Campis commited on
Commit
d7a037d
·
verified ·
1 Parent(s): fe3a9a3

Upload 18 files

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ license: other
4
+ base_model: meta-llama/Llama-3.2-1B-Instruct
5
+ tags:
6
+ - llama-factory
7
+ - lora
8
+ - generated_from_trainer
9
+ model-index:
10
+ - name: train_1B-Instruct_pippo_v6
11
+ results: []
12
+ ---
13
+
14
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
15
+ should probably proofread and complete it, then remove this comment. -->
16
+
17
+ # train_1B-Instruct_pippo_v6
18
+
19
+ This model is a fine-tuned version of [meta-llama/Llama-3.2-1B-Instruct](https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct) on the pipo_persona dataset.
20
+ It achieves the following results on the evaluation set:
21
+ - Loss: 3.6431
22
+ - Num Input Tokens Seen: 300000
23
+
24
+ ## Model description
25
+
26
+ More information needed
27
+
28
+ ## Intended uses & limitations
29
+
30
+ More information needed
31
+
32
+ ## Training and evaluation data
33
+
34
+ More information needed
35
+
36
+ ## Training procedure
37
+
38
+ ### Training hyperparameters
39
+
40
+ The following hyperparameters were used during training:
41
+ - learning_rate: 2e-05
42
+ - train_batch_size: 2
43
+ - eval_batch_size: 2
44
+ - seed: 42
45
+ - gradient_accumulation_steps: 8
46
+ - total_train_batch_size: 16
47
+ - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
48
+ - lr_scheduler_type: cosine
49
+ - num_epochs: 4.0
50
+
51
+ ### Training results
52
+
53
+
54
+
55
+ ### Framework versions
56
+
57
+ - PEFT 0.15.2
58
+ - Transformers 4.52.4
59
+ - Pytorch 2.6.0+cu124
60
+ - Datasets 3.6.0
61
+ - Tokenizers 0.21.1
adapter_config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "meta-llama/Llama-3.2-1B-Instruct",
5
+ "bias": "none",
6
+ "corda_config": null,
7
+ "eva_config": null,
8
+ "exclude_modules": null,
9
+ "fan_in_fan_out": false,
10
+ "inference_mode": true,
11
+ "init_lora_weights": true,
12
+ "layer_replication": null,
13
+ "layers_pattern": null,
14
+ "layers_to_transform": null,
15
+ "loftq_config": {},
16
+ "lora_alpha": 48,
17
+ "lora_bias": false,
18
+ "lora_dropout": 0.05,
19
+ "megatron_config": null,
20
+ "megatron_core": "megatron.core",
21
+ "modules_to_save": null,
22
+ "peft_type": "LORA",
23
+ "r": 24,
24
+ "rank_pattern": {},
25
+ "revision": null,
26
+ "target_modules": [
27
+ "down_proj",
28
+ "q_proj",
29
+ "gate_proj",
30
+ "v_proj",
31
+ "o_proj",
32
+ "up_proj"
33
+ ],
34
+ "task_type": "CAUSAL_LM",
35
+ "trainable_token_indices": null,
36
+ "use_dora": false,
37
+ "use_rslora": false
38
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a009cfb702a3432cece99f7fdd21a929e3c5bccba7e2ae9b332f7c161eb874c8
3
+ size 63726400
all_results.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 4.0,
3
+ "eval_loss": 3.643085241317749,
4
+ "eval_runtime": 12.9097,
5
+ "eval_samples_per_second": 28.893,
6
+ "eval_steps_per_second": 14.485,
7
+ "num_input_tokens_seen": 300000,
8
+ "total_flos": 1780328448000000.0,
9
+ "train_loss": 0.7932832451101314,
10
+ "train_runtime": 895.9422,
11
+ "train_samples_per_second": 6.652,
12
+ "train_steps_per_second": 0.42
13
+ }
chat_template.jinja ADDED
@@ -0,0 +1,93 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {{- bos_token }}
2
+ {%- if custom_tools is defined %}
3
+ {%- set tools = custom_tools %}
4
+ {%- endif %}
5
+ {%- if not tools_in_user_message is defined %}
6
+ {%- set tools_in_user_message = true %}
7
+ {%- endif %}
8
+ {%- if not date_string is defined %}
9
+ {%- if strftime_now is defined %}
10
+ {%- set date_string = strftime_now("%d %b %Y") %}
11
+ {%- else %}
12
+ {%- set date_string = "26 Jul 2024" %}
13
+ {%- endif %}
14
+ {%- endif %}
15
+ {%- if not tools is defined %}
16
+ {%- set tools = none %}
17
+ {%- endif %}
18
+
19
+ {#- This block extracts the system message, so we can slot it into the right place. #}
20
+ {%- if messages[0]['role'] == 'system' %}
21
+ {%- set system_message = messages[0]['content']|trim %}
22
+ {%- set messages = messages[1:] %}
23
+ {%- else %}
24
+ {%- set system_message = "" %}
25
+ {%- endif %}
26
+
27
+ {#- System message #}
28
+ {{- "<|start_header_id|>system<|end_header_id|>\n\n" }}
29
+ {%- if tools is not none %}
30
+ {{- "Environment: ipython\n" }}
31
+ {%- endif %}
32
+ {{- "Cutting Knowledge Date: December 2023\n" }}
33
+ {{- "Today Date: " + date_string + "\n\n" }}
34
+ {%- if tools is not none and not tools_in_user_message %}
35
+ {{- "You have access to the following functions. To call a function, please respond with JSON for a function call." }}
36
+ {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
37
+ {{- "Do not use variables.\n\n" }}
38
+ {%- for t in tools %}
39
+ {{- t | tojson(indent=4) }}
40
+ {{- "\n\n" }}
41
+ {%- endfor %}
42
+ {%- endif %}
43
+ {{- system_message }}
44
+ {{- "<|eot_id|>" }}
45
+
46
+ {#- Custom tools are passed in a user message with some extra guidance #}
47
+ {%- if tools_in_user_message and not tools is none %}
48
+ {#- Extract the first user message so we can plug it in here #}
49
+ {%- if messages | length != 0 %}
50
+ {%- set first_user_message = messages[0]['content']|trim %}
51
+ {%- set messages = messages[1:] %}
52
+ {%- else %}
53
+ {{- raise_exception("Cannot put tools in the first user message when there's no first user message!") }}
54
+ {%- endif %}
55
+ {{- '<|start_header_id|>user<|end_header_id|>\n\n' -}}
56
+ {{- "Given the following functions, please respond with a JSON for a function call " }}
57
+ {{- "with its proper arguments that best answers the given prompt.\n\n" }}
58
+ {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
59
+ {{- "Do not use variables.\n\n" }}
60
+ {%- for t in tools %}
61
+ {{- t | tojson(indent=4) }}
62
+ {{- "\n\n" }}
63
+ {%- endfor %}
64
+ {{- first_user_message + "<|eot_id|>"}}
65
+ {%- endif %}
66
+
67
+ {%- for message in messages %}
68
+ {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}
69
+ {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' }}
70
+ {%- elif 'tool_calls' in message %}
71
+ {%- if not message.tool_calls|length == 1 %}
72
+ {{- raise_exception("This model only supports single tool-calls at once!") }}
73
+ {%- endif %}
74
+ {%- set tool_call = message.tool_calls[0].function %}
75
+ {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}
76
+ {{- '{"name": "' + tool_call.name + '", ' }}
77
+ {{- '"parameters": ' }}
78
+ {{- tool_call.arguments | tojson }}
79
+ {{- "}" }}
80
+ {{- "<|eot_id|>" }}
81
+ {%- elif message.role == "tool" or message.role == "ipython" %}
82
+ {{- "<|start_header_id|>ipython<|end_header_id|>\n\n" }}
83
+ {%- if message.content is mapping or message.content is iterable %}
84
+ {{- message.content | tojson }}
85
+ {%- else %}
86
+ {{- message.content }}
87
+ {%- endif %}
88
+ {{- "<|eot_id|>" }}
89
+ {%- endif %}
90
+ {%- endfor %}
91
+ {%- if add_generation_prompt %}
92
+ {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' }}
93
+ {%- endif %}
eval_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 4.0,
3
+ "eval_loss": 3.643085241317749,
4
+ "eval_runtime": 12.9097,
5
+ "eval_samples_per_second": 28.893,
6
+ "eval_steps_per_second": 14.485,
7
+ "num_input_tokens_seen": 300000
8
+ }
llamaboard_config.yaml ADDED
@@ -0,0 +1,86 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ top.booster: auto
2
+ top.checkpoint_path:
3
+ - train_1B-Instruct_pippo_v4
4
+ top.finetuning_type: lora
5
+ top.model_name: Llama-3.2-1B-Instruct
6
+ top.quantization_bit: none
7
+ top.quantization_method: bnb
8
+ top.rope_scaling: none
9
+ top.template: llama3
10
+ train.additional_target: ''
11
+ train.apollo_rank: 16
12
+ train.apollo_scale: 32
13
+ train.apollo_target: all
14
+ train.apollo_update_interval: 200
15
+ train.badam_mode: layer
16
+ train.badam_switch_interval: 50
17
+ train.badam_switch_mode: ascending
18
+ train.badam_update_ratio: 0.05
19
+ train.batch_size: 2
20
+ train.compute_type: bf16
21
+ train.create_new_adapter: false
22
+ train.cutoff_len: 1024
23
+ train.dataset:
24
+ - pipo_persona
25
+ train.dataset_dir: data
26
+ train.ds_offload: false
27
+ train.ds_stage: none
28
+ train.enable_thinking: true
29
+ train.extra_args: '{"optim": "adamw_torch"}'
30
+ train.freeze_extra_modules: ''
31
+ train.freeze_language_model: false
32
+ train.freeze_multi_modal_projector: true
33
+ train.freeze_trainable_layers: 2
34
+ train.freeze_trainable_modules: all
35
+ train.freeze_vision_tower: true
36
+ train.galore_rank: 16
37
+ train.galore_scale: 2
38
+ train.galore_target: all
39
+ train.galore_update_interval: 200
40
+ train.gradient_accumulation_steps: 8
41
+ train.image_max_pixels: 768*768
42
+ train.image_min_pixels: 32*32
43
+ train.learning_rate: 2e-5
44
+ train.logging_steps: 5
45
+ train.lora_alpha: 32
46
+ train.lora_dropout: 0.1
47
+ train.lora_rank: 16
48
+ train.lora_target: q_proj,v_proj,o_proj,gate_proj,up_proj,down_proj
49
+ train.loraplus_lr_ratio: 8
50
+ train.lr_scheduler_type: cosine
51
+ train.mask_history: false
52
+ train.max_grad_norm: '1.0'
53
+ train.max_samples: '1900'
54
+ train.neat_packing: false
55
+ train.neftune_alpha: 0
56
+ train.num_train_epochs: '4'
57
+ train.packing: false
58
+ train.ppo_score_norm: false
59
+ train.ppo_whiten_rewards: false
60
+ train.pref_beta: 0.1
61
+ train.pref_ftx: 0
62
+ train.pref_loss: sigmoid
63
+ train.report_to: none
64
+ train.resize_vocab: false
65
+ train.reward_model: []
66
+ train.save_steps: 100
67
+ train.swanlab_api_key: ''
68
+ train.swanlab_link: ''
69
+ train.swanlab_mode: cloud
70
+ train.swanlab_project: llamafactory
71
+ train.swanlab_run_name: ''
72
+ train.swanlab_workspace: ''
73
+ train.train_on_prompt: false
74
+ train.training_stage: Supervised Fine-Tuning
75
+ train.use_apollo: false
76
+ train.use_badam: false
77
+ train.use_dora: true
78
+ train.use_galore: false
79
+ train.use_llama_pro: false
80
+ train.use_pissa: true
81
+ train.use_rslora: true
82
+ train.use_swanlab: false
83
+ train.val_size: 0.2
84
+ train.video_max_pixels: 256*256
85
+ train.video_min_pixels: 16*16
86
+ train.warmup_steps: 0
running_log.txt ADDED
@@ -0,0 +1,635 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [INFO|2025-07-24 16:02:15] tokenization_utils_base.py:2023 >> loading file tokenizer.json from cache at /root/.cache/huggingface/hub/models--meta-llama--Llama-3.2-1B-Instruct/snapshots/9213176726f574b556790deb65791e0c5aa438b6/tokenizer.json
2
+ [INFO|2025-07-24 16:02:15] tokenization_utils_base.py:2023 >> loading file tokenizer.model from cache at None
3
+ [INFO|2025-07-24 16:02:15] tokenization_utils_base.py:2023 >> loading file added_tokens.json from cache at None
4
+ [INFO|2025-07-24 16:02:15] tokenization_utils_base.py:2023 >> loading file special_tokens_map.json from cache at /root/.cache/huggingface/hub/models--meta-llama--Llama-3.2-1B-Instruct/snapshots/9213176726f574b556790deb65791e0c5aa438b6/special_tokens_map.json
5
+ [INFO|2025-07-24 16:02:15] tokenization_utils_base.py:2023 >> loading file tokenizer_config.json from cache at /root/.cache/huggingface/hub/models--meta-llama--Llama-3.2-1B-Instruct/snapshots/9213176726f574b556790deb65791e0c5aa438b6/tokenizer_config.json
6
+ [INFO|2025-07-24 16:02:15] tokenization_utils_base.py:2023 >> loading file chat_template.jinja from cache at None
7
+ [INFO|2025-07-24 16:02:16] tokenization_utils_base.py:2299 >> Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
8
+ [INFO|2025-07-24 16:02:17] configuration_utils.py:698 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--meta-llama--Llama-3.2-1B-Instruct/snapshots/9213176726f574b556790deb65791e0c5aa438b6/config.json
9
+ [INFO|2025-07-24 16:02:17] configuration_utils.py:770 >> Model config LlamaConfig {
10
+ "architectures": [
11
+ "LlamaForCausalLM"
12
+ ],
13
+ "attention_bias": false,
14
+ "attention_dropout": 0.0,
15
+ "bos_token_id": 128000,
16
+ "eos_token_id": [
17
+ 128001,
18
+ 128008,
19
+ 128009
20
+ ],
21
+ "head_dim": 64,
22
+ "hidden_act": "silu",
23
+ "hidden_size": 2048,
24
+ "initializer_range": 0.02,
25
+ "intermediate_size": 8192,
26
+ "max_position_embeddings": 131072,
27
+ "mlp_bias": false,
28
+ "model_type": "llama",
29
+ "num_attention_heads": 32,
30
+ "num_hidden_layers": 16,
31
+ "num_key_value_heads": 8,
32
+ "pretraining_tp": 1,
33
+ "rms_norm_eps": 1e-05,
34
+ "rope_scaling": {
35
+ "factor": 32.0,
36
+ "high_freq_factor": 4.0,
37
+ "low_freq_factor": 1.0,
38
+ "original_max_position_embeddings": 8192,
39
+ "rope_type": "llama3"
40
+ },
41
+ "rope_theta": 500000.0,
42
+ "tie_word_embeddings": true,
43
+ "torch_dtype": "bfloat16",
44
+ "transformers_version": "4.52.4",
45
+ "use_cache": true,
46
+ "vocab_size": 128256
47
+ }
48
+
49
+ [INFO|2025-07-24 16:02:17] tokenization_utils_base.py:2023 >> loading file tokenizer.json from cache at /root/.cache/huggingface/hub/models--meta-llama--Llama-3.2-1B-Instruct/snapshots/9213176726f574b556790deb65791e0c5aa438b6/tokenizer.json
50
+ [INFO|2025-07-24 16:02:17] tokenization_utils_base.py:2023 >> loading file tokenizer.model from cache at None
51
+ [INFO|2025-07-24 16:02:17] tokenization_utils_base.py:2023 >> loading file added_tokens.json from cache at None
52
+ [INFO|2025-07-24 16:02:17] tokenization_utils_base.py:2023 >> loading file special_tokens_map.json from cache at /root/.cache/huggingface/hub/models--meta-llama--Llama-3.2-1B-Instruct/snapshots/9213176726f574b556790deb65791e0c5aa438b6/special_tokens_map.json
53
+ [INFO|2025-07-24 16:02:17] tokenization_utils_base.py:2023 >> loading file tokenizer_config.json from cache at /root/.cache/huggingface/hub/models--meta-llama--Llama-3.2-1B-Instruct/snapshots/9213176726f574b556790deb65791e0c5aa438b6/tokenizer_config.json
54
+ [INFO|2025-07-24 16:02:17] tokenization_utils_base.py:2023 >> loading file chat_template.jinja from cache at None
55
+ [INFO|2025-07-24 16:02:17] tokenization_utils_base.py:2299 >> Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
56
+ [INFO|2025-07-24 16:02:17] logging.py:143 >> Add pad token: <|eot_id|>
57
+ [INFO|2025-07-24 16:02:17] logging.py:143 >> Add <|eom_id|> to stop words.
