Commit
•
c3e0053
1
Parent(s):
d6d2e80
After 5 stages / 150K steps
Browse files- README.md +202 -0
- adapter_config.json +34 -0
- adapter_model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +2361 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
base_model: deepseek-ai/deepseek-coder-1.3b-instruct
|
| 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 0.9.1.dev0
|
adapter_config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "deepseek-ai/deepseek-coder-1.3b-instruct",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": false,
|
| 7 |
+
"inference_mode": true,
|
| 8 |
+
"init_lora_weights": true,
|
| 9 |
+
"layer_replication": null,
|
| 10 |
+
"layers_pattern": null,
|
| 11 |
+
"layers_to_transform": null,
|
| 12 |
+
"loftq_config": {},
|
| 13 |
+
"lora_alpha": 64,
|
| 14 |
+
"lora_dropout": 0.05,
|
| 15 |
+
"megatron_config": null,
|
| 16 |
+
"megatron_core": "megatron.core",
|
| 17 |
+
"modules_to_save": null,
|
| 18 |
+
"peft_type": "LORA",
|
| 19 |
+
"r": 32,
|
| 20 |
+
"rank_pattern": {},
|
| 21 |
+
"revision": null,
|
| 22 |
+
"target_modules": [
|
| 23 |
+
"gate_proj",
|
| 24 |
+
"k_proj",
|
| 25 |
+
"down_proj",
|
| 26 |
+
"q_proj",
|
| 27 |
+
"v_proj",
|
| 28 |
+
"o_proj",
|
| 29 |
+
"up_proj"
|
| 30 |
+
],
|
| 31 |
+
"task_type": "CAUSAL_LM",
|
| 32 |
+
"use_dora": false,
|
| 33 |
+
"use_rslora": false
|
| 34 |
+
}
|
adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cf8d5799a19426dda0836405b58f22ac985f2cb9375ffe97e9e245a737a9b94b
|
| 3 |
+
size 119975656
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d125a26ddb220e10d32bdf14c9d0eaf1247560ab803358890c35a2d9edf9e0cd
|
| 3 |
+
size 240145026
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fbc9d904ed26e815db2d9a93ce55caf3f4748d632162cc71db4f38fe9ed69e5e
|
| 3 |
+
size 14244
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1d8902004d681d6ba488d5a81c9b9232056455215d2aeb00f396dec2c2744859
|
| 3 |
+
size 1064
|
trainer_state.json
ADDED
|
@@ -0,0 +1,2361 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.5,
|
| 5 |
+
"eval_steps": 1000,
|
| 6 |
+
"global_step": 30000,
|
| 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 |
+
"grad_norm": 6.840716361999512,
|
| 14 |
+
"learning_rate": 1.9600000000000002e-05,
|
| 15 |
+
"loss": 3.0263,
|
| 16 |
+
"step": 100
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.02,
|
| 20 |
+
"grad_norm": 3.3429949283599854,
|
| 21 |
+
"learning_rate": 3.960000000000001e-05,
|
| 22 |
+
"loss": 1.6744,
|
| 23 |
+
"step": 200
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.03,
|
| 27 |
+
"grad_norm": 5.441232681274414,
|
| 28 |
+
"learning_rate": 5.96e-05,
|
| 29 |
+
"loss": 1.5933,
|
| 30 |
+
"step": 300
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.03,
|
| 34 |
+
"grad_norm": 2.98654842376709,
|
| 35 |
+
"learning_rate": 7.960000000000001e-05,
|
| 36 |
+
"loss": 1.5397,
|
| 37 |
+
"step": 400
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.04,
|
| 41 |
+
"grad_norm": 1.9203338623046875,
|
| 42 |
+
"learning_rate": 9.960000000000001e-05,
|
| 43 |
+
"loss": 1.5443,
|
| 44 |
+
"step": 500
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.05,
|
| 48 |
+
"grad_norm": 2.706545352935791,
|
| 49 |
+
"learning_rate": 9.966779661016949e-05,
|
| 50 |
+
"loss": 1.5593,
|
| 51 |
+
"step": 600
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.06,
|
| 55 |
+
"grad_norm": 1.7645795345306396,
|
| 56 |
+
"learning_rate": 9.932881355932204e-05,
|
| 57 |
+
"loss": 1.569,
|
| 58 |
+
"step": 700
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.07,
|
| 62 |
+
"grad_norm": 1.51504647731781,
|
| 63 |
+
"learning_rate": 9.898983050847458e-05,
|
| 64 |
+
"loss": 1.5094,
|
| 65 |
+
"step": 800
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.07,
|
| 69 |
+
"grad_norm": 3.9701757431030273,
|
| 70 |
+
"learning_rate": 9.865084745762713e-05,
|
| 71 |
+
"loss": 1.5007,
|
| 72 |
+
"step": 900
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.08,
|
| 76 |
+
"grad_norm": 2.04455304145813,
|
| 77 |
+
"learning_rate": 9.831186440677966e-05,
|
| 78 |
+
"loss": 1.5154,
|
| 79 |
+
"step": 1000
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.08,
|
| 83 |
+
"eval_loss": 1.4852064847946167,
|
| 84 |
+
"eval_runtime": 93.0778,
|
| 85 |
+
"eval_samples_per_second": 10.744,
|
| 86 |
+
"eval_steps_per_second": 2.686,
|
| 87 |
+
"step": 1000
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.09,
|
| 91 |
+
"grad_norm": 1.8170721530914307,
|
| 92 |
+
"learning_rate": 9.797288135593221e-05,
|
| 93 |
+
"loss": 1.4842,
|
| 94 |
+
"step": 1100
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.1,
|
| 98 |
+
"grad_norm": 1.3413264751434326,
|
| 99 |
+
"learning_rate": 9.763389830508474e-05,
|
| 100 |
+
"loss": 1.4884,
|
| 101 |
+
"step": 1200
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.11,
|
| 105 |
+
"grad_norm": 1.753246784210205,
|
| 106 |
+
"learning_rate": 9.72949152542373e-05,
|
| 107 |
+
"loss": 1.464,
|
| 108 |
+
"step": 1300
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.12,
|
| 112 |
+
"grad_norm": 3.4083104133605957,
|
| 113 |
+
"learning_rate": 9.695593220338983e-05,
|
| 114 |
+
"loss": 1.4739,
|
| 115 |
+
"step": 1400
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.12,
|
| 119 |
+
"grad_norm": 2.3532192707061768,
|
| 120 |
+
"learning_rate": 9.661694915254238e-05,
|
| 121 |
+
"loss": 1.5031,
|
| 122 |
+
"step": 1500
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.13,
|
| 126 |
+
"grad_norm": 2.6274845600128174,
|
| 127 |
+
"learning_rate": 9.627796610169491e-05,
|
| 128 |
+
"loss": 1.4936,
|
| 129 |
+
"step": 1600
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.14,
|
| 133 |
+
"grad_norm": 3.692795991897583,
|
| 134 |
+
"learning_rate": 9.593898305084746e-05,
|
| 135 |
+
"loss": 1.4842,
|
| 136 |
+
"step": 1700
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.15,
|
| 140 |
+
"grad_norm": 2.3271782398223877,
|
| 141 |
+
"learning_rate": 9.56e-05,
|
| 142 |
+
"loss": 1.527,
|
| 143 |
+
"step": 1800
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.16,
|
| 147 |
+
"grad_norm": 1.4074125289916992,
|
| 148 |
+
"learning_rate": 9.526101694915255e-05,
|
| 149 |
+
"loss": 1.4918,
|
| 150 |
+
"step": 1900
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.17,
|
| 154 |
+
"grad_norm": 1.9484646320343018,
|
| 155 |
+
"learning_rate": 9.492203389830509e-05,
|
| 156 |
+
"loss": 1.459,
|
| 157 |
+
"step": 2000
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.17,
|
| 161 |
+
"eval_loss": 1.489809274673462,
|
| 162 |
+
"eval_runtime": 93.0028,
|
| 163 |
+
"eval_samples_per_second": 10.752,
|
| 164 |
+
"eval_steps_per_second": 2.688,
|
| 165 |
+
"step": 2000
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 0.17,
|
| 169 |
+
"grad_norm": 1.8115673065185547,
|
| 170 |
+
"learning_rate": 9.458305084745763e-05,
|
| 171 |
+
"loss": 1.4285,
|
| 172 |
+
"step": 2100
|
| 173 |
+
},
|
| 174 |
+
{
|
| 175 |
+
"epoch": 0.18,
|
| 176 |
+
"grad_norm": 1.803442358970642,
|
| 177 |
+
"learning_rate": 9.424406779661016e-05,
|
| 178 |
+
"loss": 1.5765,
|
| 179 |
+
"step": 2200
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 0.19,
|
| 183 |
+
"grad_norm": 1.2882965803146362,
|
| 184 |
+
"learning_rate": 9.39084745762712e-05,
|
| 185 |
+
"loss": 1.4512,
|
| 186 |
+
"step": 2300
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 0.2,
|
| 190 |
+
"grad_norm": 1.9917691946029663,
|
| 191 |
+
"learning_rate": 9.356949152542374e-05,
|
| 192 |
+
"loss": 1.5322,
|
| 193 |
+
"step": 2400
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"epoch": 0.21,
|
| 197 |
+
"grad_norm": 1.6726502180099487,
|
| 198 |
+
"learning_rate": 9.323050847457627e-05,
|
| 199 |
+
"loss": 1.5219,
|
| 200 |
+
"step": 2500
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 0.22,
|
| 204 |
+
"grad_norm": 3.595461845397949,
|
| 205 |
+
"learning_rate": 9.289152542372882e-05,
|
| 206 |
+
"loss": 1.444,
|
| 207 |
+
"step": 2600
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 0.23,
|
| 211 |
+
"grad_norm": 2.5381546020507812,
|
| 212 |
+
"learning_rate": 9.255254237288135e-05,
|
| 213 |
+
"loss": 1.4474,
|
| 214 |
+
"step": 2700
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"epoch": 0.23,
|
| 218 |
+
"grad_norm": 3.1601195335388184,
|
| 219 |
+
"learning_rate": 9.22135593220339e-05,
|
| 220 |
+
"loss": 1.4111,
|
| 221 |
+
"step": 2800
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 0.24,
|
| 225 |
+
"grad_norm": 2.147916078567505,
|
| 226 |
+
"learning_rate": 9.187457627118645e-05,
|
| 227 |
+
"loss": 1.4551,
|
| 228 |
+
"step": 2900
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"epoch": 0.25,
|
| 232 |
+
"grad_norm": 1.6436530351638794,
|
| 233 |
+
"learning_rate": 9.153559322033899e-05,
|
| 234 |
+
"loss": 1.4915,
|
| 235 |
+
"step": 3000
|
| 236 |
+
},
|
| 237 |
+
{
|
| 238 |
+
"epoch": 0.25,
|
| 239 |
+
"eval_loss": 1.458221197128296,
|
| 240 |
+
"eval_runtime": 93.0923,
|
| 241 |
+
"eval_samples_per_second": 10.742,
|
| 242 |
+
"eval_steps_per_second": 2.686,
|
| 243 |
+
"step": 3000
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 0.26,
|
| 247 |
+
"grad_norm": 2.2148969173431396,
|
| 248 |
+
"learning_rate": 9.119661016949152e-05,
|
| 249 |
+
