lldois/v41_v29_baseline_general_replay_lr4e7_ep10
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/v41_v29_baseline_general_replay_lr4e7_ep10
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-07-19 01:57:10 +08:00
commit 816fcdc880
17 changed files with 3323 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/v29_v19_user_world_guard_lr8e7_ep018
tags:
- llama-factory
- full
- generated_from_trainer
model-index:
- name: v41_v29_baseline_general_replay_lr4e7_ep10
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. -->
# v41_v29_baseline_general_replay_lr4e7_ep10
This model is a fine-tuned version of [lldois/v29_v19_user_world_guard_lr8e7_ep018](https://huggingface.co/lldois/v29_v19_user_world_guard_lr8e7_ep018) on the exp_v41_baseline_general 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: 4e-07
- train_batch_size: 1
- eval_batch_size: 8
- seed: 202607191
- 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: 0.03
- num_epochs: 1.0
### 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": 1.0,
"total_flos": 3.68251671698516e+17,
"train_loss": 1.7103283592543677,
"train_runtime": 6160.8721,
"train_samples_per_second": 0.496,
"train_steps_per_second": 0.124
}

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
}

61
experiment_recipe.json Normal file
View File

@@ -0,0 +1,61 @@
{
"created_at": "2026-07-15 00:59:15",
"name": "v41_v29_baseline_general_replay_lr4e7_ep10",
"base": "/home/ll/llm4rec/experiments/outputs/v29_v19_user_world_guard_lr8e7_ep018",
"dataset": "v41_baseline_general",
"dataset_manifest": {
"name": "v41_baseline_general",
"path": "/home/ll/llm4rec/experiments/data/v41_baseline_general.jsonl",
"records": 80000,
"bytes": 482190982,
"sha256": "82e09565761de669ade898e8a1f743ab8e72da7e34b6effa1c780cdf12ecf007",
"requested_components": {
"general": 32000,
"r0": 8000,
"old_rec": 22000,
"old_user": 8000,
"old_item": 10000
},
"groups": {
"general": 32000,
"old_item": 10000,
"old_user": 8000,
"r0": 8000,
"old_rec": 22000
},
"variants": {
"official_general_cot": 15976,
"official_general_direct": 16024,
"original_competition": 19997,
"sid_to_caption_direct": 2051,
"item_no_think_direct_final": 1725,
"rec_no_think_direct_final": 11007,
"item_short_think": 1757,
"user_extra_no_think_logic": 514,
"caption_to_sid_direct": 3990,
"sid_to_caption_cot": 1959,
"user_strict_array": 1360,
"user_logic_json_strict": 1129,
"user_strict_logic": 1128,
"user_array_json_strict": 1383
},
"routes": {
"think": 35508,
"no_think": 44492
},
"target_leakage": 0,
"seed": 202607158
},
"learning_rate": "4.0e-7",
"epochs": 1.0,
"stages": null,
"note": "Control run dominated by original competition supervision and general replay, with no profile-derived R3.",
"cot_policy": "Preserve meaningful CoT for /think and pure final outputs for /no_think.",
"checkpoint_policy": "save_strategy=no; only the final model is retained.",
"script": "/home/ll/llm4rec/experiments/run_v34_v43.py",
"script_sha256": "fbf01773c61579cf6159f64442fc0c8902714c84ed23b488bc9a6236a154f402",
"configs": [
"/home/ll/llm4rec/experiments/configs/v41_v29_baseline_general_replay_lr4e7_ep10.yaml"
],
"reproduce": "/home/ll/llm4rec/demo/LLaMA-Factory/.venv/bin/python /home/ll/llm4rec/experiments/run_v34_v43.py --single v41_v29_baseline_general_replay_lr4e7_ep10 --gpu <gpu>"
}

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:a6ae7d5ce183ee7336d42d903ce7a1a6b5214965560befa91d5536ad873d3b30
size 1602902832

3
runs/Jul15_04-50-53_ubuntu-System-Product-Name/events.out.tfevents.1784062253.ubuntu-System-Product-Name.1384458.0 Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:a1471c137c402e9809adedf41f52c6d867361cb90cf07e45615cc784842be511
size 22310

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
}

2308
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": 1.0,
"total_flos": 3.68251671698516e+17,
