
438
  58%|████████████ | 103/179 [00:36<00:26, 2.86it/s]
439
+
440
  58%|████████████▏ | 104/179 [00:37<00:25, 2.94it/s]
441
+
442
  59%|████████████▎ | 105/179 [00:37<00:29, 2.51it/s]
443
+
444
  59%|████████████▍ | 106/179 [00:37<00:26, 2.75it/s]
445
+
446
  60%|████████████▌ | 107/179 [00:38<00:25, 2.84it/s]
447
+
448
  60%|████████████▋ | 108/179 [00:38<00:24, 2.93it/s]
449
+
450
  61%|████████████▊ | 109/179 [00:39<00:27, 2.51it/s]
451
+
452
  61%|████████████▉ | 110/179 [00:39<00:25, 2.72it/s]
453
+
454
  62%|█████████████ | 111/179 [00:39<00:23, 2.85it/s]
455
+
456
  63%|█████████████▏ | 112/179 [00:40<00:22, 2.92it/s]
457
+
458
  63%|█████████████▎ | 113/179 [00:40<00:26, 2.52it/s]
459
+
460
  64%|█████████████▎ | 114/179 [00:40<00:23, 2.74it/s]
461
+
462
  64%|█████████████▍ | 115/179 [00:41<00:22, 2.86it/s]
463
+
464
  65%|█████████████▌ | 116/179 [00:41<00:21, 2.93it/s]
465
+
466
  65%|█████████████▋ | 117/179 [00:42<00:24, 2.51it/s]
467
+
468
  66%|█████████████▊ | 118/179 [00:42<00:22, 2.74it/s]
469
+
470
  66%|█████████████▉ | 119/179 [00:42<00:21, 2.84it/s]
471
+
472
  67%|██████████████ | 120/179 [00:42<00:20, 2.94it/s]
473
+
474
  68%|██████████████▏ | 121/179 [00:43<00:23, 2.52it/s]
475
+
476
  68%|██████████████▎ | 122/179 [00:43<00:20, 2.75it/s]
477
+
478
  69%|██████████████▍ | 123/179 [00:44<00:19, 2.87it/s]
479
+
480
  69%|██████████████▌ | 124/179 [00:44<00:18, 2.95it/s]
481
+
482
  70%|██████████████▋ | 125/179 [00:44<00:21, 2.53it/s]
483
+
484
  70%|██████████████▊ | 126/179 [00:45<00:19, 2.76it/s]
485
+
486
  71%|██████████████▉ | 127/179 [00:45<00:18, 2.88it/s]
487
+
488
  72%|███████████████ | 128/179 [00:45<00:17, 2.95it/s]
489
+
490
  72%|███████████████▏ | 129/179 [00:46<00:19, 2.51it/s]
491
+
492
  73%|███████████████▎ | 130/179 [00:46<00:17, 2.73it/s]
493
+
494
  73%|███████████████▎ | 131/179 [00:46<00:16, 2.83it/s]
495
+
496
  74%|███████████████▍ | 132/179 [00:47<00:16, 2.91it/s]
497
+
498
  74%|███████████████▌ | 133/179 [00:47<00:18, 2.49it/s]
499
+
500
  75%|███████████████▋ | 134/179 [00:48<00:16, 2.72it/s]
501
+
502
  75%|███████████████▊ | 135/179 [00:48<00:15, 2.84it/s]
503
+
504
  76%|███████████████▉ | 136/179 [00:48<00:14, 2.93it/s]
505
+
506
  77%|████████████████ | 137/179 [00:49<00:16, 2.51it/s]
507
+
508
  77%|████████████████▏ | 138/179 [00:49<00:14, 2.75it/s]
509
+
510
  78%|████████████████▎ | 139/179 [00:49<00:14, 2.85it/s]
511
+
512
  78%|████████████████▍ | 140/179 [00:50<00:13, 2.93it/s]
513
+
514
  79%|████████████████▌ | 141/179 [00:50<00:15, 2.50it/s]
515
+
516
  79%|████████████████▋ | 142/179 [00:51<00:13, 2.74it/s]
517
+
518
  80%|████████████████▊ | 143/179 [00:51<00:12, 2.85it/s]
519
+
520
  80%|████████████████▉ | 144/179 [00:51<00:11, 2.93it/s]
521
+
522
  81%|█████████████████ | 145/179 [00:52<00:13, 2.50it/s]
523
+
524
  82%|█████████████████▏ | 146/179 [00:52<00:12, 2.74it/s]
525
+
526
  82%|█████████████████▏ | 147/179 [00:52<00:11, 2.85it/s]
527
+
528
  83%|█████████████████▎ | 148/179 [00:53<00:10, 2.94it/s]
529
+
530
  83%|█████████████████▍ | 149/179 [00:53<00:11, 2.52it/s]
531
+
532
  84%|█████████████████▌ | 150/179 [00:53<00:10, 2.74it/s]
533
+
534
  84%|█████████████████▋ | 151/179 [00:54<00:09, 2.84it/s]
535
+
536
  85%|█████████████████▊ | 152/179 [00:54<00:09, 2.94it/s]
537
+
538
  85%|█████████████████▉ | 153/179 [00:55<00:10, 2.52it/s]
539
+
540
  86%|██████████████████ | 154/179 [00:55<00:09, 2.76it/s]
541
+
542
  87%|██████████████████▏ | 155/179 [00:55<00:08, 2.87it/s]
543
+
544
  87%|██████████████████▎ | 156/179 [00:56<00:07, 2.93it/s]
545
+
546
  88%|██████████████████▍ | 157/179 [00:56<00:08, 2.51it/s]
547
+
548
  88%|██████████████████▌ | 158/179 [00:56<00:07, 2.73it/s]
549
+
550
  89%|██████████████████▋ | 159/179 [00:57<00:07, 2.85it/s]
551
+
552
  89%|██████████████████▊ | 160/179 [00:57<00:06, 2.94it/s]
553
+
554
  90%|██████████████████▉ | 161/179 [00:58<00:07, 2.51it/s]
555
+
556
  91%|███████████████████ | 162/179 [00:58<00:06, 2.75it/s]
557
+
558
  91%|███████████████████ | 163/179 [00:58<00:05, 2.86it/s]
559
+
560
  92%|███████████████████▏ | 164/179 [00:58<00:05, 2.93it/s]
561
+
562
  92%|███████████████████▎ | 165/179 [00:59<00:05, 2.51it/s]
563
+
564
  93%|███████████████████▍ | 166/179 [00:59<00:04, 2.72it/s]
565
+
566
  93%|███████████████████▌ | 167/179 [01:00<00:04, 2.84it/s]
567
+
568
  94%|███████████████████▋ | 168/179 [01:00<00:03, 2.92it/s]
569
+
570
  94%|███████████████████▊ | 169/179 [01:00<00:03, 2.50it/s]
571
+
572
  95%|███████████████████▉ | 170/179 [01:01<00:03, 2.73it/s]
573
+
574
  96%|████████████████████ | 171/179 [01:01<00:02, 2.83it/s]
575
+
576
  96%|████████████████████▏| 172/179 [01:01<00:02, 2.91it/s]
577
+
578
  97%|████████████████████▎| 173/179 [01:02<00:02, 2.49it/s]
579
+
580
  97%|████████████████████▍| 174/179 [01:02<00:01, 2.72it/s]
581
+
582
  98%|████████████████████▌| 175/179 [01:03<00:01, 2.83it/s]
583
+
584
  98%|████████████████████▋| 176/179 [01:03<00:01, 2.91it/s]
585
+
586
  99%|████████████████████▊| 177/179 [01:03<00:00, 2.50it/s]
587
+
588
  99%|████████████████████▉| 178/179 [01:04<00:00, 2.72it/s]
589
+
590
 
591
+
592
 
593
+
594
  0%| | 0/1000 [01:14<?, ?it/s]
595
+
596
+
597
  [2025-10-18 19:04:31,800] [INFO] [axolotl.utils.data.wrappers.get_dataset_wrapper:87] [PID:42528] Loading dataset: AiAF/conversations with base_type: chat_template and prompt_style: None
598
+ [2025-10-18 19:04:31,818] [INFO] [axolotl.prompt_strategies.chat_template.__call__:969] [PID:42528] Using chat template:
599
+ ---
600
+ {{ bos_token }}
601
+ {% for m in messages %}
602
+ {% set role = 'model' if m['role']=='assistant' else 'user' %}
603
+ {{ '<start_of_turn>' + role + '\n' + m['content'] | trim + '<end_of_turn>\n' }}
604
+ {% endfor %}
605
+ {% if add_generation_prompt %}
606
+ {{ '<start_of_turn>model\n' }}
607
+ {% endif %}
608
+
609
+ ---
610
+
611
+
612
+
613
+
614
+
615
+
616
+
617
+
618
+
619
+
620
+
621
+
622
+
623
+
624
+
625
+
626
+
627
+
628
+
629
+
630
+
631
+
632
+
633
+
634
+
635
+
636
+
637
+
638
+
639
+
640
+
641
+ [2025-10-18 19:38:08,296] [DEBUG] [axolotl.utils.samplers.multipack.pack_parallel:177] [PID:42528] Using single process for pack_parallel, running sequentially.
642
+ [2025-10-18 19:38:19,443] [WARNING] [py.warnings._showwarnmsg:110] [PID:42528] /root/miniconda3/envs/py3.11/lib/python3.11/site-packages/datasets/formatting/torch_formatter.py:90: UserWarning: To copy construct from a tensor, it is recommended to use sourceTensor.detach().clone() or sourceTensor.detach().clone().requires_grad_(True), rather than torch.tensor(sourceTensor).
643
+ return torch.tensor(value, **{**default_dtype, **self.torch_tensor_kwargs})
644
+
645
+
646
  0%| | 1/1000 [35:40<594:06:42, 2140.94s/it]
647
 
648
+
649
  0%| | 1/1000 [35:40<594:06:42, 2140.94s/it]
650
  0%| | 2/1000 [35:48<245:35:41, 885.91s/it]
651
 
652
+
653
  0%| | 2/1000 [35:48<245:35:41, 885.91s/it]
654
  0%| | 3/1000 [35:55<134:15:37, 484.79s/it]
655
 
656
+
657
  0%| | 3/1000 [35:55<134:15:37, 484.79s/it]
658
  0%| | 4/1000 [36:03<81:59:23, 296.35s/it]
659
 
660
+
661
  0%| | 4/1000 [36:03<81:59:23, 296.35s/it]
662
  0%| | 5/1000 [36:10<53:07:06, 192.19s/it]
663
 
664
+
665
  0%| | 5/1000 [36:10<53:07:06, 192.19s/it]
666
  1%| | 6/1000 [36:18<35:43:34, 129.39s/it]
667
 
668
+
669
  1%| | 6/1000 [36:18<35:43:34, 129.39s/it]
670
  1%|▏ | 7/1000 [36:25<24:42:15, 89.56s/it]
671
 
672
+
673
  1%|▏ | 7/1000 [36:25<24:42:15, 89.56s/it]
674
  1%|▏ | 8/1000 [36:33<17:29:08, 63.46s/it]
675
 
676
+
677
  1%|▏ | 8/1000 [36:33<17:29:08, 63.46s/it]
678
  1%|▏ | 9/1000 [36:40<12:39:30, 45.98s/it]
679
 
680
+
681
  1%|▏ | 9/1000 [36:40<12:39:30, 45.98s/it]
682
  1%|▏ | 10/1000 [36:48<9:23:13, 34.13s/it]
683
 
684
+
685
  1%|▏ | 10/1000 [36:48<9:23:13, 34.13s/it]
686
  1%|▏ | 11/1000 [36:56<7:08:45, 26.01s/it]
687
 
