Upload task output 73fe8c66-6860-4437-8f6b-c2a2e7738ffa
Browse files- .gitattributes +2 -0
- README.md +170 -0
- adapter_config.json +42 -0
- adapter_model.safetensors +3 -0
- added_tokens.json +28 -0
- chat_template.jinja +5 -0
- checkpoint-2800/README.md +208 -0
- checkpoint-2800/adapter_config.json +42 -0
- checkpoint-2800/adapter_model.safetensors +3 -0
- checkpoint-2800/added_tokens.json +28 -0
- checkpoint-2800/chat_template.jinja +5 -0
- checkpoint-2800/merges.txt +0 -0
- checkpoint-2800/optimizer.pt +3 -0
- checkpoint-2800/rng_state.pth +3 -0
- checkpoint-2800/scheduler.pt +3 -0
- checkpoint-2800/special_tokens_map.json +31 -0
- checkpoint-2800/tokenizer.json +3 -0
- checkpoint-2800/tokenizer_config.json +239 -0
- checkpoint-2800/trainer_state.json +2834 -0
- checkpoint-2800/training_args.bin +3 -0
- checkpoint-2800/vocab.json +0 -0
- config.json +67 -0
- merges.txt +0 -0
- special_tokens_map.json +31 -0
- tokenizer.json +3 -0
- tokenizer_config.json +239 -0
- vocab.json +0 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,5 @@ 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 |
+
checkpoint-2800/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 37 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
|
@@ -0,0 +1,170 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
tags:
|
| 4 |
+
- axolotl
|
| 5 |
+
- base_model:adapter:/cache/models/samoline--77ac7486-9606-42a1-a847-be5998bb133c
|
| 6 |
+
- lora
|
| 7 |
+
- transformers
|
| 8 |
+
pipeline_tag: text-generation
|
| 9 |
+
base_model: samoline/77ac7486-9606-42a1-a847-be5998bb133c
|
| 10 |
+
model-index:
|
| 11 |
+
- name: app/checkpoints/73fe8c66-6860-4437-8f6b-c2a2e7738ffa/5781d468-8ce5-440d-8888-8e49c6b018ef
|
| 12 |
+
results: []
|
| 13 |
+
---
|
| 14 |
+
|
| 15 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 16 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 17 |
+
|
| 18 |
+
[<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl)
|
| 19 |
+
<details><summary>See axolotl config</summary>
|
| 20 |
+
|
| 21 |
+
axolotl version: `0.12.0.dev0`
|
| 22 |
+
```yaml
|
| 23 |
+
adapter: lora
|
| 24 |
+
base_model: samoline/77ac7486-9606-42a1-a847-be5998bb133c
|
| 25 |
+
bf16: true
|
| 26 |
+
chat_template: llama3
|
| 27 |
+
cosine_min_lr_ratio: 0.3
|
| 28 |
+
dataloader_num_workers: 12
|
| 29 |
+
dataset_prepared_path: null
|
| 30 |
+
datasets:
|
| 31 |
+
- data_files:
|
| 32 |
+
- 73fe8c66-6860-4437-8f6b-c2a2e7738ffa_train_data.json
|
| 33 |
+
ds_type: json
|
| 34 |
+
format: custom
|
| 35 |
+
path: /workspace/axolotl/data
|
| 36 |
+
type:
|
| 37 |
+
field_input: input
|
| 38 |
+
field_instruction: instruct
|
| 39 |
+
field_output: output
|
| 40 |
+
format: '{instruction} {input}'
|
| 41 |
+
no_input_format: '{instruction}'
|
| 42 |
+
system_format: '{system}'
|
| 43 |
+
system_prompt: ''
|
| 44 |
+
ddp: true
|
| 45 |
+
debug: null
|
| 46 |
+
deepspeed: null
|
| 47 |
+
device_map: cuda
|
| 48 |
+
early_stopping_patience: null
|
| 49 |
+
eval_max_new_tokens: 128
|
| 50 |
+
eval_steps: null
|
| 51 |
+
eval_table_size: null
|
| 52 |
+
evals_per_epoch: null
|
| 53 |
+
flash_attention: true
|
| 54 |
+
fp16: false
|
| 55 |
+
fsdp: null
|
| 56 |
+
fsdp_config: null
|
| 57 |
+
gradient_accumulation_steps: 1
|
| 58 |
+
gradient_checkpointing: true
|
| 59 |
+
gradient_checkpointing_kwargs:
|
| 60 |
+
use_reentrant: false
|
| 61 |
+
group_by_length: true
|
| 62 |
+
hub_model_id: null
|
| 63 |
+
hub_private_repo: false
|
| 64 |
+
hub_repo: null
|
| 65 |
+
hub_strategy: checkpoint
|
| 66 |
+
hub_token: null
|
| 67 |
+
learning_rate: 0.0002
|
| 68 |
+
liger_fused_linear_cross_entropy: true
|
| 69 |
+
liger_glu_activation: true
|
| 70 |
+
liger_layer_norm: true
|
| 71 |
+
liger_rms_norm: true
|
| 72 |
+
liger_rope: true
|
| 73 |
+
load_in_4bit: false
|
| 74 |
+
load_in_8bit: false
|
| 75 |
+
local_rank: null
|
| 76 |
+
logging_steps: null
|
| 77 |
+
lora_alpha: 64
|
| 78 |
+
lora_dropout: 0.05
|
| 79 |
+
lora_fan_in_fan_out: null
|
| 80 |
+
lora_model_dir: null
|
| 81 |
+
lora_r: 32
|
| 82 |
+
lora_target_linear: true
|
| 83 |
+
loraplus_lr_embedding: 1.0e-06
|
| 84 |
+
loraplus_lr_ratio: 16
|
| 85 |
+
lr_scheduler: cosine
|
| 86 |
+
max_grad_norm: 1
|
| 87 |
+
max_steps: 30
|
| 88 |
+
micro_batch_size: 28
|
| 89 |
+
mlflow_experiment_name: /workspace/axolotl/data/73fe8c66-6860-4437-8f6b-c2a2e7738ffa_train_data.json
|
| 90 |
+
model_card: false
|
| 91 |
+
model_type: AutoModelForCausalLM
|
| 92 |
+
num_epochs: 200
|
| 93 |
+
optimizer: adamw_bnb_8bit
|
| 94 |
+
output_dir: /app/checkpoints/73fe8c66-6860-4437-8f6b-c2a2e7738ffa/5781d468-8ce5-440d-8888-8e49c6b018ef
|
| 95 |
+
pad_to_sequence_len: true
|
| 96 |
+
plugins:
|
| 97 |
+
- axolotl.integrations.liger.LigerPlugin
|
| 98 |
+
push_every_save: true
|
| 99 |
+
push_to_hub: true
|
| 100 |
+
resume_from_checkpoint: null
|
| 101 |
+
rl: null
|
| 102 |
+
s2_attention: null
|
| 103 |
+
sample_packing: true
|
| 104 |
+
save_steps: 100
|
| 105 |
+
save_strategy: steps
|
| 106 |
+
save_total_limit: 1
|
| 107 |
+
saves_per_epoch: 0
|
| 108 |
+
sequence_len: 1024
|
| 109 |
+
strict: false
|
| 110 |
+
tf32: true
|
| 111 |
+
tokenizer_type: AutoTokenizer
|
| 112 |
+
train_on_inputs: false
|
| 113 |
+
trl: null
|
| 114 |
+
trust_remote_code: false
|
| 115 |
+
use_liger: true
|
| 116 |
+
val_set_size: 0.0
|
| 117 |
+
wandb_mode: offline
|
| 118 |
+
wandb_name: 73fe8c66-6860-4437-8f6b-c2a2e7738ffa_5781d468-8ce5-440d-8888-8e49c6b018ef
|
| 119 |
+
wandb_project: Gradients-On-Demand
|
| 120 |
+
wandb_run: null
|
| 121 |
+
wandb_runid: 73fe8c66-6860-4437-8f6b-c2a2e7738ffa_5781d468-8ce5-440d-8888-8e49c6b018ef
|
| 122 |
+
warmup_steps: 30
|
| 123 |
+
weight_decay: 0
|
| 124 |
+
xformers_attention: null
|
| 125 |
+
|
| 126 |
+
```
|
| 127 |
+
|
| 128 |
+
</details><br>
|
| 129 |
+
|
| 130 |
+
# app/checkpoints/73fe8c66-6860-4437-8f6b-c2a2e7738ffa/5781d468-8ce5-440d-8888-8e49c6b018ef
|
| 131 |
+
|
| 132 |
+
This model was trained from scratch on the None dataset.
|
| 133 |
+
|
| 134 |
+
## Model description
|
| 135 |
+
|
| 136 |
+
More information needed
|
| 137 |
+
|
| 138 |
+
## Intended uses & limitations
|
| 139 |
+
|
| 140 |
+
More information needed
|
| 141 |
+
|
| 142 |
+
## Training and evaluation data
|
| 143 |
+
|
| 144 |
+
More information needed
|
| 145 |
+
|
| 146 |
+
## Training procedure
|
| 147 |
+
|
| 148 |
+
### Training hyperparameters
|
| 149 |
+
|
| 150 |
+
The following hyperparameters were used during training:
|
| 151 |
+
- learning_rate: 0.0002
|
| 152 |
+
- train_batch_size: 28
|
| 153 |
+
- eval_batch_size: 28
|
| 154 |
+
- seed: 42
|
| 155 |
+
- optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 156 |
+
- lr_scheduler_type: cosine
|
| 157 |
+
- lr_scheduler_warmup_steps: 30
|
| 158 |
+
- training_steps: 30
|
| 159 |
+
|
| 160 |
+
### Training results
|
| 161 |
+
|
| 162 |
+
|
| 163 |
+
|
| 164 |
+
### Framework versions
|
| 165 |
+
|
| 166 |
+
- PEFT 0.17.0
|
| 167 |
+
- Transformers 4.54.1
|
| 168 |
+
- Pytorch 2.7.1+cu128
|
| 169 |
+
- Datasets 4.0.0
|
| 170 |
+
- Tokenizers 0.21.4
|
adapter_config.json
ADDED
|
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "samoline/77ac7486-9606-42a1-a847-be5998bb133c",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"corda_config": null,
|
| 7 |
+
"eva_config": null,
|
| 8 |
+
"exclude_modules": null,
|
| 9 |
+
"fan_in_fan_out": null,
|
| 10 |
+
"inference_mode": false,
|
| 11 |
+
"init_lora_weights": true,
|
| 12 |
+
"layer_replication": null,
|
| 13 |
+
"layers_pattern": null,
|
| 14 |
+
"layers_to_transform": null,
|
| 15 |
+
"loftq_config": {},
|
| 16 |
+
"lora_alpha": 64,
|
| 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 |
+
"qalora_group_size": 16,
|
| 24 |
+
"r": 32,
|
| 25 |
+
"rank_pattern": {},
|
| 26 |
+
"revision": null,
|
| 27 |
+
"target_modules": [
|
| 28 |
+
"v_proj",
|
| 29 |
+
"up_proj",
|
| 30 |
+
"o_proj",
|
| 31 |
+
"q_proj",
|
| 32 |
+
"gate_proj",
|
| 33 |
+
"k_proj",
|
| 34 |
+
"down_proj"
|
| 35 |
+
],
|
| 36 |
+
"target_parameters": [],
|
| 37 |
+
"task_type": "CAUSAL_LM",
|
| 38 |
+
"trainable_token_indices": null,
|
| 39 |
+
"use_dora": false,
|
| 40 |
+
"use_qalora": false,
|
| 41 |
+
"use_rslora": false
|
| 42 |
+
}
|
adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:29f3883c5317c3504b0fd31d3b280d40a9fe6871852d0ef93c12c755e87d9512
|
| 3 |
+
size 349243752
|
added_tokens.json
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"</think>": 151668,
|
| 3 |
+
"</tool_call>": 151658,
|
| 4 |
+
"</tool_response>": 151666,
|
| 5 |
+
"<think>": 151667,
|
| 6 |
+
"<tool_call>": 151657,
|
| 7 |
+
"<tool_response>": 151665,
|
| 8 |
+
"<|box_end|>": 151649,
|
| 9 |
+
"<|box_start|>": 151648,
|
| 10 |
+
"<|endoftext|>": 151643,
|
| 11 |
+
"<|file_sep|>": 151664,
|
| 12 |
+
"<|fim_middle|>": 151660,
|
| 13 |
+
"<|fim_pad|>": 151662,
|
| 14 |
+
"<|fim_prefix|>": 151659,
|
| 15 |
+
"<|fim_suffix|>": 151661,
|
| 16 |
+
"<|im_end|>": 151645,
|
| 17 |
+
"<|im_start|>": 151644,
|
| 18 |
+
"<|image_pad|>": 151655,
|
| 19 |
+
"<|object_ref_end|>": 151647,
|
| 20 |
+
"<|object_ref_start|>": 151646,
|
| 21 |
+
"<|quad_end|>": 151651,
|
| 22 |
+
"<|quad_start|>": 151650,
|
| 23 |
+
"<|repo_name|>": 151663,
|
| 24 |
+
"<|video_pad|>": 151656,
|
| 25 |
+
"<|vision_end|>": 151653,
|
| 26 |
+
"<|vision_pad|>": 151654,
|
| 27 |
+
"<|vision_start|>": 151652
|
| 28 |
+
}
|
chat_template.jinja
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>
|
| 2 |
+
|
| 3 |
+
'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>
|
| 4 |
+
|
| 5 |
+
' }}{% endif %}
|
checkpoint-2800/README.md
ADDED
|
@@ -0,0 +1,208 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: /cache/models/samoline--77ac7486-9606-42a1-a847-be5998bb133c
|
| 3 |
+
library_name: peft
|
| 4 |
+
pipeline_tag: text-generation
|
| 5 |
+
tags:
|
| 6 |
+
- axolotl
|
| 7 |
+
- base_model:adapter:/cache/models/samoline--77ac7486-9606-42a1-a847-be5998bb133c
|
| 8 |
+
- lora
|
| 9 |
+
- transformers
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
# Model Card for Model ID
|
| 13 |
+
|
| 14 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 15 |
+
|
| 16 |
+
|
| 17 |
+
|
| 18 |
+
## Model Details
|
| 19 |
+
|
| 20 |
+
### Model Description
|
| 21 |
+
|
| 22 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 23 |
+
|
| 24 |
+
|
| 25 |
+
|
| 26 |
+
- **Developed by:** [More Information Needed]
|
| 27 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 28 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 29 |
+
- **Model type:** [More Information Needed]
|
| 30 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 31 |
+
- **License:** [More Information Needed]
|
| 32 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 33 |
+
|
| 34 |
+
### Model Sources [optional]
|
| 35 |
+
|
| 36 |
+
<!-- Provide the basic links for the model. -->
|
| 37 |
+
|
| 38 |
+
- **Repository:** [More Information Needed]
|
| 39 |
+
- **Paper [optional]:** [More Information Needed]
|
| 40 |
+
- **Demo [optional]:** [More Information Needed]
|
| 41 |
+
|
| 42 |
+
## Uses
|
| 43 |
+
|
| 44 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 45 |
+
|
| 46 |
+
### Direct Use
|
| 47 |
+
|
| 48 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 49 |
+
|
| 50 |
+
[More Information Needed]
|
| 51 |
+
|
| 52 |
+
### Downstream Use [optional]
|
| 53 |
+
|
| 54 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 55 |
+
|
| 56 |
+
[More Information Needed]
|
| 57 |
+
|
| 58 |
+
### Out-of-Scope Use
|
| 59 |
+
|
| 60 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 61 |
+
|
| 62 |
+
[More Information Needed]
|
| 63 |
+
|
| 64 |
+
## Bias, Risks, and Limitations
|
| 65 |
+
|
| 66 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 67 |
+
|
| 68 |
+
[More Information Needed]
|
| 69 |
+
|
| 70 |
+
### Recommendations
|
| 71 |
+
|
| 72 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 73 |
+
|
| 74 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 75 |
+
|
| 76 |
+
## How to Get Started with the Model
|
| 77 |
+
|
| 78 |
+
Use the code below to get started with the model.
