Pushed patched model
Browse files- checkpoint-254/README.md +202 -0
- checkpoint-254/adapter_config.json +40 -0
- checkpoint-254/adapter_model.safetensors +3 -0
- checkpoint-254/optimizer.pt +3 -0
- checkpoint-254/rng_state.pth +3 -0
- checkpoint-254/scheduler.pt +3 -0
- checkpoint-254/trainer_state.json +3577 -0
- checkpoint-254/training_args.bin +3 -0
- checkpoint-378/README.md +202 -0
- checkpoint-378/adapter_config.json +40 -0
- checkpoint-378/adapter_model.safetensors +3 -0
- checkpoint-378/optimizer.pt +3 -0
- checkpoint-378/rng_state.pth +3 -0
- checkpoint-378/scheduler.pt +3 -0
- checkpoint-378/trainer_state.json +0 -0
- checkpoint-378/training_args.bin +3 -0
checkpoint-254/README.md
ADDED
|
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
base_model: liuhaotian/llava-v1.5-7b
|
| 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 0.11.1
|
checkpoint-254/adapter_config.json
ADDED
|
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": {
|
| 4 |
+
"base_model_class": "LlavaLlamaForCausalLM",
|
| 5 |
+
"parent_library": "llava.model.language_model.llava_llama"
|
| 6 |
+
},
|
| 7 |
+
"base_model_name_or_path": "liuhaotian/llava-v1.5-7b",
|
| 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 |
+
"out_projfc1",
|
| 27 |
+
"down_proj",
|
| 28 |
+
"gate_proj",
|
| 29 |
+
"o_proj",
|
| 30 |
+
"q_proj",
|
| 31 |
+
"fc2model.mm_projector.0",
|
| 32 |
+
"v_proj",
|
| 33 |
+
"up_proj",
|
| 34 |
+
"k_proj",
|
| 35 |
+
"model.mm_projector.2"
|
| 36 |
+
],
|
| 37 |
+
"task_type": null,
|
| 38 |
+
"use_dora": false,
|
| 39 |
+
"use_rslora": false
|
| 40 |
+
}
|
checkpoint-254/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ef82b54c54780b003580849eb4b2bb6ccb1b63117cf5dfce7f5df826495b8849
|
| 3 |
+
size 85021296
|
checkpoint-254/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3314fe6577b83ee62013b5815e5b82c9f7f20339fffd1444ac288ca8493f57e1
|
| 3 |
+
size 160812632
|
checkpoint-254/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5588fd6d57ee4cc41d7a15553d69c6ec403ce8601a2aa9c975a7f3d57e53c132
|
| 3 |
+
size 14244
|
checkpoint-254/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5e9434f32499c5e3da038f841f491b8af79fe761a5eb44c343a42ee8dd5c15aa
|
| 3 |
+
size 1064
|
checkpoint-254/trainer_state.json
ADDED
|
@@ -0,0 +1,3577 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.9350641369819641,
|
| 3 |
+
"best_model_checkpoint": "llava-v1.5-7b-chess/checkpoint-254",
|
| 4 |
+
"epoch": 2.015873015873016,
|
| 5 |
+
"eval_steps": 1,
|
| 6 |
+
"global_step": 254,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.01,
|
| 13 |
+
"learning_rate": 9.973544973544973e-05,
|
| 14 |
+
"loss": 1.9416,
|
| 15 |
+
"step": 1
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.01,
|
| 19 |
+
"eval_loss": 1.8246577978134155,
|
| 20 |
+
"eval_runtime": 11.1051,
|
| 21 |
+
"eval_samples_per_second": 5.133,
|
| 22 |
+
"eval_steps_per_second": 1.711,
|
| 23 |
+
"step": 1
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.02,
|
| 27 |
+
"learning_rate": 9.947089947089946e-05,
|
| 28 |
+
"loss": 1.8254,
|
| 29 |
+
"step": 2
|
| 30 |
+
},
|
| 31 |
+
{
|
| 32 |
+
"epoch": 0.02,
|
| 33 |
+
"eval_loss": 1.7272577285766602,
|
| 34 |
+
"eval_runtime": 11.142,
|
| 35 |
+
"eval_samples_per_second": 5.116,
|
| 36 |
+
"eval_steps_per_second": 1.705,
|
| 37 |
+
"step": 2
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.02,
|
| 41 |
+
"learning_rate": 9.920634920634922e-05,
|
| 42 |
+
"loss": 1.726,
|
| 43 |
+
"step": 3
|
| 44 |
+
},
|
| 45 |
+
{
|
| 46 |
+
"epoch": 0.02,
|
| 47 |
+
"eval_loss": 1.630748987197876,
|
| 48 |
+
"eval_runtime": 11.2506,
|
| 49 |
+
"eval_samples_per_second": 5.066,
|
| 50 |
+
"eval_steps_per_second": 1.689,
|
| 51 |
+
"step": 3
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.03,
|
| 55 |
+
"learning_rate": 9.894179894179895e-05,
|
| 56 |
+
"loss": 1.5798,
|
| 57 |
+
"step": 4
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.03,
|
| 61 |
+
"eval_loss": 1.5509014129638672,
|
| 62 |
+
"eval_runtime": 11.2587,
|
| 63 |
+
"eval_samples_per_second": 5.063,
|
| 64 |
+
"eval_steps_per_second": 1.688,
|
| 65 |
+
"step": 4
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.04,
|
| 69 |
+
"learning_rate": 9.867724867724868e-05,
|
| 70 |
+
"loss": 1.4559,
|
| 71 |
+
"step": 5
|
| 72 |
+
},
|
| 73 |
+
{
|
| 74 |
+
"epoch": 0.04,
|
| 75 |
+
"eval_loss": 1.487467885017395,
|
| 76 |
+
"eval_runtime": 11.3884,
|
| 77 |
+
"eval_samples_per_second": 5.005,
|
| 78 |
+
"eval_steps_per_second": 1.668,
|
| 79 |
+
"step": 5
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.05,
|
| 83 |
+
"learning_rate": 9.841269841269841e-05,
|
| 84 |
+
"loss": 1.4914,
|
| 85 |
+
"step": 6
|
| 86 |
+
},
|
| 87 |
+
{
|
| 88 |
+
"epoch": 0.05,
|
| 89 |
+
"eval_loss": 1.4393059015274048,
|
| 90 |
+
"eval_runtime": 11.2599,
|
| 91 |
+
"eval_samples_per_second": 5.062,
|
| 92 |
+
"eval_steps_per_second": 1.687,
|
| 93 |
+
"step": 6
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.06,
|
| 97 |
+
"learning_rate": 9.814814814814815e-05,
|
| 98 |
+
"loss": 1.4471,
|
| 99 |
+
"step": 7
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.06,
|
| 103 |
+
"eval_loss": 1.4020471572875977,
|
| 104 |
+
"eval_runtime": 11.2524,
|
| 105 |
+
"eval_samples_per_second": 5.066,
|
| 106 |
+
"eval_steps_per_second": 1.689,
|
| 107 |
+
"step": 7
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.06,
|
| 111 |
+
"learning_rate": 9.78835978835979e-05,
|
| 112 |
+
"loss": 1.2306,
|
| 113 |
+
"step": 8
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 0.06,
|
| 117 |
+
"eval_loss": 1.3740724325180054,
|
| 118 |
+
"eval_runtime": 11.2867,
|
| 119 |
+
"eval_samples_per_second": 5.05,
|
| 120 |
+
"eval_steps_per_second": 1.683,
|
| 121 |
+
"step": 8
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.07,
|
| 125 |
+
"learning_rate": 9.761904761904762e-05,
|
| 126 |
+
"loss": 1.4704,
|
| 127 |
+
"step": 9
|
| 128 |
+
},
|
| 129 |
+
{
|
| 130 |
+
"epoch": 0.07,
|
| 131 |
+
"eval_loss": 1.3502081632614136,
|
| 132 |
+
"eval_runtime": 11.1146,
|
| 133 |
+
"eval_samples_per_second": 5.128,
|
| 134 |
+
"eval_steps_per_second": 1.709,
|
| 135 |
+
"step": 9
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.08,
|
| 139 |
+
"learning_rate": 9.735449735449735e-05,
|
| 140 |
+
"loss": 1.3146,
|
| 141 |
+
"step": 10
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 0.08,
|
| 145 |
+
"eval_loss": 1.3297895193099976,
|
| 146 |
+
"eval_runtime": 11.1575,
|
| 147 |
+
"eval_samples_per_second": 5.109,
|
| 148 |
+
"eval_steps_per_second": 1.703,
|
| 149 |
+
"step": 10
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.09,
|
| 153 |
+
"learning_rate": 9.70899470899471e-05,
|
| 154 |
+
"loss": 1.3019,
|
| 155 |
+
"step": 11
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 0.09,
|
| 159 |
+
"eval_loss": 1.3097199201583862,
|
| 160 |
+
"eval_runtime": 11.2593,
|
| 161 |
+
"eval_samples_per_second": 5.062,
|
| 162 |
+
"eval_steps_per_second": 1.687,
|
| 163 |
+
"step": 11
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.1,
|
| 167 |
+
"learning_rate": 9.682539682539682e-05,
|
| 168 |
+
"loss": 1.3221,
|
| 169 |
+
"step": 12
|
| 170 |
+
},
|
| 171 |
+
{
|
| 172 |
+
"epoch": 0.1,
|
| 173 |
+
"eval_loss": 1.2873374223709106,
|
| 174 |
+
"eval_runtime": 11.3312,
|
| 175 |
+
"eval_samples_per_second": 5.03,
|
| 176 |
+
"eval_steps_per_second": 1.677,
|
| 177 |
+
"step": 12
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.1,
|
| 181 |
+
"learning_rate": 9.656084656084657e-05,
|
| 182 |
+
"loss": 1.1772,
|
| 183 |
+
"step": 13
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 0.1,
|
| 187 |
+
"eval_loss": 1.266847014427185,
|
| 188 |
+
"eval_runtime": 11.1617,
|
| 189 |
+
"eval_samples_per_second": 5.107,
|
| 190 |
+
"eval_steps_per_second": 1.702,
|
| 191 |
+
"step": 13
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.11,
|
| 195 |
+
"learning_rate": 9.62962962962963e-05,
|
| 196 |
+
"loss": 1.3181,
|
| 197 |
+
"step": 14
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 0.11,
|
| 201 |
+
"eval_loss": 1.2443625926971436,
|
| 202 |
+
"eval_runtime": 11.1487,
|
| 203 |
+
"eval_samples_per_second": 5.113,
|
| 204 |
+
"eval_steps_per_second": 1.704,
|
| 205 |
+
"step": 14
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.12,
|
| 209 |
+
"learning_rate": 9.603174603174604e-05,
|
| 210 |
+
"loss": 1.3618,
|
| 211 |
+
"step": 15
|
| 212 |
+
},
|
| 213 |
+
{
|
| 214 |
+
"epoch": 0.12,
|
| 215 |
+
"eval_loss": 1.2243196964263916,
|
| 216 |
+
"eval_runtime": 11.1938,
|
| 217 |
+
"eval_samples_per_second": 5.092,
|
| 218 |
+
"eval_steps_per_second": 1.697,
|
| 219 |
+
"step": 15
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.13,
|
| 223 |
+
"learning_rate": 9.576719576719577e-05,
|
| 224 |
+
"loss": 1.1889,
|
| 225 |
+
"step": 16
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 0.13,
|
| 229 |
+
"eval_loss": 1.2069342136383057,
|
| 230 |
+
"eval_runtime": 11.4694,
|
| 231 |
+
"eval_samples_per_second": 4.97,
|
| 232 |
+
"eval_steps_per_second": 1.657,
|
| 233 |
+
"step": 16
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.13,
|
| 237 |
+
"learning_rate": 9.550264550264551e-05,
|
| 238 |
+
"loss": 1.1392,
|
| 239 |
+
"step": 17
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 0.13,
|
| 243 |
+
"eval_loss": 1.1917818784713745,
|
| 244 |
+
"eval_runtime": 11.2495,
|
| 245 |
+
"eval_samples_per_second": 5.067,
|
| 246 |
+
"eval_steps_per_second": 1.689,
|
| 247 |
+
"step": 17
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.14,
|
| 251 |
+
"learning_rate": 9.523809523809524e-05,
|
| 252 |
+
"loss": 1.0116,
|
| 253 |
+
"step": 18
|
| 254 |
+
},
|
| 255 |
+
{
|
| 256 |
+
"epoch": 0.14,
|
| 257 |
+
"eval_loss": 1.1815506219863892,
|
| 258 |
+
"eval_runtime": 11.242,
|
| 259 |
+
"eval_samples_per_second": 5.07,
|
| 260 |
+
"eval_steps_per_second": 1.69,
|
| 261 |
+
"step": 18
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.15,
|
| 265 |
+
"learning_rate": 9.497354497354498e-05,
|
| 266 |
+
"loss": 1.1372,
|
| 267 |
+
"step": 19
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 0.15,
|
| 271 |
+
"eval_loss": 1.1708626747131348,
|
| 272 |
+
"eval_runtime": 11.2192,
|
| 273 |
+
"eval_samples_per_second": 5.081,
|
| 274 |
+
"eval_steps_per_second": 1.694,
|
| 275 |
+
"step": 19
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.16,
|
| 279 |
+
"learning_rate": 9.470899470899471e-05,
|
| 280 |
+
"loss": 1.1948,
|
| 281 |
+
"step": 20
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 0.16,
|
| 285 |
+
"eval_loss": 1.1638435125350952,
|
| 286 |
+
"eval_runtime": 11.366,
|
| 287 |
+
"eval_samples_per_second": 5.015,
|
| 288 |
+
"eval_steps_per_second": 1.672,
|
| 289 |
+
"step": 20
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.17,
|
| 293 |
+
"learning_rate": 9.444444444444444e-05,
|
| 294 |
+
"loss": 1.0286,
|
| 295 |
+
"step": 21
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 0.17,
|
| 299 |
+
"eval_loss": 1.1577672958374023,
|
| 300 |
+
"eval_runtime": 11.1403,
|
| 301 |
+
"eval_samples_per_second": 5.117,
|
| 302 |
+
"eval_steps_per_second": 1.706,
|
| 303 |
+
"step": 21
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.17,
|
| 307 |
+
"learning_rate": 9.417989417989419e-05,
|
| 308 |
+
"loss": 1.1499,
|
| 309 |
+
"step": 22
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 0.17,
|
| 313 |
+
"eval_loss": 1.151979923248291,
|
| 314 |
+
"eval_runtime": 11.2244,
|
| 315 |
+
"eval_samples_per_second": 5.078,
|
| 316 |
+
"eval_steps_per_second": 1.693,
|
| 317 |
+
"step": 22
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.18,
|
| 321 |
+
"learning_rate": 9.391534391534393e-05,
|
| 322 |
+
"loss": 1.1372,
|
| 323 |
+
"step": 23
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 0.18,
|
| 327 |
+
"eval_loss": 1.144721269607544,
|
| 328 |
+
"eval_runtime": 11.2159,
|
| 329 |
+
"eval_samples_per_second": 5.082,
|
| 330 |
+
"eval_steps_per_second": 1.694,
|
| 331 |
+
"step": 23
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.19,
|
| 335 |
+
"learning_rate": 9.365079365079366e-05,
|
| 336 |
+
"loss": 1.1184,
|
| 337 |
+
"step": 24
|
| 338 |
+
},
|
| 339 |
+
{
|
| 340 |
+
"epoch": 0.19,
|
| 341 |
+
"eval_loss": 1.1370524168014526,
|
| 342 |
+
"eval_runtime": 11.6226,
|
| 343 |
+
"eval_samples_per_second": 4.904,
|
| 344 |
+
"eval_steps_per_second": 1.635,
|
| 345 |
+
"step": 24
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.2,
|
| 349 |
+
"learning_rate": 9.338624338624339e-05,
|
| 350 |
+
"loss": 0.9123,
|
| 351 |
+
"step": 25
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 0.2,
|
| 355 |
+
"eval_loss": 1.130428671836853,
|
| 356 |
+
"eval_runtime": 11.5048,
|
| 357 |
+
"eval_samples_per_second": 4.954,
|
| 358 |
+
"eval_steps_per_second": 1.651,
|
| 359 |
+
"step": 25
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.21,
|
| 363 |
+
"learning_rate": 9.312169312169312e-05,
|
| 364 |
+
"loss": 1.0534,
|
| 365 |
+
"step": 26
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"epoch": 0.21,
|
| 369 |
+
"eval_loss": 1.125217318534851,
|
| 370 |
+
"eval_runtime": 11.2392,
|
| 371 |
+
"eval_samples_per_second": 5.072,
|
| 372 |
+
"eval_steps_per_second": 1.691,
|
| 373 |
+
"step": 26
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.21,
|
| 377 |
+
"learning_rate": 9.285714285714286e-05,
|
| 378 |
+
"loss": 0.9502,
|
| 379 |
+
"step": 27
|
| 380 |
+
},
|
| 381 |
+
{
|
| 382 |
+
"epoch": 0.21,
|
| 383 |
+
"eval_loss": 1.118015170097351,
|
| 384 |
+
"eval_runtime": 11.3322,
|
| 385 |
+
"eval_samples_per_second": 5.03,
|
| 386 |
+
"eval_steps_per_second": 1.677,
|
| 387 |
+
"step": 27
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.22,
|
| 391 |
+
"learning_rate": 9.25925925925926e-05,
|
| 392 |
+
"loss": 1.0064,
|
| 393 |
+
"step": 28
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 0.22,
|
| 397 |
+
"eval_loss": 1.1118570566177368,
|
| 398 |
+
"eval_runtime": 11.5282,
|
| 399 |
+
"eval_samples_per_second": 4.944,
|
| 400 |
+
"eval_steps_per_second": 1.648,
