Hugging Face's logo

Dash00
/
reranker-bc5cdr

Safetensors
qwen3
Model card Files
xet
Community
Dash00 commited on
Commit
a20803d
·
verified ·
1 Parent(s): c7d55b9

update files

Browse files
Files changed (19) hide show
  1. .gitattributes +1 -0
  2. added_tokens.json +28 -0
  3. args.json +356 -0
  4. chat_template.jinja +85 -0
  5. config.json +68 -0
  6. generation_config.json +12 -0
  7. merges.txt +0 -0
  8. model-00001-of-00002.safetensors +3 -0
  9. model-00002-of-00002.safetensors +3 -0
  10. model.safetensors.index.json +406 -0
  11. optimizer.pt +3 -0
  12. rng_state.pth +3 -0
  13. scheduler.pt +3 -0
  14. special_tokens_map.json +31 -0
  15. tokenizer.json +3 -0
  16. tokenizer_config.json +239 -0
  17. trainer_state.json +2094 -0
  18. training_args.bin +3 -0
  19. 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
added_tokens.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</think>": 151668,
3
+ "</tool_call>": 151658,
4
+ "</tool_response>": 151666,
5
+ "<think>": 151667,
6
+ "<tool_call>": 151657,
7
+ "<tool_response>": 151665,
8
+ "<|box_end|>": 151649,
9
+ "<|box_start|>": 151648,
10
+ "<|endoftext|>": 151643,
11
+ "<|file_sep|>": 151664,
12
+ "<|fim_middle|>": 151660,
13
+ "<|fim_pad|>": 151662,
14
+ "<|fim_prefix|>": 151659,
15
+ "<|fim_suffix|>": 151661,
16
+ "<|im_end|>": 151645,
17
+ "<|im_start|>": 151644,
18
+ "<|image_pad|>": 151655,
19
+ "<|object_ref_end|>": 151647,
20
+ "<|object_ref_start|>": 151646,
21
+ "<|quad_end|>": 151651,
22
+ "<|quad_start|>": 151650,
23
+ "<|repo_name|>": 151663,
24
+ "<|video_pad|>": 151656,
25
+ "<|vision_end|>": 151653,
26
+ "<|vision_pad|>": 151654,
27
+ "<|vision_start|>": 151652
28
+ }
args.json ADDED
@@ -0,0 +1,356 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "output_dir": "/home/serusr01/new/output/v48-20251225-153152",
3
+ "overwrite_output_dir": false,
4
+ "do_train": false,
5
+ "do_eval": false,
6
+ "do_predict": false,
7
+ "eval_strategy": "steps",
8
+ "prediction_loss_only": false,
9
+ "per_device_train_batch_size": 2,
10
+ "per_device_eval_batch_size": 2,
11
+ "per_gpu_train_batch_size": null,
12
+ "per_gpu_eval_batch_size": null,
13
+ "gradient_accumulation_steps": 8,
14
+ "eval_accumulation_steps": null,
15
+ "eval_delay": 0,
16
+ "torch_empty_cache_steps": null,
17
+ "learning_rate": 6e-06,
18
+ "weight_decay": 0.1,
19
+ "adam_beta1": 0.9,
20
+ "adam_beta2": 0.95,
21
+ "adam_epsilon": 1e-08,
22
+ "max_grad_norm": 1.0,
23
+ "num_train_epochs": 1.0,
24
+ "max_steps": -1,
25
+ "lr_scheduler_type": "cosine",
26
+ "lr_scheduler_kwargs": null,
27
+ "warmup_ratio": 0.0,
28
+ "warmup_steps": 0,
29
+ "log_level": "passive",
30
+ "log_level_replica": "warning",
31
+ "log_on_each_node": true,
32
+ "logging_dir": "/home/serusr01/new/output/v48-20251225-153152/runs",
33
+ "logging_strategy": "steps",
34
+ "logging_first_step": true,
35
+ "logging_steps": 5,
36
+ "logging_nan_inf_filter": true,
37
+ "save_strategy": "steps",
38
+ "save_steps": 400.0,
39
+ "save_total_limit": null,
40
+ "save_safetensors": true,
41
+ "save_on_each_node": false,
42
+ "save_only_model": false,
43
+ "restore_callback_states_from_checkpoint": false,
44
+ "no_cuda": false,
45
+ "use_cpu": false,
46
+ "use_mps_device": false,
47
+ "seed": 42,
48
+ "data_seed": 42,
49
+ "jit_mode_eval": false,
50
+ "bf16": true,
51
+ "fp16": false,
52
+ "fp16_opt_level": "O1",
53
+ "half_precision_backend": "auto",
54
+ "bf16_full_eval": false,
55
+ "fp16_full_eval": false,
56
+ "tf32": null,
57
+ "local_rank": 0,
58
+ "ddp_backend": null,
59
+ "tpu_num_cores": null,
60
+ "tpu_metrics_debug": false,
61
+ "debug": null,
62
+ "dataloader_drop_last": true,
63
+ "eval_steps": 100.0,
64
+ "dataloader_num_workers": null,
65
+ "dataloader_prefetch_factor": null,
66
+ "past_index": -1,
67
+ "run_name": "/home/serusr01/new/output/v48-20251225-153152",
68
+ "disable_tqdm": null,
69
+ "remove_unused_columns": true,
70
+ "label_names": [
71
+ "labels"
72
+ ],
73
+ "load_best_model_at_end": false,
74
+ "metric_for_best_model": "loss",
75
+ "greater_is_better": false,
76
+ "ignore_data_skip": false,
77
+ "fsdp": null,
78
+ "fsdp_min_num_params": 0,
79
+ "fsdp_config": null,
80
+ "fsdp_transformer_layer_cls_to_wrap": null,
81
+ "accelerator_config": {
82
+ "dispatch_batches": false
83
+ },
84
+ "parallelism_config": null,
85
+ "deepspeed": null,
86
+ "label_smoothing_factor": 0.0,
87
+ "optim": "adamw_torch",
88
+ "optim_args": null,
89
+ "adafactor": false,
90
+ "group_by_length": false,
91
+ "length_column_name": "length",
92
+ "report_to": [
93
+ "tensorboard"
94
+ ],
95
+ "project": "huggingface",
96
+ "trackio_space_id": "trackio",
97
+ "ddp_find_unused_parameters": null,
98
+ "ddp_bucket_cap_mb": null,
99
+ "ddp_broadcast_buffers": null,
100
+ "dataloader_pin_memory": true,
101
+ "dataloader_persistent_workers": false,
102
+ "skip_memory_metrics": true,
103
+ "use_legacy_prediction_loop": false,
104
+ "push_to_hub": false,
105
+ "resume_from_checkpoint": null,
106
+ "hub_model_id": null,
107
+ "hub_strategy": "every_save",
108
+ "hub_token": null,
109
+ "hub_private_repo": null,
110
+ "hub_always_push": false,
111
+ "hub_revision": null,
112
+ "gradient_checkpointing": true,
113
+ "gradient_checkpointing_kwargs": null,
114
+ "include_inputs_for_metrics": false,
115
+ "include_for_metrics": [],
116
+ "eval_do_concat_batches": true,
117
+ "fp16_backend": "auto",
118
+ "push_to_hub_model_id": null,
119
+ "push_to_hub_organization": null,
120
+ "push_to_hub_token": null,
121
+ "mp_parameters": "",
122
+ "auto_find_batch_size": false,
123
+ "full_determinism": false,
124
+ "torchdynamo": null,
125
+ "ray_scope": "last",
126
+ "ddp_timeout": 18000000,
127
+ "torch_compile": false,
128
+ "torch_compile_backend": null,
129
+ "torch_compile_mode": null,
130
+ "include_tokens_per_second": false,
131
+ "include_num_input_tokens_seen": false,
132
+ "neftune_noise_alpha": null,
133
+ "optim_target_modules": null,
134
+ "batch_eval_metrics": false,
135
+ "eval_on_start": false,
136
+ "use_liger_kernel": false,
137
+ "liger_kernel_config": null,
138
+ "eval_use_gather_object": false,
139
+ "average_tokens_across_devices": true,
140
+ "sortish_sampler": false,
141
+ "predict_with_generate": false,
142
+ "generation_max_length": null,
143
+ "generation_num_beams": null,
144
+ "generation_config": null,
145
+ "tuner_backend": "peft",
146
+ "vit_gradient_checkpointing": null,
147
+ "router_aux_loss_coef": 0.0,
148
+ "enable_dft_loss": false,
149
+ "enable_channel_loss": false,
150
+ "check_model": true,
151
+ "acc_strategy": "token",
152
+ "train_dataloader_shuffle": true,
153
+ "max_epochs": null,
154
+ "aligner_lr": null,
155
+ "vit_lr": null,
156
+ "use_logits_to_keep": null,
157
+ "ds3_gather_for_generation": true,
158
+ "resume_only_model": false,
159
+ "optimizer": null,
160
+ "loss_type": "generative_reranker",
161
+ "metric": null,
162
+ "eval_use_evalscope": false,
163
+ "eval_dataset": [],
164
+ "eval_dataset_args": null,
165
+ "eval_limit": null,
166
+ "eval_generation_config": null,
167
+ "extra_eval_args": null,
168
+ "use_flash_ckpt": false,
169
+ "use_ray": false,
170
+ "ray_exp_name": null,
171
+ "device_groups": null,
172
+ "model": "Qwen/Qwen3-Reranker-4B",
173
+ "model_type": "qwen3_reranker",
174
+ "model_revision": null,
175
+ "task_type": "generative_reranker",
176
+ "torch_dtype": "bfloat16",
177
+ "attn_impl": null,
178
+ "new_special_tokens": [],
179
+ "num_labels": null,
180
+ "problem_type": null,
181
+ "rope_scaling": null,
182
+ "device_map": null,
183
+ "max_memory": {},
184
+ "max_model_len": null,
185
+ "local_repo_path": null,
186
+ "init_strategy": null,
187
+ "template": "qwen3_reranker",
188
+ "system": null,
189
+ "max_length": 40960,
190
+ "truncation_strategy": "delete",
191
+ "max_pixels": null,
192
+ "agent_template": null,
193
+ "norm_bbox": null,
194
+ "use_chat_template": true,
195
+ "padding_free": false,
196
+ "padding_side": "left",
197
+ "loss_scale": "default",
198
+ "sequence_parallel_size": 1,
199
+ "response_prefix": null,
200
+ "template_backend": "swift",
201
+ "dataset": [
202
+ "Dash00/bc5cdr-reranking3"
203
+ ],
204
+ "val_dataset": [],
205
+ "cached_dataset": [],
206
+ "cached_val_dataset": [],
207
+ "split_dataset_ratio": 0.05,
208
+ "dataset_num_proc": 8,
209
+ "load_from_cache_file": false,
210
+ "dataset_shuffle": true,
211
+ "val_dataset_shuffle": false,
212
+ "streaming": false,
213
+ "interleave_prob": null,
214
+ "stopping_strategy": "first_exhausted",
215
+ "shuffle_buffer_size": 1000,
216
+ "download_mode": "reuse_dataset_if_exists",
217
+ "columns": {
218
+ "query": "query",
219
+ "system": "system",
220
+ "positive": "positive",
221
+ "negative": "negative"
222
+ },
223
+ "strict": false,
224
+ "model_name": null,
225
+ "model_author": null,
226
+ "custom_dataset_info": [],
227
+ "quant_method": null,
228
+ "quant_bits": null,
229
+ "hqq_axis": null,
230
+ "bnb_4bit_compute_dtype": "bfloat16",
231
+ "bnb_4bit_quant_type": "nf4",
232
+ "bnb_4bit_use_double_quant": true,
233
+ "bnb_4bit_quant_storage": null,
234
+ "max_new_tokens": 64,
235
+ "temperature": 0.0,
236
+ "top_k": null,
237
+ "top_p": null,
238
+ "repetition_penalty": null,
239
+ "num_beams": 1,
240
+ "stream": false,
241
+ "stop_words": [],
242
+ "logprobs": false,
243
+ "top_logprobs": null,
244
+ "ckpt_dir": null,
245
+ "lora_modules": [],
246
+ "train_type": "full",
247
+ "adapters": [],
248
+ "external_plugins": [],
249
+ "model_kwargs": {},
250
+ "load_args": false,
251
+ "load_data_args": false,
252
+ "packing": false,
253
+ "packing_length": null,
254
+ "packing_num_proc": 1,
255
+ "lazy_tokenize": false,
256
+ "custom_register_path": [],
257
+ "use_hf": true,
258
+ "ignore_args_error": false,
259
+ "use_swift_lora": false,
260
+ "freeze_parameters": [],
261
+ "freeze_parameters_regex": null,
262
+ "freeze_parameters_ratio": 0.0,
263
+ "trainable_parameters": [],
264
+ "trainable_parameters_regex": null,
265
+ "freeze_llm": false,
266
+ "freeze_vit": true,
267
+ "freeze_aligner": true,
268
+ "target_modules": [
269
+ "all-linear"
270
+ ],
271
+ "target_regex": null,
272
+ "target_parameters": null,
273
+ "modules_to_save": [],
274
+ "lora_rank": 8,
275
+ "lora_alpha": 32,
276
+ "lora_dropout": 0.05,
277
+ "lora_bias": "none",
278
+ "lora_dtype": null,
279
+ "lorap_lr_ratio": null,
280
+ "use_rslora": false,
281
+ "use_dora": false,
282
+ "lora_ga_batch_size": 2,
283
+ "lora_ga_iters": 2,
284
+ "lora_ga_max_length": 1024,
285
+ "lora_ga_direction": "ArB2r",
286
+ "lora_ga_scale": "stable",
287
+ "lora_ga_stable_gamma": 16,
288
+ "init_weights": true,
289
+ "fourier_n_frequency": 2000,
290
+ "fourier_scaling": 300.0,
291
+ "boft_block_size": 4,
292
+ "boft_block_num": 0,
293
+ "boft_n_butterfly_factor": 1,
294
+ "boft_dropout": 0.0,
295
+ "vera_rank": 256,
296
+ "vera_projection_prng_key": 0,
297
+ "vera_dropout": 0.0,
298
+ "vera_d_initial": 0.1,
299
+ "adapter_act": "gelu",
300
+ "adapter_length": 128,
301
+ "use_galore": false,
302
+ "galore_target_modules": null,
303
+ "galore_rank": 128,
304
+ "galore_update_proj_gap": 50,
305
+ "galore_scale": 1.0,
306
+ "galore_proj_type": "std",
307
+ "galore_optim_per_parameter": false,
308
+ "galore_with_embedding": false,
309
+ "galore_quantization": false,
310
+ "galore_proj_quant": false,
311
+ "galore_proj_bits": 4,
312
+ "galore_proj_group_size": 256,
313
+ "galore_cos_threshold": 0.4,
314
+ "galore_gamma_proj": 2,
315
+ "galore_queue_size": 5,
316
+ "adalora_target_r": 8,
317
+ "adalora_init_r": 12,
318
+ "adalora_tinit": 0,
319
+ "adalora_tfinal": 0,
320
+ "adalora_deltaT": 1,
321
+ "adalora_beta1": 0.85,
322
+ "adalora_beta2": 0.85,
323
+ "adalora_orth_reg_weight": 0.5,
324
+ "llamapro_num_new_blocks": 4,
325
+ "llamapro_num_groups": null,
326
+ "lisa_activated_layers": 0,
327
+ "lisa_step_interval": 20,
328
+ "reft_layer_key": null,
329
+ "reft_layers": null,
330
+ "reft_rank": 4,
331
+ "reft_intervention_type": "LoreftIntervention",
332
+ "reft_args": null,
333
+ "swanlab_token": null,
334
+ "swanlab_project": null,
335
+ "swanlab_workspace": null,
336
+ "swanlab_exp_name": null,
337
+ "swanlab_lark_webhook_url": null,
338
+ "swanlab_lark_secret": null,
339
+ "swanlab_mode": "cloud",
340
+ "add_version": true,
341
+ "create_checkpoint_symlink": false,
342
+ "zero_hpz_partition_size": null,
343
+ "deepspeed_autotp_size": null,
344
+ "early_stop_interval": null,
345
+ "rank": 0,
346
+ "global_world_size": 1,
347
+ "local_world_size": 1,
348
+ "model_suffix": "Qwen3-Reranker-4B",
349
+ "model_info": "ModelInfo(model_type='qwen3_reranker', model_dir='/home/serusr01/.cache/huggingface/hub/models--Qwen--Qwen3-Reranker-4B/snapshots/f16fc5d5d2b9b1d0db8280929242745d79794ef5', torch_dtype=torch.bfloat16, max_model_len=40960, quant_method=None, quant_bits=None, rope_scaling=None, is_moe_model=False, is_multimodal=False, config=None, task_type='generative_reranker', num_labels=None)",
350
+ "model_meta": "ModelMeta(model_type='qwen3_reranker', model_groups=[ModelGroup(models=[Model(ms_model_id='Qwen/Qwen3-Reranker-0.6B', hf_model_id='Qwen/Qwen3-Reranker-0.6B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-Reranker-4B', hf_model_id='Qwen/Qwen3-Reranker-4B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-Reranker-8B', hf_model_id='Qwen/Qwen3-Reranker-8B', model_path=None, ms_revision=None, hf_revision=None)], ignore_patterns=None, requires=None, tags=[])], template='qwen3_reranker', get_function=<function get_model_tokenizer_with_flash_attn at 0x740c6ee0a340>, model_arch=None, architectures=['Qwen3ForCausalLM'], additional_saved_files=[], torch_dtype=None, is_multimodal=False, is_reward=False, is_reranker=True, task_type='reranker', ignore_patterns=None, requires=[], tags=[])",
