Upload folder using huggingface_hub
Browse files- checkpoint-2084/README.md +207 -0
- checkpoint-2084/adapter_config.json +42 -0
- checkpoint-2084/adapter_model.safetensors +3 -0
- checkpoint-2084/chat_template.jinja +15 -0
- checkpoint-2084/optimizer.pt +3 -0
- checkpoint-2084/rng_state.pth +3 -0
- checkpoint-2084/scheduler.pt +3 -0
- checkpoint-2084/special_tokens_map.json +30 -0
- checkpoint-2084/tokenizer.json +0 -0
- checkpoint-2084/tokenizer_config.json +43 -0
- checkpoint-2084/trainer_state.json +1490 -0
- checkpoint-2084/training_args.bin +3 -0
- checkpoint-2605/README.md +207 -0
- checkpoint-2605/adapter_config.json +42 -0
- checkpoint-2605/adapter_model.safetensors +3 -0
- checkpoint-2605/chat_template.jinja +15 -0
- checkpoint-2605/optimizer.pt +3 -0
- checkpoint-2605/rng_state.pth +3 -0
- checkpoint-2605/scheduler.pt +3 -0
- checkpoint-2605/special_tokens_map.json +30 -0
- checkpoint-2605/tokenizer.json +0 -0
- checkpoint-2605/tokenizer_config.json +43 -0
- checkpoint-2605/trainer_state.json +1854 -0
- checkpoint-2605/training_args.bin +3 -0
checkpoint-2084/README.md
ADDED
|
@@ -0,0 +1,207 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: Henit007/modelo3_finetuned
|
| 3 |
+
library_name: peft
|
| 4 |
+
pipeline_tag: text-generation
|
| 5 |
+
tags:
|
| 6 |
+
- base_model:adapter:Henit007/modelo3_finetuned
|
| 7 |
+
- lora
|
| 8 |
+
- transformers
|
| 9 |
+
---
|
| 10 |
+
|
| 11 |
+
# Model Card for Model ID
|
| 12 |
+
|
| 13 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 14 |
+
|
| 15 |
+
|
| 16 |
+
|
| 17 |
+
## Model Details
|
| 18 |
+
|
| 19 |
+
### Model Description
|
| 20 |
+
|
| 21 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 22 |
+
|
| 23 |
+
|
| 24 |
+
|
| 25 |
+
- **Developed by:** [More Information Needed]
|
| 26 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 27 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 28 |
+
- **Model type:** [More Information Needed]
|
| 29 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 30 |
+
- **License:** [More Information Needed]
|
| 31 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 32 |
+
|
| 33 |
+
### Model Sources [optional]
|
| 34 |
+
|
| 35 |
+
<!-- Provide the basic links for the model. -->
|
| 36 |
+
|
| 37 |
+
- **Repository:** [More Information Needed]
|
| 38 |
+
- **Paper [optional]:** [More Information Needed]
|
| 39 |
+
- **Demo [optional]:** [More Information Needed]
|
| 40 |
+
|
| 41 |
+
## Uses
|
| 42 |
+
|
| 43 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 44 |
+
|
| 45 |
+
### Direct Use
|
| 46 |
+
|
| 47 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 48 |
+
|
| 49 |
+
[More Information Needed]
|
| 50 |
+
|
| 51 |
+
### Downstream Use [optional]
|
| 52 |
+
|
| 53 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 54 |
+
|
| 55 |
+
[More Information Needed]
|
| 56 |
+
|
| 57 |
+
### Out-of-Scope Use
|
| 58 |
+
|
| 59 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 60 |
+
|
| 61 |
+
[More Information Needed]
|
| 62 |
+
|
| 63 |
+
## Bias, Risks, and Limitations
|
| 64 |
+
|
| 65 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 66 |
+
|
| 67 |
+
[More Information Needed]
|
| 68 |
+
|
| 69 |
+
### Recommendations
|
| 70 |
+
|
| 71 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 72 |
+
|
| 73 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 74 |
+
|
| 75 |
+
## How to Get Started with the Model
|
| 76 |
+
|
| 77 |
+
Use the code below to get started with the model.
|
| 78 |
+
|
| 79 |
+
[More Information Needed]
|
| 80 |
+
|
| 81 |
+
## Training Details
|
| 82 |
+
|
| 83 |
+
### Training Data
|
| 84 |
+
|
| 85 |
+
<!-- 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. -->
|
| 86 |
+
|
| 87 |
+
[More Information Needed]
|
| 88 |
+
|
| 89 |
+
### Training Procedure
|
| 90 |
+
|
| 91 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 92 |
+
|
| 93 |
+
#### Preprocessing [optional]
|
| 94 |
+
|
| 95 |
+
[More Information Needed]
|
| 96 |
+
|
| 97 |
+
|
| 98 |
+
#### Training Hyperparameters
|
| 99 |
+
|
| 100 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 101 |
+
|
| 102 |
+
#### Speeds, Sizes, Times [optional]
|
| 103 |
+
|
| 104 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 105 |
+
|
| 106 |
+
[More Information Needed]
|
| 107 |
+
|
| 108 |
+
## Evaluation
|
| 109 |
+
|
| 110 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 111 |
+
|
| 112 |
+
### Testing Data, Factors & Metrics
|
| 113 |
+
|
| 114 |
+
#### Testing Data
|
| 115 |
+
|
| 116 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 117 |
+
|
| 118 |
+
[More Information Needed]
|
| 119 |
+
|
| 120 |
+
#### Factors
|
| 121 |
+
|
| 122 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 123 |
+
|
| 124 |
+
[More Information Needed]
|
| 125 |
+
|
| 126 |
+
#### Metrics
|
| 127 |
+
|
| 128 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 129 |
+
|
| 130 |
+
[More Information Needed]
|
| 131 |
+
|
| 132 |
+
### Results
|
| 133 |
+
|
| 134 |
+
[More Information Needed]
|
| 135 |
+
|
| 136 |
+
#### Summary
|
| 137 |
+
|
| 138 |
+
|
| 139 |
+
|
| 140 |
+
## Model Examination [optional]
|
| 141 |
+
|
| 142 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 143 |
+
|
| 144 |
+
[More Information Needed]
|
| 145 |
+
|
| 146 |
+
## Environmental Impact
|
| 147 |
+
|
| 148 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 149 |
+
|
| 150 |
+
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).
|
| 151 |
+
|
| 152 |
+
- **Hardware Type:** [More Information Needed]
|
| 153 |
+
- **Hours used:** [More Information Needed]
|
| 154 |
+
- **Cloud Provider:** [More Information Needed]
|
| 155 |
+
- **Compute Region:** [More Information Needed]
|
| 156 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 157 |
+
|
| 158 |
+
## Technical Specifications [optional]
|
| 159 |
+
|
| 160 |
+
### Model Architecture and Objective
|
| 161 |
+
|
| 162 |
+
[More Information Needed]
|
| 163 |
+
|
| 164 |
+
### Compute Infrastructure
|
| 165 |
+
|
| 166 |
+
[More Information Needed]
|
| 167 |
+
|
| 168 |
+
#### Hardware
|
| 169 |
+
|
| 170 |
+
[More Information Needed]
|
| 171 |
+
|
| 172 |
+
#### Software
|
| 173 |
+
|
| 174 |
+
[More Information Needed]
|
| 175 |
+
|
| 176 |
+
## Citation [optional]
|
| 177 |
+
|
| 178 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 179 |
+
|
| 180 |
+
**BibTeX:**
|
| 181 |
+
|
| 182 |
+
[More Information Needed]
|
| 183 |
+
|
| 184 |
+
**APA:**
|
| 185 |
+
|
| 186 |
+
[More Information Needed]
|
| 187 |
+
|
| 188 |
+
## Glossary [optional]
|
| 189 |
+
|
| 190 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 191 |
+
|
| 192 |
+
[More Information Needed]
|
| 193 |
+
|
| 194 |
+
## More Information [optional]
|
| 195 |
+
|
| 196 |
+
[More Information Needed]
|
| 197 |
+
|
| 198 |
+
## Model Card Authors [optional]
|
| 199 |
+
|
| 200 |
+
[More Information Needed]
|
| 201 |
+
|
| 202 |
+
## Model Card Contact
|
| 203 |
+
|
| 204 |
+
[More Information Needed]
|
| 205 |
+
### Framework versions
|
| 206 |
+
|
| 207 |
+
- PEFT 0.17.0
|
checkpoint-2084/adapter_config.json
ADDED
|
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "Henit007/modelo3_finetuned",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"corda_config": null,
|
| 7 |
+
"eva_config": null,
|
| 8 |
+
"exclude_modules": null,
|
| 9 |
+
"fan_in_fan_out": false,
|
| 10 |
+
"inference_mode": true,
|
| 11 |
+
"init_lora_weights": true,
|
| 12 |
+
"layer_replication": null,
|
| 13 |
+
"layers_pattern": null,
|
| 14 |
+
"layers_to_transform": null,
|
| 15 |
+
"loftq_config": {},
|
| 16 |
+
"lora_alpha": 64,
|
| 17 |
+
"lora_bias": false,
|
| 18 |
+
"lora_dropout": 0.05,
|
| 19 |
+
"megatron_config": null,
|
| 20 |
+
"megatron_core": "megatron.core",
|
| 21 |
+
"modules_to_save": null,
|
| 22 |
+
"peft_type": "LORA",
|
| 23 |
+
"qalora_group_size": 16,
|
| 24 |
+
"r": 8,
|
| 25 |
+
"rank_pattern": {},
|
| 26 |
+
"revision": null,
|
| 27 |
+
"target_modules": [
|
| 28 |
+
"v_proj",
|
| 29 |
+
"o_proj",
|
| 30 |
+
"down_proj",
|
| 31 |
+
"q_proj",
|
| 32 |
+
"gate_proj",
|
| 33 |
+
"k_proj",
|
| 34 |
+
"up_proj"
|
| 35 |
+
],
|
| 36 |
+
"target_parameters": null,
|
| 37 |
+
"task_type": "CAUSAL_LM",
|
| 38 |
+
"trainable_token_indices": null,
|
| 39 |
+
"use_dora": false,
|
| 40 |
+
"use_qalora": false,
|
| 41 |
+
"use_rslora": false
|
| 42 |
+
}
|
checkpoint-2084/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4982215fd1c5da20a468683c2c197e4f55f3a9af4ebd9c912ac958e5d7d214e8
|
| 3 |
+
size 25271744
|
checkpoint-2084/chat_template.jinja
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{% for message in messages %}
|
| 2 |
+
{% if message['role'] == 'user' %}
|
| 3 |
+
{{ '<|user|>
|
| 4 |
+
' + message['content'] + eos_token }}
|
| 5 |
+
{% elif message['role'] == 'system' %}
|
| 6 |
+
{{ '<|system|>
|
| 7 |
+
' + message['content'] + eos_token }}
|
| 8 |
+
{% elif message['role'] == 'assistant' %}
|
| 9 |
+
{{ '<|assistant|>
|
| 10 |
+
' + message['content'] + eos_token }}
|
| 11 |
+
{% endif %}
|
| 12 |
+
{% if loop.last and add_generation_prompt %}
|
| 13 |
+
{{ '<|assistant|>' }}
|
| 14 |
+
{% endif %}
|
| 15 |
+
{% endfor %}
|
checkpoint-2084/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6583387459d2a5433afe5365f886d74d53f7caf6a86bea9c201652888f5ef201
|
| 3 |
+
size 13686237
|
checkpoint-2084/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:176130beb5f7e89b9e21281226263690af78e10f76c7e0d154915bbc4a9dd34a
|
| 3 |
+
size 14645
|
checkpoint-2084/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fd216057c1e55ccfa677328c2f2919c9d61cef775b672a3dc72dce96c554aa74
|
| 3 |
+
size 1465
|
checkpoint-2084/special_tokens_map.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "</s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "</s>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"unk_token": {
|
| 24 |
+
"content": "<unk>",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
}
|
| 30 |
+
}
|
checkpoint-2084/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-2084/tokenizer_config.json
ADDED
|
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"add_prefix_space": null,
|
| 5 |
+
"added_tokens_decoder": {
|
| 6 |
+
"0": {
|
| 7 |
+
"content": "<unk>",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": false,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false,
|
| 12 |
+
"special": true
|
| 13 |
+
},
|
| 14 |
+
"1": {
|
| 15 |
+
"content": "<s>",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": false,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false,
|
| 20 |
+
"special": true
|
| 21 |
+
},
|
| 22 |
+
"2": {
|
| 23 |
+
"content": "</s>",
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"normalized": false,
|
| 26 |
+
"rstrip": false,
|
| 27 |
+
"single_word": false,
|
| 28 |
+
"special": true
|
| 29 |
+
}
|
| 30 |
+
},
|
| 31 |
+
"bos_token": "<s>",
|
| 32 |
+
"clean_up_tokenization_spaces": false,
|
| 33 |
+
"eos_token": "</s>",
|
| 34 |
+
"extra_special_tokens": {},
|
| 35 |
+
"legacy": false,
|
| 36 |
+
"model_max_length": 2048,
|
| 37 |
+
"pad_token": "</s>",
|
| 38 |
+
"padding_side": "right",
|
| 39 |
+
"sp_model_kwargs": {},
|
| 40 |
+
"tokenizer_class": "LlamaTokenizerFast",
|
| 41 |
+
"unk_token": "<unk>",
|
| 42 |
+
"use_default_system_prompt": false
|
| 43 |
+
}
|
checkpoint-2084/trainer_state.json
ADDED
|
@@ -0,0 +1,1490 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 4.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 2084,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.019221528111484865,
|
| 14 |
+
"grad_norm": 4.911402702331543,
|
| 15 |
+
"learning_rate": 1.724137931034483e-06,
|
| 16 |
+
"loss": 2.1561,
|
| 17 |
+
"step": 10
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.03844305622296973,
|
| 21 |
+
"grad_norm": 4.560591697692871,
|
| 22 |
+
"learning_rate": 3.6398467432950196e-06,
|
| 23 |
+
"loss": 2.1368,
|
| 24 |
+
"step": 20
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.05766458433445459,
|
| 28 |
+
"grad_norm": 6.820058345794678,
|
| 29 |
+
"learning_rate": 5.555555555555556e-06,
|
| 30 |
+
"loss": 2.3192,
|
| 31 |
+
"step": 30
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.07688611244593946,
|
| 35 |
+
"grad_norm": 7.230356693267822,
|
| 36 |
+
"learning_rate": 7.4712643678160925e-06,
|
| 37 |
+
"loss": 2.6544,
|
| 38 |
+
"step": 40
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.09610764055742431,
|
| 42 |
+
"grad_norm": 6.225106716156006,
|
| 43 |
+
"learning_rate": 9.386973180076629e-06,
|
| 44 |
+
"loss": 2.6349,
|
| 45 |
+
"step": 50
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.11532916866890917,
|
| 49 |
+
"grad_norm": 5.758670330047607,
|
| 50 |
+
"learning_rate": 1.1302681992337164e-05,
|
| 51 |
+
"loss": 2.6164,
|
| 52 |
+
"step": 60
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.13455069678039405,
|
| 56 |
+
"grad_norm": 6.433386325836182,
|
| 57 |
+
"learning_rate": 1.3218390804597702e-05,
|
| 58 |
+
"loss": 2.6651,
|
| 59 |
+
"step": 70
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.15377222489187892,
|
| 63 |
+
"grad_norm": 6.204464435577393,
|
| 64 |
+
"learning_rate": 1.5134099616858237e-05,
|
| 65 |
+
"loss": 2.5232,
|
| 66 |
+
"step": 80
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.17299375300336375,
|
| 70 |
+
"grad_norm": 6.514060974121094,
|
| 71 |
+
"learning_rate": 1.7049808429118776e-05,
|
| 72 |
+
"loss": 2.5878,
|
| 73 |
+
"step": 90
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.19221528111484862,
|
| 77 |
+
"grad_norm": 5.641262054443359,
|
| 78 |
+
"learning_rate": 1.896551724137931e-05,
|
| 79 |
+
"loss": 2.5566,
|
| 80 |
+
"step": 100
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.21143680922633348,
|
| 84 |
+
"grad_norm": 6.221690654754639,
|
| 85 |
+
"learning_rate": 2.088122605363985e-05,
|
| 86 |
+
"loss": 2.6939,
|
| 87 |
+
"step": 110
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.23065833733781835,
|
| 91 |
+
"grad_norm": 5.924990177154541,
|
| 92 |
+
"learning_rate": 2.2796934865900384e-05,
|
| 93 |
+
"loss": 2.6168,
|
| 94 |
+
"step": 120
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.2498798654493032,
|
| 98 |
+
"grad_norm": 5.515899181365967,
|
| 99 |
+
"learning_rate": 2.4712643678160922e-05,
|
| 100 |
+
"loss": 2.6026,
|
| 101 |
+
"step": 130
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.2691013935607881,
|
| 105 |
+
"grad_norm": 5.406517028808594,
|
| 106 |
+
"learning_rate": 2.662835249042146e-05,
|
| 107 |
+
"loss": 2.4847,
|
| 108 |
+
"step": 140
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.28832292167227297,
|
| 112 |
+
"grad_norm": 5.749735355377197,
|
| 113 |
+
"learning_rate": 2.8544061302681996e-05,
|
| 114 |
+
"loss": 2.621,
|
| 115 |
+
"step": 150
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.30754444978375783,
|
| 119 |
+
"grad_norm": 5.63827657699585,
|
| 120 |
+
"learning_rate": 3.045977011494253e-05,
|
| 121 |
+
"loss": 2.5422,
|
| 122 |
+
"step": 160
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.3267659778952427,
|
| 126 |
+
"grad_norm": 7.321156024932861,
|
| 127 |
+
"learning_rate": 3.2375478927203066e-05,
|
| 128 |
+
"loss": 2.4498,
|
| 129 |
+
"step": 170
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.3459875060067275,
|
| 133 |
+
"grad_norm": 5.711870193481445,
|
| 134 |
+
"learning_rate": 3.4291187739463604e-05,
|
| 135 |
+
"loss": 2.4447,
|
| 136 |
+
"step": 180
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.3652090341182124,
|
| 140 |
+
"grad_norm": 6.159710884094238,
|
| 141 |
+
"learning_rate": 3.620689655172414e-05,
|
| 142 |
+
"loss": 2.4798,
|
| 143 |
+
"step": 190
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.38443056222969724,
|
| 147 |
+
"grad_norm": 6.255421161651611,
|
| 148 |
+
"learning_rate": 3.8122605363984674e-05,
|
| 149 |
+
"loss": 2.435,