|
| 401 |
+
"step": 28
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.23,
|
| 405 |
+
"learning_rate": 9.232804232804233e-05,
|
| 406 |
+
"loss": 1.1374,
|
| 407 |
+
"step": 29
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 0.23,
|
| 411 |
+
"eval_loss": 1.1059463024139404,
|
| 412 |
+
"eval_runtime": 11.448,
|
| 413 |
+
"eval_samples_per_second": 4.979,
|
| 414 |
+
"eval_steps_per_second": 1.66,
|
| 415 |
+
"step": 29
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.24,
|
| 419 |
+
"learning_rate": 9.206349206349206e-05,
|
| 420 |
+
"loss": 0.9704,
|
| 421 |
+
"step": 30
|
| 422 |
+
},
|
| 423 |
+
{
|
| 424 |
+
"epoch": 0.24,
|
| 425 |
+
"eval_loss": 1.1008621454238892,
|
| 426 |
+
"eval_runtime": 11.2328,
|
| 427 |
+
"eval_samples_per_second": 5.074,
|
| 428 |
+
"eval_steps_per_second": 1.691,
|
| 429 |
+
"step": 30
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.25,
|
| 433 |
+
"learning_rate": 9.17989417989418e-05,
|
| 434 |
+
"loss": 1.1065,
|
| 435 |
+
"step": 31
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 0.25,
|
| 439 |
+
"eval_loss": 1.0981618165969849,
|
| 440 |
+
"eval_runtime": 11.2834,
|
| 441 |
+
"eval_samples_per_second": 5.052,
|
| 442 |
+
"eval_steps_per_second": 1.684,
|
| 443 |
+
"step": 31
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.25,
|
| 447 |
+
"learning_rate": 9.153439153439155e-05,
|
| 448 |
+
"loss": 1.0171,
|
| 449 |
+
"step": 32
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 0.25,
|
| 453 |
+
"eval_loss": 1.0968972444534302,
|
| 454 |
+
"eval_runtime": 11.3954,
|
| 455 |
+
"eval_samples_per_second": 5.002,
|
| 456 |
+
"eval_steps_per_second": 1.667,
|
| 457 |
+
"step": 32
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.26,
|
| 461 |
+
"learning_rate": 9.126984126984128e-05,
|
| 462 |
+
"loss": 1.1673,
|
| 463 |
+
"step": 33
|
| 464 |
+
},
|
| 465 |
+
{
|
| 466 |
+
"epoch": 0.26,
|
| 467 |
+
"eval_loss": 1.0943207740783691,
|
| 468 |
+
"eval_runtime": 11.2123,
|
| 469 |
+
"eval_samples_per_second": 5.084,
|
| 470 |
+
"eval_steps_per_second": 1.695,
|
| 471 |
+
"step": 33
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.27,
|
| 475 |
+
"learning_rate": 9.1005291005291e-05,
|
| 476 |
+
"loss": 1.0381,
|
| 477 |
+
"step": 34
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 0.27,
|
| 481 |
+
"eval_loss": 1.09196937084198,
|
| 482 |
+
"eval_runtime": 11.2142,
|
| 483 |
+
"eval_samples_per_second": 5.083,
|
| 484 |
+
"eval_steps_per_second": 1.694,
|
| 485 |
+
"step": 34
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.28,
|
| 489 |
+
"learning_rate": 9.074074074074075e-05,
|
| 490 |
+
"loss": 1.0529,
|
| 491 |
+
"step": 35
|
| 492 |
+
},
|
| 493 |
+
{
|
| 494 |
+
"epoch": 0.28,
|
| 495 |
+
"eval_loss": 1.091015338897705,
|
| 496 |
+
"eval_runtime": 11.2585,
|
| 497 |
+
"eval_samples_per_second": 5.063,
|
| 498 |
+
"eval_steps_per_second": 1.688,
|
| 499 |
+
"step": 35
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.29,
|
| 503 |
+
"learning_rate": 9.047619047619048e-05,
|
| 504 |
+
"loss": 1.0849,
|
| 505 |
+
"step": 36
|
| 506 |
+
},
|
| 507 |
+
{
|
| 508 |
+
"epoch": 0.29,
|
| 509 |
+
"eval_loss": 1.0885584354400635,
|
| 510 |
+
"eval_runtime": 11.3567,
|
| 511 |
+
"eval_samples_per_second": 5.019,
|
| 512 |
+
"eval_steps_per_second": 1.673,
|
| 513 |
+
"step": 36
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.29,
|
| 517 |
+
"learning_rate": 9.021164021164022e-05,
|
| 518 |
+
"loss": 1.0472,
|
| 519 |
+
"step": 37
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 0.29,
|
| 523 |
+
"eval_loss": 1.0872443914413452,
|
| 524 |
+
"eval_runtime": 11.2417,
|
| 525 |
+
"eval_samples_per_second": 5.07,
|
| 526 |
+
"eval_steps_per_second": 1.69,
|
| 527 |
+
"step": 37
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.3,
|
| 531 |
+
"learning_rate": 8.994708994708995e-05,
|
| 532 |
+
"loss": 1.0949,
|
| 533 |
+
"step": 38
|
| 534 |
+
},
|
| 535 |
+
{
|
| 536 |
+
"epoch": 0.3,
|
| 537 |
+
"eval_loss": 1.0832560062408447,
|
| 538 |
+
"eval_runtime": 11.8516,
|
| 539 |
+
"eval_samples_per_second": 4.809,
|
| 540 |
+
"eval_steps_per_second": 1.603,
|
| 541 |
+
"step": 38
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.31,
|
| 545 |
+
"learning_rate": 8.968253968253969e-05,
|
| 546 |
+
"loss": 1.0909,
|
| 547 |
+
"step": 39
|
| 548 |
+
},
|
| 549 |
+
{
|
| 550 |
+
"epoch": 0.31,
|
| 551 |
+
"eval_loss": 1.0786099433898926,
|
| 552 |
+
"eval_runtime": 11.432,
|
| 553 |
+
"eval_samples_per_second": 4.986,
|
| 554 |
+
"eval_steps_per_second": 1.662,
|
| 555 |
+
"step": 39
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.32,
|
| 559 |
+
"learning_rate": 8.941798941798942e-05,
|
| 560 |
+
"loss": 0.9484,
|
| 561 |
+
"step": 40
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 0.32,
|
| 565 |
+
"eval_loss": 1.0725367069244385,
|
| 566 |
+
"eval_runtime": 11.4482,
|
| 567 |
+
"eval_samples_per_second": 4.979,
|
| 568 |
+
"eval_steps_per_second": 1.66,
|
| 569 |
+
"step": 40
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.33,
|
| 573 |
+
"learning_rate": 8.915343915343915e-05,
|
| 574 |
+
"loss": 1.0805,
|
| 575 |
+
"step": 41
|
| 576 |
+
},
|
| 577 |
+
{
|
| 578 |
+
"epoch": 0.33,
|
| 579 |
+
"eval_loss": 1.0665147304534912,
|
| 580 |
+
"eval_runtime": 11.259,
|
| 581 |
+
"eval_samples_per_second": 5.063,
|
| 582 |
+
"eval_steps_per_second": 1.688,
|
| 583 |
+
"step": 41
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.33,
|
| 587 |
+
"learning_rate": 8.888888888888889e-05,
|
| 588 |
+
"loss": 0.9088,
|
| 589 |
+
"step": 42
|
| 590 |
+
},
|
| 591 |
+
{
|
| 592 |
+
"epoch": 0.33,
|
| 593 |
+
"eval_loss": 1.0613280534744263,
|
| 594 |
+
"eval_runtime": 11.4272,
|
| 595 |
+
"eval_samples_per_second": 4.988,
|
| 596 |
+
"eval_steps_per_second": 1.663,
|
| 597 |
+
"step": 42
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.34,
|
| 601 |
+
"learning_rate": 8.862433862433864e-05,
|
| 602 |
+
"loss": 0.91,
|
| 603 |
+
"step": 43
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 0.34,
|
| 607 |
+
"eval_loss": 1.057435154914856,
|
| 608 |
+
"eval_runtime": 11.2452,
|
| 609 |
+
"eval_samples_per_second": 5.069,
|
| 610 |
+
"eval_steps_per_second": 1.69,
|
| 611 |
+
"step": 43
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.35,
|
| 615 |
+
"learning_rate": 8.835978835978837e-05,
|
| 616 |
+
"loss": 1.0241,
|
| 617 |
+
"step": 44
|
| 618 |
+
},
|
| 619 |
+
{
|
| 620 |
+
"epoch": 0.35,
|
| 621 |
+
"eval_loss": 1.0551300048828125,
|
| 622 |
+
"eval_runtime": 11.2229,
|
| 623 |
+
"eval_samples_per_second": 5.079,
|
| 624 |
+
"eval_steps_per_second": 1.693,
|
| 625 |
+
"step": 44
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.36,
|
| 629 |
+
"learning_rate": 8.80952380952381e-05,
|
| 630 |
+
"loss": 1.0352,
|
| 631 |
+
"step": 45
|
| 632 |
+
},
|
| 633 |
+
{
|
| 634 |
+
"epoch": 0.36,
|
| 635 |
+
"eval_loss": 1.0539908409118652,
|
| 636 |
+
"eval_runtime": 11.3835,
|
| 637 |
+
"eval_samples_per_second": 5.007,
|
| 638 |
+
"eval_steps_per_second": 1.669,
|
| 639 |
+
"step": 45
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.37,
|
| 643 |
+
"learning_rate": 8.783068783068782e-05,
|
| 644 |
+
"loss": 1.0175,
|
| 645 |
+
"step": 46
|
| 646 |
+
},
|
| 647 |
+
{
|
| 648 |
+
"epoch": 0.37,
|
| 649 |
+
"eval_loss": 1.0538028478622437,
|
| 650 |
+
"eval_runtime": 11.3312,
|
| 651 |
+
"eval_samples_per_second": 5.03,
|
| 652 |
+
"eval_steps_per_second": 1.677,
|
| 653 |
+
"step": 46
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 0.37,
|
| 657 |
+
"learning_rate": 8.756613756613758e-05,
|
| 658 |
+
"loss": 0.9668,
|
| 659 |
+
"step": 47
|
| 660 |
+
},
|
| 661 |
+
{
|
| 662 |
+
"epoch": 0.37,
|
| 663 |
+
"eval_loss": 1.0534106492996216,
|
| 664 |
+
"eval_runtime": 11.2714,
|
| 665 |
+
"eval_samples_per_second": 5.057,
|
| 666 |
+
"eval_steps_per_second": 1.686,
|
| 667 |
+
"step": 47
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 0.38,
|
| 671 |
+
"learning_rate": 8.730158730158731e-05,
|
| 672 |
+
"loss": 1.0426,
|
| 673 |
+
"step": 48
|
| 674 |
+
},
|
| 675 |
+
{
|
| 676 |
+
"epoch": 0.38,
|
| 677 |
+
"eval_loss": 1.052772045135498,
|
| 678 |
+
"eval_runtime": 11.2543,
|
| 679 |
+
"eval_samples_per_second": 5.065,
|
| 680 |
+
"eval_steps_per_second": 1.688,
|
| 681 |
+
"step": 48
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.39,
|
| 685 |
+
"learning_rate": 8.703703703703704e-05,
|
| 686 |
+
"loss": 1.0044,
|
| 687 |
+
"step": 49
|
| 688 |
+
},
|
| 689 |
+
{
|
| 690 |
+
"epoch": 0.39,
|
| 691 |
+
"eval_loss": 1.0515741109848022,
|
| 692 |
+
"eval_runtime": 11.3376,
|
| 693 |
+
"eval_samples_per_second": 5.028,
|
| 694 |
+
"eval_steps_per_second": 1.676,
|
| 695 |
+
"step": 49
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 0.4,
|
| 699 |
+
"learning_rate": 8.677248677248677e-05,
|
| 700 |
+
"loss": 1.0367,
|
| 701 |
+
"step": 50
|
| 702 |
+
},
|
| 703 |
+
{
|
| 704 |
+
"epoch": 0.4,
|
| 705 |
+
"eval_loss": 1.049968957901001,
|
| 706 |
+
"eval_runtime": 11.2567,
|
| 707 |
+
"eval_samples_per_second": 5.064,
|
| 708 |
+
"eval_steps_per_second": 1.688,
|
| 709 |
+
"step": 50
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 0.4,
|
| 713 |
+
"learning_rate": 8.650793650793651e-05,
|
| 714 |
+
"loss": 1.1123,
|
| 715 |
+
"step": 51
|
| 716 |
+
},
|
| 717 |
+
{
|
| 718 |
+
"epoch": 0.4,
|
| 719 |
+
"eval_loss": 1.0470366477966309,
|
| 720 |
+
"eval_runtime": 11.1206,
|
| 721 |
+
"eval_samples_per_second": 5.126,
|
| 722 |
+
"eval_steps_per_second": 1.709,
|
| 723 |
+
"step": 51
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 0.41,
|
| 727 |
+
"learning_rate": 8.624338624338625e-05,
|
| 728 |
+
"loss": 1.0706,
|
| 729 |
+
"step": 52
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 0.41,
|
| 733 |
+
"eval_loss": 1.0442218780517578,
|
| 734 |
+
"eval_runtime": 11.2711,
|
| 735 |
+
"eval_samples_per_second": 5.057,
|
| 736 |
+
"eval_steps_per_second": 1.686,
|
| 737 |
+
"step": 52
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 0.42,
|
| 741 |
+
"learning_rate": 8.597883597883598e-05,
|
| 742 |
+
"loss": 0.9999,
|
| 743 |
+
"step": 53
|
| 744 |
+
},
|
| 745 |
+
{
|
| 746 |
+
"epoch": 0.42,
|
| 747 |
+
"eval_loss": 1.0409353971481323,
|
| 748 |
+
"eval_runtime": 11.2516,
|
| 749 |
+
"eval_samples_per_second": 5.066,
|
| 750 |
+
"eval_steps_per_second": 1.689,
|
| 751 |
+
"step": 53
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 0.43,
|
| 755 |
+
"learning_rate": 8.571428571428571e-05,
|
| 756 |
+
"loss": 1.0905,
|
| 757 |
+
"step": 54
|
| 758 |
+
},
|
| 759 |
+
{
|
| 760 |
+
"epoch": 0.43,
|
| 761 |
+
"eval_loss": 1.0385661125183105,
|
| 762 |
+
"eval_runtime": 11.328,
|
| 763 |
+
"eval_samples_per_second": 5.032,
|
| 764 |
+
"eval_steps_per_second": 1.677,
|
| 765 |
+
"step": 54
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 0.44,
|
| 769 |
+
"learning_rate": 8.544973544973546e-05,
|
| 770 |
+
"loss": 0.8978,
|
| 771 |
+
"step": 55
|
| 772 |
+
},
|
| 773 |
+
{
|
| 774 |
+
"epoch": 0.44,
|
| 775 |
+
"eval_loss": 1.0356653928756714,
|
| 776 |
+
"eval_runtime": 11.3452,
|
| 777 |
+
"eval_samples_per_second": 5.024,
|
| 778 |
+
"eval_steps_per_second": 1.675,
|
| 779 |
+
"step": 55
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 0.44,
|
| 783 |
+
"learning_rate": 8.518518518518518e-05,
|
| 784 |
+
"loss": 1.0951,
|
| 785 |
+
"step": 56
|
| 786 |
+
},
|
| 787 |
+
{
|
| 788 |
+
"epoch": 0.44,
|
| 789 |
+
"eval_loss": 1.0337508916854858,
|
| 790 |
+
"eval_runtime": 11.2553,
|
| 791 |
+
"eval_samples_per_second": 5.064,
|
| 792 |
+
"eval_steps_per_second": 1.688,
|
| 793 |
+
"step": 56
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 0.45,
|
| 797 |
+
"learning_rate": 8.492063492063493e-05,
|
| 798 |
+
"loss": 0.978,
|
| 799 |
+
"step": 57
|
| 800 |
+
},
|
| 801 |
+
{
|
| 802 |
+
"epoch": 0.45,
|
| 803 |
+
"eval_loss": 1.031426191329956,
|
| 804 |
+
"eval_runtime": 11.3396,
|
| 805 |
+
"eval_samples_per_second": 5.027,
|
| 806 |
+
"eval_steps_per_second": 1.676,
|
| 807 |
+
"step": 57
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 0.46,
|
| 811 |
+
"learning_rate": 8.465608465608466e-05,
|
| 812 |
+
"loss": 0.9974,
|
| 813 |
+
"step": 58
|
| 814 |
+
},
|
| 815 |
+
{
|
| 816 |
+
"epoch": 0.46,
|
| 817 |
+
"eval_loss": 1.0299843549728394,
|
| 818 |
+
"eval_runtime": 11.3892,
|
| 819 |
+
"eval_samples_per_second": 5.005,
|
| 820 |
+
"eval_steps_per_second": 1.668,
|
| 821 |
+
"step": 58
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 0.47,
|
| 825 |
+
"learning_rate": 8.43915343915344e-05,
|
| 826 |
+
"loss": 0.9869,
|
| 827 |
+
"step": 59
|
| 828 |
+
},
|
| 829 |
+
{
|
| 830 |
+
"epoch": 0.47,
|
| 831 |
+
"eval_loss": 1.0282464027404785,
|
| 832 |
+
"eval_runtime": 11.2739,
|
| 833 |
+
"eval_samples_per_second": 5.056,
|
| 834 |
+
"eval_steps_per_second": 1.685,
|
| 835 |
+
"step": 59
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 0.48,
|
| 839 |
+
"learning_rate": 8.412698412698413e-05,
|
| 840 |
+
"loss": 1.0325,
|
| 841 |
+
"step": 60
|
| 842 |
+
},
|
| 843 |
+
{
|
| 844 |
+
"epoch": 0.48,
|
| 845 |
+
"eval_loss": 1.0266135931015015,
|
| 846 |
+
"eval_runtime": 11.2367,
|
| 847 |
+
"eval_samples_per_second": 5.073,
|
| 848 |
+
"eval_steps_per_second": 1.691,
|
| 849 |
+
"step": 60
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 0.48,
|
| 853 |
+
"learning_rate": 8.386243386243386e-05,
|
| 854 |
+
"loss": 1.0886,
|
| 855 |
+
"step": 61
|
| 856 |
+
},
|
| 857 |
+
{
|
| 858 |
+
"epoch": 0.48,
|
| 859 |
+
"eval_loss": 1.0231937170028687,
|
| 860 |
+
"eval_runtime": 11.3652,
|
| 861 |
+
"eval_samples_per_second": 5.015,
|
| 862 |
+
"eval_steps_per_second": 1.672,
|
| 863 |
+
"step": 61
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 0.49,
|
| 867 |
+
"learning_rate": 8.35978835978836e-05,
|
| 868 |
+
"loss": 1.1033,
|
| 869 |
+
"step": 62
|
| 870 |
+
},
|
| 871 |
+
{
|
| 872 |
+
"epoch": 0.49,
|
| 873 |
+
"eval_loss": 1.0222442150115967,
|
| 874 |
+
"eval_runtime": 11.2493,
|
| 875 |
+
