jjee2 commited on
Commit
9bbbc9f
·
verified ·
1 Parent(s): edfe5db

Add GaetanMichelet__Llama-31-8B_task-2_180-samples_config-3

Browse files
GaetanMichelet__Llama-31-8B_task-2_180-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_180-samples_config-3/README.md ADDED
@@ -0,0 +1,95 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: meta-llama/Meta-Llama-3.1-8B-Instruct
3
+ datasets:
4
+ - GaetanMichelet/chat-60_ft_task-2
5
+ - GaetanMichelet/chat-120_ft_task-2
6
+ - GaetanMichelet/chat-180_ft_task-2
7
+ library_name: peft
8
+ license: llama3.1
9
+ tags:
10
+ - alignment-handbook
11
+ - trl
12
+ - sft
13
+ - generated_from_trainer
14
+ model-index:
15
+ - name: Llama-31-8B_task-2_180-samples_config-3
16
+ results: []
17
+ ---
18
+
19
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
20
+ should probably proofread and complete it, then remove this comment. -->
21
+
22
+ # Llama-31-8B_task-2_180-samples_config-3
23
+
24
+ This model is a fine-tuned version of [meta-llama/Meta-Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct) on the GaetanMichelet/chat-60_ft_task-2, the GaetanMichelet/chat-120_ft_task-2 and the GaetanMichelet/chat-180_ft_task-2 datasets.
25
+ It achieves the following results on the evaluation set:
26
+ - Loss: 0.7140
27
+
28
+ ## Model description
29
+
30
+ More information needed
31
+
32
+ ## Intended uses & limitations
33
+
34
+ More information needed
35
+
36
+ ## Training and evaluation data
37
+
38
+ More information needed
39
+
40
+ ## Training procedure
41
+
42
+ ### Training hyperparameters
43
+
44
+ The following hyperparameters were used during training:
45
+ - learning_rate: 1e-05
46
+ - train_batch_size: 1
47
+ - eval_batch_size: 1
48
+ - seed: 42
49
+ - distributed_type: multi-GPU
50
+ - gradient_accumulation_steps: 8
51
+ - total_train_batch_size: 8
52
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
53
+ - lr_scheduler_type: cosine
54
+ - lr_scheduler_warmup_ratio: 0.1
55
+ - num_epochs: 150
56
+
57
+ ### Training results
58
+
59
+ | Training Loss | Epoch | Step | Validation Loss |
60
+ |:-------------:|:-----:|:----:|:---------------:|
61
+ | 1.0365 | 1.0 | 17 | 1.1316 |
62
+ | 1.1746 | 2.0 | 34 | 1.1196 |
63
+ | 1.0933 | 3.0 | 51 | 1.0957 |
64
+ | 0.985 | 4.0 | 68 | 1.0540 |
65
+ | 0.9741 | 5.0 | 85 | 0.9950 |
66
+ | 1.0008 | 6.0 | 102 | 0.9377 |
67
+ | 0.8935 | 7.0 | 119 | 0.8939 |
68
+ | 0.8862 | 8.0 | 136 | 0.8579 |
69
+ | 0.8266 | 9.0 | 153 | 0.8294 |
70
+ | 0.7797 | 10.0 | 170 | 0.8075 |
71
+ | 0.8158 | 11.0 | 187 | 0.7903 |
72
+ | 0.6845 | 12.0 | 204 | 0.7742 |
73
+ | 0.6819 | 13.0 | 221 | 0.7598 |
74
+ | 0.7241 | 14.0 | 238 | 0.7472 |
75
+ | 0.695 | 15.0 | 255 | 0.7365 |
76
+ | 0.6982 | 16.0 | 272 | 0.7272 |
77
+ | 0.622 | 17.0 | 289 | 0.7215 |
78
+ | 0.5905 | 18.0 | 306 | 0.7156 |
79
+ | 0.6121 | 19.0 | 323 | 0.7140 |
80
+ | 0.567 | 20.0 | 340 | 0.7166 |
81
+ | 0.5471 | 21.0 | 357 | 0.7172 |
82
+ | 0.4761 | 22.0 | 374 | 0.7234 |
83
+ | 0.4967 | 23.0 | 391 | 0.7358 |
84
+ | 0.4833 | 24.0 | 408 | 0.7644 |
85
+ | 0.4071 | 25.0 | 425 | 0.8012 |
86
+ | 0.3567 | 26.0 | 442 | 0.8289 |
87
+
88
+
89
+ ### Framework versions
90
+
91
+ - PEFT 0.12.0
92
+ - Transformers 4.44.0
93
+ - Pytorch 2.1.2+cu121
94
+ - Datasets 2.20.0
95
+ - Tokenizers 0.19.1
GaetanMichelet__Llama-31-8B_task-2_180-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
+ "gate_proj",
25
+ "down_proj",
26
+ "up_proj",
27
+ "v_proj",
28
+ "o_proj",
29
+ "k_proj"
30
+ ],
31
+ "task_type": "CAUSAL_LM",
32
+ "use_dora": false,
33
+ "use_rslora": false
34
+ }
GaetanMichelet__Llama-31-8B_task-2_180-samples_config-3/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:417ecf2e864cb4dd0073d3d5bb288f9a5f59f201cbb62fc4f0134fa633622d66
3
+ size 167832240
GaetanMichelet__Llama-31-8B_task-2_180-samples_config-3/all_results.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 26.0,
3
+ "eval_loss": 0.7140286564826965,
4
+ "eval_runtime": 36.9692,
5
+ "eval_samples": 36,
6
+ "eval_samples_per_second": 0.974,
7
+ "eval_steps_per_second": 0.974,
8
+ "total_flos": 3.38458179962667e+17,
9
+ "train_loss": 0.7497456199173475,
10
+ "train_runtime": 12081.7026,
11
+ "train_samples": 136,
12
+ "train_samples_per_second": 1.689,
13
+ "train_steps_per_second": 0.211
14
+ }
GaetanMichelet__Llama-31-8B_task-2_180-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_180-samples_config-3/eval_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 26.0,
3
+ "eval_loss": 0.7140286564826965,
4
+ "eval_runtime": 36.9692,
5
+ "eval_samples": 36,
6
+ "eval_samples_per_second": 0.974,
7
+ "eval_steps_per_second": 0.974
8
+ }
GaetanMichelet__Llama-31-8B_task-2_180-samples_config-3/runs/Aug18_18-52-02_9mqd6r3-l/events.out.tfevents.1723999939.9mqd6r3-l.2971326.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b8f1ed9994c5fdec7608d99229346f6026f430894127701a28f250c33a2a0cb
3
+ size 60767
GaetanMichelet__Llama-31-8B_task-2_180-samples_config-3/runs/Aug18_18-52-02_9mqd6r3-l/events.out.tfevents.1724012072.9mqd6r3-l.2971326.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e9e2d03905faa78229acd2ce6f687cf1edb72e8432020d1f6a8a371bbaf4a8c
3
+ size 359
GaetanMichelet__Llama-31-8B_task-2_180-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_180-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_180-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_180-samples_config-3/train_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 26.0,
3
+ "total_flos": 3.38458179962667e+17,
4
+ "train_loss": 0.7497456199173475,
5
+ "train_runtime": 12081.7026,
6
+ "train_samples": 136,
7
+ "train_samples_per_second": 1.689,
8
+ "train_steps_per_second": 0.211
9
+ }
GaetanMichelet__Llama-31-8B_task-2_180-samples_config-3/trainer_state.json ADDED
@@ -0,0 +1,1813 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.7140286564826965,
3
+ "best_model_checkpoint": "data/Llama-31-8B_task-2_180-samples_config-3/checkpoint-323",
4
+ "epoch": 26.0,
5
+ "eval_steps": 500,
6
+ "global_step": 442,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.058823529411764705,
13
+ "grad_norm": 0.7734732031822205,
14
+ "learning_rate": 3.9215686274509804e-08,
15
+ "loss": 1.1412,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.11764705882352941,
20
+ "grad_norm": 0.6782335638999939,
21
+ "learning_rate": 7.843137254901961e-08,
22
+ "loss": 1.1733,
23
+ "step": 2
24
+ },
25
+ {
26
+ "epoch": 0.23529411764705882,
27
+ "grad_norm": 0.8408952951431274,
28
+ "learning_rate": 1.5686274509803921e-07,
29
+ "loss": 1.1666,
30
+ "step": 4
31
+ },
32
+ {