|
| 79 |
+
|
| 80 |
+
[More Information Needed]
|
| 81 |
+
|
| 82 |
+
## Training Details
|
| 83 |
+
|
| 84 |
+
### Training Data
|
| 85 |
+
|
| 86 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 87 |
+
|
| 88 |
+
[More Information Needed]
|
| 89 |
+
|
| 90 |
+
### Training Procedure
|
| 91 |
+
|
| 92 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 93 |
+
|
| 94 |
+
#### Preprocessing [optional]
|
| 95 |
+
|
| 96 |
+
[More Information Needed]
|
| 97 |
+
|
| 98 |
+
|
| 99 |
+
#### Training Hyperparameters
|
| 100 |
+
|
| 101 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 102 |
+
|
| 103 |
+
#### Speeds, Sizes, Times [optional]
|
| 104 |
+
|
| 105 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 106 |
+
|
| 107 |
+
[More Information Needed]
|
| 108 |
+
|
| 109 |
+
## Evaluation
|
| 110 |
+
|
| 111 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 112 |
+
|
| 113 |
+
### Testing Data, Factors & Metrics
|
| 114 |
+
|
| 115 |
+
#### Testing Data
|
| 116 |
+
|
| 117 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 118 |
+
|
| 119 |
+
[More Information Needed]
|
| 120 |
+
|
| 121 |
+
#### Factors
|
| 122 |
+
|
| 123 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 124 |
+
|
| 125 |
+
[More Information Needed]
|
| 126 |
+
|
| 127 |
+
#### Metrics
|
| 128 |
+
|
| 129 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 130 |
+
|
| 131 |
+
[More Information Needed]
|
| 132 |
+
|
| 133 |
+
### Results
|
| 134 |
+
|
| 135 |
+
[More Information Needed]
|
| 136 |
+
|
| 137 |
+
#### Summary
|
| 138 |
+
|
| 139 |
+
|
| 140 |
+
|
| 141 |
+
## Model Examination [optional]
|
| 142 |
+
|
| 143 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 144 |
+
|
| 145 |
+
[More Information Needed]
|
| 146 |
+
|
| 147 |
+
## Environmental Impact
|
| 148 |
+
|
| 149 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 150 |
+
|
| 151 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
| 152 |
+
|
| 153 |
+
- **Hardware Type:** [More Information Needed]
|
| 154 |
+
- **Hours used:** [More Information Needed]
|
| 155 |
+
- **Cloud Provider:** [More Information Needed]
|
| 156 |
+
- **Compute Region:** [More Information Needed]
|
| 157 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 158 |
+
|
| 159 |
+
## Technical Specifications [optional]
|
| 160 |
+
|
| 161 |
+
### Model Architecture and Objective
|
| 162 |
+
|
| 163 |
+
[More Information Needed]
|
| 164 |
+
|
| 165 |
+
### Compute Infrastructure
|
| 166 |
+
|
| 167 |
+
[More Information Needed]
|
| 168 |
+
|
| 169 |
+
#### Hardware
|
| 170 |
+
|
| 171 |
+
[More Information Needed]
|
| 172 |
+
|
| 173 |
+
#### Software
|
| 174 |
+
|
| 175 |
+
[More Information Needed]
|
| 176 |
+
|
| 177 |
+
## Citation [optional]
|
| 178 |
+
|
| 179 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 180 |
+
|
| 181 |
+
**BibTeX:**
|
| 182 |
+
|
| 183 |
+
[More Information Needed]
|
| 184 |
+
|
| 185 |
+
**APA:**
|
| 186 |
+
|
| 187 |
+
[More Information Needed]
|
| 188 |
+
|
| 189 |
+
## Glossary [optional]
|
| 190 |
+
|
| 191 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 192 |
+
|
| 193 |
+
[More Information Needed]
|
| 194 |
+
|
| 195 |
+
## More Information [optional]
|
| 196 |
+
|
| 197 |
+
[More Information Needed]
|
| 198 |
+
|
| 199 |
+
## Model Card Authors [optional]
|
| 200 |
+
|
| 201 |
+
[More Information Needed]
|
| 202 |
+
|
| 203 |
+
## Model Card Contact
|
| 204 |
+
|
| 205 |
+
[More Information Needed]
|
| 206 |
+
### Framework versions
|
| 207 |
+
|
| 208 |
+
- PEFT 0.17.0
|
checkpoint-2800/adapter_config.json
ADDED
|
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "/cache/models/samoline--77ac7486-9606-42a1-a847-be5998bb133c",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"corda_config": null,
|
| 7 |
+
"eva_config": null,
|
| 8 |
+
"exclude_modules": null,
|
| 9 |
+
"fan_in_fan_out": null,
|
| 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": 64,
|
| 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 |
+
"qalora_group_size": 16,
|
| 24 |
+
"r": 32,
|
| 25 |
+
"rank_pattern": {},
|
| 26 |
+
"revision": null,
|
| 27 |
+
"target_modules": [
|
| 28 |
+
"v_proj",
|
| 29 |
+
"up_proj",
|
| 30 |
+
"o_proj",
|
| 31 |
+
"q_proj",
|
| 32 |
+
"gate_proj",
|
| 33 |
+
"k_proj",
|
| 34 |
+
"down_proj"
|
| 35 |
+
],
|
| 36 |
+
"target_parameters": [],
|
| 37 |
+
"task_type": "CAUSAL_LM",
|
| 38 |
+
"trainable_token_indices": null,
|
| 39 |
+
"use_dora": false,
|
| 40 |
+
"use_qalora": false,
|
| 41 |
+
"use_rslora": false
|
| 42 |
+
}
|
checkpoint-2800/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5509468f52b969a77ad8336289168774bfe59de7a5ad703a4e855fa81dd116bf
|
| 3 |
+
size 349243752
|
checkpoint-2800/added_tokens.json
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"</think>": 151668,
|
| 3 |
+
"</tool_call>": 151658,
|
| 4 |
+
"</tool_response>": 151666,
|
| 5 |
+
"<think>": 151667,
|
| 6 |
+
"<tool_call>": 151657,
|
| 7 |
+
"<tool_response>": 151665,
|
| 8 |
+
"<|box_end|>": 151649,
|
| 9 |
+
"<|box_start|>": 151648,
|
| 10 |
+
"<|endoftext|>": 151643,
|
| 11 |
+
"<|file_sep|>": 151664,
|
| 12 |
+
"<|fim_middle|>": 151660,
|
| 13 |
+
"<|fim_pad|>": 151662,
|
| 14 |
+
"<|fim_prefix|>": 151659,
|
| 15 |
+
"<|fim_suffix|>": 151661,
|
| 16 |
+
"<|im_end|>": 151645,
|
| 17 |
+
"<|im_start|>": 151644,
|
| 18 |
+
"<|image_pad|>": 151655,
|
| 19 |
+
"<|object_ref_end|>": 151647,
|
| 20 |
+
"<|object_ref_start|>": 151646,
|
| 21 |
+
"<|quad_end|>": 151651,
|
| 22 |
+
"<|quad_start|>": 151650,
|
| 23 |
+
"<|repo_name|>": 151663,
|
| 24 |
+
"<|video_pad|>": 151656,
|
| 25 |
+
"<|vision_end|>": 151653,
|
| 26 |
+
"<|vision_pad|>": 151654,
|
| 27 |
+
"<|vision_start|>": 151652
|
| 28 |
+
}
|
checkpoint-2800/chat_template.jinja
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>
|
| 2 |
+
|
| 3 |
+
'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>
|
| 4 |
+
|
| 5 |
+
' }}{% endif %}
|
checkpoint-2800/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-2800/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bbb1630868539e9fa387786d428b8bc59b25c4f24a5fe39dd2af1433c37981a6
|
| 3 |
+
size 177909253
|
checkpoint-2800/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c7c8e4ac7948fbc587d9ba3893307ba37d4285ae0409bd4794daff48a746d24c
|
| 3 |
+
size 14645
|
checkpoint-2800/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7ede9ec9e451d8cb59ec5a4a58f4bb1b9be68d0a7e4d59b148995dc42fac7f99
|
| 3 |
+
size 1465
|
checkpoint-2800/special_tokens_map.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|im_start|>",
|
| 4 |
+
"<|im_end|>",
|
| 5 |
+
"<|object_ref_start|>",
|
| 6 |
+
"<|object_ref_end|>",
|
| 7 |
+
"<|box_start|>",
|
| 8 |
+
"<|box_end|>",
|
| 9 |
+
"<|quad_start|>",
|
| 10 |
+
"<|quad_end|>",
|
| 11 |
+
"<|vision_start|>",
|
| 12 |
+
"<|vision_end|>",
|
| 13 |
+
"<|vision_pad|>",
|
| 14 |
+
"<|image_pad|>",
|
| 15 |
+
"<|video_pad|>"
|
| 16 |
+
],
|
| 17 |
+
"eos_token": {
|
| 18 |
+
"content": "<|endoftext|>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
},
|
| 24 |
+
"pad_token": {
|
| 25 |
+
"content": "<|endoftext|>",
|
| 26 |
+
"lstrip": false,
|
| 27 |
+
"normalized": false,
|
| 28 |
+
"rstrip": false,
|
| 29 |
+
"single_word": false
|
| 30 |
+
}
|
| 31 |
+
}
|
checkpoint-2800/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
|
| 3 |
+
size 11422654
|
checkpoint-2800/tokenizer_config.json
ADDED
|
@@ -0,0 +1,239 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_prefix_space": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"151643": {
|
| 6 |
+
"content": "<|endoftext|>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"151644": {
|
| 14 |
+
"content": "<|im_start|>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"151645": {
|
| 22 |
+
"content": "<|im_end|>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
},
|
| 29 |
+
"151646": {
|
| 30 |
+
"content": "<|object_ref_start|>",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": false,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false,
|
| 35 |
+
"special": true
|
| 36 |
+
},
|
| 37 |
+
"151647": {
|
| 38 |
+
"content": "<|object_ref_end|>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false,
|
| 43 |
+
"special": true
|
| 44 |
+
},
|
| 45 |
+
"151648": {
|
| 46 |
+
"content": "<|box_start|>",
|
| 47 |
+
"lstrip": false,
|
| 48 |
+
"normalized": false,
|
| 49 |
+
"rstrip": false,
|
| 50 |
+
"single_word": false,
|
| 51 |
+
"special": true
|
| 52 |
+
},
|
| 53 |
+
"151649": {
|
| 54 |
+
"content": "<|box_end|>",
|
| 55 |
+
"lstrip": false,
|
| 56 |
+
"normalized": false,
|
| 57 |
+
"rstrip": false,
|
| 58 |
+
"single_word": false,
|
| 59 |
+
"special": true
|
| 60 |
+
},
|
| 61 |
+
"151650": {
|
| 62 |
+
"content": "<|quad_start|>",
|
| 63 |
+
"lstrip": false,
|
| 64 |
+
"normalized": false,
|
| 65 |
+
"rstrip": false,
|
| 66 |
+
"single_word": false,
|
| 67 |
+
"special": true
|
| 68 |
+
},
|
| 69 |
+
"151651": {
|
| 70 |
+
"content": "<|quad_end|>",
|
| 71 |
+
"lstrip": false,
|
| 72 |
+
"normalized": false,
|
| 73 |
+
"rstrip": false,
|
| 74 |
+
"single_word": false,
|
| 75 |
+
"special": true
|
| 76 |
+
},
|
| 77 |
+
"151652": {
|
| 78 |
+
"content": "<|vision_start|>",
|
| 79 |
+
"lstrip": false,
|
| 80 |
+
"normalized": false,
|
| 81 |
+
"rstrip": false,
|
| 82 |
+
"single_word": false,
|
| 83 |
+
"special": true
|
| 84 |
+
},
|
| 85 |
+
"151653": {
|
| 86 |
+
"content": "<|vision_end|>",
|
| 87 |
+
"lstrip": false,
|
| 88 |
+
"normalized": false,
|
| 89 |
+
"rstrip": false,
|
| 90 |
+
"single_word": false,
|
| 91 |
+
"special": true
|
| 92 |
+
},
|
| 93 |
+
"151654": {
|
| 94 |
+
"content": "<|vision_pad|>",
|
| 95 |
+
"lstrip": false,
|
| 96 |
+
"normalized": false,
|
| 97 |
+
"rstrip": false,
|
| 98 |
+
"single_word": false,
|
| 99 |
+
"special": true
|
| 100 |
+
},
|
| 101 |
+
"151655": {
|
| 102 |
+
"content": "<|image_pad|>",
|
| 103 |
+
"lstrip": false,
|
| 104 |
+
"normalized": false,
|
| 105 |
+
"rstrip": false,
|
| 106 |
+
"single_word": false,
|
| 107 |
+
"special": true
|
| 108 |
+
},
|
| 109 |
+
"151656": {
|
| 110 |
+
"content": "<|video_pad|>",
|
| 111 |
+
"lstrip": false,
|
| 112 |
+
"normalized": false,
|
| 113 |
+
"rstrip": false,
|
| 114 |
+
"single_word": false,
|
| 115 |
+
"special": true
|
| 116 |
+
},
|
| 117 |
+
"151657": {
|
| 118 |
+
"content": "<tool_call>",
|
| 119 |
+
"lstrip": false,
|
| 120 |
+
"normalized": false,
|
| 121 |
+
"rstrip": false,
|
| 122 |
+
"single_word": false,
|
| 123 |
+
"special": false
|
| 124 |
+
},
|
| 125 |
+
"151658": {
|
| 126 |
+
"content": "</tool_call>",
|
| 127 |
+
"lstrip": false,
|
| 128 |
+
"normalized": false,
|
| 129 |
+
"rstrip": false,
|
| 130 |
+
"single_word": false,
|
| 131 |
+
"special": false
|
| 132 |
+
},
|
| 133 |
+
"151659": {
|
| 134 |
+
"content": "<|fim_prefix|>",
|
| 135 |
+
"lstrip": false,
|
| 136 |
+
"normalized": false,
|
| 137 |
+
"rstrip": false,
|
| 138 |
+
"single_word": false,
|
| 139 |
+
"special": false
|
| 140 |
+
},
|
| 141 |
+
"151660": {
|
| 142 |
+
"content": "<|fim_middle|>",
|
| 143 |
+
"lstrip": false,
|
| 144 |
+
"normalized": false,
|
| 145 |
+
"rstrip": false,
|
| 146 |
+
"single_word": false,
|
| 147 |
+
"special": false
|
| 148 |
+
},
|
| 149 |
+
"151661": {
|
| 150 |
+
"content": "<|fim_suffix|>",
|
| 151 |
+
"lstrip": false,
|
| 152 |
+
"normalized": false,
|
| 153 |
+
"rstrip": false,
|
| 154 |
+
"single_word": false,
|
| 155 |
+
"special": false
|
| 156 |
+
},
|
| 157 |
+
"151662": {
|
| 158 |
+
"content": "<|fim_pad|>",
|
| 159 |
+
"lstrip": false,
|
| 160 |
+
"normalized": false,
|
| 161 |
+
"rstrip": false,
|
| 162 |
+
"single_word": false,
|
| 163 |
+
"special": false
|
| 164 |
+
},
|
| 165 |
+
"151663": {
|
| 166 |
+
"content": "<|repo_name|>",
|
| 167 |
+
"lstrip": false,
|
| 168 |
+
"normalized": false,
|
| 169 |
+
"rstrip": false,
|
| 170 |
+
"single_word": false,
|
| 171 |
+
"special": false
|
| 172 |
+
},
|
| 173 |
+
"151664": {
|
| 174 |
+
"content": "<|file_sep|>",
|
| 175 |
+
"lstrip": false,
|
| 176 |
+
"normalized": false,
|
| 177 |
+
"rstrip": false,
|
| 178 |
+
"single_word": false,
|
| 179 |
+
"special": false
|
| 180 |
+
},
|
| 181 |
+
"151665": {
|
| 182 |
+
"content": "<tool_response>",
|
| 183 |
+
"lstrip": false,
|
| 184 |
+
"normalized": false,
|
| 185 |
+
"rstrip": false,
|
| 186 |
+
"single_word": false,
|
| 187 |
+
"special": false
|
| 188 |
+
},
|
| 189 |
+
"151666": {
|
| 190 |
+
"content": "</tool_response>",
|
| 191 |
+
"lstrip": false,
|
| 192 |
+
"normalized": false,
|
| 193 |
+
"rstrip": false,
|
| 194 |
+
"single_word": false,
|
| 195 |
+
"special": false
|
| 196 |
+
},
|
| 197 |
+
"151667": {
|
| 198 |
+
"content": "<think>",
|
| 199 |
+
"lstrip": false,
|
| 200 |
+
"normalized": false,
|
| 201 |
+
"rstrip": false,
|
| 202 |
+
"single_word": false,
|
| 203 |
+
"special": false
|
| 204 |
+
},
|
| 205 |
+
"151668": {
|
| 206 |
+
"content": "</think>",
|
| 207 |
+
"lstrip": false,
|
| 208 |
+
"normalized": false,
|
| 209 |
+
"rstrip": false,
|
| 210 |
+
"single_word": false,
|
| 211 |
+
"special": false
|
| 212 |
+
}
|
| 213 |
+
},
|
| 214 |
+
"additional_special_tokens": [
|
| 215 |
+
"<|im_start|>",
|
| 216 |
+
"<|im_end|>",
|
| 217 |
+
"<|object_ref_start|>",
|
| 218 |
+
"<|object_ref_end|>",
|
| 219 |
+
"<|box_start|>",
|
| 220 |
+
"<|box_end|>",
|
| 221 |
+
"<|quad_start|>",
|
| 222 |
+
"<|quad_end|>",
|
| 223 |
+
"<|vision_start|>",
|
| 224 |
+
"<|vision_end|>",
|
| 225 |
+
"<|vision_pad|>",
|
| 226 |
+
"<|image_pad|>",
|
| 227 |
+
"<|video_pad|>"
|
| 228 |
+
],
|
| 229 |
+
"bos_token": null,
|
| 230 |
+
"clean_up_tokenization_spaces": false,
|
| 231 |
+
"eos_token": "<|endoftext|>",
|
| 232 |
+
"errors": "replace",
|
| 233 |
+
"extra_special_tokens": {},
|
| 234 |
+
"model_max_length": 131072,
|
| 235 |
+
"pad_token": "<|endoftext|>",
|
| 236 |
+
"split_special_tokens": false,
|
| 237 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 238 |
+
"unk_token": null
|
| 239 |
+
}
|
checkpoint-2800/trainer_state.json
ADDED
|
@@ -0,0 +1,2834 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 3.840877914951989,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 2800,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.013717421124828532,
|
| 14 |
+
"grad_norm": 0.07647993415594101,
|
| 15 |
+
"learning_rate": 9e-06,
|
| 16 |
+
"loss": 0.6156,
|
| 17 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 18 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 19 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 20 |
+
"step": 10
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.027434842249657063,
|
| 24 |
+
"grad_norm": 0.06708963215351105,
|
| 25 |
+
"learning_rate": 1.9e-05,
|
| 26 |
+
"loss": 0.5979,
|
| 27 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 28 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 29 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 30 |
+
"step": 20
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.0411522633744856,
|
| 34 |
+
"grad_norm": 0.07629839330911636,
|
| 35 |
+
"learning_rate": 2.9e-05,
|
| 36 |
+
"loss": 0.6237,
|
| 37 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 38 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 39 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 40 |
+
"step": 30
|
| 41 |
+
},
|
| 42 |
+
{
|
| 43 |
+
"epoch": 0.05486968449931413,
|
| 44 |
+
"grad_norm": 0.07326024025678635,
|
| 45 |
+
"learning_rate": 3.9000000000000006e-05,
|
| 46 |
+
"loss": 0.6485,
|
| 47 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 48 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 49 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 50 |
+
"step": 40
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.06858710562414266,
|
| 54 |
+
"grad_norm": 0.07892456650733948,
|
| 55 |
+
"learning_rate": 4.9e-05,
|
| 56 |
+
"loss": 0.6504,
|
| 57 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 58 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 59 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 60 |
+
"step": 50
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"epoch": 0.0823045267489712,
|
| 64 |
+
"grad_norm": 0.09194822609424591,
|
| 65 |
+
"learning_rate": 5.9e-05,
|
| 66 |
+
"loss": 0.6424,
|
| 67 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 68 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 69 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 70 |
+
"step": 60
|
| 71 |
+
},
|
| 72 |
+
{
|
| 73 |
+
"epoch": 0.09602194787379972,
|
| 74 |
+
"grad_norm": 0.10922462493181229,
|
| 75 |
+
"learning_rate": 6.9e-05,
|
| 76 |
+
"loss": 0.6368,
|
| 77 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 78 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 79 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 80 |
+
"step": 70
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.10973936899862825,
|
| 84 |
+
"grad_norm": 0.12341003865003586,
|
| 85 |
+
"learning_rate": 7.900000000000001e-05,
|
| 86 |
+
"loss": 0.5873,
|
| 87 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 88 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 89 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 90 |
+
"step": 80
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 0.12345679012345678,
|
| 94 |
+
"grad_norm": 0.13858085870742798,
|
| 95 |
+
"learning_rate": 8.900000000000001e-05,
|
| 96 |
+
"loss": 0.6311,
|
| 97 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 98 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 99 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 100 |
+
"step": 90
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.13717421124828533,
|
| 104 |
+
"grad_norm": 0.13488128781318665,
|
| 105 |
+
"learning_rate": 9.900000000000001e-05,
|
| 106 |
+
"loss": 0.6366,
|
| 107 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 108 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 109 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 110 |
+
"step": 100
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 0.15089163237311384,
|
| 114 |
+
"grad_norm": 0.1761036068201065,
|
| 115 |
+
"learning_rate": 0.000109,
|
| 116 |
+
"loss": 0.6638,
|
| 117 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 118 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 119 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 120 |
+
"step": 110
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 0.1646090534979424,
|
| 124 |
+
"grad_norm": 0.22375817596912384,
|
| 125 |
+
"learning_rate": 0.000119,
|
| 126 |
+
"loss": 0.6412,
|
| 127 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 128 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 129 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 130 |
+
"step": 120
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 0.17832647462277093,
|
| 134 |
+
"grad_norm": 0.20682518184185028,
|
| 135 |
+
"learning_rate": 0.00012900000000000002,
|
| 136 |
+
"loss": 0.6446,
|
| 137 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 138 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 139 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 140 |
+
"step": 130
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 0.19204389574759945,
|
| 144 |
+
"grad_norm": 0.22452841699123383,
|
| 145 |
+
"learning_rate": 0.000139,
|
| 146 |
+
"loss": 0.6257,
|
| 147 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 148 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 149 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 150 |
+
"step": 140
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.205761316872428,