688
+
689
  1%|▏ | 11/1000 [36:56<7:08:45, 26.01s/it]
690
  1%|▏ | 12/1000 [37:03<5:35:55, 20.40s/it]
691
 
692
+
693
  1%|▏ | 12/1000 [37:03<5:35:55, 20.40s/it]
694
  1%|▏ | 13/1000 [37:11<4:31:56, 16.53s/it]
695
 
696
+
697
  1%|▏ | 13/1000 [37:11<4:31:56, 16.53s/it]
698
  1%|▎ | 14/1000 [37:18<3:47:27, 13.84s/it]
699
 
700
+
701
  1%|▎ | 14/1000 [37:18<3:47:27, 13.84s/it]
702
  2%|▎ | 15/1000 [37:26<3:16:31, 11.97s/it]
703
 
704
+
705
  2%|▎ | 15/1000 [37:26<3:16:31, 11.97s/it]
706
  2%|▎ | 16/1000 [37:34<2:55:09, 10.68s/it]
707
 
708
+
709
  2%|▎ | 16/1000 [37:34<2:55:09, 10.68s/it]
710
  2%|▎ | 17/1000 [37:41<2:40:00, 9.77s/it]
711
 
712
+
713
  2%|▎ | 17/1000 [37:41<2:40:00, 9.77s/it]
714
  2%|▎ | 18/1000 [37:49<2:29:38, 9.14s/it]
715
 
716
+
717
  2%|▎ | 18/1000 [37:49<2:29:38, 9.14s/it]
718
  2%|▎ | 19/1000 [37:57<2:22:16, 8.70s/it]
719
 
720
+
721
  2%|▎ | 19/1000 [37:57<2:22:16, 8.70s/it]
722
  2%|▍ | 20/1000 [38:04<2:17:12, 8.40s/it]
723
 
724
+
725
  2%|▍ | 20/1000 [38:04<2:17:12, 8.40s/it]
726
  2%|▍ | 21/1000 [38:12<2:13:42, 8.19s/it]
727
 
728
+
729
  2%|▍ | 21/1000 [38:12<2:13:42, 8.19s/it]
730
  2%|▍ | 22/1000 [38:20<2:11:07, 8.04s/it]
731
 
732
+
733
  2%|▍ | 22/1000 [38:20<2:11:07, 8.04s/it]
734
  2%|▍ | 23/1000 [38:28<2:09:16, 7.94s/it]
735
 
736
+
737
  2%|▍ | 23/1000 [38:28<2:09:16, 7.94s/it]
738
  2%|▍ | 24/1000 [38:35<2:07:55, 7.86s/it]
739
 
740
+
741
  2%|▍ | 24/1000 [38:35<2:07:55, 7.86s/it]
742
  2%|▍ | 25/1000 [38:43<2:06:57, 7.81s/it]
743
 
744
+
745
  2%|▍ | 25/1000 [38:43<2:06:57, 7.81s/it]
746
  3%|▍ | 26/1000 [38:51<2:06:19, 7.78s/it]
747
 
748
+
749
  3%|▍ | 26/1000 [38:51<2:06:19, 7.78s/it]
750
  3%|▌ | 27/1000 [38:58<2:05:50, 7.76s/it]
751
 
752
+
753
  3%|▌ | 27/1000 [38:58<2:05:50, 7.76s/it]
754
  3%|▌ | 28/1000 [39:06<2:05:30, 7.75s/it]
755
 
756
+
757
  3%|▌ | 28/1000 [39:06<2:05:30, 7.75s/it]
758
  3%|▌ | 29/1000 [39:14<2:05:09, 7.73s/it]
759
 
760
+
761
  3%|▌ | 29/1000 [39:14<2:05:09, 7.73s/it]
762
  3%|▌ | 30/1000 [39:22<2:04:57, 7.73s/it]
763
 
764
+
765
  3%|▌ | 30/1000 [39:22<2:04:57, 7.73s/it]
766
  3%|▌ | 31/1000 [39:29<2:04:41, 7.72s/it]
767
 
768
+
769
  3%|▌ | 31/1000 [39:29<2:04:41, 7.72s/it]
770
  3%|▌ | 32/1000 [39:37<2:04:23, 7.71s/it]
771
 
772
+
773
  3%|▌ | 32/1000 [39:37<2:04:23, 7.71s/it]
774
  3%|▋ | 33/1000 [39:45<2:04:23, 7.72s/it]
775
 
776
+
777
  3%|▋ | 33/1000 [39:45<2:04:23, 7.72s/it]
778
  3%|▋ | 34/1000 [39:52<2:04:05, 7.71s/it]
779
 
780
+
781
  3%|▋ | 34/1000 [39:52<2:04:05, 7.71s/it]
782
  4%|▋ | 35/1000 [40:00<2:03:56, 7.71s/it]
783
 
784
+
785
  4%|▋ | 35/1000 [40:00<2:03:56, 7.71s/it]
786
  4%|▋ | 36/1000 [40:08<2:03:53, 7.71s/it]
787
 
788
+
789
  4%|▋ | 36/1000 [40:08<2:03:53, 7.71s/it]
790
  4%|▋ | 37/1000 [40:15<2:03:40, 7.71s/it]
791
 
792
+
793
  4%|▋ | 37/1000 [40:15<2:03:40, 7.71s/it]
794
  4%|▋ | 38/1000 [40:23<2:03:29, 7.70s/it]
795
 
796
+
797
  4%|▋ | 38/1000 [40:23<2:03:29, 7.70s/it]
798
  4%|▋ | 39/1000 [40:31<2:03:22, 7.70s/it]
799
 
800
+
801
  4%|▋ | 39/1000 [40:31<2:03:22, 7.70s/it]
802
  4%|▊ | 40/1000 [40:39<2:03:17, 7.71s/it]
803
 
804
+
805
  4%|▊ | 40/1000 [40:39<2:03:17, 7.71s/it]
806
  4%|▊ | 41/1000 [40:46<2:03:04, 7.70s/it]
807
 
808
+
809
  4%|▊ | 41/1000 [40:46<2:03:04, 7.70s/it]
810
  4%|▊ | 42/1000 [40:54<2:03:02, 7.71s/it]
811
 
812
+
813
  4%|▊ | 42/1000 [40:54<2:03:02, 7.71s/it]
814
  4%|▊ | 43/1000 [41:02<2:02:55, 7.71s/it]
815
 
816
+
817
  4%|▊ | 43/1000 [41:02<2:02:55, 7.71s/it]
818
  4%|▊ | 44/1000 [41:09<2:02:44, 7.70s/it]
819
 
820
+
821
  4%|▊ | 44/1000 [41:09<2:02:44, 7.70s/it]
822
  4%|▊ | 45/1000 [41:17<2:02:38, 7.71s/it]
823
 
824
+
825
  4%|▊ | 45/1000 [41:17<2:02:38, 7.71s/it]
826
  5%|▊ | 46/1000 [41:25<2:02:38, 7.71s/it]
827
 
828
+
829
  5%|▊ | 46/1000 [41:25<2:02:38, 7.71s/it]
830
  5%|▉ | 47/1000 [41:33<2:02:28, 7.71s/it]
831
 
832
+
833
  5%|▉ | 47/1000 [41:33<2:02:28, 7.71s/it]
834
  5%|▉ | 48/1000 [41:40<2:02:16, 7.71s/it]
835
 
836
+
837
  5%|▉ | 48/1000 [41:40<2:02:16, 7.71s/it]
838
  5%|▉ | 49/1000 [41:48<2:02:06, 7.70s/it]
839
 
840
+
841
  5%|▉ | 49/1000 [41:48<2:02:06, 7.70s/it]
842
  5%|▉ | 50/1000 [41:56<2:02:08, 7.71s/it]
843
 
