JacksonBrune commited on
Commit
fc34e18
·
verified ·
1 Parent(s): 58b5a67

Upload folder using huggingface_hub

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,159 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - en
4
+ license: apache-2.0
5
+ tags:
6
+ - finance
7
+ - earnings-call
8
+ - evasion-detection
9
+ - qwen3
10
+ - text-classification
11
+ base_model: Qwen/Qwen3-4B-Instruct-2507
12
+ datasets:
13
+ - earnings-call-qa
14
+ metrics:
15
+ - accuracy
16
+ - f1
17
+ model-index:
18
+ - name: Qwen3-4B-Evasion
19
+ results:
20
+ - task:
21
+ type: text-classification
22
+ name: Evasion Classification
23
+ metrics:
24
+ - type: accuracy
25
+ value: 0.7508
26
+ name: Accuracy
27
+ - type: f1
28
+ value: 0.7475
29
+ name: Weighted F1
30
+ library_name: transformers
31
+ pipeline_tag: text-classification
32
+ ---
33
+
34
+ # Qwen3-4B-Evasion
35
+
36
+ A fine-tuned model for detecting evasion levels in earnings call Q&A responses.
37
+
38
+ ## Model Description
39
+
40
+ **Qwen3-4B-Evasion** is a specialized model fine-tuned from [Qwen/Qwen3-4B-Instruct-2507](https://huggingface.co/Qwen/Qwen3-4B-Instruct-2507) for analyzing executive responses during earnings call Q&A sessions. The model classifies responses into three evasion categories based on the Rasiah taxonomy.
41
+
42
+ ## Intended Use
43
+
44
+ ### Primary Use Case
45
+ - Analyze transparency and directness of executive responses in earnings calls
46
+ - Financial discourse analysis
47
+ - Corporate communication research
48
+
49
+ ### Classification Categories
50
+
51
+ - **direct**: Clear, on-topic resolution to the question
52
+ - **intermediate**: Partially responsive, incomplete, or softened answer
53
+ - **fully_evasive**: Does not provide requested information
54
+
55
+ ## Training Details
56
+
57
+ ### Training Data
58
+ - **Dataset**: 27,097 earnings call Q&A pairs
59
+ - **Source**: Annotated by DeepSeek-V3.2 and Qwen3-Max models
60
+ - **Label Distribution**:
61
+ - intermediate: 45.4%
62
+ - direct: 29.8%
63
+ - fully_evasive: 24.9%
64
+
65
+ ### Training Configuration
66
+ - **Base Model**: Qwen/Qwen3-4B-Instruct-2507
67
+ - **Training Type**: Full parameter fine-tuning
68
+ - **Hardware**: 2x NVIDIA B200 GPUs
69
+ - **Epochs**: 2
70
+ - **Batch Size**: 32 (effective)
71
+ - **Learning Rate**: 2e-5
72
+ - **Framework**: MS-SWIFT
73
+
74
+ ## Performance
75
+
76
+ Evaluated on 297 human-annotated benchmark samples:
77
+
78
+ | Metric | Score |
79
+ |--------|-------|
80
+ | **Overall Accuracy** | 75.08% |
81
+ | **Weighted F1** | 74.75% |
82
+ | **Weighted Precision** | 77.56% |
83
+ | **Weighted Recall** | 75.08% |
84
+
85
+ ### Per-Class Performance
86
+
87
+ | Class | Precision | Recall | F1-Score | Support |
88
+ |-------|-----------|--------|----------|---------|
89
+ | direct | 86.67% | 54.74% | 67.10% | 95 |
90
+ | intermediate | 63.12% | 80.91% | 70.92% | 110 |
91
+ | fully_evasive | 85.42% | 89.13% | 87.23% | 92 |
92
+
93
+ ## Usage
94
+
95
+ ```python
96
+ from transformers import AutoModelForCausalLM, AutoTokenizer
97
+
98
+ model_name = "FutureMa/Qwen3-4B-Evasion"
99
+ model = AutoModelForCausalLM.from_pretrained(model_name, device_map="auto")
100
+ tokenizer = AutoTokenizer.from_pretrained(model_name)
101
+
102
+ # Prepare input
103
+ question = "What are your revenue projections for next quarter?"
104
+ answer = "We don't provide specific guidance on that."
105
+
106
+ prompt = f"""You are a financial discourse analyst. Classify the evasion level of this executive response.
107
+
108
+ Question: {question}
109
+ Answer: {answer}
110
+
111
+ Return JSON: {{"rasiah":"direct|intermediate|fully_evasive","confidence":0.00}}"""
112
+
113
+ messages = [{"role": "user", "content": prompt}]
114
+ text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
115
+ inputs = tokenizer([text], return_tensors="pt").to(model.device)
116
+
117
+ outputs = model.generate(**inputs, max_new_tokens=128, temperature=1)
118
+ response = tokenizer.decode(outputs[0], skip_special_tokens=True)
119
+ print(response)
120
+ ```
121
+
122
+ ## Limitations
123
+
124
+ - **Direct Class Recall**: Lower recall (54.74%) for direct responses - model tends to be conservative
125
+ - **Domain Specific**: Optimized for earnings call context, may not generalize to other domains
126
+ - **English Only**: Trained exclusively on English text
127
+ - **Confidence Calibration**: Model confidence scores may require further calibration
128
+
129
+ ## Bias and Ethical Considerations
130
+
131
+ - Training data derived from corporate earnings calls may reflect existing biases in financial communication
132
+ - Model should not be used as sole determinant for investment decisions
133
+ - Human oversight recommended for critical applications
134
+
135
+ ## Citation
136
+
137
+ ```bibtex
138
+ @misc{qwen3-4b-evasion,
139
+ author = {Shijian Ma},
140
+ title = {Qwen3-4B-Evasion: Earnings Call Evasion Detection Model},
141
+ year = {2025},
142
+ publisher = {HuggingFace},
143
+ howpublished = {\url{https://huggingface.co/FutureMa/Qwen3-4B-Evasion}}
144
+ }
145
+ ```
146
+
147
+ ## License
148
+
149
+ Apache 2.0
150
+
151
+ ## Acknowledgments
152
+
153
+ - Base model: [Qwen Team](https://huggingface.co/Qwen)
154
+ - Training framework: [MS-SWIFT](https://github.com/modelscope/ms-swift)
155
+ - Evasion taxonomy: Rasiah et al.
156
+
157
+ ## Contact
158
+
159
+ For questions or issues, please open an issue on the model repository.
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 +1,353 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "output_dir": "/home/ubuntu/ms-swift/output/qwen3-4b-evasion-full/v1-20251231-073918",
3
+ "overwrite_output_dir": false,
4
+ "do_train": false,
5
+ "do_eval": false,
6
+ "do_predict": false,
7
+ "eval_strategy": "no",
8
+ "prediction_loss_only": false,
9
+ "per_device_train_batch_size": 8,
10
+ "per_device_eval_batch_size": 1,
11
+ "per_gpu_train_batch_size": null,
12
+ "per_gpu_eval_batch_size": null,
13
+ "gradient_accumulation_steps": 2,
14
+ "eval_accumulation_steps": null,
15
+ "eval_delay": 0,
16
+ "torch_empty_cache_steps": null,
17
+ "learning_rate": 2e-05,
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": 2.0,
24
+ "max_steps": -1,
25
+ "lr_scheduler_type": "cosine",
26
+ "lr_scheduler_kwargs": null,
27
+ "warmup_ratio": 0.03,
28
+ "warmup_steps": 0,
29
+ "log_level": "passive",
30
+ "log_level_replica": "warning",
31
+ "log_on_each_node": true,
32
+ "logging_dir": "/home/ubuntu/ms-swift/output/qwen3-4b-evasion-full/v1-20251231-073918/runs",
33
+ "logging_strategy": "steps",
34
+ "logging_first_step": true,
35
+ "logging_steps": 10,
36
+ "logging_nan_inf_filter": true,
37
+ "save_strategy": "steps",
38
+ "save_steps": 500.0,
39
+ "save_total_limit": 3,
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": false,
63
+ "eval_steps": 500.0,
64
+ "dataloader_num_workers": 8,
65
+ "dataloader_prefetch_factor": null,
66
+ "past_index": -1,
67
+ "run_name": "/home/ubuntu/ms-swift/output/qwen3-4b-evasion-full/v1-20251231-073918",
68
+ "disable_tqdm": null,
69
+ "remove_unused_columns": true,
70
+ "label_names": null,
71
+ "load_best_model_at_end": false,
72
+ "metric_for_best_model": "loss",
73
+ "greater_is_better": false,
74
+ "ignore_data_skip": false,
75
+ "fsdp": [],
76
+ "fsdp_min_num_params": 0,
77
+ "fsdp_config": null,
78
+ "fsdp_transformer_layer_cls_to_wrap": null,
79
+ "accelerator_config": {
80
+ "dispatch_batches": false
81
+ },
82
+ "parallelism_config": null,
83
+ "deepspeed": null,
84
+ "label_smoothing_factor": 0.0,
85
+ "optim": "adamw_torch_fused",
86
+ "optim_args": null,
87
+ "adafactor": false,
88
+ "group_by_length": false,
