Omartificial-Intelligence-Space commited on
Commit
31eb4bc
·
verified ·
1 Parent(s): a23d2b3

upload mdoel files

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
1_Pooling/config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "word_embedding_dimension": 1024,
3
+ "pooling_mode_cls_token": false,
4
+ "pooling_mode_mean_tokens": true,
5
+ "pooling_mode_max_tokens": false,
6
+ "pooling_mode_mean_sqrt_len_tokens": false,
7
+ "pooling_mode_weightedmean_tokens": false,
8
+ "pooling_mode_lasttoken": false,
9
+ "include_prompt": true
10
+ }
README.md CHANGED
@@ -1,3 +1,727 @@
1
- ---
2
- license: apache-2.0
3
- ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - en
4
+ tags:
5
+ - sentence-transformers
6
+ - sentence-similarity
7
+ - feature-extraction
8
+ - generated_from_trainer
9
+ - dataset_size:2280319
10
+ - loss:MatryoshkaLoss
11
+ - loss:MultipleNegativesRankingLoss
12
+ base_model: Qwen/Qwen3-Embedding-0.6B
13
+ widget:
14
+ - source_sentence: I'd suggest you find a bank in your local country, and consider
15
+ opening a Euro denominated bank account with them.
16
+ sentences:
17
+ - You can mix those, but in my experience, it will be very difficult at first.
18
+ - The woman is pencilling on eye shadow.
19
+ - I am not sure if you can open a bank account in France if you are not a resident.
20
+ - source_sentence: Black and white image of a wave crashing in the ocean.
21
+ sentences:
22
+ - a small black dog in the ocean with some rocks in the background
23
+ - A woman is riding an elephant.
24
+ - A yellow and orange bird hold on to the side of a cage.
25
+ - source_sentence: If you can get over the "ick factor," you have an easily-applied
26
+ source of organic nitrogen fertilizer close at hand.
27
+ sentences:
28
+ - The NPK numbers on the fertilizer represents the percent, by weight, of Nitrogen,
29
+ P2O5 and K2O, respectively.
30
+ - Wikipedia's compilation of Time Travel Rules is a good resource to check about
31
+ this subject.
32
+ - A man is playing a flute.
33
+ - source_sentence: A man is speaking.
34
+ sentences:
35
+ - A man is dancing.
36
+ - A cougar is chasing a bear.
37
+ - For completeness, Apple's Pages has quite a few nice poster layouts.
38
+ - source_sentence: Left side of a silver train engine.
39
+ sentences:
40
+ - A monkey is riding a bus.
41
+ - One idea that's been going around at least since the 80s is that you can distinguish
42
+ between Holds and Moves.
43
+ - A close-up of a black train engine.
44
+ datasets:
45
+ - silma-ai/silma-arabic-triplets-dataset-v1.0
46
+ - sentence-transformers/stsb
47
+ pipeline_tag: sentence-similarity
48
+ library_name: sentence-transformers
49
+ ---
50
+
51
+ # SentenceTransformer based on Qwen/Qwen3-Embedding-0.6B
52
+
53
+ This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [Qwen/Qwen3-Embedding-0.6B](https://huggingface.co/Qwen/Qwen3-Embedding-0.6B) on the [silma-arabic-triplets-dataset-v1.0](https://huggingface.co/datasets/silma-ai/silma-arabic-triplets-dataset-v1.0) dataset. It maps sentences & paragraphs to a 1024-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
54
+
55
+ ## Model Details
56
+
57
+ ### Model Description
58
+ - **Model Type:** Sentence Transformer
59
+ - **Base model:** [Qwen/Qwen3-Embedding-0.6B](https://huggingface.co/Qwen/Qwen3-Embedding-0.6B) <!-- at revision a579a21d7aff542145eebef8d60ed73ec281a0b4 -->
60
+ - **Maximum Sequence Length:** 32768 tokens
61
+ - **Output Dimensionality:** 1024 dimensions
62
+ - **Similarity Function:** Cosine Similarity
63
+ - **Training Dataset:**
64
+ - [silma-arabic-triplets-dataset-v1.0](https://huggingface.co/datasets/silma-ai/silma-arabic-triplets-dataset-v1.0)
65
+ - **Language:** en
66
+ <!-- - **License:** Unknown -->
67
+
68
+ ### Model Sources
69
+
70
+ - **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
71
+ - **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
72
+ - **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
73
+
74
+ ### Full Model Architecture
75
+
76
+ ```
77
+ SentenceTransformer(
78
+ (0): Transformer({'max_seq_length': 32768, 'do_lower_case': False}) with Transformer model: Qwen3Model
79
+ (1): Pooling({'word_embedding_dimension': 1024, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
80
+ )
81
+ ```
82
+
83
+ ## Usage
84
+
85
+ ### Direct Usage (Sentence Transformers)
86
+
87
+ First install the Sentence Transformers library:
88
+
89
+ ```bash
90
+ pip install -U sentence-transformers
91
+ ```
92
+
93
+ Then you can load this model and run inference.
94
+ ```python
95
+ from sentence_transformers import SentenceTransformer
96
+
97
+ # Download from the 🤗 Hub
98
+ model = SentenceTransformer("sentence_transformers_model_id")
99
+ # Run inference
100
+ sentences = [
101
+ 'Left side of a silver train engine.',
102
+ 'A close-up of a black train engine.',
103
+ "One idea that's been going around at least since the 80s is that you can distinguish between Holds and Moves.",
104
+ ]
105
+ embeddings = model.encode(sentences)
106
+ print(embeddings.shape)
107
+ # [3, 1024]
108
+
109
+ # Get the similarity scores for the embeddings
110
+ similarities = model.similarity(embeddings, embeddings)
111
+ print(similarities.shape)
112
+ # [3, 3]
113
+ ```
114
+
115
+ <!--
116
+ ### Direct Usage (Transformers)
117
+
118
+ <details><summary>Click to see the direct usage in Transformers</summary>
119
+
120
+ </details>
121
+ -->
122
+
123
+ <!--
124
+ ### Downstream Usage (Sentence Transformers)
125
+
126
+ You can finetune this model on your own dataset.
127
+
128
+ <details><summary>Click to expand</summary>
129
+
130
+ </details>
131
+ -->
132
+
133
+ <!--
134
+ ### Out-of-Scope Use
135
+
136
+ *List how the model may foreseeably be misused and address what users ought not to do with the model.*
137
+ -->
138
+
139
+ <!--
140
+ ## Bias, Risks and Limitations
141
+
142
+ *What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
143
+ -->
144
+
145
+ <!--
146
+ ### Recommendations
147
+
148
+ *What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
149
+ -->
150
+
151
+ ## Training Details
152
+
153
+ ### Training Dataset
154
+
155
+ #### silma-arabic-triplets-dataset-v1.0
156
+
157
+ * Dataset: [silma-arabic-triplets-dataset-v1.0](https://huggingface.co/datasets/silma-ai/silma-arabic-triplets-dataset-v1.0) at [77f8f6b](https://huggingface.co/datasets/silma-ai/silma-arabic-triplets-dataset-v1.0/tree/77f8f6b223049e7e5968929f5d6cdd2320d1a6dc)
158
+ * Size: 2,280,319 training samples
159
+ * Columns: <code>anchor</code>, <code>positive</code>, and <code>negative</code>
160
+ * Approximate statistics based on the first 1000 samples:
161
+ | | anchor | positive | negative |
162
+ |:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|
163
+ | type | string | string | string |
164
+ | details | <ul><li>min: 2 tokens</li><li>mean: 17.04 tokens</li><li>max: 64 tokens</li></ul> | <ul><li>min: 2 tokens</li><li>mean: 15.17 tokens</li><li>max: 96 tokens</li></ul> | <ul><li>min: 3 tokens</li><li>mean: 14.81 tokens</li><li>max: 57 tokens</li></ul> |
165
+ * Samples:
166
+ | anchor | positive | negative |
167
+ |:-------------------------------------------------------------------------------|:-----------------------------------------------------|:------------------------------------------------------------------------|
168
+ | <code>صبي صغير وفتاة صغيرة يركبان دراجتيهما على الرصيف مع عجلات مساعدة.</code> | <code>فتى وفتاة يتعلمون ركوب الدراجات</code> | <code>الصبي الصغير يصل إلى العصا من الفتاة وهو يدير سباق التتابع</code> |
169
+ | <code>كيف أتجنب التفكير في نفسي أكثر من اللازم؟</code> | <code>كيف يمكنني تجنب التفكير أكثر من اللازم؟</code> | <code>كيف أتطوّر قدرة التفكير؟</code> |
170
+ | <code>ما هو أفضل كتاب يقرأه مراهق؟</code> | <code>ما هو أفضل كتاب للمراهقين؟</code> | <code>ما هي الكتب التي يمكن للطلاب قراءتها؟</code> |
171
+ * Loss: [<code>MatryoshkaLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#matryoshkaloss) with these parameters:
172
+ ```json
173
+ {
174
+ "loss": "MultipleNegativesRankingLoss",
175
+ "matryoshka_dims": [
176
+ 1024,
177
+ 768,
178
+ 512,
179
+ 256
180
+ ],
181
+ "matryoshka_weights": [
182
+ 1,
183
+ 1,
184
+ 1,
185
+ 1
186
+ ],
187
+ "n_dims_per_step": -1
188
+ }
189
+ ```
190
+
191
+ ### Evaluation Dataset
192
+
193
+ #### stsb
194
+
195
+ * Dataset: [stsb](https://huggingface.co/datasets/sentence-transformers/stsb) at [ab7a5ac](https://huggingface.co/datasets/sentence-transformers/stsb/tree/ab7a5ac0e35aa22088bdcf23e7fd99b220e53308)
196
+ * Size: 1,500 evaluation samples
197
+ * Columns: <code>sentence1</code>, <code>sentence2</code>, and <code>score</code>
198
+ * Approximate statistics based on the first 1000 samples:
199
+ | | sentence1 | sentence2 | score |
200
+ |:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:---------------------------------------------------------------|
201
+ | type | string | string | float |
202
+ | details | <ul><li>min: 3 tokens</li><li>mean: 12.98 tokens</li><li>max: 46 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 12.96 tokens</li><li>max: 51 tokens</li></ul> | <ul><li>min: 0.0</li><li>mean: 0.42</li><li>max: 1.0</li></ul> |
203
+ * Samples:
204
+ | sentence1 | sentence2 | score |
205
+ |:--------------------------------------------------|:------------------------------------------------------|:------------------|
206
+ | <code>A man with a hard hat is dancing.</code> | <code>A man wearing a hard hat is dancing.</code> | <code>1.0</code> |
207
+ | <code>A young child is riding a horse.</code> | <code>A child is riding a horse.</code> | <code>0.95</code> |
208
+ | <code>A man is feeding a mouse to a snake.</code> | <code>The man is feeding a mouse to the snake.</code> | <code>1.0</code> |
209
+ * Loss: [<code>MatryoshkaLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#matryoshkaloss) with these parameters:
210
+ ```json
211
+ {
212
+ "loss": "MultipleNegativesRankingLoss",
213
+ "matryoshka_dims": [
214
+ 1024,
215
+ 768,
216
+ 512,
217
+ 256
218
+ ],
219
+ "matryoshka_weights": [
220
+ 1,
221
+ 1,
222
+ 1,
223
+ 1
224
+ ],
225
+ "n_dims_per_step": -1
226
+ }
227
+ ```
228
+
229
+ ### Training Hyperparameters
230
+ #### Non-Default Hyperparameters
231
+
232
+ - `per_device_train_batch_size`: 32
233
+ - `per_device_eval_batch_size`: 32
234
+ - `warmup_ratio`: 0.1
235
+ - `bf16`: True
236
+ - `batch_sampler`: no_duplicates
237
+
238
+ #### All Hyperparameters
239
+ <details><summary>Click to expand</summary>
240
+
241
+ - `overwrite_output_dir`: False
242
+ - `do_predict`: False
243
+ - `eval_strategy`: no
244
+ - `prediction_loss_only`: True
245
+ - `per_device_train_batch_size`: 32
246
+ - `per_device_eval_batch_size`: 32
247
+ - `per_gpu_train_batch_size`: None
248
+ - `per_gpu_eval_batch_size`: None
249
+ - `gradient_accumulation_steps`: 1
250
+ - `eval_accumulation_steps`: None
251
+ - `torch_empty_cache_steps`: None
252
+ - `learning_rate`: 5e-05
253
+ - `weight_decay`: 0.0
254
+ - `adam_beta1`: 0.9
255
+ - `adam_beta2`: 0.999
256
+ - `adam_epsilon`: 1e-08
257
+ - `max_grad_norm`: 1.0
258
+ - `num_train_epochs`: 3
259
+ - `max_steps`: -1
260
+ - `lr_scheduler_type`: linear
261
+ - `lr_scheduler_kwargs`: {}
262
+ - `warmup_ratio`: 0.1
263
+ - `warmup_steps`: 0
264
+ - `log_level`: passive
265
+ - `log_level_replica`: warning
266
+ - `log_on_each_node`: True
267
+ - `logging_nan_inf_filter`: True
268