351
+ "model_dir": "/home/serusr01/.cache/huggingface/hub/models--Qwen--Qwen3-Reranker-4B/snapshots/f16fc5d5d2b9b1d0db8280929242745d79794ef5",
352
+ "_val_dataset_exists": true,
353
+ "hub": "<class 'swift.hub.hub.HFHub'>",
354
+ "evaluation_strategy": "steps",
355
+ "training_args": "TrainingArguments(output_dir='/home/serusr01/new/output/v48-20251225-153152', overwrite_output_dir=False, do_train=False, do_eval=True, do_predict=False, eval_strategy=<IntervalStrategy.STEPS: 'steps'>, prediction_loss_only=False, per_device_train_batch_size=2, per_device_eval_batch_size=2, per_gpu_train_batch_size=None, per_gpu_eval_batch_size=None, gradient_accumulation_steps=8, eval_accumulation_steps=None, eval_delay=0, torch_empty_cache_steps=None, learning_rate=6e-06, weight_decay=0.1, adam_beta1=0.9, adam_beta2=0.95, adam_epsilon=1e-08, max_grad_norm=1.0, num_train_epochs=1.0, max_steps=-1, lr_scheduler_type=<SchedulerType.COSINE: 'cosine'>, lr_scheduler_kwargs=None, warmup_ratio=0.0, warmup_steps=0, log_level='passive', log_level_replica='warning', log_on_each_node=True, logging_dir='/home/serusr01/new/output/v48-20251225-153152/runs', logging_strategy=<IntervalStrategy.STEPS: 'steps'>, logging_first_step=True, logging_steps=5, logging_nan_inf_filter=True, save_strategy=<SaveStrategy.STEPS: 'steps'>, save_steps=400, save_total_limit=None, save_safetensors=True, save_on_each_node=False, save_only_model=False, restore_callback_states_from_checkpoint=False, no_cuda=False, use_cpu=False, use_mps_device=False, seed=42, data_seed=42, jit_mode_eval=False, bf16=True, fp16=False, fp16_opt_level='O1', half_precision_backend='auto', bf16_full_eval=False, fp16_full_eval=False, tf32=None, local_rank=0, ddp_backend=None, tpu_num_cores=None, tpu_metrics_debug=False, debug=[], dataloader_drop_last=True, eval_steps=100, dataloader_num_workers=1, dataloader_prefetch_factor=10, past_index=-1, run_name='/home/serusr01/new/output/v48-20251225-153152', disable_tqdm=False, remove_unused_columns=False, label_names=['labels'], load_best_model_at_end=False, metric_for_best_model='loss', greater_is_better=False, ignore_data_skip=False, fsdp=[], fsdp_min_num_params=0, fsdp_config={'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, fsdp_transformer_layer_cls_to_wrap=None, accelerator_config=AcceleratorConfig(split_batches=False, dispatch_batches=False, even_batches=True, use_seedable_sampler=True, non_blocking=False, gradient_accumulation_kwargs=None, use_configured_state=False), parallelism_config=None, deepspeed=None, label_smoothing_factor=0.0, optim=<OptimizerNames.ADAMW_TORCH: 'adamw_torch'>, optim_args=None, adafactor=False, group_by_length=False, length_column_name='length', report_to=['tensorboard'], project='huggingface', trackio_space_id='trackio', ddp_find_unused_parameters=None, ddp_bucket_cap_mb=None, ddp_broadcast_buffers=None, dataloader_pin_memory=True, dataloader_persistent_workers=False, skip_memory_metrics=True, use_legacy_prediction_loop=False, push_to_hub=False, resume_from_checkpoint=None, hub_model_id=None, hub_strategy=<HubStrategy.EVERY_SAVE: 'every_save'>, hub_token=None, hub_private_repo=None, hub_always_push=False, hub_revision=None, gradient_checkpointing=True, gradient_checkpointing_kwargs=None, include_inputs_for_metrics=False, include_for_metrics=[], eval_do_concat_batches=True, fp16_backend='auto', push_to_hub_model_id=None, push_to_hub_organization=None, push_to_hub_token=None, mp_parameters='', auto_find_batch_size=False, full_determinism=False, torchdynamo=None, ray_scope='last', ddp_timeout=18000000, torch_compile=False, torch_compile_backend=None, torch_compile_mode=None, include_tokens_per_second=None, include_num_input_tokens_seen=None, neftune_noise_alpha=None, optim_target_modules=None, batch_eval_metrics=False, eval_on_start=False, use_liger_kernel=False, liger_kernel_config=None, eval_use_gather_object=False, average_tokens_across_devices=None, tuner_backend='peft', vit_gradient_checkpointing=True, router_aux_loss_coef=0.0, enable_dft_loss=False, enable_channel_loss=False, check_model=True, acc_strategy='token', train_dataloader_shuffle=True, max_epochs=None, aligner_lr=None, vit_lr=None, use_logits_to_keep=None, ds3_gather_for_generation=True, resume_only_model=False, optimizer=None, loss_type='generative_reranker', metric=None, eval_use_evalscope=False, eval_dataset=[], eval_dataset_args=None, eval_limit=None, eval_generation_config=None, extra_eval_args=None, use_flash_ckpt=False, sft_alpha=0, chord_sft_dataset=[], chord_sft_per_device_train_batch_size=None, chord_enable_phi_function=False, chord_mu_warmup_steps=None, chord_mu_decay_steps=None, chord_mu_peak=None, chord_mu_valley=None, train_type='full', local_repo_path=None, galore_config=None, padding_side='left', padding_free=False, task_type='generative_reranker', problem_type=None)"
356
+ }
chat_template.jinja ADDED
@@ -0,0 +1,85 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- if tools %}
2
+ {{- '<|im_start|>system\n' }}
3
+ {%- if messages[0].role == 'system' %}
4
+ {{- messages[0].content + '\n\n' }}
5
+ {%- endif %}
6
+ {{- "# 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>" }}
7
+ {%- for tool in tools %}
8
+ {{- "\n" }}
9
+ {{- tool | tojson }}
10
+ {%- endfor %}
11
+ {{- "\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" }}
12
+ {%- else %}
13
+ {%- if messages[0].role == 'system' %}
14
+ {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
15
+ {%- endif %}
16
+ {%- endif %}
17
+ {%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
18
+ {%- for message in messages[::-1] %}
19
+ {%- set index = (messages|length - 1) - loop.index0 %}
20
+ {%- if ns.multi_step_tool and message.role == "user" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
21
+ {%- set ns.multi_step_tool = false %}
22
+ {%- set ns.last_query_index = index %}
23
+ {%- endif %}
24
+ {%- endfor %}
25
+ {%- for message in messages %}
26
+ {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
27
+ {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
28
+ {%- elif message.role == "assistant" %}
29
+ {%- set content = message.content %}
30
+ {%- set reasoning_content = '' %}
31
+ {%- if message.reasoning_content is defined and message.reasoning_content is not none %}
32
+ {%- set reasoning_content = message.reasoning_content %}
33
+ {%- else %}
34
+ {%- if '</think>' in message.content %}
35
+ {%- set content = message.content.split('</think>')[-1].lstrip('\n') %}
36
+ {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
37
+ {%- endif %}
38
+ {%- endif %}
39
+ {%- if loop.index0 > ns.last_query_index %}
40
+ {%- if loop.last or (not loop.last and reasoning_content) %}
41
+ {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
42
+ {%- else %}
43
+ {{- '<|im_start|>' + message.role + '\n' + content }}
44
+ {%- endif %}
45
+ {%- else %}
46
+ {{- '<|im_start|>' + message.role + '\n' + content }}
47
+ {%- endif %}
48
+ {%- if message.tool_calls %}
49
+ {%- for tool_call in message.tool_calls %}
50
+ {%- if (loop.first and content) or (not loop.first) %}
51
+ {{- '\n' }}
52
+ {%- endif %}
53
+ {%- if tool_call.function %}
54
+ {%- set tool_call = tool_call.function %}
55
+ {%- endif %}
56
+ {{- '<tool_call>\n{"name": "' }}
57
+ {{- tool_call.name }}
58
+ {{- '", "arguments": ' }}
59
+ {%- if tool_call.arguments is string %}
60
+ {{- tool_call.arguments }}
61
+ {%- else %}
62
+ {{- tool_call.arguments | tojson }}
63
+ {%- endif %}
64
+ {{- '}\n</tool_call>' }}
65
+ {%- endfor %}
66
+ {%- endif %}
67
+ {{- '<|im_end|>\n' }}
68
+ {%- elif message.role == "tool" %}
69
+ {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
70
+ {{- '<|im_start|>user' }}
71
+ {%- endif %}
72
+ {{- '\n<tool_response>\n' }}
73
+ {{- message.content }}
74
+ {{- '\n</tool_response>' }}
75
+ {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
76
+ {{- '<|im_end|>\n' }}
77
+ {%- endif %}
78
+ {%- endif %}
79
+ {%- endfor %}
80
+ {%- if add_generation_prompt %}
81
+ {{- '<|im_start|>assistant\n' }}
82
+ {%- if enable_thinking is defined and enable_thinking is false %}
83
+ {{- '<think>\n\n</think>\n\n' }}
84
+ {%- endif %}
85
+ {%- endif %}
config.json ADDED
@@ -0,0 +1,68 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3ForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "dtype": "bfloat16",
8
+ "eos_token_id": 151645,
9
+ "head_dim": 128,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 2560,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 9728,
14
+ "layer_types": [
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
+ "full_attention"
51
+ ],
52
+ "max_position_embeddings": 40960,
53
+ "max_window_layers": 36,
54
+ "model_type": "qwen3",
55
+ "num_attention_heads": 32,
56
+ "num_hidden_layers": 36,
57
+ "num_key_value_heads": 8,
58
+ "pad_token_id": 151643,
59
+ "rms_norm_eps": 1e-06,
60
+ "rope_scaling": null,
61
+ "rope_theta": 1000000,
62
+ "sliding_window": null,
63
+ "tie_word_embeddings": true,
64
+ "transformers_version": "4.57.1",
65
+ "use_cache": false,
66
+ "use_sliding_window": false,
67
+ "vocab_size": 151669
68
+ }
generation_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_sample": true,
3
+ "eos_token_id": [
4
+ 151645,
5
+ 151643
6
+ ],
7
+ "pad_token_id": 151643,
8
+ "temperature": 0.6,
9
+ "top_k": 20,
10
+ "top_p": 0.95,
11
+ "transformers_version": "4.57.1"
12
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99fbfeaafac3e408d66051fa5eec59eda698c5357f19ba537e68fee71c4aa48a
3
+ size 4965848320
model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1decbc51a383a024c82693300fea92bff41b6f67e9a5b435c2c2347226b6e02e
3
+ size 3077766632
model.safetensors.index.json ADDED
@@ -0,0 +1,406 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_parameters": 4021784576,
4
+ "total_size": 8043569152
5
+ },
6
+ "weight_map": {
7
+ "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
10
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
11
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
13
+ "model.layers.0.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
14
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
15
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
16
+ "model.layers.0.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
17
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
18
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
19
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
20
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
21
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
22
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
23
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
24
+ "model.layers.1.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
25
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
26
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
27
+ "model.layers.1.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
28
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
29
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
30
+ "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
31
+ "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
32
+ "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
33
+ "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
34
+ "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
35
+ "model.layers.10.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
36
+ "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
37
+ "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
38
+ "model.layers.10.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
39
+ "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
40
+ "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
41
+ "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
42
+ "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
43
+ "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
44
+ "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
45
+ "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
46
+ "model.layers.11.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
47
+ "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
48
+ "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
49
+ "model.layers.11.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
50
+ "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
51
+ "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
52
+ "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
53
+ "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
54
+ "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
55
+ "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
56
+ "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
57
+ "model.layers.12.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
58
+ "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
59
+ "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
60
+ "model.layers.12.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
61
+ "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
62
+ "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
63
+ "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
64
+ "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
65
+ "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
66