|
| 154 |
+
"grad_norm": 0.2752174735069275,
|
| 155 |
+
"learning_rate": 0.00014900000000000002,
|
| 156 |
+
"loss": 0.636,
|
| 157 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 158 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 159 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 160 |
+
"step": 150
|
| 161 |
+
},
|
| 162 |
+
{
|
| 163 |
+
"epoch": 0.2194787379972565,
|
| 164 |
+
"grad_norm": 0.213674858212471,
|
| 165 |
+
"learning_rate": 0.00015900000000000002,
|
| 166 |
+
"loss": 0.6495,
|
| 167 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 168 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 169 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 170 |
+
"step": 160
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.23319615912208505,
|
| 174 |
+
"grad_norm": 0.3929201364517212,
|
| 175 |
+
"learning_rate": 0.00016900000000000002,
|
| 176 |
+
"loss": 0.6348,
|
| 177 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 178 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 179 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 180 |
+
"step": 170
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 0.24691358024691357,
|
| 184 |
+
"grad_norm": 0.33309033513069153,
|
| 185 |
+
"learning_rate": 0.00017900000000000001,
|
| 186 |
+
"loss": 0.6354,
|
| 187 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 188 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 189 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 190 |
+
"step": 180
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 0.2606310013717421,
|
| 194 |
+
"grad_norm": 0.31244829297065735,
|
| 195 |
+
"learning_rate": 0.00018899999999999999,
|
| 196 |
+
"loss": 0.7746,
|
| 197 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 198 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 199 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 200 |
+
"step": 190
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 0.27434842249657065,
|
| 204 |
+
"grad_norm": 64.621337890625,
|
| 205 |
+
"learning_rate": 0.000199,
|
| 206 |
+
"loss": 0.7354,
|
| 207 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 208 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 209 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 210 |
+
"step": 200
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 0.2880658436213992,
|
| 214 |
+
"grad_norm": 28.939149856567383,
|
| 215 |
+
"learning_rate": 0.00019999620135075551,
|
| 216 |
+
"loss": 0.7761,
|
| 217 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 218 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 219 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 220 |
+
"step": 210
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.3017832647462277,
|
| 224 |
+
"grad_norm": 0.6682184934616089,
|
| 225 |
+
"learning_rate": 0.0001999830707468668,
|
| 226 |
+
"loss": 0.6941,
|
| 227 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 228 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 229 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 230 |
+
"step": 220
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 0.31550068587105623,
|
| 234 |
+
"grad_norm": 1.1326137781143188,
|
| 235 |
+
"learning_rate": 0.00019996056305039171,
|
| 236 |
+
"loss": 0.6822,
|
| 237 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 238 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 239 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 240 |
+
"step": 230
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.3292181069958848,
|
| 244 |
+
"grad_norm": 6.208425045013428,
|
| 245 |
+
"learning_rate": 0.00019992868127715604,
|
| 246 |
+
"loss": 0.8403,
|
| 247 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 248 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 249 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 250 |
+
"step": 240
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 0.3429355281207133,
|
| 254 |
+
"grad_norm": 11.755585670471191,
|
| 255 |
+
"learning_rate": 0.00019988742969902643,
|
| 256 |
+
"loss": 0.9823,
|
| 257 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 258 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 259 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 260 |
+
"step": 250
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 0.35665294924554186,
|
| 264 |
+
"grad_norm": 4.8738322257995605,
|
| 265 |
+
"learning_rate": 0.00019983681384333775,
|
| 266 |
+
"loss": 0.884,
|
| 267 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 268 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 269 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 270 |
+
"step": 260
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 0.37037037037037035,
|
| 274 |
+
"grad_norm": 0.7805973887443542,
|
| 275 |
+
"learning_rate": 0.0001997768404921525,
|
| 276 |
+
"loss": 0.7928,
|
| 277 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 278 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 279 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 280 |
+
"step": 270
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 0.3840877914951989,
|
| 284 |
+
"grad_norm": 1.145871877670288,
|
| 285 |
+
"learning_rate": 0.00019970751768135233,
|
| 286 |
+
"loss": 0.7093,
|
| 287 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 288 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 289 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 290 |
+
"step": 280
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.39780521262002744,
|
| 294 |
+
"grad_norm": 4.424680709838867,
|
| 295 |
+
"learning_rate": 0.00019962885469956086,
|
| 296 |
+
"loss": 0.7023,
|
| 297 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 298 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 299 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 300 |
+
"step": 290
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 0.411522633744856,
|
| 304 |
+
"grad_norm": 10.622379302978516,
|
| 305 |
+
"learning_rate": 0.0001995408620868997,
|
| 306 |
+
"loss": 0.8341,
|
| 307 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 308 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 309 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 310 |
+
"step": 300
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.4252400548696845,
|
| 314 |
+
"grad_norm": 2.177061080932617,
|
| 315 |
+
"learning_rate": 0.00019944355163357554,
|
| 316 |
+
"loss": 0.7574,
|
| 317 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 318 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 319 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 320 |
+
"step": 310
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 0.438957475994513,
|
| 324 |
+
"grad_norm": 0.5784764289855957,
|
| 325 |
+
"learning_rate": 0.0001993369363783008,
|
| 326 |
+
"loss": 0.7618,
|
| 327 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 328 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 329 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 330 |
+
"step": 320
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 0.45267489711934156,
|
| 334 |
+
"grad_norm": 0.5459311604499817,
|
| 335 |
+
"learning_rate": 0.0001992210306065463,
|
| 336 |
+
"loss": 0.673,
|
| 337 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 338 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 339 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 340 |
+
"step": 330
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"epoch": 0.4663923182441701,
|
| 344 |
+
"grad_norm": 0.8941497802734375,
|
| 345 |
+
"learning_rate": 0.00019909584984862736,
|
| 346 |
+
"loss": 0.7462,
|
| 347 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 348 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 349 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 350 |
+
"step": 340
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 0.48010973936899864,
|
| 354 |
+
"grad_norm": 0.4938856065273285,
|
| 355 |
+
"learning_rate": 0.00019896141087762277,
|
| 356 |
+
"loss": 0.6977,
|
| 357 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 358 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 359 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 360 |
+
"step": 350
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.49382716049382713,
|
| 364 |
+
"grad_norm": 0.5036232471466064,
|
| 365 |
+
"learning_rate": 0.00019881773170712724,
|
| 366 |
+
"loss": 0.7159,
|
| 367 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 368 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 369 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 370 |
+
"step": 360
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 0.5075445816186557,
|
| 374 |
+
"grad_norm": 0.9854089021682739,
|
| 375 |
+
"learning_rate": 0.00019866483158883797,
|
| 376 |
+
"loss": 0.7659,
|
| 377 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 378 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 379 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 380 |
+
"step": 370
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.5212620027434842,
|
| 384 |
+
"grad_norm": 0.6602941751480103,
|
| 385 |
+
"learning_rate": 0.00019850273100997497,
|
| 386 |
+
"loss": 0.6998,
|
| 387 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 388 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 389 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 390 |
+
"step": 380
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 0.5349794238683128,
|
| 394 |
+
"grad_norm": 2.9242019653320312,
|
| 395 |
+
"learning_rate": 0.0001983314516905359,
|
| 396 |
+
"loss": 0.7436,
|
| 397 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 398 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 399 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 400 |
+
"step": 390
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"epoch": 0.5486968449931413,
|
| 404 |
+
"grad_norm": 18.221200942993164,
|
| 405 |
+
"learning_rate": 0.00019815101658038597,
|
| 406 |
+
"loss": 0.7773,
|
| 407 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 408 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 409 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 410 |
+
"step": 400
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 0.5624142661179699,
|
| 414 |
+
"grad_norm": 0.5358967781066895,
|
| 415 |
+
"learning_rate": 0.00019796144985618268,
|
| 416 |
+
"loss": 0.6956,
|
| 417 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 418 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 419 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 420 |
+
"step": 410
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 0.5761316872427984,
|
| 424 |
+
"grad_norm": 7.433400630950928,
|
| 425 |
+
"learning_rate": 0.00019776277691813641,
|
| 426 |
+
"loss": 0.7562,
|
| 427 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 428 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 429 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 430 |
+
"step": 420
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.5898491083676269,
|
| 434 |
+
"grad_norm": 0.635043203830719,
|
| 435 |
+
"learning_rate": 0.0001975550243866072,
|
| 436 |
+
"loss": 0.7056,
|
| 437 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 438 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 439 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 440 |
+
"step": 430
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 0.6035665294924554,
|
| 444 |
+
"grad_norm": 0.944600522518158,
|
| 445 |
+
"learning_rate": 0.0001973382200985376,
|
| 446 |
+
"loss": 0.7304,
|
| 447 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 448 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 449 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 450 |
+
"step": 440
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.6172839506172839,
|
| 454 |
+
"grad_norm": 0.6635257601737976,
|
| 455 |
+
"learning_rate": 0.00019711239310372301,
|
| 456 |
+
"loss": 0.7009,
|
| 457 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 458 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 459 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 460 |
+
"step": 450
|
| 461 |
+
},
|
| 462 |
+
{
|
| 463 |
+
"epoch": 0.6310013717421125,
|
| 464 |
+
"grad_norm": 0.5404139757156372,
|
| 465 |
+
"learning_rate": 0.000196877573660919,
|
| 466 |
+
"loss": 0.6927,
|
| 467 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 468 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 469 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 470 |
+
"step": 460
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 0.644718792866941,
|
| 474 |
+
"grad_norm": 2.992511749267578,
|
| 475 |
+
"learning_rate": 0.00019663379323378726,
|
| 476 |
+
"loss": 0.6929,
|
| 477 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 478 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 479 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 480 |
+
"step": 470
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 0.6584362139917695,
|
| 484 |
+
"grad_norm": 1.219659686088562,
|
| 485 |
+
"learning_rate": 0.00019638108448667946,
|
| 486 |
+
"loss": 0.7122,
|
| 487 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 488 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 489 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 490 |
+
"step": 480
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 0.6721536351165981,
|
| 494 |
+
"grad_norm": 0.7214469313621521,
|
| 495 |
+
"learning_rate": 0.0001961194812802607,
|
| 496 |
+
"loss": 0.7407,
|
| 497 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 498 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 499 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 500 |
+
"step": 490
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 0.6858710562414266,
|
| 504 |
+
"grad_norm": 0.8283047676086426,
|
| 505 |
+
"learning_rate": 0.00019584901866697232,
|
| 506 |
+
"loss": 0.7412,
|
| 507 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 508 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 509 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 510 |
+
"step": 500
|
| 511 |
+
},
|
| 512 |
+
{
|
| 513 |
+
"epoch": 0.6995884773662552,
|
| 514 |
+
"grad_norm": 0.6623634099960327,
|
| 515 |
+
"learning_rate": 0.00019556973288633548,
|
| 516 |
+
"loss": 0.7221,
|
| 517 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 518 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 519 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 520 |
+
"step": 510
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 0.7133058984910837,
|
| 524 |
+
"grad_norm": 0.7273538708686829,
|
| 525 |
+
"learning_rate": 0.00019528166136009506,
|
| 526 |
+
"loss": 0.709,
|
| 527 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 528 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 529 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 530 |
+
"step": 520
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 0.7270233196159122,
|
| 534 |
+
"grad_norm": 0.6829487085342407,
|
| 535 |
+
"learning_rate": 0.00019498484268720562,
|
| 536 |
+
"loss": 0.7278,
|
| 537 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 538 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 539 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 540 |
+
"step": 530
|
| 541 |
+
},
|
| 542 |
+
{
|
| 543 |
+
"epoch": 0.7407407407407407,
|
| 544 |
+
"grad_norm": 9.31682300567627,
|
| 545 |
+
"learning_rate": 0.00019467931663865975,
|
| 546 |
+
"loss": 0.8336,
|
| 547 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 548 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 549 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 550 |
+
"step": 540
|
| 551 |
+
},
|
| 552 |
+
{
|
| 553 |
+
"epoch": 0.7544581618655692,
|
| 554 |
+
"grad_norm": 0.7958472371101379,
|
| 555 |
+
"learning_rate": 0.0001943651241521586,
|
| 556 |
+
"loss": 0.7134,
|
| 557 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 558 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 559 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 560 |
+
"step": 550
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 0.7681755829903978,
|
| 564 |
+
"grad_norm": 0.7276667356491089,
|
| 565 |
+
"learning_rate": 0.00019404230732662705,
|
| 566 |
+
"loss": 0.726,
|
| 567 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 568 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 569 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 570 |
+
"step": 560
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 0.7818930041152263,
|
| 574 |
+
"grad_norm": 0.696487545967102,
|
| 575 |
+
"learning_rate": 0.00019371090941657271,
|
| 576 |
+
"loss": 0.7396,
|
| 577 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 578 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 579 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 580 |
+
"step": 570
|
| 581 |
+
},
|
| 582 |
+
{
|
| 583 |
+
"epoch": 0.7956104252400549,
|
| 584 |
+
"grad_norm": 0.5741664171218872,
|
| 585 |
+
"learning_rate": 0.00019337097482629,
|
| 586 |
+
"loss": 0.7318,
|
| 587 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 588 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 589 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 590 |
+
"step": 580
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 0.8093278463648834,
|
| 594 |
+
"grad_norm": 0.6711471676826477,
|
| 595 |
+
"learning_rate": 0.00019302254910391072,
|
| 596 |
+
"loss": 0.7386,
|
| 597 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 598 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 599 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 600 |
+
"step": 590
|
| 601 |
+
},
|
| 602 |
+
{
|
| 603 |
+
"epoch": 0.823045267489712,
|
| 604 |
+
"grad_norm": 0.5798461437225342,
|
| 605 |
+
"learning_rate": 0.00019266567893530087,
|
| 606 |
+
"loss": 0.7358,
|
| 607 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 608 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 609 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 610 |
+
"step": 600
|
| 611 |
+
},
|
| 612 |
+
{
|
| 613 |
+
"epoch": 0.8367626886145405,
|
| 614 |
+
"grad_norm": 0.6501106023788452,
|
| 615 |
+
"learning_rate": 0.00019230041213780496,
|
| 616 |
+
"loss": 0.7134,
|
| 617 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 618 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 619 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 620 |
+
"step": 610
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 0.850480109739369,
|
| 624 |
+
"grad_norm": 0.8635139465332031,
|
| 625 |
+
"learning_rate": 0.0001919267976538393,
|
| 626 |
+
"loss": 0.7752,
|
| 627 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 628 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 629 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 630 |
+
"step": 620
|
| 631 |
+
},
|
| 632 |
+
{
|
| 633 |
+
"epoch": 0.8641975308641975,
|
| 634 |
+
"grad_norm": 3.2115159034729004,
|
| 635 |
+
"learning_rate": 0.0001915448855443339,
|
| 636 |
+
"loss": 0.8011,
|
| 637 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 638 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 639 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 640 |
+
"step": 630
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 0.877914951989026,
|
| 644 |
+
"grad_norm": 3.5995631217956543,
|
| 645 |
+
