Upload folder using huggingface_hub
Browse files- README.md +202 -0
- adapter_config.json +33 -0
- adapter_model.safetensors +3 -0
- checkpoint-25/adapter_config.json +33 -0
- checkpoint-25/adapter_model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +2233 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
base_model: HuggingFaceM4/idefics-9b
|
| 4 |
+
---
|
| 5 |
+
|
| 6 |
+
# Model Card for Model ID
|
| 7 |
+
|
| 8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 9 |
+
|
| 10 |
+
|
| 11 |
+
|
| 12 |
+
## Model Details
|
| 13 |
+
|
| 14 |
+
### Model Description
|
| 15 |
+
|
| 16 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
- **Developed by:** [More Information Needed]
|
| 21 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 22 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 23 |
+
- **Model type:** [More Information Needed]
|
| 24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 25 |
+
- **License:** [More Information Needed]
|
| 26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 27 |
+
|
| 28 |
+
### Model Sources [optional]
|
| 29 |
+
|
| 30 |
+
<!-- Provide the basic links for the model. -->
|
| 31 |
+
|
| 32 |
+
- **Repository:** [More Information Needed]
|
| 33 |
+
- **Paper [optional]:** [More Information Needed]
|
| 34 |
+
- **Demo [optional]:** [More Information Needed]
|
| 35 |
+
|
| 36 |
+
## Uses
|
| 37 |
+
|
| 38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 39 |
+
|
| 40 |
+
### Direct Use
|
| 41 |
+
|
| 42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 43 |
+
|
| 44 |
+
[More Information Needed]
|
| 45 |
+
|
| 46 |
+
### Downstream Use [optional]
|
| 47 |
+
|
| 48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 49 |
+
|
| 50 |
+
[More Information Needed]
|
| 51 |
+
|
| 52 |
+
### Out-of-Scope Use
|
| 53 |
+
|
| 54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 55 |
+
|
| 56 |
+
[More Information Needed]
|
| 57 |
+
|
| 58 |
+
## Bias, Risks, and Limitations
|
| 59 |
+
|
| 60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 61 |
+
|
| 62 |
+
[More Information Needed]
|
| 63 |
+
|
| 64 |
+
### Recommendations
|
| 65 |
+
|
| 66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 67 |
+
|
| 68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 69 |
+
|
| 70 |
+
## How to Get Started with the Model
|
| 71 |
+
|
| 72 |
+
Use the code below to get started with the model.
|
| 73 |
+
|
| 74 |
+
[More Information Needed]
|
| 75 |
+
|
| 76 |
+
## Training Details
|
| 77 |
+
|
| 78 |
+
### Training Data
|
| 79 |
+
|
| 80 |
+
<!-- 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. -->
|
| 81 |
+
|
| 82 |
+
[More Information Needed]
|
| 83 |
+
|
| 84 |
+
### Training Procedure
|
| 85 |
+
|
| 86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 87 |
+
|
| 88 |
+
#### Preprocessing [optional]
|
| 89 |
+
|
| 90 |
+
[More Information Needed]
|
| 91 |
+
|
| 92 |
+
|
| 93 |
+
#### Training Hyperparameters
|
| 94 |
+
|
| 95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 96 |
+
|
| 97 |
+
#### Speeds, Sizes, Times [optional]
|
| 98 |
+
|
| 99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 100 |
+
|
| 101 |
+
[More Information Needed]
|
| 102 |
+
|
| 103 |
+
## Evaluation
|
| 104 |
+
|
| 105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 106 |
+
|
| 107 |
+
### Testing Data, Factors & Metrics
|
| 108 |
+
|
| 109 |
+
#### Testing Data
|
| 110 |
+
|
| 111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 112 |
+
|
| 113 |
+
[More Information Needed]
|
| 114 |
+
|
| 115 |
+
#### Factors
|
| 116 |
+
|
| 117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 118 |
+
|
| 119 |
+
[More Information Needed]
|
| 120 |
+
|
| 121 |
+
#### Metrics
|
| 122 |
+
|
| 123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 124 |
+
|
| 125 |
+
[More Information Needed]
|
| 126 |
+
|
| 127 |
+
### Results
|
| 128 |
+
|
| 129 |
+
[More Information Needed]
|
| 130 |
+
|
| 131 |
+
#### Summary
|
| 132 |
+
|
| 133 |
+
|
| 134 |
+
|
| 135 |
+
## Model Examination [optional]
|
| 136 |
+
|
| 137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 138 |
+
|
| 139 |
+
[More Information Needed]
|
| 140 |
+
|
| 141 |
+
## Environmental Impact
|
| 142 |
+
|
| 143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 144 |
+
|
| 145 |
+
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).
|
| 146 |
+
|
| 147 |
+
- **Hardware Type:** [More Information Needed]
|
| 148 |
+
- **Hours used:** [More Information Needed]
|
| 149 |
+
- **Cloud Provider:** [More Information Needed]
|
| 150 |
+
- **Compute Region:** [More Information Needed]
|
| 151 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 152 |
+
|
| 153 |
+
## Technical Specifications [optional]
|
| 154 |
+
|
| 155 |
+
### Model Architecture and Objective
|
| 156 |
+
|
| 157 |
+
[More Information Needed]
|
| 158 |
+
|
| 159 |
+
### Compute Infrastructure
|
| 160 |
+
|
| 161 |
+
[More Information Needed]
|
| 162 |
+
|
| 163 |
+
#### Hardware
|
| 164 |
+
|
| 165 |
+
[More Information Needed]
|
| 166 |
+
|
| 167 |
+
#### Software
|
| 168 |
+
|
| 169 |
+
[More Information Needed]
|
| 170 |
+
|
| 171 |
+
## Citation [optional]
|
| 172 |
+
|
| 173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 174 |
+
|
| 175 |
+
**BibTeX:**
|
| 176 |
+
|
| 177 |
+
[More Information Needed]
|
| 178 |
+
|
| 179 |
+
**APA:**
|
| 180 |
+
|
| 181 |
+
[More Information Needed]
|
| 182 |
+
|
| 183 |
+
## Glossary [optional]
|
| 184 |
+
|
| 185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 186 |
+
|
| 187 |
+
[More Information Needed]
|
| 188 |
+
|
| 189 |
+
## More Information [optional]
|
| 190 |
+
|
| 191 |
+
[More Information Needed]
|
| 192 |
+
|
| 193 |
+
## Model Card Authors [optional]
|
| 194 |
+
|
| 195 |
+
[More Information Needed]
|
| 196 |
+
|
| 197 |
+
## Model Card Contact
|
| 198 |
+
|
| 199 |
+
[More Information Needed]
|
| 200 |
+
### Framework versions
|
| 201 |
+
|
| 202 |
+
- PEFT 0.10.1.dev0
|
adapter_config.json
ADDED
|
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": {
|
| 4 |
+
"base_model_class": "PeftModel",
|
| 5 |
+
"parent_library": "peft.peft_model"
|
| 6 |
+
},
|
| 7 |
+
"base_model_name_or_path": null,
|
| 8 |
+
"bias": "none",
|
| 9 |
+
"fan_in_fan_out": false,
|
| 10 |
+
"inference_mode": true,
|
| 11 |
+
"init_lora_weights": true,
|
| 12 |
+
"layer_replication": null,
|
| 13 |
+
"layers_pattern": null,
|
| 14 |
+
"layers_to_transform": null,
|
| 15 |
+
"loftq_config": {},
|
| 16 |
+
"lora_alpha": 32,
|
| 17 |
+
"lora_dropout": 0.05,
|
| 18 |
+
"megatron_config": null,
|
| 19 |
+
"megatron_core": "megatron.core",
|
| 20 |
+
"modules_to_save": null,
|
| 21 |
+
"peft_type": "LORA",
|
| 22 |
+
"r": 16,
|
| 23 |
+
"rank_pattern": {},
|
| 24 |
+
"revision": null,
|
| 25 |
+
"target_modules": [
|
| 26 |
+
"q_proj",
|
| 27 |
+
"k_proj",
|
| 28 |
+
"v_proj"
|
| 29 |
+
],
|
| 30 |
+
"task_type": null,
|
| 31 |
+
"use_dora": false,
|
| 32 |
+
"use_rslora": false
|
| 33 |
+
}
|
adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:afa6eb41c0717012891eddcc52b79ccab9e598ff31ebf28ffaec6b21e650e449
|
| 3 |
+
size 79079832
|
checkpoint-25/adapter_config.json
ADDED
|
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": {
|
| 4 |
+
"base_model_class": "PeftModel",
|
| 5 |
+
"parent_library": "peft.peft_model"
|
| 6 |
+
},
|
| 7 |
+
"base_model_name_or_path": null,
|
| 8 |
+
"bias": "none",
|
| 9 |
+
"fan_in_fan_out": false,
|
| 10 |
+
"inference_mode": true,
|
| 11 |
+
"init_lora_weights": true,
|
| 12 |
+
"layer_replication": null,
|
| 13 |
+
"layers_pattern": null,
|
| 14 |
+
"layers_to_transform": null,
|
| 15 |
+
"loftq_config": {},
|
| 16 |
+
"lora_alpha": 32,
|
| 17 |
+
"lora_dropout": 0.05,
|
| 18 |
+
"megatron_config": null,
|
| 19 |
+
"megatron_core": "megatron.core",
|
| 20 |
+
"modules_to_save": null,
|
| 21 |
+
"peft_type": "LORA",
|
| 22 |
+
"r": 16,
|
| 23 |
+
"rank_pattern": {},
|
| 24 |
+
"revision": null,
|
| 25 |
+
"target_modules": [
|
| 26 |
+
"q_proj",
|
| 27 |
+
"k_proj",
|
| 28 |
+
"v_proj"
|
| 29 |
+
],
|
| 30 |
+
"task_type": null,
|
| 31 |
+
"use_dora": false,
|
| 32 |
+
"use_rslora": false
|
| 33 |
+
}
|
checkpoint-25/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d5cde13bbd2555977cb26644d2101aadcfa972b1420382cc71e22b0155703d8a
|
| 3 |
+
size 79079832
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:62b1eac1d49f62a3c037948446c60405463a4b833b66210f12e889165d207f70
|
| 3 |
+
size 41325130
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:acf55cd38b50bae564853bad1cc094adb5ac303a45d981058eea9e88fc0b7b2d
|
| 3 |
+
size 14244
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c7b5bf190dc871967c45091d9f1ab233b2d2ed62baca21fee5dfedb5718ffa5d
|
| 3 |
+
size 1064
|
trainer_state.json
ADDED
|
@@ -0,0 +1,2233 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.596169193934557,
|
| 5 |
+
"eval_steps": 10,
|
| 6 |
+
"global_step": 1000,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.007980845969672785,
|
| 13 |
+
"grad_norm": 0.7833889722824097,
|
| 14 |
+
"learning_rate": 0.00016,
|
| 15 |
+
"loss": 1.3081,
|
| 16 |
+
"step": 5
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.01596169193934557,
|
| 20 |
+
"grad_norm": 0.6466716527938843,
|
| 21 |
+
"learning_rate": 0.00012,
|
| 22 |
+
"loss": 1.2368,
|
| 23 |
+
"step": 10
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.01596169193934557,
|
| 27 |
+
"eval_loss": 1.2068681716918945,
|
| 28 |
+
"eval_runtime": 20.8667,
|
| 29 |
+
"eval_samples_per_second": 1.486,
|
| 30 |
+
"eval_steps_per_second": 0.767,
|
| 31 |
+
"step": 10
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.023942537909018357,
|
| 35 |
+
"grad_norm": 0.6432256698608398,
|
| 36 |
+
"learning_rate": 8e-05,
|
| 37 |
+
"loss": 1.1477,
|
| 38 |
+
"step": 15
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.03192338387869114,
|
| 42 |
+
"grad_norm": 0.6714484095573425,
|
| 43 |
+
"learning_rate": 4e-05,
|
| 44 |
+
"loss": 1.0776,
|
| 45 |
+
"step": 20
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.03192338387869114,