89
+ "length_column_name": "length",
90
+ "report_to": [
91
+ "tensorboard"
92
+ ],
93
+ "project": "huggingface",
94
+ "trackio_space_id": "trackio",
95
+ "ddp_find_unused_parameters": null,
96
+ "ddp_bucket_cap_mb": null,
97
+ "ddp_broadcast_buffers": null,
98
+ "dataloader_pin_memory": true,
99
+ "dataloader_persistent_workers": false,
100
+ "skip_memory_metrics": true,
101
+ "use_legacy_prediction_loop": false,
102
+ "push_to_hub": false,
103
+ "resume_from_checkpoint": null,
104
+ "hub_model_id": null,
105
+ "hub_strategy": "every_save",
106
+ "hub_token": null,
107
+ "hub_private_repo": null,
108
+ "hub_always_push": false,
109
+ "hub_revision": null,
110
+ "gradient_checkpointing": true,
111
+ "gradient_checkpointing_kwargs": "{\"use_reentrant\": false}",
112
+ "include_inputs_for_metrics": false,
113
+ "include_for_metrics": [],
114
+ "eval_do_concat_batches": true,
115
+ "fp16_backend": "auto",
116
+ "push_to_hub_model_id": null,
117
+ "push_to_hub_organization": null,
118
+ "push_to_hub_token": null,
119
+ "mp_parameters": "",
120
+ "auto_find_batch_size": false,
121
+ "full_determinism": false,
122
+ "torchdynamo": null,
123
+ "ray_scope": "last",
124
+ "ddp_timeout": 18000000,
125
+ "torch_compile": false,
126
+ "torch_compile_backend": null,
127
+ "torch_compile_mode": null,
128
+ "include_tokens_per_second": false,
129
+ "include_num_input_tokens_seen": false,
130
+ "neftune_noise_alpha": null,
131
+ "optim_target_modules": null,
132
+ "batch_eval_metrics": false,
133
+ "eval_on_start": false,
134
+ "use_liger_kernel": false,
135
+ "liger_kernel_config": null,
136
+ "eval_use_gather_object": false,
137
+ "average_tokens_across_devices": true,
138
+ "sortish_sampler": false,
139
+ "predict_with_generate": false,
140
+ "generation_max_length": null,
141
+ "generation_num_beams": null,
142
+ "generation_config": null,
143
+ "tuner_backend": "peft",
144
+ "vit_gradient_checkpointing": null,
145
+ "router_aux_loss_coef": 0.0,
146
+ "enable_dft_loss": false,
147
+ "enable_channel_loss": false,
148
+ "check_model": true,
149
+ "acc_strategy": "token",
150
+ "train_dataloader_shuffle": true,
151
+ "max_epochs": null,
152
+ "aligner_lr": null,
153
+ "vit_lr": null,
154
+ "use_logits_to_keep": null,
155
+ "ds3_gather_for_generation": true,
156
+ "resume_only_model": false,
157
+ "optimizer": null,
158
+ "loss_type": null,
159
+ "metric": null,
160
+ "eval_use_evalscope": false,
161
+ "eval_dataset": [],
162
+ "eval_dataset_args": null,
163
+ "eval_limit": null,
164
+ "eval_generation_config": null,
165
+ "extra_eval_args": null,
166
+ "use_flash_ckpt": false,
167
+ "use_ray": false,
168
+ "ray_exp_name": null,
169
+ "device_groups": null,
170
+ "model": "Qwen/Qwen3-4B-Instruct-2507",
171
+ "model_type": "qwen3_nothinking",
172
+ "model_revision": null,
173
+ "task_type": "causal_lm",
174
+ "torch_dtype": "bfloat16",
175
+ "attn_impl": null,
176
+ "new_special_tokens": [],
177
+ "num_labels": null,
178
+ "problem_type": null,
179
+ "rope_scaling": null,
180
+ "device_map": null,
181
+ "max_memory": {},
182
+ "max_model_len": null,
183
+ "local_repo_path": null,
184
+ "init_strategy": null,
185
+ "template": "qwen3_nothinking",
186
+ "system": null,
187
+ "max_length": 2048,
188
+ "truncation_strategy": "delete",
189
+ "max_pixels": null,
190
+ "agent_template": null,
191
+ "norm_bbox": null,
192
+ "use_chat_template": true,
193
+ "padding_side": "right",
194
+ "padding_free": false,
195
+ "loss_scale": "default",
196
+ "sequence_parallel_size": 1,
197
+ "template_backend": "swift",
198
+ "response_prefix": null,
199
+ "enable_thinking": null,
200
+ "add_non_thinking_prefix": true,
201
+ "dataset": [
202
+ "/home/ubuntu/ms-swift/data/evasion_qa27k_msswift.jsonl"
203
+ ],
204
+ "val_dataset": [],
205
+ "cached_dataset": [],
206
+ "cached_val_dataset": [],
207
+ "split_dataset_ratio": 0.0,
208
+ "dataset_num_proc": 1,
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
+ "strict": false,
219
+ "model_name": null,
220
+ "model_author": null,
221
+ "custom_dataset_info": [],
222
+ "quant_method": null,
223
+ "quant_bits": null,
224
+ "hqq_axis": null,
225
+ "bnb_4bit_compute_dtype": "bfloat16",
226
+ "bnb_4bit_quant_type": "nf4",
227
+ "bnb_4bit_use_double_quant": true,
228
+ "bnb_4bit_quant_storage": null,
229
+ "max_new_tokens": 64,
230
+ "temperature": 0.0,
231
+ "top_k": null,
232
+ "top_p": null,
233
+ "repetition_penalty": null,
234
+ "num_beams": 1,
235
+ "stream": false,
236
+ "stop_words": [],
237
+ "logprobs": false,
238
+ "top_logprobs": null,
239
+ "structured_outputs_regex": null,
240
+ "ckpt_dir": null,
241
+ "lora_modules": [],
242
+ "train_type": "full",
243
+ "adapters": [],
244
+ "external_plugins": [],
245
+ "model_kwargs": {},
246
+ "load_args": false,
247
+ "load_data_args": false,
248
+ "packing": false,
249
+ "packing_length": null,
250
+ "packing_num_proc": 1,
251
+ "lazy_tokenize": false,
252
+ "custom_register_path": [],
253
+ "use_hf": false,
254
+ "ignore_args_error": false,
255
+ "use_swift_lora": false,
256
+ "freeze_parameters": [],
257
+ "freeze_parameters_regex": null,
258
+ "freeze_parameters_ratio": 0.0,
259
+ "trainable_parameters": [],
260
+ "trainable_parameters_regex": null,
261
+ "freeze_llm": false,
262
+ "freeze_vit": true,
263
+ "freeze_aligner": true,
264
+ "target_modules": [
265
+ "all-linear"
266
+ ],
267
+ "target_regex": null,
268
+ "target_parameters": null,
269
+ "modules_to_save": [],
270
+ "lora_rank": 8,
271
+ "lora_alpha": 32,
272
+ "lora_dropout": 0.05,
273
+ "lora_bias": "none",
274
+ "lora_dtype": null,
275
+ "lorap_lr_ratio": null,
276
+ "use_rslora": false,
277
+ "use_dora": false,
278
+ "lora_ga_batch_size": 2,
279
+ "lora_ga_iters": 2,
280
+ "lora_ga_max_length": 1024,
281
+ "lora_ga_direction": "ArB2r",
282
+ "lora_ga_scale": "stable",
283
+ "lora_ga_stable_gamma": 16,
284
+ "init_weights": true,
285
+ "fourier_n_frequency": 2000,
286
+ "fourier_scaling": 300.0,
287
+ "boft_block_size": 4,
288
+ "boft_block_num": 0,
289
+ "boft_n_butterfly_factor": 1,
290
+ "boft_dropout": 0.0,
291
+ "vera_rank": 256,
292
+ "vera_projection_prng_key": 0,
293
+ "vera_dropout": 0.0,
294
+ "vera_d_initial": 0.1,
295
+ "adapter_act": "gelu",
296
+ "adapter_length": 128,
297
+ "use_galore": false,
298
+ "galore_target_modules": null,
299
+ "galore_rank": 128,
300
+ "galore_update_proj_gap": 50,
301
+ "galore_scale": 1.0,
302
+ "galore_proj_type": "std",
303
+ "galore_optim_per_parameter": false,
304
+ "galore_with_embedding": false,
305
+ "galore_quantization": false,
306
+ "galore_proj_quant": false,
307
+ "galore_proj_bits": 4,
308
+ "galore_proj_group_size": 256,
309
+ "galore_cos_threshold": 0.4,
310
+ "galore_gamma_proj": 2,
311
+ "galore_queue_size": 5,
312
+ "adalora_target_r": 8,
313
+ "adalora_init_r": 12,
314
+ "adalora_tinit": 0,
315
+ "adalora_tfinal": 0,
316
+ "adalora_deltaT": 1,
317
+ "adalora_beta1": 0.85,
318
+ "adalora_beta2": 0.85,
319
+ "adalora_orth_reg_weight": 0.5,
320
+ "llamapro_num_new_blocks": 4,
321
+ "llamapro_num_groups": null,
322
+ "lisa_activated_layers": 0,
323
+ "lisa_step_interval": 20,
324
+ "reft_layer_key": null,
325
+ "reft_layers": null,
326
+ "reft_rank": 4,
327
+ "reft_intervention_type": "LoreftIntervention",
328
+ "reft_args": null,
329
+ "swanlab_token": null,
330
+ "swanlab_project": "ms-swift",
331
+ "swanlab_workspace": null,
332
+ "swanlab_exp_name": null,
333
+ "swanlab_notification_method": null,
334
+ "swanlab_webhook_url": null,
335
+ "swanlab_secret": null,
336
+ "swanlab_mode": "cloud",
337
+ "add_version": true,
338
+ "create_checkpoint_symlink": false,
339
+ "zero_hpz_partition_size": null,
340
+ "deepspeed_autotp_size": null,