+ - `save_safetensors`: True
269
+ - `save_on_each_node`: False
270
+ - `save_only_model`: False
271
+ - `restore_callback_states_from_checkpoint`: False
272
+ - `no_cuda`: False
273
+ - `use_cpu`: False
274
+ - `use_mps_device`: False
275
+ - `seed`: 42
276
+ - `data_seed`: None
277
+ - `jit_mode_eval`: False
278
+ - `use_ipex`: False
279
+ - `bf16`: True
280
+ - `fp16`: False
281
+ - `fp16_opt_level`: O1
282
+ - `half_precision_backend`: auto
283
+ - `bf16_full_eval`: False
284
+ - `fp16_full_eval`: False
285
+ - `tf32`: None
286
+ - `local_rank`: 0
287
+ - `ddp_backend`: None
288
+ - `tpu_num_cores`: None
289
+ - `tpu_metrics_debug`: False
290
+ - `debug`: []
291
+ - `dataloader_drop_last`: True
292
+ - `dataloader_num_workers`: 0
293
+ - `dataloader_prefetch_factor`: None
294
+ - `past_index`: -1
295
+ - `disable_tqdm`: False
296
+ - `remove_unused_columns`: True
297
+ - `label_names`: None
298
+ - `load_best_model_at_end`: False
299
+ - `ignore_data_skip`: False
300
+ - `fsdp`: []
301
+ - `fsdp_min_num_params`: 0
302
+ - `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
303
+ - `tp_size`: 0
304
+ - `fsdp_transformer_layer_cls_to_wrap`: None
305
+ - `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
306
+ - `deepspeed`: None
307
+ - `label_smoothing_factor`: 0.0
308
+ - `optim`: adamw_torch
309
+ - `optim_args`: None
310
+ - `adafactor`: False
311
+ - `group_by_length`: False
312
+ - `length_column_name`: length
313
+ - `ddp_find_unused_parameters`: None
314
+ - `ddp_bucket_cap_mb`: None
315
+ - `ddp_broadcast_buffers`: False
316
+ - `dataloader_pin_memory`: True
317
+ - `dataloader_persistent_workers`: False
318
+ - `skip_memory_metrics`: True
319
+ - `use_legacy_prediction_loop`: False
320
+ - `push_to_hub`: False
321
+ - `resume_from_checkpoint`: None
322
+ - `hub_model_id`: None
323
+ - `hub_strategy`: every_save
324
+ - `hub_private_repo`: None
325
+ - `hub_always_push`: False
326
+ - `gradient_checkpointing`: False
327
+ - `gradient_checkpointing_kwargs`: None
328
+ - `include_inputs_for_metrics`: False
329
+ - `include_for_metrics`: []
330
+ - `eval_do_concat_batches`: True
331
+ - `fp16_backend`: auto
332
+ - `push_to_hub_model_id`: None
333
+ - `push_to_hub_organization`: None
334
+ - `mp_parameters`:
335
+ - `auto_find_batch_size`: False
336
+ - `full_determinism`: False
337
+ - `torchdynamo`: None
338
+ - `ray_scope`: last
339
+ - `ddp_timeout`: 1800
340
+ - `torch_compile`: False
341
+ - `torch_compile_backend`: None
342
+ - `torch_compile_mode`: None
343
+ - `include_tokens_per_second`: False
344
+ - `include_num_input_tokens_seen`: False
345
+ - `neftune_noise_alpha`: None
346
+ - `optim_target_modules`: None
347
+ - `batch_eval_metrics`: False
348
+ - `eval_on_start`: False
349
+ - `use_liger_kernel`: False
350
+ - `eval_use_gather_object`: False
351
+ - `average_tokens_across_devices`: False
352
+ - `prompts`: None
353
+ - `batch_sampler`: no_duplicates
354
+ - `multi_dataset_batch_sampler`: proportional
355
+
356
+ </details>
357
+
358
+ ### Training Logs
359
+ <details><summary>Click to expand</summary>
360
+
361
+ | Epoch | Step | Training Loss |
362
+ |:------:|:-----:|:-------------:|
363
+ | 0.2189 | 2600 | 0.2615 |
364
+ | 0.2273 | 2700 | 0.2518 |
365
+ | 0.2358 | 2800 | 0.2785 |
366
+ | 0.2442 | 2900 | 0.2541 |
367
+ | 0.2526 | 3000 | 0.266 |
368
+ | 0.2610 | 3100 | 0.2671 |
369
+ | 0.2695 | 3200 | 0.2895 |
370
+ | 0.2779 | 3300 | 0.2658 |
371
+ | 0.2863 | 3400 | 0.2622 |
372
+ | 0.2947 | 3500 | 0.2607 |
373
+ | 0.3031 | 3600 | 0.2883 |
374
+ | 0.3116 | 3700 | 0.2747 |
375
+ | 0.3200 | 3800 | 0.2525 |
376
+ | 0.3284 | 3900 | 0.2471 |
377
+ | 0.3368 | 4000 | 0.2564 |
378
+ | 0.3452 | 4100 | 0.2541 |
379
+ | 0.3537 | 4200 | 0.2421 |
380
+ | 0.3621 | 4300 | 0.2559 |
381
+ | 0.3705 | 4400 | 0.2562 |
382
+ | 0.3789 | 4500 | 0.2548 |
383
+ | 0.3873 | 4600 | 0.2504 |
384
+ | 0.3958 | 4700 | 0.2585 |
385
+ | 0.4042 | 4800 | 0.2368 |
386
+ | 0.4126 | 4900 | 0.2298 |
387
+ | 0.4210 | 5000 | 0.2277 |
388
+ | 0.4294 | 5100 | 0.2809 |
389
+ | 0.4379 | 5200 | 0.2945 |
390
+ | 0.4463 | 5300 | 0.6972 |
391
+ | 0.4547 | 5400 | 1.6206 |
392
+ | 0.4631 | 5500 | 1.48 |
393
+ | 0.4715 | 5600 | 1.3816 |
394
+ | 0.4800 | 5700 | 1.3296 |
395
+ | 0.4884 | 5800 | 1.2737 |
396
+ | 0.4968 | 5900 | 1.188 |
397
+ | 0.5052 | 6000 | 1.1852 |
398
+ | 0.5136 | 6100 | 1.1271 |
399
+ | 0.5221 | 6200 | 1.1654 |
400
+ | 0.5305 | 6300 | 1.1028 |
401
+ | 0.5389 | 6400 | 1.0713 |
402
+ | 0.5473 | 6500 | 1.0654 |
403
+ | 0.5557 | 6600 | 1.0779 |
404
+ | 0.5642 | 6700 | 1.0448 |
405
+ | 0.5726 | 6800 | 1.022 |
406
+ | 0.5810 | 6900 | 1.0037 |
407
+ | 0.5894 | 7000 | 1.026 |
408
+ | 0.5978 | 7100 | 0.9852 |
409
+ | 0.6063 | 7200 | 0.9583 |
410
+ | 0.6147 | 7300 | 0.974 |
411
+ | 0.6231 | 7400 | 0.9357 |
412
+ | 0.6315 | 7500 | 0.9426 |
413
+ | 0.6399 | 7600 | 0.9001 |
414
+ | 0.6484 | 7700 | 0.8875 |
415
+ | 0.6568 | 7800 | 0.8552 |
416
+ | 0.6652 | 7900 | 0.9011 |
417
+ | 0.6736 | 8000 | 0.8692 |
418
+ | 0.6820 | 8100 | 0.8637 |
419
+ | 0.6905 | 8200 | 0.8292 |
420
+ | 0.6989 | 8300 | 0.8226 |
421
+ | 0.7073 | 8400 | 0.8066 |
422
+ | 0.7157 | 8500 | 0.8495 |
423
+ | 0.7241 | 8600 | 0.794 |
424
+ | 0.7326 | 8700 | 0.7676 |
425
+ | 0.7410 | 8800 | 0.7671 |
426
+ | 0.7494 | 8900 | 0.769 |
427
+ | 0.7578 | 9000 | 0.7808 |
428
+ | 0.7663 | 9100 | 0.7439 |
429
+ | 0.7747 | 9200 | 0.7394 |
430
+ | 0.7831 | 9300 | 0.7662 |
431
+ | 0.7915 | 9400 | 0.7472 |
432
+ | 0.7999 | 9500 | 0.7592 |
433
+ | 0.8084 | 9600 | 0.7599 |
434
+ | 0.8168 | 9700 | 0.7397 |
435
+ | 0.8252 | 9800 | 0.1707 |
436
+ | 0.8336 | 9900 | 0.036 |
437
+ | 0.8420 | 10000 | 0.0272 |
438
+ | 0.8505 | 10100 | 0.0189 |
439
+ | 0.8589 | 10200 | 0.0139 |
440
+ | 0.8673 | 10300 | 0.0155 |
441
+ | 0.8757 | 10400 | 0.0145 |
442
+ | 0.8841 | 10500 | 0.0124 |
443
+ | 0.8926 | 10600 | 0.0098 |
444
+ | 0.9010 | 10700 | 0.0091 |
445
+ | 0.9094 | 10800 | 0.01 |
446
+ | 0.9178 | 10900 | 0.1028 |
447
+ | 0.9262 | 11000 | 0.1921 |
448
+ | 0.9347 | 11100 | 0.1521 |
449
+ | 0.9431 | 11200 | 0.1336 |
450
+ | 0.9515 | 11300 | 0.1238 |
451
+ | 0.9599 | 11400 | 0.1065 |
452
+ | 0.9683 | 11500 | 0.0955 |
453
+ | 0.9768 | 11600 | 0.0944 |
454
+ | 0.9852 | 11700 | 0.0849 |
455
+ | 0.9936 | 11800 | 0.0712 |
456
+ | 1.0020 | 11900 | 0.3673 |
457
+ | 1.0104 | 12000 | 0.4508 |
458
+ | 1.0189 | 12100 | 0.3693 |
459
+ | 1.0273 | 12200 | 0.3297 |
460
+ | 1.0357 | 12300 | 0.3452 |
461
+ | 1.0441 | 12400 | 0.3062 |
462
+ | 1.0525 | 12500 | 0.2824 |
463
+ | 1.0610 | 12600 | 0.2909 |
464
+ | 1.0694 | 12700 | 0.2688 |
465
+ | 1.0778 | 12800 | 0.261 |
466
+ | 1.0862 | 12900 | 0.2616 |
467
+ | 1.0946 | 13000 | 0.2496 |
468
+ | 1.1031 | 13100 | 0.2415 |
469
+ | 1.1115 | 13200 | 0.2469 |
470
+ | 1.1199 | 13300 | 0.2444 |
471
+ | 1.1283 | 13400 | 0.2489 |
472
+ | 1.1367 | 13500 | 0.2338 |
473
+ | 1.1452 | 13600 | 0.2185 |
474
+ | 1.1536 | 13700 | 0.2288 |
475
+ | 1.1620 | 13800 | 0.2032 |
476
+ | 1.1704 | 13900 | 0.2005 |
477
+ | 1.1788 | 14000 | 0.2053 |
478
+ | 1.1873 | 14100 | 0.2042 |
479
+ | 1.1957 | 14200 | 0.1877 |
480
+ | 1.2041 | 14300 | 0.1711 |
481
+ | 1.2125 | 14400 | 0.1973 |
482
+ | 1.2209 | 14500 | 0.1624 |
483
+ | 1.2294 | 14600 | 0.1646 |
484
+ | 1.2378 | 14700 | 0.1702 |
485
+ | 1.2462 | 14800 | 0.166 |
486
+ | 1.2546 | 14900 | 0.1689 |
487
+ | 1.2631 | 15000 | 0.1747 |
488
+ | 1.2715 | 15100 | 0.1755 |
489
+ | 1.2799 | 15200 | 0.1607 |
490
+ | 1.2883 | 15300 | 0.1462 |
491
+ | 1.2967 | 15400 | 0.1475 |
492
+ | 1.3052 | 15500 | 0.1587 |
493
+ | 1.3136 | 15600 | 0.1506 |
494
+ | 1.3220 | 15700 | 0.1467 |
495
+ | 1.3304 | 15800 | 0.1277 |
496
+ | 1.3388 | 15900 | 0.1305 |
497
+ | 1.3473 | 16000 | 0.1292 |
498
+ | 1.3557 | 16100 | 0.1286 |
499
+ | 1.3641 | 16200 | 0.1412 |
500
+ | 1.3725 | 16300 | 0.1284 |
501
+ | 1.3809 | 16400 | 0.1278 |
502
+ | 1.3894 | 16500 | 0.1227 |
503
+ | 1.3978 | 16600 | 0.1261 |
504
+ | 1.4062 | 16700 | 0.1171 |
505
+ | 1.4146 | 16800 | 0.1342 |
506
+ | 1.4230 | 16900 | 0.1431 |
507
+ | 1.4315 | 17000 | 0.1197 |
508
+ | 1.4399 | 17100 | 0.13 |
509
+ | 1.4483 | 17200 | 0.6417 |
510
+ | 1.4567 | 17300 | 1.0493 |
511
+ | 1.4651 | 17400 | 0.9416 |
512
+ | 1.4736 | 17500 | 0.9058 |
513
+ | 1.4820 | 17600 | 0.8439 |
514
+ | 1.4904 | 17700 | 0.8125 |
515
+ | 1.4988 | 17800 | 0.7498 |
516
+ | 1.5072 | 17900 | 0.6975 |
517
+ | 1.5157 | 18000 | 0.6554 |
518
+ | 1.5241 | 18100 | 0.6563 |
519
+ | 1.5325 | 18200 | 0.6458 |
520
+ | 1.5409 | 18300 | 0.6086 |
521
+ | 1.5493 | 18400 | 0.6098 |
522
+ | 1.5578 | 18500 | 0.5725 |
523
+ | 1.5662 | 18600 | 0.5794 |
524
+ | 1.5746 | 18700 | 0.5525 |
525
+ | 1.5830 | 18800 | 0.5345 |
526
+ | 1.5914 | 18900 | 0.5765 |
527
+ | 1.5999 | 19000 | 0.5097 |
528
+ | 1.6083 | 19100 | 0.5681 |
529
+ | 1.6167 | 19200 | 0.5473 |
530
+ | 1.6251 | 19300 | 0.5206 |
531
+ | 1.6335 | 19400 | 0.5175 |
532
+ | 1.6420 | 19500 | 0.4796 |
533
+ | 1.6504 | 19600 | 0.4866 |
534
+ | 1.6588 | 19700 | 0.4706 |
535
+ | 1.6672 | 19800 | 0.5092 |
536
+ | 1.6756 | 19900 | 0.4799 |
537
+ | 1.6841 | 20000 | 0.4548 |
538
+ | 1.6925 | 20100 | 0.4639 |
539
+ | 1.7009 | 20200 | 0.4297 |
540
+ | 1.7093 | 20300 | 0.4382 |
541
+ | 1.7178 | 20400 | 0.4428 |
542
+ | 1.7262 | 20500 | 0.4308 |
543
+ | 1.7346 | 20600 | 0.4038 |
544
+ | 1.7430 | 20700 | 0.3842 |
545
+ | 1.7514 | 20800 | 0.4227 |
546
+ | 1.7599 | 20900 | 0.387 |
547
+ | 1.7683 | 21000 | 0.3729 |
548
+ | 1.7767 | 21100 | 0.3768 |
549
+ | 1.7851 | 21200 | 0.3984 |
550
+ | 1.7935 | 21300 | 0.4128 |
551
+ | 1.8020 | 21400 | 0.3995 |
552
+ | 1.8104 | 21500 | 0.416 |
553
+ | 1.8188 | 21600 | 0.3488 |
554
+ | 1.8272 | 21700 | 0.0116 |
555
+ | 1.8356 | 21800 | 0.0066 |
556
+ | 1.8441 | 21900 | 0.0051 |
557
+ | 1.8525 | 22000 | 0.0064 |
558
+ | 1.8609 | 22100 | 0.0038 |
559
+ | 1.8693 | 22200 | 0.004 |
560
+ | 1.8777 | 22300 | 0.003 |
561
+ | 1.8862 | 22400 | 0.0023 |
562
+ | 1.8946 | 22500 | 0.0026 |
563
+ | 1.9030 | 22600 | 0.0021 |
564
+ | 1.9114 | 22700 | 0.0021 |
565
+ | 1.9198 | 22800 | 0.0317 |
566
+ | 1.9283 | 22900 | 0.038 |
567
+ | 1.9367 | 23000 | 0.0272 |
568
+ | 1.9451 | 23100 | 0.0282 |
569
+ | 1.9535 | 23200 | 0.0218 |
570
+ | 1.9619 | 23300 | 0.0194 |
571
+ | 1.9704 | 23400 | 0.0192 |
572
+ | 1.9788 | 23500 | 0.0197 |
573
+ | 1.9872 | 23600 | 0.0136 |
574
+ | 1.9956 | 23700 | 0.0139 |
575
+ | 2.0040 | 23800 | 0.1831 |
576
+ | 2.0125 | 23900 | 0.1384 |
577
+ | 2.0209 | 24000 | 0.1157 |
578
+ | 2.0293 | 24100 | 0.104 |
579
+ | 2.0377 | 24200 | 0.1123 |
580
+ | 2.0461 | 24300 | 0.098 |
581
+ | 2.0546 | 24400 | 0.0985 |
582
+ | 2.0630 | 24500 | 0.099 |
583
+ | 2.0714 | 24600 | 0.1033 |
584
+ | 2.0798 | 24700 | 0.0897 |
585
+ | 2.0882 | 24800 | 0.0939 |
586
+ | 2.0967 | 24900 | 0.0846 |
587
+ | 2.1051 | 25000 | 0.0913 |
588
+ | 2.1135 | 25100 | 0.0892 |
589
+ | 2.1219 | 25200 | 0.0914 |
590
+ | 2.1303 | 25300 | 0.1019 |
591
+ | 2.1388 | 25400 | 0.0858 |
592
+ | 2.1472 | 25500 | 0.0886 |
593
+ | 2.1556 | 25600 | 0.0875 |
594
+ | 2.1640 | 25700 | 0.0828 |
595
+ | 2.1724 | 25800 | 0.0769 |
596
+ | 2.1809 | 25900 | 0.0768 |
597
+ | 2.1893 | 26000 | 0.0769 |
598
+ | 2.1977 | 26100 | 0.0744 |
599
+ | 2.2061 | 26200 | 0.0675 |
600
+ | 2.2146 | 26300 | 0.071 |
601
+ | 2.2230 | 26400 | 0.0696 |
602
+ | 2.2314 | 26500 | 0.0595 |
603
+ | 2.2398 | 26600 | 0.0705 |
604
+ | 2.2482 | 26700 | 0.0641 |
605
+ | 2.2567 | 26800 | 0.0718 |
606
+ | 2.2651 | 26900 | 0.0766 |
607
+ | 2.2735 | 27000 | 0.0743 |
