Upload folder using huggingface_hub
Browse files- .gitattributes +1 -0
- README.md +209 -0
- adapter_config.json +48 -0
- adapter_model.safetensors +3 -0
- chat_template.jinja +109 -0
- tokenizer.json +3 -0
- tokenizer_config.json +15 -0
- trainer_state.json +2374 -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 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
|
@@ -0,0 +1,209 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: meta-llama/Llama-3.1-70B-Instruct
|
| 3 |
+
library_name: peft
|
| 4 |
+
pipeline_tag: text-generation
|
| 5 |
+
tags:
|
| 6 |
+
- base_model:adapter:meta-llama/Llama-3.1-70B-Instruct
|
| 7 |
+
- lora
|
| 8 |
+
- sft
|
| 9 |
+
- transformers
|
| 10 |
+
- trl
|
| 11 |
+
---
|
| 12 |
+
|
| 13 |
+
# Model Card for Model ID
|
| 14 |
+
|
| 15 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 16 |
+
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
## Model Details
|
| 20 |
+
|
| 21 |
+
### Model Description
|
| 22 |
+
|
| 23 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 24 |
+
|
| 25 |
+
|
| 26 |
+
|
| 27 |
+
- **Developed by:** [More Information Needed]
|
| 28 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 29 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 30 |
+
- **Model type:** [More Information Needed]
|
| 31 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 32 |
+
- **License:** [More Information Needed]
|
| 33 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 34 |
+
|
| 35 |
+
### Model Sources [optional]
|
| 36 |
+
|
| 37 |
+
<!-- Provide the basic links for the model. -->
|
| 38 |
+
|
| 39 |
+
- **Repository:** [More Information Needed]
|
| 40 |
+
- **Paper [optional]:** [More Information Needed]
|
| 41 |
+
- **Demo [optional]:** [More Information Needed]
|
| 42 |
+
|
| 43 |
+
## Uses
|
| 44 |
+
|
| 45 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 46 |
+
|
| 47 |
+
### Direct Use
|
| 48 |
+
|
| 49 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 50 |
+
|
| 51 |
+
[More Information Needed]
|
| 52 |
+
|
| 53 |
+
### Downstream Use [optional]
|
| 54 |
+
|
| 55 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 56 |
+
|
| 57 |
+
[More Information Needed]
|
| 58 |
+
|
| 59 |
+
### Out-of-Scope Use
|
| 60 |
+
|
| 61 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 62 |
+
|
| 63 |
+
[More Information Needed]
|
| 64 |
+
|
| 65 |
+
## Bias, Risks, and Limitations
|
| 66 |
+
|
| 67 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 68 |
+
|
| 69 |
+
[More Information Needed]
|
| 70 |
+
|
| 71 |
+
### Recommendations
|
| 72 |
+
|
| 73 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 74 |
+
|
| 75 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 76 |
+
|
| 77 |
+
## How to Get Started with the Model
|
| 78 |
+
|
| 79 |
+
Use the code below to get started with the model.
|
| 80 |
+
|
| 81 |
+
[More Information Needed]
|
| 82 |
+
|
| 83 |
+
## Training Details
|
| 84 |
+
|
| 85 |
+
### Training Data
|
| 86 |
+
|
| 87 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 88 |
+
|
| 89 |
+
[More Information Needed]
|
| 90 |
+
|
| 91 |
+
### Training Procedure
|
| 92 |
+
|
| 93 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 94 |
+
|
| 95 |
+
#### Preprocessing [optional]
|
| 96 |
+
|
| 97 |
+
[More Information Needed]
|
| 98 |
+
|
| 99 |
+
|
| 100 |
+
#### Training Hyperparameters
|
| 101 |
+
|
| 102 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 103 |
+
|
| 104 |
+
#### Speeds, Sizes, Times [optional]
|
| 105 |
+
|
| 106 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 107 |
+
|
| 108 |
+
[More Information Needed]
|
| 109 |
+
|
| 110 |
+
## Evaluation
|
| 111 |
+
|
| 112 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 113 |
+
|
| 114 |
+
### Testing Data, Factors & Metrics
|
| 115 |
+
|
| 116 |
+
#### Testing Data
|
| 117 |
+
|
| 118 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 119 |
+
|
| 120 |
+
[More Information Needed]
|
| 121 |
+
|
| 122 |
+
#### Factors
|
| 123 |
+
|
| 124 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 125 |
+
|
| 126 |
+
[More Information Needed]
|
| 127 |
+
|
| 128 |
+
#### Metrics
|
| 129 |
+
|
| 130 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 131 |
+
|
| 132 |
+
[More Information Needed]
|
| 133 |
+
|
| 134 |
+
### Results
|
| 135 |
+
|
| 136 |
+
[More Information Needed]
|
| 137 |
+
|
| 138 |
+
#### Summary
|
| 139 |
+
|
| 140 |
+
|
| 141 |
+
|
| 142 |
+
## Model Examination [optional]
|
| 143 |
+
|
| 144 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 145 |
+
|
| 146 |
+
[More Information Needed]
|
| 147 |
+
|
| 148 |
+
## Environmental Impact
|
| 149 |
+
|
| 150 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 151 |
+
|
| 152 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
| 153 |
+
|
| 154 |
+
- **Hardware Type:** [More Information Needed]
|
| 155 |
+
- **Hours used:** [More Information Needed]
|
| 156 |
+
- **Cloud Provider:** [More Information Needed]
|
| 157 |
+
- **Compute Region:** [More Information Needed]
|
| 158 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 159 |
+
|
| 160 |
+
## Technical Specifications [optional]
|
| 161 |
+
|
| 162 |
+
### Model Architecture and Objective
|
| 163 |
+
|
| 164 |
+
[More Information Needed]
|
| 165 |
+
|
| 166 |
+
### Compute Infrastructure
|
| 167 |
+
|
| 168 |
+
[More Information Needed]
|
| 169 |
+
|
| 170 |
+
#### Hardware
|
| 171 |
+
|
| 172 |
+
[More Information Needed]
|
| 173 |
+
|
| 174 |
+
#### Software
|
| 175 |
+
|
| 176 |
+
[More Information Needed]
|
| 177 |
+
|
| 178 |
+
## Citation [optional]
|
| 179 |
+
|
| 180 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 181 |
+
|
| 182 |
+
**BibTeX:**
|
| 183 |
+
|
| 184 |
+
[More Information Needed]
|
| 185 |
+
|
| 186 |
+
**APA:**
|
| 187 |
+
|
| 188 |
+
[More Information Needed]
|
| 189 |
+
|
| 190 |
+
## Glossary [optional]
|
| 191 |
+
|
| 192 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 193 |
+
|
| 194 |
+
[More Information Needed]
|
| 195 |
+
|
| 196 |
+
## More Information [optional]
|
| 197 |
+
|
| 198 |
+
[More Information Needed]
|
| 199 |
+
|
| 200 |
+
## Model Card Authors [optional]
|
| 201 |
+
|
| 202 |
+
[More Information Needed]
|
| 203 |
+
|
| 204 |
+
## Model Card Contact
|
| 205 |
+
|
| 206 |
+
[More Information Needed]
|
| 207 |
+
### Framework versions
|
| 208 |
+
|
| 209 |
+
- PEFT 0.19.1
|
adapter_config.json
ADDED
|
@@ -0,0 +1,48 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alora_invocation_tokens": null,
|
| 3 |
+
"alpha_pattern": {},
|
| 4 |
+
"arrow_config": null,
|
| 5 |
+
"auto_mapping": null,
|
| 6 |
+
"base_model_name_or_path": "meta-llama/Llama-3.1-70B-Instruct",
|
| 7 |
+
"bias": "none",
|
| 8 |
+
"corda_config": null,
|
| 9 |
+
"ensure_weight_tying": false,
|
| 10 |
+
"eva_config": null,
|
| 11 |
+
"exclude_modules": null,
|
| 12 |
+
"fan_in_fan_out": false,
|
| 13 |
+
"inference_mode": true,
|
| 14 |
+
"init_lora_weights": true,
|
| 15 |
+
"layer_replication": null,
|
| 16 |
+
"layers_pattern": null,
|
| 17 |
+
"layers_to_transform": null,
|
| 18 |
+
"loftq_config": {},
|
| 19 |
+
"lora_alpha": 128,
|
| 20 |
+
"lora_bias": false,
|
| 21 |
+
"lora_dropout": 0.05,
|
| 22 |
+
"lora_ga_config": null,
|
| 23 |
+
"megatron_config": null,
|
| 24 |
+
"megatron_core": "megatron.core",
|
| 25 |
+
"modules_to_save": null,
|
| 26 |
+
"peft_type": "LORA",
|
| 27 |
+
"peft_version": "0.18.1",
|
| 28 |
+
"qalora_group_size": 16,
|
| 29 |
+
"r": 64,
|
| 30 |
+
"rank_pattern": {},
|
| 31 |
+
"revision": null,
|
| 32 |
+
"target_modules": [
|
| 33 |
+
"k_proj",
|
| 34 |
+
"gate_proj",
|
| 35 |
+
"o_proj",
|
| 36 |
+
"up_proj",
|
| 37 |
+
"v_proj",
|
| 38 |
+
"q_proj",
|
| 39 |
+
"down_proj"
|
| 40 |
+
],
|
| 41 |
+
"target_parameters": null,
|
| 42 |
+
"task_type": "CAUSAL_LM",
|
| 43 |
+
"trainable_token_indices": null,
|
| 44 |
+
"use_bdlora": null,
|
| 45 |
+
"use_dora": false,
|
| 46 |
+
"use_qalora": false,
|
| 47 |
+
"use_rslora": false
|
| 48 |
+
}
|
adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4a708aad6f0059627e8327085f01c632f6b43247f940c9140604d6acaeca037d
|
| 3 |
+
size 3313653480
|
chat_template.jinja
ADDED
|
@@ -0,0 +1,109 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{{- bos_token }}
|
| 2 |
+
{%- if custom_tools is defined %}
|
| 3 |
+
{%- set tools = custom_tools %}
|
| 4 |
+
{%- endif %}
|
| 5 |
+
{%- if not tools_in_user_message is defined %}
|
| 6 |
+
{%- set tools_in_user_message = true %}
|
| 7 |
+
{%- endif %}
|
| 8 |
+
{%- if not date_string is defined %}
|
| 9 |
+
{%- set date_string = "26 Jul 2024" %}
|
| 10 |
+
{%- endif %}
|
| 11 |
+
{%- if not tools is defined %}
|
| 12 |
+
{%- set tools = none %}
|
| 13 |
+
{%- endif %}
|
| 14 |
+
|
| 15 |
+
{#- This block extracts the system message, so we can slot it into the right place. #}
|
| 16 |
+
{%- if messages[0]['role'] == 'system' %}
|
| 17 |
+
{%- set system_message = messages[0]['content']|trim %}
|
| 18 |
+
{%- set messages = messages[1:] %}
|
| 19 |
+
{%- else %}
|
| 20 |
+
{%- set system_message = "" %}
|
| 21 |
+
{%- endif %}
|
| 22 |
+
|
| 23 |
+
{#- System message + builtin tools #}
|
| 24 |
+
{{- "<|start_header_id|>system<|end_header_id|>\n\n" }}
|
| 25 |
+
{%- if builtin_tools is defined or tools is not none %}
|
| 26 |
+
{{- "Environment: ipython\n" }}
|
| 27 |
+
{%- endif %}
|
| 28 |
+
{%- if builtin_tools is defined %}
|
| 29 |
+
{{- "Tools: " + builtin_tools | reject('equalto', 'code_interpreter') | join(", ") + "\n\n"}}
|
| 30 |
+
{%- endif %}
|
| 31 |
+
{{- "Cutting Knowledge Date: December 2023\n" }}
|
| 32 |
+
{{- "Today Date: " + date_string + "\n\n" }}
|
| 33 |
+
{%- if tools is not none and not tools_in_user_message %}
|
| 34 |
+
{{- "You have access to the following functions. To call a function, please respond with JSON for a function call." }}
|
| 35 |
+
{{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
|
| 36 |
+
{{- "Do not use variables.\n\n" }}
|
| 37 |
+
{%- for t in tools %}
|
| 38 |
+
{{- t | tojson(indent=4) }}
|
| 39 |
+
{{- "\n\n" }}
|
| 40 |
+
{%- endfor %}
|
| 41 |
+
{%- endif %}
|
| 42 |
+
{{- system_message }}
|
| 43 |
+
{{- "<|eot_id|>" }}
|
| 44 |
+
|
| 45 |
+
{#- Custom tools are passed in a user message with some extra guidance #}
|
| 46 |
+
{%- if tools_in_user_message and not tools is none %}
|
| 47 |
+
{#- Extract the first user message so we can plug it in here #}
|
| 48 |
+
{%- if messages | length != 0 %}
|
| 49 |
+
{%- set first_user_message = messages[0]['content']|trim %}
|
| 50 |
+
{%- set messages = messages[1:] %}
|
| 51 |
+
{%- else %}
|
| 52 |
+
{{- raise_exception("Cannot put tools in the first user message when there's no first user message!") }}
|
| 53 |
+
{%- endif %}
|
| 54 |
+
{{- '<|start_header_id|>user<|end_header_id|>\n\n' -}}
|
| 55 |
+
{{- "Given the following functions, please respond with a JSON for a function call " }}
|
| 56 |
+
{{- "with its proper arguments that best answers the given prompt.\n\n" }}
|
| 57 |
+
{{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
|
| 58 |
+
{{- "Do not use variables.\n\n" }}
|
| 59 |
+
{%- for t in tools %}
|
| 60 |
+
{{- t | tojson(indent=4) }}
|
| 61 |
+
{{- "\n\n" }}
|
| 62 |
+
{%- endfor %}
|
| 63 |
+
{{- first_user_message + "<|eot_id|>"}}
|
| 64 |
+
{%- endif %}
|
| 65 |
+
|
| 66 |
+
{%- for message in messages %}
|
| 67 |
+
{%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}
|
| 68 |
+
{{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' }}
|
| 69 |
+
{%- elif 'tool_calls' in message %}
|
| 70 |
+
{%- if not message.tool_calls|length == 1 %}
|
| 71 |
+
{{- raise_exception("This model only supports single tool-calls at once!") }}
|
| 72 |
+
{%- endif %}
|
| 73 |
+
{%- set tool_call = message.tool_calls[0].function %}
|
| 74 |
+
{%- if builtin_tools is defined and tool_call.name in builtin_tools %}
|
| 75 |
+
{{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}
|
| 76 |
+
{{- "<|python_tag|>" + tool_call.name + ".call(" }}
|
| 77 |
+
{%- for arg_name, arg_val in tool_call.arguments | items %}
|
| 78 |
+
{{- arg_name + '="' + arg_val + '"' }}
|
| 79 |
+
{%- if not loop.last %}
|
| 80 |
+
{{- ", " }}
|
| 81 |
+
{%- endif %}
|
| 82 |
+
{%- endfor %}
|
| 83 |
+
{{- ")" }}
|
| 84 |
+
{%- else %}
|
| 85 |
+
{{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}
|
| 86 |
+
{{- '{"name": "' + tool_call.name + '", ' }}
|
| 87 |
+
{{- '"parameters": ' }}
|
| 88 |
+
{{- tool_call.arguments | tojson }}
|
| 89 |
+
{{- "}" }}
|
| 90 |
+
{%- endif %}
|
| 91 |
+
{%- if builtin_tools is defined %}
|
| 92 |
+
{#- This means we're in ipython mode #}
|
| 93 |
+
{{- "<|eom_id|>" }}
|
| 94 |
+
{%- else %}
|
| 95 |
+
{{- "<|eot_id|>" }}
|
| 96 |
+
{%- endif %}
|
| 97 |
+
{%- elif message.role == "tool" or message.role == "ipython" %}
|
| 98 |
+
{{- "<|start_header_id|>ipython<|end_header_id|>\n\n" }}
|
| 99 |
+
