jjee2 commited on
Commit
5bc3526
·
verified ·
1 Parent(s): 6ccbbc6

Add GaetanMichelet__Llama-31-8B_task-2_180-samples_config-4

Browse files
GaetanMichelet__Llama-31-8B_task-2_180-samples_config-4/.gitattributes ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ *.7z filter=lfs diff=lfs merge=lfs -text
2
+ *.arrow filter=lfs diff=lfs merge=lfs -text
3
+ *.bin filter=lfs diff=lfs merge=lfs -text
4
+ *.bz2 filter=lfs diff=lfs merge=lfs -text
5
+ *.ckpt filter=lfs diff=lfs merge=lfs -text
6
+ *.ftz filter=lfs diff=lfs merge=lfs -text
7
+ *.gz filter=lfs diff=lfs merge=lfs -text
8
+ *.h5 filter=lfs diff=lfs merge=lfs -text
9
+ *.joblib filter=lfs diff=lfs merge=lfs -text
10
+ *.lfs.* filter=lfs diff=lfs merge=lfs -text
11
+ *.mlmodel filter=lfs diff=lfs merge=lfs -text
12
+ *.model filter=lfs diff=lfs merge=lfs -text
13
+ *.msgpack filter=lfs diff=lfs merge=lfs -text
14
+ *.npy filter=lfs diff=lfs merge=lfs -text
15
+ *.npz filter=lfs diff=lfs merge=lfs -text
16
+ *.onnx filter=lfs diff=lfs merge=lfs -text
17
+ *.ot filter=lfs diff=lfs merge=lfs -text
18
+ *.parquet filter=lfs diff=lfs merge=lfs -text
19
+ *.pb filter=lfs diff=lfs merge=lfs -text
20
+ *.pickle filter=lfs diff=lfs merge=lfs -text
21
+ *.pkl filter=lfs diff=lfs merge=lfs -text
22
+ *.pt filter=lfs diff=lfs merge=lfs -text
23
+ *.pth filter=lfs diff=lfs merge=lfs -text
24
+ *.rar filter=lfs diff=lfs merge=lfs -text
25
+ *.safetensors filter=lfs diff=lfs merge=lfs -text
26
+ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
27
+ *.tar.* filter=lfs diff=lfs merge=lfs -text
28
+ *.tar filter=lfs diff=lfs merge=lfs -text
29
+ *.tflite filter=lfs diff=lfs merge=lfs -text
30
+ *.tgz filter=lfs diff=lfs merge=lfs -text
31
+ *.wasm filter=lfs diff=lfs merge=lfs -text
32
+ *.xz 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
GaetanMichelet__Llama-31-8B_task-2_180-samples_config-4/README.md ADDED
@@ -0,0 +1,105 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: meta-llama/Meta-Llama-3.1-8B-Instruct
3
+ datasets:
4
+ - GaetanMichelet/chat-60_ft_task-2
5
+ - GaetanMichelet/chat-120_ft_task-2
6
+ - GaetanMichelet/chat-180_ft_task-2
7
+ library_name: peft
8
+ license: llama3.1
9
+ tags:
10
+ - alignment-handbook
11
+ - trl
12
+ - sft
13
+ - generated_from_trainer
14
+ model-index:
15
+ - name: Llama-31-8B_task-2_180-samples_config-4
16
+ results: []
17
+ ---
18
+
19
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
20
+ should probably proofread and complete it, then remove this comment. -->
21
+
22
+ # Llama-31-8B_task-2_180-samples_config-4
23
+
24
+ This model is a fine-tuned version of [meta-llama/Meta-Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct) on the GaetanMichelet/chat-60_ft_task-2, the GaetanMichelet/chat-120_ft_task-2 and the GaetanMichelet/chat-180_ft_task-2 datasets.
25
+ It achieves the following results on the evaluation set:
26
+ - Loss: 0.7156
27
+
28
+ ## Model description
29
+
30
+ More information needed
31
+
32
+ ## Intended uses & limitations
33
+
34
+ More information needed
35
+
36
+ ## Training and evaluation data
37
+
38
+ More information needed
39
+
40
+ ## Training procedure
41
+
42
+ ### Training hyperparameters
43
+
44
+ The following hyperparameters were used during training:
45
+ - learning_rate: 1e-05
46
+ - train_batch_size: 1
47
+ - eval_batch_size: 1
48
+ - seed: 42
49
+ - distributed_type: multi-GPU
50
+ - gradient_accumulation_steps: 16
51
+ - total_train_batch_size: 16
52
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
53
+ - lr_scheduler_type: cosine
54
+ - lr_scheduler_warmup_ratio: 0.1
55
+ - num_epochs: 150
56
+
57
+ ### Training results
58
+
59
+ | Training Loss | Epoch | Step | Validation Loss |
60
+ |:-------------:|:-------:|:----:|:---------------:|
61
+ | 1.0917 | 0.9412 | 8 | 1.1326 |
62
+ | 1.1392 | 2.0 | 17 | 1.1271 |
63
+ | 1.1572 | 2.9412 | 25 | 1.1161 |
64
+ | 1.0856 | 4.0 | 34 | 1.0970 |
65
+ | 1.0789 | 4.9412 | 42 | 1.0719 |
66
+ | 1.0546 | 6.0 | 51 | 1.0337 |
67
+ | 0.9806 | 6.9412 | 59 | 0.9923 |
68
+ | 0.9617 | 8.0 | 68 | 0.9472 |
69
+ | 0.933 | 8.9412 | 76 | 0.9129 |
70
+ | 0.9005 | 10.0 | 85 | 0.8825 |
71
+ | 0.9183 | 10.9412 | 93 | 0.8578 |
72
+ | 0.7739 | 12.0 | 102 | 0.8335 |
73
+ | 0.7649 | 12.9412 | 110 | 0.8165 |
74
+ | 0.8197 | 14.0 | 119 | 0.8009 |
75
+ | 0.7488 | 14.9412 | 127 | 0.7889 |
76
+ | 0.7651 | 16.0 | 136 | 0.7770 |
77
+ | 0.6992 | 16.9412 | 144 | 0.7679 |
78
+ | 0.7609 | 18.0 | 153 | 0.7580 |
79
+ | 0.6868 | 18.9412 | 161 | 0.7510 |
80
+ | 0.7077 | 20.0 | 170 | 0.7437 |
81
+ | 0.6862 | 20.9412 | 178 | 0.7379 |
82
+ | 0.6939 | 22.0 | 187 | 0.7319 |
83
+ | 0.6564 | 22.9412 | 195 | 0.7275 |
84
+ | 0.6446 | 24.0 | 204 | 0.7236 |
85
+ | 0.6304 | 24.9412 | 212 | 0.7200 |
86
+ | 0.6583 | 26.0 | 221 | 0.7178 |
87
+ | 0.5974 | 26.9412 | 229 | 0.7159 |
88
+ | 0.6266 | 28.0 | 238 | 0.7159 |
89
+ | 0.6081 | 28.9412 | 246 | 0.7156 |
90
+ | 0.5853 | 30.0 | 255 | 0.7165 |
91
+ | 0.54 | 30.9412 | 263 | 0.7200 |
92
+ | 0.5438 | 32.0 | 272 | 0.7231 |
93
+ | 0.5163 | 32.9412 | 280 | 0.7268 |
94
+ | 0.5302 | 34.0 | 289 | 0.7345 |
95
+ | 0.4865 | 34.9412 | 297 | 0.7542 |
96
+ | 0.4774 | 36.0 | 306 | 0.7611 |
97
+
98
+
99
+ ### Framework versions
100
+
101
+ - PEFT 0.12.0
102
+ - Transformers 4.44.0
103
+ - Pytorch 2.1.2+cu121
104
+ - Datasets 2.20.0
105
+ - Tokenizers 0.19.1
GaetanMichelet__Llama-31-8B_task-2_180-samples_config-4/adapter_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "meta-llama/Meta-Llama-3.1-8B-Instruct",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 16,
14
+ "lora_dropout": 0.05,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 16,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "k_proj",
24
+ "down_proj",
25
+ "gate_proj",
26
+ "q_proj",
27
+ "v_proj",
28
+ "o_proj",
29
+ "up_proj"
30
+ ],
31
+ "task_type": "CAUSAL_LM",
32
+ "use_dora": false,
33
+ "use_rslora": false
34
+ }
GaetanMichelet__Llama-31-8B_task-2_180-samples_config-4/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f013ff6736a3c56cf3f2e1ce91c4ca7b6dec22499303b59a71f45a80eada264c
3
+ size 167832240
GaetanMichelet__Llama-31-8B_task-2_180-samples_config-4/all_results.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 36.0,
3
+ "eval_loss": 0.7155756950378418,
4
+ "eval_runtime": 36.9691,
5
+ "eval_samples": 36,
6
+ "eval_samples_per_second": 0.974,
7
+ "eval_steps_per_second": 0.974,
8
+ "total_flos": 4.686344037995643e+17,
9
+ "train_loss": 0.7647335636459924,
10
+ "train_runtime": 16723.6429,
11
+ "train_samples": 136,
12
+ "train_samples_per_second": 1.22,
13
+ "train_steps_per_second": 0.072
14
+ }
GaetanMichelet__Llama-31-8B_task-2_180-samples_config-4/config.json ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "meta-llama/Meta-Llama-3.1-8B-Instruct",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 128000,
9
+ "eos_token_id": [
10
+ 128001,
11
+ 128008,
12
+ 128009
13
+ ],
14
+ "hidden_act": "silu",
15
+ "hidden_size": 4096,
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 14336,
18
+ "max_position_embeddings": 131072,
19
+ "mlp_bias": false,
20
+ "model_type": "llama",
21
+ "num_attention_heads": 32,
22
+ "num_hidden_layers": 32,
23
+ "num_key_value_heads": 8,
24
+ "pretraining_tp": 1,
25
+ "quantization_config": {
26
+ "_load_in_4bit": true,
27
+ "_load_in_8bit": false,
28
+ "bnb_4bit_compute_dtype": "bfloat16",
29
+ "bnb_4bit_quant_storage": "uint8",
30
+ "bnb_4bit_quant_type": "nf4",
31
+ "bnb_4bit_use_double_quant": false,
32
+ "llm_int8_enable_fp32_cpu_offload": false,
33
+ "llm_int8_has_fp16_weight": false,
34
+ "llm_int8_skip_modules": null,
35
+ "llm_int8_threshold": 6.0,
36
+ "load_in_4bit": true,
37
+ "load_in_8bit": false,
38
+ "quant_method": "bitsandbytes"
39
+ },
40
+ "rms_norm_eps": 1e-05,
41
+ "rope_scaling": {
42
+ "factor": 8.0,
43
+ "high_freq_factor": 4.0,
44
+ "low_freq_factor": 1.0,
45
+ "original_max_position_embeddings": 8192,
46
+ "rope_type": "llama3"
47
+ },
48
+ "rope_theta": 500000.0,
49
+ "tie_word_embeddings": false,
50
+ "torch_dtype": "bfloat16",
51
+ "transformers_version": "4.44.0",
52
+ "use_cache": true,
53
+ "vocab_size": 128256
54
+ }
GaetanMichelet__Llama-31-8B_task-2_180-samples_config-4/eval_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 36.0,
3
+ "eval_loss": 0.7155756950378418,
4
+ "eval_runtime": 36.9691,
5
+ "eval_samples": 36,
6
+ "eval_samples_per_second": 0.974,
7
+ "eval_steps_per_second": 0.974
8
+ }
GaetanMichelet__Llama-31-8B_task-2_180-samples_config-4/runs/Aug18_22-14-48_9mqd6r3-l/events.out.tfevents.1724012108.9mqd6r3-l.3190443.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:04846641e3e4abf19c6f5afd1c431b29c5dfa810d72fe05e31ed3371c86a4ea0
3
+ size 49090
GaetanMichelet__Llama-31-8B_task-2_180-samples_config-4/runs/Aug18_22-14-48_9mqd6r3-l/events.out.tfevents.1724028884.9mqd6r3-l.3190443.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e712ab914267d3347af6bfca489598ae627cab49f8bdc6fe438e7e55e280b299
3
+ size 359
GaetanMichelet__Llama-31-8B_task-2_180-samples_config-4/special_tokens_map.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|begin_of_text|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|eot_id|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<|eot_id|>"
17
+ }
GaetanMichelet__Llama-31-8B_task-2_180-samples_config-4/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
GaetanMichelet__Llama-31-8B_task-2_180-samples_config-4/tokenizer_config.json ADDED
@@ -0,0 +1,2063 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "128000": {
4
+ "content": "<|begin_of_text|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "128001": {
12
+ "content": "<|end_of_text|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "128002": {
20
+ "content": "<|reserved_special_token_0|>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "128003": {
28
+ "content": "<|reserved_special_token_1|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "128004": {
36
+ "content": "<|finetune_right_pad_id|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "128005": {
44
+ "content": "<|reserved_special_token_2|>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "128006": {
52
+ "content": "<|start_header_id|>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "128007": {
60
+ "content": "<|end_header_id|>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "128008": {
68
+ "content": "<|eom_id|>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "128009": {
76
+ "content": "<|eot_id|>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "128010": {
84
+ "content": "<|python_tag|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "128011": {
92
+ "content": "<|reserved_special_token_3|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "128012": {
100
+ "content": "<|reserved_special_token_4|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "128013": {
108
+ "content": "<|reserved_special_token_5|>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "128014": {
116
+ "content": "<|reserved_special_token_6|>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "128015": {
124
+ "content": "<|reserved_special_token_7|>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "128016": {
132
+ "content": "<|reserved_special_token_8|>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "128017": {
140
+ "content": "<|reserved_special_token_9|>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "128018": {
148
+ "content": "<|reserved_special_token_10|>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "128019": {
156
+ "content": "<|reserved_special_token_11|>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "128020": {
164
+ "content": "<|reserved_special_token_12|>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "128021": {
