lldois/v18_v12_unify_replay_lr5e6_ep05
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: lldois/v18_v12_unify_replay_lr5e6_ep05
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-07-18 04:58:12 +08:00
commit 83b9eccdfc
16 changed files with 2957 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

36
.gitattributes vendored Normal file
View File

@@ -0,0 +1,36 @@
*.7z filter=lfs diff=lfs merge=lfs -text
*.arrow filter=lfs diff=lfs merge=lfs -text
*.bin filter=lfs diff=lfs merge=lfs -text
*.bz2 filter=lfs diff=lfs merge=lfs -text
*.ckpt filter=lfs diff=lfs merge=lfs -text
*.ftz filter=lfs diff=lfs merge=lfs -text
*.gz filter=lfs diff=lfs merge=lfs -text
*.h5 filter=lfs diff=lfs merge=lfs -text
*.joblib filter=lfs diff=lfs merge=lfs -text
*.lfs.* filter=lfs diff=lfs merge=lfs -text
*.mlmodel filter=lfs diff=lfs merge=lfs -text
*.model filter=lfs diff=lfs merge=lfs -text
*.msgpack filter=lfs diff=lfs merge=lfs -text
*.npy filter=lfs diff=lfs merge=lfs -text
*.npz filter=lfs diff=lfs merge=lfs -text
*.onnx filter=lfs diff=lfs merge=lfs -text
*.ot filter=lfs diff=lfs merge=lfs -text
*.parquet filter=lfs diff=lfs merge=lfs -text
*.pb filter=lfs diff=lfs merge=lfs -text
*.pickle filter=lfs diff=lfs merge=lfs -text
*.pkl filter=lfs diff=lfs merge=lfs -text
*.pt filter=lfs diff=lfs merge=lfs -text
*.pth filter=lfs diff=lfs merge=lfs -text
*.rar filter=lfs diff=lfs merge=lfs -text
*.safetensors filter=lfs diff=lfs merge=lfs -text
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
*.tar.* filter=lfs diff=lfs merge=lfs -text
*.tar filter=lfs diff=lfs merge=lfs -text
*.tflite filter=lfs diff=lfs merge=lfs -text
*.tgz filter=lfs diff=lfs merge=lfs -text
*.wasm filter=lfs diff=lfs merge=lfs -text
*.xz filter=lfs diff=lfs merge=lfs -text
*.zip filter=lfs diff=lfs merge=lfs -text
*.zst filter=lfs diff=lfs merge=lfs -text
*tfevents* filter=lfs diff=lfs merge=lfs -text
tokenizer.json filter=lfs diff=lfs merge=lfs -text

58
README.md Normal file
View File

@@ -0,0 +1,58 @@
---
library_name: transformers
license: other
base_model: lldois/v12_user_cot_focus_lr15e6
tags:
- llama-factory
- full
- generated_from_trainer
model-index:
- name: v18_v12_unify_replay_lr5e6_ep05
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# v18_v12_unify_replay_lr5e6_ep05
This model is a fine-tuned version of [lldois/v12_user_cot_focus_lr15e6](https://huggingface.co/lldois/v12_user_cot_focus_lr15e6) on the exp_v12_unify_replay dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-06
- train_batch_size: 1
- eval_batch_size: 8
- seed: 202607184
- gradient_accumulation_steps: 4
- total_train_batch_size: 4
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 0.02
- num_epochs: 0.5
### Training results
### Framework versions
- Transformers 5.6.0
- Pytorch 2.7.1+cu126
- Datasets 4.0.0
- Tokenizers 0.22.2

8
all_results.json Normal file
View File

@@ -0,0 +1,8 @@
{
"epoch": 0.5011027790030878,
"total_flos": 1.3705181662943232e+17,
"train_loss": 1.5080752087311007,
"train_runtime": 2339.7979,
"train_samples_per_second": 0.484,
"train_steps_per_second": 0.121
}