"eval_samples_per_second": 5.067,
|
| 876 |
+
"eval_steps_per_second": 1.689,
|
| 877 |
+
"step": 62
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 0.5,
|
| 881 |
+
"learning_rate": 8.333333333333334e-05,
|
| 882 |
+
"loss": 1.0087,
|
| 883 |
+
"step": 63
|
| 884 |
+
},
|
| 885 |
+
{
|
| 886 |
+
"epoch": 0.5,
|
| 887 |
+
"eval_loss": 1.020636796951294,
|
| 888 |
+
"eval_runtime": 11.2865,
|
| 889 |
+
"eval_samples_per_second": 5.05,
|
| 890 |
+
"eval_steps_per_second": 1.683,
|
| 891 |
+
"step": 63
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 0.51,
|
| 895 |
+
"learning_rate": 8.306878306878307e-05,
|
| 896 |
+
"loss": 0.8476,
|
| 897 |
+
"step": 64
|
| 898 |
+
},
|
| 899 |
+
{
|
| 900 |
+
"epoch": 0.51,
|
| 901 |
+
"eval_loss": 1.0187979936599731,
|
| 902 |
+
"eval_runtime": 11.289,
|
| 903 |
+
"eval_samples_per_second": 5.049,
|
| 904 |
+
"eval_steps_per_second": 1.683,
|
| 905 |
+
"step": 64
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 0.52,
|
| 909 |
+
"learning_rate": 8.28042328042328e-05,
|
| 910 |
+
"loss": 0.9543,
|
| 911 |
+
"step": 65
|
| 912 |
+
},
|
| 913 |
+
{
|
| 914 |
+
"epoch": 0.52,
|
| 915 |
+
"eval_loss": 1.0155143737792969,
|
| 916 |
+
"eval_runtime": 11.2374,
|
| 917 |
+
"eval_samples_per_second": 5.072,
|
| 918 |
+
"eval_steps_per_second": 1.691,
|
| 919 |
+
"step": 65
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 0.52,
|
| 923 |
+
"learning_rate": 8.253968253968255e-05,
|
| 924 |
+
"loss": 0.933,
|
| 925 |
+
"step": 66
|
| 926 |
+
},
|
| 927 |
+
{
|
| 928 |
+
"epoch": 0.52,
|
| 929 |
+
"eval_loss": 1.0131887197494507,
|
| 930 |
+
"eval_runtime": 11.2775,
|
| 931 |
+
"eval_samples_per_second": 5.054,
|
| 932 |
+
"eval_steps_per_second": 1.685,
|
| 933 |
+
"step": 66
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 0.53,
|
| 937 |
+
"learning_rate": 8.227513227513229e-05,
|
| 938 |
+
"loss": 1.0186,
|
| 939 |
+
"step": 67
|
| 940 |
+
},
|
| 941 |
+
{
|
| 942 |
+
"epoch": 0.53,
|
| 943 |
+
"eval_loss": 1.0090850591659546,
|
| 944 |
+
"eval_runtime": 11.3677,
|
| 945 |
+
"eval_samples_per_second": 5.014,
|
| 946 |
+
"eval_steps_per_second": 1.671,
|
| 947 |
+
"step": 67
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 0.54,
|
| 951 |
+
"learning_rate": 8.201058201058202e-05,
|
| 952 |
+
"loss": 0.9425,
|
| 953 |
+
"step": 68
|
| 954 |
+
},
|
| 955 |
+
{
|
| 956 |
+
"epoch": 0.54,
|
| 957 |
+
"eval_loss": 1.0056878328323364,
|
| 958 |
+
"eval_runtime": 11.0888,
|
| 959 |
+
"eval_samples_per_second": 5.14,
|
| 960 |
+
"eval_steps_per_second": 1.713,
|
| 961 |
+
"step": 68
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 0.55,
|
| 965 |
+
"learning_rate": 8.174603174603175e-05,
|
| 966 |
+
"loss": 0.9943,
|
| 967 |
+
"step": 69
|
| 968 |
+
},
|
| 969 |
+
{
|
| 970 |
+
"epoch": 0.55,
|
| 971 |
+
"eval_loss": 1.0025955438613892,
|
| 972 |
+
"eval_runtime": 11.2572,
|
| 973 |
+
"eval_samples_per_second": 5.063,
|
| 974 |
+
"eval_steps_per_second": 1.688,
|
| 975 |
+
"step": 69
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 0.56,
|
| 979 |
+
"learning_rate": 8.148148148148148e-05,
|
| 980 |
+
"loss": 1.1287,
|
| 981 |
+
"step": 70
|
| 982 |
+
},
|
| 983 |
+
{
|
| 984 |
+
"epoch": 0.56,
|
| 985 |
+
"eval_loss": 1.0005890130996704,
|
| 986 |
+
"eval_runtime": 11.2495,
|
| 987 |
+
"eval_samples_per_second": 5.067,
|
| 988 |
+
"eval_steps_per_second": 1.689,
|
| 989 |
+
"step": 70
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 0.56,
|
| 993 |
+
"learning_rate": 8.121693121693122e-05,
|
| 994 |
+
"loss": 1.0688,
|
| 995 |
+
"step": 71
|
| 996 |
+
},
|
| 997 |
+
{
|
| 998 |
+
"epoch": 0.56,
|
| 999 |
+
"eval_loss": 0.9989040493965149,
|
| 1000 |
+
"eval_runtime": 11.2643,
|
| 1001 |
+
"eval_samples_per_second": 5.06,
|
| 1002 |
+
"eval_steps_per_second": 1.687,
|
| 1003 |
+
"step": 71
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 0.57,
|
| 1007 |
+
"learning_rate": 8.095238095238096e-05,
|
| 1008 |
+
"loss": 1.0818,
|
| 1009 |
+
"step": 72
|
| 1010 |
+
},
|
| 1011 |
+
{
|
| 1012 |
+
"epoch": 0.57,
|
| 1013 |
+
"eval_loss": 0.9982772469520569,
|
| 1014 |
+
"eval_runtime": 11.121,
|
| 1015 |
+
"eval_samples_per_second": 5.125,
|
| 1016 |
+
"eval_steps_per_second": 1.708,
|
| 1017 |
+
"step": 72
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 0.58,
|
| 1021 |
+
"learning_rate": 8.068783068783069e-05,
|
| 1022 |
+
"loss": 0.9234,
|
| 1023 |
+
"step": 73
|
| 1024 |
+
},
|
| 1025 |
+
{
|
| 1026 |
+
"epoch": 0.58,
|
| 1027 |
+
"eval_loss": 0.9961081147193909,
|
| 1028 |
+
"eval_runtime": 11.268,
|
| 1029 |
+
"eval_samples_per_second": 5.059,
|
| 1030 |
+
"eval_steps_per_second": 1.686,
|
| 1031 |
+
"step": 73
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 0.59,
|
| 1035 |
+
"learning_rate": 8.042328042328042e-05,
|
| 1036 |
+
"loss": 0.9169,
|
| 1037 |
+
"step": 74
|
| 1038 |
+
},
|
| 1039 |
+
{
|
| 1040 |
+
"epoch": 0.59,
|
| 1041 |
+
"eval_loss": 0.9951977729797363,
|
| 1042 |
+
"eval_runtime": 11.3425,
|
| 1043 |
+
"eval_samples_per_second": 5.025,
|
| 1044 |
+
"eval_steps_per_second": 1.675,
|
| 1045 |
+
"step": 74
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 0.6,
|
| 1049 |
+
"learning_rate": 8.015873015873016e-05,
|
| 1050 |
+
"loss": 0.8732,
|
| 1051 |
+
"step": 75
|
| 1052 |
+
},
|
| 1053 |
+
{
|
| 1054 |
+
"epoch": 0.6,
|
| 1055 |
+
"eval_loss": 0.9947168827056885,
|
| 1056 |
+
"eval_runtime": 11.4976,
|
| 1057 |
+
"eval_samples_per_second": 4.958,
|
| 1058 |
+
"eval_steps_per_second": 1.653,
|
| 1059 |
+
"step": 75
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 0.6,
|
| 1063 |
+
"learning_rate": 7.989417989417989e-05,
|
| 1064 |
+
"loss": 1.1112,
|
| 1065 |
+
"step": 76
|
| 1066 |
+
},
|
| 1067 |
+
{
|
| 1068 |
+
"epoch": 0.6,
|
| 1069 |
+
"eval_loss": 0.9937358498573303,
|
| 1070 |
+
"eval_runtime": 11.2157,
|
| 1071 |
+
"eval_samples_per_second": 5.082,
|
| 1072 |
+
"eval_steps_per_second": 1.694,
|
| 1073 |
+
"step": 76
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 0.61,
|
| 1077 |
+
"learning_rate": 7.962962962962964e-05,
|
| 1078 |
+
"loss": 1.0538,
|
| 1079 |
+
"step": 77
|
| 1080 |
+
},
|
| 1081 |
+
{
|
| 1082 |
+
"epoch": 0.61,
|
| 1083 |
+
"eval_loss": 0.992274284362793,
|
| 1084 |
+
"eval_runtime": 11.3598,
|
| 1085 |
+
"eval_samples_per_second": 5.018,
|
| 1086 |
+
"eval_steps_per_second": 1.673,
|
| 1087 |
+
"step": 77
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 0.62,
|
| 1091 |
+
"learning_rate": 7.936507936507937e-05,
|
| 1092 |
+
"loss": 1.0636,
|
| 1093 |
+
"step": 78
|
| 1094 |
+
},
|
| 1095 |
+
{
|
| 1096 |
+
"epoch": 0.62,
|
| 1097 |
+
"eval_loss": 0.9908178448677063,
|
| 1098 |
+
"eval_runtime": 11.0889,
|
| 1099 |
+
"eval_samples_per_second": 5.14,
|
| 1100 |
+
"eval_steps_per_second": 1.713,
|
| 1101 |
+
"step": 78
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 0.63,
|
| 1105 |
+
"learning_rate": 7.910052910052911e-05,
|
| 1106 |
+
"loss": 0.9079,
|
| 1107 |
+
"step": 79
|
| 1108 |
+
},
|
| 1109 |
+
{
|
| 1110 |
+
"epoch": 0.63,
|
| 1111 |
+
"eval_loss": 0.9905064105987549,
|
| 1112 |
+
"eval_runtime": 11.1638,
|
| 1113 |
+
"eval_samples_per_second": 5.106,
|
| 1114 |
+
"eval_steps_per_second": 1.702,
|
| 1115 |
+
"step": 79
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 0.63,
|
| 1119 |
+
"learning_rate": 7.883597883597884e-05,
|
| 1120 |
+
"loss": 0.9104,
|
| 1121 |
+
"step": 80
|
| 1122 |
+
},
|
| 1123 |
+
{
|
| 1124 |
+
"epoch": 0.63,
|
| 1125 |
+
"eval_loss": 0.989557683467865,
|
| 1126 |
+
"eval_runtime": 11.4363,
|
| 1127 |
+
"eval_samples_per_second": 4.984,
|
| 1128 |
+
"eval_steps_per_second": 1.661,
|
| 1129 |
+
"step": 80
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 0.64,
|
| 1133 |
+
"learning_rate": 7.857142857142858e-05,
|
| 1134 |
+
"loss": 0.9058,
|
| 1135 |
+
"step": 81
|
| 1136 |
+
},
|
| 1137 |
+
{
|
| 1138 |
+
"epoch": 0.64,
|
| 1139 |
+
"eval_loss": 0.9902251958847046,
|
| 1140 |
+
"eval_runtime": 11.4861,
|
| 1141 |
+
"eval_samples_per_second": 4.963,
|
| 1142 |
+
"eval_steps_per_second": 1.654,
|
| 1143 |
+
"step": 81
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 0.65,
|
| 1147 |
+
"learning_rate": 7.830687830687831e-05,
|
| 1148 |
+
"loss": 0.9653,
|
| 1149 |
+
"step": 82
|
| 1150 |
+
},
|
| 1151 |
+
{
|
| 1152 |
+
"epoch": 0.65,
|
| 1153 |
+
"eval_loss": 0.9908925294876099,
|
| 1154 |
+
"eval_runtime": 11.56,
|
| 1155 |
+
"eval_samples_per_second": 4.931,
|
| 1156 |
+
"eval_steps_per_second": 1.644,
|
| 1157 |
+
"step": 82
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 0.66,
|
| 1161 |
+
"learning_rate": 7.804232804232805e-05,
|
| 1162 |
+
"loss": 0.8773,
|
| 1163 |
+
"step": 83
|
| 1164 |
+
},
|
| 1165 |
+
{
|
| 1166 |
+
"epoch": 0.66,
|
| 1167 |
+
"eval_loss": 0.9919198751449585,
|
| 1168 |
+
"eval_runtime": 11.6172,
|
| 1169 |
+
"eval_samples_per_second": 4.906,
|
| 1170 |
+
"eval_steps_per_second": 1.635,
|
| 1171 |
+
"step": 83
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 0.67,
|
| 1175 |
+
"learning_rate": 7.777777777777778e-05,
|
| 1176 |
+
"loss": 0.7942,
|
| 1177 |
+
"step": 84
|
| 1178 |
+
},
|
| 1179 |
+
{
|
| 1180 |
+
"epoch": 0.67,
|
| 1181 |
+
"eval_loss": 0.9942153096199036,
|
| 1182 |
+
"eval_runtime": 11.3584,
|
| 1183 |
+
"eval_samples_per_second": 5.018,
|
| 1184 |
+
"eval_steps_per_second": 1.673,
|
| 1185 |
+
"step": 84
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 0.67,
|
| 1189 |
+
"learning_rate": 7.751322751322751e-05,
|
| 1190 |
+
"loss": 0.894,
|
| 1191 |
+
"step": 85
|
| 1192 |
+
},
|
| 1193 |
+
{
|
| 1194 |
+
"epoch": 0.67,
|
| 1195 |
+
"eval_loss": 0.9940976500511169,
|
| 1196 |
+
"eval_runtime": 11.4867,
|
| 1197 |
+
"eval_samples_per_second": 4.962,
|
| 1198 |
+
"eval_steps_per_second": 1.654,
|
| 1199 |
+
"step": 85
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 0.68,
|
| 1203 |
+
"learning_rate": 7.724867724867725e-05,
|
| 1204 |
+
"loss": 1.0039,
|
| 1205 |
+
"step": 86
|
| 1206 |
+
},
|
| 1207 |
+
{
|
| 1208 |
+
"epoch": 0.68,
|
| 1209 |
+
"eval_loss": 0.9931285977363586,
|
| 1210 |
+
"eval_runtime": 11.171,
|
| 1211 |
+
"eval_samples_per_second": 5.102,
|
| 1212 |
+
"eval_steps_per_second": 1.701,
|
| 1213 |
+
"step": 86
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 0.69,
|
| 1217 |
+
"learning_rate": 7.6984126984127e-05,
|
| 1218 |
+
"loss": 1.0113,
|
| 1219 |
+
"step": 87
|
| 1220 |
+
},
|
| 1221 |
+
{
|
| 1222 |
+
"epoch": 0.69,
|
| 1223 |
+
"eval_loss": 0.9918901324272156,
|
| 1224 |
+
"eval_runtime": 11.2632,
|
| 1225 |
+
"eval_samples_per_second": 5.061,
|
| 1226 |
+
"eval_steps_per_second": 1.687,
|
| 1227 |
+
"step": 87
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 0.7,
|
| 1231 |
+
"learning_rate": 7.671957671957673e-05,
|
| 1232 |
+
"loss": 1.1145,
|
| 1233 |
+
"step": 88
|
| 1234 |
+
},
|
| 1235 |
+
{
|
| 1236 |
+
"epoch": 0.7,
|
| 1237 |
+
"eval_loss": 0.9903886318206787,
|
| 1238 |
+
"eval_runtime": 11.3871,
|
| 1239 |
+
"eval_samples_per_second": 5.006,
|
| 1240 |
+
"eval_steps_per_second": 1.669,
|
| 1241 |
+
"step": 88
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 0.71,
|
| 1245 |
+
"learning_rate": 7.645502645502646e-05,
|
| 1246 |
+
"loss": 0.8794,
|
| 1247 |
+
"step": 89
|
| 1248 |
+
},
|
| 1249 |
+
{
|
| 1250 |
+
"epoch": 0.71,
|
| 1251 |
+
"eval_loss": 0.9867441058158875,
|
| 1252 |
+
"eval_runtime": 11.5122,
|
| 1253 |
+
"eval_samples_per_second": 4.951,
|
| 1254 |
+
"eval_steps_per_second": 1.65,
|
| 1255 |
+
"step": 89
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 0.71,
|
| 1259 |
+
"learning_rate": 7.619047619047618e-05,
|
| 1260 |
+
"loss": 1.1085,
|
| 1261 |
+
"step": 90
|
| 1262 |
+
},
|
| 1263 |
+
{
|
| 1264 |
+
"epoch": 0.71,
|
| 1265 |
+
"eval_loss": 0.9836506843566895,
|
| 1266 |
+
"eval_runtime": 11.2029,
|
| 1267 |
+
"eval_samples_per_second": 5.088,
|
| 1268 |
+
"eval_steps_per_second": 1.696,
|
| 1269 |
+
"step": 90
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 0.72,
|
| 1273 |
+
"learning_rate": 7.592592592592593e-05,
|
| 1274 |
+
"loss": 0.9683,
|
| 1275 |
+
"step": 91
|
| 1276 |
+
},
|
| 1277 |
+
{
|
| 1278 |
+
"epoch": 0.72,
|
| 1279 |
+
"eval_loss": 0.9819443225860596,
|
| 1280 |
+
"eval_runtime": 11.4398,
|
| 1281 |
+
"eval_samples_per_second": 4.983,
|
| 1282 |
+
"eval_steps_per_second": 1.661,
|
| 1283 |
+
"step": 91
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 0.73,
|
| 1287 |
+
"learning_rate": 7.566137566137567e-05,
|
| 1288 |
+
"loss": 0.9378,
|
| 1289 |
+
"step": 92
|
| 1290 |
+
},
|
| 1291 |
+
{
|
| 1292 |
+
"epoch": 0.73,
|
| 1293 |
+
"eval_loss": 0.9801782369613647,
|
| 1294 |
+
"eval_runtime": 11.2742,
|
| 1295 |
+
"eval_samples_per_second": 5.056,
|
| 1296 |
+
"eval_steps_per_second": 1.685,
|
| 1297 |
+
"step": 92
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 0.74,
|
| 1301 |
+
"learning_rate": 7.53968253968254e-05,
|
| 1302 |
+
"loss": 1.0159,
|
| 1303 |
+
"step": 93
|
| 1304 |
+
},
|
| 1305 |
+
{
|
| 1306 |
+
"epoch": 0.74,
|
| 1307 |
+
"eval_loss": 0.9785143733024597,
|
| 1308 |
+
"eval_runtime": 11.3247,
|
| 1309 |
+
"eval_samples_per_second": 5.033,
|
| 1310 |
+
"eval_steps_per_second": 1.678,
|
| 1311 |
+
"step": 93
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 0.75,
|
| 1315 |
+
"learning_rate": 7.513227513227513e-05,
|
| 1316 |
+
"loss": 0.8486,
|
| 1317 |
+
"step": 94
|
| 1318 |
+
},
|
| 1319 |
+
{
|
| 1320 |
+
"epoch": 0.75,
|
| 1321 |
+
"eval_loss": 0.9786610007286072,
|
| 1322 |
+
"eval_runtime": 11.4473,
|
| 1323 |
+
"eval_samples_per_second": 4.979,
|
| 1324 |
+
"eval_steps_per_second": 1.66,
|
| 1325 |
+
"step": 94
|
| 1326 |
+
},
|
| 1327 |
+
{
|
| 1328 |
+
"epoch": 0.75,
|
| 1329 |
+
"learning_rate": 7.486772486772487e-05,
|
| 1330 |
+
"loss": 1.0572,
|
| 1331 |
+
"step": 95
|
| 1332 |
+
},
|
| 1333 |
+
{
|
| 1334 |
+
"epoch": 0.75,
|
| 1335 |
+
"eval_loss": 0.9791378974914551,
|
| 1336 |
+
"eval_runtime": 11.2435,
|
| 1337 |
+
"eval_samples_per_second": 5.07,
|
| 1338 |
+
"eval_steps_per_second": 1.69,
|
| 1339 |
+
"step": 95