844
+
845
  5%|▉ | 50/1000 [41:56<2:02:08, 7.71s/it][2025-10-18 19:44:42,774] [INFO] [axolotl.core.trainers.base.evaluate:376] [PID:42363] Running evaluation step...
846
+ [2025-10-18 19:44:45,590] [DEBUG] [axolotl.utils.samplers.multipack.__len__:462] [PID:42363] generate_batches time: 1.3574237823486328
847
+ [2025-10-18 19:44:46,947] [DEBUG] [axolotl.utils.samplers.multipack.__len__:462] [PID:42363] generate_batches time: 1.3563930988311768
848
+ [2025-10-18 19:44:48,307] [DEBUG] [axolotl.utils.samplers.multipack.__len__:462] [PID:42363] generate_batches time: 1.3596258163452148
849
+ [2025-10-18 19:44:49,675] [DEBUG] [axolotl.utils.samplers.multipack.__len__:462] [PID:42363] generate_batches time: 1.3678362369537354
850
+ [2025-10-18 19:44:49,675] [INFO] [axolotl.utils.samplers.multipack.calc_min_len:438] [PID:42363] gather_len_batches: [179]
851
+
852
+
853
  0%| | 0/179 [00:00<?, ?it/s]
854
+
855
  1%|▎ | 2/179 [00:00<00:28, 6.17it/s]
856
+
857
  2%|▍ | 3/179 [00:00<00:40, 4.35it/s]
858
+
859
  2%|▌ | 4/179 [00:00<00:46, 3.78it/s]
860
+
861
  3%|▋ | 5/179 [00:01<01:18, 2.21it/s]
862
+
863
  3%|▊ | 6/179 [00:02<01:09, 2.50it/s]
864
+
865
  4%|▉ | 7/179 [00:02<01:04, 2.66it/s]
866
+
867
  4%|█ | 8/179 [00:02<01:01, 2.78it/s]
868
+
869
  5%|█▏ | 9/179 [00:03<01:10, 2.42it/s]
870
+
871
  6%|█▏ | 10/179 [00:03<01:03, 2.65it/s]
872
+
873
  6%|█▎ | 11/179 [00:03<01:00, 2.77it/s]
874
+
875
  7%|█▍ | 12/179 [00:04<00:58, 2.87it/s]
876
+
877
  7%|█▌ | 13/179 [00:04<01:07, 2.46it/s]
878
+
879
  8%|█▋ | 14/179 [00:05<01:01, 2.69it/s]
880
+
881
  8%|█▊ | 15/179 [00:05<00:58, 2.80it/s]
882
+
883
  9%|█▉ | 16/179 [00:05<00:56, 2.87it/s]
884
+
885
  9%|██ | 17/179 [00:06<01:05, 2.46it/s]
886
+
887
  10%|██▏ | 18/179 [00:06<01:00, 2.68it/s]
888
+
889
  11%|██▎ | 19/179 [00:06<00:57, 2.78it/s]
890
+
891
  11%|██▍ | 20/179 [00:07<00:55, 2.86it/s]
892
+
893
  12%|██▌ | 21/179 [00:07<01:03, 2.47it/s]
894
+
895
  12%|██▋ | 22/179 [00:07<00:58, 2.68it/s]
896
+
897
  13%|██▊ | 23/179 [00:08<00:55, 2.80it/s]
898
+
899
  13%|██▉ | 24/179 [00:08<00:53, 2.87it/s]
900
+
901
  14%|███ | 25/179 [00:09<01:02, 2.47it/s]
902
+
903
  15%|███▏ | 26/179 [00:09<00:57, 2.68it/s]
904
+
905
  15%|███▎ | 27/179 [00:09<00:54, 2.79it/s]
906
+
907
  16%|███▍ | 28/179 [00:10<00:52, 2.87it/s]
908
+
909
  16%|███▌ | 29/179 [00:10<01:00, 2.46it/s]
910
+
911
  17%|███▋ | 30/179 [00:10<00:55, 2.68it/s]
912
+
913
  17%|███▊ | 31/179 [00:11<00:53, 2.79it/s]
914
+
915
  18%|██��▉ | 32/179 [00:11<00:51, 2.87it/s]
916
+
917
  18%|████ | 33/179 [00:12<00:59, 2.47it/s]
918
+
919
  19%|████▏ | 34/179 [00:12<00:54, 2.68it/s]
920
+
921
  20%|████▎ | 35/179 [00:12<00:51, 2.78it/s]
922
+
923
  20%|████▍ | 36/179 [00:13<00:50, 2.86it/s]
924
+
925
  21%|████▌ | 37/179 [00:13<00:57, 2.47it/s]
926
+
927
  21%|████▋ | 38/179 [00:13<00:52, 2.69it/s]
928
+
929
  22%|████▊ | 39/179 [00:14<00:49, 2.80it/s]
930
+
931
  22%|████▉ | 40/179 [00:14<00:48, 2.87it/s]
932
+
933
  23%|█████ | 41/179 [00:15<00:55, 2.47it/s]
934
+
935
  23%|█████▏ | 42/179 [00:15<00:50, 2.70it/s]
936
+
937
  24%|█████▎ | 43/179 [00:15<00:48, 2.79it/s]
938
+
939
  25%|█████▍ | 44/179 [00:16<00:47, 2.86it/s]
940
+
941
  25%|█████▌ | 45/179 [00:16<00:54, 2.47it/s]
942
+
943
  26%|█████▋ | 46/179 [00:16<00:49, 2.69it/s]
944
+
945
  26%|█████▊ | 47/179 [00:17<00:47, 2.80it/s]
946
+
947
  27%|█████▉ | 48/179 [00:17<00:45, 2.88it/s]
948
+
949
  27%|██████ | 49/179 [00:18<00:52, 2.48it/s]
950
+
951
  28%|██████▏ | 50/179 [00:18<00:47, 2.70it/s]
952
+
953
  28%|██████▎ | 51/179 [00:18<00:45, 2.80it/s]
954
+
955
  29%|██████▍ | 52/179 [00:19<00:44, 2.86it/s]
956
+
957
  30%|██████▌ | 53/179 [00:19<00:51, 2.46it/s]
958
+
959
  30%|██████▋ | 54/179 [00:19<00:46, 2.68it/s]
960
+
961
  31%|██████▊ | 55/179 [00:20<00:44, 2.78it/s]
962
+
963
  31%|██████▉ | 56/179 [00:20<00:42, 2.87it/s]
964
+
965
  32%|███████ | 57/179 [00:21<00:49, 2.46it/s]
966
+
967
  32%|███████▏ | 58/179 [00:21<00:45, 2.68it/s]
968
+
969
  33%|███████▎ | 59/179 [00:21<00:43, 2.79it/s]
970
+
971
  34%|███████▎ | 60/179 [00:22<00:41, 2.86it/s]
972
+
973
  34%|███████▍ | 61/179 [00:22<00:47, 2.47it/s]
974
+
975
  35%|███████▌ | 62/179 [00:22<00:43, 2.68it/s]
976
+
977
  35%|███████▋ | 63/179 [00:23<00:41, 2.80it/s]
978
+
979
  36%|███████▊ | 64/179 [00:23<00:40, 2.87it/s]
980
+
981
  36%|███████▉ | 65/179 [00:24<00:46, 2.47it/s]
982
+
983
  37%|████████ | 66/179 [00:24<00:41, 2.70it/s]
984
+
985
  37%|████████▏ | 67/179 [00:24<00:40, 2.80it/s]
986
+
987
  38%|████████▎ | 68/179 [00:24<00:38, 2.87it/s]
988
+
989
  39%|████████▍ | 69/179 [00:25<00:44, 2.46it/s]
990
+
991
  39%|████████▌ | 70/179 [00:25<00:40, 2.69it/s]
992
+
993
  40%|████████▋ | 71/179 [00:26<00:38, 2.80it/s]
994
+
995
  40%|████████▊ | 72/179 [00:26<00:37, 2.87it/s]
996
+
997
  41%|████████▉ | 73/179 [00:26<00:42, 2.47it/s]
998
+
999
  41%|█████████ | 74/179 [00:27<00:38, 2.69it/s]
1000
+
1001
  42%|█████████▏ | 75/179 [00:27<00:37, 2.80it/s]
1002
+
1003
  42%|█████████▎ | 76/179 [00:27<00:35, 2.87it/s]
1004
+
1005
  43%|█████████▍ | 77/179 [00:28<00:41, 2.48it/s]
1006
+
1007
  44%|█████████▌ | 78/179 [00:28<00:37, 2.69it/s]
1008
+
1009
  44%|█████████▋ | 79/179 [00:29<00:35, 2.79it/s]
1010
+
1011
  45%|█████████▊ | 80/179 [00:29<00:34, 2.87it/s]
1012
+
1013
  45%|█████████▉ | 81/179 [00:29<00:39, 2.47it/s]
1014
+
1015
  46%|██████████ | 82/179 [00:30<00:36, 2.69it/s]
1016
+
1017
  46%|██████████▏ | 83/179 [00:30<00:34, 2.79it/s]
1018
+
1019
  47%|██████████▎ | 84/179 [00:30<00:33, 2.87it/s]
1020
+
1021
  47%|██████████▍ | 85/179 [00:31<00:38, 2.47it/s]
1022
+
1023
  48%|██████████▌ | 86/179 [00:31<00:34, 2.69it/s]
1024
+
1025
  49%|██████████▋ | 87/179 [00:32<00:32, 2.81it/s]
1026
+
1027
  49%|██████████▊ | 88/179 [00:32<00:31, 2.88it/s]
1028
+
1029
  50%|██████████▉ | 89/179 [00:32<00:36, 2.48it/s]
1030
+
1031
  50%|███████████ | 90/179 [00:33<00:32, 2.71it/s]
1032
+
1033
  51%|███████████▏ | 91/179 [00:33<00:31, 2.81it/s]
1034
+
1035
  51%|███████████▎ | 92/179 [00:33<00:30, 2.88it/s]
1036
+
1037
  52%|███████████▍ | 93/179 [00:34<00:34, 2.47it/s]
1038
+
1039
  53%|███████████▌ | 94/179 [00:34<00:31, 2.70it/s]
1040
+
1041
  53%|███████████▋ | 95/179 [00:35<00:30, 2.79it/s]
1042
+
1043
  54%|███████████▊ | 96/179 [00:35<00:28, 2.87it/s]
1044
+
1045
  54%|███████████▉ | 97/179 [00:35<00:33, 2.48it/s]
1046
+
1047
  55%|████████████ | 98/179 [00:36<00:30, 2.69it/s]
1048
+
1049
  55%|████████████▏ | 99/179 [00:36<00:28, 2.79it/s]
1050
+
1051
  56%|███████████▋ | 100/179 [00:36<00:27, 2.87it/s]
1052
+
1053
  56%|███████████▊ | 101/179 [00:37<00:31, 2.46it/s]
1054
+
1055
  57%|███████████▉ | 102/179 [00:37<00:28, 2.69it/s]
1056
+
1057
  58%|████████████ | 103/179 [00:37<00:27, 2.80it/s]
1058
+
1059
  58%|████████████▏ | 104/179 [00:38<00:26, 2.86it/s]
1060
+
1061
  59%|████████████▎ | 105/179 [00:38<00:30, 2.46it/s]
1062
+
1063
  59%|████████████▍ | 106/179 [00:39<00:27, 2.69it/s]
1064
+
1065
  60%|████████████▌ | 107/179 [00:39<00:25, 2.79it/s]
1066
+
1067
  60%|████████████▋ | 108/179 [00:39<00:24, 2.87it/s]
1068
+
1069
  61%|████████████▊ | 109/179 [00:40<00:28, 2.45it/s]
1070
+
1071
  61%|████████████▉ | 110/179 [00:40<00:25, 2.70it/s]
1072
+
1073
  62%|█████████████ | 111/179 [00:40<00:24, 2.81it/s]
1074
+
1075
  63%|█████████████▏ | 112/179 [00:41<00:23, 2.89it/s]
1076
+
1077
  63%|█████████████▎ | 113/179 [00:41<00:26, 2.46it/s]
1078
+
1079
  64%|█████████████▎ | 114/179 [00:42<00:24, 2.70it/s]
1080
+
1081
  64%|█████████████▍ | 115/179 [00:42<00:22, 2.81it/s]
1082
+
1083
  65%|█████████████▌ | 116/179 [00:42<00:21, 2.89it/s]
1084
+
1085
  65%|█████████████▋ | 117/179 [00:43<00:25, 2.47it/s]
1086
+
1087
  66%|█████████████▊ | 118/179 [00:43<00:22, 2.68it/s]
1088
+
1089
  66%|█████████████▉ | 119/179 [00:43<00:21, 2.78it/s]
1090
+
1091
  67%|██████████████ | 120/179 [00:44<00:20, 2.86it/s]
1092
+
1093
  68%|██████████████▏ | 121/179 [00:44<00:23, 2.47it/s]
1094
+
1095
  68%|██████████████▎ | 122/179 [00:45<00:21, 2.69it/s]
1096
+
1097
  69%|██████████████▍ | 123/179 [00:45<00:20, 2.79it/s]
1098
+
1099
  69%|██████████████▌ | 124/179 [00:45<00:19, 2.87it/s]
1100
+
1101
  70%|██████████████▋ | 125/179 [00:46<00:21, 2.47it/s]
1102
+
1103
  70%|██████████████▊ | 126/179 [00:46<00:19, 2.68it/s]
1104
+
1105
  71%|██████████████▉ | 127/179 [00:46<00:18, 2.80it/s]
1106
+
1107
  72%|███████████████ | 128/179 [00:47<00:17, 2.88it/s]
1108
+
1109
  72%|███████████████▏ | 129/179 [00:47<00:20, 2.46it/s]
1110
+
1111
  73%|███████████████▎ | 130/179 [00:48<00:18, 2.68it/s]
1112
+
1113
  73%|███████████████▎ | 131/179 [00:48<00:17, 2.78it/s]
1114
+
1115
  74%|███████████████▍ | 132/179 [00:48<00:16, 2.86it/s]
1116
+
1117
  74%|███████████████▌ | 133/179 [00:49<00:18, 2.46it/s]
1118
+
1119
  75%|███████████████▋ | 134/179 [00:49<00:16, 2.68it/s]
1120
+
1121
  75%|███████████████▊ | 135/179 [00:49<00:15, 2.79it/s]
1122
+
1123
  76%|███████████████▉ | 136/179 [00:50<00:14, 2.87it/s]
1124
+
1125
  77%|████████████████ | 137/179 [00:50<00:17, 2.46it/s]
1126
+
1127
  77%|████████████████▏ | 138/179 [00:51<00:15, 2.70it/s]
1128
+
1129
  78%|████████████████▎ | 139/179 [00:51<00:14, 2.79it/s]
1130
+
1131
  78%|████████████████▍ | 140/179 [00:51<00:13, 2.86it/s]
1132
+
1133
  79%|████████████████▌ | 141/179 [00:52<00:15, 2.44it/s]
1134
+
1135
  79%|████████████████▋ | 142/179 [00:52<00:13, 2.68it/s]
1136
+
1137
  80%|████████████████▊ | 143/179 [00:52<00:12, 2.78it/s]
1138
+
1139
  80%|████████████████▉ | 144/179 [00:53<00:12, 2.85it/s]
1140
+
1141
  81%|█████████████████ | 145/179 [00:53<00:13, 2.44it/s]
1142
+
1143
  82%|█████████████████▏ | 146/179 [00:54<00:12, 2.67it/s]
1144
+
1145
  82%|█████████████████▏ | 147/179 [00:54<00:11, 2.78it/s]
1146
+
1147
  83%|█████████████████▎ | 148/179 [00:54<00:10, 2.86it/s]
1148
+
1149
  83%|█████████████████▍ | 149/179 [00:55<00:12, 2.46it/s]
1150
+
1151
  84%|█████████████████▌ | 150/179 [00:55<00:10, 2.68it/s]
1152
+
1153
  84%|█████████████████▋ | 151/179 [00:55<00:10, 2.78it/s]
1154
+
1155
  85%|█████████████████▊ | 152/179 [00:56<00:09, 2.87it/s]
1156
+
1157
  85%|█████████████████▉ | 153/179 [00:56<00:10, 2.47it/s]
1158
+
1159
  86%|██████████████████ | 154/179 [00:56<00:09, 2.68it/s]
1160
+
1161
  87%|██████████████████▏ | 155/179 [00:57<00:08, 2.78it/s]
1162
+
1163
  87%|██████████████████▎ | 156/179 [00:57<00:08, 2.86it/s]
1164
+
1165
  88%|██████████████████▍ | 157/179 [00:58<00:08, 2.46it/s]
1166
+
1167
  88%|██████████████████▌ | 158/179 [00:58<00:07, 2.68it/s]
1168
+
1169
  89%|██████████████████▋ | 159/179 [00:58<00:07, 2.79it/s]
1170
+
1171
  89%|██████████████████▊ | 160/179 [00:59<00:06, 2.88it/s]
1172
+
1173
  90%|██████████████████▉ | 161/179 [00:59<00:07, 2.48it/s]
1174
+
1175
  91%|███████████████████ | 162/179 [00:59<00:06, 2.71it/s]
1176
+
1177
  91%|███████████████████ | 163/179 [01:00<00:05, 2.81it/s]
1178
+
1179
  92%|███████████████████▏ | 164/179 [01:00<00:05, 2.89it/s]
1180
+
1181
  92%|███████████████████▎ | 165/179 [01:01<00:05, 2.47it/s]
1182
+
1183
  93%|███████████████████▍ | 166/179 [01:01<00:04, 2.69it/s]
1184
+
1185
  93%|███████████████████▌ | 167/179 [01:01<00:04, 2.79it/s]
1186
+
1187
  94%|███████████████████▋ | 168/179 [01:02<00:03, 2.87it/s]
1188
+
1189
  94%|███████████████████▊ | 169/179 [01:02<00:04, 2.47it/s]
1190
+
1191
  95%|███████████████████▉ | 170/179 [01:02<00:03, 2.69it/s]
1192
+
1193
  96%|████████████████████ | 171/179 [01:03<00:02, 2.79it/s]
1194
+
1195
  96%|████████████████████▏| 172/179 [01:03<00:02, 2.87it/s]
1196
+
1197
  97%|████████████████████▎| 173/179 [01:04<00:02, 2.47it/s]
1198
+
1199
  97%|████████████████████▍| 174/179 [01:04<00:01, 2.69it/s]
1200
+
1201
  98%|████████████████████▌| 175/179 [01:04<00:01, 2.79it/s]
1202
+
1203
  98%|████████████████████▋| 176/179 [01:05<00:01, 2.86it/s]
1204
+
1205
  99%|████████████████████▊| 177/179 [01:05<00:00, 2.47it/s]
1206
+
1207
  99%|████████████████████▉| 178/179 [01:05<00:00, 2.69it/s]
1208
+
1209
 