|
| 49 |
+
"eval_loss": 1.16266667842865,
|
| 50 |
+
"eval_runtime": 21.285,
|
| 51 |
+
"eval_samples_per_second": 1.456,
|
| 52 |
+
"eval_steps_per_second": 0.752,
|
| 53 |
+
"step": 20
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 0.03990422984836393,
|
| 57 |
+
"grad_norm": 0.6418822407722473,
|
| 58 |
+
"learning_rate": 0.0,
|
| 59 |
+
"loss": 1.1614,
|
| 60 |
+
"step": 25
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"epoch": 0.047885075818036714,
|
| 64 |
+
"grad_norm": 0.8091150522232056,
|
| 65 |
+
"learning_rate": 0.000194,
|
| 66 |
+
"loss": 1.1676,
|
| 67 |
+
"step": 30
|
| 68 |
+
},
|
| 69 |
+
{
|
| 70 |
+
"epoch": 0.047885075818036714,
|
| 71 |
+
"eval_loss": 1.151872992515564,
|
| 72 |
+
"eval_runtime": 21.3531,
|
| 73 |
+
"eval_samples_per_second": 1.452,
|
| 74 |
+
"eval_steps_per_second": 0.749,
|
| 75 |
+
"step": 30
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.055865921787709494,
|
| 79 |
+
"grad_norm": 0.7295385003089905,
|
| 80 |
+
"learning_rate": 0.000193,
|
| 81 |
+
"loss": 1.1319,
|
| 82 |
+
"step": 35
|
| 83 |
+
},
|
| 84 |
+
{
|
| 85 |
+
"epoch": 0.06384676775738228,
|
| 86 |
+
"grad_norm": 1.056991696357727,
|
| 87 |
+
"learning_rate": 0.000192,
|
| 88 |
+
"loss": 1.0188,
|
| 89 |
+
"step": 40
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 0.06384676775738228,
|
| 93 |
+
"eval_loss": 1.1241333484649658,
|
| 94 |
+
"eval_runtime": 21.3665,
|
| 95 |
+
"eval_samples_per_second": 1.451,
|
| 96 |
+
"eval_steps_per_second": 0.749,
|
| 97 |
+
"step": 40
|
| 98 |
+
},
|
| 99 |
+
{
|
| 100 |
+
"epoch": 0.07182761372705507,
|
| 101 |
+
"grad_norm": 0.7033870816230774,
|
| 102 |
+
"learning_rate": 0.000191,
|
| 103 |
+
"loss": 1.0331,
|
| 104 |
+
"step": 45
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.07980845969672785,
|
| 108 |
+
"grad_norm": 0.6337556838989258,
|
| 109 |
+
"learning_rate": 0.00019,
|
| 110 |
+
"loss": 1.1616,
|
| 111 |
+
"step": 50
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 0.07980845969672785,
|
| 115 |
+
"eval_loss": 1.1174383163452148,
|
| 116 |
+
"eval_runtime": 20.7909,
|
| 117 |
+
"eval_samples_per_second": 1.491,
|
| 118 |
+
"eval_steps_per_second": 0.77,
|
| 119 |
+
"step": 50
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 0.08778930566640064,
|
| 123 |
+
"grad_norm": 0.7127214074134827,
|
| 124 |
+
"learning_rate": 0.00018899999999999999,
|
| 125 |
+
"loss": 1.0874,
|
| 126 |
+
"step": 55
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 0.09577015163607343,
|
| 130 |
+
"grad_norm": 0.7299643158912659,
|
| 131 |
+
"learning_rate": 0.000188,
|
| 132 |
+
"loss": 1.0098,
|
| 133 |
+
"step": 60
|
| 134 |
+
},
|
| 135 |
+
{
|
| 136 |
+
"epoch": 0.09577015163607343,
|
| 137 |
+
"eval_loss": 1.106464147567749,
|
| 138 |
+
"eval_runtime": 21.2918,
|
| 139 |
+
"eval_samples_per_second": 1.456,
|
| 140 |
+
"eval_steps_per_second": 0.751,
|
| 141 |
+
"step": 60
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 0.10375099760574621,
|
| 145 |
+
"grad_norm": 0.7458897829055786,
|
| 146 |
+
"learning_rate": 0.00018700000000000002,
|
| 147 |
+
"loss": 1.0114,
|
| 148 |
+
"step": 65
|
| 149 |
+
},
|
| 150 |
+
{
|
| 151 |
+
"epoch": 0.11173184357541899,
|
| 152 |
+
"grad_norm": 0.7154062986373901,
|
| 153 |
+
"learning_rate": 0.00018600000000000002,
|
| 154 |
+
"loss": 1.0804,
|
| 155 |
+
"step": 70
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 0.11173184357541899,
|
| 159 |
+
"eval_loss": 1.087841510772705,
|
| 160 |
+
"eval_runtime": 21.2696,
|
| 161 |
+
"eval_samples_per_second": 1.457,
|
| 162 |
+
"eval_steps_per_second": 0.752,
|
| 163 |
+
"step": 70
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.11971268954509177,
|
| 167 |
+
"grad_norm": 0.630651593208313,
|
| 168 |
+
"learning_rate": 0.00018500000000000002,
|
| 169 |
+
"loss": 0.988,
|
| 170 |
+
"step": 75
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.12769353551476456,
|
| 174 |
+
"grad_norm": 0.6520997285842896,
|
| 175 |
+
"learning_rate": 0.00018400000000000003,
|
| 176 |
+
"loss": 0.9957,
|
| 177 |
+
"step": 80
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.12769353551476456,
|
| 181 |
+
"eval_loss": 1.0693910121917725,
|
| 182 |
+
"eval_runtime": 21.2801,
|
| 183 |
+
"eval_samples_per_second": 1.457,
|
| 184 |
+
"eval_steps_per_second": 0.752,
|
| 185 |
+
"step": 80
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.13567438148443736,
|
| 189 |
+
"grad_norm": 0.612789511680603,
|
| 190 |
+
"learning_rate": 0.000183,
|
| 191 |
+
"loss": 1.0659,
|
| 192 |
+
"step": 85
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.14365522745411013,
|
| 196 |
+
"grad_norm": 0.7308149337768555,
|
| 197 |
+
"learning_rate": 0.000182,
|
| 198 |
+
"loss": 1.0044,
|
| 199 |
+
"step": 90
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.14365522745411013,
|
| 203 |
+
"eval_loss": 1.0618408918380737,
|
| 204 |
+
"eval_runtime": 21.4836,
|
| 205 |
+
"eval_samples_per_second": 1.443,
|
| 206 |
+
"eval_steps_per_second": 0.745,
|
| 207 |
+
"step": 90
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 0.1516360734237829,
|
| 211 |
+
"grad_norm": 0.6600955724716187,
|
| 212 |
+
"learning_rate": 0.000181,
|
| 213 |
+
"loss": 0.936,
|
| 214 |
+
"step": 95
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"epoch": 0.1596169193934557,
|
| 218 |
+
"grad_norm": 0.5939749479293823,
|
| 219 |
+
"learning_rate": 0.00018,
|
| 220 |
+
"loss": 1.0213,
|
| 221 |
+
"step": 100
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 0.1596169193934557,
|
| 225 |
+
"eval_loss": 1.06107497215271,
|
| 226 |
+
"eval_runtime": 20.9063,
|
| 227 |
+
"eval_samples_per_second": 1.483,
|
| 228 |
+
"eval_steps_per_second": 0.765,
|
| 229 |
+
"step": 100
|
| 230 |
+
},
|
| 231 |
+
{
|
| 232 |
+
"epoch": 0.16759776536312848,
|
| 233 |
+
"grad_norm": 0.6475443840026855,
|
| 234 |
+
"learning_rate": 0.00017900000000000001,
|
| 235 |
+
"loss": 1.0099,
|
| 236 |
+
"step": 105
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 0.17557861133280128,
|
| 240 |
+
"grad_norm": 0.6048471927642822,
|
| 241 |
+
"learning_rate": 0.00017800000000000002,
|
| 242 |
+
"loss": 0.9587,
|
| 243 |
+
"step": 110
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 0.17557861133280128,
|
| 247 |
+
"eval_loss": 1.0483193397521973,
|
| 248 |
+
"eval_runtime": 21.4083,
|
| 249 |
+
"eval_samples_per_second": 1.448,
|
| 250 |
+
"eval_steps_per_second": 0.747,
|
| 251 |
+
"step": 110
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 0.18355945730247406,
|
| 255 |
+
"grad_norm": 0.5856403112411499,
|
| 256 |
+
"learning_rate": 0.00017700000000000002,
|
| 257 |
+
"loss": 0.9908,
|
| 258 |
+
"step": 115
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 0.19154030327214686,
|
| 262 |
+
"grad_norm": 0.6811533570289612,
|
| 263 |
+
"learning_rate": 0.00017600000000000002,
|
| 264 |
+
"loss": 0.9662,
|
| 265 |
+
"step": 120
|
| 266 |
+
},
|
| 267 |
+
{
|
| 268 |
+
"epoch": 0.19154030327214686,
|
| 269 |
+
"eval_loss": 1.055928349494934,
|
| 270 |
+
"eval_runtime": 21.2973,
|
| 271 |
+
"eval_samples_per_second": 1.456,
|
| 272 |
+
"eval_steps_per_second": 0.751,
|
| 273 |
+
"step": 120
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 0.19952114924181963,
|
| 277 |
+
"grad_norm": 0.5635804533958435,
|
| 278 |
+
"learning_rate": 0.000175,
|
| 279 |
+
"loss": 0.9637,
|
| 280 |
+
"step": 125
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 0.20750199521149243,
|
| 284 |
+
"grad_norm": 0.6101672053337097,
|
| 285 |
+
"learning_rate": 0.000174,
|
| 286 |
+
"loss": 0.9846,
|
| 287 |
+
"step": 130
|
| 288 |
+
},
|
| 289 |
+
{
|
| 290 |
+
"epoch": 0.20750199521149243,
|
| 291 |
+
"eval_loss": 1.0435600280761719,
|
| 292 |
+
"eval_runtime": 21.4526,
|
| 293 |
+
"eval_samples_per_second": 1.445,
|
| 294 |
+
"eval_steps_per_second": 0.746,
|
| 295 |
+
"step": 130
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 0.2154828411811652,
|
| 299 |
+
"grad_norm": 0.649726152420044,
|
| 300 |
+
"learning_rate": 0.000173,
|
| 301 |
+
"loss": 0.9995,
|
| 302 |
+
"step": 135
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 0.22346368715083798,
|
| 306 |
+
"grad_norm": 0.6642662286758423,
|
| 307 |
+
"learning_rate": 0.000172,
|
| 308 |
+
"loss": 0.9537,
|
| 309 |
+
"step": 140
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 0.22346368715083798,
|
| 313 |
+
"eval_loss": 1.0289674997329712,
|
| 314 |
+
"eval_runtime": 21.0765,
|
| 315 |
+
"eval_samples_per_second": 1.471,
|
| 316 |
+
"eval_steps_per_second": 0.759,
|
| 317 |
+
"step": 140
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.23144453312051078,
|
| 321 |
+
"grad_norm": 0.5957498550415039,
|
| 322 |
+
"learning_rate": 0.000171,
|
| 323 |
+
"loss": 1.0444,
|
| 324 |
+
"step": 145
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.23942537909018355,
|
| 328 |
+
"grad_norm": 0.7650970816612244,
|
| 329 |
+
"learning_rate": 0.00017,
|
| 330 |
+
"loss": 1.0177,
|
| 331 |
+
"step": 150
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.23942537909018355,
|
| 335 |
+
"eval_loss": 1.0302073955535889,
|
| 336 |
+
"eval_runtime": 21.0268,
|
| 337 |
+
"eval_samples_per_second": 1.474,
|
| 338 |
+
"eval_steps_per_second": 0.761,
|
| 339 |
+
"step": 150
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.24740622505985635,
|
| 343 |
+
"grad_norm": 0.6636956334114075,
|
| 344 |
+
"learning_rate": 0.00016900000000000002,
|
| 345 |
+
"loss": 0.9786,
|
| 346 |
+
"step": 155
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.2553870710295291,
|
| 350 |
+
"grad_norm": 0.7419523596763611,
|
| 351 |
+
"learning_rate": 0.000168,
|
| 352 |
+
"loss": 0.9837,
|
| 353 |
+
"step": 160
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.2553870710295291,
|
| 357 |
+
"eval_loss": 1.0296545028686523,
|
| 358 |
+
"eval_runtime": 21.4194,
|
| 359 |
+
"eval_samples_per_second": 1.447,
|
| 360 |
+
"eval_steps_per_second": 0.747,
|
| 361 |
+
"step": 160
