Training in progress, step 280, checkpoint
Browse files- .gitattributes +1 -0
- checkpoint-280/README.md +209 -0
- checkpoint-280/adapter_config.json +42 -0
- checkpoint-280/adapter_model.safetensors +3 -0
- checkpoint-280/chat_template.jinja +315 -0
- checkpoint-280/optimizer.pt +3 -0
- checkpoint-280/rng_state.pth +3 -0
- checkpoint-280/scheduler.pt +3 -0
- checkpoint-280/special_tokens_map.json +23 -0
- checkpoint-280/tokenizer.json +3 -0
- checkpoint-280/tokenizer_config.json +185 -0
- checkpoint-280/trainer_state.json +2218 -0
- checkpoint-280/training_args.bin +3 -0
.gitattributes
CHANGED
|
@@ -61,3 +61,4 @@ checkpoint-240/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
|
| 61 |
checkpoint-250/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 62 |
checkpoint-260/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 63 |
checkpoint-270/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 61 |
checkpoint-250/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 62 |
checkpoint-260/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 63 |
checkpoint-270/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 64 |
+
checkpoint-280/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
checkpoint-280/README.md
ADDED
|
@@ -0,0 +1,209 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: unsloth/gpt-oss-20b
|
| 3 |
+
library_name: peft
|
| 4 |
+
tags:
|
| 5 |
+
- base_model:adapter:unsloth/gpt-oss-20b
|
| 6 |
+
- lora
|
| 7 |
+
- sft
|
| 8 |
+
- transformers
|
| 9 |
+
- trl
|
| 10 |
+
- unsloth
|
| 11 |
+
---
|
| 12 |
+
|
| 13 |
+
# Model Card for Model ID
|
| 14 |
+
|
| 15 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 16 |
+
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
## Model Details
|
| 20 |
+
|
| 21 |
+
### Model Description
|
| 22 |
+
|
| 23 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 24 |
+
|
| 25 |
+
|
| 26 |
+
|
| 27 |
+
- **Developed by:** [More Information Needed]
|
| 28 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 29 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 30 |
+
- **Model type:** [More Information Needed]
|
| 31 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 32 |
+
- **License:** [More Information Needed]
|
| 33 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 34 |
+
|
| 35 |
+
### Model Sources [optional]
|
| 36 |
+
|
| 37 |
+
<!-- Provide the basic links for the model. -->
|
| 38 |
+
|
| 39 |
+
- **Repository:** [More Information Needed]
|
| 40 |
+
- **Paper [optional]:** [More Information Needed]
|
| 41 |
+
- **Demo [optional]:** [More Information Needed]
|
| 42 |
+
|
| 43 |
+
## Uses
|
| 44 |
+
|
| 45 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 46 |
+
|
| 47 |
+
### Direct Use
|
| 48 |
+
|
| 49 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 50 |
+
|
| 51 |
+
[More Information Needed]
|
| 52 |
+
|
| 53 |
+
### Downstream Use [optional]
|
| 54 |
+
|
| 55 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 56 |
+
|
| 57 |
+
[More Information Needed]
|
| 58 |
+
|
| 59 |
+
### Out-of-Scope Use
|
| 60 |
+
|
| 61 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 62 |
+
|
| 63 |
+
[More Information Needed]
|
| 64 |
+
|
| 65 |
+
## Bias, Risks, and Limitations
|
| 66 |
+
|
| 67 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 68 |
+
|
| 69 |
+
[More Information Needed]
|
| 70 |
+
|
| 71 |
+
### Recommendations
|
| 72 |
+
|
| 73 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 74 |
+
|
| 75 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 76 |
+
|
| 77 |
+
## How to Get Started with the Model
|
| 78 |
+
|
| 79 |
+
Use the code below to get started with the model.
|
| 80 |
+
|
| 81 |
+
[More Information Needed]
|
| 82 |
+
|
| 83 |
+
## Training Details
|
| 84 |
+
|
| 85 |
+
### Training Data
|
| 86 |
+
|
| 87 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 88 |
+
|
| 89 |
+
[More Information Needed]
|
| 90 |
+
|
| 91 |
+
### Training Procedure
|
| 92 |
+
|
| 93 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 94 |
+
|
| 95 |
+
#### Preprocessing [optional]
|
| 96 |
+
|
| 97 |
+
[More Information Needed]
|
| 98 |
+
|
| 99 |
+
|
| 100 |
+
#### Training Hyperparameters
|
| 101 |
+
|
| 102 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 103 |
+
|
| 104 |
+
#### Speeds, Sizes, Times [optional]
|
| 105 |
+
|
| 106 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 107 |
+
|
| 108 |
+
[More Information Needed]
|
| 109 |
+
|
| 110 |
+
## Evaluation
|
| 111 |
+
|
| 112 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 113 |
+
|
| 114 |
+
### Testing Data, Factors & Metrics
|
| 115 |
+
|
| 116 |
+
#### Testing Data
|
| 117 |
+
|
| 118 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 119 |
+
|
| 120 |
+
[More Information Needed]
|
| 121 |
+
|
| 122 |
+
#### Factors
|
| 123 |
+
|
| 124 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 125 |
+
|
| 126 |
+
[More Information Needed]
|
| 127 |
+
|
| 128 |
+
#### Metrics
|
| 129 |
+
|
| 130 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 131 |
+
|
| 132 |
+
[More Information Needed]
|
| 133 |
+
|
| 134 |
+
### Results
|
| 135 |
+
|
| 136 |
+
[More Information Needed]
|
| 137 |
+
|
| 138 |
+
#### Summary
|
| 139 |
+
|
| 140 |
+
|
| 141 |
+
|
| 142 |
+
## Model Examination [optional]
|
| 143 |
+
|
| 144 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 145 |
+
|
| 146 |
+
[More Information Needed]
|
| 147 |
+
|
| 148 |
+
## Environmental Impact
|
| 149 |
+
|
| 150 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 151 |
+
|
| 152 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
| 153 |
+
|
| 154 |
+
- **Hardware Type:** [More Information Needed]
|
| 155 |
+
- **Hours used:** [More Information Needed]
|
| 156 |
+
- **Cloud Provider:** [More Information Needed]
|
| 157 |
+
- **Compute Region:** [More Information Needed]
|
| 158 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 159 |
+
|
| 160 |
+
## Technical Specifications [optional]
|
| 161 |
+
|
| 162 |
+
### Model Architecture and Objective
|
| 163 |
+
|
| 164 |
+
[More Information Needed]
|
| 165 |
+
|
| 166 |
+
### Compute Infrastructure
|
| 167 |
+
|
| 168 |
+
[More Information Needed]
|
| 169 |
+
|
| 170 |
+
#### Hardware
|
| 171 |
+
|
| 172 |
+
[More Information Needed]
|
| 173 |
+
|
| 174 |
+
#### Software
|
| 175 |
+
|
| 176 |
+
[More Information Needed]
|
| 177 |
+
|
| 178 |
+
## Citation [optional]
|
| 179 |
+
|
| 180 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 181 |
+
|
| 182 |
+
**BibTeX:**
|
| 183 |
+
|
| 184 |
+
[More Information Needed]
|
| 185 |
+
|
| 186 |
+
**APA:**
|
| 187 |
+
|
| 188 |
+
[More Information Needed]
|
| 189 |
+
|
| 190 |
+
## Glossary [optional]
|
| 191 |
+
|
| 192 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 193 |
+
|
| 194 |
+
[More Information Needed]
|
| 195 |
+
|
| 196 |
+
## More Information [optional]
|
| 197 |
+
|
| 198 |
+
[More Information Needed]
|
| 199 |
+
|
| 200 |
+
## Model Card Authors [optional]
|
| 201 |
+
|
| 202 |
+
[More Information Needed]
|
| 203 |
+
|
| 204 |
+
## Model Card Contact
|
| 205 |
+
|
| 206 |
+
[More Information Needed]
|
| 207 |
+
### Framework versions
|
| 208 |
+
|
| 209 |
+
- PEFT 0.17.0
|
checkpoint-280/adapter_config.json
ADDED
|
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": {
|
| 4 |
+
"base_model_class": "GptOssForCausalLM",
|
| 5 |
+
"parent_library": "transformers.models.gpt_oss.modeling_gpt_oss"
|
| 6 |
+
},
|
| 7 |
+
"base_model_name_or_path": "unsloth/gpt-oss-20b",
|
| 8 |
+
"bias": "none",
|
| 9 |
+
"corda_config": null,
|
| 10 |
+
"eva_config": null,
|
| 11 |
+
"exclude_modules": null,
|
| 12 |
+
"fan_in_fan_out": false,
|
| 13 |
+
"inference_mode": true,
|
| 14 |
+
"init_lora_weights": true,
|
| 15 |
+
"layer_replication": null,
|
| 16 |
+
"layers_pattern": null,
|
| 17 |
+
"layers_to_transform": null,
|
| 18 |
+
"loftq_config": {},
|
| 19 |
+
"lora_alpha": 64,
|
| 20 |
+
"lora_bias": false,
|
| 21 |
+
"lora_dropout": 0.0,
|
| 22 |
+
"megatron_config": null,
|
| 23 |
+
"megatron_core": "megatron.core",
|
| 24 |
+
"modules_to_save": null,
|
| 25 |
+
"peft_type": "LORA",
|
| 26 |
+
"qalora_group_size": 16,
|
| 27 |
+
"r": 1,
|
| 28 |
+
"rank_pattern": {},
|
| 29 |
+
"revision": null,
|
| 30 |
+
"target_modules": [
|
| 31 |
+
"k_proj",
|
| 32 |
+
"q_proj",
|
| 33 |
+
"v_proj",
|
| 34 |
+
"o_proj"
|
| 35 |
+
],
|
| 36 |
+
"target_parameters": null,
|
| 37 |
+
"task_type": null,
|
| 38 |
+
"trainable_token_indices": null,
|
| 39 |
+
"use_dora": false,
|
| 40 |
+
"use_qalora": false,
|
| 41 |
+
"use_rslora": true
|
| 42 |
+
}
|
checkpoint-280/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:58319e3e57a3622cf1e7c252d45023032d5f0e118ce2a8db8f583cc696ee9e7f
|
| 3 |
+
size 2015696
|
checkpoint-280/chat_template.jinja
ADDED
|
@@ -0,0 +1,315 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{# Copyright 2025-present Unsloth. Apache 2.0 License. Unsloth chat template fixes. Edited from ggml-org & OpenAI #}
|
| 2 |
+
{#-
|
| 3 |
+
In addition to the normal inputs of `messages` and `tools`, this template also accepts the
|
| 4 |
+
following kwargs:
|
| 5 |
+
- "builtin_tools": A list, can contain "browser" and/or "python".
|
| 6 |
+
- "model_identity": A string that optionally describes the model identity.
|
| 7 |
+
- "reasoning_effort": A string that describes the reasoning effort, defaults to "medium".
|
| 8 |
+
#}
|
| 9 |
+
|
| 10 |
+
{#- Tool Definition Rendering ============================================== #}
|
| 11 |
+
{%- macro render_typescript_type(param_spec, required_params, is_nullable=false) -%}
|
| 12 |
+
{%- if param_spec.type == "array" -%}
|
| 13 |
+
{%- if param_spec['items'] -%}
|
| 14 |
+
{%- if param_spec['items']['type'] == "string" -%}
|
| 15 |
+
{{- "string[]" }}
|
| 16 |
+
{%- elif param_spec['items']['type'] == "number" -%}
|
| 17 |
+
{{- "number[]" }}
|
| 18 |
+
{%- elif param_spec['items']['type'] == "integer" -%}
|
| 19 |
+
{{- "number[]" }}
|
| 20 |
+
{%- elif param_spec['items']['type'] == "boolean" -%}
|
| 21 |
+
{{- "boolean[]" }}
|
| 22 |
+
{%- else -%}
|
| 23 |
+
{%- set inner_type = render_typescript_type(param_spec['items'], required_params) -%}
|
| 24 |
+
{%- if inner_type == "object | object" or inner_type|length > 50 -%}
|
| 25 |
+
{{- "any[]" }}
|
| 26 |
+
{%- else -%}
|
| 27 |
+
{{- inner_type + "[]" }}
|
| 28 |
+
{%- endif -%}
|
| 29 |
+
{%- endif -%}
|
| 30 |
+
{%- if param_spec.nullable -%}
|
| 31 |
+
{{- " | null" }}
|
| 32 |
+
{%- endif -%}
|
| 33 |
+
{%- else -%}
|
| 34 |
+
{{- "any[]" }}
|
| 35 |
+
{%- if param_spec.nullable -%}
|
| 36 |
+
{{- " | null" }}
|
| 37 |
+
{%- endif -%}
|
| 38 |
+
{%- endif -%}
|
| 39 |
+
{%- elif param_spec.type is defined and param_spec.type is iterable and param_spec.type is not string and param_spec.type is not mapping and param_spec.type[0] is defined -%}
|
| 40 |
+
{#- Handle array of types like ["object", "object"] from Union[dict, list] #}
|
| 41 |
+
{%- if param_spec.type | length > 1 -%}
|
| 42 |
+
{{- param_spec.type | join(" | ") }}
|
| 43 |
+
{%- else -%}
|
| 44 |
+
{{- param_spec.type[0] }}
|
| 45 |
+
{%- endif -%}
|
| 46 |
+
{%- elif param_spec.oneOf -%}
|
| 47 |
+
{#- Handle oneOf schemas - check for complex unions and fallback to any #}
|
| 48 |
+
{%- set has_object_variants = false -%}
|
| 49 |
+
{%- for variant in param_spec.oneOf -%}
|
| 50 |
+
{%- if variant.type == "object" -%}
|
| 51 |
+
{%- set has_object_variants = true -%}
|
| 52 |
+
{%- endif -%}
|
| 53 |
+
{%- endfor -%}
|
| 54 |
+
{%- if has_object_variants and param_spec.oneOf|length > 1 -%}
|
| 55 |
+
{{- "any" }}
|
| 56 |
+
{%- else -%}
|
| 57 |
+
{%- for variant in param_spec.oneOf -%}
|
| 58 |
+
{{- render_typescript_type(variant, required_params) -}}
|
| 59 |
+
{%- if variant.description %}
|
| 60 |
+
{{- "// " + variant.description }}
|
| 61 |
+
{%- endif -%}
|
| 62 |
+
{%- if variant.default is defined %}
|
| 63 |
+
{{ "// default: " + variant.default|tojson }}
|
| 64 |
+
{%- endif -%}
|
| 65 |
+
{%- if not loop.last %}
|
| 66 |
+
{{- " | " }}
|
| 67 |
+
{% endif -%}
|
| 68 |
+
{%- endfor -%}
|
| 69 |
+
{%- endif -%}
|
| 70 |
+
{%- elif param_spec.type == "string" -%}
|
| 71 |
+
{%- if param_spec.enum -%}
|
| 72 |
+
{{- '"' + param_spec.enum|join('" | "') + '"' -}}
|
| 73 |
+
{%- else -%}
|
| 74 |
+
{{- "string" }}
|
| 75 |
+
{%- if param_spec.nullable %}
|
| 76 |
+
{{- " | null" }}
|
| 77 |
+
{%- endif -%}
|
| 78 |
+
{%- endif -%}
|
| 79 |
+
{%- elif param_spec.type == "number" -%}
|
| 80 |
+
{{- "number" }}
|
| 81 |
+
{%- elif param_spec.type == "integer" -%}
|
| 82 |
+
{{- "number" }}