341
+ "early_stop_interval": null,
342
+ "rank": 0,
343
+ "global_world_size": 2,
344
+ "local_world_size": 2,
345
+ "model_suffix": "Qwen3-4B-Instruct-2507",
346
+ "model_info": "ModelInfo(model_type='qwen3_nothinking', model_dir='/home/ubuntu/.cache/modelscope/hub/models/Qwen/Qwen3-4B-Instruct-2507', torch_dtype=torch.bfloat16, max_model_len=262144, quant_method=None, quant_bits=None, rope_scaling=None, is_moe_model=False, is_multimodal=False, config=None, task_type='causal_lm', num_labels=None)",
347
+ "model_meta": "ModelMeta(model_type='qwen3_nothinking', model_groups=[ModelGroup(models=[Model(ms_model_id='Qwen/Qwen3-30B-A3B-Instruct-2507', hf_model_id='Qwen/Qwen3-30B-A3B-Instruct-2507', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-30B-A3B-Instruct-2507-FP8', hf_model_id='Qwen/Qwen3-30B-A3B-Instruct-2507-FP8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-235B-A22B-Instruct-2507', hf_model_id='Qwen/Qwen3-235B-A22B-Instruct-2507', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-235B-A22B-Instruct-2507-FP8', hf_model_id='Qwen/Qwen3-235B-A22B-Instruct-2507-FP8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='swift/Qwen3-235B-A22B-Instruct-2507-AWQ', hf_model_id=None, model_path=None, ms_revision=None, hf_revision=None)], ignore_patterns=None, requires=None, tags=[]), ModelGroup(models=[Model(ms_model_id='Qwen/Qwen3-4B-Instruct-2507', hf_model_id='Qwen/Qwen3-4B-Instruct-2507', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-4B-Instruct-2507-FP8', hf_model_id='Qwen/Qwen3-4B-Instruct-2507-FP8', model_path=None, ms_revision=None, hf_revision=None)], ignore_patterns=None, requires=None, tags=[])], template='qwen3_nothinking', get_function=<function get_model_tokenizer_with_flash_attn at 0x70c718bef490>, model_arch=None, architectures=['Qwen3MoeForCausalLM', 'Qwen3ForCausalLM'], additional_saved_files=[], torch_dtype=None, is_multimodal=False, is_reward=False, is_reranker=False, task_type=None, ignore_patterns=None, requires=['transformers>=4.51'], tags=[])",
348
+ "model_dir": "/home/ubuntu/.cache/modelscope/hub/models/Qwen/Qwen3-4B-Instruct-2507",
349
+ "_val_dataset_exists": [],
350
+ "hub": "<class 'swift.hub.hub.MSHub'>",
351
+ "evaluation_strategy": "steps",
352
+ "training_args": "Seq2SeqTrainingArguments(output_dir='/home/ubuntu/ms-swift/output/qwen3-4b-evasion-full/v1-20251231-073918', overwrite_output_dir=False, do_train=False, do_eval=False, do_predict=False, eval_strategy=<IntervalStrategy.NO: 'no'>, prediction_loss_only=False, per_device_train_batch_size=8, per_device_eval_batch_size=1, per_gpu_train_batch_size=None, per_gpu_eval_batch_size=None, gradient_accumulation_steps=2, eval_accumulation_steps=None, eval_delay=0, torch_empty_cache_steps=None, learning_rate=2e-05, weight_decay=0.1, adam_beta1=0.9, adam_beta2=0.95, adam_epsilon=1e-08, max_grad_norm=1.0, num_train_epochs=2.0, max_steps=-1, lr_scheduler_type=<SchedulerType.COSINE: 'cosine'>, lr_scheduler_kwargs=None, warmup_ratio=0.03, warmup_steps=0, log_level='passive', log_level_replica='warning', log_on_each_node=True, logging_dir='/home/ubuntu/ms-swift/output/qwen3-4b-evasion-full/v1-20251231-073918/runs', logging_strategy=<IntervalStrategy.STEPS: 'steps'>, logging_first_step=True, logging_steps=10, logging_nan_inf_filter=True, save_strategy=<SaveStrategy.STEPS: 'steps'>, save_steps=500, save_total_limit=3, 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=False, eval_steps=500.0, dataloader_num_workers=8, dataloader_prefetch_factor=2, past_index=-1, run_name='/home/ubuntu/ms-swift/output/qwen3-4b-evasion-full/v1-20251231-073918', disable_tqdm=False, remove_unused_columns=False, label_names=None, 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_FUSED: 'adamw_torch_fused'>, 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={'use_reentrant': False}, 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, sortish_sampler=False, predict_with_generate=False, generation_max_length=None, generation_num_beams=None, generation_config=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=None, 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, task_type='causal_lm', problem_type=None)"
353
+ }
chat_template.jinja ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ {%- for message in messages %}
18
+ {%- if message.content is string %}
19
+ {%- set content = message.content %}
20
+ {%- else %}
21
+ {%- set content = '' %}
22
+ {%- endif %}
23
+ {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
24
+ {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
25
+ {%- elif message.role == "assistant" %}
26
+ {{- '<|im_start|>' + message.role + '\n' + content }}
27
+ {%- if message.tool_calls %}
28
+ {%- for tool_call in message.tool_calls %}
29
+ {%- if (loop.first and content) or (not loop.first) %}
30
+ {{- '\n' }}
31
+ {%- endif %}
32
+ {%- if tool_call.function %}
33
+ {%- set tool_call = tool_call.function %}
34
+ {%- endif %}
35
+ {{- '<tool_call>\n{"name": "' }}
36
+ {{- tool_call.name }}
37
+ {{- '", "arguments": ' }}
38
+ {%- if tool_call.arguments is string %}
39
+ {{- tool_call.arguments }}
40
+ {%- else %}
41
+ {{- tool_call.arguments | tojson }}
42
+ {%- endif %}
43
+ {{- '}\n</tool_call>' }}
44
+ {%- endfor %}
45
+ {%- endif %}
46
+ {{- '<|im_end|>\n' }}
47
+ {%- elif message.role == "tool" %}
48
+ {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
49
+ {{- '<|im_start|>user' }}
50
+ {%- endif %}
51
+ {{- '\n<tool_response>\n' }}
52
+ {{- content }}
53
+ {{- '\n</tool_response>' }}
54
+ {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
55
+ {{- '<|im_end|>\n' }}
56
+ {%- endif %}
57
+ {%- endif %}
58
+ {%- endfor %}
59
+ {%- if add_generation_prompt %}
60
+ {{- '<|im_start|>assistant\n' }}
61
+ {%- 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": 262144,
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": 5000000,
62
+ "sliding_window": null,
63
+ "tie_word_embeddings": true,
64
+ "transformers_version": "4.57.3",
65
+ "use_cache": false,
66
+ "use_sliding_window": false,
67
+ "vocab_size": 151936
68
+ }
generation_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 151645,
6
+ 151643
7
+ ],
8
+ "pad_token_id": 151643,
9
+ "temperature": 0.7,
10
+ "top_k": 20,
11
+ "top_p": 0.8,
12
+ "transformers_version": "4.57.3"
13
+ }
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 sha256:85c6ac7361f9fa1628b95f7a5462511d9a711d38adef3ab0bfc5de92ad4d0c27
3
+ size 4967215360
model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e552b551f490e5c0fd54c7d0ef914e512c79e7e30481370c948678352673b03c
3
+ size 3077766632
model.safetensors.index.json ADDED
@@ -0,0 +1,406 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_parameters": 4022468096,
4
+ "total_size": 8044936192
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 sha256:39ac89e56fec4dacd012d8108324c37dc5238afe141f68f6c8dea7b7222bbe6e
3
+ size 16090225449
rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95e5fc2074c0df31522a514f862c86cb00d71c946a7f15cc9ec0e53a69fb28a7
3
+ size 14917
rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e7153eae67b6c9232a41bc996a2bf5b83229b8c7230d61911ac0fd40e64154e
3
+ size 14917
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cebc4fd0a8a189aa9b371f3e058580335b13df782675613f6af7a02d0799151b
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": 1010000,
235
+ "pad_token": "<|endoftext|>",
236
+ "split_special_tokens": false,
237
+ "tokenizer_class": "Qwen2Tokenizer",
238
+ "unk_token": null
239
+ }
trainer_state.json ADDED
@@ -0,0 +1,1394 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 2.0,
6
+ "eval_steps": 500.0,
7
+ "global_step": 1690,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.0011841326228537595,