|
| 1340 |
+
},
|
| 1341 |
+
{
|
| 1342 |
+
"epoch": 0.76,
|
| 1343 |
+
"learning_rate": 7.460317460317461e-05,
|
| 1344 |
+
"loss": 0.9379,
|
| 1345 |
+
"step": 96
|
| 1346 |
+
},
|
| 1347 |
+
{
|
| 1348 |
+
"epoch": 0.76,
|
| 1349 |
+
"eval_loss": 0.9795575141906738,
|
| 1350 |
+
"eval_runtime": 11.3264,
|
| 1351 |
+
"eval_samples_per_second": 5.033,
|
| 1352 |
+
"eval_steps_per_second": 1.678,
|
| 1353 |
+
"step": 96
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"epoch": 0.77,
|
| 1357 |
+
"learning_rate": 7.433862433862434e-05,
|
| 1358 |
+
"loss": 0.8751,
|
| 1359 |
+
"step": 97
|
| 1360 |
+
},
|
| 1361 |
+
{
|
| 1362 |
+
"epoch": 0.77,
|
| 1363 |
+
"eval_loss": 0.9804602265357971,
|
| 1364 |
+
"eval_runtime": 11.4754,
|
| 1365 |
+
"eval_samples_per_second": 4.967,
|
| 1366 |
+
"eval_steps_per_second": 1.656,
|
| 1367 |
+
"step": 97
|
| 1368 |
+
},
|
| 1369 |
+
{
|
| 1370 |
+
"epoch": 0.78,
|
| 1371 |
+
"learning_rate": 7.407407407407407e-05,
|
| 1372 |
+
"loss": 0.9252,
|
| 1373 |
+
"step": 98
|
| 1374 |
+
},
|
| 1375 |
+
{
|
| 1376 |
+
"epoch": 0.78,
|
| 1377 |
+
"eval_loss": 0.9810712933540344,
|
| 1378 |
+
"eval_runtime": 11.2682,
|
| 1379 |
+
"eval_samples_per_second": 5.058,
|
| 1380 |
+
"eval_steps_per_second": 1.686,
|
| 1381 |
+
"step": 98
|
| 1382 |
+
},
|
| 1383 |
+
{
|
| 1384 |
+
"epoch": 0.79,
|
| 1385 |
+
"learning_rate": 7.380952380952382e-05,
|
| 1386 |
+
"loss": 0.9204,
|
| 1387 |
+
"step": 99
|
| 1388 |
+
},
|
| 1389 |
+
{
|
| 1390 |
+
"epoch": 0.79,
|
| 1391 |
+
"eval_loss": 0.9811252951622009,
|
| 1392 |
+
"eval_runtime": 11.2452,
|
| 1393 |
+
"eval_samples_per_second": 5.069,
|
| 1394 |
+
"eval_steps_per_second": 1.69,
|
| 1395 |
+
"step": 99
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"epoch": 0.79,
|
| 1399 |
+
"learning_rate": 7.354497354497355e-05,
|
| 1400 |
+
"loss": 1.0881,
|
| 1401 |
+
"step": 100
|
| 1402 |
+
},
|
| 1403 |
+
{
|
| 1404 |
+
"epoch": 0.79,
|
| 1405 |
+
"eval_loss": 0.9820334315299988,
|
| 1406 |
+
"eval_runtime": 11.2336,
|
| 1407 |
+
"eval_samples_per_second": 5.074,
|
| 1408 |
+
"eval_steps_per_second": 1.691,
|
| 1409 |
+
"step": 100
|
| 1410 |
+
},
|
| 1411 |
+
{
|
| 1412 |
+
"epoch": 0.8,
|
| 1413 |
+
"learning_rate": 7.328042328042329e-05,
|
| 1414 |
+
"loss": 1.0158,
|
| 1415 |
+
"step": 101
|
| 1416 |
+
},
|
| 1417 |
+
{
|
| 1418 |
+
"epoch": 0.8,
|
| 1419 |
+
"eval_loss": 0.9812192916870117,
|
| 1420 |
+
"eval_runtime": 11.3196,
|
| 1421 |
+
"eval_samples_per_second": 5.036,
|
| 1422 |
+
"eval_steps_per_second": 1.679,
|
| 1423 |
+
"step": 101
|
| 1424 |
+
},
|
| 1425 |
+
{
|
| 1426 |
+
"epoch": 0.81,
|
| 1427 |
+
"learning_rate": 7.301587301587302e-05,
|
| 1428 |
+
"loss": 0.9741,
|
| 1429 |
+
"step": 102
|
| 1430 |
+
},
|
| 1431 |
+
{
|
| 1432 |
+
"epoch": 0.81,
|
| 1433 |
+
"eval_loss": 0.9810476303100586,
|
| 1434 |
+
"eval_runtime": 11.3145,
|
| 1435 |
+
"eval_samples_per_second": 5.038,
|
| 1436 |
+
"eval_steps_per_second": 1.679,
|
| 1437 |
+
"step": 102
|
| 1438 |
+
},
|
| 1439 |
+
{
|
| 1440 |
+
"epoch": 0.82,
|
| 1441 |
+
"learning_rate": 7.275132275132276e-05,
|
| 1442 |
+
"loss": 0.7926,
|
| 1443 |
+
"step": 103
|
| 1444 |
+
},
|
| 1445 |
+
{
|
| 1446 |
+
"epoch": 0.82,
|
| 1447 |
+
"eval_loss": 0.9799998998641968,
|
| 1448 |
+
"eval_runtime": 11.312,
|
| 1449 |
+
"eval_samples_per_second": 5.039,
|
| 1450 |
+
"eval_steps_per_second": 1.68,
|
| 1451 |
+
"step": 103
|
| 1452 |
+
},
|
| 1453 |
+
{
|
| 1454 |
+
"epoch": 0.83,
|
| 1455 |
+
"learning_rate": 7.248677248677249e-05,
|
| 1456 |
+
"loss": 1.0417,
|
| 1457 |
+
"step": 104
|
| 1458 |
+
},
|
| 1459 |
+
{
|
| 1460 |
+
"epoch": 0.83,
|
| 1461 |
+
"eval_loss": 0.9790608882904053,
|
| 1462 |
+
"eval_runtime": 11.3684,
|
| 1463 |
+
"eval_samples_per_second": 5.014,
|
| 1464 |
+
"eval_steps_per_second": 1.671,
|
| 1465 |
+
"step": 104
|
| 1466 |
+
},
|
| 1467 |
+
{
|
| 1468 |
+
"epoch": 0.83,
|
| 1469 |
+
"learning_rate": 7.222222222222222e-05,
|
| 1470 |
+
"loss": 0.9738,
|
| 1471 |
+
"step": 105
|
| 1472 |
+
},
|
| 1473 |
+
{
|
| 1474 |
+
"epoch": 0.83,
|
| 1475 |
+
"eval_loss": 0.978194534778595,
|
| 1476 |
+
"eval_runtime": 11.2366,
|
| 1477 |
+
"eval_samples_per_second": 5.073,
|
| 1478 |
+
"eval_steps_per_second": 1.691,
|
| 1479 |
+
"step": 105
|
| 1480 |
+
},
|
| 1481 |
+
{
|
| 1482 |
+
"epoch": 0.84,
|
| 1483 |
+
"learning_rate": 7.195767195767196e-05,
|
| 1484 |
+
"loss": 0.8303,
|
| 1485 |
+
"step": 106
|
| 1486 |
+
},
|
| 1487 |
+
{
|
| 1488 |
+
"epoch": 0.84,
|
| 1489 |
+
"eval_loss": 0.9778124690055847,
|
| 1490 |
+
"eval_runtime": 11.4098,
|
| 1491 |
+
"eval_samples_per_second": 4.996,
|
| 1492 |
+
"eval_steps_per_second": 1.665,
|
| 1493 |
+
"step": 106
|
| 1494 |
+
},
|
| 1495 |
+
{
|
| 1496 |
+
"epoch": 0.85,
|
| 1497 |
+
"learning_rate": 7.16931216931217e-05,
|
| 1498 |
+
"loss": 0.9291,
|
| 1499 |
+
"step": 107
|
| 1500 |
+
},
|
| 1501 |
+
{
|
| 1502 |
+
"epoch": 0.85,
|
| 1503 |
+
"eval_loss": 0.9771907925605774,
|
| 1504 |
+
"eval_runtime": 11.2524,
|
| 1505 |
+
"eval_samples_per_second": 5.066,
|
| 1506 |
+
"eval_steps_per_second": 1.689,
|
| 1507 |
+
"step": 107
|
| 1508 |
+
},
|
| 1509 |
+
{
|
| 1510 |
+
"epoch": 0.86,
|
| 1511 |
+
"learning_rate": 7.142857142857143e-05,
|
| 1512 |
+
"loss": 0.9308,
|
| 1513 |
+
"step": 108
|
| 1514 |
+
},
|
| 1515 |
+
{
|
| 1516 |
+
"epoch": 0.86,
|
| 1517 |
+
"eval_loss": 0.9771039485931396,
|
| 1518 |
+
"eval_runtime": 11.2551,
|
| 1519 |
+
"eval_samples_per_second": 5.064,
|
| 1520 |
+
"eval_steps_per_second": 1.688,
|
| 1521 |
+
"step": 108
|
| 1522 |
+
},
|
| 1523 |
+
{
|
| 1524 |
+
"epoch": 0.87,
|
| 1525 |
+
"learning_rate": 7.116402116402116e-05,
|
| 1526 |
+
"loss": 1.1245,
|
| 1527 |
+
"step": 109
|
| 1528 |
+
},
|
| 1529 |
+
{
|
| 1530 |
+
"epoch": 0.87,
|
| 1531 |
+
"eval_loss": 0.9759649038314819,
|
| 1532 |
+
"eval_runtime": 11.2261,
|
| 1533 |
+
"eval_samples_per_second": 5.077,
|
| 1534 |
+
"eval_steps_per_second": 1.692,
|
| 1535 |
+
"step": 109
|
| 1536 |
+
},
|
| 1537 |
+
{
|
| 1538 |
+
"epoch": 0.87,
|
| 1539 |
+
"learning_rate": 7.089947089947089e-05,
|
| 1540 |
+
"loss": 0.8853,
|
| 1541 |
+
"step": 110
|
| 1542 |
+
},
|
| 1543 |
+
{
|
| 1544 |
+
"epoch": 0.87,
|
| 1545 |
+
"eval_loss": 0.9750571250915527,
|
| 1546 |
+
"eval_runtime": 11.2982,
|
| 1547 |
+
"eval_samples_per_second": 5.045,
|
| 1548 |
+
"eval_steps_per_second": 1.682,
|
| 1549 |
+
"step": 110
|
| 1550 |
+
},
|
| 1551 |
+
{
|
| 1552 |
+
"epoch": 0.88,
|
| 1553 |
+
"learning_rate": 7.063492063492065e-05,
|
| 1554 |
+
"loss": 0.9007,
|
| 1555 |
+
"step": 111
|
| 1556 |
+
},
|
| 1557 |
+
{
|
| 1558 |
+
"epoch": 0.88,
|
| 1559 |
+
"eval_loss": 0.9742787480354309,
|
| 1560 |
+
"eval_runtime": 11.564,
|
| 1561 |
+
"eval_samples_per_second": 4.929,
|
| 1562 |
+
"eval_steps_per_second": 1.643,
|
| 1563 |
+
"step": 111
|
| 1564 |
+
},
|
| 1565 |
+
{
|
| 1566 |
+
"epoch": 0.89,
|
| 1567 |
+
"learning_rate": 7.037037037037038e-05,
|
| 1568 |
+
"loss": 0.8941,
|
| 1569 |
+
"step": 112
|
| 1570 |
+
},
|
| 1571 |
+
{
|
| 1572 |
+
"epoch": 0.89,
|
| 1573 |
+
"eval_loss": 0.9725750684738159,
|
| 1574 |
+
"eval_runtime": 11.2109,
|
| 1575 |
+
"eval_samples_per_second": 5.084,
|
| 1576 |
+
"eval_steps_per_second": 1.695,
|
| 1577 |
+
"step": 112
|
| 1578 |
+
},
|
| 1579 |
+
{
|
| 1580 |
+
"epoch": 0.9,
|
| 1581 |
+
"learning_rate": 7.010582010582011e-05,
|
| 1582 |
+
"loss": 1.0456,
|
| 1583 |
+
"step": 113
|
| 1584 |
+
},
|
| 1585 |
+
{
|
| 1586 |
+
"epoch": 0.9,
|
| 1587 |
+
"eval_loss": 0.970888614654541,
|
| 1588 |
+
"eval_runtime": 11.2158,
|
| 1589 |
+
"eval_samples_per_second": 5.082,
|
| 1590 |
+
"eval_steps_per_second": 1.694,
|
| 1591 |
+
"step": 113
|
| 1592 |
+
},
|
| 1593 |
+
{
|
| 1594 |
+
"epoch": 0.9,
|
| 1595 |
+
"learning_rate": 6.984126984126984e-05,
|
| 1596 |
+
"loss": 1.0988,
|
| 1597 |
+
"step": 114
|
| 1598 |
+
},
|
| 1599 |
+
{
|
| 1600 |
+
"epoch": 0.9,
|
| 1601 |
+
"eval_loss": 0.9695295095443726,
|
| 1602 |
+
"eval_runtime": 11.1973,
|
| 1603 |
+
"eval_samples_per_second": 5.091,
|
| 1604 |
+
"eval_steps_per_second": 1.697,
|
| 1605 |
+
"step": 114
|
| 1606 |
+
},
|
| 1607 |
+
{
|
| 1608 |
+
"epoch": 0.91,
|
| 1609 |
+
"learning_rate": 6.957671957671958e-05,
|
| 1610 |
+
"loss": 0.9967,
|
| 1611 |
+
"step": 115
|
| 1612 |
+
},
|
| 1613 |
+
{
|
| 1614 |
+
"epoch": 0.91,
|
| 1615 |
+
"eval_loss": 0.9678014516830444,
|
| 1616 |
+
"eval_runtime": 11.1632,
|
| 1617 |
+
"eval_samples_per_second": 5.106,
|
| 1618 |
+
"eval_steps_per_second": 1.702,
|
| 1619 |
+
"step": 115
|
| 1620 |
+
},
|
| 1621 |
+
{
|
| 1622 |
+
"epoch": 0.92,
|
| 1623 |
+
"learning_rate": 6.931216931216932e-05,
|
| 1624 |
+
"loss": 0.9641,
|
| 1625 |
+
"step": 116
|
| 1626 |
+
},
|
| 1627 |
+
{
|
| 1628 |
+
"epoch": 0.92,
|
| 1629 |
+
"eval_loss": 0.9670316576957703,
|
| 1630 |
+
"eval_runtime": 11.1753,
|
| 1631 |
+
"eval_samples_per_second": 5.101,
|
| 1632 |
+
"eval_steps_per_second": 1.7,
|
| 1633 |
+
"step": 116
|
| 1634 |
+
},
|
| 1635 |
+
{
|
| 1636 |
+
"epoch": 0.93,
|
| 1637 |
+
"learning_rate": 6.904761904761905e-05,
|
| 1638 |
+
"loss": 0.8927,
|
| 1639 |
+
"step": 117
|
| 1640 |
+
},
|
| 1641 |
+
{
|
| 1642 |
+
"epoch": 0.93,
|
| 1643 |
+
"eval_loss": 0.965987503528595,
|
| 1644 |
+
"eval_runtime": 11.4765,
|
| 1645 |
+
"eval_samples_per_second": 4.967,
|
| 1646 |
+
"eval_steps_per_second": 1.656,
|
| 1647 |
+
"step": 117
|
| 1648 |
+
},
|
| 1649 |
+
{
|
| 1650 |
+
"epoch": 0.94,
|
| 1651 |
+
"learning_rate": 6.878306878306878e-05,
|
| 1652 |
+
"loss": 1.0487,
|
| 1653 |
+
"step": 118
|
| 1654 |
+
},
|
| 1655 |
+
{
|
| 1656 |
+
"epoch": 0.94,
|
| 1657 |
+
"eval_loss": 0.9654714465141296,
|
| 1658 |
+
"eval_runtime": 11.3628,
|
| 1659 |
+
"eval_samples_per_second": 5.016,
|
| 1660 |
+
"eval_steps_per_second": 1.672,
|
| 1661 |
+
"step": 118
|
| 1662 |
+
},
|
| 1663 |
+
{
|
| 1664 |
+
"epoch": 0.94,
|
| 1665 |
+
"learning_rate": 6.851851851851852e-05,
|
| 1666 |
+
"loss": 0.9565,
|
| 1667 |
+
"step": 119
|
| 1668 |
+
},
|
| 1669 |
+
{
|
| 1670 |
+
"epoch": 0.94,
|
| 1671 |
+
"eval_loss": 0.9648447036743164,
|
| 1672 |
+
"eval_runtime": 11.2817,
|
| 1673 |
+
"eval_samples_per_second": 5.052,
|
| 1674 |
+
"eval_steps_per_second": 1.684,
|
| 1675 |
+
"step": 119
|
| 1676 |
+
},
|
| 1677 |
+
{
|
| 1678 |
+
"epoch": 0.95,
|
| 1679 |
+
"learning_rate": 6.825396825396825e-05,
|
| 1680 |
+
"loss": 1.0075,
|
| 1681 |
+
"step": 120
|
| 1682 |
+
},
|
| 1683 |
+
{
|
| 1684 |
+
"epoch": 0.95,
|
| 1685 |
+
"eval_loss": 0.96305912733078,
|
| 1686 |
+
"eval_runtime": 11.1896,
|
| 1687 |
+
"eval_samples_per_second": 5.094,
|
| 1688 |
+
"eval_steps_per_second": 1.698,
|
| 1689 |
+
"step": 120
|
| 1690 |
+
},
|
| 1691 |
+
{
|
| 1692 |
+
"epoch": 0.96,
|
| 1693 |
+
"learning_rate": 6.7989417989418e-05,
|
| 1694 |
+
"loss": 0.8491,
|
| 1695 |
+
"step": 121
|
| 1696 |
+
},
|
| 1697 |
+
{
|
| 1698 |
+
"epoch": 0.96,
|
| 1699 |
+
"eval_loss": 0.9615995287895203,
|
| 1700 |
+
"eval_runtime": 11.2744,
|
| 1701 |
+
"eval_samples_per_second": 5.056,
|
| 1702 |
+
"eval_steps_per_second": 1.685,
|
| 1703 |
+
"step": 121
|
| 1704 |
+
},
|
| 1705 |
+
{
|
| 1706 |
+
"epoch": 0.97,
|
| 1707 |
+
"learning_rate": 6.772486772486773e-05,
|
| 1708 |
+
"loss": 0.9697,
|
| 1709 |
+
"step": 122
|
| 1710 |
+
},
|
| 1711 |
+
{
|
| 1712 |
+
"epoch": 0.97,
|
| 1713 |
+
"eval_loss": 0.9624088406562805,
|
| 1714 |
+
"eval_runtime": 11.2628,
|
| 1715 |
+
"eval_samples_per_second": 5.061,
|
| 1716 |
+
"eval_steps_per_second": 1.687,
|
| 1717 |
+
"step": 122
|
| 1718 |
+
},
|
| 1719 |
+
{
|
| 1720 |
+
"epoch": 0.98,
|
| 1721 |
+
"learning_rate": 6.746031746031747e-05,
|
| 1722 |
+
"loss": 0.9846,
|
| 1723 |
+
"step": 123
|
| 1724 |
+
},
|
| 1725 |
+
{
|
| 1726 |
+
"epoch": 0.98,
|
| 1727 |
+
"eval_loss": 0.9619339108467102,
|
| 1728 |
+
"eval_runtime": 11.1615,
|
| 1729 |
+
"eval_samples_per_second": 5.107,
|
| 1730 |
+
"eval_steps_per_second": 1.702,
|
| 1731 |
+
"step": 123
|
| 1732 |
+
},
|
| 1733 |
+
{
|
| 1734 |
+
"epoch": 0.98,
|
| 1735 |
+
"learning_rate": 6.71957671957672e-05,
|
| 1736 |
+
"loss": 0.9166,
|
| 1737 |
+
"step": 124
|
| 1738 |
+
},
|
| 1739 |
+
{
|
| 1740 |
+
"epoch": 0.98,
|
| 1741 |
+
"eval_loss": 0.9619455933570862,
|
| 1742 |
+
"eval_runtime": 11.1285,
|
| 1743 |
+
"eval_samples_per_second": 5.122,
|
| 1744 |
+
"eval_steps_per_second": 1.707,
|
| 1745 |
+
"step": 124
|
| 1746 |
+
},
|
| 1747 |
+
{
|
| 1748 |
+
"epoch": 0.99,
|
| 1749 |
+
"learning_rate": 6.693121693121693e-05,
|
| 1750 |
+
"loss": 0.8547,
|
| 1751 |
+
"step": 125
|
| 1752 |
+
},
|
| 1753 |
+
{
|
| 1754 |
+
"epoch": 0.99,
|
| 1755 |
+
"eval_loss": 0.9620954990386963,
|
| 1756 |
+
"eval_runtime": 11.2673,
|
| 1757 |
+
"eval_samples_per_second": 5.059,
|
| 1758 |
+
"eval_steps_per_second": 1.686,
|
| 1759 |
+
"step": 125
|
| 1760 |
+
},
|
| 1761 |
+
{
|
| 1762 |
+
"epoch": 1.0,
|
| 1763 |
+
"learning_rate": 6.666666666666667e-05,
|
| 1764 |
+
"loss": 0.9433,
|
| 1765 |
+
"step": 126
|
| 1766 |
+
},
|
| 1767 |
+
{
|
| 1768 |
+
"epoch": 1.0,
|
| 1769 |
+
"eval_loss": 0.9631038308143616,
|
| 1770 |
+
"eval_runtime": 11.2502,
|
| 1771 |
+
"eval_samples_per_second": 5.067,
|
| 1772 |
+
"eval_steps_per_second": 1.689,
|
| 1773 |
+
"step": 126
|
| 1774 |
+
},
|
| 1775 |
+
{
|
| 1776 |
+
"epoch": 1.01,
|
| 1777 |
+
"learning_rate": 6.640211640211641e-05,
|
| 1778 |
+
"loss": 0.7734,
|
| 1779 |
+
"step": 127
|
| 1780 |
+
},
|
| 1781 |
+
{
|
| 1782 |
+
"epoch": 1.01,
|
| 1783 |
+
"eval_loss": 0.9639068841934204,
|
| 1784 |
+
"eval_runtime": 11.3228,
|
| 1785 |
+
"eval_samples_per_second": 5.034,
|
| 1786 |
+
"eval_steps_per_second": 1.678,
|
| 1787 |
+
"step": 127
|
| 1788 |
+
},
|
| 1789 |
+
{
|
| 1790 |
+
"epoch": 1.02,
|
| 1791 |
+
"learning_rate": 6.613756613756614e-05,
|
| 1792 |
+
"loss": 0.8896,
|
| 1793 |
+
"step": 128
|
| 1794 |
+
},
|
| 1795 |
+
{
|
| 1796 |
+
"epoch": 1.02,
|
| 1797 |
+
"eval_loss": 0.9645029306411743,
|
| 1798 |
+
"eval_runtime": 11.5577,
|
| 1799 |
+
"eval_samples_per_second": 4.932,
|
| 1800 |