1210
+
1211
 
1212
+
1213
  5%|▉ | 50/1000 [43:11<2:02:08, 7.71s/it]
1214
+
1215
+
1216
  [2025-10-18 19:45:58,394] [INFO] [axolotl.core.trainers.base._save:664] [PID:42363] Saving model checkpoint to ./outputs/sft/gemma-2-2b-it-rp-sft-qlora/checkpoint-50
1217
+
1218
  5%|▉ | 51/1000 [43:21<8:12:20, 31.13s/it]
1219
 
1220
+
1221
  5%|▉ | 51/1000 [43:21<8:12:20, 31.13s/it]
special_tokens_map.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<start_of_turn>",
4
+ "<end_of_turn>"
5
+ ],
6
+ "bos_token": {
7
+ "content": "<bos>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false
12
+ },
13
+ "eos_token": {
14
+ "content": "<eos>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ },
20
+ "pad_token": {
21
+ "content": "<pad>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false
26
+ },
27
+ "unk_token": {
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false
33
+ }
34
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f7eee611703c5ce5d1eee32d9cdcfe465647b8aff0c1dfb3bed7ad7dbb05060
3
+ size 34362873
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2
3
+ size 4241003
tokenizer_config.json ADDED
@@ -0,0 +1,2013 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<pad>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<eos>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "<bos>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "3": {
30
+ "content": "<unk>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "4": {
38
+ "content": "<mask>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": false
44
+ },
45
+ "5": {
46
+ "content": "<2mass>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": false
52
+ },
53
+ "6": {
54
+ "content": "[@BOS@]",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": false
60
+ },
61
+ "7": {
62
+ "content": "<unused0>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": false
68
+ },
69
+ "8": {
70
+ "content": "<unused1>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": false
76
+ },
77
+ "9": {
78
+ "content": "<unused2>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": false
84
+ },
85
+ "10": {
86
+ "content": "<unused3>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": false
92
+ },
93
+ "11": {
94
+ "content": "<unused4>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": false
100
+ },
101
+ "12": {
102
+ "content": "<unused5>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": false
108
+ },
109
+ "13": {
110
+ "content": "<unused6>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": false
116
+ },
117
+ "14": {
118
+ "content": "<unused7>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "15": {
126
+ "content": "<unused8>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "16": {
134
+ "content": "<unused9>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "17": {
142
+ "content": "<unused10>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "18": {
150
+ "content": "<unused11>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "19": {
158
+ "content": "<unused12>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "20": {
166
+ "content": "<unused13>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "21": {
174
+ "content": "<unused14>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ },
181
+ "22": {
182
+ "content": "<unused15>",
183
+ "lstrip": false,
184
+ "normalized": false,
185
+ "rstrip": false,
186
+ "single_word": false,
187
+ "special": false
188
+ },
189
+ "23": {
190
+ "content": "<unused16>",
191
+ "lstrip": false,
192
+ "normalized": false,
193
+ "rstrip": false,
194
+ "single_word": false,
195
+ "special": false
196
+ },
197
+ "24": {
198
+ "content": "<unused17>",
199
+ "lstrip": false,
200
+ "normalized": false,
201
+ "rstrip": false,
202
+ "single_word": false,
203
+ "special": false
204
+ },
205
+ "25": {
206
+ "content": "<unused18>",
207
+ "lstrip": false,
208
+ "normalized": false,
209
+ "rstrip": false,
210
+ "single_word": false,
211
+ "special": false
212
+ },
213
+ "26": {
214
+ "content": "<unused19>",
215
+ "lstrip": false,
216
+ "normalized": false,
217
+ "rstrip": false,
218
+ "single_word": false,
219
+ "special": false
220
+ },
221
+ "27": {
222
+ "content": "<unused20>",
223
+ "lstrip": false,
224
+ "normalized": false,
225
+ "rstrip": false,
226
+ "single_word": false,
227
+ "special": false
228
+ },
229
+ "28": {
230
+ "content": "<unused21>",
231
+ "lstrip": false,
232
+ "normalized": false,
233
+ "rstrip": false,
234
+ "single_word": false,
235
+ "special": false
236
+ },
237
+ "29": {
238
+ "content": "<unused22>",
239
+ "lstrip": false,
240
+ "normalized": false,
241
+ "rstrip": false,
242
+ "single_word": false,
243
+ "special": false
244
+ },
245
+ "30": {
246
+ "content": "<unused23>",
247
+ "lstrip": false,
248
+ "normalized": false,
249
+ "rstrip": false,
250
+ "single_word": false,
251
+ "special": false
252
+ },
253
+ "31": {
254
+ "content": "<unused24>",
255
+ "lstrip": false,
256
+ "normalized": false,
257
+ "rstrip": false,
258
+ "single_word": false,
259
+ "special": false
260
+ },
261
+ "32": {
262
+ "content": "<unused25>",
263
+ "lstrip": false,
264
+ "normalized": false,
265
+ "rstrip": false,
266
+ "single_word": false,
267
+ "special": false
268
+ },
269
+ "33": {
270
+ "content": "<unused26>",
271
+ "lstrip": false,
272
+ "normalized": false,
273
+ "rstrip": false,
274
+ "single_word": false,
275
+ "special": false
276
+ },
277
+ "34": {
278
+ "content": "<unused27>",
279
+ "lstrip": false,
280
+ "normalized": false,
281
+ "rstrip": false,
282
+ "single_word": false,
283
+ "special": false
284
+ },
285
+ "35": {
286
+ "content": "<unused28>",
287
+ "lstrip": false,
288
+ "normalized": false,
289
+ "rstrip": false,
290
+ "single_word": false,
291
+ "special": false
292
+ },
293
+ "36": {
294
+ "content": "<unused29>",
295
+ "lstrip": false,
296
+ "normalized": false,
297
+ "rstrip": false,
298
+ "single_word": false,
299
+ "special": false
300
+ },
301
+ "37": {
302
+ "content": "<unused30>",
303
+ "lstrip": false,
304
+ "normalized": false,
305
+ "rstrip": false,
306
+ "single_word": false,
307
+ "special": false
308
+ },
309
+ "38": {
310
+ "content": "<unused31>",
311
+ "lstrip": false,
312
+ "normalized": false,
313
+ "rstrip": false,
314
+ "single_word": false,
315
+ "special": false
316
+ },
317
+ "39": {
318
+ "content": "<unused32>",
319
+ "lstrip": false,
320
+ "normalized": false,
321
+ "rstrip": false,
322
+ "single_word": false,
323
+ "special": false
324
+ },
325
+ "40": {
326
+ "content": "<unused33>",
327
+ "lstrip": false,
328
+ "normalized": false,
329
+ "rstrip": false,
330
+ "single_word": false,
331
+ "special": false
332
+ },
333
+ "41": {
334
+ "content": "<unused34>",
335
+ "lstrip": false,
336
+ "normalized": false,
337
+ "rstrip": false,
338
+ "single_word": false,
339
+ "special": false
340
+ },
341
+ "42": {
342
+ "content": "<unused35>",
343
+ "lstrip": false,
344
+ "normalized": false,
345
+ "rstrip": false,
346
+ "single_word": false,
347
+ "special": false
348
+ },
349
+ "43": {
350
+ "content": "<unused36>",
351
+ "lstrip": false,
352
+ "normalized": false,
353
+ "rstrip": false,
354
+ "single_word": false,
355
+ "special": false
356
+ },
357
+ "44": {
358
+ "content": "<unused37>",
359
+ "lstrip": false,
360
+ "normalized": false,
361
+ "rstrip": false,
362
+ "single_word": false,
363
+ "special": false
364
+ },
365
+ "45": {
366
+ "content": "<unused38>",
367
+ "lstrip": false,
368
+ "normalized": false,
369
+ "rstrip": false,
370
+ "single_word": false,
371
+ "special": false
372
+ },
373
+ "46": {
374
+ "content": "<unused39>",
375
+ "lstrip": false,
376
+ "normalized": false,
377
+ "rstrip": false,
378
+ "single_word": false,
379
+ "special": false
380
+ },
381
+ "47": {
382
+ "content": "<unused40>",
383
+ "lstrip": false,
384
+ "normalized": false,
385
+ "rstrip": false,
386
+ "single_word": false,
387
+ "special": false
388
+ },
389
+ "48": {
390
+ "content": "<unused41>",
391
+ "lstrip": false,
392
+ "normalized": false,
393
+ "rstrip": false,
394
+ "single_word": false,
395
+ "special": false
396
+ },
397
+ "49": {
398
+ "content": "<unused42>",
399
+ "lstrip": false,
400
+ "normalized": false,
401
+ "rstrip": false,
402
+ "single_word": false,
403
+ "special": false
404
+ },
405
+ "50": {
406
+ "content": "<unused43>",
407
+ "lstrip": false,
408
+ "normalized": false,
409
+ "rstrip": false,
410
+ "single_word": false,
411
+ "special": false
412
+ },
413
+ "51": {
414
+ "content": "<unused44>",
415
+ "lstrip": false,
416
+ "normalized": false,
417
+ "rstrip": false,
418
+ "single_word": false,
419
+ "special": false
420
+ },
421
+ "52": {
422
+ "content": "<unused45>",
423
+ "lstrip": false,
424
+ "normalized": false,
425
+ "rstrip": false,
426
+ "single_word": false,
427
+ "special": false
428
+ },
429
+ "53": {
430
+ "content": "<unused46>",
431
+ "lstrip": false,
432
+ "normalized": false,
433
+ "rstrip": false,
434
+ "single_word": false,
435
+ "special": false
436
+ },
437
+ "54": {
438
+ "content": "<unused47>",
439
+ "lstrip": false,
440
+ "normalized": false,
441
+ "rstrip": false,
442
+ "single_word": false,
443
+ "special": false
444
+ },
445
+ "55": {
446
+ "content": "<unused48>",
447
+ "lstrip": false,
448
+ "normalized": false,
449
+ "rstrip": false,
450
+ "single_word": false,
451
+ "special": false
452
+ },
453
+ "56": {
454
+ "content": "<unused49>",
455
+ "lstrip": false,
456
+ "normalized": false,