58
+ [INFO|2025-07-24 16:02:17] logging.py:143 >> Loading dataset pippo_dataset_v02_1900_lines.json...
59
+ [INFO|2025-07-24 16:02:24] configuration_utils.py:698 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--meta-llama--Llama-3.2-1B-Instruct/snapshots/9213176726f574b556790deb65791e0c5aa438b6/config.json
60
+ [INFO|2025-07-24 16:02:24] configuration_utils.py:770 >> Model config LlamaConfig {
61
+ "architectures": [
62
+ "LlamaForCausalLM"
63
+ ],
64
+ "attention_bias": false,
65
+ "attention_dropout": 0.0,
66
+ "bos_token_id": 128000,
67
+ "eos_token_id": [
68
+ 128001,
69
+ 128008,
70
+ 128009
71
+ ],
72
+ "head_dim": 64,
73
+ "hidden_act": "silu",
74
+ "hidden_size": 2048,
75
+ "initializer_range": 0.02,
76
+ "intermediate_size": 8192,
77
+ "max_position_embeddings": 131072,
78
+ "mlp_bias": false,
79
+ "model_type": "llama",
80
+ "num_attention_heads": 32,
81
+ "num_hidden_layers": 16,
82
+ "num_key_value_heads": 8,
83
+ "pretraining_tp": 1,
84
+ "rms_norm_eps": 1e-05,
85
+ "rope_scaling": {
86
+ "factor": 32.0,
87
+ "high_freq_factor": 4.0,
88
+ "low_freq_factor": 1.0,
89
+ "original_max_position_embeddings": 8192,
90
+ "rope_type": "llama3"
91
+ },
92
+ "rope_theta": 500000.0,
93
+ "tie_word_embeddings": true,
94
+ "torch_dtype": "bfloat16",
95
+ "transformers_version": "4.52.4",
96
+ "use_cache": true,
97
+ "vocab_size": 128256
98
+ }
99
+
100
+ [INFO|2025-07-24 16:02:24] logging.py:143 >> KV cache is disabled during training.
101
+ [INFO|2025-07-24 16:03:23] modeling_utils.py:1151 >> loading weights file model.safetensors from cache at /root/.cache/huggingface/hub/models--meta-llama--Llama-3.2-1B-Instruct/snapshots/9213176726f574b556790deb65791e0c5aa438b6/model.safetensors
102
+ [INFO|2025-07-24 16:03:23] modeling_utils.py:2241 >> Instantiating LlamaForCausalLM model under default dtype torch.bfloat16.
103
+ [INFO|2025-07-24 16:03:23] configuration_utils.py:1135 >> Generate config GenerationConfig {
104
+ "bos_token_id": 128000,
105
+ "eos_token_id": [
106
+ 128001,
107
+ 128008,
108
+ 128009
109
+ ],
110
+ "use_cache": false
111
+ }
112
+
113
+ [INFO|2025-07-24 16:03:25] modeling_utils.py:5131 >> All model checkpoint weights were used when initializing LlamaForCausalLM.
114
+
115
+ [INFO|2025-07-24 16:03:25] modeling_utils.py:5139 >> All the weights of LlamaForCausalLM were initialized from the model checkpoint at meta-llama/Llama-3.2-1B-Instruct.
116
+ If your task is similar to the task the model of the checkpoint was trained on, you can already use LlamaForCausalLM for predictions without further training.
117
+ [INFO|2025-07-24 16:03:25] configuration_utils.py:1090 >> loading configuration file generation_config.json from cache at /root/.cache/huggingface/hub/models--meta-llama--Llama-3.2-1B-Instruct/snapshots/9213176726f574b556790deb65791e0c5aa438b6/generation_config.json
118
+ [INFO|2025-07-24 16:03:25] configuration_utils.py:1135 >> Generate config GenerationConfig {
119
+ "bos_token_id": 128000,
120
+ "do_sample": true,
121
+ "eos_token_id": [
122
+ 128001,
123
+ 128008,
124
+ 128009
125
+ ],
126
+ "temperature": 0.6,
127
+ "top_p": 0.9
128
+ }
129
+
130
+ [INFO|2025-07-24 16:03:25] logging.py:143 >> Gradient checkpointing enabled.
131
+ [INFO|2025-07-24 16:03:25] logging.py:143 >> Using torch SDPA for faster training and inference.
132
+ [INFO|2025-07-24 16:03:25] logging.py:143 >> Upcasting trainable params to float32.
133
+ [INFO|2025-07-24 16:03:25] logging.py:143 >> Fine-tuning method: DoRA
134
+ [INFO|2025-07-24 16:03:27] logging.py:143 >> Loaded adapter(s): saves/Llama-3.2-1B-Instruct/lora/train_1B-Instruct_pippo_v4
135
+ [INFO|2025-07-24 16:03:27] logging.py:143 >> trainable params: 15,925,248 || all params: 1,251,739,648 || trainable%: 1.2722
136
+ [INFO|2025-07-24 16:03:27] trainer.py:756 >> Using auto half precision backend
137
+ [INFO|2025-07-24 16:03:27] logging.py:143 >> Using LoRA+ optimizer with loraplus lr ratio 8.00.
138
+ [INFO|2025-07-24 16:03:28] trainer.py:2409 >> ***** Running training *****
139
+ [INFO|2025-07-24 16:03:28] trainer.py:2410 >> Num examples = 1,490
140
+ [INFO|2025-07-24 16:03:28] trainer.py:2411 >> Num Epochs = 4
141
+ [INFO|2025-07-24 16:03:28] trainer.py:2412 >> Instantaneous batch size per device = 2
142
+ [INFO|2025-07-24 16:03:28] trainer.py:2415 >> Total train batch size (w. parallel, distributed & accumulation) = 16
143
+ [INFO|2025-07-24 16:03:28] trainer.py:2416 >> Gradient Accumulation steps = 8
144
+ [INFO|2025-07-24 16:03:28] trainer.py:2417 >> Total optimization steps = 376
145
+ [INFO|2025-07-24 16:03:28] trainer.py:2418 >> Number of trainable parameters = 15,925,248
146
+ [INFO|2025-07-24 16:03:28] logging.py:143 >> Initial PiSSA adapter will be saved at: saves/Llama-3.2-1B-Instruct/lora/train_1B-Instruct_pippo_v6/pissa_init.
147
+ [INFO|2025-07-24 16:03:28] configuration_utils.py:698 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--meta-llama--Llama-3.2-1B-Instruct/snapshots/9213176726f574b556790deb65791e0c5aa438b6/config.json
148
+ [INFO|2025-07-24 16:03:28] configuration_utils.py:770 >> Model config LlamaConfig {
149
+ "architectures": [
150
+ "LlamaForCausalLM"
151
+ ],
152
+ "attention_bias": false,
153
+ "attention_dropout": 0.0,
154
+ "bos_token_id": 128000,
155
+ "eos_token_id": [
156
+ 128001,
157
+ 128008,
158
+ 128009
159
+ ],
160
+ "head_dim": 64,
161
+ "hidden_act": "silu",
162
+ "hidden_size": 2048,
163
+ "initializer_range": 0.02,
164
+ "intermediate_size": 8192,
165
+ "max_position_embeddings": 131072,
166
+ "mlp_bias": false,
167
+ "model_type": "llama",
168
+ "num_attention_heads": 32,
169
+ "num_hidden_layers": 16,
170
+ "num_key_value_heads": 8,
171
+ "pretraining_tp": 1,
172
+ "rms_norm_eps": 1e-05,
173
+ "rope_scaling": {
174
+ "factor": 32.0,
175
+ "high_freq_factor": 4.0,
176
+ "low_freq_factor": 1.0,
177
+ "original_max_position_embeddings": 8192,
178
+ "rope_type": "llama3"
179
+ },
180
+ "rope_theta": 500000.0,
181
+ "tie_word_embeddings": true,
182
+ "torch_dtype": "bfloat16",
183
+ "transformers_version": "4.52.4",
184
+ "use_cache": true,
185
+ "vocab_size": 128256
186
+ }
187
+
188
+ [INFO|2025-07-24 16:03:43] logging.py:143 >> {'loss': 1.1748, 'learning_rate': 1.9994e-05, 'epoch': 0.05, 'throughput': 263.90}
189
+ [INFO|2025-07-24 16:03:54] logging.py:143 >> {'loss': 1.2634, 'learning_rate': 1.9972e-05, 'epoch': 0.11, 'throughput': 304.64}
190
+ [INFO|2025-07-24 16:04:06] logging.py:143 >> {'loss': 1.4367, 'learning_rate': 1.9932e-05, 'epoch': 0.16, 'throughput': 315.40}
191
+ [INFO|2025-07-24 16:04:18] logging.py:143 >> {'loss': 1.3167, 'learning_rate': 1.9874e-05, 'epoch': 0.21, 'throughput': 323.64}
192
+ [INFO|2025-07-24 16:04:30] logging.py:143 >> {'loss': 1.4144, 'learning_rate': 1.9800e-05, 'epoch': 0.27, 'throughput': 325.70}
193
+ [INFO|2025-07-24 16:04:41] logging.py:143 >> {'loss': 1.3944, 'learning_rate': 1.9708e-05, 'epoch': 0.32, 'throughput': 331.60}
194
+ [INFO|2025-07-24 16:04:52] logging.py:143 >> {'loss': 1.3946, 'learning_rate': 1.9599e-05, 'epoch': 0.38, 'throughput': 334.75}
195
+ [INFO|2025-07-24 16:05:04] logging.py:143 >> {'loss': 1.3827, 'learning_rate': 1.9474e-05, 'epoch': 0.43, 'throughput': 336.48}
196
+ [INFO|2025-07-24 16:05:16] logging.py:143 >> {'loss': 1.4509, 'learning_rate': 1.9332e-05, 'epoch': 0.48, 'throughput': 336.58}
197
+ [INFO|2025-07-24 16:05:29] logging.py:143 >> {'loss': 1.3347, 'learning_rate': 1.9174e-05, 'epoch': 0.54, 'throughput': 335.59}
198
+ [INFO|2025-07-24 16:05:41] logging.py:143 >> {'loss': 1.3834, 'learning_rate': 1.8999e-05, 'epoch': 0.59, 'throughput': 335.37}
199
+ [INFO|2025-07-24 16:05:53] logging.py:143 >> {'loss': 1.4679, 'learning_rate': 1.8809e-05, 'epoch': 0.64, 'throughput': 335.60}
200
+ [INFO|2025-07-24 16:06:04] logging.py:143 >> {'loss': 1.3973, 'learning_rate': 1.8604e-05, 'epoch': 0.70, 'throughput': 336.68}
201
+ [INFO|2025-07-24 16:06:17] logging.py:143 >> {'loss': 1.5408, 'learning_rate': 1.8384e-05, 'epoch': 0.75, 'throughput': 335.03}
202
+ [INFO|2025-07-24 16:06:28] logging.py:143 >> {'loss': 1.4967, 'learning_rate': 1.8149e-05, 'epoch': 0.81, 'throughput': 335.55}
203
+ [INFO|2025-07-24 16:06:40] logging.py:143 >> {'loss': 1.4644, 'learning_rate': 1.7900e-05, 'epoch': 0.86, 'throughput': 336.30}
204
+ [INFO|2025-07-24 16:06:52] logging.py:143 >> {'loss': 1.4226, 'learning_rate': 1.7637e-05, 'epoch': 0.91, 'throughput': 336.02}
205
+ [INFO|2025-07-24 16:07:03] logging.py:143 >> {'loss': 1.4847, 'learning_rate': 1.7360e-05, 'epoch': 0.97, 'throughput': 336.26}
206
+ [INFO|2025-07-24 16:07:13] logging.py:143 >> {'loss': 1.2927, 'learning_rate': 1.7071e-05, 'epoch': 1.01, 'throughput': 336.91}
207
+ [INFO|2025-07-24 16:07:23] logging.py:143 >> {'loss': 0.8505, 'learning_rate': 1.6770e-05, 'epoch': 1.06, 'throughput': 338.48}
208
+ [INFO|2025-07-24 16:07:23] trainer.py:4327 >>
209
+ ***** Running Evaluation *****
210
+ [INFO|2025-07-24 16:07:23] trainer.py:4329 >> Num examples = 373
211
+ [INFO|2025-07-24 16:07:23] trainer.py:4332 >> Batch size = 2
212
+ [INFO|2025-07-24 16:07:37] trainer.py:3993 >> Saving model checkpoint to saves/Llama-3.2-1B-Instruct/lora/train_1B-Instruct_pippo_v6/checkpoint-100
213
+ [INFO|2025-07-24 16:07:37] configuration_utils.py:698 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--meta-llama--Llama-3.2-1B-Instruct/snapshots/9213176726f574b556790deb65791e0c5aa438b6/config.json
214
+ [INFO|2025-07-24 16:07:37] configuration_utils.py:770 >> Model config LlamaConfig {
215
+ "architectures": [
216
+ "LlamaForCausalLM"
217
+ ],
218
+ "attention_bias": false,
219
+ "attention_dropout": 0.0,
220
+ "bos_token_id": 128000,
221
+ "eos_token_id": [
222
+ 128001,
223
+ 128008,
224
+ 128009
225
+ ],
226
+ "head_dim": 64,
227
+ "hidden_act": "silu",
228
+ "hidden_size": 2048,
229
+ "initializer_range": 0.02,
230
+ "intermediate_size": 8192,
231
+ "max_position_embeddings": 131072,
232
+ "mlp_bias": false,
233
+ "model_type": "llama",
234
+ "num_attention_heads": 32,
235
+ "num_hidden_layers": 16,
236
+ "num_key_value_heads": 8,
237
+ "pretraining_tp": 1,
238
+ "rms_norm_eps": 1e-05,
239
+ "rope_scaling": {
240
+ "factor": 32.0,
241
+ "high_freq_factor": 4.0,
242
+ "low_freq_factor": 1.0,
243
+ "original_max_position_embeddings": 8192,
244
+ "rope_type": "llama3"
245
+ },
246
+ "rope_theta": 500000.0,
247
+ "tie_word_embeddings": true,
248
+ "torch_dtype": "bfloat16",
249
+ "transformers_version": "4.52.4",
250
+ "use_cache": true,
251