+
"eval_steps_per_second": 1.644,
|
| 1801 |
+
"step": 128
|
| 1802 |
+
},
|
| 1803 |
+
{
|
| 1804 |
+
"epoch": 1.02,
|
| 1805 |
+
"learning_rate": 6.587301587301587e-05,
|
| 1806 |
+
"loss": 0.8125,
|
| 1807 |
+
"step": 129
|
| 1808 |
+
},
|
| 1809 |
+
{
|
| 1810 |
+
"epoch": 1.02,
|
| 1811 |
+
"eval_loss": 0.9654971361160278,
|
| 1812 |
+
"eval_runtime": 11.3486,
|
| 1813 |
+
"eval_samples_per_second": 5.023,
|
| 1814 |
+
"eval_steps_per_second": 1.674,
|
| 1815 |
+
"step": 129
|
| 1816 |
+
},
|
| 1817 |
+
{
|
| 1818 |
+
"epoch": 1.03,
|
| 1819 |
+
"learning_rate": 6.560846560846561e-05,
|
| 1820 |
+
"loss": 0.9779,
|
| 1821 |
+
"step": 130
|
| 1822 |
+
},
|
| 1823 |
+
{
|
| 1824 |
+
"epoch": 1.03,
|
| 1825 |
+
"eval_loss": 0.9669473767280579,
|
| 1826 |
+
"eval_runtime": 11.2418,
|
| 1827 |
+
"eval_samples_per_second": 5.07,
|
| 1828 |
+
"eval_steps_per_second": 1.69,
|
| 1829 |
+
"step": 130
|
| 1830 |
+
},
|
| 1831 |
+
{
|
| 1832 |
+
"epoch": 1.04,
|
| 1833 |
+
"learning_rate": 6.534391534391536e-05,
|
| 1834 |
+
"loss": 0.8023,
|
| 1835 |
+
"step": 131
|
| 1836 |
+
},
|
| 1837 |
+
{
|
| 1838 |
+
"epoch": 1.04,
|
| 1839 |
+
"eval_loss": 0.9675314426422119,
|
| 1840 |
+
"eval_runtime": 11.3422,
|
| 1841 |
+
"eval_samples_per_second": 5.025,
|
| 1842 |
+
"eval_steps_per_second": 1.675,
|
| 1843 |
+
"step": 131
|
| 1844 |
+
},
|
| 1845 |
+
{
|
| 1846 |
+
"epoch": 1.05,
|
| 1847 |
+
"learning_rate": 6.507936507936509e-05,
|
| 1848 |
+
"loss": 0.9203,
|
| 1849 |
+
"step": 132
|
| 1850 |
+
},
|
| 1851 |
+
{
|
| 1852 |
+
"epoch": 1.05,
|
| 1853 |
+
"eval_loss": 0.9673454165458679,
|
| 1854 |
+
"eval_runtime": 11.2406,
|
| 1855 |
+
"eval_samples_per_second": 5.071,
|
| 1856 |
+
"eval_steps_per_second": 1.69,
|
| 1857 |
+
"step": 132
|
| 1858 |
+
},
|
| 1859 |
+
{
|
| 1860 |
+
"epoch": 1.06,
|
| 1861 |
+
"learning_rate": 6.481481481481482e-05,
|
| 1862 |
+
"loss": 0.9531,
|
| 1863 |
+
"step": 133
|
| 1864 |
+
},
|
| 1865 |
+
{
|
| 1866 |
+
"epoch": 1.06,
|
| 1867 |
+
"eval_loss": 0.9672001004219055,
|
| 1868 |
+
"eval_runtime": 11.38,
|
| 1869 |
+
"eval_samples_per_second": 5.009,
|
| 1870 |
+
"eval_steps_per_second": 1.67,
|
| 1871 |
+
"step": 133
|
| 1872 |
+
},
|
| 1873 |
+
{
|
| 1874 |
+
"epoch": 1.06,
|
| 1875 |
+
"learning_rate": 6.455026455026454e-05,
|
| 1876 |
+
"loss": 0.7756,
|
| 1877 |
+
"step": 134
|
| 1878 |
+
},
|
| 1879 |
+
{
|
| 1880 |
+
"epoch": 1.06,
|
| 1881 |
+
"eval_loss": 0.9666074514389038,
|
| 1882 |
+
"eval_runtime": 11.1727,
|
| 1883 |
+
"eval_samples_per_second": 5.102,
|
| 1884 |
+
"eval_steps_per_second": 1.701,
|
| 1885 |
+
"step": 134
|
| 1886 |
+
},
|
| 1887 |
+
{
|
| 1888 |
+
"epoch": 1.07,
|
| 1889 |
+
"learning_rate": 6.428571428571429e-05,
|
| 1890 |
+
"loss": 0.7395,
|
| 1891 |
+
"step": 135
|
| 1892 |
+
},
|
| 1893 |
+
{
|
| 1894 |
+
"epoch": 1.07,
|
| 1895 |
+
"eval_loss": 0.9651405215263367,
|
| 1896 |
+
"eval_runtime": 11.3323,
|
| 1897 |
+
"eval_samples_per_second": 5.03,
|
| 1898 |
+
"eval_steps_per_second": 1.677,
|
| 1899 |
+
"step": 135
|
| 1900 |
+
},
|
| 1901 |
+
{
|
| 1902 |
+
"epoch": 1.08,
|
| 1903 |
+
"learning_rate": 6.402116402116403e-05,
|
| 1904 |
+
"loss": 0.8366,
|
| 1905 |
+
"step": 136
|
| 1906 |
+
},
|
| 1907 |
+
{
|
| 1908 |
+
"epoch": 1.08,
|
| 1909 |
+
"eval_loss": 0.965033769607544,
|
| 1910 |
+
"eval_runtime": 11.2585,
|
| 1911 |
+
"eval_samples_per_second": 5.063,
|
| 1912 |
+
"eval_steps_per_second": 1.688,
|
| 1913 |
+
"step": 136
|
| 1914 |
+
},
|
| 1915 |
+
{
|
| 1916 |
+
"epoch": 1.09,
|
| 1917 |
+
"learning_rate": 6.375661375661376e-05,
|
| 1918 |
+
"loss": 0.9231,
|
| 1919 |
+
"step": 137
|
| 1920 |
+
},
|
| 1921 |
+
{
|
| 1922 |
+
"epoch": 1.09,
|
| 1923 |
+
"eval_loss": 0.9626837372779846,
|
| 1924 |
+
"eval_runtime": 11.1354,
|
| 1925 |
+
"eval_samples_per_second": 5.119,
|
| 1926 |
+
"eval_steps_per_second": 1.706,
|
| 1927 |
+
"step": 137
|
| 1928 |
+
},
|
| 1929 |
+
{
|
| 1930 |
+
"epoch": 1.1,
|
| 1931 |
+
"learning_rate": 6.349206349206349e-05,
|
| 1932 |
+
"loss": 0.8717,
|
| 1933 |
+
"step": 138
|
| 1934 |
+
},
|
| 1935 |
+
{
|
| 1936 |
+
"epoch": 1.1,
|
| 1937 |
+
"eval_loss": 0.9614263772964478,
|
| 1938 |
+
"eval_runtime": 11.2272,
|
| 1939 |
+
"eval_samples_per_second": 5.077,
|
| 1940 |
+
"eval_steps_per_second": 1.692,
|
| 1941 |
+
"step": 138
|
| 1942 |
+
},
|
| 1943 |
+
{
|
| 1944 |
+
"epoch": 1.1,
|
| 1945 |
+
"learning_rate": 6.322751322751323e-05,
|
| 1946 |
+
"loss": 0.8157,
|
| 1947 |
+
"step": 139
|
| 1948 |
+
},
|
| 1949 |
+
{
|
| 1950 |
+
"epoch": 1.1,
|
| 1951 |
+
"eval_loss": 0.9611877202987671,
|
| 1952 |
+
"eval_runtime": 11.3481,
|
| 1953 |
+
"eval_samples_per_second": 5.023,
|
| 1954 |
+
"eval_steps_per_second": 1.674,
|
| 1955 |
+
"step": 139
|
| 1956 |
+
},
|
| 1957 |
+
{
|
| 1958 |
+
"epoch": 1.11,
|
| 1959 |
+
"learning_rate": 6.296296296296296e-05,
|
| 1960 |
+
"loss": 0.8617,
|
| 1961 |
+
"step": 140
|
| 1962 |
+
},
|
| 1963 |
+
{
|
| 1964 |
+
"epoch": 1.11,
|
| 1965 |
+
"eval_loss": 0.9607529044151306,
|
| 1966 |
+
"eval_runtime": 11.2319,
|
| 1967 |
+
"eval_samples_per_second": 5.075,
|
| 1968 |
+
"eval_steps_per_second": 1.692,
|
| 1969 |
+
"step": 140
|
| 1970 |
+
},
|
| 1971 |
+
{
|
| 1972 |
+
"epoch": 1.12,
|
| 1973 |
+
"learning_rate": 6.26984126984127e-05,
|
| 1974 |
+
"loss": 0.7694,
|
| 1975 |
+
"step": 141
|
| 1976 |
+
},
|
| 1977 |
+
{
|
| 1978 |
+
"epoch": 1.12,
|
| 1979 |
+
"eval_loss": 0.961409866809845,
|
| 1980 |
+
"eval_runtime": 11.165,
|
| 1981 |
+
"eval_samples_per_second": 5.105,
|
| 1982 |
+
"eval_steps_per_second": 1.702,
|
| 1983 |
+
"step": 141
|
| 1984 |
+
},
|
| 1985 |
+
{
|
| 1986 |
+
"epoch": 1.13,
|
| 1987 |
+
"learning_rate": 6.243386243386243e-05,
|
| 1988 |
+
"loss": 0.8626,
|
| 1989 |
+
"step": 142
|
| 1990 |
+
},
|
| 1991 |
+
{
|
| 1992 |
+
"epoch": 1.13,
|
| 1993 |
+
"eval_loss": 0.9628212451934814,
|
| 1994 |
+
"eval_runtime": 11.2138,
|
| 1995 |
+
"eval_samples_per_second": 5.083,
|
| 1996 |
+
"eval_steps_per_second": 1.694,
|
| 1997 |
+
"step": 142
|
| 1998 |
+
},
|
| 1999 |
+
{
|
| 2000 |
+
"epoch": 1.13,
|
| 2001 |
+
"learning_rate": 6.216931216931218e-05,
|
| 2002 |
+
"loss": 0.909,
|
| 2003 |
+
"step": 143
|
| 2004 |
+
},
|
| 2005 |
+
{
|
| 2006 |
+
"epoch": 1.13,
|
| 2007 |
+
"eval_loss": 0.9622757434844971,
|
| 2008 |
+
"eval_runtime": 11.3331,
|
| 2009 |
+
"eval_samples_per_second": 5.03,
|
| 2010 |
+
"eval_steps_per_second": 1.677,
|
| 2011 |
+
"step": 143
|
| 2012 |
+
},
|
| 2013 |
+
{
|
| 2014 |
+
"epoch": 1.14,
|
| 2015 |
+
"learning_rate": 6.19047619047619e-05,
|
| 2016 |
+
"loss": 0.8004,
|
| 2017 |
+
"step": 144
|
| 2018 |
+
},
|
| 2019 |
+
{
|
| 2020 |
+
"epoch": 1.14,
|
| 2021 |
+
"eval_loss": 0.9607929587364197,
|
| 2022 |
+
"eval_runtime": 11.2614,
|
| 2023 |
+
"eval_samples_per_second": 5.062,
|
| 2024 |
+
"eval_steps_per_second": 1.687,
|
| 2025 |
+
"step": 144
|
| 2026 |
+
},
|
| 2027 |
+
{
|
| 2028 |
+
"epoch": 1.15,
|
| 2029 |
+
"learning_rate": 6.164021164021165e-05,
|
| 2030 |
+
"loss": 0.8374,
|
| 2031 |
+
"step": 145
|
| 2032 |
+
},
|
| 2033 |
+
{
|
| 2034 |
+
"epoch": 1.15,
|
| 2035 |
+
"eval_loss": 0.9604395627975464,
|
| 2036 |
+
"eval_runtime": 11.2681,
|
| 2037 |
+
"eval_samples_per_second": 5.059,
|
| 2038 |
+
"eval_steps_per_second": 1.686,
|
| 2039 |
+
"step": 145
|
| 2040 |
+
},
|
| 2041 |
+
{
|
| 2042 |
+
"epoch": 1.16,
|
| 2043 |
+
"learning_rate": 6.137566137566138e-05,
|
| 2044 |
+
"loss": 0.7996,
|
| 2045 |
+
"step": 146
|
| 2046 |
+
},
|
| 2047 |
+
{
|
| 2048 |
+
"epoch": 1.16,
|
| 2049 |
+
"eval_loss": 0.9591620564460754,
|
| 2050 |
+
"eval_runtime": 11.2545,
|
| 2051 |
+
"eval_samples_per_second": 5.065,
|
| 2052 |
+
"eval_steps_per_second": 1.688,
|
| 2053 |
+
"step": 146
|
| 2054 |
+
},
|
| 2055 |
+
{
|
| 2056 |
+
"epoch": 1.17,
|
| 2057 |
+
"learning_rate": 6.111111111111112e-05,
|
| 2058 |
+
"loss": 0.8048,
|
| 2059 |
+
"step": 147
|
| 2060 |
+
},
|
| 2061 |
+
{
|
| 2062 |
+
"epoch": 1.17,
|
| 2063 |
+
"eval_loss": 0.9589068293571472,
|
| 2064 |
+
"eval_runtime": 11.3293,
|
| 2065 |
+
"eval_samples_per_second": 5.031,
|
| 2066 |
+
"eval_steps_per_second": 1.677,
|
| 2067 |
+
"step": 147
|
| 2068 |
+
},
|
| 2069 |
+
{
|
| 2070 |
+
"epoch": 1.17,
|
| 2071 |
+
"learning_rate": 6.084656084656085e-05,
|
| 2072 |
+
"loss": 0.8036,
|
| 2073 |
+
"step": 148
|
| 2074 |
+
},
|
| 2075 |
+
{
|
| 2076 |
+
"epoch": 1.17,
|
| 2077 |
+
"eval_loss": 0.9590967297554016,
|
| 2078 |
+
"eval_runtime": 11.2762,
|
| 2079 |
+
"eval_samples_per_second": 5.055,
|
| 2080 |
+
"eval_steps_per_second": 1.685,
|
| 2081 |
+
"step": 148
|
| 2082 |
+
},
|
| 2083 |
+
{
|
| 2084 |
+
"epoch": 1.18,
|
| 2085 |
+
"learning_rate": 6.0582010582010586e-05,
|
| 2086 |
+
"loss": 0.8703,
|
| 2087 |
+
"step": 149
|
| 2088 |
+
},
|
| 2089 |
+
{
|
| 2090 |
+
"epoch": 1.18,
|
| 2091 |
+
"eval_loss": 0.9593470096588135,
|
| 2092 |
+
"eval_runtime": 11.2342,
|
| 2093 |
+
"eval_samples_per_second": 5.074,
|
| 2094 |
+
"eval_steps_per_second": 1.691,
|
| 2095 |
+
"step": 149
|
| 2096 |
+
},
|
| 2097 |
+
{
|
| 2098 |
+
"epoch": 1.19,
|
| 2099 |
+
"learning_rate": 6.0317460317460316e-05,
|
| 2100 |
+
"loss": 0.7818,
|
| 2101 |
+
"step": 150
|
| 2102 |
+
},
|
| 2103 |
+
{
|
| 2104 |
+
"epoch": 1.19,
|
| 2105 |
+
"eval_loss": 0.9604654908180237,
|
| 2106 |
+
"eval_runtime": 11.2,
|
| 2107 |
+
"eval_samples_per_second": 5.089,
|
| 2108 |
+
"eval_steps_per_second": 1.696,
|
| 2109 |
+
"step": 150
|
| 2110 |
+
},
|
| 2111 |
+
{
|
| 2112 |
+
"epoch": 1.2,
|
| 2113 |
+
"learning_rate": 6.005291005291006e-05,
|
| 2114 |
+
"loss": 0.9607,
|
| 2115 |
+
"step": 151
|
| 2116 |
+
},
|
| 2117 |
+
{
|
| 2118 |
+
"epoch": 1.2,
|
| 2119 |
+
"eval_loss": 0.9621202349662781,
|
| 2120 |
+
"eval_runtime": 11.1607,
|
| 2121 |
+
"eval_samples_per_second": 5.107,
|
| 2122 |
+
"eval_steps_per_second": 1.702,
|
| 2123 |
+
"step": 151
|
| 2124 |
+
},
|
| 2125 |
+
{
|
| 2126 |
+
"epoch": 1.21,
|
| 2127 |
+
"learning_rate": 5.9788359788359794e-05,
|
| 2128 |
+
"loss": 0.7956,
|
| 2129 |
+
"step": 152
|
| 2130 |
+
},
|
| 2131 |
+
{
|
| 2132 |
+
"epoch": 1.21,
|
| 2133 |
+
"eval_loss": 0.9638999104499817,
|
| 2134 |
+
"eval_runtime": 11.25,
|
| 2135 |
+
"eval_samples_per_second": 5.067,
|
| 2136 |
+
"eval_steps_per_second": 1.689,
|
| 2137 |
+
"step": 152
|
| 2138 |
+
},
|
| 2139 |
+
{
|
| 2140 |
+
"epoch": 1.21,
|
| 2141 |
+
"learning_rate": 5.9523809523809524e-05,
|
| 2142 |
+
"loss": 0.7905,
|
| 2143 |
+
"step": 153
|
| 2144 |
+
},
|
| 2145 |
+
{
|
| 2146 |
+
"epoch": 1.21,
|
| 2147 |
+
"eval_loss": 0.9654872417449951,
|
| 2148 |
+
"eval_runtime": 11.2628,
|
| 2149 |
+
"eval_samples_per_second": 5.061,
|
| 2150 |
+
"eval_steps_per_second": 1.687,
|
| 2151 |
+
"step": 153
|
| 2152 |
+
},
|
| 2153 |
+
{
|
| 2154 |
+
"epoch": 1.22,
|
| 2155 |
+
"learning_rate": 5.925925925925926e-05,
|
| 2156 |
+
"loss": 0.8222,
|
| 2157 |
+
"step": 154
|
| 2158 |
+
},
|
| 2159 |
+
{
|
| 2160 |
+
"epoch": 1.22,
|
| 2161 |
+
"eval_loss": 0.9671238660812378,
|
| 2162 |
+
"eval_runtime": 11.2352,
|
| 2163 |
+
"eval_samples_per_second": 5.073,
|
| 2164 |
+
"eval_steps_per_second": 1.691,
|
| 2165 |
+
"step": 154
|
| 2166 |
+
},
|
| 2167 |
+
{
|
| 2168 |
+
"epoch": 1.23,
|
| 2169 |
+
"learning_rate": 5.8994708994709e-05,
|
| 2170 |
+
"loss": 0.7141,
|
| 2171 |
+
"step": 155
|
| 2172 |
+
},
|
| 2173 |
+
{
|
| 2174 |
+
"epoch": 1.23,
|
| 2175 |
+
"eval_loss": 0.9681822657585144,
|
| 2176 |
+
"eval_runtime": 11.4061,
|
| 2177 |
+
"eval_samples_per_second": 4.997,
|
| 2178 |
+
"eval_steps_per_second": 1.666,
|
| 2179 |
+
"step": 155
|
| 2180 |
+
},
|
| 2181 |
+
{
|
| 2182 |
+
"epoch": 1.24,
|
| 2183 |
+
"learning_rate": 5.873015873015873e-05,
|
| 2184 |
+
"loss": 0.7559,
|
| 2185 |
+
"step": 156
|
| 2186 |
+
},
|
| 2187 |
+
{
|
| 2188 |
+
"epoch": 1.24,
|
| 2189 |
+
"eval_loss": 0.9698037505149841,
|
| 2190 |
+
"eval_runtime": 11.2595,
|
| 2191 |
+
"eval_samples_per_second": 5.062,
|
| 2192 |
+
"eval_steps_per_second": 1.687,
|
| 2193 |
+
"step": 156
|
| 2194 |
+
},
|
| 2195 |
+
{
|
| 2196 |
+
"epoch": 1.25,
|
| 2197 |
+
"learning_rate": 5.846560846560847e-05,
|
| 2198 |
+
"loss": 0.7906,
|
| 2199 |
+
"step": 157
|
| 2200 |
+
},
|
| 2201 |
+
{
|
| 2202 |
+
"epoch": 1.25,
|
| 2203 |
+
"eval_loss": 0.9727188348770142,
|
| 2204 |
+
"eval_runtime": 11.2154,
|
| 2205 |
+
"eval_samples_per_second": 5.082,
|
| 2206 |
+
"eval_steps_per_second": 1.694,
|
| 2207 |
+
"step": 157
|
| 2208 |
+
},
|
| 2209 |
+
{
|
| 2210 |
+
"epoch": 1.25,
|
| 2211 |
+
"learning_rate": 5.82010582010582e-05,
|
| 2212 |
+
"loss": 0.8808,
|
| 2213 |
+
"step": 158
|
| 2214 |
+
},
|
| 2215 |
+
{
|
| 2216 |
+
"epoch": 1.25,
|
| 2217 |
+
"eval_loss": 0.9737605452537537,
|
| 2218 |
+
"eval_runtime": 11.2619,
|
| 2219 |
+
"eval_samples_per_second": 5.061,
|
| 2220 |
+
"eval_steps_per_second": 1.687,
|
| 2221 |
+
"step": 158
|
| 2222 |
+
},
|
| 2223 |
+
{
|
| 2224 |
+
"epoch": 1.26,
|
| 2225 |
+
"learning_rate": 5.793650793650795e-05,
|
| 2226 |
+
"loss": 0.7659,
|
| 2227 |
+
"step": 159
|
| 2228 |
+
},
|
| 2229 |
+
{
|
| 2230 |
+
"epoch": 1.26,
|
| 2231 |
+
"eval_loss": 0.9749085307121277,
|
| 2232 |
+
"eval_runtime": 11.2907,
|
| 2233 |
+
"eval_samples_per_second": 5.048,
|
| 2234 |
+
"eval_steps_per_second": 1.683,
|
| 2235 |
+
"step": 159
|
| 2236 |
+
},
|
| 2237 |
+
{
|
| 2238 |
+
"epoch": 1.27,
|
| 2239 |
+
"learning_rate": 5.7671957671957676e-05,
|
| 2240 |
+
"loss": 0.746,
|
| 2241 |
+
"step": 160
|
| 2242 |
+
},
|
| 2243 |
+
{
|
| 2244 |
+
"epoch": 1.27,
|
| 2245 |
+
"eval_loss": 0.9759730100631714,
|
| 2246 |
+
"eval_runtime": 11.2853,
|
| 2247 |
+
"eval_samples_per_second": 5.051,
|
| 2248 |
+
"eval_steps_per_second": 1.684,
|
| 2249 |
+
"step": 160
|
| 2250 |
+
},
|
| 2251 |
+
{
|
| 2252 |
+
"epoch": 1.28,
|
| 2253 |
+
"learning_rate": 5.740740740740741e-05,
|
| 2254 |
+
"loss": 0.7761,
|
| 2255 |
+
"step": 161
|
| 2256 |
+
},
|
| 2257 |
+
{
|
| 2258 |
+
"epoch": 1.28,
|
| 2259 |
+
"eval_loss": 0.9752081632614136,
|
| 2260 |
+
"eval_runtime": 11.2755,
|
