Uploaded checkpoint-2000
Browse files- README.md +202 -0
- adapter_config.json +32 -0
- adapter_model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +1429 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
base_model: deepseek-ai/deepseek-math-7b-base
|
| 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 0.8.2
|
adapter_config.json
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "deepseek-ai/deepseek-math-7b-base",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": false,
|
| 7 |
+
"inference_mode": true,
|
| 8 |
+
"init_lora_weights": true,
|
| 9 |
+
"layers_pattern": null,
|
| 10 |
+
"layers_to_transform": null,
|
| 11 |
+
"loftq_config": {},
|
| 12 |
+
"lora_alpha": 256,
|
| 13 |
+
"lora_dropout": 0.05,
|
| 14 |
+
"megatron_config": null,
|
| 15 |
+
"megatron_core": "megatron.core",
|
| 16 |
+
"modules_to_save": null,
|
| 17 |
+
"peft_type": "LORA",
|
| 18 |
+
"r": 64,
|
| 19 |
+
"rank_pattern": {},
|
| 20 |
+
"revision": null,
|
| 21 |
+
"target_modules": [
|
| 22 |
+
"v_proj",
|
| 23 |
+
"gate_proj",
|
| 24 |
+
"k_proj",
|
| 25 |
+
"up_proj",
|
| 26 |
+
"down_proj",
|
| 27 |
+
"q_proj",
|
| 28 |
+
"o_proj"
|
| 29 |
+
],
|
| 30 |
+
"task_type": "CAUSAL_LM",
|
| 31 |
+
"use_rslora": false
|
| 32 |
+
}
|
adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3fc84fbf25ac76d7b9b75983a2801ba61ab7ce3e755053305d64f316e3765fa4
|
| 3 |
+
size 599711112
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a29686604d61421e134f450bca6c5bb3c131667f74728803abff994f0af84a35
|
| 3 |
+
size 1199663358
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ff528cb904c36dcf8dac179ac6596cbc3bbfe192a3bdc72561d10c550beb1cab
|
| 3 |
+
size 14244
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b829f4c11b736250778f8cbf3c5bcf2fa8fa98a9bd9614ac59755d87cc3c5aea
|
| 3 |
+
size 1064
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1429 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.7172314864622557,
|
| 5 |
+
"eval_steps": 2000,
|
| 6 |
+
"global_step": 2000,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.0,
|
| 13 |
+
"grad_norm": 0.9492120146751404,
|
| 14 |
+
"learning_rate": 1.0000000000000002e-06,
|
| 15 |
+
"loss": 0.9769,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.01,
|
| 20 |
+
"grad_norm": 1.344916582107544,
|
| 21 |
+
"learning_rate": 2.0000000000000003e-06,
|
| 22 |
+
"loss": 1.0718,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.01,
|
| 27 |
+
"grad_norm": 0.6680417060852051,
|
| 28 |
+
"learning_rate": 3e-06,
|
| 29 |
+
"loss": 0.8901,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.01,
|
| 34 |
+
"grad_norm": 0.8369797468185425,
|
| 35 |
+
"learning_rate": 4.000000000000001e-06,
|
| 36 |
+
"loss": 0.9398,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.02,
|
| 41 |
+
"grad_norm": 0.5738756656646729,
|
| 42 |
+
"learning_rate": 5e-06,
|
| 43 |
+
"loss": 0.9152,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.02,
|
| 48 |
+
"grad_norm": 1.028475284576416,
|
| 49 |
+
"learning_rate": 6e-06,
|
| 50 |
+
"loss": 0.849,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.03,
|
| 55 |
+
"grad_norm": 1.2893372774124146,
|
| 56 |
+
"learning_rate": 7e-06,
|
| 57 |
+
"loss": 0.7312,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.03,
|
| 62 |
+
"grad_norm": 0.8779547810554504,
|
| 63 |
+
"learning_rate": 8.000000000000001e-06,
|
| 64 |
+
"loss": 0.6707,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.03,
|
| 69 |
+
"grad_norm": 0.8972748517990112,
|
| 70 |
+
"learning_rate": 9e-06,
|
| 71 |
+
"loss": 0.6413,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.04,
|
| 76 |
+
"grad_norm": 1.505399227142334,
|
| 77 |
+
"learning_rate": 1e-05,
|
| 78 |
+
"loss": 0.6129,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.04,
|
| 83 |
+
"grad_norm": 0.6442121267318726,
|
| 84 |
+
"learning_rate": 9.989898989898991e-06,
|
| 85 |
+
"loss": 0.5579,
|
| 86 |
+
"step": 110
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.04,
|
| 90 |
+
"grad_norm": 0.623290479183197,
|
| 91 |
+
"learning_rate": 9.97979797979798e-06,
|
| 92 |
+
"loss": 0.6022,
|
| 93 |
+
"step": 120
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.05,
|
| 97 |
+
"grad_norm": 0.7216657996177673,
|
| 98 |
+
"learning_rate": 9.96969696969697e-06,
|
| 99 |
+
"loss": 0.5481,
|
| 100 |
+
"step": 130
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.05,
|
| 104 |
+
"grad_norm": 0.7031328678131104,
|
| 105 |
+
"learning_rate": 9.95959595959596e-06,
|
| 106 |
+
"loss": 0.5594,
|
| 107 |
+
"step": 140
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.05,
|
| 111 |
+
"grad_norm": 0.7411965727806091,
|
| 112 |
+
"learning_rate": 9.94949494949495e-06,
|
| 113 |
+
"loss": 0.6241,
|
| 114 |
+
"step": 150
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.06,
|
| 118 |
+
"grad_norm": 0.8735277652740479,
|
| 119 |
+
"learning_rate": 9.939393939393939e-06,
|
| 120 |
+
"loss": 0.498,
|
| 121 |
+
"step": 160
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.06,