608
+ | 2.2819 | 27100 | 0.0591 |
609
+ | 2.2903 | 27200 | 0.055 |
610
+ | 2.2988 | 27300 | 0.0642 |
611
+ | 2.3072 | 27400 | 0.0624 |
612
+ | 2.3156 | 27500 | 0.0568 |
613
+ | 2.3240 | 27600 | 0.0582 |
614
+ | 2.3324 | 27700 | 0.0477 |
615
+ | 2.3409 | 27800 | 0.0513 |
616
+ | 2.3493 | 27900 | 0.0486 |
617
+ | 2.3577 | 28000 | 0.0485 |
618
+ | 2.3661 | 28100 | 0.0571 |
619
+ | 2.3745 | 28200 | 0.0575 |
620
+ | 2.3830 | 28300 | 0.0503 |
621
+ | 2.3914 | 28400 | 0.0482 |
622
+ | 2.3998 | 28500 | 0.0578 |
623
+ | 2.4082 | 28600 | 0.0496 |
624
+ | 2.4166 | 28700 | 0.0545 |
625
+ | 2.4251 | 28800 | 0.054 |
626
+ | 2.4335 | 28900 | 0.0529 |
627
+ | 2.4419 | 29000 | 0.0604 |
628
+ | 2.4503 | 29100 | 0.462 |
629
+ | 2.4587 | 29200 | 0.5095 |
630
+ | 2.4672 | 29300 | 0.4603 |
631
+ | 2.4756 | 29400 | 0.4584 |
632
+ | 2.4840 | 29500 | 0.3933 |
633
+ | 2.4924 | 29600 | 0.3533 |
634
+ | 2.5008 | 29700 | 0.2919 |
635
+ | 2.5093 | 29800 | 0.2907 |
636
+ | 2.5177 | 29900 | 0.3201 |
637
+ | 2.5261 | 30000 | 0.2896 |
638
+ | 2.5345 | 30100 | 0.2852 |
639
+ | 2.5429 | 30200 | 0.2182 |
640
+ | 2.5514 | 30300 | 0.2423 |
641
+ | 2.5598 | 30400 | 0.2496 |
642
+ | 2.5682 | 30500 | 0.2303 |
643
+ | 2.5766 | 30600 | 0.2065 |
644
+ | 2.5850 | 30700 | 0.2031 |
645
+ | 2.5935 | 30800 | 0.2384 |
646
+ | 2.6019 | 30900 | 0.2441 |
647
+ | 2.6103 | 31000 | 0.2914 |
648
+ | 2.6187 | 31100 | 0.2695 |
649
+ | 2.6271 | 31200 | 0.2366 |
650
+ | 2.6356 | 31300 | 0.2007 |
651
+ | 2.6440 | 31400 | 0.2088 |
652
+ | 2.6524 | 31500 | 0.1975 |
653
+ | 2.6608 | 31600 | 0.2162 |
654
+ | 2.6692 | 31700 | 0.2201 |
655
+ | 2.6777 | 31800 | 0.1907 |
656
+ | 2.6861 | 31900 | 0.1675 |
657
+ | 2.6945 | 32000 | 0.1866 |
658
+
659
+ </details>
660
+
661
+ ### Framework Versions
662
+ - Python: 3.10.12
663
+ - Sentence Transformers: 3.3.1
664
+ - Transformers: 4.51.3
665
+ - PyTorch: 2.6.0+cu124
666
+ - Accelerate: 1.2.1
667
+ - Datasets: 3.5.0
668
+ - Tokenizers: 0.21.1
669
+
670
+ ## Citation
671
+
672
+ ### BibTeX
673
+
674
+ #### Sentence Transformers
675
+ ```bibtex
676
+ @inproceedings{reimers-2019-sentence-bert,
677
+ title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
678
+ author = "Reimers, Nils and Gurevych, Iryna",
679
+ booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
680
+ month = "11",
681
+ year = "2019",
682
+ publisher = "Association for Computational Linguistics",
683
+ url = "https://arxiv.org/abs/1908.10084",
684
+ }
685
+ ```
686
+
687
+ #### MatryoshkaLoss
688
+ ```bibtex
689
+ @misc{kusupati2024matryoshka,
690
+ title={Matryoshka Representation Learning},
691
+ author={Aditya Kusupati and Gantavya Bhatt and Aniket Rege and Matthew Wallingford and Aditya Sinha and Vivek Ramanujan and William Howard-Snyder and Kaifeng Chen and Sham Kakade and Prateek Jain and Ali Farhadi},
692
+ year={2024},
693
+ eprint={2205.13147},
694
+ archivePrefix={arXiv},
695
+ primaryClass={cs.LG}
696
+ }
697
+ ```
698
+
699
+ #### MultipleNegativesRankingLoss
700
+ ```bibtex
701
+ @misc{henderson2017efficient,
702
+ title={Efficient Natural Language Response Suggestion for Smart Reply},
703
+ author={Matthew Henderson and Rami Al-Rfou and Brian Strope and Yun-hsuan Sung and Laszlo Lukacs and Ruiqi Guo and Sanjiv Kumar and Balint Miklos and Ray Kurzweil},
704
+ year={2017},
705
+ eprint={1705.00652},
706
+ archivePrefix={arXiv},
707
+ primaryClass={cs.CL}
708
+ }
709
+ ```
710
+
711
+ <!--
712
+ ## Glossary
713
+
714
+ *Clearly define terms in order to be accessible across audiences.*
715
+ -->
716
+
717
+ <!--
718
+ ## Model Card Authors
719
+
720
+ *Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
721
+ -->
722
+
723
+ <!--
724
+ ## Model Card Contact
725
+
726
+ *Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
727
+ -->
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
+ }
config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3Model"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 151643,
8
+ "eos_token_id": 151643,
9
+ "head_dim": 128,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 1024,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 3072,
14
+ "max_position_embeddings": 32768,
15
+ "max_window_layers": 28,
16
+ "model_type": "qwen3",
17
+ "num_attention_heads": 16,
18
+ "num_hidden_layers": 28,
19
+ "num_key_value_heads": 8,
20
+ "rms_norm_eps": 1e-06,
21
+ "rope_scaling": null,
22
+ "rope_theta": 1000000,
23
+ "sliding_window": null,
24
+ "tie_word_embeddings": true,
25
+ "torch_dtype": "float32",
26
+ "transformers_version": "4.51.3",
27
+ "use_cache": true,
28
+ "use_sliding_window": false,
29
+ "vocab_size": 151669
30
+ }
config_sentence_transformers.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "__version__": {
3
+ "sentence_transformers": "3.3.1",
4
+ "transformers": "4.51.3",
5
+ "pytorch": "2.6.0+cu124"
6
+ },
7
+ "prompts": {},
8
+ "default_prompt_name": null,
9
+ "similarity_fn_name": "cosine"
10
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b3732cd3499a3875e220a7179b5f25b452784d230b4df7dc3071189c099ea38b
3
+ size 2383139480
modules.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "idx": 0,
4
+ "name": "0",
5
+ "path": "",
6
+ "type": "sentence_transformers.models.Transformer"
7
+ },
8
+ {
9
+ "idx": 1,
10
+ "name": "1",
11
+ "path": "1_Pooling",
12
+ "type": "sentence_transformers.models.Pooling"
13
+ }
14
+ ]
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:930a1cb040c853417c8b2ddffcf7c315a70f9f1a6f0956bdf7642e1ba7baa25a
3
+ size 4766479998
rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37da082521a1854fd9890918ac1e1cf29a15c5bd719056766a324764d00de274
3
+ size 15408
rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a29b89cc0f5e10f02dddf0f01c67d3f1ac4bc6bbf614c36024bb2c607942af7b
3
+ size 15472
rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bdd02267176cf89f336a32467643d9c67438cf9792e42d54729acf0c1cbec8b2
3
+ size 15472
rng_state_3.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bdc51c626acedd92b06c746fe3672c0ce93a72abc1225229611acc757c810e38
3
+ size 15472
rng_state_4.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a547306496b237611bfa88571926633258d4868354d036a0c5b5fe72e82f4fc
3
+ size 15472
rng_state_5.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2773c2da36842cf52624593eaf2bfeef58662222f9fe3c334d1aed14f0a94d7
3
+ size 15472
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ba0597be8406d3a44c603292e3feb3d74d1543531c3b0f91011c4d5ade1e249
3
+ size 1064
sentence_bert_config.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "max_seq_length": 32768,
3
+ "do_lower_case": false
4
+ }
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:aed98cff73772352c260a48579f3b212cb2b06ce0553446799ebf0b5465b0673
3
+ size 11422922
tokenizer_config.json ADDED
@@ -0,0 +1,240 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0].role == 'system' %}\n {{- messages[0].content + '\\n\\n' }}\n {%- endif %}\n {{- \"# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\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\" }}\n{%- else %}\n {%- if messages[0].role == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0].content + '<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n {%- set index = (messages|length - 1) - loop.index0 %}\n {%- if ns.multi_step_tool and message.role == \"user\" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}\n {%- set ns.multi_step_tool = false %}\n {%- set ns.last_query_index = index %}\n {%- endif %}\n{%- endfor %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {%- set content = message.content %}\n {%- set reasoning_content = '' %}\n {%- if message.reasoning_content is defined and message.reasoning_content is not none %}\n {%- set reasoning_content = message.reasoning_content %}\n {%- else %}\n {%- if '</think>' in message.content %}\n {%- set content = message.content.split('</think>')[-1].lstrip('\\n') %}\n {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n {%- endif %}\n {%- endif %}\n {%- if loop.index0 > ns.last_query_index %}\n {%- if loop.last or (not loop.last and reasoning_content) %}\n {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content.strip('\\n') + '\\n</think>\\n\\n' + content.lstrip('\\n') }}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- if message.tool_calls %}\n {%- for tool_call in message.tool_calls %}\n {%- if (loop.first and content) or (not loop.first) %}\n {{- '\\n' }}\n {%- endif %}\n {%- if tool_call.function %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {%- if tool_call.arguments is string %}\n {{- tool_call.arguments }}\n {%- else %}\n {{- tool_call.arguments | tojson }}\n {%- endif %}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n {%- if enable_thinking is defined and enable_thinking is false %}\n {{- '<think>\\n\\n</think>\\n\\n' }}\n {%- endif %}\n{%- endif %}",
231
+ "clean_up_tokenization_spaces": false,
232
+ "eos_token": "<|im_end|>",
233
+ "errors": "replace",
234
+ "extra_special_tokens": {},
235
+ "model_max_length": 131072,
236
+ "pad_token": "<|endoftext|>",
237
+ "split_special_tokens": false,
238
+ "tokenizer_class": "Qwen2Tokenizer",
239
+ "unk_token": null
240
+ }
trainer_state.json ADDED
@@ -0,0 +1,2274 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 2.694509936005389,
6
+ "eval_steps": 500,
7
+ "global_step": 32000,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.016840687100033683,
14
+ "grad_norm": 23.914043426513672,
15
+ "learning_rate": 2.777777777777778e-06,
16
+ "loss": 2.6825,
17
+ "step": 100
18
+ },
19
+ {
20
+ "epoch": 0.033681374200067365,
21
+ "grad_norm": 19.596776962280273,
22
+ "learning_rate": 5.583613916947251e-06,
23
+ "loss": 1.0725,
24
+ "step": 200
25
+ },
26
+ {
27
+ "epoch": 0.05052206130010104,
28
+ "grad_norm": 15.781028747558594,
29
+ "learning_rate": 8.389450056116724e-06,
30
+ "loss": 0.8306,
31
+ "step": 300
32
+ },
33
+ {
34
+ "epoch": 0.06736274840013473,
35
+ "grad_norm": 15.894832611083984,
36
+ "learning_rate": 1.1195286195286197e-05,
37
+ "loss": 0.7221,
38
+ "step": 400
39
+ },
40
+ {
41
+ "epoch": 0.08420343550016841,
42
+ "grad_norm": 14.838741302490234,
43
+ "learning_rate": 1.4001122334455668e-05,
44
+ "loss": 0.6888,
45
+ "step": 500
46
+ },
47
+ {
48
+ "epoch": 0.10104412260020208,
49
+ "grad_norm": 12.208050727844238,
50
+ "learning_rate": 1.6806958473625142e-05,
51
+ "loss": 0.6245,
52
+ "step": 600
53
+ },
54
+ {
55
+ "epoch": 0.11788480970023577,
56
+ "grad_norm": 11.734648704528809,
57
+ "learning_rate": 1.9612794612794612e-05,
58
+ "loss": 0.6413,
59
+ "step": 700
60
+ },
61
+ {
62
+ "epoch": 0.13472549680026946,
63
+ "grad_norm": 11.392744064331055,
64
+ "learning_rate": 2.2418630751964088e-05,
65
+ "loss": 0.6088,
66
+ "step": 800
67
+ },
68
+ {
69
+ "epoch": 0.15156618390030313,
70
+ "grad_norm": 11.298259735107422,
71
+ "learning_rate": 2.5224466891133558e-05,
72
+ "loss": 0.5892,
73
+ "step": 900
74
+ },
75
+ {
76
+ "epoch": 0.16840687100033683,
77
+ "grad_norm": 10.205204010009766,
78
+ "learning_rate": 2.803030303030303e-05,
79
+ "loss": 0.5764,
80
+ "step": 1000
81
+ },
82
+ {
83
+ "epoch": 0.1852475581003705,
84
+ "grad_norm": 9.070446968078613,
85
+ "learning_rate": 3.08361391694725e-05,
86
+ "loss": 0.5736,
87
+ "step": 1100
88
+ },
89
+ {
90
+ "epoch": 0.20208824520040417,
91
+ "grad_norm": 11.171720504760742,
92
+ "learning_rate": 3.364197530864198e-05,
93
+ "loss": 0.5493,
94
+ "step": 1200
95
+ },
96
+ {
