Hugging Face's logo

Gege24
/
environment_test_affine

Text Generation
PEFT
Safetensors
Transformers
qwen2
grpo
lora
trl
conversational
text-generation-inference
Model card Files
xet
 Community
Gege24 commited on
Commit
3a9a90a
·
verified ·
1 Parent(s): 406e3ab

Upload task output 1

Browse files
Files changed (11) hide show
  1. .gitattributes +1 -0
  2. adapter_config.json +46 -0
  3. added_tokens.json +24 -0
  4. chat_template.jinja +5 -0
  5. config.json +66 -0
  6. debug.log +272 -0
  7. merges.txt +0 -0
  8. special_tokens_map.json +38 -0
  9. tokenizer.json +3 -0
  10. tokenizer_config.json +207 -0
  11. vocab.json +0 -0
.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
adapter_config.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alora_invocation_tokens": null,
3
+ "alpha_pattern": {},
4
+ "arrow_config": null,
5
+ "auto_mapping": null,
6
+ "base_model_name_or_path": null,
7
+ "bias": "none",
8
+ "corda_config": null,
9
+ "ensure_weight_tying": false,
10
+ "eva_config": null,
11
+ "exclude_modules": null,
12
+ "fan_in_fan_out": null,
13
+ "inference_mode": false,
14
+ "init_lora_weights": true,
15
+ "layer_replication": null,
16
+ "layers_pattern": null,
17
+ "layers_to_transform": null,
18
+ "loftq_config": {},
19
+ "lora_alpha": 32,
20
+ "lora_bias": false,
21
+ "lora_dropout": 0.0,
22
+ "megatron_config": null,
23
+ "megatron_core": "megatron.core",
24
+ "modules_to_save": null,
25
+ "peft_type": "LORA",
26
+ "peft_version": "0.18.1",
27
+ "qalora_group_size": 16,
28
+ "r": 64,
29
+ "rank_pattern": {},
30
+ "revision": null,
31
+ "target_modules": [
32
+ "o_proj",
33
+ "v_proj",
34
+ "up_proj",
35
+ "q_proj",
36
+ "k_proj",
37
+ "down_proj",
38
+ "gate_proj"
39
+ ],
40
+ "target_parameters": [],
41
+ "task_type": "CAUSAL_LM",
42
+ "trainable_token_indices": null,
43
+ "use_dora": false,
44
+ "use_qalora": false,
45
+ "use_rslora": false
46
+ }
added_tokens.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</tool_call>": 151658,
3
+ "<tool_call>": 151657,
4
+ "<|box_end|>": 151649,
5
+ "<|box_start|>": 151648,
6
+ "<|endoftext|>": 151643,
7
+ "<|file_sep|>": 151664,
8
+ "<|fim_middle|>": 151660,
9
+ "<|fim_pad|>": 151662,
10
+ "<|fim_prefix|>": 151659,
11
+ "<|fim_suffix|>": 151661,
12
+ "<|im_end|>": 151645,
13
+ "<|im_start|>": 151644,
14
+ "<|image_pad|>": 151655,
15
+ "<|object_ref_end|>": 151647,
16
+ "<|object_ref_start|>": 151646,
17
+ "<|quad_end|>": 151651,
18
+ "<|quad_start|>": 151650,
19
+ "<|repo_name|>": 151663,
20
+ "<|video_pad|>": 151656,
21
+ "<|vision_end|>": 151653,
22
+ "<|vision_pad|>": 151654,
23
+ "<|vision_start|>": 151652
24
+ }
chat_template.jinja ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>
2
+
3
+ '+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>
4
+
5
+ ' }}{% endif %}
config.json ADDED
@@ -0,0 +1,66 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen2ForCausalLM"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "bos_token_id": 151645,
7
+ "dtype": "bfloat16",
8
+ "eos_token_id": 151645,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 2048,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 11008,
13
+ "layer_types": [
14
+ "full_attention",
15
+ "full_attention",
16
+ "full_attention",
17
+ "full_attention",
18
+ "full_attention",
19
+ "full_attention",
20
+ "full_attention",
21
+ "full_attention",
22
+ "full_attention",
23