|
| 83 |
+
{%- elif param_spec.type == "boolean" -%}
|
| 84 |
+
{{- "boolean" }}
|
| 85 |
+
|
| 86 |
+
{%- elif param_spec.type == "object" -%}
|
| 87 |
+
{%- if param_spec.properties -%}
|
| 88 |
+
{{- "{\n" }}
|
| 89 |
+
{%- for prop_name, prop_spec in param_spec.properties.items() -%}
|
| 90 |
+
{{- prop_name -}}
|
| 91 |
+
{%- if prop_name not in (param_spec.required or []) -%}
|
| 92 |
+
{{- "?" }}
|
| 93 |
+
{%- endif -%}
|
| 94 |
+
{{- ": " }}
|
| 95 |
+
{{ render_typescript_type(prop_spec, param_spec.required or []) }}
|
| 96 |
+
{%- if not loop.last -%}
|
| 97 |
+
{{-", " }}
|
| 98 |
+
{%- endif -%}
|
| 99 |
+
{%- endfor -%}
|
| 100 |
+
{{- "}" }}
|
| 101 |
+
{%- else -%}
|
| 102 |
+
{{- "object" }}
|
| 103 |
+
{%- endif -%}
|
| 104 |
+
{%- else -%}
|
| 105 |
+
{{- "any" }}
|
| 106 |
+
{%- endif -%}
|
| 107 |
+
{%- endmacro -%}
|
| 108 |
+
|
| 109 |
+
{%- macro render_tool_namespace(namespace_name, tools) -%}
|
| 110 |
+
{{- "## " + namespace_name + "\n\n" }}
|
| 111 |
+
{{- "namespace " + namespace_name + " {\n\n" }}
|
| 112 |
+
{%- for tool in tools %}
|
| 113 |
+
{%- set tool = tool.function %}
|
| 114 |
+
{{- "// " + tool.description + "\n" }}
|
| 115 |
+
{{- "type "+ tool.name + " = " }}
|
| 116 |
+
{%- if tool.parameters and tool.parameters.properties -%}
|
| 117 |
+
{{- "(_: " }}
|
| 118 |
+
{{- "{\n" }}
|
| 119 |
+
{%- for param_name, param_spec in tool.parameters.properties.items() %}
|
| 120 |
+
{{- "// " + param_spec.description + "\n" }}
|
| 121 |
+
{{- param_name }}
|
| 122 |
+
{%- if param_name not in (tool.parameters.required or []) -%}
|
| 123 |
+
{{- "?" }}
|
| 124 |
+
{%- endif -%}
|
| 125 |
+
{{- ": " }}
|
| 126 |
+
{{- render_typescript_type(param_spec, tool.parameters.required or []) }}
|
| 127 |
+
{%- if param_spec.default is defined -%}
|
| 128 |
+
{%- if param_spec.enum %}
|
| 129 |
+
{{- ", // default: " + param_spec.default }}
|
| 130 |
+
{%- elif param_spec.oneOf %}
|
| 131 |
+
{{- "// default: " + param_spec.default }}
|
| 132 |
+
{%- else %}
|
| 133 |
+
{{- ", // default: " + param_spec.default|tojson }}
|
| 134 |
+
{%- endif -%}
|
| 135 |
+
{%- endif -%}
|
| 136 |
+
{%- if not loop.last %}
|
| 137 |
+
{{- ",\n" }}
|
| 138 |
+
{%- else %}
|
| 139 |
+
{{- "\n" }}
|
| 140 |
+
{%- endif -%}
|
| 141 |
+
{%- endfor %}
|
| 142 |
+
{{- "}) => any;\n\n" }}
|
| 143 |
+
{%- else -%}
|
| 144 |
+
{{- "() => any;\n\n" }}
|
| 145 |
+
{%- endif -%}
|
| 146 |
+
{%- endfor %}
|
| 147 |
+
{{- "} // namespace " + namespace_name }}
|
| 148 |
+
{%- endmacro -%}
|
| 149 |
+
|
| 150 |
+
{%- macro render_builtin_tools(browser_tool, python_tool) -%}
|
| 151 |
+
{%- if browser_tool %}
|
| 152 |
+
{{- "## browser\n\n" }}
|
| 153 |
+
{{- "// Tool for browsing.\n" }}
|
| 154 |
+
{{- "// The `cursor` appears in brackets before each browsing display: `[{cursor}]`.\n" }}
|
| 155 |
+
{{- "// Cite information from the tool using the following format:\n" }}
|
| 156 |
+
{{- "// `【{cursor}†L{line_start}(-L{line_end})?】`, for example: `【6†L9-L11】` or `【8†L3】`.\n" }}
|
| 157 |
+
{{- "// Do not quote more than 10 words directly from the tool output.\n" }}
|
| 158 |
+
{{- "// sources=web (default: web)\n" }}
|
| 159 |
+
{{- "namespace browser {\n\n" }}
|
| 160 |
+
{{- "// Searches for information related to `query` and displays `topn` results.\n" }}
|
| 161 |
+
{{- "type search = (_: {\n" }}
|
| 162 |
+
{{- "query: string,\n" }}
|
| 163 |
+
{{- "topn?: number, // default: 10\n" }}
|
| 164 |
+
{{- "source?: string,\n" }}
|
| 165 |
+
{{- "}) => any;\n\n" }}
|
| 166 |
+
{{- "// Opens the link `id` from the page indicated by `cursor` starting at line number `loc`, showing `num_lines` lines.\n" }}
|
| 167 |
+
{{- "// Valid link ids are displayed with the formatting: `【{id}†.*】`.\n" }}
|
| 168 |
+
{{- "// If `cursor` is not provided, the most recent page is implied.\n" }}
|
| 169 |
+
{{- "// If `id` is a string, it is treated as a fully qualified URL associated with `source`.\n" }}
|
| 170 |
+
{{- "// If `loc` is not provided, the viewport will be positioned at the beginning of the document or centered on the most relevant passage, if available.\n" }}
|
| 171 |
+
{{- "// Use this function without `id` to scroll to a new location of an opened page.\n" }}
|
| 172 |
+
{{- "type open = (_: {\n" }}
|
| 173 |
+
{{- "id?: number | string, // default: -1\n" }}
|
| 174 |
+
{{- "cursor?: number, // default: -1\n" }}
|
| 175 |
+
{{- "loc?: number, // default: -1\n" }}
|
| 176 |
+
{{- "num_lines?: number, // default: -1\n" }}
|
| 177 |
+
{{- "view_source?: boolean, // default: false\n" }}
|
| 178 |
+
{{- "source?: string,\n" }}
|
| 179 |
+
{{- "}) => any;\n\n" }}
|
| 180 |
+
{{- "// Finds exact matches of `pattern` in the current page, or the page given by `cursor`.\n" }}
|
| 181 |
+
{{- "type find = (_: {\n" }}
|
| 182 |
+
{{- "pattern: string,\n" }}
|
| 183 |
+
{{- "cursor?: number, // default: -1\n" }}
|
| 184 |
+
{{- "}) => any;\n\n" }}
|
| 185 |
+
{{- "} // namespace browser\n\n" }}
|
| 186 |
+
{%- endif -%}
|
| 187 |
+
|
| 188 |
+
{%- if python_tool %}
|
| 189 |
+
{{- "## python\n\n" }}
|
| 190 |
+
{{- "Use this tool to execute Python code in your chain of thought. The code will not be shown to the user. This tool should be used for internal reasoning, but not for code that is intended to be visible to the user (e.g. when creating plots, tables, or files).\n\n" }}
|
| 191 |
+
{{- "When you send a message containing Python code to python, it will be executed in a stateful Jupyter notebook environment. python will respond with the output of the execution or time out after 120.0 seconds. The drive at '/mnt/data' can be used to save and persist user files. Internet access for this session is UNKNOWN. Depends on the cluster.\n\n" }}
|
| 192 |
+
{%- endif -%}
|
| 193 |
+
{%- endmacro -%}
|
| 194 |
+
|
| 195 |
+
{#- System Message Construction ============================================ #}
|
| 196 |
+
{%- macro build_system_message() -%}
|
| 197 |
+
{%- if model_identity is not defined %}
|
| 198 |
+
{{- "You are ChatGPT, a large language model trained by OpenAI.\n" -}}
|
| 199 |
+
{%- else %}
|
| 200 |
+
{{- model_identity }}
|
| 201 |
+
{%- endif %}
|
| 202 |
+
{{- "Knowledge cutoff: 2024-06\n" }}
|
| 203 |
+
{{- "Current date: " + strftime_now("%Y-%m-%d") + "\n\n" }}
|
| 204 |
+
{%- if reasoning_effort is not defined %}
|
| 205 |
+
{%- set reasoning_effort = "medium" %}
|
| 206 |
+
{%- endif %}
|
| 207 |
+
{{- "Reasoning: " + reasoning_effort + "\n\n" }}
|
| 208 |
+
{%- if builtin_tools is defined %}
|
| 209 |
+
{{- "# Tools\n\n" }}
|
| 210 |
+
{%- set available_builtin_tools = namespace(browser=false, python=false) %}
|
| 211 |
+
{%- for tool in builtin_tools %}
|
| 212 |
+
{%- if tool == "browser" %}
|
| 213 |
+
{%- set available_builtin_tools.browser = true %}
|
| 214 |
+
{%- elif tool == "python" %}
|
| 215 |
+
{%- set available_builtin_tools.python = true %}
|
| 216 |
+
{%- endif %}
|
| 217 |
+
{%- endfor %}
|
| 218 |
+
{{- render_builtin_tools(available_builtin_tools.browser, available_builtin_tools.python) }}
|
| 219 |
+
{%- endif -%}
|
| 220 |
+
{{- "# Valid channels: analysis, commentary, final. Channel must be included for every message." }}
|
| 221 |
+
{%- if tools is defined -%}
|
| 222 |
+
{{- "\nCalls to these tools must go to the commentary channel: 'functions'." }}
|
| 223 |
+
{%- endif -%}
|
| 224 |
+
{%- endmacro -%}
|
| 225 |
+
|
| 226 |
+
{#- Main Template Logic ================================================= #}
|
| 227 |
+
{#- Set defaults #}
|
| 228 |
+
|
| 229 |
+
{#- Render system message #}
|
| 230 |
+
{{- "<|start|>system<|message|>" }}
|
| 231 |
+
{{- build_system_message() }}
|
| 232 |
+
{{- "<|end|>" }}
|
| 233 |
+
|
| 234 |
+
{#- Extract developer message #}
|
| 235 |
+
{%- if messages[0].role == "developer" or messages[0].role == "system" %}
|
| 236 |
+
{%- set developer_message = messages[0].content %}
|
| 237 |
+
{%- set loop_messages = messages[1:] %}
|
| 238 |
+
{%- else %}
|
| 239 |
+
{%- set developer_message = "" %}
|
| 240 |
+
{%- set loop_messages = messages %}
|
| 241 |
+
{%- endif %}
|
| 242 |
+
|
| 243 |
+
{#- Render developer message #}
|
| 244 |
+
{%- if developer_message or tools %}
|
| 245 |
+
{{- "<|start|>developer<|message|>" }}
|
| 246 |
+
{%- if developer_message %}
|
| 247 |
+
{{- "# Instructions\n\n" }}
|
| 248 |
+
{{- developer_message }}
|
| 249 |
+
{%- endif %}
|
| 250 |
+
{%- if tools -%}
|
| 251 |
+
{{- "\n\n" }}
|
| 252 |
+
{{- "# Tools\n\n" }}
|
| 253 |
+
{{- render_tool_namespace("functions", tools) }}
|
| 254 |
+
{%- endif -%}
|
| 255 |
+
{{- "<|end|>" }}
|
| 256 |
+
{%- endif %}
|
| 257 |
+
|
| 258 |
+
{#- Render messages #}
|
| 259 |
+
{%- set last_tool_call = namespace(name=none) %}
|
| 260 |
+
{%- for message in loop_messages -%}
|
| 261 |
+
{#- At this point only assistant/user/tool messages should remain #}
|
| 262 |
+
{%- if message.role == 'assistant' -%}
|
| 263 |
+
{%- if "tool_calls" in message %}
|
| 264 |
+
{#- We assume max 1 tool call per message, and so we infer the tool call name #}
|
| 265 |
+
{#- in "tool" messages from the most recent assistant tool call name #}
|
| 266 |
+
{%- set tool_call = message.tool_calls[0] %}
|
| 267 |
+
{%- if tool_call.function %}
|
| 268 |
+
{%- set tool_call = tool_call.function %}
|
| 269 |
+
{%- endif %}
|
| 270 |
+
{%- if message.content %}
|
| 271 |
+
{{- "<|start|>assistant<|channel|>analysis<|message|>" + message.content + "<|end|>" }}
|
| 272 |
+
{%- endif %}
|
| 273 |
+
{{- "<|start|>assistant to=" }}
|
| 274 |
+
{{- "functions." + tool_call.name + "<|channel|>commentary json<|message|>" }}
|
| 275 |
+
{{- tool_call.arguments|tojson }}
|
| 276 |
+
{{- "<|call|>" }}
|
| 277 |
+
{%- set last_tool_call.name = tool_call.name %}
|
| 278 |
+
{%- elif "thinking" in message and loop.last and not add_generation_prompt %}
|
| 279 |
+
{#- Only render the CoT if the final turn is an assistant turn and add_generation_prompt is false #}
|
| 280 |
+
{#- This is a situation that should only occur in training, never in inference. #}
|
| 281 |
+
{{- "<|start|>assistant<|channel|>analysis<|message|>" + message.thinking + "<|end|>" }}
|
| 282 |
+
{#- <|return|> indicates the end of generation, but <|end|> does not #}
|
| 283 |
+
{#- <|return|> should never be an input to the model, but we include it as the final token #}
|
| 284 |
+
{#- when training, so the model learns to emit it. #}
|
| 285 |
+
{{- "<|start|>assistant<|channel|>final<|message|>" + message.content + "<|return|>" }}
|
| 286 |
+
{%- set last_tool_call.name = none %}
|
| 287 |
+
{%- elif "thinking" in message %}
|
| 288 |
+
{#- CoT is dropped during all previous turns, so we never render it for inference #}
|
| 289 |
+
{{- "<|start|>assistant<|channel|>final<|message|>" + message.content + "<|end|>" }}
|
| 290 |
+
{%- set last_tool_call.name = none %}
|
| 291 |
+
{%- elif loop.last and not add_generation_prompt %}
|
| 292 |
+
{#- <|return|> indicates the end of generation, but <|end|> does not #}
|
| 293 |
+
{#- <|return|> should never be an input to the model, but we include it as the final token #}
|
| 294 |
+
{#- when training, so the model learns to emit it. #}
|
| 295 |
+
{{- "<|start|>assistant<|message|>" + message.content + "<|return|>" }}
|
| 296 |
+
{%- else %}
|
| 297 |
+
{{- "<|start|>assistant<|message|>" + message.content + "<|end|>" }}
|
| 298 |
+
{%- set last_tool_call.name = none %}
|
| 299 |
+
{%- endif %}
|
| 300 |
+
{%- elif message.role == 'tool' -%}
|
| 301 |
+
{%- if last_tool_call.name is none %}
|
| 302 |
+
{{- raise_exception("Message has tool role, but there was no previous assistant message with a tool call!") }}
|
| 303 |
+
{%- endif %}
|
| 304 |
+
{{- "<|start|>functions." + last_tool_call.name }}
|
| 305 |
+
{{- " to=assistant<|channel|>commentary<|message|>" + message.content|tojson + "<|end|>" }}
|
| 306 |
+
{%- else -%}
|
| 307 |
+
{{- "<|start|>user<|message|>" + message.content + "<|end|>" }}
|
| 308 |
+
{%- endif -%}
|
| 309 |
+
{%- endfor -%}
|
| 310 |
+
|
| 311 |
+
{#- Generation prompt #}
|
| 312 |
+
{%- if add_generation_prompt -%}
|
| 313 |
+
<|start|>assistant
|
| 314 |
+
{%- endif -%}
|
| 315 |
+
{# Copyright 2025-present Unsloth. Apache 2.0 License. Unsloth chat template fixes. Edited from ggml-org & OpenAI #}
|
checkpoint-280/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:399b32fc659286c8db27ae4fe9b37de20db040e85f9c37ac244b296dcaddfbba
|
| 3 |
+
size 2951883
|
checkpoint-280/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:822b52eca5513225c20a0f93bb04a3754540e1959100314b16adbbded506b313