14
+ "grad_norm": 219.0,
15
+ "learning_rate": 3.921568627450981e-07,
16
+ "loss": 1.2013294696807861,
17
+ "step": 1,
18
+ "token_acc": 0.8954758190327613
19
+ },
20
+ {
21
+ "epoch": 0.011841326228537596,
22
+ "grad_norm": 50.0,
23
+ "learning_rate": 3.92156862745098e-06,
24
+ "loss": 0.8140333493550619,
25
+ "step": 10,
26
+ "token_acc": 0.9158278375564041
27
+ },
28
+ {
29
+ "epoch": 0.023682652457075192,
30
+ "grad_norm": 15.0625,
31
+ "learning_rate": 7.84313725490196e-06,
32
+ "loss": 0.25884711742401123,
33
+ "step": 20,
34
+ "token_acc": 0.9479379018347185
35
+ },
36
+ {
37
+ "epoch": 0.035523978685612786,
38
+ "grad_norm": 4.78125,
39
+ "learning_rate": 1.1764705882352942e-05,
40
+ "loss": 0.13083882331848146,
41
+ "step": 30,
42
+ "token_acc": 0.9458783043954325
43
+ },
44
+ {
45
+ "epoch": 0.047365304914150384,
46
+ "grad_norm": 4.65625,
47
+ "learning_rate": 1.568627450980392e-05,
48
+ "loss": 0.11950666904449463,
49
+ "step": 40,
50
+ "token_acc": 0.953747256193164
51
+ },
52
+ {
53
+ "epoch": 0.05920663114268798,
54
+ "grad_norm": 3.921875,
55
+ "learning_rate": 1.9607843137254903e-05,
56
+ "loss": 0.10617152452468873,
57
+ "step": 50,
58
+ "token_acc": 0.9590588235294117
59
+ },
60
+ {
61
+ "epoch": 0.07104795737122557,
62
+ "grad_norm": 2.25,
63
+ "learning_rate": 1.9998512057697314e-05,
64
+ "loss": 0.10807085037231445,
65
+ "step": 60,
66
+ "token_acc": 0.9589895524715422
67
+ },
68
+ {
69
+ "epoch": 0.08288928359976318,
70
+ "grad_norm": 2.375,
71
+ "learning_rate": 1.9993369121919753e-05,
72
+ "loss": 0.10784111022949219,
73
+ "step": 70,
74
+ "token_acc": 0.9572008747266479
75
+ },
76
+ {
77
+ "epoch": 0.09473060982830077,
78
+ "grad_norm": 2.9375,
79
+ "learning_rate": 1.998455471202776e-05,
80
+ "loss": 0.10691288709640503,
81
+ "step": 80,
82
+ "token_acc": 0.9570600219401347
83
+ },
84
+ {
85
+ "epoch": 0.10657193605683836,
86
+ "grad_norm": 1.578125,
87
+ "learning_rate": 1.9972072066356417e-05,
88
+ "loss": 0.11526317596435547,
89
+ "step": 90,
90
+ "token_acc": 0.9496324104489285
91
+ },
92
+ {
93
+ "epoch": 0.11841326228537596,
94
+ "grad_norm": 3.09375,
95
+ "learning_rate": 1.995592577091769e-05,
96
+ "loss": 0.10205183029174805,
97
+ "step": 100,
98
+ "token_acc": 0.9572502348888193
99
+ },
100
+ {
101
+ "epoch": 0.13025458851391356,
102
+ "grad_norm": 3.1875,
103
+ "learning_rate": 1.9936121757715598e-05,
104
+ "loss": 0.10735645294189453,
105
+ "step": 110,
106
+ "token_acc": 0.9611528822055138
107
+ },
108
+ {
109
+ "epoch": 0.14209591474245115,
110
+ "grad_norm": 1.796875,
111
+ "learning_rate": 1.991266730256683e-05,
112
+ "loss": 0.10336060523986816,
113
+ "step": 120,
114
+ "token_acc": 0.9576736165543188
115
+ },
116
+ {
117
+ "epoch": 0.15393724097098876,
118
+ "grad_norm": 2.078125,
119
+ "learning_rate": 1.9885571022427676e-05,
120
+ "loss": 0.09967223405838013,
121
+ "step": 130,
122
+ "token_acc": 0.959868317918169
123
+ },
124
+ {
125
+ "epoch": 0.16577856719952636,
126
+ "grad_norm": 1.140625,
127
+ "learning_rate": 1.9854842872228247e-05,
128
+ "loss": 0.09939006567001343,
129
+ "step": 140,
130
+ "token_acc": 0.9603572547790661
131
+ },
132
+ {
133
+ "epoch": 0.17761989342806395,
134
+ "grad_norm": 1.2890625,
135
+ "learning_rate": 1.98204941412151e-05,
136
+ "loss": 0.0902411937713623,
137
+ "step": 150,
138
+ "token_acc": 0.9632122730118973
139
+ },
140
+ {
141
+ "epoch": 0.18946121965660154,
142
+ "grad_norm": 2.984375,
143
+ "learning_rate": 1.9782537448803707e-05,
144
+ "loss": 0.10655044317245484,
145
+ "step": 160,
146
+ "token_acc": 0.9559263340154258
147
+ },
148
+ {
149
+ "epoch": 0.20130254588513913,
150
+ "grad_norm": 2.65625,
151
+ "learning_rate": 1.9740986739942146e-05,
152
+ "loss": 0.10265426635742188,
153
+ "step": 170,
154
+ "token_acc": 0.9573600877880546
155
+ },
156
+ {
157
+ "epoch": 0.21314387211367672,
158
+ "grad_norm": 1.3046875,
159
+ "learning_rate": 1.9695857279987897e-05,
160
+ "loss": 0.09765652418136597,
161
+ "step": 180,
162
+ "token_acc": 0.9597620165962111
163
+ },
164
+ {
165
+ "epoch": 0.22498519834221434,
166
+ "grad_norm": 1.4140625,
167
+ "learning_rate": 1.9647165649099465e-05,
168
+ "loss": 0.09450024366378784,
169
+ "step": 190,
170
+ "token_acc": 0.963653454488485
171
+ },
172
+ {
173
+ "epoch": 0.23682652457075193,
174
+ "grad_norm": 1.3046875,
175
+ "learning_rate": 1.9594929736144978e-05,
176
+ "loss": 0.10988011360168456,
177
+ "step": 200,
178
+ "token_acc": 0.9540840231141652
179
+ },
180
+ {
181
+ "epoch": 0.24866785079928952,
182
+ "grad_norm": 1.828125,
183
+ "learning_rate": 1.9539168732129977e-05,
184
+ "loss": 0.09797856211662292,
185
+ "step": 210,
186
+ "token_acc": 0.9617614793919448
187
+ },
188
+ {
189
+ "epoch": 0.2605091770278271,
190
+ "grad_norm": 4.15625,
191
+ "learning_rate": 1.9479903123146835e-05,
192
+ "loss": 0.09065916538238525,
193
+ "step": 220,
194
+ "token_acc": 0.9650382394256282
195
+ },
196
+ {
197
+ "epoch": 0.27235050325636473,
198
+ "grad_norm": 1.9765625,
199
+ "learning_rate": 1.9417154682848314e-05,
200
+ "loss": 0.10036060810089112,
201
+ "step": 230,
202
+ "token_acc": 0.961611076148521
203
+ },
204
+ {
205
+ "epoch": 0.2841918294849023,
206
+ "grad_norm": 2.234375,
207
+ "learning_rate": 1.935094646444815e-05,
208
+ "loss": 0.09578206539154052,
209
+ "step": 240,
210
+ "token_acc": 0.9624119028974158
211
+ },
212
+ {
213
+ "epoch": 0.2960331557134399,
214
+ "grad_norm": 2.171875,
215
+ "learning_rate": 1.928130279225149e-05,
216
+ "loss": 0.09263083934783936,
217
+ "step": 250,
218
+ "token_acc": 0.963653454488485
219
+ },
220
+ {
221
+ "epoch": 0.30787448194197753,
222
+ "grad_norm": 1.6640625,
223
+ "learning_rate": 1.920824925271838e-05,
224
+ "loss": 0.09710139036178589,
225
+ "step": 260,
226
+ "token_acc": 0.9595754643358826
227
+ },
228
+ {
229
+ "epoch": 0.3197158081705151,
230
+ "grad_norm": 3.40625,
231
+ "learning_rate": 1.9131812685063512e-05,
232
+ "loss": 0.10172030925750733,
233
+ "step": 270,
234
+ "token_acc": 0.957680250783699
235
+ },
236
+ {
237
+ "epoch": 0.3315571343990527,
238
+ "grad_norm": 1.9609375,
239
+ "learning_rate": 1.9052021171395742e-05,
240
+ "loss": 0.10712752342224122,
241
+ "step": 280,
242
+ "token_acc": 0.9577840552416823
243
+ },
244
+ {
245
+ "epoch": 0.3433984606275903,
246
+ "grad_norm": 1.0703125,
247
+ "learning_rate": 1.896890402640098e-05,
248
+ "loss": 0.09744402766227722,
249
+ "step": 290,
250
+ "token_acc": 0.9596054485674025
251
+ },
252
+ {
253
+ "epoch": 0.3552397868561279,
254
+ "grad_norm": 2.359375,
255
+ "learning_rate": 1.8882491786572226e-05,
256
+ "loss": 0.09446089267730713,
257
+ "step": 300,
258
+ "token_acc": 0.9636648394675019
259
+ },
260
+ {
261
+ "epoch": 0.36708111308466546,
262
+ "grad_norm": 1.828125,
263
+ "learning_rate": 1.8792816198990768e-05,
264
+ "loss": 0.09970860481262207,
265
+ "step": 310,
266
+ "token_acc": 0.9583398590446358
267
+ },
268
+ {
269
+ "epoch": 0.3789224393132031,
270
+ "grad_norm": 1.5390625,
271
+ "learning_rate": 1.8699910209662536e-05,
272
+ "loss": 0.09670261144638062,
273
+ "step": 320,
274
+ "token_acc": 0.9606150949317432
275
+ },
276
+ {
277
+ "epoch": 0.3907637655417407,
278
+ "grad_norm": 2.828125,
279
+ "learning_rate": 1.8603807951414093e-05,
280
+ "loss": 0.09714120626449585,
281
+ "step": 330,
282
+ "token_acc": 0.9602938877598874
283
+ },
284
+ {
285
+ "epoch": 0.40260509177027826,
286
+ "grad_norm": 1.890625,
287
+ "learning_rate": 1.850454473135249e-05,
288
+ "loss": 0.09373531341552735,
289
+ "step": 340,
290
+ "token_acc": 0.9619166536600593
291
+ },
292
+ {
293
+ "epoch": 0.4144464179988159,
294
+ "grad_norm": 2.25,
295