| 2261 |
+
"eval_samples_per_second": 5.055,
|
| 2262 |
+
"eval_steps_per_second": 1.685,
|
| 2263 |
+
"step": 161
|
| 2264 |
+
},
|
| 2265 |
+
{
|
| 2266 |
+
"epoch": 1.29,
|
| 2267 |
+
"learning_rate": 5.714285714285714e-05,
|
| 2268 |
+
"loss": 0.8106,
|
| 2269 |
+
"step": 162
|
| 2270 |
+
},
|
| 2271 |
+
{
|
| 2272 |
+
"epoch": 1.29,
|
| 2273 |
+
"eval_loss": 0.9742076396942139,
|
| 2274 |
+
"eval_runtime": 11.2173,
|
| 2275 |
+
"eval_samples_per_second": 5.081,
|
| 2276 |
+
"eval_steps_per_second": 1.694,
|
| 2277 |
+
"step": 162
|
| 2278 |
+
},
|
| 2279 |
+
{
|
| 2280 |
+
"epoch": 1.29,
|
| 2281 |
+
"learning_rate": 5.6878306878306885e-05,
|
| 2282 |
+
"loss": 1.0345,
|
| 2283 |
+
"step": 163
|
| 2284 |
+
},
|
| 2285 |
+
{
|
| 2286 |
+
"epoch": 1.29,
|
| 2287 |
+
"eval_loss": 0.971428632736206,
|
| 2288 |
+
"eval_runtime": 11.2646,
|
| 2289 |
+
"eval_samples_per_second": 5.06,
|
| 2290 |
+
"eval_steps_per_second": 1.687,
|
| 2291 |
+
"step": 163
|
| 2292 |
+
},
|
| 2293 |
+
{
|
| 2294 |
+
"epoch": 1.3,
|
| 2295 |
+
"learning_rate": 5.661375661375662e-05,
|
| 2296 |
+
"loss": 0.8811,
|
| 2297 |
+
"step": 164
|
| 2298 |
+
},
|
| 2299 |
+
{
|
| 2300 |
+
"epoch": 1.3,
|
| 2301 |
+
"eval_loss": 0.9710219502449036,
|
| 2302 |
+
"eval_runtime": 11.2704,
|
| 2303 |
+
"eval_samples_per_second": 5.057,
|
| 2304 |
+
"eval_steps_per_second": 1.686,
|
| 2305 |
+
"step": 164
|
| 2306 |
+
},
|
| 2307 |
+
{
|
| 2308 |
+
"epoch": 1.31,
|
| 2309 |
+
"learning_rate": 5.634920634920635e-05,
|
| 2310 |
+
"loss": 0.8288,
|
| 2311 |
+
"step": 165
|
| 2312 |
+
},
|
| 2313 |
+
{
|
| 2314 |
+
"epoch": 1.31,
|
| 2315 |
+
"eval_loss": 0.9695227742195129,
|
| 2316 |
+
"eval_runtime": 11.498,
|
| 2317 |
+
"eval_samples_per_second": 4.957,
|
| 2318 |
+
"eval_steps_per_second": 1.652,
|
| 2319 |
+
"step": 165
|
| 2320 |
+
},
|
| 2321 |
+
{
|
| 2322 |
+
"epoch": 1.32,
|
| 2323 |
+
"learning_rate": 5.6084656084656086e-05,
|
| 2324 |
+
"loss": 0.8506,
|
| 2325 |
+
"step": 166
|
| 2326 |
+
},
|
| 2327 |
+
{
|
| 2328 |
+
"epoch": 1.32,
|
| 2329 |
+
"eval_loss": 0.9673130512237549,
|
| 2330 |
+
"eval_runtime": 11.2551,
|
| 2331 |
+
"eval_samples_per_second": 5.064,
|
| 2332 |
+
"eval_steps_per_second": 1.688,
|
| 2333 |
+
"step": 166
|
| 2334 |
+
},
|
| 2335 |
+
{
|
| 2336 |
+
"epoch": 1.33,
|
| 2337 |
+
"learning_rate": 5.582010582010583e-05,
|
| 2338 |
+
"loss": 0.8069,
|
| 2339 |
+
"step": 167
|
| 2340 |
+
},
|
| 2341 |
+
{
|
| 2342 |
+
"epoch": 1.33,
|
| 2343 |
+
"eval_loss": 0.9665858745574951,
|
| 2344 |
+
"eval_runtime": 11.15,
|
| 2345 |
+
"eval_samples_per_second": 5.112,
|
| 2346 |
+
"eval_steps_per_second": 1.704,
|
| 2347 |
+
"step": 167
|
| 2348 |
+
},
|
| 2349 |
+
{
|
| 2350 |
+
"epoch": 1.33,
|
| 2351 |
+
"learning_rate": 5.555555555555556e-05,
|
| 2352 |
+
"loss": 0.9651,
|
| 2353 |
+
"step": 168
|
| 2354 |
+
},
|
| 2355 |
+
{
|
| 2356 |
+
"epoch": 1.33,
|
| 2357 |
+
"eval_loss": 0.96519535779953,
|
| 2358 |
+
"eval_runtime": 11.3608,
|
| 2359 |
+
"eval_samples_per_second": 5.017,
|
| 2360 |
+
"eval_steps_per_second": 1.672,
|
| 2361 |
+
"step": 168
|
| 2362 |
+
},
|
| 2363 |
+
{
|
| 2364 |
+
"epoch": 1.34,
|
| 2365 |
+
"learning_rate": 5.5291005291005294e-05,
|
| 2366 |
+
"loss": 0.9814,
|
| 2367 |
+
"step": 169
|
| 2368 |
+
},
|
| 2369 |
+
{
|
| 2370 |
+
"epoch": 1.34,
|
| 2371 |
+
"eval_loss": 0.9634275436401367,
|
| 2372 |
+
"eval_runtime": 11.1336,
|
| 2373 |
+
"eval_samples_per_second": 5.12,
|
| 2374 |
+
"eval_steps_per_second": 1.707,
|
| 2375 |
+
"step": 169
|
| 2376 |
+
},
|
| 2377 |
+
{
|
| 2378 |
+
"epoch": 1.35,
|
| 2379 |
+
"learning_rate": 5.5026455026455024e-05,
|
| 2380 |
+
"loss": 0.854,
|
| 2381 |
+
"step": 170
|
| 2382 |
+
},
|
| 2383 |
+
{
|
| 2384 |
+
"epoch": 1.35,
|
| 2385 |
+
"eval_loss": 0.9614959359169006,
|
| 2386 |
+
"eval_runtime": 11.3353,
|
| 2387 |
+
"eval_samples_per_second": 5.029,
|
| 2388 |
+
"eval_steps_per_second": 1.676,
|
| 2389 |
+
"step": 170
|
| 2390 |
+
},
|
| 2391 |
+
{
|
| 2392 |
+
"epoch": 1.36,
|
| 2393 |
+
"learning_rate": 5.4761904761904766e-05,
|
| 2394 |
+
"loss": 0.8542,
|
| 2395 |
+
"step": 171
|
| 2396 |
+
},
|
| 2397 |
+
{
|
| 2398 |
+
"epoch": 1.36,
|
| 2399 |
+
"eval_loss": 0.9592831134796143,
|
| 2400 |
+
"eval_runtime": 11.3728,
|
| 2401 |
+
"eval_samples_per_second": 5.012,
|
| 2402 |
+
"eval_steps_per_second": 1.671,
|
| 2403 |
+
"step": 171
|
| 2404 |
+
},
|
| 2405 |
+
{
|
| 2406 |
+
"epoch": 1.37,
|
| 2407 |
+
"learning_rate": 5.44973544973545e-05,
|
| 2408 |
+
"loss": 0.8012,
|
| 2409 |
+
"step": 172
|
| 2410 |
+
},
|
| 2411 |
+
{
|
| 2412 |
+
"epoch": 1.37,
|
| 2413 |
+
"eval_loss": 0.9572239518165588,
|
| 2414 |
+
"eval_runtime": 11.1863,
|
| 2415 |
+
"eval_samples_per_second": 5.096,
|
| 2416 |
+
"eval_steps_per_second": 1.699,
|
| 2417 |
+
"step": 172
|
| 2418 |
+
},
|
| 2419 |
+
{
|
| 2420 |
+
"epoch": 1.37,
|
| 2421 |
+
"learning_rate": 5.423280423280423e-05,
|
| 2422 |
+
"loss": 0.975,
|
| 2423 |
+
"step": 173
|
| 2424 |
+
},
|
| 2425 |
+
{
|
| 2426 |
+
"epoch": 1.37,
|
| 2427 |
+
"eval_loss": 0.9551581144332886,
|
| 2428 |
+
"eval_runtime": 11.2719,
|
| 2429 |
+
"eval_samples_per_second": 5.057,
|
| 2430 |
+
"eval_steps_per_second": 1.686,
|
| 2431 |
+
"step": 173
|
| 2432 |
+
},
|
| 2433 |
+
{
|
| 2434 |
+
"epoch": 1.38,
|
| 2435 |
+
"learning_rate": 5.396825396825397e-05,
|
| 2436 |
+
"loss": 0.7755,
|
| 2437 |
+
"step": 174
|
| 2438 |
+
},
|
| 2439 |
+
{
|
| 2440 |
+
"epoch": 1.38,
|
| 2441 |
+
"eval_loss": 0.9545064568519592,
|
| 2442 |
+
"eval_runtime": 11.5962,
|
| 2443 |
+
"eval_samples_per_second": 4.915,
|
| 2444 |
+
"eval_steps_per_second": 1.638,
|
| 2445 |
+
"step": 174
|
| 2446 |
+
},
|
| 2447 |
+
{
|
| 2448 |
+
"epoch": 1.39,
|
| 2449 |
+
"learning_rate": 5.370370370370371e-05,
|
| 2450 |
+
"loss": 0.8363,
|
| 2451 |
+
"step": 175
|
| 2452 |
+
},
|
| 2453 |
+
{
|
| 2454 |
+
"epoch": 1.39,
|
| 2455 |
+
"eval_loss": 0.9535031914710999,
|
| 2456 |
+
"eval_runtime": 11.4446,
|
| 2457 |
+
"eval_samples_per_second": 4.98,
|
| 2458 |
+
"eval_steps_per_second": 1.66,
|
| 2459 |
+
"step": 175
|
| 2460 |
+
},
|
| 2461 |
+
{
|
| 2462 |
+
"epoch": 1.4,
|
| 2463 |
+
"learning_rate": 5.343915343915345e-05,
|
| 2464 |
+
"loss": 0.8024,
|
| 2465 |
+
"step": 176
|
| 2466 |
+
},
|
| 2467 |
+
{
|
| 2468 |
+
"epoch": 1.4,
|
| 2469 |
+
"eval_loss": 0.9528553485870361,
|
| 2470 |
+
"eval_runtime": 11.1519,
|
| 2471 |
+
"eval_samples_per_second": 5.111,
|
| 2472 |
+
"eval_steps_per_second": 1.704,
|
| 2473 |
+
"step": 176
|
| 2474 |
+
},
|
| 2475 |
+
{
|
| 2476 |
+
"epoch": 1.4,
|
| 2477 |
+
"learning_rate": 5.3174603174603176e-05,
|
| 2478 |
+
"loss": 0.783,
|
| 2479 |
+
"step": 177
|
| 2480 |
+
},
|
| 2481 |
+
{
|
| 2482 |
+
"epoch": 1.4,
|
| 2483 |
+
"eval_loss": 0.9524054527282715,
|
| 2484 |
+
"eval_runtime": 11.2811,
|
| 2485 |
+
"eval_samples_per_second": 5.053,
|
| 2486 |
+
"eval_steps_per_second": 1.684,
|
| 2487 |
+
"step": 177
|
| 2488 |
+
},
|
| 2489 |
+
{
|
| 2490 |
+
"epoch": 1.41,
|
| 2491 |
+
"learning_rate": 5.291005291005291e-05,
|
| 2492 |
+
"loss": 0.9196,
|
| 2493 |
+
"step": 178
|
| 2494 |
+
},
|
| 2495 |
+
{
|
| 2496 |
+
"epoch": 1.41,
|
| 2497 |
+
"eval_loss": 0.9519273042678833,
|
| 2498 |
+
"eval_runtime": 11.2667,
|
| 2499 |
+
"eval_samples_per_second": 5.059,
|
| 2500 |
+
"eval_steps_per_second": 1.686,
|
| 2501 |
+
"step": 178
|
| 2502 |
+
},
|
| 2503 |
+
{
|
| 2504 |
+
"epoch": 1.42,
|
| 2505 |
+
"learning_rate": 5.2645502645502655e-05,
|
| 2506 |
+
"loss": 0.7972,
|
| 2507 |
+
"step": 179
|
| 2508 |
+
},
|
| 2509 |
+
{
|
| 2510 |
+
"epoch": 1.42,
|
| 2511 |
+
"eval_loss": 0.9521083235740662,
|
| 2512 |
+
"eval_runtime": 11.2333,
|
| 2513 |
+
"eval_samples_per_second": 5.074,
|
| 2514 |
+
"eval_steps_per_second": 1.691,
|
| 2515 |
+
"step": 179
|
| 2516 |
+
},
|
| 2517 |
+
{
|
| 2518 |
+
"epoch": 1.43,
|
| 2519 |
+
"learning_rate": 5.2380952380952384e-05,
|
| 2520 |
+
"loss": 0.713,
|
| 2521 |
+
"step": 180
|
| 2522 |
+
},
|
| 2523 |
+
{
|
| 2524 |
+
"epoch": 1.43,
|
| 2525 |
+
"eval_loss": 0.9525256752967834,
|
| 2526 |
+
"eval_runtime": 11.272,
|
| 2527 |
+
"eval_samples_per_second": 5.057,
|
| 2528 |
+
"eval_steps_per_second": 1.686,
|
| 2529 |
+
"step": 180
|
| 2530 |
+
},
|
| 2531 |
+
{
|
| 2532 |
+
"epoch": 1.44,
|
| 2533 |
+
"learning_rate": 5.211640211640212e-05,
|
| 2534 |
+
"loss": 0.8934,
|
| 2535 |
+
"step": 181
|
| 2536 |
+
},
|
| 2537 |
+
{
|
| 2538 |
+
"epoch": 1.44,
|
| 2539 |
+
"eval_loss": 0.9519696831703186,
|
| 2540 |
+
"eval_runtime": 11.2602,
|
| 2541 |
+
"eval_samples_per_second": 5.062,
|
| 2542 |
+
"eval_steps_per_second": 1.687,
|
| 2543 |
+
"step": 181
|
| 2544 |
+
},
|
| 2545 |
+
{
|
| 2546 |
+
"epoch": 1.44,
|
| 2547 |
+
"learning_rate": 5.185185185185185e-05,
|
| 2548 |
+
"loss": 0.8072,
|
| 2549 |
+
"step": 182
|
| 2550 |
+
},
|
| 2551 |
+
{
|
| 2552 |
+
"epoch": 1.44,
|
| 2553 |
+
"eval_loss": 0.9514541625976562,
|
| 2554 |
+
"eval_runtime": 11.3432,
|
| 2555 |
+
"eval_samples_per_second": 5.025,
|
| 2556 |
+
"eval_steps_per_second": 1.675,
|
| 2557 |
+
"step": 182
|
| 2558 |
+
},
|
| 2559 |
+
{
|
| 2560 |
+
"epoch": 1.45,
|
| 2561 |
+
"learning_rate": 5.158730158730159e-05,
|
| 2562 |
+
"loss": 0.8216,
|
| 2563 |
+
"step": 183
|
| 2564 |
+
},
|
| 2565 |
+
{
|
| 2566 |
+
"epoch": 1.45,
|
| 2567 |
+
"eval_loss": 0.9507673382759094,
|
| 2568 |
+
"eval_runtime": 11.1823,
|
| 2569 |
+
"eval_samples_per_second": 5.097,
|
| 2570 |
+
"eval_steps_per_second": 1.699,
|
| 2571 |
+
"step": 183
|
| 2572 |
+
},
|
| 2573 |
+
{
|
| 2574 |
+
"epoch": 1.46,
|
| 2575 |
+
"learning_rate": 5.132275132275133e-05,
|
| 2576 |
+
"loss": 0.7242,
|
| 2577 |
+
"step": 184
|
| 2578 |
+
},
|
| 2579 |
+
{
|
| 2580 |
+
"epoch": 1.46,
|
| 2581 |
+
"eval_loss": 0.950447142124176,
|
| 2582 |
+
"eval_runtime": 11.1002,
|
| 2583 |
+
"eval_samples_per_second": 5.135,
|
| 2584 |
+
"eval_steps_per_second": 1.712,
|
| 2585 |
+
"step": 184
|
| 2586 |
+
},
|
| 2587 |
+
{
|
| 2588 |
+
"epoch": 1.47,
|
| 2589 |
+
"learning_rate": 5.105820105820106e-05,
|
| 2590 |
+
"loss": 0.8381,
|
| 2591 |
+
"step": 185
|
| 2592 |
+
},
|
| 2593 |
+
{
|
| 2594 |
+
"epoch": 1.47,
|
| 2595 |
+
"eval_loss": 0.9501126408576965,
|
| 2596 |
+
"eval_runtime": 11.3125,
|
| 2597 |
+
"eval_samples_per_second": 5.039,
|
| 2598 |
+
"eval_steps_per_second": 1.68,
|
| 2599 |
+
"step": 185
|
| 2600 |
+
},
|
| 2601 |
+
{
|
| 2602 |
+
"epoch": 1.48,
|
| 2603 |
+
"learning_rate": 5.0793650793650794e-05,
|
| 2604 |
+
"loss": 0.9721,
|
| 2605 |
+
"step": 186
|
| 2606 |
+
},
|
| 2607 |
+
{
|
| 2608 |
+
"epoch": 1.48,
|
| 2609 |
+
"eval_loss": 0.9495165348052979,
|
| 2610 |
+
"eval_runtime": 11.2634,
|
| 2611 |
+
"eval_samples_per_second": 5.061,
|
| 2612 |
+
"eval_steps_per_second": 1.687,
|
| 2613 |
+
"step": 186
|
| 2614 |
+
},
|
| 2615 |
+
{
|
| 2616 |
+
"epoch": 1.48,
|
| 2617 |
+
"learning_rate": 5.052910052910054e-05,
|
| 2618 |
+
"loss": 0.9755,
|
| 2619 |
+
"step": 187
|
| 2620 |
+
},
|
| 2621 |
+
{
|
| 2622 |
+
"epoch": 1.48,
|
| 2623 |
+
"eval_loss": 0.9505437016487122,
|
| 2624 |
+
"eval_runtime": 11.1189,
|
| 2625 |
+
"eval_samples_per_second": 5.126,
|
| 2626 |
+
"eval_steps_per_second": 1.709,
|
| 2627 |
+
"step": 187
|
| 2628 |
+
},
|
| 2629 |
+
{
|
| 2630 |
+
"epoch": 1.49,
|
| 2631 |
+
"learning_rate": 5.026455026455027e-05,
|
| 2632 |
+
"loss": 0.7596,
|
| 2633 |
+
"step": 188
|
| 2634 |
+
},
|
| 2635 |
+
{
|
| 2636 |
+
"epoch": 1.49,
|
| 2637 |
+
"eval_loss": 0.9504641890525818,
|
| 2638 |
+
"eval_runtime": 11.2688,
|
| 2639 |
+
"eval_samples_per_second": 5.058,
|
| 2640 |
+
"eval_steps_per_second": 1.686,
|
| 2641 |
+
"step": 188
|
| 2642 |
+
},
|
| 2643 |
+
{
|
| 2644 |
+
"epoch": 1.5,
|
| 2645 |
+
"learning_rate": 5e-05,
|
| 2646 |
+
"loss": 0.8127,
|
| 2647 |
+
"step": 189
|
| 2648 |
+
},
|
| 2649 |
+
{
|
| 2650 |
+
"epoch": 1.5,
|
| 2651 |
+
"eval_loss": 0.9504896998405457,
|
| 2652 |
+
"eval_runtime": 11.3596,
|
| 2653 |
+
"eval_samples_per_second": 5.018,
|
| 2654 |
+
"eval_steps_per_second": 1.673,
|
| 2655 |
+
"step": 189
|
| 2656 |
+
},
|
| 2657 |
+
{
|
| 2658 |
+
"epoch": 1.51,
|
| 2659 |
+
"learning_rate": 4.973544973544973e-05,
|
| 2660 |
+
"loss": 0.7999,
|
| 2661 |
+
"step": 190
|
| 2662 |
+
},
|
| 2663 |
+
{
|
| 2664 |
+
"epoch": 1.51,
|
| 2665 |
+
"eval_loss": 0.9504294991493225,
|
| 2666 |
+
"eval_runtime": 11.6748,
|
| 2667 |
+
"eval_samples_per_second": 4.882,
|
| 2668 |
+
"eval_steps_per_second": 1.627,
|
| 2669 |
+
"step": 190
|
| 2670 |
+
},
|
| 2671 |
+
{
|
| 2672 |
+
"epoch": 1.52,
|
| 2673 |
+
"learning_rate": 4.9470899470899475e-05,
|
| 2674 |
+
"loss": 0.8556,
|
| 2675 |
+
"step": 191
|
| 2676 |
+
},
|
| 2677 |
+
{
|
| 2678 |
+
"epoch": 1.52,
|
| 2679 |
+
"eval_loss": 0.950935423374176,
|
| 2680 |
+
"eval_runtime": 11.4816,
|
| 2681 |
+
"eval_samples_per_second": 4.964,
|
| 2682 |
+
"eval_steps_per_second": 1.655,
|
| 2683 |
+
"step": 191
|
| 2684 |
+
},
|
| 2685 |
+
{
|
| 2686 |
+
"epoch": 1.52,
|
| 2687 |
+
"learning_rate": 4.9206349206349204e-05,
|
| 2688 |
+
"loss": 0.7262,
|
| 2689 |
+
"step": 192
|
| 2690 |
+
},
|
| 2691 |
+
{
|
| 2692 |
+
"epoch": 1.52,
|
| 2693 |
+
"eval_loss": 0.9509056210517883,
|
| 2694 |
+
"eval_runtime": 11.4591,
|
| 2695 |
+
"eval_samples_per_second": 4.974,
|
| 2696 |
+
"eval_steps_per_second": 1.658,
|
| 2697 |
+
"step": 192
|
| 2698 |
+
},
|
| 2699 |
+
{
|
| 2700 |
+
"epoch": 1.53,
|
| 2701 |
+
"learning_rate": 4.894179894179895e-05,
|
| 2702 |
+
"loss": 0.7748,
|
| 2703 |
+
"step": 193
|
| 2704 |
+
},
|
| 2705 |
+
{
|
| 2706 |
+
"epoch": 1.53,
|
| 2707 |
+
"eval_loss": 0.9506821632385254,
|
| 2708 |
+
"eval_runtime": 11.6655,
|
| 2709 |
+
"eval_samples_per_second": 4.886,
|
| 2710 |
+
"eval_steps_per_second": 1.629,
|
| 2711 |
+
"step": 193
|
| 2712 |
+
},
|
| 2713 |
+
{
|
| 2714 |
+
"epoch": 1.54,
|
| 2715 |
+
"learning_rate": 4.8677248677248676e-05,
|
| 2716 |
+
"loss": 0.7988,
|
| 2717 |
+
"step": 194
|
| 2718 |
+
},
|
| 2719 |
+
{
|
| 2720 |
+
"epoch": 1.54,
|
| 2721 |
+
"eval_loss": 0.9508106112480164,
|