+ "vocab_size": 128256
252
+ }
253
+
254
+ [INFO|2025-07-24 16:07:38] tokenization_utils_base.py:2356 >> chat template saved in saves/Llama-3.2-1B-Instruct/lora/train_1B-Instruct_pippo_v6/checkpoint-100/chat_template.jinja
255
+ [INFO|2025-07-24 16:07:38] tokenization_utils_base.py:2525 >> tokenizer config file saved in saves/Llama-3.2-1B-Instruct/lora/train_1B-Instruct_pippo_v6/checkpoint-100/tokenizer_config.json
256
+ [INFO|2025-07-24 16:07:38] tokenization_utils_base.py:2534 >> Special tokens file saved in saves/Llama-3.2-1B-Instruct/lora/train_1B-Instruct_pippo_v6/checkpoint-100/special_tokens_map.json
257
+ [INFO|2025-07-24 16:07:51] logging.py:143 >> {'loss': 0.7497, 'learning_rate': 1.6456e-05, 'epoch': 1.12, 'throughput': 318.10}
258
+ [INFO|2025-07-24 16:08:02] logging.py:143 >> {'loss': 0.7761, 'learning_rate': 1.6132e-05, 'epoch': 1.17, 'throughput': 319.79}
259
+ [INFO|2025-07-24 16:08:14] logging.py:143 >> {'loss': 0.7997, 'learning_rate': 1.5796e-05, 'epoch': 1.23, 'throughput': 321.09}
260
+ [INFO|2025-07-24 16:08:25] logging.py:143 >> {'loss': 0.8275, 'learning_rate': 1.5451e-05, 'epoch': 1.28, 'throughput': 322.08}
261
+ [INFO|2025-07-24 16:08:37] logging.py:143 >> {'loss': 0.8599, 'learning_rate': 1.5096e-05, 'epoch': 1.33, 'throughput': 322.83}
262
+ [INFO|2025-07-24 16:08:49] logging.py:143 >> {'loss': 0.9179, 'learning_rate': 1.4732e-05, 'epoch': 1.39, 'throughput': 323.42}
263
+ [INFO|2025-07-24 16:09:00] logging.py:143 >> {'loss': 0.8255, 'learning_rate': 1.4360e-05, 'epoch': 1.44, 'throughput': 324.25}
264
+ [INFO|2025-07-24 16:09:11] logging.py:143 >> {'loss': 0.8806, 'learning_rate': 1.3981e-05, 'epoch': 1.49, 'throughput': 325.46}
265
+ [INFO|2025-07-24 16:09:23] logging.py:143 >> {'loss': 0.8366, 'learning_rate': 1.3594e-05, 'epoch': 1.55, 'throughput': 326.15}
266
+ [INFO|2025-07-24 16:09:34] logging.py:143 >> {'loss': 0.8567, 'learning_rate': 1.3201e-05, 'epoch': 1.60, 'throughput': 327.21}
267
+ [INFO|2025-07-24 16:09:45] logging.py:143 >> {'loss': 0.8939, 'learning_rate': 1.2803e-05, 'epoch': 1.66, 'throughput': 328.25}
268
+ [INFO|2025-07-24 16:09:56] logging.py:143 >> {'loss': 0.9650, 'learning_rate': 1.2399e-05, 'epoch': 1.71, 'throughput': 329.28}
269
+ [INFO|2025-07-24 16:10:07] logging.py:143 >> {'loss': 0.8915, 'learning_rate': 1.1992e-05, 'epoch': 1.76, 'throughput': 330.41}
270
+ [INFO|2025-07-24 16:10:18] logging.py:143 >> {'loss': 0.9085, 'learning_rate': 1.1581e-05, 'epoch': 1.82, 'throughput': 331.65}
271
+ [INFO|2025-07-24 16:10:29] logging.py:143 >> {'loss': 0.8831, 'learning_rate': 1.1167e-05, 'epoch': 1.87, 'throughput': 332.58}
272
+ [INFO|2025-07-24 16:10:41] logging.py:143 >> {'loss': 1.0271, 'learning_rate': 1.0751e-05, 'epoch': 1.92, 'throughput': 332.56}
273
+ [INFO|2025-07-24 16:10:52] logging.py:143 >> {'loss': 0.9636, 'learning_rate': 1.0334e-05, 'epoch': 1.98, 'throughput': 333.29}
274
+ [INFO|2025-07-24 16:11:02] logging.py:143 >> {'loss': 0.7085, 'learning_rate': 9.9164e-06, 'epoch': 2.02, 'throughput': 333.30}
275
+ [INFO|2025-07-24 16:11:13] logging.py:143 >> {'loss': 0.5186, 'learning_rate': 9.4989e-06, 'epoch': 2.08, 'throughput': 333.84}
276
+ [INFO|2025-07-24 16:11:25] logging.py:143 >> {'loss': 0.5023, 'learning_rate': 9.0822e-06, 'epoch': 2.13, 'throughput': 334.41}
277
+ [INFO|2025-07-24 16:11:25] trainer.py:4327 >>
278
+ ***** Running Evaluation *****
279
+ [INFO|2025-07-24 16:11:25] trainer.py:4329 >> Num examples = 373
280
+ [INFO|2025-07-24 16:11:25] trainer.py:4332 >> Batch size = 2
281
+ [INFO|2025-07-24 16:11:38] trainer.py:3993 >> Saving model checkpoint to saves/Llama-3.2-1B-Instruct/lora/train_1B-Instruct_pippo_v6/checkpoint-200
282
+ [INFO|2025-07-24 16:11:39] configuration_utils.py:698 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--meta-llama--Llama-3.2-1B-Instruct/snapshots/9213176726f574b556790deb65791e0c5aa438b6/config.json
283
+ [INFO|2025-07-24 16:11:39] configuration_utils.py:770 >> Model config LlamaConfig {
284
+ "architectures": [
285
+ "LlamaForCausalLM"
286
+ ],
287
+ "attention_bias": false,
288
+ "attention_dropout": 0.0,
289
+ "bos_token_id": 128000,
290
+ "eos_token_id": [
291
+ 128001,
292
+ 128008,
293
+ 128009
294
+ ],
295
+ "head_dim": 64,
296
+ "hidden_act": "silu",
297
+ "hidden_size": 2048,
298
+ "initializer_range": 0.02,
299
+ "intermediate_size": 8192,
300
+ "max_position_embeddings": 131072,
301
+ "mlp_bias": false,
302
+ "model_type": "llama",
303
+ "num_attention_heads": 32,
304
+ "num_hidden_layers": 16,
305
+ "num_key_value_heads": 8,
306
+ "pretraining_tp": 1,
307
+ "rms_norm_eps": 1e-05,
308
+ "rope_scaling": {
309
+ "factor": 32.0,
310
+ "high_freq_factor": 4.0,
311
+ "low_freq_factor": 1.0,
312
+ "original_max_position_embeddings": 8192,
313
+ "rope_type": "llama3"
314
+ },
315
+ "rope_theta": 500000.0,
316
+ "tie_word_embeddings": true,
317
+ "torch_dtype": "bfloat16",
318
+ "transformers_version": "4.52.4",
319
+ "use_cache": true,
320
+ "vocab_size": 128256
321
+ }
322
+
323
+ [INFO|2025-07-24 16:11:39] tokenization_utils_base.py:2356 >> chat template saved in saves/Llama-3.2-1B-Instruct/lora/train_1B-Instruct_pippo_v6/checkpoint-200/chat_template.jinja
324
+ [INFO|2025-07-24 16:11:40] tokenization_utils_base.py:2525 >> tokenizer config file saved in saves/Llama-3.2-1B-Instruct/lora/train_1B-Instruct_pippo_v6/checkpoint-200/tokenizer_config.json
325
+ [INFO|2025-07-24 16:11:40] tokenization_utils_base.py:2534 >> Special tokens file saved in saves/Llama-3.2-1B-Instruct/lora/train_1B-Instruct_pippo_v6/checkpoint-200/special_tokens_map.json
326
+ [INFO|2025-07-24 16:11:53] logging.py:143 >> {'loss': 0.5145, 'learning_rate': 8.6671e-06, 'epoch': 2.18, 'throughput': 323.15}
327
+ [INFO|2025-07-24 16:12:05] logging.py:143 >> {'loss': 0.4971, 'learning_rate': 8.2544e-06, 'epoch': 2.24, 'throughput': 323.77}
328
+ [INFO|2025-07-24 16:12:16] logging.py:143 >> {'loss': 0.5042, 'learning_rate': 7.8447e-06, 'epoch': 2.29, 'throughput': 324.87}
329
+ [INFO|2025-07-24 16:12:27] logging.py:143 >> {'loss': 0.5423, 'learning_rate': 7.4387e-06, 'epoch': 2.34, 'throughput': 325.53}
330
+ [INFO|2025-07-24 16:12:39] logging.py:143 >> {'loss': 0.5913, 'learning_rate': 7.0372e-06, 'epoch': 2.40, 'throughput': 325.95}
331
+ [INFO|2025-07-24 16:12:51] logging.py:143 >> {'loss': 0.5403, 'learning_rate': 6.6409e-06, 'epoch': 2.45, 'throughput': 326.13}
332
+ [INFO|2025-07-24 16:13:02] logging.py:143 >> {'loss': 0.5301, 'learning_rate': 6.2505e-06, 'epoch': 2.50, 'throughput': 326.79}
333
+ [INFO|2025-07-24 16:13:13] logging.py:143 >> {'loss': 0.5417, 'learning_rate': 5.8666e-06, 'epoch': 2.56, 'throughput': 327.37}
334
+ [INFO|2025-07-24 16:13:25] logging.py:143 >> {'loss': 0.5358, 'learning_rate': 5.4899e-06, 'epoch': 2.61, 'throughput': 327.79}
335
+ [INFO|2025-07-24 16:13:37] logging.py:143 >> {'loss': 0.5249, 'learning_rate': 5.1211e-06, 'epoch': 2.67, 'throughput': 328.11}
336
+ [INFO|2025-07-24 16:13:48] logging.py:143 >> {'loss': 0.5134, 'learning_rate': 4.7608e-06, 'epoch': 2.72, 'throughput': 328.62}
337
+ [INFO|2025-07-24 16:14:00] logging.py:143 >> {'loss': 0.5160, 'learning_rate': 4.4096e-06, 'epoch': 2.77, 'throughput': 328.73}
338
+ [INFO|2025-07-24 16:14:11] logging.py:143 >> {'loss': 0.5611, 'learning_rate': 4.0682e-06, 'epoch': 2.83, 'throughput': 329.02}
339
+ [INFO|2025-07-24 16:14:22] logging.py:143 >> {'loss': 0.5084, 'learning_rate': 3.7371e-06, 'epoch': 2.88, 'throughput': 329.85}
340
+ [INFO|2025-07-24 16:14:33] logging.py:143 >> {'loss': 0.5458, 'learning_rate': 3.4170e-06, 'epoch': 2.93, 'throughput': 330.35}
341
+ [INFO|2025-07-24 16:14:43] logging.py:143 >> {'loss': 0.5205, 'learning_rate': 3.1084e-06, 'epoch': 2.99, 'throughput': 331.42}
342
+ [INFO|2025-07-24 16:14:52] logging.py:143 >> {'loss': 0.4058, 'learning_rate': 2.8118e-06, 'epoch': 3.03, 'throughput': 332.17}
343
+ [INFO|2025-07-24 16:15:04] logging.py:143 >> {'loss': 0.3859, 'learning_rate': 2.5277e-06, 'epoch': 3.09, 'throughput': 332.42}
344
+ [INFO|2025-07-24 16:15:14] logging.py:143 >> {'loss': 0.3724, 'learning_rate': 2.2567e-06, 'epoch': 3.14, 'throughput': 333.25}
345
+ [INFO|2025-07-24 16:15:25] logging.py:143 >> {'loss': 0.3916, 'learning_rate': 1.9991e-06, 'epoch': 3.19, 'throughput': 333.86}
346
+ [INFO|2025-07-24 16:15:25] trainer.py:4327 >>
347
+ ***** Running Evaluation *****
348
+ [INFO|2025-07-24 16:15:25] trainer.py:4329 >> Num examples = 373
349
+ [INFO|2025-07-24 16:15:25] trainer.py:4332 >> Batch size = 2
350
+ [INFO|2025-07-24 16:15:37] trainer.py:3993 >> Saving model checkpoint to saves/Llama-3.2-1B-Instruct/lora/train_1B-Instruct_pippo_v6/checkpoint-300
351
+ [INFO|2025-07-24 16:15:38] configuration_utils.py:698 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--meta-llama--Llama-3.2-1B-Instruct/snapshots/9213176726f574b556790deb65791e0c5aa438b6/config.json
352
+ [INFO|2025-07-24 16:15:38] configuration_utils.py:770 >> Model config LlamaConfig {
353
+ "architectures": [
354
+ "LlamaForCausalLM"
355
+ ],
356
+ "attention_bias": false,
357
+ "attention_dropout": 0.0,
358
+ "bos_token_id": 128000,
359
+ "eos_token_id": [
360
+ 128001,
361
+ 128008,
362
+ 128009
363
+ ],
364
+ "head_dim": 64,
365
+ "hidden_act": "silu",
366
+ "hidden_size": 2048,
367
+ "initializer_range": 0.02,
368
+ "intermediate_size": 8192,
369
+ "max_position_embeddings": 131072,
370
+ "mlp_bias": false,
371
+ "model_type": "llama",
372
+ "num_attention_heads": 32,
373
+ "num_hidden_layers": 16,
374
+ "num_key_value_heads": 8,
375
+ "pretraining_tp": 1,
376
+ "rms_norm_eps": 1e-05,
377
+ "rope_scaling": {
378
+ "factor": 32.0,
379
+ "high_freq_factor": 4.0,
380
+ "low_freq_factor": 1.0,
381
+ "original_max_position_embeddings": 8192,
382
+ "rope_type": "llama3"
383
+ },
384
+ "rope_theta": 500000.0,
385
+ "tie_word_embeddings": true,
386
+ "torch_dtype": "bfloat16",
387
+ "transformers_version": "4.52.4",
388
+ "use_cache": true,
389
+ "vocab_size": 128256
390
+ }
391
+
392
+ [INFO|2025-07-24 16:15:38] tokenization_utils_base.py:2356 >> chat template saved in saves/Llama-3.2-1B-Instruct/lora/train_1B-Instruct_pippo_v6/checkpoint-300/chat_template.jinja
393
+ [INFO|2025-07-24 16:15:39] tokenization_utils_base.py:2525 >> tokenizer config file saved in saves/Llama-3.2-1B-Instruct/lora/train_1B-Instruct_pippo_v6/checkpoint-300/tokenizer_config.json
394
+ [INFO|2025-07-24 16:15:39] tokenization_utils_base.py:2534 >> Special tokens file saved in saves/Llama-3.2-1B-Instruct/lora/train_1B-Instruct_pippo_v6/checkpoint-300/special_tokens_map.json