|
| 150 |
+
"step": 200
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.4036520903411821,
|
| 154 |
+
"grad_norm": 6.48488187789917,
|
| 155 |
+
"learning_rate": 4.003831417624521e-05,
|
| 156 |
+
"loss": 2.43,
|
| 157 |
+
"step": 210
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.42287361845266697,
|
| 161 |
+
"grad_norm": 5.98501443862915,
|
| 162 |
+
"learning_rate": 4.195402298850575e-05,
|
| 163 |
+
"loss": 2.3629,
|
| 164 |
+
"step": 220
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.44209514656415183,
|
| 168 |
+
"grad_norm": 7.079067707061768,
|
| 169 |
+
"learning_rate": 4.386973180076628e-05,
|
| 170 |
+
"loss": 2.5268,
|
| 171 |
+
"step": 230
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.4613166746756367,
|
| 175 |
+
"grad_norm": 5.06460428237915,
|
| 176 |
+
"learning_rate": 4.578544061302682e-05,
|
| 177 |
+
"loss": 2.4671,
|
| 178 |
+
"step": 240
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.48053820278712156,
|
| 182 |
+
"grad_norm": 6.475998878479004,
|
| 183 |
+
"learning_rate": 4.770114942528736e-05,
|
| 184 |
+
"loss": 2.3595,
|
| 185 |
+
"step": 250
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.4997597308986064,
|
| 189 |
+
"grad_norm": 5.529846668243408,
|
| 190 |
+
"learning_rate": 4.96168582375479e-05,
|
| 191 |
+
"loss": 2.3635,
|
| 192 |
+
"step": 260
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.5189812590100913,
|
| 196 |
+
"grad_norm": 5.878045558929443,
|
| 197 |
+
"learning_rate": 4.982935153583618e-05,
|
| 198 |
+
"loss": 2.436,
|
| 199 |
+
"step": 270
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.5382027871215762,
|
| 203 |
+
"grad_norm": 5.845484256744385,
|
| 204 |
+
"learning_rate": 4.9616040955631404e-05,
|
| 205 |
+
"loss": 2.4051,
|
| 206 |
+
"step": 280
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.557424315233061,
|
| 210 |
+
"grad_norm": 6.933780670166016,
|
| 211 |
+
"learning_rate": 4.940273037542663e-05,
|
| 212 |
+
"loss": 2.3829,
|
| 213 |
+
"step": 290
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.5766458433445459,
|
| 217 |
+
"grad_norm": 6.303454399108887,
|
| 218 |
+
"learning_rate": 4.9189419795221845e-05,
|
| 219 |
+
"loss": 2.3613,
|
| 220 |
+
"step": 300
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.5958673714560307,
|
| 224 |
+
"grad_norm": 6.88358736038208,
|
| 225 |
+
"learning_rate": 4.897610921501707e-05,
|
| 226 |
+
"loss": 2.3223,
|
| 227 |
+
"step": 310
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.6150888995675157,
|
| 231 |
+
"grad_norm": 6.72720193862915,
|
| 232 |
+
"learning_rate": 4.876279863481229e-05,
|
| 233 |
+
"loss": 2.3706,
|
| 234 |
+
"step": 320
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.6343104276790005,
|
| 238 |
+
"grad_norm": 7.726202011108398,
|
| 239 |
+
"learning_rate": 4.854948805460751e-05,
|
| 240 |
+
"loss": 2.3666,
|
| 241 |
+
"step": 330
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.6535319557904854,
|
| 245 |
+
"grad_norm": 6.805552959442139,
|
| 246 |
+
"learning_rate": 4.8336177474402734e-05,
|
| 247 |
+
"loss": 2.3535,
|
| 248 |
+
"step": 340
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.6727534839019702,
|
| 252 |
+
"grad_norm": 5.095221996307373,
|
| 253 |
+
"learning_rate": 4.812286689419796e-05,
|
| 254 |
+
"loss": 2.2583,
|
| 255 |
+
"step": 350
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.691975012013455,
|
| 259 |
+
"grad_norm": 6.583714485168457,
|
| 260 |
+
"learning_rate": 4.7909556313993175e-05,
|
| 261 |
+
"loss": 2.2992,
|
| 262 |
+
"step": 360
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.7111965401249399,
|
| 266 |
+
"grad_norm": 5.969571113586426,
|
| 267 |
+
"learning_rate": 4.76962457337884e-05,
|
| 268 |
+
"loss": 2.3388,
|
| 269 |
+
"step": 370
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.7304180682364247,
|
| 273 |
+
"grad_norm": 7.320237636566162,
|
| 274 |
+
"learning_rate": 4.7482935153583616e-05,
|
| 275 |
+
"loss": 2.2875,
|
| 276 |
+
"step": 380
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.7496395963479097,
|
| 280 |
+
"grad_norm": 6.594917297363281,
|
| 281 |
+
"learning_rate": 4.726962457337884e-05,
|
| 282 |
+
"loss": 2.1744,
|
| 283 |
+
"step": 390
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.7688611244593945,
|
| 287 |
+
"grad_norm": 6.340092658996582,
|
| 288 |
+
"learning_rate": 4.7056313993174063e-05,
|
| 289 |
+
"loss": 2.2252,
|
| 290 |
+
"step": 400
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.7880826525708794,
|
| 294 |
+
"grad_norm": 6.270530700683594,
|
| 295 |
+
"learning_rate": 4.684300341296928e-05,
|
| 296 |
+
"loss": 2.2892,
|
| 297 |
+
"step": 410
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.8073041806823642,
|
| 301 |
+
"grad_norm": 6.28891134262085,
|
| 302 |
+
"learning_rate": 4.662969283276451e-05,
|
| 303 |
+
"loss": 2.3549,
|
| 304 |
+
"step": 420
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.8265257087938491,
|
| 308 |
+
"grad_norm": 6.432322978973389,
|
| 309 |
+
"learning_rate": 4.641638225255973e-05,
|
| 310 |
+
"loss": 2.2514,
|
| 311 |
+
"step": 430
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.8457472369053339,
|
| 315 |
+
"grad_norm": 6.2773613929748535,
|
| 316 |
+
"learning_rate": 4.620307167235495e-05,
|
| 317 |
+
"loss": 2.3056,
|
| 318 |
+
"step": 440
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.8649687650168189,
|
| 322 |
+
"grad_norm": 6.604885578155518,
|
| 323 |
+
"learning_rate": 4.5989761092150176e-05,
|
| 324 |
+
"loss": 2.2911,
|
| 325 |
+
"step": 450
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.8841902931283037,
|
| 329 |
+
"grad_norm": 5.717179775238037,
|
| 330 |
+
"learning_rate": 4.577645051194539e-05,
|
| 331 |
+
"loss": 2.3191,
|
| 332 |
+
"step": 460
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.9034118212397886,
|
| 336 |
+
"grad_norm": 6.134155750274658,
|
| 337 |
+
"learning_rate": 4.556313993174062e-05,
|
| 338 |
+
"loss": 2.2451,
|
| 339 |
+
"step": 470
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.9226333493512734,
|
| 343 |
+
"grad_norm": 6.287547588348389,
|
| 344 |
+
"learning_rate": 4.534982935153584e-05,
|
| 345 |
+
"loss": 2.2448,
|
| 346 |
+
"step": 480
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.9418548774627583,
|
| 350 |
+
"grad_norm": 5.859134197235107,
|
| 351 |
+
"learning_rate": 4.513651877133106e-05,
|
| 352 |
+
"loss": 2.1997,
|
| 353 |
+
"step": 490
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.9610764055742431,
|
| 357 |
+
"grad_norm": 6.595165729522705,
|
| 358 |
+
"learning_rate": 4.492320819112628e-05,
|
| 359 |
+
"loss": 2.1794,
|
| 360 |
+
"step": 500
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.980297933685728,
|
| 364 |
+
"grad_norm": 6.322437286376953,
|
| 365 |
+
"learning_rate": 4.4709897610921506e-05,
|
| 366 |
+
"loss": 2.2895,
|
| 367 |
+
"step": 510
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.9995194617972128,
|
| 371 |
+
"grad_norm": 7.458081245422363,
|
| 372 |
+
"learning_rate": 4.449658703071672e-05,
|
| 373 |
+
"loss": 2.1918,
|
| 374 |
+
"step": 520
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 1.0172993753003363,
|
| 378 |
+
"grad_norm": 6.502513885498047,
|
| 379 |
+
"learning_rate": 4.428327645051195e-05,
|
| 380 |
+
"loss": 2.0686,
|
| 381 |
+
"step": 530
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 1.0365209034118212,
|
| 385 |
+
"grad_norm": 5.94999885559082,
|
| 386 |
+
"learning_rate": 4.406996587030717e-05,
|
| 387 |
+
"loss": 1.9922,
|
| 388 |
+
"step": 540
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 1.0557424315233062,
|
| 392 |
+
"grad_norm": 6.013510704040527,
|
| 393 |
+
"learning_rate": 4.385665529010239e-05,
|
| 394 |
+
"loss": 1.9737,
|
| 395 |
+
"step": 550
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 1.074963959634791,
|
| 399 |
+
"grad_norm": 7.001447677612305,
|
| 400 |
+
"learning_rate": 4.364334470989762e-05,
|
| 401 |
+
"loss": 2.0489,
|
| 402 |
+
"step": 560
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 1.0941854877462758,
|
| 406 |
+
"grad_norm": 7.009434700012207,
|
| 407 |
+
"learning_rate": 4.3430034129692835e-05,
|
| 408 |
+
"loss": 2.0722,
|
| 409 |
+
"step": 570
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 1.1134070158577607,
|
| 413 |
+
"grad_norm": 6.154360294342041,
|
| 414 |
+
"learning_rate": 4.321672354948806e-05,
|
| 415 |
+
"loss": 2.1033,
|
| 416 |
+
"step": 580
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 1.1326285439692456,
|
| 420 |
+
"grad_norm": 7.929754734039307,
|
| 421 |
+
"learning_rate": 4.300341296928328e-05,
|
| 422 |
+
"loss": 2.0605,
|
| 423 |
+
"step": 590
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 1.1518500720807303,
|
| 427 |
+
"grad_norm": 5.974995136260986,
|
| 428 |
+
"learning_rate": 4.27901023890785e-05,
|
| 429 |
+
"loss": 1.9992,
|
| 430 |
+
"step": 600
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 1.1710716001922152,
|
| 434 |
+
"grad_norm": 6.380578994750977,
|
| 435 |
+
"learning_rate": 4.2576791808873724e-05,
|
| 436 |
+
"loss": 2.0509,
|
| 437 |
+
"step": 610
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 1.1902931283037002,
|
| 441 |
+
"grad_norm": 6.86224889755249,
|
| 442 |
+
"learning_rate": 4.236348122866894e-05,
|
| 443 |
+
"loss": 1.9994,
|
| 444 |
+
"step": 620
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 1.209514656415185,
|
| 448 |
+
"grad_norm": 7.081135272979736,
|
| 449 |
+
"learning_rate": 4.2150170648464165e-05,
|
| 450 |
+
"loss": 2.0567,
|
| 451 |
+
"step": 630
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 1.22873618452667,
|
| 455 |
+
"grad_norm": 6.908895492553711,
|
| 456 |
+
"learning_rate": 4.193686006825939e-05,
|
| 457 |
+
"loss": 1.9874,
|
| 458 |
+
"step": 640
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 1.2479577126381547,
|
| 462 |
+
"grad_norm": 7.030237674713135,
|
| 463 |
+
"learning_rate": 4.1723549488054606e-05,
|
| 464 |
+
"loss": 2.0383,
|
| 465 |
+
"step": 650
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 1.2671792407496396,
|
| 469 |
+
"grad_norm": 7.042236804962158,
|
| 470 |
+
"learning_rate": 4.151023890784983e-05,
|
| 471 |
+
"loss": 2.076,
|
| 472 |
+
"step": 660
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 1.2864007688611245,
|
| 476 |
+
"grad_norm": 7.262955188751221,
|
| 477 |
+
"learning_rate": 4.1296928327645054e-05,
|
| 478 |
+
"loss": 1.9956,
|
| 479 |
+
"step": 670
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 1.3056222969726092,
|
| 483 |
+
"grad_norm": 7.4197211265563965,
|
| 484 |
+
"learning_rate": 4.108361774744027e-05,
|
| 485 |
+
"loss": 2.0626,
|
| 486 |
+
"step": 680
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 1.3248438250840942,
|
| 490 |
+
"grad_norm": 8.185269355773926,
|
| 491 |
+
"learning_rate": 4.0870307167235495e-05,
|
| 492 |
+
"loss": 1.9757,
|
| 493 |
+
"step": 690
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 1.344065353195579,
|
| 497 |
+
"grad_norm": 7.224545001983643,
|
| 498 |
+
"learning_rate": 4.065699658703072e-05,
|
| 499 |
+
"loss": 2.0315,
|
| 500 |
+
"step": 700
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 1.363286881307064,
|
| 504 |
+
"grad_norm": 7.302128791809082,
|
| 505 |
+
"learning_rate": 4.044368600682594e-05,
|
| 506 |
+
"loss": 2.0296,
|
| 507 |
+
"step": 710
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 1.382508409418549,
|
| 511 |
+
"grad_norm": 7.413524150848389,
|
| 512 |
+
"learning_rate": 4.0230375426621166e-05,
|
| 513 |
+
"loss": 1.9541,
|
| 514 |
+
"step": 720
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 1.4017299375300336,
|
| 518 |
+
"grad_norm": 6.2689080238342285,
|
| 519 |
+
"learning_rate": 4.0017064846416383e-05,
|
| 520 |
+
"loss": 2.0365,
|
| 521 |
+
"step": 730
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 1.4209514656415185,
|
| 525 |
+
"grad_norm": 6.926391124725342,
|
| 526 |
+
"learning_rate": 3.980375426621161e-05,
|
| 527 |
+
"loss": 2.0117,
|
| 528 |
+
"step": 740
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 1.4401729937530034,
|
| 532 |
+
"grad_norm": 6.754932403564453,
|
| 533 |
+
"learning_rate": 3.959044368600683e-05,
|
| 534 |
+
"loss": 1.9882,
|
| 535 |
+
"step": 750
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 1.4593945218644881,
|
| 539 |
+
"grad_norm": 8.279367446899414,
|
| 540 |
+
"learning_rate": 3.937713310580205e-05,
|
| 541 |
+
"loss": 2.0513,
|
| 542 |
+
"step": 760
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 1.478616049975973,
|
| 546 |
+
"grad_norm": 7.346401691436768,
|
| 547 |
+
"learning_rate": 3.916382252559727e-05,
|
| 548 |
+
"loss": 2.0274,
|
| 549 |
+
"step": 770
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 1.497837578087458,
|
| 553 |
+
"grad_norm": 6.437380313873291,
|
| 554 |
+
"learning_rate": 3.8950511945392496e-05,
|
| 555 |
+
"loss": 1.9917,
|
| 556 |
+
"step": 780
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 1.5170591061989427,
|
| 560 |
+
"grad_norm": 6.856245994567871,
|
| 561 |
+
"learning_rate": 3.873720136518771e-05,
|
| 562 |
+
"loss": 2.0252,
|
| 563 |
+
"step": 790
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 1.5362806343104278,
|
| 567 |
+
"grad_norm": 7.144432067871094,
|
| 568 |
+
"learning_rate": 3.852389078498294e-05,
|
| 569 |
+
"loss": 2.1142,
|
| 570 |
+
"step": 800
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 1.5555021624219125,
|
| 574 |
+
"grad_norm": 6.338939189910889,
|
| 575 |
+
"learning_rate": 3.8310580204778154e-05,
|
| 576 |
+
"loss": 1.9595,
|
| 577 |
+
"step": 810
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 1.5747236905333974,
|
| 581 |
+
"grad_norm": 6.92732572555542,
|
| 582 |
+
"learning_rate": 3.809726962457338e-05,
|
| 583 |
+
"loss": 1.9964,
|
| 584 |
+
"step": 820
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 1.5939452186448824,
|
| 588 |
+
"grad_norm": 6.684772491455078,
|
| 589 |
+
"learning_rate": 3.78839590443686e-05,
|
| 590 |
+
"loss": 2.0192,
|
| 591 |
+
"step": 830
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 1.613166746756367,
|
| 595 |
+
"grad_norm": 6.988185882568359,
|
| 596 |
+
"learning_rate": 3.7670648464163826e-05,
|
| 597 |
+
"loss": 1.9899,
|
| 598 |
+
"step": 840
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 1.632388274867852,
|
| 602 |
+
"grad_norm": 7.449588775634766,
|
| 603 |
+
"learning_rate": 3.745733788395905e-05,
|
| 604 |
+
"loss": 1.9278,
|
| 605 |
+
"step": 850
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 1.651609802979337,
|
| 609 |
+
"grad_norm": 7.102870941162109,
|
| 610 |
+
"learning_rate": 3.724402730375427e-05,
|
| 611 |
+
"loss": 2.0357,
|
| 612 |
+
"step": 860
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 1.6708313310908216,
|
| 616 |
+
"grad_norm": 7.227121829986572,
|
| 617 |
+
"learning_rate": 3.703071672354949e-05,
|
| 618 |
+
"loss": 1.9708,
|
| 619 |
+
"step": 870
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 1.6900528592023067,
|
| 623 |
+
"grad_norm": 7.991628170013428,
|
| 624 |
+
"learning_rate": 3.6817406143344714e-05,
|
| 625 |
+
"loss": 1.9555,
|
| 626 |
+
"step": 880
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 1.7092743873137914,
|
| 630 |
+
"grad_norm": 7.285923957824707,
|
| 631 |
+
"learning_rate": 3.660409556313993e-05,
|
| 632 |
+
"loss": 1.9692,
|
| 633 |
+
"step": 890
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 1.7284959154252764,
|
| 637 |
+
"grad_norm": 6.6300201416015625,
|
| 638 |
+
"learning_rate": 3.6390784982935155e-05,
|
| 639 |
+
"loss": 1.9664,
|
| 640 |
+
"step": 900
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 1.7477174435367613,
|
| 644 |
+
"grad_norm": 7.206388473510742,
|
| 645 |
+
"learning_rate": 3.617747440273038e-05,
|
| 646 |
+
"loss": 1.9698,
|
| 647 |
+
"step": 910
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 1.766938971648246,