"train_loss": 1.7103283592543677,
"train_runtime": 6160.8721,
"train_samples_per_second": 0.496,
"train_steps_per_second": 0.124
}

77
trainer_log.jsonl Normal file
View File

@@ -0,0 +1,77 @@
{"current_steps": 10, "total_steps": 764, "loss": 1.7698013305664062, "lr": 1.5652173913043477e-07, "epoch": 0.01309328968903437, "percentage": 1.31, "elapsed_time": "0:01:22", "remaining_time": "1:43:06"}
{"current_steps": 20, "total_steps": 764, "loss": 1.8119827270507813, "lr": 3.304347826086956e-07, "epoch": 0.02618657937806874, "percentage": 2.62, "elapsed_time": "0:02:42", "remaining_time": "1:41:01"}
{"current_steps": 30, "total_steps": 764, "loss": 1.6693140029907227, "lr": 3.9993529431919234e-07, "epoch": 0.03927986906710311, "percentage": 3.93, "elapsed_time": "0:04:03", "remaining_time": "1:39:27"}
{"current_steps": 40, "total_steps": 764, "loss": 1.6907798767089843, "lr": 3.995400223257334e-07, "epoch": 0.05237315875613748, "percentage": 5.24, "elapsed_time": "0:05:24", "remaining_time": "1:37:52"}
{"current_steps": 50, "total_steps": 764, "loss": 1.6979778289794922, "lr": 3.9878613546358986e-07, "epoch": 0.06546644844517185, "percentage": 6.54, "elapsed_time": "0:06:43", "remaining_time": "1:36:03"}
{"current_steps": 60, "total_steps": 764, "loss": 1.8435844421386718, "lr": 3.9767498862405076e-07, "epoch": 0.07855973813420622, "percentage": 7.85, "elapsed_time": "0:08:04", "remaining_time": "1:34:44"}
{"current_steps": 70, "total_steps": 764, "loss": 1.7747735977172852, "lr": 3.9620857876879474e-07, "epoch": 0.09165302782324058, "percentage": 9.16, "elapsed_time": "0:09:26", "remaining_time": "1:33:40"}
{"current_steps": 80, "total_steps": 764, "loss": 1.5791229248046874, "lr": 3.943895413409353e-07, "epoch": 0.10474631751227496, "percentage": 10.47, "elapsed_time": "0:10:44", "remaining_time": "1:31:52"}
{"current_steps": 90, "total_steps": 764, "loss": 1.7737991333007812, "lr": 3.9222114552858167e-07, "epoch": 0.11783960720130933, "percentage": 11.78, "elapsed_time": "0:12:03", "remaining_time": "1:30:20"}
{"current_steps": 100, "total_steps": 764, "loss": 1.6754600524902343, "lr": 3.8970728838942903e-07, "epoch": 0.1309328968903437, "percentage": 13.09, "elapsed_time": "0:13:23", "remaining_time": "1:28:52"}
{"current_steps": 110, "total_steps": 764, "loss": 1.663345718383789, "lr": 3.8685248784693646e-07, "epoch": 0.14402618657937807, "percentage": 14.4, "elapsed_time": "0:14:43", "remaining_time": "1:27:30"}
{"current_steps": 120, "total_steps": 764, "loss": 1.7084470748901368, "lr": 3.8366187457067924e-07, "epoch": 0.15711947626841244, "percentage": 15.71, "elapsed_time": "0:16:05", "remaining_time": "1:26:22"}
{"current_steps": 130, "total_steps": 764, "loss": 1.6630699157714843, "lr": 3.8014118275547113e-07, "epoch": 0.1702127659574468, "percentage": 17.02, "elapsed_time": "0:17:28", "remaining_time": "1:25:12"}
{"current_steps": 140, "total_steps": 764, "loss": 1.7131948471069336, "lr": 3.7629673981582394e-07, "epoch": 0.18330605564648117, "percentage": 18.32, "elapsed_time": "0:18:47", "remaining_time": "1:23:44"}
{"current_steps": 150, "total_steps": 764, "loss": 1.707387351989746, "lr": 3.7213545501427004e-07, "epoch": 0.19639934533551553, "percentage": 19.63, "elapsed_time": "0:20:06", "remaining_time": "1:22:19"}
{"current_steps": 160, "total_steps": 764, "loss": 1.6667047500610352, "lr": 3.676648070439823e-07, "epoch": 0.20949263502454993, "percentage": 20.94, "elapsed_time": "0:21:28", "remaining_time": "1:21:03"}
{"current_steps": 170, "total_steps": 764, "loss": 1.6005857467651368, "lr": 3.628928305880089e-07, "epoch": 0.2225859247135843, "percentage": 22.25, "elapsed_time": "0:22:50", "remaining_time": "1:19:48"}
{"current_steps": 180, "total_steps": 764, "loss": 1.7023710250854491, "lr": 3.578281018792787e-07, "epoch": 0.23567921440261866, "percentage": 23.56, "elapsed_time": "0:24:10", "remaining_time": "1:18:24"}