97
+ "epoch": 0.21892893230043786,
98
+ "grad_norm": 8.007598876953125,
99
+ "learning_rate": 3.644781144781145e-05,
100
+ "loss": 0.5459,
101
+ "step": 1300
102
+ },
103
+ {
104
+ "epoch": 0.23576961940047153,
105
+ "grad_norm": 8.607964515686035,
106
+ "learning_rate": 3.9253647586980925e-05,
107
+ "loss": 0.543,
108
+ "step": 1400
109
+ },
110
+ {
111
+ "epoch": 0.2526103065005052,
112
+ "grad_norm": 8.324835777282715,
113
+ "learning_rate": 4.2059483726150395e-05,
114
+ "loss": 0.5274,
115
+ "step": 1500
116
+ },
117
+ {
118
+ "epoch": 0.2694509936005389,
119
+ "grad_norm": 7.262979507446289,
120
+ "learning_rate": 4.4865319865319864e-05,
121
+ "loss": 0.5424,
122
+ "step": 1600
123
+ },
124
+ {
125
+ "epoch": 0.2862916807005726,
126
+ "grad_norm": 7.70058012008667,
127
+ "learning_rate": 4.767115600448934e-05,
128
+ "loss": 0.5193,
129
+ "step": 1700
130
+ },
131
+ {
132
+ "epoch": 0.30313236780060626,
133
+ "grad_norm": 9.130758285522461,
134
+ "learning_rate": 4.9946981037924155e-05,
135
+ "loss": 0.5344,
136
+ "step": 1800
137
+ },
138
+ {
139
+ "epoch": 0.31997305490063993,
140
+ "grad_norm": 6.3734354972839355,
141
+ "learning_rate": 4.963510479041916e-05,
142
+ "loss": 0.5133,
143
+ "step": 1900
144
+ },
145
+ {
146
+ "epoch": 0.33681374200067365,
147
+ "grad_norm": 5.812978744506836,
148
+ "learning_rate": 4.9323228542914176e-05,
149
+ "loss": 0.4755,
150
+ "step": 2000
151
+ },
152
+ {
153
+ "epoch": 0.3536544291007073,
154
+ "grad_norm": 7.685583591461182,
155
+ "learning_rate": 4.901135229540918e-05,
156
+ "loss": 0.4735,
157
+ "step": 2100
158
+ },
159
+ {
160
+ "epoch": 0.370495116200741,
161
+ "grad_norm": 5.93942928314209,
162
+ "learning_rate": 4.86994760479042e-05,
163
+ "loss": 0.4876,
164
+ "step": 2200
165
+ },
166
+ {
167
+ "epoch": 0.38733580330077466,
168
+ "grad_norm": 4.325860500335693,
169
+ "learning_rate": 4.8387599800399204e-05,
170
+ "loss": 0.4483,
171
+ "step": 2300
172
+ },
173
+ {
174
+ "epoch": 0.40417649040080833,
175
+ "grad_norm": 5.2169928550720215,
176
+ "learning_rate": 4.807572355289421e-05,
177
+ "loss": 0.4459,
178
+ "step": 2400
179
+ },
180
+ {
181
+ "epoch": 0.42101717750084205,
182
+ "grad_norm": 4.603377342224121,
183
+ "learning_rate": 4.7763847305389225e-05,
184
+ "loss": 0.4133,
185
+ "step": 2500
186
+ },
187
+ {
188
+ "epoch": 0.21892893230043786,
189
+ "grad_norm": 4.210044860839844,
190
+ "learning_rate": 3.647207409486388e-05,
191
+ "loss": 0.2615,
192
+ "step": 2600
193
+ },
194
+ {
195
+ "epoch": 0.2273492758504547,
196
+ "grad_norm": 5.636209964752197,
197
+ "learning_rate": 3.787538591074937e-05,
198
+ "loss": 0.2518,
199
+ "step": 2700
200
+ },
201
+ {
202
+ "epoch": 0.23576961940047153,
203
+ "grad_norm": 4.7418389320373535,
204
+ "learning_rate": 3.927869772663486e-05,
205
+ "loss": 0.2785,
206
+ "step": 2800
207
+ },
208
+ {
209
+ "epoch": 0.2441899629504884,
210
+ "grad_norm": 6.645480632781982,
211
+ "learning_rate": 4.0682009542520346e-05,
212
+ "loss": 0.2541,
213
+ "step": 2900
214
+ },
215
+ {
216
+ "epoch": 0.2526103065005052,
217
+ "grad_norm": 4.639427185058594,
218
+ "learning_rate": 4.2085321358405836e-05,
219
+ "loss": 0.266,
220
+ "step": 3000
221
+ },
222
+ {
223
+ "epoch": 0.26103065005052206,
224
+ "grad_norm": 3.73759388923645,
225
+ "learning_rate": 4.348863317429133e-05,
226
+ "loss": 0.2671,
227
+ "step": 3100
228
+ },
229
+ {
230
+ "epoch": 0.2694509936005389,
231
+ "grad_norm": 7.948583126068115,
232
+ "learning_rate": 4.489194499017682e-05,
233
+ "loss": 0.2895,
234
+ "step": 3200
235
+ },
236
+ {
237
+ "epoch": 0.27787133715055573,
238
+ "grad_norm": 27.404747009277344,
239
+ "learning_rate": 4.629525680606231e-05,
240
+ "loss": 0.2658,
241
+ "step": 3300
242
+ },
243
+ {
244
+ "epoch": 0.2862916807005726,
245
+ "grad_norm": 3.8111979961395264,
246
+ "learning_rate": 4.7698568621947796e-05,
247
+ "loss": 0.2622,
248
+ "step": 3400
249
+ },
250
+ {
251
+ "epoch": 0.2947120242505894,
252
+ "grad_norm": 6.846595287322998,
253
+ "learning_rate": 4.9101880437833286e-05,
254
+ "loss": 0.2607,
255
+ "step": 3500
256
+ },
257
+ {
258
+ "epoch": 0.30313236780060626,
259
+ "grad_norm": 4.529717922210693,
260
+ "learning_rate": 4.994386402619679e-05,
261
+ "loss": 0.2883,
262
+ "step": 3600
263
+ },
264
+ {
265
+ "epoch": 0.3115527113506231,
266
+ "grad_norm": 6.5379838943481445,
267
+ "learning_rate": 4.9787930765632316e-05,
268
+ "loss": 0.2747,
269
+ "step": 3700
270
+ },
271
+ {
272
+ "epoch": 0.31997305490063993,
273
+ "grad_norm": 4.162957668304443,
274
+ "learning_rate": 4.963199750506784e-05,
275
+ "loss": 0.2525,
276
+ "step": 3800
277
+ },
278
+ {
279
+ "epoch": 0.3283933984506568,
280
+ "grad_norm": 5.669950485229492,
281
+ "learning_rate": 4.947606424450336e-05,
282
+ "loss": 0.2471,
283
+ "step": 3900
284
+ },
285
+ {
286
+ "epoch": 0.33681374200067365,
287
+ "grad_norm": 6.552733898162842,
288
+ "learning_rate": 4.932013098393888e-05,
289
+ "loss": 0.2564,
290
+ "step": 4000
291
+ },
292
+ {
293
+ "epoch": 0.34523408555069046,
294
+ "grad_norm": 5.492654800415039,
295
+ "learning_rate": 4.91641977233744e-05,
296
+ "loss": 0.2541,
297
+ "step": 4100
298
+ },
299
+ {
300
+ "epoch": 0.3536544291007073,
301
+ "grad_norm": 6.248386859893799,
302
+ "learning_rate": 4.900826446280992e-05,
303
+ "loss": 0.2421,
304
+ "step": 4200
305
+ },
306
+ {
307
+ "epoch": 0.36207477265072413,
308
+ "grad_norm": 7.152673721313477,
309
+ "learning_rate": 4.8852331202245445e-05,
310
+ "loss": 0.2559,
311
+ "step": 4300
312
+ },
313
+ {
314
+ "epoch": 0.370495116200741,
315
+ "grad_norm": 7.939176082611084,
316
+ "learning_rate": 4.869639794168096e-05,
317
+ "loss": 0.2562,
318
+ "step": 4400
319
+ },
320
+ {
321
+ "epoch": 0.37891545975075785,
322
+ "grad_norm": 6.023073673248291,
323
+ "learning_rate": 4.854046468111648e-05,
324
+ "loss": 0.2548,
325
+ "step": 4500
326
+ },
327
+ {
328
+ "epoch": 0.38733580330077466,
329
+ "grad_norm": 6.619602680206299,
330
+ "learning_rate": 4.8384531420552e-05,
331
+ "loss": 0.2504,
332
+ "step": 4600
333
+ },
334
+ {
335
+ "epoch": 0.3957561468507915,
336
+ "grad_norm": 4.903266906738281,
337
+ "learning_rate": 4.8228598159987524e-05,
338
+ "loss": 0.2585,
339
+ "step": 4700
340
+ },
341
+ {
342
+ "epoch": 0.40417649040080833,
343
+ "grad_norm": 4.036454200744629,
344
+ "learning_rate": 4.8072664899423046e-05,
345
+ "loss": 0.2368,
346
+ "step": 4800
347
+ },
348
+ {
349
+ "epoch": 0.4125968339508252,
350
+ "grad_norm": 3.432321310043335,
351
+ "learning_rate": 4.791673163885857e-05,
352
+ "loss": 0.2298,
353
+ "step": 4900
354
+ },
355
+ {
356
+ "epoch": 0.42101717750084205,
357
+ "grad_norm": 4.507967472076416,
358
+ "learning_rate": 4.776079837829409e-05,
359
+ "loss": 0.2277,
360
+ "step": 5000
361
+ },
362
+ {
363
+ "epoch": 0.42943752105085886,
364
+ "grad_norm": 4.154341697692871,
365
+ "learning_rate": 4.760486511772961e-05,
366
+ "loss": 0.2809,
367
+ "step": 5100
368
+ },
369
+ {
370
+ "epoch": 0.4378578646008757,
371
+ "grad_norm": 4.294288158416748,
372
+ "learning_rate": 4.744893185716513e-05,
373
+ "loss": 0.2945,
374
+ "step": 5200
375
+ },
376
+ {
377
+ "epoch": 0.44627820815089253,
378
+ "grad_norm": 13.444978713989258,
379
+ "learning_rate": 4.729299859660066e-05,
380
+ "loss": 0.6972,
381
+ "step": 5300
382
+ },
383
+ {
384
+ "epoch": 0.4546985517009094,
385
+ "grad_norm": 13.236030578613281,
386
+ "learning_rate": 4.713706533603618e-05,
387
+ "loss": 1.6206,
388
+ "step": 5400
389
+ },
390
+ {
391
+ "epoch": 0.46311889525092625,
392
+ "grad_norm": 9.054878234863281,
393
+ "learning_rate": 4.6981132075471704e-05,
394
+ "loss": 1.48,
395
+ "step": 5500
396
+ },
397
+ {
398
+ "epoch": 0.47153923880094306,
399
+ "grad_norm": 9.235391616821289,
400
+ "learning_rate": 4.6825198814907225e-05,
401
+ "loss": 1.3816,
402
+ "step": 5600
403
+ },
404
+ {
405
+ "epoch": 0.4799595823509599,
406
+ "grad_norm": 9.566539764404297,
407
+ "learning_rate": 4.666926555434275e-05,
408
+ "loss": 1.3296,
409
+ "step": 5700
410
+ },
411
+ {
412
+ "epoch": 0.4883799259009768,
413
+ "grad_norm": 10.539976119995117,
414
+ "learning_rate": 4.651333229377827e-05,
415
+ "loss": 1.2737,
416
+ "step": 5800
417
+ },
418
+ {
419
+ "epoch": 0.4968002694509936,
420
+ "grad_norm": 10.859559059143066,
421
+ "learning_rate": 4.635739903321379e-05,
422
+ "loss": 1.188,
423
+ "step": 5900
424
+ },
425
+ {
426
+ "epoch": 0.5052206130010104,
427
+ "grad_norm": 9.153464317321777,
428
+ "learning_rate": 4.620146577264931e-05,
429
+ "loss": 1.1852,
430
+ "step": 6000
431
+ },
432
+ {
433
+ "epoch": 0.5136409565510273,
434
+ "grad_norm": 11.076135635375977,
435
+ "learning_rate": 4.604553251208483e-05,
436
+ "loss": 1.1271,
437
+ "step": 6100
438
+ },
439
+ {
440
+ "epoch": 0.5220613001010441,
441
+ "grad_norm": 11.092999458312988,
442
+ "learning_rate": 4.588959925152035e-05,
443
+ "loss": 1.1654,
444
+ "step": 6200
445
+ },
446
+ {
447
+ "epoch": 0.530481643651061,
448
+ "grad_norm": 9.680800437927246,
449
+ "learning_rate": 4.573366599095587e-05,
450
+ "loss": 1.1028,
451
+ "step": 6300
452
+ },
453
+ {
454
+ "epoch": 0.5389019872010778,
455
+ "grad_norm": 7.664565086364746,
456
+ "learning_rate": 4.557773273039139e-05,
457
+ "loss": 1.0713,
458
+ "step": 6400
459
+ },
460
+ {
461
+ "epoch": 0.5473223307510946,
462
+ "grad_norm": 8.164676666259766,
463
+ "learning_rate": 4.542179946982691e-05,
464
+ "loss": 1.0654,
465
+ "step": 6500
466
+ },
467
+ {
468
+ "epoch": 0.5557426743011115,
469
+ "grad_norm": 7.794740676879883,
470
+ "learning_rate": 4.5265866209262434e-05,
471
+ "loss": 1.0779,
472
+ "step": 6600
473
+ },
474
+ {
475
+ "epoch": 0.5641630178511283,
476
+ "grad_norm": 9.8069486618042,
477
+ "learning_rate": 4.5109932948697956e-05,
478
+ "loss": 1.0448,
479
+ "step": 6700
480
+ },
481
+ {
482
+ "epoch": 0.5725833614011452,
483
+ "grad_norm": 8.124543190002441,
484
+ "learning_rate": 4.495399968813348e-05,
485
+ "loss": 1.022,
486
+ "step": 6800
487
+ },
488
+ {
489
+ "epoch": 0.581003704951162,
490
+ "grad_norm": 9.155059814453125,
491
+ "learning_rate": 4.4798066427569005e-05,
492
+ "loss": 1.0037,
493
+ "step": 6900
494
+ },
495
+ {
496
+ "epoch": 0.5894240485011788,
497
+ "grad_norm": 8.151762962341309,
498
+ "learning_rate": 4.464213316700453e-05,
499
+ "loss": 1.026,
500
+ "step": 7000
501
+ },
502
+ {
503
+ "epoch": 0.5978443920511957,
504
+ "grad_norm": 9.232538223266602,
505
+ "learning_rate": 4.448619990644005e-05,
506
+ "loss": 0.9852,
507
+ "step": 7100
508
+ },
509
+ {
510
+ "epoch": 0.6062647356012125,
511
+ "grad_norm": 10.167255401611328,
512
+ "learning_rate": 4.433026664587557e-05,
513
+ "loss": 0.9583,
514
+ "step": 7200
515
+ },
516
+ {
517
+ "epoch": 0.6146850791512294,
518
+ "grad_norm": 8.223834991455078,
519
+ "learning_rate": 4.417433338531109e-05,
520
+ "loss": 0.974,
521
+ "step": 7300
522
+ },
523
+ {
524
+ "epoch": 0.6231054227012462,
525
+ "grad_norm": 7.129863262176514,
526
+ "learning_rate": 4.401840012474661e-05,
527
+ "loss": 0.9357,
528
+ "step": 7400
529
+ },
530
+ {
531
+ "epoch": 0.631525766251263,
532
+ "grad_norm": 9.384492874145508,
533
+ "learning_rate": 4.3862466864182135e-05,
534
+ "loss": 0.9426,
535
+ "step": 7500
536
+ },
537
+ {
538
+ "epoch": 0.6399461098012799,
539
+ "grad_norm": 10.51504135131836,
540
+ "learning_rate": 4.3706533603617656e-05,
541
+ "loss": 0.9001,
542
+ "step": 7600
543
+ },
544
+ {
545
+ "epoch": 0.6483664533512967,