{%- if message.content is mapping or message.content is iterable %}
|
| 100 |
+
{{- message.content | tojson }}
|
| 101 |
+
{%- else %}
|
| 102 |
+
{{- message.content }}
|
| 103 |
+
{%- endif %}
|
| 104 |
+
{{- "<|eot_id|>" }}
|
| 105 |
+
{%- endif %}
|
| 106 |
+
{%- endfor %}
|
| 107 |
+
{%- if add_generation_prompt %}
|
| 108 |
+
{{- '<|start_header_id|>assistant<|end_header_id|>\n\n' }}
|
| 109 |
+
{%- endif %}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
|
| 3 |
+
size 17209920
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"backend": "tokenizers",
|
| 3 |
+
"bos_token": "<|begin_of_text|>",
|
| 4 |
+
"clean_up_tokenization_spaces": true,
|
| 5 |
+
"eos_token": "<|eot_id|>",
|
| 6 |
+
"is_local": false,
|
| 7 |
+
"local_files_only": false,
|
| 8 |
+
"model_input_names": [
|
| 9 |
+
"input_ids",
|
| 10 |
+
"attention_mask"
|
| 11 |
+
],
|
| 12 |
+
"model_max_length": 131072,
|
| 13 |
+
"pad_token": "<|eot_id|>",
|
| 14 |
+
"tokenizer_class": "TokenizersBackend"
|
| 15 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,2374 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 3.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 234,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"entropy": 1.2969624996185303,
|
| 14 |
+
"epoch": 0.012861736334405145,
|
| 15 |
+
"grad_norm": 1.222815990447998,
|
| 16 |
+
"learning_rate": 0.0,
|
| 17 |
+
"loss": 2.025021553039551,
|
| 18 |
+
"mean_token_accuracy": 0.5397194549441338,
|
| 19 |
+
"num_tokens": 128512.0,
|
| 20 |
+
"step": 1
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"entropy": 1.3495921194553375,
|
| 24 |
+
"epoch": 0.02572347266881029,
|
| 25 |
+
"grad_norm": 1.2900104522705078,
|
| 26 |
+
"learning_rate": 4.166666666666667e-06,
|
| 27 |
+
"loss": 2.113243341445923,
|
| 28 |
+
"mean_token_accuracy": 0.5239669531583786,
|
| 29 |
+
"num_tokens": 258439.0,
|
| 30 |
+
"step": 2
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"entropy": 1.4065107256174088,
|
| 34 |
+
"epoch": 0.03858520900321544,
|
| 35 |
+
"grad_norm": 1.1876918077468872,
|
| 36 |
+
"learning_rate": 8.333333333333334e-06,
|
| 37 |
+
"loss": 2.0984230041503906,
|
| 38 |
+
"mean_token_accuracy": 0.525254875421524,
|
| 39 |
+
"num_tokens": 387958.0,
|
| 40 |
+
"step": 3
|
| 41 |
+
},
|
| 42 |
+
{
|
| 43 |
+
"entropy": 1.4473730325698853,
|
| 44 |
+
"epoch": 0.05144694533762058,
|
| 45 |
+
"grad_norm": 0.995452880859375,
|
| 46 |
+
"learning_rate": 1.25e-05,
|
| 47 |
+
"loss": 2.0187673568725586,
|
| 48 |
+
"mean_token_accuracy": 0.534252941608429,
|
| 49 |
+
"num_tokens": 516779.0,
|
| 50 |
+
"step": 4
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"entropy": 1.626717284321785,
|
| 54 |
+
"epoch": 0.06430868167202572,
|
| 55 |
+
"grad_norm": 0.6222253441810608,
|
| 56 |
+
"learning_rate": 1.6666666666666667e-05,
|
| 57 |
+
"loss": 1.9110387563705444,
|
| 58 |
+
"mean_token_accuracy": 0.5435223057866096,
|
| 59 |
+
"num_tokens": 645829.0,
|
| 60 |
+
"step": 5
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"entropy": 1.810067042708397,
|
| 64 |
+
"epoch": 0.07717041800643087,
|
| 65 |
+
"grad_norm": 0.42118003964424133,
|
| 66 |
+
"learning_rate": 2.0833333333333336e-05,
|
| 67 |
+
"loss": 1.8789349794387817,
|
| 68 |
+
"mean_token_accuracy": 0.5466088876128197,
|
| 69 |
+
"num_tokens": 774435.0,
|
| 70 |
+
"step": 6
|
| 71 |
+
},
|
| 72 |
+
{
|
| 73 |
+
"entropy": 1.9707088768482208,
|
| 74 |
+
"epoch": 0.09003215434083602,
|
| 75 |
+
"grad_norm": 0.4645366072654724,
|
| 76 |
+
"learning_rate": 2.5e-05,
|
| 77 |
+
"loss": 1.8074758052825928,
|
| 78 |
+
"mean_token_accuracy": 0.5567064955830574,
|
| 79 |
+
"num_tokens": 903545.0,
|
| 80 |
+
"step": 7
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"entropy": 1.9890314191579819,
|
| 84 |
+
"epoch": 0.10289389067524116,
|
| 85 |
+
"grad_norm": 0.5461070537567139,
|
| 86 |
+
"learning_rate": 2.916666666666667e-05,
|
| 87 |
+
"loss": 1.7440648078918457,
|
| 88 |
+
"mean_token_accuracy": 0.5663307011127472,
|
| 89 |
+
"num_tokens": 1033070.0,
|
| 90 |
+
"step": 8
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"entropy": 1.968129649758339,
|
| 94 |
+
"epoch": 0.1157556270096463,
|
| 95 |
+
"grad_norm": 0.5405251383781433,
|
| 96 |
+
"learning_rate": 3.3333333333333335e-05,
|
| 97 |
+
"loss": 1.7069363594055176,
|
| 98 |
+
"mean_token_accuracy": 0.5683588162064552,
|
| 99 |
+
"num_tokens": 1162755.0,
|
| 100 |
+
"step": 9
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"entropy": 1.8345413953065872,
|
| 104 |
+
"epoch": 0.12861736334405144,
|
| 105 |
+
"grad_norm": 0.42177239060401917,
|
| 106 |
+
"learning_rate": 3.7500000000000003e-05,
|
| 107 |
+
"loss": 1.65086030960083,
|
| 108 |
+
"mean_token_accuracy": 0.5773059874773026,
|
| 109 |
+
"num_tokens": 1290164.0,
|
| 110 |
+
"step": 10
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"entropy": 1.6431169360876083,
|
| 114 |
+
"epoch": 0.1414790996784566,
|
| 115 |
+
"grad_norm": 0.31144559383392334,
|
| 116 |
+
"learning_rate": 4.166666666666667e-05,
|
| 117 |
+
"loss": 1.582027792930603,
|
| 118 |
+
"mean_token_accuracy": 0.5872198939323425,
|
| 119 |
+
"num_tokens": 1419501.0,
|
| 120 |
+
"step": 11
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"entropy": 1.544620230793953,
|
| 124 |
+
"epoch": 0.15434083601286175,
|
| 125 |
+
"grad_norm": 0.27825888991355896,
|
| 126 |
+
"learning_rate": 4.5833333333333334e-05,
|
| 127 |
+
"loss": 1.5446865558624268,
|
| 128 |
+
"mean_token_accuracy": 0.594700962305069,
|
| 129 |
+
"num_tokens": 1547996.0,
|
| 130 |
+
"step": 12
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"entropy": 1.4267793744802475,
|
| 134 |
+
"epoch": 0.16720257234726688,
|
| 135 |
+
"grad_norm": 0.2835897207260132,
|
| 136 |
+
"learning_rate": 5e-05,
|
| 137 |
+
"loss": 1.509974479675293,
|
| 138 |
+
"mean_token_accuracy": 0.6006790399551392,
|
| 139 |
+
"num_tokens": 1676937.0,
|
| 140 |
+
"step": 13
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"entropy": 1.3972271531820297,
|
| 144 |
+
"epoch": 0.18006430868167203,
|
| 145 |
+
"grad_norm": 0.25854921340942383,
|
| 146 |
+
"learning_rate": 4.9997496794168726e-05,
|
| 147 |
+
"loss": 1.491778016090393,
|
| 148 |
+
"mean_token_accuracy": 0.6045994758605957,
|
| 149 |
+
"num_tokens": 1806013.0,
|
| 150 |
+
"step": 14
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"entropy": 1.4395506381988525,
|
| 154 |
+
"epoch": 0.19292604501607716,
|
| 155 |
+
"grad_norm": 0.22095996141433716,
|
| 156 |
+
"learning_rate": 4.998998767795805e-05,
|
| 157 |
+
"loss": 1.4883487224578857,
|
| 158 |
+
"mean_token_accuracy": 0.6050755307078362,
|
| 159 |
+
"num_tokens": 1935387.0,
|
| 160 |
+
"step": 15
|
| 161 |
+
},
|
| 162 |
+
{
|
| 163 |
+
"entropy": 1.4550755470991135,
|
| 164 |
+
"epoch": 0.2057877813504823,
|
| 165 |
+
"grad_norm": 0.24221676588058472,
|
| 166 |
+
"learning_rate": 4.9977474155117045e-05,
|
| 167 |
+
"loss": 1.4858245849609375,
|
| 168 |
+
"mean_token_accuracy": 0.6017315089702606,
|
| 169 |
+
"num_tokens": 2065100.0,
|
| 170 |
+
"step": 16
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"entropy": 1.4459427893161774,
|
| 174 |
+
"epoch": 0.21864951768488747,
|
| 175 |
+
"grad_norm": 0.25146999955177307,
|
| 176 |
+
"learning_rate": 4.995995873155958e-05,
|
| 177 |
+
"loss": 1.4274994134902954,
|
| 178 |
+
"mean_token_accuracy": 0.6151479333639145,
|
| 179 |
+
"num_tokens": 2194685.0,
|
| 180 |
+
"step": 17
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"entropy": 1.4442210048437119,
|
| 184 |
+
"epoch": 0.2315112540192926,
|
| 185 |
+
"grad_norm": 0.2271786779165268,
|
| 186 |
+
"learning_rate": 4.99374449148625e-05,
|
| 187 |
+
"loss": 1.4092518091201782,
|
| 188 |
+
"mean_token_accuracy": 0.6148851290345192,
|
| 189 |
+
"num_tokens": 2324963.0,
|
| 190 |
+
"step": 18
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"entropy": 1.4254360347986221,
|
| 194 |
+
"epoch": 0.24437299035369775,
|
| 195 |
+
"grad_norm": 0.18994390964508057,
|
| 196 |
+
"learning_rate": 4.9909937213563165e-05,
|
| 197 |
+
"loss": 1.3825007677078247,
|
| 198 |
+
"mean_token_accuracy": 0.6199355497956276,
|
| 199 |
+
"num_tokens": 2454343.0,
|
| 200 |
+
"step": 19
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"entropy": 1.3843167871236801,
|
| 204 |
+
"epoch": 0.2572347266881029,
|
| 205 |
+
"grad_norm": 0.18420229852199554,
|
| 206 |
+
"learning_rate": 4.987744113625665e-05,
|
| 207 |
+
"loss": 1.3471739292144775,
|
| 208 |
+
"mean_token_accuracy": 0.6283371672034264,
|
| 209 |
+
"num_tokens": 2584405.0,
|
| 210 |
+
"step": 20
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"entropy": 1.3585271686315536,
|
| 214 |
+
"epoch": 0.27009646302250806,
|
| 215 |
+
"grad_norm": 0.18983817100524902,
|
| 216 |
+
"learning_rate": 4.9839963190492576e-05,
|
| 217 |
+
"loss": 1.3283567428588867,
|
| 218 |
+
"mean_token_accuracy": 0.6319968476891518,
|
| 219 |
+
"num_tokens": 2709555.0,
|
| 220 |
+
"step": 21
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"entropy": 1.3483584225177765,
|
| 224 |
+
"epoch": 0.2829581993569132,
|
| 225 |
+
"grad_norm": 0.18332050740718842,
|
| 226 |
+
"learning_rate": 4.979751088147192e-05,
|
| 227 |
+
"loss": 1.33201003074646,
|
| 228 |
+
"mean_token_accuracy": 0.6298539489507675,
|
| 229 |
+
"num_tokens": 2839191.0,
|
| 230 |
+
"step": 22
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"entropy": 1.334426462650299,
|
| 234 |
+
"epoch": 0.2958199356913183,
|
| 235 |
+
"grad_norm": 0.16615396738052368,
|
| 236 |
+
"learning_rate": 4.975009271054409e-05,
|
| 237 |
+
"loss": 1.3058710098266602,
|
| 238 |
+
"mean_token_accuracy": 0.6357970610260963,
|
| 239 |
+
"num_tokens": 2968625.0,
|
| 240 |
+
"step": 23
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"entropy": 1.3269707262516022,
|
| 244 |
+
"epoch": 0.3086816720257235,
|
| 245 |
+
"grad_norm": 0.16659598052501678,
|
| 246 |
+
"learning_rate": 4.969771817350445e-05,
|
| 247 |
+
"loss": 1.298633337020874,
|
| 248 |
+
"mean_token_accuracy": 0.6390289217233658,
|
| 249 |
+
"num_tokens": 3098193.0,
|
| 250 |
+
"step": 24
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"entropy": 1.3264441937208176,
|
| 254 |
+
"epoch": 0.3215434083601286,
|
| 255 |
+
"grad_norm": 0.18099723756313324,
|
| 256 |
+
"learning_rate": 4.9640397758692715e-05,
|
| 257 |
+
"loss": 1.2919727563858032,
|
| 258 |
+
"mean_token_accuracy": 0.6379936411976814,
|
| 259 |
+
"num_tokens": 3226304.0,
|
| 260 |
+
"step": 25
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"entropy": 1.2971351444721222,
|
| 264 |
+
"epoch": 0.33440514469453375,
|
| 265 |
+
"grad_norm": 0.16978149116039276,
|
| 266 |
+
"learning_rate": 4.957814294489261e-05,
|
| 267 |
+
"loss": 1.283421277999878,
|
| 268 |
+
"mean_token_accuracy": 0.6396878883242607,
|
| 269 |
+
"num_tokens": 3356150.0,
|
| 270 |
+
"step": 26
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"entropy": 1.2420216798782349,
|
| 274 |
+
"epoch": 0.34726688102893893,
|
| 275 |
+
"grad_norm": 0.15654370188713074,
|
| 276 |
+
"learning_rate": 4.9510966199033174e-05,
|
| 277 |
+
"loss": 1.2411205768585205,
|
| 278 |
+
"mean_token_accuracy": 0.6497687473893166,
|
| 279 |
+
"num_tokens": 3485881.0,
|
| 280 |
+
"step": 27
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"entropy": 1.2905446141958237,
|
| 284 |
+
"epoch": 0.36012861736334406,
|
| 285 |
+
"grad_norm": 0.15767726302146912,
|
| 286 |
+
"learning_rate": 4.943888097369216e-05,
|
| 287 |
+
"loss": 1.2969235181808472,
|
| 288 |
+
"mean_token_accuracy": 0.6399867981672287,
|
| 289 |
+
"num_tokens": 3614360.0,
|
| 290 |
+
"step": 28
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"entropy": 1.2797959297895432,
|
| 294 |
+
"epoch": 0.3729903536977492,
|
| 295 |
+
"grad_norm": 0.1609920859336853,
|
| 296 |
+
"learning_rate": 4.936190170440208e-05,
|
| 297 |
+
"loss": 1.281036615371704,
|
| 298 |
+
"mean_token_accuracy": 0.6414945125579834,
|
| 299 |
+
"num_tokens": 3742757.0,
|
| 300 |
+
"step": 29
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"entropy": 1.2370718121528625,
|
| 304 |
+
"epoch": 0.3858520900321543,
|
| 305 |
+
"grad_norm": 0.15289531648159027,
|
| 306 |
+
"learning_rate": 4.928004380675941e-05,
|
| 307 |
+
"loss": 1.2397706508636475,
|
| 308 |
+
"mean_token_accuracy": 0.6485739275813103,
|
| 309 |
+
"num_tokens": 3872361.0,
|
| 310 |
+
"step": 30
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"entropy": 1.2661651074886322,
|
| 314 |
+
"epoch": 0.3987138263665595,
|
| 315 |
+
"grad_norm": 0.15539875626564026,
|
| 316 |
+
"learning_rate": 4.9193323673337476e-05,
|
| 317 |
+
"loss": 1.2545585632324219,
|
| 318 |
+
"mean_token_accuracy": 0.646148107945919,
|
| 319 |
+
"num_tokens": 4001029.0,
|
| 320 |
+
"step": 31
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"entropy": 1.259293794631958,
|
| 324 |
+
"epoch": 0.4115755627009646,