+ "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
67
+ "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
68
+ "model.layers.13.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
69
+ "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
70
+ "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
71
+ "model.layers.13.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
72
+ "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
73
+ "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
74
+ "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
75
+ "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
76
+ "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
77
+ "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
78
+ "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
79
+ "model.layers.14.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
80
+ "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
81
+ "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
82
+ "model.layers.14.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
83
+ "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
84
+ "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
85
+ "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
86
+ "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
87
+ "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
88
+ "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
89
+ "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
90
+ "model.layers.15.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
91
+ "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
92
+ "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
93
+ "model.layers.15.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
94
+ "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
95
+ "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
96
+ "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
97
+ "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
98
+ "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
99
+ "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
100
+ "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
101
+ "model.layers.16.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
102
+ "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
103
+ "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
104
+ "model.layers.16.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
105
+ "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
106
+ "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
107
+ "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
108
+ "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
109
+ "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
110
+ "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
111
+ "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
112
+ "model.layers.17.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
113
+ "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
114
+ "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
115
+ "model.layers.17.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
116
+ "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
117
+ "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
118
+ "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
119
+ "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
120
+ "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
121
+ "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
122
+ "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
123
+ "model.layers.18.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
124
+ "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
125
+ "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
126
+ "model.layers.18.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
127
+ "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
128
+ "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
129
+ "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
130
+ "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
131
+ "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
132
+ "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
133
+ "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
134
+ "model.layers.19.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
135
+ "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
136
+ "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
137
+ "model.layers.19.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
138
+ "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
139
+ "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
140
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
141
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
142
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
143
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
144
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
145
+ "model.layers.2.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
146
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
147
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
148
+ "model.layers.2.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
149
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
150
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
151
+ "model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
152
+ "model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
153
+ "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
154
+ "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
155
+ "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
156
+ "model.layers.20.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
157
+ "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
158
+ "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
159
+ "model.layers.20.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
160
+ "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
161
+ "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
162
+ "model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
163
+ "model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
164
+ "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
165
+ "model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
166
+ "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
167
+ "model.layers.21.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
168
+ "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
169
+ "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
170
+ "model.layers.21.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
171
+ "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
172
+ "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
173
+ "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
174
+ "model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
175
+ "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
176
+ "model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
177
+ "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
178
+ "model.layers.22.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
179
+ "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
180
+ "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
181
+ "model.layers.22.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
182
+ "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
183
+ "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
184
+ "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
185
+ "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
186
+ "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
187
+ "model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
188
+ "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
189
+ "model.layers.23.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
190
+ "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
191
+ "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
192
+ "model.layers.23.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
193
+ "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
194
+ "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
195
+ "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
196
+ "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
197
+ "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
198
+ "model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
199
+ "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
200
+ "model.layers.24.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
201
+ "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
202
+ "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
203
+ "model.layers.24.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
204
+ "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
205
+ "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
206
+ "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
207
+ "model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
208
+ "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
209
+ "model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
210
+ "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
211
+ "model.layers.25.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
212
+ "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
213
+ "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
214
+ "model.layers.25.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
215
+ "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
216
+ "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
217
+ "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
218
+ "model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
219
+ "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
220
+ "model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
221
+ "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
222
+ "model.layers.26.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
223
+ "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
224
+ "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
225
+ "model.layers.26.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
226
+ "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
227
+ "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
228
+ "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
229
+ "model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
230
+ "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
231
+ "model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
232
+ "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
233
+ "model.layers.27.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
234
+ "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
235
+ "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
236
+ "model.layers.27.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
237
+ "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
238
+ "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
239
+ "model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
240
+ "model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
241
+ "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
242
+ "model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
243
+ "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
244
+ "model.layers.28.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
245
+ "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
246
+ "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
247
+ "model.layers.28.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
248
+ "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
249
+ "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
250
+ "model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
251
+ "model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
252
+ "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
253
+ "model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
254
+ "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
255
+ "model.layers.29.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
256
+ "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
257
+ "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
258
+ "model.layers.29.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
259
+ "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
260
+ "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
261
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
262
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
263
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
264
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
265
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
266
+ "model.layers.3.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
267
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
268
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
269
+ "model.layers.3.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
270
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
271
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
272
+ "model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
273
+ "model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
274
+ "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
275
+ "model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
276
+ "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
277