546
+ "grad_norm": 9.259176254272461,
547
+ "learning_rate": 4.355060034305318e-05,
548
+ "loss": 0.8875,
549
+ "step": 7700
550
+ },
551
+ {
552
+ "epoch": 0.6567867969013136,
553
+ "grad_norm": 10.058541297912598,
554
+ "learning_rate": 4.33946670824887e-05,
555
+ "loss": 0.8552,
556
+ "step": 7800
557
+ },
558
+ {
559
+ "epoch": 0.6652071404513304,
560
+ "grad_norm": 8.267607688903809,
561
+ "learning_rate": 4.323873382192422e-05,
562
+ "loss": 0.9011,
563
+ "step": 7900
564
+ },
565
+ {
566
+ "epoch": 0.6736274840013473,
567
+ "grad_norm": 9.002063751220703,
568
+ "learning_rate": 4.3082800561359736e-05,
569
+ "loss": 0.8692,
570
+ "step": 8000
571
+ },
572
+ {
573
+ "epoch": 0.6820478275513641,
574
+ "grad_norm": 11.397157669067383,
575
+ "learning_rate": 4.292686730079526e-05,
576
+ "loss": 0.8637,
577
+ "step": 8100
578
+ },
579
+ {
580
+ "epoch": 0.6904681711013809,
581
+ "grad_norm": 10.458459854125977,
582
+ "learning_rate": 4.277093404023078e-05,
583
+ "loss": 0.8292,
584
+ "step": 8200
585
+ },
586
+ {
587
+ "epoch": 0.6988885146513978,
588
+ "grad_norm": 8.840250968933105,
589
+ "learning_rate": 4.26150007796663e-05,
590
+ "loss": 0.8226,
591
+ "step": 8300
592
+ },
593
+ {
594
+ "epoch": 0.7073088582014146,
595
+ "grad_norm": 7.398085117340088,
596
+ "learning_rate": 4.245906751910182e-05,
597
+ "loss": 0.8066,
598
+ "step": 8400
599
+ },
600
+ {
601
+ "epoch": 0.7157292017514315,
602
+ "grad_norm": 8.141140937805176,
603
+ "learning_rate": 4.2303134258537344e-05,
604
+ "loss": 0.8495,
605
+ "step": 8500
606
+ },
607
+ {
608
+ "epoch": 0.7241495453014483,
609
+ "grad_norm": 8.317313194274902,
610
+ "learning_rate": 4.214720099797287e-05,
611
+ "loss": 0.794,
612
+ "step": 8600
613
+ },
614
+ {
615
+ "epoch": 0.7325698888514651,
616
+ "grad_norm": 8.556983947753906,
617
+ "learning_rate": 4.1991267737408393e-05,
618
+ "loss": 0.7676,
619
+ "step": 8700
620
+ },
621
+ {
622
+ "epoch": 0.740990232401482,
623
+ "grad_norm": 7.237626075744629,
624
+ "learning_rate": 4.1835334476843915e-05,
625
+ "loss": 0.7671,
626
+ "step": 8800
627
+ },
628
+ {
629
+ "epoch": 0.7494105759514988,
630
+ "grad_norm": 11.043583869934082,
631
+ "learning_rate": 4.167940121627944e-05,
632
+ "loss": 0.769,
633
+ "step": 8900
634
+ },
635
+ {
636
+ "epoch": 0.7578309195015157,
637
+ "grad_norm": 6.836021423339844,
638
+ "learning_rate": 4.152346795571496e-05,
639
+ "loss": 0.7808,
640
+ "step": 9000
641
+ },
642
+ {
643
+ "epoch": 0.7662512630515325,
644
+ "grad_norm": 7.930835723876953,
645
+ "learning_rate": 4.136753469515048e-05,
646
+ "loss": 0.7439,
647
+ "step": 9100
648
+ },
649
+ {
650
+ "epoch": 0.7746716066015493,
651
+ "grad_norm": 7.065630912780762,
652
+ "learning_rate": 4.1211601434586e-05,
653
+ "loss": 0.7394,
654
+ "step": 9200
655
+ },
656
+ {
657
+ "epoch": 0.7830919501515662,
658
+ "grad_norm": 12.510068893432617,
659
+ "learning_rate": 4.105566817402152e-05,
660
+ "loss": 0.7662,
661
+ "step": 9300
662
+ },
663
+ {
664
+ "epoch": 0.791512293701583,
665
+ "grad_norm": 5.61587381362915,
666
+ "learning_rate": 4.0899734913457044e-05,
667
+ "loss": 0.7472,
668
+ "step": 9400
669
+ },
670
+ {
671
+ "epoch": 0.7999326372515999,
672
+ "grad_norm": 21.683469772338867,
673
+ "learning_rate": 4.0743801652892566e-05,
674
+ "loss": 0.7592,
675
+ "step": 9500
676
+ },
677
+ {
678
+ "epoch": 0.8083529808016167,
679
+ "grad_norm": 9.07845401763916,
680
+ "learning_rate": 4.058786839232809e-05,
681
+ "loss": 0.7599,
682
+ "step": 9600
683
+ },
684
+ {
685
+ "epoch": 0.8167733243516335,
686
+ "grad_norm": 7.406639575958252,
687
+ "learning_rate": 4.043193513176361e-05,
688
+ "loss": 0.7397,
689
+ "step": 9700
690
+ },
691
+ {
692
+ "epoch": 0.8251936679016504,
693
+ "grad_norm": 0.6552740931510925,
694
+ "learning_rate": 4.0276001871199124e-05,
695
+ "loss": 0.1707,
696
+ "step": 9800
697
+ },
698
+ {
699
+ "epoch": 0.8336140114516672,
700
+ "grad_norm": 0.47074249386787415,
701
+ "learning_rate": 4.0120068610634645e-05,
702
+ "loss": 0.036,
703
+ "step": 9900
704
+ },
705
+ {
706
+ "epoch": 0.8420343550016841,
707
+ "grad_norm": 1.5905348062515259,
708
+ "learning_rate": 3.996413535007017e-05,
709
+ "loss": 0.0272,
710
+ "step": 10000
711
+ },
712
+ {
713
+ "epoch": 0.8504546985517009,
714
+ "grad_norm": 0.7267942428588867,
715
+ "learning_rate": 3.980820208950569e-05,
716
+ "loss": 0.0189,
717
+ "step": 10100
718
+ },
719
+ {
720
+ "epoch": 0.8588750421017177,
721
+ "grad_norm": 0.1869667023420334,
722
+ "learning_rate": 3.965226882894122e-05,
723
+ "loss": 0.0139,
724
+ "step": 10200
725
+ },
726
+ {
727
+ "epoch": 0.8672953856517346,
728
+ "grad_norm": 0.8771575689315796,
729
+ "learning_rate": 3.949633556837674e-05,
730
+ "loss": 0.0155,
731
+ "step": 10300
732
+ },
733
+ {
734
+ "epoch": 0.8757157292017514,
735
+ "grad_norm": 0.1621396690607071,
736
+ "learning_rate": 3.934040230781226e-05,
737
+ "loss": 0.0145,
738
+ "step": 10400
739
+ },
740
+ {
741
+ "epoch": 0.8841360727517683,
742
+ "grad_norm": 0.26454639434814453,
743
+ "learning_rate": 3.918446904724778e-05,
744
+ "loss": 0.0124,
745
+ "step": 10500
746
+ },
747
+ {
748
+ "epoch": 0.8925564163017851,
749
+ "grad_norm": 0.5660475492477417,
750
+ "learning_rate": 3.90285357866833e-05,
751
+ "loss": 0.0098,
752
+ "step": 10600
753
+ },
754
+ {
755
+ "epoch": 0.9009767598518019,
756
+ "grad_norm": 0.12594054639339447,
757
+ "learning_rate": 3.8872602526118825e-05,
758
+ "loss": 0.0091,
759
+ "step": 10700
760
+ },
761
+ {
762
+ "epoch": 0.9093971034018188,
763
+ "grad_norm": 0.10871898382902145,
764
+ "learning_rate": 3.8716669265554346e-05,
765
+ "loss": 0.01,
766
+ "step": 10800
767
+ },
768
+ {
769
+ "epoch": 0.9178174469518356,
770
+ "grad_norm": 5.482397556304932,
771
+ "learning_rate": 3.856073600498987e-05,
772
+ "loss": 0.1028,
773
+ "step": 10900
774
+ },
775
+ {
776
+ "epoch": 0.9262377905018525,
777
+ "grad_norm": 5.7357659339904785,
778
+ "learning_rate": 3.840480274442539e-05,
779
+ "loss": 0.1921,
780
+ "step": 11000
781
+ },
782
+ {
783
+ "epoch": 0.9346581340518694,
784
+ "grad_norm": 1.8957055807113647,
785
+ "learning_rate": 3.824886948386091e-05,
786
+ "loss": 0.1521,
787
+ "step": 11100
788
+ },
789
+ {
790
+ "epoch": 0.9430784776018861,
791
+ "grad_norm": 7.204999923706055,
792
+ "learning_rate": 3.809293622329643e-05,
793
+ "loss": 0.1336,
794
+ "step": 11200
795
+ },
796
+ {
797
+ "epoch": 0.951498821151903,
798
+ "grad_norm": 11.601072311401367,
799
+ "learning_rate": 3.7937002962731954e-05,
800
+ "loss": 0.1238,
801
+ "step": 11300
802
+ },
803
+ {
804
+ "epoch": 0.9599191647019198,
805
+ "grad_norm": 1.993941068649292,
806
+ "learning_rate": 3.7781069702167476e-05,
807
+ "loss": 0.1065,
808
+ "step": 11400
809
+ },
810
+ {
811
+ "epoch": 0.9683395082519367,
812
+ "grad_norm": 3.342390298843384,
813
+ "learning_rate": 3.7625136441603e-05,
814
+ "loss": 0.0955,
815
+ "step": 11500
816
+ },
817
+ {
818
+ "epoch": 0.9767598518019536,
819
+ "grad_norm": 7.570684432983398,
820
+ "learning_rate": 3.746920318103851e-05,
821
+ "loss": 0.0944,
822
+ "step": 11600
823
+ },
824
+ {
825
+ "epoch": 0.9851801953519703,
826
+ "grad_norm": 3.947699546813965,
827
+ "learning_rate": 3.7313269920474034e-05,
828
+ "loss": 0.0849,
829
+ "step": 11700
830
+ },
831
+ {
832
+ "epoch": 0.9936005389019872,
833
+ "grad_norm": 5.432759761810303,
834
+ "learning_rate": 3.715733665990956e-05,
835
+ "loss": 0.0712,
836
+ "step": 11800
837
+ },
838
+ {
839
+ "epoch": 1.002020882452004,
840
+ "grad_norm": 15.626507759094238,
841
+ "learning_rate": 3.7001403399345083e-05,
842
+ "loss": 0.3673,
843
+ "step": 11900
844
+ },
845
+ {
846
+ "epoch": 1.0104412260020208,
847
+ "grad_norm": 6.4510111808776855,
848
+ "learning_rate": 3.6845470138780605e-05,
849
+ "loss": 0.4508,
850
+ "step": 12000
851
+ },
852
+ {
853
+ "epoch": 1.0188615695520378,
854
+ "grad_norm": 6.159328460693359,
855
+ "learning_rate": 3.6689536878216127e-05,
856
+ "loss": 0.3693,
857
+ "step": 12100
858
+ },
859
+ {
860
+ "epoch": 1.0272819131020545,
861
+ "grad_norm": 4.550877571105957,
862
+ "learning_rate": 3.653360361765165e-05,
863
+ "loss": 0.3297,
864
+ "step": 12200
865
+ },
866
+ {
867
+ "epoch": 1.0357022566520715,
868
+ "grad_norm": 3.226945638656616,
869
+ "learning_rate": 3.637767035708717e-05,
870
+ "loss": 0.3452,
871
+ "step": 12300
872
+ },
873
+ {
874
+ "epoch": 1.0441226002020882,
875
+ "grad_norm": 3.6009678840637207,
876
+ "learning_rate": 3.622173709652269e-05,
877
+ "loss": 0.3062,
878
+ "step": 12400
879
+ },
880
+ {
881
+ "epoch": 1.052542943752105,
882
+ "grad_norm": 2.7150795459747314,
883
+ "learning_rate": 3.606580383595821e-05,
884
+ "loss": 0.2824,
885
+ "step": 12500
886
+ },
887
+ {
888
+ "epoch": 1.060963287302122,
889
+ "grad_norm": 4.014440059661865,
890
+ "learning_rate": 3.5909870575393734e-05,
891
+ "loss": 0.2909,
892
+ "step": 12600
893
+ },
894
+ {
895
+ "epoch": 1.0693836308521387,
896
+ "grad_norm": 2.9422249794006348,
897
+ "learning_rate": 3.5753937314829256e-05,
898
+ "loss": 0.2688,
899
+ "step": 12700
900
+ },
901
+ {
902
+ "epoch": 1.0778039744021557,
903
+ "grad_norm": 3.798882484436035,
904
+ "learning_rate": 3.559800405426478e-05,
905
+ "loss": 0.261,
906
+ "step": 12800
907
+ },
908
+ {
909
+ "epoch": 1.0862243179521724,
910
+ "grad_norm": 2.825617551803589,
911
+ "learning_rate": 3.54420707937003e-05,
912
+ "loss": 0.2616,
913
+ "step": 12900
914
+ },
915
+ {
916
+ "epoch": 1.0946446615021892,
917
+ "grad_norm": 4.132945537567139,
918
+ "learning_rate": 3.528613753313582e-05,
919
+ "loss": 0.2496,
920
+ "step": 13000
921
+ },
922
+ {
923
+ "epoch": 1.1030650050522062,
924
+ "grad_norm": 5.848606109619141,
925
+ "learning_rate": 3.513020427257134e-05,
926
+ "loss": 0.2415,
927
+ "step": 13100
928
+ },
929
+ {
930
+ "epoch": 1.111485348602223,
931
+ "grad_norm": 3.019437789916992,
932
+ "learning_rate": 3.4974271012006864e-05,
933
+ "loss": 0.2469,
934
+ "step": 13200
935
+ },
936
+ {
937
+ "epoch": 1.11990569215224,
938
+ "grad_norm": 5.2769455909729,
939
+ "learning_rate": 3.4818337751442385e-05,
940
+ "loss": 0.2444,
941
+ "step": 13300
942
+ },
943
+ {
944
+ "epoch": 1.1283260357022566,
945
+ "grad_norm": 5.284823894500732,
946
+ "learning_rate": 3.46624044908779e-05,
947
+ "loss": 0.2489,
948
+ "step": 13400
949
+ },
950
+ {
951
+ "epoch": 1.1367463792522734,
952
+ "grad_norm": 1.0584665536880493,
953
+ "learning_rate": 3.450647123031343e-05,
954
+ "loss": 0.2338,
955
+ "step": 13500
956
+ },
957
+ {
958
+ "epoch": 1.1451667228022904,
959
+ "grad_norm": 37.629119873046875,
960
+ "learning_rate": 3.435053796974895e-05,
961
+ "loss": 0.2185,
962
+ "step": 13600
963
+ },
964
+ {
965
+ "epoch": 1.1535870663523071,
966
+ "grad_norm": 16.267772674560547,
967
+ "learning_rate": 3.419460470918447e-05,
968
+ "loss": 0.2288,
969
+ "step": 13700
970
+ },
971
+ {
972
+ "epoch": 1.162007409902324,
973
+ "grad_norm": 4.195704936981201,
974
+ "learning_rate": 3.403867144861999e-05,
975
+ "loss": 0.2032,
976
+ "step": 13800
977
+ },
978
+ {
979
+ "epoch": 1.1704277534523408,
980
+ "grad_norm": 3.9956605434417725,
981
+ "learning_rate": 3.3882738188055515e-05,
982
+ "loss": 0.2005,
983
+ "step": 13900
984
+ },
985
+ {
986
+ "epoch": 1.1788480970023576,
987
+ "grad_norm": 2.037095069885254,
988
+ "learning_rate": 3.3726804927491036e-05,
989
+ "loss": 0.2053,
990
+ "step": 14000
991
+ },
992
+ {
993
