jjee2 commited on
Commit
98c1421
·
verified ·
1 Parent(s): 61685f5

Add GaetanMichelet__Llama-31-8B_task-2_120-samples_config-3

Browse files
GaetanMichelet__Llama-31-8B_task-2_120-samples_config-3/.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_120-samples_config-3/README.md ADDED
@@ -0,0 +1,97 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ library_name: peft
7
+ license: llama3.1
8
+ tags:
9
+ - alignment-handbook
10
+ - trl
11
+ - sft
12
+ - generated_from_trainer
13
+ model-index:
14
+ - name: Llama-31-8B_task-2_120-samples_config-3
15
+ results: []
16
+ ---
17
+
18
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
19
+ should probably proofread and complete it, then remove this comment. -->
20
+
21
+ # Llama-31-8B_task-2_120-samples_config-3
22
+
23
+ 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 and the GaetanMichelet/chat-120_ft_task-2 datasets.
24
+ It achieves the following results on the evaluation set:
25
+ - Loss: 0.7139
26
+
27
+ ## Model description
28
+
29
+ More information needed
30
+
31
+ ## Intended uses & limitations
32
+
33
+ More information needed
34
+
35
+ ## Training and evaluation data
36
+
37
+ More information needed
38
+
39
+ ## Training procedure
40
+
41
+ ### Training hyperparameters
42
+
43
+ The following hyperparameters were used during training:
44
+ - learning_rate: 1e-05
45
+ - train_batch_size: 1
46
+ - eval_batch_size: 1
47
+ - seed: 42
48
+ - distributed_type: multi-GPU
49
+ - gradient_accumulation_steps: 8
50
+ - total_train_batch_size: 8
51
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
52
+ - lr_scheduler_type: cosine
53
+ - lr_scheduler_warmup_ratio: 0.1
54
+ - num_epochs: 150
55
+
56
+ ### Training results
57
+
58
+ | Training Loss | Epoch | Step | Validation Loss |
59
+ |:-------------:|:-----:|:----:|:---------------:|
60
+ | 1.0459 | 1.0 | 11 | 1.1227 |
61
+ | 1.0223 | 2.0 | 22 | 1.1149 |
62
+ | 1.0795 | 3.0 | 33 | 1.1018 |
63
+ | 0.9982 | 4.0 | 44 | 1.0787 |
64
+ | 0.9702 | 5.0 | 55 | 1.0444 |
65
+ | 0.9509 | 6.0 | 66 | 0.9990 |
66
+ | 0.9573 | 7.0 | 77 | 0.9500 |
67
+ | 0.8624 | 8.0 | 88 | 0.9071 |
68
+ | 0.8804 | 9.0 | 99 | 0.8747 |
69
+ | 0.8515 | 10.0 | 110 | 0.8457 |
70
+ | 0.7864 | 11.0 | 121 | 0.8208 |
71
+ | 0.8648 | 12.0 | 132 | 0.8018 |
72
+ | 0.736 | 13.0 | 143 | 0.7867 |
73
+ | 0.7882 | 14.0 | 154 | 0.7728 |
74
+ | 0.7452 | 15.0 | 165 | 0.7604 |
75
+ | 0.6818 | 16.0 | 176 | 0.7485 |
76
+ | 0.7119 | 17.0 | 187 | 0.7387 |
77
+ | 0.7107 | 18.0 | 198 | 0.7307 |
78
+ | 0.6405 | 19.0 | 209 | 0.7238 |
79
+ | 0.6075 | 20.0 | 220 | 0.7188 |
80
+ | 0.6323 | 21.0 | 231 | 0.7152 |
81
+ | 0.557 | 22.0 | 242 | 0.7139 |
82
+ | 0.5692 | 23.0 | 253 | 0.7158 |
83
+ | 0.558 | 24.0 | 264 | 0.7198 |
84
+ | 0.5153 | 25.0 | 275 | 0.7296 |
85
+ | 0.4964 | 26.0 | 286 | 0.7367 |
86
+ | 0.4713 | 27.0 | 297 | 0.7403 |
87
+ | 0.4144 | 28.0 | 308 | 0.7620 |
88
+ | 0.4184 | 29.0 | 319 | 0.7954 |
89
+
90
+
91
+ ### Framework versions
92
+
93
+ - PEFT 0.12.0
94
+ - Transformers 4.44.0
95
+ - Pytorch 2.1.2+cu121
96
+ - Datasets 2.20.0
97
+ - Tokenizers 0.19.1
GaetanMichelet__Llama-31-8B_task-2_120-samples_config-3/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
+ "q_proj",
24
+ "o_proj",
25
+ "v_proj",
26
+ "gate_proj",
27
+ "k_proj",
28
+ "up_proj",
29
+ "down_proj"
30
+ ],
31
+ "task_type": "CAUSAL_LM",
32
+ "use_dora": false,
33
+ "use_rslora": false
34
+ }
GaetanMichelet__Llama-31-8B_task-2_120-samples_config-3/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:836b7424d27a44abf5c5b6f45c04e53546551965eade0930df406ca0b14934d2
3
+ size 167832240
GaetanMichelet__Llama-31-8B_task-2_120-samples_config-3/all_results.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 29.0,
3
+ "eval_loss": 0.7138778567314148,
4
+ "eval_runtime": 24.33,
5
+ "eval_samples": 24,
6
+ "eval_samples_per_second": 0.986,
7
+ "eval_steps_per_second": 0.986,
8
+ "total_flos": 2.4257124139375e+17,
9
+ "train_loss": 0.757462413613699,
10
+ "train_runtime": 8705.8997,
11
+ "train_samples": 88,
12
+ "train_samples_per_second": 1.516,
13
+ "train_steps_per_second": 0.19
14
+ }
GaetanMichelet__Llama-31-8B_task-2_120-samples_config-3/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_120-samples_config-3/eval_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 29.0,
3
+ "eval_loss": 0.7138778567314148,
4
+ "eval_runtime": 24.33,
5
+ "eval_samples": 24,
6
+ "eval_samples_per_second": 0.986,
7
+ "eval_steps_per_second": 0.986
8
+ }
GaetanMichelet__Llama-31-8B_task-2_120-samples_config-3/runs/Aug18_09-35-13_9mqd6r3-l/events.out.tfevents.1723966527.9mqd6r3-l.2402981.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a948cf8598153176109ab9858496d85f78fef8f1e8e488fa340ac91f30911964
3
+ size 48478
GaetanMichelet__Llama-31-8B_task-2_120-samples_config-3/runs/Aug18_09-35-13_9mqd6r3-l/events.out.tfevents.1723975273.9mqd6r3-l.2402981.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:12c30d2cbec7d1a9d6e72930e74d326575a326996e6feb9aaafd9c95c373ed05
3
+ size 359
GaetanMichelet__Llama-31-8B_task-2_120-samples_config-3/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_120-samples_config-3/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