89
chat_template.jinja Normal file
View File

@@ -0,0 +1,89 @@
{%- if tools %}
{{- '<|im_start|>system\n' }}
{%- if messages[0].role == 'system' %}
{{- messages[0].content + '\n\n' }}
{%- endif %}
{{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
{%- for tool in tools %}
{{- "\n" }}
{{- tool | tojson }}
{%- endfor %}
{{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
{%- else %}
{%- if messages[0].role == 'system' %}
{{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
{%- endif %}
{%- endif %}
{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
{%- for message in messages[::-1] %}
{%- set index = (messages|length - 1) - loop.index0 %}
{%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
{%- set ns.multi_step_tool = false %}
{%- set ns.last_query_index = index %}
{%- endif %}
{%- endfor %}
{%- for message in messages %}
{%- if message.content is string %}
{%- set content = message.content %}
{%- else %}
{%- set content = '' %}
{%- endif %}
{%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
{{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
{%- elif message.role == "assistant" %}
{%- set reasoning_content = '' %}
{%- if message.reasoning_content is string %}
{%- set reasoning_content = message.reasoning_content %}
{%- else %}
{%- if '</think>' in content %}
{%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
{%- set content = content.split('</think>')[-1].lstrip('\n') %}
{%- endif %}
{%- endif %}
{%- if loop.index0 > ns.last_query_index %}
{%- if loop.last or (not loop.last and reasoning_content) %}
{{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
{%- else %}
{{- '<|im_start|>' + message.role + '\n' + content }}
{%- endif %}
{%- else %}
{{- '<|im_start|>' + message.role + '\n' + content }}
{%- endif %}
{%- if message.tool_calls %}
{%- for tool_call in message.tool_calls %}
{%- if (loop.first and content) or (not loop.first) %}
{{- '\n' }}
{%- endif %}
{%- if tool_call.function %}
{%- set tool_call = tool_call.function %}
{%- endif %}
{{- '<tool_call>\n{"name": "' }}
{{- tool_call.name }}
{{- '", "arguments": ' }}
{%- if tool_call.arguments is string %}
{{- tool_call.arguments }}
{%- else %}
{{- tool_call.arguments | tojson }}
{%- endif %}
{{- '}\n</tool_call>' }}
{%- endfor %}
{%- endif %}
{{- '<|im_end|>\n' }}
{%- elif message.role == "tool" %}
{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
{{- '<|im_start|>user' }}
{%- endif %}
{{- '\n<tool_response>\n' }}
{{- content }}
{{- '\n</tool_response>' }}
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
{{- '<|im_end|>\n' }}
{%- endif %}
{%- endif %}
{%- endfor %}
{%- if add_generation_prompt %}
{{- '<|im_start|>assistant\n' }}
{%- if enable_thinking is defined and enable_thinking is false %}
{{- '<think>\n\n</think>\n\n' }}
{%- endif %}
{%- endif %}

63
config.json Normal file
View File

@@ -0,0 +1,63 @@
{
"architectures": [
"Qwen3ForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": null,
"dtype": "bfloat16",
"eos_token_id": 151645,
"head_dim": 128,
"hidden_act": "silu",
"hidden_size": 1024,
"initializer_range": 0.02,
"intermediate_size": 3072,
"layer_types": [
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention"
],
"max_position_embeddings": 40960,
"max_window_layers": 28,
"model_type": "qwen3",
"num_attention_heads": 16,
"num_hidden_layers": 28,
"num_key_value_heads": 8,
"pad_token_id": 151643,
"rms_norm_eps": 1e-06,
"rope_parameters": {
"rope_theta": 1000000,
"rope_type": "default"
},
"sliding_window": null,
"tie_word_embeddings": false,
"transformers_version": "5.6.0",
"use_cache": false,
"use_sliding_window": false,
"vocab_size": 176253
}

12
generation_config.json Normal file
View File

@@ -0,0 +1,12 @@
{
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"temperature": 0.6,
"top_k": 20,
"top_p": 0.95,
"transformers_version": "5.6.0"
}

3
model.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ed0737abc4b2024a79654c3934d4ec837678f7e030a2350d90776e27401c28cc
size 1602902832

3
runs/Jul08_03-16-28_ubuntu-System-Product-Name/events.out.tfevents.1783451788.ubuntu-System-Product-Name.3936671.0 Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:46606d88e6fdd766d9d8f6aaff4014e89a5578576ed72504ed379e72ed0151c9
size 18015

3
tokenizer.json Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:cd4d15f596979aecbc11ba12668cb21c9fb8452ce1235cd9d7878cc950170421
size 16016554

16
tokenizer_config.json Normal file
View File

@@ -0,0 +1,16 @@
{
"add_prefix_space": false,
"backend": "tokenizers",
"bos_token": null,
"clean_up_tokenization_spaces": false,
"eos_token": "<|im_end|>",
"errors": "replace",
"is_local": true,
"local_files_only": false,
"model_max_length": 131072,
"pad_token": "<|endoftext|>",
"padding_side": "right",
"split_special_tokens": false,
"tokenizer_class": "Qwen2Tokenizer",
"unk_token": null
}