|
| 3 |
+
size 14581
|
checkpoint-280/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f3878413335ed28f62ee01e8e82b6216a4499ded9ebb2fa0a38627a4678f0a54
|
| 3 |
+
size 1465
|
checkpoint-280/special_tokens_map.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<|startoftext|>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "<|return|>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "<|reserved_200017|>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
}
|
| 23 |
+
}
|
checkpoint-280/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0614fe83cadab421296e664e1f48f4261fa8fef6e03e63bb75c20f38e37d07d3
|
| 3 |
+
size 27868174
|
checkpoint-280/tokenizer_config.json
ADDED
|
@@ -0,0 +1,185 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"199998": {
|
| 4 |
+
"content": "<|startoftext|>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"199999": {
|
| 12 |
+
"content": "<|endoftext|>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"200000": {
|
| 20 |
+
"content": "<|reserved_200000|>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"200001": {
|
| 28 |
+
"content": "<|reserved_200001|>",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"200002": {
|
| 36 |
+
"content": "<|return|>",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
},
|
| 43 |
+
"200003": {
|
| 44 |
+
"content": "<|constrain|>",
|
| 45 |
+
"lstrip": false,
|
| 46 |
+
"normalized": false,
|
| 47 |
+
"rstrip": false,
|
| 48 |
+
"single_word": false,
|
| 49 |
+
"special": true
|
| 50 |
+
},
|
| 51 |
+
"200004": {
|
| 52 |
+
"content": "<|reserved_200004|>",
|
| 53 |
+
"lstrip": false,
|
| 54 |
+
"normalized": false,
|
| 55 |
+
"rstrip": false,
|
| 56 |
+
"single_word": false,
|
| 57 |
+
"special": true
|
| 58 |
+
},
|
| 59 |
+
"200005": {
|
| 60 |
+
"content": "<|channel|>",
|
| 61 |
+
"lstrip": false,
|
| 62 |
+
"normalized": false,
|
| 63 |
+
"rstrip": false,
|
| 64 |
+
"single_word": false,
|
| 65 |
+
"special": true
|
| 66 |
+
},
|
| 67 |
+
"200006": {
|
| 68 |
+
"content": "<|start|>",
|
| 69 |
+
"lstrip": false,
|
| 70 |
+
"normalized": false,
|
| 71 |
+
"rstrip": false,
|
| 72 |
+
"single_word": false,
|
| 73 |
+
"special": true
|
| 74 |
+
},
|
| 75 |
+
"200007": {
|
| 76 |
+
"content": "<|end|>",
|
| 77 |
+
"lstrip": false,
|
| 78 |
+
"normalized": false,
|
| 79 |
+
"rstrip": false,
|
| 80 |
+
"single_word": false,
|
| 81 |
+
"special": true
|
| 82 |
+
},
|
| 83 |
+
"200008": {
|
| 84 |
+
"content": "<|message|>",
|
| 85 |
+
"lstrip": false,
|
| 86 |
+
"normalized": false,
|
| 87 |
+
"rstrip": false,
|
| 88 |
+
"single_word": false,
|
| 89 |
+
"special": true
|
| 90 |
+
},
|
| 91 |
+
"200009": {
|
| 92 |
+
"content": "<|reserved_200009|>",
|
| 93 |
+
"lstrip": false,
|
| 94 |
+
"normalized": false,
|
| 95 |
+
"rstrip": false,
|
| 96 |
+
"single_word": false,
|
| 97 |
+
"special": true
|
| 98 |
+
},
|
| 99 |
+
"200010": {
|
| 100 |
+
"content": "<|reserved_200010|>",
|
| 101 |
+
"lstrip": false,
|
| 102 |
+
"normalized": false,
|
| 103 |
+
"rstrip": false,
|
| 104 |
+
"single_word": false,
|
| 105 |
+
"special": true
|
| 106 |
+
},
|
| 107 |
+
"200011": {
|
| 108 |
+
"content": "<|reserved_200011|>",
|
| 109 |
+
"lstrip": false,
|
| 110 |
+
"normalized": false,
|
| 111 |
+
"rstrip": false,
|
| 112 |
+
"single_word": false,
|
| 113 |
+
"special": true
|
| 114 |
+
},
|
| 115 |
+
"200012": {
|
| 116 |
+
"content": "<|call|>",
|
| 117 |
+
"lstrip": false,
|
| 118 |
+
"normalized": false,
|
| 119 |
+
"rstrip": false,
|
| 120 |
+
"single_word": false,
|
| 121 |
+
"special": true
|
| 122 |
+
},
|
| 123 |
+
"200013": {
|
| 124 |
+
"content": "<|reserved_200013|>",
|
| 125 |
+
"lstrip": false,
|
| 126 |
+
"normalized": false,
|
| 127 |
+
"rstrip": false,
|
| 128 |
+
"single_word": false,
|
| 129 |
+
"special": true
|
| 130 |
+
},
|
| 131 |
+
"200014": {
|
| 132 |
+
"content": "<|reserved_200014|>",
|
| 133 |
+
"lstrip": false,
|
| 134 |
+
"normalized": false,
|
| 135 |
+
"rstrip": false,
|
| 136 |
+
"single_word": false,
|
| 137 |
+
"special": true
|
| 138 |
+
},
|
| 139 |
+
"200015": {
|
| 140 |
+
"content": "<|reserved_200015|>",
|
| 141 |
+
"lstrip": false,
|
| 142 |
+
"normalized": false,
|
| 143 |
+
"rstrip": false,
|
| 144 |
+
"single_word": false,
|
| 145 |
+
"special": true
|
| 146 |
+
},
|
| 147 |
+
"200016": {
|
| 148 |
+
"content": "<|reserved_200016|>",
|
| 149 |
+
"lstrip": false,
|
| 150 |
+
"normalized": false,
|
| 151 |
+
"rstrip": false,
|
| 152 |
+
"single_word": false,
|
| 153 |
+
"special": true
|
| 154 |
+
},
|
| 155 |
+
"200017": {
|
| 156 |
+
"content": "<|reserved_200017|>",
|
| 157 |
+
"lstrip": false,
|
| 158 |
+
"normalized": false,
|
| 159 |
+
"rstrip": false,
|
| 160 |
+
"single_word": false,
|
| 161 |
+
"special": true
|
| 162 |
+
},
|
| 163 |
+
"200018": {
|
| 164 |
+
"content": "<|endofprompt|>",
|
| 165 |
+
"lstrip": false,
|
| 166 |
+
"normalized": false,
|
| 167 |
+
"rstrip": false,
|
| 168 |
+
"single_word": false,
|
| 169 |
+
"special": true
|
| 170 |
+
}
|
| 171 |
+
},
|
| 172 |
+
"bos_token": "<|startoftext|>",
|
| 173 |
+
"clean_up_tokenization_spaces": false,
|
| 174 |
+
"eos_token": "<|return|>",
|
| 175 |
+
"extra_special_tokens": {},
|
| 176 |
+
"model_input_names": [
|
| 177 |
+
"input_ids",
|
| 178 |
+
"attention_mask"
|
| 179 |
+
],
|
| 180 |
+
"model_max_length": 131072,
|
| 181 |
+
"pad_token": "<|reserved_200017|>",
|
| 182 |
+
"padding_side": "right",
|
| 183 |
+
"tokenizer_class": "PreTrainedTokenizerFast",
|
| 184 |
+
"unk_token": null
|
| 185 |
+
}
|
checkpoint-280/trainer_state.json
ADDED
|
@@ -0,0 +1,2218 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.7466666666666667,
|
| 6 |
+
"eval_steps": 10,
|
| 7 |
+
"global_step": 280,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.0026666666666666666,
|
| 14 |
+
"grad_norm": 932.6458129882812,
|
| 15 |
+
"learning_rate": 0.0,
|
| 16 |
+
"loss": 16.4322,
|
| 17 |
+
"step": 1
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.005333333333333333,
|
| 21 |
+
"grad_norm": 906.1286010742188,
|
| 22 |
+
"learning_rate": 2.0000000000000003e-06,
|
| 23 |
+
"loss": 17.1074,
|
| 24 |
+
"step": 2
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.008,
|
| 28 |
+
"grad_norm": 957.1098022460938,
|
| 29 |
+
"learning_rate": 4.000000000000001e-06,
|
| 30 |
+
"loss": 16.2636,
|
| 31 |
+
"step": 3
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.010666666666666666,
|
| 35 |
+
"grad_norm": 999.4998779296875,
|
| 36 |
+
"learning_rate": 6e-06,
|
| 37 |
+
"loss": 16.7171,
|
| 38 |
+
"step": 4
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.013333333333333334,
|
| 42 |
+
"grad_norm": 952.225341796875,
|
| 43 |
+
"learning_rate": 8.000000000000001e-06,
|
| 44 |
+
"loss": 16.0368,
|
| 45 |
+
"step": 5
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.016,
|
| 49 |
+
"grad_norm": 967.4716186523438,
|
| 50 |
+
"learning_rate": 1e-05,
|
| 51 |
+
"loss": 15.3585,
|
| 52 |
+
"step": 6
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.018666666666666668,
|
| 56 |
+
"grad_norm": 1014.7380981445312,
|
| 57 |
+
"learning_rate": 9.972972972972975e-06,
|
| 58 |
+
"loss": 14.1371,
|
| 59 |
+
"step": 7
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.021333333333333333,
|
| 63 |
+
"grad_norm": 1001.39404296875,
|
| 64 |
+
"learning_rate": 9.945945945945947e-06,
|
| 65 |
+
"loss": 12.4417,
|
| 66 |
+
"step": 8
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.024,
|
| 70 |
+
"grad_norm": 956.663818359375,
|
| 71 |
+
"learning_rate": 9.91891891891892e-06,
|
| 72 |
+
"loss": 11.2694,
|
| 73 |
+
"step": 9
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.02666666666666667,
|
| 77 |
+
"grad_norm": 851.0857543945312,
|
| 78 |
+
"learning_rate": 9.891891891891893e-06,
|
| 79 |
+
"loss": 10.1807,
|
| 80 |
+
"step": 10
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.02666666666666667,
|
| 84 |
+
"eval_loss": 8.908344268798828,
|
| 85 |
+
"eval_runtime": 6.3541,
|
| 86 |
+
"eval_samples_per_second": 4.721,
|
| 87 |
+
"eval_steps_per_second": 2.361,
|
| 88 |
+
"step": 10
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 0.029333333333333333,
|
| 92 |
+
"grad_norm": 689.436767578125,
|
| 93 |
+
"learning_rate": 9.864864864864865e-06,
|
| 94 |
+
"loss": 8.85,
|
| 95 |
+
"step": 11
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 0.032,
|
| 99 |
+
"grad_norm": 591.1151123046875,
|
| 100 |
+
"learning_rate": 9.83783783783784e-06,
|
| 101 |
+
"loss": 8.4188,
|
| 102 |
+
"step": 12
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 0.034666666666666665,
|
| 106 |
+
"grad_norm": 414.6604919433594,
|
| 107 |
+
"learning_rate": 9.810810810810811e-06,
|
| 108 |
+
"loss": 7.1033,
|
| 109 |
+
"step": 13
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 0.037333333333333336,
|
| 113 |
+
"grad_norm": 339.56982421875,
|
| 114 |
+
"learning_rate": 9.783783783783785e-06,
|
| 115 |
+
"loss": 7.1921,
|
| 116 |
+
"step": 14
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.04,
|
| 120 |
+
"grad_norm": 304.45819091796875,
|
| 121 |
+
"learning_rate": 9.756756756756758e-06,
|
| 122 |
+
"loss": 6.5019,
|
| 123 |
+
"step": 15
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.042666666666666665,
|
| 127 |
+
"grad_norm": 244.03823852539062,
|
| 128 |
+
"learning_rate": 9.729729729729732e-06,
|
| 129 |
+
"loss": 6.4202,
|
| 130 |
+
"step": 16
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 0.04533333333333334,
|
| 134 |
+
"grad_norm": 204.49368286132812,
|
| 135 |
+
"learning_rate": 9.702702702702704e-06,
|
| 136 |
+
"loss": 5.91,
|
| 137 |
+
"step": 17
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 0.048,
|
| 141 |
+
"grad_norm": 162.0959014892578,
|
| 142 |
+
"learning_rate": 9.675675675675676e-06,
|
| 143 |
+
"loss": 5.9435,
|
| 144 |
+
"step": 18
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 0.050666666666666665,
|
| 148 |
+
"grad_norm": 160.5931396484375,
|
| 149 |
+
"learning_rate": 9.64864864864865e-06,
|
| 150 |
+
"loss": 5.6556,
|
| 151 |
+
"step": 19
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 0.05333333333333334,
|
| 155 |
+
"grad_norm": 146.50758361816406,
|
| 156 |
+
"learning_rate": 9.621621621621622e-06,
|
| 157 |
+
"loss": 5.459,
|
| 158 |
+
"step": 20
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 0.05333333333333334,
|
| 162 |
+
"eval_loss": 5.419591426849365,
|
| 163 |
+
"eval_runtime": 2.1235,
|
| 164 |
+
"eval_samples_per_second": 14.127,
|
| 165 |
+
"eval_steps_per_second": 7.064,
|
| 166 |
+
"step": 20
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 0.056,
|
| 170 |
+
"grad_norm": 131.01402282714844,
|
| 171 |
+
"learning_rate": 9.594594594594594e-06,
|
| 172 |
+
"loss": 5.5075,
|
| 173 |
+
"step": 21
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 0.058666666666666666,
|
| 177 |
+
"grad_norm": 130.70143127441406,
|
| 178 |
+
"learning_rate": 9.567567567567568e-06,
|
| 179 |
+
"loss": 5.2305,
|
| 180 |
+
"step": 22
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 0.06133333333333333,
|
| 184 |
+
"grad_norm": 118.18517303466797,
|
| 185 |
+
"learning_rate": 9.540540540540542e-06,
|
| 186 |
+
"loss": 5.0906,
|
| 187 |
+
"step": 23
|
| 188 |
+
},
|
| 189 |
+
{
|
| 190 |
+
"epoch": 0.064,
|
| 191 |
+
"grad_norm": 117.36890411376953,
|
| 192 |
+
"learning_rate": 9.513513513513514e-06,
|
| 193 |
+
"loss": 4.939,
|
| 194 |
+
"step": 24
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 0.06666666666666667,
|
| 198 |
+
"grad_norm": 116.87814331054688,
|
| 199 |
+
"learning_rate": 9.486486486486487e-06,
|
| 200 |
+
"loss": 4.7326,
|
| 201 |
+
"step": 25
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 0.06933333333333333,
|
| 205 |
+
"grad_norm": 113.54383850097656,
|
| 206 |
+
"learning_rate": 9.45945945945946e-06,
|
| 207 |
+
"loss": 4.812,
|
| 208 |
+
"step": 26
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 0.072,
|
| 212 |
+
"grad_norm": 104.74027252197266,
|
| 213 |
+
"learning_rate": 9.432432432432433e-06,
|
| 214 |
+
"loss": 4.6992,
|
| 215 |
+
"step": 27
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 0.07466666666666667,
|
| 219 |
+
"grad_norm": 93.894287109375,
|
| 220 |
+
"learning_rate": 9.405405405405407e-06,
|
| 221 |
+
"loss": 4.2069,
|
| 222 |
+
"step": 28
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 0.07733333333333334,
|
| 226 |
+
"grad_norm": 97.65583801269531,
|
| 227 |
+
"learning_rate": 9.378378378378379e-06,
|
| 228 |
+
"loss": 4.323,
|
| 229 |
+
"step": 29
|
| 230 |
+
},
|
| 231 |
+
{
|
| 232 |
+
"epoch": 0.08,
|
| 233 |
+
"grad_norm": 96.1834487915039,
|
| 234 |
+
"learning_rate": 9.351351351351353e-06,