395
+ [INFO|2025-07-24 16:15:51] logging.py:143 >> {'loss': 0.3676, 'learning_rate': 1.7556e-06, 'epoch': 3.25, 'throughput': 327.35}
396
+ [INFO|2025-07-24 16:16:03] logging.py:143 >> {'loss': 0.3798, 'learning_rate': 1.5264e-06, 'epoch': 3.30, 'throughput': 327.69}
397
+ [INFO|2025-07-24 16:16:13] logging.py:143 >> {'loss': 0.3606, 'learning_rate': 1.3120e-06, 'epoch': 3.35, 'throughput': 328.40}
398
+ [INFO|2025-07-24 16:16:24] logging.py:143 >> {'loss': 0.3938, 'learning_rate': 1.1128e-06, 'epoch': 3.41, 'throughput': 329.00}
399
+ [INFO|2025-07-24 16:16:35] logging.py:143 >> {'loss': 0.3605, 'learning_rate': 9.2909e-07, 'epoch': 3.46, 'throughput': 329.68}
400
+ [INFO|2025-07-24 16:16:45] logging.py:143 >> {'loss': 0.3781, 'learning_rate': 7.6120e-07, 'epoch': 3.52, 'throughput': 330.66}
401
+ [INFO|2025-07-24 16:16:55] logging.py:143 >> {'loss': 0.3794, 'learning_rate': 6.0944e-07, 'epoch': 3.57, 'throughput': 331.22}
402
+ [INFO|2025-07-24 16:17:06] logging.py:143 >> {'loss': 0.3526, 'learning_rate': 4.7406e-07, 'epoch': 3.62, 'throughput': 332.12}
403
+ [INFO|2025-07-24 16:17:16] logging.py:143 >> {'loss': 0.3846, 'learning_rate': 3.5531e-07, 'epoch': 3.68, 'throughput': 332.56}
404
+ [INFO|2025-07-24 16:17:27] logging.py:143 >> {'loss': 0.3855, 'learning_rate': 2.5338e-07, 'epoch': 3.73, 'throughput': 333.19}
405
+ [INFO|2025-07-24 16:17:37] logging.py:143 >> {'loss': 0.3955, 'learning_rate': 1.6847e-07, 'epoch': 3.78, 'throughput': 333.69}
406
+ [INFO|2025-07-24 16:17:48] logging.py:143 >> {'loss': 0.3400, 'learning_rate': 1.0071e-07, 'epoch': 3.84, 'throughput': 334.24}
407
+ [INFO|2025-07-24 16:17:58] logging.py:143 >> {'loss': 0.3584, 'learning_rate': 5.0222e-08, 'epoch': 3.89, 'throughput': 334.96}
408
+ [INFO|2025-07-24 16:18:09] logging.py:143 >> {'loss': 0.3608, 'learning_rate': 1.7099e-08, 'epoch': 3.94, 'throughput': 335.57}
409
+ [INFO|2025-07-24 16:18:20] logging.py:143 >> {'loss': 0.3659, 'learning_rate': 1.3962e-09, 'epoch': 4.00, 'throughput': 336.16}
410
+ [INFO|2025-07-24 16:18:20] trainer.py:3993 >> Saving model checkpoint to saves/Llama-3.2-1B-Instruct/lora/train_1B-Instruct_pippo_v6/checkpoint-376
411
+ [INFO|2025-07-24 16:18:20] configuration_utils.py:698 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--meta-llama--Llama-3.2-1B-Instruct/snapshots/9213176726f574b556790deb65791e0c5aa438b6/config.json
412
+ [INFO|2025-07-24 16:18:20] configuration_utils.py:770 >> Model config LlamaConfig {
413
+ "architectures": [
414
+ "LlamaForCausalLM"
415
+ ],
416
+ "attention_bias": false,
417
+ "attention_dropout": 0.0,
418
+ "bos_token_id": 128000,
419
+ "eos_token_id": [
420
+ 128001,
421
+ 128008,
422
+ 128009
423
+ ],
424
+ "head_dim": 64,
425
+ "hidden_act": "silu",
426
+ "hidden_size": 2048,
427
+ "initializer_range": 0.02,
428
+ "intermediate_size": 8192,
429
+ "max_position_embeddings": 131072,
430
+ "mlp_bias": false,
431
+ "model_type": "llama",
432
+ "num_attention_heads": 32,
433
+ "num_hidden_layers": 16,
434
+ "num_key_value_heads": 8,
435
+ "pretraining_tp": 1,
436
+ "rms_norm_eps": 1e-05,
437
+ "rope_scaling": {
438
+ "factor": 32.0,
439
+ "high_freq_factor": 4.0,
440
+ "low_freq_factor": 1.0,
441
+ "original_max_position_embeddings": 8192,
442
+ "rope_type": "llama3"
443
+ },
444
+ "rope_theta": 500000.0,
445
+ "tie_word_embeddings": true,
446
+ "torch_dtype": "bfloat16",
447
+ "transformers_version": "4.52.4",
448
+ "use_cache": true,
449
+ "vocab_size": 128256
450
+ }
451
+
452
+ [INFO|2025-07-24 16:18:21] tokenization_utils_base.py:2356 >> chat template saved in saves/Llama-3.2-1B-Instruct/lora/train_1B-Instruct_pippo_v6/checkpoint-376/chat_template.jinja
453
+ [INFO|2025-07-24 16:18:21] tokenization_utils_base.py:2525 >> tokenizer config file saved in saves/Llama-3.2-1B-Instruct/lora/train_1B-Instruct_pippo_v6/checkpoint-376/tokenizer_config.json
454
+ [INFO|2025-07-24 16:18:21] tokenization_utils_base.py:2534 >> Special tokens file saved in saves/Llama-3.2-1B-Instruct/lora/train_1B-Instruct_pippo_v6/checkpoint-376/special_tokens_map.json
455
+ [INFO|2025-07-24 16:18:23] trainer.py:2676 >>
456
+
457
+ Training completed. Do not forget to share your model on huggingface.co/models =)
458
+
459
+
460
+ [INFO|2025-07-24 16:18:24] logging.py:143 >> Converted PiSSA adapter will be saved at: saves/Llama-3.2-1B-Instruct/lora/train_1B-Instruct_pippo_v6/pissa_converted.
461
+ [INFO|2025-07-24 16:18:24] configuration_utils.py:698 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--meta-llama--Llama-3.2-1B-Instruct/snapshots/9213176726f574b556790deb65791e0c5aa438b6/config.json
462
+ [INFO|2025-07-24 16:18:24] configuration_utils.py:770 >> Model config LlamaConfig {
463
+ "architectures": [
464
+ "LlamaForCausalLM"
465
+ ],
466
+ "attention_bias": false,
467
+ "attention_dropout": 0.0,
468
+ "bos_token_id": 128000,
469
+ "eos_token_id": [
470
+ 128001,
471
+ 128008,
472
+ 128009
473
+ ],
474
+ "head_dim": 64,
475
+ "hidden_act": "silu",
476
+ "hidden_size": 2048,
477
+ "initializer_range": 0.02,
478
+ "intermediate_size": 8192,
479
+ "max_position_embeddings": 131072,
480
+ "mlp_bias": false,
481
+ "model_type": "llama",
482
+ "num_attention_heads": 32,
483
+ "num_hidden_layers": 16,
484
+ "num_key_value_heads": 8,
485
+ "pretraining_tp": 1,
486
+ "rms_norm_eps": 1e-05,
487
+ "rope_scaling": {
488
+ "factor": 32.0,
489
+ "high_freq_factor": 4.0,
490
+ "low_freq_factor": 1.0,
491
+ "original_max_position_embeddings": 8192,
492
+ "rope_type": "llama3"
493
+ },
494
+ "rope_theta": 500000.0,
495
+ "tie_word_embeddings": true,
496
+ "torch_dtype": "bfloat16",
497
+ "transformers_version": "4.52.4",
498
+ "use_cache": true,
499
+ "vocab_size": 128256
500
+ }
501
+
502
+ [INFO|2025-07-24 16:18:25] configuration_utils.py:698 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--meta-llama--Llama-3.2-1B-Instruct/snapshots/9213176726f574b556790deb65791e0c5aa438b6/config.json
503
+ [INFO|2025-07-24 16:18:25] configuration_utils.py:770 >> Model config LlamaConfig {
504
+ "architectures": [
505
+ "LlamaForCausalLM"
506
+ ],
507
+ "attention_bias": false,
508
+ "attention_dropout": 0.0,
509
+ "bos_token_id": 128000,
510
+ "eos_token_id": [
511
+ 128001,
512
+ 128008,
513
+ 128009
514
+ ],
515
+ "head_dim": 64,
516
+ "hidden_act": "silu",
517
+ "hidden_size": 2048,
518
+ "initializer_range": 0.02,
519
+ "intermediate_size": 8192,
520
+ "max_position_embeddings": 131072,
521
+ "mlp_bias": false,
522
+ "model_type": "llama",
523
+ "num_attention_heads": 32,
524
+ "num_hidden_layers": 16,
525
+ "num_key_value_heads": 8,
526
+ "pretraining_tp": 1,
527
+ "rms_norm_eps": 1e-05,
528
+ "rope_scaling": {
529
+ "factor": 32.0,
530
+ "high_freq_factor": 4.0,
531
+ "low_freq_factor": 1.0,
532
+ "original_max_position_embeddings": 8192,
533
+ "rope_type": "llama3"
534
+ },
535
+ "rope_theta": 500000.0,
536
+ "tie_word_embeddings": true,
537
+ "torch_dtype": "bfloat16",
538
+ "transformers_version": "4.52.4",
539
+ "use_cache": true,
540
+ "vocab_size": 128256
541
+ }
542
+
543
+ [INFO|2025-07-24 16:18:26] configuration_utils.py:698 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--meta-llama--Llama-3.2-1B-Instruct/snapshots/9213176726f574b556790deb65791e0c5aa438b6/config.json
544
+ [INFO|2025-07-24 16:18:26] configuration_utils.py:770 >> Model config LlamaConfig {
545
+ "architectures": [
546
+ "LlamaForCausalLM"
547
+ ],
548
+ "attention_bias": false,
549
+ "attention_dropout": 0.0,
550
+ "bos_token_id": 128000,
551
+ "eos_token_id": [
552
+ 128001,
553
+ 128008,
554
+ 128009
555
+ ],
556
+ "head_dim": 64,
557
+ "hidden_act": "silu",
558
+ "hidden_size": 2048,
559
+ "initializer_range": 0.02,
560
+ "intermediate_size": 8192,
561
+ "max_position_embeddings": 131072,
562
+ "mlp_bias": false,
563
+ "model_type": "llama",
564
+ "num_attention_heads": 32,
565
+ "num_hidden_layers": 16,
566
+ "num_key_value_heads": 8,
567
+ "pretraining_tp": 1,
568
+ "rms_norm_eps": 1e-05,
569
+ "rope_scaling": {
570
+ "factor": 32.0,
571
+ "high_freq_factor": 4.0,
572
+ "low_freq_factor": 1.0,
573
+ "original_max_position_embeddings": 8192,
574
+ "rope_type": "llama3"
575
+ },
576
+ "rope_theta": 500000.0,
577
+ "tie_word_embeddings": true,
578
+ "torch_dtype": "bfloat16",
579
+ "transformers_version": "4.52.4",
580
+ "use_cache": true,
581
+ "vocab_size": 128256
582
+ }
583
+
584
+ [INFO|2025-07-24 16:18:28] trainer.py:3993 >> Saving model checkpoint to saves/Llama-3.2-1B-Instruct/lora/train_1B-Instruct_pippo_v6
585
+ [INFO|2025-07-24 16:18:28] configuration_utils.py:698 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--meta-llama--Llama-3.2-1B-Instruct/snapshots/9213176726f574b556790deb65791e0c5aa438b6/config.json
586
+ [INFO|2025-07-24 16:18:28] configuration_utils.py:770 >> Model config LlamaConfig {
587
+ "architectures": [
588
+ "LlamaForCausalLM"
589
+ ],
590
+ "attention_bias": false,
591
+ "attention_dropout": 0.0,
592
+ "bos_token_id": 128000,
593
+ "eos_token_id": [
594
+ 128001,
595
+ 128008,
596
+ 128009
597
+ ],
598
+ "head_dim": 64,
599
+ "hidden_act": "silu",
600
+ "hidden_size": 2048,
601
+ "initializer_range": 0.02,
602
+ "intermediate_size": 8192,
603
+ "max_position_embeddings": 131072,
604
+ "mlp_bias": false,
605
+ "model_type": "llama",
606
+ "num_attention_heads": 32,
607
+ "num_hidden_layers": 16,
608
+ "num_key_value_heads": 8,
609
+ "pretraining_tp": 1,
610
+ "rms_norm_eps": 1e-05,
611
+ "rope_scaling": {
612
+ "factor": 32.0,
613
+ "high_freq_factor": 4.0,
614
+ "low_freq_factor": 1.0,
615
+ "original_max_position_embeddings": 8192,
616
+ "rope_type": "llama3"
617
+ },
618
+ "rope_theta": 500000.0,
619
+ "tie_word_embeddings": true,
620
+ "torch_dtype": "bfloat16",
621
+ "transformers_version": "4.52.4",
622
+ "use_cache": true,
623
+ "vocab_size": 128256
624
+ }
625
+
626
+ [INFO|2025-07-24 16:18:29] tokenization_utils_base.py:2356 >> chat template saved in saves/Llama-3.2-1B-Instruct/lora/train_1B-Instruct_pippo_v6/chat_template.jinja
627
+ [INFO|2025-07-24 16:18:29] tokenization_utils_base.py:2525 >> tokenizer config file saved in saves/Llama-3.2-1B-Instruct/lora/train_1B-Instruct_pippo_v6/tokenizer_config.json
628
+ [INFO|2025-07-24 16:18:29] tokenization_utils_base.py:2534 >> Special tokens file saved in saves/Llama-3.2-1B-Instruct/lora/train_1B-Instruct_pippo_v6/special_tokens_map.json
629
+ [WARNING|2025-07-24 16:18:30] logging.py:148 >> No metric eval_accuracy to plot.