+ "full_attention",
24
+ "full_attention",
25
+ "full_attention",
26
+ "full_attention",
27
+ "full_attention",
28
+ "full_attention",
29
+ "full_attention",
30
+ "full_attention",
31
+ "full_attention",
32
+ "full_attention",
33
+ "full_attention",
34
+ "full_attention",
35
+ "full_attention",
36
+ "full_attention",
37
+ "full_attention",
38
+ "full_attention",
39
+ "full_attention",
40
+ "full_attention",
41
+ "full_attention",
42
+ "full_attention",
43
+ "full_attention",
44
+ "full_attention",
45
+ "full_attention",
46
+ "full_attention",
47
+ "full_attention",
48
+ "full_attention",
49
+ "full_attention"
50
+ ],
51
+ "max_position_embeddings": 32768,
52
+ "max_window_layers": 70,
53
+ "model_type": "qwen2",
54
+ "num_attention_heads": 16,
55
+ "num_hidden_layers": 36,
56
+ "num_key_value_heads": 2,
57
+ "rms_norm_eps": 1e-06,
58
+ "rope_scaling": null,
59
+ "rope_theta": 1000000.0,
60
+ "sliding_window": null,
61
+ "tie_word_embeddings": true,
62
+ "transformers_version": "4.57.6",
63
+ "use_cache": false,
64
+ "use_sliding_window": false,
65
+ "vocab_size": 151936
66
+ }
debug.log ADDED
@@ -0,0 +1,272 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [2026-01-27 12:01:15,252] [DEBUG] [axolotl.utils.config.resolve_dtype:66] [PID:168] bf16 support detected, enabling for this configuration.
2
+ [2026-01-27 12:01:15,254] [DEBUG] [axolotl.utils.config.log_gpu_memory_usage:127] [PID:168] baseline 0.000GB ()
3
+ [2026-01-27 12:01:15,254] [INFO] [axolotl.cli.config.load_cfg:259] [PID:168] config:
4
+ {
5
+ "activation_offloading": false,
6
+ "adapter": "lora",
7
+ "axolotl_config_path": "/workspace/axolotl/configs/1.yml",
8
+ "base_model": "/cache/models/Qwen--Qwen2.5-3B-Instruct",
9
+ "base_model_config": "/cache/models/Qwen--Qwen2.5-3B-Instruct",
10
+ "batch_size": 8,
11
+ "bf16": true,
12
+ "capabilities": {
13
+ "bf16": true,
14
+ "compute_capability": "sm_90",
15
+ "fp8": true,
16
+ "n_gpu": 1,
17
+ "n_node": 1
18
+ },
19
+ "chat_template": "llama3",
20
+ "context_parallel_size": 1,
21
+ "dataloader_num_workers": 1,
22
+ "dataloader_pin_memory": true,
23
+ "dataloader_prefetch_factor": 256,
24
+ "dataset_num_proc": 32,
25
+ "datasets": [
26
+ {
27
+ "data_files": [
28
+ "1_train_data.json"
29
+ ],
30
+ "ds_type": "json",
31
+ "message_property_mappings": {
32
+ "content": "content",
33
+ "role": "role"
34
+ },
35
+ "path": "/workspace/axolotl/data",
36
+ "split": "train",
37
+ "trust_remote_code": false
38
+ }
39
+ ],
40
+ "ddp": false,
41
+ "device": "cuda:0",
42
+ "dion_rank_fraction": 1.0,
43
+ "dion_rank_multiple_of": 1,
44
+ "env_capabilities": {
45
+ "torch_version": "2.8.0"
46
+ },
47
+ "eval_batch_size": 8,
48
+ "eval_causal_lm_metrics": [
49
+ "sacrebleu",
50
+ "comet",
51
+ "ter",
52
+ "chrf"
53
+ ],
54
+ "eval_max_new_tokens": 128,
55
+ "eval_strategy": "no",
56
+ "eval_table_size": 0,
57
+ "experimental_skip_move_to_device": true,
58
+ "flash_attention": false,
59
+ "fp16": false,
60
+ "gradient_accumulation_steps": 1,
61
+ "gradient_checkpointing": false,
62
+ "group_by_length": false,
63
+ "include_tkps": true,
64
+ "is_falcon_derived_model": false,
65
+ "is_llama_derived_model": false,
66
+ "is_mistral_derived_model": false,
67
+ "learning_rate": 7e-06,
68
+ "lisa_layers_attribute": "model.layers",
69
+ "load_best_model_at_end": false,
70
+ "load_in_4bit": false,
71
+ "load_in_8bit": false,
72