+ "model.layers.30.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
278
+ "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
279
+ "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
280
+ "model.layers.30.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
281
+ "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
282
+ "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
283
+ "model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
284
+ "model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
285
+ "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
286
+ "model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
287
+ "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
288
+ "model.layers.31.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
289
+ "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
290
+ "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
291
+ "model.layers.31.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
292
+ "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
293
+ "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
294
+ "model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
295
+ "model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
296
+ "model.layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
297
+ "model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
298
+ "model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
299
+ "model.layers.32.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
300
+ "model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
301
+ "model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
302
+ "model.layers.32.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
303
+ "model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
304
+ "model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
305
+ "model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
306
+ "model.layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
307
+ "model.layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
308
+ "model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
309
+ "model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
310
+ "model.layers.33.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
311
+ "model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
312
+ "model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
313
+ "model.layers.33.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
314
+ "model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
315
+ "model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
316
+ "model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors",
317
+ "model.layers.34.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
318
+ "model.layers.34.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
319
+ "model.layers.34.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
320
+ "model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
321
+ "model.layers.34.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
322
+ "model.layers.34.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
323
+ "model.layers.34.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
324
+ "model.layers.34.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
325
+ "model.layers.34.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
326
+ "model.layers.34.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
327
+ "model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors",
328
+ "model.layers.35.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
329
+ "model.layers.35.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
330
+ "model.layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
331
+ "model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
332
+ "model.layers.35.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
333
+ "model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
334
+ "model.layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
335
+ "model.layers.35.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
336
+ "model.layers.35.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
337
+ "model.layers.35.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
338
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
339
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
340
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
341
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
342
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
343
+ "model.layers.4.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
344
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
345
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
346
+ "model.layers.4.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
347
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
348
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
349
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
350
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
351
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
352
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
353
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
354
+ "model.layers.5.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
355
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
356
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
357
+ "model.layers.5.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
358
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
359
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
360
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
361
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
362
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
363
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
364
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
365
+ "model.layers.6.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
366
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
367
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
368
+ "model.layers.6.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
369
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
370
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
371
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
372
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
373
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
374
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
375
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
376
+ "model.layers.7.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
377
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
378
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
379
+ "model.layers.7.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
380
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
381
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
382
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
383
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
384
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
385
+ "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
386
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
387
+ "model.layers.8.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
388
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
389
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
390
+ "model.layers.8.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
391
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
392
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
393
+ "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
394
+ "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
395
+ "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
396
+ "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
397
+ "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
398
+ "model.layers.9.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
399
+ "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
400
+ "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
401
+ "model.layers.9.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
402
+ "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
403
+ "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
404
+ "model.norm.weight": "model-00002-of-00002.safetensors"
405
+ }
406
+ }
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f0d83a883571e5a180b8c25097a91fbe3c4300723dc35cf88f7079a33502edf
3
+ size 16087485865
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:057de73c81fca002606d2b64429b0fc54652b8caaba70f5954a5ef240eb3c599
3
+ size 14709
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:450730aeac39fd0acda254d1958b9783c4d82a1b696c4bf18b5fd3b518f3cdcb
3
+ size 1465
special_tokens_map.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": {
18
+ "content": "<|im_end|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": {
25
+ "content": "<|endoftext|>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
3
+ size 11422654
tokenizer_config.json ADDED
@@ -0,0 +1,239 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "151665": {
182
+ "content": "<tool_response>",
183
+ "lstrip": false,
184
+ "normalized": false,
185
+ "rstrip": false,
186
+ "single_word": false,
187
+ "special": false
188
+ },
189
+ "151666": {
190
+ "content": "</tool_response>",
191
+ "lstrip": false,
192
+ "normalized": false,
193
+ "rstrip": false,
194
+ "single_word": false,
195
+ "special": false
196
+ },
197
+ "151667": {
198
+ "content": "<think>",
199
+ "lstrip": false,
200
+ "normalized": false,
201
+ "rstrip": false,
202
+ "single_word": false,
203
+ "special": false
204
+ },
205
+ "151668": {
206
+ "content": "</think>",
207
+ "lstrip": false,
208
+ "normalized": false,
209
+ "rstrip": false,
210
+ "single_word": false,
211
+ "special": false
212
+ }
213
+ },
214
+ "additional_special_tokens": [
215
+ "<|im_start|>",
216
+ "<|im_end|>",
217
+ "<|object_ref_start|>",
218
+ "<|object_ref_end|>",
219
+ "<|box_start|>",
220
+ "<|box_end|>",
221
+ "<|quad_start|>",
222
+ "<|quad_end|>",
223
+ "<|vision_start|>",
224
+ "<|vision_end|>",
225
+ "<|vision_pad|>",
226
+ "<|image_pad|>",
227
+ "<|video_pad|>"
228
+ ],
229
+ "bos_token": null,
230
+ "clean_up_tokenization_spaces": false,
231
+ "eos_token": "<|im_end|>",
232
+ "errors": "replace",
233
+ "extra_special_tokens": {},
234
+ "model_max_length": 131072,
235
+ "pad_token": "<|endoftext|>",
236
+ "split_special_tokens": false,
237
+ "tokenizer_class": "Qwen2Tokenizer",
238
+ "unk_token": null
239
+ }
trainer_state.json ADDED
@@ -0,0 +1,2094 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 1200,
3
+ "best_metric": 0.01394818,
4
+ "best_model_checkpoint": "/home/serusr01/new/output/v48-20251225-153152/checkpoint-1200",
5
+ "epoch": 0.5176876617773943,
6
+ "eval_steps": 100,
7
+ "global_step": 1200,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "acc": 0.5208333333333334,
14
+ "epoch": 0.0004314063848144953,
15
+ "grad_norm": 144.0,
16
+ "learning_rate": 5.999997244730563e-06,
17
+ "loss": 1.0161079168319702,
18
+ "step": 1
19
+ },
20
+ {
21
+ "acc": 0.8512820512820513,
22
+ "epoch": 0.0021570319240724763,
23
+ "grad_norm": 12.3125,
24
+ "learning_rate": 5.9999311185171385e-06,
25
+ "loss": 0.40382882952690125,
26
+ "step": 5
27
+ },
28
+ {
29
+ "acc": 0.8622047244094488,
30
+ "epoch": 0.004314063848144953,
31
+ "grad_norm": 18.75,
32
+ "learning_rate": 5.999724477231659e-06,
33
+ "loss": 0.35493576526641846,
34
+ "step": 10
35
+ },
36
+ {
37
+ "acc": 0.8986083499005965,
38
+ "epoch": 0.0064710957722174285,
39
+ "grad_norm": 17.0,
40
+ "learning_rate": 5.9993800856327355e-06,
41
+ "loss": 0.29610111713409426,
42
+ "step": 15
43
+ },
44
+ {
45
+ "acc": 0.8972868217054264,
46
+ "epoch": 0.008628127696289905,
47
+ "grad_norm": 9.125,
48
+ "learning_rate": 5.998897959535169e-06,
49
+ "loss": 0.302515435218811,
50
+ "step": 20
51
+ },
52
+ {
53
+ "acc": 0.876953125,
54
+ "epoch": 0.010785159620362382,
55
+ "grad_norm": 14.9375,
56
+ "learning_rate": 5.998278121078668e-06,
57
+ "loss": 0.3312162160873413,
58
+ "step": 25
59
+ },
60
+ {
61
+ "acc": 0.8975903614457831,
62
+ "epoch": 0.012942191544434857,
63
+ "grad_norm": 13.375,
64
+ "learning_rate": 5.997520598726825e-06,
65
+ "loss": 0.30696473121643064,
66
+ "step": 30
67
+ },
68
+ {
69
+ "acc": 0.8742632612966601,
70
+ "epoch": 0.015099223468507334,
71
+ "grad_norm": 13.25,
72
+ "learning_rate": 5.996625427265816e-06,
73
+ "loss": 0.36511917114257814,
74
+ "step": 35
75
+ },
76
+ {
77
+ "acc": 0.8631790744466801,
78
+ "epoch": 0.01725625539257981,
79
+ "grad_norm": 9.3125,
80
+ "learning_rate": 5.995592647802802e-06,
81
+ "loss": 0.338372015953064,
82
+ "step": 40
83
+ },
84
+ {
85
+ "acc": 0.8964803312629399,
86
+ "epoch": 0.019413287316652286,
87
+ "grad_norm": 6.0,
88
+ "learning_rate": 5.9944223077640325e-06,
89
+ "loss": 0.32863070964813235,
90
+ "step": 45
91
+ },
92
+ {
93
+ "acc": 0.8957915831663327,
94
+ "epoch": 0.021570319240724764,
95
+ "grad_norm": 7.96875,
96
+ "learning_rate": 5.993114460892682e-06,
97
+ "loss": 0.27804901599884035,
98
+ "step": 50
99
+ },
100
+ {
101
+ "acc": 0.8773006134969326,
102
+ "epoch": 0.02372735116479724,
103
+ "grad_norm": 8.9375,
104
+ "learning_rate": 5.9916691672463725e-06,
105
+ "loss": 0.31299686431884766,
106
+ "step": 55
107
+ },
108
+ {
109
+ "acc": 0.9154929577464789,
110
+ "epoch": 0.025884383088869714,
111
+ "grad_norm": 9.1875,
112
+ "learning_rate": 5.990086493194415e-06,