+ "epoch": 1.1872684405523746,
994
+ "grad_norm": 10.881503105163574,
995
+ "learning_rate": 3.357087166692656e-05,
996
+ "loss": 0.2042,
997
+ "step": 14100
998
+ },
999
+ {
1000
+ "epoch": 1.1956887841023913,
1001
+ "grad_norm": 5.309749126434326,
1002
+ "learning_rate": 3.341493840636208e-05,
1003
+ "loss": 0.1877,
1004
+ "step": 14200
1005
+ },
1006
+ {
1007
+ "epoch": 1.2041091276524083,
1008
+ "grad_norm": 3.2984306812286377,
1009
+ "learning_rate": 3.32590051457976e-05,
1010
+ "loss": 0.1711,
1011
+ "step": 14300
1012
+ },
1013
+ {
1014
+ "epoch": 1.212529471202425,
1015
+ "grad_norm": 3.6049394607543945,
1016
+ "learning_rate": 3.310307188523312e-05,
1017
+ "loss": 0.1973,
1018
+ "step": 14400
1019
+ },
1020
+ {
1021
+ "epoch": 1.220949814752442,
1022
+ "grad_norm": 6.268308162689209,
1023
+ "learning_rate": 3.2947138624668644e-05,
1024
+ "loss": 0.1624,
1025
+ "step": 14500
1026
+ },
1027
+ {
1028
+ "epoch": 1.2293701583024588,
1029
+ "grad_norm": 2.217378616333008,
1030
+ "learning_rate": 3.2791205364104166e-05,
1031
+ "loss": 0.1646,
1032
+ "step": 14600
1033
+ },
1034
+ {
1035
+ "epoch": 1.2377905018524755,
1036
+ "grad_norm": 4.168875694274902,
1037
+ "learning_rate": 3.263527210353969e-05,
1038
+ "loss": 0.1702,
1039
+ "step": 14700
1040
+ },
1041
+ {
1042
+ "epoch": 1.2462108454024925,
1043
+ "grad_norm": 2.362311601638794,
1044
+ "learning_rate": 3.247933884297521e-05,
1045
+ "loss": 0.166,
1046
+ "step": 14800
1047
+ },
1048
+ {
1049
+ "epoch": 1.2546311889525092,
1050
+ "grad_norm": 3.168797016143799,
1051
+ "learning_rate": 3.232340558241073e-05,
1052
+ "loss": 0.1689,
1053
+ "step": 14900
1054
+ },
1055
+ {
1056
+ "epoch": 1.263051532502526,
1057
+ "grad_norm": 3.6625378131866455,
1058
+ "learning_rate": 3.216747232184625e-05,
1059
+ "loss": 0.1747,
1060
+ "step": 15000
1061
+ },
1062
+ {
1063
+ "epoch": 1.271471876052543,
1064
+ "grad_norm": 5.1908793449401855,
1065
+ "learning_rate": 3.201153906128177e-05,
1066
+ "loss": 0.1755,
1067
+ "step": 15100
1068
+ },
1069
+ {
1070
+ "epoch": 1.2798922196025597,
1071
+ "grad_norm": 4.5366387367248535,
1072
+ "learning_rate": 3.1855605800717295e-05,
1073
+ "loss": 0.1607,
1074
+ "step": 15200
1075
+ },
1076
+ {
1077
+ "epoch": 1.2883125631525767,
1078
+ "grad_norm": 3.7079453468322754,
1079
+ "learning_rate": 3.1699672540152816e-05,
1080
+ "loss": 0.1462,
1081
+ "step": 15300
1082
+ },
1083
+ {
1084
+ "epoch": 1.2967329067025934,
1085
+ "grad_norm": 3.3219869136810303,
1086
+ "learning_rate": 3.154373927958834e-05,
1087
+ "loss": 0.1475,
1088
+ "step": 15400
1089
+ },
1090
+ {
1091
+ "epoch": 1.3051532502526104,
1092
+ "grad_norm": 2.976282835006714,
1093
+ "learning_rate": 3.138780601902386e-05,
1094
+ "loss": 0.1587,
1095
+ "step": 15500
1096
+ },
1097
+ {
1098
+ "epoch": 1.3135735938026272,
1099
+ "grad_norm": 2.854203224182129,
1100
+ "learning_rate": 3.123187275845938e-05,
1101
+ "loss": 0.1506,
1102
+ "step": 15600
1103
+ },
1104
+ {
1105
+ "epoch": 1.321993937352644,
1106
+ "grad_norm": 2.5714399814605713,
1107
+ "learning_rate": 3.10759394978949e-05,
1108
+ "loss": 0.1467,
1109
+ "step": 15700
1110
+ },
1111
+ {
1112
+ "epoch": 1.330414280902661,
1113
+ "grad_norm": 1.7303158044815063,
1114
+ "learning_rate": 3.0920006237330424e-05,
1115
+ "loss": 0.1277,
1116
+ "step": 15800
1117
+ },
1118
+ {
1119
+ "epoch": 1.3388346244526776,
1120
+ "grad_norm": 2.199556350708008,
1121
+ "learning_rate": 3.0764072976765946e-05,
1122
+ "loss": 0.1305,
1123
+ "step": 15900
1124
+ },
1125
+ {
1126
+ "epoch": 1.3472549680026944,
1127
+ "grad_norm": 1.3136367797851562,
1128
+ "learning_rate": 3.060813971620147e-05,
1129
+ "loss": 0.1292,
1130
+ "step": 16000
1131
+ },
1132
+ {
1133
+ "epoch": 1.3556753115527114,
1134
+ "grad_norm": 1.4371681213378906,
1135
+ "learning_rate": 3.045220645563699e-05,
1136
+ "loss": 0.1286,
1137
+ "step": 16100
1138
+ },
1139
+ {
1140
+ "epoch": 1.3640956551027281,
1141
+ "grad_norm": 2.634970188140869,
1142
+ "learning_rate": 3.029627319507251e-05,
1143
+ "loss": 0.1412,
1144
+ "step": 16200
1145
+ },
1146
+ {
1147
+ "epoch": 1.372515998652745,
1148
+ "grad_norm": 3.108686923980713,
1149
+ "learning_rate": 3.0140339934508032e-05,
1150
+ "loss": 0.1284,
1151
+ "step": 16300
1152
+ },
1153
+ {
1154
+ "epoch": 1.3809363422027618,
1155
+ "grad_norm": 4.35302734375,
1156
+ "learning_rate": 2.9984406673943554e-05,
1157
+ "loss": 0.1278,
1158
+ "step": 16400
1159
+ },
1160
+ {
1161
+ "epoch": 1.3893566857527788,
1162
+ "grad_norm": 2.4115021228790283,
1163
+ "learning_rate": 2.9828473413379075e-05,
1164
+ "loss": 0.1227,
1165
+ "step": 16500
1166
+ },
1167
+ {
1168
+ "epoch": 1.3977770293027956,
1169
+ "grad_norm": 0.8723605275154114,
1170
+ "learning_rate": 2.96725401528146e-05,
1171
+ "loss": 0.1261,
1172
+ "step": 16600
1173
+ },
1174
+ {
1175
+ "epoch": 1.4061973728528123,
1176
+ "grad_norm": 3.208569288253784,
1177
+ "learning_rate": 2.951660689225012e-05,
1178
+ "loss": 0.1171,
1179
+ "step": 16700
1180
+ },
1181
+ {
1182
+ "epoch": 1.4146177164028293,
1183
+ "grad_norm": 3.3627731800079346,
1184
+ "learning_rate": 2.9360673631685643e-05,
1185
+ "loss": 0.1342,
1186
+ "step": 16800
1187
+ },
1188
+ {
1189
+ "epoch": 1.423038059952846,
1190
+ "grad_norm": 2.9769978523254395,
1191
+ "learning_rate": 2.9204740371121165e-05,
1192
+ "loss": 0.1431,
1193
+ "step": 16900
1194
+ },
1195
+ {
1196
+ "epoch": 1.4314584035028628,
1197
+ "grad_norm": 2.390516996383667,
1198
+ "learning_rate": 2.904880711055668e-05,
1199
+ "loss": 0.1197,
1200
+ "step": 17000
1201
+ },
1202
+ {
1203
+ "epoch": 1.4398787470528798,
1204
+ "grad_norm": 2.3254621028900146,
1205
+ "learning_rate": 2.88928738499922e-05,
1206
+ "loss": 0.13,
1207
+ "step": 17100
1208
+ },
1209
+ {
1210
+ "epoch": 1.4482990906028965,
1211
+ "grad_norm": 9.375923156738281,
1212
+ "learning_rate": 2.8736940589427726e-05,
1213
+ "loss": 0.6417,
1214
+ "step": 17200
1215
+ },
1216
+ {
1217
+ "epoch": 1.4567194341529135,
1218
+ "grad_norm": 24.961429595947266,
1219
+ "learning_rate": 2.8581007328863248e-05,
1220
+ "loss": 1.0493,
1221
+ "step": 17300
1222
+ },
1223
+ {
1224
+ "epoch": 1.4651397777029302,
1225
+ "grad_norm": 22.577869415283203,
1226
+ "learning_rate": 2.842507406829877e-05,
1227
+ "loss": 0.9416,
1228
+ "step": 17400
1229
+ },
1230
+ {
1231
+ "epoch": 1.4735601212529472,
1232
+ "grad_norm": 18.104610443115234,
1233
+ "learning_rate": 2.826914080773429e-05,
1234
+ "loss": 0.9058,
1235
+ "step": 17500
1236
+ },
1237
+ {
1238
+ "epoch": 1.481980464802964,
1239
+ "grad_norm": 11.02493667602539,
1240
+ "learning_rate": 2.8113207547169812e-05,
1241
+ "loss": 0.8439,
1242
+ "step": 17600
1243
+ },
1244
+ {
1245
+ "epoch": 1.4904008083529807,
1246
+ "grad_norm": 7.483858585357666,
1247
+ "learning_rate": 2.7957274286605334e-05,
1248
+ "loss": 0.8125,
1249
+ "step": 17700
1250
+ },
1251
+ {
1252
+ "epoch": 1.4988211519029977,
1253
+ "grad_norm": 7.024225234985352,
1254
+ "learning_rate": 2.7801341026040855e-05,
1255
+ "loss": 0.7498,
1256
+ "step": 17800
1257
+ },
1258
+ {
1259
+ "epoch": 1.5072414954530144,
1260
+ "grad_norm": 39.53349304199219,
1261
+ "learning_rate": 2.7645407765476377e-05,
1262
+ "loss": 0.6975,
1263
+ "step": 17900
1264
+ },
1265
+ {
1266
+ "epoch": 1.5156618390030312,
1267
+ "grad_norm": 9.007433891296387,
1268
+ "learning_rate": 2.74894745049119e-05,
1269
+ "loss": 0.6554,
1270
+ "step": 18000
1271
+ },
1272
+ {
1273
+ "epoch": 1.5240821825530482,
1274
+ "grad_norm": 7.764451503753662,
1275
+ "learning_rate": 2.733354124434742e-05,
1276
+ "loss": 0.6563,
1277
+ "step": 18100
1278
+ },
1279
+ {
1280
+ "epoch": 1.5325025261030651,
1281
+ "grad_norm": 8.649127960205078,
1282
+ "learning_rate": 2.7177607983782945e-05,
1283
+ "loss": 0.6458,
1284
+ "step": 18200
1285
+ },
1286
+ {
1287
+ "epoch": 1.540922869653082,
1288
+ "grad_norm": 14.572016716003418,
1289
+ "learning_rate": 2.7021674723218467e-05,
1290
+ "loss": 0.6086,
1291
+ "step": 18300
1292
+ },
1293
+ {
1294
+ "epoch": 1.5493432132030986,
1295
+ "grad_norm": 8.887728691101074,
1296
+ "learning_rate": 2.6865741462653988e-05,
1297
+ "loss": 0.6098,
1298
+ "step": 18400
1299
+ },
1300
+ {
1301
+ "epoch": 1.5577635567531156,
1302
+ "grad_norm": 9.536375999450684,
1303
+ "learning_rate": 2.670980820208951e-05,
1304
+ "loss": 0.5725,
1305
+ "step": 18500
1306
+ },
1307
+ {
1308
+ "epoch": 1.5661839003031324,
1309
+ "grad_norm": 69.17536926269531,
1310
+ "learning_rate": 2.655387494152503e-05,
1311
+ "loss": 0.5794,
1312
+ "step": 18600
1313
+ },
1314
+ {
1315
+ "epoch": 1.5746042438531491,
1316
+ "grad_norm": 26.702865600585938,
1317
+ "learning_rate": 2.6397941680960553e-05,
1318
+ "loss": 0.5525,
1319
+ "step": 18700
1320
+ },
1321
+ {
1322
+ "epoch": 1.583024587403166,
1323
+ "grad_norm": 6.380317211151123,
1324
+ "learning_rate": 2.6242008420396068e-05,
1325
+ "loss": 0.5345,
1326
+ "step": 18800
1327
+ },
1328
+ {
1329
+ "epoch": 1.5914449309531828,
1330
+ "grad_norm": 8.336255073547363,
1331
+ "learning_rate": 2.6086075159831593e-05,
1332
+ "loss": 0.5765,
1333
+ "step": 18900
1334
+ },
1335
+ {
1336
+ "epoch": 1.5998652745031996,
1337
+ "grad_norm": 14.956998825073242,
1338
+ "learning_rate": 2.5930141899267114e-05,
1339
+ "loss": 0.5097,
1340
+ "step": 19000
1341
+ },
1342
+ {
1343
+ "epoch": 1.6082856180532166,
1344
+ "grad_norm": 16.499773025512695,
1345
+ "learning_rate": 2.5774208638702636e-05,
1346
+ "loss": 0.5681,
1347
+ "step": 19100
1348
+ },
1349
+ {
1350
+ "epoch": 1.6167059616032335,
1351
+ "grad_norm": 99.75704956054688,
1352
+ "learning_rate": 2.5618275378138157e-05,
1353
+ "loss": 0.5473,
1354
+ "step": 19200
1355
+ },
1356
+ {
1357
+ "epoch": 1.6251263051532503,
1358
+ "grad_norm": 8.305459976196289,
1359
+ "learning_rate": 2.546234211757368e-05,
1360
+ "loss": 0.5206,
1361
+ "step": 19300
1362
+ },
1363
+ {
1364
+ "epoch": 1.633546648703267,
1365
+ "grad_norm": 9.534538269042969,
1366
+ "learning_rate": 2.53064088570092e-05,
1367
+ "loss": 0.5175,
1368
+ "step": 19400
1369
+ },
1370
+ {
1371
+ "epoch": 1.641966992253284,
1372
+ "grad_norm": 10.031558990478516,
1373
+ "learning_rate": 2.5150475596444722e-05,
1374
+ "loss": 0.4796,
1375
+ "step": 19500
1376
+ },
1377
+ {
1378
+ "epoch": 1.6503873358033008,
1379
+ "grad_norm": 10.884944915771484,
1380
+ "learning_rate": 2.4994542335880244e-05,
1381
+ "loss": 0.4866,
1382
+ "step": 19600
1383
+ },
1384
+ {
1385
+ "epoch": 1.6588076793533175,
1386
+ "grad_norm": 38.82561111450195,
1387
+ "learning_rate": 2.4838609075315765e-05,
1388
+ "loss": 0.4706,
1389
+ "step": 19700
1390
+ },
1391
+ {
1392
+ "epoch": 1.6672280229033345,
1393
+ "grad_norm": 30.905010223388672,
1394
+ "learning_rate": 2.4682675814751287e-05,
1395
+ "loss": 0.5092,
1396
+ "step": 19800
1397
+ },
1398
+ {
1399
+ "epoch": 1.6756483664533512,
1400
+ "grad_norm": 6.405722141265869,
1401
+ "learning_rate": 2.452674255418681e-05,
1402
+ "loss": 0.4799,
1403
+ "step": 19900
1404
+ },
1405
+ {
1406
+ "epoch": 1.684068710003368,
1407
+ "grad_norm": 19.763652801513672,
1408
+ "learning_rate": 2.4370809293622333e-05,
1409
+ "loss": 0.4548,
1410
+ "step": 20000
1411
+ },
1412
+ {
1413
+ "epoch": 1.692489053553385,
1414
+ "grad_norm": 10.142723083496094,
1415
+ "learning_rate": 2.421487603305785e-05,
1416
+ "loss": 0.4639,
1417
+ "step": 20100
1418
+ },
1419
+ {
1420
+ "epoch": 1.700909397103402,
1421
+ "grad_norm": 11.770618438720703,
1422