GaetanMichelet__Llama-31-8B_task-2_120-samples_config-3/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_120-samples_config-3/train_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 29.0,
3
+ "total_flos": 2.4257124139375e+17,
4
+ "train_loss": 0.757462413613699,
5
+ "train_runtime": 8705.8997,
6
+ "train_samples": 88,
7
+ "train_samples_per_second": 1.516,
8
+ "train_steps_per_second": 0.19
9
+ }
GaetanMichelet__Llama-31-8B_task-2_120-samples_config-3/trainer_state.json ADDED
@@ -0,0 +1,1403 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.7138778567314148,
3
+ "best_model_checkpoint": "data/Llama-31-8B_task-2_120-samples_config-3/checkpoint-242",
4
+ "epoch": 29.0,
5
+ "eval_steps": 500,
6
+ "global_step": 319,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.09090909090909091,
13
+ "grad_norm": 0.7728238701820374,
14
+ "learning_rate": 6.060606060606061e-08,
15
+ "loss": 1.102,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.18181818181818182,
20
+ "grad_norm": 0.8360726237297058,
21
+ "learning_rate": 1.2121212121212122e-07,
22
+ "loss": 1.2412,
23
+ "step": 2
24
+ },
25
+ {
26
+ "epoch": 0.36363636363636365,
27
+ "grad_norm": 0.6940823793411255,
28
+ "learning_rate": 2.4242424242424244e-07,
29
+ "loss": 1.0332,
30
+ "step": 4
31
+ },
32
+ {
33
+ "epoch": 0.5454545454545454,
34
+ "grad_norm": 0.7341020107269287,
35
+ "learning_rate": 3.6363636363636366e-07,
36
+ "loss": 1.1054,
37
+ "step": 6
38
+ },
39
+ {
40
+ "epoch": 0.7272727272727273,
41
+ "grad_norm": 0.8064824938774109,
42
+ "learning_rate": 4.848484848484849e-07,
43
+ "loss": 1.2037,
44
+ "step": 8
45
+ },
46
+ {
47
+ "epoch": 0.9090909090909091,
48
+ "grad_norm": 0.7021966576576233,
49
+ "learning_rate": 6.060606060606061e-07,
50
+ "loss": 1.0459,
51
+ "step": 10
52
+ },
53
+ {
54
+ "epoch": 1.0,
55
+ "eval_loss": 1.122668743133545,
56
+ "eval_runtime": 24.349,
57
+ "eval_samples_per_second": 0.986,
58
+ "eval_steps_per_second": 0.986,
59
+ "step": 11
60
+ },
61
+ {
62
+ "epoch": 1.0909090909090908,
63
+ "grad_norm": 0.7579166293144226,
64
+ "learning_rate": 7.272727272727273e-07,
65
+ "loss": 1.0994,
66
+ "step": 12
67
+ },
68
+ {
69
+ "epoch": 1.2727272727272727,
70
+ "grad_norm": 0.6994158029556274,
71
+ "learning_rate": 8.484848484848486e-07,
72
+ "loss": 1.1056,
73
+ "step": 14
74
+ },
75
+ {
76
+ "epoch": 1.4545454545454546,
77
+ "grad_norm": 0.698021650314331,
78
+ "learning_rate": 9.696969696969698e-07,
79
+ "loss": 1.1576,
80
+ "step": 16
81
+ },
82
+ {
83
+ "epoch": 1.6363636363636362,
84
+ "grad_norm": 0.7830127477645874,
85
+ "learning_rate": 1.090909090909091e-06,
86
+ "loss": 1.1701,
87
+ "step": 18
88
+ },
89
+ {
90
+ "epoch": 1.8181818181818183,
91
+ "grad_norm": 0.749530553817749,
92
+ "learning_rate": 1.2121212121212122e-06,
93
+ "loss": 1.0871,
94
+ "step": 20
95
+ },
96
+ {
97
+ "epoch": 2.0,
98
+ "grad_norm": 0.6776620149612427,
99
+ "learning_rate": 1.3333333333333334e-06,
100
+ "loss": 1.0223,
101
+ "step": 22
102
+ },
103
+ {
104
+ "epoch": 2.0,
105
+ "eval_loss": 1.1149355173110962,
106
+ "eval_runtime": 24.3485,
107
+ "eval_samples_per_second": 0.986,
108
+ "eval_steps_per_second": 0.986,
109
+ "step": 22
110
+ },
111
+ {
112
+ "epoch": 2.1818181818181817,
113
+ "grad_norm": 0.6116415858268738,
114
+ "learning_rate": 1.4545454545454546e-06,
115
+ "loss": 1.0642,
116
+ "step": 24
117
+ },
118
+ {
119
+ "epoch": 2.3636363636363638,
120
+ "grad_norm": 0.7151461839675903,
121
+ "learning_rate": 1.5757575757575759e-06,
122
+ "loss": 1.1885,
123
+ "step": 26
124
+ },
125
+ {
126
+ "epoch": 2.5454545454545454,
127
+ "grad_norm": 0.7120382785797119,
128
+ "learning_rate": 1.6969696969696973e-06,
129
+ "loss": 1.0927,
130
+ "step": 28
131
+ },
132
+ {
133
+ "epoch": 2.7272727272727275,
134
+ "grad_norm": 0.6961694955825806,
135
+ "learning_rate": 1.8181818181818183e-06,
136
+ "loss": 1.0392,
137
+ "step": 30
138
+ },
139
+ {
140
+ "epoch": 2.909090909090909,
141
+ "grad_norm": 0.8099948167800903,
142
+ "learning_rate": 1.9393939393939395e-06,
143
+ "loss": 1.0795,
144
+ "step": 32
145
+ },
146
+ {
147
+ "epoch": 3.0,
148
+ "eval_loss": 1.1017646789550781,
149
+ "eval_runtime": 24.3583,
150
+ "eval_samples_per_second": 0.985,
151
+ "eval_steps_per_second": 0.985,
152
+ "step": 33
153
+ },
154
+ {
155
+ "epoch": 3.090909090909091,
156
+ "grad_norm": 0.7341113686561584,
157
+ "learning_rate": 2.0606060606060607e-06,
158
+ "loss": 1.1445,
159
+ "step": 34
160
+ },
161
+ {
162
+ "epoch": 3.2727272727272725,
163
+ "grad_norm": 0.7002806067466736,
164
+ "learning_rate": 2.181818181818182e-06,
165
+ "loss": 1.0858,
166
+ "step": 36
167
+ },
168
+ {
169
+ "epoch": 3.4545454545454546,
170
+ "grad_norm": 0.7403613328933716,
171
+ "learning_rate": 2.303030303030303e-06,
172
+ "loss": 1.0768,
173
+ "step": 38
174
+ },
175
+ {
176
+ "epoch": 3.6363636363636362,
177
+ "grad_norm": 0.7391121983528137,
178
+ "learning_rate": 2.4242424242424244e-06,
179
+ "loss": 1.035,
180
+ "step": 40
181
+ },
182
+ {
183
+ "epoch": 3.8181818181818183,
184
+ "grad_norm": 0.790711522102356,
185
+ "learning_rate": 2.5454545454545456e-06,
186
+ "loss": 1.1519,
187
+ "step": 42
188
+ },
189
+ {
190
+ "epoch": 4.0,