"learning_rate": 0.00019115472698202486,
|
| 646 |
+
"loss": 0.8575,
|
| 647 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 648 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 649 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 650 |
+
"step": 640
|
| 651 |
+
},
|
| 652 |
+
{
|
| 653 |
+
"epoch": 0.8916323731138546,
|
| 654 |
+
"grad_norm": 76.77554321289062,
|
| 655 |
+
"learning_rate": 0.0001907563742445977,
|
| 656 |
+
"loss": 0.8231,
|
| 657 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 658 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 659 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 660 |
+
"step": 650
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 0.9053497942386831,
|
| 664 |
+
"grad_norm": 1.0150165557861328,
|
| 665 |
+
"learning_rate": 0.00019034988070768254,
|
| 666 |
+
"loss": 0.9088,
|
| 667 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 668 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 669 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 670 |
+
"step": 660
|
| 671 |
+
},
|
| 672 |
+
{
|
| 673 |
+
"epoch": 0.9190672153635117,
|
| 674 |
+
"grad_norm": 41.20791244506836,
|
| 675 |
+
"learning_rate": 0.00018993530083770237,
|
| 676 |
+
"loss": 0.7364,
|
| 677 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 678 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 679 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 680 |
+
"step": 670
|
| 681 |
+
},
|
| 682 |
+
{
|
| 683 |
+
"epoch": 0.9327846364883402,
|
| 684 |
+
"grad_norm": 0.8044480085372925,
|
| 685 |
+
"learning_rate": 0.00018951269018457488,
|
| 686 |
+
"loss": 0.7491,
|
| 687 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 688 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 689 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 690 |
+
"step": 680
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 0.9465020576131687,
|
| 694 |
+
"grad_norm": 1.518044352531433,
|
| 695 |
+
"learning_rate": 0.00018908210537426956,
|
| 696 |
+
"loss": 0.7683,
|
| 697 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 698 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 699 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 700 |
+
"step": 690
|
| 701 |
+
},
|
| 702 |
+
{
|
| 703 |
+
"epoch": 0.9602194787379973,
|
| 704 |
+
"grad_norm": 2.6404244899749756,
|
| 705 |
+
"learning_rate": 0.00018864360410122,
|
| 706 |
+
"loss": 0.8235,
|
| 707 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 708 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 709 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 710 |
+
"step": 700
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 0.9739368998628258,
|
| 714 |
+
"grad_norm": 3.4350287914276123,
|
| 715 |
+
"learning_rate": 0.0001881972451205937,
|
| 716 |
+
"loss": 0.7458,
|
| 717 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 718 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 719 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 720 |
+
"step": 710
|
| 721 |
+
},
|
| 722 |
+
{
|
| 723 |
+
"epoch": 0.9876543209876543,
|
| 724 |
+
"grad_norm": 3.82545804977417,
|
| 725 |
+
"learning_rate": 0.00018774308824041902,
|
| 726 |
+
"loss": 0.7524,
|
| 727 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 728 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 729 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 730 |
+
"step": 720
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 1.0013717421124828,
|
| 734 |
+
"grad_norm": 1.0016659498214722,
|
| 735 |
+
"learning_rate": 0.0001872811943135718,
|
| 736 |
+
"loss": 0.7532,
|
| 737 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 738 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 739 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 740 |
+
"step": 730
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 1.0150891632373114,
|
| 744 |
+
"grad_norm": 1.411134123802185,
|
| 745 |
+
"learning_rate": 0.00018681162522962157,
|
| 746 |
+
"loss": 0.6945,
|
| 747 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 748 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 749 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 750 |
+
"step": 740
|
| 751 |
+
},
|
| 752 |
+
{
|
| 753 |
+
"epoch": 1.02880658436214,
|
| 754 |
+
"grad_norm": 5.619636058807373,
|
| 755 |
+
"learning_rate": 0.00018633444390653875,
|
| 756 |
+
"loss": 0.6294,
|
| 757 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 758 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 759 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 760 |
+
"step": 750
|
| 761 |
+
},
|
| 762 |
+
{
|
| 763 |
+
"epoch": 1.0425240054869684,
|
| 764 |
+
"grad_norm": 0.9333019852638245,
|
| 765 |
+
"learning_rate": 0.0001858497142822642,
|
| 766 |
+
"loss": 0.6401,
|
| 767 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 768 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 769 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 770 |
+
"step": 760
|
| 771 |
+
},
|
| 772 |
+
{
|
| 773 |
+
"epoch": 1.056241426611797,
|
| 774 |
+
"grad_norm": 0.6913846731185913,
|
| 775 |
+
"learning_rate": 0.00018535750130614247,
|
| 776 |
+
"loss": 0.594,
|
| 777 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 778 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 779 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 780 |
+
"step": 770
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 1.0699588477366255,
|
| 784 |
+
"grad_norm": 6.8243327140808105,
|
| 785 |
+
"learning_rate": 0.00018485787093021875,
|
| 786 |
+
"loss": 0.6323,
|
| 787 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 788 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 789 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 790 |
+
"step": 780
|
| 791 |
+
},
|
| 792 |
+
{
|
| 793 |
+
"epoch": 1.083676268861454,
|
| 794 |
+
"grad_norm": 0.8442447781562805,
|
| 795 |
+
"learning_rate": 0.00018435089010040222,
|
| 796 |
+
"loss": 0.6332,
|
| 797 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 798 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 799 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 800 |
+
"step": 790
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 1.0973936899862826,
|
| 804 |
+
"grad_norm": 0.8714583516120911,
|
| 805 |
+
"learning_rate": 0.00018383662674749566,
|
| 806 |
+
"loss": 0.5959,
|
| 807 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 808 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 809 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 810 |
+
"step": 800
|
| 811 |
+
},
|
| 812 |
+
{
|
| 813 |
+
"epoch": 1.1111111111111112,
|
| 814 |
+
"grad_norm": 12.768736839294434,
|
| 815 |
+
"learning_rate": 0.00018331514977809358,
|
| 816 |
+
"loss": 0.6401,
|
| 817 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 818 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 819 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 820 |
+
"step": 810
|
| 821 |
+
},
|
| 822 |
+
{
|
| 823 |
+
"epoch": 1.1248285322359397,
|
| 824 |
+
"grad_norm": 1.3638012409210205,
|
| 825 |
+
"learning_rate": 0.0001827865290653491,
|
| 826 |
+
"loss": 0.618,
|
| 827 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 828 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 829 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 830 |
+
"step": 820
|
| 831 |
+
},
|
| 832 |
+
{
|
| 833 |
+
"epoch": 1.1385459533607682,
|
| 834 |
+
"grad_norm": 1.05161714553833,
|
| 835 |
+
"learning_rate": 0.00018225083543961184,
|
| 836 |
+
"loss": 0.6312,
|
| 837 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 838 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 839 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 840 |
+
"step": 830
|
| 841 |
+
},
|
| 842 |
+
{
|
| 843 |
+
"epoch": 1.1522633744855968,
|
| 844 |
+
"grad_norm": 0.8189305067062378,
|
| 845 |
+
"learning_rate": 0.0001817081406789372,
|
| 846 |
+
"loss": 0.623,
|
| 847 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 848 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 849 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 850 |
+
"step": 840
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 1.1659807956104253,
|
| 854 |
+
"grad_norm": 9.99730110168457,
|
| 855 |
+
"learning_rate": 0.00018115851749946868,
|
| 856 |
+
"loss": 0.632,
|
| 857 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 858 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 859 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 860 |
+
"step": 850
|
| 861 |
+
},
|
| 862 |
+
{
|
| 863 |
+
"epoch": 1.1796982167352539,
|
| 864 |
+
"grad_norm": 3.584242820739746,
|
| 865 |
+
"learning_rate": 0.0001806020395456947,
|
| 866 |
+
"loss": 0.7085,
|
| 867 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 868 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 869 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 870 |
+
"step": 860
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 1.1934156378600824,
|
| 874 |
+
"grad_norm": 4.013728141784668,
|
| 875 |
+
"learning_rate": 0.0001800387813805808,
|
| 876 |
+
"loss": 0.6663,
|
| 877 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 878 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 879 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 880 |
+
"step": 870
|
| 881 |
+
},
|
| 882 |
+
{
|
| 883 |
+
"epoch": 1.2071330589849107,
|
| 884 |
+
"grad_norm": 0.778833270072937,
|
| 885 |
+
"learning_rate": 0.00017946881847557893,
|
| 886 |
+
"loss": 0.6383,
|
| 887 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 888 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 889 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 890 |
+
"step": 880
|
| 891 |
+
},
|
| 892 |
+
{
|
| 893 |
+
"epoch": 1.2208504801097393,
|
| 894 |
+
"grad_norm": 1.2759654521942139,
|
| 895 |
+
"learning_rate": 0.0001788922272005151,
|
| 896 |
+
"loss": 0.666,
|
| 897 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 898 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 899 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 900 |
+
"step": 890
|
| 901 |
+
},
|
| 902 |
+
{
|
| 903 |
+
"epoch": 1.2345679012345678,
|
| 904 |
+
"grad_norm": 3.3217387199401855,
|
| 905 |
+
"learning_rate": 0.00017830908481335632,
|
| 906 |
+
"loss": 0.6747,
|
| 907 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 908 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 909 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 910 |
+
"step": 900
|
| 911 |
+
},
|
| 912 |
+
{
|
| 913 |
+
"epoch": 1.2482853223593964,
|
| 914 |
+
"grad_norm": 0.7985875606536865,
|
| 915 |
+
"learning_rate": 0.00017771946944985877,
|
| 916 |
+
"loss": 0.6728,
|
| 917 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 918 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 919 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 920 |
+
"step": 910
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 1.262002743484225,
|
| 924 |
+
"grad_norm": 1.1496803760528564,
|
| 925 |
+
"learning_rate": 0.0001771234601130984,
|
| 926 |
+
"loss": 0.6479,
|
| 927 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 928 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 929 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 930 |
+
"step": 920
|
| 931 |
+
},
|
| 932 |
+
{
|
| 933 |
+
"epoch": 1.2757201646090535,
|
| 934 |
+
"grad_norm": 0.7988722324371338,
|
| 935 |
+
"learning_rate": 0.00017652113666288526,
|
| 936 |
+
"loss": 0.6633,
|
| 937 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 938 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 939 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 940 |
+
"step": 930
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 1.289437585733882,
|
| 944 |
+
"grad_norm": 1.0003479719161987,
|
| 945 |
+
"learning_rate": 0.00017591257980506284,
|
| 946 |
+
"loss": 0.6914,
|
| 947 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 948 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 949 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 950 |
+
"step": 940
|
| 951 |
+
},
|
| 952 |
+
{
|
| 953 |
+
"epoch": 1.3031550068587106,
|
| 954 |
+
"grad_norm": 1.2995918989181519,
|
| 955 |
+
"learning_rate": 0.0001752978710806945,
|
| 956 |
+
"loss": 0.6512,
|
| 957 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 958 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 959 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 960 |
+
"step": 950
|
| 961 |
+
},
|
| 962 |
+
{
|
| 963 |
+
"epoch": 1.316872427983539,
|
| 964 |
+
"grad_norm": 2.514435291290283,
|
| 965 |
+
"learning_rate": 0.00017467709285513738,
|
| 966 |
+
"loss": 0.6663,
|
| 967 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 968 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 969 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 970 |
+
"step": 960
|
| 971 |
+
},
|
| 972 |
+
{
|
| 973 |
+
"epoch": 1.3305898491083676,
|
| 974 |
+
"grad_norm": 0.8331915140151978,
|
| 975 |
+
"learning_rate": 0.00017405032830700656,
|
| 976 |
+
"loss": 0.6125,
|
| 977 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 978 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 979 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 980 |
+
"step": 970
|
| 981 |
+
},
|
| 982 |
+
{
|
| 983 |
+
"epoch": 1.3443072702331962,
|
| 984 |
+
"grad_norm": 0.9041861295700073,
|
| 985 |
+
"learning_rate": 0.00017341766141702947,
|
| 986 |
+
"loss": 0.6932,
|
| 987 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 988 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 989 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 990 |
+
"step": 980
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 1.3580246913580247,
|
| 994 |
+
"grad_norm": 0.6893113255500793,
|
| 995 |
+
"learning_rate": 0.0001727791769567937,
|
| 996 |
+
"loss": 0.6159,
|
| 997 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 998 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 999 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 1000 |
+
"step": 990
|
| 1001 |
+
},
|
| 1002 |
+
{
|
| 1003 |
+
"epoch": 1.3717421124828533,
|
| 1004 |
+
"grad_norm": 0.8431796431541443,
|
| 1005 |
+
"learning_rate": 0.00017213496047738795,
|
| 1006 |
+
"loss": 0.6471,
|
| 1007 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 1008 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 1009 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 1010 |
+
"step": 1000
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 1.3854595336076818,
|
| 1014 |
+
"grad_norm": 0.7642700672149658,
|
| 1015 |
+
"learning_rate": 0.0001714850982979393,
|
| 1016 |
+
"loss": 0.6815,
|
| 1017 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 1018 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 1019 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 1020 |
+
"step": 1010
|
| 1021 |
+
},
|
| 1022 |
+
{
|
| 1023 |
+
"epoch": 1.3991769547325104,
|
| 1024 |
+
"grad_norm": 2.067713975906372,
|
| 1025 |
+
"learning_rate": 0.000170829677494047,
|
| 1026 |
+
"loss": 0.6574,
|
| 1027 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 1028 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 1029 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 1030 |
+
"step": 1020
|
| 1031 |
+
},
|
| 1032 |
+
{
|
| 1033 |
+
"epoch": 1.412894375857339,
|
| 1034 |
+
"grad_norm": 109.01731872558594,
|
| 1035 |
+
"learning_rate": 0.00017016878588611522,
|
| 1036 |
+
"loss": 0.6813,
|
| 1037 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 1038 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 1039 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 1040 |
+
"step": 1030
|
| 1041 |
+
},
|
| 1042 |
+
{
|
| 1043 |
+
"epoch": 1.4266117969821672,
|
| 1044 |
+
"grad_norm": 1.0420688390731812,
|
| 1045 |
+
"learning_rate": 0.00016950251202758608,
|
| 1046 |
+
"loss": 0.7575,
|
| 1047 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 1048 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 1049 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 1050 |
+
"step": 1040
|
| 1051 |
+
},
|
| 1052 |
+
{
|
| 1053 |
+
"epoch": 1.4403292181069958,
|
| 1054 |
+
"grad_norm": 0.7815510034561157,
|
| 1055 |
+
"learning_rate": 0.00016883094519307395,
|
| 1056 |
+
"loss": 0.6414,
|
| 1057 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 1058 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 1059 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 1060 |
+
"step": 1050
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"epoch": 1.4540466392318243,
|
| 1064 |
+
"grad_norm": 0.8230787515640259,
|
| 1065 |
+
"learning_rate": 0.00016815417536640377,
|
| 1066 |
+
"loss": 0.6509,
|
| 1067 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 1068 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 1069 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 1070 |
+
"step": 1060
|
| 1071 |
+
},
|
| 1072 |
+
{
|
| 1073 |
+
"epoch": 1.4677640603566529,
|
| 1074 |
+
"grad_norm": 0.6952017545700073,
|
| 1075 |
+
"learning_rate": 0.0001674722932285539,
|
| 1076 |
+
"loss": 0.6511,
|
| 1077 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 1078 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 1079 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 1080 |
+
"step": 1070
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 1.4814814814814814,
|
| 1084 |
+
"grad_norm": 0.721723198890686,
|
| 1085 |
+
"learning_rate": 0.00016678539014550574,
|
| 1086 |
+
"loss": 0.6689,
|
| 1087 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 1088 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 1089 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 1090 |
+
"step": 1080
|
| 1091 |
+
},
|
| 1092 |
+
{
|
| 1093 |
+
"epoch": 1.49519890260631,
|
| 1094 |
+
"grad_norm": 0.8406015634536743,
|
| 1095 |
+
"learning_rate": 0.0001660935581560015,
|
| 1096 |
+
"loss": 0.6599,
|
| 1097 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 1098 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 1099 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 1100 |
+
"step": 1090
|
| 1101 |
+
},
|
| 1102 |
+
{
|
| 1103 |
+
"epoch": 1.5089163237311385,
|
| 1104 |
+
"grad_norm": 0.6411350965499878,
|
| 1105 |
+
"learning_rate": 0.0001653968899592119,
|
| 1106 |
+
"loss": 0.652,
|
| 1107 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 1108 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 1109 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 1110 |
+
"step": 1100
|
| 1111 |
+
},
|
| 1112 |
+
{
|
| 1113 |
+
"epoch": 1.522633744855967,
|
| 1114 |
+
"grad_norm": 0.7977852821350098,
|
| 1115 |
+
"learning_rate": 0.00016469547890231518,
|
| 1116 |
+
"loss": 0.6966,
|
| 1117 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 1118 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 1119 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 1120 |
+
"step": 1110
|
| 1121 |
+
},
|
| 1122 |
+
{
|
| 1123 |
+
"epoch": 1.5363511659807956,
|
| 1124 |
+
"grad_norm": 0.732109546661377,
|
| 1125 |
+
"learning_rate": 0.00016398941896798963,
|
| 1126 |
+
"loss": 0.667,
|
| 1127 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 1128 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 1129 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 1130 |
+
"step": 1120
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 1.5500685871056241,
|
| 1134 |
+
"grad_norm": 0.7646382451057434,
|
| 1135 |
+
"learning_rate": 0.0001632788047618206,
|
| 1136 |
+
"loss": 0.6728,
|