|
| 235 |
+
"loss": 4.2722,
|
| 236 |
+
"step": 30
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 0.08,
|
| 240 |
+
"eval_loss": 4.122442245483398,
|
| 241 |
+
"eval_runtime": 2.1149,
|
| 242 |
+
"eval_samples_per_second": 14.185,
|
| 243 |
+
"eval_steps_per_second": 7.092,
|
| 244 |
+
"step": 30
|
| 245 |
+
},
|
| 246 |
+
{
|
| 247 |
+
"epoch": 0.08266666666666667,
|
| 248 |
+
"grad_norm": 85.94340515136719,
|
| 249 |
+
"learning_rate": 9.324324324324325e-06,
|
| 250 |
+
"loss": 4.0937,
|
| 251 |
+
"step": 31
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 0.08533333333333333,
|
| 255 |
+
"grad_norm": 83.52753448486328,
|
| 256 |
+
"learning_rate": 9.297297297297299e-06,
|
| 257 |
+
"loss": 3.917,
|
| 258 |
+
"step": 32
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 0.088,
|
| 262 |
+
"grad_norm": 78.75122833251953,
|
| 263 |
+
"learning_rate": 9.270270270270271e-06,
|
| 264 |
+
"loss": 3.7462,
|
| 265 |
+
"step": 33
|
| 266 |
+
},
|
| 267 |
+
{
|
| 268 |
+
"epoch": 0.09066666666666667,
|
| 269 |
+
"grad_norm": 78.64039611816406,
|
| 270 |
+
"learning_rate": 9.243243243243243e-06,
|
| 271 |
+
"loss": 3.8485,
|
| 272 |
+
"step": 34
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 0.09333333333333334,
|
| 276 |
+
"grad_norm": 76.619384765625,
|
| 277 |
+
"learning_rate": 9.216216216216217e-06,
|
| 278 |
+
"loss": 3.8375,
|
| 279 |
+
"step": 35
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 0.096,
|
| 283 |
+
"grad_norm": 67.17459869384766,
|
| 284 |
+
"learning_rate": 9.189189189189191e-06,
|
| 285 |
+
"loss": 3.6146,
|
| 286 |
+
"step": 36
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 0.09866666666666667,
|
| 290 |
+
"grad_norm": 77.51924896240234,
|
| 291 |
+
"learning_rate": 9.162162162162162e-06,
|
| 292 |
+
"loss": 3.5797,
|
| 293 |
+
"step": 37
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 0.10133333333333333,
|
| 297 |
+
"grad_norm": 65.51860046386719,
|
| 298 |
+
"learning_rate": 9.135135135135136e-06,
|
| 299 |
+
"loss": 3.4923,
|
| 300 |
+
"step": 38
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 0.104,
|
| 304 |
+
"grad_norm": 59.56484603881836,
|
| 305 |
+
"learning_rate": 9.10810810810811e-06,
|
| 306 |
+
"loss": 3.3492,
|
| 307 |
+
"step": 39
|
| 308 |
+
},
|
| 309 |
+
{
|
| 310 |
+
"epoch": 0.10666666666666667,
|
| 311 |
+
"grad_norm": 61.95277404785156,
|
| 312 |
+
"learning_rate": 9.081081081081082e-06,
|
| 313 |
+
"loss": 3.208,
|
| 314 |
+
"step": 40
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 0.10666666666666667,
|
| 318 |
+
"eval_loss": 3.2251017093658447,
|
| 319 |
+
"eval_runtime": 2.108,
|
| 320 |
+
"eval_samples_per_second": 14.231,
|
| 321 |
+
"eval_steps_per_second": 7.116,
|
| 322 |
+
"step": 40
|
| 323 |
+
},
|
| 324 |
+
{
|
| 325 |
+
"epoch": 0.10933333333333334,
|
| 326 |
+
"grad_norm": 58.99920654296875,
|
| 327 |
+
"learning_rate": 9.054054054054054e-06,
|
| 328 |
+
"loss": 3.0812,
|
| 329 |
+
"step": 41
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 0.112,
|
| 333 |
+
"grad_norm": 51.660400390625,
|
| 334 |
+
"learning_rate": 9.027027027027028e-06,
|
| 335 |
+
"loss": 3.0894,
|
| 336 |
+
"step": 42
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 0.11466666666666667,
|
| 340 |
+
"grad_norm": 41.950157165527344,
|
| 341 |
+
"learning_rate": 9e-06,
|
| 342 |
+
"loss": 3.0536,
|
| 343 |
+
"step": 43
|
| 344 |
+
},
|
| 345 |
+
{
|
| 346 |
+
"epoch": 0.11733333333333333,
|
| 347 |
+
"grad_norm": 44.57719421386719,
|
| 348 |
+
"learning_rate": 8.972972972972974e-06,
|
| 349 |
+
"loss": 3.1747,
|
| 350 |
+
"step": 44
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 0.12,
|
| 354 |
+
"grad_norm": 44.626502990722656,
|
| 355 |
+
"learning_rate": 8.945945945945946e-06,
|
| 356 |
+
"loss": 2.9056,
|
| 357 |
+
"step": 45
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 0.12266666666666666,
|
| 361 |
+
"grad_norm": 46.089561462402344,
|
| 362 |
+
"learning_rate": 8.91891891891892e-06,
|
| 363 |
+
"loss": 2.8722,
|
| 364 |
+
"step": 46
|
| 365 |
+
},
|
| 366 |
+
{
|
| 367 |
+
"epoch": 0.12533333333333332,
|
| 368 |
+
"grad_norm": 39.88739013671875,
|
| 369 |
+
"learning_rate": 8.891891891891893e-06,
|
| 370 |
+
"loss": 2.7787,
|
| 371 |
+
"step": 47
|
| 372 |
+
},
|
| 373 |
+
{
|
| 374 |
+
"epoch": 0.128,
|
| 375 |
+
"grad_norm": 48.06010055541992,
|
| 376 |
+
"learning_rate": 8.864864864864866e-06,
|
| 377 |
+
"loss": 2.6416,
|
| 378 |
+
"step": 48
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 0.13066666666666665,
|
| 382 |
+
"grad_norm": 43.671119689941406,
|
| 383 |
+
"learning_rate": 8.837837837837839e-06,
|
| 384 |
+
"loss": 2.7215,
|
| 385 |
+
"step": 49
|
| 386 |
+
},
|
| 387 |
+
{
|
| 388 |
+
"epoch": 0.13333333333333333,
|
| 389 |
+
"grad_norm": 51.33174514770508,
|
| 390 |
+
"learning_rate": 8.810810810810811e-06,
|
| 391 |
+
"loss": 2.7913,
|
| 392 |
+
"step": 50
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 0.13333333333333333,
|
| 396 |
+
"eval_loss": 2.6058502197265625,
|
| 397 |
+
"eval_runtime": 2.1101,
|
| 398 |
+
"eval_samples_per_second": 14.217,
|
| 399 |
+
"eval_steps_per_second": 7.109,
|
| 400 |
+
"step": 50
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"epoch": 0.136,
|
| 404 |
+
"grad_norm": 34.640682220458984,
|
| 405 |
+
"learning_rate": 8.783783783783785e-06,
|
| 406 |
+
"loss": 2.554,
|
| 407 |
+
"step": 51
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 0.13866666666666666,
|
| 411 |
+
"grad_norm": 32.68441390991211,
|
| 412 |
+
"learning_rate": 8.756756756756759e-06,
|
| 413 |
+
"loss": 2.3897,
|
| 414 |
+
"step": 52
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 0.14133333333333334,
|
| 418 |
+
"grad_norm": 34.406028747558594,
|
| 419 |
+
"learning_rate": 8.72972972972973e-06,
|
| 420 |
+
"loss": 2.4736,
|
| 421 |
+
"step": 53
|
| 422 |
+
},
|
| 423 |
+
{
|
| 424 |
+
"epoch": 0.144,
|
| 425 |
+
"grad_norm": 38.37754821777344,
|
| 426 |
+
"learning_rate": 8.702702702702703e-06,
|
| 427 |
+
"loss": 2.4567,
|
| 428 |
+
"step": 54
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 0.14666666666666667,
|
| 432 |
+
"grad_norm": 37.39752197265625,
|
| 433 |
+
"learning_rate": 8.675675675675677e-06,
|
| 434 |
+
"loss": 2.5476,
|
| 435 |
+
"step": 55
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 0.14933333333333335,
|
| 439 |
+
"grad_norm": 32.165985107421875,
|
| 440 |
+
"learning_rate": 8.64864864864865e-06,
|
| 441 |
+
"loss": 2.3649,
|
| 442 |
+
"step": 56
|
| 443 |
+
},
|
| 444 |
+
{
|
| 445 |
+
"epoch": 0.152,
|
| 446 |
+
"grad_norm": 37.88535690307617,
|
| 447 |
+
"learning_rate": 8.621621621621622e-06,
|
| 448 |
+
"loss": 2.4366,
|
| 449 |
+
"step": 57
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 0.15466666666666667,
|
| 453 |
+
"grad_norm": 44.71893310546875,
|
| 454 |
+
"learning_rate": 8.594594594594595e-06,
|
| 455 |
+
"loss": 2.3843,
|
| 456 |
+
"step": 58
|
| 457 |
+
},
|
| 458 |
+
{
|
| 459 |
+
"epoch": 0.15733333333333333,
|
| 460 |
+
"grad_norm": 50.348106384277344,
|
| 461 |
+
"learning_rate": 8.567567567567568e-06,
|
| 462 |
+
"loss": 2.3169,
|
| 463 |
+
"step": 59
|
| 464 |
+
},
|
| 465 |
+
{
|
| 466 |
+
"epoch": 0.16,
|
| 467 |
+
"grad_norm": 39.178260803222656,
|
| 468 |
+
"learning_rate": 8.540540540540542e-06,
|
| 469 |
+
"loss": 2.15,
|
| 470 |
+
"step": 60
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 0.16,
|
| 474 |
+
"eval_loss": 2.204402208328247,
|
| 475 |
+
"eval_runtime": 1.4436,
|
| 476 |
+
"eval_samples_per_second": 20.781,
|
| 477 |
+
"eval_steps_per_second": 10.39,
|
| 478 |
+
"step": 60
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 0.16266666666666665,
|
| 482 |
+
"grad_norm": 31.640228271484375,
|
| 483 |
+
"learning_rate": 8.513513513513514e-06,
|
| 484 |
+
"loss": 2.292,
|
| 485 |
+
"step": 61
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.16533333333333333,
|
| 489 |
+
"grad_norm": 25.845205307006836,
|
| 490 |
+
"learning_rate": 8.486486486486488e-06,
|
| 491 |
+
"loss": 2.1367,
|
| 492 |
+
"step": 62
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 0.168,
|
| 496 |
+
"grad_norm": 24.244155883789062,
|
| 497 |
+
"learning_rate": 8.45945945945946e-06,
|
| 498 |
+
"loss": 2.2619,
|
| 499 |
+
"step": 63
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.17066666666666666,
|
| 503 |
+
"grad_norm": 27.788658142089844,
|
| 504 |
+
"learning_rate": 8.432432432432434e-06,
|
| 505 |
+
"loss": 2.0973,
|
| 506 |
+
"step": 64
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.17333333333333334,
|
| 510 |
+
"grad_norm": 22.125831604003906,
|
| 511 |
+
"learning_rate": 8.405405405405406e-06,
|
| 512 |
+
"loss": 2.0382,
|
| 513 |
+
"step": 65
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.176,
|
| 517 |
+
"grad_norm": 21.390626907348633,
|
| 518 |
+
"learning_rate": 8.378378378378378e-06,
|
| 519 |
+
"loss": 2.1409,
|
| 520 |
+
"step": 66
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 0.17866666666666667,
|
| 524 |
+
"grad_norm": 21.641523361206055,
|
| 525 |
+
"learning_rate": 8.351351351351352e-06,
|
| 526 |
+
"loss": 2.0422,
|
| 527 |
+
"step": 67
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.18133333333333335,
|
| 531 |
+
"grad_norm": 20.90644073486328,
|
| 532 |
+
"learning_rate": 8.324324324324326e-06,
|
| 533 |
+
"loss": 2.1016,
|
| 534 |
+
"step": 68
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.184,
|
| 538 |
+
"grad_norm": 23.33363151550293,
|
| 539 |
+
"learning_rate": 8.297297297297298e-06,
|
| 540 |
+
"loss": 2.1136,
|
| 541 |
+
"step": 69
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.18666666666666668,
|
| 545 |
+
"grad_norm": 18.258081436157227,
|
| 546 |
+
"learning_rate": 8.27027027027027e-06,
|
| 547 |
+
"loss": 1.973,
|
| 548 |
+
"step": 70
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 0.18666666666666668,
|
| 552 |
+
"eval_loss": 1.9927349090576172,
|
| 553 |
+
"eval_runtime": 1.4579,
|
| 554 |
+
"eval_samples_per_second": 20.577,
|
| 555 |
+
"eval_steps_per_second": 10.289,
|
| 556 |
+
"step": 70
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 0.18933333333333333,
|
| 560 |
+
"grad_norm": 18.579404830932617,
|
| 561 |
+
"learning_rate": 8.243243243243245e-06,
|
| 562 |
+
"loss": 2.0731,
|
| 563 |
+
"step": 71
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 0.192,
|
| 567 |
+
"grad_norm": 17.585365295410156,
|
| 568 |
+
"learning_rate": 8.216216216216217e-06,
|
| 569 |
+
"loss": 1.9039,
|
| 570 |
+
"step": 72
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 0.19466666666666665,
|
| 574 |
+
"grad_norm": 16.354633331298828,
|
| 575 |
+
"learning_rate": 8.189189189189189e-06,
|
| 576 |
+
"loss": 2.0146,
|
| 577 |
+
"step": 73
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 0.19733333333333333,
|
| 581 |
+
"grad_norm": 17.63299560546875,
|
| 582 |
+
"learning_rate": 8.162162162162163e-06,
|
| 583 |
+
"loss": 1.8823,
|
| 584 |
+
"step": 74
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 0.2,
|
| 588 |
+
"grad_norm": 16.70092010498047,
|
| 589 |
+
"learning_rate": 8.135135135135137e-06,
|
| 590 |
+
"loss": 1.8186,
|
| 591 |
+
"step": 75
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 0.20266666666666666,
|
| 595 |
+
"grad_norm": 16.694368362426758,
|
| 596 |
+
"learning_rate": 8.108108108108109e-06,
|
| 597 |
+
"loss": 1.8642,
|
| 598 |
+
"step": 76
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 0.20533333333333334,
|
| 602 |
+
"grad_norm": 16.945659637451172,
|
| 603 |
+
"learning_rate": 8.081081081081081e-06,
|
| 604 |
+
"loss": 1.832,
|
| 605 |
+
"step": 77
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 0.208,
|
| 609 |
+
"grad_norm": 14.920422554016113,
|
| 610 |
+
"learning_rate": 8.054054054054055e-06,
|
| 611 |
+
"loss": 1.8666,
|
| 612 |
+
"step": 78
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 0.21066666666666667,
|
| 616 |
+
"grad_norm": 15.18919563293457,
|
| 617 |
+
"learning_rate": 8.027027027027027e-06,
|
| 618 |
+
"loss": 1.8289,
|
| 619 |
+
"step": 79
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 0.21333333333333335,
|
| 623 |
+
"grad_norm": 16.04713249206543,
|
| 624 |
+
"learning_rate": 8.000000000000001e-06,
|
| 625 |
+
"loss": 1.8633,
|
| 626 |
+
"step": 80
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 0.21333333333333335,
|
| 630 |
+
"eval_loss": 1.8755805492401123,
|
| 631 |
+
"eval_runtime": 1.4512,
|
| 632 |
+
"eval_samples_per_second": 20.673,
|
| 633 |
+
"eval_steps_per_second": 10.336,
|
| 634 |
+
"step": 80
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 0.216,
|
| 638 |
+