+ "learning_rate": 2.4058942772493373e-05,
1423
+ "loss": 0.4297,
1424
+ "step": 20200
1425
+ },
1426
+ {
1427
+ "epoch": 1.7093297406534187,
1428
+ "grad_norm": 69.44645690917969,
1429
+ "learning_rate": 2.3903009511928894e-05,
1430
+ "loss": 0.4382,
1431
+ "step": 20300
1432
+ },
1433
+ {
1434
+ "epoch": 1.7177500842034354,
1435
+ "grad_norm": 6.592321872711182,
1436
+ "learning_rate": 2.3747076251364416e-05,
1437
+ "loss": 0.4428,
1438
+ "step": 20400
1439
+ },
1440
+ {
1441
+ "epoch": 1.7261704277534524,
1442
+ "grad_norm": 12.039219856262207,
1443
+ "learning_rate": 2.3591142990799938e-05,
1444
+ "loss": 0.4308,
1445
+ "step": 20500
1446
+ },
1447
+ {
1448
+ "epoch": 1.7345907713034692,
1449
+ "grad_norm": 7.2263994216918945,
1450
+ "learning_rate": 2.343520973023546e-05,
1451
+ "loss": 0.4038,
1452
+ "step": 20600
1453
+ },
1454
+ {
1455
+ "epoch": 1.743011114853486,
1456
+ "grad_norm": 6.700140476226807,
1457
+ "learning_rate": 2.3279276469670984e-05,
1458
+ "loss": 0.3842,
1459
+ "step": 20700
1460
+ },
1461
+ {
1462
+ "epoch": 1.751431458403503,
1463
+ "grad_norm": 5.211968898773193,
1464
+ "learning_rate": 2.3123343209106506e-05,
1465
+ "loss": 0.4227,
1466
+ "step": 20800
1467
+ },
1468
+ {
1469
+ "epoch": 1.7598518019535199,
1470
+ "grad_norm": 4.104666233062744,
1471
+ "learning_rate": 2.2967409948542027e-05,
1472
+ "loss": 0.387,
1473
+ "step": 20900
1474
+ },
1475
+ {
1476
+ "epoch": 1.7682721455035364,
1477
+ "grad_norm": 8.997115135192871,
1478
+ "learning_rate": 2.2811476687977545e-05,
1479
+ "loss": 0.3729,
1480
+ "step": 21000
1481
+ },
1482
+ {
1483
+ "epoch": 1.7766924890535534,
1484
+ "grad_norm": 10.214786529541016,
1485
+ "learning_rate": 2.2655543427413067e-05,
1486
+ "loss": 0.3768,
1487
+ "step": 21100
1488
+ },
1489
+ {
1490
+ "epoch": 1.7851128326035703,
1491
+ "grad_norm": 8.062252044677734,
1492
+ "learning_rate": 2.249961016684859e-05,
1493
+ "loss": 0.3984,
1494
+ "step": 21200
1495
+ },
1496
+ {
1497
+ "epoch": 1.793533176153587,
1498
+ "grad_norm": 8.471816062927246,
1499
+ "learning_rate": 2.234367690628411e-05,
1500
+ "loss": 0.4128,
1501
+ "step": 21300
1502
+ },
1503
+ {
1504
+ "epoch": 1.8019535197036038,
1505
+ "grad_norm": 6.631267547607422,
1506
+ "learning_rate": 2.218774364571963e-05,
1507
+ "loss": 0.3995,
1508
+ "step": 21400
1509
+ },
1510
+ {
1511
+ "epoch": 1.8103738632536208,
1512
+ "grad_norm": 7.958058834075928,
1513
+ "learning_rate": 2.2031810385155157e-05,
1514
+ "loss": 0.416,
1515
+ "step": 21500
1516
+ },
1517
+ {
1518
+ "epoch": 1.8187942068036376,
1519
+ "grad_norm": 0.48709893226623535,
1520
+ "learning_rate": 2.1875877124590678e-05,
1521
+ "loss": 0.3488,
1522
+ "step": 21600
1523
+ },
1524
+ {
1525
+ "epoch": 1.8272145503536543,
1526
+ "grad_norm": 0.13080443441867828,
1527
+ "learning_rate": 2.17199438640262e-05,
1528
+ "loss": 0.0116,
1529
+ "step": 21700
1530
+ },
1531
+ {
1532
+ "epoch": 1.8356348939036713,
1533
+ "grad_norm": 0.12103134393692017,
1534
+ "learning_rate": 2.156401060346172e-05,
1535
+ "loss": 0.0066,
1536
+ "step": 21800
1537
+ },
1538
+ {
1539
+ "epoch": 1.8440552374536883,
1540
+ "grad_norm": 0.128848135471344,
1541
+ "learning_rate": 2.140807734289724e-05,
1542
+ "loss": 0.0051,
1543
+ "step": 21900
1544
+ },
1545
+ {
1546
+ "epoch": 1.8524755810037048,
1547
+ "grad_norm": 1.0999774932861328,
1548
+ "learning_rate": 2.125214408233276e-05,
1549
+ "loss": 0.0064,
1550
+ "step": 22000
1551
+ },
1552
+ {
1553
+ "epoch": 1.8608959245537218,
1554
+ "grad_norm": 0.19511470198631287,
1555
+ "learning_rate": 2.1096210821768282e-05,
1556
+ "loss": 0.0038,
1557
+ "step": 22100
1558
+ },
1559
+ {
1560
+ "epoch": 1.8693162681037387,
1561
+ "grad_norm": 0.2998058795928955,
1562
+ "learning_rate": 2.0940277561203804e-05,
1563
+ "loss": 0.004,
1564
+ "step": 22200
1565
+ },
1566
+ {
1567
+ "epoch": 1.8777366116537555,
1568
+ "grad_norm": 0.3210146725177765,
1569
+ "learning_rate": 2.078434430063933e-05,
1570
+ "loss": 0.003,
1571
+ "step": 22300
1572
+ },
1573
+ {
1574
+ "epoch": 1.8861569552037722,
1575
+ "grad_norm": 0.08681979775428772,
1576
+ "learning_rate": 2.062841104007485e-05,
1577
+ "loss": 0.0023,
1578
+ "step": 22400
1579
+ },
1580
+ {
1581
+ "epoch": 1.8945772987537892,
1582
+ "grad_norm": 0.21799153089523315,
1583
+ "learning_rate": 2.0472477779510372e-05,
1584
+ "loss": 0.0026,
1585
+ "step": 22500
1586
+ },
1587
+ {
1588
+ "epoch": 1.902997642303806,
1589
+ "grad_norm": 0.062381282448768616,
1590
+ "learning_rate": 2.0316544518945894e-05,
1591
+ "loss": 0.0021,
1592
+ "step": 22600
1593
+ },
1594
+ {
1595
+ "epoch": 1.9114179858538227,
1596
+ "grad_norm": 0.13877958059310913,
1597
+ "learning_rate": 2.0160611258381415e-05,
1598
+ "loss": 0.0021,
1599
+ "step": 22700
1600
+ },
1601
+ {
1602
+ "epoch": 1.9198383294038397,
1603
+ "grad_norm": 0.6393685936927795,
1604
+ "learning_rate": 2.0004677997816933e-05,
1605
+ "loss": 0.0317,
1606
+ "step": 22800
1607
+ },
1608
+ {
1609
+ "epoch": 1.9282586729538567,
1610
+ "grad_norm": 1.2400928735733032,
1611
+ "learning_rate": 1.9848744737252455e-05,
1612
+ "loss": 0.038,
1613
+ "step": 22900
1614
+ },
1615
+ {
1616
+ "epoch": 1.9366790165038732,
1617
+ "grad_norm": 0.9584667086601257,
1618
+ "learning_rate": 1.9692811476687977e-05,
1619
+ "loss": 0.0272,
1620
+ "step": 23000
1621
+ },
1622
+ {
1623
+ "epoch": 1.9450993600538902,
1624
+ "grad_norm": 1.0835716724395752,
1625
+ "learning_rate": 1.9536878216123498e-05,
1626
+ "loss": 0.0282,
1627
+ "step": 23100
1628
+ },
1629
+ {
1630
+ "epoch": 1.9535197036039071,
1631
+ "grad_norm": 2.3751420974731445,
1632
+ "learning_rate": 1.9380944955559023e-05,
1633
+ "loss": 0.0218,
1634
+ "step": 23200
1635
+ },
1636
+ {
1637
+ "epoch": 1.961940047153924,
1638
+ "grad_norm": 0.33170026540756226,
1639
+ "learning_rate": 1.9225011694994545e-05,
1640
+ "loss": 0.0194,
1641
+ "step": 23300
1642
+ },
1643
+ {
1644
+ "epoch": 1.9703603907039406,
1645
+ "grad_norm": 1.3425530195236206,
1646
+ "learning_rate": 1.9069078434430066e-05,
1647
+ "loss": 0.0192,
1648
+ "step": 23400
1649
+ },
1650
+ {
1651
+ "epoch": 1.9787807342539576,
1652
+ "grad_norm": 0.2928735911846161,
1653
+ "learning_rate": 1.8913145173865588e-05,
1654
+ "loss": 0.0197,
1655
+ "step": 23500
1656
+ },
1657
+ {
1658
+ "epoch": 1.9872010778039744,
1659
+ "grad_norm": 0.1353292614221573,
1660
+ "learning_rate": 1.875721191330111e-05,
1661
+ "loss": 0.0136,
1662
+ "step": 23600
1663
+ },
1664
+ {
1665
+ "epoch": 1.9956214213539911,
1666
+ "grad_norm": 0.6597471833229065,
1667
+ "learning_rate": 1.8601278652736627e-05,
1668
+ "loss": 0.0139,
1669
+ "step": 23700
1670
+ },
1671
+ {
1672
+ "epoch": 2.004041764904008,
1673
+ "grad_norm": 2.835427761077881,
1674
+ "learning_rate": 1.844534539217215e-05,
1675
+ "loss": 0.1831,
1676
+ "step": 23800
1677
+ },
1678
+ {
1679
+ "epoch": 2.012462108454025,
1680
+ "grad_norm": 2.29437255859375,
1681
+ "learning_rate": 1.828941213160767e-05,
1682
+ "loss": 0.1384,
1683
+ "step": 23900
1684
+ },
1685
+ {
1686
+ "epoch": 2.0208824520040416,
1687
+ "grad_norm": 2.420936346054077,
1688
+ "learning_rate": 1.8133478871043196e-05,
1689
+ "loss": 0.1157,
1690
+ "step": 24000
1691
+ },
1692
+ {
1693
+ "epoch": 2.0293027955540586,
1694
+ "grad_norm": 2.158114194869995,
1695
+ "learning_rate": 1.7977545610478717e-05,
1696
+ "loss": 0.104,
1697
+ "step": 24100
1698
+ },
1699
+ {
1700
+ "epoch": 2.0377231391040755,
1701
+ "grad_norm": 2.9640002250671387,
1702
+ "learning_rate": 1.782161234991424e-05,
1703
+ "loss": 0.1123,
1704
+ "step": 24200
1705
+ },
1706
+ {
1707
+ "epoch": 2.046143482654092,
1708
+ "grad_norm": 3.13875675201416,
1709
+ "learning_rate": 1.766567908934976e-05,
1710
+ "loss": 0.098,
1711
+ "step": 24300
1712
+ },
1713
+ {
1714
+ "epoch": 2.054563826204109,
1715
+ "grad_norm": 1.8173339366912842,
1716
+ "learning_rate": 1.7509745828785282e-05,
1717
+ "loss": 0.0985,
1718
+ "step": 24400
1719
+ },
1720
+ {
1721
+ "epoch": 2.062984169754126,
1722
+ "grad_norm": 1.9323346614837646,
1723
+ "learning_rate": 1.7353812568220803e-05,
1724
+ "loss": 0.099,
1725
+ "step": 24500
1726
+ },
1727
+ {
1728
+ "epoch": 2.071404513304143,
1729
+ "grad_norm": 1.5606794357299805,
1730
+ "learning_rate": 1.719787930765632e-05,
1731
+ "loss": 0.1033,
1732
+ "step": 24600
1733
+ },
1734
+ {
1735
+ "epoch": 2.0798248568541595,
1736
+ "grad_norm": 2.589740753173828,
1737
+ "learning_rate": 1.7041946047091843e-05,
1738
+ "loss": 0.0897,
1739
+ "step": 24700
1740
+ },
1741
+ {
1742
+ "epoch": 2.0882452004041765,
1743
+ "grad_norm": 0.7438304424285889,
1744
+ "learning_rate": 1.6886012786527368e-05,
1745
+ "loss": 0.0939,
1746
+ "step": 24800
1747
+ },
1748
+ {
1749
+ "epoch": 2.0966655439541935,
1750
+ "grad_norm": 0.7309479713439941,
1751
+ "learning_rate": 1.673007952596289e-05,
1752
+ "loss": 0.0846,
1753
+ "step": 24900
1754
+ },
1755
+ {
1756
+ "epoch": 2.10508588750421,
1757
+ "grad_norm": 0.8864309787750244,
1758
+ "learning_rate": 1.657414626539841e-05,
1759
+ "loss": 0.0913,
1760
+ "step": 25000
1761
+ },
1762
+ {
1763
+ "epoch": 2.113506231054227,
1764
+ "grad_norm": 3.734173059463501,
1765
+ "learning_rate": 1.6418213004833933e-05,
1766
+ "loss": 0.0892,
1767
+ "step": 25100
1768
+ },
1769
+ {
1770
+ "epoch": 2.121926574604244,
1771
+ "grad_norm": 1.031955599784851,
1772
+ "learning_rate": 1.6262279744269454e-05,
1773
+ "loss": 0.0914,
1774
+ "step": 25200
1775
+ },
1776
+ {
1777
+ "epoch": 2.1303469181542605,
1778
+ "grad_norm": 1.262018084526062,
1779
+ "learning_rate": 1.6106346483704976e-05,
1780
+ "loss": 0.1019,
1781
+ "step": 25300
1782
+ },
1783
+ {
1784
+ "epoch": 2.1387672617042774,
1785
+ "grad_norm": 0.6608179807662964,
1786
+ "learning_rate": 1.5950413223140497e-05,
1787
+ "loss": 0.0858,
1788
+ "step": 25400
1789
+ },
1790
+ {
1791
+ "epoch": 2.1471876052542944,
1792
+ "grad_norm": 0.5380622744560242,
1793
+ "learning_rate": 1.5794479962576016e-05,
1794
+ "loss": 0.0886,
1795
+ "step": 25500
1796
+ },
1797
+ {
1798
+ "epoch": 2.1556079488043114,
1799
+ "grad_norm": 2.167166233062744,
1800
+ "learning_rate": 1.563854670201154e-05,
1801
+ "loss": 0.0875,
1802
+ "step": 25600
1803
+ },
1804
+ {
1805
+ "epoch": 2.164028292354328,
1806
+ "grad_norm": 3.2814202308654785,
1807
+ "learning_rate": 1.5482613441447062e-05,
1808
+ "loss": 0.0828,
1809
+ "step": 25700
1810
+ },
1811
+ {
1812
+ "epoch": 2.172448635904345,
1813
+ "grad_norm": 1.1189013719558716,
1814
+ "learning_rate": 1.5326680180882584e-05,
1815
+ "loss": 0.0769,
1816
+ "step": 25800
1817
+ },
1818
+ {
1819
+ "epoch": 2.180868979454362,
1820
+ "grad_norm": 0.8286951184272766,
1821
+ "learning_rate": 1.5170746920318105e-05,
1822
+ "loss": 0.0768,
1823
+ "step": 25900
1824
+ },
1825
+ {
1826
+ "epoch": 2.1892893230043784,
1827
+ "grad_norm": 0.5198948383331299,
1828
+ "learning_rate": 1.5014813659753627e-05,
1829
+ "loss": 0.0769,
1830
+ "step": 26000
1831
+ },
1832
+ {
1833
+ "epoch": 2.1977096665543954,
1834
+ "grad_norm": 1.3561586141586304,
1835
+ "learning_rate": 1.4858880399189148e-05,
1836
+ "loss": 0.0744,
1837
+ "step": 26100
1838
+ },
1839
+ {
1840
+ "epoch": 2.2061300101044123,
1841
+ "grad_norm": 2.7382802963256836,
1842
+ "learning_rate": 1.470294713862467e-05,
1843
+ "loss": 0.0675,
1844
+ "step": 26200
1845
+ },
1846
+ {
1847
+ "epoch": 2.2145503536544293,
1848
+ "grad_norm": 1.4717612266540527,
1849
+ "learning_rate": 1.4547013878060191e-05,
1850