{"current_steps": 190, "total_steps": 764, "loss": 1.7205501556396485, "lr": 3.524797232873297e-07, "epoch": 0.24877250409165302, "percentage": 24.87, "elapsed_time": "0:25:30", "remaining_time": "1:17:02"}
{"current_steps": 200, "total_steps": 764, "loss": 1.7906591415405273, "lr": 3.4685730695945973e-07, "epoch": 0.2618657937806874, "percentage": 26.18, "elapsed_time": "0:26:52", "remaining_time": "1:15:46"}
{"current_steps": 210, "total_steps": 764, "loss": 1.7032752990722657, "lr": 3.409709575457015e-07, "epoch": 0.27495908346972175, "percentage": 27.49, "elapsed_time": "0:28:12", "remaining_time": "1:14:26"}
{"current_steps": 220, "total_steps": 764, "loss": 1.767839241027832, "lr": 3.348312540386673e-07, "epoch": 0.28805237315875615, "percentage": 28.8, "elapsed_time": "0:29:33", "remaining_time": "1:13:04"}
{"current_steps": 230, "total_steps": 764, "loss": 1.6559026718139649, "lr": 3.28449230760902e-07, "epoch": 0.3011456628477905, "percentage": 30.1, "elapsed_time": "0:30:55", "remaining_time": "1:11:47"}
{"current_steps": 240, "total_steps": 764, "loss": 1.7474025726318358, "lr": 3.218363575339131e-07, "epoch": 0.3142389525368249, "percentage": 31.41, "elapsed_time": "0:32:14", "remaining_time": "1:10:23"}
{"current_steps": 250, "total_steps": 764, "loss": 1.7392288208007813, "lr": 3.1500451906451933e-07, "epoch": 0.32733224222585927, "percentage": 32.72, "elapsed_time": "0:33:32", "remaining_time": "1:08:58"}
{"current_steps": 260, "total_steps": 764, "loss": 1.7795156478881835, "lr": 3.079659935855634e-07, "epoch": 0.3404255319148936, "percentage": 34.03, "elapsed_time": "0:34:54", "remaining_time": "1:07:39"}
{"current_steps": 270, "total_steps": 764, "loss": 1.6928770065307617, "lr": 3.0073343078937755e-07, "epoch": 0.353518821603928, "percentage": 35.34, "elapsed_time": "0:36:15", "remaining_time": "1:06:19"}
{"current_steps": 280, "total_steps": 764, "loss": 1.7049606323242188, "lr": 2.9331982909365844e-07, "epoch": 0.36661211129296234, "percentage": 36.65, "elapsed_time": "0:37:36", "remaining_time": "1:05:00"}
{"current_steps": 290, "total_steps": 764, "loss": 1.7637083053588867, "lr": 2.857385122806108e-07, "epoch": 0.37970540098199673, "percentage": 37.96, "elapsed_time": "0:38:55", "remaining_time": "1:03:37"}
{"current_steps": 300, "total_steps": 764, "loss": 1.7917778015136718, "lr": 2.7800310555134313e-07, "epoch": 0.39279869067103107, "percentage": 39.27, "elapsed_time": "0:40:14", "remaining_time": "1:02:14"}
{"current_steps": 310, "total_steps": 764, "loss": 1.6547735214233399, "lr": 2.7012751103855087e-07, "epoch": 0.40589198036006546, "percentage": 40.58, "elapsed_time": "0:41:35", "remaining_time": "1:00:54"}
{"current_steps": 320, "total_steps": 764, "loss": 1.718545913696289, "lr": 2.6212588282149646e-07, "epoch": 0.41898527004909986, "percentage": 41.88, "elapsed_time": "0:42:57", "remaining_time": "0:59:35"}
{"current_steps": 330, "total_steps": 764, "loss": 1.7531944274902345, "lr": 2.5401260148818855e-07, "epoch": 0.4320785597381342, "percentage": 43.19, "elapsed_time": "0:44:16", "remaining_time": "0:58:13"}
{"current_steps": 340, "total_steps": 764, "loss": 1.8378955841064453, "lr": 2.458022482904785e-07, "epoch": 0.4451718494271686, "percentage": 44.5, "elapsed_time": "0:45:35", "remaining_time": "0:56:51"}
{"current_steps": 350, "total_steps": 764, "loss": 1.7262359619140626, "lr": 2.3750957893852184e-07, "epoch": 0.4582651391162029, "percentage": 45.81, "elapsed_time": "0:46:56", "remaining_time": "0:55:31"}
{"current_steps": 360, "total_steps": 764, "loss": 1.7179519653320312, "lr": 2.2914949708170187e-07, "epoch": 0.4713584288052373, "percentage": 47.12, "elapsed_time": "0:48:17", "remaining_time": "0:54:12"}