2163
train.log Normal file
View File

File diff suppressed because one or more lines are too long

8
train_results.json Normal file
View File

@@ -0,0 +1,8 @@
{
"epoch": 0.5011027790030878,
"total_flos": 1.3705181662943232e+17,
"train_loss": 1.5080752087311007,
"train_runtime": 2339.7979,
"train_samples_per_second": 0.484,
"train_steps_per_second": 0.121
}

57
trainer_log.jsonl Normal file
View File

@@ -0,0 +1,57 @@
{"current_steps": 5, "total_steps": 284, "loss": 1.5331814765930176, "lr": 3.3333333333333333e-06, "epoch": 0.00882223202470225, "percentage": 1.76, "elapsed_time": "0:00:41", "remaining_time": "0:38:37"}
{"current_steps": 10, "total_steps": 284, "loss": 1.5866724014282227, "lr": 4.998563448899413e-06, "epoch": 0.0176444640494045, "percentage": 3.52, "elapsed_time": "0:01:22", "remaining_time": "0:37:29"}
{"current_steps": 15, "total_steps": 284, "loss": 1.5153743743896484, "lr": 4.989790503518888e-06, "epoch": 0.02646669607410675, "percentage": 5.28, "elapsed_time": "0:02:04", "remaining_time": "0:37:20"}
{"current_steps": 20, "total_steps": 284, "loss": 1.528839683532715, "lr": 4.973070664146885e-06, "epoch": 0.035288928098809, "percentage": 7.04, "elapsed_time": "0:02:46", "remaining_time": "0:36:33"}
{"current_steps": 25, "total_steps": 284, "loss": 1.4991332054138184, "lr": 4.9484572970368516e-06, "epoch": 0.044111160123511246, "percentage": 8.8, "elapsed_time": "0:03:28", "remaining_time": "0:36:04"}
{"current_steps": 30, "total_steps": 284, "loss": 1.497140884399414, "lr": 4.916028962942763e-06, "epoch": 0.0529333921482135, "percentage": 10.56, "elapsed_time": "0:04:10", "remaining_time": "0:35:19"}
{"current_steps": 35, "total_steps": 284, "loss": 1.5790274620056153, "lr": 4.8758891663695165e-06, "epoch": 0.061755624172915746, "percentage": 12.32, "elapsed_time": "0:04:53", "remaining_time": "0:34:45"}
{"current_steps": 40, "total_steps": 284, "loss": 1.5177926063537597, "lr": 4.828166025208059e-06, "epoch": 0.070577856197618, "percentage": 14.08, "elapsed_time": "0:05:33", "remaining_time": "0:33:54"}
{"current_steps": 45, "total_steps": 284, "loss": 1.5248671531677247, "lr": 4.773011861809694e-06, "epoch": 0.07940008822232025, "percentage": 15.85, "elapsed_time": "0:06:14", "remaining_time": "0:33:09"}
{"current_steps": 50, "total_steps": 284, "loss": 1.5441174507141113, "lr": 4.710602716804784e-06, "epoch": 0.08822232024702249, "percentage": 17.61, "elapsed_time": "0:06:54", "remaining_time": "0:32:19"}
{"current_steps": 55, "total_steps": 284, "loss": 1.5332836151123046, "lr": 4.64113778721764e-06, "epoch": 0.09704455227172475, "percentage": 19.37, "elapsed_time": "0:07:35", "remaining_time": "0:31:35"}
{"current_steps": 60, "total_steps": 284, "loss": 1.5188942909240724, "lr": 4.564838790671e-06, "epoch": 0.105866784296427, "percentage": 21.13, "elapsed_time": "0:08:16", "remaining_time": "0:30:51"}
{"current_steps": 65, "total_steps": 284, "loss": 1.6403696060180664, "lr": 4.481949257709442e-06, "epoch": 0.11468901632112924, "percentage": 22.89, "elapsed_time": "0:08:54", "remaining_time": "0:30:01"}
{"current_steps": 70, "total_steps": 284, "loss": 1.4794146537780761, "lr": 4.39273375450049e-06, "epoch": 0.12351124834583149, "percentage": 24.65, "elapsed_time": "0:09:37", "remaining_time": "0:29:24"}
{"current_steps": 75, "total_steps": 284, "loss": 1.4949344635009765, "lr": 4.297477038394368e-06, "epoch": 0.13233348037053375, "percentage": 26.41, "elapsed_time": "0:10:17", "remaining_time": "0:28:40"}
{"current_steps": 80, "total_steps": 284, "loss": 1.4376185417175293, "lr": 4.196483149037707e-06, "epoch": 0.141155712395236, "percentage": 28.17, "elapsed_time": "0:11:00", "remaining_time": "0:28:03"}
{"current_steps": 85, "total_steps": 284, "loss": 1.4953926086425782, "lr": 4.090074437942155e-06, "epoch": 0.14997794441993825, "percentage": 29.93, "elapsed_time": "0:11:41", "remaining_time": "0:27:22"}
{"current_steps": 90, "total_steps": 284, "loss": 1.5234898567199706, "lr": 3.978590539605338e-06, "epoch": 0.1588001764446405, "percentage": 31.69, "elapsed_time": "0:12:23", "remaining_time": "0:26:42"}