630
+ [INFO|2025-07-24 16:18:30] trainer.py:4327 >>
631
+ ***** Running Evaluation *****
632
+ [INFO|2025-07-24 16:18:30] trainer.py:4329 >> Num examples = 373
633
+ [INFO|2025-07-24 16:18:30] trainer.py:4332 >> Batch size = 2
634
+ [INFO|2025-07-24 16:18:43] modelcard.py:450 >> Dropping the following result as it does not have all the necessary fields:
635
+ {'task': {'name': 'Causal Language Modeling', 'type': 'text-generation'}}
special_tokens_map.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ {
4
+ "content": "<|eom_id|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ }
10
+ ],
11
+ "bos_token": {
12
+ "content": "<|begin_of_text|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false
17
+ },
18
+ "eos_token": {
19
+ "content": "<|eot_id|>",
20
+ "lstrip": false,
21
+ "normalized": false,
22
+ "rstrip": false,
23
+ "single_word": false
24
+ },
25
+ "pad_token": "<|eot_id|>"
26
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
3
+ size 17209920
tokenizer_config.json ADDED
@@ -0,0 +1,2068 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "additional_special_tokens": [
2053
+ "<|eom_id|>"
2054
+ ],
2055
+ "bos_token": "<|begin_of_text|>",
2056
+ "clean_up_tokenization_spaces": true,
2057
+ "eos_token": "<|eot_id|>",
2058
+ "extra_special_tokens": {},
2059
+ "model_input_names": [
2060
+ "input_ids",
2061
+ "attention_mask"
2062
+ ],
2063
+ "model_max_length": 131072,
2064
+ "pad_token": "<|eot_id|>",
2065
+ "padding_side": "right",
2066
+ "split_special_tokens": false,
2067
+ "tokenizer_class": "PreTrainedTokenizer"
2068
+ }
train_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 4.0,
3
+ "num_input_tokens_seen": 300000,
4
+ "total_flos": 1780328448000000.0,
5
+ "train_loss": 0.7932832451101314,
6
+ "train_runtime": 895.9422,
7
+ "train_samples_per_second": 6.652,
8
+ "train_steps_per_second": 0.42
9
+ }
trainer_log.jsonl ADDED
@@ -0,0 +1,79 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {"current_steps": 5, "total_steps": 376, "loss": 1.1748, "lr": 1.9994415637302545e-05, "epoch": 0.053691275167785234, "percentage": 1.33, "elapsed_time": "0:00:15", "remaining_time": "0:19:07", "throughput": 263.9, "total_tokens": 4080}
2
+ {"current_steps": 10, "total_steps": 376, "loss": 1.2634, "lr": 1.9971739852847514e-05, "epoch": 0.10738255033557047, "percentage": 2.66, "elapsed_time": "0:00:26", "remaining_time": "0:16:10", "throughput": 304.64, "total_tokens": 8080}
3
+ {"current_steps": 15, "total_steps": 376, "loss": 1.4367, "lr": 1.9931663163249744e-05, "epoch": 0.1610738255033557, "percentage": 3.99, "elapsed_time": "0:00:38", "remaining_time": "0:15:27", "throughput": 315.4, "total_tokens": 12160}
4
+ {"current_steps": 20, "total_steps": 376, "loss": 1.3167, "lr": 1.9874255503213154e-05, "epoch": 0.21476510067114093, "percentage": 5.32, "elapsed_time": "0:00:50", "remaining_time": "0:14:51", "throughput": 323.64, "total_tokens": 16208}
5
+ {"current_steps": 25, "total_steps": 376, "loss": 1.4144, "lr": 1.979961705036587e-05, "epoch": 0.2684563758389262, "percentage": 6.65, "elapsed_time": "0:01:02", "remaining_time": "0:14:33", "throughput": 325.7, "total_tokens": 20256}
6
+ {"current_steps": 30, "total_steps": 376, "loss": 1.3944, "lr": 1.9707878050448074e-05, "epoch": 0.3221476510067114, "percentage": 7.98, "elapsed_time": "0:01:13", "remaining_time": "0:14:05", "throughput": 331.6, "total_tokens": 24304}
7
+ {"current_steps": 35, "total_steps": 376, "loss": 1.3946, "lr": 1.9599198590030308e-05, "epoch": 0.37583892617449666, "percentage": 9.31, "elapsed_time": "0:01:24", "remaining_time": "0:13:46", "throughput": 334.75, "total_tokens": 28384}
8
+ {"current_steps": 40, "total_steps": 376, "loss": 1.3827, "lr": 1.947376831715892e-05, "epoch": 0.42953020134228187, "percentage": 10.64, "elapsed_time": "0:01:36", "remaining_time": "0:13:30", "throughput": 336.48, "total_tokens": 32480}
9
+ {"current_steps": 45, "total_steps": 376, "loss": 1.4509, "lr": 1.9331806110416027e-05, "epoch": 0.48322147651006714, "percentage": 11.97, "elapsed_time": "0:01:48", "remaining_time": "0:13:20", "throughput": 336.58, "total_tokens": 36608}
10
+ {"current_steps": 50, "total_steps": 376, "loss": 1.3347, "lr": 1.9173559696971594e-05, "epoch": 0.5369127516778524, "percentage": 13.3, "elapsed_time": "0:02:01", "remaining_time": "0:13:08", "throughput": 335.59, "total_tokens": 40608}
11
+ {"current_steps": 55, "total_steps": 376, "loss": 1.3834, "lr": 1.899930522029408e-05, "epoch": 0.5906040268456376, "percentage": 14.63, "elapsed_time": "0:02:13", "remaining_time": "0:12:57", "throughput": 335.37, "total_tokens": 44672}
12
+ {"current_steps": 60, "total_steps": 376, "loss": 1.4679, "lr": 1.8809346758274014e-05, "epoch": 0.6442953020134228, "percentage": 15.96, "elapsed_time": "0:02:25", "remaining_time": "0:12:44", "throughput": 335.6, "total_tokens": 48704}
13
+ {"current_steps": 65, "total_steps": 376, "loss": 1.3973, "lr": 1.8604015792601395e-05, "epoch": 0.697986577181208, "percentage": 17.29, "elapsed_time": "0:02:36", "remaining_time": "0:12:30", "throughput": 336.68, "total_tokens": 52832}
14
+ {"current_steps": 70, "total_steps": 376, "loss": 1.5408, "lr": 1.8383670630322864e-05, "epoch": 0.7516778523489933, "percentage": 18.62, "elapsed_time": "0:02:49", "remaining_time": "0:12:19", "throughput": 335.03, "total_tokens": 56672}
15
+ {"current_steps": 75, "total_steps": 376, "loss": 1.4967, "lr": 1.8148695778588034e-05, "epoch": 0.8053691275167785, "percentage": 19.95, "elapsed_time": "0:03:00", "remaining_time": "0:12:04", "throughput": 335.55, "total_tokens": 60608}
16
+ {"current_steps": 80, "total_steps": 376, "loss": 1.4644, "lr": 1.789950127367606e-05, "epoch": 0.8590604026845637, "percentage": 21.28, "elapsed_time": "0:03:12", "remaining_time": "0:11:51", "throughput": 336.3, "total_tokens": 64640}
17
+ {"current_steps": 85, "total_steps": 376, "loss": 1.4226, "lr": 1.7636521965473324e-05, "epoch": 0.912751677852349, "percentage": 22.61, "elapsed_time": "0:03:24", "remaining_time": "0:11:38", "throughput": 336.02, "total_tokens": 68560}
18
+ {"current_steps": 90, "total_steps": 376, "loss": 1.4847, "lr": 1.7360216758650826e-05, "epoch": 0.9664429530201343, "percentage": 23.94, "elapsed_time": "0:03:35", "remaining_time": "0:11:25", "throughput": 336.26, "total_tokens": 72512}
19
+ {"current_steps": 95, "total_steps": 376, "loss": 1.2927, "lr": 1.7071067811865477e-05, "epoch": 1.010738255033557, "percentage": 25.27, "elapsed_time": "0:03:45", "remaining_time": "0:11:05", "throughput": 336.91, "total_tokens": 75808}
20
+ {"current_steps": 100, "total_steps": 376, "loss": 0.8505, "lr": 1.67695796963826e-05, "epoch": 1.0644295302013422, "percentage": 26.6, "elapsed_time": "0:03:55", "remaining_time": "0:10:51", "throughput": 338.48, "total_tokens": 79840}
21
+ {"current_steps": 100, "total_steps": 376, "eval_loss": 2.885671615600586, "epoch": 1.0644295302013422, "percentage": 26.6, "elapsed_time": "0:04:09", "remaining_time": "0:11:27", "throughput": 320.58, "total_tokens": 79840}
22
+ {"current_steps": 105, "total_steps": 376, "loss": 0.7497, "lr": 1.6456278515588023e-05, "epoch": 1.1181208053691276, "percentage": 27.93, "elapsed_time": "0:04:23", "remaining_time": "0:11:20", "throughput": 318.1, "total_tokens": 83840}
23
+ {"current_steps": 110, "total_steps": 376, "loss": 0.7761, "lr": 1.613171098692611e-05, "epoch": 1.1718120805369128, "percentage": 29.26, "elapsed_time": "0:04:34", "remaining_time": "0:11:04", "throughput": 319.79, "total_tokens": 87872}
24
+ {"current_steps": 115, "total_steps": 376, "loss": 0.7997, "lr": 1.5796443487865774e-05, "epoch": 1.225503355704698, "percentage": 30.59, "elapsed_time": "0:04:46", "remaining_time": "0:10:49", "throughput": 321.09, "total_tokens": 91888}
25
+ {"current_steps": 120, "total_steps": 376, "loss": 0.8275, "lr": 1.54510610675594e-05, "epoch": 1.279194630872483, "percentage": 31.91, "elapsed_time": "0:04:57", "remaining_time": "0:10:35", "throughput": 322.08, "total_tokens": 95888}
26
+ {"current_steps": 125, "total_steps": 376, "loss": 0.8599, "lr": 1.5096166425919176e-05, "epoch": 1.3328859060402685, "percentage": 33.24, "elapsed_time": "0:05:09", "remaining_time": "0:10:21", "throughput": 322.83, "total_tokens": 99888}
27
+ {"current_steps": 130, "total_steps": 376, "loss": 0.9179, "lr": 1.4732378861892524e-05, "epoch": 1.3865771812080536, "percentage": 34.57, "elapsed_time": "0:05:21", "remaining_time": "0:10:07", "throughput": 323.42, "total_tokens": 103840}
28
+ {"current_steps": 135, "total_steps": 376, "loss": 0.8255, "lr": 1.436033319277183e-05, "epoch": 1.440268456375839, "percentage": 35.9, "elapsed_time": "0:05:32", "remaining_time": "0:09:53", "throughput": 324.25, "total_tokens": 107824}
29
+ {"current_steps": 140, "total_steps": 376, "loss": 0.8806, "lr": 1.3980678646424308e-05, "epoch": 1.4939597315436242, "percentage": 37.23, "elapsed_time": "0:05:43", "remaining_time": "0:09:39", "throughput": 325.46, "total_tokens": 111936}
30
+ {"current_steps": 145, "total_steps": 376, "loss": 0.8366, "lr": 1.3594077728375129e-05, "epoch": 1.5476510067114093, "percentage": 38.56, "elapsed_time": "0:05:55", "remaining_time": "0:09:26", "throughput": 326.15, "total_tokens": 115952}
31
+ {"current_steps": 150, "total_steps": 376, "loss": 0.8567, "lr": 1.3201205065720699e-05, "epoch": 1.6013422818791945, "percentage": 39.89, "elapsed_time": "0:06:06", "remaining_time": "0:09:12", "throughput": 327.21, "total_tokens": 119984}
32
+ {"current_steps": 155, "total_steps": 376, "loss": 0.8939, "lr": 1.2802746229889563e-05, "epoch": 1.6550335570469799, "percentage": 41.22, "elapsed_time": "0:06:17", "remaining_time": "0:08:58", "throughput": 328.25, "total_tokens": 124032}
33
+ {"current_steps": 160, "total_steps": 376, "loss": 0.965, "lr": 1.2399396540305205e-05, "epoch": 1.7087248322147652, "percentage": 42.55, "elapsed_time": "0:06:28", "remaining_time": "0:08:44", "throughput": 329.28, "total_tokens": 128000}
34
+ {"current_steps": 165, "total_steps": 376, "loss": 0.8915, "lr": 1.1991859851038362e-05, "epoch": 1.7624161073825504, "percentage": 43.88, "elapsed_time": "0:06:39", "remaining_time": "0:08:31", "throughput": 330.41, "total_tokens": 132096}
35
+ {"current_steps": 170, "total_steps": 376, "loss": 0.9085, "lr": 1.1580847322566224e-05, "epoch": 1.8161073825503355, "percentage": 45.21, "elapsed_time": "0:06:50", "remaining_time": "0:08:17", "throughput": 331.65, "total_tokens": 136208}
36
+ {"current_steps": 175, "total_steps": 376, "loss": 0.8831, "lr": 1.1167076180781764e-05, "epoch": 1.8697986577181207, "percentage": 46.54, "elapsed_time": "0:07:01", "remaining_time": "0:08:04", "throughput": 332.58, "total_tokens": 140320}
37
+ {"current_steps": 180, "total_steps": 376, "loss": 1.0271, "lr": 1.0751268465418784e-05, "epoch": 1.923489932885906, "percentage": 47.87, "elapsed_time": "0:07:13", "remaining_time": "0:07:52", "throughput": 332.56, "total_tokens": 144176}
38
+ {"current_steps": 185, "total_steps": 376, "loss": 0.9636, "lr": 1.0334149770076747e-05, "epoch": 1.9771812080536912, "percentage": 49.2, "elapsed_time": "0:07:24", "remaining_time": "0:07:39", "throughput": 333.29, "total_tokens": 148256}
39
+ {"current_steps": 190, "total_steps": 376, "loss": 0.7085, "lr": 9.916447976043972e-06, "epoch": 2.021476510067114, "percentage": 50.53, "elapsed_time": "0:07:34", "remaining_time": "0:07:24", "throughput": 333.3, "total_tokens": 151488}
40