457
+ "rstrip": false,
458
+ "single_word": false,
459
+ "special": false
460
+ },
461
+ "57": {
462
+ "content": "<unused50>",
463
+ "lstrip": false,
464
+ "normalized": false,
465
+ "rstrip": false,
466
+ "single_word": false,
467
+ "special": false
468
+ },
469
+ "58": {
470
+ "content": "<unused51>",
471
+ "lstrip": false,
472
+ "normalized": false,
473
+ "rstrip": false,
474
+ "single_word": false,
475
+ "special": false
476
+ },
477
+ "59": {
478
+ "content": "<unused52>",
479
+ "lstrip": false,
480
+ "normalized": false,
481
+ "rstrip": false,
482
+ "single_word": false,
483
+ "special": false
484
+ },
485
+ "60": {
486
+ "content": "<unused53>",
487
+ "lstrip": false,
488
+ "normalized": false,
489
+ "rstrip": false,
490
+ "single_word": false,
491
+ "special": false
492
+ },
493
+ "61": {
494
+ "content": "<unused54>",
495
+ "lstrip": false,
496
+ "normalized": false,
497
+ "rstrip": false,
498
+ "single_word": false,
499
+ "special": false
500
+ },
501
+ "62": {
502
+ "content": "<unused55>",
503
+ "lstrip": false,
504
+ "normalized": false,
505
+ "rstrip": false,
506
+ "single_word": false,
507
+ "special": false
508
+ },
509
+ "63": {
510
+ "content": "<unused56>",
511
+ "lstrip": false,
512
+ "normalized": false,
513
+ "rstrip": false,
514
+ "single_word": false,
515
+ "special": false
516
+ },
517
+ "64": {
518
+ "content": "<unused57>",
519
+ "lstrip": false,
520
+ "normalized": false,
521
+ "rstrip": false,
522
+ "single_word": false,
523
+ "special": false
524
+ },
525
+ "65": {
526
+ "content": "<unused58>",
527
+ "lstrip": false,
528
+ "normalized": false,
529
+ "rstrip": false,
530
+ "single_word": false,
531
+ "special": false
532
+ },
533
+ "66": {
534
+ "content": "<unused59>",
535
+ "lstrip": false,
536
+ "normalized": false,
537
+ "rstrip": false,
538
+ "single_word": false,
539
+ "special": false
540
+ },
541
+ "67": {
542
+ "content": "<unused60>",
543
+ "lstrip": false,
544
+ "normalized": false,
545
+ "rstrip": false,
546
+ "single_word": false,
547
+ "special": false
548
+ },
549
+ "68": {
550
+ "content": "<unused61>",
551
+ "lstrip": false,
552
+ "normalized": false,
553
+ "rstrip": false,
554
+ "single_word": false,
555
+ "special": false
556
+ },
557
+ "69": {
558
+ "content": "<unused62>",
559
+ "lstrip": false,
560
+ "normalized": false,
561
+ "rstrip": false,
562
+ "single_word": false,
563
+ "special": false
564
+ },
565
+ "70": {
566
+ "content": "<unused63>",
567
+ "lstrip": false,
568
+ "normalized": false,
569
+ "rstrip": false,
570
+ "single_word": false,
571
+ "special": false
572
+ },
573
+ "71": {
574
+ "content": "<unused64>",
575
+ "lstrip": false,
576
+ "normalized": false,
577
+ "rstrip": false,
578
+ "single_word": false,
579
+ "special": false
580
+ },
581
+ "72": {
582
+ "content": "<unused65>",
583
+ "lstrip": false,
584
+ "normalized": false,
585
+ "rstrip": false,
586
+ "single_word": false,
587
+ "special": false
588
+ },
589
+ "73": {
590
+ "content": "<unused66>",
591
+ "lstrip": false,
592
+ "normalized": false,
593
+ "rstrip": false,
594
+ "single_word": false,
595
+ "special": false
596
+ },
597
+ "74": {
598
+ "content": "<unused67>",
599
+ "lstrip": false,
600
+ "normalized": false,
601
+ "rstrip": false,
602
+ "single_word": false,
603
+ "special": false
604
+ },
605
+ "75": {
606
+ "content": "<unused68>",
607
+ "lstrip": false,
608
+ "normalized": false,
609
+ "rstrip": false,
610
+ "single_word": false,
611
+ "special": false
612
+ },
613
+ "76": {
614
+ "content": "<unused69>",
615
+ "lstrip": false,
616
+ "normalized": false,
617
+ "rstrip": false,
618
+ "single_word": false,
619
+ "special": false
620
+ },
621
+ "77": {
622
+ "content": "<unused70>",
623
+ "lstrip": false,
624
+ "normalized": false,
625
+ "rstrip": false,
626
+ "single_word": false,
627
+ "special": false
628
+ },
629
+ "78": {
630
+ "content": "<unused71>",
631
+ "lstrip": false,
632
+ "normalized": false,
633
+ "rstrip": false,
634
+ "single_word": false,
635
+ "special": false
636
+ },
637
+ "79": {
638
+ "content": "<unused72>",
639
+ "lstrip": false,
640
+ "normalized": false,
641
+ "rstrip": false,
642
+ "single_word": false,
643
+ "special": false
644
+ },
645
+ "80": {
646
+ "content": "<unused73>",
647
+ "lstrip": false,
648
+ "normalized": false,
649
+ "rstrip": false,
650
+ "single_word": false,
651
+ "special": false
652
+ },
653
+ "81": {
654
+ "content": "<unused74>",
655
+ "lstrip": false,
656
+ "normalized": false,
657
+ "rstrip": false,
658
+ "single_word": false,
659
+ "special": false
660
+ },
661
+ "82": {
662
+ "content": "<unused75>",
663
+ "lstrip": false,
664
+ "normalized": false,
665
+ "rstrip": false,
666
+ "single_word": false,
667
+ "special": false
668
+ },
669
+ "83": {
670
+ "content": "<unused76>",
671
+ "lstrip": false,
672
+ "normalized": false,
673
+ "rstrip": false,
674
+ "single_word": false,
675
+ "special": false
676
+ },
677
+ "84": {
678
+ "content": "<unused77>",
679
+ "lstrip": false,
680
+ "normalized": false,
681
+ "rstrip": false,
682
+ "single_word": false,
683
+ "special": false
684
+ },
685
+ "85": {
686
+ "content": "<unused78>",
687
+ "lstrip": false,
688
+ "normalized": false,
689
+ "rstrip": false,
690
+ "single_word": false,
691
+ "special": false
692
+ },
693
+ "86": {
694
+ "content": "<unused79>",
695
+ "lstrip": false,
696
+ "normalized": false,
697
+ "rstrip": false,
698
+ "single_word": false,
699
+ "special": false
700
+ },
701
+ "87": {
702
+ "content": "<unused80>",
703
+ "lstrip": false,
704
+ "normalized": false,
705
+ "rstrip": false,
706
+ "single_word": false,
707
+ "special": false
708
+ },
709
+ "88": {
710
+ "content": "<unused81>",
711
+ "lstrip": false,
712
+ "normalized": false,
713
+ "rstrip": false,
714
+ "single_word": false,
715
+ "special": false
716
+ },
717
+ "89": {
718
+ "content": "<unused82>",
719
+ "lstrip": false,
720
+ "normalized": false,
721
+ "rstrip": false,
722
+ "single_word": false,
723
+ "special": false
724
+ },
725
+ "90": {
726
+ "content": "<unused83>",
727
+ "lstrip": false,
728
+ "normalized": false,
729
+ "rstrip": false,
730
+ "single_word": false,
731
+ "special": false
732
+ },
733
+ "91": {
734
+ "content": "<unused84>",
735
+ "lstrip": false,
736
+ "normalized": false,
737
+ "rstrip": false,
738
+ "single_word": false,
739
+ "special": false
740
+ },
741
+ "92": {
742
+ "content": "<unused85>",
743
+ "lstrip": false,
744
+ "normalized": false,
745
+ "rstrip": false,
746
+ "single_word": false,
747
+ "special": false
748
+ },
749
+ "93": {
750
+ "content": "<unused86>",
751
+ "lstrip": false,
752
+ "normalized": false,
753
+ "rstrip": false,
754
+ "single_word": false,
755
+ "special": false
756
+ },
757
+ "94": {
758
+ "content": "<unused87>",
759
+ "lstrip": false,
760
+ "normalized": false,
761
+ "rstrip": false,
762
+ "single_word": false,
763
+ "special": false
764
+ },
765
+ "95": {
766
+ "content": "<unused88>",
767
+ "lstrip": false,
768
+ "normalized": false,
769
+ "rstrip": false,
770
+ "single_word": false,
771
+ "special": false
772
+ },
773
+ "96": {
774
+ "content": "<unused89>",
775
+ "lstrip": false,
776
+ "normalized": false,
777
+ "rstrip": false,
778
+ "single_word": false,
779
+ "special": false
780
+ },
781
+ "97": {
782
+ "content": "<unused90>",
783
+ "lstrip": false,
784
+ "normalized": false,
785
+ "rstrip": false,
786
+ "single_word": false,
787
+ "special": false
788
+ },
789
+ "98": {
790
+ "content": "<unused91>",
791
+ "lstrip": false,
792
+ "normalized": false,
793
+ "rstrip": false,
794
+ "single_word": false,
795
+ "special": false
796
+ },
797
+ "99": {
798
+ "content": "<unused92>",
799
+ "lstrip": false,
800
+ "normalized": false,
801
+ "rstrip": false,
802
+ "single_word": false,
803
+ "special": false
804
+ },
805
+ "100": {
806
+ "content": "<unused93>",
807
+ "lstrip": false,
808
+ "normalized": false,
809
+ "rstrip": false,
810
+ "single_word": false,
811
+ "special": false
812
+ },
813
+ "101": {
814
+ "content": "<unused94>",
815
+ "lstrip": false,
816
+ "normalized": false,
817
+ "rstrip": false,
818
+ "single_word": false,
819
+ "special": false
820
+ },
821
+ "102": {
822
+ "content": "<unused95>",
823
+ "lstrip": false,
824
+ "normalized": false,
825
+ "rstrip": false,
826
+ "single_word": false,
827
+ "special": false
828
+ },
829
+ "103": {
830
+ "content": "<unused96>",
831
+ "lstrip": false,
832
+ "normalized": false,
833
+ "rstrip": false,
834
+ "single_word": false,
835
+ "special": false
836
+ },
837
+ "104": {
838
+ "content": "<unused97>",
839
+ "lstrip": false,
840
+ "normalized": false,
841
+ "rstrip": false,
842
+ "single_word": false,
843
+ "special": false
844
+ },
845
+ "105": {
846
+ "content": "<unused98>",
847
+ "lstrip": false,
848
+ "normalized": false,
849
+ "rstrip": false,
850
+ "single_word": false,
851
+ "special": false
852
+ },
853
+ "106": {
854
+ "content": "<start_of_turn>",
855
+ "lstrip": false,
856
+ "normalized": false,
857
+ "rstrip": false,
858
+ "single_word": false,
859
+ "special": true
860
+ },
861
+ "107": {
862
+ "content": "<end_of_turn>",
863
+ "lstrip": false,
864
+ "normalized": false,
865
+ "rstrip": false,
866
+ "single_word": false,
867
+ "special": true
868
+ },
869
+ "108": {
870
+ "content": "\n",
871
+ "lstrip": false,
872
+ "normalized": false,
873
+ "rstrip": false,
874
+ "single_word": false,
875
+ "special": false
876
+ },
877
+ "109": {
878
+ "content": "\n\n",