|
| 325 |
+
"grad_norm": 0.15602311491966248,
|
| 326 |
+
"learning_rate": 4.910175867040377e-05,
|
| 327 |
+
"loss": 1.2386581897735596,
|
| 328 |
+
"mean_token_accuracy": 0.6532392650842667,
|
| 329 |
+
"num_tokens": 4129746.0,
|
| 330 |
+
"step": 32
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"entropy": 1.2246208488941193,
|
| 334 |
+
"epoch": 0.42443729903536975,
|
| 335 |
+
"grad_norm": 0.15040729939937592,
|
| 336 |
+
"learning_rate": 4.9005367134442235e-05,
|
| 337 |
+
"loss": 1.2012075185775757,
|
| 338 |
+
"mean_token_accuracy": 0.6605038940906525,
|
| 339 |
+
"num_tokens": 4258908.0,
|
| 340 |
+
"step": 33
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"entropy": 1.2688497006893158,
|
| 344 |
+
"epoch": 0.43729903536977494,
|
| 345 |
+
"grad_norm": 0.14351816475391388,
|
| 346 |
+
"learning_rate": 4.890416836848127e-05,
|
| 347 |
+
"loss": 1.2468310594558716,
|
| 348 |
+
"mean_token_accuracy": 0.6454005613923073,
|
| 349 |
+
"num_tokens": 4388837.0,
|
| 350 |
+
"step": 34
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"entropy": 1.2282109707593918,
|
| 354 |
+
"epoch": 0.45016077170418006,
|
| 355 |
+
"grad_norm": 0.14232277870178223,
|
| 356 |
+
"learning_rate": 4.8798182638228166e-05,
|
| 357 |
+
"loss": 1.2170629501342773,
|
| 358 |
+
"mean_token_accuracy": 0.6531817615032196,
|
| 359 |
+
"num_tokens": 4518130.0,
|
| 360 |
+
"step": 35
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"entropy": 1.2145698070526123,
|
| 364 |
+
"epoch": 0.4630225080385852,
|
| 365 |
+
"grad_norm": 0.14945274591445923,
|
| 366 |
+
"learning_rate": 4.868743116801074e-05,
|
| 367 |
+
"loss": 1.2234522104263306,
|
| 368 |
+
"mean_token_accuracy": 0.6538028195500374,
|
| 369 |
+
"num_tokens": 4647727.0,
|
| 370 |
+
"step": 36
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"entropy": 1.2184867858886719,
|
| 374 |
+
"epoch": 0.4758842443729904,
|
| 375 |
+
"grad_norm": 0.14716529846191406,
|
| 376 |
+
"learning_rate": 4.857193613652711e-05,
|
| 377 |
+
"loss": 1.2205889225006104,
|
| 378 |
+
"mean_token_accuracy": 0.6552813798189163,
|
| 379 |
+
"num_tokens": 4776814.0,
|
| 380 |
+
"step": 37
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"entropy": 1.2501244097948074,
|
| 384 |
+
"epoch": 0.4887459807073955,
|
| 385 |
+
"grad_norm": 0.13584738969802856,
|
| 386 |
+
"learning_rate": 4.845172067240415e-05,
|
| 387 |
+
"loss": 1.232811689376831,
|
| 388 |
+
"mean_token_accuracy": 0.6496494188904762,
|
| 389 |
+
"num_tokens": 4906642.0,
|
| 390 |
+
"step": 38
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"entropy": 1.2297646403312683,
|
| 394 |
+
"epoch": 0.5016077170418006,
|
| 395 |
+
"grad_norm": 0.1445397287607193,
|
| 396 |
+
"learning_rate": 4.8326808849565936e-05,
|
| 397 |
+
"loss": 1.2179179191589355,
|
| 398 |
+
"mean_token_accuracy": 0.6524648442864418,
|
| 399 |
+
"num_tokens": 5035784.0,
|
| 400 |
+
"step": 39
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"entropy": 1.2054394781589508,
|
| 404 |
+
"epoch": 0.5144694533762058,
|
| 405 |
+
"grad_norm": 0.1438300460577011,
|
| 406 |
+
"learning_rate": 4.819722568241274e-05,
|
| 407 |
+
"loss": 1.1902542114257812,
|
| 408 |
+
"mean_token_accuracy": 0.6586381196975708,
|
| 409 |
+
"num_tokens": 5163483.0,
|
| 410 |
+
"step": 40
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"entropy": 1.1801835894584656,
|
| 414 |
+
"epoch": 0.5273311897106109,
|
| 415 |
+
"grad_norm": 0.13536524772644043,
|
| 416 |
+
"learning_rate": 4.806299712081172e-05,
|
| 417 |
+
"loss": 1.1734623908996582,
|
| 418 |
+
"mean_token_accuracy": 0.6613527312874794,
|
| 419 |
+
"num_tokens": 5289099.0,
|
| 420 |
+
"step": 41
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"entropy": 1.2093226611614227,
|
| 424 |
+
"epoch": 0.5401929260450161,
|
| 425 |
+
"grad_norm": 0.13810646533966064,
|
| 426 |
+
"learning_rate": 4.792415004490034e-05,
|
| 427 |
+
"loss": 1.2002174854278564,
|
| 428 |
+
"mean_token_accuracy": 0.6581337600946426,
|
| 429 |
+
"num_tokens": 5414735.0,
|
| 430 |
+
"step": 42
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"entropy": 1.1848722696304321,
|
| 434 |
+
"epoch": 0.5530546623794212,
|
| 435 |
+
"grad_norm": 0.1468912959098816,
|
| 436 |
+
"learning_rate": 4.77807122597034e-05,
|
| 437 |
+
"loss": 1.1885192394256592,
|
| 438 |
+
"mean_token_accuracy": 0.6589618176221848,
|
| 439 |
+
"num_tokens": 5543143.0,
|
| 440 |
+
"step": 43
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"entropy": 1.181750476360321,
|
| 444 |
+
"epoch": 0.5659163987138264,
|
| 445 |
+
"grad_norm": 0.1429019272327423,
|
| 446 |
+
"learning_rate": 4.7632712489564926e-05,
|
| 447 |
+
"loss": 1.1800310611724854,
|
| 448 |
+
"mean_token_accuracy": 0.6618404239416122,
|
| 449 |
+
"num_tokens": 5671758.0,
|
| 450 |
+
"step": 44
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"entropy": 1.223798543214798,
|
| 454 |
+
"epoch": 0.5787781350482315,
|
| 455 |
+
"grad_norm": 0.13423405587673187,
|
| 456 |
+
"learning_rate": 4.748018037239592e-05,
|
| 457 |
+
"loss": 1.2137880325317383,
|
| 458 |
+
"mean_token_accuracy": 0.6538020968437195,
|
| 459 |
+
"num_tokens": 5801203.0,
|
| 460 |
+
"step": 45
|
| 461 |
+
},
|
| 462 |
+
{
|
| 463 |
+
"entropy": 1.1596673130989075,
|
| 464 |
+
"epoch": 0.5916398713826366,
|
| 465 |
+
"grad_norm": 0.14085975289344788,
|
| 466 |
+
"learning_rate": 4.732314645373921e-05,
|
| 467 |
+
"loss": 1.1383979320526123,
|
| 468 |
+
"mean_token_accuracy": 0.6676715686917305,
|
| 469 |
+
"num_tokens": 5929286.0,
|
| 470 |
+
"step": 46
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"entropy": 1.1791094541549683,
|
| 474 |
+
"epoch": 0.6045016077170418,
|
| 475 |
+
"grad_norm": 0.14022590219974518,
|
| 476 |
+
"learning_rate": 4.7161642180652464e-05,
|
| 477 |
+
"loss": 1.1624398231506348,
|
| 478 |
+
"mean_token_accuracy": 0.6638200730085373,
|
| 479 |
+
"num_tokens": 6055494.0,
|
| 480 |
+
"step": 47
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"entropy": 1.17191481590271,
|
| 484 |
+
"epoch": 0.617363344051447,
|
| 485 |
+
"grad_norm": 0.14044098556041718,
|
| 486 |
+
"learning_rate": 4.699569989541074e-05,
|
| 487 |
+
"loss": 1.1661159992218018,
|
| 488 |
+
"mean_token_accuracy": 0.6632223278284073,
|
| 489 |
+
"num_tokens": 6184519.0,
|
| 490 |
+
"step": 48
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"entropy": 1.1261081546545029,
|
| 494 |
+
"epoch": 0.6302250803858521,
|
| 495 |
+
"grad_norm": 0.13071966171264648,
|
| 496 |
+
"learning_rate": 4.6825352829029705e-05,
|
| 497 |
+
"loss": 1.1280871629714966,
|
| 498 |
+
"mean_token_accuracy": 0.672090008854866,
|
| 499 |
+
"num_tokens": 6313996.0,
|
| 500 |
+
"step": 49
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"entropy": 1.108861967921257,
|
| 504 |
+
"epoch": 0.6430868167202572,
|
| 505 |
+
"grad_norm": 0.13524308800697327,
|
| 506 |
+
"learning_rate": 4.665063509461097e-05,
|
| 507 |
+
"loss": 1.1100517511367798,
|
| 508 |
+
"mean_token_accuracy": 0.6758645325899124,
|
| 509 |
+
"num_tokens": 6442914.0,
|
| 510 |
+
"step": 50
|
| 511 |
+
},
|
| 512 |
+
{
|
| 513 |
+
"entropy": 1.1622951924800873,
|
| 514 |
+
"epoch": 0.6559485530546624,
|
| 515 |
+
"grad_norm": 0.14350417256355286,
|
| 516 |
+
"learning_rate": 4.647158168051066e-05,
|
| 517 |
+
"loss": 1.1698243618011475,
|
| 518 |
+
"mean_token_accuracy": 0.661836288869381,
|
| 519 |
+
"num_tokens": 6569312.0,
|
| 520 |
+
"step": 51
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"entropy": 1.1530523151159286,
|
| 524 |
+
"epoch": 0.6688102893890675,
|
| 525 |
+
"grad_norm": 0.13998498022556305,
|
| 526 |
+
"learning_rate": 4.628822844333278e-05,
|
| 527 |
+
"loss": 1.135171890258789,
|
| 528 |
+
"mean_token_accuracy": 0.6697984710335732,
|
| 529 |
+
"num_tokens": 6698149.0,
|
| 530 |
+
"step": 52
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"entropy": 1.1557507067918777,
|
| 534 |
+
"epoch": 0.6816720257234726,
|
| 535 |
+
"grad_norm": 0.13826699554920197,
|
| 536 |
+
"learning_rate": 4.6100612100748765e-05,
|
| 537 |
+
"loss": 1.1333105564117432,
|
| 538 |
+
"mean_token_accuracy": 0.6696186140179634,
|
| 539 |
+
"num_tokens": 6827547.0,
|
| 540 |
+
"step": 53
|
| 541 |
+
},
|
| 542 |
+
{
|
| 543 |
+
"entropy": 1.1415271162986755,
|
| 544 |
+
"epoch": 0.6945337620578779,
|
| 545 |
+
"grad_norm": 0.14170631766319275,
|
| 546 |
+
"learning_rate": 4.59087702241444e-05,
|
| 547 |
+
"loss": 1.1154472827911377,
|
| 548 |
+
"mean_token_accuracy": 0.6728732585906982,
|
| 549 |
+
"num_tokens": 6956641.0,
|
| 550 |
+
"step": 54
|
| 551 |
+
},
|
| 552 |
+
{
|
| 553 |
+
"entropy": 1.133439689874649,
|
| 554 |
+
"epoch": 0.707395498392283,
|
| 555 |
+
"grad_norm": 0.19915136694908142,
|
| 556 |
+
"learning_rate": 4.571274123109606e-05,
|
| 557 |
+
"loss": 1.12148916721344,
|
| 558 |
+
"mean_token_accuracy": 0.6721195057034492,
|
| 559 |
+
"num_tokens": 7087072.0,
|
| 560 |
+
"step": 55
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"entropy": 1.1475654691457748,
|
| 564 |
+
"epoch": 0.7202572347266881,
|
| 565 |
+
"grad_norm": 0.1380179524421692,
|
| 566 |
+
"learning_rate": 4.551256437767719e-05,
|
| 567 |
+
"loss": 1.147176742553711,
|
| 568 |
+
"mean_token_accuracy": 0.6669263690710068,
|
| 569 |
+
"num_tokens": 7217233.0,
|
| 570 |
+
"step": 56
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"entropy": 1.1235886365175247,
|
| 574 |
+
"epoch": 0.7331189710610932,
|
| 575 |
+
"grad_norm": 0.14977428317070007,
|
| 576 |
+
"learning_rate": 4.530827975059715e-05,
|
| 577 |
+
"loss": 1.1248936653137207,
|
| 578 |
+
"mean_token_accuracy": 0.6717223599553108,
|
| 579 |
+
"num_tokens": 7345601.0,
|
| 580 |
+
"step": 57
|
| 581 |
+
},
|
| 582 |
+
{
|
| 583 |
+
"entropy": 1.0966329723596573,
|
| 584 |
+
"epoch": 0.7459807073954984,
|
| 585 |
+
"grad_norm": 0.13217344880104065,
|
| 586 |
+
"learning_rate": 4.5099928259173516e-05,
|
| 587 |
+
"loss": 1.0947030782699585,
|
| 588 |
+
"mean_token_accuracy": 0.6786246225237846,
|
| 589 |
+
"num_tokens": 7473430.0,
|
| 590 |
+
"step": 58
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"entropy": 1.1365204900503159,
|
| 594 |
+
"epoch": 0.7588424437299035,
|
| 595 |
+
"grad_norm": 0.12866446375846863,
|
| 596 |
+
"learning_rate": 4.488755162713975e-05,
|
| 597 |
+
"loss": 1.126430869102478,
|
| 598 |
+
"mean_token_accuracy": 0.6728999614715576,
|
| 599 |
+
"num_tokens": 7602826.0,
|
| 600 |
+
"step": 59
|
| 601 |
+
},
|
| 602 |
+
{
|
| 603 |
+
"entropy": 1.1535387188196182,
|
| 604 |
+
"epoch": 0.7717041800643086,
|
| 605 |
+
"grad_norm": 0.1415134221315384,
|
| 606 |
+
"learning_rate": 4.467119238428975e-05,
|
| 607 |
+
"loss": 1.1418571472167969,
|
| 608 |
+
"mean_token_accuracy": 0.6701028272509575,
|
| 609 |
+
"num_tokens": 7732028.0,
|
| 610 |
+
"step": 60
|
| 611 |
+
},
|
| 612 |
+
{
|
| 613 |
+
"entropy": 1.1234214305877686,
|
| 614 |
+
"epoch": 0.7845659163987139,
|
| 615 |
+
"grad_norm": 0.14994795620441437,
|
| 616 |
+
"learning_rate": 4.445089385796099e-05,
|
| 617 |
+
"loss": 1.1106842756271362,
|
| 618 |
+
"mean_token_accuracy": 0.6764309927821159,
|
| 619 |
+
"num_tokens": 7860385.0,
|
| 620 |
+
"step": 61
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"entropy": 1.0901593267917633,
|
| 624 |
+
"epoch": 0.797427652733119,
|
| 625 |
+
"grad_norm": 0.13637474179267883,
|
| 626 |
+
"learning_rate": 4.422670016435792e-05,
|
| 627 |
+
"loss": 1.0811570882797241,
|
| 628 |
+
"mean_token_accuracy": 0.6831180602312088,
|
| 629 |
+
"num_tokens": 7989531.0,
|
| 630 |
+
"step": 62
|
| 631 |
+
},
|
| 632 |
+
{
|
| 633 |
+
"entropy": 1.1060381978750229,
|
| 634 |
+
"epoch": 0.8102893890675241,
|
| 635 |
+
"grad_norm": 0.1306847780942917,
|
| 636 |
+
"learning_rate": 4.3998656199717435e-05,
|
| 637 |
+
"loss": 1.1069831848144531,
|
| 638 |
+
"mean_token_accuracy": 0.6745292320847511,
|
| 639 |
+
"num_tokens": 8118824.0,
|
| 640 |
+
"step": 63
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"entropy": 1.1469190865755081,
|
| 644 |
+
"epoch": 0.8231511254019293,
|
| 645 |
+
"grad_norm": 0.14836829900741577,
|
| 646 |
+
"learning_rate": 4.3766807631318106e-05,
|
| 647 |
+
"loss": 1.1478967666625977,
|
| 648 |
+
"mean_token_accuracy": 0.6674168556928635,
|
| 649 |
+
"num_tokens": 8248122.0,
|
| 650 |
+
"step": 64
|
| 651 |
+
},
|
| 652 |
+
{
|
| 653 |
+
"entropy": 1.1051507145166397,
|
| 654 |
+
"epoch": 0.8360128617363344,
|
| 655 |
+
"grad_norm": 0.1413162350654602,
|
| 656 |
+
"learning_rate": 4.353120088833501e-05,
|
| 657 |
+
"loss": 1.0933685302734375,
|
| 658 |
+
"mean_token_accuracy": 0.6783376038074493,
|
| 659 |
+
"num_tokens": 8376429.0,
|
| 660 |
+
"step": 65
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"entropy": 1.1381653249263763,
|
| 664 |
+
"epoch": 0.8488745980707395,
|
| 665 |
+
"grad_norm": 0.13279159367084503,
|
| 666 |
+