"grad_norm": 17.620529174804688,
|
| 639 |
+
"learning_rate": 7.972972972972974e-06,
|
| 640 |
+
"loss": 1.9985,
|
| 641 |
+
"step": 81
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 0.21866666666666668,
|
| 645 |
+
"grad_norm": 13.032703399658203,
|
| 646 |
+
"learning_rate": 7.945945945945946e-06,
|
| 647 |
+
"loss": 1.8214,
|
| 648 |
+
"step": 82
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 0.22133333333333333,
|
| 652 |
+
"grad_norm": 14.5070219039917,
|
| 653 |
+
"learning_rate": 7.91891891891892e-06,
|
| 654 |
+
"loss": 1.7842,
|
| 655 |
+
"step": 83
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 0.224,
|
| 659 |
+
"grad_norm": 15.286811828613281,
|
| 660 |
+
"learning_rate": 7.891891891891894e-06,
|
| 661 |
+
"loss": 1.9336,
|
| 662 |
+
"step": 84
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 0.22666666666666666,
|
| 666 |
+
"grad_norm": 14.387998580932617,
|
| 667 |
+
"learning_rate": 7.864864864864866e-06,
|
| 668 |
+
"loss": 1.9154,
|
| 669 |
+
"step": 85
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 0.22933333333333333,
|
| 673 |
+
"grad_norm": 14.496636390686035,
|
| 674 |
+
"learning_rate": 7.837837837837838e-06,
|
| 675 |
+
"loss": 1.7855,
|
| 676 |
+
"step": 86
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 0.232,
|
| 680 |
+
"grad_norm": 13.50484848022461,
|
| 681 |
+
"learning_rate": 7.810810810810812e-06,
|
| 682 |
+
"loss": 1.782,
|
| 683 |
+
"step": 87
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 0.23466666666666666,
|
| 687 |
+
"grad_norm": 16.108259201049805,
|
| 688 |
+
"learning_rate": 7.783783783783784e-06,
|
| 689 |
+
"loss": 1.986,
|
| 690 |
+
"step": 88
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 0.23733333333333334,
|
| 694 |
+
"grad_norm": 14.42662525177002,
|
| 695 |
+
"learning_rate": 7.756756756756756e-06,
|
| 696 |
+
"loss": 1.7175,
|
| 697 |
+
"step": 89
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 0.24,
|
| 701 |
+
"grad_norm": 12.877999305725098,
|
| 702 |
+
"learning_rate": 7.72972972972973e-06,
|
| 703 |
+
"loss": 1.8143,
|
| 704 |
+
"step": 90
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 0.24,
|
| 708 |
+
"eval_loss": 1.7911643981933594,
|
| 709 |
+
"eval_runtime": 1.4513,
|
| 710 |
+
"eval_samples_per_second": 20.671,
|
| 711 |
+
"eval_steps_per_second": 10.335,
|
| 712 |
+
"step": 90
|
| 713 |
+
},
|
| 714 |
+
{
|
| 715 |
+
"epoch": 0.24266666666666667,
|
| 716 |
+
"grad_norm": 14.032076835632324,
|
| 717 |
+
"learning_rate": 7.702702702702704e-06,
|
| 718 |
+
"loss": 1.8842,
|
| 719 |
+
"step": 91
|
| 720 |
+
},
|
| 721 |
+
{
|
| 722 |
+
"epoch": 0.24533333333333332,
|
| 723 |
+
"grad_norm": 14.625088691711426,
|
| 724 |
+
"learning_rate": 7.675675675675676e-06,
|
| 725 |
+
"loss": 1.8891,
|
| 726 |
+
"step": 92
|
| 727 |
+
},
|
| 728 |
+
{
|
| 729 |
+
"epoch": 0.248,
|
| 730 |
+
"grad_norm": 12.943449020385742,
|
| 731 |
+
"learning_rate": 7.648648648648649e-06,
|
| 732 |
+
"loss": 1.69,
|
| 733 |
+
"step": 93
|
| 734 |
+
},
|
| 735 |
+
{
|
| 736 |
+
"epoch": 0.25066666666666665,
|
| 737 |
+
"grad_norm": 14.895347595214844,
|
| 738 |
+
"learning_rate": 7.621621621621622e-06,
|
| 739 |
+
"loss": 1.8021,
|
| 740 |
+
"step": 94
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 0.25333333333333335,
|
| 744 |
+
"grad_norm": 14.53865909576416,
|
| 745 |
+
"learning_rate": 7.594594594594596e-06,
|
| 746 |
+
"loss": 1.7205,
|
| 747 |
+
"step": 95
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 0.256,
|
| 751 |
+
"grad_norm": 12.052194595336914,
|
| 752 |
+
"learning_rate": 7.567567567567569e-06,
|
| 753 |
+
"loss": 1.7664,
|
| 754 |
+
"step": 96
|
| 755 |
+
},
|
| 756 |
+
{
|
| 757 |
+
"epoch": 0.25866666666666666,
|
| 758 |
+
"grad_norm": 12.567586898803711,
|
| 759 |
+
"learning_rate": 7.540540540540541e-06,
|
| 760 |
+
"loss": 1.7944,
|
| 761 |
+
"step": 97
|
| 762 |
+
},
|
| 763 |
+
{
|
| 764 |
+
"epoch": 0.2613333333333333,
|
| 765 |
+
"grad_norm": 14.633405685424805,
|
| 766 |
+
"learning_rate": 7.513513513513514e-06,
|
| 767 |
+
"loss": 1.6582,
|
| 768 |
+
"step": 98
|
| 769 |
+
},
|
| 770 |
+
{
|
| 771 |
+
"epoch": 0.264,
|
| 772 |
+
"grad_norm": 13.399588584899902,
|
| 773 |
+
"learning_rate": 7.486486486486487e-06,
|
| 774 |
+
"loss": 1.8577,
|
| 775 |
+
"step": 99
|
| 776 |
+
},
|
| 777 |
+
{
|
| 778 |
+
"epoch": 0.26666666666666666,
|
| 779 |
+
"grad_norm": 12.297356605529785,
|
| 780 |
+
"learning_rate": 7.45945945945946e-06,
|
| 781 |
+
"loss": 1.817,
|
| 782 |
+
"step": 100
|
| 783 |
+
},
|
| 784 |
+
{
|
| 785 |
+
"epoch": 0.26666666666666666,
|
| 786 |
+
"eval_loss": 1.7191141843795776,
|
| 787 |
+
"eval_runtime": 1.4464,
|
| 788 |
+
"eval_samples_per_second": 20.741,
|
| 789 |
+
"eval_steps_per_second": 10.37,
|
| 790 |
+
"step": 100
|
| 791 |
+
},
|
| 792 |
+
{
|
| 793 |
+
"epoch": 0.2693333333333333,
|
| 794 |
+
"grad_norm": 13.96349048614502,
|
| 795 |
+
"learning_rate": 7.4324324324324324e-06,
|
| 796 |
+
"loss": 1.7299,
|
| 797 |
+
"step": 101
|
| 798 |
+
},
|
| 799 |
+
{
|
| 800 |
+
"epoch": 0.272,
|
| 801 |
+
"grad_norm": 12.001126289367676,
|
| 802 |
+
"learning_rate": 7.4054054054054055e-06,
|
| 803 |
+
"loss": 1.6544,
|
| 804 |
+
"step": 102
|
| 805 |
+
},
|
| 806 |
+
{
|
| 807 |
+
"epoch": 0.27466666666666667,
|
| 808 |
+
"grad_norm": 13.116267204284668,
|
| 809 |
+
"learning_rate": 7.3783783783783794e-06,
|
| 810 |
+
"loss": 1.7013,
|
| 811 |
+
"step": 103
|
| 812 |
+
},
|
| 813 |
+
{
|
| 814 |
+
"epoch": 0.2773333333333333,
|
| 815 |
+
"grad_norm": 13.404566764831543,
|
| 816 |
+
"learning_rate": 7.3513513513513525e-06,
|
| 817 |
+
"loss": 1.7313,
|
| 818 |
+
"step": 104
|
| 819 |
+
},
|
| 820 |
+
{
|
| 821 |
+
"epoch": 0.28,
|
| 822 |
+
"grad_norm": 13.112600326538086,
|
| 823 |
+
"learning_rate": 7.324324324324325e-06,
|
| 824 |
+
"loss": 1.6768,
|
| 825 |
+
"step": 105
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 0.2826666666666667,
|
| 829 |
+
"grad_norm": 11.644760131835938,
|
| 830 |
+
"learning_rate": 7.297297297297298e-06,
|
| 831 |
+
"loss": 1.7202,
|
| 832 |
+
"step": 106
|
| 833 |
+
},
|
| 834 |
+
{
|
| 835 |
+
"epoch": 0.2853333333333333,
|
| 836 |
+
"grad_norm": 12.4971923828125,
|
| 837 |
+
"learning_rate": 7.270270270270271e-06,
|
| 838 |
+
"loss": 1.6554,
|
| 839 |
+
"step": 107
|
| 840 |
+
},
|
| 841 |
+
{
|
| 842 |
+
"epoch": 0.288,
|
| 843 |
+
"grad_norm": 13.368678092956543,
|
| 844 |
+
"learning_rate": 7.243243243243244e-06,
|
| 845 |
+
"loss": 1.7155,
|
| 846 |
+
"step": 108
|
| 847 |
+
},
|
| 848 |
+
{
|
| 849 |
+
"epoch": 0.2906666666666667,
|
| 850 |
+
"grad_norm": 11.646718978881836,
|
| 851 |
+
"learning_rate": 7.216216216216216e-06,
|
| 852 |
+
"loss": 1.6875,
|
| 853 |
+
"step": 109
|
| 854 |
+
},
|
| 855 |
+
{
|
| 856 |
+
"epoch": 0.29333333333333333,
|
| 857 |
+
"grad_norm": 11.237492561340332,
|
| 858 |
+
"learning_rate": 7.189189189189189e-06,
|
| 859 |
+
"loss": 1.7969,
|
| 860 |
+
"step": 110
|
| 861 |
+
},
|
| 862 |
+
{
|
| 863 |
+
"epoch": 0.29333333333333333,
|
| 864 |
+
"eval_loss": 1.6631710529327393,
|
| 865 |
+
"eval_runtime": 1.4481,
|
| 866 |
+
"eval_samples_per_second": 20.717,
|
| 867 |
+
"eval_steps_per_second": 10.358,
|
| 868 |
+
"step": 110
|
| 869 |
+
},
|
| 870 |
+
{
|
| 871 |
+
"epoch": 0.296,
|
| 872 |
+
"grad_norm": 12.128864288330078,
|
| 873 |
+
"learning_rate": 7.162162162162163e-06,
|
| 874 |
+
"loss": 1.71,
|
| 875 |
+
"step": 111
|
| 876 |
+
},
|
| 877 |
+
{
|
| 878 |
+
"epoch": 0.2986666666666667,
|
| 879 |
+
"grad_norm": 13.497359275817871,
|
| 880 |
+
"learning_rate": 7.135135135135136e-06,
|
| 881 |
+
"loss": 1.6549,
|
| 882 |
+
"step": 112
|
| 883 |
+
},
|
| 884 |
+
{
|
| 885 |
+
"epoch": 0.30133333333333334,
|
| 886 |
+
"grad_norm": 12.220688819885254,
|
| 887 |
+
"learning_rate": 7.1081081081081085e-06,
|
| 888 |
+
"loss": 1.6311,
|
| 889 |
+
"step": 113
|
| 890 |
+
},
|
| 891 |
+
{
|
| 892 |
+
"epoch": 0.304,
|
| 893 |
+
"grad_norm": 12.031643867492676,
|
| 894 |
+
"learning_rate": 7.0810810810810815e-06,
|
| 895 |
+
"loss": 1.5752,
|
| 896 |
+
"step": 114
|
| 897 |
+
},
|
| 898 |
+
{
|
| 899 |
+
"epoch": 0.30666666666666664,
|
| 900 |
+
"grad_norm": 11.963508605957031,
|
| 901 |
+
"learning_rate": 7.054054054054055e-06,
|
| 902 |
+
"loss": 1.6123,
|
| 903 |
+
"step": 115
|
| 904 |
+
},
|
| 905 |
+
{
|
| 906 |
+
"epoch": 0.30933333333333335,
|
| 907 |
+
"grad_norm": 12.681684494018555,
|
| 908 |
+
"learning_rate": 7.027027027027028e-06,
|
| 909 |
+
"loss": 1.6943,
|
| 910 |
+
"step": 116
|
| 911 |
+
},
|
| 912 |
+
{
|
| 913 |
+
"epoch": 0.312,
|
| 914 |
+
"grad_norm": 11.903910636901855,
|
| 915 |
+
"learning_rate": 7e-06,
|
| 916 |
+
"loss": 1.7237,
|
| 917 |
+
"step": 117
|
| 918 |
+
},
|
| 919 |
+
{
|
| 920 |
+
"epoch": 0.31466666666666665,
|
| 921 |
+
"grad_norm": 12.239933967590332,
|
| 922 |
+
"learning_rate": 6.972972972972973e-06,
|
| 923 |
+
"loss": 1.532,
|
| 924 |
+
"step": 118
|
| 925 |
+
},
|
| 926 |
+
{
|
| 927 |
+
"epoch": 0.31733333333333336,
|
| 928 |
+
"grad_norm": 12.396098136901855,
|
| 929 |
+
"learning_rate": 6.945945945945947e-06,
|
| 930 |
+
"loss": 1.6313,
|
| 931 |
+
"step": 119
|
| 932 |
+
},
|
| 933 |
+
{
|
| 934 |
+
"epoch": 0.32,
|
| 935 |
+
"grad_norm": 11.794013977050781,
|
| 936 |
+
"learning_rate": 6.91891891891892e-06,
|
| 937 |
+
"loss": 1.5266,
|
| 938 |
+
"step": 120
|
| 939 |
+
},
|
| 940 |
+
{
|
| 941 |
+
"epoch": 0.32,
|
| 942 |
+
"eval_loss": 1.6251609325408936,
|
| 943 |
+
"eval_runtime": 1.46,
|
| 944 |
+
"eval_samples_per_second": 20.548,
|
| 945 |
+
"eval_steps_per_second": 10.274,
|
| 946 |
+
"step": 120
|
| 947 |
+
},
|
| 948 |
+
{
|
| 949 |
+
"epoch": 0.32266666666666666,
|
| 950 |
+
"grad_norm": 10.741290092468262,
|
| 951 |
+
"learning_rate": 6.891891891891892e-06,
|
| 952 |
+
"loss": 1.6946,
|
| 953 |
+
"step": 121
|
| 954 |
+
},
|
| 955 |
+
{
|
| 956 |
+
"epoch": 0.3253333333333333,
|
| 957 |
+
"grad_norm": 13.47004508972168,
|
| 958 |
+
"learning_rate": 6.864864864864865e-06,
|
| 959 |
+
"loss": 1.4668,
|
| 960 |
+
"step": 122
|
| 961 |
+
},
|
| 962 |
+
{
|
| 963 |
+
"epoch": 0.328,
|
| 964 |
+
"grad_norm": 12.196053504943848,
|
| 965 |
+
"learning_rate": 6.837837837837838e-06,
|
| 966 |
+
"loss": 1.7412,
|
| 967 |
+
"step": 123
|
| 968 |
+
},
|
| 969 |
+
{
|
| 970 |
+
"epoch": 0.33066666666666666,
|
| 971 |
+
"grad_norm": 13.029918670654297,
|
| 972 |
+
"learning_rate": 6.810810810810811e-06,
|
| 973 |
+
"loss": 1.5352,
|
| 974 |
+
"step": 124
|
| 975 |
+
},
|
| 976 |
+
{
|
| 977 |
+
"epoch": 0.3333333333333333,
|
| 978 |
+
"grad_norm": 11.20665454864502,
|
| 979 |
+
"learning_rate": 6.783783783783784e-06,
|
| 980 |
+
"loss": 1.5555,
|
| 981 |
+
"step": 125
|
| 982 |
+
},
|
| 983 |
+
{
|
| 984 |
+
"epoch": 0.336,
|
| 985 |
+
"grad_norm": 12.214777946472168,
|
| 986 |
+
"learning_rate": 6.7567567567567575e-06,
|
| 987 |
+
"loss": 1.5862,
|
| 988 |
+
"step": 126
|
| 989 |
+
},
|
| 990 |
+
{
|
| 991 |
+
"epoch": 0.33866666666666667,
|
| 992 |
+
"grad_norm": 13.904444694519043,
|
| 993 |
+
"learning_rate": 6.729729729729731e-06,
|
| 994 |
+
"loss": 1.7348,
|
| 995 |
+
"step": 127
|
| 996 |
+
},
|
| 997 |
+
{
|
| 998 |
+
"epoch": 0.3413333333333333,
|
| 999 |
+
"grad_norm": 12.65821361541748,
|
| 1000 |
+
"learning_rate": 6.702702702702704e-06,
|
| 1001 |
+
"loss": 1.5627,
|
| 1002 |
+
"step": 128
|
| 1003 |
+
},
|
| 1004 |
+
{
|
| 1005 |
+
"epoch": 0.344,
|
| 1006 |
+
"grad_norm": 12.02226734161377,
|
| 1007 |
+
"learning_rate": 6.675675675675676e-06,
|
| 1008 |
+
"loss": 1.5978,
|
| 1009 |
+
"step": 129
|
| 1010 |
+
},
|
| 1011 |
+
{
|
| 1012 |
+
"epoch": 0.3466666666666667,
|
| 1013 |
+
"grad_norm": 11.53661823272705,
|
| 1014 |
+
"learning_rate": 6.648648648648649e-06,
|
| 1015 |
+
"loss": 1.6756,
|
| 1016 |
+
"step": 130
|
| 1017 |
+
},
|
| 1018 |
+
{
|
| 1019 |
+
"epoch": 0.3466666666666667,
|
| 1020 |
+
"eval_loss": 1.6016688346862793,
|
| 1021 |
+
"eval_runtime": 1.4506,
|
| 1022 |
+
"eval_samples_per_second": 20.681,
|
| 1023 |
+
"eval_steps_per_second": 10.34,
|
| 1024 |
+
"step": 130
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 0.34933333333333333,
|
| 1028 |
+
"grad_norm": 13.927865028381348,
|
| 1029 |
+
"learning_rate": 6.621621621621622e-06,
|
| 1030 |
+
"loss": 1.6014,
|
| 1031 |
+
"step": 131
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 0.352,
|
| 1035 |
+
"grad_norm": 11.404069900512695,
|
| 1036 |
+
"learning_rate": 6.594594594594595e-06,
|
| 1037 |
+
"loss": 1.6191,
|
| 1038 |
+
"step": 132
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"epoch": 0.3546666666666667,
|
| 1042 |
+