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 0.2633679169992019,
|
| 365 |
+
"grad_norm": 0.5570073127746582,
|
| 366 |
+
"learning_rate": 0.000167,
|
| 367 |
+
"loss": 0.954,
|
| 368 |
+
"step": 165
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 0.2713487629688747,
|
| 372 |
+
"grad_norm": 0.5050713419914246,
|
| 373 |
+
"learning_rate": 0.000166,
|
| 374 |
+
"loss": 1.0796,
|
| 375 |
+
"step": 170
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 0.2713487629688747,
|
| 379 |
+
"eval_loss": 1.0314409732818604,
|
| 380 |
+
"eval_runtime": 21.4116,
|
| 381 |
+
"eval_samples_per_second": 1.448,
|
| 382 |
+
"eval_steps_per_second": 0.747,
|
| 383 |
+
"step": 170
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 0.27932960893854747,
|
| 387 |
+
"grad_norm": 0.48484355211257935,
|
| 388 |
+
"learning_rate": 0.000165,
|
| 389 |
+
"loss": 0.9461,
|
| 390 |
+
"step": 175
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 0.28731045490822027,
|
| 394 |
+
"grad_norm": 0.6661683320999146,
|
| 395 |
+
"learning_rate": 0.000164,
|
| 396 |
+
"loss": 1.0311,
|
| 397 |
+
"step": 180
|
| 398 |
+
},
|
| 399 |
+
{
|
| 400 |
+
"epoch": 0.28731045490822027,
|
| 401 |
+
"eval_loss": 1.0315138101577759,
|
| 402 |
+
"eval_runtime": 21.2472,
|
| 403 |
+
"eval_samples_per_second": 1.459,
|
| 404 |
+
"eval_steps_per_second": 0.753,
|
| 405 |
+
"step": 180
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 0.29529130087789307,
|
| 409 |
+
"grad_norm": 0.6185592412948608,
|
| 410 |
+
"learning_rate": 0.000163,
|
| 411 |
+
"loss": 0.9745,
|
| 412 |
+
"step": 185
|
| 413 |
+
},
|
| 414 |
+
{
|
| 415 |
+
"epoch": 0.3032721468475658,
|
| 416 |
+
"grad_norm": 0.5738425850868225,
|
| 417 |
+
"learning_rate": 0.000162,
|
| 418 |
+
"loss": 0.9619,
|
| 419 |
+
"step": 190
|
| 420 |
+
},
|
| 421 |
+
{
|
| 422 |
+
"epoch": 0.3032721468475658,
|
| 423 |
+
"eval_loss": 1.0191501379013062,
|
| 424 |
+
"eval_runtime": 21.0898,
|
| 425 |
+
"eval_samples_per_second": 1.47,
|
| 426 |
+
"eval_steps_per_second": 0.759,
|
| 427 |
+
"step": 190
|
| 428 |
+
},
|
| 429 |
+
{
|
| 430 |
+
"epoch": 0.3112529928172386,
|
| 431 |
+
"grad_norm": 0.6744123101234436,
|
| 432 |
+
"learning_rate": 0.000161,
|
| 433 |
+
"loss": 1.0097,
|
| 434 |
+
"step": 195
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 0.3192338387869114,
|
| 438 |
+
"grad_norm": 0.7204273343086243,
|
| 439 |
+
"learning_rate": 0.00016,
|
| 440 |
+
"loss": 0.9916,
|
| 441 |
+
"step": 200
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 0.3192338387869114,
|
| 445 |
+
"eval_loss": 1.0153534412384033,
|
| 446 |
+
"eval_runtime": 21.3333,
|
| 447 |
+
"eval_samples_per_second": 1.453,
|
| 448 |
+
"eval_steps_per_second": 0.75,
|
| 449 |
+
"step": 200
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 0.3272146847565842,
|
| 453 |
+
"grad_norm": 0.6031942367553711,
|
| 454 |
+
"learning_rate": 0.00015900000000000002,
|
| 455 |
+
"loss": 0.9673,
|
| 456 |
+
"step": 205
|
| 457 |
+
},
|
| 458 |
+
{
|
| 459 |
+
"epoch": 0.33519553072625696,
|
| 460 |
+
"grad_norm": 0.5967186689376831,
|
| 461 |
+
"learning_rate": 0.00015800000000000002,
|
| 462 |
+
"loss": 0.9655,
|
| 463 |
+
"step": 210
|
| 464 |
+
},
|
| 465 |
+
{
|
| 466 |
+
"epoch": 0.33519553072625696,
|
| 467 |
+
"eval_loss": 1.0138649940490723,
|
| 468 |
+
"eval_runtime": 21.1862,
|
| 469 |
+
"eval_samples_per_second": 1.463,
|
| 470 |
+
"eval_steps_per_second": 0.755,
|
| 471 |
+
"step": 210
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.34317637669592976,
|
| 475 |
+
"grad_norm": 0.6408796906471252,
|
| 476 |
+
"learning_rate": 0.00015700000000000002,
|
| 477 |
+
"loss": 0.9453,
|
| 478 |
+
"step": 215
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 0.35115722266560256,
|
| 482 |
+
"grad_norm": 0.6557004451751709,
|
| 483 |
+
"learning_rate": 0.00015600000000000002,
|
| 484 |
+
"loss": 0.9536,
|
| 485 |
+
"step": 220
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.35115722266560256,
|
| 489 |
+
"eval_loss": 1.0107518434524536,
|
| 490 |
+
"eval_runtime": 21.3902,
|
| 491 |
+
"eval_samples_per_second": 1.449,
|
| 492 |
+
"eval_steps_per_second": 0.748,
|
| 493 |
+
"step": 220
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 0.35913806863527536,
|
| 497 |
+
"grad_norm": 0.6112158894538879,
|
| 498 |
+
"learning_rate": 0.000155,
|
| 499 |
+
"loss": 0.9645,
|
| 500 |
+
"step": 225
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 0.3671189146049481,
|
| 504 |
+
"grad_norm": 0.6465075016021729,
|
| 505 |
+
"learning_rate": 0.000154,
|
| 506 |
+
"loss": 1.0773,
|
| 507 |
+
"step": 230
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.3671189146049481,
|
| 511 |
+
"eval_loss": 1.004480242729187,
|
| 512 |
+
"eval_runtime": 21.1771,
|
| 513 |
+
"eval_samples_per_second": 1.464,
|
| 514 |
+
"eval_steps_per_second": 0.756,
|
| 515 |
+
"step": 230
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 0.3750997605746209,
|
| 519 |
+
"grad_norm": 0.7187998294830322,
|
| 520 |
+
"learning_rate": 0.000153,
|
| 521 |
+
"loss": 0.9467,
|
| 522 |
+
"step": 235
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 0.3830806065442937,
|
| 526 |
+
"grad_norm": 0.8026754260063171,
|
| 527 |
+
"learning_rate": 0.000152,
|
| 528 |
+
"loss": 0.9329,
|
| 529 |
+
"step": 240
|
| 530 |
+
},
|
| 531 |
+
{
|
| 532 |
+
"epoch": 0.3830806065442937,
|
| 533 |
+
"eval_loss": 0.9965100288391113,
|
| 534 |
+
"eval_runtime": 21.1786,
|
| 535 |
+
"eval_samples_per_second": 1.464,
|
| 536 |
+
"eval_steps_per_second": 0.755,
|
| 537 |
+
"step": 240
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 0.39106145251396646,
|
| 541 |
+
"grad_norm": 0.6788911819458008,
|
| 542 |
+
"learning_rate": 0.000151,
|
| 543 |
+
"loss": 0.8683,
|
| 544 |
+
"step": 245
|
| 545 |
+
},
|
| 546 |
+
{
|
| 547 |
+
"epoch": 0.39904229848363926,
|
| 548 |
+
"grad_norm": 0.6607213020324707,
|
| 549 |
+
"learning_rate": 0.00015000000000000001,
|
| 550 |
+
"loss": 0.9826,
|
| 551 |
+
"step": 250
|
| 552 |
+
},
|
| 553 |
+
{
|
| 554 |
+
"epoch": 0.39904229848363926,
|
| 555 |
+
"eval_loss": 1.0054864883422852,
|
| 556 |
+
"eval_runtime": 21.1094,
|
| 557 |
+
"eval_samples_per_second": 1.469,
|
| 558 |
+
"eval_steps_per_second": 0.758,
|
| 559 |
+
"step": 250
|
| 560 |
+
},
|
| 561 |
+
{
|
| 562 |
+
"epoch": 0.40702314445331206,
|
| 563 |
+
"grad_norm": 0.6742439866065979,
|
| 564 |
+
"learning_rate": 0.00014900000000000002,
|
| 565 |
+
"loss": 0.9507,
|
| 566 |
+
"step": 255
|
| 567 |
+
},
|
| 568 |
+
{
|
| 569 |
+
"epoch": 0.41500399042298486,
|
| 570 |
+
"grad_norm": 0.7669168710708618,
|
| 571 |
+
"learning_rate": 0.000148,
|
| 572 |
+
"loss": 0.9609,
|
| 573 |
+
"step": 260
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 0.41500399042298486,
|
| 577 |
+
"eval_loss": 1.0046597719192505,
|
| 578 |
+
"eval_runtime": 21.2545,
|
| 579 |
+
"eval_samples_per_second": 1.459,
|
| 580 |
+
"eval_steps_per_second": 0.753,
|
| 581 |
+
"step": 260
|
| 582 |
+
},
|
| 583 |
+
{
|
| 584 |
+
"epoch": 0.4229848363926576,
|
| 585 |
+
"grad_norm": 0.6186738014221191,
|
| 586 |
+
"learning_rate": 0.000147,
|
| 587 |
+
"loss": 0.9875,
|
| 588 |
+
"step": 265
|
| 589 |
+
},
|
| 590 |
+
{
|
| 591 |
+
"epoch": 0.4309656823623304,
|
| 592 |
+
"grad_norm": 0.633393406867981,
|
| 593 |
+
"learning_rate": 0.000146,
|
| 594 |
+
"loss": 0.9949,
|
| 595 |
+
"step": 270
|
| 596 |
+
},
|
| 597 |
+
{
|
| 598 |
+
"epoch": 0.4309656823623304,
|
| 599 |
+
"eval_loss": 0.9924024343490601,
|
| 600 |
+
"eval_runtime": 20.9746,
|
| 601 |
+
"eval_samples_per_second": 1.478,
|
| 602 |
+
"eval_steps_per_second": 0.763,
|
| 603 |
+
"step": 270
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 0.4389465283320032,
|
| 607 |
+
"grad_norm": 0.5856119394302368,
|
| 608 |
+
"learning_rate": 0.000145,
|
| 609 |
+
"loss": 0.9611,
|
| 610 |
+
"step": 275
|
| 611 |
+
},
|
| 612 |
+
{
|
| 613 |
+
"epoch": 0.44692737430167595,
|
| 614 |
+
"grad_norm": 0.5712947249412537,
|
| 615 |
+
"learning_rate": 0.000144,
|
| 616 |
+
"loss": 1.0001,
|
| 617 |
+
"step": 280
|
| 618 |
+
},
|
| 619 |
+
{
|
| 620 |
+
"epoch": 0.44692737430167595,
|
| 621 |
+
"eval_loss": 0.9949964284896851,
|
| 622 |
+
"eval_runtime": 21.5928,
|
| 623 |
+
"eval_samples_per_second": 1.436,
|
| 624 |
+
"eval_steps_per_second": 0.741,
|
| 625 |
+
"step": 280
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.45490822027134875,
|
| 629 |
+
"grad_norm": 0.6601425409317017,
|
| 630 |
+
"learning_rate": 0.000143,
|
| 631 |
+
"loss": 0.9198,
|
| 632 |
+
"step": 285
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 0.46288906624102155,
|
| 636 |
+
"grad_norm": 0.6215651631355286,
|
| 637 |
+
"learning_rate": 0.000142,
|
| 638 |
+
"loss": 1.0944,
|
| 639 |
+
"step": 290
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.46288906624102155,
|
| 643 |
+
"eval_loss": 0.9959576725959778,
|
| 644 |
+
"eval_runtime": 21.3626,
|
| 645 |
+
"eval_samples_per_second": 1.451,
|
| 646 |
+
"eval_steps_per_second": 0.749,
|
| 647 |
+
"step": 290
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 0.47086991221069435,
|
| 651 |
+
"grad_norm": 0.6404448747634888,
|
| 652 |
+
"learning_rate": 0.000141,
|
| 653 |
+
"loss": 0.9556,
|
| 654 |
+
"step": 295
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 0.4788507581803671,
|
| 658 |
+
"grad_norm": 0.6889925003051758,
|
| 659 |
+
"learning_rate": 0.00014,
|
| 660 |
+
"loss": 1.011,
|
| 661 |
+
"step": 300
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 0.4788507581803671,
|
| 665 |
+
"eval_loss": 0.9947748780250549,
|
| 666 |
+
"eval_runtime": 21.4252,
|
| 667 |
+
"eval_samples_per_second": 1.447,
|
| 668 |
+
"eval_steps_per_second": 0.747,
|
| 669 |
+
"step": 300
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 0.4868316041500399,
|
| 673 |
+
"grad_norm": 0.6349315047264099,
|
| 674 |
+
"learning_rate": 0.000139,
|
| 675 |
+
"loss": 0.9343,
|
| 676 |
+
"step": 305
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 0.4948124501197127,
|
| 680 |
+
"grad_norm": 0.753274142742157,