{"current_steps": 95, "total_steps": 284, "loss": 1.5017153739929199, "lr": 3.862387287468095e-06, "epoch": 0.16762240846934273, "percentage": 33.45, "elapsed_time": "0:13:05", "remaining_time": "0:26:02"}
{"current_steps": 100, "total_steps": 284, "loss": 1.471701431274414, "lr": 3.741835578168071e-06, "epoch": 0.17644464049404499, "percentage": 35.21, "elapsed_time": "0:13:48", "remaining_time": "0:25:24"}
{"current_steps": 105, "total_steps": 284, "loss": 1.5574091911315917, "lr": 3.6173201877147134e-06, "epoch": 0.18526687251874724, "percentage": 36.97, "elapsed_time": "0:14:28", "remaining_time": "0:24:39"}
{"current_steps": 110, "total_steps": 284, "loss": 1.5162025451660157, "lr": 3.4892385433641875e-06, "epoch": 0.1940891045434495, "percentage": 38.73, "elapsed_time": "0:15:08", "remaining_time": "0:23:56"}
{"current_steps": 115, "total_steps": 284, "loss": 1.356987762451172, "lr": 3.357999455114148e-06, "epoch": 0.20291133656815175, "percentage": 40.49, "elapsed_time": "0:15:52", "remaining_time": "0:23:19"}
{"current_steps": 120, "total_steps": 284, "loss": 1.489048671722412, "lr": 3.2240218108671683e-06, "epoch": 0.211733568592854, "percentage": 42.25, "elapsed_time": "0:16:33", "remaining_time": "0:22:37"}
{"current_steps": 125, "total_steps": 284, "loss": 1.4940855979919434, "lr": 3.0877332394275806e-06, "epoch": 0.22055580061755625, "percentage": 44.01, "elapsed_time": "0:17:15", "remaining_time": "0:21:57"}
{"current_steps": 130, "total_steps": 284, "loss": 1.456082820892334, "lr": 2.949568745599182e-06, "epoch": 0.22937803264225848, "percentage": 45.77, "elapsed_time": "0:17:56", "remaining_time": "0:21:15"}
{"current_steps": 135, "total_steps": 284, "loss": 1.545342254638672, "lr": 2.8099693217402807e-06, "epoch": 0.23820026466696073, "percentage": 47.54, "elapsed_time": "0:18:38", "remaining_time": "0:20:34"}
{"current_steps": 140, "total_steps": 284, "loss": 1.4941516876220704, "lr": 2.6693805402077123e-06, "epoch": 0.24702249669166298, "percentage": 49.3, "elapsed_time": "0:19:19", "remaining_time": "0:19:52"}
{"current_steps": 145, "total_steps": 284, "loss": 1.5371488571166991, "lr": 2.52825113118245e-06, "epoch": 0.25584472871636527, "percentage": 51.06, "elapsed_time": "0:20:00", "remaining_time": "0:19:10"}
{"current_steps": 150, "total_steps": 284, "loss": 1.4182353019714355, "lr": 2.3870315504160995e-06, "epoch": 0.2646669607410675, "percentage": 52.82, "elapsed_time": "0:20:43", "remaining_time": "0:18:30"}
{"current_steps": 155, "total_steps": 284, "loss": 1.524265193939209, "lr": 2.24617254146973e-06, "epoch": 0.2734891927657697, "percentage": 54.58, "elapsed_time": "0:21:25", "remaining_time": "0:17:49"}
{"current_steps": 160, "total_steps": 284, "loss": 1.47442569732666, "lr": 2.1061236970340756e-06, "epoch": 0.282311424790472, "percentage": 56.34, "elapsed_time": "0:22:06", "remaining_time": "0:17:08"}
{"current_steps": 165, "total_steps": 284, "loss": 1.4985308647155762, "lr": 1.9673320239230783e-06, "epoch": 0.2911336568151742, "percentage": 58.1, "elapsed_time": "0:22:47", "remaining_time": "0:16:26"}
{"current_steps": 170, "total_steps": 284, "loss": 1.491645050048828, "lr": 1.830240516321008e-06, "epoch": 0.2999558888398765, "percentage": 59.86, "elapsed_time": "0:23:29", "remaining_time": "0:15:44"}
{"current_steps": 175, "total_steps": 284, "loss": 1.509144115447998, "lr": 1.6952867418370707e-06, "epoch": 0.30877812086457873, "percentage": 61.62, "elapsed_time": "0:24:10", "remaining_time": "0:15:03"}
{"current_steps": 180, "total_steps": 284, "loss": 1.464055347442627, "lr": 1.562901444880508e-06, "epoch": 0.317600352889281, "percentage": 63.38, "elapsed_time": "0:24:52", "remaining_time": "0:14:22"}
{"current_steps": 185, "total_steps": 284, "loss": 1.5107802391052245, "lr": 1.4335071718139379e-06, "epoch": 0.32642258491398324, "percentage": 65.14, "elapsed_time": "0:25:34", "remaining_time": "0:13:41"}