+ "learning_rate": 1.8402157017893795e-05,
296
+ "loss": 0.09355499744415283,
297
+ "step": 350,
298
+ "token_acc": 0.9667919799498746
299
+ },
300
+ {
301
+ "epoch": 0.42628774422735344,
302
+ "grad_norm": 0.8828125,
303
+ "learning_rate": 1.829668242736489e-05,
304
+ "loss": 0.08944010734558105,
305
+ "step": 360,
306
+ "token_acc": 0.9638327853452325
307
+ },
308
+ {
309
+ "epoch": 0.43812907045589106,
310
+ "grad_norm": 1.2265625,
311
+ "learning_rate": 1.8188159710183595e-05,
312
+ "loss": 0.09383893013000488,
313
+ "step": 370,
314
+ "token_acc": 0.9663642052565707
315
+ },
316
+ {
317
+ "epoch": 0.4499703966844287,
318
+ "grad_norm": 2.953125,
319
+ "learning_rate": 1.807662873662209e-05,
320
+ "loss": 0.09152829647064209,
321
+ "step": 380,
322
+ "token_acc": 0.9641403069213905
323
+ },
324
+ {
325
+ "epoch": 0.46181172291296624,
326
+ "grad_norm": 1.6953125,
327
+ "learning_rate": 1.796213048215896e-05,
328
+ "loss": 0.10058202743530273,
329
+ "step": 390,
330
+ "token_acc": 0.961363279409455
331
+ },
332
+ {
333
+ "epoch": 0.47365304914150386,
334
+ "grad_norm": 1.7421875,
335
+ "learning_rate": 1.7844707012425155e-05,
336
+ "loss": 0.0878696620464325,
337
+ "step": 400,
338
+ "token_acc": 0.9662956576265872
339
+ },
340
+ {
341
+ "epoch": 0.4854943753700414,
342
+ "grad_norm": 1.3828125,
343
+ "learning_rate": 1.772440146774945e-05,
344
+ "loss": 0.09355847835540772,
345
+ "step": 410,
346
+ "token_acc": 0.9618928627205997
347
+ },
348
+ {
349
+ "epoch": 0.49733570159857904,
350
+ "grad_norm": 1.3828125,
351
+ "learning_rate": 1.7601258047309096e-05,
352
+ "loss": 0.09457954168319702,
353
+ "step": 420,
354
+ "token_acc": 0.9631430363864492
355
+ },
356
+ {
357
+ "epoch": 0.5091770278271166,
358
+ "grad_norm": 1.0234375,
359
+ "learning_rate": 1.7475321992891417e-05,
360
+ "loss": 0.09055821895599366,
361
+ "step": 430,
362
+ "token_acc": 0.9654251139399654
363
+ },
364
+ {
365
+ "epoch": 0.5210183540556542,
366
+ "grad_norm": 1.9921875,
367
+ "learning_rate": 1.73466395722724e-05,
368
+ "loss": 0.09674708843231201,
369
+ "step": 440,
370
+ "token_acc": 0.9611041405269761
371
+ },
372
+ {
373
+ "epoch": 0.5328596802841918,
374
+ "grad_norm": 1.671875,
375
+ "learning_rate": 1.7215258062218323e-05,
376
+ "loss": 0.10127317905426025,
377
+ "step": 450,
378
+ "token_acc": 0.9612791973663584
379
+ },
380
+ {
381
+ "epoch": 0.5447010065127295,
382
+ "grad_norm": 2.28125,
383
+ "learning_rate": 1.708122573111669e-05,
384
+ "loss": 0.08792918920516968,
385
+ "step": 460,
386
+ "token_acc": 0.9650962591954922
387
+ },
388
+ {
389
+ "epoch": 0.5565423327412671,
390
+ "grad_norm": 2.171875,
391
+ "learning_rate": 1.6944591821242867e-05,
392
+ "loss": 0.09947954416275025,
393
+ "step": 470,
394
+ "token_acc": 0.9605057758351545
395
+ },
396
+ {
397
+ "epoch": 0.5683836589698046,
398
+ "grad_norm": 1.46875,
399
+ "learning_rate": 1.680540653066891e-05,
400
+ "loss": 0.0963528037071228,
401
+ "step": 480,
402
+ "token_acc": 0.9614842649131048
403
+ },
404
+ {
405
+ "epoch": 0.5802249851983422,
406
+ "grad_norm": 1.1015625,
407
+ "learning_rate": 1.6663720994821246e-05,
408
+ "loss": 0.0961789608001709,
409
+ "step": 490,
410
+ "token_acc": 0.9619599248591109
411
+ },
412
+ {
413
+ "epoch": 0.5920663114268798,
414
+ "grad_norm": 2.109375,
415
+ "learning_rate": 1.651958726769396e-05,
416
+ "loss": 0.090640389919281,
417
+ "step": 500,
418
+ "token_acc": 0.963166144200627
419
+ },
420
+ {
421
+ "epoch": 0.6039076376554174,
422
+ "grad_norm": 0.9140625,
423
+ "learning_rate": 1.6373058302724655e-05,
424
+ "loss": 0.08862148523330689,
425
+ "step": 510,
426
+ "token_acc": 0.9642521166509878
427
+ },
428
+ {
429
+ "epoch": 0.6157489638839551,
430
+ "grad_norm": 1.7421875,
431
+ "learning_rate": 1.6224187933339808e-05,
432
+ "loss": 0.08748204708099365,
433
+ "step": 520,
434
+ "token_acc": 0.9620749098887321
435
+ },
436
+ {
437
+ "epoch": 0.6275902901124926,
438
+ "grad_norm": 1.5546875,
439
+ "learning_rate": 1.6073030853176862e-05,
440
+ "loss": 0.09252775907516479,
441
+ "step": 530,
442
+ "token_acc": 0.9616528408201597
443
+ },
444
+ {
445
+ "epoch": 0.6394316163410302,
446
+ "grad_norm": 1.296875,
447
+ "learning_rate": 1.5919642595990275e-05,
448
+ "loss": 0.08904544115066529,
449
+ "step": 540,
450
+ "token_acc": 0.9668594653743943
451
+ },
452
+ {
453
+ "epoch": 0.6512729425695678,
454
+ "grad_norm": 1.8203125,
455
+ "learning_rate": 1.5764079515248922e-05,
456
+ "loss": 0.08241082429885864,
457
+ "step": 550,
458
+ "token_acc": 0.9658628249295333
459
+ },
460
+ {
461
+ "epoch": 0.6631142687981054,
462
+ "grad_norm": 1.6015625,
463
+ "learning_rate": 1.5606398763432318e-05,
464
+ "loss": 0.0839945912361145,
465
+ "step": 560,
466
+ "token_acc": 0.9672131147540983
467
+ },
468
+ {
469
+ "epoch": 0.6749555950266429,
470
+ "grad_norm": 1.5,
471
+ "learning_rate": 1.5446658271033336e-05,
472
+ "loss": 0.09018040895462036,
473
+ "step": 570,
474
+ "token_acc": 0.9658574784651527
475
+ },
476
+ {
477
+ "epoch": 0.6867969212551805,
478
+ "grad_norm": 1.40625,
479
+ "learning_rate": 1.528491672527504e-05,
480
+ "loss": 0.08107317686080932,
481
+ "step": 580,
482
+ "token_acc": 0.9681967726774244
483
+ },
484
+ {
485
+ "epoch": 0.6986382474837182,
486
+ "grad_norm": 1.453125,
487
+ "learning_rate": 1.512123354854955e-05,
488
+ "loss": 0.08852046132087707,
489
+ "step": 590,
490
+ "token_acc": 0.9663957486714598
491
+ },
492
+ {
493
+ "epoch": 0.7104795737122558,
494
+ "grad_norm": 1.1875,
495
+ "learning_rate": 1.4955668876586763e-05,
496
+ "loss": 0.07870029807090759,
497
+ "step": 600,
498
+ "token_acc": 0.9683862849952816
499
+ },
500
+ {
501
+ "epoch": 0.7223208999407934,
502
+ "grad_norm": 1.4609375,
503
+ "learning_rate": 1.4788283536361036e-05,
504
+ "loss": 0.0841621994972229,
505
+ "step": 610,
506
+ "token_acc": 0.9685781618224666
507
+ },
508
+ {
509
+ "epoch": 0.7341622261693309,
510
+ "grad_norm": 1.6171875,
511
+ "learning_rate": 1.4619139023743916e-05,
512
+ "loss": 0.08564043045043945,
513
+ "step": 620,
514
+ "token_acc": 0.9654417513682565
515
+ },
516
+ {
517
+ "epoch": 0.7460035523978685,
518
+ "grad_norm": 1.203125,
519
+ "learning_rate": 1.4448297480911086e-05,
520
+ "loss": 0.09037463665008545,
521
+ "step": 630,
522
+ "token_acc": 0.963363081258807
523
+ },
524
+ {
525
+ "epoch": 0.7578448786264061,
526
+ "grad_norm": 0.9609375,
527
+ "learning_rate": 1.4275821673511903e-05,
528
+ "loss": 0.09671027660369873,
529
+ "step": 640,
530
+ "token_acc": 0.959305055564251
531
+ },
532
+ {
533
+ "epoch": 0.7696862048549438,
534
+ "grad_norm": 1.5078125,
535
+ "learning_rate": 1.4101774967609854e-05,
536
+ "loss": 0.09160791039466858,
537
+ "step": 650,
538
+ "token_acc": 0.9654741446648961
539
+ },
540
+ {
541
+ "epoch": 0.7815275310834814,
542
+ "grad_norm": 1.421875,
543
+ "learning_rate": 1.392622130640243e-05,
544
+ "loss": 0.095394766330719,
545
+ "step": 660,
546
+ "token_acc": 0.9619956208945887
547
+ },
548
+ {
549
+ "epoch": 0.7933688573120189,
550
+ "grad_norm": 1.78125,
551
+ "learning_rate": 1.3749225186728991e-05,
552
+ "loss": 0.08577767610549927,
553
+ "step": 670,
554
+ "token_acc": 0.966750313676286
555
+ },
556
+ {
557
+ "epoch": 0.8052101835405565,
558
+ "grad_norm": 2.0625,
559
+ "learning_rate": 1.357085163537517e-05,
560
+ "loss": 0.09209753274917602,
561
+ "step": 680,
562
+ "token_acc": 0.9620608899297424
563
+ },
564
+ {
565
+ "epoch": 0.8170515097690941,
566
+ "grad_norm": 2.390625,
567
+ "learning_rate": 1.3391166185182651e-05,
568
+ "loss": 0.0821334183216095,
569
+ "step": 690,
570
+ "token_acc": 0.9690383111806099
571
+ },
572
+ {
573
+ "epoch": 0.8288928359976317,
574
+ "grad_norm": 1.2109375,