{"current_steps": 370, "total_steps": 764, "loss": 1.6968917846679688, "lr": 2.2073702752367623e-07, "epoch": 0.4844517184942717, "percentage": 48.43, "elapsed_time": "0:49:37", "remaining_time": "0:52:50"}
{"current_steps": 380, "total_steps": 764, "loss": 1.7417394638061523, "lr": 2.1228728921968352e-07, "epoch": 0.49754500818330605, "percentage": 49.74, "elapsed_time": "0:50:58", "remaining_time": "0:51:31"}
{"current_steps": 390, "total_steps": 764, "loss": 1.6095331192016602, "lr": 2.0381546810464044e-07, "epoch": 0.5106382978723404, "percentage": 51.05, "elapsed_time": "0:52:21", "remaining_time": "0:50:12"}
{"current_steps": 400, "total_steps": 764, "loss": 1.675015640258789, "lr": 1.9533678980086213e-07, "epoch": 0.5237315875613748, "percentage": 52.36, "elapsed_time": "0:53:43", "remaining_time": "0:48:53"}
{"current_steps": 410, "total_steps": 764, "loss": 1.8056396484375, "lr": 1.8686649225445636e-07, "epoch": 0.5368248772504092, "percentage": 53.66, "elapsed_time": "0:55:02", "remaining_time": "0:47:31"}
{"current_steps": 420, "total_steps": 764, "loss": 1.7800405502319336, "lr": 1.784197983495689e-07, "epoch": 0.5499181669394435, "percentage": 54.97, "elapsed_time": "0:56:22", "remaining_time": "0:46:10"}
{"current_steps": 430, "total_steps": 764, "loss": 1.7622718811035156, "lr": 1.700118885496989e-07, "epoch": 0.563011456628478, "percentage": 56.28, "elapsed_time": "0:57:42", "remaining_time": "0:44:49"}
{"current_steps": 440, "total_steps": 764, "loss": 1.738749885559082, "lr": 1.6165787361525235e-07, "epoch": 0.5761047463175123, "percentage": 57.59, "elapsed_time": "0:59:02", "remaining_time": "0:43:28"}
{"current_steps": 450, "total_steps": 764, "loss": 1.6596288681030273, "lr": 1.5337276744636715e-07, "epoch": 0.5891980360065466, "percentage": 58.9, "elapsed_time": "1:00:23", "remaining_time": "0:42:08"}
{"current_steps": 460, "total_steps": 764, "loss": 1.5231310844421386, "lr": 1.4517146009981576e-07, "epoch": 0.602291325695581, "percentage": 60.21, "elapsed_time": "1:01:47", "remaining_time": "0:40:50"}
{"current_steps": 470, "total_steps": 764, "loss": 1.6872207641601562, "lr": 1.3706869102847999e-07, "epoch": 0.6153846153846154, "percentage": 61.52, "elapsed_time": "1:03:07", "remaining_time": "0:39:29"}
{"current_steps": 480, "total_steps": 764, "loss": 1.7282188415527344, "lr": 1.2907902259149286e-07, "epoch": 0.6284779050736498, "percentage": 62.83, "elapsed_time": "1:04:28", "remaining_time": "0:38:08"}
{"current_steps": 490, "total_steps": 764, "loss": 1.6931528091430663, "lr": 1.2121681388265402e-07, "epoch": 0.6415711947626841, "percentage": 64.14, "elapsed_time": "1:05:51", "remaining_time": "0:36:49"}
{"current_steps": 500, "total_steps": 764, "loss": 1.7433677673339845, "lr": 1.1349619492415559e-07, "epoch": 0.6546644844517185, "percentage": 65.45, "elapsed_time": "1:07:10", "remaining_time": "0:35:27"}
{"current_steps": 510, "total_steps": 764, "loss": 1.7254501342773438, "lr": 1.0593104127199734e-07, "epoch": 0.6677577741407529, "percentage": 66.75, "elapsed_time": "1:08:29", "remaining_time": "0:34:06"}
{"current_steps": 520, "total_steps": 764, "loss": 1.6848495483398438, "lr": 9.853494907873017e-08, "epoch": 0.6808510638297872, "percentage": 68.06, "elapsed_time": "1:09:51", "remaining_time": "0:32:46"}
{"current_steps": 530, "total_steps": 764, "loss": 1.7002685546875, "lr": 9.132121065834575e-08, "epoch": 0.6939443535188216, "percentage": 69.37, "elapsed_time": "1:11:10", "remaining_time": "0:31:25"}
{"current_steps": 540, "total_steps": 764, "loss": 1.7304063796997071, "lr": 8.430279059722733e-08, "epoch": 0.707037643207856, "percentage": 70.68, "elapsed_time": "1:12:31", "remaining_time": "0:30:05"}
{"current_steps": 550, "total_steps": 764, "loss": 1.690472412109375, "lr": 7.74923024540949e-08, "epoch": 0.7201309328968903, "percentage": 71.99, "elapsed_time": "1:13:52", "remaining_time": "0:28:44"}