|
| 125 |
+
"grad_norm": 1.1062073707580566,
|
| 126 |
+
"learning_rate": 9.92929292929293e-06,
|
| 127 |
+
"loss": 0.6463,
|
| 128 |
+
"step": 170
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.06,
|
| 132 |
+
"grad_norm": 0.7930333614349365,
|
| 133 |
+
"learning_rate": 9.91919191919192e-06,
|
| 134 |
+
"loss": 0.6231,
|
| 135 |
+
"step": 180
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.07,
|
| 139 |
+
"grad_norm": 0.8774802684783936,
|
| 140 |
+
"learning_rate": 9.90909090909091e-06,
|
| 141 |
+
"loss": 0.5895,
|
| 142 |
+
"step": 190
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.07,
|
| 146 |
+
"grad_norm": 0.929542064666748,
|
| 147 |
+
"learning_rate": 9.8989898989899e-06,
|
| 148 |
+
"loss": 0.632,
|
| 149 |
+
"step": 200
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.08,
|
| 153 |
+
"grad_norm": 0.6024735569953918,
|
| 154 |
+
"learning_rate": 9.88888888888889e-06,
|
| 155 |
+
"loss": 0.5682,
|
| 156 |
+
"step": 210
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.08,
|
| 160 |
+
"grad_norm": 0.5887441635131836,
|
| 161 |
+
"learning_rate": 9.87878787878788e-06,
|
| 162 |
+
"loss": 0.5192,
|
| 163 |
+
"step": 220
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.08,
|
| 167 |
+
"grad_norm": 0.7813496589660645,
|
| 168 |
+
"learning_rate": 9.86868686868687e-06,
|
| 169 |
+
"loss": 0.5841,
|
| 170 |
+
"step": 230
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.09,
|
| 174 |
+
"grad_norm": 0.5949407815933228,
|
| 175 |
+
"learning_rate": 9.85858585858586e-06,
|
| 176 |
+
"loss": 0.5263,
|
| 177 |
+
"step": 240
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.09,
|
| 181 |
+
"grad_norm": 0.8114556670188904,
|
| 182 |
+
"learning_rate": 9.84848484848485e-06,
|
| 183 |
+
"loss": 0.5513,
|
| 184 |
+
"step": 250
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.09,
|
| 188 |
+
"grad_norm": 0.7692855596542358,
|
| 189 |
+
"learning_rate": 9.838383838383839e-06,
|
| 190 |
+
"loss": 0.5217,
|
| 191 |
+
"step": 260
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.1,
|
| 195 |
+
"grad_norm": 0.8319826126098633,
|
| 196 |
+
"learning_rate": 9.828282828282829e-06,
|
| 197 |
+
"loss": 0.4386,
|
| 198 |
+
"step": 270
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.1,
|
| 202 |
+
"grad_norm": 0.6725042462348938,
|
| 203 |
+
"learning_rate": 9.81818181818182e-06,
|
| 204 |
+
"loss": 0.4919,
|
| 205 |
+
"step": 280
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.1,
|
| 209 |
+
"grad_norm": 0.779315173625946,
|
| 210 |
+
"learning_rate": 9.80808080808081e-06,
|
| 211 |
+
"loss": 0.5281,
|
| 212 |
+
"step": 290
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.11,
|
| 216 |
+
"grad_norm": 0.8005223274230957,
|
| 217 |
+
"learning_rate": 9.797979797979798e-06,
|
| 218 |
+
"loss": 0.5206,
|
| 219 |
+
"step": 300
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.11,
|
| 223 |
+
"grad_norm": 0.6395801901817322,
|
| 224 |
+
"learning_rate": 9.787878787878788e-06,
|
| 225 |
+
"loss": 0.474,
|
| 226 |
+
"step": 310
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.11,
|
| 230 |
+
"grad_norm": 1.1016992330551147,
|
| 231 |
+
"learning_rate": 9.777777777777779e-06,
|
| 232 |
+
"loss": 0.5403,
|
| 233 |
+
"step": 320
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.12,
|
| 237 |
+
"grad_norm": 1.395189881324768,
|
| 238 |
+
"learning_rate": 9.767676767676767e-06,
|
| 239 |
+
"loss": 0.5181,
|
| 240 |
+
"step": 330
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.12,
|
| 244 |
+
"grad_norm": 0.801499605178833,
|
| 245 |
+
"learning_rate": 9.757575757575758e-06,
|
| 246 |
+
"loss": 0.5296,
|
| 247 |
+
"step": 340
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.13,
|
| 251 |
+
"grad_norm": 0.7606889605522156,
|
| 252 |
+
"learning_rate": 9.747474747474748e-06,
|
| 253 |
+
"loss": 0.5406,
|
| 254 |
+
"step": 350
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.13,
|
| 258 |
+
"grad_norm": 0.580170750617981,
|
| 259 |
+
"learning_rate": 9.737373737373738e-06,
|
| 260 |
+
"loss": 0.541,
|
| 261 |
+
"step": 360
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.13,
|
| 265 |
+
"grad_norm": 0.6730871796607971,
|
| 266 |
+
"learning_rate": 9.727272727272728e-06,
|
| 267 |
+
"loss": 0.5665,
|
| 268 |
+
"step": 370
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.14,
|
| 272 |
+
"grad_norm": 1.240430474281311,
|
| 273 |
+
"learning_rate": 9.717171717171719e-06,
|
| 274 |
+
"loss": 0.5148,
|
| 275 |
+
"step": 380
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.14,
|
| 279 |
+
"grad_norm": 0.9439683556556702,
|
| 280 |
+
"learning_rate": 9.707070707070709e-06,
|
| 281 |
+
"loss": 0.513,
|
| 282 |
+
"step": 390
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.14,
|
| 286 |
+
"grad_norm": 0.6674547791481018,
|
| 287 |
+
"learning_rate": 9.696969696969698e-06,
|
| 288 |
+
"loss": 0.5202,
|
| 289 |
+
"step": 400
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.15,
|
| 293 |
+