"loss": 1.4816,
|
| 250 |
+
"step": 3100
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 0.27,
|
| 254 |
+
"grad_norm": 2.3700318336486816,
|
| 255 |
+
"learning_rate": 9.085762711864407e-05,
|
| 256 |
+
"loss": 1.4501,
|
| 257 |
+
"step": 3200
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 0.28,
|
| 261 |
+
"grad_norm": 1.5613566637039185,
|
| 262 |
+
"learning_rate": 9.05186440677966e-05,
|
| 263 |
+
"loss": 1.4646,
|
| 264 |
+
"step": 3300
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 0.28,
|
| 268 |
+
"grad_norm": 2.175220251083374,
|
| 269 |
+
"learning_rate": 9.017966101694916e-05,
|
| 270 |
+
"loss": 1.5036,
|
| 271 |
+
"step": 3400
|
| 272 |
+
},
|
| 273 |
+
{
|
| 274 |
+
"epoch": 0.29,
|
| 275 |
+
"grad_norm": 12.032076835632324,
|
| 276 |
+
"learning_rate": 8.98406779661017e-05,
|
| 277 |
+
"loss": 1.4563,
|
| 278 |
+
"step": 3500
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 0.3,
|
| 282 |
+
"grad_norm": 1.2785927057266235,
|
| 283 |
+
"learning_rate": 8.950169491525424e-05,
|
| 284 |
+
"loss": 1.5178,
|
| 285 |
+
"step": 3600
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 0.31,
|
| 289 |
+
"grad_norm": 1.5785298347473145,
|
| 290 |
+
"learning_rate": 8.916271186440679e-05,
|
| 291 |
+
"loss": 1.4257,
|
| 292 |
+
"step": 3700
|
| 293 |
+
},
|
| 294 |
+
{
|
| 295 |
+
"epoch": 0.32,
|
| 296 |
+
"grad_norm": 3.1845338344573975,
|
| 297 |
+
"learning_rate": 8.882372881355932e-05,
|
| 298 |
+
"loss": 1.4742,
|
| 299 |
+
"step": 3800
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 0.33,
|
| 303 |
+
"grad_norm": 2.2537214756011963,
|
| 304 |
+
"learning_rate": 8.848474576271187e-05,
|
| 305 |
+
"loss": 1.4538,
|
| 306 |
+
"step": 3900
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 0.33,
|
| 310 |
+
"grad_norm": 2.092677354812622,
|
| 311 |
+
"learning_rate": 8.814576271186441e-05,
|
| 312 |
+
"loss": 1.4436,
|
| 313 |
+
"step": 4000
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 0.33,
|
| 317 |
+
"eval_loss": 1.4766532182693481,
|
| 318 |
+
"eval_runtime": 93.0059,
|
| 319 |
+
"eval_samples_per_second": 10.752,
|
| 320 |
+
"eval_steps_per_second": 2.688,
|
| 321 |
+
"step": 4000
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 0.34,
|
| 325 |
+
"grad_norm": 2.3880198001861572,
|
| 326 |
+
"learning_rate": 8.780677966101696e-05,
|
| 327 |
+
"loss": 1.4706,
|
| 328 |
+
"step": 4100
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"epoch": 0.35,
|
| 332 |
+
"grad_norm": 1.7497975826263428,
|
| 333 |
+
"learning_rate": 8.746779661016949e-05,
|
| 334 |
+
"loss": 1.4361,
|
| 335 |
+
"step": 4200
|
| 336 |
+
},
|
| 337 |
+
{
|
| 338 |
+
"epoch": 0.36,
|
| 339 |
+
"grad_norm": 2.1048712730407715,
|
| 340 |
+
"learning_rate": 8.713220338983051e-05,
|
| 341 |
+
"loss": 1.4484,
|
| 342 |
+
"step": 4300
|
| 343 |
+
},
|
| 344 |
+
{
|
| 345 |
+
"epoch": 0.37,
|
| 346 |
+
"grad_norm": 2.206047534942627,
|
| 347 |
+
"learning_rate": 8.679322033898306e-05,
|
| 348 |
+
"loss": 1.4685,
|
| 349 |
+
"step": 4400
|
| 350 |
+
},
|
| 351 |
+
{
|
| 352 |
+
"epoch": 0.38,
|
| 353 |
+
"grad_norm": 2.012110471725464,
|
| 354 |
+
"learning_rate": 8.64542372881356e-05,
|
| 355 |
+
"loss": 1.429,
|
| 356 |
+
"step": 4500
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 0.38,
|
| 360 |
+
"grad_norm": 2.0992116928100586,
|
| 361 |
+
"learning_rate": 8.611525423728813e-05,
|
| 362 |
+
"loss": 1.5028,
|
| 363 |
+
"step": 4600
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 0.39,
|
| 367 |
+
"grad_norm": 4.423650741577148,
|
| 368 |
+
"learning_rate": 8.577627118644068e-05,
|
| 369 |
+
"loss": 1.4644,
|
| 370 |
+
"step": 4700
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 0.4,
|
| 374 |
+
"grad_norm": 1.7697961330413818,
|
| 375 |
+
"learning_rate": 8.543728813559323e-05,
|
| 376 |
+
"loss": 1.4537,
|
| 377 |
+
"step": 4800
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 0.41,
|
| 381 |
+
"grad_norm": 3.925752878189087,
|
| 382 |
+
"learning_rate": 8.509830508474576e-05,
|
| 383 |
+
"loss": 1.4298,
|
| 384 |
+
"step": 4900
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 0.42,
|
| 388 |
+
"grad_norm": 1.335164189338684,
|
| 389 |
+
"learning_rate": 8.475932203389832e-05,
|
| 390 |
+
"loss": 1.4534,
|
| 391 |
+
"step": 5000
|
| 392 |
+
},
|
| 393 |
+
{
|
| 394 |
+
"epoch": 0.42,
|
| 395 |
+
"eval_loss": 1.4249181747436523,
|
| 396 |
+
"eval_runtime": 93.056,
|
| 397 |
+
"eval_samples_per_second": 10.746,
|
| 398 |
+
"eval_steps_per_second": 2.687,
|
| 399 |
+
"step": 5000
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 0.42,
|
| 403 |
+
"grad_norm": 2.5609335899353027,
|
| 404 |
+
"learning_rate": 8.442033898305085e-05,
|
| 405 |
+
"loss": 1.4444,
|
| 406 |
+
"step": 5100
|
| 407 |
+
},
|
| 408 |
+
{
|
| 409 |
+
"epoch": 0.43,
|
| 410 |
+
"grad_norm": 1.4093282222747803,
|
| 411 |
+
"learning_rate": 8.40813559322034e-05,
|
| 412 |
+
"loss": 1.4737,
|
| 413 |
+
"step": 5200
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 0.44,
|
| 417 |
+
"grad_norm": 1.9211537837982178,
|
| 418 |
+
"learning_rate": 8.374237288135593e-05,
|
| 419 |
+
"loss": 1.4108,
|
| 420 |
+
"step": 5300
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 0.45,
|
| 424 |
+
"grad_norm": 1.1686183214187622,
|
| 425 |
+
"learning_rate": 8.340338983050848e-05,
|
| 426 |
+
"loss": 1.4603,
|
| 427 |
+
"step": 5400
|
| 428 |
+
},
|
| 429 |
+
{
|
| 430 |
+
"epoch": 0.46,
|
| 431 |
+
"grad_norm": 2.1233601570129395,
|
| 432 |
+
"learning_rate": 8.306440677966102e-05,
|
| 433 |
+
"loss": 1.414,
|
| 434 |
+
"step": 5500
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 0.47,
|
| 438 |
+
"grad_norm": 1.9452950954437256,
|
| 439 |
+
"learning_rate": 8.272881355932204e-05,
|
| 440 |
+
"loss": 1.3891,
|
| 441 |
+
"step": 5600
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 0.47,
|
| 445 |
+
"grad_norm": 2.8304834365844727,
|
| 446 |
+
"learning_rate": 8.238983050847457e-05,
|
| 447 |
+
"loss": 1.4634,
|
| 448 |
+
"step": 5700
|
| 449 |
+
},
|
| 450 |
+
{
|
| 451 |
+
"epoch": 0.48,
|
| 452 |
+
"grad_norm": 2.8340227603912354,
|
| 453 |
+
"learning_rate": 8.205084745762712e-05,
|
| 454 |
+
"loss": 1.4711,
|
| 455 |
+
"step": 5800
|
| 456 |
+
},
|
| 457 |
+
{
|
| 458 |
+
"epoch": 0.49,
|
| 459 |
+
"grad_norm": 1.5472098588943481,
|
| 460 |
+
"learning_rate": 8.171186440677967e-05,
|
| 461 |
+
"loss": 1.4079,
|
| 462 |
+
"step": 5900
|
| 463 |
+
},
|
| 464 |
+
{
|
| 465 |
+
"epoch": 0.5,
|
| 466 |
+
"grad_norm": 1.8752516508102417,
|
| 467 |
+
"learning_rate": 8.137288135593221e-05,
|
| 468 |
+
"loss": 1.4255,
|
| 469 |
+
"step": 6000
|
| 470 |
+
},
|
| 471 |
+
{
|
| 472 |
+
"epoch": 0.5,
|
| 473 |
+
"eval_loss": 1.433774471282959,
|
| 474 |
+
"eval_runtime": 93.0758,
|
| 475 |
+
"eval_samples_per_second": 10.744,
|
| 476 |
+
"eval_steps_per_second": 2.686,
|
| 477 |
+
"step": 6000
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 0.51,
|
| 481 |
+
"grad_norm": 4.256100177764893,
|
| 482 |
+
"learning_rate": 8.103389830508476e-05,
|
| 483 |
+
"loss": 1.4102,
|
| 484 |
+
"step": 6100
|
| 485 |
+
},
|
| 486 |
+
{
|
| 487 |
+
"epoch": 0.52,
|
| 488 |
+
"grad_norm": 1.966732144355774,
|
| 489 |
+
"learning_rate": 8.069491525423729e-05,
|
| 490 |
+
"loss": 1.4337,
|
| 491 |
+
"step": 6200
|
| 492 |
+
},
|
| 493 |
+
{
|
| 494 |
+
"epoch": 0.53,
|
| 495 |
+
"grad_norm": 0.9053303599357605,
|
| 496 |
+
"learning_rate": 8.035593220338984e-05,
|
| 497 |
+
"loss": 1.4517,
|
| 498 |
+
"step": 6300
|
| 499 |
+
},
|
| 500 |
+
{
|
| 501 |
+
"epoch": 0.53,
|
| 502 |
+
"grad_norm": 2.6552069187164307,
|
| 503 |
+
"learning_rate": 8.001694915254237e-05,
|
| 504 |
+
"loss": 1.459,
|
| 505 |
+
"step": 6400
|
| 506 |
+
},
|
| 507 |
+
{
|
| 508 |
+
"epoch": 0.54,
|
| 509 |
+
"grad_norm": 2.2912251949310303,
|
| 510 |
+
"learning_rate": 7.967796610169492e-05,
|
| 511 |
+
"loss": 1.3857,
|
| 512 |
+
"step": 6500
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 0.55,
|
| 516 |
+
"grad_norm": 2.4170544147491455,
|
| 517 |
+
"learning_rate": 7.933898305084746e-05,
|
| 518 |
+
"loss": 1.4032,
|
| 519 |
+
"step": 6600
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 0.56,
|
| 523 |
+
"grad_norm": 1.7848442792892456,
|
| 524 |
+
"learning_rate": 7.900000000000001e-05,
|
| 525 |
+
"loss": 1.4374,
|
| 526 |
+
"step": 6700
|
| 527 |
+
},
|
| 528 |
+
{
|
| 529 |
+
"epoch": 0.57,
|
| 530 |
+
"grad_norm": 4.551065444946289,
|
| 531 |
+
"learning_rate": 7.866101694915254e-05,
|
| 532 |
+
"loss": 1.4481,
|
| 533 |
+
"step": 6800
|
| 534 |
+
},
|
| 535 |
+
{
|
| 536 |
+
"epoch": 0.57,
|
| 537 |
+
"grad_norm": 1.3571339845657349,
|
| 538 |
+
"learning_rate": 7.832203389830509e-05,
|
| 539 |
+
"loss": 1.4213,
|
| 540 |
+
"step": 6900
|
| 541 |
+
},
|
| 542 |
+
{
|
| 543 |
+
"epoch": 0.58,
|
| 544 |
+
"grad_norm": 1.5277926921844482,
|
| 545 |
+
"learning_rate": 7.798305084745763e-05,
|
| 546 |
+
"loss": 1.429,
|
| 547 |
+
"step": 7000
|
| 548 |
+
},
|
| 549 |
+
{
|
| 550 |
+
"epoch": 0.58,
|
| 551 |
+
"eval_loss": 1.394229769706726,
|
| 552 |
+
"eval_runtime": 93.0895,
|
| 553 |
+
"eval_samples_per_second": 10.742,
|
| 554 |
+
"eval_steps_per_second": 2.686,
|
| 555 |
+
"step": 7000
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.59,