+ "local_rank": 0,
73
+ "logging_steps": 1,
74
+ "lora_alpha": 32,
75
+ "lora_dropout": 0.0,
76
+ "lora_r": 64,
77
+ "lora_target_linear": true,
78
+ "loraplus_lr_embedding": 1e-06,
79
+ "lr_scheduler": "cosine",
80
+ "max_grad_norm": 1.0,
81
+ "max_steps": 100000,
82
+ "mean_resizing_embeddings": false,
83
+ "micro_batch_size": 8,
84
+ "mlflow_experiment_name": "/workspace/axolotl/data/1_train_data.json",
85
+ "model_config_type": "qwen2",
86
+ "num_epochs": 1.0,
87
+ "optimizer": "adamw_bnb_8bit",
88
+ "otel_metrics_host": "localhost",
89
+ "otel_metrics_port": 8000,
90
+ "output_dir": "/app/checkpoints/1/environment_test_affine",
91
+ "pad_to_sequence_len": true,
92
+ "pretrain_multipack_attn": true,
93
+ "profiler_steps_start": 0,
94
+ "qlora_sharded_model_loading": false,
95
+ "ray_num_workers": 1,
96
+ "resources_per_worker": {
97
+ "GPU": 1
98
+ },
99
+ "rl": "grpo",
100
+ "sample_packing": false,
101
+ "sample_packing_bin_size": 200,
102
+ "sample_packing_group_size": 100000,
103
+ "save_only_model": false,
104
+ "save_safetensors": true,
105
+ "save_steps": 10,
106
+ "save_total_limit": 1,
107
+ "sequence_len": 24000,
108
+ "shuffle_before_merging_datasets": false,
109
+ "shuffle_merged_datasets": true,
110
+ "skip_prepare_dataset": false,
111
+ "special_tokens": {
112
+ "bos_token": "<|im_end|>"
113
+ },
114
+ "streaming_multipack_buffer_size": 10000,
115
+ "strict": false,
116
+ "tensor_parallel_size": 1,
117
+ "tf32": false,
118
+ "tiled_mlp_use_original_mlp": true,
119
+ "tokenizer_config": "/cache/models/Qwen--Qwen2.5-3B-Instruct",
120
+ "tokenizer_save_jinja_files": true,
121
+ "tokenizer_type": "AutoTokenizer",
122
+ "torch_dtype": "torch.bfloat16",
123
+ "train_on_inputs": false,
124
+ "trl": {
125
+ "beta": 0.001,
126
+ "log_completions": false,
127
+ "mask_truncated_completions": false,
128
+ "max_completion_length": 512,
129
+ "num_generations": 8,
130
+ "ref_model_mixup_alpha": 0.9,
131
+ "ref_model_sync_steps": 64,
132
+ "reward_funcs": [
133
+ "affine_game.rollout_reward_func"
134
+ ],
135
+ "reward_weights": [
136
+ 1.0
137
+ ],
138
+ "rollout_func": "affine_game.rollout_first_prompt_and_completion",
139
+ "scale_rewards": true,
140
+ "sync_ref_model": false,
141
+ "temperature": 0.7,
142
+ "use_vllm": true,
143
+ "vllm_enable_sleep_mode": false,
144
+ "vllm_mode": "colocate",
145
+ "vllm_server_host": "0.0.0.0",
146
+ "vllm_server_port": 8000
147
+ },
148
+ "trust_remote_code": true,
149
+ "type_of_model": "AutoModelForCausalLM",
150
+ "use_mlflow": true,
151
+ "use_otel_metrics": false,
152
+ "use_ray": false,
153
+ "use_wandb": true,
154
+ "val_set_size": 0.0,
155
+ "vllm": {
156
+ "device": "auto",
157
+ "dtype": "auto",
158
+ "enable_prefix_caching": false,
159
+ "gpu_memory_utilization": 0.15,
160
+ "host": "0.0.0.0",
161
+ "max_model_len": 24000,
162
+ "port": 8000,
163
+ "tensor_parallel_size": 1
164
+ },
165
+ "wandb_mode": "online",
166
+ "wandb_name": "1_environment_test_affine",
167
+ "wandb_project": "Affine-GAME-Tests",
168
+ "warmup_steps": 20,
169
+ "weight_decay": 0.0,
170
+ "world_size": 1
171
+ }
172
+ [2026-01-27 12:01:15,255] [WARNING] [axolotl.cli.checks.check_user_token:46] [PID:168] Error verifying HuggingFace token. Remember to log in using `huggingface-cli login` and get your access token from https://huggingface.co/settings/tokens if you want to use gated models or datasets.