|
| 681 |
+
"learning_rate": 0.000138,
|
| 682 |
+
"loss": 0.9356,
|
| 683 |
+
"step": 310
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 0.4948124501197127,
|
| 687 |
+
"eval_loss": 0.9897598624229431,
|
| 688 |
+
"eval_runtime": 21.7041,
|
| 689 |
+
"eval_samples_per_second": 1.428,
|
| 690 |
+
"eval_steps_per_second": 0.737,
|
| 691 |
+
"step": 310
|
| 692 |
+
},
|
| 693 |
+
{
|
| 694 |
+
"epoch": 0.5027932960893855,
|
| 695 |
+
"grad_norm": 0.6351450085639954,
|
| 696 |
+
"learning_rate": 0.00013700000000000002,
|
| 697 |
+
"loss": 0.9691,
|
| 698 |
+
"step": 315
|
| 699 |
+
},
|
| 700 |
+
{
|
| 701 |
+
"epoch": 0.5107741420590582,
|
| 702 |
+
"grad_norm": 0.6660261154174805,
|
| 703 |
+
"learning_rate": 0.00013600000000000003,
|
| 704 |
+
"loss": 0.9213,
|
| 705 |
+
"step": 320
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 0.5107741420590582,
|
| 709 |
+
"eval_loss": 0.9789547920227051,
|
| 710 |
+
"eval_runtime": 20.997,
|
| 711 |
+
"eval_samples_per_second": 1.476,
|
| 712 |
+
"eval_steps_per_second": 0.762,
|
| 713 |
+
"step": 320
|
| 714 |
+
},
|
| 715 |
+
{
|
| 716 |
+
"epoch": 0.518754988028731,
|
| 717 |
+
"grad_norm": 0.7038460969924927,
|
| 718 |
+
"learning_rate": 0.00013500000000000003,
|
| 719 |
+
"loss": 0.8654,
|
| 720 |
+
"step": 325
|
| 721 |
+
},
|
| 722 |
+
{
|
| 723 |
+
"epoch": 0.5267358339984038,
|
| 724 |
+
"grad_norm": 0.6426422595977783,
|
| 725 |
+
"learning_rate": 0.000134,
|
| 726 |
+
"loss": 0.8611,
|
| 727 |
+
"step": 330
|
| 728 |
+
},
|
| 729 |
+
{
|
| 730 |
+
"epoch": 0.5267358339984038,
|
| 731 |
+
"eval_loss": 0.9792807698249817,
|
| 732 |
+
"eval_runtime": 20.7975,
|
| 733 |
+
"eval_samples_per_second": 1.491,
|
| 734 |
+
"eval_steps_per_second": 0.769,
|
| 735 |
+
"step": 330
|
| 736 |
+
},
|
| 737 |
+
{
|
| 738 |
+
"epoch": 0.5347166799680766,
|
| 739 |
+
"grad_norm": 0.5722155570983887,
|
| 740 |
+
"learning_rate": 0.000133,
|
| 741 |
+
"loss": 0.961,
|
| 742 |
+
"step": 335
|
| 743 |
+
},
|
| 744 |
+
{
|
| 745 |
+
"epoch": 0.5426975259377494,
|
| 746 |
+
"grad_norm": 0.7792693376541138,
|
| 747 |
+
"learning_rate": 0.000132,
|
| 748 |
+
"loss": 0.9647,
|
| 749 |
+
"step": 340
|
| 750 |
+
},
|
| 751 |
+
{
|
| 752 |
+
"epoch": 0.5426975259377494,
|
| 753 |
+
"eval_loss": 0.9812614321708679,
|
| 754 |
+
"eval_runtime": 21.6024,
|
| 755 |
+
"eval_samples_per_second": 1.435,
|
| 756 |
+
"eval_steps_per_second": 0.741,
|
| 757 |
+
"step": 340
|
| 758 |
+
},
|
| 759 |
+
{
|
| 760 |
+
"epoch": 0.5506783719074222,
|
| 761 |
+
"grad_norm": 0.7510095834732056,
|
| 762 |
+
"learning_rate": 0.000131,
|
| 763 |
+
"loss": 0.817,
|
| 764 |
+
"step": 345
|
| 765 |
+
},
|
| 766 |
+
{
|
| 767 |
+
"epoch": 0.5586592178770949,
|
| 768 |
+
"grad_norm": 0.6685438752174377,
|
| 769 |
+
"learning_rate": 0.00013000000000000002,
|
| 770 |
+
"loss": 0.8392,
|
| 771 |
+
"step": 350
|
| 772 |
+
},
|
| 773 |
+
{
|
| 774 |
+
"epoch": 0.5586592178770949,
|
| 775 |
+
"eval_loss": 0.9788187742233276,
|
| 776 |
+
"eval_runtime": 21.2885,
|
| 777 |
+
"eval_samples_per_second": 1.456,
|
| 778 |
+
"eval_steps_per_second": 0.752,
|
| 779 |
+
"step": 350
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 0.5666400638467678,
|
| 783 |
+
"grad_norm": 0.6660378575325012,
|
| 784 |
+
"learning_rate": 0.00012900000000000002,
|
| 785 |
+
"loss": 0.9494,
|
| 786 |
+
"step": 355
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 0.5746209098164405,
|
| 790 |
+
"grad_norm": 0.6914508938789368,
|
| 791 |
+
"learning_rate": 0.00012800000000000002,
|
| 792 |
+
"loss": 1.0105,
|
| 793 |
+
"step": 360
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 0.5746209098164405,
|
| 797 |
+
"eval_loss": 0.9770519733428955,
|
| 798 |
+
"eval_runtime": 21.0568,
|
| 799 |
+
"eval_samples_per_second": 1.472,
|
| 800 |
+
"eval_steps_per_second": 0.76,
|
| 801 |
+
"step": 360
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 0.5826017557861133,
|
| 805 |
+
"grad_norm": 0.665715217590332,
|
| 806 |
+
"learning_rate": 0.000127,
|
| 807 |
+
"loss": 0.9159,
|
| 808 |
+
"step": 365
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 0.5905826017557861,
|
| 812 |
+
"grad_norm": 0.686400830745697,
|
| 813 |
+
"learning_rate": 0.000126,
|
| 814 |
+
"loss": 1.0525,
|
| 815 |
+
"step": 370
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 0.5905826017557861,
|
| 819 |
+
"eval_loss": 0.9769095778465271,
|
| 820 |
+
"eval_runtime": 20.9592,
|
| 821 |
+
"eval_samples_per_second": 1.479,
|
| 822 |
+
"eval_steps_per_second": 0.763,
|
| 823 |
+
"step": 370
|
| 824 |
+
},
|
| 825 |
+
{
|
| 826 |
+
"epoch": 0.5985634477254589,
|
| 827 |
+
"grad_norm": 0.6291290521621704,
|
| 828 |
+
"learning_rate": 0.000125,
|
| 829 |
+
"loss": 0.801,
|
| 830 |
+
"step": 375
|
| 831 |
+
},
|
| 832 |
+
{
|
| 833 |
+
"epoch": 0.6065442936951316,
|
| 834 |
+
"grad_norm": 0.7124271988868713,
|
| 835 |
+
"learning_rate": 0.000124,
|
| 836 |
+
"loss": 0.8913,
|
| 837 |
+
"step": 380
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 0.6065442936951316,
|
| 841 |
+
"eval_loss": 0.9799799919128418,
|
| 842 |
+
"eval_runtime": 21.397,
|
| 843 |
+
"eval_samples_per_second": 1.449,
|
| 844 |
+
"eval_steps_per_second": 0.748,
|
| 845 |
+
"step": 380
|
| 846 |
+
},
|
| 847 |
+
{
|
| 848 |
+
"epoch": 0.6145251396648045,
|
| 849 |
+
"grad_norm": 0.8505049347877502,
|
| 850 |
+
"learning_rate": 0.000123,
|
| 851 |
+
"loss": 0.9319,
|
| 852 |
+
"step": 385
|
| 853 |
+
},
|
| 854 |
+
{
|
| 855 |
+
"epoch": 0.6225059856344772,
|
| 856 |
+
"grad_norm": 0.7308720350265503,
|
| 857 |
+
"learning_rate": 0.000122,
|
| 858 |
+
"loss": 0.8906,
|
| 859 |
+
"step": 390
|
| 860 |
+
},
|
| 861 |
+
{
|
| 862 |
+
"epoch": 0.6225059856344772,
|
| 863 |
+
"eval_loss": 0.9712496995925903,
|
| 864 |
+
"eval_runtime": 21.2172,
|
| 865 |
+
"eval_samples_per_second": 1.461,
|
| 866 |
+
"eval_steps_per_second": 0.754,
|
| 867 |
+
"step": 390
|
| 868 |
+
},
|
| 869 |
+
{
|
| 870 |
+
"epoch": 0.6304868316041501,
|
| 871 |
+
"grad_norm": 0.6782912611961365,
|
| 872 |
+
"learning_rate": 0.000121,
|
| 873 |
+
"loss": 0.8928,
|
| 874 |
+
"step": 395
|
| 875 |
+
},
|
| 876 |
+
{
|
| 877 |
+
"epoch": 0.6384676775738228,
|
| 878 |
+
"grad_norm": 0.5951765179634094,
|
| 879 |
+
"learning_rate": 0.00012,
|
| 880 |
+
"loss": 0.9059,
|
| 881 |
+
"step": 400
|
| 882 |
+
},
|
| 883 |
+
{
|
| 884 |
+
"epoch": 0.6384676775738228,
|
| 885 |
+
"eval_loss": 0.9641667008399963,
|
| 886 |
+
"eval_runtime": 20.89,
|
| 887 |
+
"eval_samples_per_second": 1.484,
|
| 888 |
+
"eval_steps_per_second": 0.766,
|
| 889 |
+
"step": 400
|
| 890 |
+
},
|
| 891 |
+
{
|
| 892 |
+
"epoch": 0.6464485235434956,
|
| 893 |
+
"grad_norm": 0.7105025053024292,
|
| 894 |
+
"learning_rate": 0.000119,
|
| 895 |
+
"loss": 0.8986,
|
| 896 |
+
"step": 405
|
| 897 |
+
},
|
| 898 |
+
{
|
| 899 |
+
"epoch": 0.6544293695131684,
|
| 900 |
+
"grad_norm": 0.835155725479126,
|
| 901 |
+
"learning_rate": 0.000118,
|
| 902 |
+
"loss": 0.9309,
|
| 903 |
+
"step": 410
|
| 904 |
+
},
|
| 905 |
+
{
|
| 906 |
+
"epoch": 0.6544293695131684,
|
| 907 |
+
"eval_loss": 0.9708338975906372,
|
| 908 |
+
"eval_runtime": 21.5141,
|
| 909 |
+
"eval_samples_per_second": 1.441,
|
| 910 |
+
"eval_steps_per_second": 0.744,
|
| 911 |
+
"step": 410
|
| 912 |
+
},
|
| 913 |
+
{
|
| 914 |
+
"epoch": 0.6624102154828412,
|
| 915 |
+
"grad_norm": 0.7432790994644165,
|
| 916 |
+
"learning_rate": 0.000117,
|
| 917 |
+
"loss": 0.9653,
|
| 918 |
+
"step": 415
|
| 919 |
+
},
|
| 920 |
+
{
|
| 921 |
+
"epoch": 0.6703910614525139,
|
| 922 |
+
"grad_norm": 0.590387761592865,
|
| 923 |
+
"learning_rate": 0.000116,
|
| 924 |
+
"loss": 0.8429,
|
| 925 |
+
"step": 420
|
| 926 |
+
},
|
| 927 |
+
{
|
| 928 |
+
"epoch": 0.6703910614525139,
|
| 929 |
+
"eval_loss": 0.9680631160736084,
|
| 930 |
+
"eval_runtime": 21.0468,
|
| 931 |
+
"eval_samples_per_second": 1.473,
|
| 932 |
+
"eval_steps_per_second": 0.76,
|
| 933 |
+
"step": 420
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 0.6783719074221868,
|
| 937 |
+
"grad_norm": 0.6864650249481201,
|
| 938 |
+
"learning_rate": 0.00011499999999999999,
|
| 939 |
+
"loss": 0.9585,
|
| 940 |
+
"step": 425
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 0.6863527533918595,
|
| 944 |
+
"grad_norm": 0.6845282912254333,
|
| 945 |
+
"learning_rate": 0.00011399999999999999,
|
| 946 |
+
"loss": 0.9032,
|
| 947 |
+
"step": 430
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 0.6863527533918595,
|
| 951 |
+
"eval_loss": 0.96528559923172,
|
| 952 |
+
"eval_runtime": 21.6521,
|
| 953 |
+
"eval_samples_per_second": 1.432,
|
| 954 |
+
"eval_steps_per_second": 0.739,
|
| 955 |
+
"step": 430
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 0.6943335993615323,
|
| 959 |
+
"grad_norm": 0.717858612537384,
|
| 960 |
+
"learning_rate": 0.000113,
|
| 961 |
+
"loss": 0.9401,
|
| 962 |
+
"step": 435
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 0.7023144453312051,
|
| 966 |
+
"grad_norm": 0.6566243171691895,
|
| 967 |
+
"learning_rate": 0.00011200000000000001,
|
| 968 |
+
"loss": 0.85,
|
| 969 |
+
"step": 440
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 0.7023144453312051,
|
| 973 |
+
"eval_loss": 0.9651073217391968,
|
| 974 |
+
"eval_runtime": 21.2202,
|
| 975 |
+
"eval_samples_per_second": 1.461,
|
| 976 |
+
"eval_steps_per_second": 0.754,
|
| 977 |
+
"step": 440
|
| 978 |
+
},
|
| 979 |
+
{
|
| 980 |
+
"epoch": 0.7102952913008779,
|
| 981 |
+
"grad_norm": 0.6869224905967712,
|
| 982 |
+
"learning_rate": 0.00011100000000000001,
|
| 983 |
+
"loss": 0.8701,
|
| 984 |
+
"step": 445
|
| 985 |
+
},
|
| 986 |
+
{
|
| 987 |
+
"epoch": 0.7182761372705507,
|
| 988 |
+
"grad_norm": 0.5897542834281921,
|
| 989 |
+
"learning_rate": 0.00011000000000000002,
|
| 990 |
+
"loss": 0.9531,
|
| 991 |
+
"step": 450
|
| 992 |
+
},
|
| 993 |
+
{
|
| 994 |
+
"epoch": 0.7182761372705507,
|
| 995 |
+
"eval_loss": 0.9623759984970093,
|
| 996 |
+
"eval_runtime": 21.1274,
|
| 997 |
+
"eval_samples_per_second": 1.467,