|
| 559 |
+
"grad_norm": 2.962740421295166,
|
| 560 |
+
"learning_rate": 7.764406779661018e-05,
|
| 561 |
+
"loss": 1.4396,
|
| 562 |
+
"step": 7100
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 0.6,
|
| 566 |
+
"grad_norm": 3.3276052474975586,
|
| 567 |
+
"learning_rate": 7.730508474576271e-05,
|
| 568 |
+
"loss": 1.4628,
|
| 569 |
+
"step": 7200
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.61,
|
| 573 |
+
"grad_norm": 0.9193934202194214,
|
| 574 |
+
"learning_rate": 7.696610169491526e-05,
|
| 575 |
+
"loss": 1.4234,
|
| 576 |
+
"step": 7300
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 0.62,
|
| 580 |
+
"grad_norm": 1.859925627708435,
|
| 581 |
+
"learning_rate": 7.662711864406779e-05,
|
| 582 |
+
"loss": 1.4427,
|
| 583 |
+
"step": 7400
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.62,
|
| 587 |
+
"grad_norm": 2.7623603343963623,
|
| 588 |
+
"learning_rate": 7.628813559322034e-05,
|
| 589 |
+
"loss": 1.4046,
|
| 590 |
+
"step": 7500
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 0.63,
|
| 594 |
+
"grad_norm": 2.3409364223480225,
|
| 595 |
+
"learning_rate": 7.594915254237289e-05,
|
| 596 |
+
"loss": 1.4351,
|
| 597 |
+
"step": 7600
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.64,
|
| 601 |
+
"grad_norm": 1.8644472360610962,
|
| 602 |
+
"learning_rate": 7.561016949152543e-05,
|
| 603 |
+
"loss": 1.4281,
|
| 604 |
+
"step": 7700
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 0.65,
|
| 608 |
+
"grad_norm": 2.663987398147583,
|
| 609 |
+
"learning_rate": 7.527118644067796e-05,
|
| 610 |
+
"loss": 1.3743,
|
| 611 |
+
"step": 7800
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.66,
|
| 615 |
+
"grad_norm": 1.3779089450836182,
|
| 616 |
+
"learning_rate": 7.493220338983051e-05,
|
| 617 |
+
"loss": 1.4531,
|
| 618 |
+
"step": 7900
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 0.67,
|
| 622 |
+
"grad_norm": 1.2310881614685059,
|
| 623 |
+
"learning_rate": 7.459322033898304e-05,
|
| 624 |
+
"loss": 1.427,
|
| 625 |
+
"step": 8000
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.67,
|
| 629 |
+
"eval_loss": 1.4101628065109253,
|
| 630 |
+
"eval_runtime": 92.9756,
|
| 631 |
+
"eval_samples_per_second": 10.756,
|
| 632 |
+
"eval_steps_per_second": 2.689,
|
| 633 |
+
"step": 8000
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 0.68,
|
| 637 |
+
"grad_norm": 2.426481246948242,
|
| 638 |
+
"learning_rate": 7.425762711864407e-05,
|
| 639 |
+
"loss": 1.4215,
|
| 640 |
+
"step": 8100
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 0.68,
|
| 644 |
+
"grad_norm": 3.706364154815674,
|
| 645 |
+
"learning_rate": 7.391864406779662e-05,
|
| 646 |
+
"loss": 1.3344,
|
| 647 |
+
"step": 8200
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 0.69,
|
| 651 |
+
"grad_norm": 2.511159658432007,
|
| 652 |
+
"learning_rate": 7.357966101694915e-05,
|
| 653 |
+
"loss": 1.4132,
|
| 654 |
+
"step": 8300
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 0.7,
|
| 658 |
+
"grad_norm": 2.31131911277771,
|
| 659 |
+
"learning_rate": 7.32406779661017e-05,
|
| 660 |
+
"loss": 1.4357,
|
| 661 |
+
"step": 8400
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 0.71,
|
| 665 |
+
"grad_norm": 2.3403029441833496,
|
| 666 |
+
"learning_rate": 7.290169491525423e-05,
|
| 667 |
+
"loss": 1.455,
|
| 668 |
+
"step": 8500
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 0.72,
|
| 672 |
+
"grad_norm": 2.386819362640381,
|
| 673 |
+
"learning_rate": 7.256271186440679e-05,
|
| 674 |
+
"loss": 1.374,
|
| 675 |
+
"step": 8600
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 0.72,
|
| 679 |
+
"grad_norm": 12.603606224060059,
|
| 680 |
+
"learning_rate": 7.222372881355932e-05,
|
| 681 |
+
"loss": 1.461,
|
| 682 |
+
"step": 8700
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 0.73,
|
| 686 |
+
"grad_norm": 2.5920355319976807,
|
| 687 |
+
"learning_rate": 7.188474576271187e-05,
|
| 688 |
+
"loss": 1.423,
|
| 689 |
+
"step": 8800
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 0.74,
|
| 693 |
+
"grad_norm": 3.7238869667053223,
|
| 694 |
+
"learning_rate": 7.15457627118644e-05,
|
| 695 |
+
"loss": 1.3845,
|
| 696 |
+
"step": 8900
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 0.75,
|
| 700 |
+
"grad_norm": 4.266007900238037,
|
| 701 |
+
"learning_rate": 7.120677966101695e-05,
|
| 702 |
+
"loss": 1.4293,
|
| 703 |
+
"step": 9000
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 0.75,
|
| 707 |
+
"eval_loss": 1.4198664426803589,
|
| 708 |
+
"eval_runtime": 93.0273,
|
| 709 |
+
"eval_samples_per_second": 10.75,
|
| 710 |
+
"eval_steps_per_second": 2.687,
|
| 711 |
+
"step": 9000
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 0.76,
|
| 715 |
+
"grad_norm": 2.2583582401275635,
|
| 716 |
+
"learning_rate": 7.08677966101695e-05,
|
| 717 |
+
"loss": 1.4032,
|
| 718 |
+
"step": 9100
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 0.77,
|
| 722 |
+
"grad_norm": 3.374390125274658,
|
| 723 |
+
"learning_rate": 7.052881355932204e-05,
|
| 724 |
+
"loss": 1.3469,
|
| 725 |
+
"step": 9200
|
| 726 |
+
},
|
| 727 |
+
{
|
| 728 |
+
"epoch": 0.78,
|
| 729 |
+
"grad_norm": 2.431976318359375,
|
| 730 |
+
"learning_rate": 7.018983050847457e-05,
|
| 731 |
+
"loss": 1.3861,
|
| 732 |
+
"step": 9300
|
| 733 |
+
},
|
| 734 |
+
{
|
| 735 |
+
"epoch": 0.78,
|
| 736 |
+
"grad_norm": 2.953474760055542,
|
| 737 |
+
"learning_rate": 6.985084745762712e-05,
|
| 738 |
+
"loss": 1.3406,
|
| 739 |
+
"step": 9400
|
| 740 |
+
},
|
| 741 |
+
{
|
| 742 |
+
"epoch": 0.79,
|
| 743 |
+
"grad_norm": 1.3457430601119995,
|
| 744 |
+
"learning_rate": 6.951186440677967e-05,
|
| 745 |
+
"loss": 1.4132,
|
| 746 |
+
"step": 9500
|
| 747 |
+
},
|
| 748 |
+
{
|
| 749 |
+
"epoch": 0.8,
|
| 750 |
+
"grad_norm": 3.713928699493408,
|
| 751 |
+
"learning_rate": 6.91728813559322e-05,
|
| 752 |
+
"loss": 1.4555,
|
| 753 |
+
"step": 9600
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 0.81,
|
| 757 |
+
"grad_norm": 3.0444705486297607,
|
| 758 |
+
"learning_rate": 6.883389830508476e-05,
|
| 759 |
+
"loss": 1.3372,
|
| 760 |
+
"step": 9700
|
| 761 |
+
},
|
| 762 |
+
{
|
| 763 |
+
"epoch": 0.82,
|
| 764 |
+
"grad_norm": 2.5544724464416504,
|
| 765 |
+
"learning_rate": 6.849491525423729e-05,
|
| 766 |
+
"loss": 1.4265,
|
| 767 |
+
"step": 9800
|
| 768 |
+
},
|
| 769 |
+
{
|
| 770 |
+
"epoch": 0.82,
|
| 771 |
+
"grad_norm": 3.4634218215942383,
|
| 772 |
+
"learning_rate": 6.815593220338984e-05,
|
| 773 |
+
"loss": 1.4021,
|
| 774 |
+
"step": 9900
|
| 775 |
+
},
|
| 776 |
+
{
|
| 777 |
+
"epoch": 0.83,
|
| 778 |
+
"grad_norm": 2.940263509750366,
|
| 779 |
+
"learning_rate": 6.781694915254237e-05,
|
| 780 |
+
"loss": 1.3975,
|
| 781 |
+
"step": 10000
|
| 782 |
+
},
|
| 783 |
+
{
|
| 784 |
+
"epoch": 0.83,
|
| 785 |
+
"eval_loss": 1.3409844636917114,
|
| 786 |
+
"eval_runtime": 92.9614,
|
| 787 |
+
"eval_samples_per_second": 10.757,
|
| 788 |
+
"eval_steps_per_second": 2.689,
|
| 789 |
+
"step": 10000
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 0.84,
|
| 793 |
+
"grad_norm": 2.2668895721435547,
|
| 794 |
+
"learning_rate": 6.748135593220339e-05,
|
| 795 |
+
"loss": 1.3879,
|
| 796 |
+
"step": 10100
|
| 797 |
+
},
|
| 798 |
+
{
|
| 799 |
+
"epoch": 0.85,
|
| 800 |
+
"grad_norm": 2.5967912673950195,
|
| 801 |
+
"learning_rate": 6.714237288135593e-05,
|
| 802 |
+
"loss": 1.4197,
|
| 803 |
+
"step": 10200
|
| 804 |
+
},
|
| 805 |
+
{
|
| 806 |
+
"epoch": 0.86,
|
| 807 |
+
"grad_norm": 4.100217819213867,
|
| 808 |
+
"learning_rate": 6.680338983050848e-05,
|
| 809 |
+
"loss": 1.4081,
|
| 810 |
+
"step": 10300
|
| 811 |
+
},
|
| 812 |
+
{
|
| 813 |
+
"epoch": 0.87,
|
| 814 |
+
"grad_norm": 1.7082469463348389,
|
| 815 |
+
"learning_rate": 6.646440677966101e-05,
|
| 816 |
+
"loss": 1.4103,
|
| 817 |
+
"step": 10400
|
| 818 |
+
},
|
| 819 |
+
{
|
| 820 |
+
"epoch": 0.88,
|
| 821 |
+
"grad_norm": 2.1128108501434326,
|
| 822 |
+
"learning_rate": 6.612542372881356e-05,
|
| 823 |
+
"loss": 1.44,
|
| 824 |
+
"step": 10500
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 0.88,
|
| 828 |
+
"grad_norm": 2.1471731662750244,
|
| 829 |
+
"learning_rate": 6.57864406779661e-05,
|
| 830 |
+
"loss": 1.412,
|
| 831 |
+
"step": 10600
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 0.89,
|
| 835 |
+
"grad_norm": 3.2873263359069824,
|
| 836 |
+
"learning_rate": 6.544745762711865e-05,
|
| 837 |
+
"loss": 1.4407,
|
| 838 |
+
"step": 10700
|
| 839 |
+
},
|
| 840 |
+
{
|
| 841 |
+
"epoch": 0.9,
|
| 842 |
+
"grad_norm": 3.7035319805145264,
|
| 843 |
+
"learning_rate": 6.51084745762712e-05,
|
| 844 |
+
"loss": 1.3792,
|
| 845 |
+
"step": 10800
|
| 846 |
+
},
|
| 847 |
+
{
|
| 848 |
+
"epoch": 0.91,
|
| 849 |
+
"grad_norm": 2.7462477684020996,
|
| 850 |
+
"learning_rate": 6.476949152542373e-05,
|
| 851 |
+
"loss": 1.3676,
|
| 852 |
+
"step": 10900
|
| 853 |
+
},
|
| 854 |
+
{
|
| 855 |
+
"epoch": 0.92,
|
| 856 |
+
"grad_norm": 1.895967721939087,
|
| 857 |
+
"learning_rate": 6.443050847457628e-05,
|
| 858 |
+
"loss": 1.4092,
|
| 859 |
+
"step": 11000
|
| 860 |
+
},
|
| 861 |
+
{
|
| 862 |
+
"epoch": 0.92,
|
| 863 |
+
"eval_loss": 1.4003005027770996,
|
| 864 |
+
"eval_runtime": 93.0106,
|
| 865 |
+