879
+ "lstrip": false,
880
+ "normalized": false,
881
+ "rstrip": false,
882
+ "single_word": false,
883
+ "special": false
884
+ },
885
+ "110": {
886
+ "content": "\n\n\n",
887
+ "lstrip": false,
888
+ "normalized": false,
889
+ "rstrip": false,
890
+ "single_word": false,
891
+ "special": false
892
+ },
893
+ "111": {
894
+ "content": "\n\n\n\n",
895
+ "lstrip": false,
896
+ "normalized": false,
897
+ "rstrip": false,
898
+ "single_word": false,
899
+ "special": false
900
+ },
901
+ "112": {
902
+ "content": "\n\n\n\n\n",
903
+ "lstrip": false,
904
+ "normalized": false,
905
+ "rstrip": false,
906
+ "single_word": false,
907
+ "special": false
908
+ },
909
+ "113": {
910
+ "content": "\n\n\n\n\n\n",
911
+ "lstrip": false,
912
+ "normalized": false,
913
+ "rstrip": false,
914
+ "single_word": false,
915
+ "special": false
916
+ },
917
+ "114": {
918
+ "content": "\n\n\n\n\n\n\n",
919
+ "lstrip": false,
920
+ "normalized": false,
921
+ "rstrip": false,
922
+ "single_word": false,
923
+ "special": false
924
+ },
925
+ "115": {
926
+ "content": "\n\n\n\n\n\n\n\n",
927
+ "lstrip": false,
928
+ "normalized": false,
929
+ "rstrip": false,
930
+ "single_word": false,
931
+ "special": false
932
+ },
933
+ "116": {
934
+ "content": "\n\n\n\n\n\n\n\n\n",
935
+ "lstrip": false,
936
+ "normalized": false,
937
+ "rstrip": false,
938
+ "single_word": false,
939
+ "special": false
940
+ },
941
+ "117": {
942
+ "content": "\n\n\n\n\n\n\n\n\n\n",
943
+ "lstrip": false,
944
+ "normalized": false,
945
+ "rstrip": false,
946
+ "single_word": false,
947
+ "special": false
948
+ },
949
+ "118": {
950
+ "content": "\n\n\n\n\n\n\n\n\n\n\n",
951
+ "lstrip": false,
952
+ "normalized": false,
953
+ "rstrip": false,
954
+ "single_word": false,
955
+ "special": false
956
+ },
957
+ "119": {
958
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n",
959
+ "lstrip": false,
960
+ "normalized": false,
961
+ "rstrip": false,
962
+ "single_word": false,
963
+ "special": false
964
+ },
965
+ "120": {
966
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n",
967
+ "lstrip": false,
968
+ "normalized": false,
969
+ "rstrip": false,
970
+ "single_word": false,
971
+ "special": false
972
+ },
973
+ "121": {
974
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
975
+ "lstrip": false,
976
+ "normalized": false,
977
+ "rstrip": false,
978
+ "single_word": false,
979
+ "special": false
980
+ },
981
+ "122": {
982
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
983
+ "lstrip": false,
984
+ "normalized": false,
985
+ "rstrip": false,
986
+ "single_word": false,
987
+ "special": false
988
+ },
989
+ "123": {
990
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
991
+ "lstrip": false,
992
+ "normalized": false,
993
+ "rstrip": false,
994
+ "single_word": false,
995
+ "special": false
996
+ },
997
+ "124": {
998
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
999
+ "lstrip": false,
1000
+ "normalized": false,
1001
+ "rstrip": false,
1002
+ "single_word": false,
1003
+ "special": false
1004
+ },
1005
+ "125": {
1006
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1007
+ "lstrip": false,
1008
+ "normalized": false,
1009
+ "rstrip": false,
1010
+ "single_word": false,
1011
+ "special": false
1012
+ },
1013
+ "126": {
1014
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1015
+ "lstrip": false,
1016
+ "normalized": false,
1017
+ "rstrip": false,
1018
+ "single_word": false,
1019
+ "special": false
1020
+ },
1021
+ "127": {
1022
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1023
+ "lstrip": false,
1024
+ "normalized": false,
1025
+ "rstrip": false,
1026
+ "single_word": false,
1027
+ "special": false
1028
+ },
1029
+ "128": {
1030
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1031
+ "lstrip": false,
1032
+ "normalized": false,
1033
+ "rstrip": false,
1034
+ "single_word": false,
1035
+ "special": false
1036
+ },
1037
+ "129": {
1038
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1039
+ "lstrip": false,
1040
+ "normalized": false,
1041
+ "rstrip": false,
1042
+ "single_word": false,
1043
+ "special": false
1044
+ },
1045
+ "130": {
1046
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1047
+ "lstrip": false,
1048
+ "normalized": false,
1049
+ "rstrip": false,
1050
+ "single_word": false,
1051
+ "special": false
1052
+ },
1053
+ "131": {
1054
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1055
+ "lstrip": false,
1056
+ "normalized": false,
1057
+ "rstrip": false,
1058
+ "single_word": false,
1059
+ "special": false
1060
+ },
1061
+ "132": {
1062
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1063
+ "lstrip": false,
1064
+ "normalized": false,
1065
+ "rstrip": false,
1066
+ "single_word": false,
1067
+ "special": false
1068
+ },
1069
+ "133": {
1070
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1071
+ "lstrip": false,
1072
+ "normalized": false,
1073
+ "rstrip": false,
1074
+ "single_word": false,
1075
+ "special": false
1076
+ },
1077
+ "134": {
1078
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1079
+ "lstrip": false,
1080
+ "normalized": false,
1081
+ "rstrip": false,
1082
+ "single_word": false,
1083
+ "special": false
1084
+ },
1085
+ "135": {
1086
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1087
+ "lstrip": false,
1088
+ "normalized": false,
1089
+ "rstrip": false,
1090
+ "single_word": false,
1091
+ "special": false
1092
+ },
1093
+ "136": {
1094
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1095
+ "lstrip": false,
1096
+ "normalized": false,
1097
+ "rstrip": false,
1098
+ "single_word": false,
1099
+ "special": false
1100
+ },
1101
+ "137": {
1102
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1103
+ "lstrip": false,
1104
+ "normalized": false,
1105
+ "rstrip": false,
1106
+ "single_word": false,
1107
+ "special": false
1108
+ },
1109
+ "138": {
1110
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1111
+ "lstrip": false,
1112
+ "normalized": false,
1113
+ "rstrip": false,
1114
+ "single_word": false,
1115
+ "special": false
1116
+ },
1117
+ "139": {
1118
+ "content": "▁▁",
1119
+ "lstrip": false,
1120
+ "normalized": false,
1121
+ "rstrip": false,
1122
+ "single_word": false,
1123
+ "special": false
1124
+ },
1125
+ "140": {
1126
+ "content": "▁▁▁",
1127
+ "lstrip": false,
1128
+ "normalized": false,
1129
+ "rstrip": false,
1130
+ "single_word": false,
1131
+ "special": false
1132
+ },
1133
+ "141": {
1134
+ "content": "▁▁▁▁",
1135
+ "lstrip": false,
1136
+ "normalized": false,
1137
+ "rstrip": false,
1138
+ "single_word": false,
1139
+ "special": false
1140
+ },
1141
+ "142": {
1142
+ "content": "▁▁▁▁▁",
1143
+ "lstrip": false,
1144
+ "normalized": false,
1145
+ "rstrip": false,
1146
+ "single_word": false,
1147
+ "special": false
1148
+ },
1149
+ "143": {
1150
+ "content": "▁▁▁▁▁▁",
1151
+ "lstrip": false,
1152
+ "normalized": false,
1153
+ "rstrip": false,
1154
+ "single_word": false,
1155
+ "special": false
1156
+ },
1157
+ "144": {
1158
+ "content": "▁▁▁▁▁▁▁",
1159
+ "lstrip": false,
1160
+ "normalized": false,
1161
+ "rstrip": false,
1162
+ "single_word": false,
1163
+ "special": false
1164
+ },
1165
+ "145": {
1166
+ "content": "▁▁▁▁▁▁▁▁",
1167
+ "lstrip": false,
1168
+ "normalized": false,
1169
+ "rstrip": false,
1170
+ "single_word": false,
1171
+ "special": false
1172
+ },
1173
+ "146": {
1174
+ "content": "▁▁▁▁▁▁▁▁▁",
1175
+ "lstrip": false,
1176
+ "normalized": false,
1177
+ "rstrip": false,
1178
+ "single_word": false,
1179
+ "special": false
1180
+ },
1181
+ "147": {
1182
+ "content": "▁▁▁▁▁▁▁▁▁▁",
1183
+ "lstrip": false,
1184
+ "normalized": false,
1185
+ "rstrip": false,
1186
+ "single_word": false,
1187
+ "special": false
1188
+ },
1189
+ "148": {
1190
+ "content": "▁▁▁▁▁▁▁▁▁▁▁",
1191
+ "lstrip": false,
1192
+ "normalized": false,
1193
+ "rstrip": false,
1194
+ "single_word": false,
1195
+ "special": false
1196
+ },
1197
+ "149": {
1198
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁",
1199
+ "lstrip": false,
1200
+ "normalized": false,
1201
+ "rstrip": false,
1202
+ "single_word": false,
1203
+ "special": false
1204
+ },
1205
+ "150": {
1206
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁",
1207
+ "lstrip": false,
1208
+ "normalized": false,
1209
+ "rstrip": false,
1210
+ "single_word": false,
1211
+ "special": false
1212
+ },
1213
+ "151": {
1214
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1215
+ "lstrip": false,
1216
+ "normalized": false,
1217
+ "rstrip": false,
1218
+ "single_word": false,
1219
+ "special": false
1220
+ },
1221
+ "152": {
1222
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1223
+ "lstrip": false,
1224
+ "normalized": false,
1225
+ "rstrip": false,
1226
+ "single_word": false,
1227
+ "special": false
1228
+ },
1229
+ "153": {
1230
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1231
+ "lstrip": false,
1232
+ "normalized": false,
1233
+ "rstrip": false,
1234
+ "single_word": false,
1235
+ "special": false
1236
+ },
1237
+ "154": {
1238
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1239
+ "lstrip": false,
1240
+ "normalized": false,
1241
+ "rstrip": false,
1242
+ "single_word": false,
1243
+ "special": false
1244
+ },
1245
+ "155": {
1246
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1247
+ "lstrip": false,
1248
+ "normalized": false,
1249
+ "rstrip": false,
1250
+ "single_word": false,
1251
+ "special": false
1252
+ },
1253
+ "156": {
1254
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1255