"learning_rate": 4.329188315254196e-05,
|
| 667 |
+
"loss": 1.1261053085327148,
|
| 668 |
+
"mean_token_accuracy": 0.6716507449746132,
|
| 669 |
+
"num_tokens": 8504687.0,
|
| 670 |
+
"step": 66
|
| 671 |
+
},
|
| 672 |
+
{
|
| 673 |
+
"entropy": 1.1401405185461044,
|
| 674 |
+
"epoch": 0.8617363344051447,
|
| 675 |
+
"grad_norm": 0.14999179542064667,
|
| 676 |
+
"learning_rate": 4.3048902348863116e-05,
|
| 677 |
+
"loss": 1.122992992401123,
|
| 678 |
+
"mean_token_accuracy": 0.6721775308251381,
|
| 679 |
+
"num_tokens": 8635119.0,
|
| 680 |
+
"step": 67
|
| 681 |
+
},
|
| 682 |
+
{
|
| 683 |
+
"entropy": 1.1104646772146225,
|
| 684 |
+
"epoch": 0.8745980707395499,
|
| 685 |
+
"grad_norm": 0.15244296193122864,
|
| 686 |
+
"learning_rate": 4.280230713577564e-05,
|
| 687 |
+
"loss": 1.0963469743728638,
|
| 688 |
+
"mean_token_accuracy": 0.6784974113106728,
|
| 689 |
+
"num_tokens": 8765133.0,
|
| 690 |
+
"step": 68
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"entropy": 1.1325141787528992,
|
| 694 |
+
"epoch": 0.887459807073955,
|
| 695 |
+
"grad_norm": 0.13338243961334229,
|
| 696 |
+
"learning_rate": 4.255214689556557e-05,
|
| 697 |
+
"loss": 1.133899211883545,
|
| 698 |
+
"mean_token_accuracy": 0.6714881733059883,
|
| 699 |
+
"num_tokens": 8895437.0,
|
| 700 |
+
"step": 69
|
| 701 |
+
},
|
| 702 |
+
{
|
| 703 |
+
"entropy": 1.1021241694688797,
|
| 704 |
+
"epoch": 0.9003215434083601,
|
| 705 |
+
"grad_norm": 0.14672274887561798,
|
| 706 |
+
"learning_rate": 4.229847172443866e-05,
|
| 707 |
+
"loss": 1.1050517559051514,
|
| 708 |
+
"mean_token_accuracy": 0.6782850474119186,
|
| 709 |
+
"num_tokens": 9023472.0,
|
| 710 |
+
"step": 70
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"entropy": 1.0665733218193054,
|
| 714 |
+
"epoch": 0.9131832797427653,
|
| 715 |
+
"grad_norm": 0.1326168030500412,
|
| 716 |
+
"learning_rate": 4.204133242248832e-05,
|
| 717 |
+
"loss": 1.0614970922470093,
|
| 718 |
+
"mean_token_accuracy": 0.6890874728560448,
|
| 719 |
+
"num_tokens": 9152924.0,
|
| 720 |
+
"step": 71
|
| 721 |
+
},
|
| 722 |
+
{
|
| 723 |
+
"entropy": 1.0804976969957352,
|
| 724 |
+
"epoch": 0.9260450160771704,
|
| 725 |
+
"grad_norm": 0.14258776605129242,
|
| 726 |
+
"learning_rate": 4.1780780483522575e-05,
|
| 727 |
+
"loss": 1.071770191192627,
|
| 728 |
+
"mean_token_accuracy": 0.6831802353262901,
|
| 729 |
+
"num_tokens": 9282930.0,
|
| 730 |
+
"step": 72
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"entropy": 1.0698173642158508,
|
| 734 |
+
"epoch": 0.9389067524115756,
|
| 735 |
+
"grad_norm": 0.13697165250778198,
|
| 736 |
+
"learning_rate": 4.151686808475204e-05,
|
| 737 |
+
"loss": 1.057246208190918,
|
| 738 |
+
"mean_token_accuracy": 0.6859329044818878,
|
| 739 |
+
"num_tokens": 9410776.0,
|
| 740 |
+
"step": 73
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"entropy": 1.0982066690921783,
|
| 744 |
+
"epoch": 0.9517684887459807,
|
| 745 |
+
"grad_norm": 0.14332003891468048,
|
| 746 |
+
"learning_rate": 4.1249648076341165e-05,
|
| 747 |
+
"loss": 1.08486008644104,
|
| 748 |
+
"mean_token_accuracy": 0.6810793280601501,
|
| 749 |
+
"num_tokens": 9539314.0,
|
| 750 |
+
"step": 74
|
| 751 |
+
},
|
| 752 |
+
{
|
| 753 |
+
"entropy": 1.1045535802841187,
|
| 754 |
+
"epoch": 0.9646302250803859,
|
| 755 |
+
"grad_norm": 0.14386016130447388,
|
| 756 |
+
"learning_rate": 4.0979173970824626e-05,
|
| 757 |
+
"loss": 1.1035948991775513,
|
| 758 |
+
"mean_token_accuracy": 0.6733438894152641,
|
| 759 |
+
"num_tokens": 9668102.0,
|
| 760 |
+
"step": 75
|
| 761 |
+
},
|
| 762 |
+
{
|
| 763 |
+
"entropy": 1.0924865305423737,
|
| 764 |
+
"epoch": 0.977491961414791,
|
| 765 |
+
"grad_norm": 0.13745297491550446,
|
| 766 |
+
"learning_rate": 4.070549993239106e-05,
|
| 767 |
+
"loss": 1.090521216392517,
|
| 768 |
+
"mean_token_accuracy": 0.6789770871400833,
|
| 769 |
+
"num_tokens": 9797707.0,
|
| 770 |
+
"step": 76
|
| 771 |
+
},
|
| 772 |
+
{
|
| 773 |
+
"entropy": 1.0984582901000977,
|
| 774 |
+
"epoch": 0.9903536977491961,
|
| 775 |
+
"grad_norm": 0.14490951597690582,
|
| 776 |
+
"learning_rate": 4.0428680766036384e-05,
|
| 777 |
+
"loss": 1.1076843738555908,
|
| 778 |
+
"mean_token_accuracy": 0.6759174689650536,
|
| 779 |
+
"num_tokens": 9927684.0,
|
| 780 |
+
"step": 77
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"entropy": 1.0977885921796162,
|
| 784 |
+
"epoch": 1.0,
|
| 785 |
+
"grad_norm": 0.15585829317569733,
|
| 786 |
+
"learning_rate": 4.0148771906588706e-05,
|
| 787 |
+
"loss": 1.0940134525299072,
|
| 788 |
+
"mean_token_accuracy": 0.6789492865403494,
|
| 789 |
+
"num_tokens": 9998574.0,
|
| 790 |
+
"step": 78
|
| 791 |
+
},
|
| 792 |
+
{
|
| 793 |
+
"entropy": 1.1048902124166489,
|
| 794 |
+
"epoch": 1.0128617363344052,
|
| 795 |
+
"grad_norm": 0.13507987558841705,
|
| 796 |
+
"learning_rate": 3.986582940760717e-05,
|
| 797 |
+
"loss": 1.0746995210647583,
|
| 798 |
+
"mean_token_accuracy": 0.6833242624998093,
|
| 799 |
+
"num_tokens": 10127337.0,
|
| 800 |
+
"step": 79
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"entropy": 1.1200366914272308,
|
| 804 |
+
"epoch": 1.0257234726688103,
|
| 805 |
+
"grad_norm": 0.14873428642749786,
|
| 806 |
+
"learning_rate": 3.957990993015683e-05,
|
| 807 |
+
"loss": 1.0768001079559326,
|
| 808 |
+
"mean_token_accuracy": 0.6837869137525558,
|
| 809 |
+
"num_tokens": 10253323.0,
|
| 810 |
+
"step": 80
|
| 811 |
+
},
|
| 812 |
+
{
|
| 813 |
+
"entropy": 1.1033698171377182,
|
| 814 |
+
"epoch": 1.0385852090032155,
|
| 815 |
+
"grad_norm": 0.1395098865032196,
|
| 816 |
+
"learning_rate": 3.929107073146197e-05,
|
| 817 |
+
"loss": 1.0733070373535156,
|
| 818 |
+
"mean_token_accuracy": 0.6825986951589584,
|
| 819 |
+
"num_tokens": 10383034.0,
|
| 820 |
+
"step": 81
|
| 821 |
+
},
|
| 822 |
+
{
|
| 823 |
+
"entropy": 1.0916118025779724,
|
| 824 |
+
"epoch": 1.0514469453376205,
|
| 825 |
+
"grad_norm": 0.156707301735878,
|
| 826 |
+
"learning_rate": 3.899936965343989e-05,
|
| 827 |
+
"loss": 1.0789391994476318,
|
| 828 |
+
"mean_token_accuracy": 0.6803915277123451,
|
| 829 |
+
"num_tokens": 10512684.0,
|
| 830 |
+
"step": 82
|
| 831 |
+
},
|
| 832 |
+
{
|
| 833 |
+
"entropy": 1.0437547490000725,
|
| 834 |
+
"epoch": 1.0643086816720257,
|
| 835 |
+
"grad_norm": 0.14007939398288727,
|
| 836 |
+
"learning_rate": 3.8704865111117746e-05,
|
| 837 |
+
"loss": 1.046311378479004,
|
| 838 |
+
"mean_token_accuracy": 0.6876395344734192,
|
| 839 |
+
"num_tokens": 10642582.0,
|
| 840 |
+
"step": 83
|
| 841 |
+
},
|
| 842 |
+
{
|
| 843 |
+
"entropy": 1.0586023032665253,
|
| 844 |
+
"epoch": 1.077170418006431,
|
| 845 |
+
"grad_norm": 0.14878074824810028,
|
| 846 |
+
"learning_rate": 3.840761608093456e-05,
|
| 847 |
+
"loss": 1.0626013278961182,
|
| 848 |
+
"mean_token_accuracy": 0.6854664832353592,
|
| 849 |
+
"num_tokens": 10772130.0,
|
| 850 |
+
"step": 84
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"entropy": 1.042947493493557,
|
| 854 |
+
"epoch": 1.090032154340836,
|
| 855 |
+
"grad_norm": 0.14047543704509735,
|
| 856 |
+
"learning_rate": 3.8107682088930794e-05,
|
| 857 |
+
"loss": 1.0462985038757324,
|
| 858 |
+
"mean_token_accuracy": 0.6900991648435593,
|
| 859 |
+
"num_tokens": 10902329.0,
|
| 860 |
+
"step": 85
|
| 861 |
+
},
|
| 862 |
+
{
|
| 863 |
+
"entropy": 1.0503267794847488,
|
| 864 |
+
"epoch": 1.1028938906752412,
|
| 865 |
+
"grad_norm": 0.13753578066825867,
|
| 866 |
+
"learning_rate": 3.7805123198827857e-05,
|
| 867 |
+
"loss": 1.0447890758514404,
|
| 868 |
+
"mean_token_accuracy": 0.6877391710877419,
|
| 869 |
+
"num_tokens": 11032146.0,
|
| 870 |
+
"step": 86
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"entropy": 1.0541549250483513,
|
| 874 |
+
"epoch": 1.1157556270096463,
|
| 875 |
+
"grad_norm": 0.14761823415756226,
|
| 876 |
+
"learning_rate": 3.7500000000000003e-05,
|
| 877 |
+
"loss": 1.0494050979614258,
|
| 878 |
+
"mean_token_accuracy": 0.6881443187594414,
|
| 879 |
+
"num_tokens": 11162722.0,
|
| 880 |
+
"step": 87
|
| 881 |
+
},
|
| 882 |
+
{
|
| 883 |
+
"entropy": 1.0610276013612747,
|
| 884 |
+
"epoch": 1.1286173633440515,
|
| 885 |
+
"grad_norm": 0.13982513546943665,
|
| 886 |
+
"learning_rate": 3.719237359534087e-05,
|
| 887 |
+
"loss": 1.0486375093460083,
|
| 888 |
+
"mean_token_accuracy": 0.6868740543723106,
|
| 889 |
+
"num_tokens": 11291557.0,
|
| 890 |
+
"step": 88
|
| 891 |
+
},
|
| 892 |
+
{
|
| 893 |
+
"entropy": 1.0592399910092354,
|
| 894 |
+
"epoch": 1.1414790996784565,
|
| 895 |
+
"grad_norm": 0.14512217044830322,
|
| 896 |
+
"learning_rate": 3.688230558902725e-05,
|
| 897 |
+
"loss": 1.0511451959609985,
|
| 898 |
+
"mean_token_accuracy": 0.6883272528648376,
|
| 899 |
+
"num_tokens": 11420683.0,
|
| 900 |
+
"step": 89
|
| 901 |
+
},
|
| 902 |
+
{
|
| 903 |
+
"entropy": 1.1003997921943665,
|
| 904 |
+
"epoch": 1.1543408360128617,
|
| 905 |
+
"grad_norm": 0.13833674788475037,
|
| 906 |
+
"learning_rate": 3.656985807418248e-05,
|
| 907 |
+
"loss": 1.0804483890533447,
|
| 908 |
+
"mean_token_accuracy": 0.6791831701993942,
|
| 909 |
+
"num_tokens": 11549517.0,
|
| 910 |
+
"step": 90
|
| 911 |
+
},
|
| 912 |
+
{
|
| 913 |
+
"entropy": 1.058895729482174,
|
| 914 |
+
"epoch": 1.167202572347267,
|
| 915 |
+
"grad_norm": 0.14019837975502014,
|
| 916 |
+
"learning_rate": 3.6255093620441834e-05,
|
| 917 |
+
"loss": 1.0490373373031616,
|
| 918 |
+
"mean_token_accuracy": 0.6885469257831573,
|
| 919 |
+
"num_tokens": 11678919.0,
|
| 920 |
+
"step": 91
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"entropy": 1.0490736663341522,
|
| 924 |
+
"epoch": 1.180064308681672,
|
| 925 |
+
"grad_norm": 0.15101630985736847,
|
| 926 |
+
"learning_rate": 3.593807526142261e-05,
|
| 927 |
+
"loss": 1.0475131273269653,
|
| 928 |
+
"mean_token_accuracy": 0.6890112012624741,
|
| 929 |
+
"num_tokens": 11808171.0,
|
| 930 |
+
"step": 92
|
| 931 |
+
},
|
| 932 |
+
{
|
| 933 |
+
"entropy": 1.067186251282692,
|
| 934 |
+
"epoch": 1.1929260450160772,
|
| 935 |
+
"grad_norm": 0.14192728698253632,
|
| 936 |
+
"learning_rate": 3.56188664821012e-05,
|
| 937 |
+
"loss": 1.068861961364746,
|
| 938 |
+
"mean_token_accuracy": 0.6839301511645317,
|
| 939 |
+
"num_tokens": 11937495.0,
|
| 940 |
+
"step": 93
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"entropy": 1.0729520842432976,
|
| 944 |
+
"epoch": 1.2057877813504823,
|
| 945 |
+
"grad_norm": 0.13931463658809662,
|
| 946 |
+
"learning_rate": 3.529753120609982e-05,
|
| 947 |
+
"loss": 1.0626987218856812,
|
| 948 |
+
"mean_token_accuracy": 0.6865019202232361,
|
| 949 |
+
"num_tokens": 12065721.0,
|
| 950 |
+
"step": 94
|
| 951 |
+
},
|
| 952 |
+
{
|
| 953 |
+
"entropy": 1.0651484578847885,
|
| 954 |
+
"epoch": 1.2186495176848875,
|
| 955 |
+
"grad_norm": 0.14170296490192413,
|
| 956 |
+
"learning_rate": 3.497413378288541e-05,
|
| 957 |
+
"loss": 1.065182089805603,
|
| 958 |
+
"mean_token_accuracy": 0.6859815120697021,
|
| 959 |
+
"num_tokens": 12195222.0,
|
| 960 |
+
"step": 95
|
| 961 |
+
},
|
| 962 |
+
{
|
| 963 |
+
"entropy": 1.0627811029553413,
|
| 964 |
+
"epoch": 1.2315112540192925,
|
| 965 |
+
"grad_norm": 0.15864631533622742,
|
| 966 |
+
"learning_rate": 3.464873897488322e-05,
|
| 967 |
+
"loss": 1.064727783203125,
|
| 968 |
+
"mean_token_accuracy": 0.6850855350494385,
|
| 969 |
+
"num_tokens": 12325399.0,
|
| 970 |
+
"step": 96
|
| 971 |
+
},
|
| 972 |
+
{
|
| 973 |
+
"entropy": 1.0540687665343285,
|
| 974 |
+
"epoch": 1.2443729903536977,
|
| 975 |
+
"grad_norm": 0.1563236117362976,
|
| 976 |
+
"learning_rate": 3.432141194450772e-05,
|
| 977 |
+
"loss": 1.0473036766052246,
|
| 978 |
+
"mean_token_accuracy": 0.6896297782659531,
|
| 979 |
+
"num_tokens": 12455203.0,
|
| 980 |
+
"step": 97
|
| 981 |
+
},
|
| 982 |
+
{
|
| 983 |
+
"entropy": 1.0381047055125237,
|
| 984 |
+
"epoch": 1.257234726688103,
|
| 985 |
+
"grad_norm": 0.1378972828388214,
|
| 986 |
+
"learning_rate": 3.39922182411134e-05,
|
| 987 |
+
"loss": 1.0351678133010864,
|
| 988 |
+
"mean_token_accuracy": 0.6909719184041023,
|
| 989 |
+
"num_tokens": 12582864.0,
|
| 990 |
+
"step": 98
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"entropy": 1.0567686855793,
|
| 994 |
+
"epoch": 1.270096463022508,
|
| 995 |
+
"grad_norm": 0.1447557955980301,
|
| 996 |
+
"learning_rate": 3.3661223787868094e-05,
|
| 997 |
+
"loss": 1.045164704322815,
|
| 998 |
+
"mean_token_accuracy": 0.6886090338230133,
|
| 999 |
+
"num_tokens": 12711992.0,
|
| 1000 |
+
"step": 99
|
| 1001 |
+
},
|
| 1002 |
+
{
|
| 1003 |
+
"entropy": 1.0664659440517426,
|
| 1004 |
+
"epoch": 1.2829581993569132,
|
| 1005 |
+
"grad_norm": 0.14579758048057556,
|
| 1006 |
+
"learning_rate": 3.332849486855144e-05,
|
| 1007 |
+
"loss": 1.0578923225402832,
|
| 1008 |
+
"mean_token_accuracy": 0.6857578605413437,
|
| 1009 |
+
"num_tokens": 12841160.0,
|
| 1010 |
+
"step": 100
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"entropy": 1.0501502603292465,