"eval_samples_per_second": 10.751,
|
| 866 |
+
"eval_steps_per_second": 2.688,
|
| 867 |
+
"step": 11000
|
| 868 |
+
},
|
| 869 |
+
{
|
| 870 |
+
"epoch": 0.93,
|
| 871 |
+
"grad_norm": 2.039684295654297,
|
| 872 |
+
"learning_rate": 6.409152542372881e-05,
|
| 873 |
+
"loss": 1.4015,
|
| 874 |
+
"step": 11100
|
| 875 |
+
},
|
| 876 |
+
{
|
| 877 |
+
"epoch": 0.93,
|
| 878 |
+
"grad_norm": 1.625591516494751,
|
| 879 |
+
"learning_rate": 6.375254237288136e-05,
|
| 880 |
+
"loss": 1.4362,
|
| 881 |
+
"step": 11200
|
| 882 |
+
},
|
| 883 |
+
{
|
| 884 |
+
"epoch": 0.94,
|
| 885 |
+
"grad_norm": 3.4086389541625977,
|
| 886 |
+
"learning_rate": 6.34135593220339e-05,
|
| 887 |
+
"loss": 1.4192,
|
| 888 |
+
"step": 11300
|
| 889 |
+
},
|
| 890 |
+
{
|
| 891 |
+
"epoch": 0.95,
|
| 892 |
+
"grad_norm": 1.9734954833984375,
|
| 893 |
+
"learning_rate": 6.307457627118645e-05,
|
| 894 |
+
"loss": 1.4413,
|
| 895 |
+
"step": 11400
|
| 896 |
+
},
|
| 897 |
+
{
|
| 898 |
+
"epoch": 0.96,
|
| 899 |
+
"grad_norm": 3.1704461574554443,
|
| 900 |
+
"learning_rate": 6.273559322033898e-05,
|
| 901 |
+
"loss": 1.3856,
|
| 902 |
+
"step": 11500
|
| 903 |
+
},
|
| 904 |
+
{
|
| 905 |
+
"epoch": 0.97,
|
| 906 |
+
"grad_norm": 3.659949541091919,
|
| 907 |
+
"learning_rate": 6.239661016949153e-05,
|
| 908 |
+
"loss": 1.4044,
|
| 909 |
+
"step": 11600
|
| 910 |
+
},
|
| 911 |
+
{
|
| 912 |
+
"epoch": 0.97,
|
| 913 |
+
"grad_norm": 1.8390787839889526,
|
| 914 |
+
"learning_rate": 6.205762711864406e-05,
|
| 915 |
+
"loss": 1.3704,
|
| 916 |
+
"step": 11700
|
| 917 |
+
},
|
| 918 |
+
{
|
| 919 |
+
"epoch": 0.98,
|
| 920 |
+
"grad_norm": 1.7644896507263184,
|
| 921 |
+
"learning_rate": 6.171864406779662e-05,
|
| 922 |
+
"loss": 1.4389,
|
| 923 |
+
"step": 11800
|
| 924 |
+
},
|
| 925 |
+
{
|
| 926 |
+
"epoch": 0.99,
|
| 927 |
+
"grad_norm": 2.0395686626434326,
|
| 928 |
+
"learning_rate": 6.137966101694915e-05,
|
| 929 |
+
"loss": 1.397,
|
| 930 |
+
"step": 11900
|
| 931 |
+
},
|
| 932 |
+
{
|
| 933 |
+
"epoch": 1.0,
|
| 934 |
+
"grad_norm": 1.8224962949752808,
|
| 935 |
+
"learning_rate": 6.10406779661017e-05,
|
| 936 |
+
"loss": 1.351,
|
| 937 |
+
"step": 12000
|
| 938 |
+
},
|
| 939 |
+
{
|
| 940 |
+
"epoch": 1.0,
|
| 941 |
+
"eval_loss": 1.4065361022949219,
|
| 942 |
+
"eval_runtime": 93.0021,
|
| 943 |
+
"eval_samples_per_second": 10.752,
|
| 944 |
+
"eval_steps_per_second": 2.688,
|
| 945 |
+
"step": 12000
|
| 946 |
+
},
|
| 947 |
+
{
|
| 948 |
+
"epoch": 1.01,
|
| 949 |
+
"grad_norm": 3.049715995788574,
|
| 950 |
+
"learning_rate": 6.070169491525424e-05,
|
| 951 |
+
"loss": 1.3315,
|
| 952 |
+
"step": 12100
|
| 953 |
+
},
|
| 954 |
+
{
|
| 955 |
+
"epoch": 1.02,
|
| 956 |
+
"grad_norm": 2.025336503982544,
|
| 957 |
+
"learning_rate": 6.0362711864406786e-05,
|
| 958 |
+
"loss": 1.3722,
|
| 959 |
+
"step": 12200
|
| 960 |
+
},
|
| 961 |
+
{
|
| 962 |
+
"epoch": 1.02,
|
| 963 |
+
"grad_norm": 2.9472439289093018,
|
| 964 |
+
"learning_rate": 6.002372881355932e-05,
|
| 965 |
+
"loss": 1.3185,
|
| 966 |
+
"step": 12300
|
| 967 |
+
},
|
| 968 |
+
{
|
| 969 |
+
"epoch": 1.03,
|
| 970 |
+
"grad_norm": 3.2052855491638184,
|
| 971 |
+
"learning_rate": 5.968474576271187e-05,
|
| 972 |
+
"loss": 1.3029,
|
| 973 |
+
"step": 12400
|
| 974 |
+
},
|
| 975 |
+
{
|
| 976 |
+
"epoch": 1.04,
|
| 977 |
+
"grad_norm": 3.9783244132995605,
|
| 978 |
+
"learning_rate": 5.9345762711864405e-05,
|
| 979 |
+
"loss": 1.3617,
|
| 980 |
+
"step": 12500
|
| 981 |
+
},
|
| 982 |
+
{
|
| 983 |
+
"epoch": 1.05,
|
| 984 |
+
"grad_norm": 6.090597152709961,
|
| 985 |
+
"learning_rate": 5.900677966101695e-05,
|
| 986 |
+
"loss": 1.4188,
|
| 987 |
+
"step": 12600
|
| 988 |
+
},
|
| 989 |
+
{
|
| 990 |
+
"epoch": 1.06,
|
| 991 |
+
"grad_norm": 2.486492156982422,
|
| 992 |
+
"learning_rate": 5.866779661016949e-05,
|
| 993 |
+
"loss": 1.3771,
|
| 994 |
+
"step": 12700
|
| 995 |
+
},
|
| 996 |
+
{
|
| 997 |
+
"epoch": 1.07,
|
| 998 |
+
"grad_norm": 2.2206759452819824,
|
| 999 |
+
"learning_rate": 5.832881355932204e-05,
|
| 1000 |
+
"loss": 1.3583,
|
| 1001 |
+
"step": 12800
|
| 1002 |
+
},
|
| 1003 |
+
{
|
| 1004 |
+
"epoch": 1.07,
|
| 1005 |
+
"grad_norm": 2.092623710632324,
|
| 1006 |
+
"learning_rate": 5.7989830508474577e-05,
|
| 1007 |
+
"loss": 1.344,
|
| 1008 |
+
"step": 12900
|
| 1009 |
+
},
|
| 1010 |
+
{
|
| 1011 |
+
"epoch": 1.08,
|
| 1012 |
+
"grad_norm": 1.9661636352539062,
|
| 1013 |
+
"learning_rate": 5.765084745762712e-05,
|
| 1014 |
+
"loss": 1.3364,
|
| 1015 |
+
"step": 13000
|
| 1016 |
+
},
|
| 1017 |
+
{
|
| 1018 |
+
"epoch": 1.08,
|
| 1019 |
+
"eval_loss": 1.3436501026153564,
|
| 1020 |
+
"eval_runtime": 92.9061,
|
| 1021 |
+
"eval_samples_per_second": 10.764,
|
| 1022 |
+
"eval_steps_per_second": 2.691,
|
| 1023 |
+
"step": 13000
|
| 1024 |
+
},
|
| 1025 |
+
{
|
| 1026 |
+
"epoch": 1.09,
|
| 1027 |
+
"grad_norm": 2.299858331680298,
|
| 1028 |
+
"learning_rate": 5.7311864406779656e-05,
|
| 1029 |
+
"loss": 1.327,
|
| 1030 |
+
"step": 13100
|
| 1031 |
+
},
|
| 1032 |
+
{
|
| 1033 |
+
"epoch": 1.1,
|
| 1034 |
+
"grad_norm": 1.999542474746704,
|
| 1035 |
+
"learning_rate": 5.697288135593221e-05,
|
| 1036 |
+
"loss": 1.3852,
|
| 1037 |
+
"step": 13200
|
| 1038 |
+
},
|
| 1039 |
+
{
|
| 1040 |
+
"epoch": 1.11,
|
| 1041 |
+
"grad_norm": 4.422431468963623,
|
| 1042 |
+
"learning_rate": 5.6633898305084755e-05,
|
| 1043 |
+
"loss": 1.3812,
|
| 1044 |
+
"step": 13300
|
| 1045 |
+
},
|
| 1046 |
+
{
|
| 1047 |
+
"epoch": 1.12,
|
| 1048 |
+
"grad_norm": 1.9813380241394043,
|
| 1049 |
+
"learning_rate": 5.629491525423729e-05,
|
| 1050 |
+
"loss": 1.3517,
|
| 1051 |
+
"step": 13400
|
| 1052 |
+
},
|
| 1053 |
+
{
|
| 1054 |
+
"epoch": 1.12,
|
| 1055 |
+
"grad_norm": 1.8180012702941895,
|
| 1056 |
+
"learning_rate": 5.595593220338984e-05,
|
| 1057 |
+
"loss": 1.3715,
|
| 1058 |
+
"step": 13500
|
| 1059 |
+
},
|
| 1060 |
+
{
|
| 1061 |
+
"epoch": 1.13,
|
| 1062 |
+
"grad_norm": 3.0727899074554443,
|
| 1063 |
+
"learning_rate": 5.5616949152542374e-05,
|
| 1064 |
+
"loss": 1.3278,
|
| 1065 |
+
"step": 13600
|
| 1066 |
+
},
|
| 1067 |
+
{
|
| 1068 |
+
"epoch": 1.14,
|
| 1069 |
+
"grad_norm": 1.4579344987869263,
|
| 1070 |
+
"learning_rate": 5.527796610169492e-05,
|
| 1071 |
+
"loss": 1.3649,
|
| 1072 |
+
"step": 13700
|
| 1073 |
+
},
|
| 1074 |
+
{
|
| 1075 |
+
"epoch": 1.15,
|
| 1076 |
+
"grad_norm": 1.9728525876998901,
|
| 1077 |
+
"learning_rate": 5.493898305084746e-05,
|
| 1078 |
+
"loss": 1.2894,
|
| 1079 |
+
"step": 13800
|
| 1080 |
+
},
|
| 1081 |
+
{
|
| 1082 |
+
"epoch": 1.16,
|
| 1083 |
+
"grad_norm": 3.2770729064941406,
|
| 1084 |
+
"learning_rate": 5.4600000000000006e-05,
|
| 1085 |
+
"loss": 1.3748,
|
| 1086 |
+
"step": 13900
|
| 1087 |
+
},
|
| 1088 |
+
{
|
| 1089 |
+
"epoch": 1.17,
|
| 1090 |
+
"grad_norm": 4.356542587280273,
|
| 1091 |
+
"learning_rate": 5.4261016949152545e-05,
|
| 1092 |
+
"loss": 1.3153,
|
| 1093 |
+
"step": 14000
|
| 1094 |
+
},
|
| 1095 |
+
{
|
| 1096 |
+
"epoch": 1.17,
|
| 1097 |
+
"eval_loss": 1.3724653720855713,
|
| 1098 |
+
"eval_runtime": 92.8763,
|
| 1099 |
+
"eval_samples_per_second": 10.767,
|
| 1100 |
+
"eval_steps_per_second": 2.692,
|
| 1101 |
+
"step": 14000
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 1.18,
|
| 1105 |
+
"grad_norm": 1.5841625928878784,
|
| 1106 |
+
"learning_rate": 5.392203389830509e-05,
|
| 1107 |
+
"loss": 1.3295,
|
| 1108 |
+
"step": 14100
|
| 1109 |
+
},
|
| 1110 |
+
{
|
| 1111 |
+
"epoch": 1.18,
|
| 1112 |
+
"grad_norm": 8.736273765563965,
|
| 1113 |
+
"learning_rate": 5.35864406779661e-05,
|
| 1114 |
+
"loss": 1.3146,
|
| 1115 |
+
"step": 14200
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 1.19,
|
| 1119 |
+
"grad_norm": 3.8798937797546387,
|
| 1120 |
+
"learning_rate": 5.324745762711865e-05,
|
| 1121 |
+
"loss": 1.2944,
|
| 1122 |
+
"step": 14300
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 1.2,
|
| 1126 |
+
"grad_norm": 3.1168253421783447,
|
| 1127 |
+
"learning_rate": 5.2908474576271194e-05,
|
| 1128 |
+
"loss": 1.2995,
|
| 1129 |
+
"step": 14400
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 1.21,
|
| 1133 |
+
"grad_norm": 1.7689605951309204,
|
| 1134 |
+
"learning_rate": 5.256949152542373e-05,
|
| 1135 |
+
"loss": 1.3166,
|
| 1136 |
+
"step": 14500
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 1.22,
|
| 1140 |
+
"grad_norm": 2.00744891166687,
|
| 1141 |
+
"learning_rate": 5.223050847457628e-05,
|
| 1142 |
+
"loss": 1.3385,
|
| 1143 |
+
"step": 14600
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 1.23,
|
| 1147 |
+
"grad_norm": 1.9501924514770508,
|
| 1148 |
+
"learning_rate": 5.189152542372881e-05,
|
| 1149 |
+
"loss": 1.3564,
|
| 1150 |
+
"step": 14700
|
| 1151 |
+
},
|
| 1152 |
+
{
|
| 1153 |
+
"epoch": 1.23,
|
| 1154 |
+
"grad_norm": 2.614849328994751,
|
| 1155 |
+
"learning_rate": 5.1552542372881366e-05,
|
| 1156 |
+
"loss": 1.3326,
|
| 1157 |
+
"step": 14800
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 1.24,
|
| 1161 |
+
"grad_norm": 2.0598857402801514,
|
| 1162 |
+
"learning_rate": 5.12135593220339e-05,
|
| 1163 |
+
"loss": 1.2322,
|
| 1164 |
+
"step": 14900
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 1.25,
|
| 1168 |
+
"grad_norm": 2.12611985206604,
|
| 1169 |
+