|
| 651 |
+
"grad_norm": 7.21373987197876,
|
| 652 |
+
"learning_rate": 3.5964163822525596e-05,
|
| 653 |
+
"loss": 1.9686,
|
| 654 |
+
"step": 920
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 1.786160499759731,
|
| 658 |
+
"grad_norm": 6.428858757019043,
|
| 659 |
+
"learning_rate": 3.575085324232082e-05,
|
| 660 |
+
"loss": 1.9851,
|
| 661 |
+
"step": 930
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 1.8053820278712158,
|
| 665 |
+
"grad_norm": 7.84316873550415,
|
| 666 |
+
"learning_rate": 3.5537542662116044e-05,
|
| 667 |
+
"loss": 1.9722,
|
| 668 |
+
"step": 940
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 1.8246035559827005,
|
| 672 |
+
"grad_norm": 7.756894588470459,
|
| 673 |
+
"learning_rate": 3.532423208191126e-05,
|
| 674 |
+
"loss": 1.9733,
|
| 675 |
+
"step": 950
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 1.8438250840941854,
|
| 679 |
+
"grad_norm": 6.9086480140686035,
|
| 680 |
+
"learning_rate": 3.5110921501706485e-05,
|
| 681 |
+
"loss": 1.9561,
|
| 682 |
+
"step": 960
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 1.8630466122056704,
|
| 686 |
+
"grad_norm": 7.4190802574157715,
|
| 687 |
+
"learning_rate": 3.48976109215017e-05,
|
| 688 |
+
"loss": 1.9004,
|
| 689 |
+
"step": 970
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 1.882268140317155,
|
| 693 |
+
"grad_norm": 6.598989963531494,
|
| 694 |
+
"learning_rate": 3.468430034129693e-05,
|
| 695 |
+
"loss": 1.9914,
|
| 696 |
+
"step": 980
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 1.9014896684286402,
|
| 700 |
+
"grad_norm": 7.208456516265869,
|
| 701 |
+
"learning_rate": 3.447098976109216e-05,
|
| 702 |
+
"loss": 1.9888,
|
| 703 |
+
"step": 990
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 1.920711196540125,
|
| 707 |
+
"grad_norm": 7.192534923553467,
|
| 708 |
+
"learning_rate": 3.4257679180887374e-05,
|
| 709 |
+
"loss": 1.9244,
|
| 710 |
+
"step": 1000
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 1.9399327246516098,
|
| 714 |
+
"grad_norm": 7.464297294616699,
|
| 715 |
+
"learning_rate": 3.40443686006826e-05,
|
| 716 |
+
"loss": 1.916,
|
| 717 |
+
"step": 1010
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 1.9591542527630947,
|
| 721 |
+
"grad_norm": 7.047414779663086,
|
| 722 |
+
"learning_rate": 3.383105802047782e-05,
|
| 723 |
+
"loss": 2.0045,
|
| 724 |
+
"step": 1020
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 1.9783757808745794,
|
| 728 |
+
"grad_norm": 7.436980724334717,
|
| 729 |
+
"learning_rate": 3.361774744027304e-05,
|
| 730 |
+
"loss": 2.015,
|
| 731 |
+
"step": 1030
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 1.9975973089860644,
|
| 735 |
+
"grad_norm": 6.135148525238037,
|
| 736 |
+
"learning_rate": 3.340443686006826e-05,
|
| 737 |
+
"loss": 1.9769,
|
| 738 |
+
"step": 1040
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 2.015377222489188,
|
| 742 |
+
"grad_norm": 6.220305442810059,
|
| 743 |
+
"learning_rate": 3.319112627986348e-05,
|
| 744 |
+
"loss": 1.7707,
|
| 745 |
+
"step": 1050
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 2.0345987506006726,
|
| 749 |
+
"grad_norm": 8.670418739318848,
|
| 750 |
+
"learning_rate": 3.2977815699658704e-05,
|
| 751 |
+
"loss": 1.7048,
|
| 752 |
+
"step": 1060
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 2.0538202787121578,
|
| 756 |
+
"grad_norm": 7.973430633544922,
|
| 757 |
+
"learning_rate": 3.276450511945393e-05,
|
| 758 |
+
"loss": 1.7753,
|
| 759 |
+
"step": 1070
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 2.0730418068236425,
|
| 763 |
+
"grad_norm": 7.165556907653809,
|
| 764 |
+
"learning_rate": 3.2551194539249145e-05,
|
| 765 |
+
"loss": 1.7184,
|
| 766 |
+
"step": 1080
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 2.092263334935127,
|
| 770 |
+
"grad_norm": 8.48978042602539,
|
| 771 |
+
"learning_rate": 3.233788395904437e-05,
|
| 772 |
+
"loss": 1.7799,
|
| 773 |
+
"step": 1090
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 2.1114848630466123,
|
| 777 |
+
"grad_norm": 7.75386905670166,
|
| 778 |
+
"learning_rate": 3.212457337883959e-05,
|
| 779 |
+
"loss": 1.7363,
|
| 780 |
+
"step": 1100
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 2.130706391158097,
|
| 784 |
+
"grad_norm": 7.61426305770874,
|
| 785 |
+
"learning_rate": 3.191126279863481e-05,
|
| 786 |
+
"loss": 1.7388,
|
| 787 |
+
"step": 1110
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 2.149927919269582,
|
| 791 |
+
"grad_norm": 8.537379264831543,
|
| 792 |
+
"learning_rate": 3.169795221843004e-05,
|
| 793 |
+
"loss": 1.7217,
|
| 794 |
+
"step": 1120
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 2.169149447381067,
|
| 798 |
+
"grad_norm": 8.12486457824707,
|
| 799 |
+
"learning_rate": 3.148464163822526e-05,
|
| 800 |
+
"loss": 1.7396,
|
| 801 |
+
"step": 1130
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 2.1883709754925516,
|
| 805 |
+
"grad_norm": 9.46800422668457,
|
| 806 |
+
"learning_rate": 3.127133105802048e-05,
|
| 807 |
+
"loss": 1.7526,
|
| 808 |
+
"step": 1140
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 2.2075925036040367,
|
| 812 |
+
"grad_norm": 7.893990993499756,
|
| 813 |
+
"learning_rate": 3.1058020477815705e-05,
|
| 814 |
+
"loss": 1.7482,
|
| 815 |
+
"step": 1150
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 2.2268140317155214,
|
| 819 |
+
"grad_norm": 8.076356887817383,
|
| 820 |
+
"learning_rate": 3.084470989761092e-05,
|
| 821 |
+
"loss": 1.7622,
|
| 822 |
+
"step": 1160
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 2.246035559827006,
|
| 826 |
+
"grad_norm": 7.560849666595459,
|
| 827 |
+
"learning_rate": 3.0631399317406146e-05,
|
| 828 |
+
"loss": 1.789,
|
| 829 |
+
"step": 1170
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 2.2652570879384912,
|
| 833 |
+
"grad_norm": 7.872079372406006,
|
| 834 |
+
"learning_rate": 3.0418088737201366e-05,
|
| 835 |
+
"loss": 1.7213,
|
| 836 |
+
"step": 1180
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 2.284478616049976,
|
| 840 |
+
"grad_norm": 9.256887435913086,
|
| 841 |
+
"learning_rate": 3.0204778156996587e-05,
|
| 842 |
+
"loss": 1.7497,
|
| 843 |
+
"step": 1190
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 2.3037001441614606,
|
| 847 |
+
"grad_norm": 8.256994247436523,
|
| 848 |
+
"learning_rate": 2.999146757679181e-05,
|
| 849 |
+
"loss": 1.7168,
|
| 850 |
+
"step": 1200
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 2.3229216722729458,
|
| 854 |
+
"grad_norm": 8.07515811920166,
|
| 855 |
+
"learning_rate": 2.977815699658703e-05,
|
| 856 |
+
"loss": 1.7714,
|
| 857 |
+
"step": 1210
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 2.3421432003844305,
|
| 861 |
+
"grad_norm": 7.773881435394287,
|
| 862 |
+
"learning_rate": 2.956484641638225e-05,
|
| 863 |
+
"loss": 1.7627,
|
| 864 |
+
"step": 1220
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 2.3613647284959156,
|
| 868 |
+
"grad_norm": 9.31999397277832,
|
| 869 |
+
"learning_rate": 2.9351535836177476e-05,
|
| 870 |
+
"loss": 1.7635,
|
| 871 |
+
"step": 1230
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 2.3805862566074003,
|
| 875 |
+
"grad_norm": 8.094911575317383,
|
| 876 |
+
"learning_rate": 2.9138225255972696e-05,
|
| 877 |
+
"loss": 1.8119,
|
| 878 |
+
"step": 1240
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 2.399807784718885,
|
| 882 |
+
"grad_norm": 8.966656684875488,
|
| 883 |
+
"learning_rate": 2.8924914675767916e-05,
|
| 884 |
+
"loss": 1.7844,
|
| 885 |
+
"step": 1250
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 2.41902931283037,
|
| 889 |
+
"grad_norm": 8.657224655151367,
|
| 890 |
+
"learning_rate": 2.8711604095563144e-05,
|
| 891 |
+
"loss": 1.7849,
|
| 892 |
+
"step": 1260
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 2.438250840941855,
|
| 896 |
+
"grad_norm": 8.335482597351074,
|
| 897 |
+
"learning_rate": 2.8498293515358364e-05,
|
| 898 |
+
"loss": 1.6967,
|
| 899 |
+
"step": 1270
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 2.45747236905334,
|
| 903 |
+
"grad_norm": 8.769615173339844,
|
| 904 |
+
"learning_rate": 2.8284982935153588e-05,
|
| 905 |
+
"loss": 1.8389,
|
| 906 |
+
"step": 1280
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 2.4766938971648247,
|
| 910 |
+
"grad_norm": 7.692858695983887,
|
| 911 |
+
"learning_rate": 2.807167235494881e-05,
|
| 912 |
+
"loss": 1.7602,
|
| 913 |
+
"step": 1290
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 2.4959154252763094,
|
| 917 |
+
"grad_norm": 7.612323760986328,
|
| 918 |
+
"learning_rate": 2.785836177474403e-05,
|
| 919 |
+
"loss": 1.8411,
|
| 920 |
+
"step": 1300
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 2.5151369533877945,
|
| 924 |
+
"grad_norm": 9.097857475280762,
|
| 925 |
+
"learning_rate": 2.764505119453925e-05,
|
| 926 |
+
"loss": 1.7737,
|
| 927 |
+
"step": 1310
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 2.5343584814992792,
|
| 931 |
+
"grad_norm": 9.11468505859375,
|
| 932 |
+
"learning_rate": 2.7431740614334473e-05,
|
| 933 |
+
"loss": 1.8269,
|
| 934 |
+
"step": 1320
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 2.553580009610764,
|
| 938 |
+
"grad_norm": 9.77290153503418,
|
| 939 |
+
"learning_rate": 2.7218430034129694e-05,
|
| 940 |
+
"loss": 1.7671,
|
| 941 |
+
"step": 1330
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 2.572801537722249,
|
| 945 |
+
"grad_norm": 8.101873397827148,
|
| 946 |
+
"learning_rate": 2.7005119453924914e-05,
|
| 947 |
+
"loss": 1.6804,
|
| 948 |
+
"step": 1340
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 2.5920230658337338,
|
| 952 |
+
"grad_norm": 8.107222557067871,
|
| 953 |
+
"learning_rate": 2.6791808873720138e-05,
|
| 954 |
+
"loss": 1.7327,
|
| 955 |
+
"step": 1350
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 2.6112445939452185,
|
| 959 |
+
"grad_norm": 7.96660852432251,
|
| 960 |
+
"learning_rate": 2.657849829351536e-05,
|
| 961 |
+
"loss": 1.7532,
|
| 962 |
+
"step": 1360
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 2.6304661220567036,
|
| 966 |
+
"grad_norm": 8.748746871948242,
|
| 967 |
+
"learning_rate": 2.636518771331058e-05,
|
| 968 |
+
"loss": 1.7216,
|
| 969 |
+
"step": 1370
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 2.6496876501681883,
|
| 973 |
+
"grad_norm": 8.459169387817383,
|
| 974 |
+
"learning_rate": 2.61518771331058e-05,
|
| 975 |
+
"loss": 1.755,
|
| 976 |
+
"step": 1380
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 2.668909178279673,
|
| 980 |
+
"grad_norm": 8.21006965637207,
|
| 981 |
+
"learning_rate": 2.5938566552901024e-05,
|
| 982 |
+
"loss": 1.7775,
|
| 983 |
+
"step": 1390
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 2.688130706391158,
|
| 987 |
+
"grad_norm": 7.608190059661865,
|
| 988 |
+
"learning_rate": 2.572525597269625e-05,
|
| 989 |
+
"loss": 1.6885,
|
| 990 |
+
"step": 1400
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 2.707352234502643,
|
| 994 |
+
"grad_norm": 7.753986358642578,
|
| 995 |
+
"learning_rate": 2.551194539249147e-05,
|
| 996 |
+
"loss": 1.7477,
|
| 997 |
+
"step": 1410
|
| 998 |
+
},
|
| 999 |
+
{
|
| 1000 |
+
"epoch": 2.726573762614128,
|
| 1001 |
+
"grad_norm": 9.139946937561035,
|
| 1002 |
+
"learning_rate": 2.5298634812286692e-05,
|
| 1003 |
+
"loss": 1.7118,
|
| 1004 |
+
"step": 1420
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 2.7457952907256127,
|
| 1008 |
+
"grad_norm": 8.321805000305176,
|
| 1009 |
+
"learning_rate": 2.5085324232081912e-05,
|
| 1010 |
+
"loss": 1.7373,
|
| 1011 |
+
"step": 1430
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 2.765016818837098,
|
| 1015 |
+
"grad_norm": 6.919346809387207,
|
| 1016 |
+
"learning_rate": 2.4872013651877136e-05,
|
| 1017 |
+
"loss": 1.6811,
|
| 1018 |
+
"step": 1440
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"epoch": 2.7842383469485825,
|
| 1022 |
+
"grad_norm": 8.567264556884766,
|
| 1023 |
+
"learning_rate": 2.4658703071672357e-05,
|
| 1024 |
+
"loss": 1.7402,
|
| 1025 |
+
"step": 1450
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 2.803459875060067,
|
| 1029 |
+
"grad_norm": 8.170304298400879,
|
| 1030 |
+
"learning_rate": 2.4445392491467577e-05,
|
| 1031 |
+
"loss": 1.8064,
|
| 1032 |
+
"step": 1460
|
| 1033 |
+
},
|
| 1034 |
+
{
|
| 1035 |
+
"epoch": 2.8226814031715524,
|
| 1036 |
+
"grad_norm": 8.044082641601562,
|
| 1037 |
+
"learning_rate": 2.42320819112628e-05,
|
| 1038 |
+
"loss": 1.6772,
|
| 1039 |
+
"step": 1470
|
| 1040 |
+
},
|
| 1041 |
+
{
|
| 1042 |
+
"epoch": 2.841902931283037,
|
| 1043 |
+
"grad_norm": 8.453600883483887,
|
| 1044 |
+
"learning_rate": 2.401877133105802e-05,
|
| 1045 |
+
"loss": 1.7352,
|
| 1046 |
+
"step": 1480
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 2.8611244593945218,
|
| 1050 |
+
"grad_norm": 8.70590591430664,
|
| 1051 |
+
"learning_rate": 2.3805460750853242e-05,
|
| 1052 |
+
"loss": 1.7539,
|
| 1053 |
+
"step": 1490
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 2.880345987506007,
|
| 1057 |
+
"grad_norm": 8.303061485290527,
|
| 1058 |
+
"learning_rate": 2.3592150170648466e-05,
|
| 1059 |
+
"loss": 1.7281,
|
| 1060 |
+
"step": 1500
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"epoch": 2.8995675156174916,
|
| 1064 |
+
"grad_norm": 7.61099100112915,
|
| 1065 |
+
"learning_rate": 2.3378839590443686e-05,
|
| 1066 |
+
"loss": 1.6915,
|
| 1067 |
+
"step": 1510
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"epoch": 2.9187890437289763,
|
| 1071 |
+
"grad_norm": 9.040791511535645,
|
| 1072 |
+
"learning_rate": 2.316552901023891e-05,
|
| 1073 |
+
"loss": 1.7099,
|
| 1074 |
+
"step": 1520
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 2.9380105718404614,
|
| 1078 |
+
"grad_norm": 8.227042198181152,
|
| 1079 |
+
"learning_rate": 2.295221843003413e-05,
|
| 1080 |
+
"loss": 1.7134,
|
| 1081 |
+
"step": 1530
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 2.957232099951946,
|
| 1085 |
+
"grad_norm": 7.818427085876465,
|
| 1086 |
+
"learning_rate": 2.273890784982935e-05,
|
| 1087 |
+
"loss": 1.7652,
|
| 1088 |
+
"step": 1540
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 2.976453628063431,
|
| 1092 |
+
"grad_norm": 7.761089324951172,
|
| 1093 |
+
"learning_rate": 2.2525597269624575e-05,
|
| 1094 |
+
"loss": 1.673,
|
| 1095 |
+
"step": 1550
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 2.995675156174916,
|
| 1099 |
+
"grad_norm": 9.148423194885254,
|
| 1100 |
+
"learning_rate": 2.2312286689419796e-05,
|
| 1101 |
+
"loss": 1.7545,
|
| 1102 |
+
"step": 1560
|
| 1103 |
+
},
|
| 1104 |
+
{
|
| 1105 |
+
"epoch": 3.0134550696780393,
|
| 1106 |
+
"grad_norm": 6.961498260498047,
|
| 1107 |
+
"learning_rate": 2.209897610921502e-05,
|
| 1108 |
+
"loss": 1.6289,
|
| 1109 |
+
"step": 1570
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 3.0326765977895245,
|
| 1113 |
+
"grad_norm": 8.595748901367188,
|
| 1114 |
+
"learning_rate": 2.188566552901024e-05,
|
| 1115 |
+
"loss": 1.5369,
|
| 1116 |
+
"step": 1580
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 3.051898125901009,
|
| 1120 |
+
"grad_norm": 8.743279457092285,
|
| 1121 |
+
"learning_rate": 2.1672354948805464e-05,
|
| 1122 |
+
"loss": 1.5447,
|
| 1123 |
+
"step": 1590
|
| 1124 |
+
},
|
| 1125 |
+
{
|
| 1126 |
+
"epoch": 3.071119654012494,
|
| 1127 |
+
"grad_norm": 7.540672302246094,
|
| 1128 |
+
"learning_rate": 2.1459044368600684e-05,
|
| 1129 |
+
"loss": 1.5113,
|
| 1130 |
+
"step": 1600
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 3.090341182123979,
|
| 1134 |
+
"grad_norm": 9.278829574584961,
|
| 1135 |
+
"learning_rate": 2.1245733788395905e-05,
|
| 1136 |
+
"loss": 1.5178,
|
| 1137 |
+
"step": 1610
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 3.1095627102354637,
|
| 1141 |
+
"grad_norm": 9.872568130493164,
|
| 1142 |
+