{"current_steps": 560, "total_steps": 764, "loss": 1.6513166427612305, "lr": 7.090198609081998e-08, "epoch": 0.7332242225859247, "percentage": 73.3, "elapsed_time": "1:15:12", "remaining_time": "0:27:23"}
{"current_steps": 570, "total_steps": 764, "loss": 1.827246856689453, "lr": 6.454368567485182e-08, "epoch": 0.7463175122749591, "percentage": 74.61, "elapsed_time": "1:16:30", "remaining_time": "0:26:02"}
{"current_steps": 580, "total_steps": 764, "loss": 1.6964548110961915, "lr": 5.84288283927874e-08, "epoch": 0.7594108019639935, "percentage": 75.92, "elapsed_time": "1:17:51", "remaining_time": "0:24:42"}
{"current_steps": 590, "total_steps": 764, "loss": 1.660973358154297, "lr": 5.2568403913344275e-08, "epoch": 0.7725040916530278, "percentage": 77.23, "elapsed_time": "1:19:12", "remaining_time": "0:23:21"}
{"current_steps": 600, "total_steps": 764, "loss": 1.725875473022461, "lr": 4.697294463664261e-08, "epoch": 0.7855973813420621, "percentage": 78.53, "elapsed_time": "1:20:32", "remaining_time": "0:22:00"}
{"current_steps": 610, "total_steps": 764, "loss": 1.63555965423584, "lr": 4.165250676529466e-08, "epoch": 0.7986906710310966, "percentage": 79.84, "elapsed_time": "1:21:55", "remaining_time": "0:20:40"}
{"current_steps": 620, "total_steps": 764, "loss": 1.6531944274902344, "lr": 3.6616652231319514e-08, "epoch": 0.8117839607201309, "percentage": 81.15, "elapsed_time": "1:23:18", "remaining_time": "0:19:21"}
{"current_steps": 630, "total_steps": 764, "loss": 1.6328155517578125, "lr": 3.187443151136533e-08, "epoch": 0.8248772504091653, "percentage": 82.46, "elapsed_time": "1:24:40", "remaining_time": "0:18:00"}
{"current_steps": 640, "total_steps": 764, "loss": 1.6354242324829102, "lr": 2.7434367361122502e-08, "epoch": 0.8379705400981997, "percentage": 83.77, "elapsed_time": "1:26:02", "remaining_time": "0:16:40"}
{"current_steps": 650, "total_steps": 764, "loss": 1.7544931411743163, "lr": 2.3304439498161632e-08, "epoch": 0.851063829787234, "percentage": 85.08, "elapsed_time": "1:27:21", "remaining_time": "0:15:19"}
{"current_steps": 660, "total_steps": 764, "loss": 1.6700428009033204, "lr": 1.949207026072348e-08, "epoch": 0.8641571194762684, "percentage": 86.39, "elapsed_time": "1:28:40", "remaining_time": "0:13:58"}
{"current_steps": 670, "total_steps": 764, "loss": 1.6820402145385742, "lr": 1.6004111268235156e-08, "epoch": 0.8772504091653028, "percentage": 87.7, "elapsed_time": "1:30:03", "remaining_time": "0:12:38"}
{"current_steps": 680, "total_steps": 764, "loss": 1.7066337585449218, "lr": 1.2846831107526956e-08, "epoch": 0.8903436988543372, "percentage": 89.01, "elapsed_time": "1:31:24", "remaining_time": "0:11:17"}
{"current_steps": 690, "total_steps": 764, "loss": 1.7003616333007812, "lr": 1.0025904066879687e-08, "epoch": 0.9034369885433715, "percentage": 90.31, "elapsed_time": "1:32:48", "remaining_time": "0:09:57"}
{"current_steps": 700, "total_steps": 764, "loss": 1.6916650772094726, "lr": 7.546399938149916e-09, "epoch": 0.9165302782324058, "percentage": 91.62, "elapsed_time": "1:34:07", "remaining_time": "0:08:36"}
{"current_steps": 710, "total_steps": 764, "loss": 1.6705923080444336, "lr": 5.412774905300987e-09, "epoch": 0.9296235679214403, "percentage": 92.93, "elapsed_time": "1:35:30", "remaining_time": "0:07:15"}
{"current_steps": 720, "total_steps": 764, "loss": 1.7059362411499024, "lr": 3.628863535714699e-09, "epoch": 0.9427168576104746, "percentage": 94.24, "elapsed_time": "1:36:49", "remaining_time": "0:05:55"}
{"current_steps": 730, "total_steps": 764, "loss": 1.783282470703125, "lr": 2.1978718886772608e-09, "epoch": 0.955810147299509, "percentage": 95.55, "elapsed_time": "1:38:07", "remaining_time": "0:04:34"}
{"current_steps": 740, "total_steps": 764, "loss": 1.7798967361450195, "lr": 1.1223717534248001e-09, "epoch": 0.9689034369885434, "percentage": 96.86, "elapsed_time": "1:39:26", "remaining_time": "0:03:13"}