"learning_rate": 5.0874576271186445e-05,
|
| 1170 |
+
"loss": 1.354,
|
| 1171 |
+
"step": 15000
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 1.25,
|
| 1175 |
+
"eval_loss": 1.368465542793274,
|
| 1176 |
+
"eval_runtime": 93.0272,
|
| 1177 |
+
"eval_samples_per_second": 10.75,
|
| 1178 |
+
"eval_steps_per_second": 2.687,
|
| 1179 |
+
"step": 15000
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 1.26,
|
| 1183 |
+
"grad_norm": 1.287361979484558,
|
| 1184 |
+
"learning_rate": 5.0535593220338984e-05,
|
| 1185 |
+
"loss": 1.3178,
|
| 1186 |
+
"step": 15100
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 1.27,
|
| 1190 |
+
"grad_norm": 3.340104579925537,
|
| 1191 |
+
"learning_rate": 5.019661016949153e-05,
|
| 1192 |
+
"loss": 1.3893,
|
| 1193 |
+
"step": 15200
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 1.27,
|
| 1197 |
+
"grad_norm": 2.4543209075927734,
|
| 1198 |
+
"learning_rate": 4.985762711864407e-05,
|
| 1199 |
+
"loss": 1.3597,
|
| 1200 |
+
"step": 15300
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 1.28,
|
| 1204 |
+
"grad_norm": 2.6554243564605713,
|
| 1205 |
+
"learning_rate": 4.951864406779661e-05,
|
| 1206 |
+
"loss": 1.2903,
|
| 1207 |
+
"step": 15400
|
| 1208 |
+
},
|
| 1209 |
+
{
|
| 1210 |
+
"epoch": 1.29,
|
| 1211 |
+
"grad_norm": 1.685389518737793,
|
| 1212 |
+
"learning_rate": 4.917966101694915e-05,
|
| 1213 |
+
"loss": 1.2902,
|
| 1214 |
+
"step": 15500
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 1.3,
|
| 1218 |
+
"grad_norm": 1.9464205503463745,
|
| 1219 |
+
"learning_rate": 4.88406779661017e-05,
|
| 1220 |
+
"loss": 1.3333,
|
| 1221 |
+
"step": 15600
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 1.31,
|
| 1225 |
+
"grad_norm": 2.7877588272094727,
|
| 1226 |
+
"learning_rate": 4.850169491525424e-05,
|
| 1227 |
+
"loss": 1.3016,
|
| 1228 |
+
"step": 15700
|
| 1229 |
+
},
|
| 1230 |
+
{
|
| 1231 |
+
"epoch": 1.32,
|
| 1232 |
+
"grad_norm": 1.88291335105896,
|
| 1233 |
+
"learning_rate": 4.816271186440678e-05,
|
| 1234 |
+
"loss": 1.382,
|
| 1235 |
+
"step": 15800
|
| 1236 |
+
},
|
| 1237 |
+
{
|
| 1238 |
+
"epoch": 1.32,
|
| 1239 |
+
"grad_norm": 4.62669038772583,
|
| 1240 |
+
"learning_rate": 4.782372881355933e-05,
|
| 1241 |
+
"loss": 1.3343,
|
| 1242 |
+
"step": 15900
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"epoch": 1.33,
|
| 1246 |
+
"grad_norm": 2.525221824645996,
|
| 1247 |
+
"learning_rate": 4.748474576271187e-05,
|
| 1248 |
+
"loss": 1.2822,
|
| 1249 |
+
"step": 16000
|
| 1250 |
+
},
|
| 1251 |
+
{
|
| 1252 |
+
"epoch": 1.33,
|
| 1253 |
+
"eval_loss": 1.3313556909561157,
|
| 1254 |
+
"eval_runtime": 93.0605,
|
| 1255 |
+
"eval_samples_per_second": 10.746,
|
| 1256 |
+
"eval_steps_per_second": 2.686,
|
| 1257 |
+
"step": 16000
|
| 1258 |
+
},
|
| 1259 |
+
{
|
| 1260 |
+
"epoch": 1.34,
|
| 1261 |
+
"grad_norm": 2.8074324131011963,
|
| 1262 |
+
"learning_rate": 4.714576271186441e-05,
|
| 1263 |
+
"loss": 1.3487,
|
| 1264 |
+
"step": 16100
|
| 1265 |
+
},
|
| 1266 |
+
{
|
| 1267 |
+
"epoch": 1.35,
|
| 1268 |
+
"grad_norm": 3.902251958847046,
|
| 1269 |
+
"learning_rate": 4.680677966101695e-05,
|
| 1270 |
+
"loss": 1.2796,
|
| 1271 |
+
"step": 16200
|
| 1272 |
+
},
|
| 1273 |
+
{
|
| 1274 |
+
"epoch": 1.36,
|
| 1275 |
+
"grad_norm": 3.72412109375,
|
| 1276 |
+
"learning_rate": 4.646779661016949e-05,
|
| 1277 |
+
"loss": 1.3161,
|
| 1278 |
+
"step": 16300
|
| 1279 |
+
},
|
| 1280 |
+
{
|
| 1281 |
+
"epoch": 1.37,
|
| 1282 |
+
"grad_norm": 1.7499101161956787,
|
| 1283 |
+
"learning_rate": 4.612881355932204e-05,
|
| 1284 |
+
"loss": 1.3477,
|
| 1285 |
+
"step": 16400
|
| 1286 |
+
},
|
| 1287 |
+
{
|
| 1288 |
+
"epoch": 1.38,
|
| 1289 |
+
"grad_norm": 2.252373695373535,
|
| 1290 |
+
"learning_rate": 4.578983050847458e-05,
|
| 1291 |
+
"loss": 1.3288,
|
| 1292 |
+
"step": 16500
|
| 1293 |
+
},
|
| 1294 |
+
{
|
| 1295 |
+
"epoch": 1.38,
|
| 1296 |
+
"grad_norm": 3.353426933288574,
|
| 1297 |
+
"learning_rate": 4.5450847457627125e-05,
|
| 1298 |
+
"loss": 1.3472,
|
| 1299 |
+
"step": 16600
|
| 1300 |
+
},
|
| 1301 |
+
{
|
| 1302 |
+
"epoch": 1.39,
|
| 1303 |
+
"grad_norm": 2.308408260345459,
|
| 1304 |
+
"learning_rate": 4.5111864406779664e-05,
|
| 1305 |
+
"loss": 1.3213,
|
| 1306 |
+
"step": 16700
|
| 1307 |
+
},
|
| 1308 |
+
{
|
| 1309 |
+
"epoch": 1.4,
|
| 1310 |
+
"grad_norm": 4.369659423828125,
|
| 1311 |
+
"learning_rate": 4.4772881355932204e-05,
|
| 1312 |
+
"loss": 1.2767,
|
| 1313 |
+
"step": 16800
|
| 1314 |
+
},
|
| 1315 |
+
{
|
| 1316 |
+
"epoch": 1.41,
|
| 1317 |
+
"grad_norm": 1.9831510782241821,
|
| 1318 |
+
"learning_rate": 4.443389830508475e-05,
|
| 1319 |
+
"loss": 1.2989,
|
| 1320 |
+
"step": 16900
|
| 1321 |
+
},
|
| 1322 |
+
{
|
| 1323 |
+
"epoch": 1.42,
|
| 1324 |
+
"grad_norm": 1.2581738233566284,
|
| 1325 |
+
"learning_rate": 4.409491525423729e-05,
|
| 1326 |
+
"loss": 1.3224,
|
| 1327 |
+
"step": 17000
|
| 1328 |
+
},
|
| 1329 |
+
{
|
| 1330 |
+
"epoch": 1.42,
|
| 1331 |
+
"eval_loss": 1.3554507493972778,
|
| 1332 |
+
"eval_runtime": 92.9689,
|
| 1333 |
+
"eval_samples_per_second": 10.756,
|
| 1334 |
+
"eval_steps_per_second": 2.689,
|
| 1335 |
+
"step": 17000
|
| 1336 |
+
},
|
| 1337 |
+
{
|
| 1338 |
+
"epoch": 1.43,
|
| 1339 |
+
"grad_norm": 5.903542518615723,
|
| 1340 |
+
"learning_rate": 4.375593220338983e-05,
|
| 1341 |
+
"loss": 1.3135,
|
| 1342 |
+
"step": 17100
|
| 1343 |
+
},
|
| 1344 |
+
{
|
| 1345 |
+
"epoch": 1.43,
|
| 1346 |
+
"grad_norm": 2.0982234477996826,
|
| 1347 |
+
"learning_rate": 4.3416949152542375e-05,
|
| 1348 |
+
"loss": 1.3036,
|
| 1349 |
+
"step": 17200
|
| 1350 |
+
},
|
| 1351 |
+
{
|
| 1352 |
+
"epoch": 1.44,
|
| 1353 |
+
"grad_norm": 1.5168031454086304,
|
| 1354 |
+
"learning_rate": 4.3077966101694915e-05,
|
| 1355 |
+
"loss": 1.3223,
|
| 1356 |
+
"step": 17300
|
| 1357 |
+
},
|
| 1358 |
+
{
|
| 1359 |
+
"epoch": 1.45,
|
| 1360 |
+
"grad_norm": 2.655869722366333,
|
| 1361 |
+
"learning_rate": 4.273898305084746e-05,
|
| 1362 |
+
"loss": 1.3036,
|
| 1363 |
+
"step": 17400
|
| 1364 |
+
},
|
| 1365 |
+
{
|
| 1366 |
+
"epoch": 1.46,
|
| 1367 |
+
"grad_norm": 3.1604421138763428,
|
| 1368 |
+
"learning_rate": 4.24e-05,
|
| 1369 |
+
"loss": 1.3172,
|
| 1370 |
+
"step": 17500
|
| 1371 |
+
},
|
| 1372 |
+
{
|
| 1373 |
+
"epoch": 1.47,
|
| 1374 |
+
"grad_norm": 1.9133104085922241,
|
| 1375 |
+
"learning_rate": 4.206101694915254e-05,
|
| 1376 |
+
"loss": 1.3596,
|
| 1377 |
+
"step": 17600
|
| 1378 |
+
},
|
| 1379 |
+
{
|
| 1380 |
+
"epoch": 1.48,
|
| 1381 |
+
"grad_norm": 5.270731449127197,
|
| 1382 |
+
"learning_rate": 4.1722033898305086e-05,
|
| 1383 |
+
"loss": 1.3021,
|
| 1384 |
+
"step": 17700
|
| 1385 |
+
},
|
| 1386 |
+
{
|
| 1387 |
+
"epoch": 1.48,
|
| 1388 |
+
"grad_norm": 1.63645339012146,
|
| 1389 |
+
"learning_rate": 4.1383050847457626e-05,
|
| 1390 |
+
"loss": 1.3197,
|
| 1391 |
+
"step": 17800
|
| 1392 |
+
},
|
| 1393 |
+
{
|
| 1394 |
+
"epoch": 1.49,
|
| 1395 |
+
"grad_norm": 3.240687370300293,
|
| 1396 |
+
"learning_rate": 4.104406779661017e-05,
|
| 1397 |
+
"loss": 1.347,
|
| 1398 |
+
"step": 17900
|
| 1399 |
+
},
|
| 1400 |
+
{
|
| 1401 |
+
"epoch": 1.5,
|
| 1402 |
+
"grad_norm": 2.892014265060425,
|
| 1403 |
+
"learning_rate": 4.070508474576271e-05,
|
| 1404 |
+
"loss": 1.2844,
|
| 1405 |
+
"step": 18000
|
| 1406 |
+
},
|
| 1407 |
+
{
|
| 1408 |
+
"epoch": 1.5,
|
| 1409 |
+
"eval_loss": 1.3619292974472046,
|
| 1410 |
+
"eval_runtime": 92.9703,
|
| 1411 |
+
"eval_samples_per_second": 10.756,
|
| 1412 |
+
"eval_steps_per_second": 2.689,
|
| 1413 |
+
"step": 18000
|
| 1414 |
+
},
|
| 1415 |
+
{
|
| 1416 |
+
"epoch": 1.51,
|
| 1417 |
+
"grad_norm": 1.62366783618927,
|
| 1418 |
+
"learning_rate": 4.036949152542373e-05,
|
| 1419 |
+
"loss": 1.3391,
|
| 1420 |
+
"step": 18100
|
| 1421 |
+
},
|
| 1422 |
+
{
|
| 1423 |
+
"epoch": 1.52,
|
| 1424 |
+
"grad_norm": 3.9142508506774902,
|
| 1425 |
+
"learning_rate": 4.0030508474576275e-05,
|
| 1426 |
+
"loss": 1.2751,
|
| 1427 |
+
"step": 18200
|
| 1428 |
+
},
|
| 1429 |
+
{
|
| 1430 |
+
"epoch": 1.52,
|
| 1431 |
+
"grad_norm": 3.78511381149292,
|
| 1432 |
+
"learning_rate": 3.9691525423728814e-05,
|
| 1433 |
+
"loss": 1.3169,
|
| 1434 |
+
"step": 18300
|
| 1435 |
+
},
|
| 1436 |
+
{
|
| 1437 |
+
"epoch": 1.53,
|
| 1438 |
+
"grad_norm": 2.912883758544922,
|
| 1439 |
+
"learning_rate": 3.9352542372881354e-05,
|
| 1440 |
+
"loss": 1.3224,
|
| 1441 |
+
"step": 18400
|
| 1442 |
+
},
|
| 1443 |
+
{
|
| 1444 |
+
"epoch": 1.54,
|
| 1445 |
+
"grad_norm": 2.096040725708008,
|
| 1446 |
+
"learning_rate": 3.90135593220339e-05,
|
| 1447 |
+
"loss": 1.2708,
|
| 1448 |
+
"step": 18500
|
| 1449 |
+
},
|
| 1450 |
+
{
|
| 1451 |
+
"epoch": 1.55,
|
| 1452 |
+
"grad_norm": 5.406456470489502,
|
| 1453 |
+
"learning_rate": 3.867457627118644e-05,
|
| 1454 |
+
"loss": 1.3068,
|
| 1455 |
+
"step": 18600
|
| 1456 |
+
},
|
| 1457 |
+
{
|
| 1458 |
+
"epoch": 1.56,
|
| 1459 |
+
"grad_norm": 1.6677026748657227,
|
| 1460 |
+
"learning_rate": 3.8335593220338986e-05,
|
| 1461 |
+
"loss": 1.3202,
|
| 1462 |
+
"step": 18700
|
| 1463 |
+
},
|
| 1464 |
+
{
|
| 1465 |
+
"epoch": 1.57,
|
| 1466 |
+
"grad_norm": 2.0527544021606445,
|
| 1467 |
+
"learning_rate": 3.7996610169491525e-05,
|