+ {"current_steps": 195, "total_steps": 376, "loss": 0.5186, "lr": 9.498891982128809e-06, "epoch": 2.0751677852348993, "percentage": 51.86, "elapsed_time": "0:07:45", "remaining_time": "0:07:12", "throughput": 333.84, "total_tokens": 155472}
41
+ {"current_steps": 200, "total_steps": 376, "loss": 0.5023, "lr": 9.082210432715197e-06, "epoch": 2.1288590604026845, "percentage": 53.19, "elapsed_time": "0:07:56", "remaining_time": "0:06:59", "throughput": 334.41, "total_tokens": 159504}
42
+ {"current_steps": 200, "total_steps": 376, "eval_loss": 3.4170751571655273, "epoch": 2.1288590604026845, "percentage": 53.19, "elapsed_time": "0:08:10", "remaining_time": "0:07:11", "throughput": 324.96, "total_tokens": 159504}
43
+ {"current_steps": 205, "total_steps": 376, "loss": 0.5145, "lr": 8.667130446262214e-06, "epoch": 2.1825503355704696, "percentage": 54.52, "elapsed_time": "0:08:25", "remaining_time": "0:07:01", "throughput": 323.15, "total_tokens": 163472}
44
+ {"current_steps": 210, "total_steps": 376, "loss": 0.4971, "lr": 8.25437634646637e-06, "epoch": 2.2362416107382552, "percentage": 55.85, "elapsed_time": "0:08:37", "remaining_time": "0:06:49", "throughput": 323.77, "total_tokens": 167584}
45
+ {"current_steps": 215, "total_steps": 376, "loss": 0.5042, "lr": 7.844668398300866e-06, "epoch": 2.2899328859060404, "percentage": 57.18, "elapsed_time": "0:08:48", "remaining_time": "0:06:35", "throughput": 324.87, "total_tokens": 171712}
46
+ {"current_steps": 220, "total_steps": 376, "loss": 0.5423, "lr": 7.438721551137367e-06, "epoch": 2.3436241610738255, "percentage": 58.51, "elapsed_time": "0:08:59", "remaining_time": "0:06:22", "throughput": 325.53, "total_tokens": 175696}
47
+ {"current_steps": 225, "total_steps": 376, "loss": 0.5913, "lr": 7.037244191143662e-06, "epoch": 2.3973154362416107, "percentage": 59.84, "elapsed_time": "0:09:11", "remaining_time": "0:06:10", "throughput": 325.95, "total_tokens": 179728}
48
+ {"current_steps": 230, "total_steps": 376, "loss": 0.5403, "lr": 6.640936905134212e-06, "epoch": 2.451006711409396, "percentage": 61.17, "elapsed_time": "0:09:23", "remaining_time": "0:05:57", "throughput": 326.13, "total_tokens": 183648}
49
+ {"current_steps": 235, "total_steps": 376, "loss": 0.5301, "lr": 6.2504912580307905e-06, "epoch": 2.504697986577181, "percentage": 62.5, "elapsed_time": "0:09:34", "remaining_time": "0:05:44", "throughput": 326.79, "total_tokens": 187664}
50
+ {"current_steps": 240, "total_steps": 376, "loss": 0.5417, "lr": 5.866588586066481e-06, "epoch": 2.558389261744966, "percentage": 63.83, "elapsed_time": "0:09:45", "remaining_time": "0:05:31", "throughput": 327.37, "total_tokens": 191776}
51
+ {"current_steps": 245, "total_steps": 376, "loss": 0.5358, "lr": 5.48989880783898e-06, "epoch": 2.6120805369127518, "percentage": 65.16, "elapsed_time": "0:09:57", "remaining_time": "0:05:19", "throughput": 327.79, "total_tokens": 195872}
52
+ {"current_steps": 250, "total_steps": 376, "loss": 0.5249, "lr": 5.121079255287953e-06, "epoch": 2.665771812080537, "percentage": 66.49, "elapsed_time": "0:10:08", "remaining_time": "0:05:06", "throughput": 328.11, "total_tokens": 199808}
53
+ {"current_steps": 255, "total_steps": 376, "loss": 0.5134, "lr": 4.760773526636315e-06, "epoch": 2.719463087248322, "percentage": 67.82, "elapsed_time": "0:10:20", "remaining_time": "0:04:54", "throughput": 328.62, "total_tokens": 203888}
54
+ {"current_steps": 260, "total_steps": 376, "loss": 0.516, "lr": 4.409610363297211e-06, "epoch": 2.7731543624161072, "percentage": 69.15, "elapsed_time": "0:10:32", "remaining_time": "0:04:42", "throughput": 328.73, "total_tokens": 207840}
55
+ {"current_steps": 265, "total_steps": 376, "loss": 0.5611, "lr": 4.0682025527064486e-06, "epoch": 2.826845637583893, "percentage": 70.48, "elapsed_time": "0:10:43", "remaining_time": "0:04:29", "throughput": 329.02, "total_tokens": 211856}
56
+ {"current_steps": 270, "total_steps": 376, "loss": 0.5084, "lr": 3.7371458589949337e-06, "epoch": 2.880536912751678, "percentage": 71.81, "elapsed_time": "0:10:54", "remaining_time": "0:04:16", "throughput": 329.85, "total_tokens": 215904}
57
+ {"current_steps": 275, "total_steps": 376, "loss": 0.5458, "lr": 3.4170179833671847e-06, "epoch": 2.934228187919463, "percentage": 73.14, "elapsed_time": "0:11:05", "remaining_time": "0:04:04", "throughput": 330.35, "total_tokens": 219856}
58
+ {"current_steps": 280, "total_steps": 376, "loss": 0.5205, "lr": 3.1083775560000373e-06, "epoch": 2.9879194630872483, "percentage": 74.47, "elapsed_time": "0:11:15", "remaining_time": "0:03:51", "throughput": 331.42, "total_tokens": 223984}
59
+ {"current_steps": 285, "total_steps": 376, "loss": 0.4058, "lr": 2.8117631612207084e-06, "epoch": 3.032214765100671, "percentage": 75.8, "elapsed_time": "0:11:24", "remaining_time": "0:03:38", "throughput": 332.17, "total_tokens": 227440}
60
+ {"current_steps": 290, "total_steps": 376, "loss": 0.3859, "lr": 2.527692397665311e-06, "epoch": 3.085906040268456, "percentage": 77.13, "elapsed_time": "0:11:36", "remaining_time": "0:03:26", "throughput": 332.42, "total_tokens": 231424}
61
+ {"current_steps": 295, "total_steps": 376, "loss": 0.3724, "lr": 2.256660975057867e-06, "epoch": 3.1395973154362418, "percentage": 78.46, "elapsed_time": "0:11:46", "remaining_time": "0:03:13", "throughput": 333.25, "total_tokens": 235456}
62
+ {"current_steps": 300, "total_steps": 376, "loss": 0.3916, "lr": 1.9991418491859383e-06, "epoch": 3.193288590604027, "percentage": 79.79, "elapsed_time": "0:11:57", "remaining_time": "0:03:01", "throughput": 333.86, "total_tokens": 239424}
63
+ {"current_steps": 300, "total_steps": 376, "eval_loss": 3.5844736099243164, "epoch": 3.193288590604027, "percentage": 79.79, "elapsed_time": "0:12:09", "remaining_time": "0:03:04", "throughput": 328.08, "total_tokens": 239424}
64
+ {"current_steps": 305, "total_steps": 376, "loss": 0.3676, "lr": 1.7555843965823992e-06, "epoch": 3.246979865771812, "percentage": 81.12, "elapsed_time": "0:12:23", "remaining_time": "0:02:53", "throughput": 327.35, "total_tokens": 243488}
65
+ {"current_steps": 310, "total_steps": 376, "loss": 0.3798, "lr": 1.5264136303534893e-06, "epoch": 3.3006711409395972, "percentage": 82.45, "elapsed_time": "0:12:35", "remaining_time": "0:02:40", "throughput": 327.69, "total_tokens": 247456}
66
+ {"current_steps": 315, "total_steps": 376, "loss": 0.3606, "lr": 1.3120294585216353e-06, "epoch": 3.3543624161073824, "percentage": 83.78, "elapsed_time": "0:12:45", "remaining_time": "0:02:28", "throughput": 328.4, "total_tokens": 251456}
67
+ {"current_steps": 320, "total_steps": 376, "loss": 0.3938, "lr": 1.11280598617714e-06, "epoch": 3.4080536912751676, "percentage": 85.11, "elapsed_time": "0:12:56", "remaining_time": "0:02:15", "throughput": 329.0, "total_tokens": 255504}
68
+ {"current_steps": 325, "total_steps": 376, "loss": 0.3605, "lr": 9.290908626565931e-07, "epoch": 3.461744966442953, "percentage": 86.44, "elapsed_time": "0:13:07", "remaining_time": "0:02:03", "throughput": 329.68, "total_tokens": 259472}
69
+ {"current_steps": 330, "total_steps": 376, "loss": 0.3781, "lr": 7.612046748871327e-07, "epoch": 3.5154362416107383, "percentage": 87.77, "elapsed_time": "0:13:17", "remaining_time": "0:01:51", "throughput": 330.66, "total_tokens": 263536}
70
+ {"current_steps": 335, "total_steps": 376, "loss": 0.3794, "lr": 6.094403879552213e-07, "epoch": 3.5691275167785235, "percentage": 89.1, "elapsed_time": "0:13:27", "remaining_time": "0:01:38", "throughput": 331.22, "total_tokens": 267584}
71
+ {"current_steps": 340, "total_steps": 376, "loss": 0.3526, "lr": 4.740628338761255e-07, "epoch": 3.6228187919463086, "percentage": 90.43, "elapsed_time": "0:13:37", "remaining_time": "0:01:26", "throughput": 332.12, "total_tokens": 271664}
72
+ {"current_steps": 345, "total_steps": 376, "loss": 0.3846, "lr": 3.553082494562354e-07, "epoch": 3.6765100671140942, "percentage": 91.76, "elapsed_time": "0:13:48", "remaining_time": "0:01:14", "throughput": 332.56, "total_tokens": 275664}
73
+ {"current_steps": 350, "total_steps": 376, "loss": 0.3855, "lr": 2.533838640546438e-07, "epoch": 3.7302013422818794, "percentage": 93.09, "elapsed_time": "0:13:59", "remaining_time": "0:01:02", "throughput": 333.19, "total_tokens": 279648}
74
+ {"current_steps": 355, "total_steps": 376, "loss": 0.3955, "lr": 1.6846753796336491e-07, "epoch": 3.7838926174496645, "percentage": 94.41, "elapsed_time": "0:14:09", "remaining_time": "0:00:50", "throughput": 333.69, "total_tokens": 283600}
75
+ {"current_steps": 360, "total_steps": 376, "loss": 0.34, "lr": 1.0070745203721532e-07, "epoch": 3.8375838926174497, "percentage": 95.74, "elapsed_time": "0:14:20", "remaining_time": "0:00:38", "throughput": 334.24, "total_tokens": 287600}
76
+ {"current_steps": 365, "total_steps": 376, "loss": 0.3584, "lr": 5.022184911495864e-08, "epoch": 3.891275167785235, "percentage": 97.07, "elapsed_time": "0:14:30", "remaining_time": "0:00:26", "throughput": 334.96, "total_tokens": 291712}
77
+ {"current_steps": 370, "total_steps": 376, "loss": 0.3608, "lr": 1.7098827682970885e-08, "epoch": 3.94496644295302, "percentage": 98.4, "elapsed_time": "0:14:41", "remaining_time": "0:00:14", "throughput": 335.57, "total_tokens": 295856}
78
+ {"current_steps": 375, "total_steps": 376, "loss": 0.3659, "lr": 1.3961881414292776e-09, "epoch": 3.998657718120805, "percentage": 99.73, "elapsed_time": "0:14:52", "remaining_time": "0:00:02", "throughput": 336.16, "total_tokens": 299904}
79
+ {"current_steps": 376, "total_steps": 376, "epoch": 4.0, "percentage": 100.0, "elapsed_time": "0:14:55", "remaining_time": "0:00:00", "throughput": 334.85, "total_tokens": 300000}
trainer_state.json ADDED
@@ -0,0 +1,821 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 4.0,
6
+ "eval_steps": 100,
7
+ "global_step": 376,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.053691275167785234,
14
+ "grad_norm": 8.373551368713379,
15
+ "learning_rate": 1.9994415637302545e-05,
16
+ "loss": 1.1748,
17
+ "num_input_tokens_seen": 4080,
18
+ "step": 5,
19
+ "train_runtime": 15.4659,
20
+ "train_tokens_per_second": 263.806
21
+ },
22
+ {
23
+ "epoch": 0.10738255033557047,
24
+ "grad_norm": 6.174284934997559,
25
+ "learning_rate": 1.9971739852847514e-05,
26
+ "loss": 1.2634,
27
+ "num_input_tokens_seen": 8080,
28
+ "step": 10,
29
+ "train_runtime": 26.529,
30
+ "train_tokens_per_second": 304.572
31
+ },
32
+ {
33
+ "epoch": 0.1610738255033557,
34
+ "grad_norm": 8.544853210449219,
35
+ "learning_rate": 1.9931663163249744e-05,
36
+ "loss": 1.4367,
37
+ "num_input_tokens_seen": 12160,
38
+ "step": 15,
39
+ "train_runtime": 38.5597,
40
+ "train_tokens_per_second": 315.355
41
+ },
42
+ {
43
+ "epoch": 0.21476510067114093,
44
+ "grad_norm": 7.589258193969727,
45
+ "learning_rate": 1.9874255503213154e-05,
46
+ "loss": 1.3167,
47
+ "num_input_tokens_seen": 16208,
48
+ "step": 20,
49
+ "train_runtime": 50.0852,
50
+ "train_tokens_per_second": 323.609
51
+ },
52
+ {
53
+ "epoch": 0.2684563758389262,
54
+ "grad_norm": 8.169995307922363,
55
+ "learning_rate": 1.979961705036587e-05,
56
+ "loss": 1.4144,
57
+ "num_input_tokens_seen": 20256,
58
+ "step": 25,
59
+ "train_runtime": 62.1983,
60
+ "train_tokens_per_second": 325.668
61
+ },
62
+ {
63
+ "epoch": 0.3221476510067114,
64
+ "grad_norm": 8.032195091247559,
65
+ "learning_rate": 1.9707878050448074e-05,
66
+ "loss": 1.3944,
67
+ "num_input_tokens_seen": 24304,
68
+ "step": 30,
69
+ "train_runtime": 73.2989,
70
+ "train_tokens_per_second": 331.574
71
+ },
72
+ {
73
+ "epoch": 0.37583892617449666,
74