"grad_norm": 12.802854537963867,
|
| 1043 |
+
"learning_rate": 6.567567567567567e-06,
|
| 1044 |
+
"loss": 1.7147,
|
| 1045 |
+
"step": 133
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 0.35733333333333334,
|
| 1049 |
+
"grad_norm": 13.293572425842285,
|
| 1050 |
+
"learning_rate": 6.540540540540541e-06,
|
| 1051 |
+
"loss": 1.7999,
|
| 1052 |
+
"step": 134
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 0.36,
|
| 1056 |
+
"grad_norm": 14.33857536315918,
|
| 1057 |
+
"learning_rate": 6.513513513513514e-06,
|
| 1058 |
+
"loss": 1.7601,
|
| 1059 |
+
"step": 135
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 0.3626666666666667,
|
| 1063 |
+
"grad_norm": 11.54388427734375,
|
| 1064 |
+
"learning_rate": 6.486486486486487e-06,
|
| 1065 |
+
"loss": 1.5501,
|
| 1066 |
+
"step": 136
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 0.36533333333333334,
|
| 1070 |
+
"grad_norm": 11.567480087280273,
|
| 1071 |
+
"learning_rate": 6.45945945945946e-06,
|
| 1072 |
+
"loss": 1.6299,
|
| 1073 |
+
"step": 137
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 0.368,
|
| 1077 |
+
"grad_norm": 11.44282341003418,
|
| 1078 |
+
"learning_rate": 6.432432432432433e-06,
|
| 1079 |
+
"loss": 1.5726,
|
| 1080 |
+
"step": 138
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 0.37066666666666664,
|
| 1084 |
+
"grad_norm": 14.322295188903809,
|
| 1085 |
+
"learning_rate": 6.405405405405406e-06,
|
| 1086 |
+
"loss": 1.6423,
|
| 1087 |
+
"step": 139
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 0.37333333333333335,
|
| 1091 |
+
"grad_norm": 11.916459083557129,
|
| 1092 |
+
"learning_rate": 6.378378378378379e-06,
|
| 1093 |
+
"loss": 1.6311,
|
| 1094 |
+
"step": 140
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 0.37333333333333335,
|
| 1098 |
+
"eval_loss": 1.5860799551010132,
|
| 1099 |
+
"eval_runtime": 1.4507,
|
| 1100 |
+
"eval_samples_per_second": 20.679,
|
| 1101 |
+
"eval_steps_per_second": 10.34,
|
| 1102 |
+
"step": 140
|
| 1103 |
+
},
|
| 1104 |
+
{
|
| 1105 |
+
"epoch": 0.376,
|
| 1106 |
+
"grad_norm": 11.447466850280762,
|
| 1107 |
+
"learning_rate": 6.351351351351351e-06,
|
| 1108 |
+
"loss": 1.5076,
|
| 1109 |
+
"step": 141
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 0.37866666666666665,
|
| 1113 |
+
"grad_norm": 10.863157272338867,
|
| 1114 |
+
"learning_rate": 6.324324324324325e-06,
|
| 1115 |
+
"loss": 1.5188,
|
| 1116 |
+
"step": 142
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 0.38133333333333336,
|
| 1120 |
+
"grad_norm": 11.271020889282227,
|
| 1121 |
+
"learning_rate": 6.297297297297298e-06,
|
| 1122 |
+
"loss": 1.6336,
|
| 1123 |
+
"step": 143
|
| 1124 |
+
},
|
| 1125 |
+
{
|
| 1126 |
+
"epoch": 0.384,
|
| 1127 |
+
"grad_norm": 11.583234786987305,
|
| 1128 |
+
"learning_rate": 6.270270270270271e-06,
|
| 1129 |
+
"loss": 1.4692,
|
| 1130 |
+
"step": 144
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 0.38666666666666666,
|
| 1134 |
+
"grad_norm": 12.622394561767578,
|
| 1135 |
+
"learning_rate": 6.243243243243243e-06,
|
| 1136 |
+
"loss": 1.3161,
|
| 1137 |
+
"step": 145
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 0.3893333333333333,
|
| 1141 |
+
"grad_norm": 10.768049240112305,
|
| 1142 |
+
"learning_rate": 6.2162162162162164e-06,
|
| 1143 |
+
"loss": 1.6118,
|
| 1144 |
+
"step": 146
|
| 1145 |
+
},
|
| 1146 |
+
{
|
| 1147 |
+
"epoch": 0.392,
|
| 1148 |
+
"grad_norm": 10.967697143554688,
|
| 1149 |
+
"learning_rate": 6.1891891891891895e-06,
|
| 1150 |
+
"loss": 1.5251,
|
| 1151 |
+
"step": 147
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 0.39466666666666667,
|
| 1155 |
+
"grad_norm": 11.763079643249512,
|
| 1156 |
+
"learning_rate": 6.162162162162163e-06,
|
| 1157 |
+
"loss": 1.6997,
|
| 1158 |
+
"step": 148
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"epoch": 0.3973333333333333,
|
| 1162 |
+
"grad_norm": 10.566551208496094,
|
| 1163 |
+
"learning_rate": 6.135135135135135e-06,
|
| 1164 |
+
"loss": 1.4984,
|
| 1165 |
+
"step": 149
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"epoch": 0.4,
|
| 1169 |
+
"grad_norm": 13.371134757995605,
|
| 1170 |
+
"learning_rate": 6.108108108108109e-06,
|
| 1171 |
+
"loss": 1.7244,
|
| 1172 |
+
"step": 150
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 0.4,
|
| 1176 |
+
"eval_loss": 1.5736008882522583,
|
| 1177 |
+
"eval_runtime": 1.4456,
|
| 1178 |
+
"eval_samples_per_second": 20.752,
|
| 1179 |
+
"eval_steps_per_second": 10.376,
|
| 1180 |
+
"step": 150
|
| 1181 |
+
},
|
| 1182 |
+
{
|
| 1183 |
+
"epoch": 0.4026666666666667,
|
| 1184 |
+
"grad_norm": 12.493298530578613,
|
| 1185 |
+
"learning_rate": 6.081081081081082e-06,
|
| 1186 |
+
"loss": 1.5759,
|
| 1187 |
+
"step": 151
|
| 1188 |
+
},
|
| 1189 |
+
{
|
| 1190 |
+
"epoch": 0.4053333333333333,
|
| 1191 |
+
"grad_norm": 12.431512832641602,
|
| 1192 |
+
"learning_rate": 6.054054054054055e-06,
|
| 1193 |
+
"loss": 1.5811,
|
| 1194 |
+
"step": 152
|
| 1195 |
+
},
|
| 1196 |
+
{
|
| 1197 |
+
"epoch": 0.408,
|
| 1198 |
+
"grad_norm": 11.778576850891113,
|
| 1199 |
+
"learning_rate": 6.027027027027027e-06,
|
| 1200 |
+
"loss": 1.5997,
|
| 1201 |
+
"step": 153
|
| 1202 |
+
},
|
| 1203 |
+
{
|
| 1204 |
+
"epoch": 0.4106666666666667,
|
| 1205 |
+
"grad_norm": 12.10274887084961,
|
| 1206 |
+
"learning_rate": 6e-06,
|
| 1207 |
+
"loss": 1.5589,
|
| 1208 |
+
"step": 154
|
| 1209 |
+
},
|
| 1210 |
+
{
|
| 1211 |
+
"epoch": 0.41333333333333333,
|
| 1212 |
+
"grad_norm": 12.245983123779297,
|
| 1213 |
+
"learning_rate": 5.972972972972973e-06,
|
| 1214 |
+
"loss": 1.5864,
|
| 1215 |
+
"step": 155
|
| 1216 |
+
},
|
| 1217 |
+
{
|
| 1218 |
+
"epoch": 0.416,
|
| 1219 |
+
"grad_norm": 12.401384353637695,
|
| 1220 |
+
"learning_rate": 5.945945945945947e-06,
|
| 1221 |
+
"loss": 1.5593,
|
| 1222 |
+
"step": 156
|
| 1223 |
+
},
|
| 1224 |
+
{
|
| 1225 |
+
"epoch": 0.4186666666666667,
|
| 1226 |
+
"grad_norm": 13.845521926879883,
|
| 1227 |
+
"learning_rate": 5.9189189189189185e-06,
|
| 1228 |
+
"loss": 1.4717,
|
| 1229 |
+
"step": 157
|
| 1230 |
+
},
|
| 1231 |
+
{
|
| 1232 |
+
"epoch": 0.42133333333333334,
|
| 1233 |
+
"grad_norm": 11.529600143432617,
|
| 1234 |
+
"learning_rate": 5.8918918918918924e-06,
|
| 1235 |
+
"loss": 1.5599,
|
| 1236 |
+
"step": 158
|
| 1237 |
+
},
|
| 1238 |
+
{
|
| 1239 |
+
"epoch": 0.424,
|
| 1240 |
+
"grad_norm": 11.169657707214355,
|
| 1241 |
+
"learning_rate": 5.8648648648648655e-06,
|
| 1242 |
+
"loss": 1.7053,
|
| 1243 |
+
"step": 159
|
| 1244 |
+
},
|
| 1245 |
+
{
|
| 1246 |
+
"epoch": 0.4266666666666667,
|
| 1247 |
+
"grad_norm": 13.295831680297852,
|
| 1248 |
+
"learning_rate": 5.837837837837839e-06,
|
| 1249 |
+
"loss": 1.4569,
|
| 1250 |
+
"step": 160
|
| 1251 |
+
},
|
| 1252 |
+
{
|
| 1253 |
+
"epoch": 0.4266666666666667,
|
| 1254 |
+
"eval_loss": 1.5643337965011597,
|
| 1255 |
+
"eval_runtime": 1.4526,
|
| 1256 |
+
"eval_samples_per_second": 20.652,
|
| 1257 |
+
"eval_steps_per_second": 10.326,
|
| 1258 |
+
"step": 160
|
| 1259 |
+
},
|
| 1260 |
+
{
|
| 1261 |
+
"epoch": 0.42933333333333334,
|
| 1262 |
+
"grad_norm": 12.037769317626953,
|
| 1263 |
+
"learning_rate": 5.810810810810811e-06,
|
| 1264 |
+
"loss": 1.533,
|
| 1265 |
+
"step": 161
|
| 1266 |
+
},
|
| 1267 |
+
{
|
| 1268 |
+
"epoch": 0.432,
|
| 1269 |
+
"grad_norm": 12.236255645751953,
|
| 1270 |
+
"learning_rate": 5.783783783783784e-06,
|
| 1271 |
+
"loss": 1.5459,
|
| 1272 |
+
"step": 162
|
| 1273 |
+
},
|
| 1274 |
+
{
|
| 1275 |
+
"epoch": 0.43466666666666665,
|
| 1276 |
+
"grad_norm": 12.55140209197998,
|
| 1277 |
+
"learning_rate": 5.756756756756757e-06,
|
| 1278 |
+
"loss": 1.5024,
|
| 1279 |
+
"step": 163
|
| 1280 |
+
},
|
| 1281 |
+
{
|
| 1282 |
+
"epoch": 0.43733333333333335,
|
| 1283 |
+
"grad_norm": 10.870196342468262,
|
| 1284 |
+
"learning_rate": 5.729729729729731e-06,
|
| 1285 |
+
"loss": 1.5159,
|
| 1286 |
+
"step": 164
|
| 1287 |
+
},
|
| 1288 |
+
{
|
| 1289 |
+
"epoch": 0.44,
|
| 1290 |
+
"grad_norm": 11.8145751953125,
|
| 1291 |
+
"learning_rate": 5.702702702702702e-06,
|
| 1292 |
+
"loss": 1.5292,
|
| 1293 |
+
"step": 165
|
| 1294 |
+
},
|
| 1295 |
+
{
|
| 1296 |
+
"epoch": 0.44266666666666665,
|
| 1297 |
+
"grad_norm": 11.710899353027344,
|
| 1298 |
+
"learning_rate": 5.675675675675676e-06,
|
| 1299 |
+
"loss": 1.5724,
|
| 1300 |
+
"step": 166
|
| 1301 |
+
},
|
| 1302 |
+
{
|
| 1303 |
+
"epoch": 0.44533333333333336,
|
| 1304 |
+
"grad_norm": 10.809335708618164,
|
| 1305 |
+
"learning_rate": 5.648648648648649e-06,
|
| 1306 |
+
"loss": 1.5325,
|
| 1307 |
+
"step": 167
|
| 1308 |
+
},
|
| 1309 |
+
{
|
| 1310 |
+
"epoch": 0.448,
|
| 1311 |
+
"grad_norm": 11.874850273132324,
|
| 1312 |
+
"learning_rate": 5.621621621621622e-06,
|
| 1313 |
+
"loss": 1.4954,
|
| 1314 |
+
"step": 168
|
| 1315 |
+
},
|
| 1316 |
+
{
|
| 1317 |
+
"epoch": 0.45066666666666666,
|
| 1318 |
+
"grad_norm": 11.912819862365723,
|
| 1319 |
+
"learning_rate": 5.5945945945945945e-06,
|
| 1320 |
+
"loss": 1.5614,
|
| 1321 |
+
"step": 169
|
| 1322 |
+
},
|
| 1323 |
+
{
|
| 1324 |
+
"epoch": 0.4533333333333333,
|
| 1325 |
+
"grad_norm": 13.068821907043457,
|
| 1326 |
+
"learning_rate": 5.567567567567568e-06,
|
| 1327 |
+
"loss": 1.5157,
|
| 1328 |
+
"step": 170
|
| 1329 |
+
},
|
| 1330 |
+
{
|
| 1331 |
+
"epoch": 0.4533333333333333,
|
| 1332 |
+
"eval_loss": 1.5530024766921997,
|
| 1333 |
+
"eval_runtime": 1.4596,
|
| 1334 |
+
"eval_samples_per_second": 20.554,
|
| 1335 |
+
"eval_steps_per_second": 10.277,
|
| 1336 |
+
"step": 170
|
| 1337 |
+
},
|
| 1338 |
+
{
|
| 1339 |
+
"epoch": 0.456,
|
| 1340 |
+
"grad_norm": 12.24840259552002,
|
| 1341 |
+
"learning_rate": 5.540540540540541e-06,
|
| 1342 |
+
"loss": 1.5693,
|
| 1343 |
+
"step": 171
|
| 1344 |
+
},
|
| 1345 |
+
{
|
| 1346 |
+
"epoch": 0.45866666666666667,
|
| 1347 |
+
"grad_norm": 11.337618827819824,
|
| 1348 |
+
"learning_rate": 5.513513513513515e-06,
|
| 1349 |
+
"loss": 1.5568,
|
| 1350 |
+
"step": 172
|
| 1351 |
+
},
|
| 1352 |
+
{
|
| 1353 |
+
"epoch": 0.4613333333333333,
|
| 1354 |
+
"grad_norm": 10.453991889953613,
|
| 1355 |
+
"learning_rate": 5.486486486486487e-06,
|
| 1356 |
+
"loss": 1.5001,
|
| 1357 |
+
"step": 173
|
| 1358 |
+
},
|
| 1359 |
+
{
|
| 1360 |
+
"epoch": 0.464,
|
| 1361 |
+
"grad_norm": 10.317952156066895,
|
| 1362 |
+
"learning_rate": 5.45945945945946e-06,
|
| 1363 |
+
"loss": 1.4289,
|
| 1364 |
+
"step": 174
|
| 1365 |
+
},
|
| 1366 |
+
{
|
| 1367 |
+
"epoch": 0.4666666666666667,
|
| 1368 |
+
"grad_norm": 11.70666217803955,
|
| 1369 |
+
"learning_rate": 5.432432432432433e-06,
|
| 1370 |
+
"loss": 1.3301,
|
| 1371 |
+
"step": 175
|
| 1372 |
+
},
|
| 1373 |
+
{
|
| 1374 |
+
"epoch": 0.4693333333333333,
|
| 1375 |
+
"grad_norm": 14.784002304077148,
|
| 1376 |
+
"learning_rate": 5.405405405405406e-06,
|
| 1377 |
+
"loss": 1.5322,
|
| 1378 |
+
"step": 176
|
| 1379 |
+
},
|
| 1380 |
+
{
|
| 1381 |
+
"epoch": 0.472,
|
| 1382 |
+
"grad_norm": 10.439934730529785,
|
| 1383 |
+
"learning_rate": 5.378378378378378e-06,
|
| 1384 |
+
"loss": 1.4356,
|
| 1385 |
+
"step": 177
|
| 1386 |
+
},
|
| 1387 |
+
{
|
| 1388 |
+
"epoch": 0.4746666666666667,
|
| 1389 |
+
"grad_norm": 10.800159454345703,
|
| 1390 |
+
"learning_rate": 5.351351351351351e-06,
|
| 1391 |
+
"loss": 1.6718,
|
| 1392 |
+
"step": 178
|
| 1393 |
+
},
|
| 1394 |
+
{
|
| 1395 |
+
"epoch": 0.47733333333333333,
|
| 1396 |
+
"grad_norm": 11.382489204406738,
|
| 1397 |
+
"learning_rate": 5.324324324324324e-06,
|
| 1398 |
+
"loss": 1.6329,
|
| 1399 |
+
"step": 179
|
| 1400 |
+
},
|
| 1401 |
+
{
|
| 1402 |
+
"epoch": 0.48,
|
| 1403 |
+
"grad_norm": 11.744807243347168,
|
| 1404 |
+
"learning_rate": 5.297297297297298e-06,
|
| 1405 |
+
"loss": 1.5418,
|
| 1406 |
+
"step": 180
|
| 1407 |
+
},
|
| 1408 |
+
{
|
| 1409 |
+
"epoch": 0.48,
|
| 1410 |
+
"eval_loss": 1.5468370914459229,
|
| 1411 |
+
"eval_runtime": 1.4494,
|
| 1412 |
+
"eval_samples_per_second": 20.698,
|
| 1413 |
+
"eval_steps_per_second": 10.349,
|
| 1414 |
+
"step": 180
|
| 1415 |
+
},
|
| 1416 |
+
{
|
| 1417 |
+
"epoch": 0.4826666666666667,
|
| 1418 |
+
"grad_norm": 10.518260955810547,
|
| 1419 |
+
"learning_rate": 5.2702702702702705e-06,
|
| 1420 |
+
"loss": 1.579,
|
| 1421 |
+
"step": 181
|
| 1422 |
+
},
|
| 1423 |
+
{
|
| 1424 |
+
"epoch": 0.48533333333333334,
|
| 1425 |
+
"grad_norm": 14.920302391052246,
|
| 1426 |
+
"learning_rate": 5.243243243243244e-06,
|
| 1427 |
+
"loss": 1.5459,
|
| 1428 |
+
"step": 182
|
| 1429 |
+
},
|
| 1430 |
+
{
|
| 1431 |
+
"epoch": 0.488,
|
| 1432 |
+
"grad_norm": 14.005922317504883,
|
| 1433 |
+
"learning_rate": 5.216216216216217e-06,
|
| 1434 |