|
| 998 |
+
"eval_steps_per_second": 0.757,
|
| 999 |
+
"step": 450
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 0.7262569832402235,
|
| 1003 |
+
"grad_norm": 0.7018331289291382,
|
| 1004 |
+
"learning_rate": 0.000109,
|
| 1005 |
+
"loss": 0.8888,
|
| 1006 |
+
"step": 455
|
| 1007 |
+
},
|
| 1008 |
+
{
|
| 1009 |
+
"epoch": 0.7342378292098962,
|
| 1010 |
+
"grad_norm": 0.6487181186676025,
|
| 1011 |
+
"learning_rate": 0.00010800000000000001,
|
| 1012 |
+
"loss": 0.8862,
|
| 1013 |
+
"step": 460
|
| 1014 |
+
},
|
| 1015 |
+
{
|
| 1016 |
+
"epoch": 0.7342378292098962,
|
| 1017 |
+
"eval_loss": 0.9587427973747253,
|
| 1018 |
+
"eval_runtime": 21.6398,
|
| 1019 |
+
"eval_samples_per_second": 1.433,
|
| 1020 |
+
"eval_steps_per_second": 0.739,
|
| 1021 |
+
"step": 460
|
| 1022 |
+
},
|
| 1023 |
+
{
|
| 1024 |
+
"epoch": 0.7422186751795691,
|
| 1025 |
+
"grad_norm": 0.8121400475502014,
|
| 1026 |
+
"learning_rate": 0.00010700000000000001,
|
| 1027 |
+
"loss": 0.8856,
|
| 1028 |
+
"step": 465
|
| 1029 |
+
},
|
| 1030 |
+
{
|
| 1031 |
+
"epoch": 0.7501995211492418,
|
| 1032 |
+
"grad_norm": 0.6554559469223022,
|
| 1033 |
+
"learning_rate": 0.00010600000000000002,
|
| 1034 |
+
"loss": 0.8736,
|
| 1035 |
+
"step": 470
|
| 1036 |
+
},
|
| 1037 |
+
{
|
| 1038 |
+
"epoch": 0.7501995211492418,
|
| 1039 |
+
"eval_loss": 0.9547150731086731,
|
| 1040 |
+
"eval_runtime": 21.1236,
|
| 1041 |
+
"eval_samples_per_second": 1.468,
|
| 1042 |
+
"eval_steps_per_second": 0.757,
|
| 1043 |
+
"step": 470
|
| 1044 |
+
},
|
| 1045 |
+
{
|
| 1046 |
+
"epoch": 0.7581803671189146,
|
| 1047 |
+
"grad_norm": 0.7241584062576294,
|
| 1048 |
+
"learning_rate": 0.000105,
|
| 1049 |
+
"loss": 0.8002,
|
| 1050 |
+
"step": 475
|
| 1051 |
+
},
|
| 1052 |
+
{
|
| 1053 |
+
"epoch": 0.7661612130885874,
|
| 1054 |
+
"grad_norm": 0.7639961242675781,
|
| 1055 |
+
"learning_rate": 0.00010400000000000001,
|
| 1056 |
+
"loss": 0.93,
|
| 1057 |
+
"step": 480
|
| 1058 |
+
},
|
| 1059 |
+
{
|
| 1060 |
+
"epoch": 0.7661612130885874,
|
| 1061 |
+
"eval_loss": 0.9609348773956299,
|
| 1062 |
+
"eval_runtime": 21.2046,
|
| 1063 |
+
"eval_samples_per_second": 1.462,
|
| 1064 |
+
"eval_steps_per_second": 0.755,
|
| 1065 |
+
"step": 480
|
| 1066 |
+
},
|
| 1067 |
+
{
|
| 1068 |
+
"epoch": 0.7741420590582602,
|
| 1069 |
+
"grad_norm": 0.6694309115409851,
|
| 1070 |
+
"learning_rate": 0.00010300000000000001,
|
| 1071 |
+
"loss": 0.8696,
|
| 1072 |
+
"step": 485
|
| 1073 |
+
},
|
| 1074 |
+
{
|
| 1075 |
+
"epoch": 0.7821229050279329,
|
| 1076 |
+
"grad_norm": 0.6586005687713623,
|
| 1077 |
+
"learning_rate": 0.00010200000000000001,
|
| 1078 |
+
"loss": 0.9035,
|
| 1079 |
+
"step": 490
|
| 1080 |
+
},
|
| 1081 |
+
{
|
| 1082 |
+
"epoch": 0.7821229050279329,
|
| 1083 |
+
"eval_loss": 0.9565220475196838,
|
| 1084 |
+
"eval_runtime": 21.5471,
|
| 1085 |
+
"eval_samples_per_second": 1.439,
|
| 1086 |
+
"eval_steps_per_second": 0.743,
|
| 1087 |
+
"step": 490
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 0.7901037509976058,
|
| 1091 |
+
"grad_norm": 0.6772391200065613,
|
| 1092 |
+
"learning_rate": 0.000101,
|
| 1093 |
+
"loss": 0.9016,
|
| 1094 |
+
"step": 495
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 0.7980845969672785,
|
| 1098 |
+
"grad_norm": 0.7700143456459045,
|
| 1099 |
+
"learning_rate": 0.0001,
|
| 1100 |
+
"loss": 0.8871,
|
| 1101 |
+
"step": 500
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 0.7980845969672785,
|
| 1105 |
+
"eval_loss": 0.9532312750816345,
|
| 1106 |
+
"eval_runtime": 21.3527,
|
| 1107 |
+
"eval_samples_per_second": 1.452,
|
| 1108 |
+
"eval_steps_per_second": 0.749,
|
| 1109 |
+
"step": 500
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 0.8060654429369514,
|
| 1113 |
+
"grad_norm": 0.7088077068328857,
|
| 1114 |
+
"learning_rate": 9.900000000000001e-05,
|
| 1115 |
+
"loss": 0.9628,
|
| 1116 |
+
"step": 505
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 0.8140462889066241,
|
| 1120 |
+
"grad_norm": 0.7058229446411133,
|
| 1121 |
+
"learning_rate": 9.8e-05,
|
| 1122 |
+
"loss": 0.8395,
|
| 1123 |
+
"step": 510
|
| 1124 |
+
},
|
| 1125 |
+
{
|
| 1126 |
+
"epoch": 0.8140462889066241,
|
| 1127 |
+
"eval_loss": 0.9453433752059937,
|
| 1128 |
+
"eval_runtime": 20.6711,
|
| 1129 |
+
"eval_samples_per_second": 1.5,
|
| 1130 |
+
"eval_steps_per_second": 0.774,
|
| 1131 |
+
"step": 510
|
| 1132 |
+
},
|
| 1133 |
+
{
|
| 1134 |
+
"epoch": 0.8220271348762969,
|
| 1135 |
+
"grad_norm": 0.6609935164451599,
|
| 1136 |
+
"learning_rate": 9.7e-05,
|
| 1137 |
+
"loss": 0.8693,
|
| 1138 |
+
"step": 515
|
| 1139 |
+
},
|
| 1140 |
+
{
|
| 1141 |
+
"epoch": 0.8300079808459697,
|
| 1142 |
+
"grad_norm": 0.8539516925811768,
|
| 1143 |
+
"learning_rate": 9.6e-05,
|
| 1144 |
+
"loss": 0.8661,
|
| 1145 |
+
"step": 520
|
| 1146 |
+
},
|
| 1147 |
+
{
|
| 1148 |
+
"epoch": 0.8300079808459697,
|
| 1149 |
+
"eval_loss": 0.9413149356842041,
|
| 1150 |
+
"eval_runtime": 21.4056,
|
| 1151 |
+
"eval_samples_per_second": 1.448,
|
| 1152 |
+
"eval_steps_per_second": 0.747,
|
| 1153 |
+
"step": 520
|
| 1154 |
+
},
|
| 1155 |
+
{
|
| 1156 |
+
"epoch": 0.8379888268156425,
|
| 1157 |
+
"grad_norm": 0.6991361975669861,
|
| 1158 |
+
"learning_rate": 9.5e-05,
|
| 1159 |
+
"loss": 1.0091,
|
| 1160 |
+
"step": 525
|
| 1161 |
+
},
|
| 1162 |
+
{
|
| 1163 |
+
"epoch": 0.8459696727853152,
|
| 1164 |
+
"grad_norm": 0.6568119525909424,
|
| 1165 |
+
"learning_rate": 9.4e-05,
|
| 1166 |
+
"loss": 0.8034,
|
| 1167 |
+
"step": 530
|
| 1168 |
+
},
|
| 1169 |
+
{
|
| 1170 |
+
"epoch": 0.8459696727853152,
|
| 1171 |
+
"eval_loss": 0.942388117313385,
|
| 1172 |
+
"eval_runtime": 21.1726,
|
| 1173 |
+
"eval_samples_per_second": 1.464,
|
| 1174 |
+
"eval_steps_per_second": 0.756,
|
| 1175 |
+
"step": 530
|
| 1176 |
+
},
|
| 1177 |
+
{
|
| 1178 |
+
"epoch": 0.8539505187549881,
|
| 1179 |
+
"grad_norm": 0.6941240429878235,
|
| 1180 |
+
"learning_rate": 9.300000000000001e-05,
|
| 1181 |
+
"loss": 0.8947,
|
| 1182 |
+
"step": 535
|
| 1183 |
+
},
|
| 1184 |
+
{
|
| 1185 |
+
"epoch": 0.8619313647246608,
|
| 1186 |
+
"grad_norm": 0.717548131942749,
|
| 1187 |
+
"learning_rate": 9.200000000000001e-05,
|
| 1188 |
+
"loss": 0.9049,
|
| 1189 |
+
"step": 540
|
| 1190 |
+
},
|
| 1191 |
+
{
|
| 1192 |
+
"epoch": 0.8619313647246608,
|
| 1193 |
+
"eval_loss": 0.9332796335220337,
|
| 1194 |
+
"eval_runtime": 21.1935,
|
| 1195 |
+
"eval_samples_per_second": 1.463,
|
| 1196 |
+
"eval_steps_per_second": 0.755,
|
| 1197 |
+
"step": 540
|
| 1198 |
+
},
|
| 1199 |
+
{
|
| 1200 |
+
"epoch": 0.8699122106943336,
|
| 1201 |
+
"grad_norm": 0.6851376295089722,
|
| 1202 |
+
"learning_rate": 9.1e-05,
|
| 1203 |
+
"loss": 0.9446,
|
| 1204 |
+
"step": 545
|
| 1205 |
+
},
|
| 1206 |
+
{
|
| 1207 |
+
"epoch": 0.8778930566640064,
|
| 1208 |
+
"grad_norm": 0.7654580473899841,
|
| 1209 |
+
"learning_rate": 9e-05,
|
| 1210 |
+
"loss": 0.8878,
|
| 1211 |
+
"step": 550
|
| 1212 |
+
},
|
| 1213 |
+
{
|
| 1214 |
+
"epoch": 0.8778930566640064,
|
| 1215 |
+
"eval_loss": 0.9288386106491089,
|
| 1216 |
+
"eval_runtime": 21.0235,
|
| 1217 |
+
"eval_samples_per_second": 1.475,
|
| 1218 |
+
"eval_steps_per_second": 0.761,
|
| 1219 |
+
"step": 550
|
| 1220 |
+
},
|
| 1221 |
+
{
|
| 1222 |
+
"epoch": 0.8858739026336792,
|
| 1223 |
+
"grad_norm": 0.6864151954650879,
|
| 1224 |
+
"learning_rate": 8.900000000000001e-05,
|
| 1225 |
+
"loss": 0.8758,
|
| 1226 |
+
"step": 555
|
| 1227 |
+
},
|
| 1228 |
+
{
|
| 1229 |
+
"epoch": 0.8938547486033519,
|
| 1230 |
+
"grad_norm": 0.6886463761329651,
|
| 1231 |
+
"learning_rate": 8.800000000000001e-05,
|
| 1232 |
+
"loss": 0.895,
|
| 1233 |
+
"step": 560
|
| 1234 |
+
},
|
| 1235 |
+
{
|
| 1236 |
+
"epoch": 0.8938547486033519,
|
| 1237 |
+
"eval_loss": 0.9302241802215576,
|
| 1238 |
+
"eval_runtime": 21.0245,
|
| 1239 |
+
"eval_samples_per_second": 1.474,
|
| 1240 |
+
"eval_steps_per_second": 0.761,
|
| 1241 |
+
"step": 560
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 0.9018355945730248,
|
| 1245 |
+
"grad_norm": 0.7045288681983948,
|
| 1246 |
+
"learning_rate": 8.7e-05,
|
| 1247 |
+
"loss": 0.7896,
|
| 1248 |
+
"step": 565
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 0.9098164405426975,
|
| 1252 |
+
"grad_norm": 0.8066936135292053,
|
| 1253 |
+
"learning_rate": 8.6e-05,
|
| 1254 |
+
"loss": 0.9071,
|
| 1255 |
+
"step": 570
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 0.9098164405426975,
|
| 1259 |
+
"eval_loss": 0.9250284433364868,
|
| 1260 |
+
"eval_runtime": 21.0108,
|
| 1261 |
+
"eval_samples_per_second": 1.475,
|
| 1262 |
+
"eval_steps_per_second": 0.762,
|
| 1263 |
+
"step": 570
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 0.9177972865123704,
|
| 1267 |
+
"grad_norm": 0.6377101540565491,
|
| 1268 |
+
"learning_rate": 8.5e-05,
|
| 1269 |
+
"loss": 0.8045,
|
| 1270 |
+
"step": 575
|
| 1271 |
+
},
|
| 1272 |
+
{
|
| 1273 |
+
"epoch": 0.9257781324820431,
|
| 1274 |
+
"grad_norm": 0.7454017996788025,
|
| 1275 |
+
"learning_rate": 8.4e-05,
|
| 1276 |
+
"loss": 0.9337,
|
| 1277 |
+
"step": 580
|
| 1278 |
+
},
|
| 1279 |
+
{
|
| 1280 |
+
"epoch": 0.9257781324820431,
|
| 1281 |
+
"eval_loss": 0.9239058494567871,
|
| 1282 |
+
"eval_runtime": 20.9525,
|
| 1283 |
+
"eval_samples_per_second": 1.48,
|
| 1284 |
+
"eval_steps_per_second": 0.764,
|
| 1285 |
+
"step": 580
|
| 1286 |
+
},
|
| 1287 |
+
{
|
| 1288 |
+
"epoch": 0.9337589784517158,
|
| 1289 |
+
"grad_norm": 0.6952985525131226,
|
| 1290 |
+
"learning_rate": 8.3e-05,
|
| 1291 |
+
"loss": 0.8703,
|
| 1292 |
+
"step": 585
|
| 1293 |
+
},
|
| 1294 |
+
{
|
| 1295 |
+
"epoch": 0.9417398244213887,
|
| 1296 |
+
"grad_norm": 0.7358236312866211,
|
| 1297 |
+
"learning_rate": 8.2e-05,
|
| 1298 |
+
"loss": 0.8793,
|
| 1299 |
+
"step": 590
|
| 1300 |
+
},
|
| 1301 |
+
{
|
| 1302 |
+
"epoch": 0.9417398244213887,
|
| 1303 |
+
"eval_loss": 0.9293895363807678,
|
| 1304 |
+
"eval_runtime": 20.9523,
|
| 1305 |
+
"eval_samples_per_second": 1.48,
|
| 1306 |
+
"eval_steps_per_second": 0.764,