| 1137 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 1138 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 1139 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 1140 |
+
"step": 1130
|
| 1141 |
+
},
|
| 1142 |
+
{
|
| 1143 |
+
"epoch": 1.5637860082304527,
|
| 1144 |
+
"grad_norm": 0.7732465267181396,
|
| 1145 |
+
"learning_rate": 0.00016256373149962442,
|
| 1146 |
+
"loss": 0.6438,
|
| 1147 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 1148 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 1149 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 1150 |
+
"step": 1140
|
| 1151 |
+
},
|
| 1152 |
+
{
|
| 1153 |
+
"epoch": 1.5775034293552812,
|
| 1154 |
+
"grad_norm": 0.8279727697372437,
|
| 1155 |
+
"learning_rate": 0.00016184429499469007,
|
| 1156 |
+
"loss": 0.6219,
|
| 1157 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 1158 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 1159 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 1160 |
+
"step": 1150
|
| 1161 |
+
},
|
| 1162 |
+
{
|
| 1163 |
+
"epoch": 1.5912208504801097,
|
| 1164 |
+
"grad_norm": 0.7830964922904968,
|
| 1165 |
+
"learning_rate": 0.0001611205916449413,
|
| 1166 |
+
"loss": 0.6765,
|
| 1167 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 1168 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 1169 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 1170 |
+
"step": 1160
|
| 1171 |
+
},
|
| 1172 |
+
{
|
| 1173 |
+
"epoch": 1.6049382716049383,
|
| 1174 |
+
"grad_norm": 1.0385525226593018,
|
| 1175 |
+
"learning_rate": 0.00016039271842002007,
|
| 1176 |
+
"loss": 0.6829,
|
| 1177 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 1178 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 1179 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 1180 |
+
"step": 1170
|
| 1181 |
+
},
|
| 1182 |
+
{
|
| 1183 |
+
"epoch": 1.6186556927297668,
|
| 1184 |
+
"grad_norm": 1.541650652885437,
|
| 1185 |
+
"learning_rate": 0.00015966077284829364,
|
| 1186 |
+
"loss": 0.7134,
|
| 1187 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 1188 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 1189 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 1190 |
+
"step": 1180
|
| 1191 |
+
},
|
| 1192 |
+
{
|
| 1193 |
+
"epoch": 1.6323731138545954,
|
| 1194 |
+
"grad_norm": 0.8020074367523193,
|
| 1195 |
+
"learning_rate": 0.00015892485300378649,
|
| 1196 |
+
"loss": 0.6706,
|
| 1197 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 1198 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 1199 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 1200 |
+
"step": 1190
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 1.646090534979424,
|
| 1204 |
+
"grad_norm": 1.8672761917114258,
|
| 1205 |
+
"learning_rate": 0.00015818505749303933,
|
| 1206 |
+
"loss": 0.7086,
|
| 1207 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 1208 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 1209 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 1210 |
+
"step": 1200
|
| 1211 |
+
},
|
| 1212 |
+
{
|
| 1213 |
+
"epoch": 1.6598079561042525,
|
| 1214 |
+
"grad_norm": 0.802882730960846,
|
| 1215 |
+
"learning_rate": 0.00015744148544189686,
|
| 1216 |
+
"loss": 0.6948,
|
| 1217 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 1218 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 1219 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 1220 |
+
"step": 1210
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 1.673525377229081,
|
| 1224 |
+
"grad_norm": 0.6179660558700562,
|
| 1225 |
+
"learning_rate": 0.00015669423648222562,
|
| 1226 |
+
"loss": 0.6674,
|
| 1227 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 1228 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 1229 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 1230 |
+
"step": 1220
|
| 1231 |
+
},
|
| 1232 |
+
{
|
| 1233 |
+
"epoch": 1.6872427983539096,
|
| 1234 |
+
"grad_norm": 0.7645729184150696,
|
| 1235 |
+
"learning_rate": 0.00015594341073856444,
|
| 1236 |
+
"loss": 0.6844,
|
| 1237 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 1238 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 1239 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 1240 |
+
"step": 1230
|
| 1241 |
+
},
|
| 1242 |
+
{
|
| 1243 |
+
"epoch": 1.700960219478738,
|
| 1244 |
+
"grad_norm": 0.8577654361724854,
|
| 1245 |
+
"learning_rate": 0.00015518910881470843,
|
| 1246 |
+
"loss": 0.68,
|
| 1247 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 1248 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 1249 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 1250 |
+
"step": 1240
|
| 1251 |
+
},
|
| 1252 |
+
{
|
| 1253 |
+
"epoch": 1.7146776406035666,
|
| 1254 |
+
"grad_norm": 0.7424944639205933,
|
| 1255 |
+
"learning_rate": 0.0001544314317802292,
|
| 1256 |
+
"loss": 0.6578,
|
| 1257 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 1258 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 1259 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 1260 |
+
"step": 1250
|
| 1261 |
+
},
|
| 1262 |
+
{
|
| 1263 |
+
"epoch": 1.7283950617283952,
|
| 1264 |
+
"grad_norm": 0.8607377409934998,
|
| 1265 |
+
"learning_rate": 0.00015367048115693231,
|
| 1266 |
+
"loss": 0.7255,
|
| 1267 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 1268 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 1269 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 1270 |
+
"step": 1260
|
| 1271 |
+
},
|
| 1272 |
+
{
|
| 1273 |
+
"epoch": 1.7421124828532237,
|
| 1274 |
+
"grad_norm": 0.8205728530883789,
|
| 1275 |
+
"learning_rate": 0.00015290635890525444,
|
| 1276 |
+
"loss": 0.6638,
|
| 1277 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 1278 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 1279 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 1280 |
+
"step": 1270
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 1.7558299039780523,
|
| 1284 |
+
"grad_norm": 0.6349771022796631,
|
| 1285 |
+
"learning_rate": 0.00015213916741060133,
|
| 1286 |
+
"loss": 0.6549,
|
| 1287 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 1288 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 1289 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 1290 |
+
"step": 1280
|
| 1291 |
+
},
|
| 1292 |
+
{
|
| 1293 |
+
"epoch": 1.7695473251028808,
|
| 1294 |
+
"grad_norm": 0.8347269892692566,
|
| 1295 |
+
"learning_rate": 0.00015136900946962947,
|
| 1296 |
+
"loss": 0.71,
|
| 1297 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 1298 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 1299 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 1300 |
+
"step": 1290
|
| 1301 |
+
},
|
| 1302 |
+
{
|
| 1303 |
+
"epoch": 1.7832647462277091,
|
| 1304 |
+
"grad_norm": 0.7633096575737,
|
| 1305 |
+
"learning_rate": 0.00015059598827647195,
|
| 1306 |
+
"loss": 0.6786,
|
| 1307 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 1308 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 1309 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 1310 |
+
"step": 1300
|
| 1311 |
+
},
|
| 1312 |
+
{
|
| 1313 |
+
"epoch": 1.7969821673525377,
|
| 1314 |
+
"grad_norm": 0.7618131041526794,
|
| 1315 |
+
"learning_rate": 0.0001498202074089115,
|
| 1316 |
+
"loss": 0.6747,
|
| 1317 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 1318 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 1319 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 1320 |
+
"step": 1310
|
| 1321 |
+
},
|
| 1322 |
+
{
|
| 1323 |
+
"epoch": 1.8106995884773662,
|
| 1324 |
+
"grad_norm": 0.8066633939743042,
|
| 1325 |
+
"learning_rate": 0.00014904177081450208,
|
| 1326 |
+
"loss": 0.6662,
|
| 1327 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 1328 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 1329 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 1330 |
+
"step": 1320
|
| 1331 |
+
},
|
| 1332 |
+
{
|
| 1333 |
+
"epoch": 1.8244170096021948,
|
| 1334 |
+
"grad_norm": 0.8109913468360901,
|
| 1335 |
+
"learning_rate": 0.00014826078279664082,
|
| 1336 |
+
"loss": 0.6689,
|
| 1337 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 1338 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 1339 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 1340 |
+
"step": 1330
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"epoch": 1.8381344307270233,
|
| 1344 |
+
"grad_norm": 0.7557175755500793,
|
| 1345 |
+
"learning_rate": 0.00014747734800059226,
|
| 1346 |
+
"loss": 0.7004,
|
| 1347 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 1348 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 1349 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 1350 |
+
"step": 1340
|
| 1351 |
+
},
|
| 1352 |
+
{
|
| 1353 |
+
"epoch": 1.8518518518518519,
|
| 1354 |
+
"grad_norm": 0.8399734497070312,
|
| 1355 |
+
"learning_rate": 0.00014669157139946692,
|
| 1356 |
+
"loss": 0.6962,
|
| 1357 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 1358 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 1359 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 1360 |
+
"step": 1350
|
| 1361 |
+
},
|
| 1362 |
+
{
|
| 1363 |
+
"epoch": 1.8655692729766804,
|
| 1364 |
+
"grad_norm": 0.6392534971237183,
|
| 1365 |
+
"learning_rate": 0.00014590355828015574,
|
| 1366 |
+
"loss": 0.6697,
|
| 1367 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 1368 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 1369 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 1370 |
+
"step": 1360
|
| 1371 |
+
},
|
| 1372 |
+
{
|
| 1373 |
+
"epoch": 1.879286694101509,
|
| 1374 |
+
"grad_norm": 6.284060478210449,
|
| 1375 |
+
"learning_rate": 0.00014511341422922275,
|
| 1376 |
+
"loss": 0.659,
|
| 1377 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 1378 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 1379 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 1380 |
+
"step": 1370
|
| 1381 |
+
},
|
| 1382 |
+
{
|
| 1383 |
+
"epoch": 1.8930041152263375,
|
| 1384 |
+
"grad_norm": 1.1013621091842651,
|
| 1385 |
+
"learning_rate": 0.00014432124511875734,
|
| 1386 |
+
"loss": 0.6624,
|
| 1387 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 1388 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 1389 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 1390 |
+
"step": 1380
|
| 1391 |
+
},
|
| 1392 |
+
{
|
| 1393 |
+
"epoch": 1.906721536351166,
|
| 1394 |
+
"grad_norm": 0.6934658885002136,
|
| 1395 |
+
"learning_rate": 0.0001435271570921884,
|
| 1396 |
+
"loss": 0.7113,
|
| 1397 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 1398 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 1399 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 1400 |
+
"step": 1390
|
| 1401 |
+
},
|
| 1402 |
+
{
|
| 1403 |
+
"epoch": 1.9204389574759944,
|
| 1404 |
+
"grad_norm": 0.9055446982383728,
|
| 1405 |
+
"learning_rate": 0.00014273125655006204,
|
| 1406 |
+
"loss": 0.6681,
|
| 1407 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 1408 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 1409 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 1410 |
+
"step": 1400
|
| 1411 |
+
},
|
| 1412 |
+
{
|
| 1413 |
+
"epoch": 1.934156378600823,
|
| 1414 |
+
"grad_norm": 0.6644291877746582,
|
| 1415 |
+
"learning_rate": 0.00014193365013578495,
|
| 1416 |
+
"loss": 0.6795,
|
| 1417 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 1418 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 1419 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 1420 |
+
"step": 1410
|
| 1421 |
+
},
|
| 1422 |
+
{
|
| 1423 |
+
"epoch": 1.9478737997256514,
|
| 1424 |
+
"grad_norm": 0.7042267322540283,
|
| 1425 |
+
"learning_rate": 0.00014113444472133504,
|
| 1426 |
+
"loss": 0.7092,
|
| 1427 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 1428 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 1429 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 1430 |
+
"step": 1420
|
| 1431 |
+
},
|
| 1432 |
+
{
|
| 1433 |
+
"epoch": 1.96159122085048,
|
| 1434 |
+
"grad_norm": 0.8393681645393372,
|
| 1435 |
+
"learning_rate": 0.00014033374739294175,
|
| 1436 |
+
"loss": 0.7237,
|
| 1437 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 1438 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 1439 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 1440 |
+
"step": 1430
|
| 1441 |
+
},
|
| 1442 |
+
{
|
| 1443 |
+
"epoch": 1.9753086419753085,
|
| 1444 |
+
"grad_norm": 0.7323784828186035,
|
| 1445 |
+
"learning_rate": 0.00013953166543673726,
|
| 1446 |
+
"loss": 0.6498,
|
| 1447 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 1448 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 1449 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 1450 |
+
"step": 1440
|
| 1451 |
+
},
|
| 1452 |
+
{
|
| 1453 |
+
"epoch": 1.989026063100137,
|
| 1454 |
+
"grad_norm": 4.478516101837158,
|
| 1455 |
+
"learning_rate": 0.00013872830632438135,
|
| 1456 |
+
"loss": 0.6736,
|
| 1457 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 1458 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 1459 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 1460 |
+
"step": 1450
|
| 1461 |
+
},
|
| 1462 |
+
{
|
| 1463 |
+
"epoch": 2.0027434842249656,
|
| 1464 |
+
"grad_norm": 0.7760154008865356,
|
| 1465 |
+
"learning_rate": 0.00013792377769866092,
|
| 1466 |
+
"loss": 0.6382,
|
| 1467 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 1468 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 1469 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 1470 |
+
"step": 1460
|
| 1471 |
+
},
|
| 1472 |
+
{
|
| 1473 |
+
"epoch": 2.016460905349794,
|
| 1474 |
+
"grad_norm": 0.7415499687194824,
|
| 1475 |
+
"learning_rate": 0.00013711818735906707,
|
| 1476 |
+
"loss": 0.5146,
|
| 1477 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 1478 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 1479 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 1480 |
+
"step": 1470
|
| 1481 |
+
},
|
| 1482 |
+
{
|
| 1483 |
+
"epoch": 2.0301783264746227,
|
| 1484 |
+
"grad_norm": 0.7225642800331116,
|
| 1485 |
+
"learning_rate": 0.00013631164324735094,
|
| 1486 |
+
"loss": 0.4975,
|
| 1487 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 1488 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 1489 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 1490 |
+
"step": 1480
|
| 1491 |
+
},
|
| 1492 |
+
{
|
| 1493 |
+
"epoch": 2.0438957475994513,
|
| 1494 |
+
"grad_norm": 0.8565766215324402,
|
| 1495 |
+
"learning_rate": 0.0001355042534330603,
|
| 1496 |
+
"loss": 0.51,
|
| 1497 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 1498 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 1499 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 1500 |
+
"step": 1490
|
| 1501 |
+
},
|
| 1502 |
+
{
|
| 1503 |
+
"epoch": 2.05761316872428,
|
| 1504 |
+
"grad_norm": 0.7800817489624023,
|
| 1505 |
+
"learning_rate": 0.00013469612609905938,
|
| 1506 |
+
"loss": 0.4937,
|
| 1507 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 1508 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 1509 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 1510 |
+
"step": 1500
|
| 1511 |
+
},
|
| 1512 |
+
{
|
| 1513 |
+
"epoch": 2.0713305898491083,
|
| 1514 |
+
"grad_norm": 0.6647763252258301,
|
| 1515 |
+
"learning_rate": 0.00013388736952703334,
|
| 1516 |
+
"loss": 0.4843,
|
| 1517 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 1518 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 1519 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 1520 |
+
"step": 1510
|
| 1521 |
+
},
|
| 1522 |
+
{
|
| 1523 |
+
"epoch": 2.085048010973937,
|
| 1524 |
+
"grad_norm": 3.73032808303833,
|
| 1525 |
+
"learning_rate": 0.0001330780920829795,
|
| 1526 |
+
"loss": 0.5292,
|
| 1527 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 1528 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 1529 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 1530 |
+
"step": 1520
|
| 1531 |
+
},
|
| 1532 |
+
{
|
| 1533 |
+
"epoch": 2.0987654320987654,
|
| 1534 |
+
"grad_norm": 0.7846357226371765,
|
| 1535 |
+
"learning_rate": 0.00013226840220268725,
|
| 1536 |
+
"loss": 0.5054,
|
| 1537 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 1538 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 1539 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 1540 |
+
"step": 1530
|
| 1541 |
+
},
|
| 1542 |
+
{
|
| 1543 |
+
"epoch": 2.112482853223594,
|
| 1544 |
+
"grad_norm": 0.7564026117324829,
|
| 1545 |
+
"learning_rate": 0.00013145840837720866,
|
| 1546 |
+
"loss": 0.5101,
|
| 1547 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 1548 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 1549 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 1550 |
+
"step": 1540
|
| 1551 |
+
},
|
| 1552 |
+
{
|
| 1553 |
+
"epoch": 2.1262002743484225,
|
| 1554 |
+
"grad_norm": 2.6172327995300293,
|
| 1555 |
+
"learning_rate": 0.00013064821913832172,
|
| 1556 |
+
"loss": 0.4932,
|
| 1557 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 1558 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 1559 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 1560 |
+
"step": 1550
|
| 1561 |
+
},
|
| 1562 |
+
{
|
| 1563 |
+
"epoch": 2.139917695473251,
|
| 1564 |
+
"grad_norm": 0.9523964524269104,
|
| 1565 |
+
"learning_rate": 0.00012983794304398803,
|
| 1566 |
+
"loss": 0.4972,
|
| 1567 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 1568 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 1569 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 1570 |
+
"step": 1560
|
| 1571 |
+
},
|
| 1572 |
+
{
|
| 1573 |
+
"epoch": 2.1536351165980796,
|
| 1574 |
+
"grad_norm": 0.7088386416435242,
|
| 1575 |
+
"learning_rate": 0.00012902768866380698,
|
| 1576 |
+
"loss": 0.5183,
|
| 1577 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 1578 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 1579 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 1580 |
+
"step": 1570
|
| 1581 |
+
},
|
| 1582 |
+
{
|
| 1583 |
+
"epoch": 2.167352537722908,
|
| 1584 |
+
"grad_norm": 0.7109506726264954,
|
| 1585 |
+
"learning_rate": 0.00012821756456446844,
|
| 1586 |
+
"loss": 0.5372,
|
| 1587 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 1588 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 1589 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 1590 |
+
"step": 1580
|
| 1591 |
+
},
|
| 1592 |
+
{
|
| 1593 |
+
"epoch": 2.1810699588477367,
|
| 1594 |
+
"grad_norm": 0.789664089679718,
|
| 1595 |
+
"learning_rate": 0.000127407679295206,
|
| 1596 |
+
"loss": 0.5016,
|
| 1597 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 1598 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 1599 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 1600 |
+
"step": 1590
|
| 1601 |
+
},
|
| 1602 |
+
{
|
| 1603 |
+
"epoch": 2.1947873799725652,
|
| 1604 |
+
"grad_norm": 0.7248480319976807,
|
| 1605 |
+
"learning_rate": 0.00012659814137325204,
|
| 1606 |
+
"loss": 0.5071,
|
| 1607 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 1608 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 1609 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 1610 |
+
"step": 1600
|
| 1611 |
+
},
|
| 1612 |
+
{
|
| 1613 |
+
"epoch": 2.2085048010973938,
|
| 1614 |
+
"grad_norm": 0.7603122591972351,
|
| 1615 |
+
"learning_rate": 0.00012578905926929757,
|
| 1616 |
+
"loss": 0.5209,
|
| 1617 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 1618 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 1619 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 1620 |