| 1468 |
+
"loss": 1.2886,
|
| 1469 |
+
"step": 18800
|
| 1470 |
+
},
|
| 1471 |
+
{
|
| 1472 |
+
"epoch": 1.57,
|
| 1473 |
+
"grad_norm": 3.8199574947357178,
|
| 1474 |
+
"learning_rate": 3.7657627118644065e-05,
|
| 1475 |
+
"loss": 1.3367,
|
| 1476 |
+
"step": 18900
|
| 1477 |
+
},
|
| 1478 |
+
{
|
| 1479 |
+
"epoch": 1.58,
|
| 1480 |
+
"grad_norm": 2.5120060443878174,
|
| 1481 |
+
"learning_rate": 3.731864406779661e-05,
|
| 1482 |
+
"loss": 1.2945,
|
| 1483 |
+
"step": 19000
|
| 1484 |
+
},
|
| 1485 |
+
{
|
| 1486 |
+
"epoch": 1.58,
|
| 1487 |
+
"eval_loss": 1.3452004194259644,
|
| 1488 |
+
"eval_runtime": 93.0461,
|
| 1489 |
+
"eval_samples_per_second": 10.747,
|
| 1490 |
+
"eval_steps_per_second": 2.687,
|
| 1491 |
+
"step": 19000
|
| 1492 |
+
},
|
| 1493 |
+
{
|
| 1494 |
+
"epoch": 1.59,
|
| 1495 |
+
"grad_norm": 1.0111308097839355,
|
| 1496 |
+
"learning_rate": 3.697966101694915e-05,
|
| 1497 |
+
"loss": 1.3713,
|
| 1498 |
+
"step": 19100
|
| 1499 |
+
},
|
| 1500 |
+
{
|
| 1501 |
+
"epoch": 1.6,
|
| 1502 |
+
"grad_norm": 2.966914176940918,
|
| 1503 |
+
"learning_rate": 3.66406779661017e-05,
|
| 1504 |
+
"loss": 1.3124,
|
| 1505 |
+
"step": 19200
|
| 1506 |
+
},
|
| 1507 |
+
{
|
| 1508 |
+
"epoch": 1.61,
|
| 1509 |
+
"grad_norm": 4.211293697357178,
|
| 1510 |
+
"learning_rate": 3.630508474576271e-05,
|
| 1511 |
+
"loss": 1.3617,
|
| 1512 |
+
"step": 19300
|
| 1513 |
+
},
|
| 1514 |
+
{
|
| 1515 |
+
"epoch": 1.62,
|
| 1516 |
+
"grad_norm": 1.8540898561477661,
|
| 1517 |
+
"learning_rate": 3.596610169491525e-05,
|
| 1518 |
+
"loss": 1.3393,
|
| 1519 |
+
"step": 19400
|
| 1520 |
+
},
|
| 1521 |
+
{
|
| 1522 |
+
"epoch": 1.62,
|
| 1523 |
+
"grad_norm": 4.376151084899902,
|
| 1524 |
+
"learning_rate": 3.56271186440678e-05,
|
| 1525 |
+
"loss": 1.304,
|
| 1526 |
+
"step": 19500
|
| 1527 |
+
},
|
| 1528 |
+
{
|
| 1529 |
+
"epoch": 1.63,
|
| 1530 |
+
"grad_norm": 3.297484874725342,
|
| 1531 |
+
"learning_rate": 3.528813559322034e-05,
|
| 1532 |
+
"loss": 1.276,
|
| 1533 |
+
"step": 19600
|
| 1534 |
+
},
|
| 1535 |
+
{
|
| 1536 |
+
"epoch": 1.64,
|
| 1537 |
+
"grad_norm": 3.258236885070801,
|
| 1538 |
+
"learning_rate": 3.4949152542372885e-05,
|
| 1539 |
+
"loss": 1.3191,
|
| 1540 |
+
"step": 19700
|
| 1541 |
+
},
|
| 1542 |
+
{
|
| 1543 |
+
"epoch": 1.65,
|
| 1544 |
+
"grad_norm": 4.905130863189697,
|
| 1545 |
+
"learning_rate": 3.4610169491525425e-05,
|
| 1546 |
+
"loss": 1.3228,
|
| 1547 |
+
"step": 19800
|
| 1548 |
+
},
|
| 1549 |
+
{
|
| 1550 |
+
"epoch": 1.66,
|
| 1551 |
+
"grad_norm": 2.611107110977173,
|
| 1552 |
+
"learning_rate": 3.4271186440677964e-05,
|
| 1553 |
+
"loss": 1.2464,
|
| 1554 |
+
"step": 19900
|
| 1555 |
+
},
|
| 1556 |
+
{
|
| 1557 |
+
"epoch": 1.67,
|
| 1558 |
+
"grad_norm": 4.044171333312988,
|
| 1559 |
+
"learning_rate": 3.393220338983051e-05,
|
| 1560 |
+
"loss": 1.2852,
|
| 1561 |
+
"step": 20000
|
| 1562 |
+
},
|
| 1563 |
+
{
|
| 1564 |
+
"epoch": 1.67,
|
| 1565 |
+
"eval_loss": 1.322507619857788,
|
| 1566 |
+
"eval_runtime": 93.0207,
|
| 1567 |
+
"eval_samples_per_second": 10.75,
|
| 1568 |
+
"eval_steps_per_second": 2.688,
|
| 1569 |
+
"step": 20000
|
| 1570 |
+
},
|
| 1571 |
+
{
|
| 1572 |
+
"epoch": 1.68,
|
| 1573 |
+
"grad_norm": 2.803262710571289,
|
| 1574 |
+
"learning_rate": 3.359322033898305e-05,
|
| 1575 |
+
"loss": 1.32,
|
| 1576 |
+
"step": 20100
|
| 1577 |
+
},
|
| 1578 |
+
{
|
| 1579 |
+
"epoch": 1.68,
|
| 1580 |
+
"grad_norm": 1.6002579927444458,
|
| 1581 |
+
"learning_rate": 3.325423728813559e-05,
|
| 1582 |
+
"loss": 1.2831,
|
| 1583 |
+
"step": 20200
|
| 1584 |
+
},
|
| 1585 |
+
{
|
| 1586 |
+
"epoch": 1.69,
|
| 1587 |
+
"grad_norm": 5.442947864532471,
|
| 1588 |
+
"learning_rate": 3.2915254237288136e-05,
|
| 1589 |
+
"loss": 1.2849,
|
| 1590 |
+
"step": 20300
|
| 1591 |
+
},
|
| 1592 |
+
{
|
| 1593 |
+
"epoch": 1.7,
|
| 1594 |
+
"grad_norm": 3.7041471004486084,
|
| 1595 |
+
"learning_rate": 3.257627118644068e-05,
|
| 1596 |
+
"loss": 1.2846,
|
| 1597 |
+
"step": 20400
|
| 1598 |
+
},
|
| 1599 |
+
{
|
| 1600 |
+
"epoch": 1.71,
|
| 1601 |
+
"grad_norm": 4.188296794891357,
|
| 1602 |
+
"learning_rate": 3.223728813559322e-05,
|
| 1603 |
+
"loss": 1.3026,
|
| 1604 |
+
"step": 20500
|
| 1605 |
+
},
|
| 1606 |
+
{
|
| 1607 |
+
"epoch": 1.72,
|
| 1608 |
+
"grad_norm": 3.6854124069213867,
|
| 1609 |
+
"learning_rate": 3.189830508474577e-05,
|
| 1610 |
+
"loss": 1.2429,
|
| 1611 |
+
"step": 20600
|
| 1612 |
+
},
|
| 1613 |
+
{
|
| 1614 |
+
"epoch": 1.73,
|
| 1615 |
+
"grad_norm": 3.1174068450927734,
|
| 1616 |
+
"learning_rate": 3.155932203389831e-05,
|
| 1617 |
+
"loss": 1.2728,
|
| 1618 |
+
"step": 20700
|
| 1619 |
+
},
|
| 1620 |
+
{
|
| 1621 |
+
"epoch": 1.73,
|
| 1622 |
+
"grad_norm": 1.2928777933120728,
|
| 1623 |
+
"learning_rate": 3.1220338983050854e-05,
|
| 1624 |
+
"loss": 1.291,
|
| 1625 |
+
"step": 20800
|
| 1626 |
+
},
|
| 1627 |
+
{
|
| 1628 |
+
"epoch": 1.74,
|
| 1629 |
+
"grad_norm": 3.058570146560669,
|
| 1630 |
+
"learning_rate": 3.088135593220339e-05,
|
| 1631 |
+
"loss": 1.2786,
|
| 1632 |
+
"step": 20900
|
| 1633 |
+
},
|
| 1634 |
+
{
|
| 1635 |
+
"epoch": 1.75,
|
| 1636 |
+
"grad_norm": 3.311408042907715,
|
| 1637 |
+
"learning_rate": 3.054237288135593e-05,
|
| 1638 |
+
"loss": 1.2607,
|
| 1639 |
+
"step": 21000
|
| 1640 |
+
},
|
| 1641 |
+
{
|
| 1642 |
+
"epoch": 1.75,
|
| 1643 |
+
"eval_loss": 1.2871655225753784,
|
| 1644 |
+
"eval_runtime": 93.0004,
|
| 1645 |
+
"eval_samples_per_second": 10.753,
|
| 1646 |
+
"eval_steps_per_second": 2.688,
|
| 1647 |
+
"step": 21000
|
| 1648 |
+
},
|
| 1649 |
+
{
|
| 1650 |
+
"epoch": 1.76,
|
| 1651 |
+
"grad_norm": 3.0149199962615967,
|
| 1652 |
+
"learning_rate": 3.0203389830508476e-05,
|
| 1653 |
+
"loss": 1.2897,
|
| 1654 |
+
"step": 21100
|
| 1655 |
+
},
|
| 1656 |
+
{
|
| 1657 |
+
"epoch": 1.77,
|
| 1658 |
+
"grad_norm": 3.8012924194335938,
|
| 1659 |
+
"learning_rate": 2.986440677966102e-05,
|
| 1660 |
+
"loss": 1.3003,
|
| 1661 |
+
"step": 21200
|
| 1662 |
+
},
|
| 1663 |
+
{
|
| 1664 |
+
"epoch": 1.77,
|
| 1665 |
+
"grad_norm": 1.5058399438858032,
|
| 1666 |
+
"learning_rate": 2.952542372881356e-05,
|
| 1667 |
+
"loss": 1.245,
|
| 1668 |
+
"step": 21300
|
| 1669 |
+
},
|
| 1670 |
+
{
|
| 1671 |
+
"epoch": 1.78,
|
| 1672 |
+
"grad_norm": 5.085143089294434,
|
| 1673 |
+
"learning_rate": 2.9186440677966104e-05,
|
| 1674 |
+
"loss": 1.2702,
|
| 1675 |
+
"step": 21400
|
| 1676 |
+
},
|
| 1677 |
+
{
|
| 1678 |
+
"epoch": 1.79,
|
| 1679 |
+
"grad_norm": 1.6351230144500732,
|
| 1680 |
+
"learning_rate": 2.8847457627118647e-05,
|
| 1681 |
+
"loss": 1.28,
|
| 1682 |
+
"step": 21500
|
| 1683 |
+
},
|
| 1684 |
+
{
|
| 1685 |
+
"epoch": 1.8,
|
| 1686 |
+
"grad_norm": 3.3916802406311035,
|
| 1687 |
+
"learning_rate": 2.8508474576271187e-05,
|
| 1688 |
+
"loss": 1.2621,
|
| 1689 |
+
"step": 21600
|
| 1690 |
+
},
|
| 1691 |
+
{
|
| 1692 |
+
"epoch": 1.81,
|
| 1693 |
+
"grad_norm": 2.4449045658111572,
|
| 1694 |
+
"learning_rate": 2.816949152542373e-05,
|
| 1695 |
+
"loss": 1.2968,
|
| 1696 |
+
"step": 21700
|
| 1697 |
+
},
|
| 1698 |
+
{
|
| 1699 |
+
"epoch": 1.82,
|
| 1700 |
+
"grad_norm": 2.8779613971710205,
|
| 1701 |
+
"learning_rate": 2.7830508474576273e-05,
|
| 1702 |
+
"loss": 1.3546,
|
| 1703 |
+
"step": 21800
|
| 1704 |
+
},
|
| 1705 |
+
{
|
| 1706 |
+
"epoch": 1.82,
|
| 1707 |
+
"grad_norm": 1.7994945049285889,
|
| 1708 |
+
"learning_rate": 2.7491525423728816e-05,
|
| 1709 |
+
"loss": 1.2766,
|
| 1710 |
+
"step": 21900
|
| 1711 |
+
},
|
| 1712 |
+
{
|
| 1713 |
+
"epoch": 1.83,
|
| 1714 |
+
"grad_norm": 3.81644344329834,
|
| 1715 |
+
"learning_rate": 2.7152542372881355e-05,
|
| 1716 |
+
"loss": 1.2648,
|
| 1717 |
+
"step": 22000
|
| 1718 |
+
},
|
| 1719 |
+
{
|
| 1720 |
+
"epoch": 1.83,
|
| 1721 |
+
"eval_loss": 1.322618007659912,
|
| 1722 |
+
"eval_runtime": 92.9974,
|
| 1723 |
+
"eval_samples_per_second": 10.753,
|
| 1724 |
+
"eval_steps_per_second": 2.688,
|
| 1725 |
+
"step": 22000
|
| 1726 |
+
},
|
| 1727 |
+
{
|
| 1728 |
+
"epoch": 1.84,
|
| 1729 |
+
"grad_norm": 3.8521928787231445,
|
| 1730 |
+
"learning_rate": 2.6813559322033898e-05,
|
| 1731 |
+
"loss": 1.2689,
|
| 1732 |
+
"step": 22100
|
| 1733 |
+
},
|
| 1734 |
+
{
|
| 1735 |
+
"epoch": 1.85,
|
| 1736 |
+
"grad_norm": 3.50951886177063,
|
| 1737 |
+
"learning_rate": 2.647457627118644e-05,
|
| 1738 |
+
"loss": 1.3133,
|
| 1739 |
+
"step": 22200
|
| 1740 |
+
},
|
| 1741 |
+
{
|
| 1742 |
+
"epoch": 1.86,
|
| 1743 |
+
"grad_norm": 2.187098979949951,
|
| 1744 |
+
"learning_rate": 2.6135593220338984e-05,
|
| 1745 |
+
"loss": 1.2842,
|
| 1746 |
+
"step": 22300
|
| 1747 |
+
},
|
| 1748 |
+
{
|
| 1749 |
+
"epoch": 1.87,
|
| 1750 |
+
"grad_norm": 2.276773691177368,
|
| 1751 |
+
"learning_rate": 2.5796610169491527e-05,
|
| 1752 |
+
"loss": 1.252,
|
| 1753 |
+
"step": 22400
|
| 1754 |
+
},
|
| 1755 |
+
{
|
| 1756 |
+
"epoch": 1.88,
|
| 1757 |
+
"grad_norm": 1.8711966276168823,
|
| 1758 |
+
"learning_rate": 2.5457627118644066e-05,
|
| 1759 |
+
"loss": 1.2994,
|
| 1760 |
+
"step": 22500
|
| 1761 |
+
},
|
| 1762 |
+
{
|
| 1763 |
+
"epoch": 1.88,
|
| 1764 |
+
"grad_norm": 2.4090774059295654,
|
| 1765 |
+
"learning_rate": 2.511864406779661e-05,
|
| 1766 |
+
"loss": 1.2686,
|
| 1767 |
+