|
| 1014 |
+
"epoch": 1.2958199356913183,
|
| 1015 |
+
"grad_norm": 0.14204849302768707,
|
| 1016 |
+
"learning_rate": 3.2994098114281134e-05,
|
| 1017 |
+
"loss": 1.0381393432617188,
|
| 1018 |
+
"mean_token_accuracy": 0.6887901425361633,
|
| 1019 |
+
"num_tokens": 12967285.0,
|
| 1020 |
+
"step": 101
|
| 1021 |
+
},
|
| 1022 |
+
{
|
| 1023 |
+
"entropy": 1.0534097403287888,
|
| 1024 |
+
"epoch": 1.3086816720257235,
|
| 1025 |
+
"grad_norm": 0.1419542282819748,
|
| 1026 |
+
"learning_rate": 3.265810049016959e-05,
|
| 1027 |
+
"loss": 1.0446325540542603,
|
| 1028 |
+
"mean_token_accuracy": 0.6880638003349304,
|
| 1029 |
+
"num_tokens": 13095177.0,
|
| 1030 |
+
"step": 102
|
| 1031 |
+
},
|
| 1032 |
+
{
|
| 1033 |
+
"entropy": 1.0461725443601608,
|
| 1034 |
+
"epoch": 1.3215434083601285,
|
| 1035 |
+
"grad_norm": 0.14444847404956818,
|
| 1036 |
+
"learning_rate": 3.232056928191376e-05,
|
| 1037 |
+
"loss": 1.032381296157837,
|
| 1038 |
+
"mean_token_accuracy": 0.691328376531601,
|
| 1039 |
+
"num_tokens": 13224870.0,
|
| 1040 |
+
"step": 103
|
| 1041 |
+
},
|
| 1042 |
+
{
|
| 1043 |
+
"entropy": 1.0287123173475266,
|
| 1044 |
+
"epoch": 1.3344051446945338,
|
| 1045 |
+
"grad_norm": 0.14262095093727112,
|
| 1046 |
+
"learning_rate": 3.1981572082320756e-05,
|
| 1047 |
+
"loss": 1.0161638259887695,
|
| 1048 |
+
"mean_token_accuracy": 0.6958137080073357,
|
| 1049 |
+
"num_tokens": 13355092.0,
|
| 1050 |
+
"step": 104
|
| 1051 |
+
},
|
| 1052 |
+
{
|
| 1053 |
+
"entropy": 1.0425420626997948,
|
| 1054 |
+
"epoch": 1.347266881028939,
|
| 1055 |
+
"grad_norm": 0.14054642617702484,
|
| 1056 |
+
"learning_rate": 3.164117677777191e-05,
|
| 1057 |
+
"loss": 1.037819266319275,
|
| 1058 |
+
"mean_token_accuracy": 0.690584309399128,
|
| 1059 |
+
"num_tokens": 13482910.0,
|
| 1060 |
+
"step": 105
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"entropy": 1.0867420881986618,
|
| 1064 |
+
"epoch": 1.360128617363344,
|
| 1065 |
+
"grad_norm": 0.14352700114250183,
|
| 1066 |
+
"learning_rate": 3.1299451534628135e-05,
|
| 1067 |
+
"loss": 1.0806154012680054,
|
| 1068 |
+
"mean_token_accuracy": 0.6801560521125793,
|
| 1069 |
+
"num_tokens": 13610860.0,
|
| 1070 |
+
"step": 106
|
| 1071 |
+
},
|
| 1072 |
+
{
|
| 1073 |
+
"entropy": 1.0425082966685295,
|
| 1074 |
+
"epoch": 1.3729903536977492,
|
| 1075 |
+
"grad_norm": 0.14772510528564453,
|
| 1076 |
+
"learning_rate": 3.0956464785579124e-05,
|
| 1077 |
+
"loss": 1.0282400846481323,
|
| 1078 |
+
"mean_token_accuracy": 0.6922867074608803,
|
| 1079 |
+
"num_tokens": 13739967.0,
|
| 1080 |
+
"step": 107
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"entropy": 1.033432051539421,
|
| 1084 |
+
"epoch": 1.3858520900321543,
|
| 1085 |
+
"grad_norm": 0.1441124826669693,
|
| 1086 |
+
"learning_rate": 3.061228521593931e-05,
|
| 1087 |
+
"loss": 1.0348222255706787,
|
| 1088 |
+
"mean_token_accuracy": 0.6906738951802254,
|
| 1089 |
+
"num_tokens": 13869092.0,
|
| 1090 |
+
"step": 108
|
| 1091 |
+
},
|
| 1092 |
+
{
|
| 1093 |
+
"entropy": 1.0250284597277641,
|
| 1094 |
+
"epoch": 1.3987138263665595,
|
| 1095 |
+
"grad_norm": 0.14241281151771545,
|
| 1096 |
+
"learning_rate": 3.0266981749893157e-05,
|
| 1097 |
+
"loss": 1.019615650177002,
|
| 1098 |
+
"mean_token_accuracy": 0.6946801096200943,
|
| 1099 |
+
"num_tokens": 13999751.0,
|
| 1100 |
+
"step": 109
|
| 1101 |
+
},
|
| 1102 |
+
{
|
| 1103 |
+
"entropy": 1.0539506748318672,
|
| 1104 |
+
"epoch": 1.4115755627009645,
|
| 1105 |
+
"grad_norm": 0.14640918374061584,
|
| 1106 |
+
"learning_rate": 2.9920623536692638e-05,
|
| 1107 |
+
"loss": 1.0554652214050293,
|
| 1108 |
+
"mean_token_accuracy": 0.6877814680337906,
|
| 1109 |
+
"num_tokens": 14126193.0,
|
| 1110 |
+
"step": 110
|
| 1111 |
+
},
|
| 1112 |
+
{
|
| 1113 |
+
"entropy": 1.0477852746844292,
|
| 1114 |
+
"epoch": 1.4244372990353698,
|
| 1115 |
+
"grad_norm": 0.13899168372154236,
|
| 1116 |
+
"learning_rate": 2.9573279936809667e-05,
|
| 1117 |
+
"loss": 1.0390174388885498,
|
| 1118 |
+
"mean_token_accuracy": 0.6889165490865707,
|
| 1119 |
+
"num_tokens": 14255192.0,
|
| 1120 |
+
"step": 111
|
| 1121 |
+
},
|
| 1122 |
+
{
|
| 1123 |
+
"entropy": 1.028913527727127,
|
| 1124 |
+
"epoch": 1.437299035369775,
|
| 1125 |
+
"grad_norm": 0.14846587181091309,
|
| 1126 |
+
"learning_rate": 2.9225020508046232e-05,
|
| 1127 |
+
"loss": 1.02781343460083,
|
| 1128 |
+
"mean_token_accuracy": 0.6925171986222267,
|
| 1129 |
+
"num_tokens": 14383678.0,
|
| 1130 |
+
"step": 112
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"entropy": 1.040368527173996,
|
| 1134 |
+
"epoch": 1.45016077170418,
|
| 1135 |
+
"grad_norm": 0.14321881532669067,
|
| 1136 |
+
"learning_rate": 2.8875914991604948e-05,
|
| 1137 |
+
"loss": 1.040635108947754,
|
| 1138 |
+
"mean_token_accuracy": 0.6885931342840195,
|
| 1139 |
+
"num_tokens": 14513886.0,
|
| 1140 |
+
"step": 113
|
| 1141 |
+
},
|
| 1142 |
+
{
|
| 1143 |
+
"entropy": 1.0307907313108444,
|
| 1144 |
+
"epoch": 1.4630225080385852,
|
| 1145 |
+
"grad_norm": 0.13824157416820526,
|
| 1146 |
+
"learning_rate": 2.8526033298122985e-05,
|
| 1147 |
+
"loss": 1.0185027122497559,
|
| 1148 |
+
"mean_token_accuracy": 0.6952621415257454,
|
| 1149 |
+
"num_tokens": 14644185.0,
|
| 1150 |
+
"step": 114
|
| 1151 |
+
},
|
| 1152 |
+
{
|
| 1153 |
+
"entropy": 1.0155034512281418,
|
| 1154 |
+
"epoch": 1.4758842443729905,
|
| 1155 |
+
"grad_norm": 0.14209888875484467,
|
| 1156 |
+
"learning_rate": 2.8175445493671972e-05,
|
| 1157 |
+
"loss": 0.996734619140625,
|
| 1158 |
+
"mean_token_accuracy": 0.6990666836500168,
|
| 1159 |
+
"num_tokens": 14769497.0,
|
| 1160 |
+
"step": 115
|
| 1161 |
+
},
|
| 1162 |
+
{
|
| 1163 |
+
"entropy": 1.021187648177147,
|
| 1164 |
+
"epoch": 1.4887459807073955,
|
| 1165 |
+
"grad_norm": 0.14187516272068024,
|
| 1166 |
+
"learning_rate": 2.782422178572682e-05,
|
| 1167 |
+
"loss": 1.0097088813781738,
|
| 1168 |
+
"mean_token_accuracy": 0.6962587013840675,
|
| 1169 |
+
"num_tokens": 14898899.0,
|
| 1170 |
+
"step": 116
|
| 1171 |
+
},
|
| 1172 |
+
{
|
| 1173 |
+
"entropy": 1.0390162095427513,
|
| 1174 |
+
"epoch": 1.5016077170418005,
|
| 1175 |
+
"grad_norm": 0.1539003998041153,
|
| 1176 |
+
"learning_rate": 2.7472432509106248e-05,
|
| 1177 |
+
"loss": 1.0348460674285889,
|
| 1178 |
+
"mean_token_accuracy": 0.6902582123875618,
|
| 1179 |
+
"num_tokens": 15029008.0,
|
| 1180 |
+
"step": 117
|
| 1181 |
+
},
|
| 1182 |
+
{
|
| 1183 |
+
"entropy": 1.084839791059494,
|
| 1184 |
+
"epoch": 1.5144694533762058,
|
| 1185 |
+
"grad_norm": 0.15639474987983704,
|
| 1186 |
+
"learning_rate": 2.7120148111887732e-05,
|
| 1187 |
+
"loss": 1.0750864744186401,
|
| 1188 |
+
"mean_token_accuracy": 0.6826967149972916,
|
| 1189 |
+
"num_tokens": 15157238.0,
|
| 1190 |
+
"step": 118
|
| 1191 |
+
},
|
| 1192 |
+
{
|
| 1193 |
+
"entropy": 1.0497614741325378,
|
| 1194 |
+
"epoch": 1.527331189710611,
|
| 1195 |
+
"grad_norm": 0.14684948325157166,
|
| 1196 |
+
"learning_rate": 2.6767439141299865e-05,
|
| 1197 |
+
"loss": 1.0455033779144287,
|
| 1198 |
+
"mean_token_accuracy": 0.6880874261260033,
|
| 1199 |
+
"num_tokens": 15285438.0,
|
| 1200 |
+
"step": 119
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"entropy": 1.03941510617733,
|
| 1204 |
+
"epoch": 1.540192926045016,
|
| 1205 |
+
"grad_norm": 0.143926739692688,
|
| 1206 |
+
"learning_rate": 2.6414376229594813e-05,
|
| 1207 |
+
"loss": 1.0348516702651978,
|
| 1208 |
+
"mean_token_accuracy": 0.6904465183615685,
|
| 1209 |
+
"num_tokens": 15413195.0,
|
| 1210 |
+
"step": 120
|
| 1211 |
+
},
|
| 1212 |
+
{
|
| 1213 |
+
"entropy": 1.0160878226161003,
|
| 1214 |
+
"epoch": 1.5530546623794212,
|
| 1215 |
+
"grad_norm": 0.14575257897377014,
|
| 1216 |
+
"learning_rate": 2.606103007990371e-05,
|
| 1217 |
+
"loss": 1.006327509880066,
|
| 1218 |
+
"mean_token_accuracy": 0.6950085982680321,
|
| 1219 |
+
"num_tokens": 15542436.0,
|
| 1220 |
+
"step": 121
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"entropy": 1.054566353559494,
|
| 1224 |
+
"epoch": 1.5659163987138265,
|
| 1225 |
+
"grad_norm": 0.14473803341388702,
|
| 1226 |
+
"learning_rate": 2.570747145207796e-05,
|
| 1227 |
+
"loss": 1.0497708320617676,
|
| 1228 |
+
"mean_token_accuracy": 0.6880283355712891,
|
| 1229 |
+
"num_tokens": 15669820.0,
|
| 1230 |
+
"step": 122
|
| 1231 |
+
},
|
| 1232 |
+
{
|
| 1233 |
+
"entropy": 1.0369255393743515,
|
| 1234 |
+
"epoch": 1.5787781350482315,
|
| 1235 |
+
"grad_norm": 0.14907261729240417,
|
| 1236 |
+
"learning_rate": 2.5353771148519057e-05,
|
| 1237 |
+
"loss": 1.0358316898345947,
|
| 1238 |
+
"mean_token_accuracy": 0.6919823661446571,
|
| 1239 |
+
"num_tokens": 15797917.0,
|
| 1240 |
+
"step": 123
|
| 1241 |
+
},
|
| 1242 |
+
{
|
| 1243 |
+
"entropy": 1.029112845659256,
|
| 1244 |
+
"epoch": 1.5916398713826365,
|
| 1245 |
+
"grad_norm": 0.14412133395671844,
|
| 1246 |
+
"learning_rate": 2.5e-05,
|
| 1247 |
+
"loss": 1.0267410278320312,
|
| 1248 |
+
"mean_token_accuracy": 0.6918147578835487,
|
| 1249 |
+
"num_tokens": 15926059.0,
|
| 1250 |
+
"step": 124
|
| 1251 |
+
},
|
| 1252 |
+
{
|
| 1253 |
+
"entropy": 1.0285268500447273,
|
| 1254 |
+
"epoch": 1.6045016077170418,
|
| 1255 |
+
"grad_norm": 0.1455468088388443,
|
| 1256 |
+
"learning_rate": 2.4646228851480956e-05,
|
| 1257 |
+
"loss": 1.0172383785247803,
|
| 1258 |
+
"mean_token_accuracy": 0.6961864978075027,
|
| 1259 |
+
"num_tokens": 16055416.0,
|
| 1260 |
+
"step": 125
|
| 1261 |
+
},
|
| 1262 |
+
{
|
| 1263 |
+
"entropy": 1.0407991334795952,
|
| 1264 |
+
"epoch": 1.617363344051447,
|
| 1265 |
+
"grad_norm": 0.14318124949932098,
|
| 1266 |
+
"learning_rate": 2.429252854792205e-05,
|
| 1267 |
+
"loss": 1.0395405292510986,
|
| 1268 |
+
"mean_token_accuracy": 0.6874824613332748,
|
| 1269 |
+
"num_tokens": 16185719.0,
|
| 1270 |
+
"step": 126
|
| 1271 |
+
},
|
| 1272 |
+
{
|
| 1273 |
+
"entropy": 1.0249589011073112,
|
| 1274 |
+
"epoch": 1.630225080385852,
|
| 1275 |
+
"grad_norm": 0.1448572725057602,
|
| 1276 |
+
"learning_rate": 2.39389699200963e-05,
|
| 1277 |
+
"loss": 1.015451431274414,
|
| 1278 |
+
"mean_token_accuracy": 0.6942317560315132,
|
| 1279 |
+
"num_tokens": 16314607.0,
|
| 1280 |
+
"step": 127
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"entropy": 1.039283350110054,
|
| 1284 |
+
"epoch": 1.6430868167202572,
|
| 1285 |
+
"grad_norm": 0.1484907567501068,
|
| 1286 |
+
"learning_rate": 2.358562377040519e-05,
|
| 1287 |
+
"loss": 1.028055191040039,
|
| 1288 |
+
"mean_token_accuracy": 0.6915712878108025,
|
| 1289 |
+
"num_tokens": 16441937.0,
|
| 1290 |
+
"step": 128
|
| 1291 |
+
},
|
| 1292 |
+
{
|
| 1293 |
+
"entropy": 1.0223650634288788,
|
| 1294 |
+
"epoch": 1.6559485530546625,
|
| 1295 |
+
"grad_norm": 0.14289766550064087,
|
| 1296 |
+
"learning_rate": 2.3232560858700137e-05,
|
| 1297 |
+
"loss": 1.008897304534912,
|
| 1298 |
+
"mean_token_accuracy": 0.6952646598219872,
|
| 1299 |
+
"num_tokens": 16571389.0,
|
| 1300 |
+
"step": 129
|
| 1301 |
+
},
|
| 1302 |
+
{
|
| 1303 |
+
"entropy": 0.9995019808411598,
|
| 1304 |
+
"epoch": 1.6688102893890675,
|
| 1305 |
+
"grad_norm": 0.14972709119319916,
|
| 1306 |
+
"learning_rate": 2.287985188811228e-05,
|
| 1307 |
+
"loss": 0.987511157989502,
|
| 1308 |
+
"mean_token_accuracy": 0.7003577873110771,
|
| 1309 |
+
"num_tokens": 16701314.0,
|
| 1310 |
+
"step": 130
|
| 1311 |
+
},
|
| 1312 |
+
{
|
| 1313 |
+
"entropy": 1.0168959125876427,
|
| 1314 |
+
"epoch": 1.6816720257234725,
|
| 1315 |
+
"grad_norm": 0.1496725082397461,
|
| 1316 |
+
"learning_rate": 2.2527567490893758e-05,
|
| 1317 |
+
"loss": 1.0123668909072876,
|
| 1318 |
+
"mean_token_accuracy": 0.6951291859149933,
|
| 1319 |
+
"num_tokens": 16830317.0,
|
| 1320 |
+
"step": 131
|
| 1321 |
+
},
|
| 1322 |
+
{
|
| 1323 |
+
"entropy": 1.0190805196762085,
|
| 1324 |
+
"epoch": 1.694533762057878,
|
| 1325 |
+
"grad_norm": 0.15911011397838593,
|
| 1326 |
+
"learning_rate": 2.2175778214273185e-05,
|
| 1327 |
+
"loss": 1.0175803899765015,
|
| 1328 |
+
"mean_token_accuracy": 0.6933339908719063,
|
| 1329 |
+
"num_tokens": 16959965.0,
|
| 1330 |
+
"step": 132
|
| 1331 |
+
},
|
| 1332 |
+
{
|
| 1333 |
+
"entropy": 1.0380867347121239,
|
| 1334 |
+
"epoch": 1.707395498392283,
|
| 1335 |
+
"grad_norm": 0.14191225171089172,
|
| 1336 |
+
"learning_rate": 2.182455450632803e-05,
|
| 1337 |
+
"loss": 1.0294275283813477,
|
| 1338 |
+
"mean_token_accuracy": 0.6917987540364265,
|
| 1339 |
+
"num_tokens": 17089870.0,
|
| 1340 |
+
"step": 133
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"entropy": 1.0180665403604507,
|
| 1344 |
+
"epoch": 1.720257234726688,
|
| 1345 |
+
"grad_norm": 0.1482504904270172,
|
| 1346 |
+
"learning_rate": 2.1473966701877025e-05,
|
| 1347 |
+
"loss": 1.0076394081115723,
|
| 1348 |
+
"mean_token_accuracy": 0.6966089159250259,
|
| 1349 |
+
"num_tokens": 17218254.0,
|
