初始化项目,由ModelHub XC社区提供模型
Model: bsq1989/qwen_4b_sql Source: Original Platform
This commit is contained in:
36
.gitattributes
vendored
Normal file
36
.gitattributes
vendored
Normal 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
|
||||||
131
README.md
Normal file
131
README.md
Normal file
@@ -0,0 +1,131 @@
|
|||||||
|
---
|
||||||
|
base_model: Qwen/Qwen3-4B-Base
|
||||||
|
library_name: transformers
|
||||||
|
pipeline_tag: text-generation
|
||||||
|
tags:
|
||||||
|
- text-to-sql
|
||||||
|
- sql
|
||||||
|
- qwen3
|
||||||
|
- llamafactory
|
||||||
|
- spider
|
||||||
|
- spider-test-suite
|
||||||
|
---
|
||||||
|
|
||||||
|
# qwen_4b_sql
|
||||||
|
|
||||||
|
`qwen_4b_sql` is a `Qwen3-4B-Base` model finetuned for text-to-SQL generation with full SFT on a cleaned split of `PipableAI/pip-txt-to-sql-spider-bird-dataset`.
|
||||||
|
|
||||||
|
This repository tracks the stronger 4B checkpoint from our H20 single-GPU training runs. In our internal comparison, this checkpoint outperformed the corresponding `Qwen3-1.7B-Base` baseline on Spider execution accuracy.
|
||||||
|
|
||||||
|
## Base Model
|
||||||
|
|
||||||
|
- Base model: [`Qwen/Qwen3-4B-Base`](https://huggingface.co/Qwen/Qwen3-4B-Base)
|
||||||
|
- Finetuning framework: `LLaMA-Factory`
|
||||||
|
- Training mode: `Full SFT`
|
||||||
|
- Task: `schema + question -> SQL only`
|
||||||
|
|
||||||
|
## Training Data
|
||||||
|
|
||||||
|
- Primary dataset: [`PipableAI/pip-txt-to-sql-spider-bird-dataset`](https://huggingface.co/datasets/PipableAI/pip-txt-to-sql-spider-bird-dataset)
|
||||||
|
- We used a cleaned local split derived from that dataset for train/validation
|
||||||
|
|
||||||
|
## Training Setup
|
||||||
|
|
||||||
|
- Hardware: single `NVIDIA H20 96GB`
|
||||||
|
- Precision: `bf16`
|
||||||
|
- Context length: `2048`
|
||||||
|
- Per-device train batch size: `1`
|
||||||
|
- Gradient accumulation steps: `8`
|
||||||
|
- Effective batch size: `8`
|
||||||
|
- Learning rate: `5e-6`
|
||||||
|
- Scheduler: `cosine`
|
||||||
|
- Warmup steps: `300`
|
||||||
|
- Epochs: `4.0`
|
||||||
|
- Template: `qwen3_nothink`
|
||||||
|
- Best-checkpoint selection: `load_best_model_at_end = true`
|
||||||
|
|
||||||
|
## Spider Benchmark
|
||||||
|
|
||||||
|
The following numbers are from Spider dev using the official evaluation tooling:
|
||||||
|
|
||||||
|
- Official `match` evaluation from `test-suite-sql-eval`
|
||||||
|
- Official Spider `Test Suite` execution evaluation
|
||||||
|
|
||||||
|
### Main Results
|
||||||
|
|
||||||
|
| Metric | Score |
|
||||||
|
| --- | ---: |
|
||||||
|
| Spider official exact match | 35.0% |
|
||||||
|
| Spider Test Suite execution accuracy | 67.6% |
|
||||||
|
|
||||||
|
### Difficulty Breakdown
|
||||||
|
|
||||||
|
| Difficulty | Exact Match | Test Suite Exec |
|
||||||
|
| --- | ---: | ---: |
|
||||||
|
| Easy | 64.9% | 87.5% |
|
||||||
|
| Medium | 37.4% | 72.9% |
|
||||||
|
| Hard | 16.1% | 50.0% |
|
||||||
|
| Extra | 3.6% | 42.2% |
|
||||||
|
|
||||||
|
## Notes
|
||||||
|
|
||||||
|
- This model is stronger under execution-based Spider evaluation than our best `Qwen3-1.7B-Base` run.
|
||||||
|
- In our experiments, exact-match metrics were often stricter than execution-based metrics because semantically valid SQL rewrites do not always match the Spider gold form exactly.
|
||||||
|
- A later 4B rerun with altered training settings underperformed this checkpoint on Spider and is not the checkpoint published here.
|
||||||
|
|
||||||
|
## Intended Use
|
||||||
|
|
||||||
|
This model is intended for:
|
||||||
|
|
||||||
|
- text-to-SQL research baselines
|
||||||
|
- schema-conditioned SQL generation experiments
|
||||||
|
- single-turn SQL generation from natural language plus schema text
|
||||||
|
|
||||||
|
It is not validated for:
|
||||||
|
|
||||||
|
- production-grade database access control
|
||||||
|
- unrestricted execution over arbitrary enterprise schemas
|
||||||
|
- multi-turn agent workflows without extra prompting / tooling
|
||||||
|
|
||||||
|
## Example Usage
|
||||||
|
|
||||||
|
```python
|
||||||
|
from transformers import AutoTokenizer, AutoModelForCausalLM
|
||||||
|
|
||||||
|
model_id = "bsq1989/qwen_4b_sql"
|
||||||
|
|
||||||
|
tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)
|
||||||
|
model = AutoModelForCausalLM.from_pretrained(
|
||||||
|
model_id,
|
||||||
|
torch_dtype="auto",
|
||||||
|
device_map="auto",
|
||||||
|
trust_remote_code=True,
|
||||||
|
)
|
||||||
|
|
||||||
|
prompt = """Generate SQL from the given schema and question. Output SQL only.
|
||||||
|
|
||||||
|
Schema:
|
||||||
|
CREATE TABLE twitter (TweetID INTEGER, UserID INTEGER, LocationID INTEGER, Lang TEXT, ...);
|
||||||
|
CREATE TABLE location (LocationID INTEGER, Country TEXT, City TEXT, ...);
|
||||||
|
|
||||||
|
Question:
|
||||||
|
How many tweets are in English?
|
||||||
|
"""
|
||||||
|
|
||||||
|
messages = [{"role": "user", "content": prompt}]
|
||||||
|
text = tokenizer.apply_chat_template(
|
||||||
|
messages,
|
||||||
|
tokenize=False,
|
||||||
|
add_generation_prompt=True,
|
||||||
|
)
|
||||||
|
|
||||||
|
inputs = tokenizer(text, return_tensors="pt").to(model.device)
|
||||||
|
outputs = model.generate(**inputs, max_new_tokens=256)
|
||||||
|
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
|
||||||
|
```
|
||||||
|
|
||||||
|
## Limitations
|
||||||
|
|
||||||
|
- Performance drops on more open-ended and heterogeneous SQL benchmarks than Spider.
|
||||||
|
- The model can still produce invalid column references on out-of-distribution schemas.
|
||||||
|
- Benchmark numbers here reflect our current internal setup and should be reproduced with the same evaluation pipeline for strict comparison.
|
||||||
13
all_results.json
Normal file
13
all_results.json
Normal file
@@ -0,0 +1,13 @@
|
|||||||
|
{
|
||||||
|
"effective_tokens_per_sec": 1153.798380212981,
|
||||||
|
"epoch": 4.0,
|
||||||
|
"eval_loss": 0.24901165068149567,
|
||||||
|
"eval_runtime": 46.8427,
|
||||||
|
"eval_samples_per_second": 18.786,
|
||||||
|
"eval_steps_per_second": 18.786,
|
||||||
|
"total_flos": 3.545203061907456e+17,
|
||||||
|
"train_loss": 0.08566030774240586,
|
||||||
|
"train_runtime": 13933.4985,
|
||||||
|
"train_samples_per_second": 3.772,
|
||||||
|
"train_steps_per_second": 0.472
|
||||||
|
}
|
||||||
85
chat_template.jinja
Normal file
85
chat_template.jinja
Normal file
@@ -0,0 +1,85 @@
|
|||||||
|
{%- 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 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.role == "user") or (message.role == "system" and not loop.first) %}
|
||||||
|
{{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
|
||||||
|
{%- elif message.role == "assistant" %}
|
||||||
|
{%- set content = message.content %}
|
||||||
|
{%- set reasoning_content = '' %}
|
||||||
|
{%- if message.reasoning_content is defined and message.reasoning_content is not none %}
|
||||||
|
{%- set reasoning_content = message.reasoning_content %}
|
||||||
|
{%- else %}
|
||||||
|
{%- if '</think>' in message.content %}
|
||||||
|
{%- set content = message.content.split('</think>')[-1].lstrip('\n') %}
|
||||||
|
{%- set reasoning_content = message.content.split('</think>')[0].rstrip('\n').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' }}
|
||||||
|
{{- message.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 %}
|
||||||
71
config.json
Normal file
71
config.json
Normal file
@@ -0,0 +1,71 @@
|
|||||||
|
{
|
||||||
|
"architectures": [
|
||||||
|
"Qwen3ForCausalLM"
|
||||||
|
],
|
||||||
|
"attention_bias": false,
|
||||||
|
"attention_dropout": 0.0,
|
||||||
|
"bos_token_id": null,
|
||||||
|
"dtype": "float32",
|
||||||
|
"eos_token_id": 151645,
|
||||||
|
"head_dim": 128,
|
||||||
|
"hidden_act": "silu",
|
||||||
|
"hidden_size": 2560,
|
||||||
|
"initializer_range": 0.02,
|
||||||
|
"intermediate_size": 9728,
|
||||||
|
"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",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention"
|
||||||
|
],
|
||||||
|
"max_position_embeddings": 32768,
|
||||||
|
"max_window_layers": 36,
|
||||||
|
"model_type": "qwen3",
|
||||||
|
"num_attention_heads": 32,
|
||||||
|
"num_hidden_layers": 36,
|
||||||
|
"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": true,
|
||||||
|
"transformers_version": "5.2.0",
|
||||||
|
"use_cache": false,
|
||||||
|
"use_sliding_window": false,
|
||||||
|
"vocab_size": 151936
|
||||||
|
}
|
||||||
7
eval_results.json
Normal file
7
eval_results.json
Normal file
@@ -0,0 +1,7 @@
|
|||||||
|
{
|
||||||
|
"epoch": 4.0,
|
||||||
|
"eval_loss": 0.24901165068149567,
|
||||||
|
"eval_runtime": 46.8427,
|
||||||
|
"eval_samples_per_second": 18.786,
|
||||||
|
"eval_steps_per_second": 18.786
|
||||||
|
}
|
||||||
10
generation_config.json
Normal file
10
generation_config.json
Normal file
@@ -0,0 +1,10 @@
|
|||||||
|
{
|
||||||
|
"do_sample": false,
|
||||||
|
"eos_token_id": [
|
||||||
|
151645,
|
||||||
|
151643
|
||||||
|
],
|
||||||
|
"max_new_tokens": 2048,
|
||||||
|
"pad_token_id": 151643,
|
||||||
|
"transformers_version": "5.2.0"
|
||||||
|
}
|
||||||
3
model.safetensors
Normal file
3
model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:a04a88d8d7c026499bc570cdb42e1cbc0af368cf779b2f1060543a5d47dee1a5
|
||||||
|
size 16089918232
|
||||||
3
tokenizer.json
Normal file
3
tokenizer.json
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:be75606093db2094d7cd20f3c2f385c212750648bd6ea4fb2bf507a6a4c55506
|
||||||
|
size 11422650
|
||||||
30
tokenizer_config.json
Normal file
30
tokenizer_config.json
Normal file
@@ -0,0 +1,30 @@
|
|||||||
|
{
|
||||||
|
"add_prefix_space": false,
|
||||||
|
"backend": "tokenizers",
|
||||||
|
"bos_token": null,
|
||||||
|
"clean_up_tokenization_spaces": false,
|
||||||
|
"eos_token": "<|im_end|>",
|
||||||
|
"errors": "replace",
|
||||||
|
"extra_special_tokens": [
|
||||||
|
"<|im_start|>",
|
||||||
|
"<|im_end|>",
|
||||||
|
"<|object_ref_start|>",
|
||||||
|
"<|object_ref_end|>",
|
||||||
|
"<|box_start|>",
|
||||||
|
"<|box_end|>",
|
||||||
|
"<|quad_start|>",
|
||||||
|
"<|quad_end|>",
|
||||||
|
"<|vision_start|>",
|
||||||
|
"<|vision_end|>",
|
||||||
|
"<|vision_pad|>",
|
||||||
|
"<|image_pad|>",
|
||||||
|
"<|video_pad|>"
|
||||||
|
],
|
||||||
|
"is_local": true,
|
||||||
|
"model_max_length": 131072,
|
||||||
|
"pad_token": "<|endoftext|>",
|
||||||
|
"padding_side": "right",
|
||||||
|
"split_special_tokens": false,
|
||||||
|
"tokenizer_class": "Qwen2Tokenizer",
|
||||||
|
"unk_token": null
|
||||||
|
}
|
||||||
9
train_results.json
Normal file
9
train_results.json
Normal file
@@ -0,0 +1,9 @@
|
|||||||
|
{
|
||||||
|
"effective_tokens_per_sec": 1153.798380212981,
|
||||||
|
"epoch": 4.0,
|
||||||
|
"total_flos": 3.545203061907456e+17,
|
||||||
|
"train_loss": 0.08566030774240586,
|
||||||
|
"train_runtime": 13933.4985,
|
||||||
|
"train_samples_per_second": 3.772,
|
||||||
|
"train_steps_per_second": 0.472
|
||||||
|
}
|
||||||
342
trainer_log.jsonl
Normal file
342
trainer_log.jsonl
Normal file
@@ -0,0 +1,342 @@
|
|||||||
|
{"current_steps": 20, "total_steps": 6572, "loss": 1.119423007965088, "lr": 3.166666666666667e-07, "epoch": 0.0121765601217656, "percentage": 0.3, "elapsed_time": "0:00:54", "remaining_time": "4:54:53"}
|
||||||
|
{"current_steps": 40, "total_steps": 6572, "loss": 0.8098940849304199, "lr": 6.5e-07, "epoch": 0.0243531202435312, "percentage": 0.61, "elapsed_time": "0:01:37", "remaining_time": "4:25:19"}
|
||||||
|
{"current_steps": 60, "total_steps": 6572, "loss": 0.6310151576995849, "lr": 9.833333333333334e-07, "epoch": 0.0365296803652968, "percentage": 0.91, "elapsed_time": "0:02:14", "remaining_time": "4:03:37"}
|
||||||
|
{"current_steps": 80, "total_steps": 6572, "loss": 0.5526751518249512, "lr": 1.3166666666666666e-06, "epoch": 0.0487062404870624, "percentage": 1.22, "elapsed_time": "0:02:51", "remaining_time": "3:52:34"}
|
||||||
|
{"current_steps": 100, "total_steps": 6572, "loss": 0.4834024906158447, "lr": 1.6500000000000003e-06, "epoch": 0.060882800608828, "percentage": 1.52, "elapsed_time": "0:03:29", "remaining_time": "3:45:38"}
|
||||||
|
{"current_steps": 120, "total_steps": 6572, "loss": 0.44873433113098143, "lr": 1.9833333333333335e-06, "epoch": 0.0730593607305936, "percentage": 1.83, "elapsed_time": "0:04:06", "remaining_time": "3:40:39"}
|
||||||
|
{"current_steps": 140, "total_steps": 6572, "loss": 0.38286705017089845, "lr": 2.316666666666667e-06, "epoch": 0.0852359208523592, "percentage": 2.13, "elapsed_time": "0:04:44", "remaining_time": "3:37:42"}
|
||||||
|
{"current_steps": 160, "total_steps": 6572, "loss": 0.38465352058410646, "lr": 2.6500000000000005e-06, "epoch": 0.0974124809741248, "percentage": 2.43, "elapsed_time": "0:05:21", "remaining_time": "3:34:27"}
|
||||||
|
{"current_steps": 180, "total_steps": 6572, "loss": 0.3305965900421143, "lr": 2.9833333333333337e-06, "epoch": 0.1095890410958904, "percentage": 2.74, "elapsed_time": "0:05:56", "remaining_time": "3:31:11"}
|
||||||
|
{"current_steps": 200, "total_steps": 6572, "loss": 0.2875316619873047, "lr": 3.316666666666667e-06, "epoch": 0.121765601217656, "percentage": 3.04, "elapsed_time": "0:06:33", "remaining_time": "3:28:43"}
|
||||||
|
{"current_steps": 220, "total_steps": 6572, "loss": 0.3140716075897217, "lr": 3.65e-06, "epoch": 0.1339421613394216, "percentage": 3.35, "elapsed_time": "0:07:09", "remaining_time": "3:26:36"}
|
||||||
|
{"current_steps": 240, "total_steps": 6572, "loss": 0.2985520839691162, "lr": 3.983333333333334e-06, "epoch": 0.1461187214611872, "percentage": 3.65, "elapsed_time": "0:07:45", "remaining_time": "3:24:30"}
|
||||||
|
{"current_steps": 260, "total_steps": 6572, "loss": 0.2449601411819458, "lr": 4.316666666666667e-06, "epoch": 0.1582952815829528, "percentage": 3.96, "elapsed_time": "0:08:21", "remaining_time": "3:22:57"}
|
||||||
|
{"current_steps": 280, "total_steps": 6572, "loss": 0.24566495418548584, "lr": 4.65e-06, "epoch": 0.1704718417047184, "percentage": 4.26, "elapsed_time": "0:08:58", "remaining_time": "3:21:42"}
|
||||||
|
{"current_steps": 300, "total_steps": 6572, "loss": 0.20863604545593262, "lr": 4.983333333333334e-06, "epoch": 0.182648401826484, "percentage": 4.56, "elapsed_time": "0:09:34", "remaining_time": "3:20:20"}
|
||||||
|
{"current_steps": 320, "total_steps": 6572, "loss": 0.19693111181259154, "lr": 4.9998867856224845e-06, "epoch": 0.1948249619482496, "percentage": 4.87, "elapsed_time": "0:10:11", "remaining_time": "3:19:13"}
|
||||||
|
{"current_steps": 340, "total_steps": 6572, "loss": 0.21833207607269287, "lr": 4.999523005839606e-06, "epoch": 0.2070015220700152, "percentage": 5.17, "elapsed_time": "0:10:47", "remaining_time": "3:17:45"}
|
||||||
|
{"current_steps": 360, "total_steps": 6572, "loss": 0.2382877826690674, "lr": 4.998908383543311e-06, "epoch": 0.2191780821917808, "percentage": 5.48, "elapsed_time": "0:11:21", "remaining_time": "3:16:06"}
|
||||||
|
{"current_steps": 380, "total_steps": 6572, "loss": 0.21118538379669188, "lr": 4.9980429804147276e-06, "epoch": 0.2313546423135464, "percentage": 5.78, "elapsed_time": "0:11:58", "remaining_time": "3:15:01"}
|
||||||
|
{"current_steps": 400, "total_steps": 6572, "loss": 0.18367968797683715, "lr": 4.996926883302385e-06, "epoch": 0.243531202435312, "percentage": 6.09, "elapsed_time": "0:12:34", "remaining_time": "3:13:55"}
|
||||||
|
{"current_steps": 420, "total_steps": 6572, "loss": 0.22483460903167723, "lr": 4.995560204213496e-06, "epoch": 0.2557077625570776, "percentage": 6.39, "elapsed_time": "0:13:12", "remaining_time": "3:13:22"}
|
||||||
|
{"current_steps": 440, "total_steps": 6572, "loss": 0.22673561573028564, "lr": 4.993943080302715e-06, "epoch": 0.2678843226788432, "percentage": 6.7, "elapsed_time": "0:13:50", "remaining_time": "3:12:57"}
|
||||||
|
{"current_steps": 460, "total_steps": 6572, "loss": 0.185296630859375, "lr": 4.992075673858379e-06, "epoch": 0.2800608828006088, "percentage": 7.0, "elapsed_time": "0:14:26", "remaining_time": "3:11:55"}
|
||||||
|
{"current_steps": 480, "total_steps": 6572, "loss": 0.18437937498092652, "lr": 4.989958172286214e-06, "epoch": 0.2922374429223744, "percentage": 7.3, "elapsed_time": "0:15:04", "remaining_time": "3:11:23"}
|
||||||
|
{"current_steps": 500, "total_steps": 6572, "loss": 0.1850834846496582, "lr": 4.987590788090533e-06, "epoch": 0.30441400304414, "percentage": 7.61, "elapsed_time": "0:15:42", "remaining_time": "3:10:48"}
|
||||||
|
{"current_steps": 500, "total_steps": 6572, "eval_loss": 0.2562323212623596, "epoch": 0.30441400304414, "percentage": 7.61, "elapsed_time": "0:16:30", "remaining_time": "3:20:23"}
|
||||||
|
{"current_steps": 520, "total_steps": 6572, "loss": 0.16346561908721924, "lr": 4.984973758852904e-06, "epoch": 0.3165905631659056, "percentage": 7.91, "elapsed_time": "0:18:27", "remaining_time": "3:34:45"}
|
||||||
|
{"current_steps": 540, "total_steps": 6572, "loss": 0.18838067054748536, "lr": 4.982107347208317e-06, "epoch": 0.3287671232876712, "percentage": 8.22, "elapsed_time": "0:19:03", "remaining_time": "3:32:49"}
|
||||||
|
{"current_steps": 560, "total_steps": 6572, "loss": 0.177593994140625, "lr": 4.978991840818816e-06, "epoch": 0.3409436834094368, "percentage": 8.52, "elapsed_time": "0:19:40", "remaining_time": "3:31:13"}
|
||||||
|
{"current_steps": 580, "total_steps": 6572, "loss": 0.20775914192199707, "lr": 4.975627552344638e-06, "epoch": 0.3531202435312024, "percentage": 8.83, "elapsed_time": "0:20:18", "remaining_time": "3:29:49"}
|
||||||
|
{"current_steps": 600, "total_steps": 6572, "loss": 0.16498700380325318, "lr": 4.97201481941283e-06, "epoch": 0.365296803652968, "percentage": 9.13, "elapsed_time": "0:20:55", "remaining_time": "3:28:12"}
|
||||||
|
{"current_steps": 620, "total_steps": 6572, "loss": 0.17565951347351075, "lr": 4.968154004583374e-06, "epoch": 0.3774733637747336, "percentage": 9.43, "elapsed_time": "0:21:31", "remaining_time": "3:26:35"}
|
||||||
|
{"current_steps": 640, "total_steps": 6572, "loss": 0.16204673051834106, "lr": 4.964045495312794e-06, "epoch": 0.3896499238964992, "percentage": 9.74, "elapsed_time": "0:22:07", "remaining_time": "3:24:59"}
|
||||||
|
{"current_steps": 660, "total_steps": 6572, "loss": 0.17068564891815186, "lr": 4.959689703915272e-06, "epoch": 0.4018264840182648, "percentage": 10.04, "elapsed_time": "0:22:42", "remaining_time": "3:23:27"}
|
||||||
|
{"current_steps": 680, "total_steps": 6572, "loss": 0.1589680790901184, "lr": 4.95508706752128e-06, "epoch": 0.4140030441400304, "percentage": 10.35, "elapsed_time": "0:23:19", "remaining_time": "3:22:07"}
|
||||||
|
{"current_steps": 700, "total_steps": 6572, "loss": 0.17568455934524535, "lr": 4.9502380480337e-06, "epoch": 0.426179604261796, "percentage": 10.65, "elapsed_time": "0:23:56", "remaining_time": "3:20:51"}
|
||||||
|
{"current_steps": 720, "total_steps": 6572, "loss": 0.16204804182052612, "lr": 4.9451431320814715e-06, "epoch": 0.4383561643835616, "percentage": 10.96, "elapsed_time": "0:24:33", "remaining_time": "3:19:40"}
|
||||||
|
{"current_steps": 740, "total_steps": 6572, "loss": 0.16562143564224244, "lr": 4.939802830970762e-06, "epoch": 0.4505327245053272, "percentage": 11.26, "elapsed_time": "0:25:10", "remaining_time": "3:18:26"}
|
||||||
|
{"current_steps": 760, "total_steps": 6572, "loss": 0.17697544097900392, "lr": 4.934217680633646e-06, "epoch": 0.4627092846270928, "percentage": 11.56, "elapsed_time": "0:25:46", "remaining_time": "3:17:03"}
|
||||||
|
{"current_steps": 780, "total_steps": 6572, "loss": 0.1649466037750244, "lr": 4.928388241574327e-06, "epoch": 0.4748858447488584, "percentage": 11.87, "elapsed_time": "0:26:23", "remaining_time": "3:15:55"}
|
||||||
|
{"current_steps": 800, "total_steps": 6572, "loss": 0.1602837324142456, "lr": 4.922315098812883e-06, "epoch": 0.487062404870624, "percentage": 12.17, "elapsed_time": "0:26:59", "remaining_time": "3:14:43"}
|
||||||
|
{"current_steps": 820, "total_steps": 6572, "loss": 0.142719042301178, "lr": 4.9159988618265585e-06, "epoch": 0.4992389649923896, "percentage": 12.48, "elapsed_time": "0:27:36", "remaining_time": "3:13:37"}
|
||||||
|
{"current_steps": 840, "total_steps": 6572, "loss": 0.14508233070373536, "lr": 4.9094401644886e-06, "epoch": 0.5114155251141552, "percentage": 12.78, "elapsed_time": "0:28:12", "remaining_time": "3:12:31"}
|
||||||
|
{"current_steps": 860, "total_steps": 6572, "loss": 0.1821539044380188, "lr": 4.902639665004641e-06, "epoch": 0.5235920852359208, "percentage": 13.09, "elapsed_time": "0:28:49", "remaining_time": "3:11:27"}
|
||||||
|
{"current_steps": 880, "total_steps": 6572, "loss": 0.16131887435913086, "lr": 4.89559804584665e-06, "epoch": 0.5357686453576864, "percentage": 13.39, "elapsed_time": "0:29:24", "remaining_time": "3:10:16"}
|
||||||
|
{"current_steps": 900, "total_steps": 6572, "loss": 0.17404688596725465, "lr": 4.888316013684435e-06, "epoch": 0.547945205479452, "percentage": 13.69, "elapsed_time": "0:30:01", "remaining_time": "3:09:11"}
|
||||||
|
{"current_steps": 920, "total_steps": 6572, "loss": 0.14134640693664552, "lr": 4.880794299314732e-06, "epoch": 0.5601217656012176, "percentage": 14.0, "elapsed_time": "0:30:38", "remaining_time": "3:08:12"}
|
||||||
|
{"current_steps": 940, "total_steps": 6572, "loss": 0.14891813993453978, "lr": 4.87303365758786e-06, "epoch": 0.5722983257229832, "percentage": 14.3, "elapsed_time": "0:31:15", "remaining_time": "3:07:19"}
|
||||||
|
{"current_steps": 960, "total_steps": 6572, "loss": 0.1696299910545349, "lr": 4.865034867331967e-06, "epoch": 0.5844748858447488, "percentage": 14.61, "elapsed_time": "0:31:52", "remaining_time": "3:06:21"}
|
||||||
|
{"current_steps": 980, "total_steps": 6572, "loss": 0.14085158109664916, "lr": 4.856798731274874e-06, "epoch": 0.5966514459665144, "percentage": 14.91, "elapsed_time": "0:32:29", "remaining_time": "3:05:22"}
|
||||||
|
{"current_steps": 1000, "total_steps": 6572, "loss": 0.133053982257843, "lr": 4.84832607596351e-06, "epoch": 0.60882800608828, "percentage": 15.22, "elapsed_time": "0:33:04", "remaining_time": "3:04:16"}
|
||||||
|
{"current_steps": 1000, "total_steps": 6572, "eval_loss": 0.24901165068149567, "epoch": 0.60882800608828, "percentage": 15.22, "elapsed_time": "0:33:51", "remaining_time": "3:08:37"}
|
||||||
|
{"current_steps": 1020, "total_steps": 6572, "loss": 0.12680984735488893, "lr": 4.8396177516809695e-06, "epoch": 0.6210045662100456, "percentage": 15.52, "elapsed_time": "0:36:06", "remaining_time": "3:16:32"}
|
||||||
|
{"current_steps": 1040, "total_steps": 6572, "loss": 0.14880582094192504, "lr": 4.830674632361178e-06, "epoch": 0.6331811263318112, "percentage": 15.82, "elapsed_time": "0:36:43", "remaining_time": "3:15:23"}
|
||||||
|
{"current_steps": 1060, "total_steps": 6572, "loss": 0.1447562575340271, "lr": 4.821497615501186e-06, "epoch": 0.6453576864535768, "percentage": 16.13, "elapsed_time": "0:37:21", "remaining_time": "3:14:16"}
|
||||||
|
{"current_steps": 1080, "total_steps": 6572, "loss": 0.15530819892883302, "lr": 4.812087622071104e-06, "epoch": 0.6575342465753424, "percentage": 16.43, "elapsed_time": "0:37:59", "remaining_time": "3:13:10"}
|
||||||
|
{"current_steps": 1100, "total_steps": 6572, "loss": 0.14426586627960206, "lr": 4.80244559642167e-06, "epoch": 0.669710806697108, "percentage": 16.74, "elapsed_time": "0:38:36", "remaining_time": "3:12:03"}
|
||||||
|
{"current_steps": 1120, "total_steps": 6572, "loss": 0.15436025857925414, "lr": 4.792572506189489e-06, "epoch": 0.6818873668188736, "percentage": 17.04, "elapsed_time": "0:39:13", "remaining_time": "3:10:54"}
|
||||||
|
{"current_steps": 1140, "total_steps": 6572, "loss": 0.14860854148864747, "lr": 4.782469342199915e-06, "epoch": 0.6940639269406392, "percentage": 17.35, "elapsed_time": "0:39:50", "remaining_time": "3:09:48"}
|
||||||
|
{"current_steps": 1160, "total_steps": 6572, "loss": 0.1313084125518799, "lr": 4.7721371183676205e-06, "epoch": 0.7062404870624048, "percentage": 17.65, "elapsed_time": "0:40:26", "remaining_time": "3:08:40"}
|
||||||
|
{"current_steps": 1180, "total_steps": 6572, "loss": 0.150812029838562, "lr": 4.761576871594841e-06, "epoch": 0.7184170471841704, "percentage": 17.95, "elapsed_time": "0:41:02", "remaining_time": "3:07:33"}
|
||||||
|
{"current_steps": 1200, "total_steps": 6572, "loss": 0.13278884887695314, "lr": 4.750789661667318e-06, "epoch": 0.730593607305936, "percentage": 18.26, "elapsed_time": "0:41:38", "remaining_time": "3:06:24"}
|
||||||
|
{"current_steps": 1220, "total_steps": 6572, "loss": 0.1612934350967407, "lr": 4.739776571147943e-06, "epoch": 0.7427701674277016, "percentage": 18.56, "elapsed_time": "0:42:14", "remaining_time": "3:05:16"}
|
||||||
|
{"current_steps": 1240, "total_steps": 6572, "loss": 0.16211290359497071, "lr": 4.728538705268116e-06, "epoch": 0.7549467275494672, "percentage": 18.87, "elapsed_time": "0:42:49", "remaining_time": "3:04:10"}
|
||||||
|
{"current_steps": 1260, "total_steps": 6572, "loss": 0.14386119842529296, "lr": 4.717077191816824e-06, "epoch": 0.7671232876712328, "percentage": 19.17, "elapsed_time": "0:43:26", "remaining_time": "3:03:09"}
|
||||||
|
{"current_steps": 1280, "total_steps": 6572, "loss": 0.12942540645599365, "lr": 4.705393181027463e-06, "epoch": 0.7792998477929984, "percentage": 19.48, "elapsed_time": "0:44:01", "remaining_time": "3:02:02"}
|
||||||
|
{"current_steps": 1300, "total_steps": 6572, "loss": 0.14771063327789308, "lr": 4.693487845462413e-06, "epoch": 0.791476407914764, "percentage": 19.78, "elapsed_time": "0:44:38", "remaining_time": "3:01:02"}
|
||||||
|
{"current_steps": 1320, "total_steps": 6572, "loss": 0.1276724100112915, "lr": 4.681362379895349e-06, "epoch": 0.8036529680365296, "percentage": 20.09, "elapsed_time": "0:45:14", "remaining_time": "3:00:00"}
|
||||||
|
{"current_steps": 1340, "total_steps": 6572, "loss": 0.1319241166114807, "lr": 4.6690180011913524e-06, "epoch": 0.8158295281582952, "percentage": 20.39, "elapsed_time": "0:45:50", "remaining_time": "2:58:59"}
|
||||||
|
{"current_steps": 1360, "total_steps": 6572, "loss": 0.1557891011238098, "lr": 4.6564559481847795e-06, "epoch": 0.8280060882800608, "percentage": 20.69, "elapsed_time": "0:46:27", "remaining_time": "2:58:01"}
|
||||||
|
{"current_steps": 1380, "total_steps": 6572, "loss": 0.11075855493545532, "lr": 4.643677481554947e-06, "epoch": 0.8401826484018264, "percentage": 21.0, "elapsed_time": "0:47:04", "remaining_time": "2:57:07"}
|
||||||
|
{"current_steps": 1400, "total_steps": 6572, "loss": 0.1580789566040039, "lr": 4.630683883699607e-06, "epoch": 0.852359208523592, "percentage": 21.3, "elapsed_time": "0:47:40", "remaining_time": "2:56:08"}
|
||||||
|
{"current_steps": 1420, "total_steps": 6572, "loss": 0.16006500720977784, "lr": 4.6174764586062556e-06, "epoch": 0.8645357686453576, "percentage": 21.61, "elapsed_time": "0:48:18", "remaining_time": "2:55:14"}
|
||||||
|
{"current_steps": 1440, "total_steps": 6572, "loss": 0.1462727189064026, "lr": 4.6040565317212685e-06, "epoch": 0.8767123287671232, "percentage": 21.91, "elapsed_time": "0:48:54", "remaining_time": "2:54:20"}
|
||||||
|
{"current_steps": 1460, "total_steps": 6572, "loss": 0.14725338220596312, "lr": 4.59042544981688e-06, "epoch": 0.8888888888888888, "percentage": 22.22, "elapsed_time": "0:49:30", "remaining_time": "2:53:22"}
|
||||||
|
{"current_steps": 1480, "total_steps": 6572, "loss": 0.1304166793823242, "lr": 4.5765845808560334e-06, "epoch": 0.9010654490106544, "percentage": 22.52, "elapsed_time": "0:50:07", "remaining_time": "2:52:27"}
|
||||||
|
{"current_steps": 1500, "total_steps": 6572, "loss": 0.1293134570121765, "lr": 4.562535313855094e-06, "epoch": 0.91324200913242, "percentage": 22.82, "elapsed_time": "0:50:45", "remaining_time": "2:51:38"}
|
||||||
|
{"current_steps": 1500, "total_steps": 6572, "eval_loss": 0.25538697838783264, "epoch": 0.91324200913242, "percentage": 22.82, "elapsed_time": "0:51:32", "remaining_time": "2:54:17"}
|
||||||
|
{"current_steps": 1520, "total_steps": 6572, "loss": 0.11359381675720215, "lr": 4.548279058744451e-06, "epoch": 0.9254185692541856, "percentage": 23.13, "elapsed_time": "0:53:39", "remaining_time": "2:58:20"}
|
||||||
|
{"current_steps": 1540, "total_steps": 6572, "loss": 0.15145074129104613, "lr": 4.533817246227024e-06, "epoch": 0.9375951293759512, "percentage": 23.43, "elapsed_time": "0:54:15", "remaining_time": "2:57:18"}
|
||||||
|
{"current_steps": 1560, "total_steps": 6572, "loss": 0.11953675746917725, "lr": 4.519151327634685e-06, "epoch": 0.9497716894977168, "percentage": 23.74, "elapsed_time": "0:54:52", "remaining_time": "2:56:18"}
|
||||||
|
{"current_steps": 1580, "total_steps": 6572, "loss": 0.13977375030517578, "lr": 4.504282774782605e-06, "epoch": 0.9619482496194824, "percentage": 24.04, "elapsed_time": "0:55:30", "remaining_time": "2:55:21"}
|
||||||
|
{"current_steps": 1600, "total_steps": 6572, "loss": 0.1338045358657837, "lr": 4.489213079821551e-06, "epoch": 0.974124809741248, "percentage": 24.35, "elapsed_time": "0:56:07", "remaining_time": "2:54:25"}
|
||||||
|
{"current_steps": 1620, "total_steps": 6572, "loss": 0.11776142120361328, "lr": 4.4739437550881355e-06, "epoch": 0.9863013698630136, "percentage": 24.65, "elapsed_time": "0:56:43", "remaining_time": "2:53:24"}
|
||||||
|
{"current_steps": 1640, "total_steps": 6572, "loss": 0.12504475116729735, "lr": 4.458476332953051e-06, "epoch": 0.9984779299847792, "percentage": 24.95, "elapsed_time": "0:57:19", "remaining_time": "2:52:23"}
|
||||||
|
{"current_steps": 1660, "total_steps": 6572, "loss": 0.08379222154617309, "lr": 4.442812365667281e-06, "epoch": 1.0103500761035007, "percentage": 25.26, "elapsed_time": "0:57:55", "remaining_time": "2:51:23"}
|
||||||
|
{"current_steps": 1680, "total_steps": 6572, "loss": 0.08407147526741028, "lr": 4.426953425206322e-06, "epoch": 1.0225266362252663, "percentage": 25.56, "elapsed_time": "0:58:32", "remaining_time": "2:50:27"}
|
||||||
|
{"current_steps": 1700, "total_steps": 6572, "loss": 0.08041079640388489, "lr": 4.410901103112434e-06, "epoch": 1.034703196347032, "percentage": 25.87, "elapsed_time": "0:59:08", "remaining_time": "2:49:28"}
|
||||||
|
{"current_steps": 1720, "total_steps": 6572, "loss": 0.07876392006874085, "lr": 4.394657010334908e-06, "epoch": 1.0468797564687975, "percentage": 26.17, "elapsed_time": "0:59:43", "remaining_time": "2:48:29"}
|
||||||
|
{"current_steps": 1740, "total_steps": 6572, "loss": 0.10302903652191162, "lr": 4.378222777068406e-06, "epoch": 1.059056316590563, "percentage": 26.48, "elapsed_time": "1:00:19", "remaining_time": "2:47:32"}
|
||||||
|
{"current_steps": 1760, "total_steps": 6572, "loss": 0.08733606934547425, "lr": 4.361600052589358e-06, "epoch": 1.0712328767123287, "percentage": 26.78, "elapsed_time": "1:00:55", "remaining_time": "2:46:34"}
|
||||||
|
{"current_steps": 1780, "total_steps": 6572, "loss": 0.08532609939575195, "lr": 4.344790505090447e-06, "epoch": 1.0834094368340943, "percentage": 27.08, "elapsed_time": "1:01:31", "remaining_time": "2:45:38"}
|
||||||
|
{"current_steps": 1800, "total_steps": 6572, "loss": 0.08734336495399475, "lr": 4.327795821513195e-06, "epoch": 1.09558599695586, "percentage": 27.39, "elapsed_time": "1:02:09", "remaining_time": "2:44:46"}
|
||||||
|
{"current_steps": 1820, "total_steps": 6572, "loss": 0.0913870632648468, "lr": 4.3106177073786684e-06, "epoch": 1.1077625570776255, "percentage": 27.69, "elapsed_time": "1:02:46", "remaining_time": "2:43:53"}
|
||||||
|
{"current_steps": 1840, "total_steps": 6572, "loss": 0.08115516304969787, "lr": 4.293257886616318e-06, "epoch": 1.119939117199391, "percentage": 28.0, "elapsed_time": "1:03:22", "remaining_time": "2:42:59"}
|
||||||
|
{"current_steps": 1860, "total_steps": 6572, "loss": 0.08891176581382751, "lr": 4.275718101390975e-06, "epoch": 1.1321156773211567, "percentage": 28.3, "elapsed_time": "1:03:59", "remaining_time": "2:42:07"}
|
||||||
|
{"current_steps": 1880, "total_steps": 6572, "loss": 0.07950961589813232, "lr": 4.25800011192801e-06, "epoch": 1.1442922374429223, "percentage": 28.61, "elapsed_time": "1:04:37", "remaining_time": "2:41:16"}
|
||||||
|
{"current_steps": 1900, "total_steps": 6572, "loss": 0.08310645222663879, "lr": 4.240105696336687e-06, "epoch": 1.156468797564688, "percentage": 28.91, "elapsed_time": "1:05:13", "remaining_time": "2:40:22"}
|
||||||
|
{"current_steps": 1920, "total_steps": 6572, "loss": 0.07682961225509644, "lr": 4.222036650431715e-06, "epoch": 1.1686453576864535, "percentage": 29.21, "elapsed_time": "1:05:49", "remaining_time": "2:39:29"}
|
||||||
|
{"current_steps": 1940, "total_steps": 6572, "loss": 0.07520227432250977, "lr": 4.203794787553032e-06, "epoch": 1.180821917808219, "percentage": 29.52, "elapsed_time": "1:06:26", "remaining_time": "2:38:37"}
|
||||||
|
{"current_steps": 1960, "total_steps": 6572, "loss": 0.0754019558429718, "lr": 4.185381938383821e-06, "epoch": 1.1929984779299847, "percentage": 29.82, "elapsed_time": "1:07:02", "remaining_time": "2:37:44"}
|
||||||
|
{"current_steps": 1980, "total_steps": 6572, "loss": 0.08085885643959045, "lr": 4.166799950766793e-06, "epoch": 1.2051750380517503, "percentage": 30.13, "elapsed_time": "1:07:38", "remaining_time": "2:36:51"}
|
||||||
|
{"current_steps": 2000, "total_steps": 6572, "loss": 0.0884653627872467, "lr": 4.14805068951874e-06, "epoch": 1.217351598173516, "percentage": 30.43, "elapsed_time": "1:08:14", "remaining_time": "2:36:00"}
|
||||||
|
{"current_steps": 2000, "total_steps": 6572, "eval_loss": 0.2661186456680298, "epoch": 1.217351598173516, "percentage": 30.43, "elapsed_time": "1:09:01", "remaining_time": "2:37:47"}
|
||||||
|
{"current_steps": 2020, "total_steps": 6572, "loss": 0.06684748530387878, "lr": 4.1291360362433965e-06, "epoch": 1.2295281582952815, "percentage": 30.74, "elapsed_time": "1:11:15", "remaining_time": "2:40:34"}
|
||||||
|
{"current_steps": 2040, "total_steps": 6572, "loss": 0.0720324158668518, "lr": 4.110057889142601e-06, "epoch": 1.241704718417047, "percentage": 31.04, "elapsed_time": "1:11:52", "remaining_time": "2:39:40"}
|
||||||
|
{"current_steps": 2060, "total_steps": 6572, "loss": 0.08799988031387329, "lr": 4.090818162825804e-06, "epoch": 1.2538812785388127, "percentage": 31.35, "elapsed_time": "1:12:29", "remaining_time": "2:38:47"}
|
||||||
|
{"current_steps": 2080, "total_steps": 6572, "loss": 0.09275985956192016, "lr": 4.071418788117926e-06, "epoch": 1.2660578386605783, "percentage": 31.65, "elapsed_time": "1:13:07", "remaining_time": "2:37:55"}
|
||||||
|
{"current_steps": 2100, "total_steps": 6572, "loss": 0.08431113958358764, "lr": 4.0518617118655845e-06, "epoch": 1.278234398782344, "percentage": 31.95, "elapsed_time": "1:13:43", "remaining_time": "2:37:00"}
|
||||||
|
{"current_steps": 2120, "total_steps": 6572, "loss": 0.09995608925819396, "lr": 4.032148896741717e-06, "epoch": 1.2904109589041095, "percentage": 32.26, "elapsed_time": "1:14:20", "remaining_time": "2:36:07"}
|
||||||
|
{"current_steps": 2140, "total_steps": 6572, "loss": 0.07387629747390748, "lr": 4.012282321048618e-06, "epoch": 1.302587519025875, "percentage": 32.56, "elapsed_time": "1:14:57", "remaining_time": "2:35:14"}
|
||||||
|
{"current_steps": 2160, "total_steps": 6572, "loss": 0.07667248249053955, "lr": 3.992263978519398e-06, "epoch": 1.3147640791476407, "percentage": 32.87, "elapsed_time": "1:15:34", "remaining_time": "2:34:22"}
|
||||||
|
{"current_steps": 2180, "total_steps": 6572, "loss": 0.09203824400901794, "lr": 3.972095878117904e-06, "epoch": 1.3269406392694063, "percentage": 33.17, "elapsed_time": "1:16:11", "remaining_time": "2:33:30"}
|
||||||
|
{"current_steps": 2200, "total_steps": 6572, "loss": 0.07835246920585633, "lr": 3.951780043837107e-06, "epoch": 1.339117199391172, "percentage": 33.48, "elapsed_time": "1:16:48", "remaining_time": "2:32:37"}
|
||||||
|
{"current_steps": 2220, "total_steps": 6572, "loss": 0.08577624559402466, "lr": 3.9313185144959835e-06, "epoch": 1.3512937595129375, "percentage": 33.78, "elapsed_time": "1:17:25", "remaining_time": "2:31:46"}
|
||||||
|
{"current_steps": 2240, "total_steps": 6572, "loss": 0.0789969801902771, "lr": 3.9107133435349025e-06, "epoch": 1.363470319634703, "percentage": 34.08, "elapsed_time": "1:18:01", "remaining_time": "2:30:53"}
|
||||||
|
{"current_steps": 2260, "total_steps": 6572, "loss": 0.07151145935058593, "lr": 3.889966598809557e-06, "epoch": 1.3756468797564687, "percentage": 34.39, "elapsed_time": "1:18:38", "remaining_time": "2:30:02"}
|
||||||
|
{"current_steps": 2280, "total_steps": 6572, "loss": 0.09204544425010681, "lr": 3.869080362383437e-06, "epoch": 1.3878234398782343, "percentage": 34.69, "elapsed_time": "1:19:14", "remaining_time": "2:29:10"}
|
||||||
|
{"current_steps": 2300, "total_steps": 6572, "loss": 0.11079612970352173, "lr": 3.848056730318881e-06, "epoch": 1.4, "percentage": 35.0, "elapsed_time": "1:19:54", "remaining_time": "2:28:25"}
|
||||||
|
{"current_steps": 2320, "total_steps": 6572, "loss": 0.06770140528678895, "lr": 3.826897812466728e-06, "epoch": 1.4121765601217655, "percentage": 35.3, "elapsed_time": "1:20:30", "remaining_time": "2:27:32"}
|
||||||
|
{"current_steps": 2340, "total_steps": 6572, "loss": 0.08210510611534119, "lr": 3.8056057322545763e-06, "epoch": 1.4243531202435311, "percentage": 35.61, "elapsed_time": "1:21:07", "remaining_time": "2:26:42"}
|
||||||
|
{"current_steps": 2360, "total_steps": 6572, "loss": 0.09583572745323181, "lr": 3.7841826264736888e-06, "epoch": 1.4365296803652967, "percentage": 35.91, "elapsed_time": "1:21:43", "remaining_time": "2:25:51"}
|
||||||
|
{"current_steps": 2380, "total_steps": 6572, "loss": 0.09235450625419617, "lr": 3.762630645064547e-06, "epoch": 1.4487062404870623, "percentage": 36.21, "elapsed_time": "1:22:20", "remaining_time": "2:25:01"}
|
||||||
|
{"current_steps": 2400, "total_steps": 6572, "loss": 0.08658097982406616, "lr": 3.7409519509010985e-06, "epoch": 1.460882800608828, "percentage": 36.52, "elapsed_time": "1:22:56", "remaining_time": "2:24:11"}
|
||||||
|
{"current_steps": 2420, "total_steps": 6572, "loss": 0.08892765045166015, "lr": 3.7191487195736915e-06, "epoch": 1.4730593607305935, "percentage": 36.82, "elapsed_time": "1:23:32", "remaining_time": "2:23:20"}
|
||||||
|
{"current_steps": 2440, "total_steps": 6572, "loss": 0.07849371433258057, "lr": 3.697223139170748e-06, "epoch": 1.4852359208523591, "percentage": 37.13, "elapsed_time": "1:24:09", "remaining_time": "2:22:30"}
|
||||||
|
{"current_steps": 2460, "total_steps": 6572, "loss": 0.07469035387039184, "lr": 3.6751774100591716e-06, "epoch": 1.4974124809741247, "percentage": 37.43, "elapsed_time": "1:24:45", "remaining_time": "2:21:40"}
|
||||||
|
{"current_steps": 2480, "total_steps": 6572, "loss": 0.0782626211643219, "lr": 3.6530137446635265e-06, "epoch": 1.5095890410958903, "percentage": 37.74, "elapsed_time": "1:25:20", "remaining_time": "2:20:49"}
|
||||||
|
{"current_steps": 2500, "total_steps": 6572, "loss": 0.08304058909416198, "lr": 3.630734367244012e-06, "epoch": 1.521765601217656, "percentage": 38.04, "elapsed_time": "1:25:57", "remaining_time": "2:20:00"}
|
||||||
|
{"current_steps": 2500, "total_steps": 6572, "eval_loss": 0.2771773338317871, "epoch": 1.521765601217656, "percentage": 38.04, "elapsed_time": "1:26:44", "remaining_time": "2:21:17"}
|
||||||
|
{"current_steps": 2520, "total_steps": 6572, "loss": 0.08037537932395936, "lr": 3.6083415136732374e-06, "epoch": 1.5339421613394215, "percentage": 38.34, "elapsed_time": "1:28:46", "remaining_time": "2:22:44"}
|
||||||
|
{"current_steps": 2540, "total_steps": 6572, "loss": 0.08990358114242554, "lr": 3.585837431211845e-06, "epoch": 1.5461187214611871, "percentage": 38.65, "elapsed_time": "1:29:23", "remaining_time": "2:21:53"}
|
||||||
|
{"current_steps": 2560, "total_steps": 6572, "loss": 0.0773526132106781, "lr": 3.563224378282978e-06, "epoch": 1.5582952815829527, "percentage": 38.95, "elapsed_time": "1:29:59", "remaining_time": "2:21:02"}
|
||||||
|
{"current_steps": 2580, "total_steps": 6572, "loss": 0.0777865469455719, "lr": 3.5405046242456396e-06, "epoch": 1.5704718417047183, "percentage": 39.26, "elapsed_time": "1:30:36", "remaining_time": "2:20:11"}
|
||||||
|
{"current_steps": 2600, "total_steps": 6572, "loss": 0.08037815093994141, "lr": 3.517680449166943e-06, "epoch": 1.582648401826484, "percentage": 39.56, "elapsed_time": "1:31:11", "remaining_time": "2:19:18"}
|
||||||
|
{"current_steps": 2620, "total_steps": 6572, "loss": 0.08837634325027466, "lr": 3.4947541435932976e-06, "epoch": 1.5948249619482495, "percentage": 39.87, "elapsed_time": "1:31:49", "remaining_time": "2:18:30"}
|
||||||
|
{"current_steps": 2640, "total_steps": 6572, "loss": 0.08201563358306885, "lr": 3.471728008320532e-06, "epoch": 1.6070015220700151, "percentage": 40.17, "elapsed_time": "1:32:26", "remaining_time": "2:17:41"}
|
||||||
|
{"current_steps": 2660, "total_steps": 6572, "loss": 0.07379403114318847, "lr": 3.4486043541630066e-06, "epoch": 1.6191780821917807, "percentage": 40.47, "elapsed_time": "1:33:03", "remaining_time": "2:16:51"}
|
||||||
|
{"current_steps": 2680, "total_steps": 6572, "loss": 0.08871785402297974, "lr": 3.425385501721696e-06, "epoch": 1.6313546423135463, "percentage": 40.78, "elapsed_time": "1:33:39", "remaining_time": "2:16:00"}
|
||||||
|
{"current_steps": 2700, "total_steps": 6572, "loss": 0.07757498621940613, "lr": 3.4020737811513107e-06, "epoch": 1.643531202435312, "percentage": 41.08, "elapsed_time": "1:34:16", "remaining_time": "2:15:11"}
|
||||||
|
{"current_steps": 2720, "total_steps": 6572, "loss": 0.08565697669982911, "lr": 3.3786715319264483e-06, "epoch": 1.6557077625570775, "percentage": 41.39, "elapsed_time": "1:34:52", "remaining_time": "2:14:21"}
|
||||||
|
{"current_steps": 2740, "total_steps": 6572, "loss": 0.08129348754882812, "lr": 3.355181102606816e-06, "epoch": 1.6678843226788431, "percentage": 41.69, "elapsed_time": "1:35:28", "remaining_time": "2:13:31"}
|
||||||
|
{"current_steps": 2760, "total_steps": 6572, "loss": 0.07875375747680664, "lr": 3.331604850601533e-06, "epoch": 1.6800608828006087, "percentage": 42.0, "elapsed_time": "1:36:06", "remaining_time": "2:12:43"}
|
||||||
|
{"current_steps": 2780, "total_steps": 6572, "loss": 0.08989614248275757, "lr": 3.307945141932556e-06, "epoch": 1.6922374429223743, "percentage": 42.3, "elapsed_time": "1:36:41", "remaining_time": "2:11:53"}
|
||||||
|
{"current_steps": 2800, "total_steps": 6572, "loss": 0.08251298069953919, "lr": 3.2842043509972294e-06, "epoch": 1.70441400304414, "percentage": 42.6, "elapsed_time": "1:37:18", "remaining_time": "2:11:05"}
|
||||||
|
{"current_steps": 2820, "total_steps": 6572, "loss": 0.07760271430015564, "lr": 3.2603848603300026e-06, "epoch": 1.7165905631659055, "percentage": 42.91, "elapsed_time": "1:37:56", "remaining_time": "2:10:18"}
|
||||||
|
{"current_steps": 2840, "total_steps": 6572, "loss": 0.07395396232604981, "lr": 3.236489060363329e-06, "epoch": 1.7287671232876711, "percentage": 43.21, "elapsed_time": "1:38:33", "remaining_time": "2:09:31"}
|
||||||
|
{"current_steps": 2860, "total_steps": 6572, "loss": 0.07028600573539734, "lr": 3.212519349187766e-06, "epoch": 1.7409436834094367, "percentage": 43.52, "elapsed_time": "1:39:10", "remaining_time": "2:08:42"}
|
||||||
|
{"current_steps": 2880, "total_steps": 6572, "loss": 0.08469281196594239, "lr": 3.188478132311319e-06, "epoch": 1.7531202435312023, "percentage": 43.82, "elapsed_time": "1:39:46", "remaining_time": "2:07:54"}
|
||||||
|
{"current_steps": 2900, "total_steps": 6572, "loss": 0.09567424058914184, "lr": 3.164367822418029e-06, "epoch": 1.765296803652968, "percentage": 44.13, "elapsed_time": "1:40:22", "remaining_time": "2:07:05"}
|
||||||
|
{"current_steps": 2920, "total_steps": 6572, "loss": 0.07239987254142762, "lr": 3.1401908391258474e-06, "epoch": 1.7774733637747335, "percentage": 44.43, "elapsed_time": "1:41:00", "remaining_time": "2:06:19"}
|
||||||
|
{"current_steps": 2940, "total_steps": 6572, "loss": 0.0891954243183136, "lr": 3.1159496087438098e-06, "epoch": 1.7896499238964991, "percentage": 44.74, "elapsed_time": "1:41:36", "remaining_time": "2:05:31"}
|
||||||
|
{"current_steps": 2960, "total_steps": 6572, "loss": 0.07796849608421326, "lr": 3.0916465640285426e-06, "epoch": 1.8018264840182647, "percentage": 45.04, "elapsed_time": "1:42:12", "remaining_time": "2:04:43"}
|
||||||
|
{"current_steps": 2980, "total_steps": 6572, "loss": 0.08645985722541809, "lr": 3.0672841439401223e-06, "epoch": 1.8140030441400303, "percentage": 45.34, "elapsed_time": "1:42:49", "remaining_time": "2:03:55"}
|
||||||
|
{"current_steps": 3000, "total_steps": 6572, "loss": 0.08427774310111999, "lr": 3.0428647933973103e-06, "epoch": 1.826179604261796, "percentage": 45.65, "elapsed_time": "1:43:26", "remaining_time": "2:03:10"}
|
||||||
|
{"current_steps": 3000, "total_steps": 6572, "eval_loss": 0.2774485647678375, "epoch": 1.826179604261796, "percentage": 45.65, "elapsed_time": "1:44:13", "remaining_time": "2:04:05"}
|
||||||
|
{"current_steps": 3020, "total_steps": 6572, "loss": 0.07381275296211243, "lr": 3.0183909630321865e-06, "epoch": 1.8383561643835615, "percentage": 45.95, "elapsed_time": "1:46:17", "remaining_time": "2:05:00"}
|
||||||
|
{"current_steps": 3040, "total_steps": 6572, "loss": 0.07289664745330811, "lr": 2.9938651089442184e-06, "epoch": 1.8505327245053271, "percentage": 46.26, "elapsed_time": "1:46:55", "remaining_time": "2:04:14"}
|
||||||
|
{"current_steps": 3060, "total_steps": 6572, "loss": 0.07124295830726624, "lr": 2.969289692453773e-06, "epoch": 1.8627092846270927, "percentage": 46.56, "elapsed_time": "1:47:32", "remaining_time": "2:03:25"}
|
||||||
|
{"current_steps": 3080, "total_steps": 6572, "loss": 0.08125877976417542, "lr": 2.944667179855109e-06, "epoch": 1.8748858447488583, "percentage": 46.87, "elapsed_time": "1:48:09", "remaining_time": "2:02:37"}
|
||||||
|
{"current_steps": 3100, "total_steps": 6572, "loss": 0.0724608838558197, "lr": 2.920000042168871e-06, "epoch": 1.887062404870624, "percentage": 47.17, "elapsed_time": "1:48:47", "remaining_time": "2:01:51"}
|
||||||
|
{"current_steps": 3120, "total_steps": 6572, "loss": 0.07104775309562683, "lr": 2.8952907548941057e-06, "epoch": 1.8992389649923895, "percentage": 47.47, "elapsed_time": "1:49:23", "remaining_time": "2:01:01"}
|
||||||
|
{"current_steps": 3140, "total_steps": 6572, "loss": 0.0677955150604248, "lr": 2.8705417977598277e-06, "epoch": 1.9114155251141551, "percentage": 47.78, "elapsed_time": "1:50:00", "remaining_time": "2:00:14"}
|
||||||
|
{"current_steps": 3160, "total_steps": 6572, "loss": 0.07164496779441834, "lr": 2.8457556544761687e-06, "epoch": 1.9235920852359207, "percentage": 48.08, "elapsed_time": "1:50:36", "remaining_time": "1:59:25"}
|
||||||
|
{"current_steps": 3180, "total_steps": 6572, "loss": 0.071807599067688, "lr": 2.8209348124851187e-06, "epoch": 1.9357686453576863, "percentage": 48.39, "elapsed_time": "1:51:13", "remaining_time": "1:58:38"}
|
||||||
|
{"current_steps": 3200, "total_steps": 6572, "loss": 0.095755535364151, "lr": 2.7960817627108965e-06, "epoch": 1.947945205479452, "percentage": 48.69, "elapsed_time": "1:51:50", "remaining_time": "1:57:50"}
|
||||||
|
{"current_steps": 3220, "total_steps": 6572, "loss": 0.07055851817131042, "lr": 2.77119899930997e-06, "epoch": 1.9601217656012175, "percentage": 49.0, "elapsed_time": "1:52:26", "remaining_time": "1:57:03"}
|
||||||
|
{"current_steps": 3240, "total_steps": 6572, "loss": 0.07278798818588257, "lr": 2.7462890194207513e-06, "epoch": 1.9722983257229831, "percentage": 49.3, "elapsed_time": "1:53:03", "remaining_time": "1:56:16"}
|
||||||
|
{"current_steps": 3260, "total_steps": 6572, "loss": 0.07153088450431824, "lr": 2.7213543229129956e-06, "epoch": 1.9844748858447487, "percentage": 49.6, "elapsed_time": "1:53:40", "remaining_time": "1:55:28"}
|
||||||
|
{"current_steps": 3280, "total_steps": 6572, "loss": 0.07440360188484192, "lr": 2.6963974121369242e-06, "epoch": 1.9966514459665143, "percentage": 49.91, "elapsed_time": "1:54:16", "remaining_time": "1:54:41"}
|
||||||
|
{"current_steps": 3300, "total_steps": 6572, "loss": 0.0517767608165741, "lr": 2.671420791672093e-06, "epoch": 2.008523592085236, "percentage": 50.21, "elapsed_time": "1:54:51", "remaining_time": "1:53:53"}
|
||||||
|
{"current_steps": 3320, "total_steps": 6572, "loss": 0.03812239170074463, "lr": 2.646426968076052e-06, "epoch": 2.0207001522070014, "percentage": 50.52, "elapsed_time": "1:55:27", "remaining_time": "1:53:06"}
|
||||||
|
{"current_steps": 3340, "total_steps": 6572, "loss": 0.04107579588890076, "lr": 2.6214184496327865e-06, "epoch": 2.032876712328767, "percentage": 50.82, "elapsed_time": "1:56:05", "remaining_time": "1:52:19"}
|
||||||
|
{"current_steps": 3360, "total_steps": 6572, "loss": 0.04673115909099579, "lr": 2.5963977461010022e-06, "epoch": 2.0450532724505326, "percentage": 51.13, "elapsed_time": "1:56:41", "remaining_time": "1:51:33"}
|
||||||
|
{"current_steps": 3380, "total_steps": 6572, "loss": 0.03674449622631073, "lr": 2.5713673684622524e-06, "epoch": 2.057229832572298, "percentage": 51.43, "elapsed_time": "1:57:17", "remaining_time": "1:50:46"}
|
||||||
|
{"current_steps": 3400, "total_steps": 6572, "loss": 0.03422380387783051, "lr": 2.546329828668949e-06, "epoch": 2.069406392694064, "percentage": 51.73, "elapsed_time": "1:57:53", "remaining_time": "1:49:59"}
|
||||||
|
{"current_steps": 3420, "total_steps": 6572, "loss": 0.035878732800483704, "lr": 2.5212876393922657e-06, "epoch": 2.0815829528158294, "percentage": 52.04, "elapsed_time": "1:58:29", "remaining_time": "1:49:12"}
|
||||||
|
{"current_steps": 3440, "total_steps": 6572, "loss": 0.03577531576156616, "lr": 2.496243313769986e-06, "epoch": 2.093759512937595, "percentage": 52.34, "elapsed_time": "1:59:06", "remaining_time": "1:48:27"}
|
||||||
|
{"current_steps": 3460, "total_steps": 6572, "loss": 0.04281675517559051, "lr": 2.471199365154283e-06, "epoch": 2.1059360730593606, "percentage": 52.65, "elapsed_time": "1:59:42", "remaining_time": "1:47:40"}
|
||||||
|
{"current_steps": 3480, "total_steps": 6572, "loss": 0.042955422401428224, "lr": 2.4461583068595014e-06, "epoch": 2.118112633181126, "percentage": 52.95, "elapsed_time": "2:00:20", "remaining_time": "1:46:55"}
|
||||||
|
{"current_steps": 3500, "total_steps": 6572, "loss": 0.04432957172393799, "lr": 2.421122651909918e-06, "epoch": 2.130289193302892, "percentage": 53.26, "elapsed_time": "2:00:56", "remaining_time": "1:46:09"}
|
||||||
|
{"current_steps": 3500, "total_steps": 6572, "eval_loss": 0.3123805522918701, "epoch": 2.130289193302892, "percentage": 53.26, "elapsed_time": "2:01:42", "remaining_time": "1:46:49"}
|
||||||
|
{"current_steps": 3520, "total_steps": 6572, "loss": 0.03356837034225464, "lr": 2.3960949127875556e-06, "epoch": 2.1424657534246574, "percentage": 53.56, "elapsed_time": "2:03:47", "remaining_time": "1:47:19"}
|
||||||
|
{"current_steps": 3540, "total_steps": 6572, "loss": 0.036935809254646304, "lr": 2.371077601180031e-06, "epoch": 2.154642313546423, "percentage": 53.86, "elapsed_time": "2:04:23", "remaining_time": "1:46:32"}
|
||||||
|
{"current_steps": 3560, "total_steps": 6572, "loss": 0.0395690768957138, "lr": 2.3460732277284994e-06, "epoch": 2.1668188736681886, "percentage": 54.17, "elapsed_time": "2:05:01", "remaining_time": "1:45:46"}
|
||||||
|
{"current_steps": 3580, "total_steps": 6572, "loss": 0.044693085551261905, "lr": 2.321084301775689e-06, "epoch": 2.178995433789954, "percentage": 54.47, "elapsed_time": "2:05:39", "remaining_time": "1:45:01"}
|
||||||
|
{"current_steps": 3600, "total_steps": 6572, "loss": 0.03243565857410431, "lr": 2.29611333111408e-06, "epoch": 2.19117199391172, "percentage": 54.78, "elapsed_time": "2:06:17", "remaining_time": "1:44:15"}
|
||||||
|
{"current_steps": 3620, "total_steps": 6572, "loss": 0.04325798749923706, "lr": 2.271162821734225e-06, "epoch": 2.2033485540334854, "percentage": 55.08, "elapsed_time": "2:06:56", "remaining_time": "1:43:30"}
|
||||||
|
{"current_steps": 3640, "total_steps": 6572, "loss": 0.03856868743896484, "lr": 2.2462352775732653e-06, "epoch": 2.215525114155251, "percentage": 55.39, "elapsed_time": "2:07:33", "remaining_time": "1:42:45"}
|
||||||
|
{"current_steps": 3660, "total_steps": 6572, "loss": 0.041602414846420285, "lr": 2.221333200263637e-06, "epoch": 2.2277016742770166, "percentage": 55.69, "elapsed_time": "2:08:11", "remaining_time": "1:41:59"}
|
||||||
|
{"current_steps": 3680, "total_steps": 6572, "loss": 0.04286134541034699, "lr": 2.1964590888820233e-06, "epoch": 2.239878234398782, "percentage": 56.0, "elapsed_time": "2:08:48", "remaining_time": "1:41:13"}
|
||||||
|
{"current_steps": 3700, "total_steps": 6572, "loss": 0.041756758093833925, "lr": 2.1716154396985526e-06, "epoch": 2.252054794520548, "percentage": 56.3, "elapsed_time": "2:09:25", "remaining_time": "1:40:28"}
|
||||||
|
{"current_steps": 3720, "total_steps": 6572, "loss": 0.0359495222568512, "lr": 2.1468047459262882e-06, "epoch": 2.2642313546423134, "percentage": 56.6, "elapsed_time": "2:10:03", "remaining_time": "1:39:42"}
|
||||||
|
{"current_steps": 3740, "total_steps": 6572, "loss": 0.04322676360607147, "lr": 2.12202949747101e-06, "epoch": 2.276407914764079, "percentage": 56.91, "elapsed_time": "2:10:41", "remaining_time": "1:38:57"}
|
||||||
|
{"current_steps": 3760, "total_steps": 6572, "loss": 0.04191597998142242, "lr": 2.0972921806813468e-06, "epoch": 2.2885844748858446, "percentage": 57.21, "elapsed_time": "2:11:19", "remaining_time": "1:38:13"}
|
||||||
|
{"current_steps": 3780, "total_steps": 6572, "loss": 0.041278204321861266, "lr": 2.072595278099247e-06, "epoch": 2.30076103500761, "percentage": 57.52, "elapsed_time": "2:11:58", "remaining_time": "1:37:28"}
|
||||||
|
{"current_steps": 3800, "total_steps": 6572, "loss": 0.04312986135482788, "lr": 2.047941268210849e-06, "epoch": 2.312937595129376, "percentage": 57.82, "elapsed_time": "2:12:35", "remaining_time": "1:36:43"}
|
||||||
|
{"current_steps": 3820, "total_steps": 6572, "loss": 0.04236046075820923, "lr": 2.0233326251977426e-06, "epoch": 2.3251141552511414, "percentage": 58.13, "elapsed_time": "2:13:14", "remaining_time": "1:35:59"}
|
||||||
|
{"current_steps": 3840, "total_steps": 6572, "loss": 0.04433901011943817, "lr": 1.9987718186886724e-06, "epoch": 2.337290715372907, "percentage": 58.43, "elapsed_time": "2:13:52", "remaining_time": "1:35:14"}
|
||||||
|
{"current_steps": 3860, "total_steps": 6572, "loss": 0.04127628207206726, "lr": 1.9742613135116986e-06, "epoch": 2.3494672754946726, "percentage": 58.73, "elapsed_time": "2:14:29", "remaining_time": "1:34:29"}
|
||||||
|
{"current_steps": 3880, "total_steps": 6572, "loss": 0.04586326479911804, "lr": 1.949803569446828e-06, "epoch": 2.361643835616438, "percentage": 59.04, "elapsed_time": "2:15:07", "remaining_time": "1:33:45"}
|
||||||
|
{"current_steps": 3900, "total_steps": 6572, "loss": 0.03624185025691986, "lr": 1.925401040979171e-06, "epoch": 2.373820395738204, "percentage": 59.34, "elapsed_time": "2:15:44", "remaining_time": "1:33:00"}
|
||||||
|
{"current_steps": 3920, "total_steps": 6572, "loss": 0.035064518451690674, "lr": 1.9010561770526076e-06, "epoch": 2.3859969558599694, "percentage": 59.65, "elapsed_time": "2:16:21", "remaining_time": "1:32:15"}
|
||||||
|
{"current_steps": 3940, "total_steps": 6572, "loss": 0.042050021886825564, "lr": 1.8767714208240312e-06, "epoch": 2.398173515981735, "percentage": 59.95, "elapsed_time": "2:16:59", "remaining_time": "1:31:30"}
|
||||||
|
{"current_steps": 3960, "total_steps": 6572, "loss": 0.038166466355323794, "lr": 1.852549209418154e-06, "epoch": 2.4103500761035006, "percentage": 60.26, "elapsed_time": "2:17:37", "remaining_time": "1:30:46"}
|
||||||
|
{"current_steps": 3980, "total_steps": 6572, "loss": 0.040885674953460696, "lr": 1.8283919736829332e-06, "epoch": 2.422526636225266, "percentage": 60.56, "elapsed_time": "2:18:15", "remaining_time": "1:30:02"}
|
||||||
|
{"current_steps": 4000, "total_steps": 6572, "loss": 0.040162667632102966, "lr": 1.804302137945614e-06, "epoch": 2.434703196347032, "percentage": 60.86, "elapsed_time": "2:18:51", "remaining_time": "1:29:17"}
|
||||||
|
{"current_steps": 4000, "total_steps": 6572, "eval_loss": 0.31583163142204285, "epoch": 2.434703196347032, "percentage": 60.86, "elapsed_time": "2:19:38", "remaining_time": "1:29:47"}
|
||||||
|
{"current_steps": 4020, "total_steps": 6572, "loss": 0.04170995056629181, "lr": 1.7802821197694426e-06, "epoch": 2.4468797564687974, "percentage": 61.17, "elapsed_time": "2:21:49", "remaining_time": "1:30:02"}
|
||||||
|
{"current_steps": 4040, "total_steps": 6572, "loss": 0.03834344446659088, "lr": 1.7563343297110375e-06, "epoch": 2.459056316590563, "percentage": 61.47, "elapsed_time": "2:22:25", "remaining_time": "1:29:15"}
|
||||||
|
{"current_steps": 4060, "total_steps": 6572, "loss": 0.03928310573101044, "lr": 1.732461171078486e-06, "epoch": 2.4712328767123286, "percentage": 61.78, "elapsed_time": "2:23:01", "remaining_time": "1:28:29"}
|
||||||
|
{"current_steps": 4080, "total_steps": 6572, "loss": 0.03358933925628662, "lr": 1.7086650396901489e-06, "epoch": 2.483409436834094, "percentage": 62.08, "elapsed_time": "2:23:37", "remaining_time": "1:27:43"}
|
||||||
|
{"current_steps": 4100, "total_steps": 6572, "loss": 0.03547535240650177, "lr": 1.6849483236342322e-06, "epoch": 2.49558599695586, "percentage": 62.39, "elapsed_time": "2:24:14", "remaining_time": "1:26:58"}
|
||||||
|
{"current_steps": 4120, "total_steps": 6572, "loss": 0.03600102663040161, "lr": 1.6613134030291217e-06, "epoch": 2.5077625570776254, "percentage": 62.69, "elapsed_time": "2:24:51", "remaining_time": "1:26:12"}
|
||||||
|
{"current_steps": 4140, "total_steps": 6572, "loss": 0.04347077012062073, "lr": 1.6377626497845278e-06, "epoch": 2.519939117199391, "percentage": 62.99, "elapsed_time": "2:25:27", "remaining_time": "1:25:27"}
|
||||||
|
{"current_steps": 4160, "total_steps": 6572, "loss": 0.02908192276954651, "lr": 1.6142984273634505e-06, "epoch": 2.5321156773211566, "percentage": 63.3, "elapsed_time": "2:26:04", "remaining_time": "1:24:41"}
|
||||||
|
{"current_steps": 4180, "total_steps": 6572, "loss": 0.03611198365688324, "lr": 1.5909230905449846e-06, "epoch": 2.544292237442922, "percentage": 63.6, "elapsed_time": "2:26:40", "remaining_time": "1:23:56"}
|
||||||
|
{"current_steps": 4200, "total_steps": 6572, "loss": 0.03758668601512909, "lr": 1.567638985188012e-06, "epoch": 2.556468797564688, "percentage": 63.91, "elapsed_time": "2:27:17", "remaining_time": "1:23:10"}
|
||||||
|
{"current_steps": 4220, "total_steps": 6572, "loss": 0.033633843064308167, "lr": 1.544448447995773e-06, "epoch": 2.5686453576864534, "percentage": 64.21, "elapsed_time": "2:27:53", "remaining_time": "1:22:25"}
|
||||||
|
{"current_steps": 4240, "total_steps": 6572, "loss": 0.036797890067100526, "lr": 1.52135380628137e-06, "epoch": 2.580821917808219, "percentage": 64.52, "elapsed_time": "2:28:29", "remaining_time": "1:21:40"}
|
||||||
|
{"current_steps": 4260, "total_steps": 6572, "loss": 0.039166563749313356, "lr": 1.498357377734201e-06, "epoch": 2.5929984779299846, "percentage": 64.82, "elapsed_time": "2:29:07", "remaining_time": "1:20:55"}
|
||||||
|
{"current_steps": 4280, "total_steps": 6572, "loss": 0.03717599511146545, "lr": 1.4754614701873703e-06, "epoch": 2.60517503805175, "percentage": 65.12, "elapsed_time": "2:29:44", "remaining_time": "1:20:11"}
|
||||||
|
{"current_steps": 4300, "total_steps": 6572, "loss": 0.03962793946266174, "lr": 1.4526683813860792e-06, "epoch": 2.6173515981735163, "percentage": 65.43, "elapsed_time": "2:30:20", "remaining_time": "1:19:26"}
|
||||||
|
{"current_steps": 4320, "total_steps": 6572, "loss": 0.035475924611091614, "lr": 1.4299803987570396e-06, "epoch": 2.6295281582952814, "percentage": 65.73, "elapsed_time": "2:30:57", "remaining_time": "1:18:41"}
|
||||||
|
{"current_steps": 4340, "total_steps": 6572, "loss": 0.03256964683532715, "lr": 1.4073997991789078e-06, "epoch": 2.6417047184170475, "percentage": 66.04, "elapsed_time": "2:31:35", "remaining_time": "1:17:57"}
|
||||||
|
{"current_steps": 4360, "total_steps": 6572, "loss": 0.03712306022644043, "lr": 1.384928848753792e-06, "epoch": 2.6538812785388126, "percentage": 66.34, "elapsed_time": "2:32:10", "remaining_time": "1:17:12"}
|
||||||
|
{"current_steps": 4380, "total_steps": 6572, "loss": 0.041410398483276364, "lr": 1.3625698025798322e-06, "epoch": 2.6660578386605787, "percentage": 66.65, "elapsed_time": "2:32:47", "remaining_time": "1:16:27"}
|
||||||
|
{"current_steps": 4400, "total_steps": 6572, "loss": 0.03158504366874695, "lr": 1.3403249045248907e-06, "epoch": 2.678234398782344, "percentage": 66.95, "elapsed_time": "2:33:23", "remaining_time": "1:15:43"}
|
||||||
|
{"current_steps": 4420, "total_steps": 6572, "loss": 0.03525224924087524, "lr": 1.3181963870013604e-06, "epoch": 2.69041095890411, "percentage": 67.26, "elapsed_time": "2:33:59", "remaining_time": "1:14:58"}
|
||||||
|
{"current_steps": 4440, "total_steps": 6572, "loss": 0.03239959478378296, "lr": 1.2961864707421345e-06, "epoch": 2.702587519025875, "percentage": 67.56, "elapsed_time": "2:34:36", "remaining_time": "1:14:14"}
|
||||||
|
{"current_steps": 4460, "total_steps": 6572, "loss": 0.031032082438468934, "lr": 1.2742973645777394e-06, "epoch": 2.714764079147641, "percentage": 67.86, "elapsed_time": "2:35:13", "remaining_time": "1:13:30"}
|
||||||
|
{"current_steps": 4480, "total_steps": 6572, "loss": 0.030566230416297913, "lr": 1.252531265214662e-06, "epoch": 2.726940639269406, "percentage": 68.17, "elapsed_time": "2:35:48", "remaining_time": "1:12:45"}
|
||||||
|
{"current_steps": 4500, "total_steps": 6572, "loss": 0.041362547874450685, "lr": 1.2308903570149048e-06, "epoch": 2.7391171993911723, "percentage": 68.47, "elapsed_time": "2:36:23", "remaining_time": "1:12:00"}
|
||||||
|
{"current_steps": 4500, "total_steps": 6572, "eval_loss": 0.3391737937927246, "epoch": 2.7391171993911723, "percentage": 68.47, "elapsed_time": "2:37:10", "remaining_time": "1:12:22"}
|
||||||
|
{"current_steps": 4520, "total_steps": 6572, "loss": 0.0388390064239502, "lr": 1.2093768117767613e-06, "epoch": 2.7512937595129374, "percentage": 68.78, "elapsed_time": "2:39:12", "remaining_time": "1:12:16"}
|
||||||
|
{"current_steps": 4540, "total_steps": 6572, "loss": 0.032555675506591795, "lr": 1.1879927885168733e-06, "epoch": 2.7634703196347035, "percentage": 69.08, "elapsed_time": "2:39:48", "remaining_time": "1:11:31"}
|
||||||
|
{"current_steps": 4560, "total_steps": 6572, "loss": 0.03606459796428681, "lr": 1.1667404332535504e-06, "epoch": 2.7756468797564686, "percentage": 69.39, "elapsed_time": "2:40:25", "remaining_time": "1:10:47"}
|
||||||
|
{"current_steps": 4580, "total_steps": 6572, "loss": 0.032086309790611264, "lr": 1.1456218787914128e-06, "epoch": 2.7878234398782347, "percentage": 69.69, "elapsed_time": "2:41:01", "remaining_time": "1:10:02"}
|
||||||
|
{"current_steps": 4600, "total_steps": 6572, "loss": 0.033362787961959836, "lr": 1.1246392445073438e-06, "epoch": 2.8, "percentage": 69.99, "elapsed_time": "2:41:36", "remaining_time": "1:09:16"}
|
||||||
|
{"current_steps": 4620, "total_steps": 6572, "loss": 0.03638745844364166, "lr": 1.1037946361378027e-06, "epoch": 2.812176560121766, "percentage": 70.3, "elapsed_time": "2:42:12", "remaining_time": "1:08:32"}
|
||||||
|
{"current_steps": 4640, "total_steps": 6572, "loss": 0.030933958292007447, "lr": 1.0830901455674977e-06, "epoch": 2.824353120243531, "percentage": 70.6, "elapsed_time": "2:42:49", "remaining_time": "1:07:47"}
|
||||||
|
{"current_steps": 4660, "total_steps": 6572, "loss": 0.02879139482975006, "lr": 1.0625278506194538e-06, "epoch": 2.836529680365297, "percentage": 70.91, "elapsed_time": "2:43:26", "remaining_time": "1:07:03"}
|
||||||
|
{"current_steps": 4680, "total_steps": 6572, "loss": 0.03345020413398743, "lr": 1.04210981484649e-06, "epoch": 2.8487062404870622, "percentage": 71.21, "elapsed_time": "2:44:01", "remaining_time": "1:06:18"}
|
||||||
|
{"current_steps": 4700, "total_steps": 6572, "loss": 0.02593054175376892, "lr": 1.0218380873241314e-06, "epoch": 2.8608828006088283, "percentage": 71.52, "elapsed_time": "2:44:38", "remaining_time": "1:05:34"}
|
||||||
|
{"current_steps": 4720, "total_steps": 6572, "loss": 0.03906567096710205, "lr": 1.0017147024449674e-06, "epoch": 2.8730593607305934, "percentage": 71.82, "elapsed_time": "2:45:15", "remaining_time": "1:04:50"}
|
||||||
|
{"current_steps": 4740, "total_steps": 6572, "loss": 0.03371626436710358, "lr": 9.81741679714493e-07, "epoch": 2.8852359208523595, "percentage": 72.12, "elapsed_time": "2:45:52", "remaining_time": "1:04:06"}
|
||||||
|
{"current_steps": 4760, "total_steps": 6572, "loss": 0.03090968132019043, "lr": 9.619210235484333e-07, "epoch": 2.8974124809741246, "percentage": 72.43, "elapsed_time": "2:46:29", "remaining_time": "1:03:22"}
|
||||||
|
{"current_steps": 4780, "total_steps": 6572, "loss": 0.0322105199098587, "lr": 9.422547230715931e-07, "epoch": 2.9095890410958907, "percentage": 72.73, "elapsed_time": "2:47:05", "remaining_time": "1:02:38"}
|
||||||
|
{"current_steps": 4800, "total_steps": 6572, "loss": 0.035210177302360535, "lr": 9.227447519182353e-07, "epoch": 2.921765601217656, "percentage": 73.04, "elapsed_time": "2:47:42", "remaining_time": "1:01:54"}
|
||||||
|
{"current_steps": 4820, "total_steps": 6572, "loss": 0.026842504739761353, "lr": 9.033930680340097e-07, "epoch": 2.933942161339422, "percentage": 73.34, "elapsed_time": "2:48:18", "remaining_time": "1:01:10"}
|
||||||
|
{"current_steps": 4840, "total_steps": 6572, "loss": 0.03439584076404571, "lr": 8.842016134794682e-07, "epoch": 2.946118721461187, "percentage": 73.65, "elapsed_time": "2:48:55", "remaining_time": "1:00:27"}
|
||||||
|
{"current_steps": 4860, "total_steps": 6572, "loss": 0.04011322855949402, "lr": 8.651723142351603e-07, "epoch": 2.958295281582953, "percentage": 73.95, "elapsed_time": "2:49:32", "remaining_time": "0:59:43"}
|
||||||
|
{"current_steps": 4880, "total_steps": 6572, "loss": 0.03800423145294189, "lr": 8.463070800083562e-07, "epoch": 2.9704718417047182, "percentage": 74.25, "elapsed_time": "2:50:10", "remaining_time": "0:59:00"}
|
||||||
|
{"current_steps": 4900, "total_steps": 6572, "loss": 0.03839131891727447, "lr": 8.276078040413879e-07, "epoch": 2.9826484018264843, "percentage": 74.56, "elapsed_time": "2:50:47", "remaining_time": "0:58:16"}
|
||||||
|
{"current_steps": 4920, "total_steps": 6572, "loss": 0.02721840739250183, "lr": 8.090763629216589e-07, "epoch": 2.9948249619482494, "percentage": 74.86, "elapsed_time": "2:51:25", "remaining_time": "0:57:33"}
|
||||||
|
{"current_steps": 4940, "total_steps": 6572, "loss": 0.023991990089416503, "lr": 7.907146163933102e-07, "epoch": 3.006697108066971, "percentage": 75.17, "elapsed_time": "2:52:02", "remaining_time": "0:56:50"}
|
||||||
|
{"current_steps": 4960, "total_steps": 6572, "loss": 0.01451514959335327, "lr": 7.725244071705871e-07, "epoch": 3.0188736681887365, "percentage": 75.47, "elapsed_time": "2:52:40", "remaining_time": "0:56:07"}
|
||||||
|
{"current_steps": 4980, "total_steps": 6572, "loss": 0.014327619969844819, "lr": 7.545075607529104e-07, "epoch": 3.031050228310502, "percentage": 75.78, "elapsed_time": "2:53:20", "remaining_time": "0:55:24"}
|
||||||
|
{"current_steps": 5000, "total_steps": 6572, "loss": 0.017832010984420776, "lr": 7.366658852416788e-07, "epoch": 3.0432267884322677, "percentage": 76.08, "elapsed_time": "2:53:56", "remaining_time": "0:54:41"}
|
||||||
|
{"current_steps": 5000, "total_steps": 6572, "eval_loss": 0.39115142822265625, "epoch": 3.0432267884322677, "percentage": 76.08, "elapsed_time": "2:54:44", "remaining_time": "0:54:56"}
|
||||||
|
{"current_steps": 5020, "total_steps": 6572, "loss": 0.011674411594867706, "lr": 7.190011711588101e-07, "epoch": 3.0554033485540333, "percentage": 76.38, "elapsed_time": "2:56:57", "remaining_time": "0:54:42"}
|
||||||
|
{"current_steps": 5040, "total_steps": 6572, "loss": 0.013690856099128724, "lr": 7.015151912670562e-07, "epoch": 3.067579908675799, "percentage": 76.69, "elapsed_time": "2:57:34", "remaining_time": "0:53:58"}
|
||||||
|
{"current_steps": 5060, "total_steps": 6572, "loss": 0.011978642642498016, "lr": 6.842097003920903e-07, "epoch": 3.0797564687975645, "percentage": 76.99, "elapsed_time": "2:58:10", "remaining_time": "0:53:14"}
|
||||||
|
{"current_steps": 5080, "total_steps": 6572, "loss": 0.013893941044807434, "lr": 6.67086435246406e-07, "epoch": 3.09193302891933, "percentage": 77.3, "elapsed_time": "2:58:46", "remaining_time": "0:52:30"}
|
||||||
|
{"current_steps": 5100, "total_steps": 6572, "loss": 0.009910025447607041, "lr": 6.501471142550194e-07, "epoch": 3.1041095890410957, "percentage": 77.6, "elapsed_time": "2:59:23", "remaining_time": "0:51:46"}
|
||||||
|
{"current_steps": 5120, "total_steps": 6572, "loss": 0.008863755315542222, "lr": 6.333934373830222e-07, "epoch": 3.1162861491628613, "percentage": 77.91, "elapsed_time": "2:59:59", "remaining_time": "0:51:02"}
|
||||||
|
{"current_steps": 5140, "total_steps": 6572, "loss": 0.010502541810274124, "lr": 6.168270859649761e-07, "epoch": 3.128462709284627, "percentage": 78.21, "elapsed_time": "3:00:37", "remaining_time": "0:50:19"}
|
||||||
|
{"current_steps": 5160, "total_steps": 6572, "loss": 0.012096930295228958, "lr": 6.004497225361786e-07, "epoch": 3.1406392694063925, "percentage": 78.51, "elapsed_time": "3:01:13", "remaining_time": "0:49:35"}
|
||||||
|
{"current_steps": 5180, "total_steps": 6572, "loss": 0.013278065621852875, "lr": 5.842629906658226e-07, "epoch": 3.1528158295281585, "percentage": 78.82, "elapsed_time": "3:01:52", "remaining_time": "0:48:52"}
|
||||||
|
{"current_steps": 5200, "total_steps": 6572, "loss": 0.013548998534679413, "lr": 5.682685147920481e-07, "epoch": 3.1649923896499237, "percentage": 79.12, "elapsed_time": "3:02:28", "remaining_time": "0:48:08"}
|
||||||
|
{"current_steps": 5220, "total_steps": 6572, "loss": 0.013736458122730255, "lr": 5.524679000589256e-07, "epoch": 3.1771689497716897, "percentage": 79.43, "elapsed_time": "3:03:05", "remaining_time": "0:47:25"}
|
||||||
|
{"current_steps": 5240, "total_steps": 6572, "loss": 0.013177134096622467, "lr": 5.36862732155366e-07, "epoch": 3.189345509893455, "percentage": 79.73, "elapsed_time": "3:03:42", "remaining_time": "0:46:41"}
|
||||||
|
{"current_steps": 5260, "total_steps": 6572, "loss": 0.011971819400787353, "lr": 5.214545771559879e-07, "epoch": 3.201522070015221, "percentage": 80.04, "elapsed_time": "3:04:17", "remaining_time": "0:45:58"}
|
||||||
|
{"current_steps": 5280, "total_steps": 6572, "loss": 0.014422819018363953, "lr": 5.062449813639528e-07, "epoch": 3.213698630136986, "percentage": 80.34, "elapsed_time": "3:04:53", "remaining_time": "0:45:14"}
|
||||||
|
{"current_steps": 5300, "total_steps": 6572, "loss": 0.010663678497076034, "lr": 4.912354711557856e-07, "epoch": 3.225875190258752, "percentage": 80.65, "elapsed_time": "3:05:29", "remaining_time": "0:44:31"}
|
||||||
|
{"current_steps": 5320, "total_steps": 6572, "loss": 0.011400717496871948, "lr": 4.764275528281892e-07, "epoch": 3.2380517503805173, "percentage": 80.95, "elapsed_time": "3:06:07", "remaining_time": "0:43:48"}
|
||||||
|
{"current_steps": 5340, "total_steps": 6572, "loss": 0.008456526696681977, "lr": 4.6182271244688355e-07, "epoch": 3.2502283105022833, "percentage": 81.25, "elapsed_time": "3:06:44", "remaining_time": "0:43:04"}
|
||||||
|
{"current_steps": 5360, "total_steps": 6572, "loss": 0.014539115130901337, "lr": 4.4742241569746407e-07, "epoch": 3.2624048706240485, "percentage": 81.56, "elapsed_time": "3:07:22", "remaining_time": "0:42:22"}
|
||||||
|
{"current_steps": 5380, "total_steps": 6572, "loss": 0.017625690996646882, "lr": 4.332281077383177e-07, "epoch": 3.2745814307458145, "percentage": 81.86, "elapsed_time": "3:07:58", "remaining_time": "0:41:38"}
|
||||||
|
{"current_steps": 5400, "total_steps": 6572, "loss": 0.007641100138425827, "lr": 4.1924121305558563e-07, "epoch": 3.2867579908675797, "percentage": 82.17, "elapsed_time": "3:08:37", "remaining_time": "0:40:56"}
|
||||||
|
{"current_steps": 5420, "total_steps": 6572, "loss": 0.011799700558185577, "lr": 4.054631353202121e-07, "epoch": 3.2989345509893457, "percentage": 82.47, "elapsed_time": "3:09:14", "remaining_time": "0:40:13"}
|
||||||
|
{"current_steps": 5440, "total_steps": 6572, "loss": 0.011455408483743667, "lr": 3.9189525724707634e-07, "epoch": 3.311111111111111, "percentage": 82.78, "elapsed_time": "3:09:51", "remaining_time": "0:39:30"}
|
||||||
|
{"current_steps": 5460, "total_steps": 6572, "loss": 0.012499115616083144, "lr": 3.785389404562259e-07, "epoch": 3.323287671232877, "percentage": 83.08, "elapsed_time": "3:10:28", "remaining_time": "0:38:47"}
|
||||||
|
{"current_steps": 5480, "total_steps": 6572, "loss": 0.01148865669965744, "lr": 3.653955253362351e-07, "epoch": 3.335464231354642, "percentage": 83.38, "elapsed_time": "3:11:03", "remaining_time": "0:38:04"}
|
||||||
|
{"current_steps": 5500, "total_steps": 6572, "loss": 0.012819178402423859, "lr": 3.5246633090968205e-07, "epoch": 3.347640791476408, "percentage": 83.69, "elapsed_time": "3:11:39", "remaining_time": "0:37:21"}
|
||||||
|
{"current_steps": 5500, "total_steps": 6572, "eval_loss": 0.43404534459114075, "epoch": 3.347640791476408, "percentage": 83.69, "elapsed_time": "3:12:26", "remaining_time": "0:37:30"}
|
||||||
|
{"current_steps": 5520, "total_steps": 6572, "loss": 0.013325585424900055, "lr": 3.397526547007832e-07, "epoch": 3.3598173515981733, "percentage": 83.99, "elapsed_time": "3:14:26", "remaining_time": "0:37:03"}
|
||||||
|
{"current_steps": 5540, "total_steps": 6572, "loss": 0.011712662875652313, "lr": 3.2725577260517396e-07, "epoch": 3.3719939117199393, "percentage": 84.3, "elapsed_time": "3:15:02", "remaining_time": "0:36:19"}
|
||||||
|
{"current_steps": 5560, "total_steps": 6572, "loss": 0.01580573171377182, "lr": 3.14976938761867e-07, "epoch": 3.3841704718417045, "percentage": 84.6, "elapsed_time": "3:15:38", "remaining_time": "0:35:36"}
|
||||||
|
{"current_steps": 5580, "total_steps": 6572, "loss": 0.012312603741884231, "lr": 3.029173854273909e-07, "epoch": 3.3963470319634705, "percentage": 84.91, "elapsed_time": "3:16:16", "remaining_time": "0:34:53"}
|
||||||
|
{"current_steps": 5600, "total_steps": 6572, "loss": 0.011797953397035599, "lr": 2.910783228521269e-07, "epoch": 3.4085235920852357, "percentage": 85.21, "elapsed_time": "3:16:54", "remaining_time": "0:34:10"}
|
||||||
|
{"current_steps": 5620, "total_steps": 6572, "loss": 0.012182456254959107, "lr": 2.794609391588504e-07, "epoch": 3.4207001522070017, "percentage": 85.51, "elapsed_time": "3:17:32", "remaining_time": "0:33:27"}
|
||||||
|
{"current_steps": 5640, "total_steps": 6572, "loss": 0.013599888980388641, "lr": 2.6806640022349897e-07, "epoch": 3.432876712328767, "percentage": 85.82, "elapsed_time": "3:18:08", "remaining_time": "0:32:44"}
|
||||||
|
{"current_steps": 5660, "total_steps": 6572, "loss": 0.009272868931293487, "lr": 2.5689584955816497e-07, "epoch": 3.445053272450533, "percentage": 86.12, "elapsed_time": "3:18:45", "remaining_time": "0:32:01"}
|
||||||
|
{"current_steps": 5680, "total_steps": 6572, "loss": 0.008165979385375976, "lr": 2.459504081963421e-07, "epoch": 3.457229832572298, "percentage": 86.43, "elapsed_time": "3:19:21", "remaining_time": "0:31:18"}
|
||||||
|
{"current_steps": 5700, "total_steps": 6572, "loss": 0.009182130545377731, "lr": 2.3523117458041865e-07, "epoch": 3.469406392694064, "percentage": 86.73, "elapsed_time": "3:19:56", "remaining_time": "0:30:35"}
|
||||||
|
{"current_steps": 5720, "total_steps": 6572, "loss": 0.0107998326420784, "lr": 2.2473922445144485e-07, "epoch": 3.4815829528158293, "percentage": 87.04, "elapsed_time": "3:20:34", "remaining_time": "0:29:52"}
|
||||||
|
{"current_steps": 5740, "total_steps": 6572, "loss": 0.014469687640666962, "lr": 2.144756107411733e-07, "epoch": 3.4937595129375953, "percentage": 87.34, "elapsed_time": "3:21:11", "remaining_time": "0:29:09"}
|
||||||
|
{"current_steps": 5760, "total_steps": 6572, "loss": 0.0121701680123806, "lr": 2.0444136346639333e-07, "epoch": 3.5059360730593605, "percentage": 87.64, "elapsed_time": "3:21:48", "remaining_time": "0:28:26"}
|
||||||
|
{"current_steps": 5780, "total_steps": 6572, "loss": 0.014668506383895875, "lr": 1.9463748962556096e-07, "epoch": 3.5181126331811265, "percentage": 87.95, "elapsed_time": "3:22:25", "remaining_time": "0:27:44"}
|
||||||
|
{"current_steps": 5800, "total_steps": 6572, "loss": 0.010488402843475342, "lr": 1.8506497309773885e-07, "epoch": 3.5302891933028917, "percentage": 88.25, "elapsed_time": "3:23:02", "remaining_time": "0:27:01"}
|
||||||
|
{"current_steps": 5820, "total_steps": 6572, "loss": 0.010667071491479874, "lr": 1.7572477454386257e-07, "epoch": 3.5424657534246577, "percentage": 88.56, "elapsed_time": "3:23:37", "remaining_time": "0:26:18"}
|
||||||
|
{"current_steps": 5840, "total_steps": 6572, "loss": 0.011079683899879456, "lr": 1.6661783131032726e-07, "epoch": 3.554642313546423, "percentage": 88.86, "elapsed_time": "3:24:14", "remaining_time": "0:25:35"}
|
||||||
|
{"current_steps": 5860, "total_steps": 6572, "loss": 0.009308797866106033, "lr": 1.5774505733492263e-07, "epoch": 3.566818873668189, "percentage": 89.17, "elapsed_time": "3:24:50", "remaining_time": "0:24:53"}
|
||||||
|
{"current_steps": 5880, "total_steps": 6572, "loss": 0.012319787591695785, "lr": 1.49107343055111e-07, "epoch": 3.578995433789954, "percentage": 89.47, "elapsed_time": "3:25:27", "remaining_time": "0:24:10"}
|
||||||
|
{"current_steps": 5900, "total_steps": 6572, "loss": 0.00843576118350029, "lr": 1.407055553186701e-07, "epoch": 3.59117199391172, "percentage": 89.77, "elapsed_time": "3:26:04", "remaining_time": "0:23:28"}
|
||||||
|
{"current_steps": 5920, "total_steps": 6572, "loss": 0.00938587412238121, "lr": 1.3254053729669564e-07, "epoch": 3.6033485540334853, "percentage": 90.08, "elapsed_time": "3:26:41", "remaining_time": "0:22:45"}
|
||||||
|
{"current_steps": 5940, "total_steps": 6572, "loss": 0.011934128403663636, "lr": 1.2461310839898656e-07, "epoch": 3.6155251141552514, "percentage": 90.38, "elapsed_time": "3:27:17", "remaining_time": "0:22:03"}
|
||||||
|
{"current_steps": 5960, "total_steps": 6572, "loss": 0.013170333206653595, "lr": 1.169240641918104e-07, "epoch": 3.6277016742770165, "percentage": 90.69, "elapsed_time": "3:27:54", "remaining_time": "0:21:20"}
|
||||||
|
{"current_steps": 5980, "total_steps": 6572, "loss": 0.014534834027290344, "lr": 1.0947417631806539e-07, "epoch": 3.6398782343987826, "percentage": 90.99, "elapsed_time": "3:28:31", "remaining_time": "0:20:38"}
|
||||||
|
{"current_steps": 6000, "total_steps": 6572, "loss": 0.011021688580513, "lr": 1.0226419241983865e-07, "epoch": 3.6520547945205477, "percentage": 91.3, "elapsed_time": "3:29:07", "remaining_time": "0:19:56"}
|
||||||
|
{"current_steps": 6000, "total_steps": 6572, "eval_loss": 0.44063475728034973, "epoch": 3.6520547945205477, "percentage": 91.3, "elapsed_time": "3:29:53", "remaining_time": "0:20:00"}
|
||||||
|
{"current_steps": 6020, "total_steps": 6572, "loss": 0.010764393210411071, "lr": 9.529483606337902e-08, "epoch": 3.6642313546423138, "percentage": 91.6, "elapsed_time": "3:31:58", "remaining_time": "0:19:26"}
|
||||||
|
{"current_steps": 6040, "total_steps": 6572, "loss": 0.012128306180238723, "lr": 8.856680666647882e-08, "epoch": 3.676407914764079, "percentage": 91.91, "elapsed_time": "3:32:33", "remaining_time": "0:18:43"}
|
||||||
|
{"current_steps": 6060, "total_steps": 6572, "loss": 0.011729901283979416, "lr": 8.208077942828713e-08, "epoch": 3.688584474885845, "percentage": 92.21, "elapsed_time": "3:33:10", "remaining_time": "0:18:00"}
|
||||||
|
{"current_steps": 6080, "total_steps": 6572, "loss": 0.009119105339050294, "lr": 7.58374052615457e-08, "epoch": 3.70076103500761, "percentage": 92.51, "elapsed_time": "3:33:46", "remaining_time": "0:17:17"}
|
||||||
|
{"current_steps": 6100, "total_steps": 6572, "loss": 0.017101363837718965, "lr": 6.983731072726818e-08, "epoch": 3.712937595129376, "percentage": 92.82, "elapsed_time": "3:34:23", "remaining_time": "0:16:35"}
|
||||||
|
{"current_steps": 6120, "total_steps": 6572, "loss": 0.012368235737085342, "lr": 6.408109797186118e-08, "epoch": 3.7251141552511413, "percentage": 93.12, "elapsed_time": "3:34:59", "remaining_time": "0:15:52"}
|
||||||
|
{"current_steps": 6140, "total_steps": 6572, "loss": 0.008782628178596496, "lr": 5.856934466669212e-08, "epoch": 3.7372907153729074, "percentage": 93.43, "elapsed_time": "3:35:36", "remaining_time": "0:15:10"}
|
||||||
|
{"current_steps": 6160, "total_steps": 6572, "loss": 0.008994438499212266, "lr": 5.3302603950119994e-08, "epoch": 3.7494672754946725, "percentage": 93.73, "elapsed_time": "3:36:13", "remaining_time": "0:14:27"}
|
||||||
|
{"current_steps": 6180, "total_steps": 6572, "loss": 0.011286454647779465, "lr": 4.8281404371981755e-08, "epoch": 3.7616438356164386, "percentage": 94.04, "elapsed_time": "3:36:50", "remaining_time": "0:13:45"}
|
||||||
|
{"current_steps": 6200, "total_steps": 6572, "loss": 0.011785905063152313, "lr": 4.350624984055196e-08, "epoch": 3.7738203957382037, "percentage": 94.34, "elapsed_time": "3:37:26", "remaining_time": "0:13:02"}
|
||||||
|
{"current_steps": 6220, "total_steps": 6572, "loss": 0.013624191284179688, "lr": 3.897761957196877e-08, "epoch": 3.7859969558599698, "percentage": 94.64, "elapsed_time": "3:38:01", "remaining_time": "0:12:20"}
|
||||||
|
{"current_steps": 6240, "total_steps": 6572, "loss": 0.011700452119112015, "lr": 3.469596804214548e-08, "epoch": 3.798173515981735, "percentage": 94.95, "elapsed_time": "3:38:37", "remaining_time": "0:11:37"}
|
||||||
|
{"current_steps": 6260, "total_steps": 6572, "loss": 0.011029987037181855, "lr": 3.06617249411581e-08, "epoch": 3.810350076103501, "percentage": 95.25, "elapsed_time": "3:39:12", "remaining_time": "0:10:55"}
|
||||||
|
{"current_steps": 6280, "total_steps": 6572, "loss": 0.010965974628925323, "lr": 2.687529513012488e-08, "epoch": 3.822526636225266, "percentage": 95.56, "elapsed_time": "3:39:49", "remaining_time": "0:10:13"}
|
||||||
|
{"current_steps": 6300, "total_steps": 6572, "loss": 0.012378603965044022, "lr": 2.3337058600575722e-08, "epoch": 3.834703196347032, "percentage": 95.86, "elapsed_time": "3:40:25", "remaining_time": "0:09:30"}
|
||||||
|
{"current_steps": 6320, "total_steps": 6572, "loss": 0.011792077124118805, "lr": 2.0047370436317437e-08, "epoch": 3.8468797564687973, "percentage": 96.17, "elapsed_time": "3:41:00", "remaining_time": "0:08:48"}
|
||||||
|
{"current_steps": 6340, "total_steps": 6572, "loss": 0.01145942509174347, "lr": 1.7006560777798608e-08, "epoch": 3.8590563165905634, "percentage": 96.47, "elapsed_time": "3:41:35", "remaining_time": "0:08:06"}
|
||||||
|
{"current_steps": 6360, "total_steps": 6572, "loss": 0.011088228970766067, "lr": 1.421493478897945e-08, "epoch": 3.8712328767123285, "percentage": 96.77, "elapsed_time": "3:42:11", "remaining_time": "0:07:24"}
|
||||||
|
{"current_steps": 6380, "total_steps": 6572, "loss": 0.010828402638435364, "lr": 1.1672772626704909e-08, "epoch": 3.8834094368340946, "percentage": 97.08, "elapsed_time": "3:42:47", "remaining_time": "0:06:42"}
|
||||||
|
{"current_steps": 6400, "total_steps": 6572, "loss": 0.01165580153465271, "lr": 9.38032941258965e-09, "epoch": 3.8955859969558597, "percentage": 97.38, "elapsed_time": "3:43:22", "remaining_time": "0:06:00"}
|
||||||
|
{"current_steps": 6420, "total_steps": 6572, "loss": 0.010783226788043975, "lr": 7.3378352074163215e-09, "epoch": 3.9077625570776258, "percentage": 97.69, "elapsed_time": "3:43:58", "remaining_time": "0:05:18"}
|
||||||
|
{"current_steps": 6440, "total_steps": 6572, "loss": 0.011295531690120698, "lr": 5.545494988045963e-09, "epoch": 3.919939117199391, "percentage": 97.99, "elapsed_time": "3:44:33", "remaining_time": "0:04:36"}
|
||||||
|
{"current_steps": 6460, "total_steps": 6572, "loss": 0.013613662123680115, "lr": 4.003488626848073e-09, "epoch": 3.932115677321157, "percentage": 98.3, "elapsed_time": "3:45:10", "remaining_time": "0:03:54"}
|
||||||
|
{"current_steps": 6480, "total_steps": 6572, "loss": 0.011696261167526246, "lr": 2.7119708736486615e-09, "epoch": 3.944292237442922, "percentage": 98.6, "elapsed_time": "3:45:47", "remaining_time": "0:03:12"}
|
||||||
|
{"current_steps": 6500, "total_steps": 6572, "loss": 0.010873865336179733, "lr": 1.6710713402015577e-09, "epoch": 3.956468797564688, "percentage": 98.9, "elapsed_time": "3:46:23", "remaining_time": "0:02:30"}
|
||||||
|
{"current_steps": 6500, "total_steps": 6572, "eval_loss": 0.441041499376297, "epoch": 3.956468797564688, "percentage": 98.9, "elapsed_time": "3:47:09", "remaining_time": "0:02:30"}
|
||||||
|
{"current_steps": 6520, "total_steps": 6572, "loss": 0.012961818277835846, "lr": 8.80894487179651e-10, "epoch": 3.9686453576864533, "percentage": 99.21, "elapsed_time": "3:49:12", "remaining_time": "0:01:49"}
|
||||||
|
{"current_steps": 6540, "total_steps": 6572, "loss": 0.01224210560321808, "lr": 3.4151961369188745e-10, "epoch": 3.9808219178082194, "percentage": 99.51, "elapsed_time": "3:49:48", "remaining_time": "0:01:07"}
|
||||||
|
{"current_steps": 6560, "total_steps": 6572, "loss": 0.010245455056428909, "lr": 5.300084932574612e-11, "epoch": 3.9929984779299845, "percentage": 99.82, "elapsed_time": "3:50:24", "remaining_time": "0:00:25"}
|
||||||
|
{"current_steps": 6572, "total_steps": 6572, "epoch": 4.0, "percentage": 100.0, "elapsed_time": "3:52:13", "remaining_time": "0:00:00"}
|
||||||
2443
trainer_state.json
Normal file
2443
trainer_state.json
Normal file
File diff suppressed because it is too large
Load Diff
3
training_args.bin
Normal file
3
training_args.bin
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:c1c8f0bbe96b1bd3b42d30bb419fc0c08037dc014a4a8cea153b553983982dd1
|
||||||
|
size 5585
|
||||||
BIN
training_eval_loss.png
Normal file
BIN
training_eval_loss.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 40 KiB |
BIN
training_loss.png
Normal file
BIN
training_loss.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 36 KiB |
Reference in New Issue
Block a user