"step": 22600
|
| 1768 |
+
},
|
| 1769 |
+
{
|
| 1770 |
+
"epoch": 1.89,
|
| 1771 |
+
"grad_norm": 4.18037748336792,
|
| 1772 |
+
"learning_rate": 2.4779661016949156e-05,
|
| 1773 |
+
"loss": 1.318,
|
| 1774 |
+
"step": 22700
|
| 1775 |
+
},
|
| 1776 |
+
{
|
| 1777 |
+
"epoch": 1.9,
|
| 1778 |
+
"grad_norm": 3.396822452545166,
|
| 1779 |
+
"learning_rate": 2.4440677966101695e-05,
|
| 1780 |
+
"loss": 1.27,
|
| 1781 |
+
"step": 22800
|
| 1782 |
+
},
|
| 1783 |
+
{
|
| 1784 |
+
"epoch": 1.91,
|
| 1785 |
+
"grad_norm": 3.4309394359588623,
|
| 1786 |
+
"learning_rate": 2.4101694915254238e-05,
|
| 1787 |
+
"loss": 1.2888,
|
| 1788 |
+
"step": 22900
|
| 1789 |
+
},
|
| 1790 |
+
{
|
| 1791 |
+
"epoch": 1.92,
|
| 1792 |
+
"grad_norm": 1.140385627746582,
|
| 1793 |
+
"learning_rate": 2.376271186440678e-05,
|
| 1794 |
+
"loss": 1.2936,
|
| 1795 |
+
"step": 23000
|
| 1796 |
+
},
|
| 1797 |
+
{
|
| 1798 |
+
"epoch": 1.92,
|
| 1799 |
+
"eval_loss": 1.3380318880081177,
|
| 1800 |
+
"eval_runtime": 93.0298,
|
| 1801 |
+
"eval_samples_per_second": 10.749,
|
| 1802 |
+
"eval_steps_per_second": 2.687,
|
| 1803 |
+
"step": 23000
|
| 1804 |
+
},
|
| 1805 |
+
{
|
| 1806 |
+
"epoch": 1.93,
|
| 1807 |
+
"grad_norm": 1.4485564231872559,
|
| 1808 |
+
"learning_rate": 2.3423728813559324e-05,
|
| 1809 |
+
"loss": 1.2744,
|
| 1810 |
+
"step": 23100
|
| 1811 |
+
},
|
| 1812 |
+
{
|
| 1813 |
+
"epoch": 1.93,
|
| 1814 |
+
"grad_norm": 2.8173444271087646,
|
| 1815 |
+
"learning_rate": 2.3084745762711867e-05,
|
| 1816 |
+
"loss": 1.2774,
|
| 1817 |
+
"step": 23200
|
| 1818 |
+
},
|
| 1819 |
+
{
|
| 1820 |
+
"epoch": 1.94,
|
| 1821 |
+
"grad_norm": 2.9735991954803467,
|
| 1822 |
+
"learning_rate": 2.2745762711864406e-05,
|
| 1823 |
+
"loss": 1.3241,
|
| 1824 |
+
"step": 23300
|
| 1825 |
+
},
|
| 1826 |
+
{
|
| 1827 |
+
"epoch": 1.95,
|
| 1828 |
+
"grad_norm": 2.011720657348633,
|
| 1829 |
+
"learning_rate": 2.240677966101695e-05,
|
| 1830 |
+
"loss": 1.2912,
|
| 1831 |
+
"step": 23400
|
| 1832 |
+
},
|
| 1833 |
+
{
|
| 1834 |
+
"epoch": 1.96,
|
| 1835 |
+
"grad_norm": 2.2044718265533447,
|
| 1836 |
+
"learning_rate": 2.2067796610169492e-05,
|
| 1837 |
+
"loss": 1.2904,
|
| 1838 |
+
"step": 23500
|
| 1839 |
+
},
|
| 1840 |
+
{
|
| 1841 |
+
"epoch": 1.97,
|
| 1842 |
+
"grad_norm": 3.7060163021087646,
|
| 1843 |
+
"learning_rate": 2.1728813559322035e-05,
|
| 1844 |
+
"loss": 1.2289,
|
| 1845 |
+
"step": 23600
|
| 1846 |
+
},
|
| 1847 |
+
{
|
| 1848 |
+
"epoch": 1.98,
|
| 1849 |
+
"grad_norm": 4.124302864074707,
|
| 1850 |
+
"learning_rate": 2.1389830508474575e-05,
|
| 1851 |
+
"loss": 1.2544,
|
| 1852 |
+
"step": 23700
|
| 1853 |
+
},
|
| 1854 |
+
{
|
| 1855 |
+
"epoch": 1.98,
|
| 1856 |
+
"grad_norm": 3.379523992538452,
|
| 1857 |
+
"learning_rate": 2.105084745762712e-05,
|
| 1858 |
+
"loss": 1.2604,
|
| 1859 |
+
"step": 23800
|
| 1860 |
+
},
|
| 1861 |
+
{
|
| 1862 |
+
"epoch": 1.99,
|
| 1863 |
+
"grad_norm": 7.474296569824219,
|
| 1864 |
+
"learning_rate": 2.0711864406779664e-05,
|
| 1865 |
+
"loss": 1.274,
|
| 1866 |
+
"step": 23900
|
| 1867 |
+
},
|
| 1868 |
+
{
|
| 1869 |
+
"epoch": 2.0,
|
| 1870 |
+
"grad_norm": 5.122653007507324,
|
| 1871 |
+
"learning_rate": 2.0372881355932207e-05,
|
| 1872 |
+
"loss": 1.2985,
|
| 1873 |
+
"step": 24000
|
| 1874 |
+
},
|
| 1875 |
+
{
|
| 1876 |
+
"epoch": 2.0,
|
| 1877 |
+
"eval_loss": 1.274635910987854,
|
| 1878 |
+
"eval_runtime": 93.0906,
|
| 1879 |
+
"eval_samples_per_second": 10.742,
|
| 1880 |
+
"eval_steps_per_second": 2.686,
|
| 1881 |
+
"step": 24000
|
| 1882 |
+
},
|
| 1883 |
+
{
|
| 1884 |
+
"epoch": 2.01,
|
| 1885 |
+
"grad_norm": 2.563617467880249,
|
| 1886 |
+
"learning_rate": 2.0033898305084746e-05,
|
| 1887 |
+
"loss": 1.1996,
|
| 1888 |
+
"step": 24100
|
| 1889 |
+
},
|
| 1890 |
+
{
|
| 1891 |
+
"epoch": 2.02,
|
| 1892 |
+
"grad_norm": 3.481621265411377,
|
| 1893 |
+
"learning_rate": 1.969491525423729e-05,
|
| 1894 |
+
"loss": 1.2156,
|
| 1895 |
+
"step": 24200
|
| 1896 |
+
},
|
| 1897 |
+
{
|
| 1898 |
+
"epoch": 2.02,
|
| 1899 |
+
"grad_norm": 2.6262869834899902,
|
| 1900 |
+
"learning_rate": 1.9355932203389832e-05,
|
| 1901 |
+
"loss": 1.221,
|
| 1902 |
+
"step": 24300
|
| 1903 |
+
},
|
| 1904 |
+
{
|
| 1905 |
+
"epoch": 2.03,
|
| 1906 |
+
"grad_norm": 3.437523603439331,
|
| 1907 |
+
"learning_rate": 1.9016949152542375e-05,
|
| 1908 |
+
"loss": 1.1814,
|
| 1909 |
+
"step": 24400
|
| 1910 |
+
},
|
| 1911 |
+
{
|
| 1912 |
+
"epoch": 2.04,
|
| 1913 |
+
"grad_norm": 4.948596477508545,
|
| 1914 |
+
"learning_rate": 1.8677966101694915e-05,
|
| 1915 |
+
"loss": 1.1972,
|
| 1916 |
+
"step": 24500
|
| 1917 |
+
},
|
| 1918 |
+
{
|
| 1919 |
+
"epoch": 2.05,
|
| 1920 |
+
"grad_norm": 3.0667967796325684,
|
| 1921 |
+
"learning_rate": 1.8338983050847458e-05,
|
| 1922 |
+
"loss": 1.2229,
|
| 1923 |
+
"step": 24600
|
| 1924 |
+
},
|
| 1925 |
+
{
|
| 1926 |
+
"epoch": 2.06,
|
| 1927 |
+
"grad_norm": 2.1678037643432617,
|
| 1928 |
+
"learning_rate": 1.8e-05,
|
| 1929 |
+
"loss": 1.182,
|
| 1930 |
+
"step": 24700
|
| 1931 |
+
},
|
| 1932 |
+
{
|
| 1933 |
+
"epoch": 2.07,
|
| 1934 |
+
"grad_norm": 2.7943167686462402,
|
| 1935 |
+
"learning_rate": 1.7661016949152543e-05,
|
| 1936 |
+
"loss": 1.1889,
|
| 1937 |
+
"step": 24800
|
| 1938 |
+
},
|
| 1939 |
+
{
|
| 1940 |
+
"epoch": 2.08,
|
| 1941 |
+
"grad_norm": 1.5044032335281372,
|
| 1942 |
+
"learning_rate": 1.7322033898305083e-05,
|
| 1943 |
+
"loss": 1.1796,
|
| 1944 |
+
"step": 24900
|
| 1945 |
+
},
|
| 1946 |
+
{
|
| 1947 |
+
"epoch": 2.08,
|
| 1948 |
+
"grad_norm": 3.931037425994873,
|
| 1949 |
+
"learning_rate": 1.6983050847457626e-05,
|
| 1950 |
+
"loss": 1.2159,
|
| 1951 |
+
"step": 25000
|
| 1952 |
+
},
|
| 1953 |
+
{
|
| 1954 |
+
"epoch": 2.08,
|
| 1955 |
+
"eval_loss": 1.33604097366333,
|
| 1956 |
+
"eval_runtime": 93.1418,
|
| 1957 |
+
"eval_samples_per_second": 10.736,
|
| 1958 |
+
"eval_steps_per_second": 2.684,
|
| 1959 |
+
"step": 25000
|
| 1960 |
+
},
|
| 1961 |
+
{
|
| 1962 |
+
"epoch": 2.09,
|
| 1963 |
+
"grad_norm": 5.764918804168701,
|
| 1964 |
+
"learning_rate": 1.6644067796610172e-05,
|
| 1965 |
+
"loss": 1.1995,
|
| 1966 |
+
"step": 25100
|
| 1967 |
+
},
|
| 1968 |
+
{
|
| 1969 |
+
"epoch": 2.1,
|
| 1970 |
+
"grad_norm": 2.17740535736084,
|
| 1971 |
+
"learning_rate": 1.6305084745762715e-05,
|
| 1972 |
+
"loss": 1.1873,
|
| 1973 |
+
"step": 25200
|
| 1974 |
+
},
|
| 1975 |
+
{
|
| 1976 |
+
"epoch": 2.11,
|
| 1977 |
+
"grad_norm": 3.145355224609375,
|
| 1978 |
+
"learning_rate": 1.5966101694915255e-05,
|
| 1979 |
+
"loss": 1.2101,
|
| 1980 |
+
"step": 25300
|
| 1981 |
+
},
|
| 1982 |
+
{
|
| 1983 |
+
"epoch": 2.12,
|
| 1984 |
+
"grad_norm": 5.353292942047119,
|
| 1985 |
+
"learning_rate": 1.563050847457627e-05,
|
| 1986 |
+
"loss": 1.2076,
|
| 1987 |
+
"step": 25400
|
| 1988 |
+
},
|
| 1989 |
+
{
|
| 1990 |
+
"epoch": 2.12,
|
| 1991 |
+
"grad_norm": 2.399566411972046,
|
| 1992 |
+
"learning_rate": 1.5291525423728814e-05,
|
| 1993 |
+
"loss": 1.2099,
|
| 1994 |
+
"step": 25500
|
| 1995 |
+
},
|
| 1996 |
+
{
|
| 1997 |
+
"epoch": 2.13,
|
| 1998 |
+
"grad_norm": 3.8052713871002197,
|
| 1999 |
+
"learning_rate": 1.4952542372881357e-05,
|
| 2000 |
+
"loss": 1.1932,
|
| 2001 |
+
"step": 25600
|
| 2002 |
+
},
|
| 2003 |
+
{
|
| 2004 |
+
"epoch": 2.14,
|
| 2005 |
+
"grad_norm": 4.528957843780518,
|
| 2006 |
+
"learning_rate": 1.4613559322033898e-05,
|
| 2007 |
+
"loss": 1.1838,
|
| 2008 |
+
"step": 25700
|
| 2009 |
+
},
|
| 2010 |
+
{
|
| 2011 |
+
"epoch": 2.15,
|
| 2012 |
+
"grad_norm": 3.597487449645996,
|
| 2013 |
+
"learning_rate": 1.4274576271186441e-05,
|
| 2014 |
+
"loss": 1.187,
|
| 2015 |
+
"step": 25800
|
| 2016 |
+
},
|
| 2017 |
+
{
|
| 2018 |
+
"epoch": 2.16,
|
| 2019 |
+
"grad_norm": 3.2705302238464355,
|
| 2020 |
+
"learning_rate": 1.3935593220338982e-05,
|
| 2021 |
+
"loss": 1.1829,
|
| 2022 |
+
"step": 25900
|
| 2023 |
+
},
|
| 2024 |
+
{
|
| 2025 |
+
"epoch": 2.17,
|
| 2026 |
+
"grad_norm": 3.251126289367676,
|
| 2027 |
+
"learning_rate": 1.3596610169491525e-05,
|
| 2028 |
+
"loss": 1.1888,
|
| 2029 |
+
"step": 26000
|
| 2030 |
+
},
|
| 2031 |
+
{
|
| 2032 |
+
"epoch": 2.17,
|
| 2033 |
+
"eval_loss": 1.3534026145935059,
|
| 2034 |
+
"eval_runtime": 93.1511,
|
| 2035 |
+
"eval_samples_per_second": 10.735,
|
| 2036 |
+
"eval_steps_per_second": 2.684,
|
| 2037 |
+
"step": 26000
|
| 2038 |
+
},
|
| 2039 |
+
{
|
| 2040 |
+
"epoch": 2.17,
|
| 2041 |
+
"grad_norm": 3.9193084239959717,
|
| 2042 |
+
"learning_rate": 1.325762711864407e-05,
|
| 2043 |
+
"loss": 1.2176,
|
| 2044 |
+
"step": 26100
|
| 2045 |
+
},
|
| 2046 |
+
{
|
| 2047 |
+
"epoch": 2.18,
|
| 2048 |
+
"grad_norm": 1.7747070789337158,
|
| 2049 |
+
"learning_rate": 1.2918644067796613e-05,
|
| 2050 |
+
"loss": 1.1845,
|
| 2051 |
+
"step": 26200
|
| 2052 |
+
},
|
| 2053 |
+
{
|
| 2054 |
+
"epoch": 2.19,
|
| 2055 |
+
"grad_norm": 1.7094638347625732,
|
| 2056 |
+
"learning_rate": 1.2579661016949154e-05,
|
| 2057 |
+
"loss": 1.2025,
|
| 2058 |
+
"step": 26300
|
| 2059 |
+
},
|
| 2060 |
+
{
|
| 2061 |
+
"epoch": 2.2,
|
| 2062 |
+
"grad_norm": 4.238964557647705,
|
| 2063 |
+
"learning_rate": 1.2240677966101695e-05,
|
| 2064 |
+
"loss": 1.1665,
|
| 2065 |
+
"step": 26400
|
| 2066 |
+
},
|
| 2067 |