| 1350 |
+
"step": 134
|
| 1351 |
+
},
|
| 1352 |
+
{
|
| 1353 |
+
"entropy": 1.0091007053852081,
|
| 1354 |
+
"epoch": 1.7331189710610932,
|
| 1355 |
+
"grad_norm": 0.15382039546966553,
|
| 1356 |
+
"learning_rate": 2.1124085008395054e-05,
|
| 1357 |
+
"loss": 1.003111481666565,
|
| 1358 |
+
"mean_token_accuracy": 0.70043034106493,
|
| 1359 |
+
"num_tokens": 17347960.0,
|
| 1360 |
+
"step": 135
|
| 1361 |
+
},
|
| 1362 |
+
{
|
| 1363 |
+
"entropy": 1.0102703422307968,
|
| 1364 |
+
"epoch": 1.7459807073954985,
|
| 1365 |
+
"grad_norm": 0.18475782871246338,
|
| 1366 |
+
"learning_rate": 2.0774979491953777e-05,
|
| 1367 |
+
"loss": 1.0030856132507324,
|
| 1368 |
+
"mean_token_accuracy": 0.6967976689338684,
|
| 1369 |
+
"num_tokens": 17476832.0,
|
| 1370 |
+
"step": 136
|
| 1371 |
+
},
|
| 1372 |
+
{
|
| 1373 |
+
"entropy": 1.0280822068452835,
|
| 1374 |
+
"epoch": 1.7588424437299035,
|
| 1375 |
+
"grad_norm": 0.15235531330108643,
|
| 1376 |
+
"learning_rate": 2.0426720063190335e-05,
|
| 1377 |
+
"loss": 1.0269193649291992,
|
| 1378 |
+
"mean_token_accuracy": 0.6915133595466614,
|
| 1379 |
+
"num_tokens": 17606491.0,
|
| 1380 |
+
"step": 137
|
| 1381 |
+
},
|
| 1382 |
+
{
|
| 1383 |
+
"entropy": 1.038973644375801,
|
| 1384 |
+
"epoch": 1.7717041800643085,
|
| 1385 |
+
"grad_norm": 0.1467663049697876,
|
| 1386 |
+
"learning_rate": 2.0079376463307368e-05,
|
| 1387 |
+
"loss": 1.0385396480560303,
|
| 1388 |
+
"mean_token_accuracy": 0.6904850155115128,
|
| 1389 |
+
"num_tokens": 17735828.0,
|
| 1390 |
+
"step": 138
|
| 1391 |
+
},
|
| 1392 |
+
{
|
| 1393 |
+
"entropy": 1.007546715438366,
|
| 1394 |
+
"epoch": 1.784565916398714,
|
| 1395 |
+
"grad_norm": 0.15167458355426788,
|
| 1396 |
+
"learning_rate": 1.973301825010685e-05,
|
| 1397 |
+
"loss": 1.0009288787841797,
|
| 1398 |
+
"mean_token_accuracy": 0.6996477469801903,
|
| 1399 |
+
"num_tokens": 17865343.0,
|
| 1400 |
+
"step": 139
|
| 1401 |
+
},
|
| 1402 |
+
{
|
| 1403 |
+
"entropy": 1.0457243248820305,
|
| 1404 |
+
"epoch": 1.797427652733119,
|
| 1405 |
+
"grad_norm": 0.14147217571735382,
|
| 1406 |
+
"learning_rate": 1.9387714784060685e-05,
|
| 1407 |
+
"loss": 1.0354124307632446,
|
| 1408 |
+
"mean_token_accuracy": 0.6904323399066925,
|
| 1409 |
+
"num_tokens": 17993892.0,
|
| 1410 |
+
"step": 140
|
| 1411 |
+
},
|
| 1412 |
+
{
|
| 1413 |
+
"entropy": 1.0493519008159637,
|
| 1414 |
+
"epoch": 1.810289389067524,
|
| 1415 |
+
"grad_norm": 0.14349812269210815,
|
| 1416 |
+
"learning_rate": 1.904353521442088e-05,
|
| 1417 |
+
"loss": 1.043258786201477,
|
| 1418 |
+
"mean_token_accuracy": 0.6896533966064453,
|
| 1419 |
+
"num_tokens": 18122215.0,
|
| 1420 |
+
"step": 141
|
| 1421 |
+
},
|
| 1422 |
+
{
|
| 1423 |
+
"entropy": 1.0361140668392181,
|
| 1424 |
+
"epoch": 1.8231511254019293,
|
| 1425 |
+
"grad_norm": 0.14594632387161255,
|
| 1426 |
+
"learning_rate": 1.8700548465371874e-05,
|
| 1427 |
+
"loss": 1.0246191024780273,
|
| 1428 |
+
"mean_token_accuracy": 0.6924104690551758,
|
| 1429 |
+
"num_tokens": 18250505.0,
|
| 1430 |
+
"step": 142
|
| 1431 |
+
},
|
| 1432 |
+
{
|
| 1433 |
+
"entropy": 0.996397003531456,
|
| 1434 |
+
"epoch": 1.8360128617363345,
|
| 1435 |
+
"grad_norm": 0.13873013854026794,
|
| 1436 |
+
"learning_rate": 1.8358823222228097e-05,
|
| 1437 |
+
"loss": 0.9915734529495239,
|
| 1438 |
+
"mean_token_accuracy": 0.6993561685085297,
|
| 1439 |
+
"num_tokens": 18381218.0,
|
| 1440 |
+
"step": 143
|
| 1441 |
+
},
|
| 1442 |
+
{
|
| 1443 |
+
"entropy": 1.0313754975795746,
|
| 1444 |
+
"epoch": 1.8488745980707395,
|
| 1445 |
+
"grad_norm": 0.15026451647281647,
|
| 1446 |
+
"learning_rate": 1.801842791767925e-05,
|
| 1447 |
+
"loss": 1.016987681388855,
|
| 1448 |
+
"mean_token_accuracy": 0.6936725974082947,
|
| 1449 |
+
"num_tokens": 18510172.0,
|
| 1450 |
+
"step": 144
|
| 1451 |
+
},
|
| 1452 |
+
{
|
| 1453 |
+
"entropy": 1.0371734127402306,
|
| 1454 |
+
"epoch": 1.8617363344051447,
|
| 1455 |
+
"grad_norm": 0.14328952133655548,
|
| 1456 |
+
"learning_rate": 1.7679430718086243e-05,
|
| 1457 |
+
"loss": 1.029707908630371,
|
| 1458 |
+
"mean_token_accuracy": 0.6911671832203865,
|
| 1459 |
+
"num_tokens": 18639469.0,
|
| 1460 |
+
"step": 145
|
| 1461 |
+
},
|
| 1462 |
+
{
|
| 1463 |
+
"entropy": 1.0529436096549034,
|
| 1464 |
+
"epoch": 1.87459807073955,
|
| 1465 |
+
"grad_norm": 0.15134425461292267,
|
| 1466 |
+
"learning_rate": 1.7341899509830416e-05,
|
| 1467 |
+
"loss": 1.0452293157577515,
|
| 1468 |
+
"mean_token_accuracy": 0.6891046240925789,
|
| 1469 |
+
"num_tokens": 18769333.0,
|
| 1470 |
+
"step": 146
|
| 1471 |
+
},
|
| 1472 |
+
{
|
| 1473 |
+
"entropy": 1.0049605518579483,
|
| 1474 |
+
"epoch": 1.887459807073955,
|
| 1475 |
+
"grad_norm": 0.1447063535451889,
|
| 1476 |
+
"learning_rate": 1.700590188571887e-05,
|
| 1477 |
+
"loss": 1.0040454864501953,
|
| 1478 |
+
"mean_token_accuracy": 0.6978042870759964,
|
| 1479 |
+
"num_tokens": 18897391.0,
|
| 1480 |
+
"step": 147
|
| 1481 |
+
},
|
| 1482 |
+
{
|
| 1483 |
+
"entropy": 1.0140637308359146,
|
| 1484 |
+
"epoch": 1.90032154340836,
|
| 1485 |
+
"grad_norm": 0.1438555121421814,
|
| 1486 |
+
"learning_rate": 1.667150513144856e-05,
|
| 1487 |
+
"loss": 1.007043480873108,
|
| 1488 |
+
"mean_token_accuracy": 0.698374018073082,
|
| 1489 |
+
"num_tokens": 19026977.0,
|
| 1490 |
+
"step": 148
|
| 1491 |
+
},
|
| 1492 |
+
{
|
| 1493 |
+
"entropy": 1.0184678137302399,
|
| 1494 |
+
"epoch": 1.9131832797427653,
|
| 1495 |
+
"grad_norm": 0.1421106904745102,
|
| 1496 |
+
"learning_rate": 1.633877621213192e-05,
|
| 1497 |
+
"loss": 1.01150381565094,
|
| 1498 |
+
"mean_token_accuracy": 0.6960654258728027,
|
| 1499 |
+
"num_tokens": 19154514.0,
|
| 1500 |
+
"step": 149
|
| 1501 |
+
},
|
| 1502 |
+
{
|
| 1503 |
+
"entropy": 1.0100202932953835,
|
| 1504 |
+
"epoch": 1.9260450160771705,
|
| 1505 |
+
"grad_norm": 0.1437564641237259,
|
| 1506 |
+
"learning_rate": 1.6007781758886607e-05,
|
| 1507 |
+
"loss": 1.003399133682251,
|
| 1508 |
+
"mean_token_accuracy": 0.6989860460162163,
|
| 1509 |
+
"num_tokens": 19282293.0,
|
| 1510 |
+
"step": 150
|
| 1511 |
+
},
|
| 1512 |
+
{
|
| 1513 |
+
"entropy": 1.0097703114151955,
|
| 1514 |
+
"epoch": 1.9389067524115755,
|
| 1515 |
+
"grad_norm": 0.14791278541088104,
|
| 1516 |
+
"learning_rate": 1.567858805549229e-05,
|
| 1517 |
+
"loss": 1.0031559467315674,
|
| 1518 |
+
"mean_token_accuracy": 0.6982970088720322,
|
| 1519 |
+
"num_tokens": 19412057.0,
|
| 1520 |
+
"step": 151
|
| 1521 |
+
},
|
| 1522 |
+
{
|
| 1523 |
+
"entropy": 0.9986948445439339,
|
| 1524 |
+
"epoch": 1.9517684887459807,
|
| 1525 |
+
"grad_norm": 0.14181585609912872,
|
| 1526 |
+
"learning_rate": 1.535126102511678e-05,
|
| 1527 |
+
"loss": 0.9911055564880371,
|
| 1528 |
+
"mean_token_accuracy": 0.7003660649061203,
|
| 1529 |
+
"num_tokens": 19538894.0,
|
| 1530 |
+
"step": 152
|
| 1531 |
+
},
|
| 1532 |
+
{
|
| 1533 |
+
"entropy": 1.0326199233531952,
|
| 1534 |
+
"epoch": 1.964630225080386,
|
| 1535 |
+
"grad_norm": 0.14459078013896942,
|
| 1536 |
+
"learning_rate": 1.5025866217114592e-05,
|
| 1537 |
+
"loss": 1.029758095741272,
|
| 1538 |
+
"mean_token_accuracy": 0.690429113805294,
|
| 1539 |
+
"num_tokens": 19669050.0,
|
| 1540 |
+
"step": 153
|
| 1541 |
+
},
|
| 1542 |
+
{
|
| 1543 |
+
"entropy": 1.024147979915142,
|
| 1544 |
+
"epoch": 1.977491961414791,
|
| 1545 |
+
"grad_norm": 0.14128583669662476,
|
| 1546 |
+
"learning_rate": 1.4702468793900188e-05,
|
| 1547 |
+
"loss": 1.0202356576919556,
|
| 1548 |
+
"mean_token_accuracy": 0.6920891180634499,
|
| 1549 |
+
"num_tokens": 19796666.0,
|
| 1550 |
+
"step": 154
|
| 1551 |
+
},
|
| 1552 |
+
{
|
| 1553 |
+
"entropy": 1.0354069098830223,
|
| 1554 |
+
"epoch": 1.990353697749196,
|
| 1555 |
+
"grad_norm": 0.14648661017417908,
|
| 1556 |
+
"learning_rate": 1.4381133517898804e-05,
|
| 1557 |
+
"loss": 1.0325945615768433,
|
| 1558 |
+
"mean_token_accuracy": 0.6926636919379234,
|
| 1559 |
+
"num_tokens": 19927210.0,
|
| 1560 |
+
"step": 155
|
| 1561 |
+
},
|
| 1562 |
+
{
|
| 1563 |
+
"entropy": 0.9808994829654694,
|
| 1564 |
+
"epoch": 2.0,
|
| 1565 |
+
"grad_norm": 0.1645454615354538,
|
| 1566 |
+
"learning_rate": 1.4061924738577403e-05,
|
| 1567 |
+
"loss": 0.992160975933075,
|
| 1568 |
+
"mean_token_accuracy": 0.706730475028356,
|
| 1569 |
+
"num_tokens": 19999816.0,
|
| 1570 |
+
"step": 156
|
| 1571 |
+
},
|
| 1572 |
+
{
|
| 1573 |
+
"entropy": 1.0143855810165405,
|
| 1574 |
+
"epoch": 2.012861736334405,
|
| 1575 |
+
"grad_norm": 0.15097208321094513,
|
| 1576 |
+
"learning_rate": 1.3744906379558165e-05,
|
| 1577 |
+
"loss": 0.9856299161911011,
|
| 1578 |
+
"mean_token_accuracy": 0.7038262039422989,
|
| 1579 |
+
"num_tokens": 20129551.0,
|
| 1580 |
+
"step": 157
|
| 1581 |
+
},
|
| 1582 |
+
{
|
| 1583 |
+
"entropy": 0.9946700483560562,
|
| 1584 |
+
"epoch": 2.0257234726688105,
|
| 1585 |
+
"grad_norm": 0.14270229637622833,
|
| 1586 |
+
"learning_rate": 1.3430141925817532e-05,
|
| 1587 |
+
"loss": 0.9719038605690002,
|
| 1588 |
+
"mean_token_accuracy": 0.7039921209216118,
|
| 1589 |
+
"num_tokens": 20259647.0,
|
| 1590 |
+
"step": 158
|
| 1591 |
+
},
|
| 1592 |
+
{
|
| 1593 |
+
"entropy": 1.0147498473525047,
|
| 1594 |
+
"epoch": 2.0385852090032155,
|
| 1595 |
+
"grad_norm": 0.14715144038200378,
|
| 1596 |
+
"learning_rate": 1.3117694410972748e-05,
|
| 1597 |
+
"loss": 0.9927316904067993,
|
| 1598 |
+
"mean_token_accuracy": 0.698149062693119,
|
| 1599 |
+
"num_tokens": 20389510.0,
|
| 1600 |
+
"step": 159
|
| 1601 |
+
},
|
| 1602 |
+
{
|
| 1603 |
+
"entropy": 1.0180071666836739,
|
| 1604 |
+
"epoch": 2.0514469453376205,
|
| 1605 |
+
"grad_norm": 0.14939357340335846,
|
| 1606 |
+
"learning_rate": 1.2807626404659142e-05,
|
| 1607 |
+
"loss": 0.9938769340515137,
|
| 1608 |
+
"mean_token_accuracy": 0.6993245705962181,
|
| 1609 |
+
"num_tokens": 20518012.0,
|
| 1610 |
+
"step": 160
|
| 1611 |
+
},
|
| 1612 |
+
{
|
| 1613 |
+
"entropy": 1.0051729753613472,
|
| 1614 |
+
"epoch": 2.0643086816720255,
|
| 1615 |
+
"grad_norm": 0.14741602540016174,
|
| 1616 |
+
"learning_rate": 1.2500000000000006e-05,
|
| 1617 |
+
"loss": 0.9840617179870605,
|
| 1618 |
+
"mean_token_accuracy": 0.7015254199504852,
|
| 1619 |
+
"num_tokens": 20646832.0,
|
| 1620 |
+
"step": 161
|
| 1621 |
+
},
|
| 1622 |
+
{
|
| 1623 |
+
"entropy": 0.998705729842186,
|
| 1624 |
+
"epoch": 2.077170418006431,
|
| 1625 |
+
"grad_norm": 0.15145288407802582,
|
| 1626 |
+
"learning_rate": 1.2194876801172148e-05,
|
| 1627 |
+
"loss": 0.9809376001358032,
|
| 1628 |
+
"mean_token_accuracy": 0.7015095204114914,
|
| 1629 |
+
"num_tokens": 20774143.0,
|
| 1630 |
+
"step": 162
|
| 1631 |
+
},
|
| 1632 |
+
{
|
| 1633 |
+
"entropy": 1.0045012831687927,
|
| 1634 |
+
"epoch": 2.090032154340836,
|
| 1635 |
+
"grad_norm": 0.1488005369901657,
|
| 1636 |
+
"learning_rate": 1.1892317911069212e-05,
|
| 1637 |
+
"loss": 0.9931153059005737,
|
| 1638 |
+
"mean_token_accuracy": 0.6996508315205574,
|
| 1639 |
+
"num_tokens": 20900771.0,
|
| 1640 |
+
"step": 163
|
| 1641 |
+
},
|
| 1642 |
+
{
|
| 1643 |
+
"entropy": 0.9704049155116081,
|
| 1644 |
+
"epoch": 2.102893890675241,
|
| 1645 |
+
"grad_norm": 0.14846347272396088,
|
| 1646 |
+
"learning_rate": 1.1592383919065442e-05,
|
| 1647 |
+
"loss": 0.9699604511260986,
|
| 1648 |
+
"mean_token_accuracy": 0.7040959894657135,
|
| 1649 |
+
"num_tokens": 21030176.0,
|
| 1650 |
+
"step": 164
|
| 1651 |
+
},
|
| 1652 |
+
{
|
| 1653 |
+
"entropy": 0.9908866882324219,
|
| 1654 |
+
"epoch": 2.1157556270096465,
|
| 1655 |
+
"grad_norm": 0.15188701450824738,
|
| 1656 |
+
"learning_rate": 1.1295134888882258e-05,
|
| 1657 |
+
"loss": 0.9888017177581787,
|
| 1658 |
+
"mean_token_accuracy": 0.7019331976771355,
|
| 1659 |
+
"num_tokens": 21158984.0,
|
| 1660 |
+
"step": 165
|
| 1661 |
+
},
|
| 1662 |
+
{
|
| 1663 |
+
"entropy": 0.9876426234841347,
|
| 1664 |
+
"epoch": 2.1286173633440515,
|
| 1665 |
+
"grad_norm": 0.14991621673107147,
|
| 1666 |
+
"learning_rate": 1.1000630346560117e-05,
|
| 1667 |
+
"loss": 0.9930974245071411,
|
| 1668 |
+
"mean_token_accuracy": 0.7000587806105614,
|
| 1669 |
+
"num_tokens": 21287794.0,
|
| 1670 |
+
"step": 166
|
| 1671 |
+
},
|
| 1672 |
+
{
|
| 1673 |
+
"entropy": 0.9993386119604111,
|
| 1674 |
+
"epoch": 2.1414790996784565,
|
| 1675 |
+
"grad_norm": 0.15167978405952454,
|
| 1676 |
+
"learning_rate": 1.0708929268538034e-05,
|
| 1677 |
+
"loss": 1.0022180080413818,
|
| 1678 |
+
"mean_token_accuracy": 0.6992425248026848,
|
| 1679 |
+
"num_tokens": 21416220.0,
|
| 1680 |
+
"step": 167
|
| 1681 |
+
},
|
| 1682 |
+
{
|
| 1683 |
+
"entropy": 0.9697343483567238,
|
| 1684 |
+
"epoch": 2.154340836012862,
|
| 1685 |
+
"grad_norm": 0.15201398730278015,
|
| 1686 |
+
"learning_rate": 1.0420090069843167e-05,
|
| 1687 |
+
"loss": 0.9746421575546265,
|
| 1688 |
+
"mean_token_accuracy": 0.7043134346604347,
|
| 1689 |
+
"num_tokens": 21544581.0,