|
| 1307 |
+
"step": 590
|
| 1308 |
+
},
|
| 1309 |
+
{
|
| 1310 |
+
"epoch": 0.9497206703910615,
|
| 1311 |
+
"grad_norm": 0.5817161202430725,
|
| 1312 |
+
"learning_rate": 8.1e-05,
|
| 1313 |
+
"loss": 0.8298,
|
| 1314 |
+
"step": 595
|
| 1315 |
+
},
|
| 1316 |
+
{
|
| 1317 |
+
"epoch": 0.9577015163607342,
|
| 1318 |
+
"grad_norm": 0.7251338362693787,
|
| 1319 |
+
"learning_rate": 8e-05,
|
| 1320 |
+
"loss": 0.8766,
|
| 1321 |
+
"step": 600
|
| 1322 |
+
},
|
| 1323 |
+
{
|
| 1324 |
+
"epoch": 0.9577015163607342,
|
| 1325 |
+
"eval_loss": 0.9293678998947144,
|
| 1326 |
+
"eval_runtime": 20.9457,
|
| 1327 |
+
"eval_samples_per_second": 1.48,
|
| 1328 |
+
"eval_steps_per_second": 0.764,
|
| 1329 |
+
"step": 600
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 0.965682362330407,
|
| 1333 |
+
"grad_norm": 0.8278694748878479,
|
| 1334 |
+
"learning_rate": 7.900000000000001e-05,
|
| 1335 |
+
"loss": 0.7507,
|
| 1336 |
+
"step": 605
|
| 1337 |
+
},
|
| 1338 |
+
{
|
| 1339 |
+
"epoch": 0.9736632083000798,
|
| 1340 |
+
"grad_norm": 0.7793962955474854,
|
| 1341 |
+
"learning_rate": 7.800000000000001e-05,
|
| 1342 |
+
"loss": 0.8682,
|
| 1343 |
+
"step": 610
|
| 1344 |
+
},
|
| 1345 |
+
{
|
| 1346 |
+
"epoch": 0.9736632083000798,
|
| 1347 |
+
"eval_loss": 0.9281108975410461,
|
| 1348 |
+
"eval_runtime": 21.2355,
|
| 1349 |
+
"eval_samples_per_second": 1.46,
|
| 1350 |
+
"eval_steps_per_second": 0.753,
|
| 1351 |
+
"step": 610
|
| 1352 |
+
},
|
| 1353 |
+
{
|
| 1354 |
+
"epoch": 0.9816440542697525,
|
| 1355 |
+
"grad_norm": 0.8250753283500671,
|
| 1356 |
+
"learning_rate": 7.7e-05,
|
| 1357 |
+
"loss": 0.8196,
|
| 1358 |
+
"step": 615
|
| 1359 |
+
},
|
| 1360 |
+
{
|
| 1361 |
+
"epoch": 0.9896249002394254,
|
| 1362 |
+
"grad_norm": 0.7124294638633728,
|
| 1363 |
+
"learning_rate": 7.6e-05,
|
| 1364 |
+
"loss": 0.7849,
|
| 1365 |
+
"step": 620
|
| 1366 |
+
},
|
| 1367 |
+
{
|
| 1368 |
+
"epoch": 0.9896249002394254,
|
| 1369 |
+
"eval_loss": 0.9263650178909302,
|
| 1370 |
+
"eval_runtime": 21.1863,
|
| 1371 |
+
"eval_samples_per_second": 1.463,
|
| 1372 |
+
"eval_steps_per_second": 0.755,
|
| 1373 |
+
"step": 620
|
| 1374 |
+
},
|
| 1375 |
+
{
|
| 1376 |
+
"epoch": 0.9976057462090981,
|
| 1377 |
+
"grad_norm": 0.768418550491333,
|
| 1378 |
+
"learning_rate": 7.500000000000001e-05,
|
| 1379 |
+
"loss": 0.8589,
|
| 1380 |
+
"step": 625
|
| 1381 |
+
},
|
| 1382 |
+
{
|
| 1383 |
+
"epoch": 1.005586592178771,
|
| 1384 |
+
"grad_norm": 0.6237154603004456,
|
| 1385 |
+
"learning_rate": 7.4e-05,
|
| 1386 |
+
"loss": 0.8746,
|
| 1387 |
+
"step": 630
|
| 1388 |
+
},
|
| 1389 |
+
{
|
| 1390 |
+
"epoch": 1.005586592178771,
|
| 1391 |
+
"eval_loss": 0.9216476082801819,
|
| 1392 |
+
"eval_runtime": 21.1504,
|
| 1393 |
+
"eval_samples_per_second": 1.466,
|
| 1394 |
+
"eval_steps_per_second": 0.756,
|
| 1395 |
+
"step": 630
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"epoch": 1.0135674381484436,
|
| 1399 |
+
"grad_norm": 0.691764235496521,
|
| 1400 |
+
"learning_rate": 7.3e-05,
|
| 1401 |
+
"loss": 0.8455,
|
| 1402 |
+
"step": 635
|
| 1403 |
+
},
|
| 1404 |
+
{
|
| 1405 |
+
"epoch": 1.0215482841181165,
|
| 1406 |
+
"grad_norm": 0.6523061990737915,
|
| 1407 |
+
"learning_rate": 7.2e-05,
|
| 1408 |
+
"loss": 0.8149,
|
| 1409 |
+
"step": 640
|
| 1410 |
+
},
|
| 1411 |
+
{
|
| 1412 |
+
"epoch": 1.0215482841181165,
|
| 1413 |
+
"eval_loss": 0.9180006384849548,
|
| 1414 |
+
"eval_runtime": 21.3153,
|
| 1415 |
+
"eval_samples_per_second": 1.454,
|
| 1416 |
+
"eval_steps_per_second": 0.751,
|
| 1417 |
+
"step": 640
|
| 1418 |
+
},
|
| 1419 |
+
{
|
| 1420 |
+
"epoch": 1.0295291300877893,
|
| 1421 |
+
"grad_norm": 0.9022932648658752,
|
| 1422 |
+
"learning_rate": 7.1e-05,
|
| 1423 |
+
"loss": 0.8321,
|
| 1424 |
+
"step": 645
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 1.037509976057462,
|
| 1428 |
+
"grad_norm": 0.6842184066772461,
|
| 1429 |
+
"learning_rate": 7e-05,
|
| 1430 |
+
"loss": 0.806,
|
| 1431 |
+
"step": 650
|
| 1432 |
+
},
|
| 1433 |
+
{
|
| 1434 |
+
"epoch": 1.037509976057462,
|
| 1435 |
+
"eval_loss": 0.9218840599060059,
|
| 1436 |
+
"eval_runtime": 21.1263,
|
| 1437 |
+
"eval_samples_per_second": 1.467,
|
| 1438 |
+
"eval_steps_per_second": 0.757,
|
| 1439 |
+
"step": 650
|
| 1440 |
+
},
|
| 1441 |
+
{
|
| 1442 |
+
"epoch": 1.0454908220271348,
|
| 1443 |
+
"grad_norm": 0.9547672271728516,
|
| 1444 |
+
"learning_rate": 6.9e-05,
|
| 1445 |
+
"loss": 0.8023,
|
| 1446 |
+
"step": 655
|
| 1447 |
+
},
|
| 1448 |
+
{
|
| 1449 |
+
"epoch": 1.0534716679968077,
|
| 1450 |
+
"grad_norm": 0.6439852714538574,
|
| 1451 |
+
"learning_rate": 6.800000000000001e-05,
|
| 1452 |
+
"loss": 0.7533,
|
| 1453 |
+
"step": 660
|
| 1454 |
+
},
|
| 1455 |
+
{
|
| 1456 |
+
"epoch": 1.0534716679968077,
|
| 1457 |
+
"eval_loss": 0.9165079593658447,
|
| 1458 |
+
"eval_runtime": 21.1104,
|
| 1459 |
+
"eval_samples_per_second": 1.468,
|
| 1460 |
+
"eval_steps_per_second": 0.758,
|
| 1461 |
+
"step": 660
|
| 1462 |
+
},
|
| 1463 |
+
{
|
| 1464 |
+
"epoch": 1.0614525139664805,
|
| 1465 |
+
"grad_norm": 0.7850003242492676,
|
| 1466 |
+
"learning_rate": 6.7e-05,
|
| 1467 |
+
"loss": 0.858,
|
| 1468 |
+
"step": 665
|
| 1469 |
+
},
|
| 1470 |
+
{
|
| 1471 |
+
"epoch": 1.0694333599361532,
|
| 1472 |
+
"grad_norm": 0.6285898685455322,
|
| 1473 |
+
"learning_rate": 6.6e-05,
|
| 1474 |
+
"loss": 0.7146,
|
| 1475 |
+
"step": 670
|
| 1476 |
+
},
|
| 1477 |
+
{
|
| 1478 |
+
"epoch": 1.0694333599361532,
|
| 1479 |
+
"eval_loss": 0.9204993844032288,
|
| 1480 |
+
"eval_runtime": 21.1527,
|
| 1481 |
+
"eval_samples_per_second": 1.466,
|
| 1482 |
+
"eval_steps_per_second": 0.756,
|
| 1483 |
+
"step": 670
|
| 1484 |
+
},
|
| 1485 |
+
{
|
| 1486 |
+
"epoch": 1.077414205905826,
|
| 1487 |
+
"grad_norm": 0.7350932955741882,
|
| 1488 |
+
"learning_rate": 6.500000000000001e-05,
|
| 1489 |
+
"loss": 0.8328,
|
| 1490 |
+
"step": 675
|
| 1491 |
+
},
|
| 1492 |
+
{
|
| 1493 |
+
"epoch": 1.085395051875499,
|
| 1494 |
+
"grad_norm": 0.7773166298866272,
|
| 1495 |
+
"learning_rate": 6.400000000000001e-05,
|
| 1496 |
+
"loss": 0.8075,
|
| 1497 |
+
"step": 680
|
| 1498 |
+
},
|
| 1499 |
+
{
|
| 1500 |
+
"epoch": 1.085395051875499,
|
| 1501 |
+
"eval_loss": 0.9216338992118835,
|
| 1502 |
+
"eval_runtime": 21.0323,
|
| 1503 |
+
"eval_samples_per_second": 1.474,
|
| 1504 |
+
"eval_steps_per_second": 0.761,
|
| 1505 |
+
"step": 680
|
| 1506 |
+
},
|
| 1507 |
+
{
|
| 1508 |
+
"epoch": 1.0933758978451715,
|
| 1509 |
+
"grad_norm": 0.9075634479522705,
|
| 1510 |
+
"learning_rate": 6.3e-05,
|
| 1511 |
+
"loss": 0.8809,
|
| 1512 |
+
"step": 685
|
| 1513 |
+
},
|
| 1514 |
+
{
|
| 1515 |
+
"epoch": 1.1013567438148444,
|
| 1516 |
+
"grad_norm": 0.7483291029930115,
|
| 1517 |
+
"learning_rate": 6.2e-05,
|
| 1518 |
+
"loss": 0.8302,
|
| 1519 |
+
"step": 690
|
| 1520 |
+
},
|
| 1521 |
+
{
|
| 1522 |
+
"epoch": 1.1013567438148444,
|
| 1523 |
+
"eval_loss": 0.9141597747802734,
|
| 1524 |
+
"eval_runtime": 20.8831,
|
| 1525 |
+
"eval_samples_per_second": 1.484,
|
| 1526 |
+
"eval_steps_per_second": 0.766,
|
| 1527 |
+
"step": 690
|
| 1528 |
+
},
|
| 1529 |
+
{
|
| 1530 |
+
"epoch": 1.1093375897845172,
|
| 1531 |
+
"grad_norm": 0.8029285073280334,
|
| 1532 |
+
"learning_rate": 6.1e-05,
|
| 1533 |
+
"loss": 0.7757,
|
| 1534 |
+
"step": 695
|
| 1535 |
+
},
|
| 1536 |
+
{
|
| 1537 |
+
"epoch": 1.1173184357541899,
|
| 1538 |
+
"grad_norm": 0.7638797760009766,
|
| 1539 |
+
"learning_rate": 6e-05,
|
| 1540 |
+
"loss": 0.8258,
|
| 1541 |
+
"step": 700
|
| 1542 |
+
},
|
| 1543 |
+
{
|
| 1544 |
+
"epoch": 1.1173184357541899,
|
| 1545 |
+
"eval_loss": 0.9134471416473389,
|
| 1546 |
+
"eval_runtime": 21.3635,
|
| 1547 |
+
"eval_samples_per_second": 1.451,
|
| 1548 |
+
"eval_steps_per_second": 0.749,
|
| 1549 |
+
"step": 700
|
| 1550 |
+
},
|
| 1551 |
+
{
|
| 1552 |
+
"epoch": 1.1252992817238627,
|
| 1553 |
+
"grad_norm": 0.8713815212249756,
|
| 1554 |
+
"learning_rate": 5.9e-05,
|
| 1555 |
+
"loss": 0.8017,
|
| 1556 |
+
"step": 705
|
| 1557 |
+
},
|
| 1558 |
+
{
|
| 1559 |
+
"epoch": 1.1332801276935356,
|
| 1560 |
+
"grad_norm": 0.8253017663955688,
|
| 1561 |
+
"learning_rate": 5.8e-05,
|
| 1562 |
+
"loss": 0.8873,
|
| 1563 |
+
"step": 710
|
| 1564 |
+
},
|
| 1565 |
+
{
|
| 1566 |
+
"epoch": 1.1332801276935356,
|
| 1567 |
+
"eval_loss": 0.91542649269104,
|
| 1568 |
+
"eval_runtime": 21.1885,
|
| 1569 |
+
"eval_samples_per_second": 1.463,
|
| 1570 |
+
"eval_steps_per_second": 0.755,
|
| 1571 |
+
"step": 710
|
| 1572 |
+
},
|
| 1573 |
+
{
|
| 1574 |
+
"epoch": 1.1412609736632082,
|
| 1575 |
+
"grad_norm": 0.8720806241035461,
|
| 1576 |
+
"learning_rate": 5.6999999999999996e-05,
|
| 1577 |
+
"loss": 0.8808,
|
| 1578 |
+
"step": 715
|
| 1579 |
+
},
|
| 1580 |
+
{
|
| 1581 |
+
"epoch": 1.149241819632881,
|
| 1582 |
+
"grad_norm": 0.855076253414154,
|
| 1583 |
+
"learning_rate": 5.6000000000000006e-05,
|
| 1584 |
+
"loss": 0.8285,
|
| 1585 |
+
"step": 720
|
| 1586 |
+
},
|
| 1587 |
+
{
|
| 1588 |
+
"epoch": 1.149241819632881,
|
| 1589 |
+
"eval_loss": 0.9051924347877502,
|
| 1590 |
+
"eval_runtime": 21.0529,
|
| 1591 |
+
"eval_samples_per_second": 1.472,
|
| 1592 |
+
"eval_steps_per_second": 0.76,
|
| 1593 |
+
"step": 720
|
| 1594 |
+
},
|
| 1595 |
+
{
|
| 1596 |
+
"epoch": 1.157222665602554,
|
| 1597 |
+
"grad_norm": 0.8113986849784851,
|
| 1598 |
+
"learning_rate": 5.500000000000001e-05,
|
| 1599 |
+
"loss": 0.8119,
|
| 1600 |
+
"step": 725
|
| 1601 |
+
},
|
| 1602 |
+
{
|
| 1603 |
+
"epoch": 1.1652035115722266,
|
| 1604 |
+
"grad_norm": 0.754554271697998,
|
| 1605 |
+
"learning_rate": 5.4000000000000005e-05,
|
| 1606 |
+
"loss": 0.7881,
|
| 1607 |
+
"step": 730
|
| 1608 |
+
},
|
| 1609 |
+
{
|
| 1610 |
+
"epoch": 1.1652035115722266,
|
| 1611 |
+
"eval_loss": 0.9082400798797607,
|
| 1612 |
+
"eval_runtime": 20.8583,
|
| 1613 |
+
"eval_samples_per_second": 1.486,
|
| 1614 |
+
"eval_steps_per_second": 0.767,
|
| 1615 |
+
"step": 730
|
| 1616 |
+
},
|
| 1617 |
+
{
|
| 1618 |
+