{"current_steps": 190, "total_steps": 284, "loss": 1.52694730758667, "lr": 1.3075169222731573e-06, "epoch": 0.33524481693868546, "percentage": 66.9, "elapsed_time": "0:26:14", "remaining_time": "0:12:59"}
{"current_steps": 195, "total_steps": 284, "loss": 1.4959157943725585, "lr": 1.1853328309581139e-06, "epoch": 0.34406704896338774, "percentage": 68.66, "elapsed_time": "0:26:56", "remaining_time": "0:12:17"}
{"current_steps": 200, "total_steps": 284, "loss": 1.5017786979675294, "lr": 1.0673448841024875e-06, "epoch": 0.35288928098808997, "percentage": 70.42, "elapsed_time": "0:27:37", "remaining_time": "0:11:36"}
{"current_steps": 205, "total_steps": 284, "loss": 1.5668895721435547, "lr": 9.53929674718668e-07, "epoch": 0.36171151301279225, "percentage": 72.18, "elapsed_time": "0:28:16", "remaining_time": "0:10:53"}
{"current_steps": 210, "total_steps": 284, "loss": 1.5082152366638184, "lr": 8.454492005910942e-07, "epoch": 0.3705337450374945, "percentage": 73.94, "elapsed_time": "0:28:56", "remaining_time": "0:10:12"}
{"current_steps": 215, "total_steps": 284, "loss": 1.5332984924316406, "lr": 7.422497088545436e-07, "epoch": 0.37935597706219676, "percentage": 75.7, "elapsed_time": "0:29:36", "remaining_time": "0:09:30"}
{"current_steps": 220, "total_steps": 284, "loss": 1.5301700592041017, "lr": 6.446605908452122e-07, "epoch": 0.388178209086899, "percentage": 77.46, "elapsed_time": "0:30:14", "remaining_time": "0:08:47"}
{"current_steps": 225, "total_steps": 284, "loss": 1.5099596977233887, "lr": 5.529933307520102e-07, "epoch": 0.3970004411116012, "percentage": 79.23, "elapsed_time": "0:30:56", "remaining_time": "0:08:06"}
{"current_steps": 230, "total_steps": 284, "loss": 1.4918466567993165, "lr": 4.6754051142374275e-07, "epoch": 0.4058226731363035, "percentage": 80.99, "elapsed_time": "0:31:38", "remaining_time": "0:07:25"}
{"current_steps": 235, "total_steps": 284, "loss": 1.5015207290649415, "lr": 3.8857488050544903e-07, "epoch": 0.4146449051610057, "percentage": 82.75, "elapsed_time": "0:32:19", "remaining_time": "0:06:44"}
{"current_steps": 240, "total_steps": 284, "loss": 1.5009549140930176, "lr": 3.163484798845862e-07, "epoch": 0.423467137185708, "percentage": 84.51, "elapsed_time": "0:32:58", "remaining_time": "0:06:02"}
{"current_steps": 245, "total_steps": 284, "loss": 1.5147621154785156, "lr": 2.5109184122568797e-07, "epoch": 0.4322893692104102, "percentage": 86.27, "elapsed_time": "0:33:37", "remaining_time": "0:05:21"}
{"current_steps": 250, "total_steps": 284, "loss": 1.5966561317443848, "lr": 1.9301325016119338e-07, "epoch": 0.4411116012351125, "percentage": 88.03, "elapsed_time": "0:34:15", "remaining_time": "0:04:39"}
{"current_steps": 255, "total_steps": 284, "loss": 1.5000021934509278, "lr": 1.4229808148697732e-07, "epoch": 0.44993383325981473, "percentage": 89.79, "elapsed_time": "0:34:56", "remaining_time": "0:03:58"}
{"current_steps": 260, "total_steps": 284, "loss": 1.4867940902709962, "lr": 9.91082074845215e-08, "epoch": 0.45875606528451696, "percentage": 91.55, "elapsed_time": "0:35:38", "remaining_time": "0:03:17"}
{"current_steps": 265, "total_steps": 284, "loss": 1.4553143501281738, "lr": 6.358148125822e-08, "epoch": 0.46757829730921924, "percentage": 93.31, "elapsed_time": "0:36:19", "remaining_time": "0:02:36"}
{"current_steps": 270, "total_steps": 284, "loss": 1.5283794403076172, "lr": 3.583129673691427e-08, "epoch": 0.47640052933392146, "percentage": 95.07, "elapsed_time": "0:37:00", "remaining_time": "0:01:55"}
{"current_steps": 275, "total_steps": 284, "loss": 1.4848525047302246, "lr": 1.5946226744029402e-08, "epoch": 0.48522276135862374, "percentage": 96.83, "elapsed_time": "0:37:44", "remaining_time": "0:01:14"}
{"current_steps": 280, "total_steps": 284, "loss": 1.5114261627197265, "lr": 3.989740291526212e-09, "epoch": 0.49404499338332597, "percentage": 98.59, "elapsed_time": "0:38:25", "remaining_time": "0:00:32"}
{"current_steps": 284, "total_steps": 284, "epoch": 0.5011027790030878, "percentage": 100.0, "elapsed_time": "0:38:59", "remaining_time": "0:00:00"}