{"current_steps": 750, "total_steps": 764, "loss": 1.7239389419555664, "lr": 4.0429602710385646e-10, "epoch": 0.9819967266775778, "percentage": 98.17, "elapsed_time": "1:40:48", "remaining_time": "0:01:52"}
{"current_steps": 760, "total_steps": 764, "loss": 1.678044319152832, "lr": 4.4935240953702935e-11, "epoch": 0.9950900163666121, "percentage": 99.48, "elapsed_time": "1:42:10", "remaining_time": "0:00:32"}
{"current_steps": 764, "total_steps": 764, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "1:42:40", "remaining_time": "0:00:00"}

575
trainer_state.json Normal file
View File

@@ -0,0 +1,575 @@
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.0,
"eval_steps": 500,
"global_step": 764,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.01309328968903437,
"grad_norm": 4.5625,
"learning_rate": 1.5652173913043477e-07,
"loss": 1.7698013305664062,
"step": 10
},
{
"epoch": 0.02618657937806874,
"grad_norm": 4.75,
"learning_rate": 3.304347826086956e-07,
"loss": 1.8119827270507813,
"step": 20
},
{
"epoch": 0.03927986906710311,
"grad_norm": 8.6875,
"learning_rate": 3.9993529431919234e-07,
"loss": 1.6693140029907227,
"step": 30
},
{
"epoch": 0.05237315875613748,
"grad_norm": 7.59375,
"learning_rate": 3.995400223257334e-07,
"loss": 1.6907798767089843,
"step": 40
},
{
"epoch": 0.06546644844517185,
"grad_norm": 6.5,
"learning_rate": 3.9878613546358986e-07,
"loss": 1.6979778289794922,
"step": 50
},
{
"epoch": 0.07855973813420622,
"grad_norm": 5.84375,
"learning_rate": 3.9767498862405076e-07,
"loss": 1.8435844421386718,
"step": 60
},
{
"epoch": 0.09165302782324058,
"grad_norm": 4.9375,
"learning_rate": 3.9620857876879474e-07,
"loss": 1.7747735977172852,
"step": 70
},
{
"epoch": 0.10474631751227496,
"grad_norm": 6.5,
"learning_rate": 3.943895413409353e-07,
"loss": 1.5791229248046874,
"step": 80
},
{
"epoch": 0.11783960720130933,
"grad_norm": 4.84375,
"learning_rate": 3.9222114552858167e-07,
"loss": 1.7737991333007812,
"step": 90
},
{
"epoch": 0.1309328968903437,
"grad_norm": 4.4375,
"learning_rate": 3.8970728838942903e-07,
"loss": 1.6754600524902343,
"step": 100
},
{
"epoch": 0.14402618657937807,
"grad_norm": 14.0625,
"learning_rate": 3.8685248784693646e-07,
"loss": 1.663345718383789,
"step": 110
},
{
"epoch": 0.15711947626841244,
"grad_norm": 5.0,
"learning_rate": 3.8366187457067924e-07,
"loss": 1.7084470748901368,
"step": 120
},
{
"epoch": 0.1702127659574468,
"grad_norm": 4.375,
"learning_rate": 3.8014118275547113e-07,
"loss": 1.6630699157714843,
"step": 130
},
{
"epoch": 0.18330605564648117,
"grad_norm": 4.15625,
"learning_rate": 3.7629673981582394e-07,
"loss": 1.7131948471069336,
"step": 140
},
{
"epoch": 0.19639934533551553,
"grad_norm": 5.03125,
"learning_rate": 3.7213545501427004e-07,
"loss": 1.707387351989746,
"step": 150
},
{
"epoch": 0.20949263502454993,
"grad_norm": 5.0,
"learning_rate": 3.676648070439823e-07,
"loss": 1.6667047500610352,
"step": 160
},
{
"epoch": 0.2225859247135843,
"grad_norm": 5.28125,
"learning_rate": 3.628928305880089e-07,
"loss": 1.6005857467651368,
"step": 170
},
{
"epoch": 0.23567921440261866,
"grad_norm": 5.28125,
"learning_rate": 3.578281018792787e-07,
"loss": 1.7023710250854491,
"step": 180
},
{
"epoch": 0.24877250409165302,
"grad_norm": 5.84375,
"learning_rate": 3.524797232873297e-07,
"loss": 1.7205501556396485,
"step": 190
},
{
"epoch": 0.2618657937806874,
"grad_norm": 4.5,
"learning_rate": 3.4685730695945973e-07,
"loss": 1.7906591415405273,
"step": 200
},
{
"epoch": 0.27495908346972175,
"grad_norm": 4.6875,
"learning_rate": 3.409709575457015e-07,
"loss": 1.7032752990722657,
"step": 210
},
{
"epoch": 0.28805237315875615,
"grad_norm": 4.71875,
"learning_rate": 3.348312540386673e-07,
"loss": 1.767839241027832,
"step": 220
},
{
"epoch": 0.3011456628477905,
"grad_norm": 4.375,
"learning_rate": 3.28449230760902e-07,
"loss": 1.6559026718139649,