"grad_norm": 0.8516045808792114,
|
| 294 |
+
"learning_rate": 9.686868686868688e-06,
|
| 295 |
+
"loss": 0.5162,
|
| 296 |
+
"step": 410
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.15,
|
| 300 |
+
"grad_norm": 0.8700432181358337,
|
| 301 |
+
"learning_rate": 9.676767676767678e-06,
|
| 302 |
+
"loss": 0.5392,
|
| 303 |
+
"step": 420
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.15,
|
| 307 |
+
"grad_norm": 0.5687388777732849,
|
| 308 |
+
"learning_rate": 9.666666666666667e-06,
|
| 309 |
+
"loss": 0.5106,
|
| 310 |
+
"step": 430
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.16,
|
| 314 |
+
"grad_norm": 1.2382631301879883,
|
| 315 |
+
"learning_rate": 9.656565656565657e-06,
|
| 316 |
+
"loss": 0.5074,
|
| 317 |
+
"step": 440
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.16,
|
| 321 |
+
"grad_norm": 0.8921974301338196,
|
| 322 |
+
"learning_rate": 9.646464646464647e-06,
|
| 323 |
+
"loss": 0.561,
|
| 324 |
+
"step": 450
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.16,
|
| 328 |
+
"grad_norm": 1.3508048057556152,
|
| 329 |
+
"learning_rate": 9.636363636363638e-06,
|
| 330 |
+
"loss": 0.5484,
|
| 331 |
+
"step": 460
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.17,
|
| 335 |
+
"grad_norm": 1.1822205781936646,
|
| 336 |
+
"learning_rate": 9.626262626262626e-06,
|
| 337 |
+
"loss": 0.5719,
|
| 338 |
+
"step": 470
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.17,
|
| 342 |
+
"grad_norm": 0.6617271304130554,
|
| 343 |
+
"learning_rate": 9.616161616161616e-06,
|
| 344 |
+
"loss": 0.535,
|
| 345 |
+
"step": 480
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.18,
|
| 349 |
+
"grad_norm": 0.6614571809768677,
|
| 350 |
+
"learning_rate": 9.606060606060607e-06,
|
| 351 |
+
"loss": 0.4549,
|
| 352 |
+
"step": 490
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.18,
|
| 356 |
+
"grad_norm": 0.8642953038215637,
|
| 357 |
+
"learning_rate": 9.595959595959597e-06,
|
| 358 |
+
"loss": 0.4789,
|
| 359 |
+
"step": 500
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.18,
|
| 363 |
+
"grad_norm": 0.614743173122406,
|
| 364 |
+
"learning_rate": 9.585858585858586e-06,
|
| 365 |
+
"loss": 0.4854,
|
| 366 |
+
"step": 510
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.19,
|
| 370 |
+
"grad_norm": 0.970829427242279,
|
| 371 |
+
"learning_rate": 9.575757575757576e-06,
|
| 372 |
+
"loss": 0.5196,
|
| 373 |
+
"step": 520
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.19,
|
| 377 |
+
"grad_norm": 0.7311980128288269,
|
| 378 |
+
"learning_rate": 9.565656565656566e-06,
|
| 379 |
+
"loss": 0.5106,
|
| 380 |
+
"step": 530
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.19,
|
| 384 |
+
"grad_norm": 0.765849769115448,
|
| 385 |
+
"learning_rate": 9.555555555555556e-06,
|
| 386 |
+
"loss": 0.5782,
|
| 387 |
+
"step": 540
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.2,
|
| 391 |
+
"grad_norm": 1.0889312028884888,
|
| 392 |
+
"learning_rate": 9.545454545454547e-06,
|
| 393 |
+
"loss": 0.5824,
|
| 394 |
+
"step": 550
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.2,
|
| 398 |
+
"grad_norm": 0.7402384877204895,
|
| 399 |
+
"learning_rate": 9.535353535353537e-06,
|
| 400 |
+
"loss": 0.5005,
|
| 401 |
+
"step": 560
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.2,
|
| 405 |
+
"grad_norm": 0.707028329372406,
|
| 406 |
+
"learning_rate": 9.525252525252526e-06,
|
| 407 |
+
"loss": 0.5233,
|
| 408 |
+
"step": 570
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.21,
|
| 412 |
+
"grad_norm": 0.8338315486907959,
|
| 413 |
+
"learning_rate": 9.515151515151516e-06,
|
| 414 |
+
"loss": 0.4694,
|
| 415 |
+
"step": 580
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.21,
|
| 419 |
+
"grad_norm": 0.7450662851333618,
|
| 420 |
+
"learning_rate": 9.505050505050506e-06,
|
| 421 |
+
"loss": 0.4762,
|
| 422 |
+
"step": 590
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.22,
|
| 426 |
+
"grad_norm": 0.7595840692520142,
|
| 427 |
+
"learning_rate": 9.494949494949497e-06,
|
| 428 |
+
"loss": 0.5018,
|
| 429 |
+
"step": 600
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.22,
|
| 433 |
+
"grad_norm": 0.5880123376846313,
|
| 434 |
+
"learning_rate": 9.484848484848485e-06,
|
| 435 |
+
"loss": 0.5228,
|
| 436 |
+
"step": 610
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.22,
|
| 440 |
+
"grad_norm": 0.9635146260261536,
|
| 441 |
+
"learning_rate": 9.474747474747475e-06,
|
| 442 |
+
"loss": 0.4987,
|
| 443 |
+
"step": 620
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.23,
|
| 447 |
+
"grad_norm": 1.1274373531341553,
|
| 448 |
+
"learning_rate": 9.464646464646466e-06,
|
| 449 |
+
"loss": 0.5085,
|
| 450 |
+
"step": 630
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.23,
|
| 454 |
+
"grad_norm": 1.1324831247329712,
|
| 455 |
+
"learning_rate": 9.454545454545456e-06,
|
| 456 |
+
"loss": 0.504,
|
| 457 |
+
"step": 640
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.23,
|
| 461 |
+