+ "lstrip": false,
1256
+ "normalized": false,
1257
+ "rstrip": false,
1258
+ "single_word": false,
1259
+ "special": false
1260
+ },
1261
+ "157": {
1262
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1263
+ "lstrip": false,
1264
+ "normalized": false,
1265
+ "rstrip": false,
1266
+ "single_word": false,
1267
+ "special": false
1268
+ },
1269
+ "158": {
1270
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1271
+ "lstrip": false,
1272
+ "normalized": false,
1273
+ "rstrip": false,
1274
+ "single_word": false,
1275
+ "special": false
1276
+ },
1277
+ "159": {
1278
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1279
+ "lstrip": false,
1280
+ "normalized": false,
1281
+ "rstrip": false,
1282
+ "single_word": false,
1283
+ "special": false
1284
+ },
1285
+ "160": {
1286
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1287
+ "lstrip": false,
1288
+ "normalized": false,
1289
+ "rstrip": false,
1290
+ "single_word": false,
1291
+ "special": false
1292
+ },
1293
+ "161": {
1294
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1295
+ "lstrip": false,
1296
+ "normalized": false,
1297
+ "rstrip": false,
1298
+ "single_word": false,
1299
+ "special": false
1300
+ },
1301
+ "162": {
1302
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1303
+ "lstrip": false,
1304
+ "normalized": false,
1305
+ "rstrip": false,
1306
+ "single_word": false,
1307
+ "special": false
1308
+ },
1309
+ "163": {
1310
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1311
+ "lstrip": false,
1312
+ "normalized": false,
1313
+ "rstrip": false,
1314
+ "single_word": false,
1315
+ "special": false
1316
+ },
1317
+ "164": {
1318
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1319
+ "lstrip": false,
1320
+ "normalized": false,
1321
+ "rstrip": false,
1322
+ "single_word": false,
1323
+ "special": false
1324
+ },
1325
+ "165": {
1326
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1327
+ "lstrip": false,
1328
+ "normalized": false,
1329
+ "rstrip": false,
1330
+ "single_word": false,
1331
+ "special": false
1332
+ },
1333
+ "166": {
1334
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1335
+ "lstrip": false,
1336
+ "normalized": false,
1337
+ "rstrip": false,
1338
+ "single_word": false,
1339
+ "special": false
1340
+ },
1341
+ "167": {
1342
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1343
+ "lstrip": false,
1344
+ "normalized": false,
1345
+ "rstrip": false,
1346
+ "single_word": false,
1347
+ "special": false
1348
+ },
1349
+ "168": {
1350
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1351
+ "lstrip": false,
1352
+ "normalized": false,
1353
+ "rstrip": false,
1354
+ "single_word": false,
1355
+ "special": false
1356
+ },
1357
+ "169": {
1358
+ "content": "<table>",
1359
+ "lstrip": false,
1360
+ "normalized": false,
1361
+ "rstrip": false,
1362
+ "single_word": false,
1363
+ "special": false
1364
+ },
1365
+ "170": {
1366
+ "content": "<caption>",
1367
+ "lstrip": false,
1368
+ "normalized": false,
1369
+ "rstrip": false,
1370
+ "single_word": false,
1371
+ "special": false
1372
+ },
1373
+ "171": {
1374
+ "content": "<thead>",
1375
+ "lstrip": false,
1376
+ "normalized": false,
1377
+ "rstrip": false,
1378
+ "single_word": false,
1379
+ "special": false
1380
+ },
1381
+ "172": {
1382
+ "content": "<tbody>",
1383
+ "lstrip": false,
1384
+ "normalized": false,
1385
+ "rstrip": false,
1386
+ "single_word": false,
1387
+ "special": false
1388
+ },
1389
+ "173": {
1390
+ "content": "<tfoot>",
1391
+ "lstrip": false,
1392
+ "normalized": false,
1393
+ "rstrip": false,
1394
+ "single_word": false,
1395
+ "special": false
1396
+ },
1397
+ "174": {
1398
+ "content": "<tr>",
1399
+ "lstrip": false,
1400
+ "normalized": false,
1401
+ "rstrip": false,
1402
+ "single_word": false,
1403
+ "special": false
1404
+ },
1405
+ "175": {
1406
+ "content": "<th>",
1407
+ "lstrip": false,
1408
+ "normalized": false,
1409
+ "rstrip": false,
1410
+ "single_word": false,
1411
+ "special": false
1412
+ },
1413
+ "176": {
1414
+ "content": "<td>",
1415
+ "lstrip": false,
1416
+ "normalized": false,
1417
+ "rstrip": false,
1418
+ "single_word": false,
1419
+ "special": false
1420
+ },
1421
+ "177": {
1422
+ "content": "</table>",
1423
+ "lstrip": false,
1424
+ "normalized": false,
1425
+ "rstrip": false,
1426
+ "single_word": false,
1427
+ "special": false
1428
+ },
1429
+ "178": {
1430
+ "content": "</caption>",
1431
+ "lstrip": false,
1432
+ "normalized": false,
1433
+ "rstrip": false,
1434
+ "single_word": false,
1435
+ "special": false
1436
+ },
1437
+ "179": {
1438
+ "content": "</thead>",
1439
+ "lstrip": false,
1440
+ "normalized": false,
1441
+ "rstrip": false,
1442
+ "single_word": false,
1443
+ "special": false
1444
+ },
1445
+ "180": {
1446
+ "content": "</tbody>",
1447
+ "lstrip": false,
1448
+ "normalized": false,
1449
+ "rstrip": false,
1450
+ "single_word": false,
1451
+ "special": false
1452
+ },
1453
+ "181": {
1454
+ "content": "</tfoot>",
1455
+ "lstrip": false,
1456
+ "normalized": false,
1457
+ "rstrip": false,
1458
+ "single_word": false,
1459
+ "special": false
1460
+ },
1461
+ "182": {
1462
+ "content": "</tr>",
1463
+ "lstrip": false,
1464
+ "normalized": false,
1465
+ "rstrip": false,
1466
+ "single_word": false,
1467
+ "special": false
1468
+ },
1469
+ "183": {
1470
+ "content": "</th>",
1471
+ "lstrip": false,
1472
+ "normalized": false,
1473
+ "rstrip": false,
1474
+ "single_word": false,
1475
+ "special": false
1476
+ },
1477
+ "184": {
1478
+ "content": "</td>",
1479
+ "lstrip": false,
1480
+ "normalized": false,
1481
+ "rstrip": false,
1482
+ "single_word": false,
1483
+ "special": false
1484
+ },
1485
+ "185": {
1486
+ "content": "<h1>",
1487
+ "lstrip": false,
1488
+ "normalized": false,
1489
+ "rstrip": false,
1490
+ "single_word": false,
1491
+ "special": false
1492
+ },
1493
+ "186": {
1494
+ "content": "<h2>",
1495
+ "lstrip": false,
1496
+ "normalized": false,
1497
+ "rstrip": false,
1498
+ "single_word": false,
1499
+ "special": false
1500
+ },
1501
+ "187": {
1502
+ "content": "<h3>",
1503
+ "lstrip": false,
1504
+ "normalized": false,
1505
+ "rstrip": false,
1506
+ "single_word": false,
1507
+ "special": false
1508
+ },
1509
+ "188": {
1510
+ "content": "<h4>",
1511
+ "lstrip": false,
1512
+ "normalized": false,
1513
+ "rstrip": false,
1514
+ "single_word": false,
1515
+ "special": false
1516
+ },
1517
+ "189": {
1518
+ "content": "<h5>",
1519
+ "lstrip": false,
1520
+ "normalized": false,
1521
+ "rstrip": false,
1522
+ "single_word": false,
1523
+ "special": false
1524
+ },
1525
+ "190": {
1526
+ "content": "<h6>",
1527
+ "lstrip": false,
1528
+ "normalized": false,
1529
+ "rstrip": false,
1530
+ "single_word": false,
1531
+ "special": false
1532
+ },
1533
+ "191": {
1534
+ "content": "<blockquote>",
1535
+ "lstrip": false,
1536
+ "normalized": false,
1537
+ "rstrip": false,
1538
+ "single_word": false,
1539
+ "special": false
1540
+ },
1541
+ "192": {
1542
+ "content": "</h1>",
1543
+ "lstrip": false,
1544
+ "normalized": false,
1545
+ "rstrip": false,
1546
+ "single_word": false,
1547
+ "special": false
1548
+ },
1549
+ "193": {
1550
+ "content": "</h2>",
1551
+ "lstrip": false,
1552
+ "normalized": false,
1553
+ "rstrip": false,
1554
+ "single_word": false,
1555
+ "special": false
1556
+ },
1557
+ "194": {
1558
+ "content": "</h3>",
1559
+ "lstrip": false,
1560
+ "normalized": false,
1561
+ "rstrip": false,
1562
+ "single_word": false,
1563
+ "special": false
1564
+ },
1565
+ "195": {
1566
+ "content": "</h4>",
1567
+ "lstrip": false,
1568
+ "normalized": false,
1569
+ "rstrip": false,
1570
+ "single_word": false,
1571
+ "special": false
1572
+ },
1573
+ "196": {
1574
+ "content": "</h5>",
1575
+ "lstrip": false,
1576
+ "normalized": false,
1577
+ "rstrip": false,
1578
+ "single_word": false,
1579
+ "special": false
1580
+ },
1581
+ "197": {
1582
+ "content": "</h6>",
1583
+ "lstrip": false,
1584
+ "normalized": false,
1585
+ "rstrip": false,
1586
+ "single_word": false,
1587
+ "special": false
1588
+ },
1589
+ "198": {
1590
+ "content": "</blockquote>",
1591
+ "lstrip": false,
1592
+ "normalized": false,
1593
+ "rstrip": false,
1594
+ "single_word": false,
1595
+ "special": false
1596
+ },
1597
+ "199": {
1598
+ "content": "<strong>",
1599
+ "lstrip": false,
1600
+ "normalized": false,
1601
+ "rstrip": false,
1602
+ "single_word": false,
1603
+ "special": false
1604
+ },
1605
+ "200": {
1606
+ "content": "<em>",
1607
+ "lstrip": false,
1608
+ "normalized": false,
1609
+ "rstrip": false,
1610
+ "single_word": false,
1611
+ "special": false
1612
+ },
1613
+ "201": {
1614
+ "content": "<b>",
1615
+ "lstrip": false,
1616
+ "normalized": false,
1617
+ "rstrip": false,
1618
+ "single_word": false,
1619
+ "special": false
1620
+ },
1621
+ "202": {
1622
+ "content": "<i>",
1623
+ "lstrip": false,
1624
+ "normalized": false,
1625
+ "rstrip": false,
1626
+ "single_word": false,
1627
+ "special": false
1628
+ },
1629
+ "203": {
1630
+ "content": "<u>",
1631
+ "lstrip": false,
1632
+ "normalized": false,
1633
+ "rstrip": false,
1634
+ "single_word": false,
1635
+ "special": false
1636
+ },
1637
+ "204": {
1638
+ "content": "<s>",
1639
+ "lstrip": false,
1640
+ "normalized": false,
1641
+ "rstrip": false,
1642
+ "single_word": false,
1643
+ "special": false
1644
+ },
1645
+ "205": {
1646
+ "content": "<sub>",
1647
+ "lstrip": false,
1648
+ "normalized": false,