+
"step": 1610
|
| 1621 |
+
},
|
| 1622 |
+
{
|
| 1623 |
+
"epoch": 2.2222222222222223,
|
| 1624 |
+
"grad_norm": 0.946079671382904,
|
| 1625 |
+
"learning_rate": 0.00012498054139295826,
|
| 1626 |
+
"loss": 0.51,
|
| 1627 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 1628 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 1629 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 1630 |
+
"step": 1620
|
| 1631 |
+
},
|
| 1632 |
+
{
|
| 1633 |
+
"epoch": 2.235939643347051,
|
| 1634 |
+
"grad_norm": 0.6936349868774414,
|
| 1635 |
+
"learning_rate": 0.00012417269607824832,
|
| 1636 |
+
"loss": 0.5253,
|
| 1637 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 1638 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 1639 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 1640 |
+
"step": 1630
|
| 1641 |
+
},
|
| 1642 |
+
{
|
| 1643 |
+
"epoch": 2.2496570644718794,
|
| 1644 |
+
"grad_norm": 0.8792118430137634,
|
| 1645 |
+
"learning_rate": 0.00012336563156906496,
|
| 1646 |
+
"loss": 0.5161,
|
| 1647 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 1648 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 1649 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 1650 |
+
"step": 1640
|
| 1651 |
+
},
|
| 1652 |
+
{
|
| 1653 |
+
"epoch": 2.263374485596708,
|
| 1654 |
+
"grad_norm": 0.7459379434585571,
|
| 1655 |
+
"learning_rate": 0.0001225594560046844,
|
| 1656 |
+
"loss": 0.5124,
|
| 1657 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 1658 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 1659 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 1660 |
+
"step": 1650
|
| 1661 |
+
},
|
| 1662 |
+
{
|
| 1663 |
+
"epoch": 2.2770919067215365,
|
| 1664 |
+
"grad_norm": 0.7608845233917236,
|
| 1665 |
+
"learning_rate": 0.00012175427740527264,
|
| 1666 |
+
"loss": 0.5483,
|
| 1667 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 1668 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 1669 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 1670 |
+
"step": 1660
|
| 1671 |
+
},
|
| 1672 |
+
{
|
| 1673 |
+
"epoch": 2.290809327846365,
|
| 1674 |
+
"grad_norm": 2.453911781311035,
|
| 1675 |
+
"learning_rate": 0.00012095020365741114,
|
| 1676 |
+
"loss": 0.5328,
|
| 1677 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 1678 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 1679 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 1680 |
+
"step": 1670
|
| 1681 |
+
},
|
| 1682 |
+
{
|
| 1683 |
+
"epoch": 2.3045267489711936,
|
| 1684 |
+
"grad_norm": 0.7783582806587219,
|
| 1685 |
+
"learning_rate": 0.00012014734249964163,
|
| 1686 |
+
"loss": 0.5102,
|
| 1687 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 1688 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 1689 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 1690 |
+
"step": 1680
|
| 1691 |
+
},
|
| 1692 |
+
{
|
| 1693 |
+
"epoch": 2.318244170096022,
|
| 1694 |
+
"grad_norm": 0.7636036276817322,
|
| 1695 |
+
"learning_rate": 0.00011934580150802968,
|
| 1696 |
+
"loss": 0.5447,
|
| 1697 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 1698 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 1699 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 1700 |
+
"step": 1690
|
| 1701 |
+
},
|
| 1702 |
+
{
|
| 1703 |
+
"epoch": 2.3319615912208507,
|
| 1704 |
+
"grad_norm": 0.8092122077941895,
|
| 1705 |
+
"learning_rate": 0.00011854568808175073,
|
| 1706 |
+
"loss": 0.5467,
|
| 1707 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 1708 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 1709 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 1710 |
+
"step": 1700
|
| 1711 |
+
},
|
| 1712 |
+
{
|
| 1713 |
+
"epoch": 2.3456790123456788,
|
| 1714 |
+
"grad_norm": 0.8830114006996155,
|
| 1715 |
+
"learning_rate": 0.0001177471094286994,
|
| 1716 |
+
"loss": 0.5321,
|
| 1717 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 1718 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 1719 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 1720 |
+
"step": 1710
|
| 1721 |
+
},
|
| 1722 |
+
{
|
| 1723 |
+
"epoch": 2.3593964334705078,
|
| 1724 |
+
"grad_norm": 0.7924231886863708,
|
| 1725 |
+
"learning_rate": 0.00011695017255112479,
|
| 1726 |
+
"loss": 0.5538,
|
| 1727 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 1728 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 1729 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 1730 |
+
"step": 1720
|
| 1731 |
+
},
|
| 1732 |
+
{
|
| 1733 |
+
"epoch": 2.373113854595336,
|
| 1734 |
+
"grad_norm": 0.7238515615463257,
|
| 1735 |
+
"learning_rate": 0.00011615498423129302,
|
| 1736 |
+
"loss": 0.5552,
|
| 1737 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 1738 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 1739 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 1740 |
+
"step": 1730
|
| 1741 |
+
},
|
| 1742 |
+
{
|
| 1743 |
+
"epoch": 2.386831275720165,
|
| 1744 |
+
"grad_norm": 0.9980413317680359,
|
| 1745 |
+
"learning_rate": 0.00011536165101717955,
|
| 1746 |
+
"loss": 0.5397,
|
| 1747 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 1748 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 1749 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 1750 |
+
"step": 1740
|
| 1751 |
+
},
|
| 1752 |
+
{
|
| 1753 |
+
"epoch": 2.400548696844993,
|
| 1754 |
+
"grad_norm": 0.8962424397468567,
|
| 1755 |
+
"learning_rate": 0.00011457027920819245,
|
| 1756 |
+
"loss": 0.5394,
|
| 1757 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 1758 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 1759 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 1760 |
+
"step": 1750
|
| 1761 |
+
},
|
| 1762 |
+
{
|
| 1763 |
+
"epoch": 2.4142661179698215,
|
| 1764 |
+
"grad_norm": 0.9112607836723328,
|
| 1765 |
+
"learning_rate": 0.00011378097484092954,
|
| 1766 |
+
"loss": 0.5615,
|
| 1767 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 1768 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 1769 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 1770 |
+
"step": 1760
|
| 1771 |
+
},
|
| 1772 |
+
{
|
| 1773 |
+
"epoch": 2.42798353909465,
|
| 1774 |
+
"grad_norm": 0.8417477607727051,
|
| 1775 |
+
"learning_rate": 0.00011299384367497018,
|
| 1776 |
+
"loss": 0.5208,
|
| 1777 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 1778 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 1779 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 1780 |
+
"step": 1770
|
| 1781 |
+
},
|
| 1782 |
+
{
|
| 1783 |
+
"epoch": 2.4417009602194786,
|
| 1784 |
+
"grad_norm": 0.8456352353096008,
|
| 1785 |
+
"learning_rate": 0.00011220899117870478,
|
| 1786 |
+
"loss": 0.516,
|
| 1787 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 1788 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 1789 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 1790 |
+
"step": 1780
|
| 1791 |
+
},
|
| 1792 |
+
{
|
| 1793 |
+
"epoch": 2.455418381344307,
|
| 1794 |
+
"grad_norm": 0.8153683543205261,
|
| 1795 |
+
"learning_rate": 0.00011142652251520264,
|
| 1796 |
+
"loss": 0.5437,
|
| 1797 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 1798 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 1799 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 1800 |
+
"step": 1790
|
| 1801 |
+
},
|
| 1802 |
+
{
|
| 1803 |
+
"epoch": 2.4691358024691357,
|
| 1804 |
+
"grad_norm": 0.7875564694404602,
|
| 1805 |
+
"learning_rate": 0.00011064654252812138,
|
| 1806 |
+
"loss": 0.5577,
|
| 1807 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 1808 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 1809 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 1810 |
+
"step": 1800
|
| 1811 |
+
},
|
| 1812 |
+
{
|
| 1813 |
+
"epoch": 2.482853223593964,
|
| 1814 |
+
"grad_norm": 0.7574247717857361,
|
| 1815 |
+
"learning_rate": 0.0001098691557276586,
|
| 1816 |
+
"loss": 0.5037,
|
| 1817 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 1818 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 1819 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 1820 |
+
"step": 1810
|
| 1821 |
+
},
|
| 1822 |
+
{
|
| 1823 |
+
"epoch": 2.4965706447187928,
|
| 1824 |
+
"grad_norm": 0.8989032506942749,
|
| 1825 |
+
"learning_rate": 0.00010909446627654856,
|
| 1826 |
+
"loss": 0.5816,
|
| 1827 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 1828 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 1829 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 1830 |
+
"step": 1820
|
| 1831 |
+
},
|
| 1832 |
+
{
|
| 1833 |
+
"epoch": 2.5102880658436213,
|
| 1834 |
+
"grad_norm": 0.7678958177566528,
|
| 1835 |
+
"learning_rate": 0.00010832257797610541,
|
| 1836 |
+
"loss": 0.5178,
|
| 1837 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 1838 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 1839 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 1840 |
+
"step": 1830
|
| 1841 |
+
},
|
| 1842 |
+
{
|
| 1843 |
+
"epoch": 2.52400548696845,
|
| 1844 |
+
"grad_norm": 0.7127401828765869,
|
| 1845 |
+
"learning_rate": 0.0001075535942523146,
|
| 1846 |
+
"loss": 0.5007,
|
| 1847 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 1848 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 1849 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 1850 |
+
"step": 1840
|
| 1851 |
+
},
|
| 1852 |
+
{
|
| 1853 |
+
"epoch": 2.5377229080932784,
|
| 1854 |
+
"grad_norm": 0.8298234343528748,
|
| 1855 |
+
"learning_rate": 0.00010678761814197491,
|
| 1856 |
+
"loss": 0.5464,
|
| 1857 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 1858 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 1859 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 1860 |
+
"step": 1850
|
| 1861 |
+
},
|
| 1862 |
+
{
|
| 1863 |
+
"epoch": 2.551440329218107,
|
| 1864 |
+
"grad_norm": 0.8467006087303162,
|
| 1865 |
+
"learning_rate": 0.00010602475227889228,
|
| 1866 |
+
"loss": 0.5369,
|
| 1867 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 1868 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 1869 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 1870 |
+
"step": 1860
|
| 1871 |
+
},
|
| 1872 |
+
{
|
| 1873 |
+
"epoch": 2.5651577503429355,
|
| 1874 |
+
"grad_norm": 0.8315374255180359,
|
| 1875 |
+
"learning_rate": 0.00010526509888012803,
|
| 1876 |
+
"loss": 0.5154,
|
| 1877 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 1878 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 1879 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 1880 |
+
"step": 1870
|
| 1881 |
+
},
|
| 1882 |
+
{
|
| 1883 |
+
"epoch": 2.578875171467764,
|
| 1884 |
+
"grad_norm": 0.8053838610649109,
|
| 1885 |
+
"learning_rate": 0.00010450875973230246,
|
| 1886 |
+
"loss": 0.5551,
|
| 1887 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 1888 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 1889 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 1890 |
+
"step": 1880
|
| 1891 |
+
},
|
| 1892 |
+
{
|
| 1893 |
+
"epoch": 2.5925925925925926,
|
| 1894 |
+
"grad_norm": 0.7011913657188416,
|
| 1895 |
+
"learning_rate": 0.00010375583617795659,
|
| 1896 |
+
"loss": 0.5243,
|
| 1897 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 1898 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 1899 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 1900 |
+
"step": 1890
|
| 1901 |
+
},
|
| 1902 |
+
{
|
| 1903 |
+
"epoch": 2.606310013717421,
|
| 1904 |
+
"grad_norm": 0.7647907137870789,
|
| 1905 |
+
"learning_rate": 0.00010300642910197304,
|
| 1906 |
+
"loss": 0.5601,
|
| 1907 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 1908 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 1909 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 1910 |
+
"step": 1900
|
| 1911 |
+
},
|
| 1912 |
+
{
|
| 1913 |
+
"epoch": 2.6200274348422496,
|
| 1914 |
+
"grad_norm": 0.7914022207260132,
|
| 1915 |
+
"learning_rate": 0.0001022606389180585,
|
| 1916 |
+
"loss": 0.545,
|
| 1917 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 1918 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 1919 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 1920 |
+
"step": 1910
|
| 1921 |
+
},
|
| 1922 |
+
{
|
| 1923 |
+
"epoch": 2.633744855967078,
|
| 1924 |
+
"grad_norm": 0.7425740361213684,
|
| 1925 |
+
"learning_rate": 0.00010151856555528907,
|
| 1926 |
+
"loss": 0.5305,
|
| 1927 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 1928 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 1929 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 1930 |
+
"step": 1920
|
| 1931 |
+
},
|
| 1932 |
+
{
|
| 1933 |
+
"epoch": 2.6474622770919067,
|
| 1934 |
+
"grad_norm": 0.7688199877738953,
|
| 1935 |
+
"learning_rate": 0.0001007803084447208,
|
| 1936 |
+
"loss": 0.5683,
|
| 1937 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 1938 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 1939 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 1940 |
+
"step": 1930
|
| 1941 |
+
},
|
| 1942 |
+
{
|
| 1943 |
+
"epoch": 2.6611796982167353,
|
| 1944 |
+
"grad_norm": 0.7170693874359131,
|
| 1945 |
+
"learning_rate": 0.00010004596650606673,
|
| 1946 |
+
"loss": 0.5388,
|
| 1947 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 1948 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 1949 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 1950 |
+
"step": 1940
|
| 1951 |
+
},
|
| 1952 |
+
{
|
| 1953 |
+
"epoch": 2.674897119341564,
|
| 1954 |
+
"grad_norm": 0.7940158247947693,
|
| 1955 |
+
"learning_rate": 9.931563813444269e-05,
|
| 1956 |
+
"loss": 0.5474,
|
| 1957 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 1958 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 1959 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 1960 |
+
"step": 1950
|
| 1961 |
+
},
|
| 1962 |
+
{
|
| 1963 |
+
"epoch": 2.6886145404663924,
|
| 1964 |
+
"grad_norm": 0.7597416043281555,
|
| 1965 |
+
"learning_rate": 9.858942118718306e-05,
|
| 1966 |
+
"loss": 0.4845,
|
| 1967 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 1968 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 1969 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 1970 |
+
"step": 1960
|
| 1971 |
+
},
|
| 1972 |
+
{
|
| 1973 |
+
"epoch": 2.702331961591221,
|
| 1974 |
+
"grad_norm": 2.3203823566436768,
|
| 1975 |
+
"learning_rate": 9.786741297072906e-05,
|
| 1976 |
+
"loss": 0.559,
|
| 1977 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 1978 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 1979 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 1980 |
+
"step": 1970
|
| 1981 |
+
},
|
| 1982 |
+
{
|
| 1983 |
+
"epoch": 2.7160493827160495,
|
| 1984 |
+
"grad_norm": 2.501943349838257,
|
| 1985 |
+
"learning_rate": 9.714971022759012e-05,
|
| 1986 |
+
"loss": 0.5723,
|
| 1987 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 1988 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 1989 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 1990 |
+
"step": 1980
|
| 1991 |
+
},
|
| 1992 |
+
{
|
| 1993 |
+
"epoch": 2.729766803840878,
|
| 1994 |
+
"grad_norm": 0.7488245964050293,
|
| 1995 |
+
"learning_rate": 9.64364091233819e-05,
|
| 1996 |
+
"loss": 0.5359,
|
| 1997 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 1998 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 1999 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 2000 |
+
"step": 1990
|
| 2001 |
+
},
|
| 2002 |
+
{
|
| 2003 |
+
"epoch": 2.7434842249657065,
|
| 2004 |
+
"grad_norm": 0.8807633519172668,
|
| 2005 |
+
"learning_rate": 9.57276052339403e-05,
|
| 2006 |
+
"loss": 0.5554,
|
| 2007 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 2008 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 2009 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 2010 |
+
"step": 2000
|
| 2011 |
+
},
|
| 2012 |
+
{
|
| 2013 |
+
"epoch": 2.757201646090535,
|
| 2014 |
+
"grad_norm": 0.8114855885505676,
|
| 2015 |
+
"learning_rate": 9.502339353251581e-05,
|
| 2016 |
+
"loss": 0.5416,
|
| 2017 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 2018 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 2019 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 2020 |
+
"step": 2010
|
| 2021 |
+
},
|
| 2022 |
+
{
|
| 2023 |
+
"epoch": 2.7709190672153636,
|
| 2024 |
+
"grad_norm": 0.7909035682678223,
|
| 2025 |
+
"learning_rate": 9.432386837704732e-05,
|
| 2026 |
+
"loss": 0.5306,
|
| 2027 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 2028 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 2029 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 2030 |
+
"step": 2020
|
| 2031 |
+
},
|
| 2032 |
+
{
|
| 2033 |
+
"epoch": 2.784636488340192,
|
| 2034 |
+
"grad_norm": 0.7736451625823975,
|
| 2035 |
+
"learning_rate": 9.362912349751967e-05,
|
| 2036 |
+
"loss": 0.5286,
|
| 2037 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 2038 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 2039 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 2040 |
+
"step": 2030
|
| 2041 |
+
},
|
| 2042 |
+
{
|
| 2043 |
+
"epoch": 2.7983539094650207,
|
| 2044 |
+
"grad_norm": 0.8794904351234436,
|
| 2045 |
+
"learning_rate": 9.293925198340407e-05,
|
| 2046 |
+
"loss": 0.5407,
|
| 2047 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 2048 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 2049 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 2050 |
+
"step": 2040
|
| 2051 |
+
},
|
| 2052 |
+
{
|
| 2053 |
+
"epoch": 2.8120713305898493,
|
| 2054 |
+
"grad_norm": 0.7630151510238647,
|
| 2055 |
+
"learning_rate": 9.22543462711855e-05,
|
| 2056 |
+
"loss": 0.5468,
|
| 2057 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 2058 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 2059 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 2060 |
+
"step": 2050
|
| 2061 |
+
},
|
| 2062 |
+
{
|
| 2063 |
+
"epoch": 2.825788751714678,
|
| 2064 |
+
"grad_norm": 0.8964723944664001,
|
| 2065 |
+
"learning_rate": 9.15744981319767e-05,
|
| 2066 |
+
"loss": 0.5619,
|
| 2067 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 2068 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 2069 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 2070 |
+
"step": 2060
|
| 2071 |
+
},
|
| 2072 |
+
{
|
| 2073 |
+
"epoch": 2.8395061728395063,
|
| 2074 |
+
"grad_norm": 0.80915766954422,
|
| 2075 |
+
"learning_rate": 9.089979865922174e-05,
|
| 2076 |
+
"loss": 0.5236,
|
| 2077 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 2078 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 2079 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 2080 |
+
"step": 2070
|
| 2081 |
+
},
|
| 2082 |
+
{
|
| 2083 |
+
"epoch": 2.8532235939643344,
|
| 2084 |
+
"grad_norm": 0.8071470260620117,
|
| 2085 |
+
"learning_rate": 9.023033825649055e-05,
|
| 2086 |
+
"loss": 0.5107,
|
| 2087 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 2088 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 2089 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 2090 |
+
"step": 2080
|
| 2091 |
+
},
|
| 2092 |
+
{
|
| 2093 |
+
"epoch": 2.8669410150891634,
|
| 2094 |
+
"grad_norm": 0.8840852379798889,
|
| 2095 |
+
"learning_rate": 8.956620662536533e-05,
|
| 2096 |
+
"loss": 0.5634,
|
| 2097 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 2098 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 2099 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 2100 |
+
"step": 2090
|
| 2101 |
+
},
|
| 2102 |
+
{
|