191
+ "grad_norm": 0.633929967880249,
192
+ "learning_rate": 2.666666666666667e-06,
193
+ "loss": 0.9982,
194
+ "step": 44
195
+ },
196
+ {
197
+ "epoch": 4.0,
198
+ "eval_loss": 1.078678011894226,
199
+ "eval_runtime": 24.3517,
200
+ "eval_samples_per_second": 0.986,
201
+ "eval_steps_per_second": 0.986,
202
+ "step": 44
203
+ },
204
+ {
205
+ "epoch": 4.181818181818182,
206
+ "grad_norm": 0.7980412840843201,
207
+ "learning_rate": 2.7878787878787885e-06,
208
+ "loss": 1.1463,
209
+ "step": 46
210
+ },
211
+ {
212
+ "epoch": 4.363636363636363,
213
+ "grad_norm": 0.7583560347557068,
214
+ "learning_rate": 2.9090909090909093e-06,
215
+ "loss": 1.0093,
216
+ "step": 48
217
+ },
218
+ {
219
+ "epoch": 4.545454545454545,
220
+ "grad_norm": 0.7219624519348145,
221
+ "learning_rate": 3.0303030303030305e-06,
222
+ "loss": 1.0371,
223
+ "step": 50
224
+ },
225
+ {
226
+ "epoch": 4.7272727272727275,
227
+ "grad_norm": 0.7923340797424316,
228
+ "learning_rate": 3.1515151515151517e-06,
229
+ "loss": 1.1243,
230
+ "step": 52
231
+ },
232
+ {
233
+ "epoch": 4.909090909090909,
234
+ "grad_norm": 0.6717983484268188,
235
+ "learning_rate": 3.272727272727273e-06,
236
+ "loss": 0.9702,
237
+ "step": 54
238
+ },
239
+ {
240
+ "epoch": 5.0,
241
+ "eval_loss": 1.0444384813308716,
242
+ "eval_runtime": 24.3479,
243
+ "eval_samples_per_second": 0.986,
244
+ "eval_steps_per_second": 0.986,
245
+ "step": 55
246
+ },
247
+ {
248
+ "epoch": 5.090909090909091,
249
+ "grad_norm": 0.6388964653015137,
250
+ "learning_rate": 3.3939393939393946e-06,
251
+ "loss": 0.9427,
252
+ "step": 56
253
+ },
254
+ {
255
+ "epoch": 5.2727272727272725,
256
+ "grad_norm": 0.8183718919754028,
257
+ "learning_rate": 3.5151515151515154e-06,
258
+ "loss": 1.0683,
259
+ "step": 58
260
+ },
261
+ {
262
+ "epoch": 5.454545454545454,
263
+ "grad_norm": 0.7228857278823853,
264
+ "learning_rate": 3.6363636363636366e-06,
265
+ "loss": 1.0193,
266
+ "step": 60
267
+ },
268
+ {
269
+ "epoch": 5.636363636363637,
270
+ "grad_norm": 0.6639413237571716,
271
+ "learning_rate": 3.757575757575758e-06,
272
+ "loss": 1.0165,
273
+ "step": 62
274
+ },
275
+ {
276
+ "epoch": 5.818181818181818,
277
+ "grad_norm": 0.7365549802780151,
278
+ "learning_rate": 3.878787878787879e-06,
279
+ "loss": 1.0233,
280
+ "step": 64
281
+ },
282
+ {
283
+ "epoch": 6.0,
284
+ "grad_norm": 0.642576277256012,
285
+ "learning_rate": 4.000000000000001e-06,
286
+ "loss": 0.9509,
287
+ "step": 66
288
+ },
289
+ {
290
+ "epoch": 6.0,
291
+ "eval_loss": 0.9990049004554749,
292
+ "eval_runtime": 24.3532,
293
+ "eval_samples_per_second": 0.985,
294
+ "eval_steps_per_second": 0.985,
295
+ "step": 66
296
+ },
297
+ {
298
+ "epoch": 6.181818181818182,
299
+ "grad_norm": 0.6555075645446777,
300
+ "learning_rate": 4.1212121212121215e-06,
301
+ "loss": 0.9929,
302
+ "step": 68
303
+ },
304
+ {
305
+ "epoch": 6.363636363636363,
306
+ "grad_norm": 0.5816611647605896,
307
+ "learning_rate": 4.242424242424243e-06,
308
+ "loss": 0.9891,
309
+ "step": 70
310
+ },
311
+ {
312
+ "epoch": 6.545454545454545,
313
+ "grad_norm": 0.5633305907249451,
314
+ "learning_rate": 4.363636363636364e-06,
315
+ "loss": 0.9197,
316
+ "step": 72
317
+ },
318
+ {
319
+ "epoch": 6.7272727272727275,
320
+ "grad_norm": 0.5987116098403931,
321
+ "learning_rate": 4.4848484848484855e-06,
322
+ "loss": 0.9596,
323
+ "step": 74
324
+ },
325
+ {
326
+ "epoch": 6.909090909090909,
327
+ "grad_norm": 0.5823273658752441,
328
+ "learning_rate": 4.606060606060606e-06,
329
+ "loss": 0.9573,
330
+ "step": 76
331
+ },
332
+ {
333
+ "epoch": 7.0,
334
+ "eval_loss": 0.9499709606170654,
335
+ "eval_runtime": 24.3506,
336
+ "eval_samples_per_second": 0.986,
337
+ "eval_steps_per_second": 0.986,
338
+ "step": 77
339
+ },
340
+ {
341
+ "epoch": 7.090909090909091,
342
+ "grad_norm": 0.5255045890808105,
343
+ "learning_rate": 4.727272727272728e-06,
344
+ "loss": 0.8918,
345
+ "step": 78
346
+ },
347
+ {
348
+ "epoch": 7.2727272727272725,
349
+ "grad_norm": 0.5354146957397461,
350
+ "learning_rate": 4.848484848484849e-06,
351
+ "loss": 0.9815,
352
+ "step": 80
353
+ },
354
+ {
355
+ "epoch": 7.454545454545454,
356
+ "grad_norm": 0.4640227258205414,
357
+ "learning_rate": 4.9696969696969696e-06,
358
+ "loss": 0.8863,
359
+ "step": 82
360
+ },
361
+ {
362
+ "epoch": 7.636363636363637,
363
+ "grad_norm": 0.4414072334766388,
364
+ "learning_rate": 5.090909090909091e-06,
365
+ "loss": 0.9009,
366
+ "step": 84
367
+ },
368
+ {
369
+ "epoch": 7.818181818181818,
370
+ "grad_norm": 0.42416912317276,
371
+ "learning_rate": 5.212121212121213e-06,
372
+ "loss": 0.9165,
373
+ "step": 86
374
+ },
375
+ {
376
+ "epoch": 8.0,
377
+ "grad_norm": 0.3701015114784241,
378
+ "learning_rate": 5.333333333333334e-06,
379
+ "loss": 0.8624,
380
+ "step": 88
381
+ },
382
+ {
383
+ "epoch": 8.0,
384
+ "eval_loss": 0.9071061015129089,
385
+ "eval_runtime": 24.3464,
386
+ "eval_samples_per_second": 0.986,
387
+ "eval_steps_per_second": 0.986,
388
+ "step": 88
389
+ },
390
+ {
391
+ "epoch": 8.181818181818182,
392
+ "grad_norm": 0.3807128369808197,
393
+ "learning_rate": 5.4545454545454545e-06,
394
+ "loss": 0.8405,
395
+ "step": 90
396
+ },
397
+ {
398