172
+ "content": "<|reserved_special_token_13|>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "128022": {
180
+ "content": "<|reserved_special_token_14|>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "128023": {
188
+ "content": "<|reserved_special_token_15|>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "128024": {
196
+ "content": "<|reserved_special_token_16|>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "128025": {
204
+ "content": "<|reserved_special_token_17|>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "128026": {
212
+ "content": "<|reserved_special_token_18|>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "128027": {
220
+ "content": "<|reserved_special_token_19|>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "128028": {
228
+ "content": "<|reserved_special_token_20|>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "128029": {
236
+ "content": "<|reserved_special_token_21|>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "128030": {
244
+ "content": "<|reserved_special_token_22|>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "128031": {
252
+ "content": "<|reserved_special_token_23|>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "128032": {
260
+ "content": "<|reserved_special_token_24|>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "128033": {
268
+ "content": "<|reserved_special_token_25|>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "128034": {
276
+ "content": "<|reserved_special_token_26|>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "128035": {
284
+ "content": "<|reserved_special_token_27|>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "128036": {
292
+ "content": "<|reserved_special_token_28|>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "128037": {
300
+ "content": "<|reserved_special_token_29|>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "128038": {
308
+ "content": "<|reserved_special_token_30|>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "128039": {
316
+ "content": "<|reserved_special_token_31|>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "128040": {
324
+ "content": "<|reserved_special_token_32|>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "128041": {
332
+ "content": "<|reserved_special_token_33|>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "128042": {
340
+ "content": "<|reserved_special_token_34|>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "128043": {
348
+ "content": "<|reserved_special_token_35|>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "128044": {
356
+ "content": "<|reserved_special_token_36|>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "128045": {
364
+ "content": "<|reserved_special_token_37|>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "128046": {
372
+ "content": "<|reserved_special_token_38|>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "128047": {
380
+ "content": "<|reserved_special_token_39|>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "128048": {
388
+ "content": "<|reserved_special_token_40|>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "128049": {
396
+ "content": "<|reserved_special_token_41|>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "128050": {
404
+ "content": "<|reserved_special_token_42|>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "128051": {
412
+ "content": "<|reserved_special_token_43|>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "128052": {
420
+ "content": "<|reserved_special_token_44|>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "128053": {
428
+ "content": "<|reserved_special_token_45|>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "128054": {
436
+ "content": "<|reserved_special_token_46|>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "128055": {
444
+ "content": "<|reserved_special_token_47|>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "128056": {
452
+ "content": "<|reserved_special_token_48|>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "128057": {
460
+ "content": "<|reserved_special_token_49|>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "128058": {
468
+ "content": "<|reserved_special_token_50|>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "128059": {
476
+ "content": "<|reserved_special_token_51|>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "128060": {
484
+ "content": "<|reserved_special_token_52|>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "128061": {
492
+ "content": "<|reserved_special_token_53|>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "128062": {
500
+ "content": "<|reserved_special_token_54|>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "128063": {
508
+ "content": "<|reserved_special_token_55|>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "128064": {
516
+ "content": "<|reserved_special_token_56|>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "128065": {
524
+ "content": "<|reserved_special_token_57|>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "128066": {
532
+ "content": "<|reserved_special_token_58|>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "128067": {
540
+ "content": "<|reserved_special_token_59|>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "128068": {
548
+ "content": "<|reserved_special_token_60|>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "128069": {
556
+ "content": "<|reserved_special_token_61|>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "128070": {
564
+ "content": "<|reserved_special_token_62|>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "128071": {
572
+ "content": "<|reserved_special_token_63|>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "128072": {
580
+ "content": "<|reserved_special_token_64|>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "128073": {
588
+ "content": "<|reserved_special_token_65|>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "128074": {
596
+ "content": "<|reserved_special_token_66|>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "128075": {
604
+ "content": "<|reserved_special_token_67|>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "128076": {
612
+ "content": "<|reserved_special_token_68|>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "128077": {
620
+ "content": "<|reserved_special_token_69|>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "128078": {
628
+ "content": "<|reserved_special_token_70|>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "128079": {
636
+ "content": "<|reserved_special_token_71|>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "128080": {
644
+ "content": "<|reserved_special_token_72|>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "128081": {
652
+ "content": "<|reserved_special_token_73|>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "128082": {
660
+ "content": "<|reserved_special_token_74|>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "128083": {
668
+ "content": "<|reserved_special_token_75|>",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "128084": {
676
+ "content": "<|reserved_special_token_76|>",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "128085": {
684
+ "content": "<|reserved_special_token_77|>",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "128086": {
692
+ "content": "<|reserved_special_token_78|>",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "128087": {
700
+ "content": "<|reserved_special_token_79|>",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "128088": {
708
+ "content": "<|reserved_special_token_80|>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "128089": {
716
+ "content": "<|reserved_special_token_81|>",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "128090": {
724
+ "content": "<|reserved_special_token_82|>",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "128091": {
732
+ "content": "<|reserved_special_token_83|>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "128092": {
740
+ "content": "<|reserved_special_token_84|>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "128093": {
748
+ "content": "<|reserved_special_token_85|>",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "128094": {
756
+ "content": "<|reserved_special_token_86|>",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "128095": {
764
+ "content": "<|reserved_special_token_87|>",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "128096": {
772
+ "content": "<|reserved_special_token_88|>",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "128097": {
780
+ "content": "<|reserved_special_token_89|>",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "128098": {
788
+ "content": "<|reserved_special_token_90|>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "128099": {
796
+ "content": "<|reserved_special_token_91|>",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "128100": {
804
+ "content": "<|reserved_special_token_92|>",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "128101": {
812
+ "content": "<|reserved_special_token_93|>",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "128102": {
820
+ "content": "<|reserved_special_token_94|>",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ },
827
+ "128103": {
828
+ "content": "<|reserved_special_token_95|>",
829
+ "lstrip": false,
830
+ "normalized": false,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": true
834
+ },
835
+ "128104": {
836
+ "content": "<|reserved_special_token_96|>",
837
+ "lstrip": false,
838
+ "normalized": false,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": true
842
+ },
843
+ "128105": {
844
+ "content": "<|reserved_special_token_97|>",
845
+ "lstrip": false,
846
+ "normalized": false,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": true
850
+ },
851
+ "128106": {
852
+ "content": "<|reserved_special_token_98|>",
853
+ "lstrip": false,
854
+ "normalized": false,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": true
858
+ },
859
+ "128107": {
860
+ "content": "<|reserved_special_token_99|>",
861
+ "lstrip": false,
862
+ "normalized": false,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": true
866
+ },
867
+ "128108": {
868
+ "content": "<|reserved_special_token_100|>",
869
+ "lstrip": false,
870
+ "normalized": false,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": true
874
+ },
875
+ "128109": {
876
+ "content": "<|reserved_special_token_101|>",
877
+ "lstrip": false,
878
+ "normalized": false,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": true
882
+ },
883
+ "128110": {
884
+ "content": "<|reserved_special_token_102|>",
885
+ "lstrip": false,
886
+ "normalized": false,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": true
890
+ },
891
+ "128111": {
892
+ "content": "<|reserved_special_token_103|>",
893
+ "lstrip": false,
894
+ "normalized": false,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": true
898
+ },
899
+ "128112": {
900
+ "content": "<|reserved_special_token_104|>",
901
+ "lstrip": false,
902
+ "normalized": false,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": true
906
+ },
907
+ "128113": {
908
+ "content": "<|reserved_special_token_105|>",
909
+ "lstrip": false,
910
+ "normalized": false,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": true
914
+ },
915
+ "128114": {
916
+ "content": "<|reserved_special_token_106|>",
917
+ "lstrip": false,
918
+ "normalized": false,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": true
922
+ },
923
+ "128115": {
924
+ "content": "<|reserved_special_token_107|>",
925
+ "lstrip": false,
926
+ "normalized": false,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": true
930
+ },
931
+ "128116": {
932
