yacineai7 commited on
Commit
1c145fe
·
verified ·
1 Parent(s): a324881

Upload folder using huggingface_hub

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ checkpoint-6076/tokenizer.json filter=lfs diff=lfs merge=lfs -text
checkpoint-6076/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
+ }
checkpoint-6076/chat_template.jinja ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- if tools %}
2
+ {{- '<|im_start|>system\n' }}
3
+ {%- if messages[0]['role'] == 'system' %}
4
+ {{- messages[0]['content'] }}
5
+ {%- else %}
6
+ {{- 'You are a helpful assistant.' }}
7
+ {%- endif %}
8
+ {{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
9
+ {%- for tool in tools %}
10
+ {{- "\n" }}
11
+ {{- tool | tojson }}
12
+ {%- endfor %}
13
+ {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
14
+ {%- else %}
15
+ {%- if messages[0]['role'] == 'system' %}
16
+ {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
17
+ {%- else %}
18
+ {{- '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}
19
+ {%- endif %}
20
+ {%- endif %}
21
+ {%- for message in messages %}
22
+ {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
23
+ {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
24
+ {%- elif message.role == "assistant" %}
25
+ {{- '<|im_start|>' + message.role }}
26
+ {%- if message.content %}
27
+ {{- '\n' + message.content }}
28
+ {%- endif %}
29
+ {%- for tool_call in message.tool_calls %}
30
+ {%- if tool_call.function is defined %}
31
+ {%- set tool_call = tool_call.function %}
32
+ {%- endif %}
33
+ {{- '\n<tool_call>\n{"name": "' }}
34
+ {{- tool_call.name }}
35
+ {{- '", "arguments": ' }}
36
+ {{- tool_call.arguments | tojson }}
37
+ {{- '}\n</tool_call>' }}
38
+ {%- endfor %}
39
+ {{- '<|im_end|>\n' }}
40
+ {%- elif message.role == "tool" %}
41
+ {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
42
+ {{- '<|im_start|>user' }}
43
+ {%- endif %}
44
+ {{- '\n<tool_response>\n' }}
45
+ {{- message.content }}
46
+ {{- '\n</tool_response>' }}
47
+ {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
48
+ {{- '<|im_end|>\n' }}
49
+ {%- endif %}
50
+ {%- endif %}
51
+ {%- endfor %}
52
+ {%- if add_generation_prompt %}
53
+ {{- '<|im_start|>assistant\n' }}
54
+ {%- endif %}
checkpoint-6076/config.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen2ForCausalLM"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "dtype": "float32",
7
+ "eos_token_id": 151643,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 896,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 4864,
12
+ "layer_types": [
13
+ "full_attention",
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
+ ],
38
+ "max_position_embeddings": 32768,
39
+ "max_window_layers": 24,
40
+ "model_type": "qwen2",
41
+ "num_attention_heads": 14,
42
+ "num_hidden_layers": 24,
43
+ "num_key_value_heads": 2,
44
+ "pad_token_id": 151643,
45
+ "rms_norm_eps": 1e-06,
46
+ "rope_scaling": null,
47
+ "rope_theta": 1000000.0,
48
+ "sliding_window": null,
49
+ "tie_word_embeddings": true,
50
+ "transformers_version": "4.57.1",
51
+ "use_cache": true,
52
+ "use_mrope": false,
53
+ "use_sliding_window": false,
54
+ "vocab_size": 151936
55
+ }
checkpoint-6076/generation_config.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "eos_token_id": [
3
+ 151643
4
+ ],
5
+ "max_new_tokens": 2048,
6
+ "pad_token_id": 151643,
7
+ "transformers_version": "4.57.1"
8
+ }
checkpoint-6076/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-6076/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b06aa8d0b88f318cb27df8abe401cfe448a222e857d4ecbacc5df0d0f07111ff
3
+ size 1976163472
checkpoint-6076/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78a535aa9ef4f40c729898a27be53811d2fbdbeb23d71874c504b6e9438fd926
3
+ size 3952509771