1649
+ "rstrip": false,
1650
+ "single_word": false,
1651
+ "special": false
1652
+ },
1653
+ "206": {
1654
+ "content": "<sup>",
1655
+ "lstrip": false,
1656
+ "normalized": false,
1657
+ "rstrip": false,
1658
+ "single_word": false,
1659
+ "special": false
1660
+ },
1661
+ "207": {
1662
+ "content": "<code>",
1663
+ "lstrip": false,
1664
+ "normalized": false,
1665
+ "rstrip": false,
1666
+ "single_word": false,
1667
+ "special": false
1668
+ },
1669
+ "208": {
1670
+ "content": "</strong>",
1671
+ "lstrip": false,
1672
+ "normalized": false,
1673
+ "rstrip": false,
1674
+ "single_word": false,
1675
+ "special": false
1676
+ },
1677
+ "209": {
1678
+ "content": "</em>",
1679
+ "lstrip": false,
1680
+ "normalized": false,
1681
+ "rstrip": false,
1682
+ "single_word": false,
1683
+ "special": false
1684
+ },
1685
+ "210": {
1686
+ "content": "</b>",
1687
+ "lstrip": false,
1688
+ "normalized": false,
1689
+ "rstrip": false,
1690
+ "single_word": false,
1691
+ "special": false
1692
+ },
1693
+ "211": {
1694
+ "content": "</i>",
1695
+ "lstrip": false,
1696
+ "normalized": false,
1697
+ "rstrip": false,
1698
+ "single_word": false,
1699
+ "special": false
1700
+ },
1701
+ "212": {
1702
+ "content": "</u>",
1703
+ "lstrip": false,
1704
+ "normalized": false,
1705
+ "rstrip": false,
1706
+ "single_word": false,
1707
+ "special": false
1708
+ },
1709
+ "213": {
1710
+ "content": "</s>",
1711
+ "lstrip": false,
1712
+ "normalized": false,
1713
+ "rstrip": false,
1714
+ "single_word": false,
1715
+ "special": false
1716
+ },
1717
+ "214": {
1718
+ "content": "</sub>",
1719
+ "lstrip": false,
1720
+ "normalized": false,
1721
+ "rstrip": false,
1722
+ "single_word": false,
1723
+ "special": false
1724
+ },
1725
+ "215": {
1726
+ "content": "</sup>",
1727
+ "lstrip": false,
1728
+ "normalized": false,
1729
+ "rstrip": false,
1730
+ "single_word": false,
1731
+ "special": false
1732
+ },
1733
+ "216": {
1734
+ "content": "</code>",
1735
+ "lstrip": false,
1736
+ "normalized": false,
1737
+ "rstrip": false,
1738
+ "single_word": false,
1739
+ "special": false
1740
+ },
1741
+ "255968": {
1742
+ "content": "[toxicity=0]",
1743
+ "lstrip": false,
1744
+ "normalized": false,
1745
+ "rstrip": false,
1746
+ "single_word": false,
1747
+ "special": false
1748
+ },
1749
+ "255969": {
1750
+ "content": "\t\t",
1751
+ "lstrip": false,
1752
+ "normalized": false,
1753
+ "rstrip": false,
1754
+ "single_word": false,
1755
+ "special": false
1756
+ },
1757
+ "255970": {
1758
+ "content": "\t\t\t",
1759
+ "lstrip": false,
1760
+ "normalized": false,
1761
+ "rstrip": false,
1762
+ "single_word": false,
1763
+ "special": false
1764
+ },
1765
+ "255971": {
1766
+ "content": "\t\t\t\t",
1767
+ "lstrip": false,
1768
+ "normalized": false,
1769
+ "rstrip": false,
1770
+ "single_word": false,
1771
+ "special": false
1772
+ },
1773
+ "255972": {
1774
+ "content": "\t\t\t\t\t",
1775
+ "lstrip": false,
1776
+ "normalized": false,
1777
+ "rstrip": false,
1778
+ "single_word": false,
1779
+ "special": false
1780
+ },
1781
+ "255973": {
1782
+ "content": "\t\t\t\t\t\t",
1783
+ "lstrip": false,
1784
+ "normalized": false,
1785
+ "rstrip": false,
1786
+ "single_word": false,
1787
+ "special": false
1788
+ },
1789
+ "255974": {
1790
+ "content": "\t\t\t\t\t\t\t",
1791
+ "lstrip": false,
1792
+ "normalized": false,
1793
+ "rstrip": false,
1794
+ "single_word": false,
1795
+ "special": false
1796
+ },
1797
+ "255975": {
1798
+ "content": "\t\t\t\t\t\t\t\t",
1799
+ "lstrip": false,
1800
+ "normalized": false,
1801
+ "rstrip": false,
1802
+ "single_word": false,
1803
+ "special": false
1804
+ },
1805
+ "255976": {
1806
+ "content": "\t\t\t\t\t\t\t\t\t",
1807
+ "lstrip": false,
1808
+ "normalized": false,
1809
+ "rstrip": false,
1810
+ "single_word": false,
1811
+ "special": false
1812
+ },
1813
+ "255977": {
1814
+ "content": "\t\t\t\t\t\t\t\t\t\t",
1815
+ "lstrip": false,
1816
+ "normalized": false,
1817
+ "rstrip": false,
1818
+ "single_word": false,
1819
+ "special": false
1820
+ },
1821
+ "255978": {
1822
+ "content": "\t\t\t\t\t\t\t\t\t\t\t",
1823
+ "lstrip": false,
1824
+ "normalized": false,
1825
+ "rstrip": false,
1826
+ "single_word": false,
1827
+ "special": false
1828
+ },
1829
+ "255979": {
1830
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t",
1831
+ "lstrip": false,
1832
+ "normalized": false,
1833
+ "rstrip": false,
1834
+ "single_word": false,
1835
+ "special": false
1836
+ },
1837
+ "255980": {
1838
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t",
1839
+ "lstrip": false,
1840
+ "normalized": false,
1841
+ "rstrip": false,
1842
+ "single_word": false,
1843
+ "special": false
1844
+ },
1845
+ "255981": {
1846
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1847
+ "lstrip": false,
1848
+ "normalized": false,
1849
+ "rstrip": false,
1850
+ "single_word": false,
1851
+ "special": false
1852
+ },
1853
+ "255982": {
1854
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1855
+ "lstrip": false,
1856
+ "normalized": false,
1857
+ "rstrip": false,
1858
+ "single_word": false,
1859
+ "special": false
1860
+ },
1861
+ "255983": {
1862
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1863
+ "lstrip": false,
1864
+ "normalized": false,
1865
+ "rstrip": false,
1866
+ "single_word": false,
1867
+ "special": false
1868
+ },
1869
+ "255984": {
1870
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1871
+ "lstrip": false,
1872
+ "normalized": false,
1873
+ "rstrip": false,
1874
+ "single_word": false,
1875
+ "special": false
1876
+ },
1877
+ "255985": {
1878
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1879
+ "lstrip": false,
1880
+ "normalized": false,
1881
+ "rstrip": false,
1882
+ "single_word": false,
1883
+ "special": false
1884
+ },
1885
+ "255986": {
1886
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1887
+ "lstrip": false,
1888
+ "normalized": false,
1889
+ "rstrip": false,
1890
+ "single_word": false,
1891
+ "special": false
1892
+ },
1893
+ "255987": {
1894
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1895
+ "lstrip": false,
1896
+ "normalized": false,
1897
+ "rstrip": false,
1898
+ "single_word": false,
1899
+ "special": false
1900
+ },
1901
+ "255988": {
1902
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1903
+ "lstrip": false,
1904
+ "normalized": false,
1905
+ "rstrip": false,
1906
+ "single_word": false,
1907
+ "special": false
1908
+ },
1909
+ "255989": {
1910
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1911
+ "lstrip": false,
1912
+ "normalized": false,
1913
+ "rstrip": false,
1914
+ "single_word": false,
1915
+ "special": false
1916
+ },
1917
+ "255990": {
1918
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1919
+ "lstrip": false,
1920
+ "normalized": false,
1921
+ "rstrip": false,
1922
+ "single_word": false,
1923
+ "special": false
1924
+ },
1925
+ "255991": {
1926
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1927
+ "lstrip": false,
1928
+ "normalized": false,
1929
+ "rstrip": false,
1930
+ "single_word": false,
1931
+ "special": false
1932
+ },
1933
+ "255992": {
1934
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1935
+ "lstrip": false,
1936
+ "normalized": false,
1937
+ "rstrip": false,
1938
+ "single_word": false,
1939
+ "special": false
1940
+ },
1941
+ "255993": {
1942
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1943
+ "lstrip": false,
1944
+ "normalized": false,
1945
+ "rstrip": false,
1946
+ "single_word": false,
1947
+ "special": false
1948
+ },
1949
+ "255994": {
1950
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1951
+ "lstrip": false,
1952
+ "normalized": false,
1953
+ "rstrip": false,
1954
+ "single_word": false,
1955
+ "special": false
1956
+ },
1957
+ "255995": {
1958
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1959
+ "lstrip": false,
1960
+ "normalized": false,
1961
+ "rstrip": false,
1962
+ "single_word": false,
1963
+ "special": false
1964
+ },
1965
+ "255996": {
1966
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1967
+ "lstrip": false,
1968
+ "normalized": false,
1969
+ "rstrip": false,
1970
+ "single_word": false,
1971
+ "special": false
1972
+ },
1973
+ "255997": {
1974
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1975
+ "lstrip": false,
1976
+ "normalized": false,
1977
+ "rstrip": false,
1978
+ "single_word": false,
1979
+ "special": false
1980
+ },
1981
+ "255998": {
1982
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1983
+ "lstrip": false,
1984
+ "normalized": false,
1985
+ "rstrip": false,
1986
+ "single_word": false,
1987
+ "special": false
1988
+ },
1989
+ "255999": {
1990
+ "content": "<unused99>",
1991
+ "lstrip": false,
1992
+ "normalized": false,
1993
+ "rstrip": false,
1994
+ "single_word": false,
1995
+ "special": false
1996
+ }
1997
+ },
1998
+ "additional_special_tokens": [
1999
+ "<start_of_turn>",
2000
+ "<end_of_turn>"
2001
+ ],
2002
+ "bos_token": "<bos>",
2003
+ "clean_up_tokenization_spaces": false,
2004
+ "eos_token": "<eos>",
2005
+ "extra_special_tokens": {},
2006
+ "model_max_length": 1000000000000000019884624838656,
2007
+ "pad_token": "<pad>",
2008
+ "sp_model_kwargs": {},
2009
+ "spaces_between_special_tokens": false,
2010
+ "tokenizer_class": "GemmaTokenizer",
2011
+ "unk_token": "<unk>",
2012
+ "use_default_system_prompt": false
2013
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:160bc79c61adc8822e5ee348615ceccb98c78918aa92d15516c997b4855ce7ee
3
+ size 7377