33
+ "epoch": 0.35294117647058826,
34
+ "grad_norm": 0.7287867069244385,
35
+ "learning_rate": 2.3529411764705883e-07,
36
+ "loss": 1.1801,
37
+ "step": 6
38
+ },
39
+ {
40
+ "epoch": 0.47058823529411764,
41
+ "grad_norm": 0.7565770745277405,
42
+ "learning_rate": 3.1372549019607843e-07,
43
+ "loss": 1.1116,
44
+ "step": 8
45
+ },
46
+ {
47
+ "epoch": 0.5882352941176471,
48
+ "grad_norm": 0.6836811304092407,
49
+ "learning_rate": 3.921568627450981e-07,
50
+ "loss": 1.1475,
51
+ "step": 10
52
+ },
53
+ {
54
+ "epoch": 0.7058823529411765,
55
+ "grad_norm": 0.6788910627365112,
56
+ "learning_rate": 4.7058823529411767e-07,
57
+ "loss": 1.0752,
58
+ "step": 12
59
+ },
60
+ {
61
+ "epoch": 0.8235294117647058,
62
+ "grad_norm": 0.6463932991027832,
63
+ "learning_rate": 5.490196078431373e-07,
64
+ "loss": 1.1428,
65
+ "step": 14
66
+ },
67
+ {
68
+ "epoch": 0.9411764705882353,
69
+ "grad_norm": 0.7503110766410828,
70
+ "learning_rate": 6.274509803921569e-07,
71
+ "loss": 1.0365,
72
+ "step": 16
73
+ },
74
+ {
75
+ "epoch": 1.0,
76
+ "eval_loss": 1.131649374961853,
77
+ "eval_runtime": 37.0173,
78
+ "eval_samples_per_second": 0.973,
79
+ "eval_steps_per_second": 0.973,
80
+ "step": 17
81
+ },
82
+ {
83
+ "epoch": 1.0588235294117647,
84
+ "grad_norm": 0.7130016088485718,
85
+ "learning_rate": 7.058823529411766e-07,
86
+ "loss": 1.1439,
87
+ "step": 18
88
+ },
89
+ {
90
+ "epoch": 1.1764705882352942,
91
+ "grad_norm": 0.69338458776474,
92
+ "learning_rate": 7.843137254901962e-07,
93
+ "loss": 1.1374,
94
+ "step": 20
95
+ },
96
+ {
97
+ "epoch": 1.2941176470588236,
98
+ "grad_norm": 0.6517343521118164,
99
+ "learning_rate": 8.627450980392157e-07,
100
+ "loss": 1.1213,
101
+ "step": 22
102
+ },
103
+ {
104
+ "epoch": 1.4117647058823528,
105
+ "grad_norm": 0.685614287853241,
106
+ "learning_rate": 9.411764705882353e-07,
107
+ "loss": 1.1182,
108
+ "step": 24
109
+ },
110
+ {
111
+ "epoch": 1.5294117647058822,
112
+ "grad_norm": 0.6998293995857239,
113
+ "learning_rate": 1.019607843137255e-06,
114
+ "loss": 1.0508,
115
+ "step": 26
116
+ },
117
+ {
118
+ "epoch": 1.6470588235294117,
119
+ "grad_norm": 0.6757376194000244,
120
+ "learning_rate": 1.0980392156862745e-06,
121
+ "loss": 1.0773,
122
+ "step": 28
123
+ },
124
+ {
125
+ "epoch": 1.7647058823529411,
126
+ "grad_norm": 0.7003068327903748,
127
+ "learning_rate": 1.1764705882352942e-06,
128
+ "loss": 1.1765,
129
+ "step": 30
130
+ },
131
+ {
132
+ "epoch": 1.8823529411764706,
133
+ "grad_norm": 0.75652676820755,
134
+ "learning_rate": 1.2549019607843137e-06,
135
+ "loss": 1.0897,
136
+ "step": 32
137
+ },
138
+ {
139
+ "epoch": 2.0,
140
+ "grad_norm": 0.8910195231437683,
141
+ "learning_rate": 1.3333333333333334e-06,
142
+ "loss": 1.1746,
143
+ "step": 34
144
+ },
145
+ {
146
+ "epoch": 2.0,
147
+ "eval_loss": 1.119631290435791,
148
+ "eval_runtime": 37.0058,
149
+ "eval_samples_per_second": 0.973,
150
+ "eval_steps_per_second": 0.973,
151
+ "step": 34
152
+ },
153
+ {
154
+ "epoch": 2.1176470588235294,
155
+ "grad_norm": 0.6963354349136353,
156
+ "learning_rate": 1.4117647058823531e-06,
157
+ "loss": 1.0914,
158
+ "step": 36
159
+ },
160
+ {
161
+ "epoch": 2.235294117647059,
162
+ "grad_norm": 0.6639174818992615,
163
+ "learning_rate": 1.4901960784313726e-06,
164
+ "loss": 1.1038,
165
+ "step": 38
166
+ },
167
+ {
168
+ "epoch": 2.3529411764705883,
169
+ "grad_norm": 0.7396222949028015,
170
+ "learning_rate": 1.5686274509803923e-06,
171
+ "loss": 1.0596,
172
+ "step": 40
173
+ },
174
+ {
175
+ "epoch": 2.4705882352941178,
176
+ "grad_norm": 0.7213342189788818,
177
+ "learning_rate": 1.6470588235294118e-06,
178
+ "loss": 1.0962,
179
+ "step": 42
180
+ },
181
+ {
182
+ "epoch": 2.588235294117647,
183
+ "grad_norm": 0.7507779002189636,
184
+ "learning_rate": 1.7254901960784315e-06,
185
+ "loss": 1.0945,
186
+ "step": 44
187
+ },
188
+ {
189
+ "epoch": 2.7058823529411766,
190
+ "grad_norm": 0.803626298904419,
191
+ "learning_rate": 1.8039215686274512e-06,
192
+ "loss": 1.1417,
193
+ "step": 46
194
+ },
195
+ {
196
+ "epoch": 2.8235294117647056,
197
+ "grad_norm": 0.8166558742523193,
198
+ "learning_rate": 1.8823529411764707e-06,
199
+ "loss": 1.1391,
200
+ "step": 48
201
+ },
202
+ {
203
+ "epoch": 2.9411764705882355,
204
+ "grad_norm": 0.7504469752311707,
205
+ "learning_rate": 1.96078431372549e-06,
206
+ "loss": 1.0933,
207
+ "step": 50
208
+ },
209
+ {
210
+ "epoch": 3.0,
211
+ "eval_loss": 1.0957257747650146,
212
+ "eval_runtime": 37.0081,
213
+ "eval_samples_per_second": 0.973,
214
+ "eval_steps_per_second": 0.973,
215
+ "step": 51
216
+ },
217
+ {
218
+ "epoch": 3.0588235294117645,
219
+ "grad_norm": 0.7341092228889465,
220
+ "learning_rate": 2.03921568627451e-06,
221
+ "loss": 1.0645,
222
+ "step": 52
223
+ },
224
+ {
225
+ "epoch": 3.176470588235294,
226
+ "grad_norm": 0.7262235283851624,
227
+ "learning_rate": 2.1176470588235296e-06,
228
+ "loss": 1.1047,
229
+ "step": 54
230
+ },
231
+ {
232
+ "epoch": 3.2941176470588234,
233
+ "grad_norm": 0.6933767795562744,
234
+ "learning_rate": 2.196078431372549e-06,
235
+ "loss": 1.0305,
236
+ "step": 56
237
+ },
238
+ {
239
+ "epoch": 3.411764705882353,
240
+ "grad_norm": 0.8481059670448303,
241
+ "learning_rate": 2.274509803921569e-06,
242
+ "loss": 1.1403,
243
+ "step": 58
244
+ },
245
+ {
246
+ "epoch": 3.5294117647058822,
247
+ "grad_norm": 0.7597863078117371,
248
+ "learning_rate": 2.3529411764705885e-06,
249
+ "loss": 1.0537,
250
+ "step": 60
251
+ },
252
+ {
253
+ "epoch": 3.6470588235294117,
254
+ "grad_norm": 0.7542691826820374,
255
+ "learning_rate": 2.431372549019608e-06,
256
+ "loss": 1.0815,
257
+ "step": 62
258
+ },
259
+ {
260
+ "epoch": 3.764705882352941,
261
+ "grad_norm": 0.7457835674285889,
262
+ "learning_rate": 2.5098039215686274e-06,
263
+ "loss": 1.0747,
264
+ "step": 64
265
+ },
266
+ {
267
+ "epoch": 3.8823529411764706,
268
+ "grad_norm": 0.6987655758857727,
269
+ "learning_rate": 2.5882352941176473e-06,
270
+ "loss": 1.1015,
271
+ "step": 66
272
+ },
273
+ {
274
+ "epoch": 4.0,
275
+ "grad_norm": 0.7653221487998962,
276
+ "learning_rate": 2.666666666666667e-06,
277
+ "loss": 0.985,
278
+ "step": 68
279
+ },
280
+ {
281
+ "epoch": 4.0,
282
+ "eval_loss": 1.0540263652801514,
283
+ "eval_runtime": 37.0036,
284
+ "eval_samples_per_second": 0.973,
285
+ "eval_steps_per_second": 0.973,
286
+ "step": 68
287
+ },
288
+ {
289
+ "epoch": 4.117647058823529,
290
+ "grad_norm": 0.6138588190078735,
291
+ "learning_rate": 2.7450980392156867e-06,
292
+ "loss": 1.0818,
293
+ "step": 70
294
+ },
295
+ {
296