checkpoint-6076/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1255b82ec9f462fef6f8c2f4a8ee876c4b6d998a53c99546a4eddcc1aabaefc7
3
+ size 14645
checkpoint-6076/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5261e8785819a88964889856a601e63dc23b68d91d8ac5fa42f8772369126d2a
3
+ size 1465
checkpoint-6076/special_tokens_map.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": {
18
+ "content": "<|endoftext|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": "<|endoftext|>"
25
+ }
checkpoint-6076/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
3
+ size 11421896
checkpoint-6076/tokenizer_config.json ADDED
@@ -0,0 +1,207 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151659": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151660": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151661": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151662": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151663": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151664": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ }
181
+ },
182
+ "additional_special_tokens": [
183
+ "<|im_start|>",
184
+ "<|im_end|>",
185
+ "<|object_ref_start|>",
186
+ "<|object_ref_end|>",
187
+ "<|box_start|>",
188
+ "<|box_end|>",
189
+ "<|quad_start|>",
190
+ "<|quad_end|>",
191
+ "<|vision_start|>",
192
+ "<|vision_end|>",
193
+ "<|vision_pad|>",
194
+ "<|image_pad|>",
195
+ "<|video_pad|>"
196
+ ],
197
+ "bos_token": null,
198
+ "clean_up_tokenization_spaces": false,
199
+ "eos_token": "<|endoftext|>",
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
+ }
checkpoint-6076/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-6076/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ffa843d837d5c2b40028a15284c2bb3d04eafcdbed988f0362e91fab06ea32bf
3
+ size 6161
checkpoint-6076/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
logs/trainer_20251111_112434.log ADDED
@@ -0,0 +1,158 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2025-11-11 11:24:34,344 - INFO - SFT Config: SFTConfig(
2
+ _n_gpu=1,
3
+ accelerator_config={'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None, 'use_configured_state': False},
4
+ activation_offloading=False,
5
+ adafactor=False,
6
+ adam_beta1=0.9,
7
+ adam_beta2=0.999,
8
+ adam_epsilon=1e-08,
9
+ assistant_only_loss=False,
10
+ auto_find_batch_size=False,
11
+ average_tokens_across_devices=True,
12
+ batch_eval_metrics=True,
13
+ bf16=False,
14
+ bf16_full_eval=False,
15
+ chat_template_path=None,
16
+ completion_only_loss=True,
17
+ data_seed=42,
18
+ dataloader_drop_last=False,
19
+ dataloader_num_workers=0,
20
+ dataloader_persistent_workers=False,
21
+ dataloader_pin_memory=True,
22
+ dataloader_prefetch_factor=None,
23
+ dataset_kwargs=None,
24
+ dataset_num_proc=None,
25
+ dataset_text_field=text,
26
+ ddp_backend=None,
27
+ ddp_broadcast_buffers=None,
28
+ ddp_bucket_cap_mb=None,
29
+ ddp_find_unused_parameters=None,
30
+ ddp_timeout=1800,
31
+ debug=[],
32
+ deepspeed=None,
33
+ disable_tqdm=False,
34
+ do_eval=True,
35
+ do_predict=False,
36
+ do_train=False,
37
+ eos_token=<EOS_TOKEN>,
38
+ eval_accumulation_steps=None,
39
+ eval_delay=0,
40
+ eval_do_concat_batches=True,
41
+ eval_on_start=True,
42
+ eval_packing=None,
43
+ eval_steps=0.1,
44
+ eval_strategy=IntervalStrategy.STEPS,
45
+ eval_use_gather_object=False,
46
+ fp16=False,
47
+ fp16_backend=auto,
48
+ fp16_full_eval=False,
49
+ fp16_opt_level=O1,
50
+ fsdp=[],
51
+ fsdp_config={'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False},
52
+ fsdp_min_num_params=0,
53
+ fsdp_transformer_layer_cls_to_wrap=None,
54
+ full_determinism=False,
55
+ gradient_accumulation_steps=2,
56
+ gradient_checkpointing=False,
57
+ gradient_checkpointing_kwargs=None,
58
+ greater_is_better=None,
59
+ group_by_length=False,
60
+ half_precision_backend=auto,
61
+ hub_always_push=False,
62