"step": 230
},
{
"epoch": 0.3142389525368249,
"grad_norm": 4.0625,
"learning_rate": 3.218363575339131e-07,
"loss": 1.7474025726318358,
"step": 240
},
{
"epoch": 0.32733224222585927,
"grad_norm": 4.71875,
"learning_rate": 3.1500451906451933e-07,
"loss": 1.7392288208007813,
"step": 250
},
{
"epoch": 0.3404255319148936,
"grad_norm": 4.6875,
"learning_rate": 3.079659935855634e-07,
"loss": 1.7795156478881835,
"step": 260
},
{
"epoch": 0.353518821603928,
"grad_norm": 6.6875,
"learning_rate": 3.0073343078937755e-07,
"loss": 1.6928770065307617,
"step": 270
},
{
"epoch": 0.36661211129296234,
"grad_norm": 5.28125,
"learning_rate": 2.9331982909365844e-07,
"loss": 1.7049606323242188,
"step": 280
},
{
"epoch": 0.37970540098199673,
"grad_norm": 5.375,
"learning_rate": 2.857385122806108e-07,
"loss": 1.7637083053588867,
"step": 290
},
{
"epoch": 0.39279869067103107,
"grad_norm": 4.28125,
"learning_rate": 2.7800310555134313e-07,
"loss": 1.7917778015136718,
"step": 300
},
{
"epoch": 0.40589198036006546,
"grad_norm": 6.09375,
"learning_rate": 2.7012751103855087e-07,
"loss": 1.6547735214233399,
"step": 310
},
{
"epoch": 0.41898527004909986,
"grad_norm": 4.78125,
"learning_rate": 2.6212588282149646e-07,
"loss": 1.718545913696289,
"step": 320
},
{
"epoch": 0.4320785597381342,
"grad_norm": 5.40625,
"learning_rate": 2.5401260148818855e-07,
"loss": 1.7531944274902345,
"step": 330
},
{
"epoch": 0.4451718494271686,
"grad_norm": 7.75,
"learning_rate": 2.458022482904785e-07,
"loss": 1.8378955841064453,
"step": 340
},
{
"epoch": 0.4582651391162029,
"grad_norm": 4.21875,
"learning_rate": 2.3750957893852184e-07,
"loss": 1.7262359619140626,
"step": 350
},
{
"epoch": 0.4713584288052373,
"grad_norm": 4.3125,
"learning_rate": 2.2914949708170187e-07,
"loss": 1.7179519653320312,
"step": 360
},
{
"epoch": 0.4844517184942717,
"grad_norm": 4.34375,
"learning_rate": 2.2073702752367623e-07,
"loss": 1.6968917846679688,
"step": 370
},
{
"epoch": 0.49754500818330605,
"grad_norm": 4.1875,
"learning_rate": 2.1228728921968352e-07,
"loss": 1.7417394638061523,
"step": 380
},
{
"epoch": 0.5106382978723404,
"grad_norm": 4.5,
"learning_rate": 2.0381546810464044e-07,
"loss": 1.6095331192016602,
"step": 390
},
{
"epoch": 0.5237315875613748,
"grad_norm": 5.3125,
"learning_rate": 1.9533678980086213e-07,
"loss": 1.675015640258789,
"step": 400
},
{
"epoch": 0.5368248772504092,
"grad_norm": 6.15625,
"learning_rate": 1.8686649225445636e-07,
"loss": 1.8056396484375,
"step": 410
},
{
"epoch": 0.5499181669394435,
"grad_norm": 4.8125,
"learning_rate": 1.784197983495689e-07,
"loss": 1.7800405502319336,
"step": 420
},
{
"epoch": 0.563011456628478,
"grad_norm": 5.09375,
"learning_rate": 1.700118885496989e-07,
"loss": 1.7622718811035156,
"step": 430
},
{
"epoch": 0.5761047463175123,
"grad_norm": 4.84375,
"learning_rate": 1.6165787361525235e-07,
"loss": 1.738749885559082,
"step": 440
},
{
"epoch": 0.5891980360065466,
"grad_norm": 4.375,
"learning_rate": 1.5337276744636715e-07,
"loss": 1.6596288681030273,
"step": 450
},
{
"epoch": 0.602291325695581,
"grad_norm": 8.625,
"learning_rate": 1.4517146009981576e-07,
"loss": 1.5231310844421386,
"step": 460
},
{
"epoch": 0.6153846153846154,
"grad_norm": 8.0,
"learning_rate": 1.3706869102847999e-07,
"loss": 1.6872207641601562,
"step": 470
},
{
"epoch": 0.6284779050736498,
"grad_norm": 4.125,
"learning_rate": 1.2907902259149286e-07,
"loss": 1.7282188415527344,
"step": 480
},
{
"epoch": 0.6415711947626841,
"grad_norm": 5.4375,
"learning_rate": 1.2121681388265402e-07,
"loss": 1.6931528091430663,
"step": 490
},
{
"epoch": 0.6546644844517185,
"grad_norm": 6.84375,
"learning_rate": 1.1349619492415559e-07,
"loss": 1.7433677673339845,
"step": 500
},
{
"epoch": 0.6677577741407529,
"grad_norm": 4.5,
"learning_rate": 1.0593104127199734e-07,
"loss": 1.7254501342773438,
"step": 510
},
{
"epoch": 0.6808510638297872,