575
+ "learning_rate": 1.3210234850972966e-05,
576
+ "loss": 0.09119898080825806,
577
+ "step": 700,
578
+ "token_acc": 0.9637817497648166
579
+ },
580
+ {
581
+ "epoch": 0.8407341622261694,
582
+ "grad_norm": 1.8671875,
583
+ "learning_rate": 1.3028124105294255e-05,
584
+ "loss": 0.0862145483493805,
585
+ "step": 710,
586
+ "token_acc": 0.9672259683236631
587
+ },
588
+ {
589
+ "epoch": 0.8525754884547069,
590
+ "grad_norm": 1.34375,
591
+ "learning_rate": 1.2844900853999847e-05,
592
+ "loss": 0.08162487745285034,
593
+ "step": 720,
594
+ "token_acc": 0.9676405906377631
595
+ },
596
+ {
597
+ "epoch": 0.8644168146832445,
598
+ "grad_norm": 1.7890625,
599
+ "learning_rate": 1.2660632411667648e-05,
600
+ "loss": 0.08193669319152833,
601
+ "step": 730,
602
+ "token_acc": 0.9653278945716975
603
+ },
604
+ {
605
+ "epoch": 0.8762581409117821,
606
+ "grad_norm": 1.6015625,
607
+ "learning_rate": 1.2475386476869364e-05,
608
+ "loss": 0.09078997969627381,
609
+ "step": 740,
610
+ "token_acc": 0.9639045825486503
611
+ },
612
+ {
613
+ "epoch": 0.8880994671403197,
614
+ "grad_norm": 1.671875,
615
+ "learning_rate": 1.2289231107298672e-05,
616
+ "loss": 0.09944761395454407,
617
+ "step": 750,
618
+ "token_acc": 0.9596546310832025
619
+ },
620
+ {
621
+ "epoch": 0.8999407933688574,
622
+ "grad_norm": 1.1171875,
623
+ "learning_rate": 1.2102234694767401e-05,
624
+ "loss": 0.0917394757270813,
625
+ "step": 760,
626
+ "token_acc": 0.9615505335844319
627
+ },
628
+ {
629
+ "epoch": 0.9117821195973949,
630
+ "grad_norm": 1.609375,
631
+ "learning_rate": 1.1914465940079036e-05,
632
+ "loss": 0.08656581044197083,
633
+ "step": 770,
634
+ "token_acc": 0.9671951028096061
635
+ },
636
+ {
637
+ "epoch": 0.9236234458259325,
638
+ "grad_norm": 1.28125,
639
+ "learning_rate": 1.1725993827788625e-05,
640
+ "loss": 0.08798307180404663,
641
+ "step": 780,
642
+ "token_acc": 0.9632065132299984
643
+ },
644
+ {
645
+ "epoch": 0.9354647720544701,
646
+ "grad_norm": 1.4765625,
647
+ "learning_rate": 1.1536887600858487e-05,
648
+ "loss": 0.08726394176483154,
649
+ "step": 790,
650
+ "token_acc": 0.9665934755332497
651
+ },
652
+ {
653
+ "epoch": 0.9473060982830077,
654
+ "grad_norm": 0.89453125,
655
+ "learning_rate": 1.134721673521897e-05,
656
+ "loss": 0.0808544933795929,
657
+ "step": 800,
658
+ "token_acc": 0.9646211646837821
659
+ },
660
+ {
661
+ "epoch": 0.9591474245115453,
662
+ "grad_norm": 1.3671875,
663
+ "learning_rate": 1.1157050914243614e-05,
664
+ "loss": 0.08560880422592163,
665
+ "step": 810,
666
+ "token_acc": 0.9667189952904238
667
+ },
668
+ {
669
+ "epoch": 0.9709887507400828,
670
+ "grad_norm": 1.3359375,
671
+ "learning_rate": 1.0966460003148115e-05,
672
+ "loss": 0.0828078031539917,
673
+ "step": 820,
674
+ "token_acc": 0.9668499607227022
675
+ },
676
+ {
677
+ "epoch": 0.9828300769686205,
678
+ "grad_norm": 1.921875,
679
+ "learning_rate": 1.0775514023322444e-05,
680
+ "loss": 0.09345529675483703,
681
+ "step": 830,
682
+ "token_acc": 0.9608886107634543
683
+ },
684
+ {
685
+ "epoch": 0.9946714031971581,
686
+ "grad_norm": 1.2578125,
687
+ "learning_rate": 1.058428312660566e-05,
688
+ "loss": 0.08514059782028198,
689
+ "step": 840,
690
+ "token_acc": 0.9657169693174703
691
+ },
692
+ {
693
+ "epoch": 1.0059206631142688,
694
+ "grad_norm": 1.015625,
695
+ "learning_rate": 1.0392837569512715e-05,
696
+ "loss": 0.08234425187110901,
697
+ "step": 850,
698
+ "token_acc": 0.9645318540931249
699
+ },
700
+ {
701
+ "epoch": 1.0177619893428065,
702
+ "grad_norm": 1.8359375,
703
+ "learning_rate": 1.020124768742286e-05,
704
+ "loss": 0.07545605897903443,
705
+ "step": 860,
706
+ "token_acc": 0.9709147771696638
707
+ },
708
+ {
709
+ "epoch": 1.029603315571344,
710
+ "grad_norm": 1.1640625,
711
+ "learning_rate": 1.0009583868739053e-05,
712
+ "loss": 0.07274842262268066,
713
+ "step": 870,
714
+ "token_acc": 0.9721873035826524
715
+ },
716
+ {
717
+ "epoch": 1.0414446417998815,
718
+ "grad_norm": 1.3359375,
719
+ "learning_rate": 9.817916529027898e-06,
720
+ "loss": 0.07491129636764526,
721
+ "step": 880,
722
+ "token_acc": 0.9713480507280413
723
+ },
724
+ {
725
+ "epoch": 1.0532859680284192,
726
+ "grad_norm": 1.15625,
727
+ "learning_rate": 9.626316085149588e-06,
728
+ "loss": 0.07744649052619934,
729
+ "step": 890,
730
+ "token_acc": 0.9709102283390679
731
+ },
732
+ {
733
+ "epoch": 1.0651272942569567,
734
+ "grad_norm": 1.1953125,
735
+ "learning_rate": 9.43485292938739e-06,
736
+ "loss": 0.07794994711875916,
737
+ "step": 900,
738
+ "token_acc": 0.970647931303669
739
+ },
740
+ {
741
+ "epoch": 1.0769686204854945,
742
+ "grad_norm": 1.0234375,
743
+ "learning_rate": 9.243597403586145e-06,
744
+ "loss": 0.0824435293674469,
745
+ "step": 910,
746
+ "token_acc": 0.9683633516053249
747
+ },
748
+ {
749
+ "epoch": 1.088809946714032,
750
+ "grad_norm": 0.91796875,
751
+ "learning_rate": 9.052619773309318e-06,
752
+ "loss": 0.07359167337417602,
753
+ "step": 920,
754
+ "token_acc": 0.9754111198120595
755
+ },
756
+ {
757
+ "epoch": 1.1006512729425695,
758
+ "grad_norm": 1.0625,
759
+ "learning_rate": 8.861990202024046e-06,
760
+ "loss": 0.07806094288825989,
761
+ "step": 930,
762
+ "token_acc": 0.9696922355881894
763
+ },
764
+ {
765
+ "epoch": 1.1124925991711072,
766
+ "grad_norm": 2.0,
767
+ "learning_rate": 8.67177872532372e-06,
768
+ "loss": 0.07662028670310975,
769
+ "step": 940,
770
+ "token_acc": 0.9707960433349034
771
+ },
772
+ {
773
+ "epoch": 1.1243339253996447,
774
+ "grad_norm": 1.5,
775
+ "learning_rate": 8.482055225197532e-06,
776
+ "loss": 0.07939339876174926,
777
+ "step": 950,
778
+ "token_acc": 0.9700156985871271
779
+ },
780
+ {
781
+ "epoch": 1.1361752516281824,
782
+ "grad_norm": 2.046875,
783
+ "learning_rate": 8.292889404356461e-06,
784
+ "loss": 0.07178534269332885,
785
+ "step": 960,
786
+ "token_acc": 0.9713704630788486
787
+ },
788
+ {
789
+ "epoch": 1.14801657785672,
790
+ "grad_norm": 1.453125,
791
+ "learning_rate": 8.104350760625122e-06,
792
+ "loss": 0.07578552961349487,
793
+ "step": 970,
794
+ "token_acc": 0.9700093720712277
795
+ },
796
+ {
797
+ "epoch": 1.1598579040852575,
798
+ "grad_norm": 1.3828125,
799
+ "learning_rate": 7.916508561408892e-06,
800
+ "loss": 0.07551709413528443,
801
+ "step": 980,
802
+ "token_acc": 0.9736513875896476
803
+ },
804
+ {
805
+ "epoch": 1.1716992303137952,
806
+ "grad_norm": 1.0625,
807
+ "learning_rate": 7.729431818245678e-06,
808
+ "loss": 0.06962672472000123,
809
+ "step": 990,
810
+ "token_acc": 0.9749726263100266
811
+ },
812
+ {
813
+ "epoch": 1.1835405565423327,
814
+ "grad_norm": 1.546875,
815
+ "learning_rate": 7.543189261451716e-06,
816
+ "loss": 0.07484488487243653,
817
+ "step": 1000,
818
+ "token_acc": 0.9705790297339593
819
+ },
820
+ {
821
+ "epoch": 1.1953818827708704,
822
+ "grad_norm": 1.328125,
823
+ "learning_rate": 7.35784931487064e-06,
824
+ "loss": 0.07622098922729492,
825
+ "step": 1010,
826
+ "token_acc": 0.970372680492749
827
+ },
828
+ {
829
+ "epoch": 1.207223208999408,
830
+ "grad_norm": 2.390625,
831
+ "learning_rate": 7.173480070735209e-06,
832
+ "loss": 0.07499848604202271,
833
+ "step": 1020,
834
+ "token_acc": 0.9686574146265399
835
+ },
836
+ {
837
+ "epoch": 1.2190645352279454,
838
+ "grad_norm": 1.2109375,
839
+ "learning_rate": 6.990149264650814e-06,
840
+ "loss": 0.07203071117401123,
841
+ "step": 1030,
842
+ "token_acc": 0.972574831531108
843
+ },
844
+ {
845
+ "epoch": 1.2309058614564832,
846
+ "grad_norm": 1.375,
847
+ "learning_rate": 6.807924250710019e-06,
848
+ "loss": 0.07002646923065185,
849
+ "step": 1040,
850
+ "token_acc": 0.9741379310344828
851
+ },
852
+ {
853
+ "epoch": 1.2427471876850207,
854
+ "grad_norm": 1.328125,