| 2103 |
+
"epoch": 2.8806584362139915,
|
| 2104 |
+
"grad_norm": 0.7312631011009216,
|
| 2105 |
+
"learning_rate": 8.890749275342172e-05,
|
| 2106 |
+
"loss": 0.5474,
|
| 2107 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 2108 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 2109 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 2110 |
+
"step": 2100
|
| 2111 |
+
},
|
| 2112 |
+
{
|
| 2113 |
+
"epoch": 2.8943758573388205,
|
| 2114 |
+
"grad_norm": 0.7186003923416138,
|
| 2115 |
+
"learning_rate": 8.82542849023049e-05,
|
| 2116 |
+
"loss": 0.5145,
|
| 2117 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 2118 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 2119 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 2120 |
+
"step": 2110
|
| 2121 |
+
},
|
| 2122 |
+
{
|
| 2123 |
+
"epoch": 2.9080932784636486,
|
| 2124 |
+
"grad_norm": 0.8214620351791382,
|
| 2125 |
+
"learning_rate": 8.760667059590368e-05,
|
| 2126 |
+
"loss": 0.5331,
|
| 2127 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 2128 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 2129 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 2130 |
+
"step": 2120
|
| 2131 |
+
},
|
| 2132 |
+
{
|
| 2133 |
+
"epoch": 2.9218106995884776,
|
| 2134 |
+
"grad_norm": 0.7750139832496643,
|
| 2135 |
+
"learning_rate": 8.696473660862283e-05,
|
| 2136 |
+
"loss": 0.5462,
|
| 2137 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 2138 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 2139 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 2140 |
+
"step": 2130
|
| 2141 |
+
},
|
| 2142 |
+
{
|
| 2143 |
+
"epoch": 2.9355281207133057,
|
| 2144 |
+
"grad_norm": 0.78326016664505,
|
| 2145 |
+
"learning_rate": 8.632856895375632e-05,
|
| 2146 |
+
"loss": 0.5477,
|
| 2147 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 2148 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 2149 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 2150 |
+
"step": 2140
|
| 2151 |
+
},
|
| 2152 |
+
{
|
| 2153 |
+
"epoch": 2.9492455418381347,
|
| 2154 |
+
"grad_norm": 0.7657549977302551,
|
| 2155 |
+
"learning_rate": 8.569825287196208e-05,
|
| 2156 |
+
"loss": 0.5261,
|
| 2157 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 2158 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 2159 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 2160 |
+
"step": 2150
|
| 2161 |
+
},
|
| 2162 |
+
{
|
| 2163 |
+
"epoch": 2.962962962962963,
|
| 2164 |
+
"grad_norm": 0.9171452522277832,
|
| 2165 |
+
"learning_rate": 8.507387281984083e-05,
|
| 2166 |
+
"loss": 0.5434,
|
| 2167 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 2168 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 2169 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 2170 |
+
"step": 2160
|
| 2171 |
+
},
|
| 2172 |
+
{
|
| 2173 |
+
"epoch": 2.9766803840877913,
|
| 2174 |
+
"grad_norm": 1.8923577070236206,
|
| 2175 |
+
"learning_rate": 8.445551245861934e-05,
|
| 2176 |
+
"loss": 0.5523,
|
| 2177 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 2178 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 2179 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 2180 |
+
"step": 2170
|
| 2181 |
+
},
|
| 2182 |
+
{
|
| 2183 |
+
"epoch": 2.99039780521262,
|
| 2184 |
+
"grad_norm": 0.7663477063179016,
|
| 2185 |
+
"learning_rate": 8.384325464294096e-05,
|
| 2186 |
+
"loss": 0.553,
|
| 2187 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 2188 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 2189 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 2190 |
+
"step": 2180
|
| 2191 |
+
},
|
| 2192 |
+
{
|
| 2193 |
+
"epoch": 3.0041152263374484,
|
| 2194 |
+
"grad_norm": 0.7628344297409058,
|
| 2195 |
+
"learning_rate": 8.323718140976341e-05,
|
| 2196 |
+
"loss": 0.4983,
|
| 2197 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 2198 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 2199 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 2200 |
+
"step": 2190
|
| 2201 |
+
},
|
| 2202 |
+
{
|
| 2203 |
+
"epoch": 3.017832647462277,
|
| 2204 |
+
"grad_norm": 0.7593643069267273,
|
| 2205 |
+
"learning_rate": 8.263737396736702e-05,
|
| 2206 |
+
"loss": 0.3582,
|
| 2207 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 2208 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 2209 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 2210 |
+
"step": 2200
|
| 2211 |
+
},
|
| 2212 |
+
{
|
| 2213 |
+
"epoch": 3.0315500685871055,
|
| 2214 |
+
"grad_norm": 0.712845504283905,
|
| 2215 |
+
"learning_rate": 8.204391268447322e-05,
|
| 2216 |
+
"loss": 0.3437,
|
| 2217 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 2218 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 2219 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 2220 |
+
"step": 2210
|
| 2221 |
+
},
|
| 2222 |
+
{
|
| 2223 |
+
"epoch": 3.045267489711934,
|
| 2224 |
+
"grad_norm": 0.8284991979598999,
|
| 2225 |
+
"learning_rate": 8.145687707947609e-05,
|
| 2226 |
+
"loss": 0.3391,
|
| 2227 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 2228 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 2229 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 2230 |
+
"step": 2220
|
| 2231 |
+
},
|
| 2232 |
+
{
|
| 2233 |
+
"epoch": 3.0589849108367626,
|
| 2234 |
+
"grad_norm": 0.8405755162239075,
|
| 2235 |
+
"learning_rate": 8.087634580978748e-05,
|
| 2236 |
+
"loss": 0.3439,
|
| 2237 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 2238 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 2239 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 2240 |
+
"step": 2230
|
| 2241 |
+
},
|
| 2242 |
+
{
|
| 2243 |
+
"epoch": 3.072702331961591,
|
| 2244 |
+
"grad_norm": 0.7382900714874268,
|
| 2245 |
+
"learning_rate": 8.03023966612977e-05,
|
| 2246 |
+
"loss": 0.3752,
|
| 2247 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 2248 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 2249 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 2250 |
+
"step": 2240
|
| 2251 |
+
},
|
| 2252 |
+
{
|
| 2253 |
+
"epoch": 3.0864197530864197,
|
| 2254 |
+
"grad_norm": 0.9108150601387024,
|
| 2255 |
+
"learning_rate": 7.973510653795295e-05,
|
| 2256 |
+
"loss": 0.3502,
|
| 2257 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 2258 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 2259 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 2260 |
+
"step": 2250
|
| 2261 |
+
},
|
| 2262 |
+
{
|
| 2263 |
+
"epoch": 3.1001371742112482,
|
| 2264 |
+
"grad_norm": 0.7082058191299438,
|
| 2265 |
+
"learning_rate": 7.917455145145076e-05,
|
| 2266 |
+
"loss": 0.3479,
|
| 2267 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 2268 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 2269 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 2270 |
+
"step": 2260
|
| 2271 |
+
},
|
| 2272 |
+
{
|
| 2273 |
+
"epoch": 3.113854595336077,
|
| 2274 |
+
"grad_norm": 0.82919842004776,
|
| 2275 |
+
"learning_rate": 7.862080651105533e-05,
|
| 2276 |
+
"loss": 0.3725,
|
| 2277 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 2278 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 2279 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 2280 |
+
"step": 2270
|
| 2281 |
+
},
|
| 2282 |
+
{
|
| 2283 |
+
"epoch": 3.1275720164609053,
|
| 2284 |
+
"grad_norm": 0.7340407371520996,
|
| 2285 |
+
"learning_rate": 7.807394591353337e-05,
|
| 2286 |
+
"loss": 0.381,
|
| 2287 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 2288 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 2289 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 2290 |
+
"step": 2280
|
| 2291 |
+
},
|
| 2292 |
+
{
|
| 2293 |
+
"epoch": 3.141289437585734,
|
| 2294 |
+
"grad_norm": 0.8041258454322815,
|
| 2295 |
+
"learning_rate": 7.75340429332125e-05,
|
| 2296 |
+
"loss": 0.3991,
|
| 2297 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 2298 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 2299 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 2300 |
+
"step": 2290
|
| 2301 |
+
},
|
| 2302 |
+
{
|
| 2303 |
+
"epoch": 3.1550068587105624,
|
| 2304 |
+
"grad_norm": 0.7833622097969055,
|
| 2305 |
+
"learning_rate": 7.700116991216316e-05,
|
| 2306 |
+
"loss": 0.3595,
|
| 2307 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 2308 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 2309 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 2310 |
+
"step": 2300
|
| 2311 |
+
},
|
| 2312 |
+
{
|
| 2313 |
+
"epoch": 3.168724279835391,
|
| 2314 |
+
"grad_norm": 0.8091015815734863,
|
| 2315 |
+
"learning_rate": 7.647539825050549e-05,
|
| 2316 |
+
"loss": 0.3828,
|
| 2317 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 2318 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 2319 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 2320 |
+
"step": 2310
|
| 2321 |
+
},
|
| 2322 |
+
{
|
| 2323 |
+
"epoch": 3.1824417009602195,
|
| 2324 |
+
"grad_norm": 0.8447887301445007,
|
| 2325 |
+
"learning_rate": 7.595679839684217e-05,
|
| 2326 |
+
"loss": 0.3633,
|
| 2327 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 2328 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 2329 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 2330 |
+
"step": 2320
|
| 2331 |
+
},
|
| 2332 |
+
{
|
| 2333 |
+
"epoch": 3.196159122085048,
|
| 2334 |
+
"grad_norm": 0.8927395939826965,
|
| 2335 |
+
"learning_rate": 7.54454398388192e-05,
|
| 2336 |
+
"loss": 0.3581,
|
| 2337 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 2338 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 2339 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 2340 |
+
"step": 2330
|
| 2341 |
+
},
|
| 2342 |
+
{
|
| 2343 |
+
"epoch": 3.2098765432098766,
|
| 2344 |
+
"grad_norm": 0.8085030913352966,
|
| 2345 |
+
"learning_rate": 7.494139109381503e-05,
|
| 2346 |
+
"loss": 0.3692,
|
| 2347 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 2348 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 2349 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 2350 |
+
"step": 2340
|
| 2351 |
+
},
|
| 2352 |
+
{
|
| 2353 |
+
"epoch": 3.223593964334705,
|
| 2354 |
+
"grad_norm": 0.7799023389816284,
|
| 2355 |
+
"learning_rate": 7.444471969975989e-05,
|
| 2356 |
+
"loss": 0.3636,
|
| 2357 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 2358 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 2359 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 2360 |
+
"step": 2350
|
| 2361 |
+
},
|
| 2362 |
+
{
|
| 2363 |
+
"epoch": 3.2373113854595337,
|
| 2364 |
+
"grad_norm": 0.7880516648292542,
|
| 2365 |
+
"learning_rate": 7.395549220608635e-05,
|
| 2366 |
+
"loss": 0.3681,
|
| 2367 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 2368 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 2369 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 2370 |
+
"step": 2360
|
| 2371 |
+
},
|
| 2372 |
+
{
|
| 2373 |
+
"epoch": 3.251028806584362,
|
| 2374 |
+
"grad_norm": 0.8505073189735413,
|
| 2375 |
+
"learning_rate": 7.347377416481226e-05,
|
| 2376 |
+
"loss": 0.3486,
|
| 2377 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 2378 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 2379 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 2380 |
+
"step": 2370
|
| 2381 |
+
},
|
| 2382 |
+
{
|
| 2383 |
+
"epoch": 3.2647462277091908,
|
| 2384 |
+
"grad_norm": 0.7163586616516113,
|
| 2385 |
+
"learning_rate": 7.299963012175744e-05,
|
| 2386 |
+
"loss": 0.3557,
|
| 2387 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 2388 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 2389 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 2390 |
+
"step": 2380
|
| 2391 |
+
},
|
| 2392 |
+
{
|
| 2393 |
+
"epoch": 3.2784636488340193,
|
| 2394 |
+
"grad_norm": 0.7703651189804077,
|
| 2395 |
+
"learning_rate": 7.253312360789504e-05,
|
| 2396 |
+
"loss": 0.368,
|
| 2397 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 2398 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 2399 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 2400 |
+
"step": 2390
|
| 2401 |
+
},
|
| 2402 |
+
{
|
| 2403 |
+
"epoch": 3.292181069958848,
|
| 2404 |
+
"grad_norm": 0.8175843954086304,
|
| 2405 |
+
"learning_rate": 7.207431713083911e-05,
|
| 2406 |
+
"loss": 0.3823,
|
| 2407 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 2408 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 2409 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 2410 |
+
"step": 2400
|
| 2411 |
+
},
|
| 2412 |
+
{
|
| 2413 |
+
"epoch": 3.3058984910836764,
|
| 2414 |
+
"grad_norm": 0.845107913017273,
|
| 2415 |
+
"learning_rate": 7.162327216646898e-05,
|
| 2416 |
+
"loss": 0.3601,
|
| 2417 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 2418 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 2419 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 2420 |
+
"step": 2410
|
| 2421 |
+
},
|
| 2422 |
+
{
|
| 2423 |
+
"epoch": 3.319615912208505,
|
| 2424 |
+
"grad_norm": 0.7847314476966858,
|
| 2425 |
+
"learning_rate": 7.118004915069216e-05,
|
| 2426 |
+
"loss": 0.3599,
|
| 2427 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 2428 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 2429 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 2430 |
+
"step": 2420
|
| 2431 |
+
},
|
| 2432 |
+
{
|
| 2433 |
+
"epoch": 3.3333333333333335,
|
| 2434 |
+
"grad_norm": 0.7950928807258606,
|
| 2435 |
+
"learning_rate": 7.074470747134649e-05,
|
| 2436 |
+
"loss": 0.3665,
|
| 2437 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 2438 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 2439 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 2440 |
+
"step": 2430
|
| 2441 |
+
},
|
| 2442 |
+
{
|
| 2443 |
+
"epoch": 3.347050754458162,
|
| 2444 |
+
"grad_norm": 0.7914710640907288,
|
| 2445 |
+
"learning_rate": 7.031730546024266e-05,
|
| 2446 |
+
"loss": 0.3619,
|
| 2447 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 2448 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 2449 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 2450 |
+
"step": 2440
|
| 2451 |
+
},
|
| 2452 |
+
{
|
| 2453 |
+
"epoch": 3.3607681755829906,
|
| 2454 |
+
"grad_norm": 0.7692461013793945,
|
| 2455 |
+
"learning_rate": 6.989790038534824e-05,
|
| 2456 |
+
"loss": 0.3793,
|
| 2457 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 2458 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 2459 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 2460 |
+
"step": 2450
|
| 2461 |
+
},
|
| 2462 |
+
{
|
| 2463 |
+
"epoch": 3.374485596707819,
|
| 2464 |
+
"grad_norm": 0.7980906367301941,
|
| 2465 |
+
"learning_rate": 6.948654844311447e-05,
|
| 2466 |
+
"loss": 0.3715,
|
| 2467 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 2468 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 2469 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 2470 |
+
"step": 2460
|
| 2471 |
+
},
|
| 2472 |
+
{
|
| 2473 |
+
"epoch": 3.388203017832647,
|
| 2474 |
+
"grad_norm": 1.3232189416885376,
|
| 2475 |
+
"learning_rate": 6.908330475094624e-05,
|
| 2476 |
+
"loss": 0.3708,
|
| 2477 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 2478 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 2479 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 2480 |
+
"step": 2470
|
| 2481 |
+
},
|
| 2482 |
+
{
|
| 2483 |
+
"epoch": 3.401920438957476,
|
| 2484 |
+
"grad_norm": 1.1973260641098022,
|
| 2485 |
+
"learning_rate": 6.8688223339817e-05,
|
| 2486 |
+
"loss": 0.4042,
|
| 2487 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 2488 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 2489 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 2490 |
+
"step": 2480
|
| 2491 |
+
},
|
| 2492 |
+
{
|
| 2493 |
+
"epoch": 3.4156378600823043,
|
| 2494 |
+
"grad_norm": 0.8183542490005493,
|
| 2495 |
+
"learning_rate": 6.830135714702901e-05,
|
| 2496 |
+
"loss": 0.4086,
|
| 2497 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 2498 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 2499 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 2500 |
+
"step": 2490
|
| 2501 |
+
},
|
| 2502 |
+
{
|
| 2503 |
+
"epoch": 3.4293552812071333,
|
| 2504 |
+
"grad_norm": 0.7338152527809143,
|
| 2505 |
+
"learning_rate": 6.792275800912032e-05,
|
| 2506 |
+
"loss": 0.368,
|
| 2507 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 2508 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 2509 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 2510 |
+
"step": 2500
|
| 2511 |
+
},
|
| 2512 |
+
{
|
| 2513 |
+
"epoch": 3.4430727023319614,
|
| 2514 |
+
"grad_norm": 0.8890711069107056,
|
| 2515 |
+
"learning_rate": 6.755247665491909e-05,
|
| 2516 |
+
"loss": 0.3802,
|
| 2517 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 2518 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 2519 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 2520 |
+
"step": 2510
|
| 2521 |
+
},
|
| 2522 |
+
{
|
| 2523 |
+
"epoch": 3.45679012345679,
|
| 2524 |
+
"grad_norm": 1.2834925651550293,
|
| 2525 |
+
"learning_rate": 6.719056269874638e-05,
|
| 2526 |
+
"loss": 0.3907,
|
| 2527 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 2528 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 2529 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 2530 |
+
"step": 2520
|
| 2531 |
+
},
|
| 2532 |
+
{
|
| 2533 |
+
"epoch": 3.4705075445816185,
|
| 2534 |
+
"grad_norm": 0.7763440012931824,
|
| 2535 |
+
"learning_rate": 6.683706463376829e-05,
|
| 2536 |
+
"loss": 0.3675,
|
| 2537 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 2538 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 2539 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 2540 |
+
"step": 2530
|
| 2541 |
+
},
|
| 2542 |
+
{
|
| 2543 |
+
"epoch": 3.484224965706447,
|
| 2544 |
+
"grad_norm": 0.7616425156593323,
|
| 2545 |
+
"learning_rate": 6.649202982549838e-05,
|
| 2546 |
+
"loss": 0.3897,
|
| 2547 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 2548 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 2549 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 2550 |
+
"step": 2540
|
| 2551 |
+
},
|
| 2552 |
+
{
|
| 2553 |
+
"epoch": 3.4979423868312756,
|
| 2554 |
+
"grad_norm": 0.8777288198471069,
|
| 2555 |
+
"learning_rate": 6.615550450545103e-05,
|
| 2556 |
+
"loss": 0.3698,
|
| 2557 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 2558 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 2559 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 2560 |
+
"step": 2550
|
| 2561 |
+
},
|
| 2562 |
+
{
|
| 2563 |
+
"epoch": 3.511659807956104,
|
| 2564 |
+
"grad_norm": 0.9963846206665039,
|
| 2565 |
+
"learning_rate": 6.58275337649469e-05,
|
| 2566 |
+
"loss": 0.3776,
|
| 2567 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 2568 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 2569 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 2570 |
+
"step": 2560
|
| 2571 |
+
},
|
| 2572 |
+
{
|
| 2573 |
+
"epoch": 3.5253772290809327,
|
| 2574 |
+
"grad_norm": 0.7394435405731201,
|
| 2575 |
+
"learning_rate": 6.550816154907109e-05,
|
| 2576 |
+
"loss": 0.3846,
|
| 2577 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 2578 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 2579 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 2580 |
+
"step": 2570
|
| 2581 |
+
},
|
| 2582 |
+
{
|
| 2583 |
+
"epoch": 3.539094650205761,
|
| 2584 |
+
"grad_norm": 0.9232655763626099,
|
| 2585 |
+
"learning_rate": 6.519743065078491e-05,
|
| 2586 |
+
"loss": 0.3952,