+ "epoch": 8.363636363636363,
399
+ "grad_norm": 0.39005354046821594,
400
+ "learning_rate": 5.575757575757577e-06,
401
+ "loss": 0.8492,
402
+ "step": 92
403
+ },
404
+ {
405
+ "epoch": 8.545454545454545,
406
+ "grad_norm": 0.3477958142757416,
407
+ "learning_rate": 5.696969696969698e-06,
408
+ "loss": 0.8703,
409
+ "step": 94
410
+ },
411
+ {
412
+ "epoch": 8.727272727272727,
413
+ "grad_norm": 0.34921929240226746,
414
+ "learning_rate": 5.8181818181818185e-06,
415
+ "loss": 0.9232,
416
+ "step": 96
417
+ },
418
+ {
419
+ "epoch": 8.909090909090908,
420
+ "grad_norm": 0.38983580470085144,
421
+ "learning_rate": 5.93939393939394e-06,
422
+ "loss": 0.8804,
423
+ "step": 98
424
+ },
425
+ {
426
+ "epoch": 9.0,
427
+ "eval_loss": 0.8746969103813171,
428
+ "eval_runtime": 24.3504,
429
+ "eval_samples_per_second": 0.986,
430
+ "eval_steps_per_second": 0.986,
431
+ "step": 99
432
+ },
433
+ {
434
+ "epoch": 9.090909090909092,
435
+ "grad_norm": 0.3402298390865326,
436
+ "learning_rate": 6.060606060606061e-06,
437
+ "loss": 0.8316,
438
+ "step": 100
439
+ },
440
+ {
441
+ "epoch": 9.272727272727273,
442
+ "grad_norm": 0.3445686399936676,
443
+ "learning_rate": 6.181818181818182e-06,
444
+ "loss": 0.8235,
445
+ "step": 102
446
+ },
447
+ {
448
+ "epoch": 9.454545454545455,
449
+ "grad_norm": 0.375674307346344,
450
+ "learning_rate": 6.303030303030303e-06,
451
+ "loss": 0.8982,
452
+ "step": 104
453
+ },
454
+ {
455
+ "epoch": 9.636363636363637,
456
+ "grad_norm": 0.3227982223033905,
457
+ "learning_rate": 6.424242424242425e-06,
458
+ "loss": 0.7633,
459
+ "step": 106
460
+ },
461
+ {
462
+ "epoch": 9.818181818181818,
463
+ "grad_norm": 0.38300326466560364,
464
+ "learning_rate": 6.545454545454546e-06,
465
+ "loss": 0.852,
466
+ "step": 108
467
+ },
468
+ {
469
+ "epoch": 10.0,
470
+ "grad_norm": 0.32602500915527344,
471
+ "learning_rate": 6.666666666666667e-06,
472
+ "loss": 0.8515,
473
+ "step": 110
474
+ },
475
+ {
476
+ "epoch": 10.0,
477
+ "eval_loss": 0.8457457423210144,
478
+ "eval_runtime": 24.3488,
479
+ "eval_samples_per_second": 0.986,
480
+ "eval_steps_per_second": 0.986,
481
+ "step": 110
482
+ },
483
+ {
484
+ "epoch": 10.181818181818182,
485
+ "grad_norm": 0.3338332176208496,
486
+ "learning_rate": 6.787878787878789e-06,
487
+ "loss": 0.825,
488
+ "step": 112
489
+ },
490
+ {
491
+ "epoch": 10.363636363636363,
492
+ "grad_norm": 0.44083863496780396,
493
+ "learning_rate": 6.90909090909091e-06,
494
+ "loss": 0.8433,
495
+ "step": 114
496
+ },
497
+ {
498
+ "epoch": 10.545454545454545,
499
+ "grad_norm": 0.3659360408782959,
500
+ "learning_rate": 7.030303030303031e-06,
501
+ "loss": 0.8081,
502
+ "step": 116
503
+ },
504
+ {
505
+ "epoch": 10.727272727272727,
506
+ "grad_norm": 0.35738250613212585,
507
+ "learning_rate": 7.151515151515152e-06,
508
+ "loss": 0.8144,
509
+ "step": 118
510
+ },
511
+ {
512
+ "epoch": 10.909090909090908,
513
+ "grad_norm": 0.33010390400886536,
514
+ "learning_rate": 7.272727272727273e-06,
515
+ "loss": 0.7864,
516
+ "step": 120
517
+ },
518
+ {
519
+ "epoch": 11.0,
520
+ "eval_loss": 0.8207831382751465,
521
+ "eval_runtime": 24.3504,
522
+ "eval_samples_per_second": 0.986,
523
+ "eval_steps_per_second": 0.986,
524
+ "step": 121
525
+ },
526
+ {
527
+ "epoch": 11.090909090909092,
528
+ "grad_norm": 0.329024076461792,
529
+ "learning_rate": 7.393939393939395e-06,
530
+ "loss": 0.7717,
531
+ "step": 122
532
+ },
533
+ {
534
+ "epoch": 11.272727272727273,
535
+ "grad_norm": 0.32361382246017456,
536
+ "learning_rate": 7.515151515151516e-06,
537
+ "loss": 0.7642,
538
+ "step": 124
539
+ },
540
+ {
541
+ "epoch": 11.454545454545455,
542
+ "grad_norm": 0.33380502462387085,
543
+ "learning_rate": 7.636363636363638e-06,
544
+ "loss": 0.7893,
545
+ "step": 126
546
+ },
547
+ {
548
+ "epoch": 11.636363636363637,
549
+ "grad_norm": 0.3214806318283081,
550
+ "learning_rate": 7.757575757575758e-06,
551
+ "loss": 0.7901,
552
+ "step": 128
553
+ },
554
+ {
555
+ "epoch": 11.818181818181818,
556
+ "grad_norm": 0.3193203806877136,
557
+ "learning_rate": 7.87878787878788e-06,
558
+ "loss": 0.7028,
559
+ "step": 130
560
+ },
561
+ {
562
+ "epoch": 12.0,
563
+ "grad_norm": 0.32331448793411255,
564
+ "learning_rate": 8.000000000000001e-06,
565
+ "loss": 0.8648,
566
+ "step": 132
567
+ },
568
+ {
569
+ "epoch": 12.0,
570
+ "eval_loss": 0.8018015027046204,
571
+ "eval_runtime": 24.3516,
572
+ "eval_samples_per_second": 0.986,
573
+ "eval_steps_per_second": 0.986,
574
+ "step": 132
575
+ },
576
+ {
577
+ "epoch": 12.181818181818182,
578
+ "grad_norm": 0.2892431616783142,
579
+ "learning_rate": 8.121212121212121e-06,
580
+ "loss": 0.764,
581
+ "step": 134
582
+ },
583
+ {
584
+ "epoch": 12.363636363636363,
585
+ "grad_norm": 0.3037986755371094,
586
+ "learning_rate": 8.242424242424243e-06,
587
+ "loss": 0.7343,
588
+ "step": 136
589
+ },
590
+ {
591
+ "epoch": 12.545454545454545,
592
+ "grad_norm": 0.3432358205318451,
593
+ "learning_rate": 8.363636363636365e-06,
594
+ "loss": 0.7794,
595
+ "step": 138
596
+ },
597
+ {
598
+ "epoch": 12.727272727272727,
599
+ "grad_norm": 0.3149927258491516,
600
+ "learning_rate": 8.484848484848486e-06,
601
+ "loss": 0.8031,
602
+ "step": 140