855
+ "learning_rate": 6.626871976747289e-06,
856
+ "loss": 0.07481561303138733,
857
+ "step": 1050,
858
+ "token_acc": 0.9709576138147566
859
+ },
860
+ {
861
+ "epoch": 1.2545885139135584,
862
+ "grad_norm": 1.2734375,
863
+ "learning_rate": 6.44705895974294e-06,
864
+ "loss": 0.06933027505874634,
865
+ "step": 1060,
866
+ "token_acc": 0.9734443746071653
867
+ },
868
+ {
869
+ "epoch": 1.266429840142096,
870
+ "grad_norm": 1.5625,
871
+ "learning_rate": 6.268551261385414e-06,
872
+ "loss": 0.0675657868385315,
873
+ "step": 1070,
874
+ "token_acc": 0.9746320075164422
875
+ },
876
+ {
877
+ "epoch": 1.2782711663706334,
878
+ "grad_norm": 1.5546875,
879
+ "learning_rate": 6.091414463800789e-06,
880
+ "loss": 0.07069060802459717,
881
+ "step": 1080,
882
+ "token_acc": 0.973655323819978
883
+ },
884
+ {
885
+ "epoch": 1.2901124925991712,
886
+ "grad_norm": 1.125,
887
+ "learning_rate": 5.915713645458514e-06,
888
+ "loss": 0.07225958108901978,
889
+ "step": 1090,
890
+ "token_acc": 0.9728201099764336
891
+ },
892
+ {
893
+ "epoch": 1.3019538188277087,
894
+ "grad_norm": 1.6171875,
895
+ "learning_rate": 5.741513357262147e-06,
896
+ "loss": 0.07490838170051575,
897
+ "step": 1100,
898
+ "token_acc": 0.970542149796302
899
+ },
900
+ {
901
+ "epoch": 1.3137951450562464,
902
+ "grad_norm": 1.3359375,
903
+ "learning_rate": 5.568877598833935e-06,
904
+ "loss": 0.07528679370880127,
905
+ "step": 1110,
906
+ "token_acc": 0.970496409615985
907
+ },
908
+ {
909
+ "epoch": 1.325636471284784,
910
+ "grad_norm": 1.453125,
911
+ "learning_rate": 5.3978697950019484e-06,
912
+ "loss": 0.07579593658447266,
913
+ "step": 1120,
914
+ "token_acc": 0.9716936625255543
915
+ },
916
+ {
917
+ "epoch": 1.3374777975133214,
918
+ "grad_norm": 1.6640625,
919
+ "learning_rate": 5.228552772498335e-06,
920
+ "loss": 0.06750929355621338,
921
+ "step": 1130,
922
+ "token_acc": 0.9741029641185648
923
+ },
924
+ {
925
+ "epoch": 1.3493191237418591,
926
+ "grad_norm": 1.6875,
927
+ "learning_rate": 5.060988736877366e-06,
928
+ "loss": 0.07841302156448364,
929
+ "step": 1140,
930
+ "token_acc": 0.9696400625978091
931
+ },
932
+ {
933
+ "epoch": 1.3611604499703966,
934
+ "grad_norm": 1.3671875,
935
+ "learning_rate": 4.895239249661662e-06,
936
+ "loss": 0.08451638221740723,
937
+ "step": 1150,
938
+ "token_acc": 0.967736883320282
939
+ },
940
+ {
941
+ "epoch": 1.3730017761989344,
942
+ "grad_norm": 1.0234375,
943
+ "learning_rate": 4.731365205725056e-06,
944
+ "loss": 0.074539315700531,
945
+ "step": 1160,
946
+ "token_acc": 0.9703715315880233
947
+ },
948
+ {
949
+ "epoch": 1.3848431024274719,
950
+ "grad_norm": 1.3359375,
951
+ "learning_rate": 4.569426810920347e-06,
952
+ "loss": 0.068775475025177,
953
+ "step": 1170,
954
+ "token_acc": 0.9716523101018011
955
+ },
956
+ {
957
+ "epoch": 1.3966844286560094,
958
+ "grad_norm": 1.2265625,
959
+ "learning_rate": 4.409483559960221e-06,
960
+ "loss": 0.07150940299034118,
961
+ "step": 1180,
962
+ "token_acc": 0.9737005913476502
963
+ },
964
+ {
965
+ "epoch": 1.4085257548845471,
966
+ "grad_norm": 1.890625,
967
+ "learning_rate": 4.251594214559416e-06,
968
+ "loss": 0.08267040252685547,
969
+ "step": 1190,
970
+ "token_acc": 0.9680350987151363
971
+ },
972
+ {
973
+ "epoch": 1.4203670811130846,
974
+ "grad_norm": 1.46875,
975
+ "learning_rate": 4.095816781846219e-06,
976
+ "loss": 0.0697063684463501,
977
+ "step": 1200,
978
+ "token_acc": 0.9751095804633688
979
+ },
980
+ {
981
+ "epoch": 1.4322084073416224,
982
+ "grad_norm": 1.203125,
983
+ "learning_rate": 3.942208493051137e-06,
984
+ "loss": 0.07361778020858764,
985
+ "step": 1210,
986
+ "token_acc": 0.9734901960784313
987
+ },
988
+ {
989
+ "epoch": 1.4440497335701599,
990
+ "grad_norm": 1.4609375,
991
+ "learning_rate": 3.7908257824806814e-06,
992
+ "loss": 0.07019197940826416,
993
+ "step": 1220,
994
+ "token_acc": 0.9710122218740207
995
+ },
996
+ {
997
+ "epoch": 1.4558910597986974,
998
+ "grad_norm": 1.5859375,
999
+ "learning_rate": 3.6417242667838917e-06,
1000
+ "loss": 0.07444216012954712,
1001
+ "step": 1230,
1002
+ "token_acc": 0.9728040012503908
1003
+ },
1004
+ {
1005
+ "epoch": 1.467732386027235,
1006
+ "grad_norm": 1.4375,
1007
+ "learning_rate": 3.4949587245192983e-06,
1008
+ "loss": 0.06847925186157226,
1009
+ "step": 1240,
1010
+ "token_acc": 0.9746320075164422
1011
+ },
1012
+ {
1013
+ "epoch": 1.4795737122557726,
1014
+ "grad_norm": 1.625,
1015
+ "learning_rate": 3.3505830760297543e-06,
1016
+ "loss": 0.0696124255657196,
1017
+ "step": 1250,
1018
+ "token_acc": 0.9730534231552561
1019
+ },
1020
+ {
1021
+ "epoch": 1.4914150384843103,
1022
+ "grad_norm": 1.3203125,
1023
+ "learning_rate": 3.2086503636325895e-06,
1024
+ "loss": 0.07145707607269287,
1025
+ "step": 1260,
1026
+ "token_acc": 0.9749294891883422
1027
+ },
1028
+ {
1029
+ "epoch": 1.5032563647128478,
1030
+ "grad_norm": 1.8515625,
1031
+ "learning_rate": 3.069212732132345e-06,
1032
+ "loss": 0.07296675443649292,
1033
+ "step": 1270,
1034
+ "token_acc": 0.9725662329518734
1035
+ },
1036
+ {
1037
+ "epoch": 1.5150976909413854,
1038
+ "grad_norm": 2.625,
1039
+ "learning_rate": 2.9323214096632335e-06,
1040
+ "loss": 0.07637610435485839,
1041
+ "step": 1280,
1042
+ "token_acc": 0.9721566776781501
1043
+ },
1044
+ {
1045
+ "epoch": 1.526939017169923,
1046
+ "grad_norm": 1.4375,
1047
+ "learning_rate": 2.798026688868386e-06,
1048
+ "loss": 0.07028791308403015,
1049
+ "step": 1290,
1050
+ "token_acc": 0.9726801695713613
1051
+ },
1052
+ {
1053
+ "epoch": 1.5387803433984606,
1054
+ "grad_norm": 1.7578125,
1055
+ "learning_rate": 2.6663779084227926e-06,
1056
+ "loss": 0.0738570511341095,
1057
+ "step": 1300,
1058
+ "token_acc": 0.9717247879359096
1059
+ },
1060
+ {
1061
+ "epoch": 1.5506216696269983,
1062
+ "grad_norm": 2.046875,
1063
+ "learning_rate": 2.5374234349066985e-06,
1064
+ "loss": 0.07539566755294799,
1065
+ "step": 1310,
1066
+ "token_acc": 0.9680968096809681
1067
+ },
1068
+ {
1069
+ "epoch": 1.5624629958555358,
1070
+ "grad_norm": 1.09375,
1071
+ "learning_rate": 2.411210645036173e-06,
1072
+ "loss": 0.07291572093963623,
1073
+ "step": 1320,
1074
+ "token_acc": 0.972758405977584
1075
+ },
1076
+ {
1077
+ "epoch": 1.5743043220840733,
1078
+ "grad_norm": 1.6484375,
1079
+ "learning_rate": 2.2877859082573194e-06,
1080
+ "loss": 0.07078194618225098,
1081
+ "step": 1330,
1082
+ "token_acc": 0.9733229329173166
1083
+ },
1084
+ {
1085
+ "epoch": 1.586145648312611,
1086
+ "grad_norm": 1.53125,
1087
+ "learning_rate": 2.16719456971057e-06,
1088
+ "loss": 0.07727055549621582,
1089
+ "step": 1340,
1090
+ "token_acc": 0.9690154136520919
1091
+ },
1092
+ {
1093
+ "epoch": 1.5979869745411486,
1094
+ "grad_norm": 1.125,
1095
+ "learning_rate": 2.0494809335712697e-06,
1096
+ "loss": 0.06905415058135986,
1097
+ "step": 1350,
1098
+ "token_acc": 0.9750783699059561
1099
+ },
1100
+ {
1101
+ "epoch": 1.6098283007696863,
1102
+ "grad_norm": 1.8046875,
1103
+ "learning_rate": 1.9346882467727323e-06,
1104
+ "loss": 0.07434183359146118,
1105
+ "step": 1360,
1106
+ "token_acc": 0.9726091720143998
1107
+ },
1108
+ {
1109
+ "epoch": 1.6216696269982238,
1110
+ "grad_norm": 0.96875,
1111
+ "learning_rate": 1.8228586831177032e-06,
1112
+ "loss": 0.06618231534957886,
1113
+ "step": 1370,
1114
+ "token_acc": 0.9750900830330566
1115
+ },
1116
+ {
1117
+ "epoch": 1.6335109532267613,
1118
+ "grad_norm": 1.34375,
1119
+ "learning_rate": 1.7140333277840837e-06,
1120
+ "loss": 0.07258784770965576,
1121
+ "step": 1380,
1122
+ "token_acc": 0.9727699530516432
1123
+ },
1124
+ {
1125
+ "epoch": 1.6453522794552988,
1126
+ "grad_norm": 1.1875,
1127
+ "learning_rate": 1.6082521622306003e-06,
1128
+ "loss": 0.0752481460571289,