|
| 1690 |
+
"step": 168
|
| 1691 |
+
},
|
| 1692 |
+
{
|
| 1693 |
+
"entropy": 0.9662765711545944,
|
| 1694 |
+
"epoch": 2.167202572347267,
|
| 1695 |
+
"grad_norm": 0.14762073755264282,
|
| 1696 |
+
"learning_rate": 1.0134170592392836e-05,
|
| 1697 |
+
"loss": 0.9753881096839905,
|
| 1698 |
+
"mean_token_accuracy": 0.702050969004631,
|
| 1699 |
+
"num_tokens": 21674877.0,
|
| 1700 |
+
"step": 169
|
| 1701 |
+
},
|
| 1702 |
+
{
|
| 1703 |
+
"entropy": 0.9745886772871017,
|
| 1704 |
+
"epoch": 2.180064308681672,
|
| 1705 |
+
"grad_norm": 0.15288156270980835,
|
| 1706 |
+
"learning_rate": 9.851228093411296e-06,
|
| 1707 |
+
"loss": 0.9781433939933777,
|
| 1708 |
+
"mean_token_accuracy": 0.7020246610045433,
|
| 1709 |
+
"num_tokens": 21804650.0,
|
| 1710 |
+
"step": 170
|
| 1711 |
+
},
|
| 1712 |
+
{
|
| 1713 |
+
"entropy": 0.9887658506631851,
|
| 1714 |
+
"epoch": 2.192926045016077,
|
| 1715 |
+
"grad_norm": 0.1461670845746994,
|
| 1716 |
+
"learning_rate": 9.571319233963627e-06,
|
| 1717 |
+
"loss": 0.9779214262962341,
|
| 1718 |
+
"mean_token_accuracy": 0.703081913292408,
|
| 1719 |
+
"num_tokens": 21933944.0,
|
| 1720 |
+
"step": 171
|
| 1721 |
+
},
|
| 1722 |
+
{
|
| 1723 |
+
"entropy": 0.972991868853569,
|
| 1724 |
+
"epoch": 2.2057877813504825,
|
| 1725 |
+
"grad_norm": 0.14857877790927887,
|
| 1726 |
+
"learning_rate": 9.29450006760894e-06,
|
| 1727 |
+
"loss": 0.9676029086112976,
|
| 1728 |
+
"mean_token_accuracy": 0.7069084197282791,
|
| 1729 |
+
"num_tokens": 22062831.0,
|
| 1730 |
+
"step": 172
|
| 1731 |
+
},
|
| 1732 |
+
{
|
| 1733 |
+
"entropy": 1.0113277956843376,
|
| 1734 |
+
"epoch": 2.2186495176848875,
|
| 1735 |
+
"grad_norm": 0.15487462282180786,
|
| 1736 |
+
"learning_rate": 9.020826029175384e-06,
|
| 1737 |
+
"loss": 1.006070613861084,
|
| 1738 |
+
"mean_token_accuracy": 0.6965017765760422,
|
| 1739 |
+
"num_tokens": 22191464.0,
|
| 1740 |
+
"step": 173
|
| 1741 |
+
},
|
| 1742 |
+
{
|
| 1743 |
+
"entropy": 0.9916297346353531,
|
| 1744 |
+
"epoch": 2.2315112540192925,
|
| 1745 |
+
"grad_norm": 0.14774714410305023,
|
| 1746 |
+
"learning_rate": 8.750351923658832e-06,
|
| 1747 |
+
"loss": 0.9754974842071533,
|
| 1748 |
+
"mean_token_accuracy": 0.7031588032841682,
|
| 1749 |
+
"num_tokens": 22321437.0,
|
| 1750 |
+
"step": 174
|
| 1751 |
+
},
|
| 1752 |
+
{
|
| 1753 |
+
"entropy": 1.0356281399726868,
|
| 1754 |
+
"epoch": 2.244372990353698,
|
| 1755 |
+
"grad_norm": 0.15343612432479858,
|
| 1756 |
+
"learning_rate": 8.483131915247968e-06,
|
| 1757 |
+
"loss": 1.017188549041748,
|
| 1758 |
+
"mean_token_accuracy": 0.693478174507618,
|
| 1759 |
+
"num_tokens": 22449634.0,
|
| 1760 |
+
"step": 175
|
| 1761 |
+
},
|
| 1762 |
+
{
|
| 1763 |
+
"entropy": 1.0122131705284119,
|
| 1764 |
+
"epoch": 2.257234726688103,
|
| 1765 |
+
"grad_norm": 0.14862875640392303,
|
| 1766 |
+
"learning_rate": 8.219219516477428e-06,
|
| 1767 |
+
"loss": 0.9908279180526733,
|
| 1768 |
+
"mean_token_accuracy": 0.6987990885972977,
|
| 1769 |
+
"num_tokens": 22577836.0,
|
| 1770 |
+
"step": 176
|
| 1771 |
+
},
|
| 1772 |
+
{
|
| 1773 |
+
"entropy": 1.0197054371237755,
|
| 1774 |
+
"epoch": 2.270096463022508,
|
| 1775 |
+
"grad_norm": 0.15119275450706482,
|
| 1776 |
+
"learning_rate": 7.958667577511683e-06,
|
| 1777 |
+
"loss": 0.9980366826057434,
|
| 1778 |
+
"mean_token_accuracy": 0.6982897073030472,
|
| 1779 |
+
"num_tokens": 22706085.0,
|
| 1780 |
+
"step": 177
|
| 1781 |
+
},
|
| 1782 |
+
{
|
| 1783 |
+
"entropy": 1.000802867114544,
|
| 1784 |
+
"epoch": 2.282958199356913,
|
| 1785 |
+
"grad_norm": 0.14366647601127625,
|
| 1786 |
+
"learning_rate": 7.701528275561348e-06,
|
| 1787 |
+
"loss": 0.9737733602523804,
|
| 1788 |
+
"mean_token_accuracy": 0.7044953107833862,
|
| 1789 |
+
"num_tokens": 22834748.0,
|
| 1790 |
+
"step": 178
|
| 1791 |
+
},
|
| 1792 |
+
{
|
| 1793 |
+
"entropy": 0.9863439574837685,
|
| 1794 |
+
"epoch": 2.2958199356913185,
|
| 1795 |
+
"grad_norm": 0.14263279736042023,
|
| 1796 |
+
"learning_rate": 7.447853104434438e-06,
|
| 1797 |
+
"loss": 0.9751866459846497,
|
| 1798 |
+
"mean_token_accuracy": 0.7027714774012566,
|
| 1799 |
+
"num_tokens": 22961691.0,
|
| 1800 |
+
"step": 179
|
| 1801 |
+
},
|
| 1802 |
+
{
|
| 1803 |
+
"entropy": 0.9606952220201492,
|
| 1804 |
+
"epoch": 2.3086816720257235,
|
| 1805 |
+
"grad_norm": 0.15060292184352875,
|
| 1806 |
+
"learning_rate": 7.197692864224365e-06,
|
| 1807 |
+
"loss": 0.9443936347961426,
|
| 1808 |
+
"mean_token_accuracy": 0.7106149792671204,
|
| 1809 |
+
"num_tokens": 23090767.0,
|
| 1810 |
+
"step": 180
|
| 1811 |
+
},
|
| 1812 |
+
{
|
| 1813 |
+
"entropy": 0.9733371436595917,
|
| 1814 |
+
"epoch": 2.3215434083601285,
|
| 1815 |
+
"grad_norm": 0.14608748257160187,
|
| 1816 |
+
"learning_rate": 6.951097651136889e-06,
|
| 1817 |
+
"loss": 0.9657639265060425,
|
| 1818 |
+
"mean_token_accuracy": 0.706763505935669,
|
| 1819 |
+
"num_tokens": 23220713.0,
|
| 1820 |
+
"step": 181
|
| 1821 |
+
},
|
| 1822 |
+
{
|
| 1823 |
+
"entropy": 0.9712415337562561,
|
| 1824 |
+
"epoch": 2.334405144694534,
|
| 1825 |
+
"grad_norm": 0.1487581729888916,
|
| 1826 |
+
"learning_rate": 6.708116847458043e-06,
|
| 1827 |
+
"loss": 0.959854781627655,
|
| 1828 |
+
"mean_token_accuracy": 0.7069366499781609,
|
| 1829 |
+
"num_tokens": 23349717.0,
|
| 1830 |
+
"step": 182
|
| 1831 |
+
},
|
| 1832 |
+
{
|
| 1833 |
+
"entropy": 0.9718986302614212,
|
| 1834 |
+
"epoch": 2.347266881028939,
|
| 1835 |
+
"grad_norm": 0.14684326946735382,
|
| 1836 |
+
"learning_rate": 6.468799111665003e-06,
|
| 1837 |
+
"loss": 0.9676629900932312,
|
| 1838 |
+
"mean_token_accuracy": 0.7048570662736893,
|
| 1839 |
+
"num_tokens": 23478878.0,
|
| 1840 |
+
"step": 183
|
| 1841 |
+
},
|
| 1842 |
+
{
|
| 1843 |
+
"entropy": 0.9988474324345589,
|
| 1844 |
+
"epoch": 2.360128617363344,
|
| 1845 |
+
"grad_norm": 0.14926955103874207,
|
| 1846 |
+
"learning_rate": 6.23319236868189e-06,
|
| 1847 |
+
"loss": 0.9989900588989258,
|
| 1848 |
+
"mean_token_accuracy": 0.6979110315442085,
|
| 1849 |
+
"num_tokens": 23609398.0,
|
| 1850 |
+
"step": 184
|
| 1851 |
+
},
|
| 1852 |
+
{
|
| 1853 |
+
"entropy": 1.0037187412381172,
|
| 1854 |
+
"epoch": 2.372990353697749,
|
| 1855 |
+
"grad_norm": 0.15062850713729858,
|
| 1856 |
+
"learning_rate": 6.001343800282569e-06,
|
| 1857 |
+
"loss": 1.0000722408294678,
|
| 1858 |
+
"mean_token_accuracy": 0.6993377730250359,
|
| 1859 |
+
"num_tokens": 23738018.0,
|
| 1860 |
+
"step": 185
|
| 1861 |
+
},
|
| 1862 |
+
{
|
| 1863 |
+
"entropy": 0.9782311767339706,
|
| 1864 |
+
"epoch": 2.3858520900321545,
|
| 1865 |
+
"grad_norm": 0.14419959485530853,
|
| 1866 |
+
"learning_rate": 5.7732998356420796e-06,
|
| 1867 |
+
"loss": 0.9765899777412415,
|
| 1868 |
+
"mean_token_accuracy": 0.702816791832447,
|
| 1869 |
+
"num_tokens": 23867248.0,
|
| 1870 |
+
"step": 186
|
| 1871 |
+
},
|
| 1872 |
+
{
|
| 1873 |
+
"entropy": 0.9830808639526367,
|
| 1874 |
+
"epoch": 2.3987138263665595,
|
| 1875 |
+
"grad_norm": 0.1496494710445404,
|
| 1876 |
+
"learning_rate": 5.549106142039018e-06,
|
| 1877 |
+
"loss": 0.9824045896530151,
|
| 1878 |
+
"mean_token_accuracy": 0.7036417871713638,
|
| 1879 |
+
"num_tokens": 23990063.0,
|
| 1880 |
+
"step": 187
|
| 1881 |
+
},
|
| 1882 |
+
{
|
| 1883 |
+
"entropy": 1.0006206557154655,
|
| 1884 |
+
"epoch": 2.4115755627009645,
|
| 1885 |
+
"grad_norm": 0.14769846200942993,
|
| 1886 |
+
"learning_rate": 5.328807615710246e-06,
|
| 1887 |
+
"loss": 0.9914774894714355,
|
| 1888 |
+
"mean_token_accuracy": 0.7003512755036354,
|
| 1889 |
+
"num_tokens": 24117998.0,
|
| 1890 |
+
"step": 188
|
| 1891 |
+
},
|
| 1892 |
+
{
|
| 1893 |
+
"entropy": 0.9960543289780617,
|
| 1894 |
+
"epoch": 2.42443729903537,
|
| 1895 |
+
"grad_norm": 0.14919231832027435,
|
| 1896 |
+
"learning_rate": 5.112448372860257e-06,
|
| 1897 |
+
"loss": 0.9938825368881226,
|
| 1898 |
+
"mean_token_accuracy": 0.7001635283231735,
|
| 1899 |
+
"num_tokens": 24246395.0,
|
| 1900 |
+
"step": 189
|
| 1901 |
+
},
|
| 1902 |
+
{
|
| 1903 |
+
"entropy": 0.969782643020153,
|
| 1904 |
+
"epoch": 2.437299035369775,
|
| 1905 |
+
"grad_norm": 0.1437661498785019,
|
| 1906 |
+
"learning_rate": 4.900071740826489e-06,
|
| 1907 |
+
"loss": 0.9636502265930176,
|
| 1908 |
+
"mean_token_accuracy": 0.7052842155098915,
|
| 1909 |
+
"num_tokens": 24375083.0,
|
| 1910 |
+
"step": 190
|
| 1911 |
+
},
|
| 1912 |
+
{
|
| 1913 |
+
"entropy": 0.9985753521323204,
|
| 1914 |
+
"epoch": 2.45016077170418,
|
| 1915 |
+
"grad_norm": 0.1478334367275238,
|
| 1916 |
+
"learning_rate": 4.691720249402856e-06,
|
| 1917 |
+
"loss": 0.9916254878044128,
|
| 1918 |
+
"mean_token_accuracy": 0.7017218321561813,
|
| 1919 |
+
"num_tokens": 24504249.0,
|
| 1920 |
+
"step": 191
|
| 1921 |
+
},
|
| 1922 |
+
{
|
| 1923 |
+
"entropy": 1.0174183622002602,
|
| 1924 |
+
"epoch": 2.463022508038585,
|
| 1925 |
+
"grad_norm": 0.1463613063097,
|
| 1926 |
+
"learning_rate": 4.487435622322814e-06,
|
| 1927 |
+
"loss": 1.0077807903289795,
|
| 1928 |
+
"mean_token_accuracy": 0.6966395974159241,
|
| 1929 |
+
"num_tokens": 24633736.0,
|
| 1930 |
+
"step": 192
|
| 1931 |
+
},
|
| 1932 |
+
{
|
| 1933 |
+
"entropy": 1.0191529616713524,
|
| 1934 |
+
"epoch": 2.4758842443729905,
|
| 1935 |
+
"grad_norm": 0.1539534330368042,
|
| 1936 |
+
"learning_rate": 4.2872587689039484e-06,
|
| 1937 |
+
"loss": 1.02093505859375,
|
| 1938 |
+
"mean_token_accuracy": 0.6929882690310478,
|
| 1939 |
+
"num_tokens": 24764322.0,
|
| 1940 |
+
"step": 193
|
| 1941 |
+
},
|
| 1942 |
+
{
|
| 1943 |
+
"entropy": 0.9834636375308037,
|
| 1944 |
+
"epoch": 2.4887459807073955,
|
| 1945 |
+
"grad_norm": 0.14389380812644958,
|
| 1946 |
+
"learning_rate": 4.091229775855598e-06,
|
| 1947 |
+
"loss": 0.9757540225982666,
|
| 1948 |
+
"mean_token_accuracy": 0.7044370919466019,
|
| 1949 |
+
"num_tokens": 24894140.0,
|
| 1950 |
+
"step": 194
|
| 1951 |
+
},
|
| 1952 |
+
{
|
| 1953 |
+
"entropy": 0.9720609411597252,
|
| 1954 |
+
"epoch": 2.5016077170418005,
|
| 1955 |
+
"grad_norm": 0.14187121391296387,
|
| 1956 |
+
"learning_rate": 3.8993878992512415e-06,
|
| 1957 |
+
"loss": 0.959560215473175,
|
| 1958 |
+
"mean_token_accuracy": 0.7082379162311554,
|
| 1959 |
+
"num_tokens": 25023082.0,
|
| 1960 |
+
"step": 195
|
| 1961 |
+
},
|
| 1962 |
+
{
|
| 1963 |
+
"entropy": 1.0143597051501274,
|
| 1964 |
+
"epoch": 2.514469453376206,
|
| 1965 |
+
"grad_norm": 0.1516728550195694,
|
| 1966 |
+
"learning_rate": 3.711771556667218e-06,
|
| 1967 |
+
"loss": 0.9982469081878662,
|
| 1968 |
+
"mean_token_accuracy": 0.6964723244309425,
|
| 1969 |
+
"num_tokens": 25152092.0,
|
| 1970 |
+
"step": 196
|
| 1971 |
+
},
|
| 1972 |
+
{
|
| 1973 |
+
"entropy": 0.9826101660728455,
|
| 1974 |
+
"epoch": 2.527331189710611,
|
| 1975 |
+
"grad_norm": 0.14548565447330475,
|
| 1976 |
+
"learning_rate": 3.5284183194893488e-06,
|
| 1977 |
+
"loss": 0.9657119512557983,
|
| 1978 |
+
"mean_token_accuracy": 0.7059699892997742,
|
| 1979 |
+
"num_tokens": 25281262.0,
|
| 1980 |
+
"step": 197
|
| 1981 |
+
},
|
| 1982 |
+
{
|
| 1983 |
+
"entropy": 0.988068088889122,
|
| 1984 |
+
"epoch": 2.540192926045016,
|
| 1985 |
+
"grad_norm": 0.14584684371948242,
|
| 1986 |
+
"learning_rate": 3.3493649053890326e-06,
|
| 1987 |
+
"loss": 0.974069356918335,
|
| 1988 |
+
"mean_token_accuracy": 0.7047757878899574,
|
| 1989 |
+
"num_tokens": 25409681.0,
|
| 1990 |
+
"step": 198
|
| 1991 |
+
},
|
| 1992 |
+
{
|
| 1993 |
+
"entropy": 0.9741279184818268,
|
| 1994 |
+
"epoch": 2.553054662379421,
|
| 1995 |
+
"grad_norm": 0.1395328938961029,
|
| 1996 |
+
"learning_rate": 3.1746471709702964e-06,
|
| 1997 |
+
"loss": 0.9705372452735901,
|
| 1998 |
+
"mean_token_accuracy": 0.7048429250717163,
|
| 1999 |
+
"num_tokens": 25538523.0,
|
| 2000 |
+
"step": 199
|
| 2001 |
+
},
|
| 2002 |
+
{
|
| 2003 |
+
"entropy": 0.9832991883158684,
|
| 2004 |
+
"epoch": 2.5659163987138265,
|
| 2005 |
+
"grad_norm": 0.16734182834625244,
|
| 2006 |
+
"learning_rate": 3.0043001045892695e-06,
|
| 2007 |
+
"loss": 0.970828652381897,
|
| 2008 |
+
"mean_token_accuracy": 0.7034261524677277,
|
| 2009 |
+
"num_tokens": 25666896.0,
|
| 2010 |
+
"step": 200
|
| 2011 |
+
},
|
| 2012 |
+
{
|
| 2013 |
+
"entropy": 0.9968943223357201,
|
| 2014 |
+
"epoch": 2.5787781350482315,
|
| 2015 |
+
"grad_norm": 0.14664772152900696,
|
| 2016 |
+
"learning_rate": 2.8383578193475315e-06,
|
| 2017 |
+
"loss": 0.9886881113052368,
|
| 2018 |
+
"mean_token_accuracy": 0.7005996480584145,
|
| 2019 |
+
"num_tokens": 25795814.0,
|
| 2020 |
+
"step": 201
|
| 2021 |
+
},
|
| 2022 |
+
{
|
| 2023 |
+
"entropy": 0.9984467178583145,
|
| 2024 |
+
"epoch": 2.5916398713826365,
|
| 2025 |
+
"grad_norm": 0.14841625094413757,
|
| 2026 |
+
"learning_rate": 2.676853546260791e-06,
|
| 2027 |
+
"loss": 0.9910497069358826,
|
| 2028 |
+
"mean_token_accuracy": 0.7002272084355354,
|
| 2029 |
+
"num_tokens": 25925524.0,