113
+ "loss": 0.2637639045715332,
114
+ "step": 60
115
+ },
116
+ {
117
+ "acc": 0.8927125506072875,
118
+ "epoch": 0.028041415012942193,
119
+ "grad_norm": 9.5,
120
+ "learning_rate": 5.988366511414766e-06,
121
+ "loss": 0.30198609828948975,
122
+ "step": 65
123
+ },
124
+ {
125
+ "acc": 0.9156118143459916,
126
+ "epoch": 0.030198446937014668,
127
+ "grad_norm": 9.0625,
128
+ "learning_rate": 5.986509300890691e-06,
129
+ "loss": 0.24096782207489015,
130
+ "step": 70
131
+ },
132
+ {
133
+ "acc": 0.8798449612403101,
134
+ "epoch": 0.032355478861087146,
135
+ "grad_norm": 7.4375,
136
+ "learning_rate": 5.984514946907133e-06,
137
+ "loss": 0.2953530550003052,
138
+ "step": 75
139
+ },
140
+ {
141
+ "acc": 0.8818737270875764,
142
+ "epoch": 0.03451251078515962,
143
+ "grad_norm": 15.9375,
144
+ "learning_rate": 5.982383541046798e-06,
145
+ "loss": 0.3139867067337036,
146
+ "step": 80
147
+ },
148
+ {
149
+ "acc": 0.9300567107750473,
150
+ "epoch": 0.036669542709232096,
151
+ "grad_norm": 6.5,
152
+ "learning_rate": 5.98011518118595e-06,
153
+ "loss": 0.20404579639434814,
154
+ "step": 85
155
+ },
156
+ {
157
+ "acc": 0.9036885245901639,
158
+ "epoch": 0.03882657463330457,
159
+ "grad_norm": 9.75,
160
+ "learning_rate": 5.977709971489917e-06,
161
+ "loss": 0.2777871131896973,
162
+ "step": 90
163
+ },
164
+ {
165
+ "acc": 0.8767676767676768,
166
+ "epoch": 0.040983606557377046,
167
+ "grad_norm": 12.3125,
168
+ "learning_rate": 5.975168022408304e-06,
169
+ "loss": 0.31117370128631594,
170
+ "step": 95
171
+ },
172
+ {
173
+ "acc": 0.9202334630350194,
174
+ "epoch": 0.04314063848144953,
175
+ "grad_norm": 5.9375,
176
+ "learning_rate": 5.972489450669929e-06,
177
+ "loss": 0.23061840534210204,
178
+ "step": 100
179
+ },
180
+ {
181
+ "epoch": 0.04314063848144953,
182
+ "eval_acc": 0.9116072164099185,
183
+ "eval_loss": 0.031446851789951324,
184
+ "eval_mrr": 0.8872438524590165,
185
+ "eval_ndcg": 0.9145527118078347,
186
+ "eval_runtime": 92.9513,
187
+ "eval_samples_per_second": 21.0,
188
+ "eval_steps_per_second": 10.5,
189
+ "step": 100
190
+ },
191
+ {
192
+ "acc": 0.9188118811881189,
193
+ "epoch": 0.045297670405522,
194
+ "grad_norm": 10.6875,
195
+ "learning_rate": 5.969674379277452e-06,
196
+ "loss": 0.253974175453186,
197
+ "step": 105
198
+ },
199
+ {
200
+ "acc": 0.916030534351145,
201
+ "epoch": 0.04745470232959448,
202
+ "grad_norm": 8.5,
203
+ "learning_rate": 5.9667229375017345e-06,
204
+ "loss": 0.21623244285583496,
205
+ "step": 110
206
+ },
207
+ {
208
+ "acc": 0.9288461538461539,
209
+ "epoch": 0.04961173425366695,
210
+ "grad_norm": 9.4375,
211
+ "learning_rate": 5.9636352608759e-06,
212
+ "loss": 0.2198498487472534,
213
+ "step": 115
214
+ },
215
+ {
216
+ "acc": 0.8913480885311871,
217
+ "epoch": 0.05176876617773943,
218
+ "grad_norm": 10.1875,
219
+ "learning_rate": 5.960411491189113e-06,
220
+ "loss": 0.3081125497817993,
221
+ "step": 120
222
+ },
223
+ {
224
+ "acc": 0.8951612903225806,
225
+ "epoch": 0.05392579810181191,
226
+ "grad_norm": 10.125,
227
+ "learning_rate": 5.957051776480063e-06,
228
+ "loss": 0.2795823335647583,
229
+ "step": 125
230
+ },
231
+ {
232
+ "acc": 0.91,
233
+ "epoch": 0.056082830025884385,
234
+ "grad_norm": 10.375,
235
+ "learning_rate": 5.953556271030172e-06,
236
+ "loss": 0.24584596157073973,
237
+ "step": 130
238
+ },
239
+ {
240
+ "acc": 0.9195402298850575,
241
+ "epoch": 0.05823986194995686,
242
+ "grad_norm": 10.0,
243
+ "learning_rate": 5.949925135356506e-06,
244
+ "loss": 0.20374622344970703,
245
+ "step": 135
246
+ },
247
+ {
248
+ "acc": 0.9190283400809717,
249
+ "epoch": 0.060396893874029335,
250
+ "grad_norm": 13.25,
251
+ "learning_rate": 5.946158536204403e-06,
252
+ "loss": 0.2638064384460449,
253
+ "step": 140
254
+ },
255
+ {
256
+ "acc": 0.9001956947162426,
257
+ "epoch": 0.06255392579810182,
258
+ "grad_norm": 7.21875,
259
+ "learning_rate": 5.942256646539821e-06,
260
+ "loss": 0.2462130069732666,
261
+ "step": 145
262
+ },
263
+ {
264
+ "acc": 0.9201520912547528,
265
+ "epoch": 0.06471095772217429,
266
+ "grad_norm": 7.21875,
267
+ "learning_rate": 5.9382196455413914e-06,
268
+ "loss": 0.25420570373535156,
269
+ "step": 150
270
+ },
271
+ {
272
+ "acc": 0.9288702928870293,
273
+ "epoch": 0.06686798964624677,
274
+ "grad_norm": 10.1875,
275
+ "learning_rate": 5.9340477185921895e-06,
276
+ "loss": 0.2146221160888672,
277
+ "step": 155
278
+ },
279
+ {
280
+ "acc": 0.904397705544933,
281
+ "epoch": 0.06902502157031924,
282
+ "grad_norm": 27.875,
283
+ "learning_rate": 5.9297410572712245e-06,
284
+ "loss": 0.2619572877883911,
285
+ "step": 160
286
+ },
287
+ {
288
+ "acc": 0.903041825095057,
289
+ "epoch": 0.07118205349439172,
290
+ "grad_norm": 8.1875,
291
+ "learning_rate": 5.925299859344643e-06,
292
+ "loss": 0.2647380352020264,
293
+ "step": 165
294
+ },
295
+ {
296
+ "acc": 0.9238095238095239,
297
+ "epoch": 0.07333908541846419,
298
+ "grad_norm": 9.75,
299
+ "learning_rate": 5.9207243287566444e-06,
300
+ "loss": 0.2059628963470459,
301
+ "step": 170
302
+ },
303
+ {
304
+ "acc": 0.9080234833659491,
305
+ "epoch": 0.07549611734253667,
306
+ "grad_norm": 19.0,
307
+ "learning_rate": 5.916014675620117e-06,
308
+ "loss": 0.22357699871063233,
309
+ "step": 175
310
+ },
311
+ {
312
+ "acc": 0.9107883817427386,
313
+ "epoch": 0.07765314926660914,
314
+ "grad_norm": 12.125,
315
+ "learning_rate": 5.911171116206986e-06,
316
+ "loss": 0.23458666801452638,
317
+ "step": 180
318
+ },
319
+ {
320
+ "acc": 0.9092664092664092,
321
+ "epoch": 0.07981018119068162,
322
+ "grad_norm": 10.3125,
323
+ "learning_rate": 5.9061938729382915e-06,
324
+ "loss": 0.2300126552581787,
325
+ "step": 185
326
+ },
327
+ {
328
+ "acc": 0.924901185770751,
329
+ "epoch": 0.08196721311475409,
330
+ "grad_norm": 12.25,
331
+ "learning_rate": 5.901083174373961e-06,
332
+ "loss": 0.21468648910522461,
333
+ "step": 190
334
+ },
335
+ {
336
+ "acc": 0.9180327868852459,
337
+ "epoch": 0.08412424503882658,
338
+ "grad_norm": 9.375,
339
+ "learning_rate": 5.895839255202328e-06,
340
+ "loss": 0.2179854154586792,
341
+ "step": 195
342
+ },
343
+ {
344
+ "acc": 0.935871743486974,
345
+ "epoch": 0.08628127696289906,
346
+ "grad_norm": 11.9375,
347
+ "learning_rate": 5.8904623562293435e-06,
348
+ "loss": 0.22542862892150878,
349
+ "step": 200
350
+ },
351
+ {
352
+ "epoch": 0.08628127696289906,
353
+ "eval_acc": 0.9252821484471538,
354
+ "eval_loss": 0.02712932601571083,
355
+ "eval_mrr": 0.9001439305230289,
356
+ "eval_ndcg": 0.9243608674894062,
357
+ "eval_runtime": 85.9276,
358
+ "eval_samples_per_second": 22.717,
359
+ "eval_steps_per_second": 11.358,
360
+ "step": 200
361
+ },
362
+ {
363
+ "acc": 0.9358178053830227,
364
+ "epoch": 0.08843830888697153,
365
+ "grad_norm": 5.96875,
366
+ "learning_rate": 5.884952724367524e-06,
367
+ "loss": 0.20223827362060548,
368
+ "step": 205
369
+ },
370
+ {
371
+ "acc": 0.9375,
372
+ "epoch": 0.090595340811044,
373
+ "grad_norm": 7.1875,
374
+ "learning_rate": 5.879310612624611e-06,
375
+ "loss": 0.19913212060928345,
376
+ "step": 210
377
+ },
378
+ {
379
+ "acc": 0.9217557251908397,
380
+ "epoch": 0.09275237273511648,
381
+ "grad_norm": 18.5,
382
+ "learning_rate": 5.873536280091955e-06,
383
+ "loss": 0.21275293827056885,
384
+ "step": 215
385
+ },
386
+ {
387
+ "acc": 0.9144050104384134,
388
+ "epoch": 0.09490940465918896,
389
+ "grad_norm": 14.375,
390
+ "learning_rate": 5.867629991932611e-06,
391
+ "loss": 0.23634729385375977,
392
+ "step": 220
393
+ },
394
+ {
395
+ "acc": 0.9239766081871345,
396
+ "epoch": 0.09706643658326143,
397
+ "grad_norm": 13.125,
398
+ "learning_rate": 5.861592019369172e-06,
399
+ "loss": 0.2160120725631714,
400
+ "step": 225
401
+ },
402
+ {
403
+ "acc": 0.8967611336032388,
404
+ "epoch": 0.0992234685073339,
405
+ "grad_norm": 12.0625,
406
+ "learning_rate": 5.855422639671309e-06,
407
+ "loss": 0.25560975074768066,
408
+ "step": 230
409
+ },
410
+ {
411
+ "acc": 0.9405940594059405,
412
+ "epoch": 0.10138050043140638,
413
+ "grad_norm": 11.3125,
414
+ "learning_rate": 5.849122136143034e-06,
415
+ "loss": 0.20292723178863525,
416
+ "step": 235
417
+ },
418
+ {
419
+ "acc": 0.9289827255278311,
420
+ "epoch": 0.10353753235547886,
421
+ "grad_norm": 16.125,
422
+ "learning_rate": 5.842690798109697e-06,
423
+ "loss": 0.19165314435958863,
424
+ "step": 240
425
+ },
426
+ {
427
+ "acc": 0.9137931034482759,
428
+ "epoch": 0.10569456427955133,
429
+ "grad_norm": 14.375,
430
+ "learning_rate": 5.8361289209047004e-06,
431
+ "loss": 0.22526559829711915,
432
+ "step": 245
433
+ },
434
+ {
435
+ "acc": 0.9123505976095617,
436
+ "epoch": 0.10785159620362382,
437
+ "grad_norm": 11.375,
438
+ "learning_rate": 5.829436805855932e-06,
439
+ "loss": 0.1998949646949768,
440
+ "step": 250
441
+ },
442
+ {
443
+ "acc": 0.9298245614035088,
444
+ "epoch": 0.1100086281276963,
445
+ "grad_norm": 9.3125,
446
+ "learning_rate": 5.82261476027193e-06,
447
+ "loss": 0.211327862739563,
448
+ "step": 255
449
+ },
450
+ {
451
+ "acc": 0.9357429718875502,
452
+ "epoch": 0.11216566005176877,
453
+ "grad_norm": 23.375,
454
+ "learning_rate": 5.8156630974277715e-06,
455
+ "loss": 0.21703736782073973,
456
+ "step": 260
457
+ },
458
+ {
459
+ "acc": 0.9092783505154639,
460
+ "epoch": 0.11432269197584125,
461
+ "grad_norm": 17.875,
462
+ "learning_rate": 5.808582136550686e-06,
463
+ "loss": 0.2739748954772949,
464
+ "step": 265
465
+ },
466
+ {
467
+ "acc": 0.9468302658486708,
468
+ "epoch": 0.11647972389991372,
469
+ "grad_norm": 9.9375,
470
+ "learning_rate": 5.8013722028053985e-06,
471
+ "loss": 0.14410748481750488,
472
+ "step": 270
473
+ },
474
+ {
475
+ "acc": 0.9310344827586207,
476
+ "epoch": 0.1186367558239862,
477
+ "grad_norm": 8.5,
478
+ "learning_rate": 5.794033627279193e-06,
479
+ "loss": 0.1934072494506836,
480
+ "step": 275
481
+ },
482
+ {
483
+ "acc": 0.9155470249520153,
484
+ "epoch": 0.12079378774805867,
485
+ "grad_norm": 11.4375,
486
+ "learning_rate": 5.786566746966714e-06,
487
+ "loss": 0.20481424331665038,
488
+ "step": 280
489
+ },
490
+ {
491
+ "acc": 0.9216494845360824,
492
+ "epoch": 0.12295081967213115,
493
+ "grad_norm": 12.5,
494
+ "learning_rate": 5.778971904754485e-06,
495
+ "loss": 0.22041404247283936,
496
+ "step": 285
497
+ },
498
+ {
499
+ "acc": 0.917864476386037,
500
+ "epoch": 0.12510785159620363,
501
+ "grad_norm": 19.375,
502
+ "learning_rate": 5.771249449405169e-06,
503
+ "loss": 0.20896604061126708,
504
+ "step": 290
505
+ },
506
+ {
507
+ "acc": 0.950592885375494,
508
+ "epoch": 0.1272648835202761,
509
+ "grad_norm": 16.875,
510
+ "learning_rate": 5.763399735541551e-06,
511
+ "loss": 0.1629479169845581,
512
+ "step": 295
513
+ },
514
+ {
515
+ "acc": 0.9405737704918032,
516
+ "epoch": 0.12942191544434858,
517
+ "grad_norm": 13.25,
518
+ "learning_rate": 5.755423123630251e-06,
519
+ "loss": 0.19808459281921387,
520
+ "step": 300
521
+ },
522
+ {
523
+ "epoch": 0.12942191544434858,
524
+ "eval_acc": 0.9337671966389324,
525
+ "eval_loss": 0.024512404575943947,
526
+ "eval_mrr": 0.9131787909836067,
527
+ "eval_ndcg": 0.9342680843294187,
528
+ "eval_runtime": 79.6383,
529
+ "eval_samples_per_second": 24.511,
530
+ "eval_steps_per_second": 12.255,
531
+ "step": 300
532
+ },
533
+ {
534
+ "acc": 0.9308943089430894,
535
+ "epoch": 0.13157894736842105,
536
+ "grad_norm": 14.125,
537
+ "learning_rate": 5.747319979965173e-06,
538
+ "loss": 0.20357720851898192,
539
+ "step": 305
540
+ },
541
+ {
542
+ "acc": 0.9433962264150944,
543
+ "epoch": 0.13373597929249353,
544
+ "grad_norm": 14.6875,
545
+ "learning_rate": 5.739090676650683e-06,
546
+ "loss": 0.15039076805114746,
547
+ "step": 310
548
+ },
549
+ {
550
+ "acc": 0.9392712550607287,
551
+ "epoch": 0.135893011216566,
552
+ "grad_norm": 8.625,
553
+ "learning_rate": 5.730735591584529e-06,
554
+ "loss": 0.16305069923400878,
555
+ "step": 315
556
+ },
557
+ {
558
+ "acc": 0.9192307692307692,
559
+ "epoch": 0.13805004314063848,
560
+ "grad_norm": 12.75,
561
+ "learning_rate": 5.722255108440474e-06,
562
+ "loss": 0.2407283067703247,
563
+ "step": 320
564
+ },
565
+ {
566
+ "acc": 0.9298597194388778,
567
+ "epoch": 0.14020707506471095,
568
+ "grad_norm": 12.125,
569
+ "learning_rate": 5.713649616650687e-06,
570
+ "loss": 0.2122425317764282,
571
+ "step": 325
572
+ },
573
+ {
574
+ "acc": 0.9352226720647774,
575
+ "epoch": 0.14236410698878343,
576
+ "grad_norm": 11.125,
577
+ "learning_rate": 5.7049195113878585e-06,
578
+ "loss": 0.19069076776504518,
579
+ "step": 330
580
+ },
581
+ {
582
+ "acc": 0.9189765458422174,
583
+ "epoch": 0.14452113891285592,
584
+ "grad_norm": 17.75,
585
+ "learning_rate": 5.696065193547054e-06,
586
+ "loss": 0.22681286334991455,
587
+ "step": 335
588
+ },
589
+ {
590
+ "acc": 0.943579766536965,
591
+ "epoch": 0.14667817083692838,
592
+ "grad_norm": 14.8125,
593
+ "learning_rate": 5.6870870697273e-06,
594
+ "loss": 0.1799636721611023,
595
+ "step": 340
596
+ },
597
+ {
598
+ "acc": 0.9392712550607287,
599
+ "epoch": 0.14883520276100087,
600
+ "grad_norm": 8.0625,
601
+ "learning_rate": 5.677985552212919e-06,
602
+ "loss": 0.21220760345458983,
603
+ "step": 345
604
+ },
605
+ {
606
+ "acc": 0.9386138613861386,
607
+ "epoch": 0.15099223468507333,
608
+ "grad_norm": 15.0625,
609
+ "learning_rate": 5.668761058954594e-06,
610
+ "loss": 0.19215874671936034,
611
+ "step": 350
612
+ },
613
+ {
614
+ "acc": 0.9487704918032787,
615
+ "epoch": 0.15314926660914582,
616
+ "grad_norm": 9.75,
617
+ "learning_rate": 5.659414013550172e-06,
618
+ "loss": 0.17874677181243898,
619
+ "step": 355
620