"grad_norm": 0.5410157442092896,
|
| 462 |
+
"learning_rate": 9.444444444444445e-06,
|
| 463 |
+
"loss": 0.4619,
|
| 464 |
+
"step": 650
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.24,
|
| 468 |
+
"grad_norm": 0.7583281993865967,
|
| 469 |
+
"learning_rate": 9.434343434343435e-06,
|
| 470 |
+
"loss": 0.5162,
|
| 471 |
+
"step": 660
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.24,
|
| 475 |
+
"grad_norm": 0.6546668410301208,
|
| 476 |
+
"learning_rate": 9.424242424242425e-06,
|
| 477 |
+
"loss": 0.4969,
|
| 478 |
+
"step": 670
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 0.24,
|
| 482 |
+
"grad_norm": 0.6070376634597778,
|
| 483 |
+
"learning_rate": 9.414141414141414e-06,
|
| 484 |
+
"loss": 0.4805,
|
| 485 |
+
"step": 680
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.25,
|
| 489 |
+
"grad_norm": 1.0108693838119507,
|
| 490 |
+
"learning_rate": 9.404040404040404e-06,
|
| 491 |
+
"loss": 0.4808,
|
| 492 |
+
"step": 690
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 0.25,
|
| 496 |
+
"grad_norm": 0.8799183368682861,
|
| 497 |
+
"learning_rate": 9.393939393939396e-06,
|
| 498 |
+
"loss": 0.5082,
|
| 499 |
+
"step": 700
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.25,
|
| 503 |
+
"grad_norm": 1.3432070016860962,
|
| 504 |
+
"learning_rate": 9.383838383838385e-06,
|
| 505 |
+
"loss": 0.4353,
|
| 506 |
+
"step": 710
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.26,
|
| 510 |
+
"grad_norm": 0.6518195271492004,
|
| 511 |
+
"learning_rate": 9.373737373737375e-06,
|
| 512 |
+
"loss": 0.4933,
|
| 513 |
+
"step": 720
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.26,
|
| 517 |
+
"grad_norm": 0.6736329793930054,
|
| 518 |
+
"learning_rate": 9.363636363636365e-06,
|
| 519 |
+
"loss": 0.5342,
|
| 520 |
+
"step": 730
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 0.27,
|
| 524 |
+
"grad_norm": 0.776785135269165,
|
| 525 |
+
"learning_rate": 9.353535353535354e-06,
|
| 526 |
+
"loss": 0.5162,
|
| 527 |
+
"step": 740
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.27,
|
| 531 |
+
"grad_norm": 0.9443957805633545,
|
| 532 |
+
"learning_rate": 9.343434343434344e-06,
|
| 533 |
+
"loss": 0.4486,
|
| 534 |
+
"step": 750
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.27,
|
| 538 |
+
"grad_norm": 0.8882728815078735,
|
| 539 |
+
"learning_rate": 9.333333333333334e-06,
|
| 540 |
+
"loss": 0.4774,
|
| 541 |
+
"step": 760
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.28,
|
| 545 |
+
"grad_norm": 0.819239616394043,
|
| 546 |
+
"learning_rate": 9.323232323232325e-06,
|
| 547 |
+
"loss": 0.5,
|
| 548 |
+
"step": 770
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 0.28,
|
| 552 |
+
"grad_norm": 0.8829065561294556,
|
| 553 |
+
"learning_rate": 9.313131313131313e-06,
|
| 554 |
+
"loss": 0.4655,
|
| 555 |
+
"step": 780
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.28,
|
| 559 |
+
"grad_norm": 1.1993345022201538,
|
| 560 |
+
"learning_rate": 9.303030303030303e-06,
|
| 561 |
+
"loss": 0.5392,
|
| 562 |
+
"step": 790
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 0.29,
|
| 566 |
+
"grad_norm": 0.681409478187561,
|
| 567 |
+
"learning_rate": 9.292929292929294e-06,
|
| 568 |
+
"loss": 0.5076,
|
| 569 |
+
"step": 800
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.29,
|
| 573 |
+
"grad_norm": 1.075088381767273,
|
| 574 |
+
"learning_rate": 9.282828282828284e-06,
|
| 575 |
+
"loss": 0.4953,
|
| 576 |
+
"step": 810
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 0.29,
|
| 580 |
+
"grad_norm": 0.7040195465087891,
|
| 581 |
+
"learning_rate": 9.272727272727273e-06,
|
| 582 |
+
"loss": 0.5596,
|
| 583 |
+
"step": 820
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.3,
|
| 587 |
+
"grad_norm": 1.1210192441940308,
|
| 588 |
+
"learning_rate": 9.262626262626263e-06,
|
| 589 |
+
"loss": 0.5299,
|
| 590 |
+
"step": 830
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 0.3,
|
| 594 |
+
"grad_norm": 0.583011269569397,
|
| 595 |
+
"learning_rate": 9.252525252525253e-06,
|
| 596 |
+
"loss": 0.497,
|
| 597 |
+
"step": 840
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.3,
|
| 601 |
+
"grad_norm": 0.6583887338638306,
|
| 602 |
+
"learning_rate": 9.242424242424244e-06,
|
| 603 |
+
"loss": 0.5556,
|
| 604 |
+
"step": 850
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 0.31,
|
| 608 |
+
"grad_norm": 0.8040810227394104,
|
| 609 |
+
"learning_rate": 9.232323232323232e-06,
|
| 610 |
+
"loss": 0.5257,
|
| 611 |
+
"step": 860
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.31,
|
| 615 |
+
"grad_norm": 0.9269919991493225,
|
| 616 |
+
"learning_rate": 9.222222222222224e-06,
|
| 617 |
+
"loss": 0.4421,
|
| 618 |
+
"step": 870
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 0.32,
|
| 622 |
+
"grad_norm": 0.9947918653488159,
|
| 623 |
+
"learning_rate": 9.212121212121213e-06,
|
| 624 |
+
"loss": 0.5297,
|
| 625 |
+
"step": 880
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.32,
|
| 629 |
+