603
+ },
604
+ {
605
+ "epoch": 12.909090909090908,
606
+ "grad_norm": 0.29204079508781433,
607
+ "learning_rate": 8.606060606060606e-06,
608
+ "loss": 0.736,
609
+ "step": 142
610
+ },
611
+ {
612
+ "epoch": 13.0,
613
+ "eval_loss": 0.786732017993927,
614
+ "eval_runtime": 24.3508,
615
+ "eval_samples_per_second": 0.986,
616
+ "eval_steps_per_second": 0.986,
617
+ "step": 143
618
+ },
619
+ {
620
+ "epoch": 13.090909090909092,
621
+ "grad_norm": 0.3326067626476288,
622
+ "learning_rate": 8.727272727272728e-06,
623
+ "loss": 0.7661,
624
+ "step": 144
625
+ },
626
+ {
627
+ "epoch": 13.272727272727273,
628
+ "grad_norm": 0.3473084270954132,
629
+ "learning_rate": 8.84848484848485e-06,
630
+ "loss": 0.7727,
631
+ "step": 146
632
+ },
633
+ {
634
+ "epoch": 13.454545454545455,
635
+ "grad_norm": 0.28269076347351074,
636
+ "learning_rate": 8.969696969696971e-06,
637
+ "loss": 0.7282,
638
+ "step": 148
639
+ },
640
+ {
641
+ "epoch": 13.636363636363637,
642
+ "grad_norm": 0.32704994082450867,
643
+ "learning_rate": 9.090909090909091e-06,
644
+ "loss": 0.6916,
645
+ "step": 150
646
+ },
647
+ {
648
+ "epoch": 13.818181818181818,
649
+ "grad_norm": 0.3217592239379883,
650
+ "learning_rate": 9.212121212121213e-06,
651
+ "loss": 0.7475,
652
+ "step": 152
653
+ },
654
+ {
655
+ "epoch": 14.0,
656
+ "grad_norm": 0.3401748836040497,
657
+ "learning_rate": 9.333333333333334e-06,
658
+ "loss": 0.7882,
659
+ "step": 154
660
+ },
661
+ {
662
+ "epoch": 14.0,
663
+ "eval_loss": 0.7727737426757812,
664
+ "eval_runtime": 24.3475,
665
+ "eval_samples_per_second": 0.986,
666
+ "eval_steps_per_second": 0.986,
667
+ "step": 154
668
+ },
669
+ {
670
+ "epoch": 14.181818181818182,
671
+ "grad_norm": 0.3393374979496002,
672
+ "learning_rate": 9.454545454545456e-06,
673
+ "loss": 0.6774,
674
+ "step": 156
675
+ },
676
+ {
677
+ "epoch": 14.363636363636363,
678
+ "grad_norm": 0.28455665707588196,
679
+ "learning_rate": 9.575757575757576e-06,
680
+ "loss": 0.7579,
681
+ "step": 158
682
+ },
683
+ {
684
+ "epoch": 14.545454545454545,
685
+ "grad_norm": 0.30775022506713867,
686
+ "learning_rate": 9.696969696969698e-06,
687
+ "loss": 0.7331,
688
+ "step": 160
689
+ },
690
+ {
691
+ "epoch": 14.727272727272727,
692
+ "grad_norm": 0.3098331689834595,
693
+ "learning_rate": 9.81818181818182e-06,
694
+ "loss": 0.7255,
695
+ "step": 162
696
+ },
697
+ {
698
+ "epoch": 14.909090909090908,
699
+ "grad_norm": 0.39052486419677734,
700
+ "learning_rate": 9.939393939393939e-06,
701
+ "loss": 0.7452,
702
+ "step": 164
703
+ },
704
+ {
705
+ "epoch": 15.0,
706
+ "eval_loss": 0.7604131698608398,
707
+ "eval_runtime": 24.3513,
708
+ "eval_samples_per_second": 0.986,
709
+ "eval_steps_per_second": 0.986,
710
+ "step": 165
711
+ },
712
+ {
713
+ "epoch": 15.090909090909092,
714
+ "grad_norm": 0.31109246611595154,
715
+ "learning_rate": 9.999988811118232e-06,
716
+ "loss": 0.6938,
717
+ "step": 166
718
+ },
719
+ {
720
+ "epoch": 15.272727272727273,
721
+ "grad_norm": 0.3080443739891052,
722
+ "learning_rate": 9.999899300364534e-06,
723
+ "loss": 0.6979,
724
+ "step": 168
725
+ },
726
+ {
727
+ "epoch": 15.454545454545455,
728
+ "grad_norm": 0.37110060453414917,
729
+ "learning_rate": 9.999720280459576e-06,
730
+ "loss": 0.7866,
731
+ "step": 170
732
+ },
733
+ {
734
+ "epoch": 15.636363636363637,
735
+ "grad_norm": 0.9138216972351074,
736
+ "learning_rate": 9.999451754608208e-06,
737
+ "loss": 0.683,
738
+ "step": 172
739
+ },
740
+ {
741
+ "epoch": 15.818181818181818,
742
+ "grad_norm": 0.37108689546585083,
743
+ "learning_rate": 9.99909372761763e-06,
744
+ "loss": 0.7214,
745
+ "step": 174
746
+ },
747
+ {
748
+ "epoch": 16.0,
749
+ "grad_norm": 0.32667478919029236,
750
+ "learning_rate": 9.99864620589731e-06,
751
+ "loss": 0.6818,
752
+ "step": 176
753
+ },
754
+ {
755
+ "epoch": 16.0,
756
+ "eval_loss": 0.7484579086303711,
757
+ "eval_runtime": 24.3469,
758
+ "eval_samples_per_second": 0.986,
759
+ "eval_steps_per_second": 0.986,
760
+ "step": 176
761
+ },
762
+ {
763
+ "epoch": 16.181818181818183,
764
+ "grad_norm": 0.32395023107528687,
765
+ "learning_rate": 9.998109197458865e-06,
766
+ "loss": 0.6817,
767
+ "step": 178
768
+ },
769
+ {
770
+ "epoch": 16.363636363636363,
771
+ "grad_norm": 0.33770957589149475,
772
+ "learning_rate": 9.997482711915926e-06,
773
+ "loss": 0.7282,
774
+ "step": 180
775
+ },
776
+ {
777
+ "epoch": 16.545454545454547,
778
+ "grad_norm": 0.3693891763687134,
779
+ "learning_rate": 9.996766760483955e-06,
780
+ "loss": 0.6857,
781
+ "step": 182
782
+ },
783
+ {
784
+ "epoch": 16.727272727272727,
785
+ "grad_norm": 0.32818594574928284,
786
+ "learning_rate": 9.995961355980052e-06,
787
+ "loss": 0.653,
788
+ "step": 184
789
+ },
790
+ {
791
+ "epoch": 16.90909090909091,
792
+ "grad_norm": 0.3677254915237427,
793
+ "learning_rate": 9.99506651282272e-06,
794
+ "loss": 0.7119,
795
+ "step": 186
796
+ },
797
+ {
798
+ "epoch": 17.0,
799
+ "eval_loss": 0.7387299537658691,
800
+ "eval_runtime": 24.3449,
801
+ "eval_samples_per_second": 0.986,
802
+ "eval_steps_per_second": 0.986,
803
+ "step": 187
804
+ },
805
+ {
806
+ "epoch": 17.09090909090909,
807
+ "grad_norm": 0.33137425780296326,
808