+ },
621
+ {
622
+ "acc": 0.9449901768172888,
623
+ "epoch": 0.15530629853321828,
624
+ "grad_norm": 15.1875,
625
+ "learning_rate": 5.649944845225219e-06,
626
+ "loss": 0.17652757167816163,
627
+ "step": 360
628
+ },
629
+ {
630
+ "acc": 0.9281314168377823,
631
+ "epoch": 0.15746333045729077,
632
+ "grad_norm": 28.25,
633
+ "learning_rate": 5.6403539888133056e-06,
634
+ "loss": 0.2142080545425415,
635
+ "step": 365
636
+ },
637
+ {
638
+ "acc": 0.950920245398773,
639
+ "epoch": 0.15962036238136323,
640
+ "grad_norm": 12.0625,
641
+ "learning_rate": 5.63064188473604e-06,
642
+ "loss": 0.17437468767166137,
643
+ "step": 370
644
+ },
645
+ {
646
+ "acc": 0.9422680412371134,
647
+ "epoch": 0.16177739430543572,
648
+ "grad_norm": 19.75,
649
+ "learning_rate": 5.6208089789828435e-06,
650
+ "loss": 0.18122278451919555,
651
+ "step": 375
652
+ },
653
+ {
654
+ "acc": 0.9439071566731141,
655
+ "epoch": 0.16393442622950818,
656
+ "grad_norm": 13.8125,
657
+ "learning_rate": 5.610855723090466e-06,
658
+ "loss": 0.18091570138931273,
659
+ "step": 380
660
+ },
661
+ {
662
+ "acc": 0.923728813559322,
663
+ "epoch": 0.16609145815358067,
664
+ "grad_norm": 29.875,
665
+ "learning_rate": 5.600782574122259e-06,
666
+ "loss": 0.24442174434661865,
667
+ "step": 385
668
+ },
669
+ {
670
+ "acc": 0.9310344827586207,
671
+ "epoch": 0.16824849007765316,
672
+ "grad_norm": 16.75,
673
+ "learning_rate": 5.590589994647182e-06,
674
+ "loss": 0.20708949565887452,
675
+ "step": 390
676
+ },
677
+ {
678
+ "acc": 0.9395161290322581,
679
+ "epoch": 0.17040552200172562,
680
+ "grad_norm": 8.0625,
681
+ "learning_rate": 5.58027845271856e-06,
682
+ "loss": 0.21145825386047362,
683
+ "step": 395
684
+ },
685
+ {
686
+ "acc": 0.9618473895582329,
687
+ "epoch": 0.1725625539257981,
688
+ "grad_norm": 8.5,
689
+ "learning_rate": 5.569848421852592e-06,
690
+ "loss": 0.12078192234039306,
691
+ "step": 400
692
+ },
693
+ {
694
+ "epoch": 0.1725625539257981,
695
+ "eval_acc": 0.9410989373094983,
696
+ "eval_loss": 0.02222530171275139,
697
+ "eval_mrr": 0.9228056693989071,
698
+ "eval_ndcg": 0.9416691570915218,
699
+ "eval_runtime": 87.651,
700
+ "eval_samples_per_second": 22.27,
701
+ "eval_steps_per_second": 11.135,
702
+ "step": 400
703
+ },
704
+ {
705
+ "acc": 0.951310861423221,
706
+ "epoch": 0.17471958584987057,
707
+ "grad_norm": 9.25,
708
+ "learning_rate": 5.559300381006607e-06,
709
+ "loss": 0.1467392086982727,
710
+ "step": 405
711
+ },
712
+ {
713
+ "acc": 0.9362139917695473,
714
+ "epoch": 0.17687661777394306,
715
+ "grad_norm": 9.5625,
716
+ "learning_rate": 5.548634814557066e-06,
717
+ "loss": 0.16467268466949464,
718
+ "step": 410
719
+ },
720
+ {
721
+ "acc": 0.9474671669793621,
722
+ "epoch": 0.17903364969801552,
723
+ "grad_norm": 21.0,
724
+ "learning_rate": 5.537852212277326e-06,
725
+ "loss": 0.16810253858566285,
726
+ "step": 415
727
+ },
728
+ {
729
+ "acc": 0.9329388560157791,
730
+ "epoch": 0.181190681622088,
731
+ "grad_norm": 21.75,
732
+ "learning_rate": 5.5269530693151425e-06,
733
+ "loss": 0.15131351947784424,
734
+ "step": 420
735
+ },
736
+ {
737
+ "acc": 0.9265536723163842,
738
+ "epoch": 0.18334771354616047,
739
+ "grad_norm": 26.25,
740
+ "learning_rate": 5.5159378861699356e-06,
741
+ "loss": 0.2086423635482788,
742
+ "step": 425
743
+ },
744
+ {
745
+ "acc": 0.9393939393939394,
746
+ "epoch": 0.18550474547023296,
747
+ "grad_norm": 9.875,
748
+ "learning_rate": 5.504807168669804e-06,
749
+ "loss": 0.19425034523010254,
750
+ "step": 430
751
+ },
752
+ {
753
+ "acc": 0.9387351778656127,
754
+ "epoch": 0.18766177739430542,
755
+ "grad_norm": 40.0,
756
+ "learning_rate": 5.4935614279482984e-06,
757
+ "loss": 0.1988288640975952,
758
+ "step": 435
759
+ },
760
+ {
761
+ "acc": 0.9350912778904665,
762
+ "epoch": 0.1898188093183779,
763
+ "grad_norm": 29.125,
764
+ "learning_rate": 5.482201180420952e-06,
765
+ "loss": 0.1814996600151062,
766
+ "step": 440
767
+ },
768
+ {
769
+ "acc": 0.9528688524590164,
770
+ "epoch": 0.1919758412424504,
771
+ "grad_norm": 17.25,
772
+ "learning_rate": 5.4707269477615584e-06,
773
+ "loss": 0.1311618208885193,
774
+ "step": 445
775
+ },
776
+ {
777
+ "acc": 0.9548872180451128,
778
+ "epoch": 0.19413287316652286,
779
+ "grad_norm": 21.375,
780
+ "learning_rate": 5.4591392568782275e-06,
781
+ "loss": 0.15495063066482545,
782
+ "step": 450
783
+ },
784
+ {
785
+ "acc": 0.9633204633204633,
786
+ "epoch": 0.19628990509059535,
787
+ "grad_norm": 14.8125,
788
+ "learning_rate": 5.447438639889178e-06,
789
+ "loss": 0.12518519163131714,
790
+ "step": 455
791
+ },
792
+ {
793
+ "acc": 0.9411764705882353,
794
+ "epoch": 0.1984469370146678,
795
+ "grad_norm": 17.875,
796
+ "learning_rate": 5.435625634098311e-06,
797
+ "loss": 0.17223405838012695,
798
+ "step": 460
799
+ },
800
+ {
801
+ "acc": 0.9486166007905138,
802
+ "epoch": 0.2006039689387403,
803
+ "grad_norm": 19.0,
804
+ "learning_rate": 5.423700781970527e-06,
805
+ "loss": 0.14980016946792601,
806
+ "step": 465
807
+ },
808
+ {
809
+ "acc": 0.9354838709677419,
810
+ "epoch": 0.20276100086281276,
811
+ "grad_norm": 23.0,
812
+ "learning_rate": 5.411664631106827e-06,
813
+ "loss": 0.1699580192565918,
814
+ "step": 470
815
+ },
816
+ {
817
+ "acc": 0.9409368635437881,
818
+ "epoch": 0.20491803278688525,
819
+ "grad_norm": 11.6875,
820
+ "learning_rate": 5.399517734219159e-06,
821
+ "loss": 0.2162698268890381,
822
+ "step": 475
823
+ },
824
+ {
825
+ "acc": 0.9535353535353536,
826
+ "epoch": 0.2070750647109577,
827
+ "grad_norm": 16.625,
828
+ "learning_rate": 5.387260649105032e-06,
829
+ "loss": 0.15655677318572997,
830
+ "step": 480
831
+ },
832
+ {
833
+ "acc": 0.9541984732824428,
834
+ "epoch": 0.2092320966350302,
835
+ "grad_norm": 14.4375,
836
+ "learning_rate": 5.374893938621913e-06,
837
+ "loss": 0.15797934532165528,
838
+ "step": 485
839
+ },
840
+ {
841
+ "acc": 0.9343629343629344,
842
+ "epoch": 0.21138912855910266,
843
+ "grad_norm": 6.59375,
844
+ "learning_rate": 5.362418170661375e-06,
845
+ "loss": 0.2039581060409546,
846
+ "step": 490
847
+ },
848
+ {
849
+ "acc": 0.9559386973180076,
850
+ "epoch": 0.21354616048317515,
851
+ "grad_norm": 16.625,
852
+ "learning_rate": 5.3498339181230125e-06,
853
+ "loss": 0.1275785207748413,
854
+ "step": 495
855
+ },
856
+ {
857
+ "acc": 0.9521988527724665,
858
+ "epoch": 0.21570319240724764,
859
+ "grad_norm": 8.1875,
860
+ "learning_rate": 5.3371417588881456e-06,
861
+ "loss": 0.16547932624816894,
862
+ "step": 500
863
+ },
864
+ {
865
+ "epoch": 0.21570319240724764,
866
+ "eval_acc": 0.9440645852211879,
867
+ "eval_loss": 0.0200980044901371,
868
+ "eval_mrr": 0.9341749609679937,
869
+ "eval_ndcg": 0.9502093836313069,
870
+ "eval_runtime": 89.2845,
871
+ "eval_samples_per_second": 21.863,
872
+ "eval_steps_per_second": 10.931,
873
+ "step": 500
874
+ },
875
+ {
876
+ "acc": 0.9288617886178862,
877
+ "epoch": 0.2178602243313201,
878
+ "grad_norm": 17.0,
879
+ "learning_rate": 5.324342275793272e-06,
880
+ "loss": 0.22141244411468505,
881
+ "step": 505
882
+ },
883
+ {
884
+ "acc": 0.9502982107355865,
885
+ "epoch": 0.2200172562553926,
886
+ "grad_norm": 11.0,
887
+ "learning_rate": 5.3114360566033085e-06,
888
+ "loss": 0.13880524635314942,
889
+ "step": 510
890
+ },
891
+ {
892
+ "acc": 0.9284253578732107,
893
+ "epoch": 0.22217428817946505,
894
+ "grad_norm": 10.125,
895
+ "learning_rate": 5.298423693984598e-06,
896
+ "loss": 0.22597496509552,
897
+ "step": 515
898
+ },
899
+ {
900
+ "acc": 0.9553398058252427,
901
+ "epoch": 0.22433132010353754,
902
+ "grad_norm": 20.75,
903
+ "learning_rate": 5.285305785477699e-06,
904
+ "loss": 0.16823456287384034,
905
+ "step": 520
906
+ },
907
+ {
908
+ "acc": 0.9405940594059405,
909
+ "epoch": 0.22648835202761,
910
+ "grad_norm": 9.875,
911
+ "learning_rate": 5.272082933469936e-06,
912
+ "loss": 0.18091850280761718,
913
+ "step": 525
914
+ },
915
+ {
916
+ "acc": 0.9634888438133874,
917
+ "epoch": 0.2286453839516825,
918
+ "grad_norm": 9.6875,
919
+ "learning_rate": 5.258755745167744e-06,
920
+ "loss": 0.13490262031555175,
921
+ "step": 530
922
+ },
923
+ {
924
+ "acc": 0.9320754716981132,
925
+ "epoch": 0.23080241587575495,
926
+ "grad_norm": 18.625,
927
+ "learning_rate": 5.245324832568787e-06,
928
+ "loss": 0.19664840698242186,
929
+ "step": 535
930
+ },
931
+ {
932
+ "acc": 0.9470588235294117,
933
+ "epoch": 0.23295944779982744,
934
+ "grad_norm": 10.3125,
935
+ "learning_rate": 5.2317908124338475e-06,
936
+ "loss": 0.14916815757751464,
937
+ "step": 540
938
+ },
939
+ {
940
+ "acc": 0.9350912778904665,
941
+ "epoch": 0.2351164797238999,
942
+ "grad_norm": 12.0625,
943
+ "learning_rate": 5.21815430625851e-06,
944
+ "loss": 0.1888782262802124,
945
+ "step": 545
946
+ },
947
+ {
948
+ "acc": 0.9365079365079365,
949
+ "epoch": 0.2372735116479724,
950
+ "grad_norm": 14.6875,
951
+ "learning_rate": 5.204415940244618e-06,
952
+ "loss": 0.18109892606735228,
953
+ "step": 550
954
+ },
955
+ {
956
+ "acc": 0.9479768786127167,
957
+ "epoch": 0.23943054357204488,
958
+ "grad_norm": 35.0,
959
+ "learning_rate": 5.1905763452715215e-06,
960
+ "loss": 0.150074303150177,
961
+ "step": 555
962
+ },
963
+ {
964
+ "acc": 0.9408284023668639,
965
+ "epoch": 0.24158757549611734,
966
+ "grad_norm": 10.0625,
967
+ "learning_rate": 5.176636156867102e-06,
968
+ "loss": 0.13501374721527098,
969
+ "step": 560
970
+ },
971
+ {
972
+ "acc": 0.9490196078431372,
973
+ "epoch": 0.24374460742018983,
974
+ "grad_norm": 11.5625,
975
+ "learning_rate": 5.162596015178593e-06,
976
+ "loss": 0.14429715871810914,
977
+ "step": 565
978
+ },
979
+ {
980
+ "acc": 0.961038961038961,
981
+ "epoch": 0.2459016393442623,
982
+ "grad_norm": 4.53125,
983
+ "learning_rate": 5.14845656494318e-06,
984
+ "loss": 0.10108070373535157,
985
+ "step": 570
986
+ },
987
+ {
988
+ "acc": 0.9427402862985685,
989
+ "epoch": 0.24805867126833478,
990
+ "grad_norm": 13.5,
991
+ "learning_rate": 5.134218455458396e-06,
992
+ "loss": 0.16440529823303224,
993
+ "step": 575
994
+ },
995
+ {
996
+ "acc": 0.9512670565302144,
997
+ "epoch": 0.25021570319240727,
998
+ "grad_norm": 23.0,
999
+ "learning_rate": 5.119882340552303e-06,
1000
+ "loss": 0.15792548656463623,
1001
+ "step": 580
1002
+ },
1003
+ {
1004
+ "acc": 0.9310344827586207,
1005
+ "epoch": 0.25237273511647973,
1006
+ "grad_norm": 20.375,
1007
+ "learning_rate": 5.105448878553472e-06,
1008
+ "loss": 0.17942277193069459,
1009
+ "step": 585
1010
+ },
1011
+ {
1012
+ "acc": 0.9586614173228346,
1013
+ "epoch": 0.2545297670405522,
1014
+ "grad_norm": 6.21875,
1015
+ "learning_rate": 5.0909187322607434e-06,
1016
+ "loss": 0.1267695426940918,
1017
+ "step": 590
1018
+ },
1019
+ {
1020
+ "acc": 0.9421157684630739,
1021
+ "epoch": 0.25668679896462465,
1022
+ "grad_norm": 10.8125,
1023
+ "learning_rate": 5.076292568912801e-06,
1024
+ "loss": 0.17552590370178223,
1025
+ "step": 595
1026
+ },
1027
+ {
1028
+ "acc": 0.9418837675350702,
1029
+ "epoch": 0.25884383088869717,
1030
+ "grad_norm": 15.5625,
1031
+ "learning_rate": 5.061571060157525e-06,
1032
+ "loss": 0.1582822322845459,
1033
+ "step": 600
1034
+ },
1035
+ {
1036
+ "epoch": 0.25884383088869717,
1037
+ "eval_acc": 0.9523848751956504,
1038
+ "eval_loss": 0.01805831491947174,
1039
+ "eval_mrr": 0.9341017759562842,
1040
+ "eval_ndcg": 0.9502097307474537,
1041
+ "eval_runtime": 80.1164,
1042
+ "eval_samples_per_second": 24.365,
1043
+ "eval_steps_per_second": 12.182,
1044
+ "step": 600
1045
+ },
1046
+ {
1047
+ "acc": 0.9516806722689075,
1048
+ "epoch": 0.26100086281276963,
1049
+ "grad_norm": 9.5625,
1050
+ "learning_rate": 5.04675488202115e-06,
1051
+ "loss": 0.1585369348526001,
1052
+ "step": 605
1053
+ },
1054
+ {
1055
+ "acc": 0.967479674796748,
1056
+ "epoch": 0.2631578947368421,
1057
+ "grad_norm": 14.375,
1058
+ "learning_rate": 5.031844714877224e-06,
1059
+ "loss": 0.14685235023498536,
1060
+ "step": 610
1061
+ },
1062
+ {
1063
+ "acc": 0.9669902912621359,
1064
+ "epoch": 0.2653149266609146,
1065
+ "grad_norm": 11.875,
1066
+ "learning_rate": 5.016841243415359e-06,
1067
+ "loss": 0.09848676323890686,
1068
+ "step": 615
1069
+ },
1070
+ {
1071
+ "acc": 0.9692622950819673,
1072
+ "epoch": 0.26747195858498707,
1073
+ "grad_norm": 11.875,
1074
+ "learning_rate": 5.001745156609801e-06,
1075
+ "loss": 0.09488856792449951,
1076
+ "step": 620
1077
+ },
1078
+ {
1079
+ "acc": 0.962,
1080
+ "epoch": 0.26962899050905953,
1081
+ "grad_norm": 8.625,
1082
+ "learning_rate": 4.9865571476877775e-06,
1083
+ "loss": 0.10182394981384277,
1084
+ "step": 625
1085
+ },
1086
+ {
1087
+ "acc": 0.9538152610441767,
1088
+ "epoch": 0.271786022433132,
1089
+ "grad_norm": 13.0,
1090
+ "learning_rate": 4.9712779140976725e-06,
1091
+ "loss": 0.14965349435806274,
1092
+ "step": 630
1093
+ },
1094
+ {
1095
+ "acc": 0.9563567362428842,
1096
+ "epoch": 0.2739430543572045,
1097
+ "grad_norm": 15.5625,
1098
+ "learning_rate": 4.9559081574769965e-06,
1099
+ "loss": 0.14634023904800414,
1100
+ "step": 635
1101
+ },
1102
+ {
1103
+ "acc": 0.9402390438247012,
1104
+ "epoch": 0.27610008628127697,
1105
+ "grad_norm": 19.875,
1106
+ "learning_rate": 4.9404485836201695e-06,
1107
+ "loss": 0.15552909374237062,
1108
+ "step": 640
1109
+ },
1110
+ {
1111
+ "acc": 0.9487666034155597,
1112
+ "epoch": 0.27825711820534943,
1113
+ "grad_norm": 38.25,
1114
+ "learning_rate": 4.924899902446105e-06,
1115
+ "loss": 0.16740797758102416,
1116
+ "step": 645
1117
+ },
1118
+ {
1119
+ "acc": 0.9620253164556962,
1120
+ "epoch": 0.2804141501294219,
1121
+ "grad_norm": 8.9375,
1122
+ "learning_rate": 4.909262827965613e-06,