"grad_norm": 0.6900811791419983,
|
| 630 |
+
"learning_rate": 9.202020202020203e-06,
|
| 631 |
+
"loss": 0.4833,
|
| 632 |
+
"step": 890
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 0.32,
|
| 636 |
+
"grad_norm": 0.8033557534217834,
|
| 637 |
+
"learning_rate": 9.191919191919193e-06,
|
| 638 |
+
"loss": 0.4894,
|
| 639 |
+
"step": 900
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.33,
|
| 643 |
+
"grad_norm": 0.635124683380127,
|
| 644 |
+
"learning_rate": 9.181818181818184e-06,
|
| 645 |
+
"loss": 0.4554,
|
| 646 |
+
"step": 910
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 0.33,
|
| 650 |
+
"grad_norm": 0.7293840646743774,
|
| 651 |
+
"learning_rate": 9.171717171717172e-06,
|
| 652 |
+
"loss": 0.4693,
|
| 653 |
+
"step": 920
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 0.33,
|
| 657 |
+
"grad_norm": 0.7628031373023987,
|
| 658 |
+
"learning_rate": 9.161616161616162e-06,
|
| 659 |
+
"loss": 0.5181,
|
| 660 |
+
"step": 930
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 0.34,
|
| 664 |
+
"grad_norm": 1.0783181190490723,
|
| 665 |
+
"learning_rate": 9.151515151515153e-06,
|
| 666 |
+
"loss": 0.4632,
|
| 667 |
+
"step": 940
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 0.34,
|
| 671 |
+
"grad_norm": 0.5340379476547241,
|
| 672 |
+
"learning_rate": 9.141414141414143e-06,
|
| 673 |
+
"loss": 0.4664,
|
| 674 |
+
"step": 950
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 0.34,
|
| 678 |
+
"grad_norm": 0.9029551148414612,
|
| 679 |
+
"learning_rate": 9.131313131313132e-06,
|
| 680 |
+
"loss": 0.5333,
|
| 681 |
+
"step": 960
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.35,
|
| 685 |
+
"grad_norm": 0.7257616519927979,
|
| 686 |
+
"learning_rate": 9.121212121212122e-06,
|
| 687 |
+
"loss": 0.5168,
|
| 688 |
+
"step": 970
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 0.35,
|
| 692 |
+
"grad_norm": 0.761325478553772,
|
| 693 |
+
"learning_rate": 9.111111111111112e-06,
|
| 694 |
+
"loss": 0.5606,
|
| 695 |
+
"step": 980
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 0.36,
|
| 699 |
+
"grad_norm": 0.8582245707511902,
|
| 700 |
+
"learning_rate": 9.1010101010101e-06,
|
| 701 |
+
"loss": 0.4332,
|
| 702 |
+
"step": 990
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 0.36,
|
| 706 |
+
"grad_norm": 0.8598415851593018,
|
| 707 |
+
"learning_rate": 9.090909090909091e-06,
|
| 708 |
+
"loss": 0.5884,
|
| 709 |
+
"step": 1000
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 0.36,
|
| 713 |
+
"grad_norm": 0.8292351365089417,
|
| 714 |
+
"learning_rate": 9.080808080808081e-06,
|
| 715 |
+
"loss": 0.4848,
|
| 716 |
+
"step": 1010
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 0.37,
|
| 720 |
+
"grad_norm": 1.0559266805648804,
|
| 721 |
+
"learning_rate": 9.070707070707072e-06,
|
| 722 |
+
"loss": 0.4588,
|
| 723 |
+
"step": 1020
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 0.37,
|
| 727 |
+
"grad_norm": 0.6693033576011658,
|
| 728 |
+
"learning_rate": 9.06060606060606e-06,
|
| 729 |
+
"loss": 0.5333,
|
| 730 |
+
"step": 1030
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 0.37,
|
| 734 |
+
"grad_norm": 0.8114706873893738,
|
| 735 |
+
"learning_rate": 9.050505050505052e-06,
|
| 736 |
+
"loss": 0.5166,
|
| 737 |
+
"step": 1040
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 0.38,
|
| 741 |
+
"grad_norm": 0.8659316301345825,
|
| 742 |
+
"learning_rate": 9.040404040404042e-06,
|
| 743 |
+
"loss": 0.4504,
|
| 744 |
+
"step": 1050
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 0.38,
|
| 748 |
+
"grad_norm": 0.9083582758903503,
|
| 749 |
+
"learning_rate": 9.030303030303031e-06,
|
| 750 |
+
"loss": 0.5611,
|
| 751 |
+
"step": 1060
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 0.38,
|
| 755 |
+
"grad_norm": 0.6691566109657288,
|
| 756 |
+
"learning_rate": 9.020202020202021e-06,
|
| 757 |
+
"loss": 0.5192,
|
| 758 |
+
"step": 1070
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 0.39,
|
| 762 |
+
"grad_norm": 0.5889317989349365,
|
| 763 |
+
"learning_rate": 9.010101010101012e-06,
|
| 764 |
+
"loss": 0.4515,
|
| 765 |
+
"step": 1080
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 0.39,
|
| 769 |
+
"grad_norm": 0.9215373992919922,
|
| 770 |
+
"learning_rate": 9e-06,
|
| 771 |
+
"loss": 0.4776,
|
| 772 |
+
"step": 1090
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 0.39,
|
| 776 |
+
"grad_norm": 0.7439729571342468,
|
| 777 |
+
"learning_rate": 8.98989898989899e-06,
|
| 778 |
+
"loss": 0.4656,
|
| 779 |
+
"step": 1100
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 0.4,
|
| 783 |
+
"grad_norm": 1.1780657768249512,
|
| 784 |
+
"learning_rate": 8.97979797979798e-06,
|
| 785 |
+
"loss": 0.4933,
|
| 786 |
+
"step": 1110
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 0.4,
|
| 790 |
+
"grad_norm": 0.9686077833175659,
|
| 791 |
+
"learning_rate": 8.969696969696971e-06,
|
| 792 |
+
"loss": 0.5167,
|
| 793 |
+
"step": 1120
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 0.41,