+ "loss": 0.071,
1851
+ "step": 26300
1852
+ },
1853
+ {
1854
+ "epoch": 2.222970697204446,
1855
+ "grad_norm": 2.3162336349487305,
1856
+ "learning_rate": 1.4391080617495711e-05,
1857
+ "loss": 0.0696,
1858
+ "step": 26400
1859
+ },
1860
+ {
1861
+ "epoch": 2.231391040754463,
1862
+ "grad_norm": 0.35251349210739136,
1863
+ "learning_rate": 1.4235147356931233e-05,
1864
+ "loss": 0.0595,
1865
+ "step": 26500
1866
+ },
1867
+ {
1868
+ "epoch": 2.23981138430448,
1869
+ "grad_norm": 2.207399368286133,
1870
+ "learning_rate": 1.4079214096366754e-05,
1871
+ "loss": 0.0705,
1872
+ "step": 26600
1873
+ },
1874
+ {
1875
+ "epoch": 2.2482317278544963,
1876
+ "grad_norm": 2.2342419624328613,
1877
+ "learning_rate": 1.3923280835802278e-05,
1878
+ "loss": 0.0641,
1879
+ "step": 26700
1880
+ },
1881
+ {
1882
+ "epoch": 2.2566520714045133,
1883
+ "grad_norm": 1.604312539100647,
1884
+ "learning_rate": 1.37673475752378e-05,
1885
+ "loss": 0.0718,
1886
+ "step": 26800
1887
+ },
1888
+ {
1889
+ "epoch": 2.2650724149545303,
1890
+ "grad_norm": 2.674197196960449,
1891
+ "learning_rate": 1.361141431467332e-05,
1892
+ "loss": 0.0766,
1893
+ "step": 26900
1894
+ },
1895
+ {
1896
+ "epoch": 2.273492758504547,
1897
+ "grad_norm": 2.6131813526153564,
1898
+ "learning_rate": 1.3455481054108842e-05,
1899
+ "loss": 0.0743,
1900
+ "step": 27000
1901
+ },
1902
+ {
1903
+ "epoch": 2.2819131020545638,
1904
+ "grad_norm": 0.4795171618461609,
1905
+ "learning_rate": 1.3299547793544364e-05,
1906
+ "loss": 0.0591,
1907
+ "step": 27100
1908
+ },
1909
+ {
1910
+ "epoch": 2.2903334456045807,
1911
+ "grad_norm": 0.6082819700241089,
1912
+ "learning_rate": 1.3143614532979887e-05,
1913
+ "loss": 0.055,
1914
+ "step": 27200
1915
+ },
1916
+ {
1917
+ "epoch": 2.2987537891545973,
1918
+ "grad_norm": 1.9809715747833252,
1919
+ "learning_rate": 1.2987681272415405e-05,
1920
+ "loss": 0.0642,
1921
+ "step": 27300
1922
+ },
1923
+ {
1924
+ "epoch": 2.3071741327046142,
1925
+ "grad_norm": 2.095233678817749,
1926
+ "learning_rate": 1.2831748011850927e-05,
1927
+ "loss": 0.0624,
1928
+ "step": 27400
1929
+ },
1930
+ {
1931
+ "epoch": 2.315594476254631,
1932
+ "grad_norm": 0.3463571071624756,
1933
+ "learning_rate": 1.267581475128645e-05,
1934
+ "loss": 0.0568,
1935
+ "step": 27500
1936
+ },
1937
+ {
1938
+ "epoch": 2.324014819804648,
1939
+ "grad_norm": 0.37240880727767944,
1940
+ "learning_rate": 1.2519881490721972e-05,
1941
+ "loss": 0.0582,
1942
+ "step": 27600
1943
+ },
1944
+ {
1945
+ "epoch": 2.3324351633546647,
1946
+ "grad_norm": 0.3742882311344147,
1947
+ "learning_rate": 1.2363948230157493e-05,
1948
+ "loss": 0.0477,
1949
+ "step": 27700
1950
+ },
1951
+ {
1952
+ "epoch": 2.3408555069046817,
1953
+ "grad_norm": 0.3263934850692749,
1954
+ "learning_rate": 1.2208014969593015e-05,
1955
+ "loss": 0.0513,
1956
+ "step": 27800
1957
+ },
1958
+ {
1959
+ "epoch": 2.3492758504546987,
1960
+ "grad_norm": 0.7098066806793213,
1961
+ "learning_rate": 1.2052081709028536e-05,
1962
+ "loss": 0.0486,
1963
+ "step": 27900
1964
+ },
1965
+ {
1966
+ "epoch": 2.357696194004715,
1967
+ "grad_norm": 0.8197891712188721,
1968
+ "learning_rate": 1.1896148448464058e-05,
1969
+ "loss": 0.0485,
1970
+ "step": 28000
1971
+ },
1972
+ {
1973
+ "epoch": 2.366116537554732,
1974
+ "grad_norm": 0.7206839919090271,
1975
+ "learning_rate": 1.174021518789958e-05,
1976
+ "loss": 0.0571,
1977
+ "step": 28100
1978
+ },
1979
+ {
1980
+ "epoch": 2.374536881104749,
1981
+ "grad_norm": 0.4567437767982483,
1982
+ "learning_rate": 1.1584281927335101e-05,
1983
+ "loss": 0.0575,
1984
+ "step": 28200
1985
+ },
1986
+ {
1987
+ "epoch": 2.382957224654766,
1988
+ "grad_norm": 1.4102520942687988,
1989
+ "learning_rate": 1.1428348666770623e-05,
1990
+ "loss": 0.0503,
1991
+ "step": 28300
1992
+ },
1993
+ {
1994
+ "epoch": 2.3913775682047826,
1995
+ "grad_norm": 0.22976179420948029,
1996
+ "learning_rate": 1.1272415406206144e-05,
1997
+ "loss": 0.0482,
1998
+ "step": 28400
1999
+ },
2000
+ {
2001
+ "epoch": 2.3997979117547996,
2002
+ "grad_norm": 0.8997607231140137,
2003
+ "learning_rate": 1.1116482145641666e-05,
2004
+ "loss": 0.0578,
2005
+ "step": 28500
2006
+ },
2007
+ {
2008
+ "epoch": 2.4082182553048166,
2009
+ "grad_norm": 0.5438327789306641,
2010
+ "learning_rate": 1.0960548885077187e-05,
2011
+ "loss": 0.0496,
2012
+ "step": 28600
2013
+ },
2014
+ {
2015
+ "epoch": 2.416638598854833,
2016
+ "grad_norm": 0.38543766736984253,
2017
+ "learning_rate": 1.0804615624512709e-05,
2018
+ "loss": 0.0545,
2019
+ "step": 28700
2020
+ },
2021
+ {
2022
+ "epoch": 2.42505894240485,
2023
+ "grad_norm": 0.45761021971702576,
2024
+ "learning_rate": 1.064868236394823e-05,
2025
+ "loss": 0.054,
2026
+ "step": 28800
2027
+ },
2028
+ {
2029
+ "epoch": 2.433479285954867,
2030
+ "grad_norm": 1.072931170463562,
2031
+ "learning_rate": 1.0492749103383752e-05,
2032
+ "loss": 0.0529,
2033
+ "step": 28900
2034
+ },
2035
+ {
2036
+ "epoch": 2.441899629504884,
2037
+ "grad_norm": 0.8028556704521179,
2038
+ "learning_rate": 1.0336815842819274e-05,
2039
+ "loss": 0.0604,
2040
+ "step": 29000
2041
+ },
2042
+ {
2043
+ "epoch": 2.4503199730549006,
2044
+ "grad_norm": 5.610771656036377,
2045
+ "learning_rate": 1.0180882582254795e-05,
2046
+ "loss": 0.462,
2047
+ "step": 29100
2048
+ },
2049
+ {
2050
+ "epoch": 2.4587403166049175,
2051
+ "grad_norm": 8.661577224731445,
2052
+ "learning_rate": 1.0024949321690318e-05,
2053
+ "loss": 0.5095,
2054
+ "step": 29200
2055
+ },
2056
+ {
2057
+ "epoch": 2.4671606601549345,
2058
+ "grad_norm": 5.638516902923584,
2059
+ "learning_rate": 9.869016061125838e-06,
2060
+ "loss": 0.4603,
2061
+ "step": 29300
2062
+ },
2063
+ {
2064
+ "epoch": 2.475581003704951,
2065
+ "grad_norm": 6.656158447265625,
2066
+ "learning_rate": 9.71308280056136e-06,
2067
+ "loss": 0.4584,
2068
+ "step": 29400
2069
+ },
2070
+ {
2071
+ "epoch": 2.484001347254968,
2072
+ "grad_norm": 5.3289923667907715,
2073
+ "learning_rate": 9.557149539996881e-06,
2074
+ "loss": 0.3933,
2075
+ "step": 29500
2076
+ },
2077
+ {
2078
+ "epoch": 2.492421690804985,
2079
+ "grad_norm": 4.8232831954956055,
2080
+ "learning_rate": 9.401216279432405e-06,
2081
+ "loss": 0.3533,
2082
+ "step": 29600
2083
+ },
2084
+ {
2085
+ "epoch": 2.5008420343550015,
2086
+ "grad_norm": 5.679427623748779,
2087
+ "learning_rate": 9.245283018867924e-06,
2088
+ "loss": 0.2919,
2089
+ "step": 29700
2090
+ },
2091
+ {
2092
+ "epoch": 2.5092623779050185,
2093
+ "grad_norm": 3.5916316509246826,
2094
+ "learning_rate": 9.089349758303446e-06,
2095
+ "loss": 0.2907,
2096
+ "step": 29800
2097
+ },
2098
+ {
2099
+ "epoch": 2.5176827214550355,
2100
+ "grad_norm": 4.971811294555664,
2101
+ "learning_rate": 8.933416497738968e-06,
2102
+ "loss": 0.3201,
2103
+ "step": 29900
2104
+ },
2105
+ {
2106
+ "epoch": 2.526103065005052,
2107
+ "grad_norm": 7.323381423950195,
2108
+ "learning_rate": 8.77748323717449e-06,
2109
+ "loss": 0.2896,
2110
+ "step": 30000
2111
+ },
2112
+ {
2113
+ "epoch": 2.534523408555069,
2114
+ "grad_norm": 3.5097551345825195,
2115
+ "learning_rate": 8.621549976610012e-06,
2116
+ "loss": 0.2852,
2117
+ "step": 30100
2118
+ },
2119
+ {
2120
+ "epoch": 2.542943752105086,
2121
+ "grad_norm": 3.7720704078674316,
2122
+ "learning_rate": 8.465616716045532e-06,
2123
+ "loss": 0.2182,
2124
+ "step": 30200
2125
+ },
2126
+ {
2127
+ "epoch": 2.551364095655103,
2128
+ "grad_norm": 6.767735481262207,
2129
+ "learning_rate": 8.309683455481054e-06,
2130
+ "loss": 0.2423,
2131
+ "step": 30300
2132
+ },
2133
+ {
2134
+ "epoch": 2.5597844392051194,
2135
+ "grad_norm": 3.3460731506347656,
2136
+ "learning_rate": 8.153750194916577e-06,
2137
+ "loss": 0.2496,
2138
+ "step": 30400
2139
+ },
2140
+ {
2141
+ "epoch": 2.5682047827551364,
2142
+ "grad_norm": 17.407913208007812,
2143
+ "learning_rate": 7.997816934352099e-06,
2144
+ "loss": 0.2303,
2145
+ "step": 30500
2146
+ },
2147
+ {
2148
+ "epoch": 2.5766251263051534,
2149
+ "grad_norm": 3.996459722518921,
2150
+ "learning_rate": 7.841883673787618e-06,
2151
+ "loss": 0.2065,
2152
+ "step": 30600
2153
+ },
2154
+ {
2155
+ "epoch": 2.58504546985517,
2156
+ "grad_norm": 2.772590398788452,
2157
+ "learning_rate": 7.68595041322314e-06,
2158
+ "loss": 0.2031,
2159
+ "step": 30700
2160
+ },
2161
+ {
2162
+ "epoch": 2.593465813405187,
2163
+ "grad_norm": 4.046528339385986,
2164
+ "learning_rate": 7.5300171526586624e-06,
2165
+ "loss": 0.2384,
2166
+ "step": 30800
2167
+ },
2168
+ {
2169
+ "epoch": 2.601886156955204,
2170
+ "grad_norm": 2.2654547691345215,
2171
+ "learning_rate": 7.374083892094184e-06,
2172
+ "loss": 0.2441,
2173
+ "step": 30900
2174
+ },
2175
+ {
2176
+ "epoch": 2.610306500505221,
2177
+ "grad_norm": 4.873164176940918,
2178
+ "learning_rate": 7.218150631529706e-06,
2179
+ "loss": 0.2914,
2180
+ "step": 31000
2181
+ },
2182
+ {
2183
+ "epoch": 2.6187268440552374,
2184
+ "grad_norm": 2.461027145385742,
2185
+ "learning_rate": 7.062217370965227e-06,
2186
+ "loss": 0.2695,
2187
+ "step": 31100
2188
+ },
2189
+ {
2190
+ "epoch": 2.6271471876052543,
2191
+ "grad_norm": 7.631922245025635,
2192
+ "learning_rate": 6.906284110400749e-06,
2193
+ "loss": 0.2366,
2194
+ "step": 31200
2195
+ },
2196
+ {
2197
+ "epoch": 2.635567531155271,
2198
+ "grad_norm": 2.1125121116638184,
2199
+ "learning_rate": 6.75035084983627e-06,
2200
+ "loss": 0.2007,
2201
+ "step": 31300
2202
+ },
2203
+ {
2204
+ "epoch": 2.643987874705288,
2205
+ "grad_norm": 3.188915967941284,
2206
+ "learning_rate": 6.594417589271793e-06,
2207
+ "loss": 0.2088,
2208
+ "step": 31400
2209
+ },
2210
+ {
2211
+ "epoch": 2.652408218255305,
2212
+ "grad_norm": 3.0127580165863037,
2213
+ "learning_rate": 6.438484328707313e-06,
2214
+ "loss": 0.1975,
2215
+ "step": 31500
2216
+ },
2217
+ {
2218
+ "epoch": 2.660828561805322,
2219
+ "grad_norm": 1.8730789422988892,
2220
+ "learning_rate": 6.282551068142835e-06,
2221
+ "loss": 0.2162,
2222
+ "step": 31600
2223
+ },
2224
+ {
2225
+ "epoch": 2.6692489053553388,
2226
+ "grad_norm": 6.462364673614502,
2227
+ "learning_rate": 6.1266178075783565e-06,
2228
+ "loss": 0.2201,
2229
+ "step": 31700
2230
+ },
2231
+ {
2232
+ "epoch": 2.6776692489053553,
2233
+ "grad_norm": 5.668213844299316,
2234
+ "learning_rate": 5.970684547013879e-06,
2235
+ "loss": 0.1907,
2236
+ "step": 31800
2237
+ },
2238
+ {
2239
+ "epoch": 2.6860895924553723,
2240
+ "grad_norm": 2.8429136276245117,
2241
+ "learning_rate": 5.8147512864494e-06,
2242
+ "loss": 0.1675,
2243
+ "step": 31900
2244
+ },
2245
+ {
2246
+ "epoch": 2.694509936005389,
2247
+ "grad_norm": 3.140132188796997,
2248
+ "learning_rate": 5.658818025884922e-06,
2249
+ "loss": 0.1866,
2250
+ "step": 32000
2251
+ }
2252
+ ],
2253
+ "logging_steps": 100,
2254
+ "max_steps": 35628,
2255
+ "num_input_tokens_seen": 0,
2256
+ "num_train_epochs": 3,
2257
+ "save_steps": 500,
2258
+ "stateful_callbacks": {
2259
+ "TrainerControl": {
2260
+ "args": {
2261
+ "should_epoch_stop": false,
2262
+ "should_evaluate": false,
2263
+ "should_log": false,
2264
+ "should_save": true,
2265
+ "should_training_stop": false
2266
+ },
2267
+ "attributes": {}
2268
+ }
2269
+ },
2270
+ "total_flos": 0.0,
2271
+ "train_batch_size": 64,
2272
+ "trial_name": null,
2273
+ "trial_params": null
2274
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f5f5e79079adecb3d2fe96a0f8a6b0c56742f44e7d29a6c4fcf98bcc4967a119
3
+ size 5688
vocab.json ADDED
The diff for this file is too large to render. See raw diff