"learning_rate": 2.1032423208191125e-05,
|
| 1143 |
+
"loss": 1.5606,
|
| 1144 |
+
"step": 1620
|
| 1145 |
+
},
|
| 1146 |
+
{
|
| 1147 |
+
"epoch": 3.1287842383469484,
|
| 1148 |
+
"grad_norm": 8.62325668334961,
|
| 1149 |
+
"learning_rate": 2.081911262798635e-05,
|
| 1150 |
+
"loss": 1.4871,
|
| 1151 |
+
"step": 1630
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 3.1480057664584336,
|
| 1155 |
+
"grad_norm": 8.459789276123047,
|
| 1156 |
+
"learning_rate": 2.0605802047781573e-05,
|
| 1157 |
+
"loss": 1.5561,
|
| 1158 |
+
"step": 1640
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"epoch": 3.1672272945699183,
|
| 1162 |
+
"grad_norm": 9.252559661865234,
|
| 1163 |
+
"learning_rate": 2.0392491467576794e-05,
|
| 1164 |
+
"loss": 1.5595,
|
| 1165 |
+
"step": 1650
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"epoch": 3.1864488226814034,
|
| 1169 |
+
"grad_norm": 9.68213939666748,
|
| 1170 |
+
"learning_rate": 2.0179180887372014e-05,
|
| 1171 |
+
"loss": 1.5517,
|
| 1172 |
+
"step": 1660
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 3.205670350792888,
|
| 1176 |
+
"grad_norm": 9.817381858825684,
|
| 1177 |
+
"learning_rate": 1.9965870307167238e-05,
|
| 1178 |
+
"loss": 1.4966,
|
| 1179 |
+
"step": 1670
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 3.224891878904373,
|
| 1183 |
+
"grad_norm": 9.264698028564453,
|
| 1184 |
+
"learning_rate": 1.975255972696246e-05,
|
| 1185 |
+
"loss": 1.5443,
|
| 1186 |
+
"step": 1680
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 3.244113407015858,
|
| 1190 |
+
"grad_norm": 8.848346710205078,
|
| 1191 |
+
"learning_rate": 1.953924914675768e-05,
|
| 1192 |
+
"loss": 1.4929,
|
| 1193 |
+
"step": 1690
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 3.2633349351273426,
|
| 1197 |
+
"grad_norm": 9.325592994689941,
|
| 1198 |
+
"learning_rate": 1.93259385665529e-05,
|
| 1199 |
+
"loss": 1.5259,
|
| 1200 |
+
"step": 1700
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 3.2825564632388273,
|
| 1204 |
+
"grad_norm": 10.281765937805176,
|
| 1205 |
+
"learning_rate": 1.9112627986348127e-05,
|
| 1206 |
+
"loss": 1.5497,
|
| 1207 |
+
"step": 1710
|
| 1208 |
+
},
|
| 1209 |
+
{
|
| 1210 |
+
"epoch": 3.3017779913503125,
|
| 1211 |
+
"grad_norm": 8.460485458374023,
|
| 1212 |
+
"learning_rate": 1.8899317406143347e-05,
|
| 1213 |
+
"loss": 1.5051,
|
| 1214 |
+
"step": 1720
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 3.320999519461797,
|
| 1218 |
+
"grad_norm": 9.479697227478027,
|
| 1219 |
+
"learning_rate": 1.8686006825938568e-05,
|
| 1220 |
+
"loss": 1.5353,
|
| 1221 |
+
"step": 1730
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 3.340221047573282,
|
| 1225 |
+
"grad_norm": 8.678592681884766,
|
| 1226 |
+
"learning_rate": 1.8472696245733788e-05,
|
| 1227 |
+
"loss": 1.5865,
|
| 1228 |
+
"step": 1740
|
| 1229 |
+
},
|
| 1230 |
+
{
|
| 1231 |
+
"epoch": 3.359442575684767,
|
| 1232 |
+
"grad_norm": 9.709846496582031,
|
| 1233 |
+
"learning_rate": 1.8259385665529012e-05,
|
| 1234 |
+
"loss": 1.5572,
|
| 1235 |
+
"step": 1750
|
| 1236 |
+
},
|
| 1237 |
+
{
|
| 1238 |
+
"epoch": 3.3786641037962517,
|
| 1239 |
+
"grad_norm": 9.438785552978516,
|
| 1240 |
+
"learning_rate": 1.8046075085324232e-05,
|
| 1241 |
+
"loss": 1.5867,
|
| 1242 |
+
"step": 1760
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"epoch": 3.397885631907737,
|
| 1246 |
+
"grad_norm": 8.967934608459473,
|
| 1247 |
+
"learning_rate": 1.7832764505119453e-05,
|
| 1248 |
+
"loss": 1.49,
|
| 1249 |
+
"step": 1770
|
| 1250 |
+
},
|
| 1251 |
+
{
|
| 1252 |
+
"epoch": 3.4171071600192215,
|
| 1253 |
+
"grad_norm": 9.989371299743652,
|
| 1254 |
+
"learning_rate": 1.7619453924914677e-05,
|
| 1255 |
+
"loss": 1.5461,
|
| 1256 |
+
"step": 1780
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 3.4363286881307062,
|
| 1260 |
+
"grad_norm": 8.968268394470215,
|
| 1261 |
+
"learning_rate": 1.74061433447099e-05,
|
| 1262 |
+
"loss": 1.6002,
|
| 1263 |
+
"step": 1790
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 3.4555502162421914,
|
| 1267 |
+
"grad_norm": 9.105525016784668,
|
| 1268 |
+
"learning_rate": 1.719283276450512e-05,
|
| 1269 |
+
"loss": 1.5934,
|
| 1270 |
+
"step": 1800
|
| 1271 |
+
},
|
| 1272 |
+
{
|
| 1273 |
+
"epoch": 3.474771744353676,
|
| 1274 |
+
"grad_norm": 8.997435569763184,
|
| 1275 |
+
"learning_rate": 1.697952218430034e-05,
|
| 1276 |
+
"loss": 1.5687,
|
| 1277 |
+
"step": 1810
|
| 1278 |
+
},
|
| 1279 |
+
{
|
| 1280 |
+
"epoch": 3.4939932724651612,
|
| 1281 |
+
"grad_norm": 9.625081062316895,
|
| 1282 |
+
"learning_rate": 1.6766211604095562e-05,
|
| 1283 |
+
"loss": 1.5684,
|
| 1284 |
+
"step": 1820
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 3.513214800576646,
|
| 1288 |
+
"grad_norm": 8.427741050720215,
|
| 1289 |
+
"learning_rate": 1.6552901023890786e-05,
|
| 1290 |
+
"loss": 1.4639,
|
| 1291 |
+
"step": 1830
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 3.5324363286881306,
|
| 1295 |
+
"grad_norm": 10.164386749267578,
|
| 1296 |
+
"learning_rate": 1.6339590443686006e-05,
|
| 1297 |
+
"loss": 1.5512,
|
| 1298 |
+
"step": 1840
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 3.5516578567996158,
|
| 1302 |
+
"grad_norm": 9.009414672851562,
|
| 1303 |
+
"learning_rate": 1.612627986348123e-05,
|
| 1304 |
+
"loss": 1.5127,
|
| 1305 |
+
"step": 1850
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 3.5708793849111005,
|
| 1309 |
+
"grad_norm": 11.138776779174805,
|
| 1310 |
+
"learning_rate": 1.591296928327645e-05,
|
| 1311 |
+
"loss": 1.4763,
|
| 1312 |
+
"step": 1860
|
| 1313 |
+
},
|
| 1314 |
+
{
|
| 1315 |
+
"epoch": 3.590100913022585,
|
| 1316 |
+
"grad_norm": 8.983370780944824,
|
| 1317 |
+
"learning_rate": 1.5699658703071675e-05,
|
| 1318 |
+
"loss": 1.5661,
|
| 1319 |
+
"step": 1870
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 3.6093224411340703,
|
| 1323 |
+
"grad_norm": 9.458341598510742,
|
| 1324 |
+
"learning_rate": 1.5486348122866895e-05,
|
| 1325 |
+
"loss": 1.5151,
|
| 1326 |
+
"step": 1880
|
| 1327 |
+
},
|
| 1328 |
+
{
|
| 1329 |
+
"epoch": 3.628543969245555,
|
| 1330 |
+
"grad_norm": 9.019761085510254,
|
| 1331 |
+
"learning_rate": 1.5273037542662116e-05,
|
| 1332 |
+
"loss": 1.5646,
|
| 1333 |
+
"step": 1890
|
| 1334 |
+
},
|
| 1335 |
+
{
|
| 1336 |
+
"epoch": 3.6477654973570397,
|
| 1337 |
+
"grad_norm": 9.247156143188477,
|
| 1338 |
+
"learning_rate": 1.5059726962457338e-05,
|
| 1339 |
+
"loss": 1.5257,
|
| 1340 |
+
"step": 1900
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"epoch": 3.666987025468525,
|
| 1344 |
+
"grad_norm": 9.937666893005371,
|
| 1345 |
+
"learning_rate": 1.484641638225256e-05,
|
| 1346 |
+
"loss": 1.5934,
|
| 1347 |
+
"step": 1910
|
| 1348 |
+
},
|
| 1349 |
+
{
|
| 1350 |
+
"epoch": 3.6862085535800095,
|
| 1351 |
+
"grad_norm": 8.887203216552734,
|
| 1352 |
+
"learning_rate": 1.4633105802047784e-05,
|
| 1353 |
+
"loss": 1.5373,
|
| 1354 |
+
"step": 1920
|
| 1355 |
+
},
|
| 1356 |
+
{
|
| 1357 |
+
"epoch": 3.7054300816914942,
|
| 1358 |
+
"grad_norm": 8.323814392089844,
|
| 1359 |
+
"learning_rate": 1.4419795221843004e-05,
|
| 1360 |
+
"loss": 1.5178,
|
| 1361 |
+
"step": 1930
|
| 1362 |
+
},
|
| 1363 |
+
{
|
| 1364 |
+
"epoch": 3.7246516098029794,
|
| 1365 |
+
"grad_norm": 8.78007984161377,
|
| 1366 |
+
"learning_rate": 1.4206484641638227e-05,
|
| 1367 |
+
"loss": 1.5283,
|
| 1368 |
+
"step": 1940
|
| 1369 |
+
},
|
| 1370 |
+
{
|
| 1371 |
+
"epoch": 3.743873137914464,
|
| 1372 |
+
"grad_norm": 10.119393348693848,
|
| 1373 |
+
"learning_rate": 1.3993174061433447e-05,
|
| 1374 |
+
"loss": 1.5611,
|
| 1375 |
+
"step": 1950
|
| 1376 |
+
},
|
| 1377 |
+
{
|
| 1378 |
+
"epoch": 3.763094666025949,
|
| 1379 |
+
"grad_norm": 8.493330001831055,
|
| 1380 |
+
"learning_rate": 1.377986348122867e-05,
|
| 1381 |
+
"loss": 1.5285,
|
| 1382 |
+
"step": 1960
|
| 1383 |
+
},
|
| 1384 |
+
{
|
| 1385 |
+
"epoch": 3.782316194137434,
|
| 1386 |
+
"grad_norm": 9.496063232421875,
|
| 1387 |
+
"learning_rate": 1.3566552901023891e-05,
|
| 1388 |
+
"loss": 1.4765,
|
| 1389 |
+
"step": 1970
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 3.801537722248919,
|
| 1393 |
+
"grad_norm": 9.950116157531738,
|
| 1394 |
+
"learning_rate": 1.3353242320819112e-05,
|
| 1395 |
+
"loss": 1.522,
|
| 1396 |
+
"step": 1980
|
| 1397 |
+
},
|
| 1398 |
+
{
|
| 1399 |
+
"epoch": 3.8207592503604038,
|
| 1400 |
+
"grad_norm": 9.816246032714844,
|
| 1401 |
+
"learning_rate": 1.3139931740614336e-05,
|
| 1402 |
+
"loss": 1.5085,
|
| 1403 |
+
"step": 1990
|
| 1404 |
+
},
|
| 1405 |
+
{
|
| 1406 |
+
"epoch": 3.8399807784718885,
|
| 1407 |
+
"grad_norm": 9.766254425048828,
|
| 1408 |
+
"learning_rate": 1.2926621160409558e-05,
|
| 1409 |
+
"loss": 1.6145,
|
| 1410 |
+
"step": 2000
|
| 1411 |
+
},
|
| 1412 |
+
{
|
| 1413 |
+
"epoch": 3.8592023065833736,
|
| 1414 |
+
"grad_norm": 9.258591651916504,
|
| 1415 |
+
"learning_rate": 1.2713310580204778e-05,
|
| 1416 |
+
"loss": 1.5292,
|
| 1417 |
+
"step": 2010
|
| 1418 |
+
},
|
| 1419 |
+
{
|
| 1420 |
+
"epoch": 3.8784238346948583,
|
| 1421 |
+
"grad_norm": 9.976773262023926,
|
| 1422 |
+
"learning_rate": 1.25e-05,
|
| 1423 |
+
"loss": 1.5811,
|
| 1424 |
+
"step": 2020
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 3.897645362806343,
|
| 1428 |
+
"grad_norm": 9.001440048217773,
|
| 1429 |
+
"learning_rate": 1.2286689419795223e-05,
|
| 1430 |
+
"loss": 1.5401,
|
| 1431 |
+
"step": 2030
|
| 1432 |
+
},
|
| 1433 |
+
{
|
| 1434 |
+
"epoch": 3.916866890917828,
|
| 1435 |
+
"grad_norm": 10.00130558013916,
|
| 1436 |
+
"learning_rate": 1.2073378839590445e-05,
|
| 1437 |
+
"loss": 1.6257,
|
| 1438 |
+
"step": 2040
|
| 1439 |
+
},
|
| 1440 |
+
{
|
| 1441 |
+
"epoch": 3.936088419029313,
|
| 1442 |
+
"grad_norm": 8.235420227050781,
|
| 1443 |
+
"learning_rate": 1.1860068259385667e-05,
|
| 1444 |
+
"loss": 1.4888,
|
| 1445 |
+
"step": 2050
|
| 1446 |
+
},
|
| 1447 |
+
{
|
| 1448 |
+
"epoch": 3.9553099471407975,
|
| 1449 |
+
"grad_norm": 9.468134880065918,
|
| 1450 |
+
"learning_rate": 1.1646757679180888e-05,
|
| 1451 |
+
"loss": 1.6077,
|
| 1452 |
+
"step": 2060
|
| 1453 |
+
},
|
| 1454 |
+
{
|
| 1455 |
+
"epoch": 3.9745314752522827,
|
| 1456 |
+
"grad_norm": 8.448241233825684,
|
| 1457 |
+
"learning_rate": 1.143344709897611e-05,
|
| 1458 |
+
"loss": 1.5568,
|
| 1459 |
+
"step": 2070
|
| 1460 |
+
},
|
| 1461 |
+
{
|
| 1462 |
+
"epoch": 3.9937530033637674,
|
| 1463 |
+
"grad_norm": 9.615592956542969,
|
| 1464 |
+
"learning_rate": 1.1220136518771332e-05,
|
| 1465 |
+
"loss": 1.6119,
|
| 1466 |
+
"step": 2080
|
| 1467 |
+
}
|
| 1468 |
+
],
|
| 1469 |
+
"logging_steps": 10,
|
| 1470 |
+
"max_steps": 2605,
|
| 1471 |
+
"num_input_tokens_seen": 0,
|
| 1472 |
+
"num_train_epochs": 5,
|
| 1473 |
+
"save_steps": 500,
|
| 1474 |
+
"stateful_callbacks": {
|
| 1475 |
+
"TrainerControl": {
|
| 1476 |
+
"args": {
|
| 1477 |
+
"should_epoch_stop": false,
|
| 1478 |
+
"should_evaluate": false,
|
| 1479 |
+
"should_log": false,
|
| 1480 |
+
"should_save": true,
|
| 1481 |
+
"should_training_stop": false
|
| 1482 |
+
},
|
| 1483 |
+
"attributes": {}
|
| 1484 |
+
}
|
| 1485 |
+
},
|
| 1486 |
+
"total_flos": 7489484208488448.0,
|
| 1487 |
+
"train_batch_size": 4,
|
| 1488 |
+
"trial_name": null,
|
| 1489 |
+
"trial_params": null
|
| 1490 |
+
}
|
checkpoint-2084/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8f3f2c51094de7b2e8fb357753c21db50fbd28d5b3e8bc9181e6be1839b36076
|
| 3 |
+
size 5713
|
checkpoint-2605/README.md
ADDED
|
@@ -0,0 +1,207 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: Henit007/modelo3_finetuned
|
| 3 |
+
library_name: peft
|
| 4 |
+
pipeline_tag: text-generation
|
| 5 |
+
tags:
|
| 6 |
+
- base_model:adapter:Henit007/modelo3_finetuned
|
| 7 |
+
- lora
|
| 8 |
+
- transformers
|
| 9 |
+
---
|
| 10 |
+
|
| 11 |
+
# Model Card for Model ID
|
| 12 |
+
|
| 13 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 14 |
+
|
| 15 |
+
|
| 16 |
+
|
| 17 |
+
## Model Details
|
| 18 |
+
|
| 19 |
+
### Model Description
|
| 20 |
+
|
| 21 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 22 |
+
|
| 23 |
+
|
| 24 |
+
|
| 25 |
+
- **Developed by:** [More Information Needed]
|
| 26 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 27 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 28 |
+
- **Model type:** [More Information Needed]
|
| 29 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 30 |
+
- **License:** [More Information Needed]
|
| 31 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 32 |
+
|
| 33 |
+
### Model Sources [optional]
|
| 34 |
+
|
| 35 |
+
<!-- Provide the basic links for the model. -->
|
| 36 |
+
|
| 37 |
+
- **Repository:** [More Information Needed]
|
| 38 |
+
- **Paper [optional]:** [More Information Needed]
|
| 39 |
+
- **Demo [optional]:** [More Information Needed]
|
| 40 |
+
|
| 41 |
+
## Uses
|
| 42 |
+
|
| 43 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 44 |
+
|
| 45 |
+
### Direct Use
|
| 46 |
+
|
| 47 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 48 |
+
|
| 49 |
+
[More Information Needed]
|
| 50 |
+
|
| 51 |
+
### Downstream Use [optional]
|
| 52 |
+
|
| 53 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 54 |
+
|
| 55 |
+
[More Information Needed]
|
| 56 |
+
|
| 57 |
+
### Out-of-Scope Use
|
| 58 |
+
|
| 59 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 60 |
+
|
| 61 |
+
[More Information Needed]
|
| 62 |
+
|
| 63 |
+
## Bias, Risks, and Limitations
|
| 64 |
+
|
| 65 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 66 |
+
|
| 67 |
+
[More Information Needed]
|
| 68 |
+
|
| 69 |
+
### Recommendations
|
| 70 |
+
|
| 71 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 72 |
+
|
| 73 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 74 |
+
|
| 75 |
+
## How to Get Started with the Model
|
| 76 |
+
|
| 77 |
+
Use the code below to get started with the model.
|
| 78 |
+
|
| 79 |
+
[More Information Needed]
|
| 80 |
+
|
| 81 |
+
## Training Details
|
| 82 |
+
|
| 83 |
+
### Training Data
|
| 84 |
+
|
| 85 |
+
<!-- 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. -->
|
| 86 |
+
|
| 87 |
+
[More Information Needed]
|
| 88 |
+
|
| 89 |
+
### Training Procedure
|
| 90 |
+
|
| 91 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 92 |
+
|
| 93 |
+
#### Preprocessing [optional]
|
| 94 |
+
|
| 95 |
+
[More Information Needed]
|
| 96 |
+
|
| 97 |
+
|
| 98 |
+
#### Training Hyperparameters
|
| 99 |
+
|
| 100 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 101 |
+
|
| 102 |
+
#### Speeds, Sizes, Times [optional]
|
| 103 |
+
|
| 104 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 105 |
+
|
| 106 |
+
[More Information Needed]
|
| 107 |
+
|
| 108 |
+
## Evaluation
|
| 109 |
+
|
| 110 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 111 |
+
|
| 112 |
+
### Testing Data, Factors & Metrics
|
| 113 |
+
|
| 114 |
+
#### Testing Data
|
| 115 |
+
|
| 116 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 117 |
+
|
| 118 |
+
[More Information Needed]
|
| 119 |
+
|
| 120 |
+
#### Factors
|
| 121 |
+
|
| 122 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 123 |
+
|
| 124 |
+
[More Information Needed]
|
| 125 |
+
|
| 126 |
+
#### Metrics
|
| 127 |
+
|
| 128 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 129 |
+
|
| 130 |
+
[More Information Needed]
|
| 131 |
+
|
| 132 |
+
### Results
|
| 133 |
+
|
| 134 |
+
[More Information Needed]
|
| 135 |
+
|
| 136 |
+
#### Summary
|
| 137 |
+
|
| 138 |
+
|
| 139 |
+
|
| 140 |
+
## Model Examination [optional]
|
| 141 |
+
|
| 142 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 143 |
+
|
| 144 |
+
[More Information Needed]
|
| 145 |
+
|
| 146 |
+
## Environmental Impact
|
| 147 |
+
|
| 148 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 149 |
+
|
| 150 |
+
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).