|
| 797 |
+
"grad_norm": 0.829994261264801,
|
| 798 |
+
"learning_rate": 8.95959595959596e-06,
|
| 799 |
+
"loss": 0.491,
|
| 800 |
+
"step": 1130
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 0.41,
|
| 804 |
+
"grad_norm": 0.6313827633857727,
|
| 805 |
+
"learning_rate": 8.94949494949495e-06,
|
| 806 |
+
"loss": 0.4864,
|
| 807 |
+
"step": 1140
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 0.41,
|
| 811 |
+
"grad_norm": 0.596537709236145,
|
| 812 |
+
"learning_rate": 8.93939393939394e-06,
|
| 813 |
+
"loss": 0.4807,
|
| 814 |
+
"step": 1150
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 0.42,
|
| 818 |
+
"grad_norm": 0.8714896440505981,
|
| 819 |
+
"learning_rate": 8.92929292929293e-06,
|
| 820 |
+
"loss": 0.512,
|
| 821 |
+
"step": 1160
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 0.42,
|
| 825 |
+
"grad_norm": 0.9466399550437927,
|
| 826 |
+
"learning_rate": 8.919191919191919e-06,
|
| 827 |
+
"loss": 0.4883,
|
| 828 |
+
"step": 1170
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 0.42,
|
| 832 |
+
"grad_norm": 0.7337993383407593,
|
| 833 |
+
"learning_rate": 8.90909090909091e-06,
|
| 834 |
+
"loss": 0.4757,
|
| 835 |
+
"step": 1180
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 0.43,
|
| 839 |
+
"grad_norm": 0.7684504985809326,
|
| 840 |
+
"learning_rate": 8.8989898989899e-06,
|
| 841 |
+
"loss": 0.5224,
|
| 842 |
+
"step": 1190
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 0.43,
|
| 846 |
+
"grad_norm": 0.6455299854278564,
|
| 847 |
+
"learning_rate": 8.888888888888888e-06,
|
| 848 |
+
"loss": 0.5346,
|
| 849 |
+
"step": 1200
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 0.43,
|
| 853 |
+
"grad_norm": 0.7279661893844604,
|
| 854 |
+
"learning_rate": 8.87878787878788e-06,
|
| 855 |
+
"loss": 0.4845,
|
| 856 |
+
"step": 1210
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 0.44,
|
| 860 |
+
"grad_norm": 0.7996425032615662,
|
| 861 |
+
"learning_rate": 8.86868686868687e-06,
|
| 862 |
+
"loss": 0.4812,
|
| 863 |
+
"step": 1220
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 0.44,
|
| 867 |
+
"grad_norm": 0.7299336791038513,
|
| 868 |
+
"learning_rate": 8.85858585858586e-06,
|
| 869 |
+
"loss": 0.4985,
|
| 870 |
+
"step": 1230
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 0.44,
|
| 874 |
+
"grad_norm": 0.7462379932403564,
|
| 875 |
+
"learning_rate": 8.84848484848485e-06,
|
| 876 |
+
"loss": 0.5742,
|
| 877 |
+
"step": 1240
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 0.45,
|
| 881 |
+
"grad_norm": 0.7165307998657227,
|
| 882 |
+
"learning_rate": 8.83838383838384e-06,
|
| 883 |
+
"loss": 0.4627,
|
| 884 |
+
"step": 1250
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 0.45,
|
| 888 |
+
"grad_norm": 0.7239411473274231,
|
| 889 |
+
"learning_rate": 8.82828282828283e-06,
|
| 890 |
+
"loss": 0.5469,
|
| 891 |
+
"step": 1260
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 0.46,
|
| 895 |
+
"grad_norm": 0.5761345028877258,
|
| 896 |
+
"learning_rate": 8.818181818181819e-06,
|
| 897 |
+
"loss": 0.4391,
|
| 898 |
+
"step": 1270
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 0.46,
|
| 902 |
+
"grad_norm": 0.8207817077636719,
|
| 903 |
+
"learning_rate": 8.808080808080809e-06,
|
| 904 |
+
"loss": 0.5477,
|
| 905 |
+
"step": 1280
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 0.46,
|
| 909 |
+
"grad_norm": 0.9331930875778198,
|
| 910 |
+
"learning_rate": 8.7979797979798e-06,
|
| 911 |
+
"loss": 0.4975,
|
| 912 |
+
"step": 1290
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 0.47,
|
| 916 |
+
"grad_norm": 1.0401968955993652,
|
| 917 |
+
"learning_rate": 8.787878787878788e-06,
|
| 918 |
+
"loss": 0.5149,
|
| 919 |
+
"step": 1300
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 0.47,
|
| 923 |
+
"grad_norm": 0.7848596572875977,
|
| 924 |
+
"learning_rate": 8.777777777777778e-06,
|
| 925 |
+
"loss": 0.5448,
|
| 926 |
+
"step": 1310
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 0.47,
|
| 930 |
+
"grad_norm": 1.5979989767074585,
|
| 931 |
+
"learning_rate": 8.767676767676768e-06,
|
| 932 |
+
"loss": 0.4861,
|
| 933 |
+
"step": 1320
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 0.48,
|
| 937 |
+
"grad_norm": 0.7734145522117615,
|
| 938 |
+
"learning_rate": 8.757575757575759e-06,
|
| 939 |
+
"loss": 0.5955,
|
| 940 |
+
"step": 1330
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 0.48,
|
| 944 |
+
"grad_norm": 0.9506089687347412,
|
| 945 |
+
"learning_rate": 8.747474747474747e-06,
|
| 946 |
+
"loss": 0.5212,
|
| 947 |
+
"step": 1340
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 0.48,
|
| 951 |
+
"grad_norm": 0.7118907570838928,
|
| 952 |
+
"learning_rate": 8.737373737373738e-06,
|
| 953 |
+
"loss": 0.474,
|
| 954 |
+
"step": 1350
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 0.49,
|
| 958 |
+
"grad_norm": 1.0045005083084106,
|
| 959 |
+
"learning_rate": 8.727272727272728e-06,
|
| 960 |
+
"loss": 0.509,
|
| 961 |
+