+ "epoch": 4.235294117647059,
297
+ "grad_norm": 0.7161767482757568,
298
+ "learning_rate": 2.8235294117647062e-06,
299
+ "loss": 1.0233,
300
+ "step": 72
301
+ },
302
+ {
303
+ "epoch": 4.352941176470588,
304
+ "grad_norm": 0.5691388845443726,
305
+ "learning_rate": 2.901960784313726e-06,
306
+ "loss": 1.0152,
307
+ "step": 74
308
+ },
309
+ {
310
+ "epoch": 4.470588235294118,
311
+ "grad_norm": 0.6562293171882629,
312
+ "learning_rate": 2.980392156862745e-06,
313
+ "loss": 1.0299,
314
+ "step": 76
315
+ },
316
+ {
317
+ "epoch": 4.588235294117647,
318
+ "grad_norm": 0.6522495150566101,
319
+ "learning_rate": 3.058823529411765e-06,
320
+ "loss": 1.0341,
321
+ "step": 78
322
+ },
323
+ {
324
+ "epoch": 4.705882352941177,
325
+ "grad_norm": 0.6249567270278931,
326
+ "learning_rate": 3.1372549019607846e-06,
327
+ "loss": 0.9573,
328
+ "step": 80
329
+ },
330
+ {
331
+ "epoch": 4.823529411764706,
332
+ "grad_norm": 0.6513485312461853,
333
+ "learning_rate": 3.2156862745098045e-06,
334
+ "loss": 1.0373,
335
+ "step": 82
336
+ },
337
+ {
338
+ "epoch": 4.9411764705882355,
339
+ "grad_norm": 0.6425153613090515,
340
+ "learning_rate": 3.2941176470588236e-06,
341
+ "loss": 0.9741,
342
+ "step": 84
343
+ },
344
+ {
345
+ "epoch": 5.0,
346
+ "eval_loss": 0.99503093957901,
347
+ "eval_runtime": 37.0007,
348
+ "eval_samples_per_second": 0.973,
349
+ "eval_steps_per_second": 0.973,
350
+ "step": 85
351
+ },
352
+ {
353
+ "epoch": 5.0588235294117645,
354
+ "grad_norm": 0.645844042301178,
355
+ "learning_rate": 3.3725490196078435e-06,
356
+ "loss": 0.9862,
357
+ "step": 86
358
+ },
359
+ {
360
+ "epoch": 5.176470588235294,
361
+ "grad_norm": 0.6497894525527954,
362
+ "learning_rate": 3.450980392156863e-06,
363
+ "loss": 0.9873,
364
+ "step": 88
365
+ },
366
+ {
367
+ "epoch": 5.294117647058823,
368
+ "grad_norm": 0.5283099412918091,
369
+ "learning_rate": 3.529411764705883e-06,
370
+ "loss": 0.9488,
371
+ "step": 90
372
+ },
373
+ {
374
+ "epoch": 5.411764705882353,
375
+ "grad_norm": 0.4905494451522827,
376
+ "learning_rate": 3.6078431372549024e-06,
377
+ "loss": 0.9606,
378
+ "step": 92
379
+ },
380
+ {
381
+ "epoch": 5.529411764705882,
382
+ "grad_norm": 0.5407238602638245,
383
+ "learning_rate": 3.6862745098039223e-06,
384
+ "loss": 0.888,
385
+ "step": 94
386
+ },
387
+ {
388
+ "epoch": 5.647058823529412,
389
+ "grad_norm": 0.5735270977020264,
390
+ "learning_rate": 3.7647058823529414e-06,
391
+ "loss": 0.916,
392
+ "step": 96
393
+ },
394
+ {
395
+ "epoch": 5.764705882352941,
396
+ "grad_norm": 0.5201605558395386,
397
+ "learning_rate": 3.843137254901962e-06,
398
+ "loss": 0.982,
399
+ "step": 98
400
+ },
401
+ {
402
+ "epoch": 5.882352941176471,
403
+ "grad_norm": 0.4470115303993225,
404
+ "learning_rate": 3.92156862745098e-06,
405
+ "loss": 0.9389,
406
+ "step": 100
407
+ },
408
+ {
409
+ "epoch": 6.0,
410
+ "grad_norm": 0.3844221532344818,
411
+ "learning_rate": 4.000000000000001e-06,
412
+ "loss": 1.0008,
413
+ "step": 102
414
+ },
415
+ {
416
+ "epoch": 6.0,
417
+ "eval_loss": 0.937701940536499,
418
+ "eval_runtime": 37.0036,
419
+ "eval_samples_per_second": 0.973,
420
+ "eval_steps_per_second": 0.973,
421
+ "step": 102
422
+ },
423
+ {
424
+ "epoch": 6.117647058823529,
425
+ "grad_norm": 0.4652542173862457,
426
+ "learning_rate": 4.07843137254902e-06,
427
+ "loss": 0.915,
428
+ "step": 104
429
+ },
430
+ {
431
+ "epoch": 6.235294117647059,
432
+ "grad_norm": 0.4144337773323059,
433
+ "learning_rate": 4.15686274509804e-06,
434
+ "loss": 0.8833,
435
+ "step": 106
436
+ },
437
+ {
438
+ "epoch": 6.352941176470588,
439
+ "grad_norm": 0.4218851327896118,
440
+ "learning_rate": 4.235294117647059e-06,
441
+ "loss": 0.8672,
442
+ "step": 108
443
+ },
444
+ {
445
+ "epoch": 6.470588235294118,
446
+ "grad_norm": 0.4070567786693573,
447
+ "learning_rate": 4.313725490196079e-06,
448
+ "loss": 0.9036,
449
+ "step": 110
450
+ },
451
+ {
452
+ "epoch": 6.588235294117647,
453
+ "grad_norm": 0.36765947937965393,
454
+ "learning_rate": 4.392156862745098e-06,
455
+ "loss": 0.9384,
456
+ "step": 112
457
+ },
458
+ {
459
+ "epoch": 6.705882352941177,
460
+ "grad_norm": 0.3613109886646271,
461
+ "learning_rate": 4.4705882352941184e-06,
462
+ "loss": 0.904,
463
+ "step": 114
464
+ },
465
+ {
466
+ "epoch": 6.823529411764706,
467
+ "grad_norm": 0.36222243309020996,
468
+ "learning_rate": 4.549019607843138e-06,
469
+ "loss": 0.8641,
470
+ "step": 116
471
+ },
472
+ {
473
+ "epoch": 6.9411764705882355,
474
+ "grad_norm": 0.42111915349960327,
475
+ "learning_rate": 4.627450980392157e-06,
476
+ "loss": 0.8935,
477
+ "step": 118
478
+ },
479
+ {
480
+ "epoch": 7.0,
481
+ "eval_loss": 0.8938563466072083,
482
+ "eval_runtime": 37.0541,
483
+ "eval_samples_per_second": 0.972,
484
+ "eval_steps_per_second": 0.972,
485
+ "step": 119
486
+ },
487
+ {
488
+ "epoch": 7.0588235294117645,
489
+ "grad_norm": 0.35050034523010254,
490
+ "learning_rate": 4.705882352941177e-06,
491
+ "loss": 0.9626,
492
+ "step": 120
493
+ },
494
+ {
495
+ "epoch": 7.176470588235294,
496
+ "grad_norm": 0.37680429220199585,
497
+ "learning_rate": 4.784313725490196e-06,
498
+ "loss": 0.8818,
499
+ "step": 122
500
+ },
501
+ {
502
+ "epoch": 7.294117647058823,
503
+ "grad_norm": 0.3310965895652771,
504
+ "learning_rate": 4.862745098039216e-06,
505
+ "loss": 0.8631,
506
+ "step": 124
507
+ },
508
+ {
509
+ "epoch": 7.411764705882353,
510
+ "grad_norm": 0.3843957781791687,
511
+ "learning_rate": 4.941176470588236e-06,
512
+ "loss": 0.8506,
513
+ "step": 126
514
+ },
515
+ {
516
+ "epoch": 7.529411764705882,
517
+ "grad_norm": 0.3577839732170105,
518
+ "learning_rate": 5.019607843137255e-06,
519
+ "loss": 0.841,
520
+ "step": 128
521
+ },
522
+ {
523
+ "epoch": 7.647058823529412,
524
+ "grad_norm": 0.3117690682411194,
525
+ "learning_rate": 5.098039215686274e-06,
526
+ "loss": 0.8576,
527
+ "step": 130
528
+ },
529
+ {
530
+ "epoch": 7.764705882352941,
531
+ "grad_norm": 0.37441667914390564,
532
+ "learning_rate": 5.176470588235295e-06,
533
+ "loss": 0.8127,
534
+ "step": 132
535
+ },
536
+ {
537
+ "epoch": 7.882352941176471,
538
+ "grad_norm": 0.3178256154060364,
539
+ "learning_rate": 5.254901960784314e-06,
540
+ "loss": 0.8554,
541
+ "step": 134
542
+ },
543
+ {
544
+ "epoch": 8.0,
545
+ "grad_norm": 0.3216207027435303,
546
+ "learning_rate": 5.333333333333334e-06,
547
+ "loss": 0.8862,
548
+ "step": 136
549
+ },
550
+ {
551
+ "epoch": 8.0,
552
+ "eval_loss": 0.8579282760620117,
553
+ "eval_runtime": 37.0044,
554
+ "eval_samples_per_second": 0.973,
555