+
"loss": 1.4835,
|
| 1435 |
+
"step": 183
|
| 1436 |
+
},
|
| 1437 |
+
{
|
| 1438 |
+
"epoch": 0.49066666666666664,
|
| 1439 |
+
"grad_norm": 13.020917892456055,
|
| 1440 |
+
"learning_rate": 5.18918918918919e-06,
|
| 1441 |
+
"loss": 1.5315,
|
| 1442 |
+
"step": 184
|
| 1443 |
+
},
|
| 1444 |
+
{
|
| 1445 |
+
"epoch": 0.49333333333333335,
|
| 1446 |
+
"grad_norm": 11.8460054397583,
|
| 1447 |
+
"learning_rate": 5.162162162162162e-06,
|
| 1448 |
+
"loss": 1.4567,
|
| 1449 |
+
"step": 185
|
| 1450 |
+
},
|
| 1451 |
+
{
|
| 1452 |
+
"epoch": 0.496,
|
| 1453 |
+
"grad_norm": 12.585269927978516,
|
| 1454 |
+
"learning_rate": 5.135135135135135e-06,
|
| 1455 |
+
"loss": 1.5409,
|
| 1456 |
+
"step": 186
|
| 1457 |
+
},
|
| 1458 |
+
{
|
| 1459 |
+
"epoch": 0.49866666666666665,
|
| 1460 |
+
"grad_norm": 10.893098831176758,
|
| 1461 |
+
"learning_rate": 5.108108108108108e-06,
|
| 1462 |
+
"loss": 1.5523,
|
| 1463 |
+
"step": 187
|
| 1464 |
+
},
|
| 1465 |
+
{
|
| 1466 |
+
"epoch": 0.5013333333333333,
|
| 1467 |
+
"grad_norm": 13.312434196472168,
|
| 1468 |
+
"learning_rate": 5.081081081081082e-06,
|
| 1469 |
+
"loss": 1.408,
|
| 1470 |
+
"step": 188
|
| 1471 |
+
},
|
| 1472 |
+
{
|
| 1473 |
+
"epoch": 0.504,
|
| 1474 |
+
"grad_norm": 11.251080513000488,
|
| 1475 |
+
"learning_rate": 5.054054054054054e-06,
|
| 1476 |
+
"loss": 1.559,
|
| 1477 |
+
"step": 189
|
| 1478 |
+
},
|
| 1479 |
+
{
|
| 1480 |
+
"epoch": 0.5066666666666667,
|
| 1481 |
+
"grad_norm": 11.128360748291016,
|
| 1482 |
+
"learning_rate": 5.027027027027027e-06,
|
| 1483 |
+
"loss": 1.6048,
|
| 1484 |
+
"step": 190
|
| 1485 |
+
},
|
| 1486 |
+
{
|
| 1487 |
+
"epoch": 0.5066666666666667,
|
| 1488 |
+
"eval_loss": 1.5399889945983887,
|
| 1489 |
+
"eval_runtime": 1.4761,
|
| 1490 |
+
"eval_samples_per_second": 20.324,
|
| 1491 |
+
"eval_steps_per_second": 10.162,
|
| 1492 |
+
"step": 190
|
| 1493 |
+
},
|
| 1494 |
+
{
|
| 1495 |
+
"epoch": 0.5093333333333333,
|
| 1496 |
+
"grad_norm": 11.423062324523926,
|
| 1497 |
+
"learning_rate": 5e-06,
|
| 1498 |
+
"loss": 1.6389,
|
| 1499 |
+
"step": 191
|
| 1500 |
+
},
|
| 1501 |
+
{
|
| 1502 |
+
"epoch": 0.512,
|
| 1503 |
+
"grad_norm": 11.651025772094727,
|
| 1504 |
+
"learning_rate": 4.9729729729729735e-06,
|
| 1505 |
+
"loss": 1.5658,
|
| 1506 |
+
"step": 192
|
| 1507 |
+
},
|
| 1508 |
+
{
|
| 1509 |
+
"epoch": 0.5146666666666667,
|
| 1510 |
+
"grad_norm": 11.046283721923828,
|
| 1511 |
+
"learning_rate": 4.9459459459459466e-06,
|
| 1512 |
+
"loss": 1.4467,
|
| 1513 |
+
"step": 193
|
| 1514 |
+
},
|
| 1515 |
+
{
|
| 1516 |
+
"epoch": 0.5173333333333333,
|
| 1517 |
+
"grad_norm": 12.875414848327637,
|
| 1518 |
+
"learning_rate": 4.91891891891892e-06,
|
| 1519 |
+
"loss": 1.5826,
|
| 1520 |
+
"step": 194
|
| 1521 |
+
},
|
| 1522 |
+
{
|
| 1523 |
+
"epoch": 0.52,
|
| 1524 |
+
"grad_norm": 12.292638778686523,
|
| 1525 |
+
"learning_rate": 4.891891891891893e-06,
|
| 1526 |
+
"loss": 1.483,
|
| 1527 |
+
"step": 195
|
| 1528 |
+
},
|
| 1529 |
+
{
|
| 1530 |
+
"epoch": 0.5226666666666666,
|
| 1531 |
+
"grad_norm": 11.317679405212402,
|
| 1532 |
+
"learning_rate": 4.864864864864866e-06,
|
| 1533 |
+
"loss": 1.6073,
|
| 1534 |
+
"step": 196
|
| 1535 |
+
},
|
| 1536 |
+
{
|
| 1537 |
+
"epoch": 0.5253333333333333,
|
| 1538 |
+
"grad_norm": 12.65168571472168,
|
| 1539 |
+
"learning_rate": 4.837837837837838e-06,
|
| 1540 |
+
"loss": 1.5852,
|
| 1541 |
+
"step": 197
|
| 1542 |
+
},
|
| 1543 |
+
{
|
| 1544 |
+
"epoch": 0.528,
|
| 1545 |
+
"grad_norm": 14.210925102233887,
|
| 1546 |
+
"learning_rate": 4.810810810810811e-06,
|
| 1547 |
+
"loss": 1.6664,
|
| 1548 |
+
"step": 198
|
| 1549 |
+
},
|
| 1550 |
+
{
|
| 1551 |
+
"epoch": 0.5306666666666666,
|
| 1552 |
+
"grad_norm": 12.766249656677246,
|
| 1553 |
+
"learning_rate": 4.783783783783784e-06,
|
| 1554 |
+
"loss": 1.6201,
|
| 1555 |
+
"step": 199
|
| 1556 |
+
},
|
| 1557 |
+
{
|
| 1558 |
+
"epoch": 0.5333333333333333,
|
| 1559 |
+
"grad_norm": 12.087968826293945,
|
| 1560 |
+
"learning_rate": 4.756756756756757e-06,
|
| 1561 |
+
"loss": 1.5182,
|
| 1562 |
+
"step": 200
|
| 1563 |
+
},
|
| 1564 |
+
{
|
| 1565 |
+
"epoch": 0.5333333333333333,
|
| 1566 |
+
"eval_loss": 1.5342140197753906,
|
| 1567 |
+
"eval_runtime": 1.4482,
|
| 1568 |
+
"eval_samples_per_second": 20.716,
|
| 1569 |
+
"eval_steps_per_second": 10.358,
|
| 1570 |
+
"step": 200
|
| 1571 |
+
},
|
| 1572 |
+
{
|
| 1573 |
+
"epoch": 0.536,
|
| 1574 |
+
"grad_norm": 14.878036499023438,
|
| 1575 |
+
"learning_rate": 4.72972972972973e-06,
|
| 1576 |
+
"loss": 1.6464,
|
| 1577 |
+
"step": 201
|
| 1578 |
+
},
|
| 1579 |
+
{
|
| 1580 |
+
"epoch": 0.5386666666666666,
|
| 1581 |
+
"grad_norm": 11.994093894958496,
|
| 1582 |
+
"learning_rate": 4.702702702702703e-06,
|
| 1583 |
+
"loss": 1.4874,
|
| 1584 |
+
"step": 202
|
| 1585 |
+
},
|
| 1586 |
+
{
|
| 1587 |
+
"epoch": 0.5413333333333333,
|
| 1588 |
+
"grad_norm": 16.825557708740234,
|
| 1589 |
+
"learning_rate": 4.675675675675676e-06,
|
| 1590 |
+
"loss": 1.6089,
|
| 1591 |
+
"step": 203
|
| 1592 |
+
},
|
| 1593 |
+
{
|
| 1594 |
+
"epoch": 0.544,
|
| 1595 |
+
"grad_norm": 10.64698314666748,
|
| 1596 |
+
"learning_rate": 4.6486486486486495e-06,
|
| 1597 |
+
"loss": 1.5708,
|
| 1598 |
+
"step": 204
|
| 1599 |
+
},
|
| 1600 |
+
{
|
| 1601 |
+
"epoch": 0.5466666666666666,
|
| 1602 |
+
"grad_norm": 12.136466979980469,
|
| 1603 |
+
"learning_rate": 4.621621621621622e-06,
|
| 1604 |
+
"loss": 1.686,
|
| 1605 |
+
"step": 205
|
| 1606 |
+
},
|
| 1607 |
+
{
|
| 1608 |
+
"epoch": 0.5493333333333333,
|
| 1609 |
+
"grad_norm": 11.439790725708008,
|
| 1610 |
+
"learning_rate": 4.594594594594596e-06,
|
| 1611 |
+
"loss": 1.6251,
|
| 1612 |
+
"step": 206
|
| 1613 |
+
},
|
| 1614 |
+
{
|
| 1615 |
+
"epoch": 0.552,
|
| 1616 |
+
"grad_norm": 11.850600242614746,
|
| 1617 |
+
"learning_rate": 4.567567567567568e-06,
|
| 1618 |
+
"loss": 1.5279,
|
| 1619 |
+
"step": 207
|
| 1620 |
+
},
|
| 1621 |
+
{
|
| 1622 |
+
"epoch": 0.5546666666666666,
|
| 1623 |
+
"grad_norm": 11.281230926513672,
|
| 1624 |
+
"learning_rate": 4.540540540540541e-06,
|
| 1625 |
+
"loss": 1.4779,
|
| 1626 |
+
"step": 208
|
| 1627 |
+
},
|
| 1628 |
+
{
|
| 1629 |
+
"epoch": 0.5573333333333333,
|
| 1630 |
+
"grad_norm": 11.568439483642578,
|
| 1631 |
+
"learning_rate": 4.513513513513514e-06,
|
| 1632 |
+
"loss": 1.717,
|
| 1633 |
+
"step": 209
|
| 1634 |
+
},
|
| 1635 |
+
{
|
| 1636 |
+
"epoch": 0.56,
|
| 1637 |
+
"grad_norm": 10.368412017822266,
|
| 1638 |
+
"learning_rate": 4.486486486486487e-06,
|
| 1639 |
+
"loss": 1.5628,
|
| 1640 |
+
"step": 210
|
| 1641 |
+
},
|
| 1642 |
+
{
|
| 1643 |
+
"epoch": 0.56,
|
| 1644 |
+
"eval_loss": 1.529217004776001,
|
| 1645 |
+
"eval_runtime": 1.4476,
|
| 1646 |
+
"eval_samples_per_second": 20.724,
|
| 1647 |
+
"eval_steps_per_second": 10.362,
|
| 1648 |
+
"step": 210
|
| 1649 |
+
},
|
| 1650 |
+
{
|
| 1651 |
+
"epoch": 0.5626666666666666,
|
| 1652 |
+
"grad_norm": 12.218080520629883,
|
| 1653 |
+
"learning_rate": 4.45945945945946e-06,
|
| 1654 |
+
"loss": 1.5924,
|
| 1655 |
+
"step": 211
|
| 1656 |
+
},
|
| 1657 |
+
{
|
| 1658 |
+
"epoch": 0.5653333333333334,
|
| 1659 |
+
"grad_norm": 10.668429374694824,
|
| 1660 |
+
"learning_rate": 4.432432432432433e-06,
|
| 1661 |
+
"loss": 1.5156,
|
| 1662 |
+
"step": 212
|
| 1663 |
+
},
|
| 1664 |
+
{
|
| 1665 |
+
"epoch": 0.568,
|
| 1666 |
+
"grad_norm": 10.990684509277344,
|
| 1667 |
+
"learning_rate": 4.4054054054054054e-06,
|
| 1668 |
+
"loss": 1.6046,
|
| 1669 |
+
"step": 213
|
| 1670 |
+
},
|
| 1671 |
+
{
|
| 1672 |
+
"epoch": 0.5706666666666667,
|
| 1673 |
+
"grad_norm": 12.811287879943848,
|
| 1674 |
+
"learning_rate": 4.378378378378379e-06,
|
| 1675 |
+
"loss": 1.5945,
|
| 1676 |
+
"step": 214
|
| 1677 |
+
},
|
| 1678 |
+
{
|
| 1679 |
+
"epoch": 0.5733333333333334,
|
| 1680 |
+
"grad_norm": 11.771529197692871,
|
| 1681 |
+
"learning_rate": 4.351351351351352e-06,
|
| 1682 |
+
"loss": 1.5792,
|
| 1683 |
+
"step": 215
|
| 1684 |
+
},
|
| 1685 |
+
{
|
| 1686 |
+
"epoch": 0.576,
|
| 1687 |
+
"grad_norm": 11.0822114944458,
|
| 1688 |
+
"learning_rate": 4.324324324324325e-06,
|
| 1689 |
+
"loss": 1.6252,
|
| 1690 |
+
"step": 216
|
| 1691 |
+
},
|
| 1692 |
+
{
|
| 1693 |
+
"epoch": 0.5786666666666667,
|
| 1694 |
+
"grad_norm": 11.860054016113281,
|
| 1695 |
+
"learning_rate": 4.297297297297298e-06,
|
| 1696 |
+
"loss": 1.4526,
|
| 1697 |
+
"step": 217
|
| 1698 |
+
},
|
| 1699 |
+
{
|
| 1700 |
+
"epoch": 0.5813333333333334,
|
| 1701 |
+
"grad_norm": 11.882978439331055,
|
| 1702 |
+
"learning_rate": 4.270270270270271e-06,
|
| 1703 |
+
"loss": 1.3806,
|
| 1704 |
+
"step": 218
|
| 1705 |
+
},
|
| 1706 |
+
{
|
| 1707 |
+
"epoch": 0.584,
|
| 1708 |
+
"grad_norm": 11.159905433654785,
|
| 1709 |
+
"learning_rate": 4.243243243243244e-06,
|
| 1710 |
+
"loss": 1.5448,
|
| 1711 |
+
"step": 219
|
| 1712 |
+
},
|
| 1713 |
+
{
|
| 1714 |
+
"epoch": 0.5866666666666667,
|
| 1715 |
+
"grad_norm": 12.598294258117676,
|
| 1716 |
+
"learning_rate": 4.216216216216217e-06,
|
| 1717 |
+
"loss": 1.531,
|
| 1718 |
+
"step": 220
|
| 1719 |
+
},
|
| 1720 |
+
{
|
| 1721 |
+
"epoch": 0.5866666666666667,
|
| 1722 |
+
"eval_loss": 1.5237351655960083,
|
| 1723 |
+
"eval_runtime": 1.505,
|
| 1724 |
+
"eval_samples_per_second": 19.934,
|
| 1725 |
+
"eval_steps_per_second": 9.967,
|
| 1726 |
+
"step": 220
|
| 1727 |
+
},
|
| 1728 |
+
{
|
| 1729 |
+
"epoch": 0.5893333333333334,
|
| 1730 |
+
"grad_norm": 12.2394437789917,
|
| 1731 |
+
"learning_rate": 4.189189189189189e-06,
|
| 1732 |
+
"loss": 1.4149,
|
| 1733 |
+
"step": 221
|
| 1734 |
+
},
|
| 1735 |
+
{
|
| 1736 |
+
"epoch": 0.592,
|
| 1737 |
+
"grad_norm": 11.620826721191406,
|
| 1738 |
+
"learning_rate": 4.162162162162163e-06,
|
| 1739 |
+
"loss": 1.6498,
|
| 1740 |
+
"step": 222
|
| 1741 |
+
},
|
| 1742 |
+
{
|
| 1743 |
+
"epoch": 0.5946666666666667,
|
| 1744 |
+
"grad_norm": 13.30986213684082,
|
| 1745 |
+
"learning_rate": 4.135135135135135e-06,
|
| 1746 |
+
"loss": 1.6125,
|
| 1747 |
+
"step": 223
|
| 1748 |
+
},
|
| 1749 |
+
{
|
| 1750 |
+
"epoch": 0.5973333333333334,
|
| 1751 |
+
"grad_norm": 10.7543363571167,
|
| 1752 |
+
"learning_rate": 4.108108108108108e-06,
|
| 1753 |
+
"loss": 1.5335,
|
| 1754 |
+
"step": 224
|
| 1755 |
+
},
|
| 1756 |
+
{
|
| 1757 |
+
"epoch": 0.6,
|
| 1758 |
+
"grad_norm": 12.820805549621582,
|
| 1759 |
+
"learning_rate": 4.0810810810810815e-06,
|
| 1760 |
+
"loss": 1.4477,
|
| 1761 |
+
"step": 225
|
| 1762 |
+
},
|
| 1763 |
+
{
|
| 1764 |
+
"epoch": 0.6026666666666667,
|
| 1765 |
+
"grad_norm": 10.250899314880371,
|
| 1766 |
+
"learning_rate": 4.0540540540540545e-06,
|
| 1767 |
+
"loss": 1.5308,
|
| 1768 |
+
"step": 226
|
| 1769 |
+
},
|
| 1770 |
+
{
|
| 1771 |
+
"epoch": 0.6053333333333333,
|
| 1772 |
+
"grad_norm": 11.902603149414062,
|
| 1773 |
+
"learning_rate": 4.027027027027028e-06,
|
| 1774 |
+
"loss": 1.5168,
|
| 1775 |
+
"step": 227
|
| 1776 |
+
},
|
| 1777 |
+
{
|
| 1778 |
+
"epoch": 0.608,
|
| 1779 |
+
"grad_norm": 11.358914375305176,
|
| 1780 |
+
"learning_rate": 4.000000000000001e-06,
|
| 1781 |
+
"loss": 1.5414,
|
| 1782 |
+
"step": 228
|
| 1783 |
+
},
|
| 1784 |
+
{
|
| 1785 |
+
"epoch": 0.6106666666666667,
|
| 1786 |
+
"grad_norm": 10.709514617919922,
|
| 1787 |
+
"learning_rate": 3.972972972972973e-06,
|
| 1788 |
+
"loss": 1.4812,
|
| 1789 |
+
"step": 229
|
| 1790 |
+
},
|
| 1791 |
+
{
|
| 1792 |
+
"epoch": 0.6133333333333333,
|
| 1793 |
+
"grad_norm": 10.724623680114746,
|
| 1794 |
+
"learning_rate": 3.945945945945947e-06,
|
| 1795 |
+
"loss": 1.5425,
|
| 1796 |
+
"step": 230
|
| 1797 |
+
},
|
| 1798 |
+
{
|
| 1799 |
+
"epoch": 0.6133333333333333,
|
| 1800 |
+
"eval_loss": 1.5228849649429321,
|
| 1801 |
+
"eval_runtime": 1.4436,
|
| 1802 |
+
"eval_samples_per_second": 20.781,
|
| 1803 |
+
"eval_steps_per_second": 10.39,
|
| 1804 |
+
"step": 230
|
| 1805 |
+
},
|
| 1806 |
+
{
|
| 1807 |
+
"epoch": 0.616,
|
| 1808 |
+
"grad_norm": 11.70534896850586,
|
| 1809 |
+
"learning_rate": 3.918918918918919e-06,
|
| 1810 |
+
"loss": 1.5146,
|
| 1811 |
+
"step": 231
|
| 1812 |
+
},
|
| 1813 |
+
{
|
| 1814 |
+
"epoch": 0.6186666666666667,
|
| 1815 |
+
"grad_norm": 9.500643730163574,
|
| 1816 |
+
"learning_rate": 3.891891891891892e-06,
|
| 1817 |
+
"loss": 1.4185,
|
| 1818 |
+
"step": 232
|
| 1819 |
+
},
|
| 1820 |
+
{
|
| 1821 |
+
"epoch": 0.6213333333333333,
|
| 1822 |
+
"grad_norm": 11.755574226379395,
|
| 1823 |
+
"learning_rate": 3.864864864864865e-06,
|
| 1824 |
+
"loss": 1.5805,
|
| 1825 |
+
"step": 233
|
| 1826 |
+
},
|
| 1827 |
+
{
|
| 1828 |
+
"epoch": 0.624,
|
| 1829 |
+