"step": 1360
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 0.49,
|
| 965 |
+
"grad_norm": 1.1283302307128906,
|
| 966 |
+
"learning_rate": 8.717171717171718e-06,
|
| 967 |
+
"loss": 0.5096,
|
| 968 |
+
"step": 1370
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 0.49,
|
| 972 |
+
"grad_norm": 1.3884085416793823,
|
| 973 |
+
"learning_rate": 8.707070707070707e-06,
|
| 974 |
+
"loss": 0.5008,
|
| 975 |
+
"step": 1380
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 0.5,
|
| 979 |
+
"grad_norm": 0.7452566027641296,
|
| 980 |
+
"learning_rate": 8.696969696969699e-06,
|
| 981 |
+
"loss": 0.4792,
|
| 982 |
+
"step": 1390
|
| 983 |
+
},
|
| 984 |
+
{
|
| 985 |
+
"epoch": 0.5,
|
| 986 |
+
"grad_norm": 1.3434414863586426,
|
| 987 |
+
"learning_rate": 8.686868686868687e-06,
|
| 988 |
+
"loss": 0.5385,
|
| 989 |
+
"step": 1400
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 0.51,
|
| 993 |
+
"grad_norm": 0.9600369930267334,
|
| 994 |
+
"learning_rate": 8.676767676767678e-06,
|
| 995 |
+
"loss": 0.4743,
|
| 996 |
+
"step": 1410
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 0.51,
|
| 1000 |
+
"grad_norm": 0.6895599961280823,
|
| 1001 |
+
"learning_rate": 8.666666666666668e-06,
|
| 1002 |
+
"loss": 0.5639,
|
| 1003 |
+
"step": 1420
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 0.51,
|
| 1007 |
+
"grad_norm": 0.9460670948028564,
|
| 1008 |
+
"learning_rate": 8.656565656565658e-06,
|
| 1009 |
+
"loss": 0.5957,
|
| 1010 |
+
"step": 1430
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 0.52,
|
| 1014 |
+
"grad_norm": 0.6181186437606812,
|
| 1015 |
+
"learning_rate": 8.646464646464647e-06,
|
| 1016 |
+
"loss": 0.5032,
|
| 1017 |
+
"step": 1440
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 0.52,
|
| 1021 |
+
"grad_norm": 0.6992838382720947,
|
| 1022 |
+
"learning_rate": 8.636363636363637e-06,
|
| 1023 |
+
"loss": 0.5371,
|
| 1024 |
+
"step": 1450
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 0.52,
|
| 1028 |
+
"grad_norm": 0.6007195711135864,
|
| 1029 |
+
"learning_rate": 8.626262626262627e-06,
|
| 1030 |
+
"loss": 0.4446,
|
| 1031 |
+
"step": 1460
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 0.53,
|
| 1035 |
+
"grad_norm": 0.8171485662460327,
|
| 1036 |
+
"learning_rate": 8.616161616161618e-06,
|
| 1037 |
+
"loss": 0.4835,
|
| 1038 |
+
"step": 1470
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"epoch": 0.53,
|
| 1042 |
+
"grad_norm": 0.9369902610778809,
|
| 1043 |
+
"learning_rate": 8.606060606060606e-06,
|
| 1044 |
+
"loss": 0.5437,
|
| 1045 |
+
"step": 1480
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 0.53,
|
| 1049 |
+
"grad_norm": 1.1894652843475342,
|
| 1050 |
+
"learning_rate": 8.595959595959596e-06,
|
| 1051 |
+
"loss": 0.5151,
|
| 1052 |
+
"step": 1490
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 0.54,
|
| 1056 |
+
"grad_norm": 0.694837212562561,
|
| 1057 |
+
"learning_rate": 8.585858585858587e-06,
|
| 1058 |
+
"loss": 0.488,
|
| 1059 |
+
"step": 1500
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 0.54,
|
| 1063 |
+
"grad_norm": 0.8813522458076477,
|
| 1064 |
+
"learning_rate": 8.575757575757575e-06,
|
| 1065 |
+
"loss": 0.5129,
|
| 1066 |
+
"step": 1510
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 0.55,
|
| 1070 |
+
"grad_norm": 1.0121350288391113,
|
| 1071 |
+
"learning_rate": 8.565656565656566e-06,
|
| 1072 |
+
"loss": 0.5165,
|
| 1073 |
+
"step": 1520
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 0.55,
|
| 1077 |
+
"grad_norm": 0.7935439944267273,
|
| 1078 |
+
"learning_rate": 8.555555555555556e-06,
|
| 1079 |
+
"loss": 0.4736,
|
| 1080 |
+
"step": 1530
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 0.55,
|
| 1084 |
+
"grad_norm": 0.7670463919639587,
|
| 1085 |
+
"learning_rate": 8.545454545454546e-06,
|
| 1086 |
+
"loss": 0.5214,
|
| 1087 |
+
"step": 1540
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 0.56,
|
| 1091 |
+
"grad_norm": 1.212927222251892,
|
| 1092 |
+
"learning_rate": 8.535353535353535e-06,
|
| 1093 |
+
"loss": 0.5125,
|
| 1094 |
+
"step": 1550
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 0.56,
|
| 1098 |
+
"grad_norm": 0.7966919541358948,
|
| 1099 |
+
"learning_rate": 8.525252525252527e-06,
|
| 1100 |
+
"loss": 0.4823,
|
| 1101 |
+
"step": 1560
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 0.56,
|
| 1105 |
+
"grad_norm": 1.0880494117736816,
|
| 1106 |
+
"learning_rate": 8.515151515151517e-06,
|
| 1107 |
+
"loss": 0.478,
|
| 1108 |
+
"step": 1570
|
| 1109 |
+
},
|
| 1110 |
+
{
|
| 1111 |
+
"epoch": 0.57,
|
| 1112 |
+
"grad_norm": 1.0308737754821777,
|
| 1113 |
+
"learning_rate": 8.505050505050506e-06,
|
| 1114 |
+
"loss": 0.5368,
|
| 1115 |
+
"step": 1580
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 0.57,
|
| 1119 |
+
"grad_norm": 0.7291275262832642,
|
| 1120 |
+
"learning_rate": 8.494949494949496e-06,
|
| 1121 |
+
"loss": 0.4838,
|
| 1122 |
+
"step": 1590
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 0.57,