"grad_norm": 4.96875,
"learning_rate": 9.853494907873017e-08,
"loss": 1.6848495483398438,
"step": 520
},
{
"epoch": 0.6939443535188216,
"grad_norm": 4.8125,
"learning_rate": 9.132121065834575e-08,
"loss": 1.7002685546875,
"step": 530
},
{
"epoch": 0.707037643207856,
"grad_norm": 5.15625,
"learning_rate": 8.430279059722733e-08,
"loss": 1.7304063796997071,
"step": 540
},
{
"epoch": 0.7201309328968903,
"grad_norm": 7.09375,
"learning_rate": 7.74923024540949e-08,
"loss": 1.690472412109375,
"step": 550
},
{
"epoch": 0.7332242225859247,
"grad_norm": 4.40625,
"learning_rate": 7.090198609081998e-08,
"loss": 1.6513166427612305,
"step": 560
},
{
"epoch": 0.7463175122749591,
"grad_norm": 4.9375,
"learning_rate": 6.454368567485182e-08,
"loss": 1.827246856689453,
"step": 570
},
{
"epoch": 0.7594108019639935,
"grad_norm": 4.59375,
"learning_rate": 5.84288283927874e-08,
"loss": 1.6964548110961915,
"step": 580
},
{
"epoch": 0.7725040916530278,
"grad_norm": 6.625,
"learning_rate": 5.2568403913344275e-08,
"loss": 1.660973358154297,
"step": 590
},
{
"epoch": 0.7855973813420621,
"grad_norm": 4.71875,
"learning_rate": 4.697294463664261e-08,
"loss": 1.725875473022461,
"step": 600
},
{
"epoch": 0.7986906710310966,
"grad_norm": 4.0625,
"learning_rate": 4.165250676529466e-08,
"loss": 1.63555965423584,
"step": 610
},
{
"epoch": 0.8117839607201309,
"grad_norm": 3.796875,
"learning_rate": 3.6616652231319514e-08,
"loss": 1.6531944274902344,
"step": 620
},
{
"epoch": 0.8248772504091653,
"grad_norm": 5.5625,
"learning_rate": 3.187443151136533e-08,
"loss": 1.6328155517578125,
"step": 630
},
{
"epoch": 0.8379705400981997,
"grad_norm": 5.25,
"learning_rate": 2.7434367361122502e-08,
"loss": 1.6354242324829102,
"step": 640
},
{
"epoch": 0.851063829787234,
"grad_norm": 4.40625,
"learning_rate": 2.3304439498161632e-08,
"loss": 1.7544931411743163,
"step": 650
},
{
"epoch": 0.8641571194762684,
"grad_norm": 4.34375,
"learning_rate": 1.949207026072348e-08,
"loss": 1.6700428009033204,
"step": 660
},
{
"epoch": 0.8772504091653028,
"grad_norm": 5.25,
"learning_rate": 1.6004111268235156e-08,
"loss": 1.6820402145385742,
"step": 670
},
{
"epoch": 0.8903436988543372,
"grad_norm": 5.25,
"learning_rate": 1.2846831107526956e-08,
"loss": 1.7066337585449218,
"step": 680
},
{
"epoch": 0.9034369885433715,
"grad_norm": 4.875,
"learning_rate": 1.0025904066879687e-08,
"loss": 1.7003616333007812,
"step": 690
},
{
"epoch": 0.9165302782324058,
"grad_norm": 4.25,
"learning_rate": 7.546399938149916e-09,
"loss": 1.6916650772094726,
"step": 700
},
{
"epoch": 0.9296235679214403,
"grad_norm": 4.5,
"learning_rate": 5.412774905300987e-09,
"loss": 1.6705923080444336,
"step": 710
},
{
"epoch": 0.9427168576104746,
"grad_norm": 4.90625,
"learning_rate": 3.628863535714699e-09,
"loss": 1.7059362411499024,
"step": 720
},
{
"epoch": 0.955810147299509,
"grad_norm": 4.90625,
"learning_rate": 2.1978718886772608e-09,
"loss": 1.783282470703125,
"step": 730
},
{
"epoch": 0.9689034369885434,
"grad_norm": 4.5625,
"learning_rate": 1.1223717534248001e-09,
"loss": 1.7798967361450195,
"step": 740
},
{
"epoch": 0.9819967266775778,
"grad_norm": 4.1875,
"learning_rate": 4.0429602710385646e-10,
"loss": 1.7239389419555664,
"step": 750
},
{
"epoch": 0.9950900163666121,
"grad_norm": 4.40625,
"learning_rate": 4.4935240953702935e-11,
"loss": 1.678044319152832,
"step": 760
},
{
"epoch": 1.0,
"step": 764,
"total_flos": 3.68251671698516e+17,
"train_loss": 1.7103283592543677,
"train_runtime": 6160.8721,
"train_samples_per_second": 0.496,
"train_steps_per_second": 0.124
}
],
"logging_steps": 10,
"max_steps": 764,
"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": 3.68251671698516e+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 sha256:6f8005754a149e6988e5773636e0de07b759393f25fcd87f09af86ea52682869
size 6033

BIN
training_loss.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 57 KiB