435
trainer_state.json Normal file
View File

@@ -0,0 +1,435 @@
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.5011027790030878,
"eval_steps": 500,
"global_step": 284,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.00882223202470225,
"grad_norm": 3.421875,
"learning_rate": 3.3333333333333333e-06,
"loss": 1.5331814765930176,
"step": 5
},
{
"epoch": 0.0176444640494045,
"grad_norm": 3.375,
"learning_rate": 4.998563448899413e-06,
"loss": 1.5866724014282227,
"step": 10
},
{
"epoch": 0.02646669607410675,
"grad_norm": 5.46875,
"learning_rate": 4.989790503518888e-06,
"loss": 1.5153743743896484,
"step": 15
},
{
"epoch": 0.035288928098809,
"grad_norm": 4.1875,
"learning_rate": 4.973070664146885e-06,
"loss": 1.528839683532715,
"step": 20
},
{
"epoch": 0.044111160123511246,
"grad_norm": 3.203125,
"learning_rate": 4.9484572970368516e-06,
"loss": 1.4991332054138184,
"step": 25
},
{
"epoch": 0.0529333921482135,
"grad_norm": 2.171875,
"learning_rate": 4.916028962942763e-06,
"loss": 1.497140884399414,
"step": 30
},
{
"epoch": 0.061755624172915746,
"grad_norm": 2.140625,
"learning_rate": 4.8758891663695165e-06,
"loss": 1.5790274620056153,
"step": 35
},
{
"epoch": 0.070577856197618,
"grad_norm": 2.484375,
"learning_rate": 4.828166025208059e-06,
"loss": 1.5177926063537597,
"step": 40
},
{
"epoch": 0.07940008822232025,
"grad_norm": 2.5,
"learning_rate": 4.773011861809694e-06,
"loss": 1.5248671531677247,
"step": 45
},
{
"epoch": 0.08822232024702249,
"grad_norm": 2.25,
"learning_rate": 4.710602716804784e-06,
"loss": 1.5441174507141113,
"step": 50
},
{
"epoch": 0.09704455227172475,
"grad_norm": 2.140625,
"learning_rate": 4.64113778721764e-06,
"loss": 1.5332836151123046,
"step": 55
},
{
"epoch": 0.105866784296427,
"grad_norm": 5.46875,
"learning_rate": 4.564838790671e-06,
"loss": 1.5188942909240724,
"step": 60
},
{
"epoch": 0.11468901632112924,
"grad_norm": 2.78125,
"learning_rate": 4.481949257709442e-06,
"loss": 1.6403696060180664,
"step": 65
},
{
"epoch": 0.12351124834583149,
"grad_norm": 2.6875,
"learning_rate": 4.39273375450049e-06,
"loss": 1.4794146537780761,
"step": 70
},
{
"epoch": 0.13233348037053375,
"grad_norm": 2.09375,
"learning_rate": 4.297477038394368e-06,
"loss": 1.4949344635009765,
"step": 75
},
{
"epoch": 0.141155712395236,
"grad_norm": 2.28125,
"learning_rate": 4.196483149037707e-06,
"loss": 1.4376185417175293,
"step": 80
},
{
"epoch": 0.14997794441993825,
"grad_norm": 2.484375,
"learning_rate": 4.090074437942155e-06,
"loss": 1.4953926086425782,
"step": 85
},
{
"epoch": 0.1588001764446405,
"grad_norm": 2.890625,
"learning_rate": 3.978590539605338e-06,
"loss": 1.5234898567199706,
"step": 90
},
{
"epoch": 0.16762240846934273,
"grad_norm": 2.046875,
"learning_rate": 3.862387287468095e-06,
"loss": 1.5017153739929199,
"step": 95
},
{
"epoch": 0.17644464049404499,
"grad_norm": 2.875,