1129
+ "step": 1390,
1130
+ "token_acc": 0.9715364050951407
1131
+ },
1132
+ {
1133
+ "epoch": 1.6571936056838366,
1134
+ "grad_norm": 1.3984375,
1135
+ "learning_rate": 1.5055540495079802e-06,
1136
+ "loss": 0.06541621685028076,
1137
+ "step": 1400,
1138
+ "token_acc": 0.9767806714778788
1139
+ },
1140
+ {
1141
+ "epoch": 1.6690349319123743,
1142
+ "grad_norm": 1.90625,
1143
+ "learning_rate": 1.4059767199810125e-06,
1144
+ "loss": 0.0707894206047058,
1145
+ "step": 1410,
1146
+ "token_acc": 0.9731301068510371
1147
+ },
1148
+ {
1149
+ "epoch": 1.6808762581409118,
1150
+ "grad_norm": 1.3203125,
1151
+ "learning_rate": 1.3095567574667589e-06,
1152
+ "loss": 0.07458854913711548,
1153
+ "step": 1420,
1154
+ "token_acc": 0.9726630007855459
1155
+ },
1156
+ {
1157
+ "epoch": 1.6927175843694493,
1158
+ "grad_norm": 1.65625,
1159
+ "learning_rate": 1.216329585793975e-06,
1160
+ "loss": 0.06724110841751099,
1161
+ "step": 1430,
1162
+ "token_acc": 0.9734000938820216
1163
+ },
1164
+ {
1165
+ "epoch": 1.7045589105979868,
1166
+ "grad_norm": 1.46875,
1167
+ "learning_rate": 1.1263294557887216e-06,
1168
+ "loss": 0.07588486671447754,
1169
+ "step": 1440,
1170
+ "token_acc": 0.9710873664362036
1171
+ },
1172
+ {
1173
+ "epoch": 1.7164002368265245,
1174
+ "grad_norm": 2.046875,
1175
+ "learning_rate": 1.0395894326909163e-06,
1176
+ "loss": 0.07099611163139344,
1177
+ "step": 1450,
1178
+ "token_acc": 0.9723091364205256
1179
+ },
1180
+ {
1181
+ "epoch": 1.7282415630550623,
1182
+ "grad_norm": 1.921875,
1183
+ "learning_rate": 9.561413840064637e-07,
1184
+ "loss": 0.06974682807922364,
1185
+ "step": 1460,
1186
+ "token_acc": 0.9720609009574636
1187
+ },
1188
+ {
1189
+ "epoch": 1.7400828892835998,
1190
+ "grad_norm": 1.2578125,
1191
+ "learning_rate": 8.760159677994174e-07,
1192
+ "loss": 0.06880149841308594,
1193
+ "step": 1470,
1194
+ "token_acc": 0.9749019607843137
1195
+ },
1196
+ {
1197
+ "epoch": 1.7519242155121373,
1198
+ "grad_norm": 1.90625,
1199
+ "learning_rate": 7.992426214284787e-07,
1200
+ "loss": 0.07654795646667481,
1201
+ "step": 1480,
1202
+ "token_acc": 0.969967151572032
1203
+ },
1204
+ {
1205
+ "epoch": 1.7637655417406748,
1206
+ "grad_norm": 1.3671875,
1207
+ "learning_rate": 7.258495507319885e-07,
1208
+ "loss": 0.06865710020065308,
1209
+ "step": 1490,
1210
+ "token_acc": 0.9735068192506663
1211
+ },
1212
+ {
1213
+ "epoch": 1.7756068679692125,
1214
+ "grad_norm": 1.34375,
1215
+ "learning_rate": 6.558637196653372e-07,
1216
+ "loss": 0.06818960905075074,
1217
+ "step": 1500,
1218
+ "token_acc": 0.9739225484072455
1219
+ },
1220
+ {
1221
+ "epoch": 1.7874481941977503,
1222
+ "grad_norm": 1.7578125,
1223
+ "learning_rate": 5.893108403946634e-07,
1224
+ "loss": 0.07731307148933411,
1225
+ "step": 1510,
1226
+ "token_acc": 0.9705836332342357
1227
+ },
1228
+ {
1229
+ "epoch": 1.7992895204262878,
1230
+ "grad_norm": 1.1484375,
1231
+ "learning_rate": 5.262153638504286e-07,
1232
+ "loss": 0.07072955965995789,
1233
+ "step": 1520,
1234
+ "token_acc": 0.9747514596812372
1235
+ },
1236
+ {
1237
+ "epoch": 1.8111308466548253,
1238
+ "grad_norm": 1.40625,
1239
+ "learning_rate": 4.6660047074436945e-07,
1240
+ "loss": 0.07091631889343261,
1241
+ "step": 1530,
1242
+ "token_acc": 0.9746914544602406
1243
+ },
1244
+ {
1245
+ "epoch": 1.8229721728833628,
1246
+ "grad_norm": 1.6328125,
1247
+ "learning_rate": 4.10488063053105e-07,
1248
+ "loss": 0.062443327903747556,
1249
+ "step": 1540,
1250
+ "token_acc": 0.976577139287945
1251
+ },
1252
+ {
1253
+ "epoch": 1.8348134991119005,
1254
+ "grad_norm": 1.6015625,
1255
+ "learning_rate": 3.57898755971553e-07,
1256
+ "loss": 0.07588485479354859,
1257
+ "step": 1550,
1258
+ "token_acc": 0.973754100921731
1259
+ },
1260
+ {
1261
+ "epoch": 1.8466548253404382,
1262
+ "grad_norm": 1.4375,
1263
+ "learning_rate": 3.088518703390908e-07,
1264
+ "loss": 0.07371261715888977,
1265
+ "step": 1560,
1266
+ "token_acc": 0.9696590553644041
1267
+ },
1268
+ {
1269
+ "epoch": 1.8584961515689757,
1270
+ "grad_norm": 1.1484375,
1271
+ "learning_rate": 2.633654255412554e-07,
1272
+ "loss": 0.06826964616775513,
1273
+ "step": 1570,
1274
+ "token_acc": 0.9750783699059561
1275
+ },
1276
+ {
1277
+ "epoch": 1.8703374777975132,
1278
+ "grad_norm": 1.5078125,
1279
+ "learning_rate": 2.214561328895748e-07,
1280
+ "loss": 0.06952533721923829,
1281
+ "step": 1580,
1282
+ "token_acc": 0.9716478696741855
1283
+ },
1284
+ {
1285
+ "epoch": 1.8821788040260508,
1286
+ "grad_norm": 1.7890625,
1287
+ "learning_rate": 1.8313938948198884e-07,
1288
+ "loss": 0.07293472290039063,
1289
+ "step": 1590,
1290
+ "token_acc": 0.9714820009350164
1291
+ },
1292
+ {
1293
+ "epoch": 1.8940201302545885,
1294
+ "grad_norm": 1.625,
1295
+ "learning_rate": 1.484292725460934e-07,
1296
+ "loss": 0.07688854336738586,
1297
+ "step": 1600,
1298
+ "token_acc": 0.9702054257487847
1299
+ },
1300
+ {
1301
+ "epoch": 1.9058614564831262,
1302
+ "grad_norm": 1.3359375,
1303
+ "learning_rate": 1.173385342672917e-07,
1304
+ "loss": 0.07143334150314332,
1305
+ "step": 1610,
1306
+ "token_acc": 0.970491288651703
1307
+ },
1308
+ {
1309
+ "epoch": 1.9177027827116637,
1310
+ "grad_norm": 1.921875,
1311
+ "learning_rate": 8.987859710375524e-08,
1312
+ "loss": 0.081912100315094,
1313
+ "step": 1620,
1314
+ "token_acc": 0.9685150375939849
1315
+ },
1316
+ {
1317
+ "epoch": 1.9295441089402012,
1318
+ "grad_norm": 1.8203125,
1319
+ "learning_rate": 6.605954958991523e-08,
1320
+ "loss": 0.07874792218208312,
1321
+ "step": 1630,
1322
+ "token_acc": 0.9696588586700204
1323
+ },
1324
+ {
1325
+ "epoch": 1.9413854351687387,
1326
+ "grad_norm": 1.5546875,
1327
+ "learning_rate": 4.5890142630027336e-08,
1328
+ "loss": 0.0735186517238617,
1329
+ "step": 1640,
1330
+ "token_acc": 0.9709894934922377
1331
+ },
1332
+ {
1333
+ "epoch": 1.9532267613972765,
1334
+ "grad_norm": 1.9765625,
1335
+ "learning_rate": 2.9377786283167897e-08,
1336
+ "loss": 0.0773587942123413,
1337
+ "step": 1650,
1338
+ "token_acc": 0.9692741809060982
1339
+ },
1340
+ {
1341
+ "epoch": 1.9650680876258142,
1342
+ "grad_norm": 1.796875,
1343
+ "learning_rate": 1.6528547040842724e-08,
1344
+ "loss": 0.06999446153640747,
1345
+ "step": 1660,
1346
+ "token_acc": 0.9743669896842764
1347
+ },
1348
+ {
1349
+ "epoch": 1.9769094138543517,
1350
+ "grad_norm": 1.5859375,
1351
+ "learning_rate": 7.3471455982143665e-09,
1352
+ "loss": 0.07299281358718872,
1353
+ "step": 1670,
1354
+ "token_acc": 0.9729179711959924
1355
+ },
1356
+ {
1357
+ "epoch": 1.9887507400828892,
1358
+ "grad_norm": 1.34375,
1359
+ "learning_rate": 1.8369551197594538e-09,
1360
+ "loss": 0.067216557264328,
1361
+ "step": 1680,
1362
+ "token_acc": 0.9730407523510972
1363
+ },
1364
+ {
1365
+ "epoch": 2.0,
1366
+ "grad_norm": 2.65625,
1367
+ "learning_rate": 0.0,
1368
+ "loss": 0.07405292987823486,
1369
+ "step": 1690,
1370
+ "token_acc": 0.9716838024608124
1371
+ }
1372
+ ],
1373
+ "logging_steps": 10,
1374
+ "max_steps": 1690,
1375
+ "num_input_tokens_seen": 0,
1376
+ "num_train_epochs": 2,
1377
+ "save_steps": 500,
1378
+ "stateful_callbacks": {
1379
+ "TrainerControl": {
1380
+ "args": {
1381
+ "should_epoch_stop": false,
1382
+ "should_evaluate": false,
1383
+ "should_log": false,
1384
+ "should_save": true,
1385
+ "should_training_stop": true
1386
+ },
1387
+ "attributes": {}
1388
+ }
1389
+ },
1390
+ "total_flos": 1.7276889282044232e+18,
1391
+ "train_batch_size": 8,
1392
+ "trial_name": null,
1393
+ "trial_params": null
1394
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e7fbd87625cc50123815e7aff873d4789ca3015538e01899b3d2b9db87882bd
3
+ size 7057
vocab.json ADDED
The diff for this file is too large to render. See raw diff