|
| 151 |
+
|
| 152 |
+
- **Hardware Type:** [More Information Needed]
|
| 153 |
+
- **Hours used:** [More Information Needed]
|
| 154 |
+
- **Cloud Provider:** [More Information Needed]
|
| 155 |
+
- **Compute Region:** [More Information Needed]
|
| 156 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 157 |
+
|
| 158 |
+
## Technical Specifications [optional]
|
| 159 |
+
|
| 160 |
+
### Model Architecture and Objective
|
| 161 |
+
|
| 162 |
+
[More Information Needed]
|
| 163 |
+
|
| 164 |
+
### Compute Infrastructure
|
| 165 |
+
|
| 166 |
+
[More Information Needed]
|
| 167 |
+
|
| 168 |
+
#### Hardware
|
| 169 |
+
|
| 170 |
+
[More Information Needed]
|
| 171 |
+
|
| 172 |
+
#### Software
|
| 173 |
+
|
| 174 |
+
[More Information Needed]
|
| 175 |
+
|
| 176 |
+
## Citation [optional]
|
| 177 |
+
|
| 178 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 179 |
+
|
| 180 |
+
**BibTeX:**
|
| 181 |
+
|
| 182 |
+
[More Information Needed]
|
| 183 |
+
|
| 184 |
+
**APA:**
|
| 185 |
+
|
| 186 |
+
[More Information Needed]
|
| 187 |
+
|
| 188 |
+
## Glossary [optional]
|
| 189 |
+
|
| 190 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 191 |
+
|
| 192 |
+
[More Information Needed]
|
| 193 |
+
|
| 194 |
+
## More Information [optional]
|
| 195 |
+
|
| 196 |
+
[More Information Needed]
|
| 197 |
+
|
| 198 |
+
## Model Card Authors [optional]
|
| 199 |
+
|
| 200 |
+
[More Information Needed]
|
| 201 |
+
|
| 202 |
+
## Model Card Contact
|
| 203 |
+
|
| 204 |
+
[More Information Needed]
|
| 205 |
+
### Framework versions
|
| 206 |
+
|
| 207 |
+
- PEFT 0.17.0
|
checkpoint-2605/adapter_config.json
ADDED
|
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "Henit007/modelo3_finetuned",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"corda_config": null,
|
| 7 |
+
"eva_config": null,
|
| 8 |
+
"exclude_modules": null,
|
| 9 |
+
"fan_in_fan_out": false,
|
| 10 |
+
"inference_mode": true,
|
| 11 |
+
"init_lora_weights": true,
|
| 12 |
+
"layer_replication": null,
|
| 13 |
+
"layers_pattern": null,
|
| 14 |
+
"layers_to_transform": null,
|
| 15 |
+
"loftq_config": {},
|
| 16 |
+
"lora_alpha": 64,
|
| 17 |
+
"lora_bias": false,
|
| 18 |
+
"lora_dropout": 0.05,
|
| 19 |
+
"megatron_config": null,
|
| 20 |
+
"megatron_core": "megatron.core",
|
| 21 |
+
"modules_to_save": null,
|
| 22 |
+
"peft_type": "LORA",
|
| 23 |
+
"qalora_group_size": 16,
|
| 24 |
+
"r": 8,
|
| 25 |
+
"rank_pattern": {},
|
| 26 |
+
"revision": null,
|
| 27 |
+
"target_modules": [
|
| 28 |
+
"v_proj",
|
| 29 |
+
"o_proj",
|
| 30 |
+
"down_proj",
|
| 31 |
+
"q_proj",
|
| 32 |
+
"gate_proj",
|
| 33 |
+
"k_proj",
|
| 34 |
+
"up_proj"
|
| 35 |
+
],
|
| 36 |
+
"target_parameters": null,
|
| 37 |
+
"task_type": "CAUSAL_LM",
|
| 38 |
+
"trainable_token_indices": null,
|
| 39 |
+
"use_dora": false,
|
| 40 |
+
"use_qalora": false,
|
| 41 |
+
"use_rslora": false
|
| 42 |
+
}
|
checkpoint-2605/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6280608e290ab7bb9c3e55824440dff2dede7c094c9bc557b288875ed8393276
|
| 3 |
+
size 25271744
|
checkpoint-2605/chat_template.jinja
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{% for message in messages %}
|
| 2 |
+
{% if message['role'] == 'user' %}
|
| 3 |
+
{{ '<|user|>
|
| 4 |
+
' + message['content'] + eos_token }}
|
| 5 |
+
{% elif message['role'] == 'system' %}
|
| 6 |
+
{{ '<|system|>
|
| 7 |
+
' + message['content'] + eos_token }}
|
| 8 |
+
{% elif message['role'] == 'assistant' %}
|
| 9 |
+
{{ '<|assistant|>
|
| 10 |
+
' + message['content'] + eos_token }}
|
| 11 |
+
{% endif %}
|
| 12 |
+
{% if loop.last and add_generation_prompt %}
|
| 13 |
+
{{ '<|assistant|>' }}
|
| 14 |
+
{% endif %}
|
| 15 |
+
{% endfor %}
|
checkpoint-2605/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:44efac9724b679fbf00282e4739633111e8aed26bffb7b219da68e04dcc25588
|
| 3 |
+
size 13686237
|
checkpoint-2605/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ee19345623931c9b7735e76ec4cc9cef226f971e10e0257bdec47621a7f6d808
|
| 3 |
+
size 14645
|
checkpoint-2605/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:270a5716ceff542c84591c8b92fd5b1dadcc0ddd8d45642aff598977b4e2a576
|
| 3 |
+
size 1465
|
checkpoint-2605/special_tokens_map.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "</s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "</s>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"unk_token": {
|
| 24 |
+
"content": "<unk>",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
}
|
| 30 |
+
}
|
checkpoint-2605/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-2605/tokenizer_config.json
ADDED
|
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"add_prefix_space": null,
|
| 5 |
+
"added_tokens_decoder": {
|
| 6 |
+
"0": {
|
| 7 |
+
"content": "<unk>",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": false,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false,
|
| 12 |
+
"special": true
|
| 13 |
+
},
|
| 14 |
+
"1": {
|
| 15 |
+
"content": "<s>",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": false,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false,
|
| 20 |
+
"special": true
|
| 21 |
+
},
|
| 22 |
+
"2": {
|
| 23 |
+
"content": "</s>",
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"normalized": false,
|
| 26 |
+
"rstrip": false,
|
| 27 |
+
"single_word": false,
|
| 28 |
+
"special": true
|
| 29 |
+
}
|
| 30 |
+
},
|
| 31 |
+
"bos_token": "<s>",
|
| 32 |
+
"clean_up_tokenization_spaces": false,
|
| 33 |
+
"eos_token": "</s>",
|
| 34 |
+
"extra_special_tokens": {},
|
| 35 |
+
"legacy": false,
|
| 36 |
+
"model_max_length": 2048,
|
| 37 |
+
"pad_token": "</s>",
|
| 38 |
+
"padding_side": "right",
|
| 39 |
+
"sp_model_kwargs": {},
|
| 40 |
+
"tokenizer_class": "LlamaTokenizerFast",
|
| 41 |
+
"unk_token": "<unk>",
|
| 42 |
+
"use_default_system_prompt": false
|
| 43 |
+
}
|
checkpoint-2605/trainer_state.json
ADDED
|
@@ -0,0 +1,1854 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 5.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 2605,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.019221528111484865,
|
| 14 |
+
"grad_norm": 4.911402702331543,
|
| 15 |
+
"learning_rate": 1.724137931034483e-06,
|
| 16 |
+
"loss": 2.1561,
|
| 17 |
+
"step": 10
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.03844305622296973,
|
| 21 |
+
"grad_norm": 4.560591697692871,
|
| 22 |
+
"learning_rate": 3.6398467432950196e-06,
|
| 23 |
+
"loss": 2.1368,
|
| 24 |
+
"step": 20
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.05766458433445459,
|
| 28 |
+
"grad_norm": 6.820058345794678,
|
| 29 |
+
"learning_rate": 5.555555555555556e-06,
|
| 30 |
+
"loss": 2.3192,
|
| 31 |
+
"step": 30
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.07688611244593946,
|
| 35 |
+
"grad_norm": 7.230356693267822,
|
| 36 |
+
"learning_rate": 7.4712643678160925e-06,
|
| 37 |
+
"loss": 2.6544,
|
| 38 |
+
"step": 40
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.09610764055742431,
|
| 42 |
+
"grad_norm": 6.225106716156006,
|
| 43 |
+
"learning_rate": 9.386973180076629e-06,
|
| 44 |
+
"loss": 2.6349,
|
| 45 |
+
"step": 50
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.11532916866890917,
|
| 49 |
+
"grad_norm": 5.758670330047607,
|
| 50 |
+
"learning_rate": 1.1302681992337164e-05,
|
| 51 |
+
"loss": 2.6164,
|
| 52 |
+
"step": 60
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.13455069678039405,
|
| 56 |
+
"grad_norm": 6.433386325836182,
|
| 57 |
+
"learning_rate": 1.3218390804597702e-05,
|
| 58 |
+
"loss": 2.6651,
|
| 59 |
+
"step": 70
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.15377222489187892,
|
| 63 |
+
"grad_norm": 6.204464435577393,
|
| 64 |
+
"learning_rate": 1.5134099616858237e-05,
|
| 65 |
+
"loss": 2.5232,
|
| 66 |
+
"step": 80
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.17299375300336375,
|
| 70 |
+
"grad_norm": 6.514060974121094,
|
| 71 |
+
"learning_rate": 1.7049808429118776e-05,
|
| 72 |
+
"loss": 2.5878,
|
| 73 |
+
"step": 90
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.19221528111484862,
|
| 77 |
+
"grad_norm": 5.641262054443359,
|
| 78 |
+
"learning_rate": 1.896551724137931e-05,
|
| 79 |
+
"loss": 2.5566,
|
| 80 |
+
"step": 100
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.21143680922633348,
|
| 84 |
+
"grad_norm": 6.221690654754639,
|
| 85 |
+
"learning_rate": 2.088122605363985e-05,
|
| 86 |
+
"loss": 2.6939,
|
| 87 |
+
"step": 110
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.23065833733781835,
|
| 91 |
+
"grad_norm": 5.924990177154541,
|
| 92 |
+
"learning_rate": 2.2796934865900384e-05,
|
| 93 |
+
"loss": 2.6168,
|
| 94 |
+
"step": 120
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.2498798654493032,
|
| 98 |
+
"grad_norm": 5.515899181365967,
|
| 99 |
+
"learning_rate": 2.4712643678160922e-05,
|
| 100 |
+
"loss": 2.6026,
|
| 101 |
+
"step": 130
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.2691013935607881,
|
| 105 |
+
"grad_norm": 5.406517028808594,
|
| 106 |
+
"learning_rate": 2.662835249042146e-05,
|
| 107 |
+
"loss": 2.4847,
|
| 108 |
+
"step": 140
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.28832292167227297,
|
| 112 |
+
"grad_norm": 5.749735355377197,
|
| 113 |
+
"learning_rate": 2.8544061302681996e-05,
|
| 114 |
+
"loss": 2.621,
|
| 115 |
+
"step": 150
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.30754444978375783,
|
| 119 |
+
"grad_norm": 5.63827657699585,
|
| 120 |
+
"learning_rate": 3.045977011494253e-05,
|
| 121 |
+
"loss": 2.5422,
|
| 122 |
+
"step": 160
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.3267659778952427,
|
| 126 |
+
"grad_norm": 7.321156024932861,
|
| 127 |
+
"learning_rate": 3.2375478927203066e-05,
|
| 128 |
+
"loss": 2.4498,
|
| 129 |
+
"step": 170
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.3459875060067275,
|
| 133 |
+
"grad_norm": 5.711870193481445,
|
| 134 |
+
"learning_rate": 3.4291187739463604e-05,
|
| 135 |
+
"loss": 2.4447,
|
| 136 |
+
"step": 180
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.3652090341182124,
|
| 140 |
+
"grad_norm": 6.159710884094238,
|
| 141 |
+
"learning_rate": 3.620689655172414e-05,
|
| 142 |
+
"loss": 2.4798,
|
| 143 |
+
"step": 190
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.38443056222969724,
|
| 147 |
+
"grad_norm": 6.255421161651611,
|
| 148 |
+
"learning_rate": 3.8122605363984674e-05,
|
| 149 |
+
"loss": 2.435,
|
| 150 |
+
"step": 200
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.4036520903411821,
|
| 154 |
+
"grad_norm": 6.48488187789917,
|
| 155 |
+
"learning_rate": 4.003831417624521e-05,
|
| 156 |
+
"loss": 2.43,
|
| 157 |
+
"step": 210
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.42287361845266697,
|
| 161 |
+
"grad_norm": 5.98501443862915,
|
| 162 |
+
"learning_rate": 4.195402298850575e-05,
|
| 163 |
+
"loss": 2.3629,
|
| 164 |
+
"step": 220
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.44209514656415183,
|
| 168 |
+
"grad_norm": 7.079067707061768,
|
| 169 |
+
"learning_rate": 4.386973180076628e-05,
|
| 170 |
+
"loss": 2.5268,
|
| 171 |
+
"step": 230
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.4613166746756367,
|
| 175 |
+
"grad_norm": 5.06460428237915,
|
| 176 |
+
"learning_rate": 4.578544061302682e-05,
|
| 177 |
+
"loss": 2.4671,
|
| 178 |
+
"step": 240
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.48053820278712156,
|
| 182 |
+
"grad_norm": 6.475998878479004,
|
| 183 |
+
"learning_rate": 4.770114942528736e-05,
|
| 184 |
+
"loss": 2.3595,
|
| 185 |
+
"step": 250
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.4997597308986064,
|
| 189 |
+
"grad_norm": 5.529846668243408,
|
| 190 |
+
"learning_rate": 4.96168582375479e-05,
|
| 191 |
+
"loss": 2.3635,
|
| 192 |
+
"step": 260
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.5189812590100913,
|
| 196 |
+
"grad_norm": 5.878045558929443,
|
| 197 |
+
"learning_rate": 4.982935153583618e-05,
|
| 198 |
+
"loss": 2.436,
|
| 199 |
+
"step": 270
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.5382027871215762,
|
| 203 |
+
"grad_norm": 5.845484256744385,
|
| 204 |
+
"learning_rate": 4.9616040955631404e-05,
|
| 205 |
+
"loss": 2.4051,
|
| 206 |
+
"step": 280
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.557424315233061,
|
| 210 |
+
"grad_norm": 6.933780670166016,
|
| 211 |
+
"learning_rate": 4.940273037542663e-05,
|
| 212 |
+
"loss": 2.3829,
|
| 213 |
+
"step": 290
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.5766458433445459,
|
| 217 |
+
"grad_norm": 6.303454399108887,
|
| 218 |
+
"learning_rate": 4.9189419795221845e-05,
|
| 219 |
+
"loss": 2.3613,
|
| 220 |
+
"step": 300
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.5958673714560307,
|
| 224 |
+
"grad_norm": 6.88358736038208,
|
| 225 |
+
"learning_rate": 4.897610921501707e-05,
|
| 226 |
+
"loss": 2.3223,
|
| 227 |
+
"step": 310
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.6150888995675157,
|
| 231 |
+
"grad_norm": 6.72720193862915,
|
| 232 |
+
"learning_rate": 4.876279863481229e-05,
|
| 233 |
+
"loss": 2.3706,
|
| 234 |
+
"step": 320
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.6343104276790005,
|
| 238 |
+
"grad_norm": 7.726202011108398,
|
| 239 |
+
"learning_rate": 4.854948805460751e-05,
|
| 240 |
+
"loss": 2.3666,
|
| 241 |
+
"step": 330
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.6535319557904854,
|
| 245 |
+
"grad_norm": 6.805552959442139,
|
| 246 |
+
"learning_rate": 4.8336177474402734e-05,
|
| 247 |
+
"loss": 2.3535,
|
| 248 |
+
"step": 340
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.6727534839019702,
|
| 252 |
+
"grad_norm": 5.095221996307373,
|
| 253 |
+
"learning_rate": 4.812286689419796e-05,
|
| 254 |
+
"loss": 2.2583,
|
| 255 |
+
"step": 350
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.691975012013455,
|
| 259 |
+
"grad_norm": 6.583714485168457,
|
| 260 |
+
"learning_rate": 4.7909556313993175e-05,
|
| 261 |
+
"loss": 2.2992,
|
| 262 |
+
"step": 360
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.7111965401249399,
|
| 266 |
+
"grad_norm": 5.969571113586426,
|
| 267 |
+
"learning_rate": 4.76962457337884e-05,
|
| 268 |
+
"loss": 2.3388,
|
| 269 |
+
"step": 370
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.7304180682364247,
|
| 273 |
+
"grad_norm": 7.320237636566162,
|
| 274 |
+
"learning_rate": 4.7482935153583616e-05,
|
| 275 |
+
"loss": 2.2875,
|
| 276 |
+
"step": 380
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.7496395963479097,
|
| 280 |
+
"grad_norm": 6.594917297363281,
|
| 281 |
+
"learning_rate": 4.726962457337884e-05,
|
| 282 |
+
"loss": 2.1744,
|
| 283 |
+
"step": 390
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.7688611244593945,
|
| 287 |
+
"grad_norm": 6.340092658996582,
|
| 288 |
+
"learning_rate": 4.7056313993174063e-05,
|
| 289 |
+
"loss": 2.2252,
|
| 290 |
+
"step": 400
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.7880826525708794,
|
| 294 |
+
"grad_norm": 6.270530700683594,
|
| 295 |
+
"learning_rate": 4.684300341296928e-05,
|
| 296 |
+
"loss": 2.2892,
|
| 297 |
+
"step": 410
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.8073041806823642,
|
| 301 |
+
"grad_norm": 6.28891134262085,
|
| 302 |
+
"learning_rate": 4.662969283276451e-05,
|
| 303 |
+
"loss": 2.3549,
|
| 304 |
+
"step": 420
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.8265257087938491,
|
| 308 |
+
"grad_norm": 6.432322978973389,
|
| 309 |
+
"learning_rate": 4.641638225255973e-05,
|
| 310 |
+
"loss": 2.2514,
|
| 311 |
+
"step": 430
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.8457472369053339,
|
| 315 |
+
"grad_norm": 6.2773613929748535,
|
| 316 |
+
"learning_rate": 4.620307167235495e-05,
|
| 317 |
+
"loss": 2.3056,
|
| 318 |
+
"step": 440
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.8649687650168189,
|
| 322 |
+
"grad_norm": 6.604885578155518,
|
| 323 |
+
"learning_rate": 4.5989761092150176e-05,
|
| 324 |
+
"loss": 2.2911,
|
| 325 |
+
"step": 450
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.8841902931283037,
|
| 329 |
+
"grad_norm": 5.717179775238037,
|
| 330 |
+
"learning_rate": 4.577645051194539e-05,
|
| 331 |
+
"loss": 2.3191,
|
| 332 |
+
"step": 460
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.9034118212397886,
|
| 336 |
+
"grad_norm": 6.134155750274658,
|
| 337 |
+
"learning_rate": 4.556313993174062e-05,