+ "learning_rate": 9.994082247031613e-06,
809
+ "loss": 0.6706,
810
+ "step": 188
811
+ },
812
+ {
813
+ "epoch": 17.272727272727273,
814
+ "grad_norm": 0.34344998002052307,
815
+ "learning_rate": 9.993008576227248e-06,
816
+ "loss": 0.656,
817
+ "step": 190
818
+ },
819
+ {
820
+ "epoch": 17.454545454545453,
821
+ "grad_norm": 0.4169725775718689,
822
+ "learning_rate": 9.991845519630679e-06,
823
+ "loss": 0.6647,
824
+ "step": 192
825
+ },
826
+ {
827
+ "epoch": 17.636363636363637,
828
+ "grad_norm": 0.4314097762107849,
829
+ "learning_rate": 9.99059309806317e-06,
830
+ "loss": 0.6885,
831
+ "step": 194
832
+ },
833
+ {
834
+ "epoch": 17.818181818181817,
835
+ "grad_norm": 0.3693665862083435,
836
+ "learning_rate": 9.989251333945813e-06,
837
+ "loss": 0.6567,
838
+ "step": 196
839
+ },
840
+ {
841
+ "epoch": 18.0,
842
+ "grad_norm": 0.42939141392707825,
843
+ "learning_rate": 9.987820251299121e-06,
844
+ "loss": 0.7107,
845
+ "step": 198
846
+ },
847
+ {
848
+ "epoch": 18.0,
849
+ "eval_loss": 0.7306709289550781,
850
+ "eval_runtime": 24.3524,
851
+ "eval_samples_per_second": 0.986,
852
+ "eval_steps_per_second": 0.986,
853
+ "step": 198
854
+ },
855
+ {
856
+ "epoch": 18.181818181818183,
857
+ "grad_norm": 0.3910067677497864,
858
+ "learning_rate": 9.986299875742612e-06,
859
+ "loss": 0.6819,
860
+ "step": 200
861
+ },
862
+ {
863
+ "epoch": 18.363636363636363,
864
+ "grad_norm": 0.3679266571998596,
865
+ "learning_rate": 9.984690234494338e-06,
866
+ "loss": 0.6852,
867
+ "step": 202
868
+ },
869
+ {
870
+ "epoch": 18.545454545454547,
871
+ "grad_norm": 0.36058109998703003,
872
+ "learning_rate": 9.982991356370404e-06,
873
+ "loss": 0.6231,
874
+ "step": 204
875
+ },
876
+ {
877
+ "epoch": 18.727272727272727,
878
+ "grad_norm": 0.4211237132549286,
879
+ "learning_rate": 9.98120327178445e-06,
880
+ "loss": 0.6758,
881
+ "step": 206
882
+ },
883
+ {
884
+ "epoch": 18.90909090909091,
885
+ "grad_norm": 0.3913659155368805,
886
+ "learning_rate": 9.979326012747106e-06,
887
+ "loss": 0.6405,
888
+ "step": 208
889
+ },
890
+ {
891
+ "epoch": 19.0,
892
+ "eval_loss": 0.7237685322761536,
893
+ "eval_runtime": 24.3475,
894
+ "eval_samples_per_second": 0.986,
895
+ "eval_steps_per_second": 0.986,
896
+ "step": 209
897
+ },
898
+ {
899
+ "epoch": 19.09090909090909,
900
+ "grad_norm": 0.3846379816532135,
901
+ "learning_rate": 9.977359612865424e-06,
902
+ "loss": 0.5929,
903
+ "step": 210
904
+ },
905
+ {
906
+ "epoch": 19.272727272727273,
907
+ "grad_norm": 0.44087332487106323,
908
+ "learning_rate": 9.975304107342268e-06,
909
+ "loss": 0.627,
910
+ "step": 212
911
+ },
912
+ {
913
+ "epoch": 19.454545454545453,
914
+ "grad_norm": 0.467111200094223,
915
+ "learning_rate": 9.973159532975691e-06,
916
+ "loss": 0.6858,
917
+ "step": 214
918
+ },
919
+ {
920
+ "epoch": 19.636363636363637,
921
+ "grad_norm": 0.43696919083595276,
922
+ "learning_rate": 9.970925928158275e-06,
923
+ "loss": 0.6414,
924
+ "step": 216
925
+ },
926
+ {
927
+ "epoch": 19.818181818181817,
928
+ "grad_norm": 0.4129337966442108,
929
+ "learning_rate": 9.968603332876435e-06,
930
+ "loss": 0.6621,
931
+ "step": 218
932
+ },
933
+ {
934
+ "epoch": 20.0,
935
+ "grad_norm": 0.4260455369949341,
936
+ "learning_rate": 9.966191788709716e-06,
937
+ "loss": 0.6075,
938
+ "step": 220
939
+ },
940
+ {
941
+ "epoch": 20.0,
942
+ "eval_loss": 0.7188207507133484,
943
+ "eval_runtime": 24.3505,
944
+ "eval_samples_per_second": 0.986,
945
+ "eval_steps_per_second": 0.986,
946
+ "step": 220
947
+ },
948
+ {
949
+ "epoch": 20.181818181818183,
950
+ "grad_norm": 0.4215308725833893,
951
+ "learning_rate": 9.963691338830045e-06,
952
+ "loss": 0.611,
953
+ "step": 222
954
+ },
955
+ {
956
+ "epoch": 20.363636363636363,
957
+ "grad_norm": 0.4364253282546997,
958
+ "learning_rate": 9.961102028000948e-06,
959
+ "loss": 0.5843,
960
+ "step": 224
961
+ },
962
+ {
963
+ "epoch": 20.545454545454547,
964
+ "grad_norm": 0.45465582609176636,
965
+ "learning_rate": 9.958423902576764e-06,
966
+ "loss": 0.6556,
967
+ "step": 226
968
+ },
969
+ {
970
+ "epoch": 20.727272727272727,
971
+ "grad_norm": 0.43474891781806946,
972
+ "learning_rate": 9.955657010501807e-06,
973
+ "loss": 0.6197,
974
+ "step": 228
975
+ },
976
+ {
977
+ "epoch": 20.90909090909091,
978
+ "grad_norm": 0.4751872420310974,
979
+ "learning_rate": 9.952801401309504e-06,
980
+ "loss": 0.6323,
981
+ "step": 230
982
+ },
983
+ {
984
+ "epoch": 21.0,
985
+ "eval_loss": 0.7152169346809387,
986
+ "eval_runtime": 24.3508,
987
+ "eval_samples_per_second": 0.986,
988
+ "eval_steps_per_second": 0.986,
989
+ "step": 231
990
+ },
991
+ {
992
+ "epoch": 21.09090909090909,
993
+ "grad_norm": 0.4626959264278412,
994
+ "learning_rate": 9.949857126121519e-06,
995
+ "loss": 0.624,
996
+ "step": 232
997
+ },
998
+ {
999
+ "epoch": 21.272727272727273,
1000
+ "grad_norm": 0.45061811804771423,
1001
+ "learning_rate": 9.946824237646823e-06,
1002
+ "loss": 0.6272,
1003
+ "step": 234
1004
+ },
1005
+ {
1006
+ "epoch": 21.454545454545453,
1007
+ "grad_norm": 0.4539961814880371,
1008
+ "learning_rate": 9.94370279018077e-06,
1009
+ "loss": 0.6137,
1010
+ "step": 236
1011
+ },
1012
+ {
1013
+ "epoch": 21.636363636363637,
1014