173
+ [2026-01-27 12:01:15,461] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:285] [PID:168] EOS: 151645 / <|im_end|>
174
+ [2026-01-27 12:01:15,461] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:286] [PID:168] BOS: 151645 / <|im_end|>
175
+ [2026-01-27 12:01:15,461] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:287] [PID:168] PAD: 151643 / <|endoftext|>
176
+ [2026-01-27 12:01:15,461] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:288] [PID:168] UNK: None / None
177
+ [2026-01-27 12:01:15,462] [INFO] [axolotl.utils.data.shared.load_preprocessed_dataset:481] [PID:168] Unable to find prepared dataset in last_run_prepared/ba0ae834220c702ae7aefbdbfde66c85
178
+
179
+ [2026-01-27 12:01:16,103] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:285] [PID:168] EOS: 151645 / <|im_end|>
180
+ [2026-01-27 12:01:16,103] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:286] [PID:168] BOS: 151645 / <|im_end|>
181
+ [2026-01-27 12:01:16,103] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:287] [PID:168] PAD: 151643 / <|endoftext|>
182
+ [2026-01-27 12:01:16,103] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:288] [PID:168] UNK: None / None
183
+
184
+
185
+ [2026-01-27 12:01:19,857] [DEBUG] [axolotl.train.setup_model_and_tokenizer:70] [PID:168] loading tokenizer... /cache/models/Qwen--Qwen2.5-3B-Instruct
186
+ [2026-01-27 12:01:20,034] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:285] [PID:168] EOS: 151645 / <|im_end|>
187
+ [2026-01-27 12:01:20,034] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:286] [PID:168] BOS: 151645 / <|im_end|>
188
+ [2026-01-27 12:01:20,034] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:287] [PID:168] PAD: 151643 / <|endoftext|>
189
+ [2026-01-27 12:01:20,034] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:288] [PID:168] UNK: None / None
190
+ [2026-01-27 12:01:20,034] [DEBUG] [axolotl.train.setup_model_and_tokenizer:82] [PID:168] Loading model
191
+ [2026-01-27 12:01:20,046] [DEBUG] [axolotl.monkeypatch.transformers.trainer_loss_calc.patch_evaluation_loop:87] [PID:168] Patched Trainer.evaluation_loop with nanmean loss calculation
192
+ [2026-01-27 12:01:20,047] [DEBUG] [axolotl.monkeypatch.transformers.trainer_loss_calc.patch_maybe_log_save_evaluate:138] [PID:168] Patched Trainer._maybe_log_save_evaluate with nanmean loss calculation
193
+
194
+ [2026-01-27 12:01:20,672] [INFO] [axolotl.loaders.model._configure_embedding_dtypes:347] [PID:168] Converting modules to torch.bfloat16
195
+ [2026-01-27 12:01:21,066] [DEBUG] [axolotl.loaders.model.log_gpu_memory_usage:127] [PID:168] Memory usage after model load 0.000GB ()
196
+ [2026-01-27 12:01:21,067] [INFO] [axolotl.loaders.adapter.load_lora:81] [PID:168] found linear modules: ['down_proj', 'gate_proj', 'k_proj', 'o_proj', 'q_proj', 'up_proj', 'v_proj']
197
+ trainable params: 119,734,272 || all params: 3,205,672,960 || trainable%: 3.7351
198
+ [2026-01-27 12:01:21,942] [DEBUG] [axolotl.loaders.model.log_gpu_memory_usage:127] [PID:168] after adapters 0.000GB ()
199
+ [2026-01-27 12:01:22,623] [DEBUG] [axolotl.train.setup_reference_model:126] [PID:168] Passing model_ref: None to RL trainer
200
+ [2026-01-27 12:01:28,798] [WARNING] [py.warnings._showwarnmsg:110] [PID:168] /workspace/axolotl/src/axolotl/core/trainers/mixins/optimizer.py:209: UserWarning: You are importing from 'rollout_func', which is an experimental feature. This API may change or be removed at any time without prior notice. Silence this warning by setting environment variable TRL_EXPERIMENTAL_SILENCE=1.