"learning_rate": 3.741835578168071e-06,
"loss": 1.471701431274414,
"step": 100
},
{
"epoch": 0.18526687251874724,
"grad_norm": 2.796875,
"learning_rate": 3.6173201877147134e-06,
"loss": 1.5574091911315917,
"step": 105
},
{
"epoch": 0.1940891045434495,
"grad_norm": 1.9921875,
"learning_rate": 3.4892385433641875e-06,
"loss": 1.5162025451660157,
"step": 110
},
{
"epoch": 0.20291133656815175,
"grad_norm": 5.40625,
"learning_rate": 3.357999455114148e-06,
"loss": 1.356987762451172,
"step": 115
},
{
"epoch": 0.211733568592854,
"grad_norm": 2.484375,
"learning_rate": 3.2240218108671683e-06,
"loss": 1.489048671722412,
"step": 120
},
{
"epoch": 0.22055580061755625,
"grad_norm": 2.03125,
"learning_rate": 3.0877332394275806e-06,
"loss": 1.4940855979919434,
"step": 125
},
{
"epoch": 0.22937803264225848,
"grad_norm": 4.0625,
"learning_rate": 2.949568745599182e-06,
"loss": 1.456082820892334,
"step": 130
},
{
"epoch": 0.23820026466696073,
"grad_norm": 7.53125,
"learning_rate": 2.8099693217402807e-06,
"loss": 1.545342254638672,
"step": 135
},
{
"epoch": 0.24702249669166298,
"grad_norm": 2.125,
"learning_rate": 2.6693805402077123e-06,
"loss": 1.4941516876220704,
"step": 140
},
{
"epoch": 0.25584472871636527,
"grad_norm": 2.828125,
"learning_rate": 2.52825113118245e-06,
"loss": 1.5371488571166991,
"step": 145
},
{
"epoch": 0.2646669607410675,
"grad_norm": 2.328125,
"learning_rate": 2.3870315504160995e-06,
"loss": 1.4182353019714355,
"step": 150
},
{
"epoch": 0.2734891927657697,
"grad_norm": 2.3125,
"learning_rate": 2.24617254146973e-06,
"loss": 1.524265193939209,
"step": 155
},
{
"epoch": 0.282311424790472,
"grad_norm": 2.28125,
"learning_rate": 2.1061236970340756e-06,
"loss": 1.47442569732666,
"step": 160
},
{
"epoch": 0.2911336568151742,
"grad_norm": 5.0,
"learning_rate": 1.9673320239230783e-06,
"loss": 1.4985308647155762,
"step": 165
},
{
"epoch": 0.2999558888398765,
"grad_norm": 2.421875,
"learning_rate": 1.830240516321008e-06,
"loss": 1.491645050048828,
"step": 170
},
{
"epoch": 0.30877812086457873,
"grad_norm": 4.125,
"learning_rate": 1.6952867418370707e-06,
"loss": 1.509144115447998,
"step": 175
},
{
"epoch": 0.317600352889281,
"grad_norm": 4.625,
"learning_rate": 1.562901444880508e-06,
"loss": 1.464055347442627,
"step": 180
},
{
"epoch": 0.32642258491398324,
"grad_norm": 6.375,
"learning_rate": 1.4335071718139379e-06,
"loss": 1.5107802391052245,
"step": 185
},
{
"epoch": 0.33524481693868546,
"grad_norm": 2.8125,
"learning_rate": 1.3075169222731573e-06,
"loss": 1.52694730758667,
"step": 190
},
{
"epoch": 0.34406704896338774,
"grad_norm": 2.09375,
"learning_rate": 1.1853328309581139e-06,
"loss": 1.4959157943725585,
"step": 195
},
{
"epoch": 0.35288928098808997,
"grad_norm": 2.390625,
"learning_rate": 1.0673448841024875e-06,
"loss": 1.5017786979675294,
"step": 200
},
{
"epoch": 0.36171151301279225,
"grad_norm": 2.625,