1123
+ "loss": 0.13096400499343872,
1124
+ "step": 650
1125
+ },
1126
+ {
1127
+ "acc": 0.9373737373737374,
1128
+ "epoch": 0.2825711820534944,
1129
+ "grad_norm": 23.375,
1130
+ "learning_rate": 4.893538078248613e-06,
1131
+ "loss": 0.19330756664276122,
1132
+ "step": 655
1133
+ },
1134
+ {
1135
+ "acc": 0.9327902240325866,
1136
+ "epoch": 0.28472821397756687,
1137
+ "grad_norm": 31.25,
1138
+ "learning_rate": 4.877726375391156e-06,
1139
+ "loss": 0.17176212072372438,
1140
+ "step": 660
1141
+ },
1142
+ {
1143
+ "acc": 0.9481037924151696,
1144
+ "epoch": 0.28688524590163933,
1145
+ "grad_norm": 17.125,
1146
+ "learning_rate": 4.861828445482269e-06,
1147
+ "loss": 0.15666646957397462,
1148
+ "step": 665
1149
+ },
1150
+ {
1151
+ "acc": 0.9557344064386318,
1152
+ "epoch": 0.28904227782571185,
1153
+ "grad_norm": 15.875,
1154
+ "learning_rate": 4.8458450185706095e-06,
1155
+ "loss": 0.12006416320800781,
1156
+ "step": 670
1157
+ },
1158
+ {
1159
+ "acc": 0.9530612244897959,
1160
+ "epoch": 0.2911993097497843,
1161
+ "grad_norm": 13.375,
1162
+ "learning_rate": 4.829776828630942e-06,
1163
+ "loss": 0.12216727733612061,
1164
+ "step": 675
1165
+ },
1166
+ {
1167
+ "acc": 0.9454545454545454,
1168
+ "epoch": 0.29335634167385677,
1169
+ "grad_norm": 12.8125,
1170
+ "learning_rate": 4.813624613530434e-06,
1171
+ "loss": 0.1579872488975525,
1172
+ "step": 680
1173
+ },
1174
+ {
1175
+ "acc": 0.94831013916501,
1176
+ "epoch": 0.29551337359792923,
1177
+ "grad_norm": 10.75,
1178
+ "learning_rate": 4.79738911499477e-06,
1179
+ "loss": 0.14849933385848998,
1180
+ "step": 685
1181
+ },
1182
+ {
1183
+ "acc": 0.958904109589041,
1184
+ "epoch": 0.29767040552200175,
1185
+ "grad_norm": 9.125,
1186
+ "learning_rate": 4.781071078574092e-06,
1187
+ "loss": 0.12549154758453368,
1188
+ "step": 690
1189
+ },
1190
+ {
1191
+ "acc": 0.943359375,
1192
+ "epoch": 0.2998274374460742,
1193
+ "grad_norm": 19.25,
1194
+ "learning_rate": 4.764671253608765e-06,
1195
+ "loss": 0.11965863704681397,
1196
+ "step": 695
1197
+ },
1198
+ {
1199
+ "acc": 0.9474747474747475,
1200
+ "epoch": 0.30198446937014667,
1201
+ "grad_norm": 24.5,
1202
+ "learning_rate": 4.748190393194964e-06,
1203
+ "loss": 0.15644127130508423,
1204
+ "step": 700
1205
+ },
1206
+ {
1207
+ "epoch": 0.30198446937014667,
1208
+ "eval_acc": 0.9549386275640498,
1209
+ "eval_loss": 0.017001556232571602,
1210
+ "eval_mrr": 0.9429937548790007,
1211
+ "eval_ndcg": 0.9569733975457528,
1212
+ "eval_runtime": 87.9286,
1213
+ "eval_samples_per_second": 22.2,
1214
+ "eval_steps_per_second": 11.1,
1215
+ "step": 700
1216
+ },
1217
+ {
1218
+ "acc": 0.9433962264150944,
1219
+ "epoch": 0.30414150129421913,
1220
+ "grad_norm": 14.875,
1221
+ "learning_rate": 4.731629254150091e-06,
1222
+ "loss": 0.1656881332397461,
1223
+ "step": 705
1224
+ },
1225
+ {
1226
+ "acc": 0.9484536082474226,
1227
+ "epoch": 0.30629853321829165,
1228
+ "grad_norm": 16.875,
1229
+ "learning_rate": 4.714988596978023e-06,
1230
+ "loss": 0.16551544666290283,
1231
+ "step": 710
1232
+ },
1233
+ {
1234
+ "acc": 0.9601593625498008,
1235
+ "epoch": 0.3084555651423641,
1236
+ "grad_norm": 13.0625,
1237
+ "learning_rate": 4.698269185834188e-06,
1238
+ "loss": 0.13289109468460084,
1239
+ "step": 715
1240
+ },
1241
+ {
1242
+ "acc": 0.9621928166351607,
1243
+ "epoch": 0.31061259706643657,
1244
+ "grad_norm": 6.625,
1245
+ "learning_rate": 4.681471788490473e-06,
1246
+ "loss": 0.13107165098190307,
1247
+ "step": 720
1248
+ },
1249
+ {
1250
+ "acc": 0.9474708171206225,
1251
+ "epoch": 0.3127696289905091,
1252
+ "grad_norm": 17.125,
1253
+ "learning_rate": 4.664597176299972e-06,
1254
+ "loss": 0.15164241790771485,
1255
+ "step": 725
1256
+ },
1257
+ {
1258
+ "acc": 0.9386138613861386,
1259
+ "epoch": 0.31492666091458155,
1260
+ "grad_norm": 13.25,
1261
+ "learning_rate": 4.647646124161557e-06,
1262
+ "loss": 0.14998191595077515,
1263
+ "step": 730
1264
+ },
1265
+ {
1266
+ "acc": 0.9588014981273408,
1267
+ "epoch": 0.317083692838654,
1268
+ "grad_norm": 17.0,
1269
+ "learning_rate": 4.6306194104843005e-06,
1270
+ "loss": 0.1452179431915283,
1271
+ "step": 735
1272
+ },
1273
+ {
1274
+ "acc": 0.9697542533081286,
1275
+ "epoch": 0.31924072476272647,
1276
+ "grad_norm": 21.75,
1277
+ "learning_rate": 4.613517817151725e-06,
1278
+ "loss": 0.0863348662853241,
1279
+ "step": 740
1280
+ },
1281
+ {
1282
+ "acc": 0.9271653543307087,
1283
+ "epoch": 0.321397756686799,
1284
+ "grad_norm": 22.25,
1285
+ "learning_rate": 4.596342129485904e-06,
1286
+ "loss": 0.2219313383102417,
1287
+ "step": 745
1288
+ },
1289
+ {
1290
+ "acc": 0.948559670781893,
1291
+ "epoch": 0.32355478861087145,
1292
+ "grad_norm": 17.25,
1293
+ "learning_rate": 4.579093136211394e-06,
1294
+ "loss": 0.14628000259399415,
1295
+ "step": 750
1296
+ },
1297
+ {
1298
+ "acc": 0.9550321199143469,
1299
+ "epoch": 0.3257118205349439,
1300
+ "grad_norm": 19.375,
1301
+ "learning_rate": 4.561771629419018e-06,
1302
+ "loss": 0.14832402467727662,
1303
+ "step": 755
1304
+ },
1305
+ {
1306
+ "acc": 0.9540918163672655,
1307
+ "epoch": 0.32786885245901637,
1308
+ "grad_norm": 24.875,
1309
+ "learning_rate": 4.544378404529493e-06,
1310
+ "loss": 0.16552494764328002,
1311
+ "step": 760
1312
+ },
1313
+ {
1314
+ "acc": 0.9468302658486708,
1315
+ "epoch": 0.3300258843830889,
1316
+ "grad_norm": 11.75,
1317
+ "learning_rate": 4.526914260256897e-06,
1318
+ "loss": 0.18186469078063966,
1319
+ "step": 765
1320
+ },
1321
+ {
1322
+ "acc": 0.9342915811088296,
1323
+ "epoch": 0.33218291630716135,
1324
+ "grad_norm": 29.0,
1325
+ "learning_rate": 4.509379998572003e-06,
1326
+ "loss": 0.189409601688385,
1327
+ "step": 770
1328
+ },
1329
+ {
1330
+ "acc": 0.9652509652509652,
1331
+ "epoch": 0.3343399482312338,
1332
+ "grad_norm": 8.125,
1333
+ "learning_rate": 4.491776424665441e-06,
1334
+ "loss": 0.11067872047424317,
1335
+ "step": 775
1336
+ },
1337
+ {
1338
+ "acc": 0.9634408602150538,
1339
+ "epoch": 0.3364969801553063,
1340
+ "grad_norm": 19.125,
1341
+ "learning_rate": 4.474104346910724e-06,
1342
+ "loss": 0.12605880498886107,
1343
+ "step": 780
1344
+ },
1345
+ {
1346
+ "acc": 0.9620493358633776,
1347
+ "epoch": 0.3386540120793788,
1348
+ "grad_norm": 16.625,
1349
+ "learning_rate": 4.4563645768271375e-06,
1350
+ "loss": 0.1279581904411316,
1351
+ "step": 785
1352
+ },
1353
+ {
1354
+ "acc": 0.9608610567514677,
1355
+ "epoch": 0.34081104400345125,
1356
+ "grad_norm": 26.125,
1357
+ "learning_rate": 4.438557929042457e-06,
1358
+ "loss": 0.13559631109237671,
1359
+ "step": 790
1360
+ },
1361
+ {
1362
+ "acc": 0.963265306122449,
1363
+ "epoch": 0.3429680759275237,
1364
+ "grad_norm": 16.75,
1365
+ "learning_rate": 4.4206852212555544e-06,
1366
+ "loss": 0.11860382556915283,
1367
+ "step": 795
1368
+ },
1369
+ {
1370
+ "acc": 0.9424184261036468,
1371
+ "epoch": 0.3451251078515962,
1372
+ "grad_norm": 27.25,
1373
+ "learning_rate": 4.402747274198838e-06,
1374
+ "loss": 0.1454222559928894,
1375
+ "step": 800
1376
+ },
1377
+ {
1378
+ "epoch": 0.3451251078515962,
1379
+ "eval_acc": 0.9581514128017135,
1380
+ "eval_loss": 0.01614278368651867,
1381
+ "eval_mrr": 0.9435499609679938,
1382
+ "eval_ndcg": 0.9573436789903933,
1383
+ "eval_runtime": 106.3602,
1384
+ "eval_samples_per_second": 18.353,
1385
+ "eval_steps_per_second": 9.176,
1386
+ "step": 800
1387
+ },
1388
+ {
1389
+ "acc": 0.9533468559837728,
1390
+ "epoch": 0.3472821397756687,
1391
+ "grad_norm": 23.125,
1392
+ "learning_rate": 4.384744911600571e-06,
1393
+ "loss": 0.15178160667419432,
1394
+ "step": 805
1395
+ },
1396
+ {
1397
+ "acc": 0.9653767820773931,
1398
+ "epoch": 0.34943917169974115,
1399
+ "grad_norm": 16.625,
1400
+ "learning_rate": 4.36667896014704e-06,
1401
+ "loss": 0.12023615837097168,
1402
+ "step": 810
1403
+ },
1404
+ {
1405
+ "acc": 0.9449715370018975,
1406
+ "epoch": 0.3515962036238136,
1407
+ "grad_norm": 15.0625,
1408
+ "learning_rate": 4.3485502494445945e-06,
1409
+ "loss": 0.1382935166358948,
1410
+ "step": 815
1411
+ },
1412
+ {
1413
+ "acc": 0.9700598802395209,
1414
+ "epoch": 0.3537532355478861,
1415
+ "grad_norm": 4.75,
1416
+ "learning_rate": 4.330359611981552e-06,
1417
+ "loss": 0.09947049617767334,
1418
+ "step": 820
1419
+ },
1420
+ {
1421
+ "acc": 0.9504132231404959,
1422
+ "epoch": 0.3559102674719586,
1423
+ "grad_norm": 11.4375,
1424
+ "learning_rate": 4.312107883089969e-06,
1425
+ "loss": 0.15309990644454957,
1426
+ "step": 825
1427
+ },
1428
+ {
1429
+ "acc": 0.9606625258799172,
1430
+ "epoch": 0.35806729939603105,
1431
+ "grad_norm": 13.375,
1432
+ "learning_rate": 4.293795900907278e-06,
1433
+ "loss": 0.1290311336517334,
1434
+ "step": 830
1435
+ },
1436
+ {
1437
+ "acc": 0.9569471624266145,
1438
+ "epoch": 0.36022433132010356,
1439
+ "grad_norm": 13.875,
1440
+ "learning_rate": 4.275424506337804e-06,
1441
+ "loss": 0.1386420726776123,
1442
+ "step": 835
1443
+ },
1444
+ {
1445
+ "acc": 0.9567779960707269,
1446
+ "epoch": 0.362381363244176,
1447
+ "grad_norm": 15.0,
1448
+ "learning_rate": 4.256994543014147e-06,
1449
+ "loss": 0.13683913946151732,
1450
+ "step": 840
1451
+ },
1452
+ {
1453
+ "acc": 0.978515625,
1454
+ "epoch": 0.3645383951682485,
1455
+ "grad_norm": 10.875,
1456
+ "learning_rate": 4.2385068572584416e-06,
1457
+ "loss": 0.07557401657104493,
1458
+ "step": 845
1459
+ },
1460
+ {
1461
+ "acc": 0.9506903353057199,
1462
+ "epoch": 0.36669542709232095,
1463
+ "grad_norm": 21.875,
1464
+ "learning_rate": 4.2199622980434965e-06,
1465
+ "loss": 0.15320024490356446,
1466
+ "step": 850
1467
+ },
1468
+ {
1469
+ "acc": 0.9474708171206225,
1470
+ "epoch": 0.36885245901639346,
1471
+ "grad_norm": 30.875,
1472
+ "learning_rate": 4.2013617169537995e-06,
1473
+ "loss": 0.15146974325180054,
1474
+ "step": 855
1475
+ },
1476
+ {
1477
+ "acc": 0.936127744510978,
1478
+ "epoch": 0.3710094909404659,
1479
+ "grad_norm": 13.9375,
1480
+ "learning_rate": 4.182705968146426e-06,
1481
+ "loss": 0.18005824089050293,
1482
+ "step": 860
1483
+ },
1484
+ {
1485
+ "acc": 0.9661354581673307,
1486
+ "epoch": 0.3731665228645384,
1487
+ "grad_norm": 11.0625,
1488
+ "learning_rate": 4.163995908311802e-06,
1489
+ "loss": 0.10441750288009644,
1490
+ "step": 865
1491
+ },
1492
+ {
1493
+ "acc": 0.9671179883945842,
1494
+ "epoch": 0.37532355478861085,
1495
+ "grad_norm": 11.625,
1496
+ "learning_rate": 4.145232396634372e-06,
1497
+ "loss": 0.11835912466049195,
1498
+ "step": 870
1499
+ },
1500
+ {
1501
+ "acc": 0.9686888454011742,
1502
+ "epoch": 0.37748058671268336,
1503
+ "grad_norm": 8.1875,
1504
+ "learning_rate": 4.126416294753141e-06,
1505
+ "loss": 0.08334695696830749,
1506
+ "step": 875
1507
+ },
1508
+ {
1509
+ "acc": 0.9533898305084746,
1510
+ "epoch": 0.3796376186367558,
1511
+ "grad_norm": 15.0625,
1512
+ "learning_rate": 4.1075484667221095e-06,
1513
+ "loss": 0.1570521354675293,
1514
+ "step": 880
1515
+ },
1516
+ {
1517
+ "acc": 0.9628865979381444,
1518
+ "epoch": 0.3817946505608283,
1519
+ "grad_norm": 11.875,
1520
+ "learning_rate": 4.088629778970591e-06,
1521
+ "loss": 0.10125092267990113,
1522
+ "step": 885
1523
+ },
1524
+ {
1525
+ "acc": 0.9517102615694165,
1526
+ "epoch": 0.3839516824849008,
1527
+ "grad_norm": 10.3125,
1528
+ "learning_rate": 4.06966110026343e-06,
1529
+ "loss": 0.15835769176483155,
1530
+ "step": 890
1531
+ },
1532
+ {
1533
+ "acc": 0.9445506692160612,
1534
+ "epoch": 0.38610871440897326,
1535
+ "grad_norm": 51.0,
1536
+ "learning_rate": 4.050643301661107e-06,
1537
+ "loss": 0.17581632137298583,
1538
+ "step": 895
1539
+ },
1540
+ {
1541
+ "acc": 0.9544554455445544,
1542
+ "epoch": 0.3882657463330457,
1543
+ "grad_norm": 17.75,
1544
+ "learning_rate": 4.0315772564797325e-06,
1545
+ "loss": 0.16853252649307252,
1546
+ "step": 900
1547
+ },
1548
+ {
1549
+ "epoch": 0.3882657463330457,
1550
+ "eval_acc": 0.9614465771480353,
1551
+ "eval_loss": 0.015336191281676292,
1552
+ "eval_mrr": 0.9436902322404371,
1553
+ "eval_ndcg": 0.9575083647474146,
1554
+ "eval_runtime": 79.2201,
1555
+ "eval_samples_per_second": 24.64,
1556
+ "eval_steps_per_second": 12.32,
1557
+ "step": 900
1558
+ },
1559
+ {
1560
+ "acc": 0.9625984251968503,
1561
+ "epoch": 0.3904227782571182,
1562
+ "grad_norm": 9.5625,
1563
+ "learning_rate": 4.012463840250949e-06,
1564
+ "loss": 0.11725049018859864,
1565
+ "step": 905
1566
+ },
1567
+ {
1568
+ "acc": 0.9578313253012049,
1569
+ "epoch": 0.3925798101811907,
1570
+ "grad_norm": 26.125,
1571
+ "learning_rate": 3.993303930681726e-06,
1572
+ "loss": 0.11894035339355469,
1573
+ "step": 910
1574
+ },
1575
+ {
1576
+ "acc": 0.952,
1577
+ "epoch": 0.39473684210526316,
1578
+ "grad_norm": 26.375,
1579
+ "learning_rate": 3.974098407614051e-06,
1580
+ "loss": 0.14351377487182618,
1581
+ "step": 915
1582
+ },
1583
+ {
1584
+ "acc": 0.9588477366255144,
1585
+ "epoch": 0.3968938740293356,
1586
+ "grad_norm": 33.75,
1587
+ "learning_rate": 3.954848152984529e-06,
1588
+ "loss": 0.12398861646652222,
1589
+ "step": 920
1590
+ },
1591
+ {
1592
+ "acc": 0.9679358717434869,
1593
+ "epoch": 0.3990509059534081,
1594
+ "grad_norm": 10.4375,
1595
+ "learning_rate": 3.935554050783885e-06,
1596
+ "loss": 0.10695126056671142,
1597
+ "step": 925
1598
+ },
1599
+ {
1600
+ "acc": 0.9646365422396856,
1601
+ "epoch": 0.4012079378774806,
1602
+ "grad_norm": 9.5,
1603
+ "learning_rate": 3.916216987016363e-06,
1604
+ "loss": 0.11947808265686036,
1605
+ "step": 930
1606
+ },
1607
+ {
1608
+ "acc": 0.9588235294117647,
1609
+ "epoch": 0.40336496980155306,
1610
+ "grad_norm": 19.375,
1611
+ "learning_rate": 3.8968378496590485e-06,
1612