+ "grad_norm": 7.009624004364014,
75
+ "learning_rate": 1.9599198590030308e-05,
76
+ "loss": 1.3946,
77
+ "num_input_tokens_seen": 28384,
78
+ "step": 35,
79
+ "train_runtime": 84.7962,
80
+ "train_tokens_per_second": 334.732
81
+ },
82
+ {
83
+ "epoch": 0.42953020134228187,
84
+ "grad_norm": 7.077579498291016,
85
+ "learning_rate": 1.947376831715892e-05,
86
+ "loss": 1.3827,
87
+ "num_input_tokens_seen": 32480,
88
+ "step": 40,
89
+ "train_runtime": 96.5334,
90
+ "train_tokens_per_second": 336.464
91
+ },
92
+ {
93
+ "epoch": 0.48322147651006714,
94
+ "grad_norm": 6.77874755859375,
95
+ "learning_rate": 1.9331806110416027e-05,
96
+ "loss": 1.4509,
97
+ "num_input_tokens_seen": 36608,
98
+ "step": 45,
99
+ "train_runtime": 108.7688,
100
+ "train_tokens_per_second": 336.567
101
+ },
102
+ {
103
+ "epoch": 0.5369127516778524,
104
+ "grad_norm": 6.446975231170654,
105
+ "learning_rate": 1.9173559696971594e-05,
106
+ "loss": 1.3347,
107
+ "num_input_tokens_seen": 40608,
108
+ "step": 50,
109
+ "train_runtime": 121.0098,
110
+ "train_tokens_per_second": 335.576
111
+ },
112
+ {
113
+ "epoch": 0.5906040268456376,
114
+ "grad_norm": 7.034291744232178,
115
+ "learning_rate": 1.899930522029408e-05,
116
+ "loss": 1.3834,
117
+ "num_input_tokens_seen": 44672,
118
+ "step": 55,
119
+ "train_runtime": 133.2088,
120
+ "train_tokens_per_second": 335.353
121
+ },
122
+ {
123
+ "epoch": 0.6442953020134228,
124
+ "grad_norm": 6.512075424194336,
125
+ "learning_rate": 1.8809346758274014e-05,
126
+ "loss": 1.4679,
127
+ "num_input_tokens_seen": 48704,
128
+ "step": 60,
129
+ "train_runtime": 145.1301,
130
+ "train_tokens_per_second": 335.589
131
+ },
132
+ {
133
+ "epoch": 0.697986577181208,
134
+ "grad_norm": 5.968503475189209,
135
+ "learning_rate": 1.8604015792601395e-05,
136
+ "loss": 1.3973,
137
+ "num_input_tokens_seen": 52832,
138
+ "step": 65,
139
+ "train_runtime": 156.9248,
140
+ "train_tokens_per_second": 336.671
141
+ },
142
+ {
143
+ "epoch": 0.7516778523489933,
144
+ "grad_norm": 6.824077129364014,
145
+ "learning_rate": 1.8383670630322864e-05,
146
+ "loss": 1.5408,
147
+ "num_input_tokens_seen": 56672,
148
+ "step": 70,
149
+ "train_runtime": 169.159,
150
+ "train_tokens_per_second": 335.022
151
+ },
152
+ {
153
+ "epoch": 0.8053691275167785,
154
+ "grad_norm": 6.580747127532959,
155
+ "learning_rate": 1.8148695778588034e-05,
156
+ "loss": 1.4967,
157
+ "num_input_tokens_seen": 60608,
158
+ "step": 75,
159
+ "train_runtime": 180.627,
160
+ "train_tokens_per_second": 335.542
161
+ },
162
+ {
163
+ "epoch": 0.8590604026845637,
164
+ "grad_norm": 6.616082191467285,
165
+ "learning_rate": 1.789950127367606e-05,
166
+ "loss": 1.4644,
167
+ "num_input_tokens_seen": 64640,
168
+ "step": 80,
169
+ "train_runtime": 192.2131,
170
+ "train_tokens_per_second": 336.293
171
+ },
172
+ {
173
+ "epoch": 0.912751677852349,
174
+ "grad_norm": 6.736894607543945,
175
+ "learning_rate": 1.7636521965473324e-05,
176
+ "loss": 1.4226,
177
+ "num_input_tokens_seen": 68560,
178
+ "step": 85,
179
+ "train_runtime": 204.0434,
180
+ "train_tokens_per_second": 336.007
181
+ },
182
+ {
183
+ "epoch": 0.9664429530201343,
184
+ "grad_norm": 6.567346572875977,
185
+ "learning_rate": 1.7360216758650826e-05,
186
+ "loss": 1.4847,
187
+ "num_input_tokens_seen": 72512,
188
+ "step": 90,
189
+ "train_runtime": 215.6473,
190
+ "train_tokens_per_second": 336.253
191
+ },
192
+ {
193
+ "epoch": 1.010738255033557,
194
+ "grad_norm": 4.928441047668457,
195
+ "learning_rate": 1.7071067811865477e-05,
196
+ "loss": 1.2927,
197
+ "num_input_tokens_seen": 75808,
198
+ "step": 95,
199
+ "train_runtime": 225.0164,
200
+ "train_tokens_per_second": 336.9
201
+ },
202
+ {
203
+ "epoch": 1.0644295302013422,
204
+ "grad_norm": 5.473133087158203,
205
+ "learning_rate": 1.67695796963826e-05,
206
+ "loss": 0.8505,
207
+ "num_input_tokens_seen": 79840,
208
+ "step": 100,
209
+ "train_runtime": 235.8823,
210
+ "train_tokens_per_second": 338.474
211
+ },
212
+ {
213
+ "epoch": 1.0644295302013422,
214
+ "eval_loss": 2.885671615600586,
215
+ "eval_runtime": 13.1654,
216
+ "eval_samples_per_second": 28.332,
217
+ "eval_steps_per_second": 14.204,
218
+ "num_input_tokens_seen": 79840,
219
+ "step": 100
220
+ },
221
+ {
222
+ "epoch": 1.1181208053691276,
223
+ "grad_norm": 7.370046138763428,
224
+ "learning_rate": 1.6456278515588023e-05,
225
+ "loss": 0.7497,
226
+ "num_input_tokens_seen": 83840,
227
+ "step": 105,
228
+ "train_runtime": 263.568,
229
+ "train_tokens_per_second": 318.096
230
+ },
231
+ {
232
+ "epoch": 1.1718120805369128,
233
+ "grad_norm": 6.678887844085693,
234
+ "learning_rate": 1.613171098692611e-05,
235
+ "loss": 0.7761,
236
+ "num_input_tokens_seen": 87872,
237
+ "step": 110,
238
+ "train_runtime": 274.7842,
239
+ "train_tokens_per_second": 319.786
240
+ },
241
+ {
242
+ "epoch": 1.225503355704698,
243
+ "grad_norm": 5.9977707862854,
244
+ "learning_rate": 1.5796443487865774e-05,
245
+ "loss": 0.7997,
246
+ "num_input_tokens_seen": 91888,
247
+ "step": 115,
248
+ "train_runtime": 286.1784,
249
+ "train_tokens_per_second": 321.086
250
+ },
251
+ {
252
+ "epoch": 1.279194630872483,
253
+ "grad_norm": 6.782074451446533,
254
+ "learning_rate": 1.54510610675594e-05,
255
+ "loss": 0.8275,
256
+ "num_input_tokens_seen": 95888,
257
+ "step": 120,
258
+ "train_runtime": 297.7215,
259
+ "train_tokens_per_second": 322.073
260
+ },
261
+ {
262
+ "epoch": 1.3328859060402685,
263
+ "grad_norm": 6.483254909515381,
264
+ "learning_rate": 1.5096166425919176e-05,
265
+ "loss": 0.8599,
266
+ "num_input_tokens_seen": 99888,
267
+ "step": 125,
268
+ "train_runtime": 309.418,
269
+ "train_tokens_per_second": 322.825
270
+ },
271
+ {
272
+ "epoch": 1.3865771812080536,
273
+ "grad_norm": 6.478480815887451,
274
+ "learning_rate": 1.4732378861892524e-05,
275
+ "loss": 0.9179,
276
+ "num_input_tokens_seen": 103840,
277
+ "step": 130,
278
+ "train_runtime": 321.0761,
279
+ "train_tokens_per_second": 323.412
280
+ },
281
+ {
282
+ "epoch": 1.440268456375839,
283
+ "grad_norm": 5.326768398284912,
284
+ "learning_rate": 1.436033319277183e-05,
285
+ "loss": 0.8255,
286
+ "num_input_tokens_seen": 107824,
287
+ "step": 135,
288
+ "train_runtime": 332.5409,
289
+ "train_tokens_per_second": 324.243
290
+ },
291
+ {
292
+ "epoch": 1.4939597315436242,
293
+ "grad_norm": 5.588732719421387,
294
+ "learning_rate": 1.3980678646424308e-05,
295
+ "loss": 0.8806,
296
+ "num_input_tokens_seen": 111936,
297
+ "step": 140,
298
+ "train_runtime": 343.9421,
299
+ "train_tokens_per_second": 325.45
300
+ },
301
+ {
302
+ "epoch": 1.5476510067114093,
303
+ "grad_norm": 4.919476509094238,
304
+ "learning_rate": 1.3594077728375129e-05,
305
+ "loss": 0.8366,
306
+ "num_input_tokens_seen": 115952,
307
+ "step": 145,
308
+ "train_runtime": 355.5203,
309
+ "train_tokens_per_second": 326.147
310
+ },
311
+ {
312
+ "epoch": 1.6013422818791945,
313
+ "grad_norm": 5.641396522521973,
314
+ "learning_rate": 1.3201205065720699e-05,
315
+ "loss": 0.8567,
316
+ "num_input_tokens_seen": 119984,
317
+ "step": 150,
318
+ "train_runtime": 366.6895,
319
+ "train_tokens_per_second": 327.209
320
+ },
321
+ {
322
+ "epoch": 1.6550335570469799,
323
+ "grad_norm": 6.353975296020508,
324
+ "learning_rate": 1.2802746229889563e-05,
325
+ "loss": 0.8939,
326
+ "num_input_tokens_seen": 124032,
327
+ "step": 155,
328
+ "train_runtime": 377.8594,
329
+ "train_tokens_per_second": 328.249
330
+ },
331
+ {
332
+ "epoch": 1.7087248322147652,
333
+ "grad_norm": 6.592543125152588,
334
+ "learning_rate": 1.2399396540305205e-05,
335
+ "loss": 0.965,
336
+ "num_input_tokens_seen": 128000,
337
+ "step": 160,
338
+ "train_runtime": 388.7376,
339
+ "train_tokens_per_second": 329.271
340
+ },
341
+ {
342
+ "epoch": 1.7624161073825504,
343
+ "grad_norm": 6.394205570220947,
344
+ "learning_rate": 1.1991859851038362e-05,
345
+ "loss": 0.8915,
346
+ "num_input_tokens_seen": 132096,
347
+ "step": 165,
348
+ "train_runtime": 399.8008,
349
+ "train_tokens_per_second": 330.405
350
+ },
351
+ {
352
+ "epoch": 1.8161073825503355,
353
+ "grad_norm": 6.431347846984863,
354
+ "learning_rate": 1.1580847322566224e-05,
355
+ "loss": 0.9085,
356
+ "num_input_tokens_seen": 136208,
357
+ "step": 170,
358
+ "train_runtime": 410.7015,
359
+ "train_tokens_per_second": 331.647
360
+ },
361
+ {
362
+ "epoch": 1.8697986577181207,
363
+ "grad_norm": 6.055410385131836,
364
+ "learning_rate": 1.1167076180781764e-05,
365
+ "loss": 0.8831,
366
+ "num_input_tokens_seen": 140320,
367
+ "step": 175,
368
+ "train_runtime": 421.922,
369
+ "train_tokens_per_second": 332.573
370
+ },
371
+ {
372
+ "epoch": 1.923489932885906,
373
+ "grad_norm": 6.936720848083496,
374
+ "learning_rate": 1.0751268465418784e-05,
375
+ "loss": 1.0271,
376
+ "num_input_tokens_seen": 144176,
377
+ "step": 180,
378
+ "train_runtime": 433.5402,
379
+ "train_tokens_per_second": 332.555
380
+ },
381
+ {
382
+ "epoch": 1.9771812080536912,
383
+ "grad_norm": 6.763705253601074,
384
+ "learning_rate": 1.0334149770076747e-05,
385
+ "loss": 0.9636,
386
+ "num_input_tokens_seen": 148256,
387
+ "step": 185,
388
+ "train_runtime": 444.8309,
389
+ "train_tokens_per_second": 333.286
390
+ },
391
+ {
392
+ "epoch": 2.021476510067114,
393
+ "grad_norm": 3.6498420238494873,
394
+ "learning_rate": 9.916447976043972e-06,
395
+ "loss": 0.7085,
396
+ "num_input_tokens_seen": 151488,
397
+ "step": 190,
398
+ "train_runtime": 454.5144,
399
+ "train_tokens_per_second": 333.296
400
+ },
401
+ {
402
+ "epoch": 2.0751677852348993,
403
+ "grad_norm": 4.591700553894043,
404
+ "learning_rate": 9.498891982128809e-06,
405
+ "loss": 0.5186,
406
+ "num_input_tokens_seen": 155472,
407
+ "step": 195,
408
+ "train_runtime": 465.7186,
409
+ "train_tokens_per_second": 333.832
410
+ },
411
+ {
412
+ "epoch": 2.1288590604026845,
413
+ "grad_norm": 5.094573497772217,
414
+ "learning_rate": 9.082210432715197e-06,
415
+ "loss": 0.5023,
416
+ "num_input_tokens_seen": 159504,
417
+ "step": 200,
418
+ "train_runtime": 476.9786,
419
+ "train_tokens_per_second": 334.405
420
+ },
421
+ {
422
+ "epoch": 2.1288590604026845,
423
+ "eval_loss": 3.4170751571655273,
424
+ "eval_runtime": 13.8611,
425
+ "eval_samples_per_second": 26.91,
426
+ "eval_steps_per_second": 13.491,
427
+ "num_input_tokens_seen": 159504,
428
+ "step": 200
429
+ },
430
+ {
431
+ "epoch": 2.1825503355704696,
432
+ "grad_norm": 5.766697406768799,
433
+ "learning_rate": 8.667130446262214e-06,
434
+ "loss": 0.5145,
435
+ "num_input_tokens_seen": 163472,
436
+ "step": 205,
437
+ "train_runtime": 505.879,
438
+ "train_tokens_per_second": 323.144
439
+ },
440
+ {
441
+ "epoch": 2.2362416107382552,
442
+ "grad_norm": 4.821939945220947,
443
+ "learning_rate": 8.25437634646637e-06,
444
+ "loss": 0.4971,
445
+ "num_input_tokens_seen": 167584,
446
+ "step": 210,
447
+ "train_runtime": 517.6135,
448
+ "train_tokens_per_second": 323.763
449
+ },
450
+ {
451
+ "epoch": 2.2899328859060404,
452
+ "grad_norm": 5.04258394241333,
453
+ "learning_rate": 7.844668398300866e-06,
454
+ "loss": 0.5042,
455
+ "num_input_tokens_seen": 171712,
456
+ "step": 215,
457
+ "train_runtime": 528.5686,
458
+ "train_tokens_per_second": 324.862
459
+ },
460
+ {
461
+ "epoch": 2.3436241610738255,
462
+ "grad_norm": 3.9442596435546875,
463
+ "learning_rate": 7.438721551137367e-06,
464
+ "loss": 0.5423,
465
+ "num_input_tokens_seen": 175696,
466
+ "step": 220,
467
+ "train_runtime": 539.7243,
468
+ "train_tokens_per_second": 325.529
469
+ },
470
+ {
471
+ "epoch": 2.3973154362416107,
472
+ "grad_norm": 4.744536399841309,
473