+
{
|
| 2068 |
+
"epoch": 2.21,
|
| 2069 |
+
"grad_norm": 1.669313669204712,
|
| 2070 |
+
"learning_rate": 1.1901694915254238e-05,
|
| 2071 |
+
"loss": 1.1792,
|
| 2072 |
+
"step": 26500
|
| 2073 |
+
},
|
| 2074 |
+
{
|
| 2075 |
+
"epoch": 2.22,
|
| 2076 |
+
"grad_norm": 8.226383209228516,
|
| 2077 |
+
"learning_rate": 1.1562711864406781e-05,
|
| 2078 |
+
"loss": 1.1591,
|
| 2079 |
+
"step": 26600
|
| 2080 |
+
},
|
| 2081 |
+
{
|
| 2082 |
+
"epoch": 2.23,
|
| 2083 |
+
"grad_norm": 3.0040552616119385,
|
| 2084 |
+
"learning_rate": 1.1223728813559322e-05,
|
| 2085 |
+
"loss": 1.2112,
|
| 2086 |
+
"step": 26700
|
| 2087 |
+
},
|
| 2088 |
+
{
|
| 2089 |
+
"epoch": 2.23,
|
| 2090 |
+
"grad_norm": 1.9113960266113281,
|
| 2091 |
+
"learning_rate": 1.0884745762711865e-05,
|
| 2092 |
+
"loss": 1.164,
|
| 2093 |
+
"step": 26800
|
| 2094 |
+
},
|
| 2095 |
+
{
|
| 2096 |
+
"epoch": 2.24,
|
| 2097 |
+
"grad_norm": 2.2811169624328613,
|
| 2098 |
+
"learning_rate": 1.0545762711864406e-05,
|
| 2099 |
+
"loss": 1.1807,
|
| 2100 |
+
"step": 26900
|
| 2101 |
+
},
|
| 2102 |
+
{
|
| 2103 |
+
"epoch": 2.25,
|
| 2104 |
+
"grad_norm": 3.2554876804351807,
|
| 2105 |
+
"learning_rate": 1.020677966101695e-05,
|
| 2106 |
+
"loss": 1.2362,
|
| 2107 |
+
"step": 27000
|
| 2108 |
+
},
|
| 2109 |
+
{
|
| 2110 |
+
"epoch": 2.25,
|
| 2111 |
+
"eval_loss": 1.315274715423584,
|
| 2112 |
+
"eval_runtime": 93.1384,
|
| 2113 |
+
"eval_samples_per_second": 10.737,
|
| 2114 |
+
"eval_steps_per_second": 2.684,
|
| 2115 |
+
"step": 27000
|
| 2116 |
+
},
|
| 2117 |
+
{
|
| 2118 |
+
"epoch": 2.26,
|
| 2119 |
+
"grad_norm": 3.656125545501709,
|
| 2120 |
+
"learning_rate": 9.867796610169492e-06,
|
| 2121 |
+
"loss": 1.1712,
|
| 2122 |
+
"step": 27100
|
| 2123 |
+
},
|
| 2124 |
+
{
|
| 2125 |
+
"epoch": 2.27,
|
| 2126 |
+
"grad_norm": 4.444190502166748,
|
| 2127 |
+
"learning_rate": 9.528813559322035e-06,
|
| 2128 |
+
"loss": 1.2532,
|
| 2129 |
+
"step": 27200
|
| 2130 |
+
},
|
| 2131 |
+
{
|
| 2132 |
+
"epoch": 2.27,
|
| 2133 |
+
"grad_norm": 5.304549217224121,
|
| 2134 |
+
"learning_rate": 9.189830508474576e-06,
|
| 2135 |
+
"loss": 1.1848,
|
| 2136 |
+
"step": 27300
|
| 2137 |
+
},
|
| 2138 |
+
{
|
| 2139 |
+
"epoch": 2.28,
|
| 2140 |
+
"grad_norm": 4.003425121307373,
|
| 2141 |
+
"learning_rate": 8.85084745762712e-06,
|
| 2142 |
+
"loss": 1.1601,
|
| 2143 |
+
"step": 27400
|
| 2144 |
+
},
|
| 2145 |
+
{
|
| 2146 |
+
"epoch": 2.29,
|
| 2147 |
+
"grad_norm": 4.701766490936279,
|
| 2148 |
+
"learning_rate": 8.511864406779662e-06,
|
| 2149 |
+
"loss": 1.1682,
|
| 2150 |
+
"step": 27500
|
| 2151 |
+
},
|
| 2152 |
+
{
|
| 2153 |
+
"epoch": 2.3,
|
| 2154 |
+
"grad_norm": 4.16826057434082,
|
| 2155 |
+
"learning_rate": 8.172881355932203e-06,
|
| 2156 |
+
"loss": 1.1806,
|
| 2157 |
+
"step": 27600
|
| 2158 |
+
},
|
| 2159 |
+
{
|
| 2160 |
+
"epoch": 2.31,
|
| 2161 |
+
"grad_norm": 3.569227695465088,
|
| 2162 |
+
"learning_rate": 7.833898305084746e-06,
|
| 2163 |
+
"loss": 1.1295,
|
| 2164 |
+
"step": 27700
|
| 2165 |
+
},
|
| 2166 |
+
{
|
| 2167 |
+
"epoch": 2.32,
|
| 2168 |
+
"grad_norm": 6.8756890296936035,
|
| 2169 |
+
"learning_rate": 7.494915254237289e-06,
|
| 2170 |
+
"loss": 1.1863,
|
| 2171 |
+
"step": 27800
|
| 2172 |
+
},
|
| 2173 |
+
{
|
| 2174 |
+
"epoch": 2.33,
|
| 2175 |
+
"grad_norm": 4.841982364654541,
|
| 2176 |
+
"learning_rate": 7.155932203389831e-06,
|
| 2177 |
+
"loss": 1.1651,
|
| 2178 |
+
"step": 27900
|
| 2179 |
+
},
|
| 2180 |
+
{
|
| 2181 |
+
"epoch": 2.33,
|
| 2182 |
+
"grad_norm": 6.766154766082764,
|
| 2183 |
+
"learning_rate": 6.816949152542373e-06,
|
| 2184 |
+
"loss": 1.1831,
|
| 2185 |
+
"step": 28000
|
| 2186 |
+
},
|
| 2187 |
+
{
|
| 2188 |
+
"epoch": 2.33,
|
| 2189 |
+
"eval_loss": 1.3225314617156982,
|
| 2190 |
+
"eval_runtime": 93.1704,
|
| 2191 |
+
"eval_samples_per_second": 10.733,
|
| 2192 |
+
"eval_steps_per_second": 2.683,
|
| 2193 |
+
"step": 28000
|
| 2194 |
+
},
|
| 2195 |
+
{
|
| 2196 |
+
"epoch": 2.34,
|
| 2197 |
+
"grad_norm": 4.122812747955322,
|
| 2198 |
+
"learning_rate": 6.477966101694915e-06,
|
| 2199 |
+
"loss": 1.1934,
|
| 2200 |
+
"step": 28100
|
| 2201 |
+
},
|
| 2202 |
+
{
|
| 2203 |
+
"epoch": 2.35,
|
| 2204 |
+
"grad_norm": 2.2169628143310547,
|
| 2205 |
+
"learning_rate": 6.1389830508474575e-06,
|
| 2206 |
+
"loss": 1.1044,
|
| 2207 |
+
"step": 28200
|
| 2208 |
+
},
|
| 2209 |
+
{
|
| 2210 |
+
"epoch": 2.36,
|
| 2211 |
+
"grad_norm": 3.0423035621643066,
|
| 2212 |
+
"learning_rate": 5.8e-06,
|
| 2213 |
+
"loss": 1.1876,
|
| 2214 |
+
"step": 28300
|
| 2215 |
+
},
|
| 2216 |
+
{
|
| 2217 |
+
"epoch": 2.37,
|
| 2218 |
+
"grad_norm": 3.517133951187134,
|
| 2219 |
+
"learning_rate": 5.4610169491525424e-06,
|
| 2220 |
+
"loss": 1.2411,
|
| 2221 |
+
"step": 28400
|
| 2222 |
+
},
|
| 2223 |
+
{
|
| 2224 |
+
"epoch": 2.38,
|
| 2225 |
+
"grad_norm": 3.3230624198913574,
|
| 2226 |
+
"learning_rate": 5.1220338983050845e-06,
|
| 2227 |
+
"loss": 1.189,
|
| 2228 |
+
"step": 28500
|
| 2229 |
+
},
|
| 2230 |
+
{
|
| 2231 |
+
"epoch": 2.38,
|
| 2232 |
+
"grad_norm": 5.101288795471191,
|
| 2233 |
+
"learning_rate": 4.7830508474576274e-06,
|
| 2234 |
+
"loss": 1.1435,
|
| 2235 |
+
"step": 28600
|
| 2236 |
+
},
|
| 2237 |
+
{
|
| 2238 |
+
"epoch": 2.39,
|
| 2239 |
+
"grad_norm": 3.061377763748169,
|
| 2240 |
+
"learning_rate": 4.4440677966101695e-06,
|
| 2241 |
+
"loss": 1.1902,
|
| 2242 |
+
"step": 28700
|
| 2243 |
+
},
|
| 2244 |
+
{
|
| 2245 |
+
"epoch": 2.4,
|
| 2246 |
+
"grad_norm": 3.9341752529144287,
|
| 2247 |
+
"learning_rate": 4.1050847457627124e-06,
|
| 2248 |
+
"loss": 1.22,
|
| 2249 |
+
"step": 28800
|
| 2250 |
+
},
|
| 2251 |
+
{
|
| 2252 |
+
"epoch": 2.41,
|
| 2253 |
+
"grad_norm": 3.691490888595581,
|
| 2254 |
+
"learning_rate": 3.766101694915254e-06,
|
| 2255 |
+
"loss": 1.2105,
|
| 2256 |
+
"step": 28900
|
| 2257 |
+
},
|
| 2258 |
+
{
|
| 2259 |
+
"epoch": 2.42,
|
| 2260 |
+
"grad_norm": 3.67085599899292,
|
| 2261 |
+
"learning_rate": 3.427118644067797e-06,
|
| 2262 |
+
"loss": 1.1909,
|
| 2263 |
+
"step": 29000
|
| 2264 |
+
},
|
| 2265 |
+
{
|
| 2266 |
+
"epoch": 2.42,
|
| 2267 |
+
"eval_loss": 1.294958472251892,
|
| 2268 |
+
"eval_runtime": 93.09,
|
| 2269 |
+
"eval_samples_per_second": 10.742,
|
| 2270 |
+
"eval_steps_per_second": 2.686,
|
| 2271 |
+
"step": 29000
|
| 2272 |
+
},
|
| 2273 |
+
{
|
| 2274 |
+
"epoch": 2.42,
|
| 2275 |
+
"grad_norm": 4.373409748077393,
|
| 2276 |
+
"learning_rate": 3.088135593220339e-06,
|
| 2277 |
+
"loss": 1.2423,
|
| 2278 |
+
"step": 29100
|
| 2279 |
+
},
|
| 2280 |
+
{
|
| 2281 |
+
"epoch": 2.43,
|
| 2282 |
+
"grad_norm": 4.1964006423950195,
|
| 2283 |
+
"learning_rate": 2.7491525423728816e-06,
|
| 2284 |
+
"loss": 1.1482,
|
| 2285 |
+
"step": 29200
|
| 2286 |
+
},
|
| 2287 |
+
{
|
| 2288 |
+
"epoch": 2.44,
|
| 2289 |
+
"grad_norm": 4.233890056610107,
|
| 2290 |
+
"learning_rate": 2.4135593220338984e-06,
|
| 2291 |
+
"loss": 1.1824,
|
| 2292 |
+
"step": 29300
|
| 2293 |
+
},
|
| 2294 |
+
{
|
| 2295 |
+
"epoch": 2.45,
|
| 2296 |
+
"grad_norm": 3.9279072284698486,
|
| 2297 |
+
"learning_rate": 2.0745762711864404e-06,
|
| 2298 |
+
"loss": 1.1466,
|
| 2299 |
+
"step": 29400
|
| 2300 |
+
},
|
| 2301 |
+
{
|
| 2302 |
+
"epoch": 2.46,
|
| 2303 |
+
"grad_norm": 3.39454984664917,
|
| 2304 |
+
"learning_rate": 1.7355932203389831e-06,
|
| 2305 |
+
"loss": 1.1302,
|
| 2306 |
+
"step": 29500
|
| 2307 |
+
},
|
| 2308 |
+
{
|
| 2309 |
+
"epoch": 2.47,
|
| 2310 |
+
"grad_norm": 1.3635748624801636,
|
| 2311 |
+
"learning_rate": 1.3966101694915254e-06,
|
| 2312 |
+
"loss": 1.214,
|
| 2313 |
+
"step": 29600
|
| 2314 |
+
},
|
| 2315 |
+
{
|
| 2316 |
+
"epoch": 2.48,
|
| 2317 |
+
"grad_norm": 3.5587875843048096,
|
| 2318 |
+
"learning_rate": 1.057627118644068e-06,
|
| 2319 |
+
"loss": 1.1981,
|
| 2320 |
+
"step": 29700
|
| 2321 |
+
},
|
| 2322 |
+
{
|
| 2323 |
+
"epoch": 2.48,
|
| 2324 |
+
"grad_norm": 7.449352741241455,
|
| 2325 |
+
"learning_rate": 7.186440677966102e-07,
|
| 2326 |
+
"loss": 1.1196,
|
| 2327 |
+
"step": 29800
|
| 2328 |
+
},
|
| 2329 |
+
{
|
| 2330 |
+
"epoch": 2.49,
|
| 2331 |
+
"grad_norm": 2.7902631759643555,
|
| 2332 |
+
"learning_rate": 3.796610169491526e-07,
|
| 2333 |
+
"loss": 1.1452,
|
| 2334 |
+
"step": 29900
|
| 2335 |
+
},
|
| 2336 |
+
{
|
| 2337 |
+
"epoch": 2.5,
|
| 2338 |
+
"grad_norm": 4.423699855804443,
|
| 2339 |
+
"learning_rate": 4.067796610169492e-08,
|
| 2340 |
+
"loss": 1.197,
|
| 2341 |
+
"step": 30000
|
| 2342 |
+
},
|
| 2343 |
+
{
|
| 2344 |
+
"epoch": 2.5,
|
| 2345 |
+
"eval_loss": 1.2965623140335083,
|
| 2346 |
+
"eval_runtime": 93.1115,
|
| 2347 |
+
"eval_samples_per_second": 10.74,
|
| 2348 |
+
"eval_steps_per_second": 2.685,
|
| 2349 |
+
"step": 30000
|
| 2350 |
+
}
|
| 2351 |
+
],
|
| 2352 |
+
"logging_steps": 100,
|
| 2353 |
+
"max_steps": 30000,
|
| 2354 |
+
"num_input_tokens_seen": 0,
|
| 2355 |
+
"num_train_epochs": 3,
|
| 2356 |
+
"save_steps": 2000,
|
| 2357 |
+
"total_flos": 4.8306377981952e+17,
|
| 2358 |
+
"train_batch_size": 4,
|
| 2359 |
+
"trial_name": null,
|
| 2360 |
+
"trial_params": null
|
| 2361 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a2b88ba55a2975145e701c8ea2dfa9c2fa18c0f92e0e08a2c67c81e0266309c6
|
| 3 |
+
size 4856
|