+ "content": "<|reserved_special_token_108|>",
933
+ "lstrip": false,
934
+ "normalized": false,
935
+ "rstrip": false,
936
+ "single_word": false,
937
+ "special": true
938
+ },
939
+ "128117": {
940
+ "content": "<|reserved_special_token_109|>",
941
+ "lstrip": false,
942
+ "normalized": false,
943
+ "rstrip": false,
944
+ "single_word": false,
945
+ "special": true
946
+ },
947
+ "128118": {
948
+ "content": "<|reserved_special_token_110|>",
949
+ "lstrip": false,
950
+ "normalized": false,
951
+ "rstrip": false,
952
+ "single_word": false,
953
+ "special": true
954
+ },
955
+ "128119": {
956
+ "content": "<|reserved_special_token_111|>",
957
+ "lstrip": false,
958
+ "normalized": false,
959
+ "rstrip": false,
960
+ "single_word": false,
961
+ "special": true
962
+ },
963
+ "128120": {
964
+ "content": "<|reserved_special_token_112|>",
965
+ "lstrip": false,
966
+ "normalized": false,
967
+ "rstrip": false,
968
+ "single_word": false,
969
+ "special": true
970
+ },
971
+ "128121": {
972
+ "content": "<|reserved_special_token_113|>",
973
+ "lstrip": false,
974
+ "normalized": false,
975
+ "rstrip": false,
976
+ "single_word": false,
977
+ "special": true
978
+ },
979
+ "128122": {
980
+ "content": "<|reserved_special_token_114|>",
981
+ "lstrip": false,
982
+ "normalized": false,
983
+ "rstrip": false,
984
+ "single_word": false,
985
+ "special": true
986
+ },
987
+ "128123": {
988
+ "content": "<|reserved_special_token_115|>",
989
+ "lstrip": false,
990
+ "normalized": false,
991
+ "rstrip": false,
992
+ "single_word": false,
993
+ "special": true
994
+ },
995
+ "128124": {
996
+ "content": "<|reserved_special_token_116|>",
997
+ "lstrip": false,
998
+ "normalized": false,
999
+ "rstrip": false,
1000
+ "single_word": false,
1001
+ "special": true
1002
+ },
1003
+ "128125": {
1004
+ "content": "<|reserved_special_token_117|>",
1005
+ "lstrip": false,
1006
+ "normalized": false,
1007
+ "rstrip": false,
1008
+ "single_word": false,
1009
+ "special": true
1010
+ },
1011
+ "128126": {
1012
+ "content": "<|reserved_special_token_118|>",
1013
+ "lstrip": false,
1014
+ "normalized": false,
1015
+ "rstrip": false,
1016
+ "single_word": false,
1017
+ "special": true
1018
+ },
1019
+ "128127": {
1020
+ "content": "<|reserved_special_token_119|>",
1021
+ "lstrip": false,
1022
+ "normalized": false,
1023
+ "rstrip": false,
1024
+ "single_word": false,
1025
+ "special": true
1026
+ },
1027
+ "128128": {
1028
+ "content": "<|reserved_special_token_120|>",
1029
+ "lstrip": false,
1030
+ "normalized": false,
1031
+ "rstrip": false,
1032
+ "single_word": false,
1033
+ "special": true
1034
+ },
1035
+ "128129": {
1036
+ "content": "<|reserved_special_token_121|>",
1037
+ "lstrip": false,
1038
+ "normalized": false,
1039
+ "rstrip": false,
1040
+ "single_word": false,
1041
+ "special": true
1042
+ },
1043
+ "128130": {
1044
+ "content": "<|reserved_special_token_122|>",
1045
+ "lstrip": false,
1046
+ "normalized": false,
1047
+ "rstrip": false,
1048
+ "single_word": false,
1049
+ "special": true
1050
+ },
1051
+ "128131": {
1052
+ "content": "<|reserved_special_token_123|>",
1053
+ "lstrip": false,
1054
+ "normalized": false,
1055
+ "rstrip": false,
1056
+ "single_word": false,
1057
+ "special": true
1058
+ },
1059
+ "128132": {
1060
+ "content": "<|reserved_special_token_124|>",
1061
+ "lstrip": false,
1062
+ "normalized": false,
1063
+ "rstrip": false,
1064
+ "single_word": false,
1065
+ "special": true
1066
+ },
1067
+ "128133": {
1068
+ "content": "<|reserved_special_token_125|>",
1069
+ "lstrip": false,
1070
+ "normalized": false,
1071
+ "rstrip": false,
1072
+ "single_word": false,
1073
+ "special": true
1074
+ },
1075
+ "128134": {
1076
+ "content": "<|reserved_special_token_126|>",
1077
+ "lstrip": false,
1078
+ "normalized": false,
1079
+ "rstrip": false,
1080
+ "single_word": false,
1081
+ "special": true
1082
+ },
1083
+ "128135": {
1084
+ "content": "<|reserved_special_token_127|>",
1085
+ "lstrip": false,
1086
+ "normalized": false,
1087
+ "rstrip": false,
1088
+ "single_word": false,
1089
+ "special": true
1090
+ },
1091
+ "128136": {
1092
+ "content": "<|reserved_special_token_128|>",
1093
+ "lstrip": false,
1094
+ "normalized": false,
1095
+ "rstrip": false,
1096
+ "single_word": false,
1097
+ "special": true
1098
+ },
1099
+ "128137": {
1100
+ "content": "<|reserved_special_token_129|>",
1101
+ "lstrip": false,
1102
+ "normalized": false,
1103
+ "rstrip": false,
1104
+ "single_word": false,
1105
+ "special": true
1106
+ },
1107
+ "128138": {
1108
+ "content": "<|reserved_special_token_130|>",
1109
+ "lstrip": false,
1110
+ "normalized": false,
1111
+ "rstrip": false,
1112
+ "single_word": false,
1113
+ "special": true
1114
+ },
1115
+ "128139": {
1116
+ "content": "<|reserved_special_token_131|>",
1117
+ "lstrip": false,
1118
+ "normalized": false,
1119
+ "rstrip": false,
1120
+ "single_word": false,
1121
+ "special": true
1122
+ },
1123
+ "128140": {
1124
+ "content": "<|reserved_special_token_132|>",
1125
+ "lstrip": false,
1126
+ "normalized": false,
1127
+ "rstrip": false,
1128
+ "single_word": false,
1129
+ "special": true
1130
+ },
1131
+ "128141": {
1132
+ "content": "<|reserved_special_token_133|>",
1133
+ "lstrip": false,
1134
+ "normalized": false,
1135
+ "rstrip": false,
1136
+ "single_word": false,
1137
+ "special": true
1138
+ },
1139
+ "128142": {
1140
+ "content": "<|reserved_special_token_134|>",
1141
+ "lstrip": false,
1142
+ "normalized": false,
1143
+ "rstrip": false,
1144
+ "single_word": false,
1145
+ "special": true
1146
+ },
1147
+ "128143": {
1148
+ "content": "<|reserved_special_token_135|>",
1149
+ "lstrip": false,
1150
+ "normalized": false,
1151
+ "rstrip": false,
1152
+ "single_word": false,
1153
+ "special": true
1154
+ },
1155
+ "128144": {
1156
+ "content": "<|reserved_special_token_136|>",
1157
+ "lstrip": false,
1158
+ "normalized": false,
1159
+ "rstrip": false,
1160
+ "single_word": false,
1161
+ "special": true
1162
+ },
1163
+ "128145": {
1164
+ "content": "<|reserved_special_token_137|>",
1165
+ "lstrip": false,
1166
+ "normalized": false,
1167
+ "rstrip": false,
1168
+ "single_word": false,
1169
+ "special": true
1170
+ },
1171
+ "128146": {
1172
+ "content": "<|reserved_special_token_138|>",
1173
+ "lstrip": false,
1174
+ "normalized": false,
1175
+ "rstrip": false,
1176
+ "single_word": false,
1177
+ "special": true
1178
+ },
1179
+ "128147": {
1180
+ "content": "<|reserved_special_token_139|>",
1181
+ "lstrip": false,
1182
+ "normalized": false,
1183
+ "rstrip": false,
1184
+ "single_word": false,
1185
+ "special": true
1186
+ },
1187
+ "128148": {
1188
+ "content": "<|reserved_special_token_140|>",
1189
+ "lstrip": false,
1190
+ "normalized": false,
1191
+ "rstrip": false,
1192
+ "single_word": false,
1193
+ "special": true
1194
+ },
1195
+ "128149": {
1196
+ "content": "<|reserved_special_token_141|>",
1197
+ "lstrip": false,
1198
+ "normalized": false,
1199
+ "rstrip": false,
1200
+ "single_word": false,
1201
+ "special": true
1202
+ },
1203
+ "128150": {
1204
+ "content": "<|reserved_special_token_142|>",
1205
+ "lstrip": false,
1206
+ "normalized": false,
1207
+ "rstrip": false,
1208
+ "single_word": false,
1209
+ "special": true
1210
+ },
1211
+ "128151": {
1212
+ "content": "<|reserved_special_token_143|>",
1213
+ "lstrip": false,
1214
+ "normalized": false,
1215
+ "rstrip": false,
1216
+ "single_word": false,
1217
+ "special": true
1218
+ },
1219
+ "128152": {
1220
+ "content": "<|reserved_special_token_144|>",
1221
+ "lstrip": false,
1222
+ "normalized": false,
1223
+ "rstrip": false,
1224
+ "single_word": false,
1225
+ "special": true
1226
+ },
1227
+ "128153": {
1228
+ "content": "<|reserved_special_token_145|>",
1229
+ "lstrip": false,
1230
+ "normalized": false,
1231
+ "rstrip": false,
1232
+ "single_word": false,
1233
+ "special": true
1234
+ },
1235
+ "128154": {
1236
+ "content": "<|reserved_special_token_146|>",
1237
+ "lstrip": false,
1238
+ "normalized": false,
1239
+ "rstrip": false,
1240
+ "single_word": false,
1241
+ "special": true
1242
+ },
1243
+ "128155": {
1244
+ "content": "<|reserved_special_token_147|>",
1245
+ "lstrip": false,
1246
+ "normalized": false,
1247
+ "rstrip": false,
1248
+ "single_word": false,
1249
+ "special": true
1250
+ },
1251
+ "128156": {
1252
+ "content": "<|reserved_special_token_148|>",
1253
+ "lstrip": false,
1254
+ "normalized": false,
1255
+ "rstrip": false,
1256
+ "single_word": false,
1257
+ "special": true
1258
+ },
1259
+ "128157": {
1260
+ "content": "<|reserved_special_token_149|>",
1261
+ "lstrip": false,
1262
+ "normalized": false,
1263
+ "rstrip": false,
1264
+ "single_word": false,
1265
+ "special": true
1266
+ },
1267
+ "128158": {
1268
+ "content": "<|reserved_special_token_150|>",
1269
+ "lstrip": false,
1270
+ "normalized": false,
1271
+ "rstrip": false,
1272
+ "single_word": false,
1273
+ "special": true
1274
+ },
1275
+ "128159": {
1276
+ "content": "<|reserved_special_token_151|>",
1277
+ "lstrip": false,
1278
+ "normalized": false,
1279
+ "rstrip": false,
1280
+ "single_word": false,
1281
+ "special": true
1282
+ },
1283
+ "128160": {
1284
+ "content": "<|reserved_special_token_152|>",
1285
+ "lstrip": false,
1286
+ "normalized": false,
1287
+ "rstrip": false,
1288
+ "single_word": false,
1289
+ "special": true
1290
+ },
1291
+ "128161": {
1292
+ "content": "<|reserved_special_token_153|>",
1293
+ "lstrip": false,
1294
+ "normalized": false,
1295
+ "rstrip": false,
1296
+ "single_word": false,
1297
+ "special": true
1298
+ },
1299
+ "128162": {
1300
+ "content": "<|reserved_special_token_154|>",
1301
+ "lstrip": false,
1302
+ "normalized": false,
1303
+ "rstrip": false,
1304
+ "single_word": false,
1305
+ "special": true
1306
+ },
1307
+ "128163": {
1308
+ "content": "<|reserved_special_token_155|>",
1309
+ "lstrip": false,
1310
+ "normalized": false,
1311
+ "rstrip": false,
1312
+ "single_word": false,
1313
+ "special": true
1314
+ },
1315
+ "128164": {
1316
+ "content": "<|reserved_special_token_156|>",
1317
+ "lstrip": false,
1318
+ "normalized": false,
1319
+ "rstrip": false,
1320
+ "single_word": false,
1321
+ "special": true
1322
+ },
1323
+ "128165": {
1324
+ "content": "<|reserved_special_token_157|>",
1325
+ "lstrip": false,
1326
+ "normalized": false,
1327
+ "rstrip": false,
1328
+ "single_word": false,
1329
+ "special": true
1330
+ },
1331
+ "128166": {
1332
+ "content": "<|reserved_special_token_158|>",
1333
+ "lstrip": false,
1334
+ "normalized": false,
1335
+ "rstrip": false,
1336
+ "single_word": false,
1337
+ "special": true
1338
+ },
1339
+ "128167": {
1340
+ "content": "<|reserved_special_token_159|>",
1341
+ "lstrip": false,
1342
+ "normalized": false,
1343
+ "rstrip": false,
1344
+ "single_word": false,
1345
+ "special": true
1346
+ },
1347
+ "128168": {
1348
+ "content": "<|reserved_special_token_160|>",
1349
+ "lstrip": false,
1350
+ "normalized": false,
1351
+ "rstrip": false,
1352
+ "single_word": false,
1353
+ "special": true
1354
+ },
1355
+ "128169": {
1356
+ "content": "<|reserved_special_token_161|>",
1357
+ "lstrip": false,
1358
+ "normalized": false,
1359
+ "rstrip": false,
1360
+ "single_word": false,
1361
+ "special": true
1362
+ },
1363
+ "128170": {
1364
+ "content": "<|reserved_special_token_162|>",
1365
+ "lstrip": false,
1366
+ "normalized": false,
1367
+ "rstrip": false,
1368
+ "single_word": false,
1369
+ "special": true
1370
+ },
1371
+ "128171": {
1372
+ "content": "<|reserved_special_token_163|>",
1373
+ "lstrip": false,
1374
+ "normalized": false,
1375
+ "rstrip": false,
1376
+ "single_word": false,
1377
+ "special": true
1378
+ },
1379
+ "128172": {
1380
+ "content": "<|reserved_special_token_164|>",
1381
+ "lstrip": false,