"learning_rate": 9.53929674718668e-07,
"loss": 1.5668895721435547,
"step": 205
},
{
"epoch": 0.3705337450374945,
"grad_norm": 2.296875,
"learning_rate": 8.454492005910942e-07,
"loss": 1.5082152366638184,
"step": 210
},
{
"epoch": 0.37935597706219676,
"grad_norm": 2.421875,
"learning_rate": 7.422497088545436e-07,
"loss": 1.5332984924316406,
"step": 215
},
{
"epoch": 0.388178209086899,
"grad_norm": 3.265625,
"learning_rate": 6.446605908452122e-07,
"loss": 1.5301700592041017,
"step": 220
},
{
"epoch": 0.3970004411116012,
"grad_norm": 2.203125,
"learning_rate": 5.529933307520102e-07,
"loss": 1.5099596977233887,
"step": 225
},
{
"epoch": 0.4058226731363035,
"grad_norm": 2.25,
"learning_rate": 4.6754051142374275e-07,
"loss": 1.4918466567993165,
"step": 230
},
{
"epoch": 0.4146449051610057,
"grad_norm": 5.0,
"learning_rate": 3.8857488050544903e-07,
"loss": 1.5015207290649415,
"step": 235
},
{
"epoch": 0.423467137185708,
"grad_norm": 2.796875,
"learning_rate": 3.163484798845862e-07,
"loss": 1.5009549140930176,
"step": 240
},
{
"epoch": 0.4322893692104102,
"grad_norm": 3.21875,
"learning_rate": 2.5109184122568797e-07,
"loss": 1.5147621154785156,
"step": 245
},
{
"epoch": 0.4411116012351125,
"grad_norm": 1.9765625,
"learning_rate": 1.9301325016119338e-07,
"loss": 1.5966561317443848,
"step": 250
},
{
"epoch": 0.44993383325981473,
"grad_norm": 2.609375,
"learning_rate": 1.4229808148697732e-07,
"loss": 1.5000021934509278,
"step": 255
},
{
"epoch": 0.45875606528451696,
"grad_norm": 2.15625,
"learning_rate": 9.91082074845215e-08,
"loss": 1.4867940902709962,
"step": 260
},
{
"epoch": 0.46757829730921924,
"grad_norm": 2.234375,
"learning_rate": 6.358148125822e-08,
"loss": 1.4553143501281738,
"step": 265
},
{
"epoch": 0.47640052933392146,
"grad_norm": 5.40625,
"learning_rate": 3.583129673691427e-08,
"loss": 1.5283794403076172,
"step": 270
},
{
"epoch": 0.48522276135862374,
"grad_norm": 4.625,
"learning_rate": 1.5946226744029402e-08,
"loss": 1.4848525047302246,
"step": 275
},
{
"epoch": 0.49404499338332597,
"grad_norm": 2.75,
"learning_rate": 3.989740291526212e-09,
"loss": 1.5114261627197265,
"step": 280
},
{
"epoch": 0.5011027790030878,
"step": 284,
"total_flos": 1.3705181662943232e+17,
"train_loss": 1.5080752087311007,
"train_runtime": 2339.7979,
"train_samples_per_second": 0.484,
"train_steps_per_second": 0.121
}
],
"logging_steps": 5,
"max_steps": 284,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 500,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": false,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 1.3705181662943232e+17,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}

3
training_args.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:f7799ab63fa5e8c3521addbb3d4879ddeda5d81a77924fe1e8420481f85659e4
size 6033

BIN
training_loss.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 51 KiB