+ "eval_steps_per_second": 0.973,
556
+ "step": 136
557
+ },
558
+ {
559
+ "epoch": 8.117647058823529,
560
+ "grad_norm": 0.341949462890625,
561
+ "learning_rate": 5.411764705882353e-06,
562
+ "loss": 0.8519,
563
+ "step": 138
564
+ },
565
+ {
566
+ "epoch": 8.235294117647058,
567
+ "grad_norm": 0.3150944113731384,
568
+ "learning_rate": 5.4901960784313735e-06,
569
+ "loss": 0.8338,
570
+ "step": 140
571
+ },
572
+ {
573
+ "epoch": 8.352941176470589,
574
+ "grad_norm": 0.3646303713321686,
575
+ "learning_rate": 5.568627450980393e-06,
576
+ "loss": 0.8381,
577
+ "step": 142
578
+ },
579
+ {
580
+ "epoch": 8.470588235294118,
581
+ "grad_norm": 0.334943950176239,
582
+ "learning_rate": 5.6470588235294125e-06,
583
+ "loss": 0.879,
584
+ "step": 144
585
+ },
586
+ {
587
+ "epoch": 8.588235294117647,
588
+ "grad_norm": 0.3029642403125763,
589
+ "learning_rate": 5.725490196078431e-06,
590
+ "loss": 0.7807,
591
+ "step": 146
592
+ },
593
+ {
594
+ "epoch": 8.705882352941176,
595
+ "grad_norm": 0.30906420946121216,
596
+ "learning_rate": 5.803921568627452e-06,
597
+ "loss": 0.7946,
598
+ "step": 148
599
+ },
600
+ {
601
+ "epoch": 8.823529411764707,
602
+ "grad_norm": 0.34527918696403503,
603
+ "learning_rate": 5.882352941176471e-06,
604
+ "loss": 0.8397,
605
+ "step": 150
606
+ },
607
+ {
608
+ "epoch": 8.941176470588236,
609
+ "grad_norm": 0.3913155794143677,
610
+ "learning_rate": 5.96078431372549e-06,
611
+ "loss": 0.8266,
612
+ "step": 152
613
+ },
614
+ {
615
+ "epoch": 9.0,
616
+ "eval_loss": 0.8293797969818115,
617
+ "eval_runtime": 37.0023,
618
+ "eval_samples_per_second": 0.973,
619
+ "eval_steps_per_second": 0.973,
620
+ "step": 153
621
+ },
622
+ {
623
+ "epoch": 9.058823529411764,
624
+ "grad_norm": 0.3411412835121155,
625
+ "learning_rate": 6.03921568627451e-06,
626
+ "loss": 0.8249,
627
+ "step": 154
628
+ },
629
+ {
630
+ "epoch": 9.176470588235293,
631
+ "grad_norm": 0.28964897990226746,
632
+ "learning_rate": 6.11764705882353e-06,
633
+ "loss": 0.7887,
634
+ "step": 156
635
+ },
636
+ {
637
+ "epoch": 9.294117647058824,
638
+ "grad_norm": 0.36540400981903076,
639
+ "learning_rate": 6.19607843137255e-06,
640
+ "loss": 0.7434,
641
+ "step": 158
642
+ },
643
+ {
644
+ "epoch": 9.411764705882353,
645
+ "grad_norm": 0.3152979016304016,
646
+ "learning_rate": 6.274509803921569e-06,
647
+ "loss": 0.7864,
648
+ "step": 160
649
+ },
650
+ {
651
+ "epoch": 9.529411764705882,
652
+ "grad_norm": 0.28152012825012207,
653
+ "learning_rate": 6.352941176470589e-06,
654
+ "loss": 0.777,
655
+ "step": 162
656
+ },
657
+ {
658
+ "epoch": 9.647058823529411,
659
+ "grad_norm": 0.37814223766326904,
660
+ "learning_rate": 6.431372549019609e-06,
661
+ "loss": 0.8319,
662
+ "step": 164
663
+ },
664
+ {
665
+ "epoch": 9.764705882352942,
666
+ "grad_norm": 0.3085719645023346,
667
+ "learning_rate": 6.5098039215686285e-06,
668
+ "loss": 0.7986,
669
+ "step": 166
670
+ },
671
+ {
672
+ "epoch": 9.882352941176471,
673
+ "grad_norm": 0.29185226559638977,
674
+ "learning_rate": 6.588235294117647e-06,
675
+ "loss": 0.8292,
676
+ "step": 168
677
+ },
678
+ {
679
+ "epoch": 10.0,
680
+ "grad_norm": 0.30540931224823,
681
+ "learning_rate": 6.666666666666667e-06,
682
+ "loss": 0.7797,
683
+ "step": 170
684
+ },
685
+ {
686
+ "epoch": 10.0,
687
+ "eval_loss": 0.807489275932312,
688
+ "eval_runtime": 37.0049,
689
+ "eval_samples_per_second": 0.973,
690
+ "eval_steps_per_second": 0.973,
691
+ "step": 170
692
+ },
693
+ {
694
+ "epoch": 10.117647058823529,
695
+ "grad_norm": 0.3091186285018921,
696
+ "learning_rate": 6.745098039215687e-06,
697
+ "loss": 0.7765,
698
+ "step": 172
699
+ },
700
+ {
701
+ "epoch": 10.235294117647058,
702
+ "grad_norm": 0.30727335810661316,
703
+ "learning_rate": 6.8235294117647065e-06,
704
+ "loss": 0.7505,
705
+ "step": 174
706
+ },
707
+ {
708
+ "epoch": 10.352941176470589,
709
+ "grad_norm": 0.2999902665615082,
710
+ "learning_rate": 6.901960784313726e-06,
711
+ "loss": 0.7233,
712
+ "step": 176
713
+ },
714
+ {
715
+ "epoch": 10.470588235294118,
716
+ "grad_norm": 0.2925303876399994,
717
+ "learning_rate": 6.9803921568627454e-06,
718
+ "loss": 0.7613,
719
+ "step": 178
720
+ },
721
+ {
722
+ "epoch": 10.588235294117647,
723
+ "grad_norm": 0.28137609362602234,
724
+ "learning_rate": 7.058823529411766e-06,
725
+ "loss": 0.7336,
726
+ "step": 180
727
+ },
728
+ {
729
+ "epoch": 10.705882352941176,
730
+ "grad_norm": 0.3438097834587097,
731
+ "learning_rate": 7.137254901960785e-06,
732
+ "loss": 0.822,
733
+ "step": 182
734
+ },
735
+ {
736
+ "epoch": 10.823529411764707,
737
+ "grad_norm": 0.3309740722179413,
738
+ "learning_rate": 7.215686274509805e-06,
739
+ "loss": 0.8488,
740
+ "step": 184
741
+ },
742
+ {
743
+ "epoch": 10.941176470588236,
744
+ "grad_norm": 0.33822691440582275,
745
+ "learning_rate": 7.294117647058823e-06,
746
+ "loss": 0.8158,
747
+ "step": 186
748
+ },
749
+ {
750
+ "epoch": 11.0,
751
+ "eval_loss": 0.790329098701477,
752
+ "eval_runtime": 37.0086,
753
+ "eval_samples_per_second": 0.973,
754
+ "eval_steps_per_second": 0.973,
755
+ "step": 187
756
+ },
757
+ {
758
+ "epoch": 11.058823529411764,
759
+ "grad_norm": 0.3196800649166107,
760
+ "learning_rate": 7.372549019607845e-06,
761
+ "loss": 0.7996,
762
+ "step": 188
763
+ },
764
+ {
765
+ "epoch": 11.176470588235293,
766
+ "grad_norm": 0.2967463731765747,
767
+ "learning_rate": 7.450980392156863e-06,
768
+ "loss": 0.7102,
769
+ "step": 190
770
+ },
771
+ {
772
+ "epoch": 11.294117647058824,
773
+ "grad_norm": 0.32051464915275574,
774
+ "learning_rate": 7.529411764705883e-06,
775
+ "loss": 0.8008,
776
+ "step": 192
777
+ },
778
+ {
779
+ "epoch": 11.411764705882353,
780
+ "grad_norm": 0.399475634098053,
781
+ "learning_rate": 7.607843137254902e-06,
782
+ "loss": 0.8271,
783
+ "step": 194
784
+ },
785
+ {
786
+ "epoch": 11.529411764705882,
787
+ "grad_norm": 0.3100043535232544,
788
+ "learning_rate": 7.686274509803923e-06,
789
+ "loss": 0.7954,
790
+ "step": 196
791
+ },
792
+ {
793
+ "epoch": 11.647058823529411,
794
+ "grad_norm": 0.31522953510284424,
795
+ "learning_rate": 7.764705882352941e-06,
796
+ "loss": 0.712,
797
+ "step": 198
798
+ },
799
+ {
800
+ "epoch": 11.764705882352942,
801
+ "grad_norm": 0.3450244665145874,
802
+ "learning_rate": 7.84313725490196e-06,
803
+ "loss": 0.7329,
804
+ "step": 200
805
+ },
806
+ {
807
+ "epoch": 11.882352941176471,
808
+ "grad_norm": 0.3267311453819275,
809
+ "learning_rate": 7.92156862745098e-06,
810
+ "loss": 0.7275,
811
+ "step": 202
812
+ },
813
+ {
814
+ "epoch": 12.0,
815
+ "grad_norm": 0.42111936211586,