+ "learning_rate": 7.037244191143662e-06,
474
+ "loss": 0.5913,
475
+ "num_input_tokens_seen": 179728,
476
+ "step": 225,
477
+ "train_runtime": 551.4106,
478
+ "train_tokens_per_second": 325.942
479
+ },
480
+ {
481
+ "epoch": 2.451006711409396,
482
+ "grad_norm": 3.8527259826660156,
483
+ "learning_rate": 6.640936905134212e-06,
484
+ "loss": 0.5403,
485
+ "num_input_tokens_seen": 183648,
486
+ "step": 230,
487
+ "train_runtime": 563.1128,
488
+ "train_tokens_per_second": 326.13
489
+ },
490
+ {
491
+ "epoch": 2.504697986577181,
492
+ "grad_norm": 5.313571453094482,
493
+ "learning_rate": 6.2504912580307905e-06,
494
+ "loss": 0.5301,
495
+ "num_input_tokens_seen": 187664,
496
+ "step": 235,
497
+ "train_runtime": 574.2745,
498
+ "train_tokens_per_second": 326.784
499
+ },
500
+ {
501
+ "epoch": 2.558389261744966,
502
+ "grad_norm": 4.798688888549805,
503
+ "learning_rate": 5.866588586066481e-06,
504
+ "loss": 0.5417,
505
+ "num_input_tokens_seen": 191776,
506
+ "step": 240,
507
+ "train_runtime": 585.8109,
508
+ "train_tokens_per_second": 327.368
509
+ },
510
+ {
511
+ "epoch": 2.6120805369127518,
512
+ "grad_norm": 4.535137176513672,
513
+ "learning_rate": 5.48989880783898e-06,
514
+ "loss": 0.5358,
515
+ "num_input_tokens_seen": 195872,
516
+ "step": 245,
517
+ "train_runtime": 597.5628,
518
+ "train_tokens_per_second": 327.785
519
+ },
520
+ {
521
+ "epoch": 2.665771812080537,
522
+ "grad_norm": 4.101404666900635,
523
+ "learning_rate": 5.121079255287953e-06,
524
+ "loss": 0.5249,
525
+ "num_input_tokens_seen": 199808,
526
+ "step": 250,
527
+ "train_runtime": 608.9706,
528
+ "train_tokens_per_second": 328.108
529
+ },
530
+ {
531
+ "epoch": 2.719463087248322,
532
+ "grad_norm": 4.927453994750977,
533
+ "learning_rate": 4.760773526636315e-06,
534
+ "loss": 0.5134,
535
+ "num_input_tokens_seen": 203888,
536
+ "step": 255,
537
+ "train_runtime": 620.4402,
538
+ "train_tokens_per_second": 328.618
539
+ },
540
+ {
541
+ "epoch": 2.7731543624161072,
542
+ "grad_norm": 4.203514575958252,
543
+ "learning_rate": 4.409610363297211e-06,
544
+ "loss": 0.516,
545
+ "num_input_tokens_seen": 207840,
546
+ "step": 260,
547
+ "train_runtime": 632.2498,
548
+ "train_tokens_per_second": 328.731
549
+ },
550
+ {
551
+ "epoch": 2.826845637583893,
552
+ "grad_norm": 3.7994656562805176,
553
+ "learning_rate": 4.0682025527064486e-06,
554
+ "loss": 0.5611,
555
+ "num_input_tokens_seen": 211856,
556
+ "step": 265,
557
+ "train_runtime": 643.9121,
558
+ "train_tokens_per_second": 329.014
559
+ },
560
+ {
561
+ "epoch": 2.880536912751678,
562
+ "grad_norm": 4.413597583770752,
563
+ "learning_rate": 3.7371458589949337e-06,
564
+ "loss": 0.5084,
565
+ "num_input_tokens_seen": 215904,
566
+ "step": 270,
567
+ "train_runtime": 654.5637,
568
+ "train_tokens_per_second": 329.844
569
+ },
570
+ {
571
+ "epoch": 2.934228187919463,
572
+ "grad_norm": 4.6744384765625,
573
+ "learning_rate": 3.4170179833671847e-06,
574
+ "loss": 0.5458,
575
+ "num_input_tokens_seen": 219856,
576
+ "step": 275,
577
+ "train_runtime": 665.522,
578
+ "train_tokens_per_second": 330.351
579
+ },
580
+ {
581
+ "epoch": 2.9879194630872483,
582
+ "grad_norm": 4.479729652404785,
583
+ "learning_rate": 3.1083775560000373e-06,
584
+ "loss": 0.5205,
585
+ "num_input_tokens_seen": 223984,
586
+ "step": 280,
587
+ "train_runtime": 675.8425,
588
+ "train_tokens_per_second": 331.414
589
+ },
590
+ {
591
+ "epoch": 3.032214765100671,
592
+ "grad_norm": 2.398268938064575,
593
+ "learning_rate": 2.8117631612207084e-06,
594
+ "loss": 0.4058,
595
+ "num_input_tokens_seen": 227440,
596
+ "step": 285,
597
+ "train_runtime": 684.7066,
598
+ "train_tokens_per_second": 332.171
599
+ },
600
+ {
601
+ "epoch": 3.085906040268456,
602
+ "grad_norm": 2.7196109294891357,
603
+ "learning_rate": 2.527692397665311e-06,
604
+ "loss": 0.3859,
605
+ "num_input_tokens_seen": 231424,
606
+ "step": 290,
607
+ "train_runtime": 696.1897,
608
+ "train_tokens_per_second": 332.415
609
+ },
610
+ {
611
+ "epoch": 3.1395973154362418,
612
+ "grad_norm": 2.9645609855651855,
613
+ "learning_rate": 2.256660975057867e-06,
614
+ "loss": 0.3724,
615
+ "num_input_tokens_seen": 235456,
616
+ "step": 295,
617
+ "train_runtime": 706.5398,
618
+ "train_tokens_per_second": 333.252
619
+ },
620
+ {
621
+ "epoch": 3.193288590604027,
622
+ "grad_norm": 3.25144624710083,
623
+ "learning_rate": 1.9991418491859383e-06,
624
+ "loss": 0.3916,
625
+ "num_input_tokens_seen": 239424,
626
+ "step": 300,
627
+ "train_runtime": 717.153,
628
+ "train_tokens_per_second": 333.853
629
+ },
630
+ {
631
+ "epoch": 3.193288590604027,
632
+ "eval_loss": 3.5844736099243164,
633
+ "eval_runtime": 12.6192,
634
+ "eval_samples_per_second": 29.558,
635
+ "eval_steps_per_second": 14.819,
636
+ "num_input_tokens_seen": 239424,
637
+ "step": 300
638
+ },
639
+ {
640
+ "epoch": 3.246979865771812,
641
+ "grad_norm": 3.184697151184082,
642
+ "learning_rate": 1.7555843965823992e-06,
643
+ "loss": 0.3676,
644
+ "num_input_tokens_seen": 243488,
645
+ "step": 305,
646
+ "train_runtime": 743.816,
647
+ "train_tokens_per_second": 327.35
648
+ },
649
+ {
650
+ "epoch": 3.3006711409395972,
651
+ "grad_norm": 3.306453227996826,
652
+ "learning_rate": 1.5264136303534893e-06,
653
+ "loss": 0.3798,
654
+ "num_input_tokens_seen": 247456,
655
+ "step": 310,
656
+ "train_runtime": 755.1587,
657
+ "train_tokens_per_second": 327.687
658
+ },
659
+ {
660
+ "epoch": 3.3543624161073824,
661
+ "grad_norm": 3.3960649967193604,
662
+ "learning_rate": 1.3120294585216353e-06,
663
+ "loss": 0.3606,
664
+ "num_input_tokens_seen": 251456,
665
+ "step": 315,
666
+ "train_runtime": 765.7156,
667
+ "train_tokens_per_second": 328.393
668
+ },
669
+ {
670
+ "epoch": 3.4080536912751676,
671
+ "grad_norm": 3.560805320739746,
672
+ "learning_rate": 1.11280598617714e-06,
673
+ "loss": 0.3938,
674
+ "num_input_tokens_seen": 255504,
675
+ "step": 320,
676
+ "train_runtime": 776.6023,
677
+ "train_tokens_per_second": 329.002
678
+ },
679
+ {
680
+ "epoch": 3.461744966442953,
681
+ "grad_norm": 3.646918773651123,
682
+ "learning_rate": 9.290908626565931e-07,
683
+ "loss": 0.3605,
684
+ "num_input_tokens_seen": 259472,
685
+ "step": 325,
686
+ "train_runtime": 787.0463,
687
+ "train_tokens_per_second": 329.678
688
+ },
689
+ {
690
+ "epoch": 3.5154362416107383,
691
+ "grad_norm": 2.9772727489471436,
692
+ "learning_rate": 7.612046748871327e-07,
693
+ "loss": 0.3781,
694
+ "num_input_tokens_seen": 263536,
695
+ "step": 330,
696
+ "train_runtime": 797.017,
697
+ "train_tokens_per_second": 330.653
698
+ },
699
+ {
700
+ "epoch": 3.5691275167785235,
701
+ "grad_norm": 2.8137423992156982,
702
+ "learning_rate": 6.094403879552213e-07,
703
+ "loss": 0.3794,
704
+ "num_input_tokens_seen": 267584,
705
+ "step": 335,
706
+ "train_runtime": 807.8723,
707
+ "train_tokens_per_second": 331.221
708
+ },
709
+ {
710
+ "epoch": 3.6228187919463086,
711
+ "grad_norm": 2.8694584369659424,
712
+ "learning_rate": 4.740628338761255e-07,
713
+ "loss": 0.3526,
714
+ "num_input_tokens_seen": 271664,
715
+ "step": 340,
716
+ "train_runtime": 817.9687,
717
+ "train_tokens_per_second": 332.12
718
+ },
719
+ {
720
+ "epoch": 3.6765100671140942,
721
+ "grad_norm": 3.0649948120117188,
722
+ "learning_rate": 3.553082494562354e-07,
723
+ "loss": 0.3846,
724
+ "num_input_tokens_seen": 275664,
725
+ "step": 345,
726
+ "train_runtime": 828.9328,
727
+ "train_tokens_per_second": 332.553
728
+ },
729
+ {
730
+ "epoch": 3.7302013422818794,
731
+ "grad_norm": 4.392162322998047,
732
+ "learning_rate": 2.533838640546438e-07,
733
+ "loss": 0.3855,
734
+ "num_input_tokens_seen": 279648,
735
+ "step": 350,
736
+ "train_runtime": 839.3162,
737
+ "train_tokens_per_second": 333.186
738
+ },
739
+ {
740
+ "epoch": 3.7838926174496645,
741
+ "grad_norm": 3.539325475692749,
742
+ "learning_rate": 1.6846753796336491e-07,
743
+ "loss": 0.3955,
744
+ "num_input_tokens_seen": 283600,
745
+ "step": 355,
746
+ "train_runtime": 849.891,
747
+ "train_tokens_per_second": 333.69
748
+ },
749
+ {
750
+ "epoch": 3.8375838926174497,
751
+ "grad_norm": 3.1544559001922607,
752
+ "learning_rate": 1.0070745203721532e-07,
753
+ "loss": 0.34,
754
+ "num_input_tokens_seen": 287600,
755
+ "step": 360,
756
+ "train_runtime": 860.4738,
757
+ "train_tokens_per_second": 334.234
758
+ },
759
+ {
760
+ "epoch": 3.891275167785235,
761
+ "grad_norm": 3.2322452068328857,
762
+ "learning_rate": 5.022184911495864e-08,
763
+ "loss": 0.3584,
764
+ "num_input_tokens_seen": 291712,
765
+ "step": 365,
766
+ "train_runtime": 870.8827,
767
+ "train_tokens_per_second": 334.961
768
+ },
769
+ {
770
+ "epoch": 3.94496644295302,
771
+ "grad_norm": 3.279101610183716,
772
+ "learning_rate": 1.7098827682970885e-08,
773
+ "loss": 0.3608,
774
+ "num_input_tokens_seen": 295856,
775
+ "step": 370,
776
+ "train_runtime": 881.666,
777
+ "train_tokens_per_second": 335.565
778
+ },
779
+ {
780
+ "epoch": 3.998657718120805,
781
+ "grad_norm": 3.604062080383301,
782
+ "learning_rate": 1.3961881414292776e-09,
783
+ "loss": 0.3659,
784
+ "num_input_tokens_seen": 299904,
785
+ "step": 375,
786
+ "train_runtime": 892.1532,
787
+ "train_tokens_per_second": 336.158
788
+ },
789
+ {
790
+ "epoch": 4.0,
791
+ "num_input_tokens_seen": 300000,
792
+ "step": 376,
793
+ "total_flos": 1780328448000000.0,
794
+ "train_loss": 0.7932832451101314,
795
+ "train_runtime": 895.9422,
796
+ "train_samples_per_second": 6.652,
797
+ "train_steps_per_second": 0.42
798
+ }
799
+ ],
800
+ "logging_steps": 5,
801
+ "max_steps": 376,
802
+ "num_input_tokens_seen": 300000,
803
+ "num_train_epochs": 4,
804
+ "save_steps": 100,
805
+ "stateful_callbacks": {
806
+ "TrainerControl": {
807
+ "args": {
808
+ "should_epoch_stop": false,
809
+ "should_evaluate": false,
810
+ "should_log": false,
811
+ "should_save": true,
812
+ "should_training_stop": true
813
+ },
814
+ "attributes": {}
815
+ }
816
+ },
817
+ "total_flos": 1780328448000000.0,
818
+ "train_batch_size": 2,
819
+ "trial_name": null,
820
+ "trial_params": null
821
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:33993b60fd6ce357901ae84544b5451fdd8d4d3dc51c04aa377491c86c3089cd
3
+ size 5752
training_args.yaml ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ adapter_name_or_path: saves/Llama-3.2-1B-Instruct/lora/train_1B-Instruct_pippo_v4
2
+ bf16: true
3
+ cutoff_len: 1024
4
+ dataset: pipo_persona
5
+ dataset_dir: data
6
+ ddp_timeout: 180000000
7
+ do_train: true
8
+ enable_thinking: true
9
+ eval_steps: 100
10
+ eval_strategy: steps
11
+ finetuning_type: lora
12
+ flash_attn: auto
13
+ gradient_accumulation_steps: 8
14
+ include_num_input_tokens_seen: true
15
+ learning_rate: 2.0e-05
16
+ logging_steps: 5
17
+ lora_alpha: 32
18
+ lora_dropout: 0.1
19
+ lora_rank: 16
20
+ lora_target: q_proj,v_proj,o_proj,gate_proj,up_proj,down_proj
21
+ loraplus_lr_ratio: 8
22
+ lr_scheduler_type: cosine
23
+ max_grad_norm: 1.0
24
+ max_samples: 1900
25
+ model_name_or_path: meta-llama/Llama-3.2-1B-Instruct
26
+ num_train_epochs: 4.0
27
+ optim: adamw_torch
28
+ output_dir: saves/Llama-3.2-1B-Instruct/lora/train_1B-Instruct_pippo_v6
29
+ packing: false
30
+ per_device_eval_batch_size: 2
31
+ per_device_train_batch_size: 2
32
+ pissa_convert: true
33
+ pissa_init: true
34
+ plot_loss: true
35
+ preprocessing_num_workers: 16
36
+ report_to: none
37
+ save_steps: 100
38
+ stage: sft
39
+ template: llama3
40
+ trust_remote_code: true
41
+ use_dora: true
42
+ use_rslora: true
43
+ val_size: 0.2
44
+ warmup_steps: 0
training_eval_loss.png ADDED
training_loss.png ADDED