+ "grad_norm": 0.5059633255004883,
1015
+ "learning_rate": 9.940492839604103e-06,
1016
+ "loss": 0.5831,
1017
+ "step": 238
1018
+ },
1019
+ {
1020
+ "epoch": 21.818181818181817,
1021
+ "grad_norm": 0.46466246247291565,
1022
+ "learning_rate": 9.937194443381972e-06,
1023
+ "loss": 0.6131,
1024
+ "step": 240
1025
+ },
1026
+ {
1027
+ "epoch": 22.0,
1028
+ "grad_norm": 0.5081361532211304,
1029
+ "learning_rate": 9.933807660562898e-06,
1030
+ "loss": 0.557,
1031
+ "step": 242
1032
+ },
1033
+ {
1034
+ "epoch": 22.0,
1035
+ "eval_loss": 0.7138778567314148,
1036
+ "eval_runtime": 24.3506,
1037
+ "eval_samples_per_second": 0.986,
1038
+ "eval_steps_per_second": 0.986,
1039
+ "step": 242
1040
+ },
1041
+ {
1042
+ "epoch": 22.181818181818183,
1043
+ "grad_norm": 0.4696747064590454,
1044
+ "learning_rate": 9.930332551777709e-06,
1045
+ "loss": 0.5765,
1046
+ "step": 244
1047
+ },
1048
+ {
1049
+ "epoch": 22.363636363636363,
1050
+ "grad_norm": 0.4927414655685425,
1051
+ "learning_rate": 9.926769179238467e-06,
1052
+ "loss": 0.6057,
1053
+ "step": 246
1054
+ },
1055
+ {
1056
+ "epoch": 22.545454545454547,
1057
+ "grad_norm": 0.5349259376525879,
1058
+ "learning_rate": 9.923117606737347e-06,
1059
+ "loss": 0.6059,
1060
+ "step": 248
1061
+ },
1062
+ {
1063
+ "epoch": 22.727272727272727,
1064
+ "grad_norm": 0.5289928317070007,
1065
+ "learning_rate": 9.919377899645497e-06,
1066
+ "loss": 0.5736,
1067
+ "step": 250
1068
+ },
1069
+ {
1070
+ "epoch": 22.90909090909091,
1071
+ "grad_norm": 0.5489732027053833,
1072
+ "learning_rate": 9.915550124911866e-06,
1073
+ "loss": 0.5692,
1074
+ "step": 252
1075
+ },
1076
+ {
1077
+ "epoch": 23.0,
1078
+ "eval_loss": 0.7158213257789612,
1079
+ "eval_runtime": 24.36,
1080
+ "eval_samples_per_second": 0.985,
1081
+ "eval_steps_per_second": 0.985,
1082
+ "step": 253
1083
+ },
1084
+ {
1085
+ "epoch": 23.09090909090909,
1086
+ "grad_norm": 0.5354622602462769,
1087
+ "learning_rate": 9.91163435106201e-06,
1088
+ "loss": 0.5341,
1089
+ "step": 254
1090
+ },
1091
+ {
1092
+ "epoch": 23.272727272727273,
1093
+ "grad_norm": 0.488086074590683,
1094
+ "learning_rate": 9.907630648196857e-06,
1095
+ "loss": 0.593,
1096
+ "step": 256
1097
+ },
1098
+ {
1099
+ "epoch": 23.454545454545453,
1100
+ "grad_norm": 0.545102059841156,
1101
+ "learning_rate": 9.903539087991462e-06,
1102
+ "loss": 0.568,
1103
+ "step": 258
1104
+ },
1105
+ {
1106
+ "epoch": 23.636363636363637,
1107
+ "grad_norm": 0.5522411465644836,
1108
+ "learning_rate": 9.899359743693715e-06,
1109
+ "loss": 0.5498,
1110
+ "step": 260
1111
+ },
1112
+ {
1113
+ "epoch": 23.818181818181817,
1114
+ "grad_norm": 0.6323682069778442,
1115
+ "learning_rate": 9.895092690123036e-06,
1116
+ "loss": 0.5401,
1117
+ "step": 262
1118
+ },
1119
+ {
1120
+ "epoch": 24.0,
1121
+ "grad_norm": 0.5789000988006592,
1122
+ "learning_rate": 9.890738003669029e-06,
1123
+ "loss": 0.558,
1124
+ "step": 264
1125
+ },
1126
+ {
1127
+ "epoch": 24.0,
1128
+ "eval_loss": 0.719824492931366,
1129
+ "eval_runtime": 24.3548,
1130
+ "eval_samples_per_second": 0.985,
1131
+ "eval_steps_per_second": 0.985,
1132
+ "step": 264
1133
+ },
1134
+ {
1135
+ "epoch": 24.181818181818183,
1136
+ "grad_norm": 0.5536386966705322,
1137
+ "learning_rate": 9.886295762290125e-06,
1138
+ "loss": 0.5058,
1139
+ "step": 266
1140
+ },
1141
+ {
1142
+ "epoch": 24.363636363636363,
1143
+ "grad_norm": 0.6637153029441833,
1144
+ "learning_rate": 9.881766045512176e-06,
1145
+ "loss": 0.5807,
1146
+ "step": 268
1147
+ },
1148
+ {
1149
+ "epoch": 24.545454545454547,
1150
+ "grad_norm": 0.619708240032196,
1151
+ "learning_rate": 9.877148934427037e-06,
1152
+ "loss": 0.5592,
1153
+ "step": 270
1154
+ },
1155
+ {
1156
+ "epoch": 24.727272727272727,
1157
+ "grad_norm": 0.6658281087875366,
1158
+ "learning_rate": 9.872444511691108e-06,
1159
+ "loss": 0.5266,
1160
+ "step": 272
1161
+ },
1162
+ {
1163
+ "epoch": 24.90909090909091,
1164
+ "grad_norm": 0.6834419369697571,
1165
+ "learning_rate": 9.867652861523866e-06,
1166
+ "loss": 0.5153,
1167
+ "step": 274
1168
+ },
1169
+ {
1170
+ "epoch": 25.0,
1171
+ "eval_loss": 0.7296044230461121,
1172
+ "eval_runtime": 24.3588,
1173
+ "eval_samples_per_second": 0.985,
1174
+ "eval_steps_per_second": 0.985,
1175
+ "step": 275
1176
+ },
1177
+ {
1178
+ "epoch": 25.09090909090909,
1179
+ "grad_norm": 0.667942225933075,
1180
+ "learning_rate": 9.862774069706346e-06,
1181
+ "loss": 0.4993,
1182
+ "step": 276
1183
+ },
1184
+ {
1185
+ "epoch": 25.272727272727273,
1186
+ "grad_norm": 0.6705055236816406,
1187
+ "learning_rate": 9.85780822357961e-06,
1188
+ "loss": 0.5251,
1189
+ "step": 278
1190
+ },
1191
+ {
1192
+ "epoch": 25.454545454545453,
1193
+ "grad_norm": 0.7730400562286377,
1194
+ "learning_rate": 9.85275541204318e-06,
1195
+ "loss": 0.5414,
1196
+ "step": 280
1197
+ },
1198
+ {
1199
+ "epoch": 25.636363636363637,
1200
+ "grad_norm": 0.6594474911689758,
1201
+ "learning_rate": 9.847615725553457e-06,
1202
+ "loss": 0.5029,
1203
+ "step": 282
1204
+ },
1205
+ {
1206
+ "epoch": 25.818181818181817,
1207
+ "grad_norm": 0.6896001696586609,
1208
+ "learning_rate": 9.842389256122086e-06,
1209
+ "loss": 0.4927,
1210
+ "step": 284
1211
+ },
1212