816
+ "learning_rate": 8.000000000000001e-06,
817
+ "loss": 0.6845,
818
+ "step": 204
819
+ },
820
+ {
821
+ "epoch": 12.0,
822
+ "eval_loss": 0.7741987705230713,
823
+ "eval_runtime": 37.0028,
824
+ "eval_samples_per_second": 0.973,
825
+ "eval_steps_per_second": 0.973,
826
+ "step": 204
827
+ },
828
+ {
829
+ "epoch": 12.117647058823529,
830
+ "grad_norm": 0.33904674649238586,
831
+ "learning_rate": 8.07843137254902e-06,
832
+ "loss": 0.7635,
833
+ "step": 206
834
+ },
835
+ {
836
+ "epoch": 12.235294117647058,
837
+ "grad_norm": 0.33812686800956726,
838
+ "learning_rate": 8.15686274509804e-06,
839
+ "loss": 0.8239,
840
+ "step": 208
841
+ },
842
+ {
843
+ "epoch": 12.352941176470589,
844
+ "grad_norm": 0.34535664319992065,
845
+ "learning_rate": 8.23529411764706e-06,
846
+ "loss": 0.7084,
847
+ "step": 210
848
+ },
849
+ {
850
+ "epoch": 12.470588235294118,
851
+ "grad_norm": 0.330837219953537,
852
+ "learning_rate": 8.31372549019608e-06,
853
+ "loss": 0.6769,
854
+ "step": 212
855
+ },
856
+ {
857
+ "epoch": 12.588235294117647,
858
+ "grad_norm": 0.31368908286094666,
859
+ "learning_rate": 8.392156862745099e-06,
860
+ "loss": 0.7651,
861
+ "step": 214
862
+ },
863
+ {
864
+ "epoch": 12.705882352941176,
865
+ "grad_norm": 0.35061123967170715,
866
+ "learning_rate": 8.470588235294118e-06,
867
+ "loss": 0.7452,
868
+ "step": 216
869
+ },
870
+ {
871
+ "epoch": 12.823529411764707,
872
+ "grad_norm": 0.32111451029777527,
873
+ "learning_rate": 8.549019607843138e-06,
874
+ "loss": 0.718,
875
+ "step": 218
876
+ },
877
+ {
878
+ "epoch": 12.941176470588236,
879
+ "grad_norm": 0.3150181174278259,
880
+ "learning_rate": 8.627450980392157e-06,
881
+ "loss": 0.6819,
882
+ "step": 220
883
+ },
884
+ {
885
+ "epoch": 13.0,
886
+ "eval_loss": 0.7598351240158081,
887
+ "eval_runtime": 37.0068,
888
+ "eval_samples_per_second": 0.973,
889
+ "eval_steps_per_second": 0.973,
890
+ "step": 221
891
+ },
892
+ {
893
+ "epoch": 13.058823529411764,
894
+ "grad_norm": 0.3078894019126892,
895
+ "learning_rate": 8.705882352941177e-06,
896
+ "loss": 0.7151,
897
+ "step": 222
898
+ },
899
+ {
900
+ "epoch": 13.176470588235293,
901
+ "grad_norm": 0.3273066282272339,
902
+ "learning_rate": 8.784313725490196e-06,
903
+ "loss": 0.6766,
904
+ "step": 224
905
+ },
906
+ {
907
+ "epoch": 13.294117647058824,
908
+ "grad_norm": 0.30240604281425476,
909
+ "learning_rate": 8.862745098039216e-06,
910
+ "loss": 0.665,
911
+ "step": 226
912
+ },
913
+ {
914
+ "epoch": 13.411764705882353,
915
+ "grad_norm": 0.3365361988544464,
916
+ "learning_rate": 8.941176470588237e-06,
917
+ "loss": 0.73,
918
+ "step": 228
919
+ },
920
+ {
921
+ "epoch": 13.529411764705882,
922
+ "grad_norm": 0.3776240646839142,
923
+ "learning_rate": 9.019607843137256e-06,
924
+ "loss": 0.7319,
925
+ "step": 230
926
+ },
927
+ {
928
+ "epoch": 13.647058823529411,
929
+ "grad_norm": 0.32826074957847595,
930
+ "learning_rate": 9.098039215686276e-06,
931
+ "loss": 0.7021,
932
+ "step": 232
933
+ },
934
+ {
935
+ "epoch": 13.764705882352942,
936
+ "grad_norm": 0.3192596435546875,
937
+ "learning_rate": 9.176470588235294e-06,
938
+ "loss": 0.7333,
939
+ "step": 234
940
+ },
941
+ {
942
+ "epoch": 13.882352941176471,
943
+ "grad_norm": 0.36111271381378174,
944
+ "learning_rate": 9.254901960784315e-06,
945
+ "loss": 0.7633,
946
+ "step": 236
947
+ },
948
+ {
949
+ "epoch": 14.0,
950
+ "grad_norm": 0.3694405257701874,
951
+ "learning_rate": 9.333333333333334e-06,
952
+ "loss": 0.7241,
953
+ "step": 238
954
+ },
955
+ {
956
+ "epoch": 14.0,
957
+ "eval_loss": 0.7471711039543152,
958
+ "eval_runtime": 37.0047,
959
+ "eval_samples_per_second": 0.973,
960
+ "eval_steps_per_second": 0.973,
961
+ "step": 238
962
+ },
963
+ {
964
+ "epoch": 14.117647058823529,
965
+ "grad_norm": 0.3688935339450836,
966
+ "learning_rate": 9.411764705882354e-06,
967
+ "loss": 0.742,
968
+ "step": 240
969
+ },
970
+ {
971
+ "epoch": 14.235294117647058,
972
+ "grad_norm": 0.41638877987861633,
973
+ "learning_rate": 9.490196078431373e-06,
974
+ "loss": 0.7049,
975
+ "step": 242
976
+ },
977
+ {
978
+ "epoch": 14.352941176470589,
979
+ "grad_norm": 0.3489099442958832,
980
+ "learning_rate": 9.568627450980393e-06,
981
+ "loss": 0.6517,
982
+ "step": 244
983
+ },
984
+ {
985
+ "epoch": 14.470588235294118,
986
+ "grad_norm": 0.3671415448188782,
987
+ "learning_rate": 9.647058823529412e-06,
988
+ "loss": 0.7233,
989
+ "step": 246
990
+ },
991
+ {
992
+ "epoch": 14.588235294117647,
993
+ "grad_norm": 0.37552204728126526,
994
+ "learning_rate": 9.725490196078432e-06,
995
+ "loss": 0.701,
996
+ "step": 248
997
+ },
998
+ {
999
+ "epoch": 14.705882352941176,
1000
+ "grad_norm": 0.43261757493019104,
1001
+ "learning_rate": 9.803921568627451e-06,
1002
+ "loss": 0.6979,
1003
+ "step": 250
1004
+ },
1005
+ {
1006
+ "epoch": 14.823529411764707,
1007
+ "grad_norm": 0.37599849700927734,
1008
+ "learning_rate": 9.882352941176472e-06,
1009
+ "loss": 0.6462,
1010
+ "step": 252
1011
+ },
1012
+ {
1013
+ "epoch": 14.941176470588236,
1014
+ "grad_norm": 0.3583243191242218,
1015
+ "learning_rate": 9.960784313725492e-06,
1016
+ "loss": 0.695,
1017
+ "step": 254
1018
+ },
1019
+ {
1020
+ "epoch": 15.0,
1021
+ "eval_loss": 0.7365108132362366,
1022
+ "eval_runtime": 37.003,
1023
+ "eval_samples_per_second": 0.973,
1024
+ "eval_steps_per_second": 0.973,
1025
+ "step": 255
1026
+ },
1027
+ {
1028
+ "epoch": 15.058823529411764,
1029
+ "grad_norm": 0.4206070005893707,
1030
+ "learning_rate": 9.999995315380667e-06,
1031
+ "loss": 0.6862,
1032
+ "step": 256
1033
+ },
1034
+ {
1035
+ "epoch": 15.176470588235293,
1036
+ "grad_norm": 0.47259286046028137,
1037
+ "learning_rate": 9.99995783847866e-06,
1038
+ "loss": 0.6933,
1039
+ "step": 258
1040
+ },
1041
+ {
1042
+ "epoch": 15.294117647058824,
1043
+ "grad_norm": 0.3962372839450836,
1044
+ "learning_rate": 9.999882884955554e-06,
1045
+ "loss": 0.6643,
1046
+ "step": 260
1047
+ },
1048
+ {
1049
+ "epoch": 15.411764705882353,
1050
+ "grad_norm": 0.37228551506996155,
1051
+ "learning_rate": 9.99977045537315e-06,
1052
+ "loss": 0.6676,
1053
+ "step": 262
1054
+ },
1055
+ {
1056
+ "epoch": 15.529411764705882,
1057
+ "grad_norm": 0.4293304979801178,
1058
+ "learning_rate": 9.999620550574155e-06,
1059
+ "loss": 0.6497,
1060
+ "step": 264
1061
+ },
1062
+ {
1063
+ "epoch": 15.647058823529411,
1064
+ "grad_norm": 0.4316819906234741,
1065
+ "learning_rate": 9.999433171682158e-06,
1066
+ "loss": 0.6687,
1067
+ "step": 266
1068
+ },
1069
+ {
1070
+ "epoch": 15.764705882352942,
1071