"grad_norm": 11.309388160705566,
|
| 1830 |
+
"learning_rate": 3.837837837837838e-06,
|
| 1831 |
+
"loss": 1.5481,
|
| 1832 |
+
"step": 234
|
| 1833 |
+
},
|
| 1834 |
+
{
|
| 1835 |
+
"epoch": 0.6266666666666667,
|
| 1836 |
+
"grad_norm": 10.823451042175293,
|
| 1837 |
+
"learning_rate": 3.810810810810811e-06,
|
| 1838 |
+
"loss": 1.4996,
|
| 1839 |
+
"step": 235
|
| 1840 |
+
},
|
| 1841 |
+
{
|
| 1842 |
+
"epoch": 0.6293333333333333,
|
| 1843 |
+
"grad_norm": 10.33895492553711,
|
| 1844 |
+
"learning_rate": 3.7837837837837844e-06,
|
| 1845 |
+
"loss": 1.5545,
|
| 1846 |
+
"step": 236
|
| 1847 |
+
},
|
| 1848 |
+
{
|
| 1849 |
+
"epoch": 0.632,
|
| 1850 |
+
"grad_norm": 12.343066215515137,
|
| 1851 |
+
"learning_rate": 3.756756756756757e-06,
|
| 1852 |
+
"loss": 1.4629,
|
| 1853 |
+
"step": 237
|
| 1854 |
+
},
|
| 1855 |
+
{
|
| 1856 |
+
"epoch": 0.6346666666666667,
|
| 1857 |
+
"grad_norm": 10.669163703918457,
|
| 1858 |
+
"learning_rate": 3.72972972972973e-06,
|
| 1859 |
+
"loss": 1.4943,
|
| 1860 |
+
"step": 238
|
| 1861 |
+
},
|
| 1862 |
+
{
|
| 1863 |
+
"epoch": 0.6373333333333333,
|
| 1864 |
+
"grad_norm": 19.491622924804688,
|
| 1865 |
+
"learning_rate": 3.7027027027027028e-06,
|
| 1866 |
+
"loss": 1.4613,
|
| 1867 |
+
"step": 239
|
| 1868 |
+
},
|
| 1869 |
+
{
|
| 1870 |
+
"epoch": 0.64,
|
| 1871 |
+
"grad_norm": 11.280375480651855,
|
| 1872 |
+
"learning_rate": 3.6756756756756763e-06,
|
| 1873 |
+
"loss": 1.5251,
|
| 1874 |
+
"step": 240
|
| 1875 |
+
},
|
| 1876 |
+
{
|
| 1877 |
+
"epoch": 0.64,
|
| 1878 |
+
"eval_loss": 1.5189076662063599,
|
| 1879 |
+
"eval_runtime": 1.4647,
|
| 1880 |
+
"eval_samples_per_second": 20.482,
|
| 1881 |
+
"eval_steps_per_second": 10.241,
|
| 1882 |
+
"step": 240
|
| 1883 |
+
},
|
| 1884 |
+
{
|
| 1885 |
+
"epoch": 0.6426666666666667,
|
| 1886 |
+
"grad_norm": 11.986125946044922,
|
| 1887 |
+
"learning_rate": 3.648648648648649e-06,
|
| 1888 |
+
"loss": 1.5283,
|
| 1889 |
+
"step": 241
|
| 1890 |
+
},
|
| 1891 |
+
{
|
| 1892 |
+
"epoch": 0.6453333333333333,
|
| 1893 |
+
"grad_norm": 11.676025390625,
|
| 1894 |
+
"learning_rate": 3.621621621621622e-06,
|
| 1895 |
+
"loss": 1.5087,
|
| 1896 |
+
"step": 242
|
| 1897 |
+
},
|
| 1898 |
+
{
|
| 1899 |
+
"epoch": 0.648,
|
| 1900 |
+
"grad_norm": 11.277451515197754,
|
| 1901 |
+
"learning_rate": 3.5945945945945946e-06,
|
| 1902 |
+
"loss": 1.5804,
|
| 1903 |
+
"step": 243
|
| 1904 |
+
},
|
| 1905 |
+
{
|
| 1906 |
+
"epoch": 0.6506666666666666,
|
| 1907 |
+
"grad_norm": 9.987862586975098,
|
| 1908 |
+
"learning_rate": 3.567567567567568e-06,
|
| 1909 |
+
"loss": 1.5514,
|
| 1910 |
+
"step": 244
|
| 1911 |
+
},
|
| 1912 |
+
{
|
| 1913 |
+
"epoch": 0.6533333333333333,
|
| 1914 |
+
"grad_norm": 11.72730827331543,
|
| 1915 |
+
"learning_rate": 3.5405405405405408e-06,
|
| 1916 |
+
"loss": 1.51,
|
| 1917 |
+
"step": 245
|
| 1918 |
+
},
|
| 1919 |
+
{
|
| 1920 |
+
"epoch": 0.656,
|
| 1921 |
+
"grad_norm": 11.331317901611328,
|
| 1922 |
+
"learning_rate": 3.513513513513514e-06,
|
| 1923 |
+
"loss": 1.4503,
|
| 1924 |
+
"step": 246
|
| 1925 |
+
},
|
| 1926 |
+
{
|
| 1927 |
+
"epoch": 0.6586666666666666,
|
| 1928 |
+
"grad_norm": 10.42099666595459,
|
| 1929 |
+
"learning_rate": 3.4864864864864865e-06,
|
| 1930 |
+
"loss": 1.4682,
|
| 1931 |
+
"step": 247
|
| 1932 |
+
},
|
| 1933 |
+
{
|
| 1934 |
+
"epoch": 0.6613333333333333,
|
| 1935 |
+
"grad_norm": 12.430152893066406,
|
| 1936 |
+
"learning_rate": 3.45945945945946e-06,
|
| 1937 |
+
"loss": 1.5126,
|
| 1938 |
+
"step": 248
|
| 1939 |
+
},
|
| 1940 |
+
{
|
| 1941 |
+
"epoch": 0.664,
|
| 1942 |
+
"grad_norm": 12.36617660522461,
|
| 1943 |
+
"learning_rate": 3.4324324324324326e-06,
|
| 1944 |
+
"loss": 1.5373,
|
| 1945 |
+
"step": 249
|
| 1946 |
+
},
|
| 1947 |
+
{
|
| 1948 |
+
"epoch": 0.6666666666666666,
|
| 1949 |
+
"grad_norm": 11.66644287109375,
|
| 1950 |
+
"learning_rate": 3.4054054054054057e-06,
|
| 1951 |
+
"loss": 1.5439,
|
| 1952 |
+
"step": 250
|
| 1953 |
+
},
|
| 1954 |
+
{
|
| 1955 |
+
"epoch": 0.6666666666666666,
|
| 1956 |
+
"eval_loss": 1.5144615173339844,
|
| 1957 |
+
"eval_runtime": 1.4468,
|
| 1958 |
+
"eval_samples_per_second": 20.735,
|
| 1959 |
+
"eval_steps_per_second": 10.368,
|
| 1960 |
+
"step": 250
|
| 1961 |
+
},
|
| 1962 |
+
{
|
| 1963 |
+
"epoch": 0.6693333333333333,
|
| 1964 |
+
"grad_norm": 11.48746395111084,
|
| 1965 |
+
"learning_rate": 3.3783783783783788e-06,
|
| 1966 |
+
"loss": 1.4353,
|
| 1967 |
+
"step": 251
|
| 1968 |
+
},
|
| 1969 |
+
{
|
| 1970 |
+
"epoch": 0.672,
|
| 1971 |
+
"grad_norm": 11.128070831298828,
|
| 1972 |
+
"learning_rate": 3.351351351351352e-06,
|
| 1973 |
+
"loss": 1.5068,
|
| 1974 |
+
"step": 252
|
| 1975 |
+
},
|
| 1976 |
+
{
|
| 1977 |
+
"epoch": 0.6746666666666666,
|
| 1978 |
+
"grad_norm": 12.601024627685547,
|
| 1979 |
+
"learning_rate": 3.3243243243243245e-06,
|
| 1980 |
+
"loss": 1.5039,
|
| 1981 |
+
"step": 253
|
| 1982 |
+
},
|
| 1983 |
+
{
|
| 1984 |
+
"epoch": 0.6773333333333333,
|
| 1985 |
+
"grad_norm": 11.611284255981445,
|
| 1986 |
+
"learning_rate": 3.2972972972972976e-06,
|
| 1987 |
+
"loss": 1.5565,
|
| 1988 |
+
"step": 254
|
| 1989 |
+
},
|
| 1990 |
+
{
|
| 1991 |
+
"epoch": 0.68,
|
| 1992 |
+
"grad_norm": 12.905797958374023,
|
| 1993 |
+
"learning_rate": 3.2702702702702706e-06,
|
| 1994 |
+
"loss": 1.5206,
|
| 1995 |
+
"step": 255
|
| 1996 |
+
},
|
| 1997 |
+
{
|
| 1998 |
+
"epoch": 0.6826666666666666,
|
| 1999 |
+
"grad_norm": 12.170700073242188,
|
| 2000 |
+
"learning_rate": 3.2432432432432437e-06,
|
| 2001 |
+
"loss": 1.2695,
|
| 2002 |
+
"step": 256
|
| 2003 |
+
},
|
| 2004 |
+
{
|
| 2005 |
+
"epoch": 0.6853333333333333,
|
| 2006 |
+
"grad_norm": 12.405909538269043,
|
| 2007 |
+
"learning_rate": 3.2162162162162164e-06,
|
| 2008 |
+
"loss": 1.5179,
|
| 2009 |
+
"step": 257
|
| 2010 |
+
},
|
| 2011 |
+
{
|
| 2012 |
+
"epoch": 0.688,
|
| 2013 |
+
"grad_norm": 13.01850414276123,
|
| 2014 |
+
"learning_rate": 3.1891891891891894e-06,
|
| 2015 |
+
"loss": 1.4435,
|
| 2016 |
+
"step": 258
|
| 2017 |
+
},
|
| 2018 |
+
{
|
| 2019 |
+
"epoch": 0.6906666666666667,
|
| 2020 |
+
"grad_norm": 11.52682113647461,
|
| 2021 |
+
"learning_rate": 3.1621621621621625e-06,
|
| 2022 |
+
"loss": 1.3751,
|
| 2023 |
+
"step": 259
|
| 2024 |
+
},
|
| 2025 |
+
{
|
| 2026 |
+
"epoch": 0.6933333333333334,
|
| 2027 |
+
"grad_norm": 10.300020217895508,
|
| 2028 |
+
"learning_rate": 3.1351351351351356e-06,
|
| 2029 |
+
"loss": 1.4654,
|
| 2030 |
+
"step": 260
|
| 2031 |
+
},
|
| 2032 |
+
{
|
| 2033 |
+
"epoch": 0.6933333333333334,
|
| 2034 |
+
"eval_loss": 1.5129177570343018,
|
| 2035 |
+
"eval_runtime": 1.4415,
|
| 2036 |
+
"eval_samples_per_second": 20.811,
|
| 2037 |
+
"eval_steps_per_second": 10.406,
|
| 2038 |
+
"step": 260
|
| 2039 |
+
},
|
| 2040 |
+
{
|
| 2041 |
+
"epoch": 0.696,
|
| 2042 |
+
"grad_norm": 11.269693374633789,
|
| 2043 |
+
"learning_rate": 3.1081081081081082e-06,
|
| 2044 |
+
"loss": 1.6435,
|
| 2045 |
+
"step": 261
|
| 2046 |
+
},
|
| 2047 |
+
{
|
| 2048 |
+
"epoch": 0.6986666666666667,
|
| 2049 |
+
"grad_norm": 11.508820533752441,
|
| 2050 |
+
"learning_rate": 3.0810810810810817e-06,
|
| 2051 |
+
"loss": 1.4721,
|
| 2052 |
+
"step": 262
|
| 2053 |
+
},
|
| 2054 |
+
{
|
| 2055 |
+
"epoch": 0.7013333333333334,
|
| 2056 |
+
"grad_norm": 10.975653648376465,
|
| 2057 |
+
"learning_rate": 3.0540540540540544e-06,
|
| 2058 |
+
"loss": 1.672,
|
| 2059 |
+
"step": 263
|
| 2060 |
+
},
|
| 2061 |
+
{
|
| 2062 |
+
"epoch": 0.704,
|
| 2063 |
+
"grad_norm": 13.16110897064209,
|
| 2064 |
+
"learning_rate": 3.0270270270270274e-06,
|
| 2065 |
+
"loss": 1.4838,
|
| 2066 |
+
"step": 264
|
| 2067 |
+
},
|
| 2068 |
+
{
|
| 2069 |
+
"epoch": 0.7066666666666667,
|
| 2070 |
+
"grad_norm": 13.65386962890625,
|
| 2071 |
+
"learning_rate": 3e-06,
|
| 2072 |
+
"loss": 1.618,
|
| 2073 |
+
"step": 265
|
| 2074 |
+
},
|
| 2075 |
+
{
|
| 2076 |
+
"epoch": 0.7093333333333334,
|
| 2077 |
+
"grad_norm": 12.109015464782715,
|
| 2078 |
+
"learning_rate": 2.9729729729729736e-06,
|
| 2079 |
+
"loss": 1.4518,
|
| 2080 |
+
"step": 266
|
| 2081 |
+
},
|
| 2082 |
+
{
|
| 2083 |
+
"epoch": 0.712,
|
| 2084 |
+
"grad_norm": 11.558544158935547,
|
| 2085 |
+
"learning_rate": 2.9459459459459462e-06,
|
| 2086 |
+
"loss": 1.4772,
|
| 2087 |
+
"step": 267
|
| 2088 |
+
},
|
| 2089 |
+
{
|
| 2090 |
+
"epoch": 0.7146666666666667,
|
| 2091 |
+
"grad_norm": 12.302791595458984,
|
| 2092 |
+
"learning_rate": 2.9189189189189193e-06,
|
| 2093 |
+
"loss": 1.6029,
|
| 2094 |
+
"step": 268
|
| 2095 |
+
},
|
| 2096 |
+
{
|
| 2097 |
+
"epoch": 0.7173333333333334,
|
| 2098 |
+
"grad_norm": 12.268084526062012,
|
| 2099 |
+
"learning_rate": 2.891891891891892e-06,
|
| 2100 |
+
"loss": 1.4477,
|
| 2101 |
+
"step": 269
|
| 2102 |
+
},
|
| 2103 |
+
{
|
| 2104 |
+
"epoch": 0.72,
|
| 2105 |
+
"grad_norm": 11.1484375,
|
| 2106 |
+
"learning_rate": 2.8648648648648654e-06,
|
| 2107 |
+
"loss": 1.6031,
|
| 2108 |
+
"step": 270
|
| 2109 |
+
},
|
| 2110 |
+
{
|
| 2111 |
+
"epoch": 0.72,
|
| 2112 |
+
"eval_loss": 1.5090078115463257,
|
| 2113 |
+
"eval_runtime": 1.4443,
|
| 2114 |
+
"eval_samples_per_second": 20.772,
|
| 2115 |
+
"eval_steps_per_second": 10.386,
|
| 2116 |
+
"step": 270
|
| 2117 |
+
},
|
| 2118 |
+
{
|
| 2119 |
+
"epoch": 0.7226666666666667,
|
| 2120 |
+
"grad_norm": 10.918089866638184,
|
| 2121 |
+
"learning_rate": 2.837837837837838e-06,
|
| 2122 |
+
"loss": 1.3471,
|
| 2123 |
+
"step": 271
|
| 2124 |
+
},
|
| 2125 |
+
{
|
| 2126 |
+
"epoch": 0.7253333333333334,
|
| 2127 |
+
"grad_norm": 12.327642440795898,
|
| 2128 |
+
"learning_rate": 2.810810810810811e-06,
|
| 2129 |
+
"loss": 1.562,
|
| 2130 |
+
"step": 272
|
| 2131 |
+
},
|
| 2132 |
+
{
|
| 2133 |
+
"epoch": 0.728,
|
| 2134 |
+
"grad_norm": 11.135960578918457,
|
| 2135 |
+
"learning_rate": 2.783783783783784e-06,
|
| 2136 |
+
"loss": 1.5001,
|
| 2137 |
+
"step": 273
|
| 2138 |
+
},
|
| 2139 |
+
{
|
| 2140 |
+
"epoch": 0.7306666666666667,
|
| 2141 |
+
"grad_norm": 11.357678413391113,
|
| 2142 |
+
"learning_rate": 2.7567567567567573e-06,
|
| 2143 |
+
"loss": 1.4937,
|
| 2144 |
+
"step": 274
|
| 2145 |
+
},
|
| 2146 |
+
{
|
| 2147 |
+
"epoch": 0.7333333333333333,
|
| 2148 |
+
"grad_norm": 11.794831275939941,
|
| 2149 |
+
"learning_rate": 2.72972972972973e-06,
|
| 2150 |
+
"loss": 1.4711,
|
| 2151 |
+
"step": 275
|
| 2152 |
+
},
|
| 2153 |
+
{
|
| 2154 |
+
"epoch": 0.736,
|
| 2155 |
+
"grad_norm": 12.003959655761719,
|
| 2156 |
+
"learning_rate": 2.702702702702703e-06,
|
| 2157 |
+
"loss": 1.4683,
|
| 2158 |
+
"step": 276
|
| 2159 |
+
},
|
| 2160 |
+
{
|
| 2161 |
+
"epoch": 0.7386666666666667,
|
| 2162 |
+
"grad_norm": 11.9353666305542,
|
| 2163 |
+
"learning_rate": 2.6756756756756757e-06,
|
| 2164 |
+
"loss": 1.4963,
|
| 2165 |
+
"step": 277
|
| 2166 |
+
},
|
| 2167 |
+
{
|
| 2168 |
+
"epoch": 0.7413333333333333,
|
| 2169 |
+
"grad_norm": 10.868412971496582,
|
| 2170 |
+
"learning_rate": 2.648648648648649e-06,
|
| 2171 |
+
"loss": 1.4788,
|
| 2172 |
+
"step": 278
|
| 2173 |
+
},
|
| 2174 |
+
{
|
| 2175 |
+
"epoch": 0.744,
|
| 2176 |
+
"grad_norm": 10.403037071228027,
|
| 2177 |
+
"learning_rate": 2.621621621621622e-06,
|
| 2178 |
+
"loss": 1.4361,
|
| 2179 |
+
"step": 279
|
| 2180 |
+
},
|
| 2181 |
+
{
|
| 2182 |
+
"epoch": 0.7466666666666667,
|
| 2183 |
+
"grad_norm": 14.62988567352295,
|
| 2184 |
+
"learning_rate": 2.594594594594595e-06,
|
| 2185 |
+
"loss": 1.406,
|
| 2186 |
+
"step": 280
|
| 2187 |
+
},
|
| 2188 |
+
{
|
| 2189 |
+
"epoch": 0.7466666666666667,
|
| 2190 |
+
"eval_loss": 1.5082733631134033,
|
| 2191 |
+
"eval_runtime": 1.4412,
|
| 2192 |
+
"eval_samples_per_second": 20.816,
|
| 2193 |
+
"eval_steps_per_second": 10.408,
|
| 2194 |
+
"step": 280
|
| 2195 |
+
}
|
| 2196 |
+
],
|
| 2197 |
+
"logging_steps": 1,
|
| 2198 |
+
"max_steps": 375,
|
| 2199 |
+
"num_input_tokens_seen": 0,
|
| 2200 |
+
"num_train_epochs": 1,
|
| 2201 |
+
"save_steps": 10,
|
| 2202 |
+
"stateful_callbacks": {
|
| 2203 |
+
"TrainerControl": {
|
| 2204 |
+
"args": {
|
| 2205 |
+
"should_epoch_stop": false,
|
| 2206 |
+
"should_evaluate": false,
|
| 2207 |
+
"should_log": false,
|
| 2208 |
+
"should_save": true,
|
| 2209 |
+
"should_training_stop": false
|
| 2210 |
+
},
|
| 2211 |
+
"attributes": {}
|
| 2212 |
+
}
|
| 2213 |
+
},
|
| 2214 |
+
"total_flos": 6.073129780394342e+16,
|
| 2215 |
+
"train_batch_size": 2,
|
| 2216 |
+
"trial_name": null,
|
| 2217 |
+
"trial_params": null
|
| 2218 |
+
}
|
checkpoint-280/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d9be6ec0ef23215e7a2981248f495d079f207788f8c83f8ffb26b9d7f76671d5
|
| 3 |
+
size 6097
|