201
+ super().__init__(*args, **kwargs)
202
+
203
+
204
+
205
+
206
+
207
+
208
+
209
+ [2026-01-27 12:02:04,465] [INFO] [axolotl.train.save_initial_configs:413] [PID:168] Pre-saving adapter config to /app/checkpoints/1/environment_test_affine...
210
+ [2026-01-27 12:02:04,466] [INFO] [axolotl.train.save_initial_configs:417] [PID:168] Pre-saving tokenizer to /app/checkpoints/1/environment_test_affine...
211
+ [2026-01-27 12:02:04,572] [INFO] [axolotl.train.save_initial_configs:422] [PID:168] Pre-saving model config to /app/checkpoints/1/environment_test_affine...
212
+ [2026-01-27 12:02:04,575] [INFO] [axolotl.train.execute_training:212] [PID:168] Starting trainer...
213
+ [rank0]: Traceback (most recent call last):
214
+ [rank0]: File "<frozen runpy>", line 198, in _run_module_as_main
215
+ [rank0]: File "<frozen runpy>", line 88, in _run_code
216
+ [rank0]: File "/workspace/axolotl/src/axolotl/cli/train.py", line 121, in <module>
217
+ [rank0]: fire.Fire(do_cli)
218
+ [rank0]: File "/root/miniconda3/envs/py3.11/lib/python3.11/site-packages/fire/core.py", line 135, in Fire
219
+ [rank0]: component_trace = _Fire(component, args, parsed_flag_args, context, name)
220
+ [rank0]: ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
221
+ [rank0]: File "/root/miniconda3/envs/py3.11/lib/python3.11/site-packages/fire/core.py", line 468, in _Fire
222
+ [rank0]: component, remaining_args = _CallAndUpdateTrace(
223
+ [rank0]: ^^^^^^^^^^^^^^^^^^^^
224
+ [rank0]: File "/root/miniconda3/envs/py3.11/lib/python3.11/site-packages/fire/core.py", line 684, in _CallAndUpdateTrace
225
+ [rank0]: component = fn(*varargs, **kwargs)
226
+ [rank0]: ^^^^^^^^^^^^^^^^^^^^^^
227
+ [rank0]: File "/workspace/axolotl/src/axolotl/cli/train.py", line 88, in do_cli
228
+ [rank0]: return do_train(parsed_cfg, parsed_cli_args)
229
+ [rank0]: ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
230
+ [rank0]: File "/workspace/axolotl/src/axolotl/cli/train.py", line 45, in do_train
231
+ [rank0]: model, tokenizer, trainer = train(cfg=cfg, dataset_meta=dataset_meta)
232
+ [rank0]: ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
233
+ [rank0]: File "/workspace/axolotl/src/axolotl/telemetry/errors.py", line 124, in wrapper
234
+ [rank0]: return func(*args, **kwargs)
235
+ [rank0]: ^^^^^^^^^^^^^^^^^^^^^
236
+ [rank0]: File "/workspace/axolotl/src/axolotl/train.py", line 598, in train
237
+ [rank0]: execute_training(cfg, trainer, resume_from_checkpoint)
238
+ [rank0]: File "/workspace/axolotl/src/axolotl/train.py", line 213, in execute_training
239
+ [rank0]: trainer.train(resume_from_checkpoint=resume_from_checkpoint)
240
+ [rank0]: File "/root/miniconda3/envs/py3.11/lib/python3.11/site-packages/transformers/trainer.py", line 2325, in train
241
+ [rank0]: return inner_training_loop(
242
+ [rank0]: ^^^^^^^^^^^^^^^^^^^^
243
+ [rank0]: File "/root/miniconda3/envs/py3.11/lib/python3.11/site-packages/transformers/trainer.py", line 2573, in _inner_training_loop
244
+ [rank0]: self.control = self.callback_handler.on_train_begin(args, self.state, self.control)
245
+ [rank0]: ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
246
+ [rank0]: File "/root/miniconda3/envs/py3.11/lib/python3.11/site-packages/transformers/trainer_callback.py", line 506, in on_train_begin
247
+ [rank0]: return self.call_event("on_train_begin", args, state, control)
248
+ [rank0]: ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
249
+ [rank0]: File "/root/miniconda3/envs/py3.11/lib/python3.11/site-packages/transformers/trainer_callback.py", line 556, in call_event
250