+ "grad_norm": 0.4474015533924103,
1072
+ "learning_rate": 9.999208320101643e-06,
1073
+ "loss": 0.6935,
1074
+ "step": 268
1075
+ },
1076
+ {
1077
+ "epoch": 15.882352941176471,
1078
+ "grad_norm": 0.4514879584312439,
1079
+ "learning_rate": 9.998945997517957e-06,
1080
+ "loss": 0.6542,
1081
+ "step": 270
1082
+ },
1083
+ {
1084
+ "epoch": 16.0,
1085
+ "grad_norm": 0.5015867948532104,
1086
+ "learning_rate": 9.99864620589731e-06,
1087
+ "loss": 0.6982,
1088
+ "step": 272
1089
+ },
1090
+ {
1091
+ "epoch": 16.0,
1092
+ "eval_loss": 0.7271888256072998,
1093
+ "eval_runtime": 37.0158,
1094
+ "eval_samples_per_second": 0.973,
1095
+ "eval_steps_per_second": 0.973,
1096
+ "step": 272
1097
+ },
1098
+ {
1099
+ "epoch": 16.11764705882353,
1100
+ "grad_norm": 0.5128858685493469,
1101
+ "learning_rate": 9.998308947486753e-06,
1102
+ "loss": 0.6414,
1103
+ "step": 274
1104
+ },
1105
+ {
1106
+ "epoch": 16.235294117647058,
1107
+ "grad_norm": 0.40119990706443787,
1108
+ "learning_rate": 9.997934224814173e-06,
1109
+ "loss": 0.628,
1110
+ "step": 276
1111
+ },
1112
+ {
1113
+ "epoch": 16.352941176470587,
1114
+ "grad_norm": 0.4133683145046234,
1115
+ "learning_rate": 9.997522040688258e-06,
1116
+ "loss": 0.7072,
1117
+ "step": 278
1118
+ },
1119
+ {
1120
+ "epoch": 16.470588235294116,
1121
+ "grad_norm": 0.41614237427711487,
1122
+ "learning_rate": 9.997072398198492e-06,
1123
+ "loss": 0.6526,
1124
+ "step": 280
1125
+ },
1126
+ {
1127
+ "epoch": 16.58823529411765,
1128
+ "grad_norm": 0.4795832931995392,
1129
+ "learning_rate": 9.996585300715117e-06,
1130
+ "loss": 0.6583,
1131
+ "step": 282
1132
+ },
1133
+ {
1134
+ "epoch": 16.705882352941178,
1135
+ "grad_norm": 0.4348108470439911,
1136
+ "learning_rate": 9.996060751889114e-06,
1137
+ "loss": 0.6728,
1138
+ "step": 284
1139
+ },
1140
+ {
1141
+ "epoch": 16.823529411764707,
1142
+ "grad_norm": 0.4476607143878937,
1143
+ "learning_rate": 9.995498755652186e-06,
1144
+ "loss": 0.626,
1145
+ "step": 286
1146
+ },
1147
+ {
1148
+ "epoch": 16.941176470588236,
1149
+ "grad_norm": 0.4528913199901581,
1150
+ "learning_rate": 9.994899316216709e-06,
1151
+ "loss": 0.622,
1152
+ "step": 288
1153
+ },
1154
+ {
1155
+ "epoch": 17.0,
1156
+ "eval_loss": 0.7215262055397034,
1157
+ "eval_runtime": 36.9993,
1158
+ "eval_samples_per_second": 0.973,
1159
+ "eval_steps_per_second": 0.973,
1160
+ "step": 289
1161
+ },
1162
+ {
1163
+ "epoch": 17.058823529411764,
1164
+ "grad_norm": 0.5009466409683228,
1165
+ "learning_rate": 9.994262438075713e-06,
1166
+ "loss": 0.7081,
1167
+ "step": 290
1168
+ },
1169
+ {
1170
+ "epoch": 17.176470588235293,
1171
+ "grad_norm": 0.475374698638916,
1172
+ "learning_rate": 9.993588126002848e-06,
1173
+ "loss": 0.6229,
1174
+ "step": 292
1175
+ },
1176
+ {
1177
+ "epoch": 17.294117647058822,
1178
+ "grad_norm": 0.4642236828804016,
1179
+ "learning_rate": 9.992876385052346e-06,
1180
+ "loss": 0.5844,
1181
+ "step": 294
1182
+ },
1183
+ {
1184
+ "epoch": 17.41176470588235,
1185
+ "grad_norm": 0.4536580741405487,
1186
+ "learning_rate": 9.992127220558976e-06,
1187
+ "loss": 0.6135,
1188
+ "step": 296
1189
+ },
1190
+ {
1191
+ "epoch": 17.529411764705884,
1192
+ "grad_norm": 0.45987674593925476,
1193
+ "learning_rate": 9.991340638138022e-06,
1194
+ "loss": 0.6511,
1195
+ "step": 298
1196
+ },
1197
+ {
1198
+ "epoch": 17.647058823529413,
1199
+ "grad_norm": 0.4978199899196625,
1200
+ "learning_rate": 9.990516643685222e-06,
1201
+ "loss": 0.6424,
1202
+ "step": 300
1203
+ },
1204
+ {
1205
+ "epoch": 17.764705882352942,
1206
+ "grad_norm": 0.49036839604377747,
1207
+ "learning_rate": 9.98965524337673e-06,
1208
+ "loss": 0.6773,
1209
+ "step": 302
1210
+ },
1211
+ {
1212
+ "epoch": 17.88235294117647,
1213
+ "grad_norm": 0.5300158858299255,
1214
+ "learning_rate": 9.988756443669081e-06,
1215
+ "loss": 0.6364,
1216
+ "step": 304
1217
+ },
1218
+ {
1219
+ "epoch": 18.0,
1220
+ "grad_norm": 0.4950679540634155,
1221
+ "learning_rate": 9.987820251299121e-06,
1222
+ "loss": 0.5905,
1223
+ "step": 306
1224
+ },
1225
+ {
1226
+ "epoch": 18.0,
1227
+ "eval_loss": 0.7155699133872986,
1228
+ "eval_runtime": 37.0042,
1229
+ "eval_samples_per_second": 0.973,
1230
+ "eval_steps_per_second": 0.973,
1231
+ "step": 306
1232
+ },
1233
+ {
1234
+ "epoch": 18.11764705882353,
1235
+ "grad_norm": 0.5069499611854553,
1236
+ "learning_rate": 9.98684667328398e-06,
1237
+ "loss": 0.6123,
1238
+ "step": 308
1239
+ },
1240
+ {
1241
+ "epoch": 18.235294117647058,
1242
+ "grad_norm": 0.46550482511520386,
1243
+ "learning_rate": 9.985835716921e-06,
1244
+ "loss": 0.6102,
1245
+ "step": 310
1246
+ },
1247
+ {
1248
+ "epoch": 18.352941176470587,
1249
+ "grad_norm": 0.7860422730445862,
1250
+ "learning_rate": 9.984787389787689e-06,
1251
+ "loss": 0.6273,
1252
+ "step": 312
1253
+ },
1254
+ {
1255
+ "epoch": 18.470588235294116,
1256
+ "grad_norm": 0.49825742840766907,
1257
+ "learning_rate": 9.983701699741668e-06,
1258
+ "loss": 0.6297,
1259
+ "step": 314
1260
+ },
1261
+ {
1262
+ "epoch": 18.58823529411765,
1263
+ "grad_norm": 0.5290573239326477,
1264
+ "learning_rate": 9.982578654920601e-06,
1265
+ "loss": 0.6238,
1266
+ "step": 316
1267
+ },
1268
+ {
1269
+ "epoch": 18.705882352941178,
1270
+ "grad_norm": 0.5185476541519165,
1271
+ "learning_rate": 9.981418263742148e-06,
1272
+ "loss": 0.5702,
1273
+ "step": 318
1274
+ },
1275
+ {
1276
+ "epoch": 18.823529411764707,
1277
+ "grad_norm": 0.5360794067382812,
1278
+ "learning_rate": 9.980220534903889e-06,
1279
+ "loss": 0.6082,
1280
+ "step": 320
1281
+ },
1282
+ {
1283
+ "epoch": 18.941176470588236,
1284
+ "grad_norm": 0.5598728656768799,
1285
+ "learning_rate": 9.978985477383264e-06,
1286
+ "loss": 0.6121,
1287
+ "step": 322
1288
+ },
1289
+ {
1290
+ "epoch": 19.0,
1291
+ "eval_loss": 0.7140286564826965,
1292
+ "eval_runtime": 36.9943,
1293
+ "eval_samples_per_second": 0.973,
1294
+ "eval_steps_per_second": 0.973,
1295
+ "step": 323
1296
+ },
1297
+ {
1298
+ "epoch": 19.058823529411764,
1299
+ "grad_norm": 0.5005812048912048,
1300
+ "learning_rate": 9.97771310043751e-06,
1301
+ "loss": 0.5964,
1302
+ "step": 324
1303
+ },
1304
+ {
1305
+ "epoch": 19.176470588235293,
1306
+ "grad_norm": 0.5243679881095886,
1307
+ "learning_rate": 9.97640341360358e-06,
1308
+ "loss": 0.643,
1309
+ "step": 326
1310
+ },
1311
+ {
1312
+ "epoch": 19.294117647058822,
1313
+ "grad_norm": 0.5746588706970215,
1314
+ "learning_rate": 9.975056426698094e-06,
1315
+ "loss": 0.587,
1316
+ "step": 328
1317
+ },
1318
+ {
1319
+ "epoch": 19.41176470588235,
1320
+ "grad_norm": 0.5213414430618286,