"epoch": 1.1731843575418994,
|
| 1619 |
+
"grad_norm": 0.9242857694625854,
|
| 1620 |
+
"learning_rate": 5.300000000000001e-05,
|
| 1621 |
+
"loss": 0.7508,
|
| 1622 |
+
"step": 735
|
| 1623 |
+
},
|
| 1624 |
+
{
|
| 1625 |
+
"epoch": 1.1811652035115723,
|
| 1626 |
+
"grad_norm": 0.7203059792518616,
|
| 1627 |
+
"learning_rate": 5.2000000000000004e-05,
|
| 1628 |
+
"loss": 0.8788,
|
| 1629 |
+
"step": 740
|
| 1630 |
+
},
|
| 1631 |
+
{
|
| 1632 |
+
"epoch": 1.1811652035115723,
|
| 1633 |
+
"eval_loss": 0.9105547666549683,
|
| 1634 |
+
"eval_runtime": 20.8797,
|
| 1635 |
+
"eval_samples_per_second": 1.485,
|
| 1636 |
+
"eval_steps_per_second": 0.766,
|
| 1637 |
+
"step": 740
|
| 1638 |
+
},
|
| 1639 |
+
{
|
| 1640 |
+
"epoch": 1.189146049481245,
|
| 1641 |
+
"grad_norm": 0.821240246295929,
|
| 1642 |
+
"learning_rate": 5.1000000000000006e-05,
|
| 1643 |
+
"loss": 0.767,
|
| 1644 |
+
"step": 745
|
| 1645 |
+
},
|
| 1646 |
+
{
|
| 1647 |
+
"epoch": 1.1971268954509178,
|
| 1648 |
+
"grad_norm": 1.0884546041488647,
|
| 1649 |
+
"learning_rate": 5e-05,
|
| 1650 |
+
"loss": 0.8585,
|
| 1651 |
+
"step": 750
|
| 1652 |
+
},
|
| 1653 |
+
{
|
| 1654 |
+
"epoch": 1.1971268954509178,
|
| 1655 |
+
"eval_loss": 0.9092571139335632,
|
| 1656 |
+
"eval_runtime": 21.2995,
|
| 1657 |
+
"eval_samples_per_second": 1.455,
|
| 1658 |
+
"eval_steps_per_second": 0.751,
|
| 1659 |
+
"step": 750
|
| 1660 |
+
},
|
| 1661 |
+
{
|
| 1662 |
+
"epoch": 1.2051077414205906,
|
| 1663 |
+
"grad_norm": 0.7183963656425476,
|
| 1664 |
+
"learning_rate": 4.9e-05,
|
| 1665 |
+
"loss": 0.8462,
|
| 1666 |
+
"step": 755
|
| 1667 |
+
},
|
| 1668 |
+
{
|
| 1669 |
+
"epoch": 1.2130885873902635,
|
| 1670 |
+
"grad_norm": 0.7556672692298889,
|
| 1671 |
+
"learning_rate": 4.8e-05,
|
| 1672 |
+
"loss": 0.7203,
|
| 1673 |
+
"step": 760
|
| 1674 |
+
},
|
| 1675 |
+
{
|
| 1676 |
+
"epoch": 1.2130885873902635,
|
| 1677 |
+
"eval_loss": 0.9125378727912903,
|
| 1678 |
+
"eval_runtime": 20.9445,
|
| 1679 |
+
"eval_samples_per_second": 1.48,
|
| 1680 |
+
"eval_steps_per_second": 0.764,
|
| 1681 |
+
"step": 760
|
| 1682 |
+
},
|
| 1683 |
+
{
|
| 1684 |
+
"epoch": 1.2210694333599361,
|
| 1685 |
+
"grad_norm": 0.8119292259216309,
|
| 1686 |
+
"learning_rate": 4.7e-05,
|
| 1687 |
+
"loss": 0.8294,
|
| 1688 |
+
"step": 765
|
| 1689 |
+
},
|
| 1690 |
+
{
|
| 1691 |
+
"epoch": 1.229050279329609,
|
| 1692 |
+
"grad_norm": 0.7207946181297302,
|
| 1693 |
+
"learning_rate": 4.600000000000001e-05,
|
| 1694 |
+
"loss": 0.8084,
|
| 1695 |
+
"step": 770
|
| 1696 |
+
},
|
| 1697 |
+
{
|
| 1698 |
+
"epoch": 1.229050279329609,
|
| 1699 |
+
"eval_loss": 0.9099369645118713,
|
| 1700 |
+
"eval_runtime": 20.5873,
|
| 1701 |
+
"eval_samples_per_second": 1.506,
|
| 1702 |
+
"eval_steps_per_second": 0.777,
|
| 1703 |
+
"step": 770
|
| 1704 |
+
},
|
| 1705 |
+
{
|
| 1706 |
+
"epoch": 1.2370311252992816,
|
| 1707 |
+
"grad_norm": 0.9262428283691406,
|
| 1708 |
+
"learning_rate": 4.5e-05,
|
| 1709 |
+
"loss": 0.7861,
|
| 1710 |
+
"step": 775
|
| 1711 |
+
},
|
| 1712 |
+
{
|
| 1713 |
+
"epoch": 1.2450119712689545,
|
| 1714 |
+
"grad_norm": 0.9154334664344788,
|
| 1715 |
+
"learning_rate": 4.4000000000000006e-05,
|
| 1716 |
+
"loss": 0.7298,
|
| 1717 |
+
"step": 780
|
| 1718 |
+
},
|
| 1719 |
+
{
|
| 1720 |
+
"epoch": 1.2450119712689545,
|
| 1721 |
+
"eval_loss": 0.9098423719406128,
|
| 1722 |
+
"eval_runtime": 21.1045,
|
| 1723 |
+
"eval_samples_per_second": 1.469,
|
| 1724 |
+
"eval_steps_per_second": 0.758,
|
| 1725 |
+
"step": 780
|
| 1726 |
+
},
|
| 1727 |
+
{
|
| 1728 |
+
"epoch": 1.2529928172386273,
|
| 1729 |
+
"grad_norm": 0.8377973437309265,
|
| 1730 |
+
"learning_rate": 4.3e-05,
|
| 1731 |
+
"loss": 0.7593,
|
| 1732 |
+
"step": 785
|
| 1733 |
+
},
|
| 1734 |
+
{
|
| 1735 |
+
"epoch": 1.2609736632083002,
|
| 1736 |
+
"grad_norm": 0.8660017848014832,
|
| 1737 |
+
"learning_rate": 4.2e-05,
|
| 1738 |
+
"loss": 0.7811,
|
| 1739 |
+
"step": 790
|
| 1740 |
+
},
|
| 1741 |
+
{
|
| 1742 |
+
"epoch": 1.2609736632083002,
|
| 1743 |
+
"eval_loss": 0.9046799540519714,
|
| 1744 |
+
"eval_runtime": 20.9842,
|
| 1745 |
+
"eval_samples_per_second": 1.477,
|
| 1746 |
+
"eval_steps_per_second": 0.762,
|
| 1747 |
+
"step": 790
|
| 1748 |
+
},
|
| 1749 |
+
{
|
| 1750 |
+
"epoch": 1.2689545091779728,
|
| 1751 |
+
"grad_norm": 0.7700662612915039,
|
| 1752 |
+
"learning_rate": 4.1e-05,
|
| 1753 |
+
"loss": 0.8493,
|
| 1754 |
+
"step": 795
|
| 1755 |
+
},
|
| 1756 |
+
{
|
| 1757 |
+
"epoch": 1.2769353551476457,
|
| 1758 |
+
"grad_norm": 0.8167340159416199,
|
| 1759 |
+
"learning_rate": 4e-05,
|
| 1760 |
+
"loss": 0.7774,
|
| 1761 |
+
"step": 800
|
| 1762 |
+
},
|
| 1763 |
+
{
|
| 1764 |
+
"epoch": 1.2769353551476457,
|
| 1765 |
+
"eval_loss": 0.8998985886573792,
|
| 1766 |
+
"eval_runtime": 21.1467,
|
| 1767 |
+
"eval_samples_per_second": 1.466,
|
| 1768 |
+
"eval_steps_per_second": 0.757,
|
| 1769 |
+
"step": 800
|
| 1770 |
+
},
|
| 1771 |
+
{
|
| 1772 |
+
"epoch": 1.2849162011173183,
|
| 1773 |
+
"grad_norm": 0.8162097334861755,
|
| 1774 |
+
"learning_rate": 3.9000000000000006e-05,
|
| 1775 |
+
"loss": 0.7892,
|
| 1776 |
+
"step": 805
|
| 1777 |
+
},
|
| 1778 |
+
{
|
| 1779 |
+
"epoch": 1.2928970470869912,
|
| 1780 |
+
"grad_norm": 0.8468261957168579,
|
| 1781 |
+
"learning_rate": 3.8e-05,
|
| 1782 |
+
"loss": 0.8324,
|
| 1783 |
+
"step": 810
|
| 1784 |
+
},
|
| 1785 |
+
{
|
| 1786 |
+
"epoch": 1.2928970470869912,
|
| 1787 |
+
"eval_loss": 0.8993770480155945,
|
| 1788 |
+
"eval_runtime": 20.9539,
|
| 1789 |
+
"eval_samples_per_second": 1.479,
|
| 1790 |
+
"eval_steps_per_second": 0.764,
|
| 1791 |
+
"step": 810
|
| 1792 |
+
},
|
| 1793 |
+
{
|
| 1794 |
+
"epoch": 1.300877893056664,
|
| 1795 |
+
"grad_norm": 0.746923565864563,
|
| 1796 |
+
"learning_rate": 3.7e-05,
|
| 1797 |
+
"loss": 0.7961,
|
| 1798 |
+
"step": 815
|
| 1799 |
+
},
|
| 1800 |
+
{
|
| 1801 |
+
"epoch": 1.3088587390263369,
|
| 1802 |
+
"grad_norm": 0.7284272313117981,
|
| 1803 |
+
"learning_rate": 3.6e-05,
|
| 1804 |
+
"loss": 0.6872,
|
| 1805 |
+
"step": 820
|
| 1806 |
+
},
|
| 1807 |
+
{
|
| 1808 |
+
"epoch": 1.3088587390263369,
|
| 1809 |
+
"eval_loss": 0.8972273468971252,
|
| 1810 |
+
"eval_runtime": 20.6969,
|
| 1811 |
+
"eval_samples_per_second": 1.498,
|
| 1812 |
+
"eval_steps_per_second": 0.773,
|
| 1813 |
+
"step": 820
|
| 1814 |
+
},
|
| 1815 |
+
{
|
| 1816 |
+
"epoch": 1.3168395849960095,
|
| 1817 |
+
"grad_norm": 0.8922063708305359,
|
| 1818 |
+
"learning_rate": 3.5e-05,
|
| 1819 |
+
"loss": 0.8041,
|
| 1820 |
+
"step": 825
|
| 1821 |
+
},
|
| 1822 |
+
{
|
| 1823 |
+
"epoch": 1.3248204309656824,
|
| 1824 |
+
"grad_norm": 0.7598963975906372,
|
| 1825 |
+
"learning_rate": 3.4000000000000007e-05,
|
| 1826 |
+
"loss": 0.7028,
|
| 1827 |
+
"step": 830
|
| 1828 |
+
},
|
| 1829 |
+
{
|
| 1830 |
+
"epoch": 1.3248204309656824,
|
| 1831 |
+
"eval_loss": 0.8973636031150818,
|
| 1832 |
+
"eval_runtime": 20.8738,
|
| 1833 |
+
"eval_samples_per_second": 1.485,
|
| 1834 |
+
"eval_steps_per_second": 0.767,
|
| 1835 |
+
"step": 830
|
| 1836 |
+
},
|
| 1837 |
+
{
|
| 1838 |
+
"epoch": 1.3328012769353552,
|
| 1839 |
+
"grad_norm": 0.7866420745849609,
|
| 1840 |
+
"learning_rate": 3.3e-05,
|
| 1841 |
+
"loss": 0.8392,
|
| 1842 |
+
"step": 835
|
| 1843 |
+
},
|
| 1844 |
+
{
|
| 1845 |
+
"epoch": 1.3407821229050279,
|
| 1846 |
+
"grad_norm": 0.8417834639549255,
|
| 1847 |
+
"learning_rate": 3.2000000000000005e-05,
|
| 1848 |
+
"loss": 0.7329,
|
| 1849 |
+
"step": 840
|
| 1850 |
+
},
|
| 1851 |
+
{
|
| 1852 |
+
"epoch": 1.3407821229050279,
|
| 1853 |
+
"eval_loss": 0.9000219106674194,
|
| 1854 |
+
"eval_runtime": 21.0159,
|
| 1855 |
+
"eval_samples_per_second": 1.475,
|
| 1856 |
+
"eval_steps_per_second": 0.761,
|
| 1857 |
+
"step": 840
|
| 1858 |
+
},
|
| 1859 |
+
{
|
| 1860 |
+
"epoch": 1.3487629688747007,
|
| 1861 |
+
"grad_norm": 0.8085408806800842,
|
| 1862 |
+
"learning_rate": 3.1e-05,
|
| 1863 |
+
"loss": 0.7452,
|
| 1864 |
+
"step": 845
|
| 1865 |
+
},
|
| 1866 |
+
{
|
| 1867 |
+
"epoch": 1.3567438148443736,
|
| 1868 |
+
"grad_norm": 0.9095738530158997,
|
| 1869 |
+
"learning_rate": 3e-05,
|
| 1870 |
+
"loss": 0.8114,
|
| 1871 |
+
"step": 850
|
| 1872 |
+
},
|
| 1873 |
+
{
|
| 1874 |
+
"epoch": 1.3567438148443736,
|
| 1875 |
+
"eval_loss": 0.899355411529541,
|
| 1876 |
+
"eval_runtime": 21.1951,
|
| 1877 |
+
"eval_samples_per_second": 1.463,
|
| 1878 |
+
"eval_steps_per_second": 0.755,
|
| 1879 |
+
"step": 850
|
| 1880 |
+
},
|
| 1881 |
+
{
|
| 1882 |
+
"epoch": 1.3647246608140464,
|
| 1883 |
+
"grad_norm": 0.8077012896537781,
|
| 1884 |
+
"learning_rate": 2.9e-05,
|
| 1885 |
+
"loss": 0.7842,
|
| 1886 |
+
"step": 855
|
| 1887 |
+
},
|
| 1888 |
+
{
|
| 1889 |
+
"epoch": 1.372705506783719,
|
| 1890 |
+
"grad_norm": 0.9387809038162231,
|
| 1891 |
+
"learning_rate": 2.8000000000000003e-05,
|
| 1892 |
+
"loss": 0.7739,
|
| 1893 |
+
"step": 860
|
| 1894 |
+
},
|
| 1895 |
+
{
|
| 1896 |
+
"epoch": 1.372705506783719,
|
| 1897 |
+
"eval_loss": 0.9006592631340027,
|
| 1898 |
+
"eval_runtime": 20.7294,
|
| 1899 |
+
"eval_samples_per_second": 1.495,
|
| 1900 |
+
"eval_steps_per_second": 0.772,
|
| 1901 |
+
"step": 860
|
| 1902 |
+
},
|
| 1903 |
+
{
|
| 1904 |
+
"epoch": 1.380686352753392,
|
| 1905 |
+
"grad_norm": 0.8230510950088501,
|
| 1906 |
+
"learning_rate": 2.7000000000000002e-05,
|
| 1907 |
+
"loss": 0.7765,
|
| 1908 |
+
"step": 865
|
| 1909 |
+
},
|
| 1910 |
+
{
|
| 1911 |
+
"epoch": 1.3886671987230645,
|
| 1912 |
+
"grad_norm": 0.9421499371528625,
|
| 1913 |
+
"learning_rate": 2.6000000000000002e-05,
|
| 1914 |
+
"loss": 0.7469,
|
| 1915 |
+
"step": 870
|
| 1916 |
+
},
|
| 1917 |
+
{
|
| 1918 |
+
"epoch": 1.3886671987230645,
|
| 1919 |
+
"eval_loss": 0.8988057374954224,
|
| 1920 |
+
"eval_runtime": 20.7795,
|
| 1921 |
+
"eval_samples_per_second": 1.492,
|
| 1922 |
+
"eval_steps_per_second": 0.77,
|
| 1923 |
+
"step": 870
|
| 1924 |
+
},
|
| 1925 |
+
{
|
| 1926 |
+
"epoch": 1.3966480446927374,
|
| 1927 |
+
"grad_norm": 0.8720149993896484,