|
| 338 |
+
"loss": 2.2451,
|
| 339 |
+
"step": 470
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.9226333493512734,
|
| 343 |
+
"grad_norm": 6.287547588348389,
|
| 344 |
+
"learning_rate": 4.534982935153584e-05,
|
| 345 |
+
"loss": 2.2448,
|
| 346 |
+
"step": 480
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.9418548774627583,
|
| 350 |
+
"grad_norm": 5.859134197235107,
|
| 351 |
+
"learning_rate": 4.513651877133106e-05,
|
| 352 |
+
"loss": 2.1997,
|
| 353 |
+
"step": 490
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.9610764055742431,
|
| 357 |
+
"grad_norm": 6.595165729522705,
|
| 358 |
+
"learning_rate": 4.492320819112628e-05,
|
| 359 |
+
"loss": 2.1794,
|
| 360 |
+
"step": 500
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.980297933685728,
|
| 364 |
+
"grad_norm": 6.322437286376953,
|
| 365 |
+
"learning_rate": 4.4709897610921506e-05,
|
| 366 |
+
"loss": 2.2895,
|
| 367 |
+
"step": 510
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.9995194617972128,
|
| 371 |
+
"grad_norm": 7.458081245422363,
|
| 372 |
+
"learning_rate": 4.449658703071672e-05,
|
| 373 |
+
"loss": 2.1918,
|
| 374 |
+
"step": 520
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 1.0172993753003363,
|
| 378 |
+
"grad_norm": 6.502513885498047,
|
| 379 |
+
"learning_rate": 4.428327645051195e-05,
|
| 380 |
+
"loss": 2.0686,
|
| 381 |
+
"step": 530
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 1.0365209034118212,
|
| 385 |
+
"grad_norm": 5.94999885559082,
|
| 386 |
+
"learning_rate": 4.406996587030717e-05,
|
| 387 |
+
"loss": 1.9922,
|
| 388 |
+
"step": 540
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 1.0557424315233062,
|
| 392 |
+
"grad_norm": 6.013510704040527,
|
| 393 |
+
"learning_rate": 4.385665529010239e-05,
|
| 394 |
+
"loss": 1.9737,
|
| 395 |
+
"step": 550
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 1.074963959634791,
|
| 399 |
+
"grad_norm": 7.001447677612305,
|
| 400 |
+
"learning_rate": 4.364334470989762e-05,
|
| 401 |
+
"loss": 2.0489,
|
| 402 |
+
"step": 560
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 1.0941854877462758,
|
| 406 |
+
"grad_norm": 7.009434700012207,
|
| 407 |
+
"learning_rate": 4.3430034129692835e-05,
|
| 408 |
+
"loss": 2.0722,
|
| 409 |
+
"step": 570
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 1.1134070158577607,
|
| 413 |
+
"grad_norm": 6.154360294342041,
|
| 414 |
+
"learning_rate": 4.321672354948806e-05,
|
| 415 |
+
"loss": 2.1033,
|
| 416 |
+
"step": 580
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 1.1326285439692456,
|
| 420 |
+
"grad_norm": 7.929754734039307,
|
| 421 |
+
"learning_rate": 4.300341296928328e-05,
|
| 422 |
+
"loss": 2.0605,
|
| 423 |
+
"step": 590
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 1.1518500720807303,
|
| 427 |
+
"grad_norm": 5.974995136260986,
|
| 428 |
+
"learning_rate": 4.27901023890785e-05,
|
| 429 |
+
"loss": 1.9992,
|
| 430 |
+
"step": 600
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 1.1710716001922152,
|
| 434 |
+
"grad_norm": 6.380578994750977,
|
| 435 |
+
"learning_rate": 4.2576791808873724e-05,
|
| 436 |
+
"loss": 2.0509,
|
| 437 |
+
"step": 610
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 1.1902931283037002,
|
| 441 |
+
"grad_norm": 6.86224889755249,
|
| 442 |
+
"learning_rate": 4.236348122866894e-05,
|
| 443 |
+
"loss": 1.9994,
|
| 444 |
+
"step": 620
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 1.209514656415185,
|
| 448 |
+
"grad_norm": 7.081135272979736,
|
| 449 |
+
"learning_rate": 4.2150170648464165e-05,
|
| 450 |
+
"loss": 2.0567,
|
| 451 |
+
"step": 630
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 1.22873618452667,
|
| 455 |
+
"grad_norm": 6.908895492553711,
|
| 456 |
+
"learning_rate": 4.193686006825939e-05,
|
| 457 |
+
"loss": 1.9874,
|
| 458 |
+
"step": 640
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 1.2479577126381547,
|
| 462 |
+
"grad_norm": 7.030237674713135,
|
| 463 |
+
"learning_rate": 4.1723549488054606e-05,
|
| 464 |
+
"loss": 2.0383,
|
| 465 |
+
"step": 650
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 1.2671792407496396,
|
| 469 |
+
"grad_norm": 7.042236804962158,
|
| 470 |
+
"learning_rate": 4.151023890784983e-05,
|
| 471 |
+
"loss": 2.076,
|
| 472 |
+
"step": 660
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 1.2864007688611245,
|
| 476 |
+
"grad_norm": 7.262955188751221,
|
| 477 |
+
"learning_rate": 4.1296928327645054e-05,
|
| 478 |
+
"loss": 1.9956,
|
| 479 |
+
"step": 670
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 1.3056222969726092,
|
| 483 |
+
"grad_norm": 7.4197211265563965,
|
| 484 |
+
"learning_rate": 4.108361774744027e-05,
|
| 485 |
+
"loss": 2.0626,
|
| 486 |
+
"step": 680
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 1.3248438250840942,
|
| 490 |
+
"grad_norm": 8.185269355773926,
|
| 491 |
+
"learning_rate": 4.0870307167235495e-05,
|
| 492 |
+
"loss": 1.9757,
|
| 493 |
+
"step": 690
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 1.344065353195579,
|
| 497 |
+
"grad_norm": 7.224545001983643,
|
| 498 |
+
"learning_rate": 4.065699658703072e-05,
|
| 499 |
+
"loss": 2.0315,
|
| 500 |
+
"step": 700
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 1.363286881307064,
|
| 504 |
+
"grad_norm": 7.302128791809082,
|
| 505 |
+
"learning_rate": 4.044368600682594e-05,
|
| 506 |
+
"loss": 2.0296,
|
| 507 |
+
"step": 710
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 1.382508409418549,
|
| 511 |
+
"grad_norm": 7.413524150848389,
|
| 512 |
+
"learning_rate": 4.0230375426621166e-05,
|
| 513 |
+
"loss": 1.9541,
|
| 514 |
+
"step": 720
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 1.4017299375300336,
|
| 518 |
+
"grad_norm": 6.2689080238342285,
|
| 519 |
+
"learning_rate": 4.0017064846416383e-05,
|
| 520 |
+
"loss": 2.0365,
|
| 521 |
+
"step": 730
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 1.4209514656415185,
|
| 525 |
+
"grad_norm": 6.926391124725342,
|
| 526 |
+
"learning_rate": 3.980375426621161e-05,
|
| 527 |
+
"loss": 2.0117,
|
| 528 |
+
"step": 740
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 1.4401729937530034,
|
| 532 |
+
"grad_norm": 6.754932403564453,
|
| 533 |
+
"learning_rate": 3.959044368600683e-05,
|
| 534 |
+
"loss": 1.9882,
|
| 535 |
+
"step": 750
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 1.4593945218644881,
|
| 539 |
+
"grad_norm": 8.279367446899414,
|
| 540 |
+
"learning_rate": 3.937713310580205e-05,
|
| 541 |
+
"loss": 2.0513,
|
| 542 |
+
"step": 760
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 1.478616049975973,
|
| 546 |
+
"grad_norm": 7.346401691436768,
|
| 547 |
+
"learning_rate": 3.916382252559727e-05,
|
| 548 |
+
"loss": 2.0274,
|
| 549 |
+
"step": 770
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 1.497837578087458,
|
| 553 |
+
"grad_norm": 6.437380313873291,
|
| 554 |
+
"learning_rate": 3.8950511945392496e-05,
|
| 555 |
+
"loss": 1.9917,
|
| 556 |
+
"step": 780
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 1.5170591061989427,
|
| 560 |
+
"grad_norm": 6.856245994567871,
|
| 561 |
+
"learning_rate": 3.873720136518771e-05,
|
| 562 |
+
"loss": 2.0252,
|
| 563 |
+
"step": 790
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 1.5362806343104278,
|
| 567 |
+
"grad_norm": 7.144432067871094,
|
| 568 |
+
"learning_rate": 3.852389078498294e-05,
|
| 569 |
+
"loss": 2.1142,
|
| 570 |
+
"step": 800
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 1.5555021624219125,
|
| 574 |
+
"grad_norm": 6.338939189910889,
|
| 575 |
+
"learning_rate": 3.8310580204778154e-05,
|
| 576 |
+
"loss": 1.9595,
|
| 577 |
+
"step": 810
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 1.5747236905333974,
|
| 581 |
+
"grad_norm": 6.92732572555542,
|
| 582 |
+
"learning_rate": 3.809726962457338e-05,
|
| 583 |
+
"loss": 1.9964,
|
| 584 |
+
"step": 820
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 1.5939452186448824,
|
| 588 |
+
"grad_norm": 6.684772491455078,
|
| 589 |
+
"learning_rate": 3.78839590443686e-05,
|
| 590 |
+
"loss": 2.0192,
|
| 591 |
+
"step": 830
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 1.613166746756367,
|
| 595 |
+
"grad_norm": 6.988185882568359,
|
| 596 |
+
"learning_rate": 3.7670648464163826e-05,
|
| 597 |
+
"loss": 1.9899,
|
| 598 |
+
"step": 840
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 1.632388274867852,
|
| 602 |
+
"grad_norm": 7.449588775634766,
|
| 603 |
+
"learning_rate": 3.745733788395905e-05,
|
| 604 |
+
"loss": 1.9278,
|
| 605 |
+
"step": 850
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 1.651609802979337,
|
| 609 |
+
"grad_norm": 7.102870941162109,
|
| 610 |
+
"learning_rate": 3.724402730375427e-05,
|
| 611 |
+
"loss": 2.0357,
|
| 612 |
+
"step": 860
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 1.6708313310908216,
|
| 616 |
+
"grad_norm": 7.227121829986572,
|
| 617 |
+
"learning_rate": 3.703071672354949e-05,
|
| 618 |
+
"loss": 1.9708,
|
| 619 |
+
"step": 870
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 1.6900528592023067,
|
| 623 |
+
"grad_norm": 7.991628170013428,
|
| 624 |
+
"learning_rate": 3.6817406143344714e-05,
|
| 625 |
+
"loss": 1.9555,
|
| 626 |
+
"step": 880
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 1.7092743873137914,
|
| 630 |
+
"grad_norm": 7.285923957824707,
|
| 631 |
+
"learning_rate": 3.660409556313993e-05,
|
| 632 |
+
"loss": 1.9692,
|
| 633 |
+
"step": 890
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 1.7284959154252764,
|
| 637 |
+
"grad_norm": 6.6300201416015625,
|
| 638 |
+
"learning_rate": 3.6390784982935155e-05,
|
| 639 |
+
"loss": 1.9664,
|
| 640 |
+
"step": 900
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 1.7477174435367613,
|
| 644 |
+
"grad_norm": 7.206388473510742,
|
| 645 |
+
"learning_rate": 3.617747440273038e-05,
|
| 646 |
+
"loss": 1.9698,
|
| 647 |
+
"step": 910
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 1.766938971648246,
|
| 651 |
+
"grad_norm": 7.21373987197876,
|
| 652 |
+
"learning_rate": 3.5964163822525596e-05,
|
| 653 |
+
"loss": 1.9686,
|
| 654 |
+
"step": 920
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 1.786160499759731,
|
| 658 |
+
"grad_norm": 6.428858757019043,
|
| 659 |
+
"learning_rate": 3.575085324232082e-05,
|
| 660 |
+
"loss": 1.9851,
|
| 661 |
+
"step": 930
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 1.8053820278712158,
|
| 665 |
+
"grad_norm": 7.84316873550415,
|
| 666 |
+
"learning_rate": 3.5537542662116044e-05,
|
| 667 |
+
"loss": 1.9722,
|
| 668 |
+
"step": 940
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 1.8246035559827005,
|
| 672 |
+
"grad_norm": 7.756894588470459,
|
| 673 |
+
"learning_rate": 3.532423208191126e-05,
|
| 674 |
+
"loss": 1.9733,
|
| 675 |
+
"step": 950
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 1.8438250840941854,
|
| 679 |
+
"grad_norm": 6.9086480140686035,
|
| 680 |
+
"learning_rate": 3.5110921501706485e-05,
|
| 681 |
+
"loss": 1.9561,
|
| 682 |
+
"step": 960
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 1.8630466122056704,
|
| 686 |
+
"grad_norm": 7.4190802574157715,
|
| 687 |
+
"learning_rate": 3.48976109215017e-05,
|
| 688 |
+
"loss": 1.9004,
|
| 689 |
+
"step": 970
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 1.882268140317155,
|
| 693 |
+
"grad_norm": 6.598989963531494,
|
| 694 |
+
"learning_rate": 3.468430034129693e-05,
|
| 695 |
+
"loss": 1.9914,
|
| 696 |
+
"step": 980
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 1.9014896684286402,
|
| 700 |
+
"grad_norm": 7.208456516265869,
|
| 701 |
+
"learning_rate": 3.447098976109216e-05,
|
| 702 |
+
"loss": 1.9888,
|
| 703 |
+
"step": 990
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 1.920711196540125,
|
| 707 |
+
"grad_norm": 7.192534923553467,
|
| 708 |
+
"learning_rate": 3.4257679180887374e-05,
|
| 709 |
+
"loss": 1.9244,
|
| 710 |
+
"step": 1000
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 1.9399327246516098,
|
| 714 |
+
"grad_norm": 7.464297294616699,
|
| 715 |
+
"learning_rate": 3.40443686006826e-05,
|
| 716 |
+
"loss": 1.916,
|
| 717 |
+
"step": 1010
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 1.9591542527630947,
|
| 721 |
+
"grad_norm": 7.047414779663086,
|
| 722 |
+
"learning_rate": 3.383105802047782e-05,
|
| 723 |
+
"loss": 2.0045,
|
| 724 |
+
"step": 1020
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 1.9783757808745794,
|
| 728 |
+
"grad_norm": 7.436980724334717,
|
| 729 |
+
"learning_rate": 3.361774744027304e-05,
|
| 730 |
+
"loss": 2.015,
|
| 731 |
+
"step": 1030
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 1.9975973089860644,
|
| 735 |
+
"grad_norm": 6.135148525238037,
|
| 736 |
+
"learning_rate": 3.340443686006826e-05,
|
| 737 |
+
"loss": 1.9769,
|
| 738 |
+
"step": 1040
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 2.015377222489188,
|
| 742 |
+
"grad_norm": 6.220305442810059,
|
| 743 |
+
"learning_rate": 3.319112627986348e-05,
|
| 744 |
+
"loss": 1.7707,
|
| 745 |
+
"step": 1050
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 2.0345987506006726,
|
| 749 |
+
"grad_norm": 8.670418739318848,
|
| 750 |
+
"learning_rate": 3.2977815699658704e-05,
|
| 751 |
+
"loss": 1.7048,
|
| 752 |
+
"step": 1060
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 2.0538202787121578,
|
| 756 |
+
"grad_norm": 7.973430633544922,
|
| 757 |
+
"learning_rate": 3.276450511945393e-05,
|
| 758 |
+
"loss": 1.7753,
|
| 759 |
+
"step": 1070
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 2.0730418068236425,
|
| 763 |
+
"grad_norm": 7.165556907653809,
|
| 764 |
+
"learning_rate": 3.2551194539249145e-05,
|
| 765 |
+
"loss": 1.7184,
|
| 766 |
+
"step": 1080
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 2.092263334935127,
|
| 770 |
+
"grad_norm": 8.48978042602539,
|
| 771 |
+
"learning_rate": 3.233788395904437e-05,
|
| 772 |
+
"loss": 1.7799,
|
| 773 |
+
"step": 1090
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 2.1114848630466123,
|
| 777 |
+
"grad_norm": 7.75386905670166,
|
| 778 |
+
"learning_rate": 3.212457337883959e-05,
|
| 779 |
+
"loss": 1.7363,
|
| 780 |
+
"step": 1100
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 2.130706391158097,
|
| 784 |
+
"grad_norm": 7.61426305770874,
|
| 785 |
+
"learning_rate": 3.191126279863481e-05,
|
| 786 |
+
"loss": 1.7388,
|
| 787 |
+
"step": 1110
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 2.149927919269582,
|
| 791 |
+
"grad_norm": 8.537379264831543,
|
| 792 |
+
"learning_rate": 3.169795221843004e-05,
|
| 793 |
+
"loss": 1.7217,
|
| 794 |
+
"step": 1120
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 2.169149447381067,
|
| 798 |
+
"grad_norm": 8.12486457824707,
|
| 799 |
+
"learning_rate": 3.148464163822526e-05,
|
| 800 |
+
"loss": 1.7396,
|
| 801 |
+
"step": 1130
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 2.1883709754925516,
|
| 805 |
+
"grad_norm": 9.46800422668457,
|
| 806 |
+
"learning_rate": 3.127133105802048e-05,
|
| 807 |
+
"loss": 1.7526,
|
| 808 |
+
"step": 1140
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 2.2075925036040367,
|
| 812 |
+
"grad_norm": 7.893990993499756,
|
| 813 |
+
"learning_rate": 3.1058020477815705e-05,
|
| 814 |
+
"loss": 1.7482,
|
| 815 |
+
"step": 1150
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 2.2268140317155214,
|
| 819 |
+
"grad_norm": 8.076356887817383,
|
| 820 |
+
"learning_rate": 3.084470989761092e-05,
|
| 821 |
+
"loss": 1.7622,
|
| 822 |
+
"step": 1160
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 2.246035559827006,
|
| 826 |
+
"grad_norm": 7.560849666595459,
|
| 827 |
+
"learning_rate": 3.0631399317406146e-05,
|
| 828 |
+
"loss": 1.789,
|
| 829 |
+
"step": 1170
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 2.2652570879384912,
|
| 833 |
+
"grad_norm": 7.872079372406006,
|
| 834 |
+
"learning_rate": 3.0418088737201366e-05,
|
| 835 |
+
"loss": 1.7213,
|
| 836 |
+
"step": 1180
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 2.284478616049976,
|
| 840 |
+
"grad_norm": 9.256887435913086,
|
| 841 |
+
"learning_rate": 3.0204778156996587e-05,
|
| 842 |
+
"loss": 1.7497,
|
| 843 |
+
"step": 1190
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 2.3037001441614606,
|
| 847 |
+
"grad_norm": 8.256994247436523,
|
| 848 |
+
"learning_rate": 2.999146757679181e-05,
|
| 849 |
+
"loss": 1.7168,
|
| 850 |
+
"step": 1200