1321
+ "learning_rate": 9.973672149817232e-06,
1322
+ "loss": 0.5835,
1323
+ "step": 330
1324
+ },
1325
+ {
1326
+ "epoch": 19.529411764705884,
1327
+ "grad_norm": 0.6261019706726074,
1328
+ "learning_rate": 9.972250593336689e-06,
1329
+ "loss": 0.5884,
1330
+ "step": 332
1331
+ },
1332
+ {
1333
+ "epoch": 19.647058823529413,
1334
+ "grad_norm": 0.5905741453170776,
1335
+ "learning_rate": 9.970791767911581e-06,
1336
+ "loss": 0.588,
1337
+ "step": 334
1338
+ },
1339
+ {
1340
+ "epoch": 19.764705882352942,
1341
+ "grad_norm": 0.5681843757629395,
1342
+ "learning_rate": 9.96929568447637e-06,
1343
+ "loss": 0.554,
1344
+ "step": 336
1345
+ },
1346
+ {
1347
+ "epoch": 19.88235294117647,
1348
+ "grad_norm": 0.6130782961845398,
1349
+ "learning_rate": 9.967762354244778e-06,
1350
+ "loss": 0.6003,
1351
+ "step": 338
1352
+ },
1353
+ {
1354
+ "epoch": 20.0,
1355
+ "grad_norm": 0.6039074659347534,
1356
+ "learning_rate": 9.966191788709716e-06,
1357
+ "loss": 0.567,
1358
+ "step": 340
1359
+ },
1360
+ {
1361
+ "epoch": 20.0,
1362
+ "eval_loss": 0.7166150808334351,
1363
+ "eval_runtime": 36.9981,
1364
+ "eval_samples_per_second": 0.973,
1365
+ "eval_steps_per_second": 0.973,
1366
+ "step": 340
1367
+ },
1368
+ {
1369
+ "epoch": 20.11764705882353,
1370
+ "grad_norm": 0.661340594291687,
1371
+ "learning_rate": 9.964583999643174e-06,
1372
+ "loss": 0.5771,
1373
+ "step": 342
1374
+ },
1375
+ {
1376
+ "epoch": 20.235294117647058,
1377
+ "grad_norm": 0.6773268580436707,
1378
+ "learning_rate": 9.962938999096159e-06,
1379
+ "loss": 0.5611,
1380
+ "step": 344
1381
+ },
1382
+ {
1383
+ "epoch": 20.352941176470587,
1384
+ "grad_norm": 0.6907221674919128,
1385
+ "learning_rate": 9.961256799398584e-06,
1386
+ "loss": 0.5961,
1387
+ "step": 346
1388
+ },
1389
+ {
1390
+ "epoch": 20.470588235294116,
1391
+ "grad_norm": 0.6799242496490479,
1392
+ "learning_rate": 9.95953741315919e-06,
1393
+ "loss": 0.605,
1394
+ "step": 348
1395
+ },
1396
+ {
1397
+ "epoch": 20.58823529411765,
1398
+ "grad_norm": 0.6507272720336914,
1399
+ "learning_rate": 9.957780853265441e-06,
1400
+ "loss": 0.5564,
1401
+ "step": 350
1402
+ },
1403
+ {
1404
+ "epoch": 20.705882352941178,
1405
+ "grad_norm": 0.7043225765228271,
1406
+ "learning_rate": 9.955987132883435e-06,
1407
+ "loss": 0.5069,
1408
+ "step": 352
1409
+ },
1410
+ {
1411
+ "epoch": 20.823529411764707,
1412
+ "grad_norm": 0.7170704007148743,
1413
+ "learning_rate": 9.954156265457801e-06,
1414
+ "loss": 0.5671,
1415
+ "step": 354
1416
+ },
1417
+ {
1418
+ "epoch": 20.941176470588236,
1419
+ "grad_norm": 0.6098182797431946,
1420
+ "learning_rate": 9.952288264711601e-06,
1421
+ "loss": 0.5471,
1422
+ "step": 356
1423
+ },
1424
+ {
1425
+ "epoch": 21.0,
1426
+ "eval_loss": 0.7171775698661804,
1427
+ "eval_runtime": 36.9995,
1428
+ "eval_samples_per_second": 0.973,
1429
+ "eval_steps_per_second": 0.973,
1430
+ "step": 357
1431
+ },
1432
+ {
1433
+ "epoch": 21.058823529411764,
1434
+ "grad_norm": 0.7199786305427551,
1435
+ "learning_rate": 9.950383144646221e-06,
1436
+ "loss": 0.5856,
1437
+ "step": 358
1438
+ },
1439
+ {
1440
+ "epoch": 21.176470588235293,
1441
+ "grad_norm": 0.748616635799408,
1442
+ "learning_rate": 9.948440919541277e-06,
1443
+ "loss": 0.5347,
1444
+ "step": 360
1445
+ },
1446
+ {
1447
+ "epoch": 21.294117647058822,
1448
+ "grad_norm": 0.7035663723945618,
1449
+ "learning_rate": 9.946461603954499e-06,
1450
+ "loss": 0.5433,
1451
+ "step": 362
1452
+ },
1453
+ {
1454
+ "epoch": 21.41176470588235,
1455
+ "grad_norm": 0.7293503880500793,
1456
+ "learning_rate": 9.944445212721619e-06,
1457
+ "loss": 0.5473,
1458
+ "step": 364
1459
+ },
1460
+ {
1461
+ "epoch": 21.529411764705884,
1462
+ "grad_norm": 0.7407766580581665,
1463
+ "learning_rate": 9.942391760956277e-06,
1464
+ "loss": 0.527,
1465
+ "step": 366
1466
+ },
1467
+ {
1468
+ "epoch": 21.647058823529413,
1469
+ "grad_norm": 0.7856358289718628,
1470
+ "learning_rate": 9.940301264049885e-06,
1471
+ "loss": 0.5372,
1472
+ "step": 368
1473
+ },
1474
+ {
1475
+ "epoch": 21.764705882352942,
1476
+ "grad_norm": 0.7008533477783203,
1477
+ "learning_rate": 9.938173737671531e-06,
1478
+ "loss": 0.5375,
1479
+ "step": 370
1480
+ },
1481
+ {
1482
+ "epoch": 21.88235294117647,
1483
+ "grad_norm": 0.7586143612861633,
1484
+ "learning_rate": 9.936009197767847e-06,
1485
+ "loss": 0.5467,
1486
+ "step": 372
1487
+ },
1488
+ {
1489
+ "epoch": 22.0,
1490
+ "grad_norm": 0.8423267602920532,
1491
+ "learning_rate": 9.933807660562898e-06,
1492
+ "loss": 0.4761,
1493
+ "step": 374
1494
+ },
1495
+ {
1496
+ "epoch": 22.0,
1497
+ "eval_loss": 0.7233606576919556,
1498
+ "eval_runtime": 37.0054,
1499
+ "eval_samples_per_second": 0.973,
1500
+ "eval_steps_per_second": 0.973,
1501
+ "step": 374
1502
+ },
1503
+ {
1504
+ "epoch": 22.11764705882353,
1505
+ "grad_norm": 0.882168710231781,
1506
+ "learning_rate": 9.931569142558057e-06,
1507
+ "loss": 0.562,
1508
+ "step": 376
1509
+ },
1510
+ {
1511
+ "epoch": 22.235294117647058,
1512
+ "grad_norm": 0.8616783618927002,
1513
+ "learning_rate": 9.929293660531889e-06,
1514
+ "loss": 0.5039,
1515
+ "step": 378
1516
+ },
1517
+ {
1518
+ "epoch": 22.352941176470587,
1519
+ "grad_norm": 0.9095832705497742,
1520
+ "learning_rate": 9.926981231540007e-06,
1521
+ "loss": 0.4744,
1522
+ "step": 380
1523
+ },
1524
+ {
1525
+ "epoch": 22.470588235294116,
1526
+ "grad_norm": 0.8473853468894958,
1527
+ "learning_rate": 9.924631872914967e-06,
1528
+ "loss": 0.4976,
1529
+ "step": 382
1530
+ },
1531
+ {
1532
+ "epoch": 22.58823529411765,
1533
+ "grad_norm": 0.844835102558136,
1534
+ "learning_rate": 9.922245602266119e-06,
1535
+ "loss": 0.4721,
1536
+ "step": 384
1537
+ },
1538
+ {
1539
+ "epoch": 22.705882352941178,
1540
+ "grad_norm": 0.820750892162323,
1541
+ "learning_rate": 9.919822437479488e-06,
1542
+ "loss": 0.4995,
1543
+ "step": 386
1544
+ },
1545
+ {
1546
+ "epoch": 22.823529411764707,
1547
+ "grad_norm": 0.823648989200592,
1548
+ "learning_rate": 9.91736239671763e-06,
1549
+ "loss": 0.5061,
1550
+ "step": 388
1551
+ },
1552
+ {
1553
+ "epoch": 22.941176470588236,
1554
+ "grad_norm": 0.8103899359703064,
1555
+ "learning_rate": 9.91486549841951e-06,
1556
+ "loss": 0.4967,
1557
+ "step": 390
1558
+ },
1559
+ {
1560
+ "epoch": 23.0,
1561
+ "eval_loss": 0.7357540726661682,
1562
+ "eval_runtime": 37.0101,
1563
+ "eval_samples_per_second": 0.973,
1564
+ "eval_steps_per_second": 0.973,
1565
+ "step": 391
1566
+ },
1567
+ {
1568
+ "epoch": 23.058823529411764,
1569
+ "grad_norm": 0.7696477174758911,
1570