|
| 1928 |
+
"learning_rate": 2.5e-05,
|
| 1929 |
+
"loss": 0.7674,
|
| 1930 |
+
"step": 875
|
| 1931 |
+
},
|
| 1932 |
+
{
|
| 1933 |
+
"epoch": 1.4046288906624103,
|
| 1934 |
+
"grad_norm": 0.9915176033973694,
|
| 1935 |
+
"learning_rate": 2.4e-05,
|
| 1936 |
+
"loss": 0.7925,
|
| 1937 |
+
"step": 880
|
| 1938 |
+
},
|
| 1939 |
+
{
|
| 1940 |
+
"epoch": 1.4046288906624103,
|
| 1941 |
+
"eval_loss": 0.8960800170898438,
|
| 1942 |
+
"eval_runtime": 21.1416,
|
| 1943 |
+
"eval_samples_per_second": 1.466,
|
| 1944 |
+
"eval_steps_per_second": 0.757,
|
| 1945 |
+
"step": 880
|
| 1946 |
+
},
|
| 1947 |
+
{
|
| 1948 |
+
"epoch": 1.4126097366320831,
|
| 1949 |
+
"grad_norm": 0.8962202072143555,
|
| 1950 |
+
"learning_rate": 2.3000000000000003e-05,
|
| 1951 |
+
"loss": 0.7848,
|
| 1952 |
+
"step": 885
|
| 1953 |
+
},
|
| 1954 |
+
{
|
| 1955 |
+
"epoch": 1.4205905826017557,
|
| 1956 |
+
"grad_norm": 0.9091677069664001,
|
| 1957 |
+
"learning_rate": 2.2000000000000003e-05,
|
| 1958 |
+
"loss": 0.8638,
|
| 1959 |
+
"step": 890
|
| 1960 |
+
},
|
| 1961 |
+
{
|
| 1962 |
+
"epoch": 1.4205905826017557,
|
| 1963 |
+
"eval_loss": 0.893966555595398,
|
| 1964 |
+
"eval_runtime": 21.0044,
|
| 1965 |
+
"eval_samples_per_second": 1.476,
|
| 1966 |
+
"eval_steps_per_second": 0.762,
|
| 1967 |
+
"step": 890
|
| 1968 |
+
},
|
| 1969 |
+
{
|
| 1970 |
+
"epoch": 1.4285714285714286,
|
| 1971 |
+
"grad_norm": 0.7839522361755371,
|
| 1972 |
+
"learning_rate": 2.1e-05,
|
| 1973 |
+
"loss": 0.8426,
|
| 1974 |
+
"step": 895
|
| 1975 |
+
},
|
| 1976 |
+
{
|
| 1977 |
+
"epoch": 1.4365522745411012,
|
| 1978 |
+
"grad_norm": 0.8735964894294739,
|
| 1979 |
+
"learning_rate": 2e-05,
|
| 1980 |
+
"loss": 0.852,
|
| 1981 |
+
"step": 900
|
| 1982 |
+
},
|
| 1983 |
+
{
|
| 1984 |
+
"epoch": 1.4365522745411012,
|
| 1985 |
+
"eval_loss": 0.8946609497070312,
|
| 1986 |
+
"eval_runtime": 20.7777,
|
| 1987 |
+
"eval_samples_per_second": 1.492,
|
| 1988 |
+
"eval_steps_per_second": 0.77,
|
| 1989 |
+
"step": 900
|
| 1990 |
+
},
|
| 1991 |
+
{
|
| 1992 |
+
"epoch": 1.444533120510774,
|
| 1993 |
+
"grad_norm": 0.8208412528038025,
|
| 1994 |
+
"learning_rate": 1.9e-05,
|
| 1995 |
+
"loss": 0.7983,
|
| 1996 |
+
"step": 905
|
| 1997 |
+
},
|
| 1998 |
+
{
|
| 1999 |
+
"epoch": 1.452513966480447,
|
| 2000 |
+
"grad_norm": 0.9176042675971985,
|
| 2001 |
+
"learning_rate": 1.8e-05,
|
| 2002 |
+
"loss": 0.8296,
|
| 2003 |
+
"step": 910
|
| 2004 |
+
},
|
| 2005 |
+
{
|
| 2006 |
+
"epoch": 1.452513966480447,
|
| 2007 |
+
"eval_loss": 0.8942002654075623,
|
| 2008 |
+
"eval_runtime": 21.0465,
|
| 2009 |
+
"eval_samples_per_second": 1.473,
|
| 2010 |
+
"eval_steps_per_second": 0.76,
|
| 2011 |
+
"step": 910
|
| 2012 |
+
},
|
| 2013 |
+
{
|
| 2014 |
+
"epoch": 1.4604948124501198,
|
| 2015 |
+
"grad_norm": 0.7592383027076721,
|
| 2016 |
+
"learning_rate": 1.7000000000000003e-05,
|
| 2017 |
+
"loss": 0.809,
|
| 2018 |
+
"step": 915
|
| 2019 |
+
},
|
| 2020 |
+
{
|
| 2021 |
+
"epoch": 1.4684756584197924,
|
| 2022 |
+
"grad_norm": 0.8816229701042175,
|
| 2023 |
+
"learning_rate": 1.6000000000000003e-05,
|
| 2024 |
+
"loss": 0.7502,
|
| 2025 |
+
"step": 920
|
| 2026 |
+
},
|
| 2027 |
+
{
|
| 2028 |
+
"epoch": 1.4684756584197924,
|
| 2029 |
+
"eval_loss": 0.8975324034690857,
|
| 2030 |
+
"eval_runtime": 21.1221,
|
| 2031 |
+
"eval_samples_per_second": 1.468,
|
| 2032 |
+
"eval_steps_per_second": 0.758,
|
| 2033 |
+
"step": 920
|
| 2034 |
+
},
|
| 2035 |
+
{
|
| 2036 |
+
"epoch": 1.4764565043894653,
|
| 2037 |
+
"grad_norm": 0.8397924900054932,
|
| 2038 |
+
"learning_rate": 1.5e-05,
|
| 2039 |
+
"loss": 0.791,
|
| 2040 |
+
"step": 925
|
| 2041 |
+
},
|
| 2042 |
+
{
|
| 2043 |
+
"epoch": 1.484437350359138,
|
| 2044 |
+
"grad_norm": 0.9116021394729614,
|
| 2045 |
+
"learning_rate": 1.4000000000000001e-05,
|
| 2046 |
+
"loss": 0.77,
|
| 2047 |
+
"step": 930
|
| 2048 |
+
},
|
| 2049 |
+
{
|
| 2050 |
+
"epoch": 1.484437350359138,
|
| 2051 |
+
"eval_loss": 0.8986864686012268,
|
| 2052 |
+
"eval_runtime": 21.0542,
|
| 2053 |
+
"eval_samples_per_second": 1.472,
|
| 2054 |
+
"eval_steps_per_second": 0.76,
|
| 2055 |
+
"step": 930
|
| 2056 |
+
},
|
| 2057 |
+
{
|
| 2058 |
+
"epoch": 1.4924181963288108,
|
| 2059 |
+
"grad_norm": 0.8789558410644531,
|
| 2060 |
+
"learning_rate": 1.3000000000000001e-05,
|
| 2061 |
+
"loss": 0.8362,
|
| 2062 |
+
"step": 935
|
| 2063 |
+
},
|
| 2064 |
+
{
|
| 2065 |
+
"epoch": 1.5003990422984836,
|
| 2066 |
+
"grad_norm": 1.1174862384796143,
|
| 2067 |
+
"learning_rate": 1.2e-05,
|
| 2068 |
+
"loss": 0.7821,
|
| 2069 |
+
"step": 940
|
| 2070 |
+
},
|
| 2071 |
+
{
|
| 2072 |
+
"epoch": 1.5003990422984836,
|
| 2073 |
+
"eval_loss": 0.8970634341239929,
|
| 2074 |
+
"eval_runtime": 20.7967,
|
| 2075 |
+
"eval_samples_per_second": 1.491,
|
| 2076 |
+
"eval_steps_per_second": 0.769,
|
| 2077 |
+
"step": 940
|
| 2078 |
+
},
|
| 2079 |
+
{
|
| 2080 |
+
"epoch": 1.5083798882681565,
|
| 2081 |
+
"grad_norm": 0.8152345418930054,
|
| 2082 |
+
"learning_rate": 1.1000000000000001e-05,
|
| 2083 |
+
"loss": 0.7953,
|
| 2084 |
+
"step": 945
|
| 2085 |
+
},
|
| 2086 |
+
{
|
| 2087 |
+
"epoch": 1.5163607342378294,
|
| 2088 |
+
"grad_norm": 0.8047603964805603,
|
| 2089 |
+
"learning_rate": 1e-05,
|
| 2090 |
+
"loss": 0.7759,
|
| 2091 |
+
"step": 950
|
| 2092 |
+
},
|
| 2093 |
+
{
|
| 2094 |
+
"epoch": 1.5163607342378294,
|
| 2095 |
+
"eval_loss": 0.8968480229377747,
|
| 2096 |
+
"eval_runtime": 21.2746,
|
| 2097 |
+
"eval_samples_per_second": 1.457,
|
| 2098 |
+
"eval_steps_per_second": 0.752,
|
| 2099 |
+
"step": 950
|
| 2100 |
+
},
|
| 2101 |
+
{
|
| 2102 |
+
"epoch": 1.524341580207502,
|
| 2103 |
+
"grad_norm": 0.8262729048728943,
|
| 2104 |
+
"learning_rate": 9e-06,
|
| 2105 |
+
"loss": 0.8128,
|
| 2106 |
+
"step": 955
|
| 2107 |
+
},
|
| 2108 |
+
{
|
| 2109 |
+
"epoch": 1.5323224261771746,
|
| 2110 |
+
"grad_norm": 0.8479042649269104,
|
| 2111 |
+
"learning_rate": 8.000000000000001e-06,
|
| 2112 |
+
"loss": 0.7778,
|
| 2113 |
+
"step": 960
|
| 2114 |
+
},
|
| 2115 |
+
{
|
| 2116 |
+
"epoch": 1.5323224261771746,
|
| 2117 |
+
"eval_loss": 0.8949146270751953,
|
| 2118 |
+
"eval_runtime": 21.0684,
|
| 2119 |
+
"eval_samples_per_second": 1.471,
|
| 2120 |
+
"eval_steps_per_second": 0.759,
|
| 2121 |
+
"step": 960
|
| 2122 |
+
},
|
| 2123 |
+
{
|
| 2124 |
+
"epoch": 1.5403032721468475,
|
| 2125 |
+
"grad_norm": 0.7638890147209167,
|
| 2126 |
+
"learning_rate": 7.000000000000001e-06,
|
| 2127 |
+
"loss": 0.8371,
|
| 2128 |
+
"step": 965
|
| 2129 |
+
},
|
| 2130 |
+
{
|
| 2131 |
+
"epoch": 1.5482841181165203,
|
| 2132 |
+
"grad_norm": 1.009861707687378,
|
| 2133 |
+
"learning_rate": 6e-06,
|
| 2134 |
+
"loss": 0.6906,
|
| 2135 |
+
"step": 970
|
| 2136 |
+
},
|
| 2137 |
+
{
|
| 2138 |
+
"epoch": 1.5482841181165203,
|
| 2139 |
+
"eval_loss": 0.8940587043762207,
|
| 2140 |
+
"eval_runtime": 21.4138,
|
| 2141 |
+
"eval_samples_per_second": 1.448,
|
| 2142 |
+
"eval_steps_per_second": 0.747,
|
| 2143 |
+
"step": 970
|
| 2144 |
+
},
|
| 2145 |
+
{
|
| 2146 |
+
"epoch": 1.5562649640861932,
|
| 2147 |
+
"grad_norm": 0.8926388025283813,
|
| 2148 |
+
"learning_rate": 5e-06,
|
| 2149 |
+
"loss": 0.7935,
|
| 2150 |
+
"step": 975
|
| 2151 |
+
},
|
| 2152 |
+
{
|
| 2153 |
+
"epoch": 1.564245810055866,
|
| 2154 |
+
"grad_norm": 0.7741861939430237,
|
| 2155 |
+
"learning_rate": 4.000000000000001e-06,
|
| 2156 |
+
"loss": 0.8137,
|
| 2157 |
+
"step": 980
|
| 2158 |
+
},
|
| 2159 |
+
{
|
| 2160 |
+
"epoch": 1.564245810055866,
|
| 2161 |
+
"eval_loss": 0.895005464553833,
|
| 2162 |
+
"eval_runtime": 20.8613,
|
| 2163 |
+
"eval_samples_per_second": 1.486,
|
| 2164 |
+
"eval_steps_per_second": 0.767,
|
| 2165 |
+
"step": 980
|
| 2166 |
+
},
|
| 2167 |
+
{
|
| 2168 |
+
"epoch": 1.5722266560255387,
|
| 2169 |
+
"grad_norm": 0.950386106967926,
|
| 2170 |
+
"learning_rate": 3e-06,
|
| 2171 |
+
"loss": 0.6965,
|
| 2172 |
+
"step": 985
|
| 2173 |
+
},
|
| 2174 |
+
{
|
| 2175 |
+
"epoch": 1.5802075019952115,
|
| 2176 |
+
"grad_norm": 0.846916675567627,
|
| 2177 |
+
"learning_rate": 2.0000000000000003e-06,
|
| 2178 |
+
"loss": 0.799,
|
| 2179 |
+
"step": 990
|
| 2180 |
+
},
|
| 2181 |
+
{
|
| 2182 |
+
"epoch": 1.5802075019952115,
|
| 2183 |
+
"eval_loss": 0.8942360281944275,
|
| 2184 |
+
"eval_runtime": 21.1875,
|
| 2185 |
+
"eval_samples_per_second": 1.463,
|
| 2186 |
+
"eval_steps_per_second": 0.755,
|
| 2187 |
+
"step": 990
|
| 2188 |
+
},
|
| 2189 |
+
{
|
| 2190 |
+
"epoch": 1.5881883479648842,
|
| 2191 |
+
"grad_norm": 0.8533262610435486,
|
| 2192 |
+
"learning_rate": 1.0000000000000002e-06,
|
| 2193 |
+
"loss": 0.753,
|
| 2194 |
+
"step": 995
|
| 2195 |
+
},
|
| 2196 |
+
{
|
| 2197 |
+
"epoch": 1.596169193934557,
|
| 2198 |
+
"grad_norm": 0.7492548227310181,
|
| 2199 |
+
"learning_rate": 0.0,
|
| 2200 |
+
"loss": 0.7454,
|
| 2201 |
+
"step": 1000
|
| 2202 |
+
},
|
| 2203 |
+
{
|
| 2204 |
+
"epoch": 1.596169193934557,
|
| 2205 |
+
"eval_loss": 0.8934003114700317,
|
| 2206 |
+
"eval_runtime": 21.313,
|
| 2207 |
+
"eval_samples_per_second": 1.455,
|
| 2208 |
+
"eval_steps_per_second": 0.751,
|
| 2209 |
+
"step": 1000
|
| 2210 |
+
}
|
| 2211 |
+
],
|
| 2212 |
+
"logging_steps": 5,
|
| 2213 |
+
"max_steps": 1000,
|
| 2214 |
+
"num_input_tokens_seen": 0,
|
| 2215 |
+
"num_train_epochs": 2,
|
| 2216 |
+
"save_steps": 25,
|
| 2217 |
+
"stateful_callbacks": {
|
| 2218 |
+
"TrainerControl": {
|
| 2219 |
+
"args": {
|
| 2220 |
+
"should_epoch_stop": false,
|
| 2221 |
+
"should_evaluate": false,
|
| 2222 |
+
"should_log": false,
|
| 2223 |
+
"should_save": true,
|
| 2224 |
+
"should_training_stop": true
|
| 2225 |
+
},
|
| 2226 |
+
"attributes": {}
|
| 2227 |
+
}
|
| 2228 |
+
},
|
| 2229 |
+
"total_flos": 5.292030717299424e+16,
|
| 2230 |
+
"train_batch_size": 2,
|
| 2231 |
+
"trial_name": null,
|
| 2232 |
+
"trial_params": null
|
| 2233 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:99cae4c698d6c09f742f5e009c4f2966341f70462d72147713e459928f621868
|
| 3 |
+
size 5176
|