|
| 2030 |
+
"step": 202
|
| 2031 |
+
},
|
| 2032 |
+
{
|
| 2033 |
+
"entropy": 0.9846226349473,
|
| 2034 |
+
"epoch": 2.604501607717042,
|
| 2035 |
+
"grad_norm": 0.14504557847976685,
|
| 2036 |
+
"learning_rate": 2.5198196276040782e-06,
|
| 2037 |
+
"loss": 0.9722692966461182,
|
| 2038 |
+
"mean_token_accuracy": 0.7056987211108208,
|
| 2039 |
+
"num_tokens": 26055184.0,
|
| 2040 |
+
"step": 203
|
| 2041 |
+
},
|
| 2042 |
+
{
|
| 2043 |
+
"entropy": 1.0102949291467667,
|
| 2044 |
+
"epoch": 2.617363344051447,
|
| 2045 |
+
"grad_norm": 0.14757543802261353,
|
| 2046 |
+
"learning_rate": 2.3672875104350844e-06,
|
| 2047 |
+
"loss": 0.9945117235183716,
|
| 2048 |
+
"mean_token_accuracy": 0.698897622525692,
|
| 2049 |
+
"num_tokens": 26184353.0,
|
| 2050 |
+
"step": 204
|
| 2051 |
+
},
|
| 2052 |
+
{
|
| 2053 |
+
"entropy": 0.9994086995720863,
|
| 2054 |
+
"epoch": 2.630225080385852,
|
| 2055 |
+
"grad_norm": 0.14748479425907135,
|
| 2056 |
+
"learning_rate": 2.219287740296605e-06,
|
| 2057 |
+
"loss": 0.9939561486244202,
|
| 2058 |
+
"mean_token_accuracy": 0.6975871846079826,
|
| 2059 |
+
"num_tokens": 26313066.0,
|
| 2060 |
+
"step": 205
|
| 2061 |
+
},
|
| 2062 |
+
{
|
| 2063 |
+
"entropy": 0.9975132793188095,
|
| 2064 |
+
"epoch": 2.643086816720257,
|
| 2065 |
+
"grad_norm": 0.1443839818239212,
|
| 2066 |
+
"learning_rate": 2.075849955099668e-06,
|
| 2067 |
+
"loss": 0.9907892942428589,
|
| 2068 |
+
"mean_token_accuracy": 0.699777752161026,
|
| 2069 |
+
"num_tokens": 26442692.0,
|
| 2070 |
+
"step": 206
|
| 2071 |
+
},
|
| 2072 |
+
{
|
| 2073 |
+
"entropy": 1.0035064443945885,
|
| 2074 |
+
"epoch": 2.6559485530546625,
|
| 2075 |
+
"grad_norm": 0.14282147586345673,
|
| 2076 |
+
"learning_rate": 1.937002879188285e-06,
|
| 2077 |
+
"loss": 0.9950806498527527,
|
| 2078 |
+
"mean_token_accuracy": 0.6995139196515083,
|
| 2079 |
+
"num_tokens": 26571893.0,
|
| 2080 |
+
"step": 207
|
| 2081 |
+
},
|
| 2082 |
+
{
|
| 2083 |
+
"entropy": 0.9895152673125267,
|
| 2084 |
+
"epoch": 2.6688102893890675,
|
| 2085 |
+
"grad_norm": 0.14651040732860565,
|
| 2086 |
+
"learning_rate": 1.8027743175872664e-06,
|
| 2087 |
+
"loss": 0.983437180519104,
|
| 2088 |
+
"mean_token_accuracy": 0.7047524750232697,
|
| 2089 |
+
"num_tokens": 26700860.0,
|
| 2090 |
+
"step": 208
|
| 2091 |
+
},
|
| 2092 |
+
{
|
| 2093 |
+
"entropy": 0.9806164056062698,
|
| 2094 |
+
"epoch": 2.6816720257234725,
|
| 2095 |
+
"grad_norm": 0.1419828236103058,
|
| 2096 |
+
"learning_rate": 1.673191150434067e-06,
|
| 2097 |
+
"loss": 0.9723012447357178,
|
| 2098 |
+
"mean_token_accuracy": 0.7045335248112679,
|
| 2099 |
+
"num_tokens": 26830268.0,
|
| 2100 |
+
"step": 209
|
| 2101 |
+
},
|
| 2102 |
+
{
|
| 2103 |
+
"entropy": 1.003640703856945,
|
| 2104 |
+
"epoch": 2.694533762057878,
|
| 2105 |
+
"grad_norm": 0.26877644658088684,
|
| 2106 |
+
"learning_rate": 1.5482793275958529e-06,
|
| 2107 |
+
"loss": 0.9935470819473267,
|
| 2108 |
+
"mean_token_accuracy": 0.6985340863466263,
|
| 2109 |
+
"num_tokens": 26959109.0,
|
| 2110 |
+
"step": 210
|
| 2111 |
+
},
|
| 2112 |
+
{
|
| 2113 |
+
"entropy": 1.0105368196964264,
|
| 2114 |
+
"epoch": 2.707395498392283,
|
| 2115 |
+
"grad_norm": 0.16719378530979156,
|
| 2116 |
+
"learning_rate": 1.428063863472895e-06,
|
| 2117 |
+
"loss": 0.998131275177002,
|
| 2118 |
+
"mean_token_accuracy": 0.6997055560350418,
|
| 2119 |
+
"num_tokens": 27088875.0,
|
| 2120 |
+
"step": 211
|
| 2121 |
+
},
|
| 2122 |
+
{
|
| 2123 |
+
"entropy": 1.001611903309822,
|
| 2124 |
+
"epoch": 2.720257234726688,
|
| 2125 |
+
"grad_norm": 0.14638130366802216,
|
| 2126 |
+
"learning_rate": 1.312568831989258e-06,
|
| 2127 |
+
"loss": 0.9942350387573242,
|
| 2128 |
+
"mean_token_accuracy": 0.6993389204144478,
|
| 2129 |
+
"num_tokens": 27218005.0,
|
| 2130 |
+
"step": 212
|
| 2131 |
+
},
|
| 2132 |
+
{
|
| 2133 |
+
"entropy": 0.9718720093369484,
|
| 2134 |
+
"epoch": 2.733118971061093,
|
| 2135 |
+
"grad_norm": 0.1539345532655716,
|
| 2136 |
+
"learning_rate": 1.201817361771837e-06,
|
| 2137 |
+
"loss": 0.9664239287376404,
|
| 2138 |
+
"mean_token_accuracy": 0.707412488758564,
|
| 2139 |
+
"num_tokens": 27345118.0,
|
| 2140 |
+
"step": 213
|
| 2141 |
+
},
|
| 2142 |
+
{
|
| 2143 |
+
"entropy": 0.9780362546443939,
|
| 2144 |
+
"epoch": 2.7459807073954985,
|
| 2145 |
+
"grad_norm": 0.14015953242778778,
|
| 2146 |
+
"learning_rate": 1.095831631518729e-06,
|
| 2147 |
+
"loss": 0.9685409069061279,
|
| 2148 |
+
"mean_token_accuracy": 0.706133060157299,
|
| 2149 |
+
"num_tokens": 27473155.0,
|
| 2150 |
+
"step": 214
|
| 2151 |
+
},
|
| 2152 |
+
{
|
| 2153 |
+
"entropy": 0.9646907821297646,
|
| 2154 |
+
"epoch": 2.7588424437299035,
|
| 2155 |
+
"grad_norm": 0.14137625694274902,
|
| 2156 |
+
"learning_rate": 9.946328655577624e-07,
|
| 2157 |
+
"loss": 0.9556713700294495,
|
| 2158 |
+
"mean_token_accuracy": 0.7085167616605759,
|
| 2159 |
+
"num_tokens": 27602992.0,
|
| 2160 |
+
"step": 215
|
| 2161 |
+
},
|
| 2162 |
+
{
|
| 2163 |
+
"entropy": 0.969658762216568,
|
| 2164 |
+
"epoch": 2.7717041800643085,
|
| 2165 |
+
"grad_norm": 0.14186272025108337,
|
| 2166 |
+
"learning_rate": 8.98241329596236e-07,
|
| 2167 |
+
"loss": 0.963873565196991,
|
| 2168 |
+
"mean_token_accuracy": 0.705694705247879,
|
| 2169 |
+
"num_tokens": 27732425.0,
|
| 2170 |
+
"step": 216
|
| 2171 |
+
},
|
| 2172 |
+
{
|
| 2173 |
+
"entropy": 0.9947944805026054,
|
| 2174 |
+
"epoch": 2.784565916398714,
|
| 2175 |
+
"grad_norm": 0.14323608577251434,
|
| 2176 |
+
"learning_rate": 8.066763266625282e-07,
|
| 2177 |
+
"loss": 0.9879176020622253,
|
| 2178 |
+
"mean_token_accuracy": 0.7011514753103256,
|
| 2179 |
+
"num_tokens": 27861591.0,
|
| 2180 |
+
"step": 217
|
| 2181 |
+
},
|
| 2182 |
+
{
|
| 2183 |
+
"entropy": 0.9838699772953987,
|
| 2184 |
+
"epoch": 2.797427652733119,
|
| 2185 |
+
"grad_norm": 0.14354315400123596,
|
| 2186 |
+
"learning_rate": 7.199561932405952e-07,
|
| 2187 |
+
"loss": 0.9724022150039673,
|
| 2188 |
+
"mean_token_accuracy": 0.7043187394738197,
|
| 2189 |
+
"num_tokens": 27991145.0,
|
| 2190 |
+
"step": 218
|
| 2191 |
+
},
|
| 2192 |
+
{
|
| 2193 |
+
"entropy": 0.9758647233247757,
|
| 2194 |
+
"epoch": 2.810289389067524,
|
| 2195 |
+
"grad_norm": 0.14615927636623383,
|
| 2196 |
+
"learning_rate": 6.380982955979192e-07,
|
| 2197 |
+
"loss": 0.9710283279418945,
|
| 2198 |
+
"mean_token_accuracy": 0.7058038115501404,
|
| 2199 |
+
"num_tokens": 28121049.0,
|
| 2200 |
+
"step": 219
|
| 2201 |
+
},
|
| 2202 |
+
{
|
| 2203 |
+
"entropy": 0.9719097539782524,
|
| 2204 |
+
"epoch": 2.823151125401929,
|
| 2205 |
+
"grad_norm": 0.15186373889446259,
|
| 2206 |
+
"learning_rate": 5.611190263078464e-07,
|
| 2207 |
+
"loss": 0.9629349708557129,
|
| 2208 |
+
"mean_token_accuracy": 0.7060469463467598,
|
| 2209 |
+
"num_tokens": 28251006.0,
|
| 2210 |
+
"step": 220
|
| 2211 |
+
},
|
| 2212 |
+
{
|
| 2213 |
+
"entropy": 0.9855683818459511,
|
| 2214 |
+
"epoch": 2.8360128617363345,
|
| 2215 |
+
"grad_norm": 0.1452024132013321,
|
| 2216 |
+
"learning_rate": 4.890338009668316e-07,
|
| 2217 |
+
"loss": 0.9732274413108826,
|
| 2218 |
+
"mean_token_accuracy": 0.7041314393281937,
|
| 2219 |
+
"num_tokens": 28380271.0,
|
| 2220 |
+
"step": 221
|
| 2221 |
+
},
|
| 2222 |
+
{
|
| 2223 |
+
"entropy": 0.9635618776082993,
|
| 2224 |
+
"epoch": 2.8488745980707395,
|
| 2225 |
+
"grad_norm": 0.14456729590892792,
|
| 2226 |
+
"learning_rate": 4.2185705510739415e-07,
|
| 2227 |
+
"loss": 0.9557806253433228,
|
| 2228 |
+
"mean_token_accuracy": 0.7088164985179901,
|
| 2229 |
+
"num_tokens": 28510489.0,
|
| 2230 |
+
"step": 222
|
| 2231 |
+
},
|
| 2232 |
+
{
|
| 2233 |
+
"entropy": 1.0085260719060898,
|
| 2234 |
+
"epoch": 2.861736334405145,
|
| 2235 |
+
"grad_norm": 0.1431344598531723,
|
| 2236 |
+
"learning_rate": 3.5960224130728857e-07,
|
| 2237 |
+
"loss": 1.0044658184051514,
|
| 2238 |
+
"mean_token_accuracy": 0.696587473154068,
|
| 2239 |
+
"num_tokens": 28638550.0,
|
| 2240 |
+
"step": 223
|
| 2241 |
+
},
|
| 2242 |
+
{
|
| 2243 |
+
"entropy": 1.0058645457029343,
|
| 2244 |
+
"epoch": 2.87459807073955,
|
| 2245 |
+
"grad_norm": 0.1409962773323059,
|
| 2246 |
+
"learning_rate": 3.0228182649555126e-07,
|
| 2247 |
+
"loss": 0.9938859939575195,
|
| 2248 |
+
"mean_token_accuracy": 0.7006662487983704,
|
| 2249 |
+
"num_tokens": 28768669.0,
|
| 2250 |
+
"step": 224
|
| 2251 |
+
},
|
| 2252 |
+
{
|
| 2253 |
+
"entropy": 0.9956894516944885,
|
| 2254 |
+
"epoch": 2.887459807073955,
|
| 2255 |
+
"grad_norm": 0.14797310531139374,
|
| 2256 |
+
"learning_rate": 2.499072894559057e-07,
|
| 2257 |
+
"loss": 0.9848740696907043,
|
| 2258 |
+
"mean_token_accuracy": 0.7025537341833115,
|
| 2259 |
+
"num_tokens": 28897003.0,
|
| 2260 |
+
"step": 225
|
| 2261 |
+
},
|
| 2262 |
+
{
|
| 2263 |
+
"entropy": 0.9903870970010757,
|
| 2264 |
+
"epoch": 2.90032154340836,
|
| 2265 |
+
"grad_norm": 0.14364922046661377,
|
| 2266 |
+
"learning_rate": 2.0248911852807916e-07,
|
| 2267 |
+
"loss": 0.9792647957801819,
|
| 2268 |
+
"mean_token_accuracy": 0.7026231661438942,
|
| 2269 |
+
"num_tokens": 29022883.0,
|
| 2270 |
+
"step": 226
|
| 2271 |
+
},
|
| 2272 |
+
{
|
| 2273 |
+
"entropy": 0.9798277169466019,
|
| 2274 |
+
"epoch": 2.913183279742765,
|
| 2275 |
+
"grad_norm": 0.14528293907642365,
|
| 2276 |
+
"learning_rate": 1.6003680950742728e-07,
|
| 2277 |
+
"loss": 0.9743708372116089,
|
| 2278 |
+
"mean_token_accuracy": 0.7052473574876785,
|
| 2279 |
+
"num_tokens": 29150724.0,
|
| 2280 |
+
"step": 227
|
| 2281 |
+
},
|
| 2282 |
+
{
|
| 2283 |
+
"entropy": 1.003961905837059,
|
| 2284 |
+
"epoch": 2.9260450160771705,
|
| 2285 |
+
"grad_norm": 0.14702223241329193,
|
| 2286 |
+
"learning_rate": 1.2255886374334946e-07,
|
| 2287 |
+
"loss": 1.0036938190460205,
|
| 2288 |
+
"mean_token_accuracy": 0.6962004378437996,
|
| 2289 |
+
"num_tokens": 29280359.0,
|
| 2290 |
+
"step": 228
|
| 2291 |
+
},
|
| 2292 |
+
{
|
| 2293 |
+
"entropy": 0.9913759529590607,
|
| 2294 |
+
"epoch": 2.9389067524115755,
|
| 2295 |
+
"grad_norm": 0.14192230999469757,
|
| 2296 |
+
"learning_rate": 9.006278643683696e-08,
|
| 2297 |
+
"loss": 0.9827680587768555,
|
| 2298 |
+
"mean_token_accuracy": 0.7011790797114372,
|
| 2299 |
+
"num_tokens": 29410482.0,
|
| 2300 |
+
"step": 229
|
| 2301 |
+
},
|
| 2302 |
+
{
|
| 2303 |
+
"entropy": 0.9629239290952682,
|
| 2304 |
+
"epoch": 2.951768488745981,
|
| 2305 |
+
"grad_norm": 0.14842632412910461,
|
| 2306 |
+
"learning_rate": 6.255508513750841e-08,
|
| 2307 |
+
"loss": 0.954397439956665,
|
| 2308 |
+
"mean_token_accuracy": 0.708974651992321,
|
| 2309 |
+
"num_tokens": 29540979.0,
|
| 2310 |
+
"step": 230
|
| 2311 |
+
},
|
| 2312 |
+
{
|
| 2313 |
+
"entropy": 0.9984769746661186,
|
| 2314 |
+
"epoch": 2.964630225080386,
|
| 2315 |
+
"grad_norm": 0.14408619701862335,
|
| 2316 |
+
"learning_rate": 4.004126844042444e-08,
|
| 2317 |
+
"loss": 0.9900475740432739,
|
| 2318 |
+
"mean_token_accuracy": 0.699671782553196,
|
| 2319 |
+
"num_tokens": 29669764.0,
|
| 2320 |
+
"step": 231
|
| 2321 |
+
},
|
| 2322 |
+
{
|
| 2323 |
+
"entropy": 0.9829242154955864,
|
| 2324 |
+
"epoch": 2.977491961414791,
|
| 2325 |
+
"grad_norm": 0.1520869880914688,
|
| 2326 |
+
"learning_rate": 2.2525844882964607e-08,
|
| 2327 |
+
"loss": 0.9738559126853943,
|
| 2328 |
+
"mean_token_accuracy": 0.7055443450808525,
|
| 2329 |
+
"num_tokens": 29798608.0,
|
| 2330 |
+
"step": 232
|
| 2331 |
+
},
|
| 2332 |
+
{
|
| 2333 |
+
"entropy": 0.9934249892830849,
|
| 2334 |
+
"epoch": 2.990353697749196,
|
| 2335 |
+
"grad_norm": 0.14561671018600464,
|
| 2336 |
+
"learning_rate": 1.0012322041960676e-08,
|
| 2337 |
+
"loss": 0.983726978302002,
|
| 2338 |
+
"mean_token_accuracy": 0.7004626914858818,
|
| 2339 |
+
"num_tokens": 29927865.0,
|
| 2340 |
+
"step": 233
|
| 2341 |
+
},
|
| 2342 |
+
{
|
| 2343 |
+
"entropy": 0.9948156376679739,
|
| 2344 |
+
"epoch": 3.0,
|
| 2345 |
+
"grad_norm": 0.17473426461219788,
|
| 2346 |
+
"learning_rate": 2.503205831277944e-09,
|
| 2347 |
+
"loss": 0.9984904527664185,
|
| 2348 |
+
"mean_token_accuracy": 0.6967108050982157,
|
| 2349 |
+
"num_tokens": 29999036.0,
|
| 2350 |
+
"step": 234
|
| 2351 |
+
}
|
| 2352 |
+
],
|
| 2353 |
+
"logging_steps": 1,
|
| 2354 |
+
"max_steps": 234,
|
| 2355 |
+
"num_input_tokens_seen": 0,
|
| 2356 |
+
"num_train_epochs": 3,
|
| 2357 |
+
"save_steps": 500,
|
| 2358 |
+
"stateful_callbacks": {
|
| 2359 |
+
"TrainerControl": {
|
| 2360 |
+
"args": {
|
| 2361 |
+
"should_epoch_stop": false,
|
| 2362 |
+
"should_evaluate": false,
|
| 2363 |
+
"should_log": false,
|
| 2364 |
+
"should_save": true,
|
| 2365 |
+
"should_training_stop": true
|
| 2366 |
+
},
|
| 2367 |
+
"attributes": {}
|
| 2368 |
+
}
|
| 2369 |
+
},
|
| 2370 |
+
"total_flos": 3.1722382507691213e+18,
|
| 2371 |
+
"train_batch_size": 1,
|
| 2372 |
+
"trial_name": null,
|
| 2373 |
+
"trial_params": null
|
| 2374 |
+
}
|