+ "learning_rate": 9.912331761300341e-06,
1571
+ "loss": 0.5004,
1572
+ "step": 392
1573
+ },
1574
+ {
1575
+ "epoch": 23.176470588235293,
1576
+ "grad_norm": 0.7803938984870911,
1577
+ "learning_rate": 9.909761204351469e-06,
1578
+ "loss": 0.4903,
1579
+ "step": 394
1580
+ },
1581
+ {
1582
+ "epoch": 23.294117647058822,
1583
+ "grad_norm": 0.9065766930580139,
1584
+ "learning_rate": 9.90715384684021e-06,
1585
+ "loss": 0.505,
1586
+ "step": 396
1587
+ },
1588
+ {
1589
+ "epoch": 23.41176470588235,
1590
+ "grad_norm": 1.1152830123901367,
1591
+ "learning_rate": 9.904509708309723e-06,
1592
+ "loss": 0.4312,
1593
+ "step": 398
1594
+ },
1595
+ {
1596
+ "epoch": 23.529411764705884,
1597
+ "grad_norm": 1.0776093006134033,
1598
+ "learning_rate": 9.901828808578846e-06,
1599
+ "loss": 0.4503,
1600
+ "step": 400
1601
+ },
1602
+ {
1603
+ "epoch": 23.647058823529413,
1604
+ "grad_norm": 1.0322400331497192,
1605
+ "learning_rate": 9.899111167741966e-06,
1606
+ "loss": 0.4685,
1607
+ "step": 402
1608
+ },
1609
+ {
1610
+ "epoch": 23.764705882352942,
1611
+ "grad_norm": 0.9414217472076416,
1612
+ "learning_rate": 9.896356806168851e-06,
1613
+ "loss": 0.4757,
1614
+ "step": 404
1615
+ },
1616
+ {
1617
+ "epoch": 23.88235294117647,
1618
+ "grad_norm": 1.1830779314041138,
1619
+ "learning_rate": 9.89356574450451e-06,
1620
+ "loss": 0.4408,
1621
+ "step": 406
1622
+ },
1623
+ {
1624
+ "epoch": 24.0,
1625
+ "grad_norm": 0.9795882105827332,
1626
+ "learning_rate": 9.890738003669029e-06,
1627
+ "loss": 0.4833,
1628
+ "step": 408
1629
+ },
1630
+ {
1631
+ "epoch": 24.0,
1632
+ "eval_loss": 0.7643568515777588,
1633
+ "eval_runtime": 37.0004,
1634
+ "eval_samples_per_second": 0.973,
1635
+ "eval_steps_per_second": 0.973,
1636
+ "step": 408
1637
+ },
1638
+ {
1639
+ "epoch": 24.11764705882353,
1640
+ "grad_norm": 1.2952356338500977,
1641
+ "learning_rate": 9.887873604857424e-06,
1642
+ "loss": 0.4299,
1643
+ "step": 410
1644
+ },
1645
+ {
1646
+ "epoch": 24.235294117647058,
1647
+ "grad_norm": 1.2539509534835815,
1648
+ "learning_rate": 9.884972569539471e-06,
1649
+ "loss": 0.4488,
1650
+ "step": 412
1651
+ },
1652
+ {
1653
+ "epoch": 24.352941176470587,
1654
+ "grad_norm": 1.0663094520568848,
1655
+ "learning_rate": 9.882034919459556e-06,
1656
+ "loss": 0.4152,
1657
+ "step": 414
1658
+ },
1659
+ {
1660
+ "epoch": 24.470588235294116,
1661
+ "grad_norm": 1.03883957862854,
1662
+ "learning_rate": 9.879060676636502e-06,
1663
+ "loss": 0.4435,
1664
+ "step": 416
1665
+ },
1666
+ {
1667
+ "epoch": 24.58823529411765,
1668
+ "grad_norm": 0.9475598931312561,
1669
+ "learning_rate": 9.876049863363415e-06,
1670
+ "loss": 0.4408,
1671
+ "step": 418
1672
+ },
1673
+ {
1674
+ "epoch": 24.705882352941178,
1675
+ "grad_norm": 0.9946249723434448,
1676
+ "learning_rate": 9.873002502207502e-06,
1677
+ "loss": 0.4292,
1678
+ "step": 420
1679
+ },
1680
+ {
1681
+ "epoch": 24.823529411764707,
1682
+ "grad_norm": 1.135332465171814,
1683
+ "learning_rate": 9.86991861600992e-06,
1684
+ "loss": 0.4057,
1685
+ "step": 422
1686
+ },
1687
+ {
1688
+ "epoch": 24.941176470588236,
1689
+ "grad_norm": 1.7003220319747925,
1690
+ "learning_rate": 9.866798227885588e-06,
1691
+ "loss": 0.4071,
1692
+ "step": 424
1693
+ },
1694
+ {
1695
+ "epoch": 25.0,
1696
+ "eval_loss": 0.8012258410453796,
1697
+ "eval_runtime": 37.0059,
1698
+ "eval_samples_per_second": 0.973,
1699
+ "eval_steps_per_second": 0.973,
1700
+ "step": 425
1701
+ },
1702
+ {
1703
+ "epoch": 25.058823529411764,
1704
+ "grad_norm": 1.124939203262329,
1705
+ "learning_rate": 9.863641361223025e-06,
1706
+ "loss": 0.3795,
1707
+ "step": 426
1708
+ },
1709
+ {
1710
+ "epoch": 25.176470588235293,
1711
+ "grad_norm": 1.2946455478668213,
1712
+ "learning_rate": 9.860448039684169e-06,
1713
+ "loss": 0.3631,
1714
+ "step": 428
1715
+ },
1716
+ {
1717
+ "epoch": 25.294117647058822,
1718
+ "grad_norm": 1.2063255310058594,
1719
+ "learning_rate": 9.857218287204204e-06,
1720
+ "loss": 0.3786,
1721
+ "step": 430
1722
+ },
1723
+ {
1724
+ "epoch": 25.41176470588235,
1725
+ "grad_norm": 1.1833475828170776,
1726
+ "learning_rate": 9.853952127991374e-06,
1727
+ "loss": 0.403,
1728
+ "step": 432
1729
+ },
1730
+ {
1731
+ "epoch": 25.529411764705884,
1732
+ "grad_norm": 1.2458750009536743,
1733
+ "learning_rate": 9.850649586526808e-06,
1734
+ "loss": 0.3626,
1735
+ "step": 434
1736
+ },
1737
+ {
1738
+ "epoch": 25.647058823529413,
1739
+ "grad_norm": 1.2201582193374634,
1740
+ "learning_rate": 9.847310687564335e-06,
1741
+ "loss": 0.3774,
1742
+ "step": 436
1743
+ },
1744
+ {
1745
+ "epoch": 25.764705882352942,
1746
+ "grad_norm": 1.2703592777252197,
1747
+ "learning_rate": 9.843935456130295e-06,
1748
+ "loss": 0.4078,
1749
+ "step": 438
1750
+ },
1751
+ {
1752
+ "epoch": 25.88235294117647,
1753
+ "grad_norm": 1.8023614883422852,
1754
+ "learning_rate": 9.840523917523354e-06,
1755
+ "loss": 0.406,
1756
+ "step": 440
1757
+ },
1758
+ {
1759
+ "epoch": 26.0,
1760
+ "grad_norm": 1.3355423212051392,
1761
+ "learning_rate": 9.83707609731432e-06,
1762
+ "loss": 0.3567,
1763
+ "step": 442
1764
+ },
1765
+ {
1766
+ "epoch": 26.0,
1767
+ "eval_loss": 0.8288628458976746,
1768
+ "eval_runtime": 37.0058,
1769
+ "eval_samples_per_second": 0.973,
1770
+ "eval_steps_per_second": 0.973,
1771
+ "step": 442
1772
+ },
1773
+ {
1774
+ "epoch": 26.0,
1775
+ "step": 442,
1776
+ "total_flos": 3.38458179962667e+17,
1777
+ "train_loss": 0.7497456199173475,
1778
+ "train_runtime": 12081.7026,
1779
+ "train_samples_per_second": 1.689,
1780
+ "train_steps_per_second": 0.211
1781
+ }
1782
+ ],
1783
+ "logging_steps": 2,
1784
+ "max_steps": 2550,
1785
+ "num_input_tokens_seen": 0,
1786
+ "num_train_epochs": 150,
1787
+ "save_steps": 25,
1788
+ "stateful_callbacks": {
1789
+ "EarlyStoppingCallback": {
1790
+ "args": {
1791
+ "early_stopping_patience": 7,
1792
+ "early_stopping_threshold": 0.0
1793
+ },
1794
+ "attributes": {
1795
+ "early_stopping_patience_counter": 0
1796
+ }
1797
+ },
1798
+ "TrainerControl": {
1799
+ "args": {
1800
+ "should_epoch_stop": false,
1801
+ "should_evaluate": false,
1802
+ "should_log": false,
1803
+ "should_save": true,
1804
+ "should_training_stop": true
1805
+ },
1806
+ "attributes": {}
1807
+ }
1808
+ },
1809
+ "total_flos": 3.38458179962667e+17,
1810
+ "train_batch_size": 1,
1811
+ "trial_name": null,
1812
+ "trial_params": null
1813
+ }
GaetanMichelet__Llama-31-8B_task-2_180-samples_config-3/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bfbd4d909e22ae43f925bdf497b8700609f251caed1288309868259c9e2373a4
3
+ size 6264