1382
+ "normalized": false,
1383
+ "rstrip": false,
1384
+ "single_word": false,
1385
+ "special": true
1386
+ },
1387
+ "128173": {
1388
+ "content": "<|reserved_special_token_165|>",
1389
+ "lstrip": false,
1390
+ "normalized": false,
1391
+ "rstrip": false,
1392
+ "single_word": false,
1393
+ "special": true
1394
+ },
1395
+ "128174": {
1396
+ "content": "<|reserved_special_token_166|>",
1397
+ "lstrip": false,
1398
+ "normalized": false,
1399
+ "rstrip": false,
1400
+ "single_word": false,
1401
+ "special": true
1402
+ },
1403
+ "128175": {
1404
+ "content": "<|reserved_special_token_167|>",
1405
+ "lstrip": false,
1406
+ "normalized": false,
1407
+ "rstrip": false,
1408
+ "single_word": false,
1409
+ "special": true
1410
+ },
1411
+ "128176": {
1412
+ "content": "<|reserved_special_token_168|>",
1413
+ "lstrip": false,
1414
+ "normalized": false,
1415
+ "rstrip": false,
1416
+ "single_word": false,
1417
+ "special": true
1418
+ },
1419
+ "128177": {
1420
+ "content": "<|reserved_special_token_169|>",
1421
+ "lstrip": false,
1422
+ "normalized": false,
1423
+ "rstrip": false,
1424
+ "single_word": false,
1425
+ "special": true
1426
+ },
1427
+ "128178": {
1428
+ "content": "<|reserved_special_token_170|>",
1429
+ "lstrip": false,
1430
+ "normalized": false,
1431
+ "rstrip": false,
1432
+ "single_word": false,
1433
+ "special": true
1434
+ },
1435
+ "128179": {
1436
+ "content": "<|reserved_special_token_171|>",
1437
+ "lstrip": false,
1438
+ "normalized": false,
1439
+ "rstrip": false,
1440
+ "single_word": false,
1441
+ "special": true
1442
+ },
1443
+ "128180": {
1444
+ "content": "<|reserved_special_token_172|>",
1445
+ "lstrip": false,
1446
+ "normalized": false,
1447
+ "rstrip": false,
1448
+ "single_word": false,
1449
+ "special": true
1450
+ },
1451
+ "128181": {
1452
+ "content": "<|reserved_special_token_173|>",
1453
+ "lstrip": false,
1454
+ "normalized": false,
1455
+ "rstrip": false,
1456
+ "single_word": false,
1457
+ "special": true
1458
+ },
1459
+ "128182": {
1460
+ "content": "<|reserved_special_token_174|>",
1461
+ "lstrip": false,
1462
+ "normalized": false,
1463
+ "rstrip": false,
1464
+ "single_word": false,
1465
+ "special": true
1466
+ },
1467
+ "128183": {
1468
+ "content": "<|reserved_special_token_175|>",
1469
+ "lstrip": false,
1470
+ "normalized": false,
1471
+ "rstrip": false,
1472
+ "single_word": false,
1473
+ "special": true
1474
+ },
1475
+ "128184": {
1476
+ "content": "<|reserved_special_token_176|>",
1477
+ "lstrip": false,
1478
+ "normalized": false,
1479
+ "rstrip": false,
1480
+ "single_word": false,
1481
+ "special": true
1482
+ },
1483
+ "128185": {
1484
+ "content": "<|reserved_special_token_177|>",
1485
+ "lstrip": false,
1486
+ "normalized": false,
1487
+ "rstrip": false,
1488
+ "single_word": false,
1489
+ "special": true
1490
+ },
1491
+ "128186": {
1492
+ "content": "<|reserved_special_token_178|>",
1493
+ "lstrip": false,
1494
+ "normalized": false,
1495
+ "rstrip": false,
1496
+ "single_word": false,
1497
+ "special": true
1498
+ },
1499
+ "128187": {
1500
+ "content": "<|reserved_special_token_179|>",
1501
+ "lstrip": false,
1502
+ "normalized": false,
1503
+ "rstrip": false,
1504
+ "single_word": false,
1505
+ "special": true
1506
+ },
1507
+ "128188": {
1508
+ "content": "<|reserved_special_token_180|>",
1509
+ "lstrip": false,
1510
+ "normalized": false,
1511
+ "rstrip": false,
1512
+ "single_word": false,
1513
+ "special": true
1514
+ },
1515
+ "128189": {
1516
+ "content": "<|reserved_special_token_181|>",
1517
+ "lstrip": false,
1518
+ "normalized": false,
1519
+ "rstrip": false,
1520
+ "single_word": false,
1521
+ "special": true
1522
+ },
1523
+ "128190": {
1524
+ "content": "<|reserved_special_token_182|>",
1525
+ "lstrip": false,
1526
+ "normalized": false,
1527
+ "rstrip": false,
1528
+ "single_word": false,
1529
+ "special": true
1530
+ },
1531
+ "128191": {
1532
+ "content": "<|reserved_special_token_183|>",
1533
+ "lstrip": false,
1534
+ "normalized": false,
1535
+ "rstrip": false,
1536
+ "single_word": false,
1537
+ "special": true
1538
+ },
1539
+ "128192": {
1540
+ "content": "<|reserved_special_token_184|>",
1541
+ "lstrip": false,
1542
+ "normalized": false,
1543
+ "rstrip": false,
1544
+ "single_word": false,
1545
+ "special": true
1546
+ },
1547
+ "128193": {
1548
+ "content": "<|reserved_special_token_185|>",
1549
+ "lstrip": false,
1550
+ "normalized": false,
1551
+ "rstrip": false,
1552
+ "single_word": false,
1553
+ "special": true
1554
+ },
1555
+ "128194": {
1556
+ "content": "<|reserved_special_token_186|>",
1557
+ "lstrip": false,
1558
+ "normalized": false,
1559
+ "rstrip": false,
1560
+ "single_word": false,
1561
+ "special": true
1562
+ },
1563
+ "128195": {
1564
+ "content": "<|reserved_special_token_187|>",
1565
+ "lstrip": false,
1566
+ "normalized": false,
1567
+ "rstrip": false,
1568
+ "single_word": false,
1569
+ "special": true
1570
+ },
1571
+ "128196": {
1572
+ "content": "<|reserved_special_token_188|>",
1573
+ "lstrip": false,
1574
+ "normalized": false,
1575
+ "rstrip": false,
1576
+ "single_word": false,
1577
+ "special": true
1578
+ },
1579
+ "128197": {
1580
+ "content": "<|reserved_special_token_189|>",
1581
+ "lstrip": false,
1582
+ "normalized": false,
1583
+ "rstrip": false,
1584
+ "single_word": false,
1585
+ "special": true
1586
+ },
1587
+ "128198": {
1588
+ "content": "<|reserved_special_token_190|>",
1589
+ "lstrip": false,
1590
+ "normalized": false,
1591
+ "rstrip": false,
1592
+ "single_word": false,
1593
+ "special": true
1594
+ },
1595
+ "128199": {
1596
+ "content": "<|reserved_special_token_191|>",
1597
+ "lstrip": false,
1598
+ "normalized": false,
1599
+ "rstrip": false,
1600
+ "single_word": false,
1601
+ "special": true
1602
+ },
1603
+ "128200": {
1604
+ "content": "<|reserved_special_token_192|>",
1605
+ "lstrip": false,
1606
+ "normalized": false,
1607
+ "rstrip": false,
1608
+ "single_word": false,
1609
+ "special": true
1610
+ },
1611
+ "128201": {
1612
+ "content": "<|reserved_special_token_193|>",
1613
+ "lstrip": false,
1614
+ "normalized": false,
1615
+ "rstrip": false,
1616
+ "single_word": false,
1617
+ "special": true
1618
+ },
1619
+ "128202": {
1620
+ "content": "<|reserved_special_token_194|>",
1621
+ "lstrip": false,
1622
+ "normalized": false,
1623
+ "rstrip": false,
1624
+ "single_word": false,
1625
+ "special": true
1626
+ },
1627
+ "128203": {
1628
+ "content": "<|reserved_special_token_195|>",
1629
+ "lstrip": false,
1630
+ "normalized": false,
1631
+ "rstrip": false,
1632
+ "single_word": false,
1633
+ "special": true
1634
+ },
1635
+ "128204": {
1636
+ "content": "<|reserved_special_token_196|>",
1637
+ "lstrip": false,
1638
+ "normalized": false,
1639
+ "rstrip": false,
1640
+ "single_word": false,
1641
+ "special": true
1642
+ },
1643
+ "128205": {
1644
+ "content": "<|reserved_special_token_197|>",
1645
+ "lstrip": false,
1646
+ "normalized": false,
1647
+ "rstrip": false,
1648
+ "single_word": false,
1649
+ "special": true
1650
+ },
1651
+ "128206": {
1652
+ "content": "<|reserved_special_token_198|>",
1653
+ "lstrip": false,
1654
+ "normalized": false,
1655
+ "rstrip": false,
1656
+ "single_word": false,
1657
+ "special": true
1658
+ },
1659
+ "128207": {
1660
+ "content": "<|reserved_special_token_199|>",
1661
+ "lstrip": false,
1662
+ "normalized": false,
1663
+ "rstrip": false,
1664
+ "single_word": false,
1665
+ "special": true
1666
+ },
1667
+ "128208": {
1668
+ "content": "<|reserved_special_token_200|>",
1669
+ "lstrip": false,
1670
+ "normalized": false,
1671
+ "rstrip": false,
1672
+ "single_word": false,
1673
+ "special": true
1674
+ },
1675
+ "128209": {
1676
+ "content": "<|reserved_special_token_201|>",
1677
+ "lstrip": false,
1678
+ "normalized": false,
1679
+ "rstrip": false,
1680
+ "single_word": false,
1681
+ "special": true
1682
+ },
1683
+ "128210": {
1684
+ "content": "<|reserved_special_token_202|>",
1685
+ "lstrip": false,
1686
+ "normalized": false,
1687
+ "rstrip": false,
1688
+ "single_word": false,
1689
+ "special": true
1690
+ },
1691
+ "128211": {
1692
+ "content": "<|reserved_special_token_203|>",
1693
+ "lstrip": false,
1694
+ "normalized": false,
1695
+ "rstrip": false,
1696
+ "single_word": false,
1697
+ "special": true
1698
+ },
1699
+ "128212": {
1700
+ "content": "<|reserved_special_token_204|>",
1701
+ "lstrip": false,
1702
+ "normalized": false,
1703
+ "rstrip": false,
1704
+ "single_word": false,
1705
+ "special": true
1706
+ },
1707
+ "128213": {
1708
+ "content": "<|reserved_special_token_205|>",
1709
+ "lstrip": false,
1710
+ "normalized": false,
1711
+ "rstrip": false,
1712
+ "single_word": false,
1713
+ "special": true
1714
+ },
1715
+ "128214": {
1716
+ "content": "<|reserved_special_token_206|>",
1717
+ "lstrip": false,
1718
+ "normalized": false,
1719
+ "rstrip": false,
1720
+ "single_word": false,
1721
+ "special": true
1722
+ },
1723
+ "128215": {
1724
+ "content": "<|reserved_special_token_207|>",
1725
+ "lstrip": false,
1726
+ "normalized": false,
1727
+ "rstrip": false,
1728
+ "single_word": false,
1729
+ "special": true
1730
+ },
1731
+ "128216": {
1732
+ "content": "<|reserved_special_token_208|>",
1733
+ "lstrip": false,
1734
+ "normalized": false,
1735
+ "rstrip": false,
1736
+ "single_word": false,
1737
+ "special": true
1738
+ },
1739
+ "128217": {
1740
+ "content": "<|reserved_special_token_209|>",
1741
+ "lstrip": false,
1742
+ "normalized": false,
1743
+ "rstrip": false,
1744
+ "single_word": false,
1745
+ "special": true
1746
+ },
1747
+ "128218": {
1748
+ "content": "<|reserved_special_token_210|>",
1749
+ "lstrip": false,
1750
+ "normalized": false,
1751
+ "rstrip": false,
1752
+ "single_word": false,
1753
+ "special": true
1754
+ },
1755
+ "128219": {
1756
+ "content": "<|reserved_special_token_211|>",
1757
+ "lstrip": false,
1758
+ "normalized": false,
1759
+ "rstrip": false,
1760
+ "single_word": false,
1761
+ "special": true
1762
+ },
1763
+ "128220": {
1764
+ "content": "<|reserved_special_token_212|>",
1765
+ "lstrip": false,
1766
+ "normalized": false,
1767
+ "rstrip": false,
1768
+ "single_word": false,
1769
+ "special": true
1770
+ },
1771
+ "128221": {
1772
+ "content": "<|reserved_special_token_213|>",
1773
+ "lstrip": false,
1774
+ "normalized": false,
1775
+ "rstrip": false,
1776
+ "single_word": false,
1777
+ "special": true
1778
+ },
1779
+ "128222": {
1780
+ "content": "<|reserved_special_token_214|>",
1781
+ "lstrip": false,
1782
+ "normalized": false,
1783
+ "rstrip": false,
1784
+ "single_word": false,
1785
+ "special": true
1786
+ },
1787
+ "128223": {
1788
+ "content": "<|reserved_special_token_215|>",
1789
+ "lstrip": false,
1790
+ "normalized": false,
1791
+ "rstrip": false,
1792
+ "single_word": false,
1793
+ "special": true
1794
+ },
1795
+ "128224": {
1796
+ "content": "<|reserved_special_token_216|>",
1797
+ "lstrip": false,
1798
+ "normalized": false,
1799
+ "rstrip": false,
1800
+ "single_word": false,
1801
+ "special": true
1802
+ },
1803
+ "128225": {
1804
+ "content": "<|reserved_special_token_217|>",
1805
+ "lstrip": false,
1806
+ "normalized": false,
1807
+ "rstrip": false,
1808
+ "single_word": false,
1809
+ "special": true
1810
+ },
1811
+ "128226": {
1812
+ "content": "<|reserved_special_token_218|>",
1813
+ "lstrip": false,
1814
+ "normalized": false,
1815
+ "rstrip": false,
1816
+ "single_word": false,
1817
+ "special": true
1818
+ },
1819
+ "128227": {
1820
+ "content": "<|reserved_special_token_219|>",
1821
+ "lstrip": false,
1822
+ "normalized": false,
1823
+ "rstrip": false,
1824
+ "single_word": false,
1825
+ "special": true
1826
+ },
1827
+ "128228": {
1828
+ "content": "<|reserved_special_token_220|>",
1829