|
| 2587 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 2588 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 2589 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 2590 |
+
"step": 2580
|
| 2591 |
+
},
|
| 2592 |
+
{
|
| 2593 |
+
"epoch": 3.5528120713305897,
|
| 2594 |
+
"grad_norm": 0.862237274646759,
|
| 2595 |
+
"learning_rate": 6.489538270519197e-05,
|
| 2596 |
+
"loss": 0.3966,
|
| 2597 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 2598 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 2599 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 2600 |
+
"step": 2590
|
| 2601 |
+
},
|
| 2602 |
+
{
|
| 2603 |
+
"epoch": 3.5665294924554183,
|
| 2604 |
+
"grad_norm": 1.9497557878494263,
|
| 2605 |
+
"learning_rate": 6.460205818395948e-05,
|
| 2606 |
+
"loss": 0.3815,
|
| 2607 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 2608 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 2609 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 2610 |
+
"step": 2600
|
| 2611 |
+
},
|
| 2612 |
+
{
|
| 2613 |
+
"epoch": 3.580246913580247,
|
| 2614 |
+
"grad_norm": 0.8796144723892212,
|
| 2615 |
+
"learning_rate": 6.43174963898955e-05,
|
| 2616 |
+
"loss": 0.4087,
|
| 2617 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 2618 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 2619 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 2620 |
+
"step": 2610
|
| 2621 |
+
},
|
| 2622 |
+
{
|
| 2623 |
+
"epoch": 3.5939643347050754,
|
| 2624 |
+
"grad_norm": 0.8544576168060303,
|
| 2625 |
+
"learning_rate": 6.404173545168258e-05,
|
| 2626 |
+
"loss": 0.3885,
|
| 2627 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 2628 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 2629 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 2630 |
+
"step": 2620
|
| 2631 |
+
},
|
| 2632 |
+
{
|
| 2633 |
+
"epoch": 3.607681755829904,
|
| 2634 |
+
"grad_norm": 0.7616961598396301,
|
| 2635 |
+
"learning_rate": 6.377481231876892e-05,
|
| 2636 |
+
"loss": 0.3882,
|
| 2637 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 2638 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 2639 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 2640 |
+
"step": 2630
|
| 2641 |
+
},
|
| 2642 |
+
{
|
| 2643 |
+
"epoch": 3.6213991769547325,
|
| 2644 |
+
"grad_norm": 0.885047435760498,
|
| 2645 |
+
"learning_rate": 6.351676275641755e-05,
|
| 2646 |
+
"loss": 0.3775,
|
| 2647 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 2648 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 2649 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 2650 |
+
"step": 2640
|
| 2651 |
+
},
|
| 2652 |
+
{
|
| 2653 |
+
"epoch": 3.635116598079561,
|
| 2654 |
+
"grad_norm": 0.8627099990844727,
|
| 2655 |
+
"learning_rate": 6.326762134091401e-05,
|
| 2656 |
+
"loss": 0.4065,
|
| 2657 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 2658 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 2659 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 2660 |
+
"step": 2650
|
| 2661 |
+
},
|
| 2662 |
+
{
|
| 2663 |
+
"epoch": 3.6488340192043895,
|
| 2664 |
+
"grad_norm": 0.8460981845855713,
|
| 2665 |
+
"learning_rate": 6.302742145493348e-05,
|
| 2666 |
+
"loss": 0.4087,
|
| 2667 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 2668 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 2669 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 2670 |
+
"step": 2660
|
| 2671 |
+
},
|
| 2672 |
+
{
|
| 2673 |
+
"epoch": 3.662551440329218,
|
| 2674 |
+
"grad_norm": 0.8746662735939026,
|
| 2675 |
+
"learning_rate": 6.279619528306789e-05,
|
| 2676 |
+
"loss": 0.3963,
|
| 2677 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 2678 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 2679 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 2680 |
+
"step": 2670
|
| 2681 |
+
},
|
| 2682 |
+
{
|
| 2683 |
+
"epoch": 3.6762688614540466,
|
| 2684 |
+
"grad_norm": 1.2835209369659424,
|
| 2685 |
+
"learning_rate": 6.25739738075133e-05,
|
| 2686 |
+
"loss": 0.3934,
|
| 2687 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 2688 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 2689 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 2690 |
+
"step": 2680
|
| 2691 |
+
},
|
| 2692 |
+
{
|
| 2693 |
+
"epoch": 3.689986282578875,
|
| 2694 |
+
"grad_norm": 0.8834695219993591,
|
| 2695 |
+
"learning_rate": 6.236078680391872e-05,
|
| 2696 |
+
"loss": 0.432,
|
| 2697 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 2698 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 2699 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 2700 |
+
"step": 2690
|
| 2701 |
+
},
|
| 2702 |
+
{
|
| 2703 |
+
"epoch": 3.7037037037037037,
|
| 2704 |
+
"grad_norm": 0.7898237705230713,
|
| 2705 |
+
"learning_rate": 6.215666283739641e-05,
|
| 2706 |
+
"loss": 0.3863,
|
| 2707 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 2708 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 2709 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 2710 |
+
"step": 2700
|
| 2711 |
+
},
|
| 2712 |
+
{
|
| 2713 |
+
"epoch": 3.7174211248285323,
|
| 2714 |
+
"grad_norm": 0.8337833881378174,
|
| 2715 |
+
"learning_rate": 6.196162925869437e-05,
|
| 2716 |
+
"loss": 0.3857,
|
| 2717 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 2718 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 2719 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 2720 |
+
"step": 2710
|
| 2721 |
+
},
|
| 2722 |
+
{
|
| 2723 |
+
"epoch": 3.731138545953361,
|
| 2724 |
+
"grad_norm": 0.877326250076294,
|
| 2725 |
+
"learning_rate": 6.177571220053165e-05,
|
| 2726 |
+
"loss": 0.3947,
|
| 2727 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 2728 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 2729 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 2730 |
+
"step": 2720
|
| 2731 |
+
},
|
| 2732 |
+
{
|
| 2733 |
+
"epoch": 3.7448559670781894,
|
| 2734 |
+
"grad_norm": 0.7795323133468628,
|
| 2735 |
+
"learning_rate": 6.159893657409672e-05,
|
| 2736 |
+
"loss": 0.3715,
|
| 2737 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 2738 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 2739 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 2740 |
+
"step": 2730
|
| 2741 |
+
},
|
| 2742 |
+
{
|
| 2743 |
+
"epoch": 3.758573388203018,
|
| 2744 |
+
"grad_norm": 0.8641867637634277,
|
| 2745 |
+
"learning_rate": 6.143132606570974e-05,
|
| 2746 |
+
"loss": 0.3872,
|
| 2747 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 2748 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 2749 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 2750 |
+
"step": 2740
|
| 2751 |
+
},
|
| 2752 |
+
{
|
| 2753 |
+
"epoch": 3.7722908093278464,
|
| 2754 |
+
"grad_norm": 0.7897931337356567,
|
| 2755 |
+
"learning_rate": 6.127290313364864e-05,
|
| 2756 |
+
"loss": 0.3816,
|
| 2757 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 2758 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 2759 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 2760 |
+
"step": 2750
|
| 2761 |
+
},
|
| 2762 |
+
{
|
| 2763 |
+
"epoch": 3.786008230452675,
|
| 2764 |
+
"grad_norm": 1.6518064737319946,
|
| 2765 |
+
"learning_rate": 6.112368900514006e-05,
|
| 2766 |
+
"loss": 0.4066,
|
| 2767 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 2768 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 2769 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 2770 |
+
"step": 2760
|
| 2771 |
+
},
|
| 2772 |
+
{
|
| 2773 |
+
"epoch": 3.7997256515775035,
|
| 2774 |
+
"grad_norm": 0.8603875637054443,
|
| 2775 |
+
"learning_rate": 6.098370367351497e-05,
|
| 2776 |
+
"loss": 0.4307,
|
| 2777 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 2778 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 2779 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 2780 |
+
"step": 2770
|
| 2781 |
+
},
|
| 2782 |
+
{
|
| 2783 |
+
"epoch": 3.813443072702332,
|
| 2784 |
+
"grad_norm": 0.8134470582008362,
|
| 2785 |
+
"learning_rate": 6.085296589552988e-05,
|
| 2786 |
+
"loss": 0.3833,
|
| 2787 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 2788 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 2789 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 2790 |
+
"step": 2780
|
| 2791 |
+
},
|
| 2792 |
+
{
|
| 2793 |
+
"epoch": 3.8271604938271606,
|
| 2794 |
+
"grad_norm": 0.8172202110290527,
|
| 2795 |
+
"learning_rate": 6.073149318885347e-05,
|
| 2796 |
+
"loss": 0.3911,
|
| 2797 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 2798 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 2799 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 2800 |
+
"step": 2790
|
| 2801 |
+
},
|
| 2802 |
+
{
|
| 2803 |
+
"epoch": 3.840877914951989,
|
| 2804 |
+
"grad_norm": 0.8131387829780579,
|
| 2805 |
+
"learning_rate": 6.061930182971951e-05,
|
| 2806 |
+
"loss": 0.4076,
|
| 2807 |
+
"memory/device_memory_reserved(gib)": 34.31,
|
| 2808 |
+
"memory/max_memory_active(gib)": 33.17,
|
| 2809 |
+
"memory/max_memory_allocated(gib)": 33.17,
|
| 2810 |
+
"step": 2800
|
| 2811 |
+
}
|
| 2812 |
+
],
|
| 2813 |
+
"logging_steps": 10,
|
| 2814 |
+
"max_steps": 2914,
|
| 2815 |
+
"num_input_tokens_seen": 0,
|
| 2816 |
+
"num_train_epochs": 4,
|
| 2817 |
+
"save_steps": 100,
|
| 2818 |
+
"stateful_callbacks": {
|
| 2819 |
+
"TrainerControl": {
|
| 2820 |
+
"args": {
|
| 2821 |
+
"should_epoch_stop": false,
|
| 2822 |
+
"should_evaluate": false,
|
| 2823 |
+
"should_log": false,
|
| 2824 |
+
"should_save": true,
|
| 2825 |
+
"should_training_stop": false
|
| 2826 |
+
},
|
| 2827 |
+
"attributes": {}
|
| 2828 |
+
}
|
| 2829 |
+
},
|
| 2830 |
+
"total_flos": 3.684284172223906e+18,
|
| 2831 |
+
"train_batch_size": 28,
|
| 2832 |
+
"trial_name": null,
|
| 2833 |
+
"trial_params": null
|
| 2834 |
+
}
|
checkpoint-2800/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:72e8ffac0b1c04ef847d40d39691702ad69aae5796c3add97ba4e6809b86b7f7
|
| 3 |
+
size 8017
|
checkpoint-2800/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
config.json
ADDED
|
@@ -0,0 +1,67 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen3ForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"eos_token_id": 151643,
|
| 8 |
+
"head_dim": 128,
|
| 9 |
+
"hidden_act": "silu",
|
| 10 |
+
"hidden_size": 4096,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"intermediate_size": 12288,
|
| 13 |
+
"layer_types": [
|
| 14 |
+
"full_attention",
|
| 15 |
+
"full_attention",
|
| 16 |
+
"full_attention",
|
| 17 |
+
"full_attention",
|
| 18 |
+
"full_attention",
|
| 19 |
+
"full_attention",
|
| 20 |
+
"full_attention",
|
| 21 |
+
"full_attention",
|
| 22 |
+
"full_attention",
|
| 23 |
+
"full_attention",
|
| 24 |
+
"full_attention",
|
| 25 |
+
"full_attention",
|
| 26 |
+
"full_attention",
|
| 27 |
+
"full_attention",
|
| 28 |
+
"full_attention",
|
| 29 |
+
"full_attention",
|
| 30 |
+
"full_attention",
|
| 31 |
+
"full_attention",
|
| 32 |
+
"full_attention",
|
| 33 |
+
"full_attention",
|
| 34 |
+
"full_attention",
|
| 35 |
+
"full_attention",
|
| 36 |
+
"full_attention",
|
| 37 |
+
"full_attention",
|
| 38 |
+
"full_attention",
|
| 39 |
+
"full_attention",
|
| 40 |
+
"full_attention",
|
| 41 |
+
"full_attention",
|
| 42 |
+
"full_attention",
|
| 43 |
+
"full_attention",
|
| 44 |
+
"full_attention",
|
| 45 |
+
"full_attention",
|
| 46 |
+
"full_attention",
|
| 47 |
+
"full_attention",
|
| 48 |
+
"full_attention",
|
| 49 |
+
"full_attention"
|
| 50 |
+
],
|
| 51 |
+
"max_position_embeddings": 32768,
|
| 52 |
+
"max_window_layers": 36,
|
| 53 |
+
"model_type": "qwen3",
|
| 54 |
+
"num_attention_heads": 32,
|
| 55 |
+
"num_hidden_layers": 36,
|
| 56 |
+
"num_key_value_heads": 8,
|
| 57 |
+
"rms_norm_eps": 1e-06,
|
| 58 |
+
"rope_scaling": null,
|
| 59 |
+
"rope_theta": 1000000,
|
| 60 |
+
"sliding_window": null,
|
| 61 |
+
"tie_word_embeddings": false,
|
| 62 |
+
"torch_dtype": "bfloat16",
|
| 63 |
+
"transformers_version": "4.54.1",
|
| 64 |
+
"use_cache": false,
|
| 65 |
+
"use_sliding_window": false,
|
| 66 |
+
"vocab_size": 151936
|
| 67 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|im_start|>",
|
| 4 |
+
"<|im_end|>",
|
| 5 |
+
"<|object_ref_start|>",
|
| 6 |
+
"<|object_ref_end|>",
|
| 7 |
+
"<|box_start|>",
|
| 8 |
+
"<|box_end|>",
|
| 9 |
+
"<|quad_start|>",
|
| 10 |
+
"<|quad_end|>",
|
| 11 |
+
"<|vision_start|>",
|
| 12 |
+
"<|vision_end|>",
|
| 13 |
+
"<|vision_pad|>",
|
| 14 |
+
"<|image_pad|>",
|
| 15 |
+
"<|video_pad|>"
|
| 16 |
+
],
|
| 17 |
+
"eos_token": {
|
| 18 |
+
"content": "<|endoftext|>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
},
|
| 24 |
+
"pad_token": {
|
| 25 |
+
"content": "<|endoftext|>",
|
| 26 |
+
"lstrip": false,
|
| 27 |
+
"normalized": false,
|
| 28 |
+
"rstrip": false,
|
| 29 |
+
"single_word": false
|
| 30 |
+
}
|
| 31 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
|
| 3 |
+
size 11422654
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,239 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_prefix_space": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"151643": {
|
| 6 |
+
"content": "<|endoftext|>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"151644": {
|
| 14 |
+
"content": "<|im_start|>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"151645": {
|
| 22 |
+
"content": "<|im_end|>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
},
|
| 29 |
+
"151646": {
|
| 30 |
+
"content": "<|object_ref_start|>",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": false,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false,
|
| 35 |
+
"special": true
|
| 36 |
+
},
|
| 37 |
+
"151647": {
|
| 38 |
+
"content": "<|object_ref_end|>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false,
|
| 43 |
+
"special": true
|
| 44 |
+
},
|
| 45 |
+
"151648": {
|
| 46 |
+
"content": "<|box_start|>",
|
| 47 |
+
"lstrip": false,
|
| 48 |
+
"normalized": false,
|
| 49 |
+
"rstrip": false,
|
| 50 |
+
"single_word": false,
|
| 51 |
+
"special": true
|
| 52 |
+
},
|
| 53 |
+
"151649": {
|
| 54 |
+
"content": "<|box_end|>",
|
| 55 |
+
"lstrip": false,
|
| 56 |
+
"normalized": false,
|
| 57 |
+
"rstrip": false,
|
| 58 |
+
"single_word": false,
|
| 59 |
+
"special": true
|
| 60 |
+
},
|
| 61 |
+
"151650": {
|
| 62 |
+
"content": "<|quad_start|>",
|
| 63 |
+
"lstrip": false,
|
| 64 |
+
"normalized": false,
|
| 65 |
+
"rstrip": false,
|
| 66 |
+
"single_word": false,
|
| 67 |
+
"special": true
|
| 68 |
+
},
|
| 69 |
+
"151651": {
|
| 70 |
+
"content": "<|quad_end|>",
|
| 71 |
+
"lstrip": false,
|
| 72 |
+
"normalized": false,
|
| 73 |
+
"rstrip": false,
|
| 74 |
+
"single_word": false,
|
| 75 |
+
"special": true
|
| 76 |
+
},
|
| 77 |
+
"151652": {
|
| 78 |
+
"content": "<|vision_start|>",
|
| 79 |
+
"lstrip": false,
|
| 80 |
+
"normalized": false,
|
| 81 |
+
"rstrip": false,
|
| 82 |
+
"single_word": false,
|
| 83 |
+
"special": true
|
| 84 |
+
},
|
| 85 |
+
"151653": {
|
| 86 |
+
"content": "<|vision_end|>",
|
| 87 |
+
"lstrip": false,
|
| 88 |
+
"normalized": false,
|
| 89 |
+
"rstrip": false,
|
| 90 |
+
"single_word": false,
|
| 91 |
+
"special": true
|
| 92 |
+
},
|
| 93 |
+
"151654": {
|
| 94 |
+
"content": "<|vision_pad|>",
|
| 95 |
+
"lstrip": false,
|
| 96 |
+
"normalized": false,
|
| 97 |
+
"rstrip": false,
|
| 98 |
+
"single_word": false,
|
| 99 |
+
"special": true
|
| 100 |
+
},
|
| 101 |
+
"151655": {
|
| 102 |
+
"content": "<|image_pad|>",
|
| 103 |
+
"lstrip": false,
|
| 104 |
+
"normalized": false,
|
| 105 |
+
"rstrip": false,
|
| 106 |
+
"single_word": false,
|
| 107 |
+
"special": true
|
| 108 |
+
},
|
| 109 |
+
"151656": {
|
| 110 |
+
"content": "<|video_pad|>",
|
| 111 |
+
"lstrip": false,
|
| 112 |
+
"normalized": false,
|
| 113 |
+
"rstrip": false,
|
| 114 |
+
"single_word": false,
|
| 115 |
+
"special": true
|
| 116 |
+
},
|
| 117 |
+
"151657": {
|
| 118 |
+
"content": "<tool_call>",
|
| 119 |
+
"lstrip": false,
|
| 120 |
+
"normalized": false,
|
| 121 |
+
"rstrip": false,
|
| 122 |
+
"single_word": false,
|
| 123 |
+
"special": false
|
| 124 |
+
},
|
| 125 |
+
"151658": {
|
| 126 |
+
"content": "</tool_call>",
|
| 127 |
+
"lstrip": false,
|
| 128 |
+
"normalized": false,
|
| 129 |
+
"rstrip": false,
|
| 130 |
+
"single_word": false,
|
| 131 |
+
"special": false
|
| 132 |
+
},
|
| 133 |
+
"151659": {
|
| 134 |
+
"content": "<|fim_prefix|>",
|
| 135 |
+
"lstrip": false,
|
| 136 |
+
"normalized": false,
|
| 137 |
+
"rstrip": false,
|
| 138 |
+
"single_word": false,
|
| 139 |
+
"special": false
|
| 140 |
+
},
|
| 141 |
+
"151660": {
|
| 142 |
+
"content": "<|fim_middle|>",
|
| 143 |
+
"lstrip": false,
|
| 144 |
+
"normalized": false,
|
| 145 |
+
"rstrip": false,
|
| 146 |
+
"single_word": false,
|
| 147 |
+
"special": false
|
| 148 |
+
},
|
| 149 |
+
"151661": {
|
| 150 |
+
"content": "<|fim_suffix|>",
|
| 151 |
+
"lstrip": false,
|
| 152 |
+
"normalized": false,
|
| 153 |
+
"rstrip": false,
|
| 154 |
+
"single_word": false,
|
| 155 |
+
"special": false
|
| 156 |
+
},
|
| 157 |
+
"151662": {
|
| 158 |
+
"content": "<|fim_pad|>",
|
| 159 |
+
"lstrip": false,
|
| 160 |
+
"normalized": false,
|
| 161 |
+
"rstrip": false,
|
| 162 |
+
"single_word": false,
|
| 163 |
+
"special": false
|
| 164 |
+
},
|
| 165 |
+
"151663": {
|
| 166 |
+
"content": "<|repo_name|>",
|
| 167 |
+
"lstrip": false,
|
| 168 |
+
"normalized": false,
|
| 169 |
+
"rstrip": false,
|
| 170 |
+
"single_word": false,
|
| 171 |
+
"special": false
|
| 172 |
+
},
|
| 173 |
+
"151664": {
|
| 174 |
+
"content": "<|file_sep|>",
|
| 175 |
+
"lstrip": false,
|
| 176 |
+
"normalized": false,
|
| 177 |
+
"rstrip": false,
|
| 178 |
+
"single_word": false,
|
| 179 |
+
"special": false
|
| 180 |
+
},
|
| 181 |
+
"151665": {
|
| 182 |
+
"content": "<tool_response>",
|
| 183 |
+
"lstrip": false,
|
| 184 |
+
"normalized": false,
|
| 185 |
+
"rstrip": false,
|
| 186 |
+
"single_word": false,
|
| 187 |
+
"special": false
|
| 188 |
+
},
|
| 189 |
+
"151666": {
|
| 190 |
+
"content": "</tool_response>",
|
| 191 |
+
"lstrip": false,
|
| 192 |
+
"normalized": false,
|
| 193 |
+
"rstrip": false,
|
| 194 |
+
"single_word": false,
|
| 195 |
+
"special": false
|
| 196 |
+
},
|
| 197 |
+
"151667": {
|
| 198 |
+
"content": "<think>",
|
| 199 |
+
"lstrip": false,
|
| 200 |
+
"normalized": false,
|
| 201 |
+
"rstrip": false,
|
| 202 |
+
"single_word": false,
|
| 203 |
+
"special": false
|
| 204 |
+
},
|
| 205 |
+
"151668": {
|
| 206 |
+
"content": "</think>",
|
| 207 |
+
"lstrip": false,
|
| 208 |
+
"normalized": false,
|
| 209 |
+
"rstrip": false,
|
| 210 |
+
"single_word": false,
|
| 211 |
+
"special": false
|
| 212 |
+
}
|
| 213 |
+
},
|
| 214 |
+
"additional_special_tokens": [
|
| 215 |
+
"<|im_start|>",
|
| 216 |
+
"<|im_end|>",
|
| 217 |
+
"<|object_ref_start|>",
|
| 218 |
+
"<|object_ref_end|>",
|
| 219 |
+
"<|box_start|>",
|
| 220 |
+
"<|box_end|>",
|
| 221 |
+
"<|quad_start|>",
|
| 222 |
+
"<|quad_end|>",
|
| 223 |
+
"<|vision_start|>",
|
| 224 |
+
"<|vision_end|>",
|
| 225 |
+
"<|vision_pad|>",
|
| 226 |
+
"<|image_pad|>",
|
| 227 |
+
"<|video_pad|>"
|
| 228 |
+
],
|
| 229 |
+
"bos_token": null,
|
| 230 |
+
"clean_up_tokenization_spaces": false,
|
| 231 |
+
"eos_token": "<|endoftext|>",
|
| 232 |
+
"errors": "replace",
|
| 233 |
+
"extra_special_tokens": {},
|
| 234 |
+
"model_max_length": 131072,
|
| 235 |
+
"pad_token": "<|endoftext|>",
|
| 236 |
+
"split_special_tokens": false,
|
| 237 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 238 |
+
"unk_token": null
|
| 239 |
+
}
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|