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 2.3229216722729458,
|
| 854 |
+
"grad_norm": 8.07515811920166,
|
| 855 |
+
"learning_rate": 2.977815699658703e-05,
|
| 856 |
+
"loss": 1.7714,
|
| 857 |
+
"step": 1210
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 2.3421432003844305,
|
| 861 |
+
"grad_norm": 7.773881435394287,
|
| 862 |
+
"learning_rate": 2.956484641638225e-05,
|
| 863 |
+
"loss": 1.7627,
|
| 864 |
+
"step": 1220
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 2.3613647284959156,
|
| 868 |
+
"grad_norm": 9.31999397277832,
|
| 869 |
+
"learning_rate": 2.9351535836177476e-05,
|
| 870 |
+
"loss": 1.7635,
|
| 871 |
+
"step": 1230
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 2.3805862566074003,
|
| 875 |
+
"grad_norm": 8.094911575317383,
|
| 876 |
+
"learning_rate": 2.9138225255972696e-05,
|
| 877 |
+
"loss": 1.8119,
|
| 878 |
+
"step": 1240
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 2.399807784718885,
|
| 882 |
+
"grad_norm": 8.966656684875488,
|
| 883 |
+
"learning_rate": 2.8924914675767916e-05,
|
| 884 |
+
"loss": 1.7844,
|
| 885 |
+
"step": 1250
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 2.41902931283037,
|
| 889 |
+
"grad_norm": 8.657224655151367,
|
| 890 |
+
"learning_rate": 2.8711604095563144e-05,
|
| 891 |
+
"loss": 1.7849,
|
| 892 |
+
"step": 1260
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 2.438250840941855,
|
| 896 |
+
"grad_norm": 8.335482597351074,
|
| 897 |
+
"learning_rate": 2.8498293515358364e-05,
|
| 898 |
+
"loss": 1.6967,
|
| 899 |
+
"step": 1270
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 2.45747236905334,
|
| 903 |
+
"grad_norm": 8.769615173339844,
|
| 904 |
+
"learning_rate": 2.8284982935153588e-05,
|
| 905 |
+
"loss": 1.8389,
|
| 906 |
+
"step": 1280
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 2.4766938971648247,
|
| 910 |
+
"grad_norm": 7.692858695983887,
|
| 911 |
+
"learning_rate": 2.807167235494881e-05,
|
| 912 |
+
"loss": 1.7602,
|
| 913 |
+
"step": 1290
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 2.4959154252763094,
|
| 917 |
+
"grad_norm": 7.612323760986328,
|
| 918 |
+
"learning_rate": 2.785836177474403e-05,
|
| 919 |
+
"loss": 1.8411,
|
| 920 |
+
"step": 1300
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 2.5151369533877945,
|
| 924 |
+
"grad_norm": 9.097857475280762,
|
| 925 |
+
"learning_rate": 2.764505119453925e-05,
|
| 926 |
+
"loss": 1.7737,
|
| 927 |
+
"step": 1310
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 2.5343584814992792,
|
| 931 |
+
"grad_norm": 9.11468505859375,
|
| 932 |
+
"learning_rate": 2.7431740614334473e-05,
|
| 933 |
+
"loss": 1.8269,
|
| 934 |
+
"step": 1320
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 2.553580009610764,
|
| 938 |
+
"grad_norm": 9.77290153503418,
|
| 939 |
+
"learning_rate": 2.7218430034129694e-05,
|
| 940 |
+
"loss": 1.7671,
|
| 941 |
+
"step": 1330
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 2.572801537722249,
|
| 945 |
+
"grad_norm": 8.101873397827148,
|
| 946 |
+
"learning_rate": 2.7005119453924914e-05,
|
| 947 |
+
"loss": 1.6804,
|
| 948 |
+
"step": 1340
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 2.5920230658337338,
|
| 952 |
+
"grad_norm": 8.107222557067871,
|
| 953 |
+
"learning_rate": 2.6791808873720138e-05,
|
| 954 |
+
"loss": 1.7327,
|
| 955 |
+
"step": 1350
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 2.6112445939452185,
|
| 959 |
+
"grad_norm": 7.96660852432251,
|
| 960 |
+
"learning_rate": 2.657849829351536e-05,
|
| 961 |
+
"loss": 1.7532,
|
| 962 |
+
"step": 1360
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 2.6304661220567036,
|
| 966 |
+
"grad_norm": 8.748746871948242,
|
| 967 |
+
"learning_rate": 2.636518771331058e-05,
|
| 968 |
+
"loss": 1.7216,
|
| 969 |
+
"step": 1370
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 2.6496876501681883,
|
| 973 |
+
"grad_norm": 8.459169387817383,
|
| 974 |
+
"learning_rate": 2.61518771331058e-05,
|
| 975 |
+
"loss": 1.755,
|
| 976 |
+
"step": 1380
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 2.668909178279673,
|
| 980 |
+
"grad_norm": 8.21006965637207,
|
| 981 |
+
"learning_rate": 2.5938566552901024e-05,
|
| 982 |
+
"loss": 1.7775,
|
| 983 |
+
"step": 1390
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 2.688130706391158,
|
| 987 |
+
"grad_norm": 7.608190059661865,
|
| 988 |
+
"learning_rate": 2.572525597269625e-05,
|
| 989 |
+
"loss": 1.6885,
|
| 990 |
+
"step": 1400
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 2.707352234502643,
|
| 994 |
+
"grad_norm": 7.753986358642578,
|
| 995 |
+
"learning_rate": 2.551194539249147e-05,
|
| 996 |
+
"loss": 1.7477,
|
| 997 |
+
"step": 1410
|
| 998 |
+
},
|
| 999 |
+
{
|
| 1000 |
+
"epoch": 2.726573762614128,
|
| 1001 |
+
"grad_norm": 9.139946937561035,
|
| 1002 |
+
"learning_rate": 2.5298634812286692e-05,
|
| 1003 |
+
"loss": 1.7118,
|
| 1004 |
+
"step": 1420
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 2.7457952907256127,
|
| 1008 |
+
"grad_norm": 8.321805000305176,
|
| 1009 |
+
"learning_rate": 2.5085324232081912e-05,
|
| 1010 |
+
"loss": 1.7373,
|
| 1011 |
+
"step": 1430
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 2.765016818837098,
|
| 1015 |
+
"grad_norm": 6.919346809387207,
|
| 1016 |
+
"learning_rate": 2.4872013651877136e-05,
|
| 1017 |
+
"loss": 1.6811,
|
| 1018 |
+
"step": 1440
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"epoch": 2.7842383469485825,
|
| 1022 |
+
"grad_norm": 8.567264556884766,
|
| 1023 |
+
"learning_rate": 2.4658703071672357e-05,
|
| 1024 |
+
"loss": 1.7402,
|
| 1025 |
+
"step": 1450
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 2.803459875060067,
|
| 1029 |
+
"grad_norm": 8.170304298400879,
|
| 1030 |
+
"learning_rate": 2.4445392491467577e-05,
|
| 1031 |
+
"loss": 1.8064,
|
| 1032 |
+
"step": 1460
|
| 1033 |
+
},
|
| 1034 |
+
{
|
| 1035 |
+
"epoch": 2.8226814031715524,
|
| 1036 |
+
"grad_norm": 8.044082641601562,
|
| 1037 |
+
"learning_rate": 2.42320819112628e-05,
|
| 1038 |
+
"loss": 1.6772,
|
| 1039 |
+
"step": 1470
|
| 1040 |
+
},
|
| 1041 |
+
{
|
| 1042 |
+
"epoch": 2.841902931283037,
|
| 1043 |
+
"grad_norm": 8.453600883483887,
|
| 1044 |
+
"learning_rate": 2.401877133105802e-05,
|
| 1045 |
+
"loss": 1.7352,
|
| 1046 |
+
"step": 1480
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 2.8611244593945218,
|
| 1050 |
+
"grad_norm": 8.70590591430664,
|
| 1051 |
+
"learning_rate": 2.3805460750853242e-05,
|
| 1052 |
+
"loss": 1.7539,
|
| 1053 |
+
"step": 1490
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 2.880345987506007,
|
| 1057 |
+
"grad_norm": 8.303061485290527,
|
| 1058 |
+
"learning_rate": 2.3592150170648466e-05,
|
| 1059 |
+
"loss": 1.7281,
|
| 1060 |
+
"step": 1500
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"epoch": 2.8995675156174916,
|
| 1064 |
+
"grad_norm": 7.61099100112915,
|
| 1065 |
+
"learning_rate": 2.3378839590443686e-05,
|
| 1066 |
+
"loss": 1.6915,
|
| 1067 |
+
"step": 1510
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"epoch": 2.9187890437289763,
|
| 1071 |
+
"grad_norm": 9.040791511535645,
|
| 1072 |
+
"learning_rate": 2.316552901023891e-05,
|
| 1073 |
+
"loss": 1.7099,
|
| 1074 |
+
"step": 1520
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 2.9380105718404614,
|
| 1078 |
+
"grad_norm": 8.227042198181152,
|
| 1079 |
+
"learning_rate": 2.295221843003413e-05,
|
| 1080 |
+
"loss": 1.7134,
|
| 1081 |
+
"step": 1530
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 2.957232099951946,
|
| 1085 |
+
"grad_norm": 7.818427085876465,
|
| 1086 |
+
"learning_rate": 2.273890784982935e-05,
|
| 1087 |
+
"loss": 1.7652,
|
| 1088 |
+
"step": 1540
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 2.976453628063431,
|
| 1092 |
+
"grad_norm": 7.761089324951172,
|
| 1093 |
+
"learning_rate": 2.2525597269624575e-05,
|
| 1094 |
+
"loss": 1.673,
|
| 1095 |
+
"step": 1550
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 2.995675156174916,
|
| 1099 |
+
"grad_norm": 9.148423194885254,
|
| 1100 |
+
"learning_rate": 2.2312286689419796e-05,
|
| 1101 |
+
"loss": 1.7545,
|
| 1102 |
+
"step": 1560
|
| 1103 |
+
},
|
| 1104 |
+
{
|
| 1105 |
+
"epoch": 3.0134550696780393,
|
| 1106 |
+
"grad_norm": 6.961498260498047,
|
| 1107 |
+
"learning_rate": 2.209897610921502e-05,
|
| 1108 |
+
"loss": 1.6289,
|
| 1109 |
+
"step": 1570
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 3.0326765977895245,
|
| 1113 |
+
"grad_norm": 8.595748901367188,
|
| 1114 |
+
"learning_rate": 2.188566552901024e-05,
|
| 1115 |
+
"loss": 1.5369,
|
| 1116 |
+
"step": 1580
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 3.051898125901009,
|
| 1120 |
+
"grad_norm": 8.743279457092285,
|
| 1121 |
+
"learning_rate": 2.1672354948805464e-05,
|
| 1122 |
+
"loss": 1.5447,
|
| 1123 |
+
"step": 1590
|
| 1124 |
+
},
|
| 1125 |
+
{
|
| 1126 |
+
"epoch": 3.071119654012494,
|
| 1127 |
+
"grad_norm": 7.540672302246094,
|
| 1128 |
+
"learning_rate": 2.1459044368600684e-05,
|
| 1129 |
+
"loss": 1.5113,
|
| 1130 |
+
"step": 1600
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 3.090341182123979,
|
| 1134 |
+
"grad_norm": 9.278829574584961,
|
| 1135 |
+
"learning_rate": 2.1245733788395905e-05,
|
| 1136 |
+
"loss": 1.5178,
|
| 1137 |
+
"step": 1610
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 3.1095627102354637,
|
| 1141 |
+
"grad_norm": 9.872568130493164,
|
| 1142 |
+
"learning_rate": 2.1032423208191125e-05,
|
| 1143 |
+
"loss": 1.5606,
|
| 1144 |
+
"step": 1620
|
| 1145 |
+
},
|
| 1146 |
+
{
|
| 1147 |
+
"epoch": 3.1287842383469484,
|
| 1148 |
+
"grad_norm": 8.62325668334961,
|
| 1149 |
+
"learning_rate": 2.081911262798635e-05,
|
| 1150 |
+
"loss": 1.4871,
|
| 1151 |
+
"step": 1630
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 3.1480057664584336,
|
| 1155 |
+
"grad_norm": 8.459789276123047,
|
| 1156 |
+
"learning_rate": 2.0605802047781573e-05,
|
| 1157 |
+
"loss": 1.5561,
|
| 1158 |
+
"step": 1640
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"epoch": 3.1672272945699183,
|
| 1162 |
+
"grad_norm": 9.252559661865234,
|
| 1163 |
+
"learning_rate": 2.0392491467576794e-05,
|
| 1164 |
+
"loss": 1.5595,
|
| 1165 |
+
"step": 1650
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"epoch": 3.1864488226814034,
|
| 1169 |
+
"grad_norm": 9.68213939666748,
|
| 1170 |
+
"learning_rate": 2.0179180887372014e-05,
|
| 1171 |
+
"loss": 1.5517,
|
| 1172 |
+
"step": 1660
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 3.205670350792888,
|
| 1176 |
+
"grad_norm": 9.817381858825684,
|
| 1177 |
+
"learning_rate": 1.9965870307167238e-05,
|
| 1178 |
+
"loss": 1.4966,
|
| 1179 |
+
"step": 1670
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 3.224891878904373,
|
| 1183 |
+
"grad_norm": 9.264698028564453,
|
| 1184 |
+
"learning_rate": 1.975255972696246e-05,
|
| 1185 |
+
"loss": 1.5443,
|
| 1186 |
+
"step": 1680
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 3.244113407015858,
|
| 1190 |
+
"grad_norm": 8.848346710205078,
|
| 1191 |
+
"learning_rate": 1.953924914675768e-05,
|
| 1192 |
+
"loss": 1.4929,
|
| 1193 |
+
"step": 1690
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 3.2633349351273426,
|
| 1197 |
+
"grad_norm": 9.325592994689941,
|
| 1198 |
+
"learning_rate": 1.93259385665529e-05,
|
| 1199 |
+
"loss": 1.5259,
|
| 1200 |
+
"step": 1700
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 3.2825564632388273,
|
| 1204 |
+
"grad_norm": 10.281765937805176,
|
| 1205 |
+
"learning_rate": 1.9112627986348127e-05,
|
| 1206 |
+
"loss": 1.5497,
|
| 1207 |
+
"step": 1710
|
| 1208 |
+
},
|
| 1209 |
+
{
|
| 1210 |
+
"epoch": 3.3017779913503125,
|
| 1211 |
+
"grad_norm": 8.460485458374023,
|
| 1212 |
+
"learning_rate": 1.8899317406143347e-05,
|
| 1213 |
+
"loss": 1.5051,
|
| 1214 |
+
"step": 1720
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 3.320999519461797,
|
| 1218 |
+
"grad_norm": 9.479697227478027,
|
| 1219 |
+
"learning_rate": 1.8686006825938568e-05,
|
| 1220 |
+
"loss": 1.5353,
|
| 1221 |
+
"step": 1730
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 3.340221047573282,
|
| 1225 |
+
"grad_norm": 8.678592681884766,
|
| 1226 |
+
"learning_rate": 1.8472696245733788e-05,
|
| 1227 |
+
"loss": 1.5865,
|
| 1228 |
+
"step": 1740
|
| 1229 |
+
},
|
| 1230 |
+
{
|
| 1231 |
+
"epoch": 3.359442575684767,
|
| 1232 |
+
"grad_norm": 9.709846496582031,
|
| 1233 |
+
"learning_rate": 1.8259385665529012e-05,
|
| 1234 |
+
"loss": 1.5572,
|
| 1235 |
+
"step": 1750
|
| 1236 |
+
},
|
| 1237 |
+
{
|
| 1238 |
+
"epoch": 3.3786641037962517,
|
| 1239 |
+
"grad_norm": 9.438785552978516,
|
| 1240 |
+
"learning_rate": 1.8046075085324232e-05,
|
| 1241 |
+
"loss": 1.5867,
|
| 1242 |
+
"step": 1760
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"epoch": 3.397885631907737,
|
| 1246 |
+
"grad_norm": 8.967934608459473,
|
| 1247 |
+
"learning_rate": 1.7832764505119453e-05,
|
| 1248 |
+
"loss": 1.49,
|
| 1249 |
+
"step": 1770
|
| 1250 |
+
},
|
| 1251 |
+
{
|
| 1252 |
+
"epoch": 3.4171071600192215,
|
| 1253 |
+
"grad_norm": 9.989371299743652,
|
| 1254 |
+
"learning_rate": 1.7619453924914677e-05,
|
| 1255 |
+
"loss": 1.5461,
|
| 1256 |
+
"step": 1780
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 3.4363286881307062,
|
| 1260 |
+
"grad_norm": 8.968268394470215,
|
| 1261 |
+
"learning_rate": 1.74061433447099e-05,
|
| 1262 |
+
"loss": 1.6002,
|
| 1263 |
+
"step": 1790
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 3.4555502162421914,
|
| 1267 |
+
"grad_norm": 9.105525016784668,
|
| 1268 |
+
"learning_rate": 1.719283276450512e-05,
|
| 1269 |
+
"loss": 1.5934,
|
| 1270 |
+
"step": 1800
|
| 1271 |
+
},
|
| 1272 |
+
{
|
| 1273 |
+
"epoch": 3.474771744353676,
|
| 1274 |
+
"grad_norm": 8.997435569763184,
|
| 1275 |
+
"learning_rate": 1.697952218430034e-05,
|
| 1276 |
+
"loss": 1.5687,
|
| 1277 |
+
"step": 1810
|
| 1278 |
+
},
|
| 1279 |
+
{
|
| 1280 |
+
"epoch": 3.4939932724651612,
|
| 1281 |
+
"grad_norm": 9.625081062316895,
|
| 1282 |
+
"learning_rate": 1.6766211604095562e-05,
|
| 1283 |
+
"loss": 1.5684,
|
| 1284 |
+
"step": 1820
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 3.513214800576646,
|
| 1288 |
+
"grad_norm": 8.427741050720215,
|
| 1289 |
+
"learning_rate": 1.6552901023890786e-05,
|
| 1290 |
+
"loss": 1.4639,
|
| 1291 |
+
"step": 1830
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 3.5324363286881306,
|
| 1295 |
+
"grad_norm": 10.164386749267578,
|
| 1296 |
+
"learning_rate": 1.6339590443686006e-05,
|
| 1297 |
+
"loss": 1.5512,
|
| 1298 |
+
"step": 1840
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 3.5516578567996158,
|
| 1302 |
+
"grad_norm": 9.009414672851562,
|
| 1303 |
+
"learning_rate": 1.612627986348123e-05,
|
| 1304 |
+
"loss": 1.5127,
|
| 1305 |
+
"step": 1850
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 3.5708793849111005,
|
| 1309 |
+
"grad_norm": 11.138776779174805,
|
| 1310 |
+
"learning_rate": 1.591296928327645e-05,
|
| 1311 |
+
"loss": 1.4763,
|
| 1312 |
+
"step": 1860
|
| 1313 |
+
},
|
| 1314 |
+
{
|
| 1315 |
+
"epoch": 3.590100913022585,
|
| 1316 |
+
"grad_norm": 8.983370780944824,
|
| 1317 |
+
"learning_rate": 1.5699658703071675e-05,
|
| 1318 |
+
"loss": 1.5661,
|
| 1319 |
+
"step": 1870
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 3.6093224411340703,
|
| 1323 |
+
"grad_norm": 9.458341598510742,
|
| 1324 |
+
"learning_rate": 1.5486348122866895e-05,
|
| 1325 |
+
"loss": 1.5151,
|
| 1326 |
+
"step": 1880
|
| 1327 |
+
},
|
| 1328 |
+
{
|
| 1329 |
+
"epoch": 3.628543969245555,
|
| 1330 |
+
"grad_norm": 9.019761085510254,
|
| 1331 |
+
"learning_rate": 1.5273037542662116e-05,
|
| 1332 |
+
"loss": 1.5646,
|
| 1333 |
+
"step": 1890
|
| 1334 |
+
},
|
| 1335 |
+
{
|
| 1336 |
+
"epoch": 3.6477654973570397,
|
| 1337 |
+
"grad_norm": 9.247156143188477,
|
| 1338 |
+
"learning_rate": 1.5059726962457338e-05,
|
| 1339 |
+
"loss": 1.5257,
|
| 1340 |
+
"step": 1900
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"epoch": 3.666987025468525,
|
| 1344 |
+
"grad_norm": 9.937666893005371,
|
| 1345 |
+
"learning_rate": 1.484641638225256e-05,
|
| 1346 |
+
"loss": 1.5934,
|
| 1347 |
+
"step": 1910
|
| 1348 |
+
},
|
| 1349 |
+
{
|
| 1350 |
+
"epoch": 3.6862085535800095,
|
| 1351 |
+
"grad_norm": 8.887203216552734,
|
| 1352 |
+
"learning_rate": 1.4633105802047784e-05,
|
| 1353 |
+