+ "loss": 0.12318050861358643,
1613
+ "step": 935
1614
+ },
1615
+ {
1616
+ "acc": 0.9699812382739212,
1617
+ "epoch": 0.4055220017256255,
1618
+ "grad_norm": 9.5625,
1619
+ "learning_rate": 3.877417528621087e-06,
1620
+ "loss": 0.08819143176078796,
1621
+ "step": 940
1622
+ },
1623
+ {
1624
+ "acc": 0.9529411764705882,
1625
+ "epoch": 0.40767903364969804,
1626
+ "grad_norm": 25.0,
1627
+ "learning_rate": 3.8579569157028195e-06,
1628
+ "loss": 0.1318346619606018,
1629
+ "step": 945
1630
+ },
1631
+ {
1632
+ "acc": 0.9395085066162571,
1633
+ "epoch": 0.4098360655737705,
1634
+ "grad_norm": 14.875,
1635
+ "learning_rate": 3.838456904554829e-06,
1636
+ "loss": 0.14923615455627443,
1637
+ "step": 950
1638
+ },
1639
+ {
1640
+ "acc": 0.9635974304068522,
1641
+ "epoch": 0.41199309749784296,
1642
+ "grad_norm": 11.25,
1643
+ "learning_rate": 3.8189183906369035e-06,
1644
+ "loss": 0.10555909872055054,
1645
+ "step": 955
1646
+ },
1647
+ {
1648
+ "acc": 0.9612244897959183,
1649
+ "epoch": 0.4141501294219154,
1650
+ "grad_norm": 27.0,
1651
+ "learning_rate": 3.799342271176918e-06,
1652
+ "loss": 0.11741663217544555,
1653
+ "step": 960
1654
+ },
1655
+ {
1656
+ "acc": 0.9591397849462365,
1657
+ "epoch": 0.41630716134598794,
1658
+ "grad_norm": 11.875,
1659
+ "learning_rate": 3.7797294451296307e-06,
1660
+ "loss": 0.1104978084564209,
1661
+ "step": 965
1662
+ },
1663
+ {
1664
+ "acc": 0.9538461538461539,
1665
+ "epoch": 0.4184641932700604,
1666
+ "grad_norm": 32.0,
1667
+ "learning_rate": 3.7600808131354033e-06,
1668
+ "loss": 0.12546448707580565,
1669
+ "step": 970
1670
+ },
1671
+ {
1672
+ "acc": 0.9642147117296223,
1673
+ "epoch": 0.42062122519413286,
1674
+ "grad_norm": 17.375,
1675
+ "learning_rate": 3.740397277478841e-06,
1676
+ "loss": 0.15062413215637208,
1677
+ "step": 975
1678
+ },
1679
+ {
1680
+ "acc": 0.9447731755424064,
1681
+ "epoch": 0.4227782571182053,
1682
+ "grad_norm": 20.25,
1683
+ "learning_rate": 3.720679742047358e-06,
1684
+ "loss": 0.19598883390426636,
1685
+ "step": 980
1686
+ },
1687
+ {
1688
+ "acc": 0.9592668024439919,
1689
+ "epoch": 0.42493528904227784,
1690
+ "grad_norm": 8.4375,
1691
+ "learning_rate": 3.700929112289674e-06,
1692
+ "loss": 0.11623775959014893,
1693
+ "step": 985
1694
+ },
1695
+ {
1696
+ "acc": 0.9693486590038314,
1697
+ "epoch": 0.4270923209663503,
1698
+ "grad_norm": 17.625,
1699
+ "learning_rate": 3.681146295174234e-06,
1700
+ "loss": 0.1038408637046814,
1701
+ "step": 990
1702
+ },
1703
+ {
1704
+ "acc": 0.9513184584178499,
1705
+ "epoch": 0.42924935289042276,
1706
+ "grad_norm": 6.40625,
1707
+ "learning_rate": 3.6613321991475553e-06,
1708
+ "loss": 0.16103934049606322,
1709
+ "step": 995
1710
+ },
1711
+ {
1712
+ "acc": 0.9710982658959537,
1713
+ "epoch": 0.4314063848144953,
1714
+ "grad_norm": 35.5,
1715
+ "learning_rate": 3.6414877340925163e-06,
1716
+ "loss": 0.1310266375541687,
1717
+ "step": 1000
1718
+ },
1719
+ {
1720
+ "epoch": 0.4314063848144953,
1721
+ "eval_acc": 0.9601285114095065,
1722
+ "eval_loss": 0.01538186427205801,
1723
+ "eval_mrr": 0.9503037177985949,
1724
+ "eval_ndcg": 0.9625558802620603,
1725
+ "eval_runtime": 84.007,
1726
+ "eval_samples_per_second": 23.236,
1727
+ "eval_steps_per_second": 11.618,
1728
+ "step": 1000
1729
+ },
1730
+ {
1731
+ "acc": 0.9592668024439919,
1732
+ "epoch": 0.43356341673856774,
1733
+ "grad_norm": 14.5625,
1734
+ "learning_rate": 3.6216138112865695e-06,
1735
+ "loss": 0.11078298091888428,
1736
+ "step": 1005
1737
+ },
1738
+ {
1739
+ "acc": 0.9509433962264151,
1740
+ "epoch": 0.4357204486626402,
1741
+ "grad_norm": 31.75,
1742
+ "learning_rate": 3.601711343359897e-06,
1743
+ "loss": 0.12666620016098024,
1744
+ "step": 1010
1745
+ },
1746
+ {
1747
+ "acc": 0.958984375,
1748
+ "epoch": 0.43787748058671266,
1749
+ "grad_norm": 7.84375,
1750
+ "learning_rate": 3.5817812442535008e-06,
1751
+ "loss": 0.10231037139892578,
1752
+ "step": 1015
1753
+ },
1754
+ {
1755
+ "acc": 0.9519038076152304,
1756
+ "epoch": 0.4400345125107852,
1757
+ "grad_norm": 34.75,
1758
+ "learning_rate": 3.561824429177234e-06,
1759
+ "loss": 0.14617985486984253,
1760
+ "step": 1020
1761
+ },
1762
+ {
1763
+ "acc": 0.9489603024574669,
1764
+ "epoch": 0.44219154443485764,
1765
+ "grad_norm": 24.75,
1766
+ "learning_rate": 3.541841814567774e-06,
1767
+ "loss": 0.15405564308166503,
1768
+ "step": 1025
1769
+ },
1770
+ {
1771
+ "acc": 0.9458413926499033,
1772
+ "epoch": 0.4443485763589301,
1773
+ "grad_norm": 25.875,
1774
+ "learning_rate": 3.521834318046539e-06,
1775
+ "loss": 0.1635340690612793,
1776
+ "step": 1030
1777
+ },
1778
+ {
1779
+ "acc": 0.964509394572025,
1780
+ "epoch": 0.44650560828300256,
1781
+ "grad_norm": 10.9375,
1782
+ "learning_rate": 3.5018028583775472e-06,
1783
+ "loss": 0.10313594341278076,
1784
+ "step": 1035
1785
+ },
1786
+ {
1787
+ "acc": 0.9542857142857143,
1788
+ "epoch": 0.4486626402070751,
1789
+ "grad_norm": 23.375,
1790
+ "learning_rate": 3.481748355425229e-06,
1791
+ "loss": 0.13693466186523437,
1792
+ "step": 1040
1793
+ },
1794
+ {
1795
+ "acc": 0.9563567362428842,
1796
+ "epoch": 0.45081967213114754,
1797
+ "grad_norm": 22.875,
1798
+ "learning_rate": 3.4616717301121857e-06,
1799
+ "loss": 0.123587965965271,
1800
+ "step": 1045
1801
+ },
1802
+ {
1803
+ "acc": 0.9590163934426229,
1804
+ "epoch": 0.45297670405522,
1805
+ "grad_norm": 12.5,
1806
+ "learning_rate": 3.441573904376899e-06,
1807
+ "loss": 0.13192965984344482,
1808
+ "step": 1050
1809
+ },
1810
+ {
1811
+ "acc": 0.9732824427480916,
1812
+ "epoch": 0.4551337359792925,
1813
+ "grad_norm": 20.875,
1814
+ "learning_rate": 3.4214558011313937e-06,
1815
+ "loss": 0.09249483346939087,
1816
+ "step": 1055
1817
+ },
1818
+ {
1819
+ "acc": 0.9580838323353293,
1820
+ "epoch": 0.457290767903365,
1821
+ "grad_norm": 26.75,
1822
+ "learning_rate": 3.4013183442188606e-06,
1823
+ "loss": 0.11342880725860596,
1824
+ "step": 1060
1825
+ },
1826
+ {
1827
+ "acc": 0.9686274509803922,
1828
+ "epoch": 0.45944779982743744,
1829
+ "grad_norm": 22.375,
1830
+ "learning_rate": 3.381162458371229e-06,
1831
+ "loss": 0.08873859643936158,
1832
+ "step": 1065
1833
+ },
1834
+ {
1835
+ "acc": 0.969758064516129,
1836
+ "epoch": 0.4616048317515099,
1837
+ "grad_norm": 39.0,
1838
+ "learning_rate": 3.3609890691667005e-06,
1839
+ "loss": 0.0837608277797699,
1840
+ "step": 1070
1841
+ },
1842
+ {
1843
+ "acc": 0.962671905697446,
1844
+ "epoch": 0.4637618636755824,
1845
+ "grad_norm": 16.375,
1846
+ "learning_rate": 3.340799102987251e-06,
1847
+ "loss": 0.11619801521301269,
1848
+ "step": 1075
1849
+ },
1850
+ {
1851
+ "acc": 0.9606003752345216,
1852
+ "epoch": 0.4659188955996549,
1853
+ "grad_norm": 15.0625,
1854
+ "learning_rate": 3.320593486976088e-06,
1855
+ "loss": 0.10996119976043701,
1856
+ "step": 1080
1857
+ },
1858
+ {
1859
+ "acc": 0.955193482688391,
1860
+ "epoch": 0.46807592752372734,
1861
+ "grad_norm": 24.5,
1862
+ "learning_rate": 3.300373148995072e-06,
1863
+ "loss": 0.12069922685623169,
1864
+ "step": 1085
1865
+ },
1866
+ {
1867
+ "acc": 0.9691991786447639,
1868
+ "epoch": 0.4702329594477998,
1869
+ "grad_norm": 7.90625,
1870
+ "learning_rate": 3.280139017582113e-06,
1871
+ "loss": 0.14299554824829103,
1872
+ "step": 1090
1873
+ },
1874
+ {
1875
+ "acc": 0.9743589743589743,
1876
+ "epoch": 0.4723899913718723,
1877
+ "grad_norm": 10.875,
1878
+ "learning_rate": 3.2598920219085285e-06,
1879
+ "loss": 0.08163526654243469,
1880
+ "step": 1095
1881
+ },
1882
+ {
1883
+ "acc": 0.9682242990654205,
1884
+ "epoch": 0.4745470232959448,
1885
+ "grad_norm": 9.25,
1886
+ "learning_rate": 3.2396330917363754e-06,
1887
+ "loss": 0.108160400390625,
1888
+ "step": 1100
1889
+ },
1890
+ {
1891
+ "epoch": 0.4745470232959448,
1892
+ "eval_acc": 0.964494604168383,
1893
+ "eval_loss": 0.014143780805170536,
1894
+ "eval_mrr": 0.9522601971116316,
1895
+ "eval_ndcg": 0.963948349172127,
1896
+ "eval_runtime": 88.1934,
1897
+ "eval_samples_per_second": 22.133,
1898
+ "eval_steps_per_second": 11.067,
1899
+ "step": 1100
1900
+ },
1901
+ {
1902
+ "acc": 0.9725490196078431,
1903
+ "epoch": 0.47670405522001724,
1904
+ "grad_norm": 11.875,
1905
+ "learning_rate": 3.219363157375755e-06,
1906
+ "loss": 0.08103461265563965,
1907
+ "step": 1105
1908
+ },
1909
+ {
1910
+ "acc": 0.97678916827853,
1911
+ "epoch": 0.47886108714408976,
1912
+ "grad_norm": 26.5,
1913
+ "learning_rate": 3.1990831496420897e-06,
1914
+ "loss": 0.08858168721199036,
1915
+ "step": 1110
1916
+ },
1917
+ {
1918
+ "acc": 0.9602385685884692,
1919
+ "epoch": 0.4810181190681622,
1920
+ "grad_norm": 15.6875,
1921
+ "learning_rate": 3.1787939998133853e-06,
1922
+ "loss": 0.11988803148269653,
1923
+ "step": 1115
1924
+ },
1925
+ {
1926
+ "acc": 0.9718875502008032,
1927
+ "epoch": 0.4831751509922347,
1928
+ "grad_norm": 19.0,
1929
+ "learning_rate": 3.158496639587459e-06,
1930
+ "loss": 0.09709318280220032,
1931
+ "step": 1120
1932
+ },
1933
+ {
1934
+ "acc": 0.948559670781893,
1935
+ "epoch": 0.48533218291630714,
1936
+ "grad_norm": 17.75,
1937
+ "learning_rate": 3.1381920010391566e-06,
1938
+ "loss": 0.1310401439666748,
1939
+ "step": 1125
1940
+ },
1941
+ {
1942
+ "acc": 0.9658444022770398,
1943
+ "epoch": 0.48748921484037966,
1944
+ "grad_norm": 27.875,
1945
+ "learning_rate": 3.1178810165775532e-06,
1946
+ "loss": 0.11905833482742309,
1947
+ "step": 1130
1948
+ },
1949
+ {
1950
+ "acc": 0.967680608365019,
1951
+ "epoch": 0.4896462467644521,
1952
+ "grad_norm": 14.9375,
1953
+ "learning_rate": 3.0975646189031345e-06,
1954
+ "loss": 0.09188791513442993,
1955
+ "step": 1135
1956
+ },
1957
+ {
1958
+ "acc": 0.9701195219123506,
1959
+ "epoch": 0.4918032786885246,
1960
+ "grad_norm": 14.3125,
1961
+ "learning_rate": 3.0772437409649664e-06,
1962
+ "loss": 0.09571850299835205,
1963
+ "step": 1140
1964
+ },
1965
+ {
1966
+ "acc": 0.9606741573033708,
1967
+ "epoch": 0.49396031061259704,
1968
+ "grad_norm": 16.875,
1969
+ "learning_rate": 3.056919315917851e-06,
1970
+ "loss": 0.1439572811126709,
1971
+ "step": 1145
1972
+ },
1973
+ {
1974
+ "acc": 0.9613152804642167,
1975
+ "epoch": 0.49611734253666956,
1976
+ "grad_norm": 23.625,
1977
+ "learning_rate": 3.0365922770794798e-06,
1978
+ "loss": 0.11582168340682983,
1979
+ "step": 1150
1980
+ },
1981
+ {
1982
+ "acc": 0.980276134122288,
1983
+ "epoch": 0.498274374460742,
1984
+ "grad_norm": 18.0,
1985
+ "learning_rate": 3.016263557887571e-06,
1986
+ "loss": 0.0658139169216156,
1987
+ "step": 1155
1988
+ },
1989
+ {
1990
+ "acc": 0.9581673306772909,
1991
+ "epoch": 0.5004314063848145,
1992
+ "grad_norm": 9.1875,
1993
+ "learning_rate": 2.995934091857007e-06,
1994
+ "loss": 0.11524436473846436,
1995
+ "step": 1160
1996
+ },
1997
+ {
1998
+ "acc": 0.9642105263157895,
1999
+ "epoch": 0.502588438308887,
2000
+ "grad_norm": 28.125,
2001
+ "learning_rate": 2.975604812536964e-06,
2002
+ "loss": 0.10523393154144287,
2003
+ "step": 1165
2004
+ },
2005
+ {
2006
+ "acc": 0.9673076923076923,
2007
+ "epoch": 0.5047454702329595,
2008
+ "grad_norm": 14.75,
2009
+ "learning_rate": 2.9552766534680456e-06,
2010
+ "loss": 0.10329176187515259,
2011
+ "step": 1170
2012
+ },
2013
+ {
2014
+ "acc": 0.9471544715447154,
2015
+ "epoch": 0.5069025021570319,
2016
+ "grad_norm": 22.5,
2017
+ "learning_rate": 2.9349505481394128e-06,
2018
+ "loss": 0.15873119831085206,
2019
+ "step": 1175
2020
+ },
2021
+ {
2022
+ "acc": 0.9680638722554891,
2023
+ "epoch": 0.5090595340811044,
2024
+ "grad_norm": 14.25,
2025
+ "learning_rate": 2.914627429945915e-06,
2026
+ "loss": 0.10048485994338989,
2027
+ "step": 1180
2028
+ },
2029
+ {
2030
+ "acc": 0.9631067961165048,
2031
+ "epoch": 0.5112165660051768,
2032
+ "grad_norm": 38.25,
2033
+ "learning_rate": 2.894308232145232e-06,
2034
+ "loss": 0.10857952833175659,
2035
+ "step": 1185
2036
+ },
2037
+ {
2038
+ "acc": 0.9545454545454546,
2039
+ "epoch": 0.5133735979292493,
2040
+ "grad_norm": 23.125,
2041
+ "learning_rate": 2.8739938878150124e-06,
2042
+ "loss": 0.11859817504882812,
2043
+ "step": 1190
2044
+ },
2045
+ {
2046
+ "acc": 0.9759036144578314,
2047
+ "epoch": 0.5155306298533219,
2048
+ "grad_norm": 14.8125,
2049
+ "learning_rate": 2.8536853298100302e-06,
2050
+ "loss": 0.06508604288101197,
2051
+ "step": 1195
2052
+ },
2053
+ {
2054
+ "acc": 0.9620253164556962,
2055
+ "epoch": 0.5176876617773943,
2056
+ "grad_norm": 10.6875,
2057
+ "learning_rate": 2.833383490719347e-06,
2058
+ "loss": 0.13556112051010133,
2059
+ "step": 1200
2060
+ },
2061
+ {
2062
+ "epoch": 0.5176876617773943,
2063
+ "eval_acc": 0.964824120603015,
2064
+ "eval_loss": 0.013948180712759495,
2065
+ "eval_mrr": 0.9515539617486339,
2066
+ "eval_ndcg": 0.9634276661273489,
2067
+ "eval_runtime": 79.2148,
2068
+ "eval_samples_per_second": 24.642,
2069
+ "eval_steps_per_second": 12.321,
2070
+ "step": 1200
2071
+ }
2072
+ ],
2073
+ "logging_steps": 5,
2074
+ "max_steps": 2318,
2075
+ "num_input_tokens_seen": 0,
2076
+ "num_train_epochs": 1,
2077
+ "save_steps": 400,
2078
+ "stateful_callbacks": {
2079
+ "TrainerControl": {
2080
+ "args": {
2081
+ "should_epoch_stop": false,
2082
+ "should_evaluate": false,
2083
+ "should_log": false,
2084
+ "should_save": true,
2085
+ "should_training_stop": false
2086
+ },
2087
+ "attributes": {}
2088
+ }
2089
+ },
2090
+ "total_flos": 3.559934048421806e+17,
2091
+ "train_batch_size": 2,
2092
+ "trial_name": null,
2093
+ "trial_params": null
2094
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2b2e844988a395150af9cfe6f58bdaef23ed0ff7edbf20cf58e92ed20abbf4c
3
+ size 6929
vocab.json ADDED
The diff for this file is too large to render. See raw diff