+ {
1213
+ "epoch": 26.0,
1214
+ "grad_norm": 0.714022159576416,
1215
+ "learning_rate": 9.83707609731432e-06,
1216
+ "loss": 0.4964,
1217
+ "step": 286
1218
+ },
1219
+ {
1220
+ "epoch": 26.0,
1221
+ "eval_loss": 0.7366821765899658,
1222
+ "eval_runtime": 24.3662,
1223
+ "eval_samples_per_second": 0.985,
1224
+ "eval_steps_per_second": 0.985,
1225
+ "step": 286
1226
+ },
1227
+ {
1228
+ "epoch": 26.181818181818183,
1229
+ "grad_norm": 0.8182728886604309,
1230
+ "learning_rate": 9.831676344247343e-06,
1231
+ "loss": 0.4601,
1232
+ "step": 288
1233
+ },
1234
+ {
1235
+ "epoch": 26.363636363636363,
1236
+ "grad_norm": 0.8259897828102112,
1237
+ "learning_rate": 9.826190093588564e-06,
1238
+ "loss": 0.5021,
1239
+ "step": 290
1240
+ },
1241
+ {
1242
+ "epoch": 26.545454545454547,
1243
+ "grad_norm": 0.8739567995071411,
1244
+ "learning_rate": 9.820617443553889e-06,
1245
+ "loss": 0.5133,
1246
+ "step": 292
1247
+ },
1248
+ {
1249
+ "epoch": 26.727272727272727,
1250
+ "grad_norm": 0.798852801322937,
1251
+ "learning_rate": 9.814958493905962e-06,
1252
+ "loss": 0.4688,
1253
+ "step": 294
1254
+ },
1255
+ {
1256
+ "epoch": 26.90909090909091,
1257
+ "grad_norm": 0.7111189365386963,
1258
+ "learning_rate": 9.80921334595238e-06,
1259
+ "loss": 0.4713,
1260
+ "step": 296
1261
+ },
1262
+ {
1263
+ "epoch": 27.0,
1264
+ "eval_loss": 0.7402606010437012,
1265
+ "eval_runtime": 24.3554,
1266
+ "eval_samples_per_second": 0.985,
1267
+ "eval_steps_per_second": 0.985,
1268
+ "step": 297
1269
+ },
1270
+ {
1271
+ "epoch": 27.09090909090909,
1272
+ "grad_norm": 0.7679806351661682,
1273
+ "learning_rate": 9.80338210254388e-06,
1274
+ "loss": 0.4414,
1275
+ "step": 298
1276
+ },
1277
+ {
1278
+ "epoch": 27.272727272727273,
1279
+ "grad_norm": 0.7741813659667969,
1280
+ "learning_rate": 9.797464868072489e-06,
1281
+ "loss": 0.4424,
1282
+ "step": 300
1283
+ },
1284
+ {
1285
+ "epoch": 27.454545454545453,
1286
+ "grad_norm": 0.7848456501960754,
1287
+ "learning_rate": 9.791461748469669e-06,
1288
+ "loss": 0.461,
1289
+ "step": 302
1290
+ },
1291
+ {
1292
+ "epoch": 27.636363636363637,
1293
+ "grad_norm": 0.9988805055618286,
1294
+ "learning_rate": 9.785372851204415e-06,
1295
+ "loss": 0.4594,
1296
+ "step": 304
1297
+ },
1298
+ {
1299
+ "epoch": 27.818181818181817,
1300
+ "grad_norm": 1.017672061920166,
1301
+ "learning_rate": 9.779198285281326e-06,
1302
+ "loss": 0.4656,
1303
+ "step": 306
1304
+ },
1305
+ {
1306
+ "epoch": 28.0,
1307
+ "grad_norm": 0.8862157464027405,
1308
+ "learning_rate": 9.77293816123866e-06,
1309
+ "loss": 0.4144,
1310
+ "step": 308
1311
+ },
1312
+ {
1313
+ "epoch": 28.0,
1314
+ "eval_loss": 0.7620039582252502,
1315
+ "eval_runtime": 24.3481,
1316
+ "eval_samples_per_second": 0.986,
1317
+ "eval_steps_per_second": 0.986,
1318
+ "step": 308
1319
+ },
1320
+ {
1321
+ "epoch": 28.181818181818183,
1322
+ "grad_norm": 1.078522801399231,
1323
+ "learning_rate": 9.766592591146353e-06,
1324
+ "loss": 0.4126,
1325
+ "step": 310
1326
+ },
1327
+ {
1328
+ "epoch": 28.363636363636363,
1329
+ "grad_norm": 0.8740026354789734,
1330
+ "learning_rate": 9.760161688604008e-06,
1331
+ "loss": 0.4104,
1332
+ "step": 312
1333
+ },
1334
+ {
1335
+ "epoch": 28.545454545454547,
1336
+ "grad_norm": 1.2476239204406738,
1337
+ "learning_rate": 9.753645568738872e-06,
1338
+ "loss": 0.4275,
1339
+ "step": 314
1340
+ },
1341
+ {
1342
+ "epoch": 28.727272727272727,
1343
+ "grad_norm": 1.1232469081878662,
1344
+ "learning_rate": 9.747044348203766e-06,
1345
+ "loss": 0.4,
1346
+ "step": 316
1347
+ },
1348
+ {
1349
+ "epoch": 28.90909090909091,
1350
+ "grad_norm": 0.9635869860649109,
1351
+ "learning_rate": 9.740358145174999e-06,
1352
+ "loss": 0.4184,
1353
+ "step": 318
1354
+ },
1355
+ {
1356
+ "epoch": 29.0,
1357
+ "eval_loss": 0.7954289317131042,
1358
+ "eval_runtime": 24.3558,
1359
+ "eval_samples_per_second": 0.985,
1360
+ "eval_steps_per_second": 0.985,
1361
+ "step": 319
1362
+ },
1363
+ {
1364
+ "epoch": 29.0,
1365
+ "step": 319,
1366
+ "total_flos": 2.4257124139375e+17,
1367
+ "train_loss": 0.757462413613699,
1368
+ "train_runtime": 8705.8997,
1369
+ "train_samples_per_second": 1.516,
1370
+ "train_steps_per_second": 0.19
1371
+ }
1372
+ ],
1373
+ "logging_steps": 2,
1374
+ "max_steps": 1650,
1375
+ "num_input_tokens_seen": 0,
1376
+ "num_train_epochs": 150,
1377
+ "save_steps": 25,
1378
+ "stateful_callbacks": {
1379
+ "EarlyStoppingCallback": {
1380
+ "args": {
1381
+ "early_stopping_patience": 7,
1382
+ "early_stopping_threshold": 0.0
1383
+ },
1384
+ "attributes": {
1385
+ "early_stopping_patience_counter": 0
1386
+ }
1387
+ },
1388
+ "TrainerControl": {
1389
+ "args": {
1390
+ "should_epoch_stop": false,
1391
+ "should_evaluate": false,
1392
+ "should_log": false,
1393
+ "should_save": true,
1394
+ "should_training_stop": true
1395
+ },
1396
+ "attributes": {}
1397
+ }
1398
+ },
1399
+ "total_flos": 2.4257124139375e+17,
1400
+ "train_batch_size": 1,
1401
+ "trial_name": null,
1402
+ "trial_params": null
1403
+ }
GaetanMichelet__Llama-31-8B_task-2_120-samples_config-3/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0890948678f7e10c6b1a4b3faef22cba7bab03455aec5ae3874b086ef02d1c5f
3
+ size 6264