| 2722 |
+
"eval_runtime": 11.2436,
|
| 2723 |
+
"eval_samples_per_second": 5.07,
|
| 2724 |
+
"eval_steps_per_second": 1.69,
|
| 2725 |
+
"step": 194
|
| 2726 |
+
},
|
| 2727 |
+
{
|
| 2728 |
+
"epoch": 1.55,
|
| 2729 |
+
"learning_rate": 4.841269841269841e-05,
|
| 2730 |
+
"loss": 0.9548,
|
| 2731 |
+
"step": 195
|
| 2732 |
+
},
|
| 2733 |
+
{
|
| 2734 |
+
"epoch": 1.55,
|
| 2735 |
+
"eval_loss": 0.9502134323120117,
|
| 2736 |
+
"eval_runtime": 11.2836,
|
| 2737 |
+
"eval_samples_per_second": 5.052,
|
| 2738 |
+
"eval_steps_per_second": 1.684,
|
| 2739 |
+
"step": 195
|
| 2740 |
+
},
|
| 2741 |
+
{
|
| 2742 |
+
"epoch": 1.56,
|
| 2743 |
+
"learning_rate": 4.814814814814815e-05,
|
| 2744 |
+
"loss": 0.8198,
|
| 2745 |
+
"step": 196
|
| 2746 |
+
},
|
| 2747 |
+
{
|
| 2748 |
+
"epoch": 1.56,
|
| 2749 |
+
"eval_loss": 0.9500845670700073,
|
| 2750 |
+
"eval_runtime": 11.2561,
|
| 2751 |
+
"eval_samples_per_second": 5.064,
|
| 2752 |
+
"eval_steps_per_second": 1.688,
|
| 2753 |
+
"step": 196
|
| 2754 |
+
},
|
| 2755 |
+
{
|
| 2756 |
+
"epoch": 1.56,
|
| 2757 |
+
"learning_rate": 4.7883597883597884e-05,
|
| 2758 |
+
"loss": 0.8214,
|
| 2759 |
+
"step": 197
|
| 2760 |
+
},
|
| 2761 |
+
{
|
| 2762 |
+
"epoch": 1.56,
|
| 2763 |
+
"eval_loss": 0.9501683712005615,
|
| 2764 |
+
"eval_runtime": 11.2431,
|
| 2765 |
+
"eval_samples_per_second": 5.07,
|
| 2766 |
+
"eval_steps_per_second": 1.69,
|
| 2767 |
+
"step": 197
|
| 2768 |
+
},
|
| 2769 |
+
{
|
| 2770 |
+
"epoch": 1.57,
|
| 2771 |
+
"learning_rate": 4.761904761904762e-05,
|
| 2772 |
+
"loss": 0.8485,
|
| 2773 |
+
"step": 198
|
| 2774 |
+
},
|
| 2775 |
+
{
|
| 2776 |
+
"epoch": 1.57,
|
| 2777 |
+
"eval_loss": 0.9491482973098755,
|
| 2778 |
+
"eval_runtime": 11.4349,
|
| 2779 |
+
"eval_samples_per_second": 4.985,
|
| 2780 |
+
"eval_steps_per_second": 1.662,
|
| 2781 |
+
"step": 198
|
| 2782 |
+
},
|
| 2783 |
+
{
|
| 2784 |
+
"epoch": 1.58,
|
| 2785 |
+
"learning_rate": 4.7354497354497356e-05,
|
| 2786 |
+
"loss": 0.8415,
|
| 2787 |
+
"step": 199
|
| 2788 |
+
},
|
| 2789 |
+
{
|
| 2790 |
+
"epoch": 1.58,
|
| 2791 |
+
"eval_loss": 0.9494752883911133,
|
| 2792 |
+
"eval_runtime": 11.45,
|
| 2793 |
+
"eval_samples_per_second": 4.978,
|
| 2794 |
+
"eval_steps_per_second": 1.659,
|
| 2795 |
+
"step": 199
|
| 2796 |
+
},
|
| 2797 |
+
{
|
| 2798 |
+
"epoch": 1.59,
|
| 2799 |
+
"learning_rate": 4.708994708994709e-05,
|
| 2800 |
+
"loss": 0.789,
|
| 2801 |
+
"step": 200
|
| 2802 |
+
},
|
| 2803 |
+
{
|
| 2804 |
+
"epoch": 1.59,
|
| 2805 |
+
"eval_loss": 0.9499990940093994,
|
| 2806 |
+
"eval_runtime": 11.1948,
|
| 2807 |
+
"eval_samples_per_second": 5.092,
|
| 2808 |
+
"eval_steps_per_second": 1.697,
|
| 2809 |
+
"step": 200
|
| 2810 |
+
},
|
| 2811 |
+
{
|
| 2812 |
+
"epoch": 1.6,
|
| 2813 |
+
"learning_rate": 4.682539682539683e-05,
|
| 2814 |
+
"loss": 0.7414,
|
| 2815 |
+
"step": 201
|
| 2816 |
+
},
|
| 2817 |
+
{
|
| 2818 |
+
"epoch": 1.6,
|
| 2819 |
+
"eval_loss": 0.950614869594574,
|
| 2820 |
+
"eval_runtime": 11.2016,
|
| 2821 |
+
"eval_samples_per_second": 5.089,
|
| 2822 |
+
"eval_steps_per_second": 1.696,
|
| 2823 |
+
"step": 201
|
| 2824 |
+
},
|
| 2825 |
+
{
|
| 2826 |
+
"epoch": 1.6,
|
| 2827 |
+
"learning_rate": 4.656084656084656e-05,
|
| 2828 |
+
"loss": 0.9238,
|
| 2829 |
+
"step": 202
|
| 2830 |
+
},
|
| 2831 |
+
{
|
| 2832 |
+
"epoch": 1.6,
|
| 2833 |
+
"eval_loss": 0.9510459303855896,
|
| 2834 |
+
"eval_runtime": 11.2692,
|
| 2835 |
+
"eval_samples_per_second": 5.058,
|
| 2836 |
+
"eval_steps_per_second": 1.686,
|
| 2837 |
+
"step": 202
|
| 2838 |
+
},
|
| 2839 |
+
{
|
| 2840 |
+
"epoch": 1.61,
|
| 2841 |
+
"learning_rate": 4.62962962962963e-05,
|
| 2842 |
+
"loss": 0.7716,
|
| 2843 |
+
"step": 203
|
| 2844 |
+
},
|
| 2845 |
+
{
|
| 2846 |
+
"epoch": 1.61,
|
| 2847 |
+
"eval_loss": 0.9512655138969421,
|
| 2848 |
+
"eval_runtime": 11.25,
|
| 2849 |
+
"eval_samples_per_second": 5.067,
|
| 2850 |
+
"eval_steps_per_second": 1.689,
|
| 2851 |
+
"step": 203
|
| 2852 |
+
},
|
| 2853 |
+
{
|
| 2854 |
+
"epoch": 1.62,
|
| 2855 |
+
"learning_rate": 4.603174603174603e-05,
|
| 2856 |
+
"loss": 0.78,
|
| 2857 |
+
"step": 204
|
| 2858 |
+
},
|
| 2859 |
+
{
|
| 2860 |
+
"epoch": 1.62,
|
| 2861 |
+
"eval_loss": 0.9526160955429077,
|
| 2862 |
+
"eval_runtime": 11.2309,
|
| 2863 |
+
"eval_samples_per_second": 5.075,
|
| 2864 |
+
"eval_steps_per_second": 1.692,
|
| 2865 |
+
"step": 204
|
| 2866 |
+
},
|
| 2867 |
+
{
|
| 2868 |
+
"epoch": 1.63,
|
| 2869 |
+
"learning_rate": 4.576719576719577e-05,
|
| 2870 |
+
"loss": 0.8149,
|
| 2871 |
+
"step": 205
|
| 2872 |
+
},
|
| 2873 |
+
{
|
| 2874 |
+
"epoch": 1.63,
|
| 2875 |
+
"eval_loss": 0.9529213309288025,
|
| 2876 |
+
"eval_runtime": 11.4627,
|
| 2877 |
+
"eval_samples_per_second": 4.973,
|
| 2878 |
+
"eval_steps_per_second": 1.658,
|
| 2879 |
+
"step": 205
|
| 2880 |
+
},
|
| 2881 |
+
{
|
| 2882 |
+
"epoch": 1.63,
|
| 2883 |
+
"learning_rate": 4.55026455026455e-05,
|
| 2884 |
+
"loss": 0.9315,
|
| 2885 |
+
"step": 206
|
| 2886 |
+
},
|
| 2887 |
+
{
|
| 2888 |
+
"epoch": 1.63,
|
| 2889 |
+
"eval_loss": 0.9526896476745605,
|
| 2890 |
+
"eval_runtime": 11.349,
|
| 2891 |
+
"eval_samples_per_second": 5.022,
|
| 2892 |
+
"eval_steps_per_second": 1.674,
|
| 2893 |
+
"step": 206
|
| 2894 |
+
},
|
| 2895 |
+
{
|
| 2896 |
+
"epoch": 1.64,
|
| 2897 |
+
"learning_rate": 4.523809523809524e-05,
|
| 2898 |
+
"loss": 0.8562,
|
| 2899 |
+
"step": 207
|
| 2900 |
+
},
|
| 2901 |
+
{
|
| 2902 |
+
"epoch": 1.64,
|
| 2903 |
+
"eval_loss": 0.9522102475166321,
|
| 2904 |
+
"eval_runtime": 11.2689,
|
| 2905 |
+
"eval_samples_per_second": 5.058,
|
| 2906 |
+
"eval_steps_per_second": 1.686,
|
| 2907 |
+
"step": 207
|
| 2908 |
+
},
|
| 2909 |
+
{
|
| 2910 |
+
"epoch": 1.65,
|
| 2911 |
+
"learning_rate": 4.4973544973544974e-05,
|
| 2912 |
+
"loss": 0.6728,
|
| 2913 |
+
"step": 208
|
| 2914 |
+
},
|
| 2915 |
+
{
|
| 2916 |
+
"epoch": 1.65,
|
| 2917 |
+
"eval_loss": 0.9524990320205688,
|
| 2918 |
+
"eval_runtime": 11.3464,
|
| 2919 |
+
"eval_samples_per_second": 5.024,
|
| 2920 |
+
"eval_steps_per_second": 1.675,
|
| 2921 |
+
"step": 208
|
| 2922 |
+
},
|
| 2923 |
+
{
|
| 2924 |
+
"epoch": 1.66,
|
| 2925 |
+
"learning_rate": 4.470899470899471e-05,
|
| 2926 |
+
"loss": 0.8107,
|
| 2927 |
+
"step": 209
|
| 2928 |
+
},
|
| 2929 |
+
{
|
| 2930 |
+
"epoch": 1.66,
|
| 2931 |
+
"eval_loss": 0.9504749178886414,
|
| 2932 |
+
"eval_runtime": 11.3852,
|
| 2933 |
+
"eval_samples_per_second": 5.006,
|
| 2934 |
+
"eval_steps_per_second": 1.669,
|
| 2935 |
+
"step": 209
|
| 2936 |
+
},
|
| 2937 |
+
{
|
| 2938 |
+
"epoch": 1.67,
|
| 2939 |
+
"learning_rate": 4.4444444444444447e-05,
|
| 2940 |
+
"loss": 0.7363,
|
| 2941 |
+
"step": 210
|
| 2942 |
+
},
|
| 2943 |
+
{
|
| 2944 |
+
"epoch": 1.67,
|
| 2945 |
+
"eval_loss": 0.9504967927932739,
|
| 2946 |
+
"eval_runtime": 11.2458,
|
| 2947 |
+
"eval_samples_per_second": 5.069,
|
| 2948 |
+
"eval_steps_per_second": 1.69,
|
| 2949 |
+
"step": 210
|
| 2950 |
+
},
|
| 2951 |
+
{
|
| 2952 |
+
"epoch": 1.67,
|
| 2953 |
+
"learning_rate": 4.417989417989418e-05,
|
| 2954 |
+
"loss": 0.8278,
|
| 2955 |
+
"step": 211
|
| 2956 |
+
},
|
| 2957 |
+
{
|
| 2958 |
+
"epoch": 1.67,
|
| 2959 |
+
"eval_loss": 0.9501346349716187,
|
| 2960 |
+
"eval_runtime": 11.3631,
|
| 2961 |
+
"eval_samples_per_second": 5.016,
|
| 2962 |
+
"eval_steps_per_second": 1.672,
|
| 2963 |
+
"step": 211
|
| 2964 |
+
},
|
| 2965 |
+
{
|
| 2966 |
+
"epoch": 1.68,
|
| 2967 |
+
"learning_rate": 4.391534391534391e-05,
|
| 2968 |
+
"loss": 0.7827,
|
| 2969 |
+
"step": 212
|
| 2970 |
+
},
|
| 2971 |
+
{
|
| 2972 |
+
"epoch": 1.68,
|
| 2973 |
+
"eval_loss": 0.9484946727752686,
|
| 2974 |
+
"eval_runtime": 11.3608,
|
| 2975 |
+
"eval_samples_per_second": 5.017,
|
| 2976 |
+
"eval_steps_per_second": 1.672,
|
| 2977 |
+
"step": 212
|
| 2978 |
+
},
|
| 2979 |
+
{
|
| 2980 |
+
"epoch": 1.69,
|
| 2981 |
+
"learning_rate": 4.3650793650793655e-05,
|
| 2982 |
+
"loss": 0.6884,
|
| 2983 |
+
"step": 213
|
| 2984 |
+
},
|
| 2985 |
+
{
|
| 2986 |
+
"epoch": 1.69,
|
| 2987 |
+
"eval_loss": 0.9481523633003235,
|
| 2988 |
+
"eval_runtime": 11.3269,
|
| 2989 |
+
"eval_samples_per_second": 5.032,
|
| 2990 |
+
"eval_steps_per_second": 1.677,
|
| 2991 |
+
"step": 213
|
| 2992 |
+
},
|
| 2993 |
+
{
|
| 2994 |
+
"epoch": 1.7,
|
| 2995 |
+
"learning_rate": 4.3386243386243384e-05,
|
| 2996 |
+
"loss": 0.7418,
|
| 2997 |
+
"step": 214
|
| 2998 |
+
},
|
| 2999 |
+
{
|
| 3000 |
+
"epoch": 1.7,
|
| 3001 |
+
"eval_loss": 0.9482589960098267,
|
| 3002 |
+
"eval_runtime": 11.3957,
|
| 3003 |
+
"eval_samples_per_second": 5.002,
|
| 3004 |
+
"eval_steps_per_second": 1.667,
|
| 3005 |
+
"step": 214
|
| 3006 |
+
},
|
| 3007 |
+
{
|
| 3008 |
+
"epoch": 1.71,
|
| 3009 |
+
"learning_rate": 4.312169312169313e-05,
|
| 3010 |
+
"loss": 0.8012,
|
| 3011 |
+
"step": 215
|
| 3012 |
+
},
|
| 3013 |
+
{
|
| 3014 |
+
"epoch": 1.71,
|
| 3015 |
+
"eval_loss": 0.9473200440406799,
|
| 3016 |
+
"eval_runtime": 11.4932,
|
| 3017 |
+
"eval_samples_per_second": 4.959,
|
| 3018 |
+
"eval_steps_per_second": 1.653,
|
| 3019 |
+
"step": 215
|
| 3020 |
+
},
|
| 3021 |
+
{
|
| 3022 |
+
"epoch": 1.71,
|
| 3023 |
+
"learning_rate": 4.2857142857142856e-05,
|
| 3024 |
+
"loss": 0.7137,
|
| 3025 |
+
"step": 216
|
| 3026 |
+
},
|
| 3027 |
+
{
|
| 3028 |
+
"epoch": 1.71,
|
| 3029 |
+
"eval_loss": 0.9463203549385071,
|
| 3030 |
+
"eval_runtime": 11.442,
|
| 3031 |
+
"eval_samples_per_second": 4.982,
|
| 3032 |
+
"eval_steps_per_second": 1.661,
|
| 3033 |
+
"step": 216
|
| 3034 |
+
},
|
| 3035 |
+
{
|
| 3036 |
+
"epoch": 1.72,
|
| 3037 |
+
"learning_rate": 4.259259259259259e-05,
|
| 3038 |
+
"loss": 0.8202,
|
| 3039 |
+
"step": 217
|
| 3040 |
+
},
|
| 3041 |
+
{
|
| 3042 |
+
"epoch": 1.72,
|
| 3043 |
+
"eval_loss": 0.9461511969566345,
|
| 3044 |
+
"eval_runtime": 11.4253,
|
| 3045 |
+
"eval_samples_per_second": 4.989,
|
| 3046 |
+
"eval_steps_per_second": 1.663,
|
| 3047 |
+
"step": 217
|
| 3048 |
+
},
|
| 3049 |
+
{
|
| 3050 |
+
"epoch": 1.73,
|
| 3051 |
+
"learning_rate": 4.232804232804233e-05,
|
| 3052 |
+
"loss": 0.7196,
|
| 3053 |
+
"step": 218
|
| 3054 |
+
},
|
| 3055 |
+
{
|
| 3056 |
+
"epoch": 1.73,
|
| 3057 |
+
"eval_loss": 0.9457988142967224,
|
| 3058 |
+
"eval_runtime": 11.4121,
|
| 3059 |
+
"eval_samples_per_second": 4.995,
|
| 3060 |
+
"eval_steps_per_second": 1.665,
|
| 3061 |
+
"step": 218
|
| 3062 |
+
},
|
| 3063 |
+
{
|
| 3064 |
+
"epoch": 1.74,
|
| 3065 |
+
"learning_rate": 4.2063492063492065e-05,
|
| 3066 |
+
"loss": 0.8195,
|
| 3067 |
+
"step": 219
|
| 3068 |
+
},
|
| 3069 |
+
{
|
| 3070 |
+
"epoch": 1.74,
|
| 3071 |
+
"eval_loss": 0.9461942911148071,
|
| 3072 |
+
"eval_runtime": 11.5171,
|
| 3073 |
+
"eval_samples_per_second": 4.949,
|
| 3074 |
+
"eval_steps_per_second": 1.65,
|
| 3075 |
+
"step": 219
|
| 3076 |
+
},
|
| 3077 |
+
{
|
| 3078 |
+
"epoch": 1.75,
|
| 3079 |
+
"learning_rate": 4.17989417989418e-05,
|
| 3080 |
+
"loss": 0.8813,
|
| 3081 |
+
"step": 220
|
| 3082 |
+
},
|
| 3083 |
+
{
|
| 3084 |
+
"epoch": 1.75,
|
| 3085 |
+
"eval_loss": 0.9455254673957825,
|
| 3086 |
+
"eval_runtime": 11.3423,
|
| 3087 |
+
"eval_samples_per_second": 5.025,
|
| 3088 |
+
"eval_steps_per_second": 1.675,
|
| 3089 |
+
"step": 220
|
| 3090 |
+
},
|
| 3091 |
+
{
|
| 3092 |
+
"epoch": 1.75,
|
| 3093 |
+
"learning_rate": 4.153439153439154e-05,
|
| 3094 |
+
"loss": 0.7291,
|
| 3095 |
+
"step": 221
|
| 3096 |
+
},
|
| 3097 |
+
{
|
| 3098 |
+
"epoch": 1.75,
|
| 3099 |
+
"eval_loss": 0.9450626969337463,
|
| 3100 |
+
"eval_runtime": 11.3241,
|
| 3101 |
+
"eval_samples_per_second": 5.034,
|
| 3102 |
+
"eval_steps_per_second": 1.678,
|
| 3103 |
+
"step": 221
|
| 3104 |
+
},
|
| 3105 |
+
{
|
| 3106 |
+
"epoch": 1.76,
|
| 3107 |
+
"learning_rate": 4.126984126984127e-05,
|
| 3108 |
+
"loss": 0.8033,
|
| 3109 |
+
"step": 222
|
| 3110 |
+
},
|
| 3111 |
+
{
|
| 3112 |
+
"epoch": 1.76,
|
| 3113 |
+
"eval_loss": 0.943817675113678,
|
| 3114 |
+
"eval_runtime": 11.236,
|
| 3115 |
+
"eval_samples_per_second": 5.073,
|
| 3116 |
+
"eval_steps_per_second": 1.691,
|
| 3117 |
+
"step": 222
|
| 3118 |
+
},
|
| 3119 |
+
{
|
| 3120 |
+
"epoch": 1.77,
|
| 3121 |
+
"learning_rate": 4.100529100529101e-05,
|
| 3122 |
+
"loss": 0.7453,
|
| 3123 |
+
"step": 223
|
| 3124 |
+
},
|
| 3125 |
+
{
|
| 3126 |
+
"epoch": 1.77,
|
| 3127 |
+
"eval_loss": 0.9435564279556274,
|
| 3128 |
+
"eval_runtime": 11.3459,
|
| 3129 |
+
"eval_samples_per_second": 5.024,
|
| 3130 |
+
"eval_steps_per_second": 1.675,
|
| 3131 |
+
"step": 223
|
| 3132 |
+
},
|
| 3133 |
+
{
|
| 3134 |
+
"epoch": 1.78,
|
| 3135 |
+
"learning_rate": 4.074074074074074e-05,
|
| 3136 |
+
"loss": 0.7112,
|
| 3137 |
+
"step": 224
|
| 3138 |
+
},
|
| 3139 |
+
{
|
| 3140 |
+
"epoch": 1.78,
|
| 3141 |
+
"eval_loss": 0.943976104259491,
|
| 3142 |
+
"eval_runtime": 11.3955,
|
| 3143 |
+
"eval_samples_per_second": 5.002,
|
| 3144 |
+
"eval_steps_per_second": 1.667,
|
| 3145 |
+
"step": 224
|
| 3146 |
+
},
|
| 3147 |
+
{
|
| 3148 |
+
"epoch": 1.79,
|
| 3149 |
+
"learning_rate": 4.047619047619048e-05,
|
| 3150 |
+
"loss": 0.817,
|
| 3151 |
+
"step": 225
|
| 3152 |
+
},
|
| 3153 |
+
{
|
| 3154 |
+
"epoch": 1.79,
|
| 3155 |
+
"eval_loss": 0.9434075355529785,
|
| 3156 |
+
"eval_runtime": 11.2349,
|
| 3157 |
+
"eval_samples_per_second": 5.073,
|
| 3158 |
+
"eval_steps_per_second": 1.691,
|
| 3159 |
+
"step": 225
|
| 3160 |
+
},
|
| 3161 |
+
{
|
| 3162 |
+
"epoch": 1.79,
|
| 3163 |
+
"learning_rate": 4.021164021164021e-05,
|
| 3164 |
+
"loss": 0.7895,
|
| 3165 |
+
"step": 226
|
| 3166 |
+
},
|
| 3167 |
+
{
|
| 3168 |
+
"epoch": 1.79,
|
| 3169 |
+
"eval_loss": 0.9428831338882446,
|
| 3170 |
+
"eval_runtime": 11.3622,
|
| 3171 |
+
"eval_samples_per_second": 5.017,
|
| 3172 |
+
"eval_steps_per_second": 1.672,
|
| 3173 |
+
"step": 226
|
| 3174 |
+
},
|
| 3175 |
+
{
|
| 3176 |
+
"epoch": 1.8,
|
| 3177 |
+
"learning_rate": 3.9947089947089946e-05,
|
| 3178 |
+
"loss": 0.7245,
|
| 3179 |
+
"step": 227
|
| 3180 |
+
},
|
| 3181 |
+
{
|
| 3182 |
+
"epoch": 1.8,