+ "lstrip": false,
1830
+ "normalized": false,
1831
+ "rstrip": false,
1832
+ "single_word": false,
1833
+ "special": true
1834
+ },
1835
+ "128229": {
1836
+ "content": "<|reserved_special_token_221|>",
1837
+ "lstrip": false,
1838
+ "normalized": false,
1839
+ "rstrip": false,
1840
+ "single_word": false,
1841
+ "special": true
1842
+ },
1843
+ "128230": {
1844
+ "content": "<|reserved_special_token_222|>",
1845
+ "lstrip": false,
1846
+ "normalized": false,
1847
+ "rstrip": false,
1848
+ "single_word": false,
1849
+ "special": true
1850
+ },
1851
+ "128231": {
1852
+ "content": "<|reserved_special_token_223|>",
1853
+ "lstrip": false,
1854
+ "normalized": false,
1855
+ "rstrip": false,
1856
+ "single_word": false,
1857
+ "special": true
1858
+ },
1859
+ "128232": {
1860
+ "content": "<|reserved_special_token_224|>",
1861
+ "lstrip": false,
1862
+ "normalized": false,
1863
+ "rstrip": false,
1864
+ "single_word": false,
1865
+ "special": true
1866
+ },
1867
+ "128233": {
1868
+ "content": "<|reserved_special_token_225|>",
1869
+ "lstrip": false,
1870
+ "normalized": false,
1871
+ "rstrip": false,
1872
+ "single_word": false,
1873
+ "special": true
1874
+ },
1875
+ "128234": {
1876
+ "content": "<|reserved_special_token_226|>",
1877
+ "lstrip": false,
1878
+ "normalized": false,
1879
+ "rstrip": false,
1880
+ "single_word": false,
1881
+ "special": true
1882
+ },
1883
+ "128235": {
1884
+ "content": "<|reserved_special_token_227|>",
1885
+ "lstrip": false,
1886
+ "normalized": false,
1887
+ "rstrip": false,
1888
+ "single_word": false,
1889
+ "special": true
1890
+ },
1891
+ "128236": {
1892
+ "content": "<|reserved_special_token_228|>",
1893
+ "lstrip": false,
1894
+ "normalized": false,
1895
+ "rstrip": false,
1896
+ "single_word": false,
1897
+ "special": true
1898
+ },
1899
+ "128237": {
1900
+ "content": "<|reserved_special_token_229|>",
1901
+ "lstrip": false,
1902
+ "normalized": false,
1903
+ "rstrip": false,
1904
+ "single_word": false,
1905
+ "special": true
1906
+ },
1907
+ "128238": {
1908
+ "content": "<|reserved_special_token_230|>",
1909
+ "lstrip": false,
1910
+ "normalized": false,
1911
+ "rstrip": false,
1912
+ "single_word": false,
1913
+ "special": true
1914
+ },
1915
+ "128239": {
1916
+ "content": "<|reserved_special_token_231|>",
1917
+ "lstrip": false,
1918
+ "normalized": false,
1919
+ "rstrip": false,
1920
+ "single_word": false,
1921
+ "special": true
1922
+ },
1923
+ "128240": {
1924
+ "content": "<|reserved_special_token_232|>",
1925
+ "lstrip": false,
1926
+ "normalized": false,
1927
+ "rstrip": false,
1928
+ "single_word": false,
1929
+ "special": true
1930
+ },
1931
+ "128241": {
1932
+ "content": "<|reserved_special_token_233|>",
1933
+ "lstrip": false,
1934
+ "normalized": false,
1935
+ "rstrip": false,
1936
+ "single_word": false,
1937
+ "special": true
1938
+ },
1939
+ "128242": {
1940
+ "content": "<|reserved_special_token_234|>",
1941
+ "lstrip": false,
1942
+ "normalized": false,
1943
+ "rstrip": false,
1944
+ "single_word": false,
1945
+ "special": true
1946
+ },
1947
+ "128243": {
1948
+ "content": "<|reserved_special_token_235|>",
1949
+ "lstrip": false,
1950
+ "normalized": false,
1951
+ "rstrip": false,
1952
+ "single_word": false,
1953
+ "special": true
1954
+ },
1955
+ "128244": {
1956
+ "content": "<|reserved_special_token_236|>",
1957
+ "lstrip": false,
1958
+ "normalized": false,
1959
+ "rstrip": false,
1960
+ "single_word": false,
1961
+ "special": true
1962
+ },
1963
+ "128245": {
1964
+ "content": "<|reserved_special_token_237|>",
1965
+ "lstrip": false,
1966
+ "normalized": false,
1967
+ "rstrip": false,
1968
+ "single_word": false,
1969
+ "special": true
1970
+ },
1971
+ "128246": {
1972
+ "content": "<|reserved_special_token_238|>",
1973
+ "lstrip": false,
1974
+ "normalized": false,
1975
+ "rstrip": false,
1976
+ "single_word": false,
1977
+ "special": true
1978
+ },
1979
+ "128247": {
1980
+ "content": "<|reserved_special_token_239|>",
1981
+ "lstrip": false,
1982
+ "normalized": false,
1983
+ "rstrip": false,
1984
+ "single_word": false,
1985
+ "special": true
1986
+ },
1987
+ "128248": {
1988
+ "content": "<|reserved_special_token_240|>",
1989
+ "lstrip": false,
1990
+ "normalized": false,
1991
+ "rstrip": false,
1992
+ "single_word": false,
1993
+ "special": true
1994
+ },
1995
+ "128249": {
1996
+ "content": "<|reserved_special_token_241|>",
1997
+ "lstrip": false,
1998
+ "normalized": false,
1999
+ "rstrip": false,
2000
+ "single_word": false,
2001
+ "special": true
2002
+ },
2003
+ "128250": {
2004
+ "content": "<|reserved_special_token_242|>",
2005
+ "lstrip": false,
2006
+ "normalized": false,
2007
+ "rstrip": false,
2008
+ "single_word": false,
2009
+ "special": true
2010
+ },
2011
+ "128251": {
2012
+ "content": "<|reserved_special_token_243|>",
2013
+ "lstrip": false,
2014
+ "normalized": false,
2015
+ "rstrip": false,
2016
+ "single_word": false,
2017
+ "special": true
2018
+ },
2019
+ "128252": {
2020
+ "content": "<|reserved_special_token_244|>",
2021
+ "lstrip": false,
2022
+ "normalized": false,
2023
+ "rstrip": false,
2024
+ "single_word": false,
2025
+ "special": true
2026
+ },
2027
+ "128253": {
2028
+ "content": "<|reserved_special_token_245|>",
2029
+ "lstrip": false,
2030
+ "normalized": false,
2031
+ "rstrip": false,
2032
+ "single_word": false,
2033
+ "special": true
2034
+ },
2035
+ "128254": {
2036
+ "content": "<|reserved_special_token_246|>",
2037
+ "lstrip": false,
2038
+ "normalized": false,
2039
+ "rstrip": false,
2040
+ "single_word": false,
2041
+ "special": true
2042
+ },
2043
+ "128255": {
2044
+ "content": "<|reserved_special_token_247|>",
2045
+ "lstrip": false,
2046
+ "normalized": false,
2047
+ "rstrip": false,
2048
+ "single_word": false,
2049
+ "special": true
2050
+ }
2051
+ },
2052
+ "bos_token": "<|begin_of_text|>",
2053
+ "chat_template": "{{- bos_token }}\n{%- if custom_tools is defined %}\n {%- set tools = custom_tools %}\n{%- endif %}\n{%- if not tools_in_user_message is defined %}\n {%- set tools_in_user_message = true %}\n{%- endif %}\n{%- if not date_string is defined %}\n {%- set date_string = \"26 Jul 2024\" %}\n{%- endif %}\n{%- if not tools is defined %}\n {%- set tools = none %}\n{%- endif %}\n\n{#- This block extracts the system message, so we can slot it into the right place. #}\n{%- if messages[0]['role'] == 'system' %}\n {%- set system_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n{%- else %}\n {%- set system_message = \"\" %}\n{%- endif %}\n\n{#- System message + builtin tools #}\n{{- \"<|start_header_id|>system<|end_header_id|>\\n\\n\" }}\n{%- if builtin_tools is defined or tools is not none %}\n {{- \"Environment: ipython\\n\" }}\n{%- endif %}\n{%- if builtin_tools is defined %}\n {{- \"Tools: \" + builtin_tools | reject('equalto', 'code_interpreter') | join(\", \") + \"\\n\\n\"}}\n{%- endif %}\n{{- \"Cutting Knowledge Date: December 2023\\n\" }}\n{{- \"Today Date: \" + date_string + \"\\n\\n\" }}\n{%- if tools is not none and not tools_in_user_message %}\n {{- \"You have access to the following functions. To call a function, please respond with JSON for a function call.\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\\n\\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\\n\\n\" }}\n {%- endfor %}\n{%- endif %}\n{{- system_message }}\n{{- \"<|eot_id|>\" }}\n\n{#- Custom tools are passed in a user message with some extra guidance #}\n{%- if tools_in_user_message and not tools is none %}\n {#- Extract the first user message so we can plug it in here #}\n {%- if messages | length != 0 %}\n {%- set first_user_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n {%- else %}\n {{- raise_exception(\"Cannot put tools in the first user message when there's no first user message!\") }}\n{%- endif %}\n {{- '<|start_header_id|>user<|end_header_id|>\\n\\n' -}}\n {{- \"Given the following functions, please respond with a JSON for a function call \" }}\n {{- \"with its proper arguments that best answers the given prompt.\\n\\n\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\\n\\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\\n\\n\" }}\n {%- endfor %}\n {{- first_user_message + \"<|eot_id|>\"}}\n{%- endif %}\n\n{%- for message in messages %}\n {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}\n {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\\n\\n'+ message['content'] | trim + '<|eot_id|>' }}\n {%- elif 'tool_calls' in message %}\n {%- if not message.tool_calls|length == 1 %}\n {{- raise_exception(\"This model only supports single tool-calls at once!\") }}\n {%- endif %}\n {%- set tool_call = message.tool_calls[0].function %}\n {%- if builtin_tools is defined and tool_call.name in builtin_tools %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n {{- \"<|python_tag|>\" + tool_call.name + \".call(\" }}\n {%- for arg_name, arg_val in tool_call.arguments | items %}\n {{- arg_name + '=\"' + arg_val + '\"' }}\n {%- if not loop.last %}\n {{- \", \" }}\n {%- endif %}\n {%- endfor %}\n {{- \")\" }}\n {%- else %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n {{- '{\"name\": \"' + tool_call.name + '\", ' }}\n {{- '\"parameters\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- \"}\" }}\n {%- endif %}\n {%- if builtin_tools is defined %}\n {#- This means we're in ipython mode #}\n {{- \"<|eom_id|>\" }}\n {%- else %}\n {{- \"<|eot_id|>\" }}\n {%- endif %}\n {%- elif message.role == \"tool\" or message.role == \"ipython\" %}\n {{- \"<|start_header_id|>ipython<|end_header_id|>\\n\\n\" }}\n {%- if message.content is mapping or message.content is iterable %}\n {{- message.content | tojson }}\n {%- else %}\n {{- message.content }}\n {%- endif %}\n {{- \"<|eot_id|>\" }}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' }}\n{%- endif %}\n",
2054
+ "clean_up_tokenization_spaces": true,
2055
+ "eos_token": "<|eot_id|>",
2056
+ "model_input_names": [
2057
+ "input_ids",
2058
+ "attention_mask"
2059
+ ],
2060
+ "model_max_length": 2048,
2061
+ "pad_token": "<|eot_id|>",
2062
+ "tokenizer_class": "PreTrainedTokenizerFast"
2063
+ }
GaetanMichelet__Llama-31-8B_task-2_180-samples_config-4/train_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 36.0,
3
+ "total_flos": 4.686344037995643e+17,
4
+ "train_loss": 0.7647335636459924,
5
+ "train_runtime": 16723.6429,
6
+ "train_samples": 136,
7
+ "train_samples_per_second": 1.22,
8
+ "train_steps_per_second": 0.072
9
+ }
GaetanMichelet__Llama-31-8B_task-2_180-samples_config-4/trainer_state.json ADDED
@@ -0,0 +1,1417 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.7155756950378418,
3
+ "best_model_checkpoint": "data/Llama-31-8B_task-2_180-samples_config-4/checkpoint-246",
4
+ "epoch": 36.0,
5
+ "eval_steps": 500,
6
+ "global_step": 306,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.11764705882352941,
13
+ "grad_norm": 0.6938014030456543,
14
+ "learning_rate": 8.333333333333334e-08,
15
+ "loss": 1.1573,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.23529411764705882,
20
+ "grad_norm": 0.7594343423843384,
21
+ "learning_rate": 1.6666666666666668e-07,
22
+ "loss": 1.1671,
23
+ "step": 2
24
+ },
25
+ {
26
+ "epoch": 0.47058823529411764,
27
+ "grad_norm": 0.7093557715415955,
28
+ "learning_rate": 3.3333333333333335e-07,
29
+ "loss": 1.1466,
30
+ "step": 4
31
+ },
32
+ {
33
+ "epoch": 0.7058823529411765,
34
+ "grad_norm": 0.6927754878997803,
35
+ "learning_rate": 5.000000000000001e-07,
36
+ "loss": 1.1113,
37
+ "step": 6
38
+ },
39
+ {
40
+ "epoch": 0.9411764705882353,
41
+ "grad_norm": 0.6476206183433533,
42
+ "learning_rate": 6.666666666666667e-07,
43
+ "loss": 1.0917,
44
+ "step": 8
45
+ },
46
+ {
47
+ "epoch": 0.9411764705882353,
48
+ "eval_loss": 1.1325923204421997,
49
+ "eval_runtime": 37.009,
50
+ "eval_samples_per_second": 0.973,
51
+ "eval_steps_per_second": 0.973,
52
+ "step": 8
53
+ },
54
+ {
55
+ "epoch": 1.1764705882352942,
56
+ "grad_norm": 0.6894296407699585,
57
+ "learning_rate": 8.333333333333333e-07,
58
+ "loss": 1.1424,
59
+ "step": 10
60
+ },
61
+ {
62
+ "epoch": 1.4117647058823528,
63
+ "grad_norm": 0.6622559428215027,
64
+ "learning_rate": 1.0000000000000002e-06,
65
+ "loss": 1.1225,
66
+ "step": 12
67
+ },
68
+ {
69
+ "epoch": 1.6470588235294117,
70
+ "grad_norm": 0.6495747566223145,
71
+ "learning_rate": 1.1666666666666668e-06,
72
+ "loss": 1.0675,
73
+ "step": 14
74
+ },
75
+ {
76
+ "epoch": 1.8823529411764706,
77
+ "grad_norm": 0.7559149861335754,
78
+ "learning_rate": 1.3333333333333334e-06,
79
+ "loss": 1.1392,
80
+ "step": 16
81
+ },
82
+ {
83
+ "epoch": 2.0,
84
+ "eval_loss": 1.1271247863769531,
85
+ "eval_runtime": 36.9985,
86
+ "eval_samples_per_second": 0.973,
87
+ "eval_steps_per_second": 0.973,
88
+ "step": 17
89
+ },
90
+ {
91
+ "epoch": 2.1176470588235294,
92
+ "grad_norm": 0.6588976979255676,
93
+ "learning_rate": 1.5e-06,
94
+ "loss": 1.1406,
95
+ "step": 18
96
+ },
97
+ {
98
+ "epoch": 2.3529411764705883,
99
+ "grad_norm": 0.6868743300437927,
100
+ "learning_rate": 1.6666666666666667e-06,
101
+ "loss": 1.0912,
102
+ "step": 20
103
+ },
104
+ {
105
+ "epoch": 2.588235294117647,
106
+ "grad_norm": 0.699292778968811,
107
+ "learning_rate": 1.8333333333333333e-06,
108
+ "loss": 1.1073,
109
+ "step": 22
110
+ },
111
+ {
112
+ "epoch": 2.8235294117647056,
113
+ "grad_norm": 0.7510226964950562,
114
+ "learning_rate": 2.0000000000000003e-06,
115
+ "loss": 1.1572,
116
+ "step": 24
117
+ },
118
+ {
119
+ "epoch": 2.9411764705882355,
120
+ "eval_loss": 1.1161284446716309,
121
+ "eval_runtime": 37.0046,
122
+ "eval_samples_per_second": 0.973,
123
+ "eval_steps_per_second": 0.973,
124
+ "step": 25
125
+ },
126
+ {
127
+ "epoch": 3.0588235294117645,
128
+ "grad_norm": 0.7101291418075562,
129
+ "learning_rate": 2.166666666666667e-06,
130
+ "loss": 1.0988,
131
+ "step": 26
132
+ },
133
+ {
134
+ "epoch": 3.2941176470588234,
135
+ "grad_norm": 0.5981112718582153,
136
+ "learning_rate": 2.3333333333333336e-06,
137
+ "loss": 1.0899,
138
+ "step": 28
139
+ },
140
+ {
141
+ "epoch": 3.5294117647058822,
142
+ "grad_norm": 0.7123465538024902,
143
+ "learning_rate": 2.5e-06,
144
+ "loss": 1.1263,
145
+ "step": 30
146
+ },
147
+ {
148
+ "epoch": 3.764705882352941,
149
+ "grad_norm": 0.6823212504386902,
150
+ "learning_rate": 2.666666666666667e-06,
151
+ "loss": 1.1119,
152
+ "step": 32
153
+ },
154
+ {
155
+ "epoch": 4.0,
156
+ "grad_norm": 0.7324620485305786,
157
+ "learning_rate": 2.8333333333333335e-06,
158
+ "loss": 1.0856,
159
+ "step": 34
160
+ },
161
+ {
162
+ "epoch": 4.0,
163
+ "eval_loss": 1.0970431566238403,
164
+ "eval_runtime": 37.0081,
165
+ "eval_samples_per_second": 0.973,
166
+ "eval_steps_per_second": 0.973,
167
+ "step": 34
168
+ },
169
+ {
170
+ "epoch": 4.235294117647059,
171
+ "grad_norm": 0.7198031544685364,
172
+ "learning_rate": 3e-06,
173
+ "loss": 1.1012,
174
+ "step": 36
175
+ },
176
+ {
177
+ "epoch": 4.470588235294118,
178
+ "grad_norm": 0.7194771766662598,
179
+ "learning_rate": 3.1666666666666667e-06,
180
+ "loss": 1.0752,
181
+ "step": 38
182
+ },
183
+ {
184
+ "epoch": 4.705882352941177,
185
+ "grad_norm": 0.702494740486145,
186
+ "learning_rate": 3.3333333333333333e-06,
187
+ "loss": 1.0602,
188
+ "step": 40
189
+ },
190
+ {
191
+ "epoch": 4.9411764705882355,
192
+ "grad_norm": 0.6754999160766602,
193
+ "learning_rate": 3.5e-06,
194
+ "loss": 1.0789,
195
+ "step": 42
196
+ },
197
+ {
198
+ "epoch": 4.9411764705882355,
199
+ "eval_loss": 1.0719497203826904,
200
+ "eval_runtime": 37.0094,
201
+ "eval_samples_per_second": 0.973,
202
+ "eval_steps_per_second": 0.973,
203
+ "step": 42
204
+ },
205
+ {
206
+ "epoch": 5.176470588235294,
207
+ "grad_norm": 0.7691217660903931,
208
+ "learning_rate": 3.6666666666666666e-06,
209
+ "loss": 1.0709,
210
+ "step": 44
211
+ },
212
+ {
213
+ "epoch": 5.411764705882353,
214
+ "grad_norm": 0.6451730132102966,
215
+ "learning_rate": 3.833333333333334e-06,
216
+ "loss": 1.0372,
217
+ "step": 46
218
+ },
219
+ {
220
+ "epoch": 5.647058823529412,
221
+ "grad_norm": 0.6900641322135925,
222
+ "learning_rate": 4.000000000000001e-06,
223
+ "loss": 0.9947,
224
+ "step": 48
225
+ },
226
+ {
227
+ "epoch": 5.882352941176471,
228
+ "grad_norm": 0.6281608939170837,
229
+ "learning_rate": 4.166666666666667e-06,
230
+ "loss": 1.0546,
231
+ "step": 50
232
+ },
233
+ {
234
+ "epoch": 6.0,
235
+ "eval_loss": 1.0336723327636719,
236
+ "eval_runtime": 37.0003,
237
+ "eval_samples_per_second": 0.973,
238
+ "eval_steps_per_second": 0.973,
239
+ "step": 51
240
+ },
241
+ {
242
+ "epoch": 6.117647058823529,
243
+ "grad_norm": 0.6548106074333191,
244
+ "learning_rate": 4.333333333333334e-06,
245
+ "loss": 1.0604,
246
+ "step": 52
247
+ },
248
+ {
249
+ "epoch": 6.352941176470588,
250
+ "grad_norm": 0.6569029688835144,
251
+ "learning_rate": 4.5e-06,
252
+ "loss": 0.9777,
253
+ "step": 54
254
+ },
255
+ {
256
+ "epoch": 6.588235294117647,
257
+ "grad_norm": 0.6138703227043152,
258
+ "learning_rate": 4.666666666666667e-06,
259
+ "loss": 1.0248,
260
+ "step": 56
261
+ },
262
+ {
263
+ "epoch": 6.823529411764706,
264
+ "grad_norm": 0.5528715252876282,
265
+ "learning_rate": 4.833333333333333e-06,
266
+ "loss": 0.9806,
267
+ "step": 58
268
+ },
269
+ {
270
+ "epoch": 6.9411764705882355,
271
+ "eval_loss": 0.9922827482223511,
272
+ "eval_runtime": 37.0043,
273
+ "eval_samples_per_second": 0.973,
274
+ "eval_steps_per_second": 0.973,
275
+ "step": 59
276
+ },
277
+ {
278
+ "epoch": 7.0588235294117645,
279
+ "grad_norm": 0.5543631315231323,
280
+ "learning_rate": 5e-06,
281
+ "loss": 1.0264,
282
+ "step": 60
283
+ },
284
+ {
285
+ "epoch": 7.294117647058823,
286
+ "grad_norm": 0.5159863233566284,
287
+ "learning_rate": 5.1666666666666675e-06,
288
+ "loss": 0.9702,
289
+ "step": 62
290
+ },
291
+ {
292
+ "epoch": 7.529411764705882,
293
+ "grad_norm": 0.5009753704071045,
294
+ "learning_rate": 5.333333333333334e-06,
295
+ "loss": 0.9452,
296
+ "step": 64
297
+ },
298
+ {
299
+ "epoch": 7.764705882352941,
300
+ "grad_norm": 0.49283164739608765,
301
+ "learning_rate": 5.500000000000001e-06,
302
+ "loss": 0.9367,
303
+ "step": 66
304
+ },
305
+ {
306
+ "epoch": 8.0,
307
+ "grad_norm": 0.47310400009155273,
308
+ "learning_rate": 5.666666666666667e-06,
309
+ "loss": 0.9617,
310
+ "step": 68
311
+ },
312
+ {
313
+ "epoch": 8.0,
314
+ "eval_loss": 0.9472079873085022,
315
+ "eval_runtime": 37.0171,
316
+ "eval_samples_per_second": 0.973,
317
+ "eval_steps_per_second": 0.973,
318
+ "step": 68
319
+ },
320
+ {
321
+ "epoch": 8.235294117647058,
322
+ "grad_norm": 0.3864011764526367,
323
+ "learning_rate": 5.833333333333334e-06,
324
+ "loss": 0.9326,
325
+ "step": 70
326
+ },
327
+ {
328
+ "epoch": 8.470588235294118,
329
+ "grad_norm": 0.37244734168052673,
330
+ "learning_rate": 6e-06,
331
+ "loss": 0.948,
332
+ "step": 72
333
+ },
334
+ {
335
+ "epoch": 8.705882352941176,
336
+ "grad_norm": 0.3857339322566986,
337
+ "learning_rate": 6.166666666666667e-06,
338
+ "loss": 0.8741,
339
+ "step": 74
340
+ },
341
+ {
342
+ "epoch": 8.941176470588236,
343
+ "grad_norm": 0.39583349227905273,
344
+ "learning_rate": 6.333333333333333e-06,
345
+ "loss": 0.933,
346
+ "step": 76
347
+ },
348
+ {
349
+ "epoch": 8.941176470588236,
350
+ "eval_loss": 0.912886381149292,
351
+ "eval_runtime": 37.0055,
352
+ "eval_samples_per_second": 0.973,
353
+ "eval_steps_per_second": 0.973,
354
+ "step": 76
355
+ },
356
+ {
357
+ "epoch": 9.176470588235293,
358
+ "grad_norm": 0.30479201674461365,
359
+ "learning_rate": 6.5000000000000004e-06,
360
+ "loss": 0.8891,
361
+ "step": 78
362
+ },
363
+ {
364
+ "epoch": 9.411764705882353,
365
+ "grad_norm": 0.30881431698799133,
366
+ "learning_rate": 6.666666666666667e-06,
367
+ "loss": 0.848,
368
+ "step": 80
369
+ },
370
+ {
371
+ "epoch": 9.647058823529411,
372
+ "grad_norm": 0.3065626919269562,
373
+ "learning_rate": 6.833333333333334e-06,
374
+ "loss": 0.8886,
375
+ "step": 82
376
+ },
377
+ {
378
+ "epoch": 9.882352941176471,
379
+ "grad_norm": 0.3278353214263916,
380
+ "learning_rate": 7e-06,
381
+ "loss": 0.9005,
382
+ "step": 84
383
+ },
384
+ {
385
+ "epoch": 10.0,
386
+ "eval_loss": 0.8825066089630127,
387
+ "eval_runtime": 36.9987,
388
+ "eval_samples_per_second": 0.973,
389
+ "eval_steps_per_second": 0.973,
390
+ "step": 85
391
+ },
392
+ {
393
+ "epoch": 10.117647058823529,
394
+ "grad_norm": 0.3112061023712158,
395
+ "learning_rate": 7.166666666666667e-06,
396
+ "loss": 0.8631,
397
+ "step": 86
398
+ },
399
+ {
400
+ "epoch": 10.352941176470589,
401
+ "grad_norm": 0.2803957164287567,
402
+ "learning_rate": 7.333333333333333e-06,
403
+ "loss": 0.8166,
404
+ "step": 88
405
+ },
406
+ {
407
+ "epoch": 10.588235294117647,
408
+ "grad_norm": 0.2763586938381195,
409
+ "learning_rate": 7.500000000000001e-06,
410
+ "loss": 0.8208,
411
+ "step": 90
412
+ },
413
+ {
414
+ "epoch": 10.823529411764707,
415
+ "grad_norm": 0.29917630553245544,
416
+ "learning_rate": 7.666666666666667e-06,
417
+ "loss": 0.9183,
418
+ "step": 92
419
+ },
420
+ {
421
+ "epoch": 10.941176470588236,
422
+ "eval_loss": 0.8577808141708374,
423
+ "eval_runtime": 37.0008,
424
+ "eval_samples_per_second": 0.973,
425
+ "eval_steps_per_second": 0.973,
426
+ "step": 93
427
+ },
428
+ {
429
+ "epoch": 11.058823529411764,
430
+ "grad_norm": 0.2617398202419281,
431
+ "learning_rate": 7.833333333333333e-06,
432
+ "loss": 0.8786,
433
+ "step": 94
434
+ },
435
+ {
436
+ "epoch": 11.294117647058824,
437
+ "grad_norm": 0.251274436712265,
438
+ "learning_rate": 8.000000000000001e-06,
439
+ "loss": 0.8257,
440
+ "step": 96
441
+ },
442
+ {
443
+ "epoch": 11.529411764705882,
444
+ "grad_norm": 0.27396726608276367,
445
+ "learning_rate": 8.166666666666668e-06,
446
+ "loss": 0.8913,
447
+ "step": 98
448
+ },
449
+ {
450
+ "epoch": 11.764705882352942,
451
+ "grad_norm": 0.27446839213371277,
452
+ "learning_rate": 8.333333333333334e-06,
453
+ "loss": 0.7921,
454
+ "step": 100
455
+ },
456
+ {
457
+ "epoch": 12.0,
458
+ "grad_norm": 0.24932074546813965,
459
+ "learning_rate": 8.5e-06,
460
+ "loss": 0.7739,
461
+ "step": 102
462
+ },
463
+ {
464
+ "epoch": 12.0,
465
+ "eval_loss": 0.8334917426109314,
466
+ "eval_runtime": 37.0127,
467
+ "eval_samples_per_second": 0.973,
468
+ "eval_steps_per_second": 0.973,
469
+ "step": 102
470
+ },
471
+ {
472
+ "epoch": 12.235294117647058,
473
+ "grad_norm": 0.297094464302063,
474
+ "learning_rate": 8.666666666666668e-06,
475
+ "loss": 0.8754,
476
+ "step": 104
477
+ },
478
+ {
479
+ "epoch": 12.470588235294118,
480
+ "grad_norm": 0.23659107089042664,
481
+ "learning_rate": 8.833333333333334e-06,
482
+ "loss": 0.764,
483
+ "step": 106
484
+ },
485
+ {
486
+ "epoch": 12.705882352941176,
487
+ "grad_norm": 0.23405446112155914,
488
+ "learning_rate": 9e-06,
489
+ "loss": 0.8218,
490
+ "step": 108
491
+ },
492
+ {
493
+ "epoch": 12.941176470588236,
494
+ "grad_norm": 0.23257797956466675,
495
+ "learning_rate": 9.166666666666666e-06,
496
+ "loss": 0.7649,
497
+ "step": 110
498
+ },
499
+ {
500
+ "epoch": 12.941176470588236,
501
+ "eval_loss": 0.8164898157119751,
502
+ "eval_runtime": 37.01,
503
+ "eval_samples_per_second": 0.973,
504
+ "eval_steps_per_second": 0.973,
505
+ "step": 110
506
+ },
507
+ {
508
+ "epoch": 13.176470588235293,
509
+ "grad_norm": 0.23545639216899872,
510
+ "learning_rate": 9.333333333333334e-06,
511
+ "loss": 0.7674,
512
+ "step": 112
513
+ },
514
+ {
515
+ "epoch": 13.411764705882353,
516
+ "grad_norm": 0.26143553853034973,
517
+ "learning_rate": 9.5e-06,
518
+ "loss": 0.7662,
519
+ "step": 114
520
+ },
521
+ {
522
+ "epoch": 13.647058823529411,
523
+ "grad_norm": 0.21934638917446136,
524
+ "learning_rate": 9.666666666666667e-06,
525
+ "loss": 0.7928,
526
+ "step": 116
527
+ },
528
+ {
529
+ "epoch": 13.882352941176471,
530
+ "grad_norm": 0.2396870255470276,
531
+ "learning_rate": 9.833333333333333e-06,
532
+ "loss": 0.8197,
533
+ "step": 118
534
+ },
535
+ {
536
+ "epoch": 14.0,
537
+ "eval_loss": 0.8008810877799988,
538
+ "eval_runtime": 36.9979,
539
+ "eval_samples_per_second": 0.973,
540
+ "eval_steps_per_second": 0.973,
541
+ "step": 119
542
+ },
543
+ {
544
+ "epoch": 14.117647058823529,
545
+ "grad_norm": 0.24245895445346832,
546
+ "learning_rate": 1e-05,
547
+ "loss": 0.8115,
548
+ "step": 120
549
+ },
550
+ {
551
+ "epoch": 14.352941176470589,
552
+ "grad_norm": 0.23691204190254211,
553
+ "learning_rate": 9.999915384288723e-06,
554
+ "loss": 0.7565,
555
+ "step": 122
556
+ },
557
+ {
558
+ "epoch": 14.588235294117647,
559
+ "grad_norm": 0.21797290444374084,
560
+ "learning_rate": 9.999661540018812e-06,
561
+ "loss": 0.7858,
562
+ "step": 124
563
+ },
564
+ {
565
+ "epoch": 14.823529411764707,
566
+ "grad_norm": 0.23253759741783142,
567
+ "learning_rate": 9.999238475781957e-06,
568
+ "loss": 0.7488,
569
+ "step": 126
570
+ },
571
+ {
572
+ "epoch": 14.941176470588236,
573
+ "eval_loss": 0.7888637185096741,
574
+ "eval_runtime": 36.999,
575
+ "eval_samples_per_second": 0.973,
576
+ "eval_steps_per_second": 0.973,
577
+ "step": 127
578
+ },
579
+ {
580
+ "epoch": 15.058823529411764,
581
+ "grad_norm": 0.2564374804496765,
582
+ "learning_rate": 9.99864620589731e-06,
583
+ "loss": 0.7646,
584
+ "step": 128
585
+ },
586
+ {
587
+ "epoch": 15.294117647058824,
588
+ "grad_norm": 0.23032395541667938,
589
+ "learning_rate": 9.997884750411004e-06,
590
+ "loss": 0.7598,
591
+ "step": 130
592
+ },
593
+ {
594
+ "epoch": 15.529411764705882,
595
+ "grad_norm": 0.22293731570243835,
596
+ "learning_rate": 9.99695413509548e-06,
597
+ "loss": 0.733,
598
+ "step": 132
599
+ },
600
+ {
601
+ "epoch": 15.764705882352942,
602
+ "grad_norm": 0.2295634150505066,
603
+ "learning_rate": 9.995854391448607e-06,
604
+ "loss": 0.7611,
605
+ "step": 134
606
+ },
607
+ {
608
+ "epoch": 16.0,
609
+ "grad_norm": 0.24928726255893707,
610
+ "learning_rate": 9.994585556692624e-06,
611
+ "loss": 0.7651,
612
+ "step": 136
613
+ },
614
+ {
615
+ "epoch": 16.0,
616
+ "eval_loss": 0.7769894003868103,
617
+ "eval_runtime": 36.9969,
618
+ "eval_samples_per_second": 0.973,
619
+ "eval_steps_per_second": 0.973,
620
+ "step": 136
621
+ },
622
+ {
623
+ "epoch": 16.235294117647058,
624
+ "grad_norm": 0.21673335134983063,
625
+ "learning_rate": 9.993147673772869e-06,
626
+ "loss": 0.7225,
627
+ "step": 138
628
+ },
629
+ {
630
+ "epoch": 16.470588235294116,
631
+ "grad_norm": 0.22104425728321075,
632
+ "learning_rate": 9.991540791356342e-06,
633
+ "loss": 0.7727,
634
+ "step": 140
635
+ },
636
+ {
637
+ "epoch": 16.705882352941178,
638
+ "grad_norm": 0.23531343042850494,
639
+ "learning_rate": 9.989764963830038e-06,
640
+ "loss": 0.7589,
641
+ "step": 142
642
+ },
643
+ {
644
+ "epoch": 16.941176470588236,
645
+ "grad_norm": 0.21621249616146088,
646
+ "learning_rate": 9.987820251299121e-06,
647
+ "loss": 0.6992,
648
+ "step": 144
649
+ },
650
+ {
651
+ "epoch": 16.941176470588236,
652
+ "eval_loss": 0.7678544521331787,
653
+ "eval_runtime": 36.9951,
654
+ "eval_samples_per_second": 0.973,
655
+ "eval_steps_per_second": 0.973,
656
+ "step": 144
657
+ },
658
+ {
659
+ "epoch": 17.176470588235293,
660
+ "grad_norm": 0.242046520113945,
661
+ "learning_rate": 9.985706719584888e-06,
662
+ "loss": 0.7617,
663
+ "step": 146
664
+ },
665
+ {
666
+ "epoch": 17.41176470588235,
667
+ "grad_norm": 0.21592232584953308,
668
+ "learning_rate": 9.98342444022253e-06,
669
+ "loss": 0.6826,
670
+ "step": 148
671
+ },
672
+ {
673
+ "epoch": 17.647058823529413,
674
+ "grad_norm": 0.2592144310474396,
675
+ "learning_rate": 9.980973490458728e-06,
676
+ "loss": 0.7452,
677
+ "step": 150
678
+ },
679
+ {
680
+ "epoch": 17.88235294117647,
681
+ "grad_norm": 0.2321804314851761,
682
+ "learning_rate": 9.978353953249023e-06,
683
+ "loss": 0.7609,
684
+ "step": 152
685
+ },
686
+ {
687
+ "epoch": 18.0,
688
+ "eval_loss": 0.7580164670944214,
689
+ "eval_runtime": 37.0023,
690
+ "eval_samples_per_second": 0.973,
691
+ "eval_steps_per_second": 0.973,
692
+ "step": 153
693
+ },
694
+ {
695
+ "epoch": 18.11764705882353,
696
+ "grad_norm": 0.2417711317539215,
697
+ "learning_rate": 9.975565917255017e-06,
698
+ "loss": 0.6975,
699
+ "step": 154
700
+ },
701
+ {
702
+ "epoch": 18.352941176470587,
703
+ "grad_norm": 0.2503942549228668,
704
+ "learning_rate": 9.972609476841368e-06,
705
+ "loss": 0.7259,
706
+ "step": 156
707
+ },
708
+ {
709
+ "epoch": 18.58823529411765,
710
+ "grad_norm": 0.23440955579280853,
711
+ "learning_rate": 9.9694847320726e-06,
712
+ "loss": 0.7242,
713
+ "step": 158
714
+ },
715
+ {
716
+ "epoch": 18.823529411764707,
717
+ "grad_norm": 0.2478140890598297,
718
+ "learning_rate": 9.966191788709716e-06,
719
+ "loss": 0.6868,
720
+ "step": 160
721
+ },
722
+ {
723
+ "epoch": 18.941176470588236,
724
+ "eval_loss": 0.7510344386100769,
725
+ "eval_runtime": 37.0057,
726
+ "eval_samples_per_second": 0.973,
727
+ "eval_steps_per_second": 0.973,
728
+ "step": 161
729
+ },
730
+ {
731
+ "epoch": 19.058823529411764,
732
+ "grad_norm": 0.2523338496685028,
733
+ "learning_rate": 9.962730758206612e-06,
734
+ "loss": 0.7132,
735
+ "step": 162
736
+ },
737
+ {
738
+ "epoch": 19.294117647058822,
739
+ "grad_norm": 0.2554718255996704,
740
+ "learning_rate": 9.959101757706308e-06,
741
+ "loss": 0.7306,
742
+ "step": 164
743
+ },
744
+ {
745
+ "epoch": 19.529411764705884,
746
+ "grad_norm": 0.2540837526321411,
747
+ "learning_rate": 9.955304910036993e-06,
748
+ "loss": 0.6959,
749
+ "step": 166
750
+ },
751
+ {
752
+ "epoch": 19.764705882352942,
753
+ "grad_norm": 0.23473863303661346,
754
+ "learning_rate": 9.951340343707852e-06,
755
+ "loss": 0.677,
756
+ "step": 168
757
+ },
758
+ {
759
+ "epoch": 20.0,
760
+ "grad_norm": 0.26500314474105835,
761
+ "learning_rate": 9.947208192904722e-06,
762
+ "loss": 0.7077,
763
+ "step": 170
764
+ },
765
+ {
766
+ "epoch": 20.0,
767
+ "eval_loss": 0.7436654567718506,
768
+ "eval_runtime": 37.0063,
769
+ "eval_samples_per_second": 0.973,
770
+ "eval_steps_per_second": 0.973,
771
+ "step": 170
772
+ },
773
+ {
774
+ "epoch": 20.235294117647058,
775
+ "grad_norm": 0.2688054144382477,
776
+ "learning_rate": 9.942908597485558e-06,
777
+ "loss": 0.7092,
778
+ "step": 172
779
+ },
780
+ {
781
+ "epoch": 20.470588235294116,
782
+ "grad_norm": 0.24925930798053741,
783
+ "learning_rate": 9.938441702975689e-06,
784
+ "loss": 0.7176,
785
+ "step": 174
786
+ },
787
+ {
788
+ "epoch": 20.705882352941178,
789
+ "grad_norm": 0.2611039876937866,
790
+ "learning_rate": 9.933807660562898e-06,
791
+ "loss": 0.6457,
792
+ "step": 176
793
+ },
794
+ {
795
+ "epoch": 20.941176470588236,
796
+ "grad_norm": 0.2844160497188568,
797
+ "learning_rate": 9.929006627092298e-06,
798
+ "loss": 0.6862,
799
+ "step": 178
800
+ },
801
+ {
802
+ "epoch": 20.941176470588236,
803
+ "eval_loss": 0.7379278540611267,
804
+ "eval_runtime": 36.9999,
805
+ "eval_samples_per_second": 0.973,
806
+ "eval_steps_per_second": 0.973,
807
+ "step": 178
808
+ },
809
+ {
810
+ "epoch": 21.176470588235293,
811
+ "grad_norm": 0.27488094568252563,
812
+ "learning_rate": 9.924038765061042e-06,
813
+ "loss": 0.7067,
814
+ "step": 180
815
+ },
816
+ {
817
+ "epoch": 21.41176470588235,
818
+ "grad_norm": 0.24594415724277496,
819
+ "learning_rate": 9.918904242612794e-06,
820
+ "loss": 0.6842,
821
+ "step": 182
822
+ },
823
+ {
824
+ "epoch": 21.647058823529413,
825
+ "grad_norm": 0.2662781774997711,
826
+ "learning_rate": 9.913603233532067e-06,
827
+ "loss": 0.6661,
828
+ "step": 184
829
+ },
830
+ {
831
+ "epoch": 21.88235294117647,
832
+ "grad_norm": 0.2941681146621704,
833
+ "learning_rate": 9.908135917238321e-06,
834
+ "loss": 0.6939,
835
+ "step": 186
836
+ },
837
+ {
838
+ "epoch": 22.0,
839
+ "eval_loss": 0.7319392561912537,
840
+ "eval_runtime": 37.0166,
841
+ "eval_samples_per_second": 0.973,
842
+ "eval_steps_per_second": 0.973,
843
+ "step": 187
844
+ },
845
+ {
846
+ "epoch": 22.11764705882353,
847
+ "grad_norm": 0.3132288157939911,
848
+ "learning_rate": 9.902502478779897e-06,
849
+ "loss": 0.6804,
850
+ "step": 188
851
+ },
852
+ {
853
+ "epoch": 22.352941176470587,
854
+ "grad_norm": 0.2927018105983734,
855
+ "learning_rate": 9.896703108827758e-06,
856
+ "loss": 0.649,
857
+ "step": 190
858
+ },
859
+ {
860
+ "epoch": 22.58823529411765,
861
+ "grad_norm": 0.28771597146987915,
862
+ "learning_rate": 9.890738003669029e-06,
863
+ "loss": 0.6525,
864
+ "step": 192
865
+ },
866
+ {
867
+ "epoch": 22.823529411764707,
868
+ "grad_norm": 0.31475573778152466,
869
+ "learning_rate": 9.884607365200355e-06,
870
+ "loss": 0.6564,
871
+ "step": 194
872
+ },
873
+ {
874
+ "epoch": 22.941176470588236,
875
+ "eval_loss": 0.7275494933128357,
876
+ "eval_runtime": 37.002,
877
+ "eval_samples_per_second": 0.973,
878
+ "eval_steps_per_second": 0.973,
879
+ "step": 195
880
+ },
881
+ {
882
+ "epoch": 23.058823529411764,
883
+ "grad_norm": 0.29836949706077576,
884
+ "learning_rate": 9.878311400921072e-06,
885
+ "loss": 0.6561,
886
+ "step": 196
887
+ },
888
+ {
889
+ "epoch": 23.294117647058822,
890
+ "grad_norm": 0.30295827984809875,
891
+ "learning_rate": 9.871850323926178e-06,
892
+ "loss": 0.6815,
893
+ "step": 198
894
+ },
895
+ {
896
+ "epoch": 23.529411764705884,
897
+ "grad_norm": 0.2973706126213074,
898
+ "learning_rate": 9.86522435289912e-06,
899
+ "loss": 0.6261,
900
+ "step": 200
901
+ },
902
+ {
903
+ "epoch": 23.764705882352942,
904
+ "grad_norm": 0.32414522767066956,
905
+ "learning_rate": 9.858433712104403e-06,
906
+ "loss": 0.6752,
907
+ "step": 202
908
+ },
909
+ {
910
+ "epoch": 24.0,
911
+ "grad_norm": 0.30349239706993103,
912
+ "learning_rate": 9.851478631379982e-06,
913
+ "loss": 0.6446,
914
+ "step": 204
915
+ },
916
+ {
917
+ "epoch": 24.0,
918
+ "eval_loss": 0.7236446738243103,
919
+ "eval_runtime": 37.004,
920
+ "eval_samples_per_second": 0.973,
921
+ "eval_steps_per_second": 0.973,
922
+ "step": 204
923
+ },
924
+ {
925
+ "epoch": 24.235294117647058,
926
+ "grad_norm": 0.30559128522872925,
927
+ "learning_rate": 9.844359346129504e-06,
928
+ "loss": 0.6672,
929
+ "step": 206
930
+ },
931
+ {
932
+ "epoch": 24.470588235294116,
933
+ "grad_norm": 0.2979726195335388,
934
+ "learning_rate": 9.83707609731432e-06,
935
+ "loss": 0.6283,
936
+ "step": 208
937
+ },
938
+ {
939
+ "epoch": 24.705882352941178,
940
+ "grad_norm": 0.3105686604976654,
941
+ "learning_rate": 9.829629131445342e-06,
942
+ "loss": 0.6412,
943
+ "step": 210
944
+ },
945
+ {
946
+ "epoch": 24.941176470588236,
947
+ "grad_norm": 0.3595413863658905,
948
+ "learning_rate": 9.822018700574696e-06,
949
+ "loss": 0.6304,
950
+ "step": 212
951
+ },
952
+ {
953
+ "epoch": 24.941176470588236,
954
+ "eval_loss": 0.7200143337249756,
955
+ "eval_runtime": 37.0035,
956
+ "eval_samples_per_second": 0.973,
957
+ "eval_steps_per_second": 0.973,
958
+ "step": 212
959
+ },
960
+ {
961
+ "epoch": 25.176470588235293,
962
+ "grad_norm": 0.3050694763660431,
963
+ "learning_rate": 9.81424506228719e-06,
964
+ "loss": 0.6179,
965
+ "step": 214
966
+ },
967
+ {
968
+ "epoch": 25.41176470588235,
969
+ "grad_norm": 0.3428696095943451,
970
+ "learning_rate": 9.806308479691595e-06,
971
+ "loss": 0.6223,
972
+ "step": 216
973
+ },
974
+ {
975
+ "epoch": 25.647058823529413,
976
+ "grad_norm": 0.3474690616130829,
977
+ "learning_rate": 9.798209221411748e-06,
978
+ "loss": 0.652,
979
+ "step": 218
980
+ },
981
+ {
982
+ "epoch": 25.88235294117647,
983
+ "grad_norm": 0.38103392720222473,
984
+ "learning_rate": 9.789947561577445e-06,
985
+ "loss": 0.6583,
986
+ "step": 220
987
+ },
988
+ {
989
+ "epoch": 26.0,
990
+ "eval_loss": 0.7177853584289551,
991
+ "eval_runtime": 37.0015,
992
+ "eval_samples_per_second": 0.973,
993
+ "eval_steps_per_second": 0.973,
994
+ "step": 221
995
+ },
996
+ {
997
+ "epoch": 26.11764705882353,
998
+ "grad_norm": 0.3361453413963318,
999
+ "learning_rate": 9.781523779815178e-06,
1000
+ "loss": 0.6239,
1001
+ "step": 222
1002
+ },
1003
+ {
1004
+ "epoch": 26.352941176470587,
1005
+ "grad_norm": 0.38879382610321045,
1006
+ "learning_rate": 9.77293816123866e-06,
1007
+ "loss": 0.6229,
1008
+ "step": 224
1009
+ },
1010
+ {
1011
+ "epoch": 26.58823529411765,
1012
+ "grad_norm": 0.3591279685497284,
1013
+ "learning_rate": 9.764190996439181e-06,
1014
+ "loss": 0.6374,
1015
+ "step": 226
1016
+ },
1017
+ {
1018
+ "epoch": 26.823529411764707,
1019
+ "grad_norm": 0.3179728388786316,
1020
+ "learning_rate": 9.755282581475769e-06,
1021
+ "loss": 0.5974,
1022
+ "step": 228
1023
+ },
1024
+ {
1025
+ "epoch": 26.941176470588236,
1026
+ "eval_loss": 0.7159412503242493,
1027
+ "eval_runtime": 36.9995,
1028
+ "eval_samples_per_second": 0.973,
1029
+ "eval_steps_per_second": 0.973,
1030
+ "step": 229
1031
+ },
1032
+ {
1033
+ "epoch": 27.058823529411764,
1034
+ "grad_norm": 0.3596520721912384,
1035
+ "learning_rate": 9.74621321786517e-06,
1036
+ "loss": 0.6042,
1037
+ "step": 230
1038
+ },
1039
+ {
1040
+ "epoch": 27.294117647058822,
1041
+ "grad_norm": 0.36043640971183777,
1042
+ "learning_rate": 9.736983212571646e-06,
1043
+ "loss": 0.6058,
1044
+ "step": 232
1045
+ },
1046
+ {
1047
+ "epoch": 27.529411764705884,
1048
+ "grad_norm": 0.35985061526298523,
1049
+ "learning_rate": 9.727592877996585e-06,
1050
+ "loss": 0.5959,
1051
+ "step": 234
1052
+ },
1053
+ {
1054
+ "epoch": 27.764705882352942,
1055
+ "grad_norm": 0.3502049446105957,
1056
+ "learning_rate": 9.718042531967918e-06,
1057
+ "loss": 0.5894,
1058
+ "step": 236
1059
+ },
1060
+ {
1061
+ "epoch": 28.0,
1062
+ "grad_norm": 0.3679797053337097,
1063
+ "learning_rate": 9.708332497729378e-06,
1064
+ "loss": 0.6266,
1065
+ "step": 238
1066
+ },
1067
+ {
1068
+ "epoch": 28.0,
1069
+ "eval_loss": 0.7158757448196411,
1070
+ "eval_runtime": 37.0093,
1071
+ "eval_samples_per_second": 0.973,
1072
+ "eval_steps_per_second": 0.973,
1073
+ "step": 238
1074
+ },
1075
+ {
1076
+ "epoch": 28.235294117647058,
1077
+ "grad_norm": 0.35959428548812866,
1078
+ "learning_rate": 9.698463103929542e-06,
1079
+ "loss": 0.5731,
1080
+ "step": 240
1081
+ },
1082
+ {
1083
+ "epoch": 28.470588235294116,
1084
+ "grad_norm": 0.3938836455345154,
1085
+ "learning_rate": 9.688434684610725e-06,
1086
+ "loss": 0.5868,
1087
+ "step": 242
1088
+ },
1089
+ {
1090
+ "epoch": 28.705882352941178,
1091
+ "grad_norm": 0.6573047637939453,
1092
+ "learning_rate": 9.678247579197658e-06,
1093
+ "loss": 0.6126,
1094
+ "step": 244
1095
+ },
1096
+ {
1097
+ "epoch": 28.941176470588236,
1098
+ "grad_norm": 0.3609618842601776,
1099
+ "learning_rate": 9.667902132486009e-06,
1100
+ "loss": 0.6081,
1101
+ "step": 246
1102
+ },
1103
+ {
1104
+ "epoch": 28.941176470588236,
1105
+ "eval_loss": 0.7155756950378418,
1106
+ "eval_runtime": 37.01,
1107
+ "eval_samples_per_second": 0.973,
1108
+ "eval_steps_per_second": 0.973,
1109
+ "step": 246
1110
+ },
1111
+ {
1112
+ "epoch": 29.176470588235293,
1113
+ "grad_norm": 0.38799017667770386,
1114
+ "learning_rate": 9.657398694630713e-06,
1115
+ "loss": 0.5564,
1116
+ "step": 248
1117
+ },
1118
+ {
1119
+ "epoch": 29.41176470588235,
1120
+ "grad_norm": 0.4135487675666809,
1121
+ "learning_rate": 9.646737621134112e-06,
1122
+ "loss": 0.6149,
1123
+ "step": 250
1124
+ },
1125
+ {
1126
+ "epoch": 29.647058823529413,
1127
+ "grad_norm": 0.3742540180683136,
1128
+ "learning_rate": 9.635919272833938e-06,
1129
+ "loss": 0.5747,
1130
+ "step": 252
1131
+ },
1132
+ {
1133
+ "epoch": 29.88235294117647,
1134
+ "grad_norm": 0.40949445962905884,
1135
+ "learning_rate": 9.62494401589108e-06,
1136
+ "loss": 0.5853,
1137
+ "step": 254
1138
+ },
1139
+ {
1140
+ "epoch": 30.0,
1141
+ "eval_loss": 0.7164749503135681,
1142
+ "eval_runtime": 37.0011,
1143
+ "eval_samples_per_second": 0.973,
1144
+ "eval_steps_per_second": 0.973,
1145
+ "step": 255
1146
+ },
1147
+ {
1148
+ "epoch": 30.11764705882353,
1149
+ "grad_norm": 0.4069327414035797,
1150
+ "learning_rate": 9.613812221777212e-06,
1151
+ "loss": 0.5611,
1152
+ "step": 256
1153
+ },
1154
+ {
1155
+ "epoch": 30.352941176470587,
1156
+ "grad_norm": 0.4262481927871704,
1157
+ "learning_rate": 9.602524267262202e-06,
1158
+ "loss": 0.5845,
1159
+ "step": 258
1160
+ },
1161
+ {
1162
+ "epoch": 30.58823529411765,
1163
+ "grad_norm": 0.42745286226272583,
1164
+ "learning_rate": 9.591080534401371e-06,
1165
+ "loss": 0.5742,
1166
+ "step": 260
1167
+ },
1168
+ {
1169
+ "epoch": 30.823529411764707,
1170
+ "grad_norm": 0.4548822343349457,
1171
+ "learning_rate": 9.579481410522556e-06,
1172
+ "loss": 0.54,
1173
+ "step": 262
1174
+ },
1175
+ {
1176
+ "epoch": 30.941176470588236,
1177
+ "eval_loss": 0.7200043201446533,
1178
+ "eval_runtime": 37.0013,
1179
+ "eval_samples_per_second": 0.973,
1180
+ "eval_steps_per_second": 0.973,
1181
+ "step": 263
1182
+ },
1183
+ {
1184
+ "epoch": 31.058823529411764,
1185
+ "grad_norm": 0.41799986362457275,
1186
+ "learning_rate": 9.567727288213005e-06,
1187
+ "loss": 0.5325,
1188
+ "step": 264
1189
+ },
1190
+ {
1191
+ "epoch": 31.294117647058822,
1192
+ "grad_norm": 0.4568859338760376,
1193
+ "learning_rate": 9.555818565306086e-06,
1194
+ "loss": 0.5688,
1195
+ "step": 266
1196
+ },
1197
+ {
1198
+ "epoch": 31.529411764705884,
1199
+ "grad_norm": 0.441699355840683,
1200
+ "learning_rate": 9.543755644867823e-06,
1201
+ "loss": 0.5628,
1202
+ "step": 268
1203
+ },
1204
+ {
1205
+ "epoch": 31.764705882352942,
1206
+ "grad_norm": 0.45061326026916504,
1207
+ "learning_rate": 9.531538935183252e-06,
1208
+ "loss": 0.5419,
1209
+ "step": 270
1210
+ },
1211
+ {
1212
+ "epoch": 32.0,
1213
+ "grad_norm": 0.4943307638168335,
1214
+ "learning_rate": 9.519168849742603e-06,
1215
+ "loss": 0.5438,
1216
+ "step": 272
1217
+ },
1218
+ {
1219
+ "epoch": 32.0,
1220
+ "eval_loss": 0.7231061458587646,
1221
+ "eval_runtime": 37.0086,
1222
+ "eval_samples_per_second": 0.973,
1223
+ "eval_steps_per_second": 0.973,
1224
+ "step": 272
1225
+ },
1226
+ {
1227
+ "epoch": 32.23529411764706,
1228
+ "grad_norm": 0.46770891547203064,
1229
+ "learning_rate": 9.506645807227311e-06,
1230
+ "loss": 0.5162,
1231
+ "step": 274
1232
+ },
1233
+ {
1234
+ "epoch": 32.470588235294116,
1235
+ "grad_norm": 0.48194897174835205,
1236
+ "learning_rate": 9.493970231495836e-06,
1237
+ "loss": 0.5715,
1238
+ "step": 276
1239
+ },
1240
+ {
1241
+ "epoch": 32.705882352941174,
1242
+ "grad_norm": 0.47527700662612915,
1243
+ "learning_rate": 9.481142551569318e-06,
1244
+ "loss": 0.5233,
1245
+ "step": 278
1246
+ },
1247
+ {
1248
+ "epoch": 32.94117647058823,
1249
+ "grad_norm": 0.5583000779151917,
1250
+ "learning_rate": 9.468163201617063e-06,
1251
+ "loss": 0.5163,
1252
+ "step": 280
1253
+ },
1254
+ {
1255
+ "epoch": 32.94117647058823,
1256
+ "eval_loss": 0.7267724275588989,
1257
+ "eval_runtime": 37.0063,
1258
+ "eval_samples_per_second": 0.973,
1259
+ "eval_steps_per_second": 0.973,
1260
+ "step": 280
1261
+ },
1262
+ {
1263
+ "epoch": 33.1764705882353,
1264
+ "grad_norm": 0.5567420125007629,
1265
+ "learning_rate": 9.45503262094184e-06,
1266
+ "loss": 0.5146,
1267
+ "step": 282
1268
+ },
1269
+ {
1270
+ "epoch": 33.411764705882355,
1271
+ "grad_norm": 0.5160362124443054,
1272
+ "learning_rate": 9.441751253965022e-06,
1273
+ "loss": 0.5227,
1274
+ "step": 284
1275
+ },
1276
+ {
1277
+ "epoch": 33.64705882352941,
1278
+ "grad_norm": 0.5851587057113647,
1279
+ "learning_rate": 9.428319550211531e-06,
1280
+ "loss": 0.4936,
1281
+ "step": 286
1282
+ },
1283
+ {
1284
+ "epoch": 33.88235294117647,
1285
+ "grad_norm": 0.564764142036438,
1286
+ "learning_rate": 9.414737964294636e-06,
1287
+ "loss": 0.5302,
1288
+ "step": 288
1289
+ },
1290
+ {
1291
+ "epoch": 34.0,
1292
+ "eval_loss": 0.7345450520515442,
1293
+ "eval_runtime": 37.0031,
1294
+ "eval_samples_per_second": 0.973,
1295
+ "eval_steps_per_second": 0.973,
1296
+ "step": 289
1297
+ },
1298
+ {
1299
+ "epoch": 34.11764705882353,
1300
+ "grad_norm": 0.5420270562171936,
1301
+ "learning_rate": 9.401006955900555e-06,
1302
+ "loss": 0.5254,
1303
+ "step": 290
1304
+ },
1305
+ {
1306
+ "epoch": 34.35294117647059,
1307
+ "grad_norm": 0.5466279983520508,
1308
+ "learning_rate": 9.38712698977291e-06,
1309
+ "loss": 0.5236,
1310
+ "step": 292
1311
+ },
1312
+ {
1313
+ "epoch": 34.588235294117645,
1314
+ "grad_norm": 0.5974857807159424,
1315
+ "learning_rate": 9.37309853569698e-06,
1316
+ "loss": 0.4812,
1317
+ "step": 294
1318
+ },
1319
+ {
1320
+ "epoch": 34.8235294117647,
1321
+ "grad_norm": 0.6072189807891846,
1322
+ "learning_rate": 9.358922068483813e-06,
1323
+ "loss": 0.4865,
1324
+ "step": 296
1325
+ },
1326
+ {
1327
+ "epoch": 34.94117647058823,
1328
+ "eval_loss": 0.7542312145233154,
1329
+ "eval_runtime": 37.0073,
1330
+ "eval_samples_per_second": 0.973,
1331
+ "eval_steps_per_second": 0.973,
1332
+ "step": 297
1333
+ },
1334
+ {
1335
+ "epoch": 35.05882352941177,
1336
+ "grad_norm": 0.7493066191673279,
1337
+ "learning_rate": 9.344598067954151e-06,
1338
+ "loss": 0.4651,
1339
+ "step": 298
1340
+ },
1341
+ {
1342
+ "epoch": 35.294117647058826,
1343
+ "grad_norm": 0.6359327435493469,
1344
+ "learning_rate": 9.330127018922195e-06,
1345
+ "loss": 0.5043,
1346
+ "step": 300
1347
+ },
1348
+ {
1349
+ "epoch": 35.529411764705884,
1350
+ "grad_norm": 0.5997797846794128,
1351
+ "learning_rate": 9.315509411179182e-06,
1352
+ "loss": 0.4598,
1353
+ "step": 302
1354
+ },
1355
+ {
1356
+ "epoch": 35.76470588235294,
1357
+ "grad_norm": 0.586499810218811,
1358
+ "learning_rate": 9.30074573947683e-06,
1359
+ "loss": 0.4543,
1360
+ "step": 304
1361
+ },
1362
+ {
1363
+ "epoch": 36.0,
1364
+ "grad_norm": 0.6805587410926819,
1365
+ "learning_rate": 9.285836503510562e-06,
1366
+ "loss": 0.4774,
1367
+ "step": 306
1368
+ },
1369
+ {
1370
+ "epoch": 36.0,
1371
+ "eval_loss": 0.7611451148986816,
1372
+ "eval_runtime": 37.0054,
1373
+ "eval_samples_per_second": 0.973,
1374
+ "eval_steps_per_second": 0.973,
1375
+ "step": 306
1376
+ },
1377
+ {
1378
+ "epoch": 36.0,
1379
+ "step": 306,
1380
+ "total_flos": 4.686344037995643e+17,
1381
+ "train_loss": 0.7647335636459924,
1382
+ "train_runtime": 16723.6429,
1383
+ "train_samples_per_second": 1.22,
1384
+ "train_steps_per_second": 0.072
1385
+ }
1386
+ ],
1387
+ "logging_steps": 2,
1388
+ "max_steps": 1200,
1389
+ "num_input_tokens_seen": 0,
1390
+ "num_train_epochs": 150,
1391
+ "save_steps": 25,
1392
+ "stateful_callbacks": {
1393
+ "EarlyStoppingCallback": {
1394
+ "args": {
1395
+ "early_stopping_patience": 7,
1396
+ "early_stopping_threshold": 0.0
1397
+ },
1398
+ "attributes": {
1399
+ "early_stopping_patience_counter": 0
1400
+ }
1401
+ },
1402
+ "TrainerControl": {
1403
+ "args": {
1404
+ "should_epoch_stop": false,
1405
+ "should_evaluate": false,
1406
+ "should_log": false,
1407
+ "should_save": true,
1408
+ "should_training_stop": true
1409
+ },
1410
+ "attributes": {}
1411
+ }
1412
+ },
1413
+ "total_flos": 4.686344037995643e+17,
1414
+ "train_batch_size": 1,
1415
+ "trial_name": null,
1416
+ "trial_params": null
1417
+ }
GaetanMichelet__Llama-31-8B_task-2_180-samples_config-4/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:552d25c301dd1ea613d40db5bf5c0fc0263353806563c9d5d24cf15b4e89145e
3
+ size 6264