+ [rank0]: result = getattr(callback, event)(
251
+ [rank0]: ^^^^^^^^^^^^^^^^^^^^^^^^^
252
+ [rank0]: File "/root/miniconda3/envs/py3.11/lib/python3.11/site-packages/transformers/integrations/integration_utils.py", line 966, in on_train_begin
253
+ [rank0]: self.setup(args, state, model, **kwargs)
254
+ [rank0]: File "/root/miniconda3/envs/py3.11/lib/python3.11/site-packages/transformers/integrations/integration_utils.py", line 893, in setup
255
+ [rank0]: self._wandb.init(
256
+ [rank0]: File "/root/miniconda3/envs/py3.11/lib/python3.11/site-packages/wandb/sdk/wandb_init.py", line 1597, in init
257
+ [rank0]: get_sentry().reraise(e)
258
+ [rank0]: File "/root/miniconda3/envs/py3.11/lib/python3.11/site-packages/wandb/analytics/sentry.py", line 190, in reraise
259
+ [rank0]: raise exc.with_traceback(tb)
260
+ [rank0]: File "/root/miniconda3/envs/py3.11/lib/python3.11/site-packages/wandb/sdk/wandb_init.py", line 1518, in init
261
+ [rank0]: wi.maybe_login(init_settings)
262
+ [rank0]: File "/root/miniconda3/envs/py3.11/lib/python3.11/site-packages/wandb/sdk/wandb_init.py", line 196, in maybe_login
263
+ [rank0]: wandb_login._login(
264
+ [rank0]: File "/root/miniconda3/envs/py3.11/lib/python3.11/site-packages/wandb/sdk/wandb_login.py", line 190, in _login
265
+ [rank0]: auth = _find_or_prompt_for_key(
266
+ [rank0]: ^^^^^^^^^^^^^^^^^^^^^^^^
267
+ [rank0]: File "/root/miniconda3/envs/py3.11/lib/python3.11/site-packages/wandb/sdk/wandb_login.py", line 266, in _find_or_prompt_for_key
268
+ [rank0]: auth = wbauth.authenticate_session(
269
+ [rank0]: ^^^^^^^^^^^^^^^^^^^^^^^^^^^^
270
+ [rank0]: File "/root/miniconda3/envs/py3.11/lib/python3.11/site-packages/wandb/sdk/lib/wbauth/authenticate.py", line 138, in authenticate_session
271
+ [rank0]: raise UsageError(
272
+ [rank0]: wandb.errors.errors.UsageError: No API key configured. Use `wandb login` to log in.
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "bos_token": {
18
+ "content": "<|im_end|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "eos_token": {
25
+ "content": "<|im_end|>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ },
31
+ "pad_token": {
32
+ "content": "<|endoftext|>",
33
+ "lstrip": false,
34
+ "normalized": false,
35
+ "rstrip": false,
36
+ "single_word": false
37
+ }
38
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
3
+ size 11421896
tokenizer_config.json ADDED
@@ -0,0 +1,207 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151659": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151660": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151661": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151662": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151663": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151664": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ }
181
+ },
182
+ "additional_special_tokens": [
183
+ "<|im_start|>",
184
+ "<|im_end|>",
185
+ "<|object_ref_start|>",
186
+ "<|object_ref_end|>",
187
+ "<|box_start|>",
188
+ "<|box_end|>",
189
+ "<|quad_start|>",
190
+ "<|quad_end|>",
191
+ "<|vision_start|>",
192
+ "<|vision_end|>",
193
+ "<|vision_pad|>",
194
+ "<|image_pad|>",
195
+ "<|video_pad|>"
196
+ ],
197
+ "bos_token": "<|im_end|>",
198
+ "clean_up_tokenization_spaces": false,
199
+ "eos_token": "<|im_end|>",
200
+ "errors": "replace",
201
+ "extra_special_tokens": {},
202
+ "model_max_length": 131072,
203
+ "pad_token": "<|endoftext|>",
204
+ "split_special_tokens": false,
205
+ "tokenizer_class": "Qwen2Tokenizer",
206
+ "unk_token": null
207
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff