Upload folder using huggingface_hub
Browse files- .gitattributes +1 -0
- README.md +58 -0
- checkpoint-252/chat_template.jinja +61 -0
- checkpoint-252/config.json +71 -0
- checkpoint-252/generation_config.json +12 -0
- checkpoint-252/model.safetensors +3 -0
- checkpoint-252/optimizer.pt +3 -0
- checkpoint-252/rng_state.pth +3 -0
- checkpoint-252/scheduler.pt +3 -0
- checkpoint-252/tokenizer.json +3 -0
- checkpoint-252/tokenizer_config.json +29 -0
- checkpoint-252/trainer_state.json +2576 -0
- checkpoint-252/training_args.bin +3 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
checkpoint-252/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
|
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: Qwen/Qwen3-4B-Instruct-2507
|
| 3 |
+
library_name: transformers
|
| 4 |
+
model_name: output-Qwen3-4B-Instruct-2507
|
| 5 |
+
tags:
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
- trl
|
| 8 |
+
- sft
|
| 9 |
+
licence: license
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
# Model Card for output-Qwen3-4B-Instruct-2507
|
| 13 |
+
|
| 14 |
+
This model is a fine-tuned version of [Qwen/Qwen3-4B-Instruct-2507](https://huggingface.co/Qwen/Qwen3-4B-Instruct-2507).
|
| 15 |
+
It has been trained using [TRL](https://github.com/huggingface/trl).
|
| 16 |
+
|
| 17 |
+
## Quick start
|
| 18 |
+
|
| 19 |
+
```python
|
| 20 |
+
from transformers import pipeline
|
| 21 |
+
|
| 22 |
+
question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
|
| 23 |
+
generator = pipeline("text-generation", model="None", device="cuda")
|
| 24 |
+
output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
|
| 25 |
+
print(output["generated_text"])
|
| 26 |
+
```
|
| 27 |
+
|
| 28 |
+
## Training procedure
|
| 29 |
+
|
| 30 |
+
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/easwar-chess-none/chess-reasoning-v1/runs/62lqonw3)
|
| 31 |
+
|
| 32 |
+
|
| 33 |
+
|
| 34 |
+
This model was trained with SFT.
|
| 35 |
+
|
| 36 |
+
### Framework versions
|
| 37 |
+
|
| 38 |
+
- TRL: 0.29.1
|
| 39 |
+
- Transformers: 5.4.0
|
| 40 |
+
- Pytorch: 2.11.0
|
| 41 |
+
- Datasets: 4.8.4
|
| 42 |
+
- Tokenizers: 0.22.2
|
| 43 |
+
|
| 44 |
+
## Citations
|
| 45 |
+
|
| 46 |
+
|
| 47 |
+
|
| 48 |
+
Cite TRL as:
|
| 49 |
+
|
| 50 |
+
```bibtex
|
| 51 |
+
@software{vonwerra2020trl,
|
| 52 |
+
title = {{TRL: Transformers Reinforcement Learning}},
|
| 53 |
+
author = {von Werra, Leandro and Belkada, Younes and Tunstall, Lewis and Beeching, Edward and Thrush, Tristan and Lambert, Nathan and Huang, Shengyi and Rasul, Kashif and Gallouédec, Quentin},
|
| 54 |
+
license = {Apache-2.0},
|
| 55 |
+
url = {https://github.com/huggingface/trl},
|
| 56 |
+
year = {2020}
|
| 57 |
+
}
|
| 58 |
+
```
|
checkpoint-252/chat_template.jinja
ADDED
|
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{%- if tools %}
|
| 2 |
+
{{- '<|im_start|>system\n' }}
|
| 3 |
+
{%- if messages[0].role == 'system' %}
|
| 4 |
+
{{- messages[0].content + '\n\n' }}
|
| 5 |
+
{%- endif %}
|
| 6 |
+
{{- "# 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>" }}
|
| 7 |
+
{%- for tool in tools %}
|
| 8 |
+
{{- "\n" }}
|
| 9 |
+
{{- tool | tojson }}
|
| 10 |
+
{%- endfor %}
|
| 11 |
+
{{- "\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" }}
|
| 12 |
+
{%- else %}
|
| 13 |
+
{%- if messages[0].role == 'system' %}
|
| 14 |
+
{{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
|
| 15 |
+
{%- endif %}
|
| 16 |
+
{%- endif %}
|
| 17 |
+
{%- for message in messages %}
|
| 18 |
+
{%- if message.content is string %}
|
| 19 |
+
{%- set content = message.content %}
|
| 20 |
+
{%- else %}
|
| 21 |
+
{%- set content = '' %}
|
| 22 |
+
{%- endif %}
|
| 23 |
+
{%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
|
| 24 |
+
{{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
|
| 25 |
+
{%- elif message.role == "assistant" %}
|
| 26 |
+
{{- '<|im_start|>' + message.role + '\n' + content }}
|
| 27 |
+
{%- if message.tool_calls %}
|
| 28 |
+
{%- for tool_call in message.tool_calls %}
|
| 29 |
+
{%- if (loop.first and content) or (not loop.first) %}
|
| 30 |
+
{{- '\n' }}
|
| 31 |
+
{%- endif %}
|
| 32 |
+
{%- if tool_call.function %}
|
| 33 |
+
{%- set tool_call = tool_call.function %}
|
| 34 |
+
{%- endif %}
|
| 35 |
+
{{- '<tool_call>\n{"name": "' }}
|
| 36 |
+
{{- tool_call.name }}
|
| 37 |
+
{{- '", "arguments": ' }}
|
| 38 |
+
{%- if tool_call.arguments is string %}
|
| 39 |
+
{{- tool_call.arguments }}
|
| 40 |
+
{%- else %}
|
| 41 |
+
{{- tool_call.arguments | tojson }}
|
| 42 |
+
{%- endif %}
|
| 43 |
+
{{- '}\n</tool_call>' }}
|
| 44 |
+
{%- endfor %}
|
| 45 |
+
{%- endif %}
|
| 46 |
+
{{- '<|im_end|>\n' }}
|
| 47 |
+
{%- elif message.role == "tool" %}
|
| 48 |
+
{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
|
| 49 |
+
{{- '<|im_start|>user' }}
|
| 50 |
+
{%- endif %}
|
| 51 |
+
{{- '\n<tool_response>\n' }}
|
| 52 |
+
{{- content }}
|
| 53 |
+
{{- '\n</tool_response>' }}
|
| 54 |
+
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
| 55 |
+
{{- '<|im_end|>\n' }}
|
| 56 |
+
{%- endif %}
|
| 57 |
+
{%- endif %}
|
| 58 |
+
{%- endfor %}
|
| 59 |
+
{%- if add_generation_prompt %}
|
| 60 |
+
{{- '<|im_start|>assistant\n' }}
|
| 61 |
+
{%- endif %}
|
checkpoint-252/config.json
ADDED
|
@@ -0,0 +1,71 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen3ForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": null,
|
| 8 |
+
"dtype": "bfloat16",
|
| 9 |
+
"eos_token_id": 151645,
|
| 10 |
+
"head_dim": 128,
|
| 11 |
+
"hidden_act": "silu",
|
| 12 |
+
"hidden_size": 2560,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 9728,
|
| 15 |
+
"layer_types": [
|
| 16 |
+
"full_attention",
|
| 17 |
+
"full_attention",
|
| 18 |
+
"full_attention",
|
| 19 |
+
"full_attention",
|
| 20 |
+
"full_attention",
|
| 21 |
+
"full_attention",
|
| 22 |
+
"full_attention",
|
| 23 |
+
"full_attention",
|
| 24 |
+
"full_attention",
|
| 25 |
+
"full_attention",
|
| 26 |
+
"full_attention",
|
| 27 |
+
"full_attention",
|
| 28 |
+
"full_attention",
|
| 29 |
+
"full_attention",
|
| 30 |
+
"full_attention",
|
| 31 |
+
"full_attention",
|
| 32 |
+
"full_attention",
|
| 33 |
+
"full_attention",
|
| 34 |
+
"full_attention",
|
| 35 |
+
"full_attention",
|
| 36 |
+
"full_attention",
|
| 37 |
+
"full_attention",
|
| 38 |
+
"full_attention",
|
| 39 |
+
"full_attention",
|
| 40 |
+
"full_attention",
|
| 41 |
+
"full_attention",
|
| 42 |
+
"full_attention",
|
| 43 |
+
"full_attention",
|
| 44 |
+
"full_attention",
|
| 45 |
+
"full_attention",
|
| 46 |
+
"full_attention",
|
| 47 |
+
"full_attention",
|
| 48 |
+
"full_attention",
|
| 49 |
+
"full_attention",
|
| 50 |
+
"full_attention",
|
| 51 |
+
"full_attention"
|
| 52 |
+
],
|
| 53 |
+
"max_position_embeddings": 262144,
|
| 54 |
+
"max_window_layers": 36,
|
| 55 |
+
"model_type": "qwen3",
|
| 56 |
+
"num_attention_heads": 32,
|
| 57 |
+
"num_hidden_layers": 36,
|
| 58 |
+
"num_key_value_heads": 8,
|
| 59 |
+
"pad_token_id": 151643,
|
| 60 |
+
"rms_norm_eps": 1e-06,
|
| 61 |
+
"rope_parameters": {
|
| 62 |
+
"rope_theta": 5000000,
|
| 63 |
+
"rope_type": "default"
|
| 64 |
+
},
|
| 65 |
+
"sliding_window": null,
|
| 66 |
+
"tie_word_embeddings": true,
|
| 67 |
+
"transformers_version": "5.4.0",
|
| 68 |
+
"use_cache": false,
|
| 69 |
+
"use_sliding_window": false,
|
| 70 |
+
"vocab_size": 151936
|
| 71 |
+
}
|
checkpoint-252/generation_config.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"do_sample": true,
|
| 3 |
+
"eos_token_id": [
|
| 4 |
+
151645,
|
| 5 |
+
151643
|
| 6 |
+
],
|
| 7 |
+
"pad_token_id": 151643,
|
| 8 |
+
"temperature": 0.7,
|
| 9 |
+
"top_k": 20,
|
| 10 |
+
"top_p": 0.8,
|
| 11 |
+
"transformers_version": "5.4.0"
|
| 12 |
+
}
|
checkpoint-252/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:87e98d2fda061bca85218341c3c4745bc5602dd0d5081c462a6664041a054091
|
| 3 |
+
size 8044982080
|
checkpoint-252/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9fa392122983ecdf2e4368491bb02a4642c7f0b56bde106ba58da03f51ee3b71
|
| 3 |
+
size 16090225449
|
checkpoint-252/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:718a0f3db00824213036a2c0441849791319b7d9cf189065873bb26a7020738e
|
| 3 |
+
size 14645
|
checkpoint-252/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b06b4859b82670c608748c562d8e5dacd1516d097a11a46dd624fe8bdaf03e6f
|
| 3 |
+
size 1465
|
checkpoint-252/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:be75606093db2094d7cd20f3c2f385c212750648bd6ea4fb2bf507a6a4c55506
|
| 3 |
+
size 11422650
|
checkpoint-252/tokenizer_config.json
ADDED
|
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"backend": "tokenizers",
|
| 4 |
+
"bos_token": null,
|
| 5 |
+
"clean_up_tokenization_spaces": false,
|
| 6 |
+
"eos_token": "<|im_end|>",
|
| 7 |
+
"errors": "replace",
|
| 8 |
+
"extra_special_tokens": [
|
| 9 |
+
"<|im_start|>",
|
| 10 |
+
"<|im_end|>",
|
| 11 |
+
"<|object_ref_start|>",
|
| 12 |
+
"<|object_ref_end|>",
|
| 13 |
+
"<|box_start|>",
|
| 14 |
+
"<|box_end|>",
|
| 15 |
+
"<|quad_start|>",
|
| 16 |
+
"<|quad_end|>",
|
| 17 |
+
"<|vision_start|>",
|
| 18 |
+
"<|vision_end|>",
|
| 19 |
+
"<|vision_pad|>",
|
| 20 |
+
"<|image_pad|>",
|
| 21 |
+
"<|video_pad|>"
|
| 22 |
+
],
|
| 23 |
+
"is_local": false,
|
| 24 |
+
"model_max_length": 1010000,
|
| 25 |
+
"pad_token": "<|endoftext|>",
|
| 26 |
+
"split_special_tokens": false,
|
| 27 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 28 |
+
"unk_token": null
|
| 29 |
+
}
|
checkpoint-252/trainer_state.json
ADDED
|
@@ -0,0 +1,2576 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 3.0,
|
| 6 |
+
"eval_steps": 200,
|
| 7 |
+
"global_step": 252,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"entropy": 1.0494567453861237,
|
| 14 |
+
"epoch": 0.011904761904761904,
|
| 15 |
+
"grad_norm": 3.25,
|
| 16 |
+
"learning_rate": 2e-05,
|
| 17 |
+
"loss": 2.3006844520568848,
|
| 18 |
+
"mean_token_accuracy": 0.5718516036868095,
|
| 19 |
+
"num_tokens": 27309.0,
|
| 20 |
+
"step": 1
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"entropy": 1.4309201687574387,
|
| 24 |
+
"epoch": 0.023809523809523808,
|
| 25 |
+
"grad_norm": 0.73828125,
|
| 26 |
+
"learning_rate": 1.999922292480975e-05,
|
| 27 |
+
"loss": 1.5732698440551758,
|
| 28 |
+
"mean_token_accuracy": 0.6426078528165817,
|
| 29 |
+
"num_tokens": 53222.0,
|
| 30 |
+
"step": 2
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"entropy": 1.6588206142187119,
|
| 34 |
+
"epoch": 0.03571428571428571,
|
| 35 |
+
"grad_norm": 0.52734375,
|
| 36 |
+
"learning_rate": 1.9996891820008165e-05,
|
| 37 |
+
"loss": 1.5225862264633179,
|
| 38 |
+
"mean_token_accuracy": 0.6484016999602318,
|
| 39 |
+
"num_tokens": 80191.0,
|
| 40 |
+
"step": 3
|
| 41 |
+
},
|
| 42 |
+
{
|
| 43 |
+
"entropy": 1.5771028399467468,
|
| 44 |
+
"epoch": 0.047619047619047616,
|
| 45 |
+
"grad_norm": 0.43359375,
|
| 46 |
+
"learning_rate": 1.9993007047883988e-05,
|
| 47 |
+
"loss": 1.362404227256775,
|
| 48 |
+
"mean_token_accuracy": 0.6749871224164963,
|
| 49 |
+
"num_tokens": 106227.0,
|
| 50 |
+
"step": 4
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"entropy": 1.4989110380411148,
|
| 54 |
+
"epoch": 0.05952380952380952,
|
| 55 |
+
"grad_norm": 0.333984375,
|
| 56 |
+
"learning_rate": 1.9987569212189224e-05,
|
| 57 |
+
"loss": 1.2965717315673828,
|
| 58 |
+
"mean_token_accuracy": 0.6907966956496239,
|
| 59 |
+
"num_tokens": 133050.0,
|
| 60 |
+
"step": 5
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"entropy": 1.433018073439598,
|
| 64 |
+
"epoch": 0.07142857142857142,
|
| 65 |
+
"grad_norm": 0.328125,
|
| 66 |
+
"learning_rate": 1.9980579158045322e-05,
|
| 67 |
+
"loss": 1.2726430892944336,
|
| 68 |
+
"mean_token_accuracy": 0.6866589412093163,
|
| 69 |
+
"num_tokens": 159164.0,
|
| 70 |
+
"step": 6
|
| 71 |
+
},
|
| 72 |
+
{
|
| 73 |
+
"entropy": 1.393497884273529,
|
| 74 |
+
"epoch": 0.08333333333333333,
|
| 75 |
+
"grad_norm": 0.322265625,
|
| 76 |
+
"learning_rate": 1.9972037971811802e-05,
|
| 77 |
+
"loss": 1.2401988506317139,
|
| 78 |
+
"mean_token_accuracy": 0.6934479027986526,
|
| 79 |
+
"num_tokens": 185172.0,
|
| 80 |
+
"step": 7
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"entropy": 1.3325403779745102,
|
| 84 |
+
"epoch": 0.09523809523809523,
|
| 85 |
+
"grad_norm": 0.31640625,
|
| 86 |
+
"learning_rate": 1.9961946980917457e-05,
|
| 87 |
+
"loss": 1.1832386255264282,
|
| 88 |
+
"mean_token_accuracy": 0.7075331285595894,
|
| 89 |
+
"num_tokens": 211963.0,
|
| 90 |
+
"step": 8
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"entropy": 1.3557329028844833,
|
| 94 |
+
"epoch": 0.10714285714285714,
|
| 95 |
+
"grad_norm": 0.298828125,
|
| 96 |
+
"learning_rate": 1.9950307753654016e-05,
|
| 97 |
+
"loss": 1.2336500883102417,
|
| 98 |
+
"mean_token_accuracy": 0.6940329149365425,
|
| 99 |
+
"num_tokens": 237773.0,
|
| 100 |
+
"step": 9
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"entropy": 1.3284195959568024,
|
| 104 |
+
"epoch": 0.11904761904761904,
|
| 105 |
+
"grad_norm": 0.27734375,
|
| 106 |
+
"learning_rate": 1.9937122098932428e-05,
|
| 107 |
+
"loss": 1.1534968614578247,
|
| 108 |
+
"mean_token_accuracy": 0.7091642618179321,
|
| 109 |
+
"num_tokens": 264529.0,
|
| 110 |
+
"step": 10
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"entropy": 1.311100259423256,
|
| 114 |
+
"epoch": 0.13095238095238096,
|
| 115 |
+
"grad_norm": 0.263671875,
|
| 116 |
+
"learning_rate": 1.9922392066001724e-05,
|
| 117 |
+
"loss": 1.1124509572982788,
|
| 118 |
+
"mean_token_accuracy": 0.71821578592062,
|
| 119 |
+
"num_tokens": 291892.0,
|
| 120 |
+
"step": 11
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"entropy": 1.3356539607048035,
|
| 124 |
+
"epoch": 0.14285714285714285,
|
| 125 |
+
"grad_norm": 0.255859375,
|
| 126 |
+
"learning_rate": 1.9906119944130527e-05,
|
| 127 |
+
"loss": 1.1072099208831787,
|
| 128 |
+
"mean_token_accuracy": 0.7180067598819733,
|
| 129 |
+
"num_tokens": 318784.0,
|
| 130 |
+
"step": 12
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"entropy": 1.3447266072034836,
|
| 134 |
+
"epoch": 0.15476190476190477,
|
| 135 |
+
"grad_norm": 0.251953125,
|
| 136 |
+
"learning_rate": 1.9888308262251286e-05,
|
| 137 |
+
"loss": 1.1118253469467163,
|
| 138 |
+
"mean_token_accuracy": 0.7157415449619293,
|
| 139 |
+
"num_tokens": 345251.0,
|
| 140 |
+
"step": 13
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"entropy": 1.3487544059753418,
|
| 144 |
+
"epoch": 0.16666666666666666,
|
| 145 |
+
"grad_norm": 0.275390625,
|
| 146 |
+
"learning_rate": 1.9868959788567213e-05,
|
| 147 |
+
"loss": 1.101747751235962,
|
| 148 |
+
"mean_token_accuracy": 0.7200475409626961,
|
| 149 |
+
"num_tokens": 370047.0,
|
| 150 |
+
"step": 14
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"entropy": 1.340834841132164,
|
| 154 |
+
"epoch": 0.17857142857142858,
|
| 155 |
+
"grad_norm": 0.26171875,
|
| 156 |
+
"learning_rate": 1.9848077530122083e-05,
|
| 157 |
+
"loss": 1.0545036792755127,
|
| 158 |
+
"mean_token_accuracy": 0.7277030423283577,
|
| 159 |
+
"num_tokens": 395849.0,
|
| 160 |
+
"step": 15
|
| 161 |
+
},
|
| 162 |
+
{
|
| 163 |
+
"entropy": 1.376106932759285,
|
| 164 |
+
"epoch": 0.19047619047619047,
|
| 165 |
+
"grad_norm": 0.255859375,
|
| 166 |
+
"learning_rate": 1.9825664732332886e-05,
|
| 167 |
+
"loss": 1.1372387409210205,
|
| 168 |
+
"mean_token_accuracy": 0.7086482048034668,
|
| 169 |
+
"num_tokens": 422584.0,
|
| 170 |
+
"step": 16
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"entropy": 1.346299633383751,
|
| 174 |
+
"epoch": 0.20238095238095238,
|
| 175 |
+
"grad_norm": 0.2451171875,
|
| 176 |
+
"learning_rate": 1.9801724878485438e-05,
|
| 177 |
+
"loss": 1.0804857015609741,
|
| 178 |
+
"mean_token_accuracy": 0.7215344980359077,
|
| 179 |
+
"num_tokens": 448091.0,
|
| 180 |
+
"step": 17
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"entropy": 1.2913489788770676,
|
| 184 |
+
"epoch": 0.21428571428571427,
|
| 185 |
+
"grad_norm": 0.240234375,
|
| 186 |
+
"learning_rate": 1.977626168919305e-05,
|
| 187 |
+
"loss": 1.0192596912384033,
|
| 188 |
+
"mean_token_accuracy": 0.740901842713356,
|
| 189 |
+
"num_tokens": 474916.0,
|
| 190 |
+
"step": 18
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"entropy": 1.3171072006225586,
|
| 194 |
+
"epoch": 0.2261904761904762,
|
| 195 |
+
"grad_norm": 0.2333984375,
|
| 196 |
+
"learning_rate": 1.9749279121818235e-05,
|
| 197 |
+
"loss": 1.0609946250915527,
|
| 198 |
+
"mean_token_accuracy": 0.7298643589019775,
|
| 199 |
+
"num_tokens": 501552.0,
|
| 200 |
+
"step": 19
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"entropy": 1.311616376042366,
|
| 204 |
+
"epoch": 0.23809523809523808,
|
| 205 |
+
"grad_norm": 0.251953125,
|
| 206 |
+
"learning_rate": 1.9720781369857747e-05,
|
| 207 |
+
"loss": 1.0525301694869995,
|
| 208 |
+
"mean_token_accuracy": 0.7259486094117165,
|
| 209 |
+
"num_tokens": 527463.0,
|
| 210 |
+
"step": 20
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"entropy": 1.3294030278921127,
|
| 214 |
+
"epoch": 0.25,
|
| 215 |
+
"grad_norm": 0.228515625,
|
| 216 |
+
"learning_rate": 1.969077286229078e-05,
|
| 217 |
+
"loss": 1.0771116018295288,
|
| 218 |
+
"mean_token_accuracy": 0.7219423204660416,
|
| 219 |
+
"num_tokens": 554225.0,
|
| 220 |
+
"step": 21
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"entropy": 1.2698159664869308,
|
| 224 |
+
"epoch": 0.2619047619047619,
|
| 225 |
+
"grad_norm": 0.220703125,
|
| 226 |
+
"learning_rate": 1.9659258262890683e-05,
|
| 227 |
+
"loss": 0.9951949119567871,
|
| 228 |
+
"mean_token_accuracy": 0.7395628690719604,
|
| 229 |
+
"num_tokens": 580513.0,
|
| 230 |
+
"step": 22
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"entropy": 1.285600259900093,
|
| 234 |
+
"epoch": 0.27380952380952384,
|
| 235 |
+
"grad_norm": 0.2314453125,
|
| 236 |
+
"learning_rate": 1.962624246950012e-05,
|
| 237 |
+
"loss": 1.017578363418579,
|
| 238 |
+
"mean_token_accuracy": 0.7323780730366707,
|
| 239 |
+
"num_tokens": 606397.0,
|
| 240 |
+
"step": 23
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"entropy": 1.287465438246727,
|
| 244 |
+
"epoch": 0.2857142857142857,
|
| 245 |
+
"grad_norm": 0.232421875,
|
| 246 |
+
"learning_rate": 1.9591730613269878e-05,
|
| 247 |
+
"loss": 1.0441396236419678,
|
| 248 |
+
"mean_token_accuracy": 0.7301788926124573,
|
| 249 |
+
"num_tokens": 633019.0,
|
| 250 |
+
"step": 24
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"entropy": 1.260251984000206,
|
| 254 |
+
"epoch": 0.2976190476190476,
|
| 255 |
+
"grad_norm": 0.23046875,
|
| 256 |
+
"learning_rate": 1.955572805786141e-05,
|
| 257 |
+
"loss": 0.9977378845214844,
|
| 258 |
+
"mean_token_accuracy": 0.7360019683837891,
|
| 259 |
+
"num_tokens": 659559.0,
|
| 260 |
+
"step": 25
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"entropy": 1.2459818571805954,
|
| 264 |
+
"epoch": 0.30952380952380953,
|
| 265 |
+
"grad_norm": 0.2373046875,
|
| 266 |
+
"learning_rate": 1.9518240398613226e-05,
|
| 267 |
+
"loss": 0.9966230392456055,
|
| 268 |
+
"mean_token_accuracy": 0.7403357177972794,
|
| 269 |
+
"num_tokens": 686301.0,
|
| 270 |
+
"step": 26
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"entropy": 1.2732659578323364,
|
| 274 |
+
"epoch": 0.32142857142857145,
|
| 275 |
+
"grad_norm": 0.2392578125,
|
| 276 |
+
"learning_rate": 1.947927346167132e-05,
|
| 277 |
+
"loss": 1.0405187606811523,
|
| 278 |
+
"mean_token_accuracy": 0.7255821749567986,
|
| 279 |
+
"num_tokens": 712849.0,
|
| 280 |
+
"step": 27
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"entropy": 1.2356024384498596,
|
| 284 |
+
"epoch": 0.3333333333333333,
|
| 285 |
+
"grad_norm": 0.21875,
|
| 286 |
+
"learning_rate": 1.9438833303083677e-05,
|
| 287 |
+
"loss": 0.9517513513565063,
|
| 288 |
+
"mean_token_accuracy": 0.7443812191486359,
|
| 289 |
+
"num_tokens": 738885.0,
|
| 290 |
+
"step": 28
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"entropy": 1.2620837837457657,
|
| 294 |
+
"epoch": 0.34523809523809523,
|
| 295 |
+
"grad_norm": 0.228515625,
|
| 296 |
+
"learning_rate": 1.9396926207859085e-05,
|
| 297 |
+
"loss": 1.0259062051773071,
|
| 298 |
+
"mean_token_accuracy": 0.7276915162801743,
|
| 299 |
+
"num_tokens": 765741.0,
|
| 300 |
+
"step": 29
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"entropy": 1.2437313944101334,
|
| 304 |
+
"epoch": 0.35714285714285715,
|
| 305 |
+
"grad_norm": 0.2333984375,
|
| 306 |
+
"learning_rate": 1.935355868899034e-05,
|
| 307 |
+
"loss": 0.9744393825531006,
|
| 308 |
+
"mean_token_accuracy": 0.7423476874828339,
|
| 309 |
+
"num_tokens": 791180.0,
|
| 310 |
+
"step": 30
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"entropy": 1.2606688439846039,
|
| 314 |
+
"epoch": 0.36904761904761907,
|
| 315 |
+
"grad_norm": 0.2294921875,
|
| 316 |
+
"learning_rate": 1.9308737486442045e-05,
|
| 317 |
+
"loss": 1.0080578327178955,
|
| 318 |
+
"mean_token_accuracy": 0.7328718677163124,
|
| 319 |
+
"num_tokens": 817215.0,
|
| 320 |
+
"step": 31
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"entropy": 1.2107220739126205,
|
| 324 |
+
"epoch": 0.38095238095238093,
|
| 325 |
+
"grad_norm": 0.216796875,
|
| 326 |
+
"learning_rate": 1.926246956610309e-05,
|
| 327 |
+
"loss": 0.9275428056716919,
|
| 328 |
+
"mean_token_accuracy": 0.7561154067516327,
|
| 329 |
+
"num_tokens": 842758.0,
|
| 330 |
+
"step": 32
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"entropy": 1.2505638897418976,
|
| 334 |
+
"epoch": 0.39285714285714285,
|
| 335 |
+
"grad_norm": 0.2236328125,
|
| 336 |
+
"learning_rate": 1.921476211870408e-05,
|
| 337 |
+
"loss": 0.988660991191864,
|
| 338 |
+
"mean_token_accuracy": 0.7380376160144806,
|
| 339 |
+
"num_tokens": 869333.0,
|
| 340 |
+
"step": 33
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"entropy": 1.2321503013372421,
|
| 344 |
+
"epoch": 0.40476190476190477,
|
| 345 |
+
"grad_norm": 0.2216796875,
|
| 346 |
+
"learning_rate": 1.9165622558699763e-05,
|
| 347 |
+
"loss": 0.9799079298973083,
|
| 348 |
+
"mean_token_accuracy": 0.7438922673463821,
|
| 349 |
+
"num_tokens": 895603.0,
|
| 350 |
+
"step": 34
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"entropy": 1.2264672666788101,
|
| 354 |
+
"epoch": 0.4166666666666667,
|
| 355 |
+
"grad_norm": 0.21875,
|
| 356 |
+
"learning_rate": 1.9115058523116734e-05,
|
| 357 |
+
"loss": 0.942933201789856,
|
| 358 |
+
"mean_token_accuracy": 0.7487473487854004,
|
| 359 |
+
"num_tokens": 922166.0,
|
| 360 |
+
"step": 35
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"entropy": 1.234758123755455,
|
| 364 |
+
"epoch": 0.42857142857142855,
|
| 365 |
+
"grad_norm": 0.2158203125,
|
| 366 |
+
"learning_rate": 1.9063077870366504e-05,
|
| 367 |
+
"loss": 0.9918478727340698,
|
| 368 |
+
"mean_token_accuracy": 0.7380805388092995,
|
| 369 |
+
"num_tokens": 949316.0,
|
| 370 |
+
"step": 36
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"entropy": 1.2392372637987137,
|
| 374 |
+
"epoch": 0.44047619047619047,
|
| 375 |
+
"grad_norm": 0.2294921875,
|
| 376 |
+
"learning_rate": 1.900968867902419e-05,
|
| 377 |
+
"loss": 0.9514465928077698,
|
| 378 |
+
"mean_token_accuracy": 0.7454220503568649,
|
| 379 |
+
"num_tokens": 974399.0,
|
| 380 |
+
"step": 37
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"entropy": 1.202688753604889,
|
| 384 |
+
"epoch": 0.4523809523809524,
|
| 385 |
+
"grad_norm": 0.2333984375,
|
| 386 |
+
"learning_rate": 1.895489924657301e-05,
|
| 387 |
+
"loss": 0.9055959582328796,
|
| 388 |
+
"mean_token_accuracy": 0.7554031237959862,
|
| 389 |
+
"num_tokens": 1000802.0,
|
| 390 |
+
"step": 38
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"entropy": 1.230818286538124,
|
| 394 |
+
"epoch": 0.4642857142857143,
|
| 395 |
+
"grad_norm": 0.2255859375,
|
| 396 |
+
"learning_rate": 1.8898718088114688e-05,
|
| 397 |
+
"loss": 0.9365515112876892,
|
| 398 |
+
"mean_token_accuracy": 0.7501723319292068,
|
| 399 |
+
"num_tokens": 1026890.0,
|
| 400 |
+
"step": 39
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"entropy": 1.2267395704984665,
|
| 404 |
+
"epoch": 0.47619047619047616,
|
| 405 |
+
"grad_norm": 0.2158203125,
|
| 406 |
+
"learning_rate": 1.8841153935046098e-05,
|
| 407 |
+
"loss": 0.9159681797027588,
|
| 408 |
+
"mean_token_accuracy": 0.7491171285510063,
|
| 409 |
+
"num_tokens": 1053091.0,
|
| 410 |
+
"step": 40
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"entropy": 1.1970189958810806,
|
| 414 |
+
"epoch": 0.4880952380952381,
|
| 415 |
+
"grad_norm": 0.2138671875,
|
| 416 |
+
"learning_rate": 1.8782215733702286e-05,
|
| 417 |
+
"loss": 0.8979389071464539,
|
| 418 |
+
"mean_token_accuracy": 0.7574636936187744,
|
| 419 |
+
"num_tokens": 1079663.0,
|
| 420 |
+
"step": 41
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"entropy": 1.2507815808057785,
|
| 424 |
+
"epoch": 0.5,
|
| 425 |
+
"grad_norm": 0.228515625,
|
| 426 |
+
"learning_rate": 1.8721912643966055e-05,
|
| 427 |
+
"loss": 0.9719507098197937,
|
| 428 |
+
"mean_token_accuracy": 0.742218367755413,
|
| 429 |
+
"num_tokens": 1105048.0,
|
| 430 |
+
"step": 42
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"entropy": 1.2222629934549332,
|
| 434 |
+
"epoch": 0.5119047619047619,
|
| 435 |
+
"grad_norm": 0.2197265625,
|
| 436 |
+
"learning_rate": 1.866025403784439e-05,
|
| 437 |
+
"loss": 0.9402767419815063,
|
| 438 |
+
"mean_token_accuracy": 0.748046763241291,
|
| 439 |
+
"num_tokens": 1132222.0,
|
| 440 |
+
"step": 43
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"entropy": 1.2003469914197922,
|
| 444 |
+
"epoch": 0.5238095238095238,
|
| 445 |
+
"grad_norm": 0.2177734375,
|
| 446 |
+
"learning_rate": 1.8597249498011906e-05,
|
| 447 |
+
"loss": 0.8898881077766418,
|
| 448 |
+
"mean_token_accuracy": 0.7626642361283302,
|
| 449 |
+
"num_tokens": 1157814.0,
|
| 450 |
+
"step": 44
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"entropy": 1.2209035754203796,
|
| 454 |
+
"epoch": 0.5357142857142857,
|
| 455 |
+
"grad_norm": 0.2177734375,
|
| 456 |
+
"learning_rate": 1.8532908816321557e-05,
|
| 457 |
+
"loss": 0.9445702433586121,
|
| 458 |
+
"mean_token_accuracy": 0.7497504875063896,
|
| 459 |
+
"num_tokens": 1184124.0,
|
| 460 |
+
"step": 45
|
| 461 |
+
},
|
| 462 |
+
{
|
| 463 |
+
"entropy": 1.2391884326934814,
|
| 464 |
+
"epoch": 0.5476190476190477,
|
| 465 |
+
"grad_norm": 0.22265625,
|
| 466 |
+
"learning_rate": 1.8467241992282842e-05,
|
| 467 |
+
"loss": 0.9409447312355042,
|
| 468 |
+
"mean_token_accuracy": 0.7404728680849075,
|
| 469 |
+
"num_tokens": 1210393.0,
|
| 470 |
+
"step": 46
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"entropy": 1.2089068293571472,
|
| 474 |
+
"epoch": 0.5595238095238095,
|
| 475 |
+
"grad_norm": 0.2265625,
|
| 476 |
+
"learning_rate": 1.8400259231507716e-05,
|
| 477 |
+
"loss": 0.8960930705070496,
|
| 478 |
+
"mean_token_accuracy": 0.7594130486249924,
|
| 479 |
+
"num_tokens": 1236048.0,
|
| 480 |
+
"step": 47
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"entropy": 1.2001971304416656,
|
| 484 |
+
"epoch": 0.5714285714285714,
|
| 485 |
+
"grad_norm": 0.28515625,
|
| 486 |
+
"learning_rate": 1.833197094412449e-05,
|
| 487 |
+
"loss": 0.900606632232666,
|
| 488 |
+
"mean_token_accuracy": 0.7573259472846985,
|
| 489 |
+
"num_tokens": 1261791.0,
|
| 490 |
+
"step": 48
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"entropy": 1.2007492184638977,
|
| 494 |
+
"epoch": 0.5833333333333334,
|
| 495 |
+
"grad_norm": 0.23046875,
|
| 496 |
+
"learning_rate": 1.826238774315995e-05,
|
| 497 |
+
"loss": 0.892056405544281,
|
| 498 |
+
"mean_token_accuracy": 0.7559861242771149,
|
| 499 |
+
"num_tokens": 1287305.0,
|
| 500 |
+
"step": 49
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"entropy": 1.211816444993019,
|
| 504 |
+
"epoch": 0.5952380952380952,
|
| 505 |
+
"grad_norm": 0.2373046875,
|
| 506 |
+
"learning_rate": 1.819152044288992e-05,
|
| 507 |
+
"loss": 0.9308467507362366,
|
| 508 |
+
"mean_token_accuracy": 0.74553432315588,
|
| 509 |
+
"num_tokens": 1312769.0,
|
| 510 |
+
"step": 50
|
| 511 |
+
},
|
| 512 |
+
{
|
| 513 |
+
"entropy": 1.191390410065651,
|
| 514 |
+
"epoch": 0.6071428571428571,
|
| 515 |
+
"grad_norm": 0.23046875,
|
| 516 |
+
"learning_rate": 1.811938005715857e-05,
|
| 517 |
+
"loss": 0.896440327167511,
|
| 518 |
+
"mean_token_accuracy": 0.7532382532954216,
|
| 519 |
+
"num_tokens": 1338512.0,
|
| 520 |
+
"step": 51
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"entropy": 1.2459852695465088,
|
| 524 |
+
"epoch": 0.6190476190476191,
|
| 525 |
+
"grad_norm": 0.2412109375,
|
| 526 |
+
"learning_rate": 1.8045977797666685e-05,
|
| 527 |
+
"loss": 0.992501974105835,
|
| 528 |
+
"mean_token_accuracy": 0.7368015274405479,
|
| 529 |
+
"num_tokens": 1363546.0,
|
| 530 |
+
"step": 52
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"entropy": 1.1912168115377426,
|
| 534 |
+
"epoch": 0.6309523809523809,
|
| 535 |
+
"grad_norm": 0.2275390625,
|
| 536 |
+
"learning_rate": 1.7971325072229227e-05,
|
| 537 |
+
"loss": 0.9404975771903992,
|
| 538 |
+
"mean_token_accuracy": 0.7475577220320702,
|
| 539 |
+
"num_tokens": 1390501.0,
|
| 540 |
+
"step": 53
|
| 541 |
+
},
|
| 542 |
+
{
|
| 543 |
+
"entropy": 1.2136415243148804,
|
| 544 |
+
"epoch": 0.6428571428571429,
|
| 545 |
+
"grad_norm": 0.23046875,
|
| 546 |
+
"learning_rate": 1.7895433483002356e-05,
|
| 547 |
+
"loss": 0.9598132371902466,
|
| 548 |
+
"mean_token_accuracy": 0.7476249039173126,
|
| 549 |
+
"num_tokens": 1416027.0,
|
| 550 |
+
"step": 54
|
| 551 |
+
},
|
| 552 |
+
{
|
| 553 |
+
"entropy": 1.1992420703172684,
|
| 554 |
+
"epoch": 0.6547619047619048,
|
| 555 |
+
"grad_norm": 0.2353515625,
|
| 556 |
+
"learning_rate": 1.78183148246803e-05,
|
| 557 |
+
"loss": 0.9130250811576843,
|
| 558 |
+
"mean_token_accuracy": 0.748944066464901,
|
| 559 |
+
"num_tokens": 1442485.0,
|
| 560 |
+
"step": 55
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"entropy": 1.199160858988762,
|
| 564 |
+
"epoch": 0.6666666666666666,
|
| 565 |
+
"grad_norm": 0.212890625,
|
| 566 |
+
"learning_rate": 1.7739981082662275e-05,
|
| 567 |
+
"loss": 0.9233703017234802,
|
| 568 |
+
"mean_token_accuracy": 0.7508212402462959,
|
| 569 |
+
"num_tokens": 1469875.0,
|
| 570 |
+
"step": 56
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"entropy": 1.2234519720077515,
|
| 574 |
+
"epoch": 0.6785714285714286,
|
| 575 |
+
"grad_norm": 0.224609375,
|
| 576 |
+
"learning_rate": 1.766044443118978e-05,
|
| 577 |
+
"loss": 0.931207537651062,
|
| 578 |
+
"mean_token_accuracy": 0.7512670606374741,
|
| 579 |
+
"num_tokens": 1495641.0,
|
| 580 |
+
"step": 57
|
| 581 |
+
},
|
| 582 |
+
{
|
| 583 |
+
"entropy": 1.1871410608291626,
|
| 584 |
+
"epoch": 0.6904761904761905,
|
| 585 |
+
"grad_norm": 0.232421875,
|
| 586 |
+
"learning_rate": 1.757971723145453e-05,
|
| 587 |
+
"loss": 0.8872414231300354,
|
| 588 |
+
"mean_token_accuracy": 0.7571859434247017,
|
| 589 |
+
"num_tokens": 1521893.0,
|
| 590 |
+
"step": 58
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"entropy": 1.2121420055627823,
|
| 594 |
+
"epoch": 0.7023809523809523,
|
| 595 |
+
"grad_norm": 0.2275390625,
|
| 596 |
+
"learning_rate": 1.7497812029677344e-05,
|
| 597 |
+
"loss": 0.8940609693527222,
|
| 598 |
+
"mean_token_accuracy": 0.7537769973278046,
|
| 599 |
+
"num_tokens": 1546611.0,
|
| 600 |
+
"step": 59
|
| 601 |
+
},
|
| 602 |
+
{
|
| 603 |
+
"entropy": 1.2078164517879486,
|
| 604 |
+
"epoch": 0.7142857142857143,
|
| 605 |
+
"grad_norm": 0.2177734375,
|
| 606 |
+
"learning_rate": 1.741474155515827e-05,
|
| 607 |
+
"loss": 0.9187013506889343,
|
| 608 |
+
"mean_token_accuracy": 0.7539865076541901,
|
| 609 |
+
"num_tokens": 1573642.0,
|
| 610 |
+
"step": 60
|
| 611 |
+
},
|
| 612 |
+
{
|
| 613 |
+
"entropy": 1.2090130001306534,
|
| 614 |
+
"epoch": 0.7261904761904762,
|
| 615 |
+
"grad_norm": 0.2216796875,
|
| 616 |
+
"learning_rate": 1.7330518718298263e-05,
|
| 617 |
+
"loss": 0.9223328828811646,
|
| 618 |
+
"mean_token_accuracy": 0.7508932426571846,
|
| 619 |
+
"num_tokens": 1600715.0,
|
| 620 |
+
"step": 61
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"entropy": 1.2016019374132156,
|
| 624 |
+
"epoch": 0.7380952380952381,
|
| 625 |
+
"grad_norm": 0.216796875,
|
| 626 |
+
"learning_rate": 1.7245156608592727e-05,
|
| 627 |
+
"loss": 0.8950364589691162,
|
| 628 |
+
"mean_token_accuracy": 0.7588292881846428,
|
| 629 |
+
"num_tokens": 1627520.0,
|
| 630 |
+
"step": 62
|
| 631 |
+
},
|
| 632 |
+
{
|
| 633 |
+
"entropy": 1.234247699379921,
|
| 634 |
+
"epoch": 0.75,
|
| 635 |
+
"grad_norm": 0.2412109375,
|
| 636 |
+
"learning_rate": 1.7158668492597186e-05,
|
| 637 |
+
"loss": 0.950704038143158,
|
| 638 |
+
"mean_token_accuracy": 0.7440979778766632,
|
| 639 |
+
"num_tokens": 1652694.0,
|
| 640 |
+
"step": 63
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"entropy": 1.1987243592739105,
|
| 644 |
+
"epoch": 0.7619047619047619,
|
| 645 |
+
"grad_norm": 0.224609375,
|
| 646 |
+
"learning_rate": 1.7071067811865477e-05,
|
| 647 |
+
"loss": 0.9169787764549255,
|
| 648 |
+
"mean_token_accuracy": 0.749868243932724,
|
| 649 |
+
"num_tokens": 1678752.0,
|
| 650 |
+
"step": 64
|
| 651 |
+
},
|
| 652 |
+
{
|
| 653 |
+
"entropy": 1.2067360877990723,
|
| 654 |
+
"epoch": 0.7738095238095238,
|
| 655 |
+
"grad_norm": 0.216796875,
|
| 656 |
+
"learning_rate": 1.698236818086073e-05,
|
| 657 |
+
"loss": 0.9410067200660706,
|
| 658 |
+
"mean_token_accuracy": 0.7454248741269112,
|
| 659 |
+
"num_tokens": 1705052.0,
|
| 660 |
+
"step": 65
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"entropy": 1.175739899277687,
|
| 664 |
+
"epoch": 0.7857142857142857,
|
| 665 |
+
"grad_norm": 0.21875,
|
| 666 |
+
"learning_rate": 1.689258338483947e-05,
|
| 667 |
+
"loss": 0.8811770677566528,
|
| 668 |
+
"mean_token_accuracy": 0.7612746432423592,
|
| 669 |
+
"num_tokens": 1731320.0,
|
| 670 |
+
"step": 66
|
| 671 |
+
},
|
| 672 |
+
{
|
| 673 |
+
"entropy": 1.2032074332237244,
|
| 674 |
+
"epoch": 0.7976190476190477,
|
| 675 |
+
"grad_norm": 0.2177734375,
|
| 676 |
+
"learning_rate": 1.6801727377709195e-05,
|
| 677 |
+
"loss": 0.8974794149398804,
|
| 678 |
+
"mean_token_accuracy": 0.7525004893541336,
|
| 679 |
+
"num_tokens": 1757343.0,
|
| 680 |
+
"step": 67
|
| 681 |
+
},
|
| 682 |
+
{
|
| 683 |
+
"entropy": 1.1771471053361893,
|
| 684 |
+
"epoch": 0.8095238095238095,
|
| 685 |
+
"grad_norm": 0.220703125,
|
| 686 |
+
"learning_rate": 1.67098142798597e-05,
|
| 687 |
+
"loss": 0.8747112154960632,
|
| 688 |
+
"mean_token_accuracy": 0.7630033940076828,
|
| 689 |
+
"num_tokens": 1783385.0,
|
| 690 |
+
"step": 68
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"entropy": 1.1831130683422089,
|
| 694 |
+
"epoch": 0.8214285714285714,
|
| 695 |
+
"grad_norm": 0.224609375,
|
| 696 |
+
"learning_rate": 1.6616858375968596e-05,
|
| 697 |
+
"loss": 0.8969507217407227,
|
| 698 |
+
"mean_token_accuracy": 0.7549743354320526,
|
| 699 |
+
"num_tokens": 1809358.0,
|
| 700 |
+
"step": 69
|
| 701 |
+
},
|
| 702 |
+
{
|
| 703 |
+
"entropy": 1.1840351969003677,
|
| 704 |
+
"epoch": 0.8333333333333334,
|
| 705 |
+
"grad_norm": 0.2177734375,
|
| 706 |
+
"learning_rate": 1.6522874112781213e-05,
|
| 707 |
+
"loss": 0.8991947174072266,
|
| 708 |
+
"mean_token_accuracy": 0.7609456926584244,
|
| 709 |
+
"num_tokens": 1835687.0,
|
| 710 |
+
"step": 70
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"entropy": 1.1689308136701584,
|
| 714 |
+
"epoch": 0.8452380952380952,
|
| 715 |
+
"grad_norm": 0.21875,
|
| 716 |
+
"learning_rate": 1.6427876096865394e-05,
|
| 717 |
+
"loss": 0.8942866921424866,
|
| 718 |
+
"mean_token_accuracy": 0.7570540234446526,
|
| 719 |
+
"num_tokens": 1863074.0,
|
| 720 |
+
"step": 71
|
| 721 |
+
},
|
| 722 |
+
{
|
| 723 |
+
"entropy": 1.176902562379837,
|
| 724 |
+
"epoch": 0.8571428571428571,
|
| 725 |
+
"grad_norm": 0.212890625,
|
| 726 |
+
"learning_rate": 1.6331879092341402e-05,
|
| 727 |
+
"loss": 0.8916264772415161,
|
| 728 |
+
"mean_token_accuracy": 0.7569359466433525,
|
| 729 |
+
"num_tokens": 1889483.0,
|
| 730 |
+
"step": 72
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"entropy": 1.1485393792390823,
|
| 734 |
+
"epoch": 0.8690476190476191,
|
| 735 |
+
"grad_norm": 0.1953125,
|
| 736 |
+
"learning_rate": 1.6234898018587336e-05,
|
| 737 |
+
"loss": 0.8300937414169312,
|
| 738 |
+
"mean_token_accuracy": 0.7689579054713249,
|
| 739 |
+
"num_tokens": 1916554.0,
|
| 740 |
+
"step": 73
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"entropy": 1.188908874988556,
|
| 744 |
+
"epoch": 0.8809523809523809,
|
| 745 |
+
"grad_norm": 0.2236328125,
|
| 746 |
+
"learning_rate": 1.6136947947920477e-05,
|
| 747 |
+
"loss": 0.8971793055534363,
|
| 748 |
+
"mean_token_accuracy": 0.7554975599050522,
|
| 749 |
+
"num_tokens": 1942761.0,
|
| 750 |
+
"step": 74
|
| 751 |
+
},
|
| 752 |
+
{
|
| 753 |
+
"entropy": 1.1443840563297272,
|
| 754 |
+
"epoch": 0.8928571428571429,
|
| 755 |
+
"grad_norm": 0.208984375,
|
| 756 |
+
"learning_rate": 1.6038044103254775e-05,
|
| 757 |
+
"loss": 0.8417671918869019,
|
| 758 |
+
"mean_token_accuracy": 0.7658839598298073,
|
| 759 |
+
"num_tokens": 1970108.0,
|
| 760 |
+
"step": 75
|
| 761 |
+
},
|
| 762 |
+
{
|
| 763 |
+
"entropy": 1.1925117820501328,
|
| 764 |
+
"epoch": 0.9047619047619048,
|
| 765 |
+
"grad_norm": 0.224609375,
|
| 766 |
+
"learning_rate": 1.5938201855735017e-05,
|
| 767 |
+
"loss": 0.9137139320373535,
|
| 768 |
+
"mean_token_accuracy": 0.7506694570183754,
|
| 769 |
+
"num_tokens": 1996053.0,
|
| 770 |
+
"step": 76
|
| 771 |
+
},
|
| 772 |
+
{
|
| 773 |
+
"entropy": 1.146860048174858,
|
| 774 |
+
"epoch": 0.9166666666666666,
|
| 775 |
+
"grad_norm": 0.208984375,
|
| 776 |
+
"learning_rate": 1.5837436722347902e-05,
|
| 777 |
+
"loss": 0.8144647479057312,
|
| 778 |
+
"mean_token_accuracy": 0.7788625955581665,
|
| 779 |
+
"num_tokens": 2022462.0,
|
| 780 |
+
"step": 77
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"entropy": 1.1756789684295654,
|
| 784 |
+
"epoch": 0.9285714285714286,
|
| 785 |
+
"grad_norm": 0.2138671875,
|
| 786 |
+
"learning_rate": 1.573576436351046e-05,
|
| 787 |
+
"loss": 0.8733536601066589,
|
| 788 |
+
"mean_token_accuracy": 0.7620046883821487,
|
| 789 |
+
"num_tokens": 2049019.0,
|
| 790 |
+
"step": 78
|
| 791 |
+
},
|
| 792 |
+
{
|
| 793 |
+
"entropy": 1.1542808413505554,
|
| 794 |
+
"epoch": 0.9404761904761905,
|
| 795 |
+
"grad_norm": 0.2060546875,
|
| 796 |
+
"learning_rate": 1.563320058063622e-05,
|
| 797 |
+
"loss": 0.842410147190094,
|
| 798 |
+
"mean_token_accuracy": 0.7684632763266563,
|
| 799 |
+
"num_tokens": 2075647.0,
|
| 800 |
+
"step": 79
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"entropy": 1.1835035681724548,
|
| 804 |
+
"epoch": 0.9523809523809523,
|
| 805 |
+
"grad_norm": 0.216796875,
|
| 806 |
+
"learning_rate": 1.5529761313679396e-05,
|
| 807 |
+
"loss": 0.8729836344718933,
|
| 808 |
+
"mean_token_accuracy": 0.7571216598153114,
|
| 809 |
+
"num_tokens": 2101511.0,
|
| 810 |
+
"step": 80
|
| 811 |
+
},
|
| 812 |
+
{
|
| 813 |
+
"entropy": 1.1786216050386429,
|
| 814 |
+
"epoch": 0.9642857142857143,
|
| 815 |
+
"grad_norm": 0.2421875,
|
| 816 |
+
"learning_rate": 1.5425462638657597e-05,
|
| 817 |
+
"loss": 0.9298287034034729,
|
| 818 |
+
"mean_token_accuracy": 0.750826895236969,
|
| 819 |
+
"num_tokens": 2128981.0,
|
| 820 |
+
"step": 81
|
| 821 |
+
},
|
| 822 |
+
{
|
| 823 |
+
"entropy": 1.1665120720863342,
|
| 824 |
+
"epoch": 0.9761904761904762,
|
| 825 |
+
"grad_norm": 0.2216796875,
|
| 826 |
+
"learning_rate": 1.5320320765153367e-05,
|
| 827 |
+
"loss": 0.8446856141090393,
|
| 828 |
+
"mean_token_accuracy": 0.7674100771546364,
|
| 829 |
+
"num_tokens": 2155665.0,
|
| 830 |
+
"step": 82
|
| 831 |
+
},
|
| 832 |
+
{
|
| 833 |
+
"entropy": 1.180627018213272,
|
| 834 |
+
"epoch": 0.9880952380952381,
|
| 835 |
+
"grad_norm": 0.2216796875,
|
| 836 |
+
"learning_rate": 1.5214352033794981e-05,
|
| 837 |
+
"loss": 0.8966464996337891,
|
| 838 |
+
"mean_token_accuracy": 0.7552101761102676,
|
| 839 |
+
"num_tokens": 2182098.0,
|
| 840 |
+
"step": 83
|
| 841 |
+
},
|
| 842 |
+
{
|
| 843 |
+
"entropy": 1.174801453948021,
|
| 844 |
+
"epoch": 1.0,
|
| 845 |
+
"grad_norm": 0.228515625,
|
| 846 |
+
"learning_rate": 1.5107572913716859e-05,
|
| 847 |
+
"loss": 0.9110517501831055,
|
| 848 |
+
"mean_token_accuracy": 0.7524702101945877,
|
| 849 |
+
"num_tokens": 2206852.0,
|
| 850 |
+
"step": 84
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"entropy": 1.1386308819055557,
|
| 854 |
+
"epoch": 1.0119047619047619,
|
| 855 |
+
"grad_norm": 0.2109375,
|
| 856 |
+
"learning_rate": 1.5000000000000002e-05,
|
| 857 |
+
"loss": 0.8197644352912903,
|
| 858 |
+
"mean_token_accuracy": 0.7711560949683189,
|
| 859 |
+
"num_tokens": 2233877.0,
|
| 860 |
+
"step": 85
|
| 861 |
+
},
|
| 862 |
+
{
|
| 863 |
+
"entropy": 1.1694304198026657,
|
| 864 |
+
"epoch": 1.0238095238095237,
|
| 865 |
+
"grad_norm": 0.216796875,
|
| 866 |
+
"learning_rate": 1.4891650011092896e-05,
|
| 867 |
+
"loss": 0.8406116366386414,
|
| 868 |
+
"mean_token_accuracy": 0.7672885581851006,
|
| 869 |
+
"num_tokens": 2259853.0,
|
| 870 |
+
"step": 86
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"entropy": 1.163503646850586,
|
| 874 |
+
"epoch": 1.0357142857142858,
|
| 875 |
+
"grad_norm": 0.2158203125,
|
| 876 |
+
"learning_rate": 1.4782539786213184e-05,
|
| 877 |
+
"loss": 0.8342965841293335,
|
| 878 |
+
"mean_token_accuracy": 0.7698492407798767,
|
| 879 |
+
"num_tokens": 2286573.0,
|
| 880 |
+
"step": 87
|
| 881 |
+
},
|
| 882 |
+
{
|
| 883 |
+
"entropy": 1.140608012676239,
|
| 884 |
+
"epoch": 1.0476190476190477,
|
| 885 |
+
"grad_norm": 0.2060546875,
|
| 886 |
+
"learning_rate": 1.4672686282730622e-05,
|
| 887 |
+
"loss": 0.8190659284591675,
|
| 888 |
+
"mean_token_accuracy": 0.7743507474660873,
|
| 889 |
+
"num_tokens": 2312393.0,
|
| 890 |
+
"step": 88
|
| 891 |
+
},
|
| 892 |
+
{
|
| 893 |
+
"entropy": 1.1497679501771927,
|
| 894 |
+
"epoch": 1.0595238095238095,
|
| 895 |
+
"grad_norm": 0.2138671875,
|
| 896 |
+
"learning_rate": 1.4562106573531632e-05,
|
| 897 |
+
"loss": 0.8387782573699951,
|
| 898 |
+
"mean_token_accuracy": 0.7691004797816277,
|
| 899 |
+
"num_tokens": 2338407.0,
|
| 900 |
+
"step": 89
|
| 901 |
+
},
|
| 902 |
+
{
|
| 903 |
+
"entropy": 1.122629627585411,
|
| 904 |
+
"epoch": 1.0714285714285714,
|
| 905 |
+
"grad_norm": 0.2060546875,
|
| 906 |
+
"learning_rate": 1.4450817844365924e-05,
|
| 907 |
+
"loss": 0.821854293346405,
|
| 908 |
+
"mean_token_accuracy": 0.7695046216249466,
|
| 909 |
+
"num_tokens": 2365270.0,
|
| 910 |
+
"step": 90
|
| 911 |
+
},
|
| 912 |
+
{
|
| 913 |
+
"entropy": 1.1272503286600113,
|
| 914 |
+
"epoch": 1.0833333333333333,
|
| 915 |
+
"grad_norm": 0.216796875,
|
| 916 |
+
"learning_rate": 1.4338837391175582e-05,
|
| 917 |
+
"loss": 0.8212571144104004,
|
| 918 |
+
"mean_token_accuracy": 0.7709975987672806,
|
| 919 |
+
"num_tokens": 2391281.0,
|
| 920 |
+
"step": 91
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"entropy": 1.127255380153656,
|
| 924 |
+
"epoch": 1.0952380952380953,
|
| 925 |
+
"grad_norm": 0.2177734375,
|
| 926 |
+
"learning_rate": 1.4226182617406996e-05,
|
| 927 |
+
"loss": 0.8506991267204285,
|
| 928 |
+
"mean_token_accuracy": 0.7657980620861053,
|
| 929 |
+
"num_tokens": 2417731.0,
|
| 930 |
+
"step": 92
|
| 931 |
+
},
|
| 932 |
+
{
|
| 933 |
+
"entropy": 1.1089943200349808,
|
| 934 |
+
"epoch": 1.1071428571428572,
|
| 935 |
+
"grad_norm": 0.2109375,
|
| 936 |
+
"learning_rate": 1.4112871031306118e-05,
|
| 937 |
+
"loss": 0.8343423008918762,
|
| 938 |
+
"mean_token_accuracy": 0.7691437527537346,
|
| 939 |
+
"num_tokens": 2444368.0,
|
| 940 |
+
"step": 93
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"entropy": 1.1271415501832962,
|
| 944 |
+
"epoch": 1.119047619047619,
|
| 945 |
+
"grad_norm": 0.224609375,
|
| 946 |
+
"learning_rate": 1.3998920243197408e-05,
|
| 947 |
+
"loss": 0.8489895462989807,
|
| 948 |
+
"mean_token_accuracy": 0.7649731263518333,
|
| 949 |
+
"num_tokens": 2470388.0,
|
| 950 |
+
"step": 94
|
| 951 |
+
},
|
| 952 |
+
{
|
| 953 |
+
"entropy": 1.1003229320049286,
|
| 954 |
+
"epoch": 1.130952380952381,
|
| 955 |
+
"grad_norm": 0.21875,
|
| 956 |
+
"learning_rate": 1.3884347962746949e-05,
|
| 957 |
+
"loss": 0.8006178736686707,
|
| 958 |
+
"mean_token_accuracy": 0.7761545479297638,
|
| 959 |
+
"num_tokens": 2496905.0,
|
| 960 |
+
"step": 95
|
| 961 |
+
},
|
| 962 |
+
{
|
| 963 |
+
"entropy": 1.1041414737701416,
|
| 964 |
+
"epoch": 1.1428571428571428,
|
| 965 |
+
"grad_norm": 0.220703125,
|
| 966 |
+
"learning_rate": 1.3769171996210053e-05,
|
| 967 |
+
"loss": 0.8553689122200012,
|
| 968 |
+
"mean_token_accuracy": 0.764044426381588,
|
| 969 |
+
"num_tokens": 2523652.0,
|
| 970 |
+
"step": 96
|
| 971 |
+
},
|
| 972 |
+
{
|
| 973 |
+
"entropy": 1.110143706202507,
|
| 974 |
+
"epoch": 1.1547619047619047,
|
| 975 |
+
"grad_norm": 0.220703125,
|
| 976 |
+
"learning_rate": 1.3653410243663953e-05,
|
| 977 |
+
"loss": 0.8074391484260559,
|
| 978 |
+
"mean_token_accuracy": 0.7706331759691238,
|
| 979 |
+
"num_tokens": 2548790.0,
|
| 980 |
+
"step": 97
|
| 981 |
+
},
|
| 982 |
+
{
|
| 983 |
+
"entropy": 1.1172381490468979,
|
| 984 |
+
"epoch": 1.1666666666666667,
|
| 985 |
+
"grad_norm": 0.2236328125,
|
| 986 |
+
"learning_rate": 1.3537080696225815e-05,
|
| 987 |
+
"loss": 0.8375645875930786,
|
| 988 |
+
"mean_token_accuracy": 0.7649935036897659,
|
| 989 |
+
"num_tokens": 2575096.0,
|
| 990 |
+
"step": 98
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"entropy": 1.1418239027261734,
|
| 994 |
+
"epoch": 1.1785714285714286,
|
| 995 |
+
"grad_norm": 0.2412109375,
|
| 996 |
+
"learning_rate": 1.342020143325669e-05,
|
| 997 |
+
"loss": 0.8995247483253479,
|
| 998 |
+
"mean_token_accuracy": 0.7510313019156456,
|
| 999 |
+
"num_tokens": 2602353.0,
|
| 1000 |
+
"step": 99
|
| 1001 |
+
},
|
| 1002 |
+
{
|
| 1003 |
+
"entropy": 1.0998874455690384,
|
| 1004 |
+
"epoch": 1.1904761904761905,
|
| 1005 |
+
"grad_norm": 0.23046875,
|
| 1006 |
+
"learning_rate": 1.3302790619551673e-05,
|
| 1007 |
+
"loss": 0.8080697059631348,
|
| 1008 |
+
"mean_token_accuracy": 0.7733101099729538,
|
| 1009 |
+
"num_tokens": 2628852.0,
|
| 1010 |
+
"step": 100
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"entropy": 1.1344088912010193,
|
| 1014 |
+
"epoch": 1.2023809523809523,
|
| 1015 |
+
"grad_norm": 0.2255859375,
|
| 1016 |
+
"learning_rate": 1.3184866502516846e-05,
|
| 1017 |
+
"loss": 0.8783486485481262,
|
| 1018 |
+
"mean_token_accuracy": 0.7589947134256363,
|
| 1019 |
+
"num_tokens": 2655409.0,
|
| 1020 |
+
"step": 101
|
| 1021 |
+
},
|
| 1022 |
+
{
|
| 1023 |
+
"entropy": 1.1111710369586945,
|
| 1024 |
+
"epoch": 1.2142857142857142,
|
| 1025 |
+
"grad_norm": 0.224609375,
|
| 1026 |
+
"learning_rate": 1.3066447409333345e-05,
|
| 1027 |
+
"loss": 0.8078486919403076,
|
| 1028 |
+
"mean_token_accuracy": 0.7743134796619415,
|
| 1029 |
+
"num_tokens": 2681389.0,
|
| 1030 |
+
"step": 102
|
| 1031 |
+
},
|
| 1032 |
+
{
|
| 1033 |
+
"entropy": 1.130819410085678,
|
| 1034 |
+
"epoch": 1.2261904761904763,
|
| 1035 |
+
"grad_norm": 0.2177734375,
|
| 1036 |
+
"learning_rate": 1.2947551744109044e-05,
|
| 1037 |
+
"loss": 0.8322258591651917,
|
| 1038 |
+
"mean_token_accuracy": 0.769818089902401,
|
| 1039 |
+
"num_tokens": 2707806.0,
|
| 1040 |
+
"step": 103
|
| 1041 |
+
},
|
| 1042 |
+
{
|
| 1043 |
+
"entropy": 1.1183798164129257,
|
| 1044 |
+
"epoch": 1.2380952380952381,
|
| 1045 |
+
"grad_norm": 0.2265625,
|
| 1046 |
+
"learning_rate": 1.2828197985018276e-05,
|
| 1047 |
+
"loss": 0.8078725337982178,
|
| 1048 |
+
"mean_token_accuracy": 0.7757357433438301,
|
| 1049 |
+
"num_tokens": 2733442.0,
|
| 1050 |
+
"step": 104
|
| 1051 |
+
},
|
| 1052 |
+
{
|
| 1053 |
+
"entropy": 1.1384148299694061,
|
| 1054 |
+
"epoch": 1.25,
|
| 1055 |
+
"grad_norm": 0.2314453125,
|
| 1056 |
+
"learning_rate": 1.2708404681430054e-05,
|
| 1057 |
+
"loss": 0.856360137462616,
|
| 1058 |
+
"mean_token_accuracy": 0.7635187655687332,
|
| 1059 |
+
"num_tokens": 2759424.0,
|
| 1060 |
+
"step": 105
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"entropy": 1.1452041417360306,
|
| 1064 |
+
"epoch": 1.2619047619047619,
|
| 1065 |
+
"grad_norm": 0.2421875,
|
| 1066 |
+
"learning_rate": 1.2588190451025209e-05,
|
| 1067 |
+
"loss": 0.9050104022026062,
|
| 1068 |
+
"mean_token_accuracy": 0.750573143362999,
|
| 1069 |
+
"num_tokens": 2786367.0,
|
| 1070 |
+
"step": 106
|
| 1071 |
+
},
|
| 1072 |
+
{
|
| 1073 |
+
"entropy": 1.1285814046859741,
|
| 1074 |
+
"epoch": 1.2738095238095237,
|
| 1075 |
+
"grad_norm": 0.216796875,
|
| 1076 |
+
"learning_rate": 1.2467573976902936e-05,
|
| 1077 |
+
"loss": 0.8008386492729187,
|
| 1078 |
+
"mean_token_accuracy": 0.7742740660905838,
|
| 1079 |
+
"num_tokens": 2812132.0,
|
| 1080 |
+
"step": 107
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"entropy": 1.1281604319810867,
|
| 1084 |
+
"epoch": 1.2857142857142856,
|
| 1085 |
+
"grad_norm": 0.2255859375,
|
| 1086 |
+
"learning_rate": 1.2346574004677154e-05,
|
| 1087 |
+
"loss": 0.8196746706962585,
|
| 1088 |
+
"mean_token_accuracy": 0.7726086974143982,
|
| 1089 |
+
"num_tokens": 2838298.0,
|
| 1090 |
+
"step": 108
|
| 1091 |
+
},
|
| 1092 |
+
{
|
| 1093 |
+
"entropy": 1.1383277475833893,
|
| 1094 |
+
"epoch": 1.2976190476190477,
|
| 1095 |
+
"grad_norm": 0.228515625,
|
| 1096 |
+
"learning_rate": 1.2225209339563144e-05,
|
| 1097 |
+
"loss": 0.8370059132575989,
|
| 1098 |
+
"mean_token_accuracy": 0.7635474875569344,
|
| 1099 |
+
"num_tokens": 2865310.0,
|
| 1100 |
+
"step": 109
|
| 1101 |
+
},
|
| 1102 |
+
{
|
| 1103 |
+
"entropy": 1.1403304636478424,
|
| 1104 |
+
"epoch": 1.3095238095238095,
|
| 1105 |
+
"grad_norm": 0.216796875,
|
| 1106 |
+
"learning_rate": 1.210349884345496e-05,
|
| 1107 |
+
"loss": 0.8350245952606201,
|
| 1108 |
+
"mean_token_accuracy": 0.7653406709432602,
|
| 1109 |
+
"num_tokens": 2891493.0,
|
| 1110 |
+
"step": 110
|
| 1111 |
+
},
|
| 1112 |
+
{
|
| 1113 |
+
"entropy": 1.126132920384407,
|
| 1114 |
+
"epoch": 1.3214285714285714,
|
| 1115 |
+
"grad_norm": 0.2255859375,
|
| 1116 |
+
"learning_rate": 1.1981461431993978e-05,
|
| 1117 |
+
"loss": 0.8264559507369995,
|
| 1118 |
+
"mean_token_accuracy": 0.7698510065674782,
|
| 1119 |
+
"num_tokens": 2917435.0,
|
| 1120 |
+
"step": 111
|
| 1121 |
+
},
|
| 1122 |
+
{
|
| 1123 |
+
"entropy": 1.1356945484876633,
|
| 1124 |
+
"epoch": 1.3333333333333333,
|
| 1125 |
+
"grad_norm": 0.23046875,
|
| 1126 |
+
"learning_rate": 1.1859116071629148e-05,
|
| 1127 |
+
"loss": 0.8438840508460999,
|
| 1128 |
+
"mean_token_accuracy": 0.7598991841077805,
|
| 1129 |
+
"num_tokens": 2943915.0,
|
| 1130 |
+
"step": 112
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"entropy": 1.127932071685791,
|
| 1134 |
+
"epoch": 1.3452380952380953,
|
| 1135 |
+
"grad_norm": 0.2158203125,
|
| 1136 |
+
"learning_rate": 1.1736481776669307e-05,
|
| 1137 |
+
"loss": 0.8465971350669861,
|
| 1138 |
+
"mean_token_accuracy": 0.7641785144805908,
|
| 1139 |
+
"num_tokens": 2970567.0,
|
| 1140 |
+
"step": 113
|
| 1141 |
+
},
|
| 1142 |
+
{
|
| 1143 |
+
"entropy": 1.1035424768924713,
|
| 1144 |
+
"epoch": 1.3571428571428572,
|
| 1145 |
+
"grad_norm": 0.216796875,
|
| 1146 |
+
"learning_rate": 1.1613577606328068e-05,
|
| 1147 |
+
"loss": 0.796665370464325,
|
| 1148 |
+
"mean_token_accuracy": 0.7764606773853302,
|
| 1149 |
+
"num_tokens": 2996884.0,
|
| 1150 |
+
"step": 114
|
| 1151 |
+
},
|
| 1152 |
+
{
|
| 1153 |
+
"entropy": 1.1041745096445084,
|
| 1154 |
+
"epoch": 1.369047619047619,
|
| 1155 |
+
"grad_norm": 0.212890625,
|
| 1156 |
+
"learning_rate": 1.1490422661761744e-05,
|
| 1157 |
+
"loss": 0.8078674674034119,
|
| 1158 |
+
"mean_token_accuracy": 0.7755235582590103,
|
| 1159 |
+
"num_tokens": 3022892.0,
|
| 1160 |
+
"step": 115
|
| 1161 |
+
},
|
| 1162 |
+
{
|
| 1163 |
+
"entropy": 1.1297542303800583,
|
| 1164 |
+
"epoch": 1.380952380952381,
|
| 1165 |
+
"grad_norm": 0.22265625,
|
| 1166 |
+
"learning_rate": 1.1367036083100735e-05,
|
| 1167 |
+
"loss": 0.845131516456604,
|
| 1168 |
+
"mean_token_accuracy": 0.7647897973656654,
|
| 1169 |
+
"num_tokens": 3048844.0,
|
| 1170 |
+
"step": 116
|
| 1171 |
+
},
|
| 1172 |
+
{
|
| 1173 |
+
"entropy": 1.115392044186592,
|
| 1174 |
+
"epoch": 1.3928571428571428,
|
| 1175 |
+
"grad_norm": 0.2333984375,
|
| 1176 |
+
"learning_rate": 1.1243437046474854e-05,
|
| 1177 |
+
"loss": 0.8097545504570007,
|
| 1178 |
+
"mean_token_accuracy": 0.7723855003714561,
|
| 1179 |
+
"num_tokens": 3074806.0,
|
| 1180 |
+
"step": 117
|
| 1181 |
+
},
|
| 1182 |
+
{
|
| 1183 |
+
"entropy": 1.126968502998352,
|
| 1184 |
+
"epoch": 1.4047619047619047,
|
| 1185 |
+
"grad_norm": 0.232421875,
|
| 1186 |
+
"learning_rate": 1.1119644761033079e-05,
|
| 1187 |
+
"loss": 0.8312132358551025,
|
| 1188 |
+
"mean_token_accuracy": 0.7707365080714226,
|
| 1189 |
+
"num_tokens": 3100660.0,
|
| 1190 |
+
"step": 118
|
| 1191 |
+
},
|
| 1192 |
+
{
|
| 1193 |
+
"entropy": 1.1252721548080444,
|
| 1194 |
+
"epoch": 1.4166666666666667,
|
| 1195 |
+
"grad_norm": 0.2236328125,
|
| 1196 |
+
"learning_rate": 1.0995678465958168e-05,
|
| 1197 |
+
"loss": 0.8202887177467346,
|
| 1198 |
+
"mean_token_accuracy": 0.7648059278726578,
|
| 1199 |
+
"num_tokens": 3126427.0,
|
| 1200 |
+
"step": 119
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"entropy": 1.144352748990059,
|
| 1204 |
+
"epoch": 1.4285714285714286,
|
| 1205 |
+
"grad_norm": 0.22265625,
|
| 1206 |
+
"learning_rate": 1.0871557427476585e-05,
|
| 1207 |
+
"loss": 0.8726206421852112,
|
| 1208 |
+
"mean_token_accuracy": 0.7587710469961166,
|
| 1209 |
+
"num_tokens": 3153355.0,
|
| 1210 |
+
"step": 120
|
| 1211 |
+
},
|
| 1212 |
+
{
|
| 1213 |
+
"entropy": 1.1297250092029572,
|
| 1214 |
+
"epoch": 1.4404761904761905,
|
| 1215 |
+
"grad_norm": 0.2216796875,
|
| 1216 |
+
"learning_rate": 1.0747300935864245e-05,
|
| 1217 |
+
"loss": 0.8322736024856567,
|
| 1218 |
+
"mean_token_accuracy": 0.7670553028583527,
|
| 1219 |
+
"num_tokens": 3179491.0,
|
| 1220 |
+
"step": 121
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"entropy": 1.099809244275093,
|
| 1224 |
+
"epoch": 1.4523809523809523,
|
| 1225 |
+
"grad_norm": 0.2236328125,
|
| 1226 |
+
"learning_rate": 1.0622928302448523e-05,
|
| 1227 |
+
"loss": 0.8082002997398376,
|
| 1228 |
+
"mean_token_accuracy": 0.7719271555542946,
|
| 1229 |
+
"num_tokens": 3207329.0,
|
| 1230 |
+
"step": 122
|
| 1231 |
+
},
|
| 1232 |
+
{
|
| 1233 |
+
"entropy": 1.135951966047287,
|
| 1234 |
+
"epoch": 1.4642857142857144,
|
| 1235 |
+
"grad_norm": 0.232421875,
|
| 1236 |
+
"learning_rate": 1.0498458856606972e-05,
|
| 1237 |
+
"loss": 0.8370299935340881,
|
| 1238 |
+
"mean_token_accuracy": 0.7657874599099159,
|
| 1239 |
+
"num_tokens": 3233160.0,
|
| 1240 |
+
"step": 123
|
| 1241 |
+
},
|
| 1242 |
+
{
|
| 1243 |
+
"entropy": 1.134585291147232,
|
| 1244 |
+
"epoch": 1.4761904761904763,
|
| 1245 |
+
"grad_norm": 0.22265625,
|
| 1246 |
+
"learning_rate": 1.037391194276326e-05,
|
| 1247 |
+
"loss": 0.8596113324165344,
|
| 1248 |
+
"mean_token_accuracy": 0.7584040239453316,
|
| 1249 |
+
"num_tokens": 3259695.0,
|
| 1250 |
+
"step": 124
|
| 1251 |
+
},
|
| 1252 |
+
{
|
| 1253 |
+
"entropy": 1.1345889419317245,
|
| 1254 |
+
"epoch": 1.4880952380952381,
|
| 1255 |
+
"grad_norm": 0.2236328125,
|
| 1256 |
+
"learning_rate": 1.0249306917380731e-05,
|
| 1257 |
+
"loss": 0.8585492372512817,
|
| 1258 |
+
"mean_token_accuracy": 0.7621477544307709,
|
| 1259 |
+
"num_tokens": 3286287.0,
|
| 1260 |
+
"step": 125
|
| 1261 |
+
},
|
| 1262 |
+
{
|
| 1263 |
+
"entropy": 1.1395476311445236,
|
| 1264 |
+
"epoch": 1.5,
|
| 1265 |
+
"grad_norm": 0.216796875,
|
| 1266 |
+
"learning_rate": 1.0124663145954152e-05,
|
| 1267 |
+
"loss": 0.853608250617981,
|
| 1268 |
+
"mean_token_accuracy": 0.7603440955281258,
|
| 1269 |
+
"num_tokens": 3312811.0,
|
| 1270 |
+
"step": 126
|
| 1271 |
+
},
|
| 1272 |
+
{
|
| 1273 |
+
"entropy": 1.1343800723552704,
|
| 1274 |
+
"epoch": 1.5119047619047619,
|
| 1275 |
+
"grad_norm": 0.234375,
|
| 1276 |
+
"learning_rate": 1e-05,
|
| 1277 |
+
"loss": 0.855441689491272,
|
| 1278 |
+
"mean_token_accuracy": 0.7621574178338051,
|
| 1279 |
+
"num_tokens": 3338485.0,
|
| 1280 |
+
"step": 127
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"entropy": 1.147290289402008,
|
| 1284 |
+
"epoch": 1.5238095238095237,
|
| 1285 |
+
"grad_norm": 0.2373046875,
|
| 1286 |
+
"learning_rate": 9.87533685404585e-06,
|
| 1287 |
+
"loss": 0.8562023639678955,
|
| 1288 |
+
"mean_token_accuracy": 0.7617470622062683,
|
| 1289 |
+
"num_tokens": 3363352.0,
|
| 1290 |
+
"step": 128
|
| 1291 |
+
},
|
| 1292 |
+
{
|
| 1293 |
+
"entropy": 1.0908429026603699,
|
| 1294 |
+
"epoch": 1.5357142857142856,
|
| 1295 |
+
"grad_norm": 0.2275390625,
|
| 1296 |
+
"learning_rate": 9.750693082619274e-06,
|
| 1297 |
+
"loss": 0.7935777902603149,
|
| 1298 |
+
"mean_token_accuracy": 0.7803073972463608,
|
| 1299 |
+
"num_tokens": 3389709.0,
|
| 1300 |
+
"step": 129
|
| 1301 |
+
},
|
| 1302 |
+
{
|
| 1303 |
+
"entropy": 1.1274128407239914,
|
| 1304 |
+
"epoch": 1.5476190476190477,
|
| 1305 |
+
"grad_norm": 0.2236328125,
|
| 1306 |
+
"learning_rate": 9.626088057236745e-06,
|
| 1307 |
+
"loss": 0.8381516337394714,
|
| 1308 |
+
"mean_token_accuracy": 0.7682216316461563,
|
| 1309 |
+
"num_tokens": 3415496.0,
|
| 1310 |
+
"step": 130
|
| 1311 |
+
},
|
| 1312 |
+
{
|
| 1313 |
+
"entropy": 1.1263544410467148,
|
| 1314 |
+
"epoch": 1.5595238095238095,
|
| 1315 |
+
"grad_norm": 0.2177734375,
|
| 1316 |
+
"learning_rate": 9.501541143393028e-06,
|
| 1317 |
+
"loss": 0.8319387435913086,
|
| 1318 |
+
"mean_token_accuracy": 0.7662338837981224,
|
| 1319 |
+
"num_tokens": 3441710.0,
|
| 1320 |
+
"step": 131
|
| 1321 |
+
},
|
| 1322 |
+
{
|
| 1323 |
+
"entropy": 1.1065820306539536,
|
| 1324 |
+
"epoch": 1.5714285714285714,
|
| 1325 |
+
"grad_norm": 0.2177734375,
|
| 1326 |
+
"learning_rate": 9.377071697551479e-06,
|
| 1327 |
+
"loss": 0.8057957887649536,
|
| 1328 |
+
"mean_token_accuracy": 0.7757579833269119,
|
| 1329 |
+
"num_tokens": 3468647.0,
|
| 1330 |
+
"step": 132
|
| 1331 |
+
},
|
| 1332 |
+
{
|
| 1333 |
+
"entropy": 1.1226835697889328,
|
| 1334 |
+
"epoch": 1.5833333333333335,
|
| 1335 |
+
"grad_norm": 0.2177734375,
|
| 1336 |
+
"learning_rate": 9.252699064135759e-06,
|
| 1337 |
+
"loss": 0.8140422701835632,
|
| 1338 |
+
"mean_token_accuracy": 0.7766503915190697,
|
| 1339 |
+
"num_tokens": 3494627.0,
|
| 1340 |
+
"step": 133
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"entropy": 1.1279116421937943,
|
| 1344 |
+
"epoch": 1.5952380952380953,
|
| 1345 |
+
"grad_norm": 0.2158203125,
|
| 1346 |
+
"learning_rate": 9.128442572523418e-06,
|
| 1347 |
+
"loss": 0.8333442807197571,
|
| 1348 |
+
"mean_token_accuracy": 0.7701004445552826,
|
| 1349 |
+
"num_tokens": 3520726.0,
|
| 1350 |
+
"step": 134
|
| 1351 |
+
},
|
| 1352 |
+
{
|
| 1353 |
+
"entropy": 1.118562862277031,
|
| 1354 |
+
"epoch": 1.6071428571428572,
|
| 1355 |
+
"grad_norm": 0.2255859375,
|
| 1356 |
+
"learning_rate": 9.004321534041836e-06,
|
| 1357 |
+
"loss": 0.8082501292228699,
|
| 1358 |
+
"mean_token_accuracy": 0.7714490741491318,
|
| 1359 |
+
"num_tokens": 3546604.0,
|
| 1360 |
+
"step": 135
|
| 1361 |
+
},
|
| 1362 |
+
{
|
| 1363 |
+
"entropy": 1.1184325218200684,
|
| 1364 |
+
"epoch": 1.619047619047619,
|
| 1365 |
+
"grad_norm": 0.224609375,
|
| 1366 |
+
"learning_rate": 8.880355238966923e-06,
|
| 1367 |
+
"loss": 0.8013947606086731,
|
| 1368 |
+
"mean_token_accuracy": 0.7703685536980629,
|
| 1369 |
+
"num_tokens": 3572560.0,
|
| 1370 |
+
"step": 136
|
| 1371 |
+
},
|
| 1372 |
+
{
|
| 1373 |
+
"entropy": 1.1083856672048569,
|
| 1374 |
+
"epoch": 1.630952380952381,
|
| 1375 |
+
"grad_norm": 0.2177734375,
|
| 1376 |
+
"learning_rate": 8.756562953525151e-06,
|
| 1377 |
+
"loss": 0.8402643799781799,
|
| 1378 |
+
"mean_token_accuracy": 0.7718946933746338,
|
| 1379 |
+
"num_tokens": 3600409.0,
|
| 1380 |
+
"step": 137
|
| 1381 |
+
},
|
| 1382 |
+
{
|
| 1383 |
+
"entropy": 1.1246822774410248,
|
| 1384 |
+
"epoch": 1.6428571428571428,
|
| 1385 |
+
"grad_norm": 0.2216796875,
|
| 1386 |
+
"learning_rate": 8.632963916899268e-06,
|
| 1387 |
+
"loss": 0.8138586282730103,
|
| 1388 |
+
"mean_token_accuracy": 0.7705142721533775,
|
| 1389 |
+
"num_tokens": 3626126.0,
|
| 1390 |
+
"step": 138
|
| 1391 |
+
},
|
| 1392 |
+
{
|
| 1393 |
+
"entropy": 1.1232711374759674,
|
| 1394 |
+
"epoch": 1.6547619047619047,
|
| 1395 |
+
"grad_norm": 0.2236328125,
|
| 1396 |
+
"learning_rate": 8.509577338238255e-06,
|
| 1397 |
+
"loss": 0.8325715065002441,
|
| 1398 |
+
"mean_token_accuracy": 0.7666014134883881,
|
| 1399 |
+
"num_tokens": 3652299.0,
|
| 1400 |
+
"step": 139
|
| 1401 |
+
},
|
| 1402 |
+
{
|
| 1403 |
+
"entropy": 1.1074089109897614,
|
| 1404 |
+
"epoch": 1.6666666666666665,
|
| 1405 |
+
"grad_norm": 0.21875,
|
| 1406 |
+
"learning_rate": 8.386422393671934e-06,
|
| 1407 |
+
"loss": 0.7925585508346558,
|
| 1408 |
+
"mean_token_accuracy": 0.7779242396354675,
|
| 1409 |
+
"num_tokens": 3678732.0,
|
| 1410 |
+
"step": 140
|
| 1411 |
+
},
|
| 1412 |
+
{
|
| 1413 |
+
"entropy": 1.127850890159607,
|
| 1414 |
+
"epoch": 1.6785714285714286,
|
| 1415 |
+
"grad_norm": 0.2119140625,
|
| 1416 |
+
"learning_rate": 8.263518223330698e-06,
|
| 1417 |
+
"loss": 0.8398563861846924,
|
| 1418 |
+
"mean_token_accuracy": 0.7660870477557182,
|
| 1419 |
+
"num_tokens": 3705434.0,
|
| 1420 |
+
"step": 141
|
| 1421 |
+
},
|
| 1422 |
+
{
|
| 1423 |
+
"entropy": 1.1316388994455338,
|
| 1424 |
+
"epoch": 1.6904761904761905,
|
| 1425 |
+
"grad_norm": 0.2197265625,
|
| 1426 |
+
"learning_rate": 8.140883928370855e-06,
|
| 1427 |
+
"loss": 0.8630028963088989,
|
| 1428 |
+
"mean_token_accuracy": 0.7604737058281898,
|
| 1429 |
+
"num_tokens": 3732503.0,
|
| 1430 |
+
"step": 142
|
| 1431 |
+
},
|
| 1432 |
+
{
|
| 1433 |
+
"entropy": 1.1168327778577805,
|
| 1434 |
+
"epoch": 1.7023809523809523,
|
| 1435 |
+
"grad_norm": 0.203125,
|
| 1436 |
+
"learning_rate": 8.018538568006027e-06,
|
| 1437 |
+
"loss": 0.8182620406150818,
|
| 1438 |
+
"mean_token_accuracy": 0.7686956897377968,
|
| 1439 |
+
"num_tokens": 3759558.0,
|
| 1440 |
+
"step": 143
|
| 1441 |
+
},
|
| 1442 |
+
{
|
| 1443 |
+
"entropy": 1.1009707152843475,
|
| 1444 |
+
"epoch": 1.7142857142857144,
|
| 1445 |
+
"grad_norm": 0.2119140625,
|
| 1446 |
+
"learning_rate": 7.896501156545044e-06,
|
| 1447 |
+
"loss": 0.7965549230575562,
|
| 1448 |
+
"mean_token_accuracy": 0.7743760347366333,
|
| 1449 |
+
"num_tokens": 3786872.0,
|
| 1450 |
+
"step": 144
|
| 1451 |
+
},
|
| 1452 |
+
{
|
| 1453 |
+
"entropy": 1.0930486172437668,
|
| 1454 |
+
"epoch": 1.7261904761904763,
|
| 1455 |
+
"grad_norm": 0.22265625,
|
| 1456 |
+
"learning_rate": 7.774790660436857e-06,
|
| 1457 |
+
"loss": 0.7760134935379028,
|
| 1458 |
+
"mean_token_accuracy": 0.784682035446167,
|
| 1459 |
+
"num_tokens": 3812661.0,
|
| 1460 |
+
"step": 145
|
| 1461 |
+
},
|
| 1462 |
+
{
|
| 1463 |
+
"entropy": 1.1450048387050629,
|
| 1464 |
+
"epoch": 1.7380952380952381,
|
| 1465 |
+
"grad_norm": 0.216796875,
|
| 1466 |
+
"learning_rate": 7.653425995322852e-06,
|
| 1467 |
+
"loss": 0.8734183311462402,
|
| 1468 |
+
"mean_token_accuracy": 0.7527253702282906,
|
| 1469 |
+
"num_tokens": 3839385.0,
|
| 1470 |
+
"step": 146
|
| 1471 |
+
},
|
| 1472 |
+
{
|
| 1473 |
+
"entropy": 1.1145509034395218,
|
| 1474 |
+
"epoch": 1.75,
|
| 1475 |
+
"grad_norm": 0.2236328125,
|
| 1476 |
+
"learning_rate": 7.532426023097063e-06,
|
| 1477 |
+
"loss": 0.7770429849624634,
|
| 1478 |
+
"mean_token_accuracy": 0.7795330286026001,
|
| 1479 |
+
"num_tokens": 3864694.0,
|
| 1480 |
+
"step": 147
|
| 1481 |
+
},
|
| 1482 |
+
{
|
| 1483 |
+
"entropy": 1.1127979755401611,
|
| 1484 |
+
"epoch": 1.7619047619047619,
|
| 1485 |
+
"grad_norm": 0.21484375,
|
| 1486 |
+
"learning_rate": 7.411809548974792e-06,
|
| 1487 |
+
"loss": 0.8262644410133362,
|
| 1488 |
+
"mean_token_accuracy": 0.7699695378541946,
|
| 1489 |
+
"num_tokens": 3890836.0,
|
| 1490 |
+
"step": 148
|
| 1491 |
+
},
|
| 1492 |
+
{
|
| 1493 |
+
"entropy": 1.1189321875572205,
|
| 1494 |
+
"epoch": 1.7738095238095237,
|
| 1495 |
+
"grad_norm": 0.2236328125,
|
| 1496 |
+
"learning_rate": 7.291595318569951e-06,
|
| 1497 |
+
"loss": 0.8311002850532532,
|
| 1498 |
+
"mean_token_accuracy": 0.7660280093550682,
|
| 1499 |
+
"num_tokens": 3917364.0,
|
| 1500 |
+
"step": 149
|
| 1501 |
+
},
|
| 1502 |
+
{
|
| 1503 |
+
"entropy": 1.0803979188203812,
|
| 1504 |
+
"epoch": 1.7857142857142856,
|
| 1505 |
+
"grad_norm": 0.21484375,
|
| 1506 |
+
"learning_rate": 7.171802014981726e-06,
|
| 1507 |
+
"loss": 0.7628324627876282,
|
| 1508 |
+
"mean_token_accuracy": 0.7882028222084045,
|
| 1509 |
+
"num_tokens": 3943383.0,
|
| 1510 |
+
"step": 150
|
| 1511 |
+
},
|
| 1512 |
+
{
|
| 1513 |
+
"entropy": 1.1122339814901352,
|
| 1514 |
+
"epoch": 1.7976190476190477,
|
| 1515 |
+
"grad_norm": 0.2197265625,
|
| 1516 |
+
"learning_rate": 7.052448255890958e-06,
|
| 1517 |
+
"loss": 0.8079776167869568,
|
| 1518 |
+
"mean_token_accuracy": 0.7733784541487694,
|
| 1519 |
+
"num_tokens": 3968880.0,
|
| 1520 |
+
"step": 151
|
| 1521 |
+
},
|
| 1522 |
+
{
|
| 1523 |
+
"entropy": 1.1262486726045609,
|
| 1524 |
+
"epoch": 1.8095238095238095,
|
| 1525 |
+
"grad_norm": 0.228515625,
|
| 1526 |
+
"learning_rate": 6.933552590666659e-06,
|
| 1527 |
+
"loss": 0.8450883626937866,
|
| 1528 |
+
"mean_token_accuracy": 0.76470497995615,
|
| 1529 |
+
"num_tokens": 3994252.0,
|
| 1530 |
+
"step": 152
|
| 1531 |
+
},
|
| 1532 |
+
{
|
| 1533 |
+
"entropy": 1.1084678769111633,
|
| 1534 |
+
"epoch": 1.8214285714285714,
|
| 1535 |
+
"grad_norm": 0.2138671875,
|
| 1536 |
+
"learning_rate": 6.815133497483157e-06,
|
| 1537 |
+
"loss": 0.8062177896499634,
|
| 1538 |
+
"mean_token_accuracy": 0.7726119607686996,
|
| 1539 |
+
"num_tokens": 4021377.0,
|
| 1540 |
+
"step": 153
|
| 1541 |
+
},
|
| 1542 |
+
{
|
| 1543 |
+
"entropy": 1.097622349858284,
|
| 1544 |
+
"epoch": 1.8333333333333335,
|
| 1545 |
+
"grad_norm": 0.2265625,
|
| 1546 |
+
"learning_rate": 6.697209380448333e-06,
|
| 1547 |
+
"loss": 0.7983017563819885,
|
| 1548 |
+
"mean_token_accuracy": 0.774423360824585,
|
| 1549 |
+
"num_tokens": 4048074.0,
|
| 1550 |
+
"step": 154
|
| 1551 |
+
},
|
| 1552 |
+
{
|
| 1553 |
+
"entropy": 1.111462488770485,
|
| 1554 |
+
"epoch": 1.8452380952380953,
|
| 1555 |
+
"grad_norm": 0.22265625,
|
| 1556 |
+
"learning_rate": 6.579798566743314e-06,
|
| 1557 |
+
"loss": 0.8211446404457092,
|
| 1558 |
+
"mean_token_accuracy": 0.7687254920601845,
|
| 1559 |
+
"num_tokens": 4074401.0,
|
| 1560 |
+
"step": 155
|
| 1561 |
+
},
|
| 1562 |
+
{
|
| 1563 |
+
"entropy": 1.091482549905777,
|
| 1564 |
+
"epoch": 1.8571428571428572,
|
| 1565 |
+
"grad_norm": 0.2060546875,
|
| 1566 |
+
"learning_rate": 6.462919303774186e-06,
|
| 1567 |
+
"loss": 0.7832185626029968,
|
| 1568 |
+
"mean_token_accuracy": 0.7785474807024002,
|
| 1569 |
+
"num_tokens": 4101171.0,
|
| 1570 |
+
"step": 156
|
| 1571 |
+
},
|
| 1572 |
+
{
|
| 1573 |
+
"entropy": 1.1196855455636978,
|
| 1574 |
+
"epoch": 1.869047619047619,
|
| 1575 |
+
"grad_norm": 0.2216796875,
|
| 1576 |
+
"learning_rate": 6.34658975633605e-06,
|
| 1577 |
+
"loss": 0.8435440063476562,
|
| 1578 |
+
"mean_token_accuracy": 0.7660573944449425,
|
| 1579 |
+
"num_tokens": 4127519.0,
|
| 1580 |
+
"step": 157
|
| 1581 |
+
},
|
| 1582 |
+
{
|
| 1583 |
+
"entropy": 1.090627670288086,
|
| 1584 |
+
"epoch": 1.880952380952381,
|
| 1585 |
+
"grad_norm": 0.2060546875,
|
| 1586 |
+
"learning_rate": 6.230828003789949e-06,
|
| 1587 |
+
"loss": 0.7934207320213318,
|
| 1588 |
+
"mean_token_accuracy": 0.7779519408941269,
|
| 1589 |
+
"num_tokens": 4154910.0,
|
| 1590 |
+
"step": 158
|
| 1591 |
+
},
|
| 1592 |
+
{
|
| 1593 |
+
"entropy": 1.130862444639206,
|
| 1594 |
+
"epoch": 1.8928571428571428,
|
| 1595 |
+
"grad_norm": 0.2255859375,
|
| 1596 |
+
"learning_rate": 6.115652037253054e-06,
|
| 1597 |
+
"loss": 0.8495190739631653,
|
| 1598 |
+
"mean_token_accuracy": 0.7622320130467415,
|
| 1599 |
+
"num_tokens": 4180994.0,
|
| 1600 |
+
"step": 159
|
| 1601 |
+
},
|
| 1602 |
+
{
|
| 1603 |
+
"entropy": 1.10136216878891,
|
| 1604 |
+
"epoch": 1.9047619047619047,
|
| 1605 |
+
"grad_norm": 0.2138671875,
|
| 1606 |
+
"learning_rate": 6.001079756802592e-06,
|
| 1607 |
+
"loss": 0.7951112389564514,
|
| 1608 |
+
"mean_token_accuracy": 0.7760354280471802,
|
| 1609 |
+
"num_tokens": 4206873.0,
|
| 1610 |
+
"step": 160
|
| 1611 |
+
},
|
| 1612 |
+
{
|
| 1613 |
+
"entropy": 1.0941227227449417,
|
| 1614 |
+
"epoch": 1.9166666666666665,
|
| 1615 |
+
"grad_norm": 0.2158203125,
|
| 1616 |
+
"learning_rate": 5.887128968693887e-06,
|
| 1617 |
+
"loss": 0.7749046087265015,
|
| 1618 |
+
"mean_token_accuracy": 0.7782920673489571,
|
| 1619 |
+
"num_tokens": 4232763.0,
|
| 1620 |
+
"step": 161
|
| 1621 |
+
},
|
| 1622 |
+
{
|
| 1623 |
+
"entropy": 1.0888655632734299,
|
| 1624 |
+
"epoch": 1.9285714285714286,
|
| 1625 |
+
"grad_norm": 0.21484375,
|
| 1626 |
+
"learning_rate": 5.773817382593008e-06,
|
| 1627 |
+
"loss": 0.8022912740707397,
|
| 1628 |
+
"mean_token_accuracy": 0.772666685283184,
|
| 1629 |
+
"num_tokens": 4258969.0,
|
| 1630 |
+
"step": 162
|
| 1631 |
+
},
|
| 1632 |
+
{
|
| 1633 |
+
"entropy": 1.1020135283470154,
|
| 1634 |
+
"epoch": 1.9404761904761905,
|
| 1635 |
+
"grad_norm": 0.21484375,
|
| 1636 |
+
"learning_rate": 5.66116260882442e-06,
|
| 1637 |
+
"loss": 0.8075801134109497,
|
| 1638 |
+
"mean_token_accuracy": 0.7722523957490921,
|
| 1639 |
+
"num_tokens": 4285853.0,
|
| 1640 |
+
"step": 163
|
| 1641 |
+
},
|
| 1642 |
+
{
|
| 1643 |
+
"entropy": 1.1252782344818115,
|
| 1644 |
+
"epoch": 1.9523809523809523,
|
| 1645 |
+
"grad_norm": 0.2333984375,
|
| 1646 |
+
"learning_rate": 5.549182155634076e-06,
|
| 1647 |
+
"loss": 0.8001527190208435,
|
| 1648 |
+
"mean_token_accuracy": 0.7735483199357986,
|
| 1649 |
+
"num_tokens": 4310282.0,
|
| 1650 |
+
"step": 164
|
| 1651 |
+
},
|
| 1652 |
+
{
|
| 1653 |
+
"entropy": 1.110137328505516,
|
| 1654 |
+
"epoch": 1.9642857142857144,
|
| 1655 |
+
"grad_norm": 0.2080078125,
|
| 1656 |
+
"learning_rate": 5.43789342646837e-06,
|
| 1657 |
+
"loss": 0.8033909797668457,
|
| 1658 |
+
"mean_token_accuracy": 0.7731057927012444,
|
| 1659 |
+
"num_tokens": 4336076.0,
|
| 1660 |
+
"step": 165
|
| 1661 |
+
},
|
| 1662 |
+
{
|
| 1663 |
+
"entropy": 1.1079717725515366,
|
| 1664 |
+
"epoch": 1.9761904761904763,
|
| 1665 |
+
"grad_norm": 0.2197265625,
|
| 1666 |
+
"learning_rate": 5.32731371726938e-06,
|
| 1667 |
+
"loss": 0.7891072034835815,
|
| 1668 |
+
"mean_token_accuracy": 0.7758950665593147,
|
| 1669 |
+
"num_tokens": 4361690.0,
|
| 1670 |
+
"step": 166
|
| 1671 |
+
},
|
| 1672 |
+
{
|
| 1673 |
+
"entropy": 1.111808881163597,
|
| 1674 |
+
"epoch": 1.9880952380952381,
|
| 1675 |
+
"grad_norm": 0.2177734375,
|
| 1676 |
+
"learning_rate": 5.217460213786822e-06,
|
| 1677 |
+
"loss": 0.8317010402679443,
|
| 1678 |
+
"mean_token_accuracy": 0.7686774134635925,
|
| 1679 |
+
"num_tokens": 4388453.0,
|
| 1680 |
+
"step": 167
|
| 1681 |
+
},
|
| 1682 |
+
{
|
| 1683 |
+
"entropy": 1.0940789729356766,
|
| 1684 |
+
"epoch": 2.0,
|
| 1685 |
+
"grad_norm": 0.2197265625,
|
| 1686 |
+
"learning_rate": 5.108349988907111e-06,
|
| 1687 |
+
"loss": 0.7986106872558594,
|
| 1688 |
+
"mean_token_accuracy": 0.7781749367713928,
|
| 1689 |
+
"num_tokens": 4413704.0,
|
| 1690 |
+
"step": 168
|
| 1691 |
+
},
|
| 1692 |
+
{
|
| 1693 |
+
"entropy": 1.1143835335969925,
|
| 1694 |
+
"epoch": 2.011904761904762,
|
| 1695 |
+
"grad_norm": 0.21875,
|
| 1696 |
+
"learning_rate": 5.000000000000003e-06,
|
| 1697 |
+
"loss": 0.800915539264679,
|
| 1698 |
+
"mean_token_accuracy": 0.7711915224790573,
|
| 1699 |
+
"num_tokens": 4440194.0,
|
| 1700 |
+
"step": 169
|
| 1701 |
+
},
|
| 1702 |
+
{
|
| 1703 |
+
"entropy": 1.0910003781318665,
|
| 1704 |
+
"epoch": 2.0238095238095237,
|
| 1705 |
+
"grad_norm": 0.2080078125,
|
| 1706 |
+
"learning_rate": 4.892427086283147e-06,
|
| 1707 |
+
"loss": 0.7806589603424072,
|
| 1708 |
+
"mean_token_accuracy": 0.7765552401542664,
|
| 1709 |
+
"num_tokens": 4466934.0,
|
| 1710 |
+
"step": 170
|
| 1711 |
+
},
|
| 1712 |
+
{
|
| 1713 |
+
"entropy": 1.1028515249490738,
|
| 1714 |
+
"epoch": 2.0357142857142856,
|
| 1715 |
+
"grad_norm": 0.2119140625,
|
| 1716 |
+
"learning_rate": 4.78564796620502e-06,
|
| 1717 |
+
"loss": 0.7799363136291504,
|
| 1718 |
+
"mean_token_accuracy": 0.7761322408914566,
|
| 1719 |
+
"num_tokens": 4493010.0,
|
| 1720 |
+
"step": 171
|
| 1721 |
+
},
|
| 1722 |
+
{
|
| 1723 |
+
"entropy": 1.1085332185029984,
|
| 1724 |
+
"epoch": 2.0476190476190474,
|
| 1725 |
+
"grad_norm": 0.2119140625,
|
| 1726 |
+
"learning_rate": 4.679679234846636e-06,
|
| 1727 |
+
"loss": 0.7984216213226318,
|
| 1728 |
+
"mean_token_accuracy": 0.7793152034282684,
|
| 1729 |
+
"num_tokens": 4518942.0,
|
| 1730 |
+
"step": 172
|
| 1731 |
+
},
|
| 1732 |
+
{
|
| 1733 |
+
"entropy": 1.124870389699936,
|
| 1734 |
+
"epoch": 2.0595238095238093,
|
| 1735 |
+
"grad_norm": 0.2373046875,
|
| 1736 |
+
"learning_rate": 4.5745373613424075e-06,
|
| 1737 |
+
"loss": 0.7885993719100952,
|
| 1738 |
+
"mean_token_accuracy": 0.7786193862557411,
|
| 1739 |
+
"num_tokens": 4543683.0,
|
| 1740 |
+
"step": 173
|
| 1741 |
+
},
|
| 1742 |
+
{
|
| 1743 |
+
"entropy": 1.1041023209691048,
|
| 1744 |
+
"epoch": 2.0714285714285716,
|
| 1745 |
+
"grad_norm": 0.224609375,
|
| 1746 |
+
"learning_rate": 4.470238686320606e-06,
|
| 1747 |
+
"loss": 0.8044976592063904,
|
| 1748 |
+
"mean_token_accuracy": 0.7772313058376312,
|
| 1749 |
+
"num_tokens": 4569451.0,
|
| 1750 |
+
"step": 174
|
| 1751 |
+
},
|
| 1752 |
+
{
|
| 1753 |
+
"entropy": 1.109834685921669,
|
| 1754 |
+
"epoch": 2.0833333333333335,
|
| 1755 |
+
"grad_norm": 0.2275390625,
|
| 1756 |
+
"learning_rate": 4.3667994193637794e-06,
|
| 1757 |
+
"loss": 0.802185595035553,
|
| 1758 |
+
"mean_token_accuracy": 0.7703160792589188,
|
| 1759 |
+
"num_tokens": 4595980.0,
|
| 1760 |
+
"step": 175
|
| 1761 |
+
},
|
| 1762 |
+
{
|
| 1763 |
+
"entropy": 1.1169404536485672,
|
| 1764 |
+
"epoch": 2.0952380952380953,
|
| 1765 |
+
"grad_norm": 0.2734375,
|
| 1766 |
+
"learning_rate": 4.264235636489542e-06,
|
| 1767 |
+
"loss": 0.8406084775924683,
|
| 1768 |
+
"mean_token_accuracy": 0.7628436088562012,
|
| 1769 |
+
"num_tokens": 4623082.0,
|
| 1770 |
+
"step": 176
|
| 1771 |
+
},
|
| 1772 |
+
{
|
| 1773 |
+
"entropy": 1.0920062735676765,
|
| 1774 |
+
"epoch": 2.107142857142857,
|
| 1775 |
+
"grad_norm": 0.2109375,
|
| 1776 |
+
"learning_rate": 4.162563277652104e-06,
|
| 1777 |
+
"loss": 0.807350754737854,
|
| 1778 |
+
"mean_token_accuracy": 0.7676851376891136,
|
| 1779 |
+
"num_tokens": 4651364.0,
|
| 1780 |
+
"step": 177
|
| 1781 |
+
},
|
| 1782 |
+
{
|
| 1783 |
+
"entropy": 1.0805025100708008,
|
| 1784 |
+
"epoch": 2.119047619047619,
|
| 1785 |
+
"grad_norm": 0.20703125,
|
| 1786 |
+
"learning_rate": 4.061798144264986e-06,
|
| 1787 |
+
"loss": 0.7802121043205261,
|
| 1788 |
+
"mean_token_accuracy": 0.7830931693315506,
|
| 1789 |
+
"num_tokens": 4678114.0,
|
| 1790 |
+
"step": 178
|
| 1791 |
+
},
|
| 1792 |
+
{
|
| 1793 |
+
"entropy": 1.1019368171691895,
|
| 1794 |
+
"epoch": 2.130952380952381,
|
| 1795 |
+
"grad_norm": 0.2080078125,
|
| 1796 |
+
"learning_rate": 3.961955896745224e-06,
|
| 1797 |
+
"loss": 0.8179029226303101,
|
| 1798 |
+
"mean_token_accuracy": 0.7715626880526543,
|
| 1799 |
+
"num_tokens": 4704903.0,
|
| 1800 |
+
"step": 179
|
| 1801 |
+
},
|
| 1802 |
+
{
|
| 1803 |
+
"entropy": 1.1142058372497559,
|
| 1804 |
+
"epoch": 2.142857142857143,
|
| 1805 |
+
"grad_norm": 0.2138671875,
|
| 1806 |
+
"learning_rate": 3.8630520520795275e-06,
|
| 1807 |
+
"loss": 0.820464015007019,
|
| 1808 |
+
"mean_token_accuracy": 0.767073430120945,
|
| 1809 |
+
"num_tokens": 4730882.0,
|
| 1810 |
+
"step": 180
|
| 1811 |
+
},
|
| 1812 |
+
{
|
| 1813 |
+
"entropy": 1.0781855285167694,
|
| 1814 |
+
"epoch": 2.1547619047619047,
|
| 1815 |
+
"grad_norm": 0.2177734375,
|
| 1816 |
+
"learning_rate": 3.7651019814126656e-06,
|
| 1817 |
+
"loss": 0.7623270153999329,
|
| 1818 |
+
"mean_token_accuracy": 0.7844816967844963,
|
| 1819 |
+
"num_tokens": 4756693.0,
|
| 1820 |
+
"step": 181
|
| 1821 |
+
},
|
| 1822 |
+
{
|
| 1823 |
+
"entropy": 1.0938004553318024,
|
| 1824 |
+
"epoch": 2.1666666666666665,
|
| 1825 |
+
"grad_norm": 0.205078125,
|
| 1826 |
+
"learning_rate": 3.6681209076586035e-06,
|
| 1827 |
+
"loss": 0.780868649482727,
|
| 1828 |
+
"mean_token_accuracy": 0.7797767668962479,
|
| 1829 |
+
"num_tokens": 4783150.0,
|
| 1830 |
+
"step": 182
|
| 1831 |
+
},
|
| 1832 |
+
{
|
| 1833 |
+
"entropy": 1.1012120842933655,
|
| 1834 |
+
"epoch": 2.1785714285714284,
|
| 1835 |
+
"grad_norm": 0.2041015625,
|
| 1836 |
+
"learning_rate": 3.5721239031346067e-06,
|
| 1837 |
+
"loss": 0.8160427212715149,
|
| 1838 |
+
"mean_token_accuracy": 0.7717493698000908,
|
| 1839 |
+
"num_tokens": 4809980.0,
|
| 1840 |
+
"step": 183
|
| 1841 |
+
},
|
| 1842 |
+
{
|
| 1843 |
+
"entropy": 1.1437917947769165,
|
| 1844 |
+
"epoch": 2.1904761904761907,
|
| 1845 |
+
"grad_norm": 0.23046875,
|
| 1846 |
+
"learning_rate": 3.4771258872187917e-06,
|
| 1847 |
+
"loss": 0.8643677830696106,
|
| 1848 |
+
"mean_token_accuracy": 0.7510505765676498,
|
| 1849 |
+
"num_tokens": 4834990.0,
|
| 1850 |
+
"step": 184
|
| 1851 |
+
},
|
| 1852 |
+
{
|
| 1853 |
+
"entropy": 1.1224986612796783,
|
| 1854 |
+
"epoch": 2.2023809523809526,
|
| 1855 |
+
"grad_norm": 0.236328125,
|
| 1856 |
+
"learning_rate": 3.3831416240314085e-06,
|
| 1857 |
+
"loss": 0.8391753435134888,
|
| 1858 |
+
"mean_token_accuracy": 0.7646627351641655,
|
| 1859 |
+
"num_tokens": 4860271.0,
|
| 1860 |
+
"step": 185
|
| 1861 |
+
},
|
| 1862 |
+
{
|
| 1863 |
+
"entropy": 1.1111707538366318,
|
| 1864 |
+
"epoch": 2.2142857142857144,
|
| 1865 |
+
"grad_norm": 0.2119140625,
|
| 1866 |
+
"learning_rate": 3.290185720140301e-06,
|
| 1867 |
+
"loss": 0.8266609311103821,
|
| 1868 |
+
"mean_token_accuracy": 0.7683383226394653,
|
| 1869 |
+
"num_tokens": 4887403.0,
|
| 1870 |
+
"step": 186
|
| 1871 |
+
},
|
| 1872 |
+
{
|
| 1873 |
+
"entropy": 1.0867665261030197,
|
| 1874 |
+
"epoch": 2.2261904761904763,
|
| 1875 |
+
"grad_norm": 0.2119140625,
|
| 1876 |
+
"learning_rate": 3.1982726222908046e-06,
|
| 1877 |
+
"loss": 0.7631702423095703,
|
| 1878 |
+
"mean_token_accuracy": 0.7865067571401596,
|
| 1879 |
+
"num_tokens": 4913478.0,
|
| 1880 |
+
"step": 187
|
| 1881 |
+
},
|
| 1882 |
+
{
|
| 1883 |
+
"entropy": 1.107857659459114,
|
| 1884 |
+
"epoch": 2.238095238095238,
|
| 1885 |
+
"grad_norm": 0.212890625,
|
| 1886 |
+
"learning_rate": 3.10741661516053e-06,
|
| 1887 |
+
"loss": 0.8279802799224854,
|
| 1888 |
+
"mean_token_accuracy": 0.7636834606528282,
|
| 1889 |
+
"num_tokens": 4940367.0,
|
| 1890 |
+
"step": 188
|
| 1891 |
+
},
|
| 1892 |
+
{
|
| 1893 |
+
"entropy": 1.0950567573308945,
|
| 1894 |
+
"epoch": 2.25,
|
| 1895 |
+
"grad_norm": 0.21484375,
|
| 1896 |
+
"learning_rate": 3.017631819139273e-06,
|
| 1897 |
+
"loss": 0.7990702986717224,
|
| 1898 |
+
"mean_token_accuracy": 0.775329478085041,
|
| 1899 |
+
"num_tokens": 4966500.0,
|
| 1900 |
+
"step": 189
|
| 1901 |
+
},
|
| 1902 |
+
{
|
| 1903 |
+
"entropy": 1.1100285053253174,
|
| 1904 |
+
"epoch": 2.261904761904762,
|
| 1905 |
+
"grad_norm": 0.220703125,
|
| 1906 |
+
"learning_rate": 2.9289321881345257e-06,
|
| 1907 |
+
"loss": 0.7843649387359619,
|
| 1908 |
+
"mean_token_accuracy": 0.7755291163921356,
|
| 1909 |
+
"num_tokens": 4992143.0,
|
| 1910 |
+
"step": 190
|
| 1911 |
+
},
|
| 1912 |
+
{
|
| 1913 |
+
"entropy": 1.090055227279663,
|
| 1914 |
+
"epoch": 2.2738095238095237,
|
| 1915 |
+
"grad_norm": 0.212890625,
|
| 1916 |
+
"learning_rate": 2.8413315074028157e-06,
|
| 1917 |
+
"loss": 0.7791961431503296,
|
| 1918 |
+
"mean_token_accuracy": 0.7800277844071388,
|
| 1919 |
+
"num_tokens": 5018477.0,
|
| 1920 |
+
"step": 191
|
| 1921 |
+
},
|
| 1922 |
+
{
|
| 1923 |
+
"entropy": 1.0741526409983635,
|
| 1924 |
+
"epoch": 2.2857142857142856,
|
| 1925 |
+
"grad_norm": 0.21484375,
|
| 1926 |
+
"learning_rate": 2.7548433914072736e-06,
|
| 1927 |
+
"loss": 0.7515400052070618,
|
| 1928 |
+
"mean_token_accuracy": 0.785953663289547,
|
| 1929 |
+
"num_tokens": 5044293.0,
|
| 1930 |
+
"step": 192
|
| 1931 |
+
},
|
| 1932 |
+
{
|
| 1933 |
+
"entropy": 1.08182904869318,
|
| 1934 |
+
"epoch": 2.2976190476190474,
|
| 1935 |
+
"grad_norm": 0.203125,
|
| 1936 |
+
"learning_rate": 2.669481281701739e-06,
|
| 1937 |
+
"loss": 0.7701444625854492,
|
| 1938 |
+
"mean_token_accuracy": 0.7801418378949165,
|
| 1939 |
+
"num_tokens": 5071488.0,
|
| 1940 |
+
"step": 193
|
| 1941 |
+
},
|
| 1942 |
+
{
|
| 1943 |
+
"entropy": 1.1468330323696136,
|
| 1944 |
+
"epoch": 2.3095238095238093,
|
| 1945 |
+
"grad_norm": 0.2265625,
|
| 1946 |
+
"learning_rate": 2.5852584448417327e-06,
|
| 1947 |
+
"loss": 0.8802750110626221,
|
| 1948 |
+
"mean_token_accuracy": 0.756720781326294,
|
| 1949 |
+
"num_tokens": 5097447.0,
|
| 1950 |
+
"step": 194
|
| 1951 |
+
},
|
| 1952 |
+
{
|
| 1953 |
+
"entropy": 1.0781276375055313,
|
| 1954 |
+
"epoch": 2.3214285714285716,
|
| 1955 |
+
"grad_norm": 0.205078125,
|
| 1956 |
+
"learning_rate": 2.502187970322657e-06,
|
| 1957 |
+
"loss": 0.768257200717926,
|
| 1958 |
+
"mean_token_accuracy": 0.7819816321134567,
|
| 1959 |
+
"num_tokens": 5124041.0,
|
| 1960 |
+
"step": 195
|
| 1961 |
+
},
|
| 1962 |
+
{
|
| 1963 |
+
"entropy": 1.0870239287614822,
|
| 1964 |
+
"epoch": 2.3333333333333335,
|
| 1965 |
+
"grad_norm": 0.2109375,
|
| 1966 |
+
"learning_rate": 2.420282768545469e-06,
|
| 1967 |
+
"loss": 0.8156233429908752,
|
| 1968 |
+
"mean_token_accuracy": 0.7710027247667313,
|
| 1969 |
+
"num_tokens": 5151020.0,
|
| 1970 |
+
"step": 196
|
| 1971 |
+
},
|
| 1972 |
+
{
|
| 1973 |
+
"entropy": 1.1158137768507004,
|
| 1974 |
+
"epoch": 2.3452380952380953,
|
| 1975 |
+
"grad_norm": 0.22265625,
|
| 1976 |
+
"learning_rate": 2.339555568810221e-06,
|
| 1977 |
+
"loss": 0.8283431529998779,
|
| 1978 |
+
"mean_token_accuracy": 0.7646451517939568,
|
| 1979 |
+
"num_tokens": 5177398.0,
|
| 1980 |
+
"step": 197
|
| 1981 |
+
},
|
| 1982 |
+
{
|
| 1983 |
+
"entropy": 1.104174643754959,
|
| 1984 |
+
"epoch": 2.357142857142857,
|
| 1985 |
+
"grad_norm": 0.2177734375,
|
| 1986 |
+
"learning_rate": 2.2600189173377263e-06,
|
| 1987 |
+
"loss": 0.8111021518707275,
|
| 1988 |
+
"mean_token_accuracy": 0.7714014053344727,
|
| 1989 |
+
"num_tokens": 5203526.0,
|
| 1990 |
+
"step": 198
|
| 1991 |
+
},
|
| 1992 |
+
{
|
| 1993 |
+
"entropy": 1.0948980003595352,
|
| 1994 |
+
"epoch": 2.369047619047619,
|
| 1995 |
+
"grad_norm": 0.208984375,
|
| 1996 |
+
"learning_rate": 2.1816851753197023e-06,
|
| 1997 |
+
"loss": 0.7999440431594849,
|
| 1998 |
+
"mean_token_accuracy": 0.7765351012349129,
|
| 1999 |
+
"num_tokens": 5229649.0,
|
| 2000 |
+
"step": 199
|
| 2001 |
+
},
|
| 2002 |
+
{
|
| 2003 |
+
"entropy": 1.1040179580450058,
|
| 2004 |
+
"epoch": 2.380952380952381,
|
| 2005 |
+
"grad_norm": 0.2216796875,
|
| 2006 |
+
"learning_rate": 2.104566516997647e-06,
|
| 2007 |
+
"loss": 0.7910847067832947,
|
| 2008 |
+
"mean_token_accuracy": 0.7759528011083603,
|
| 2009 |
+
"num_tokens": 5255150.0,
|
| 2010 |
+
"step": 200
|
| 2011 |
+
},
|
| 2012 |
+
{
|
| 2013 |
+
"epoch": 2.380952380952381,
|
| 2014 |
+
"eval_entropy": 1.1016432423340647,
|
| 2015 |
+
"eval_loss": 0.850182056427002,
|
| 2016 |
+
"eval_mean_token_accuracy": 0.7646622657775879,
|
| 2017 |
+
"eval_num_tokens": 5255150.0,
|
| 2018 |
+
"eval_runtime": 20.7435,
|
| 2019 |
+
"eval_samples_per_second": 7.231,
|
| 2020 |
+
"eval_steps_per_second": 0.916,
|
| 2021 |
+
"step": 200
|
| 2022 |
+
},
|
| 2023 |
+
{
|
| 2024 |
+
"entropy": 1.1015710830688477,
|
| 2025 |
+
"epoch": 2.392857142857143,
|
| 2026 |
+
"grad_norm": 0.2177734375,
|
| 2027 |
+
"learning_rate": 2.0286749277707783e-06,
|
| 2028 |
+
"loss": 0.7965137958526611,
|
| 2029 |
+
"mean_token_accuracy": 0.775518424808979,
|
| 2030 |
+
"num_tokens": 5280462.0,
|
| 2031 |
+
"step": 201
|
| 2032 |
+
},
|
| 2033 |
+
{
|
| 2034 |
+
"entropy": 1.073985680937767,
|
| 2035 |
+
"epoch": 2.4047619047619047,
|
| 2036 |
+
"grad_norm": 0.21484375,
|
| 2037 |
+
"learning_rate": 1.9540222023333165e-06,
|
| 2038 |
+
"loss": 0.7600584030151367,
|
| 2039 |
+
"mean_token_accuracy": 0.7819822654128075,
|
| 2040 |
+
"num_tokens": 5307159.0,
|
| 2041 |
+
"step": 202
|
| 2042 |
+
},
|
| 2043 |
+
{
|
| 2044 |
+
"entropy": 1.1074542552232742,
|
| 2045 |
+
"epoch": 2.4166666666666665,
|
| 2046 |
+
"grad_norm": 0.220703125,
|
| 2047 |
+
"learning_rate": 1.880619942841435e-06,
|
| 2048 |
+
"loss": 0.8110378980636597,
|
| 2049 |
+
"mean_token_accuracy": 0.7697334587574005,
|
| 2050 |
+
"num_tokens": 5333284.0,
|
| 2051 |
+
"step": 203
|
| 2052 |
+
},
|
| 2053 |
+
{
|
| 2054 |
+
"entropy": 1.0784734338521957,
|
| 2055 |
+
"epoch": 2.4285714285714284,
|
| 2056 |
+
"grad_norm": 0.20703125,
|
| 2057 |
+
"learning_rate": 1.808479557110081e-06,
|
| 2058 |
+
"loss": 0.7567155361175537,
|
| 2059 |
+
"mean_token_accuracy": 0.7863621711730957,
|
| 2060 |
+
"num_tokens": 5359494.0,
|
| 2061 |
+
"step": 204
|
| 2062 |
+
},
|
| 2063 |
+
{
|
| 2064 |
+
"entropy": 1.1178395748138428,
|
| 2065 |
+
"epoch": 2.4404761904761907,
|
| 2066 |
+
"grad_norm": 0.2255859375,
|
| 2067 |
+
"learning_rate": 1.7376122568400533e-06,
|
| 2068 |
+
"loss": 0.8341485857963562,
|
| 2069 |
+
"mean_token_accuracy": 0.7668850645422935,
|
| 2070 |
+
"num_tokens": 5385894.0,
|
| 2071 |
+
"step": 205
|
| 2072 |
+
},
|
| 2073 |
+
{
|
| 2074 |
+
"entropy": 1.0967416018247604,
|
| 2075 |
+
"epoch": 2.4523809523809526,
|
| 2076 |
+
"grad_norm": 0.2177734375,
|
| 2077 |
+
"learning_rate": 1.6680290558755119e-06,
|
| 2078 |
+
"loss": 0.7977155447006226,
|
| 2079 |
+
"mean_token_accuracy": 0.7702686116099358,
|
| 2080 |
+
"num_tokens": 5411830.0,
|
| 2081 |
+
"step": 206
|
| 2082 |
+
},
|
| 2083 |
+
{
|
| 2084 |
+
"entropy": 1.1018935441970825,
|
| 2085 |
+
"epoch": 2.4642857142857144,
|
| 2086 |
+
"grad_norm": 0.2177734375,
|
| 2087 |
+
"learning_rate": 1.599740768492286e-06,
|
| 2088 |
+
"loss": 0.8191432952880859,
|
| 2089 |
+
"mean_token_accuracy": 0.7678048387169838,
|
| 2090 |
+
"num_tokens": 5438295.0,
|
| 2091 |
+
"step": 207
|
| 2092 |
+
},
|
| 2093 |
+
{
|
| 2094 |
+
"entropy": 1.0825640261173248,
|
| 2095 |
+
"epoch": 2.4761904761904763,
|
| 2096 |
+
"grad_norm": 0.216796875,
|
| 2097 |
+
"learning_rate": 1.5327580077171589e-06,
|
| 2098 |
+
"loss": 0.789887011051178,
|
| 2099 |
+
"mean_token_accuracy": 0.7770953327417374,
|
| 2100 |
+
"num_tokens": 5464705.0,
|
| 2101 |
+
"step": 208
|
| 2102 |
+
},
|
| 2103 |
+
{
|
| 2104 |
+
"entropy": 1.1018773317337036,
|
| 2105 |
+
"epoch": 2.488095238095238,
|
| 2106 |
+
"grad_norm": 0.216796875,
|
| 2107 |
+
"learning_rate": 1.467091183678444e-06,
|
| 2108 |
+
"loss": 0.7919491529464722,
|
| 2109 |
+
"mean_token_accuracy": 0.7767357230186462,
|
| 2110 |
+
"num_tokens": 5490516.0,
|
| 2111 |
+
"step": 209
|
| 2112 |
+
},
|
| 2113 |
+
{
|
| 2114 |
+
"entropy": 1.1184441447257996,
|
| 2115 |
+
"epoch": 2.5,
|
| 2116 |
+
"grad_norm": 0.22265625,
|
| 2117 |
+
"learning_rate": 1.4027505019880972e-06,
|
| 2118 |
+
"loss": 0.8499428033828735,
|
| 2119 |
+
"mean_token_accuracy": 0.7632577866315842,
|
| 2120 |
+
"num_tokens": 5516680.0,
|
| 2121 |
+
"step": 210
|
| 2122 |
+
},
|
| 2123 |
+
{
|
| 2124 |
+
"entropy": 1.0862347781658173,
|
| 2125 |
+
"epoch": 2.511904761904762,
|
| 2126 |
+
"grad_norm": 0.2041015625,
|
| 2127 |
+
"learning_rate": 1.339745962155613e-06,
|
| 2128 |
+
"loss": 0.7583701610565186,
|
| 2129 |
+
"mean_token_accuracy": 0.7843123078346252,
|
| 2130 |
+
"num_tokens": 5542288.0,
|
| 2131 |
+
"step": 211
|
| 2132 |
+
},
|
| 2133 |
+
{
|
| 2134 |
+
"entropy": 1.097862184047699,
|
| 2135 |
+
"epoch": 2.5238095238095237,
|
| 2136 |
+
"grad_norm": 0.208984375,
|
| 2137 |
+
"learning_rate": 1.278087356033947e-06,
|
| 2138 |
+
"loss": 0.783574104309082,
|
| 2139 |
+
"mean_token_accuracy": 0.7759824991226196,
|
| 2140 |
+
"num_tokens": 5568234.0,
|
| 2141 |
+
"step": 212
|
| 2142 |
+
},
|
| 2143 |
+
{
|
| 2144 |
+
"entropy": 1.0988486558198929,
|
| 2145 |
+
"epoch": 2.5357142857142856,
|
| 2146 |
+
"grad_norm": 0.2177734375,
|
| 2147 |
+
"learning_rate": 1.2177842662977136e-06,
|
| 2148 |
+
"loss": 0.7944028973579407,
|
| 2149 |
+
"mean_token_accuracy": 0.7767082825303078,
|
| 2150 |
+
"num_tokens": 5594208.0,
|
| 2151 |
+
"step": 213
|
| 2152 |
+
},
|
| 2153 |
+
{
|
| 2154 |
+
"entropy": 1.0893902629613876,
|
| 2155 |
+
"epoch": 2.5476190476190474,
|
| 2156 |
+
"grad_norm": 0.208984375,
|
| 2157 |
+
"learning_rate": 1.1588460649539036e-06,
|
| 2158 |
+
"loss": 0.7720337510108948,
|
| 2159 |
+
"mean_token_accuracy": 0.7832249104976654,
|
| 2160 |
+
"num_tokens": 5620184.0,
|
| 2161 |
+
"step": 214
|
| 2162 |
+
},
|
| 2163 |
+
{
|
| 2164 |
+
"entropy": 1.1016841530799866,
|
| 2165 |
+
"epoch": 2.5595238095238093,
|
| 2166 |
+
"grad_norm": 0.220703125,
|
| 2167 |
+
"learning_rate": 1.1012819118853147e-06,
|
| 2168 |
+
"loss": 0.7969903945922852,
|
| 2169 |
+
"mean_token_accuracy": 0.7736426144838333,
|
| 2170 |
+
"num_tokens": 5646695.0,
|
| 2171 |
+
"step": 215
|
| 2172 |
+
},
|
| 2173 |
+
{
|
| 2174 |
+
"entropy": 1.0920927673578262,
|
| 2175 |
+
"epoch": 2.571428571428571,
|
| 2176 |
+
"grad_norm": 0.2119140625,
|
| 2177 |
+
"learning_rate": 1.0451007534269908e-06,
|
| 2178 |
+
"loss": 0.7718170285224915,
|
| 2179 |
+
"mean_token_accuracy": 0.7819743752479553,
|
| 2180 |
+
"num_tokens": 5672524.0,
|
| 2181 |
+
"step": 216
|
| 2182 |
+
},
|
| 2183 |
+
{
|
| 2184 |
+
"entropy": 1.107266440987587,
|
| 2185 |
+
"epoch": 2.5833333333333335,
|
| 2186 |
+
"grad_norm": 0.224609375,
|
| 2187 |
+
"learning_rate": 9.903113209758098e-07,
|
| 2188 |
+
"loss": 0.8304149508476257,
|
| 2189 |
+
"mean_token_accuracy": 0.7672121822834015,
|
| 2190 |
+
"num_tokens": 5699060.0,
|
| 2191 |
+
"step": 217
|
| 2192 |
+
},
|
| 2193 |
+
{
|
| 2194 |
+
"entropy": 1.0764499753713608,
|
| 2195 |
+
"epoch": 2.5952380952380953,
|
| 2196 |
+
"grad_norm": 0.212890625,
|
| 2197 |
+
"learning_rate": 9.369221296335007e-07,
|
| 2198 |
+
"loss": 0.7635530829429626,
|
| 2199 |
+
"mean_token_accuracy": 0.7877878844738007,
|
| 2200 |
+
"num_tokens": 5725051.0,
|
| 2201 |
+
"step": 218
|
| 2202 |
+
},
|
| 2203 |
+
{
|
| 2204 |
+
"entropy": 1.0995107293128967,
|
| 2205 |
+
"epoch": 2.607142857142857,
|
| 2206 |
+
"grad_norm": 0.216796875,
|
| 2207 |
+
"learning_rate": 8.849414768832687e-07,
|
| 2208 |
+
"loss": 0.8118206858634949,
|
| 2209 |
+
"mean_token_accuracy": 0.7716490253806114,
|
| 2210 |
+
"num_tokens": 5752373.0,
|
| 2211 |
+
"step": 219
|
| 2212 |
+
},
|
| 2213 |
+
{
|
| 2214 |
+
"entropy": 1.0860945731401443,
|
| 2215 |
+
"epoch": 2.619047619047619,
|
| 2216 |
+
"grad_norm": 0.2099609375,
|
| 2217 |
+
"learning_rate": 8.343774413002382e-07,
|
| 2218 |
+
"loss": 0.7682137489318848,
|
| 2219 |
+
"mean_token_accuracy": 0.7820399552583694,
|
| 2220 |
+
"num_tokens": 5778613.0,
|
| 2221 |
+
"step": 220
|
| 2222 |
+
},
|
| 2223 |
+
{
|
| 2224 |
+
"entropy": 1.1067247688770294,
|
| 2225 |
+
"epoch": 2.630952380952381,
|
| 2226 |
+
"grad_norm": 0.212890625,
|
| 2227 |
+
"learning_rate": 7.852378812959227e-07,
|
| 2228 |
+
"loss": 0.8284558653831482,
|
| 2229 |
+
"mean_token_accuracy": 0.7689725607633591,
|
| 2230 |
+
"num_tokens": 5805434.0,
|
| 2231 |
+
"step": 221
|
| 2232 |
+
},
|
| 2233 |
+
{
|
| 2234 |
+
"entropy": 1.0849140882492065,
|
| 2235 |
+
"epoch": 2.642857142857143,
|
| 2236 |
+
"grad_norm": 0.205078125,
|
| 2237 |
+
"learning_rate": 7.375304338969135e-07,
|
| 2238 |
+
"loss": 0.7875180840492249,
|
| 2239 |
+
"mean_token_accuracy": 0.7756547182798386,
|
| 2240 |
+
"num_tokens": 5832316.0,
|
| 2241 |
+
"step": 222
|
| 2242 |
+
},
|
| 2243 |
+
{
|
| 2244 |
+
"entropy": 1.115451768040657,
|
| 2245 |
+
"epoch": 2.6547619047619047,
|
| 2246 |
+
"grad_norm": 0.21484375,
|
| 2247 |
+
"learning_rate": 6.912625135579587e-07,
|
| 2248 |
+
"loss": 0.8203433752059937,
|
| 2249 |
+
"mean_token_accuracy": 0.7700524106621742,
|
| 2250 |
+
"num_tokens": 5858167.0,
|
| 2251 |
+
"step": 223
|
| 2252 |
+
},
|
| 2253 |
+
{
|
| 2254 |
+
"entropy": 1.0904614925384521,
|
| 2255 |
+
"epoch": 2.6666666666666665,
|
| 2256 |
+
"grad_norm": 0.224609375,
|
| 2257 |
+
"learning_rate": 6.464413110096601e-07,
|
| 2258 |
+
"loss": 0.7759373188018799,
|
| 2259 |
+
"mean_token_accuracy": 0.7771004885435104,
|
| 2260 |
+
"num_tokens": 5884359.0,
|
| 2261 |
+
"step": 224
|
| 2262 |
+
},
|
| 2263 |
+
{
|
| 2264 |
+
"entropy": 1.0829641073942184,
|
| 2265 |
+
"epoch": 2.678571428571429,
|
| 2266 |
+
"grad_norm": 0.216796875,
|
| 2267 |
+
"learning_rate": 6.030737921409169e-07,
|
| 2268 |
+
"loss": 0.789995014667511,
|
| 2269 |
+
"mean_token_accuracy": 0.7763750106096268,
|
| 2270 |
+
"num_tokens": 5910953.0,
|
| 2271 |
+
"step": 225
|
| 2272 |
+
},
|
| 2273 |
+
{
|
| 2274 |
+
"entropy": 1.100945070385933,
|
| 2275 |
+
"epoch": 2.6904761904761907,
|
| 2276 |
+
"grad_norm": 0.2216796875,
|
| 2277 |
+
"learning_rate": 5.611666969163243e-07,
|
| 2278 |
+
"loss": 0.7801922559738159,
|
| 2279 |
+
"mean_token_accuracy": 0.7809778973460197,
|
| 2280 |
+
"num_tokens": 5936246.0,
|
| 2281 |
+
"step": 226
|
| 2282 |
+
},
|
| 2283 |
+
{
|
| 2284 |
+
"entropy": 1.094831421971321,
|
| 2285 |
+
"epoch": 2.7023809523809526,
|
| 2286 |
+
"grad_norm": 0.2138671875,
|
| 2287 |
+
"learning_rate": 5.207265383286831e-07,
|
| 2288 |
+
"loss": 0.802288830280304,
|
| 2289 |
+
"mean_token_accuracy": 0.7725913003087044,
|
| 2290 |
+
"num_tokens": 5963034.0,
|
| 2291 |
+
"step": 227
|
| 2292 |
+
},
|
| 2293 |
+
{
|
| 2294 |
+
"entropy": 1.1124836802482605,
|
| 2295 |
+
"epoch": 2.7142857142857144,
|
| 2296 |
+
"grad_norm": 0.21875,
|
| 2297 |
+
"learning_rate": 4.817596013867765e-07,
|
| 2298 |
+
"loss": 0.8340546488761902,
|
| 2299 |
+
"mean_token_accuracy": 0.765786811709404,
|
| 2300 |
+
"num_tokens": 5989514.0,
|
| 2301 |
+
"step": 228
|
| 2302 |
+
},
|
| 2303 |
+
{
|
| 2304 |
+
"entropy": 1.1165993362665176,
|
| 2305 |
+
"epoch": 2.7261904761904763,
|
| 2306 |
+
"grad_norm": 0.21484375,
|
| 2307 |
+
"learning_rate": 4.4427194213859216e-07,
|
| 2308 |
+
"loss": 0.8222470283508301,
|
| 2309 |
+
"mean_token_accuracy": 0.7660126239061356,
|
| 2310 |
+
"num_tokens": 6015850.0,
|
| 2311 |
+
"step": 229
|
| 2312 |
+
},
|
| 2313 |
+
{
|
| 2314 |
+
"entropy": 1.1128047853708267,
|
| 2315 |
+
"epoch": 2.738095238095238,
|
| 2316 |
+
"grad_norm": 0.22265625,
|
| 2317 |
+
"learning_rate": 4.082693867301224e-07,
|
| 2318 |
+
"loss": 0.8243576288223267,
|
| 2319 |
+
"mean_token_accuracy": 0.7661043703556061,
|
| 2320 |
+
"num_tokens": 6042209.0,
|
| 2321 |
+
"step": 230
|
| 2322 |
+
},
|
| 2323 |
+
{
|
| 2324 |
+
"entropy": 1.0889495462179184,
|
| 2325 |
+
"epoch": 2.75,
|
| 2326 |
+
"grad_norm": 0.208984375,
|
| 2327 |
+
"learning_rate": 3.7375753049987974e-07,
|
| 2328 |
+
"loss": 0.7938658595085144,
|
| 2329 |
+
"mean_token_accuracy": 0.7809677720069885,
|
| 2330 |
+
"num_tokens": 6069318.0,
|
| 2331 |
+
"step": 231
|
| 2332 |
+
},
|
| 2333 |
+
{
|
| 2334 |
+
"entropy": 1.1063835173845291,
|
| 2335 |
+
"epoch": 2.761904761904762,
|
| 2336 |
+
"grad_norm": 0.21484375,
|
| 2337 |
+
"learning_rate": 3.4074173710931804e-07,
|
| 2338 |
+
"loss": 0.8031449317932129,
|
| 2339 |
+
"mean_token_accuracy": 0.7716307789087296,
|
| 2340 |
+
"num_tokens": 6095421.0,
|
| 2341 |
+
"step": 232
|
| 2342 |
+
},
|
| 2343 |
+
{
|
| 2344 |
+
"entropy": 1.0925931185483932,
|
| 2345 |
+
"epoch": 2.7738095238095237,
|
| 2346 |
+
"grad_norm": 0.2265625,
|
| 2347 |
+
"learning_rate": 3.0922713770922155e-07,
|
| 2348 |
+
"loss": 0.7671008110046387,
|
| 2349 |
+
"mean_token_accuracy": 0.7852345705032349,
|
| 2350 |
+
"num_tokens": 6120669.0,
|
| 2351 |
+
"step": 233
|
| 2352 |
+
},
|
| 2353 |
+
{
|
| 2354 |
+
"entropy": 1.0808859765529633,
|
| 2355 |
+
"epoch": 2.7857142857142856,
|
| 2356 |
+
"grad_norm": 0.21484375,
|
| 2357 |
+
"learning_rate": 2.7921863014225504e-07,
|
| 2358 |
+
"loss": 0.7566604614257812,
|
| 2359 |
+
"mean_token_accuracy": 0.7864194139838219,
|
| 2360 |
+
"num_tokens": 6146379.0,
|
| 2361 |
+
"step": 234
|
| 2362 |
+
},
|
| 2363 |
+
{
|
| 2364 |
+
"entropy": 1.1180297583341599,
|
| 2365 |
+
"epoch": 2.7976190476190474,
|
| 2366 |
+
"grad_norm": 0.22265625,
|
| 2367 |
+
"learning_rate": 2.507208781817638e-07,
|
| 2368 |
+
"loss": 0.8459954857826233,
|
| 2369 |
+
"mean_token_accuracy": 0.7657622396945953,
|
| 2370 |
+
"num_tokens": 6172360.0,
|
| 2371 |
+
"step": 235
|
| 2372 |
+
},
|
| 2373 |
+
{
|
| 2374 |
+
"entropy": 1.09176704287529,
|
| 2375 |
+
"epoch": 2.8095238095238093,
|
| 2376 |
+
"grad_norm": 0.205078125,
|
| 2377 |
+
"learning_rate": 2.2373831080695463e-07,
|
| 2378 |
+
"loss": 0.7911088466644287,
|
| 2379 |
+
"mean_token_accuracy": 0.7778226584196091,
|
| 2380 |
+
"num_tokens": 6199270.0,
|
| 2381 |
+
"step": 236
|
| 2382 |
+
},
|
| 2383 |
+
{
|
| 2384 |
+
"entropy": 1.1062865853309631,
|
| 2385 |
+
"epoch": 2.821428571428571,
|
| 2386 |
+
"grad_norm": 0.2216796875,
|
| 2387 |
+
"learning_rate": 1.9827512151456175e-07,
|
| 2388 |
+
"loss": 0.8155214190483093,
|
| 2389 |
+
"mean_token_accuracy": 0.771714448928833,
|
| 2390 |
+
"num_tokens": 6225009.0,
|
| 2391 |
+
"step": 237
|
| 2392 |
+
},
|
| 2393 |
+
{
|
| 2394 |
+
"entropy": 1.115729421377182,
|
| 2395 |
+
"epoch": 2.8333333333333335,
|
| 2396 |
+
"grad_norm": 0.220703125,
|
| 2397 |
+
"learning_rate": 1.7433526766711727e-07,
|
| 2398 |
+
"loss": 0.8296111226081848,
|
| 2399 |
+
"mean_token_accuracy": 0.7672879844903946,
|
| 2400 |
+
"num_tokens": 6250868.0,
|
| 2401 |
+
"step": 238
|
| 2402 |
+
},
|
| 2403 |
+
{
|
| 2404 |
+
"entropy": 1.0913526266813278,
|
| 2405 |
+
"epoch": 2.8452380952380953,
|
| 2406 |
+
"grad_norm": 0.2109375,
|
| 2407 |
+
"learning_rate": 1.519224698779198e-07,
|
| 2408 |
+
"loss": 0.775915801525116,
|
| 2409 |
+
"mean_token_accuracy": 0.7825674042105675,
|
| 2410 |
+
"num_tokens": 6276930.0,
|
| 2411 |
+
"step": 239
|
| 2412 |
+
},
|
| 2413 |
+
{
|
| 2414 |
+
"entropy": 1.093573346734047,
|
| 2415 |
+
"epoch": 2.857142857142857,
|
| 2416 |
+
"grad_norm": 0.220703125,
|
| 2417 |
+
"learning_rate": 1.3104021143278911e-07,
|
| 2418 |
+
"loss": 0.7870185971260071,
|
| 2419 |
+
"mean_token_accuracy": 0.7790666744112968,
|
| 2420 |
+
"num_tokens": 6303822.0,
|
| 2421 |
+
"step": 240
|
| 2422 |
+
},
|
| 2423 |
+
{
|
| 2424 |
+
"entropy": 1.0675100684165955,
|
| 2425 |
+
"epoch": 2.869047619047619,
|
| 2426 |
+
"grad_norm": 0.2138671875,
|
| 2427 |
+
"learning_rate": 1.1169173774871478e-07,
|
| 2428 |
+
"loss": 0.7764073014259338,
|
| 2429 |
+
"mean_token_accuracy": 0.7834136635065079,
|
| 2430 |
+
"num_tokens": 6330367.0,
|
| 2431 |
+
"step": 241
|
| 2432 |
+
},
|
| 2433 |
+
{
|
| 2434 |
+
"entropy": 1.1061383187770844,
|
| 2435 |
+
"epoch": 2.880952380952381,
|
| 2436 |
+
"grad_norm": 0.2119140625,
|
| 2437 |
+
"learning_rate": 9.388005586947191e-08,
|
| 2438 |
+
"loss": 0.8234024047851562,
|
| 2439 |
+
"mean_token_accuracy": 0.7703361287713051,
|
| 2440 |
+
"num_tokens": 6356783.0,
|
| 2441 |
+
"step": 242
|
| 2442 |
+
},
|
| 2443 |
+
{
|
| 2444 |
+
"entropy": 1.0825785994529724,
|
| 2445 |
+
"epoch": 2.892857142857143,
|
| 2446 |
+
"grad_norm": 0.216796875,
|
| 2447 |
+
"learning_rate": 7.760793399827937e-08,
|
| 2448 |
+
"loss": 0.7715331315994263,
|
| 2449 |
+
"mean_token_accuracy": 0.7832503244280815,
|
| 2450 |
+
"num_tokens": 6382945.0,
|
| 2451 |
+
"step": 243
|
| 2452 |
+
},
|
| 2453 |
+
{
|
| 2454 |
+
"entropy": 1.112140253186226,
|
| 2455 |
+
"epoch": 2.9047619047619047,
|
| 2456 |
+
"grad_norm": 0.2158203125,
|
| 2457 |
+
"learning_rate": 6.287790106757396e-08,
|
| 2458 |
+
"loss": 0.8297468423843384,
|
| 2459 |
+
"mean_token_accuracy": 0.7650200128555298,
|
| 2460 |
+
"num_tokens": 6409925.0,
|
| 2461 |
+
"step": 244
|
| 2462 |
+
},
|
| 2463 |
+
{
|
| 2464 |
+
"entropy": 1.0952338576316833,
|
| 2465 |
+
"epoch": 2.9166666666666665,
|
| 2466 |
+
"grad_norm": 0.20703125,
|
| 2467 |
+
"learning_rate": 4.9692246345985905e-08,
|
| 2468 |
+
"loss": 0.802385687828064,
|
| 2469 |
+
"mean_token_accuracy": 0.7693765163421631,
|
| 2470 |
+
"num_tokens": 6436469.0,
|
| 2471 |
+
"step": 245
|
| 2472 |
+
},
|
| 2473 |
+
{
|
| 2474 |
+
"entropy": 1.1076784878969193,
|
| 2475 |
+
"epoch": 2.928571428571429,
|
| 2476 |
+
"grad_norm": 0.212890625,
|
| 2477 |
+
"learning_rate": 3.805301908254455e-08,
|
| 2478 |
+
"loss": 0.8204672336578369,
|
| 2479 |
+
"mean_token_accuracy": 0.7711711004376411,
|
| 2480 |
+
"num_tokens": 6463005.0,
|
| 2481 |
+
"step": 246
|
| 2482 |
+
},
|
| 2483 |
+
{
|
| 2484 |
+
"entropy": 1.090786725282669,
|
| 2485 |
+
"epoch": 2.9404761904761907,
|
| 2486 |
+
"grad_norm": 0.2041015625,
|
| 2487 |
+
"learning_rate": 2.796202818819871e-08,
|
| 2488 |
+
"loss": 0.8098682761192322,
|
| 2489 |
+
"mean_token_accuracy": 0.773357167840004,
|
| 2490 |
+
"num_tokens": 6490495.0,
|
| 2491 |
+
"step": 247
|
| 2492 |
+
},
|
| 2493 |
+
{
|
| 2494 |
+
"entropy": 1.0970018655061722,
|
| 2495 |
+
"epoch": 2.9523809523809526,
|
| 2496 |
+
"grad_norm": 0.2177734375,
|
| 2497 |
+
"learning_rate": 1.9420841954681525e-08,
|
| 2498 |
+
"loss": 0.8029658198356628,
|
| 2499 |
+
"mean_token_accuracy": 0.7747255638241768,
|
| 2500 |
+
"num_tokens": 6516957.0,
|
| 2501 |
+
"step": 248
|
| 2502 |
+
},
|
| 2503 |
+
{
|
| 2504 |
+
"entropy": 1.0752539932727814,
|
| 2505 |
+
"epoch": 2.9642857142857144,
|
| 2506 |
+
"grad_norm": 0.2109375,
|
| 2507 |
+
"learning_rate": 1.2430787810776556e-08,
|
| 2508 |
+
"loss": 0.801226019859314,
|
| 2509 |
+
"mean_token_accuracy": 0.7782684937119484,
|
| 2510 |
+
"num_tokens": 6544240.0,
|
| 2511 |
+
"step": 249
|
| 2512 |
+
},
|
| 2513 |
+
{
|
| 2514 |
+
"entropy": 1.0858174860477448,
|
| 2515 |
+
"epoch": 2.9761904761904763,
|
| 2516 |
+
"grad_norm": 0.208984375,
|
| 2517 |
+
"learning_rate": 6.992952116013918e-09,
|
| 2518 |
+
"loss": 0.7791233062744141,
|
| 2519 |
+
"mean_token_accuracy": 0.7781018689274788,
|
| 2520 |
+
"num_tokens": 6570925.0,
|
| 2521 |
+
"step": 250
|
| 2522 |
+
},
|
| 2523 |
+
{
|
| 2524 |
+
"entropy": 1.0985930263996124,
|
| 2525 |
+
"epoch": 2.988095238095238,
|
| 2526 |
+
"grad_norm": 0.2216796875,
|
| 2527 |
+
"learning_rate": 3.1081799918375454e-09,
|
| 2528 |
+
"loss": 0.7869044542312622,
|
| 2529 |
+
"mean_token_accuracy": 0.7782788202166557,
|
| 2530 |
+
"num_tokens": 6596366.0,
|
| 2531 |
+
"step": 251
|
| 2532 |
+
},
|
| 2533 |
+
{
|
| 2534 |
+
"entropy": 1.1129964143037796,
|
| 2535 |
+
"epoch": 3.0,
|
| 2536 |
+
"grad_norm": 0.228515625,
|
| 2537 |
+
"learning_rate": 7.770751902513862e-10,
|
| 2538 |
+
"loss": 0.8193890452384949,
|
| 2539 |
+
"mean_token_accuracy": 0.7702639102935791,
|
| 2540 |
+
"num_tokens": 6620556.0,
|
| 2541 |
+
"step": 252
|
| 2542 |
+
},
|
| 2543 |
+
{
|
| 2544 |
+
"epoch": 3.0,
|
| 2545 |
+
"eval_entropy": 1.1019742865311473,
|
| 2546 |
+
"eval_loss": 0.8498820066452026,
|
| 2547 |
+
"eval_mean_token_accuracy": 0.7648934659204984,
|
| 2548 |
+
"eval_num_tokens": 6620556.0,
|
| 2549 |
+
"eval_runtime": 20.9234,
|
| 2550 |
+
"eval_samples_per_second": 7.169,
|
| 2551 |
+
"eval_steps_per_second": 0.908,
|
| 2552 |
+
"step": 252
|
| 2553 |
+
}
|
| 2554 |
+
],
|
| 2555 |
+
"logging_steps": 1,
|
| 2556 |
+
"max_steps": 252,
|
| 2557 |
+
"num_input_tokens_seen": 0,
|
| 2558 |
+
"num_train_epochs": 3,
|
| 2559 |
+
"save_steps": 1000,
|
| 2560 |
+
"stateful_callbacks": {
|
| 2561 |
+
"TrainerControl": {
|
| 2562 |
+
"args": {
|
| 2563 |
+
"should_epoch_stop": false,
|
| 2564 |
+
"should_evaluate": false,
|
| 2565 |
+
"should_log": false,
|
| 2566 |
+
"should_save": true,
|
| 2567 |
+
"should_training_stop": true
|
| 2568 |
+
},
|
| 2569 |
+
"attributes": {}
|
| 2570 |
+
}
|
| 2571 |
+
},
|
| 2572 |
+
"total_flos": 1.5249393952995226e+17,
|
| 2573 |
+
"train_batch_size": 2,
|
| 2574 |
+
"trial_name": null,
|
| 2575 |
+
"trial_params": null
|
| 2576 |
+
}
|
checkpoint-252/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7696c0cbccb75f037774b0541b503c37e7348fd323064137ea38046614a2da9c
|
| 3 |
+
size 5649
|