"loss": 1.5373,
|
| 1354 |
+
"step": 1920
|
| 1355 |
+
},
|
| 1356 |
+
{
|
| 1357 |
+
"epoch": 3.7054300816914942,
|
| 1358 |
+
"grad_norm": 8.323814392089844,
|
| 1359 |
+
"learning_rate": 1.4419795221843004e-05,
|
| 1360 |
+
"loss": 1.5178,
|
| 1361 |
+
"step": 1930
|
| 1362 |
+
},
|
| 1363 |
+
{
|
| 1364 |
+
"epoch": 3.7246516098029794,
|
| 1365 |
+
"grad_norm": 8.78007984161377,
|
| 1366 |
+
"learning_rate": 1.4206484641638227e-05,
|
| 1367 |
+
"loss": 1.5283,
|
| 1368 |
+
"step": 1940
|
| 1369 |
+
},
|
| 1370 |
+
{
|
| 1371 |
+
"epoch": 3.743873137914464,
|
| 1372 |
+
"grad_norm": 10.119393348693848,
|
| 1373 |
+
"learning_rate": 1.3993174061433447e-05,
|
| 1374 |
+
"loss": 1.5611,
|
| 1375 |
+
"step": 1950
|
| 1376 |
+
},
|
| 1377 |
+
{
|
| 1378 |
+
"epoch": 3.763094666025949,
|
| 1379 |
+
"grad_norm": 8.493330001831055,
|
| 1380 |
+
"learning_rate": 1.377986348122867e-05,
|
| 1381 |
+
"loss": 1.5285,
|
| 1382 |
+
"step": 1960
|
| 1383 |
+
},
|
| 1384 |
+
{
|
| 1385 |
+
"epoch": 3.782316194137434,
|
| 1386 |
+
"grad_norm": 9.496063232421875,
|
| 1387 |
+
"learning_rate": 1.3566552901023891e-05,
|
| 1388 |
+
"loss": 1.4765,
|
| 1389 |
+
"step": 1970
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 3.801537722248919,
|
| 1393 |
+
"grad_norm": 9.950116157531738,
|
| 1394 |
+
"learning_rate": 1.3353242320819112e-05,
|
| 1395 |
+
"loss": 1.522,
|
| 1396 |
+
"step": 1980
|
| 1397 |
+
},
|
| 1398 |
+
{
|
| 1399 |
+
"epoch": 3.8207592503604038,
|
| 1400 |
+
"grad_norm": 9.816246032714844,
|
| 1401 |
+
"learning_rate": 1.3139931740614336e-05,
|
| 1402 |
+
"loss": 1.5085,
|
| 1403 |
+
"step": 1990
|
| 1404 |
+
},
|
| 1405 |
+
{
|
| 1406 |
+
"epoch": 3.8399807784718885,
|
| 1407 |
+
"grad_norm": 9.766254425048828,
|
| 1408 |
+
"learning_rate": 1.2926621160409558e-05,
|
| 1409 |
+
"loss": 1.6145,
|
| 1410 |
+
"step": 2000
|
| 1411 |
+
},
|
| 1412 |
+
{
|
| 1413 |
+
"epoch": 3.8592023065833736,
|
| 1414 |
+
"grad_norm": 9.258591651916504,
|
| 1415 |
+
"learning_rate": 1.2713310580204778e-05,
|
| 1416 |
+
"loss": 1.5292,
|
| 1417 |
+
"step": 2010
|
| 1418 |
+
},
|
| 1419 |
+
{
|
| 1420 |
+
"epoch": 3.8784238346948583,
|
| 1421 |
+
"grad_norm": 9.976773262023926,
|
| 1422 |
+
"learning_rate": 1.25e-05,
|
| 1423 |
+
"loss": 1.5811,
|
| 1424 |
+
"step": 2020
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 3.897645362806343,
|
| 1428 |
+
"grad_norm": 9.001440048217773,
|
| 1429 |
+
"learning_rate": 1.2286689419795223e-05,
|
| 1430 |
+
"loss": 1.5401,
|
| 1431 |
+
"step": 2030
|
| 1432 |
+
},
|
| 1433 |
+
{
|
| 1434 |
+
"epoch": 3.916866890917828,
|
| 1435 |
+
"grad_norm": 10.00130558013916,
|
| 1436 |
+
"learning_rate": 1.2073378839590445e-05,
|
| 1437 |
+
"loss": 1.6257,
|
| 1438 |
+
"step": 2040
|
| 1439 |
+
},
|
| 1440 |
+
{
|
| 1441 |
+
"epoch": 3.936088419029313,
|
| 1442 |
+
"grad_norm": 8.235420227050781,
|
| 1443 |
+
"learning_rate": 1.1860068259385667e-05,
|
| 1444 |
+
"loss": 1.4888,
|
| 1445 |
+
"step": 2050
|
| 1446 |
+
},
|
| 1447 |
+
{
|
| 1448 |
+
"epoch": 3.9553099471407975,
|
| 1449 |
+
"grad_norm": 9.468134880065918,
|
| 1450 |
+
"learning_rate": 1.1646757679180888e-05,
|
| 1451 |
+
"loss": 1.6077,
|
| 1452 |
+
"step": 2060
|
| 1453 |
+
},
|
| 1454 |
+
{
|
| 1455 |
+
"epoch": 3.9745314752522827,
|
| 1456 |
+
"grad_norm": 8.448241233825684,
|
| 1457 |
+
"learning_rate": 1.143344709897611e-05,
|
| 1458 |
+
"loss": 1.5568,
|
| 1459 |
+
"step": 2070
|
| 1460 |
+
},
|
| 1461 |
+
{
|
| 1462 |
+
"epoch": 3.9937530033637674,
|
| 1463 |
+
"grad_norm": 9.615592956542969,
|
| 1464 |
+
"learning_rate": 1.1220136518771332e-05,
|
| 1465 |
+
"loss": 1.6119,
|
| 1466 |
+
"step": 2080
|
| 1467 |
+
},
|
| 1468 |
+
{
|
| 1469 |
+
"epoch": 4.011532916866891,
|
| 1470 |
+
"grad_norm": 8.427413940429688,
|
| 1471 |
+
"learning_rate": 1.1006825938566554e-05,
|
| 1472 |
+
"loss": 1.5303,
|
| 1473 |
+
"step": 2090
|
| 1474 |
+
},
|
| 1475 |
+
{
|
| 1476 |
+
"epoch": 4.030754444978376,
|
| 1477 |
+
"grad_norm": 7.633726119995117,
|
| 1478 |
+
"learning_rate": 1.0793515358361775e-05,
|
| 1479 |
+
"loss": 1.368,
|
| 1480 |
+
"step": 2100
|
| 1481 |
+
},
|
| 1482 |
+
{
|
| 1483 |
+
"epoch": 4.049975973089861,
|
| 1484 |
+
"grad_norm": 9.611651420593262,
|
| 1485 |
+
"learning_rate": 1.0580204778156999e-05,
|
| 1486 |
+
"loss": 1.3859,
|
| 1487 |
+
"step": 2110
|
| 1488 |
+
},
|
| 1489 |
+
{
|
| 1490 |
+
"epoch": 4.069197501201345,
|
| 1491 |
+
"grad_norm": 10.329586029052734,
|
| 1492 |
+
"learning_rate": 1.0366894197952219e-05,
|
| 1493 |
+
"loss": 1.4339,
|
| 1494 |
+
"step": 2120
|
| 1495 |
+
},
|
| 1496 |
+
{
|
| 1497 |
+
"epoch": 4.08841902931283,
|
| 1498 |
+
"grad_norm": 10.441389083862305,
|
| 1499 |
+
"learning_rate": 1.0153583617747441e-05,
|
| 1500 |
+
"loss": 1.4027,
|
| 1501 |
+
"step": 2130
|
| 1502 |
+
},
|
| 1503 |
+
{
|
| 1504 |
+
"epoch": 4.1076405574243156,
|
| 1505 |
+
"grad_norm": 11.6917085647583,
|
| 1506 |
+
"learning_rate": 9.940273037542662e-06,
|
| 1507 |
+
"loss": 1.44,
|
| 1508 |
+
"step": 2140
|
| 1509 |
+
},
|
| 1510 |
+
{
|
| 1511 |
+
"epoch": 4.1268620855358,
|
| 1512 |
+
"grad_norm": 9.722172737121582,
|
| 1513 |
+
"learning_rate": 9.726962457337886e-06,
|
| 1514 |
+
"loss": 1.376,
|
| 1515 |
+
"step": 2150
|
| 1516 |
+
},
|
| 1517 |
+
{
|
| 1518 |
+
"epoch": 4.146083613647285,
|
| 1519 |
+
"grad_norm": 9.619889259338379,
|
| 1520 |
+
"learning_rate": 9.513651877133106e-06,
|
| 1521 |
+
"loss": 1.3754,
|
| 1522 |
+
"step": 2160
|
| 1523 |
+
},
|
| 1524 |
+
{
|
| 1525 |
+
"epoch": 4.16530514175877,
|
| 1526 |
+
"grad_norm": 10.17457103729248,
|
| 1527 |
+
"learning_rate": 9.300341296928328e-06,
|
| 1528 |
+
"loss": 1.3115,
|
| 1529 |
+
"step": 2170
|
| 1530 |
+
},
|
| 1531 |
+
{
|
| 1532 |
+
"epoch": 4.184526669870254,
|
| 1533 |
+
"grad_norm": 9.053975105285645,
|
| 1534 |
+
"learning_rate": 9.08703071672355e-06,
|
| 1535 |
+
"loss": 1.3668,
|
| 1536 |
+
"step": 2180
|
| 1537 |
+
},
|
| 1538 |
+
{
|
| 1539 |
+
"epoch": 4.2037481979817395,
|
| 1540 |
+
"grad_norm": 9.389638900756836,
|
| 1541 |
+
"learning_rate": 8.873720136518773e-06,
|
| 1542 |
+
"loss": 1.4006,
|
| 1543 |
+
"step": 2190
|
| 1544 |
+
},
|
| 1545 |
+
{
|
| 1546 |
+
"epoch": 4.222969726093225,
|
| 1547 |
+
"grad_norm": 10.160106658935547,
|
| 1548 |
+
"learning_rate": 8.660409556313993e-06,
|
| 1549 |
+
"loss": 1.4084,
|
| 1550 |
+
"step": 2200
|
| 1551 |
+
},
|
| 1552 |
+
{
|
| 1553 |
+
"epoch": 4.242191254204709,
|
| 1554 |
+
"grad_norm": 11.254199981689453,
|
| 1555 |
+
"learning_rate": 8.447098976109215e-06,
|
| 1556 |
+
"loss": 1.4647,
|
| 1557 |
+
"step": 2210
|
| 1558 |
+
},
|
| 1559 |
+
{
|
| 1560 |
+
"epoch": 4.261412782316194,
|
| 1561 |
+
"grad_norm": 10.098913192749023,
|
| 1562 |
+
"learning_rate": 8.233788395904437e-06,
|
| 1563 |
+
"loss": 1.427,
|
| 1564 |
+
"step": 2220
|
| 1565 |
+
},
|
| 1566 |
+
{
|
| 1567 |
+
"epoch": 4.280634310427679,
|
| 1568 |
+
"grad_norm": 10.879392623901367,
|
| 1569 |
+
"learning_rate": 8.02047781569966e-06,
|
| 1570 |
+
"loss": 1.4457,
|
| 1571 |
+
"step": 2230
|
| 1572 |
+
},
|
| 1573 |
+
{
|
| 1574 |
+
"epoch": 4.299855838539164,
|
| 1575 |
+
"grad_norm": 9.308858871459961,
|
| 1576 |
+
"learning_rate": 7.80716723549488e-06,
|
| 1577 |
+
"loss": 1.3712,
|
| 1578 |
+
"step": 2240
|
| 1579 |
+
},
|
| 1580 |
+
{
|
| 1581 |
+
"epoch": 4.319077366650649,
|
| 1582 |
+
"grad_norm": 10.300002098083496,
|
| 1583 |
+
"learning_rate": 7.593856655290103e-06,
|
| 1584 |
+
"loss": 1.3592,
|
| 1585 |
+
"step": 2250
|
| 1586 |
+
},
|
| 1587 |
+
{
|
| 1588 |
+
"epoch": 4.338298894762134,
|
| 1589 |
+
"grad_norm": 10.036710739135742,
|
| 1590 |
+
"learning_rate": 7.3805460750853244e-06,
|
| 1591 |
+
"loss": 1.4002,
|
| 1592 |
+
"step": 2260
|
| 1593 |
+
},
|
| 1594 |
+
{
|
| 1595 |
+
"epoch": 4.357520422873619,
|
| 1596 |
+
"grad_norm": 9.933674812316895,
|
| 1597 |
+
"learning_rate": 7.167235494880546e-06,
|
| 1598 |
+
"loss": 1.3751,
|
| 1599 |
+
"step": 2270
|
| 1600 |
+
},
|
| 1601 |
+
{
|
| 1602 |
+
"epoch": 4.376741950985103,
|
| 1603 |
+
"grad_norm": 11.534444808959961,
|
| 1604 |
+
"learning_rate": 6.953924914675768e-06,
|
| 1605 |
+
"loss": 1.3938,
|
| 1606 |
+
"step": 2280
|
| 1607 |
+
},
|
| 1608 |
+
{
|
| 1609 |
+
"epoch": 4.395963479096588,
|
| 1610 |
+
"grad_norm": 10.834949493408203,
|
| 1611 |
+
"learning_rate": 6.74061433447099e-06,
|
| 1612 |
+
"loss": 1.476,
|
| 1613 |
+
"step": 2290
|
| 1614 |
+
},
|
| 1615 |
+
{
|
| 1616 |
+
"epoch": 4.415185007208073,
|
| 1617 |
+
"grad_norm": 10.888574600219727,
|
| 1618 |
+
"learning_rate": 6.5273037542662115e-06,
|
| 1619 |
+
"loss": 1.4017,
|
| 1620 |
+
"step": 2300
|
| 1621 |
+
},
|
| 1622 |
+
{
|
| 1623 |
+
"epoch": 4.434406535319558,
|
| 1624 |
+
"grad_norm": 10.21182918548584,
|
| 1625 |
+
"learning_rate": 6.313993174061434e-06,
|
| 1626 |
+
"loss": 1.432,
|
| 1627 |
+
"step": 2310
|
| 1628 |
+
},
|
| 1629 |
+
{
|
| 1630 |
+
"epoch": 4.453628063431043,
|
| 1631 |
+
"grad_norm": 10.255495071411133,
|
| 1632 |
+
"learning_rate": 6.100682593856656e-06,
|
| 1633 |
+
"loss": 1.3986,
|
| 1634 |
+
"step": 2320
|
| 1635 |
+
},
|
| 1636 |
+
{
|
| 1637 |
+
"epoch": 4.472849591542528,
|
| 1638 |
+
"grad_norm": 9.658021926879883,
|
| 1639 |
+
"learning_rate": 5.887372013651877e-06,
|
| 1640 |
+
"loss": 1.384,
|
| 1641 |
+
"step": 2330
|
| 1642 |
+
},
|
| 1643 |
+
{
|
| 1644 |
+
"epoch": 4.492071119654012,
|
| 1645 |
+
"grad_norm": 10.915364265441895,
|
| 1646 |
+
"learning_rate": 5.674061433447099e-06,
|
| 1647 |
+
"loss": 1.4102,
|
| 1648 |
+
"step": 2340
|
| 1649 |
+
},
|
| 1650 |
+
{
|
| 1651 |
+
"epoch": 4.511292647765497,
|
| 1652 |
+
"grad_norm": 9.598386764526367,
|
| 1653 |
+
"learning_rate": 5.4607508532423215e-06,
|
| 1654 |
+
"loss": 1.362,
|
| 1655 |
+
"step": 2350
|
| 1656 |
+
},
|
| 1657 |
+
{
|
| 1658 |
+
"epoch": 4.5305141758769825,
|
| 1659 |
+
"grad_norm": 11.112643241882324,
|
| 1660 |
+
"learning_rate": 5.247440273037543e-06,
|
| 1661 |
+
"loss": 1.4069,
|
| 1662 |
+
"step": 2360
|
| 1663 |
+
},
|
| 1664 |
+
{
|
| 1665 |
+
"epoch": 4.549735703988467,
|
| 1666 |
+
"grad_norm": 10.625088691711426,
|
| 1667 |
+
"learning_rate": 5.034129692832765e-06,
|
| 1668 |
+
"loss": 1.3952,
|
| 1669 |
+
"step": 2370
|
| 1670 |
+
},
|
| 1671 |
+
{
|
| 1672 |
+
"epoch": 4.568957232099952,
|
| 1673 |
+
"grad_norm": 10.471019744873047,
|
| 1674 |
+
"learning_rate": 4.820819112627987e-06,
|
| 1675 |
+
"loss": 1.4068,
|
| 1676 |
+
"step": 2380
|
| 1677 |
+
},
|
| 1678 |
+
{
|
| 1679 |
+
"epoch": 4.588178760211437,
|
| 1680 |
+
"grad_norm": 10.431234359741211,
|
| 1681 |
+
"learning_rate": 4.6075085324232085e-06,
|
| 1682 |
+
"loss": 1.4116,
|
| 1683 |
+
"step": 2390
|
| 1684 |
+
},
|
| 1685 |
+
{
|
| 1686 |
+
"epoch": 4.607400288322921,
|
| 1687 |
+
"grad_norm": 10.526016235351562,
|
| 1688 |
+
"learning_rate": 4.394197952218431e-06,
|
| 1689 |
+
"loss": 1.3311,
|
| 1690 |
+
"step": 2400
|
| 1691 |
+
},
|
| 1692 |
+
{
|
| 1693 |
+
"epoch": 4.626621816434406,
|
| 1694 |
+
"grad_norm": 10.347298622131348,
|
| 1695 |
+
"learning_rate": 4.180887372013652e-06,
|
| 1696 |
+
"loss": 1.3508,
|
| 1697 |
+
"step": 2410
|
| 1698 |
+
},
|
| 1699 |
+
{
|
| 1700 |
+
"epoch": 4.6458433445458915,
|
| 1701 |
+
"grad_norm": 9.437437057495117,
|
| 1702 |
+
"learning_rate": 3.967576791808874e-06,
|
| 1703 |
+
"loss": 1.3888,
|
| 1704 |
+
"step": 2420
|
| 1705 |
+
},
|
| 1706 |
+
{
|
| 1707 |
+
"epoch": 4.665064872657377,
|
| 1708 |
+
"grad_norm": 9.274221420288086,
|
| 1709 |
+
"learning_rate": 3.754266211604096e-06,
|
| 1710 |
+
"loss": 1.3586,
|
| 1711 |
+
"step": 2430
|
| 1712 |
+
},
|
| 1713 |
+
{
|
| 1714 |
+
"epoch": 4.684286400768861,
|
| 1715 |
+
"grad_norm": 10.08513069152832,
|
| 1716 |
+
"learning_rate": 3.5409556313993173e-06,
|
| 1717 |
+
"loss": 1.3351,
|
| 1718 |
+
"step": 2440
|
| 1719 |
+
},
|
| 1720 |
+
{
|
| 1721 |
+
"epoch": 4.703507928880346,
|
| 1722 |
+
"grad_norm": 10.008994102478027,
|
| 1723 |
+
"learning_rate": 3.3276450511945395e-06,
|
| 1724 |
+
"loss": 1.3078,
|
| 1725 |
+
"step": 2450
|
| 1726 |
+
},
|
| 1727 |
+
{
|
| 1728 |
+
"epoch": 4.722729456991831,
|
| 1729 |
+
"grad_norm": 8.64718246459961,
|
| 1730 |
+
"learning_rate": 3.1143344709897613e-06,
|
| 1731 |
+
"loss": 1.3553,
|
| 1732 |
+
"step": 2460
|
| 1733 |
+
},
|
| 1734 |
+
{
|
| 1735 |
+
"epoch": 4.7419509851033155,
|
| 1736 |
+
"grad_norm": 10.21820068359375,
|
| 1737 |
+
"learning_rate": 2.901023890784983e-06,
|
| 1738 |
+
"loss": 1.3782,
|
| 1739 |
+
"step": 2470
|
| 1740 |
+
},
|
| 1741 |
+
{
|
| 1742 |
+
"epoch": 4.761172513214801,
|
| 1743 |
+
"grad_norm": 10.363849639892578,
|
| 1744 |
+
"learning_rate": 2.687713310580205e-06,
|
| 1745 |
+
"loss": 1.3658,
|
| 1746 |
+
"step": 2480
|
| 1747 |
+
},
|
| 1748 |
+
{
|
| 1749 |
+
"epoch": 4.780394041326286,
|
| 1750 |
+
"grad_norm": 11.896404266357422,
|
| 1751 |
+
"learning_rate": 2.474402730375427e-06,
|
| 1752 |
+
"loss": 1.3566,
|
| 1753 |
+
"step": 2490
|
| 1754 |
+
},
|
| 1755 |
+
{
|
| 1756 |
+
"epoch": 4.79961556943777,
|
| 1757 |
+
"grad_norm": 9.402819633483887,
|
| 1758 |
+
"learning_rate": 2.2610921501706487e-06,
|
| 1759 |
+
"loss": 1.3692,
|
| 1760 |
+
"step": 2500
|
| 1761 |
+
},
|
| 1762 |
+
{
|
| 1763 |
+
"epoch": 4.818837097549255,
|
| 1764 |
+
"grad_norm": 11.33333683013916,
|
| 1765 |
+
"learning_rate": 2.0477815699658705e-06,
|
| 1766 |
+
"loss": 1.4347,
|
| 1767 |
+
"step": 2510
|
| 1768 |
+
},
|
| 1769 |
+
{
|
| 1770 |
+
"epoch": 4.83805862566074,
|
| 1771 |
+
"grad_norm": 10.20227336883545,
|
| 1772 |
+
"learning_rate": 1.8344709897610922e-06,
|
| 1773 |
+
"loss": 1.4151,
|
| 1774 |
+
"step": 2520
|
| 1775 |
+
},
|
| 1776 |
+
{
|
| 1777 |
+
"epoch": 4.8572801537722246,
|
| 1778 |
+
"grad_norm": 10.206210136413574,
|
| 1779 |
+
"learning_rate": 1.621160409556314e-06,
|
| 1780 |
+
"loss": 1.3516,
|
| 1781 |
+
"step": 2530
|
| 1782 |
+
},
|
| 1783 |
+
{
|
| 1784 |
+
"epoch": 4.87650168188371,
|
| 1785 |
+
"grad_norm": 10.120949745178223,
|
| 1786 |
+
"learning_rate": 1.407849829351536e-06,
|
| 1787 |
+
"loss": 1.3973,
|
| 1788 |
+
"step": 2540
|
| 1789 |
+
},
|
| 1790 |
+
{
|
| 1791 |
+
"epoch": 4.895723209995195,
|
| 1792 |
+
"grad_norm": 10.073768615722656,
|
| 1793 |
+
"learning_rate": 1.194539249146758e-06,
|
| 1794 |
+
"loss": 1.3755,
|
| 1795 |
+
"step": 2550
|
| 1796 |
+
},
|
| 1797 |
+
{
|
| 1798 |
+
"epoch": 4.91494473810668,
|
| 1799 |
+
"grad_norm": 11.21468448638916,
|
| 1800 |
+
"learning_rate": 9.812286689419797e-07,
|
| 1801 |
+
"loss": 1.3614,
|
| 1802 |
+
"step": 2560
|
| 1803 |
+
},
|
| 1804 |
+
{
|
| 1805 |
+
"epoch": 4.934166266218164,
|
| 1806 |
+
"grad_norm": 11.302360534667969,
|
| 1807 |
+
"learning_rate": 7.679180887372014e-07,
|
| 1808 |
+
"loss": 1.4116,
|
| 1809 |
+
"step": 2570
|
| 1810 |
+
},
|
| 1811 |
+
{
|
| 1812 |
+
"epoch": 4.953387794329649,
|
| 1813 |
+
"grad_norm": 9.757354736328125,
|
| 1814 |
+
"learning_rate": 5.546075085324233e-07,
|
| 1815 |
+
"loss": 1.346,
|
| 1816 |
+
"step": 2580
|
| 1817 |
+
},
|
| 1818 |
+
{
|
| 1819 |
+
"epoch": 4.972609322441134,
|
| 1820 |
+
"grad_norm": 9.289881706237793,
|
| 1821 |
+
"learning_rate": 3.412969283276451e-07,
|
| 1822 |
+
"loss": 1.4193,
|
| 1823 |
+
"step": 2590
|
| 1824 |
+
},
|
| 1825 |
+
{
|
| 1826 |
+
"epoch": 4.991830850552619,
|
| 1827 |
+
"grad_norm": 11.2091064453125,
|
| 1828 |
+
"learning_rate": 1.279863481228669e-07,
|
| 1829 |
+
"loss": 1.4567,
|
| 1830 |
+
"step": 2600
|
| 1831 |
+
}
|
| 1832 |
+
],
|
| 1833 |
+
"logging_steps": 10,
|
| 1834 |
+
"max_steps": 2605,
|
| 1835 |
+
"num_input_tokens_seen": 0,
|
| 1836 |
+
"num_train_epochs": 5,
|
| 1837 |
+
"save_steps": 500,
|
| 1838 |
+
"stateful_callbacks": {
|
| 1839 |
+
"TrainerControl": {
|
| 1840 |
+
"args": {
|
| 1841 |
+
"should_epoch_stop": false,
|
| 1842 |
+
"should_evaluate": false,
|
| 1843 |
+
"should_log": false,
|
| 1844 |
+
"should_save": true,
|
| 1845 |
+
"should_training_stop": true
|
| 1846 |
+
},
|
| 1847 |
+
"attributes": {}
|
| 1848 |
+
}
|
| 1849 |
+
},
|
| 1850 |
+
"total_flos": 9359482190499840.0,
|
| 1851 |
+
"train_batch_size": 4,
|
| 1852 |
+
"trial_name": null,
|
| 1853 |
+
"trial_params": null
|
| 1854 |
+
}
|
checkpoint-2605/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8f3f2c51094de7b2e8fb357753c21db50fbd28d5b3e8bc9181e6be1839b36076
|
| 3 |
+
size 5713
|