|
| 3183 |
+
"eval_loss": 0.9428912401199341,
|
| 3184 |
+
"eval_runtime": 11.2865,
|
| 3185 |
+
"eval_samples_per_second": 5.05,
|
| 3186 |
+
"eval_steps_per_second": 1.683,
|
| 3187 |
+
"step": 227
|
| 3188 |
+
},
|
| 3189 |
+
{
|
| 3190 |
+
"epoch": 1.81,
|
| 3191 |
+
"learning_rate": 3.968253968253968e-05,
|
| 3192 |
+
"loss": 0.7244,
|
| 3193 |
+
"step": 228
|
| 3194 |
+
},
|
| 3195 |
+
{
|
| 3196 |
+
"epoch": 1.81,
|
| 3197 |
+
"eval_loss": 0.9429775476455688,
|
| 3198 |
+
"eval_runtime": 11.2166,
|
| 3199 |
+
"eval_samples_per_second": 5.082,
|
| 3200 |
+
"eval_steps_per_second": 1.694,
|
| 3201 |
+
"step": 228
|
| 3202 |
+
},
|
| 3203 |
+
{
|
| 3204 |
+
"epoch": 1.82,
|
| 3205 |
+
"learning_rate": 3.941798941798942e-05,
|
| 3206 |
+
"loss": 0.7241,
|
| 3207 |
+
"step": 229
|
| 3208 |
+
},
|
| 3209 |
+
{
|
| 3210 |
+
"epoch": 1.82,
|
| 3211 |
+
"eval_loss": 0.943901002407074,
|
| 3212 |
+
"eval_runtime": 11.2593,
|
| 3213 |
+
"eval_samples_per_second": 5.062,
|
| 3214 |
+
"eval_steps_per_second": 1.687,
|
| 3215 |
+
"step": 229
|
| 3216 |
+
},
|
| 3217 |
+
{
|
| 3218 |
+
"epoch": 1.83,
|
| 3219 |
+
"learning_rate": 3.9153439153439155e-05,
|
| 3220 |
+
"loss": 0.7879,
|
| 3221 |
+
"step": 230
|
| 3222 |
+
},
|
| 3223 |
+
{
|
| 3224 |
+
"epoch": 1.83,
|
| 3225 |
+
"eval_loss": 0.9442031383514404,
|
| 3226 |
+
"eval_runtime": 11.3453,
|
| 3227 |
+
"eval_samples_per_second": 5.024,
|
| 3228 |
+
"eval_steps_per_second": 1.675,
|
| 3229 |
+
"step": 230
|
| 3230 |
+
},
|
| 3231 |
+
{
|
| 3232 |
+
"epoch": 1.83,
|
| 3233 |
+
"learning_rate": 3.888888888888889e-05,
|
| 3234 |
+
"loss": 1.0106,
|
| 3235 |
+
"step": 231
|
| 3236 |
+
},
|
| 3237 |
+
{
|
| 3238 |
+
"epoch": 1.83,
|
| 3239 |
+
"eval_loss": 0.944178581237793,
|
| 3240 |
+
"eval_runtime": 11.2853,
|
| 3241 |
+
"eval_samples_per_second": 5.051,
|
| 3242 |
+
"eval_steps_per_second": 1.684,
|
| 3243 |
+
"step": 231
|
| 3244 |
+
},
|
| 3245 |
+
{
|
| 3246 |
+
"epoch": 1.84,
|
| 3247 |
+
"learning_rate": 3.862433862433863e-05,
|
| 3248 |
+
"loss": 0.8942,
|
| 3249 |
+
"step": 232
|
| 3250 |
+
},
|
| 3251 |
+
{
|
| 3252 |
+
"epoch": 1.84,
|
| 3253 |
+
"eval_loss": 0.9436543583869934,
|
| 3254 |
+
"eval_runtime": 11.5347,
|
| 3255 |
+
"eval_samples_per_second": 4.942,
|
| 3256 |
+
"eval_steps_per_second": 1.647,
|
| 3257 |
+
"step": 232
|
| 3258 |
+
},
|
| 3259 |
+
{
|
| 3260 |
+
"epoch": 1.85,
|
| 3261 |
+
"learning_rate": 3.835978835978836e-05,
|
| 3262 |
+
"loss": 0.8406,
|
| 3263 |
+
"step": 233
|
| 3264 |
+
},
|
| 3265 |
+
{
|
| 3266 |
+
"epoch": 1.85,
|
| 3267 |
+
"eval_loss": 0.9440739154815674,
|
| 3268 |
+
"eval_runtime": 11.1759,
|
| 3269 |
+
"eval_samples_per_second": 5.1,
|
| 3270 |
+
"eval_steps_per_second": 1.7,
|
| 3271 |
+
"step": 233
|
| 3272 |
+
},
|
| 3273 |
+
{
|
| 3274 |
+
"epoch": 1.86,
|
| 3275 |
+
"learning_rate": 3.809523809523809e-05,
|
| 3276 |
+
"loss": 0.6819,
|
| 3277 |
+
"step": 234
|
| 3278 |
+
},
|
| 3279 |
+
{
|
| 3280 |
+
"epoch": 1.86,
|
| 3281 |
+
"eval_loss": 0.9439970254898071,
|
| 3282 |
+
"eval_runtime": 11.2746,
|
| 3283 |
+
"eval_samples_per_second": 5.056,
|
| 3284 |
+
"eval_steps_per_second": 1.685,
|
| 3285 |
+
"step": 234
|
| 3286 |
+
},
|
| 3287 |
+
{
|
| 3288 |
+
"epoch": 1.87,
|
| 3289 |
+
"learning_rate": 3.7830687830687835e-05,
|
| 3290 |
+
"loss": 0.7755,
|
| 3291 |
+
"step": 235
|
| 3292 |
+
},
|
| 3293 |
+
{
|
| 3294 |
+
"epoch": 1.87,
|
| 3295 |
+
"eval_loss": 0.9441021084785461,
|
| 3296 |
+
"eval_runtime": 11.2612,
|
| 3297 |
+
"eval_samples_per_second": 5.062,
|
| 3298 |
+
"eval_steps_per_second": 1.687,
|
| 3299 |
+
"step": 235
|
| 3300 |
+
},
|
| 3301 |
+
{
|
| 3302 |
+
"epoch": 1.87,
|
| 3303 |
+
"learning_rate": 3.7566137566137564e-05,
|
| 3304 |
+
"loss": 0.827,
|
| 3305 |
+
"step": 236
|
| 3306 |
+
},
|
| 3307 |
+
{
|
| 3308 |
+
"epoch": 1.87,
|
| 3309 |
+
"eval_loss": 0.9449384808540344,
|
| 3310 |
+
"eval_runtime": 11.2369,
|
| 3311 |
+
"eval_samples_per_second": 5.073,
|
| 3312 |
+
"eval_steps_per_second": 1.691,
|
| 3313 |
+
"step": 236
|
| 3314 |
+
},
|
| 3315 |
+
{
|
| 3316 |
+
"epoch": 1.88,
|
| 3317 |
+
"learning_rate": 3.730158730158731e-05,
|
| 3318 |
+
"loss": 0.8764,
|
| 3319 |
+
"step": 237
|
| 3320 |
+
},
|
| 3321 |
+
{
|
| 3322 |
+
"epoch": 1.88,
|
| 3323 |
+
"eval_loss": 0.9446438550949097,
|
| 3324 |
+
"eval_runtime": 11.27,
|
| 3325 |
+
"eval_samples_per_second": 5.058,
|
| 3326 |
+
"eval_steps_per_second": 1.686,
|
| 3327 |
+
"step": 237
|
| 3328 |
+
},
|
| 3329 |
+
{
|
| 3330 |
+
"epoch": 1.89,
|
| 3331 |
+
"learning_rate": 3.7037037037037037e-05,
|
| 3332 |
+
"loss": 0.7458,
|
| 3333 |
+
"step": 238
|
| 3334 |
+
},
|
| 3335 |
+
{
|
| 3336 |
+
"epoch": 1.89,
|
| 3337 |
+
"eval_loss": 0.9437587261199951,
|
| 3338 |
+
"eval_runtime": 11.3557,
|
| 3339 |
+
"eval_samples_per_second": 5.019,
|
| 3340 |
+
"eval_steps_per_second": 1.673,
|
| 3341 |
+
"step": 238
|
| 3342 |
+
},
|
| 3343 |
+
{
|
| 3344 |
+
"epoch": 1.9,
|
| 3345 |
+
"learning_rate": 3.677248677248677e-05,
|
| 3346 |
+
"loss": 0.9094,
|
| 3347 |
+
"step": 239
|
| 3348 |
+
},
|
| 3349 |
+
{
|
| 3350 |
+
"epoch": 1.9,
|
| 3351 |
+
"eval_loss": 0.9439199566841125,
|
| 3352 |
+
"eval_runtime": 11.2235,
|
| 3353 |
+
"eval_samples_per_second": 5.079,
|
| 3354 |
+
"eval_steps_per_second": 1.693,
|
| 3355 |
+
"step": 239
|
| 3356 |
+
},
|
| 3357 |
+
{
|
| 3358 |
+
"epoch": 1.9,
|
| 3359 |
+
"learning_rate": 3.650793650793651e-05,
|
| 3360 |
+
"loss": 0.9898,
|
| 3361 |
+
"step": 240
|
| 3362 |
+
},
|
| 3363 |
+
{
|
| 3364 |
+
"epoch": 1.9,
|
| 3365 |
+
"eval_loss": 0.942205548286438,
|
| 3366 |
+
"eval_runtime": 11.3626,
|
| 3367 |
+
"eval_samples_per_second": 5.016,
|
| 3368 |
+
"eval_steps_per_second": 1.672,
|
| 3369 |
+
"step": 240
|
| 3370 |
+
},
|
| 3371 |
+
{
|
| 3372 |
+
"epoch": 1.91,
|
| 3373 |
+
"learning_rate": 3.6243386243386245e-05,
|
| 3374 |
+
"loss": 0.7391,
|
| 3375 |
+
"step": 241
|
| 3376 |
+
},
|
| 3377 |
+
{
|
| 3378 |
+
"epoch": 1.91,
|
| 3379 |
+
"eval_loss": 0.9424855709075928,
|
| 3380 |
+
"eval_runtime": 11.4265,
|
| 3381 |
+
"eval_samples_per_second": 4.988,
|
| 3382 |
+
"eval_steps_per_second": 1.663,
|
| 3383 |
+
"step": 241
|
| 3384 |
+
},
|
| 3385 |
+
{
|
| 3386 |
+
"epoch": 1.92,
|
| 3387 |
+
"learning_rate": 3.597883597883598e-05,
|
| 3388 |
+
"loss": 0.9334,
|
| 3389 |
+
"step": 242
|
| 3390 |
+
},
|
| 3391 |
+
{
|
| 3392 |
+
"epoch": 1.92,
|
| 3393 |
+
"eval_loss": 0.9417003393173218,
|
| 3394 |
+
"eval_runtime": 11.2556,
|
| 3395 |
+
"eval_samples_per_second": 5.064,
|
| 3396 |
+
"eval_steps_per_second": 1.688,
|
| 3397 |
+
"step": 242
|
| 3398 |
+
},
|
| 3399 |
+
{
|
| 3400 |
+
"epoch": 1.93,
|
| 3401 |
+
"learning_rate": 3.571428571428572e-05,
|
| 3402 |
+
"loss": 1.0044,
|
| 3403 |
+
"step": 243
|
| 3404 |
+
},
|
| 3405 |
+
{
|
| 3406 |
+
"epoch": 1.93,
|
| 3407 |
+
"eval_loss": 0.9410524368286133,
|
| 3408 |
+
"eval_runtime": 11.3604,
|
| 3409 |
+
"eval_samples_per_second": 5.017,
|
| 3410 |
+
"eval_steps_per_second": 1.672,
|
| 3411 |
+
"step": 243
|
| 3412 |
+
},
|
| 3413 |
+
{
|
| 3414 |
+
"epoch": 1.94,
|
| 3415 |
+
"learning_rate": 3.5449735449735446e-05,
|
| 3416 |
+
"loss": 0.8364,
|
| 3417 |
+
"step": 244
|
| 3418 |
+
},
|
| 3419 |
+
{
|
| 3420 |
+
"epoch": 1.94,
|
| 3421 |
+
"eval_loss": 0.9403824806213379,
|
| 3422 |
+
"eval_runtime": 11.2473,
|
| 3423 |
+
"eval_samples_per_second": 5.068,
|
| 3424 |
+
"eval_steps_per_second": 1.689,
|
| 3425 |
+
"step": 244
|
| 3426 |
+
},
|
| 3427 |
+
{
|
| 3428 |
+
"epoch": 1.94,
|
| 3429 |
+
"learning_rate": 3.518518518518519e-05,
|
| 3430 |
+
"loss": 0.8561,
|
| 3431 |
+
"step": 245
|
| 3432 |
+
},
|
| 3433 |
+
{
|
| 3434 |
+
"epoch": 1.94,
|
| 3435 |
+
"eval_loss": 0.9392634630203247,
|
| 3436 |
+
"eval_runtime": 11.46,
|
| 3437 |
+
"eval_samples_per_second": 4.974,
|
| 3438 |
+
"eval_steps_per_second": 1.658,
|
| 3439 |
+
"step": 245
|
| 3440 |
+
},
|
| 3441 |
+
{
|
| 3442 |
+
"epoch": 1.95,
|
| 3443 |
+
"learning_rate": 3.492063492063492e-05,
|
| 3444 |
+
"loss": 0.7015,
|
| 3445 |
+
"step": 246
|
| 3446 |
+
},
|
| 3447 |
+
{
|
| 3448 |
+
"epoch": 1.95,
|
| 3449 |
+
"eval_loss": 0.9377325773239136,
|
| 3450 |
+
"eval_runtime": 11.6413,
|
| 3451 |
+
"eval_samples_per_second": 4.896,
|
| 3452 |
+
"eval_steps_per_second": 1.632,
|
| 3453 |
+
"step": 246
|
| 3454 |
+
},
|
| 3455 |
+
{
|
| 3456 |
+
"epoch": 1.96,
|
| 3457 |
+
"learning_rate": 3.465608465608466e-05,
|
| 3458 |
+
"loss": 0.7486,
|
| 3459 |
+
"step": 247
|
| 3460 |
+
},
|
| 3461 |
+
{
|
| 3462 |
+
"epoch": 1.96,
|
| 3463 |
+
"eval_loss": 0.9382759928703308,
|
| 3464 |
+
"eval_runtime": 11.5771,
|
| 3465 |
+
"eval_samples_per_second": 4.924,
|
| 3466 |
+
"eval_steps_per_second": 1.641,
|
| 3467 |
+
"step": 247
|
| 3468 |
+
},
|
| 3469 |
+
{
|
| 3470 |
+
"epoch": 1.97,
|
| 3471 |
+
"learning_rate": 3.439153439153439e-05,
|
| 3472 |
+
"loss": 0.8333,
|
| 3473 |
+
"step": 248
|
| 3474 |
+
},
|
| 3475 |
+
{
|
| 3476 |
+
"epoch": 1.97,
|
| 3477 |
+
"eval_loss": 0.9375688433647156,
|
| 3478 |
+
"eval_runtime": 11.2607,
|
| 3479 |
+
"eval_samples_per_second": 5.062,
|
| 3480 |
+
"eval_steps_per_second": 1.687,
|
| 3481 |
+
"step": 248
|
| 3482 |
+
},
|
| 3483 |
+
{
|
| 3484 |
+
"epoch": 1.98,
|
| 3485 |
+
"learning_rate": 3.412698412698413e-05,
|
| 3486 |
+
"loss": 0.8034,
|
| 3487 |
+
"step": 249
|
| 3488 |
+
},
|
| 3489 |
+
{
|
| 3490 |
+
"epoch": 1.98,
|
| 3491 |
+
"eval_loss": 0.9364966750144958,
|
| 3492 |
+
"eval_runtime": 11.227,
|
| 3493 |
+
"eval_samples_per_second": 5.077,
|
| 3494 |
+
"eval_steps_per_second": 1.692,
|
| 3495 |
+
"step": 249
|
| 3496 |
+
},
|
| 3497 |
+
{
|
| 3498 |
+
"epoch": 1.98,
|
| 3499 |
+
"learning_rate": 3.386243386243386e-05,
|
| 3500 |
+
"loss": 0.8792,
|
| 3501 |
+
"step": 250
|
| 3502 |
+
},
|
| 3503 |
+
{
|
| 3504 |
+
"epoch": 1.98,
|
| 3505 |
+
"eval_loss": 0.9363824129104614,
|
| 3506 |
+
"eval_runtime": 11.3231,
|
| 3507 |
+
"eval_samples_per_second": 5.034,
|
| 3508 |
+
"eval_steps_per_second": 1.678,
|
| 3509 |
+
"step": 250
|
| 3510 |
+
},
|
| 3511 |
+
{
|
| 3512 |
+
"epoch": 1.99,
|
| 3513 |
+
"learning_rate": 3.35978835978836e-05,
|
| 3514 |
+
"loss": 0.8516,
|
| 3515 |
+
"step": 251
|
| 3516 |
+
},
|
| 3517 |
+
{
|
| 3518 |
+
"epoch": 1.99,
|
| 3519 |
+
"eval_loss": 0.9360049962997437,
|
| 3520 |
+
"eval_runtime": 11.3097,
|
| 3521 |
+
"eval_samples_per_second": 5.04,
|
| 3522 |
+
"eval_steps_per_second": 1.68,
|
| 3523 |
+
"step": 251
|
| 3524 |
+
},
|
| 3525 |
+
{
|
| 3526 |
+
"epoch": 2.0,
|
| 3527 |
+
"learning_rate": 3.3333333333333335e-05,
|
| 3528 |
+
"loss": 0.8426,
|
| 3529 |
+
"step": 252
|
| 3530 |
+
},
|
| 3531 |
+
{
|
| 3532 |
+
"epoch": 2.0,
|
| 3533 |
+
"eval_loss": 0.9354138374328613,
|
| 3534 |
+
"eval_runtime": 11.3548,
|
| 3535 |
+
"eval_samples_per_second": 5.02,
|
| 3536 |
+
"eval_steps_per_second": 1.673,
|
| 3537 |
+
"step": 252
|
| 3538 |
+
},
|
| 3539 |
+
{
|
| 3540 |
+
"epoch": 2.01,
|
| 3541 |
+
"learning_rate": 3.306878306878307e-05,
|
| 3542 |
+
"loss": 0.7673,
|
| 3543 |
+
"step": 253
|
| 3544 |
+
},
|
| 3545 |
+
{
|
| 3546 |
+
"epoch": 2.01,
|
| 3547 |
+
"eval_loss": 0.935636043548584,
|
| 3548 |
+
"eval_runtime": 11.2919,
|
| 3549 |
+
"eval_samples_per_second": 5.048,
|
| 3550 |
+
"eval_steps_per_second": 1.683,
|
| 3551 |
+
"step": 253
|
| 3552 |
+
},
|
| 3553 |
+
{
|
| 3554 |
+
"epoch": 2.02,
|
| 3555 |
+
"learning_rate": 3.280423280423281e-05,
|
| 3556 |
+
"loss": 0.7638,
|
| 3557 |
+
"step": 254
|
| 3558 |
+
},
|
| 3559 |
+
{
|
| 3560 |
+
"epoch": 2.02,
|
| 3561 |
+
"eval_loss": 0.9350641369819641,
|
| 3562 |
+
"eval_runtime": 11.586,
|
| 3563 |
+
"eval_samples_per_second": 4.92,
|
| 3564 |
+
"eval_steps_per_second": 1.64,
|
| 3565 |
+
"step": 254
|
| 3566 |
+
}
|
| 3567 |
+
],
|
| 3568 |
+
"logging_steps": 1,
|
| 3569 |
+
"max_steps": 378,
|
| 3570 |
+
"num_input_tokens_seen": 0,
|
| 3571 |
+
"num_train_epochs": 3,
|
| 3572 |
+
"save_steps": 1,
|
| 3573 |
+
"total_flos": 6722291169718272.0,
|
| 3574 |
+
"train_batch_size": 4,
|
| 3575 |
+
"trial_name": null,
|
| 3576 |
+
"trial_params": null
|
| 3577 |
+
}
|
checkpoint-254/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:21ebce185f4cf8a72d849ddd59a0d404ad4285dbbb457099ca03460f0ebf9d53
|
| 3 |
+
size 4728
|
checkpoint-378/README.md
ADDED
|
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
base_model: liuhaotian/llava-v1.5-7b
|
| 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 0.11.1
|
checkpoint-378/adapter_config.json
ADDED
|
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": {
|
| 4 |
+
"base_model_class": "LlavaLlamaForCausalLM",
|
| 5 |
+
"parent_library": "llava.model.language_model.llava_llama"
|
| 6 |
+
},
|
| 7 |
+
"base_model_name_or_path": "liuhaotian/llava-v1.5-7b",
|
| 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 |
+
"out_projfc1",
|
| 27 |
+
"down_proj",
|
| 28 |
+
"gate_proj",
|
| 29 |
+
"o_proj",
|
| 30 |
+
"q_proj",
|
| 31 |
+
"fc2model.mm_projector.0",
|
| 32 |
+
"v_proj",
|
| 33 |
+
"up_proj",
|
| 34 |
+
"k_proj",
|
| 35 |
+
"model.mm_projector.2"
|
| 36 |
+
],
|
| 37 |
+
"task_type": null,
|
| 38 |
+
"use_dora": false,
|
| 39 |
+
"use_rslora": false
|
| 40 |
+
}
|
checkpoint-378/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a3dfcdc535390ba42c03db5c7d7bb0749bf151eb37f893c0b4c2b9d9304e590a
|
| 3 |
+
size 85021296
|
checkpoint-378/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d5f4890f3c0755e581fe93bf2bfbe2496976dcbfbc59e38de99d282ab1bc20da
|
| 3 |
+
size 160812632
|
checkpoint-378/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5bac4d8307755eb2ce164700667aa07768522aea0f67a4da4226ef937903ad84
|
| 3 |
+
size 14244
|
checkpoint-378/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9ec3657a353fdb756c65955d3c93beb7d6a30da959bfeaa033c089d99748130a
|
| 3 |
+
size 1064
|
checkpoint-378/trainer_state.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-378/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:21ebce185f4cf8a72d849ddd59a0d404ad4285dbbb457099ca03460f0ebf9d53
|
| 3 |
+
size 4728
|