+ hub_model_id=None,
63
+ hub_private_repo=False,
64
+ hub_revision=None,
65
+ hub_strategy=HubStrategy.EVERY_SAVE,
66
+ hub_token=<HUB_TOKEN>,
67
+ ignore_data_skip=False,
68
+ include_for_metrics=[],
69
+ include_inputs_for_metrics=False,
70
+ include_num_input_tokens_seen=no,
71
+ include_tokens_per_second=False,
72
+ jit_mode_eval=False,
73
+ label_names=None,
74
+ label_smoothing_factor=0.0,
75
+ learning_rate=2e-05,
76
+ length_column_name=length,
77
+ liger_kernel_config=None,
78
+ load_best_model_at_end=False,
79
+ local_rank=0,
80
+ log_level=info,
81
+ log_level_replica=warning,
82
+ log_on_each_node=True,
83
+ logging_dir=./runs,
84
+ logging_first_step=True,
85
+ logging_nan_inf_filter=True,
86
+ logging_steps=5,
87
+ logging_strategy=IntervalStrategy.STEPS,
88
+ loss_type=nll,
89
+ lr_scheduler_kwargs={},
90
+ lr_scheduler_type=SchedulerType.COSINE,
91
+ max_grad_norm=1.0,
92
+ max_length=1024,
93
+ max_steps=-1,
94
+ metric_for_best_model=None,
95
+ model_init_kwargs=None,
96
+ mp_parameters=,
97
+ neftune_noise_alpha=None,
98
+ no_cuda=False,
99
+ num_train_epochs=2,
100
+ optim=OptimizerNames.ADAMW_TORCH_FUSED,
101
+ optim_args=None,
102
+ optim_target_modules=None,
103
+ output_dir=./models,
104
+ overwrite_output_dir=False,
105
+ packing=False,
106
+ packing_strategy=bfd,
107
+ pad_to_multiple_of=None,
108
+ pad_token=<PAD_TOKEN>,
109
+ padding_free=False,
110
+ parallelism_config=None,
111
+ past_index=-1,
112
+ per_device_eval_batch_size=6,
113
+ per_device_train_batch_size=6,
114
+ prediction_loss_only=False,
115
+ project=huggingface,
116
+ push_to_hub=False,
117
+ push_to_hub_model_id=None,
118
+ push_to_hub_organization=None,
119
+ push_to_hub_token=<PUSH_TO_HUB_TOKEN>,
120
+ ray_scope=last,
121
+ remove_unused_columns=True,
122
+ report_to=['tensorboard'],
123
+ restore_callback_states_from_checkpoint=False,
124
+ resume_from_checkpoint=None,
125
+ run_name=None,
126
+ save_on_each_node=False,
127
+ save_only_model=False,
128
+ save_safetensors=True,
129
+ save_steps=0.1,
130
+ save_strategy=SaveStrategy.STEPS,
131
+ save_total_limit=3,
132
+ seed=42,
133
+ skip_memory_metrics=True,
134
+ tf32=None,
135
+ torch_compile=False,
136
+ torch_compile_backend=None,
137
+ torch_compile_mode=None,
138
+ torch_empty_cache_steps=None,
139
+ torchdynamo=None,
140
+ tpu_metrics_debug=False,
141
+ tpu_num_cores=None,
142
+ trackio_space_id=trackio,
143
+ use_cpu=False,
144
+ use_legacy_prediction_loop=False,
145
+ use_liger_kernel=False,
146
+ use_mps_device=False,
147
+ warmup_ratio=0.05,
148
+ warmup_steps=0,
149
+ weight_decay=0.01,
150
+ )
151
+ 2025-11-11 11:24:34,344 - INFO - Data Config: data_train_path='./data/train_sft_data.jsonl' data_dev_path='./data/dev_preprocessed_human.jsonl' data_test_path='./data/test_preprocessed_human.jsonl' db_train_path='./data/train.db' db_dev_path='./data/dev.db' db_test_path='./data/test.db' do_sample_train=False do_sample_dev=False do_sample_test=False n_sample_train=200 n_sample_dev=50 n_sample_test=50
152
+ 2025-11-11 11:25:42,178 - INFO - Starting full pipeline.
153
+ 2025-11-11 11:25:42,178 - INFO - Training model...
154
+ 2025-11-11 13:23:39,551 - INFO - Training completed.
155
+ 2025-11-11 13:47:01,198 - INFO - Final Dev Metrics: {'lf_accuracy': 0.7649813858532485, 'execution_accuracy': 0.8046115047436051}
156
+ 2025-11-11 13:47:01,198 - INFO - Running final test evaluation...
157
+ 2025-11-11 14:31:11,980 - INFO - Test Metrics: {'lf_accuracy': 0.7681140965236215, 'execution_accuracy': 0.807143766713358}
158
+ 2025-11-11 14:31:11,980 - INFO - Final Test Metrics: {'lf_accuracy': 0.7681140965236215, 'execution_accuracy': 0.807143766713358}
runs/events.out.tfevents ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f97380cd8f03bcaae316824a12fcaa20dfa2d9468751233f32ea92f3d184025a
3
+ size 475268