|
| 1126 |
+
"grad_norm": 0.6764214038848877,
|
| 1127 |
+
"learning_rate": 8.484848484848486e-06,
|
| 1128 |
+
"loss": 0.4882,
|
| 1129 |
+
"step": 1600
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 0.58,
|
| 1133 |
+
"grad_norm": 1.051628828048706,
|
| 1134 |
+
"learning_rate": 8.474747474747475e-06,
|
| 1135 |
+
"loss": 0.4564,
|
| 1136 |
+
"step": 1610
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 0.58,
|
| 1140 |
+
"grad_norm": 0.8614614605903625,
|
| 1141 |
+
"learning_rate": 8.464646464646465e-06,
|
| 1142 |
+
"loss": 0.5632,
|
| 1143 |
+
"step": 1620
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 0.58,
|
| 1147 |
+
"grad_norm": 1.1045228242874146,
|
| 1148 |
+
"learning_rate": 8.454545454545455e-06,
|
| 1149 |
+
"loss": 0.4535,
|
| 1150 |
+
"step": 1630
|
| 1151 |
+
},
|
| 1152 |
+
{
|
| 1153 |
+
"epoch": 0.59,
|
| 1154 |
+
"grad_norm": 0.8160364031791687,
|
| 1155 |
+
"learning_rate": 8.444444444444446e-06,
|
| 1156 |
+
"loss": 0.4964,
|
| 1157 |
+
"step": 1640
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 0.59,
|
| 1161 |
+
"grad_norm": 0.7776429653167725,
|
| 1162 |
+
"learning_rate": 8.434343434343434e-06,
|
| 1163 |
+
"loss": 0.4554,
|
| 1164 |
+
"step": 1650
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 0.6,
|
| 1168 |
+
"grad_norm": 0.7589672207832336,
|
| 1169 |
+
"learning_rate": 8.424242424242425e-06,
|
| 1170 |
+
"loss": 0.4458,
|
| 1171 |
+
"step": 1660
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 0.6,
|
| 1175 |
+
"grad_norm": 0.825233519077301,
|
| 1176 |
+
"learning_rate": 8.414141414141415e-06,
|
| 1177 |
+
"loss": 0.4814,
|
| 1178 |
+
"step": 1670
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 0.6,
|
| 1182 |
+
"grad_norm": 0.8226912617683411,
|
| 1183 |
+
"learning_rate": 8.404040404040405e-06,
|
| 1184 |
+
"loss": 0.4892,
|
| 1185 |
+
"step": 1680
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 0.61,
|
| 1189 |
+
"grad_norm": 0.9273412823677063,
|
| 1190 |
+
"learning_rate": 8.393939393939394e-06,
|
| 1191 |
+
"loss": 0.5143,
|
| 1192 |
+
"step": 1690
|
| 1193 |
+
},
|
| 1194 |
+
{
|
| 1195 |
+
"epoch": 0.61,
|
| 1196 |
+
"grad_norm": 0.9043828248977661,
|
| 1197 |
+
"learning_rate": 8.383838383838384e-06,
|
| 1198 |
+
"loss": 0.4598,
|
| 1199 |
+
"step": 1700
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 0.61,
|
| 1203 |
+
"grad_norm": 2.2596805095672607,
|
| 1204 |
+
"learning_rate": 8.373737373737374e-06,
|
| 1205 |
+
"loss": 0.5415,
|
| 1206 |
+
"step": 1710
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"epoch": 0.62,
|
| 1210 |
+
"grad_norm": 1.0041202306747437,
|
| 1211 |
+
"learning_rate": 8.363636363636365e-06,
|
| 1212 |
+
"loss": 0.5899,
|
| 1213 |
+
"step": 1720
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 0.62,
|
| 1217 |
+
"grad_norm": 0.9188370704650879,
|
| 1218 |
+
"learning_rate": 8.353535353535355e-06,
|
| 1219 |
+
"loss": 0.5119,
|
| 1220 |
+
"step": 1730
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 0.62,
|
| 1224 |
+
"grad_norm": 0.7778961062431335,
|
| 1225 |
+
"learning_rate": 8.343434343434345e-06,
|
| 1226 |
+
"loss": 0.5237,
|
| 1227 |
+
"step": 1740
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 0.63,
|
| 1231 |
+
"grad_norm": 0.7438649535179138,
|
| 1232 |
+
"learning_rate": 8.333333333333334e-06,
|
| 1233 |
+
"loss": 0.4999,
|
| 1234 |
+
"step": 1750
|
| 1235 |
+
},
|
| 1236 |
+
{
|
| 1237 |
+
"epoch": 0.63,
|
| 1238 |
+
"grad_norm": 0.5649489760398865,
|
| 1239 |
+
"learning_rate": 8.323232323232324e-06,
|
| 1240 |
+
"loss": 0.552,
|
| 1241 |
+
"step": 1760
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 0.63,
|
| 1245 |
+
"grad_norm": 0.5625451803207397,
|
| 1246 |
+
"learning_rate": 8.313131313131314e-06,
|
| 1247 |
+
"loss": 0.4549,
|
| 1248 |
+
"step": 1770
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 0.64,
|
| 1252 |
+
"grad_norm": 1.3711755275726318,
|
| 1253 |
+
"learning_rate": 8.303030303030305e-06,
|
| 1254 |
+
"loss": 0.445,
|
| 1255 |
+
"step": 1780
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 0.64,
|
| 1259 |
+
"grad_norm": 1.4339165687561035,
|
| 1260 |
+
"learning_rate": 8.292929292929293e-06,
|
| 1261 |
+
"loss": 0.4975,
|
| 1262 |
+
"step": 1790
|
| 1263 |
+
},
|
| 1264 |
+
{
|
| 1265 |
+
"epoch": 0.65,
|
| 1266 |
+
"grad_norm": 0.8113200068473816,
|
| 1267 |
+
"learning_rate": 8.282828282828283e-06,
|
| 1268 |
+
"loss": 0.5288,
|
| 1269 |
+
"step": 1800
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 0.65,
|
| 1273 |
+
"grad_norm": 1.1567124128341675,
|
| 1274 |
+
"learning_rate": 8.272727272727274e-06,
|
| 1275 |
+
"loss": 0.4669,
|
| 1276 |
+
"step": 1810
|
| 1277 |
+
},
|
| 1278 |
+
{
|
| 1279 |
+
"epoch": 0.65,
|
| 1280 |
+
"grad_norm": 0.7966761589050293,
|
| 1281 |
+
"learning_rate": 8.262626262626264e-06,
|
| 1282 |
+
"loss": 0.4856,
|
| 1283 |
+
"step": 1820
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 0.66,
|
| 1287 |
+
"grad_norm": 1.0181186199188232,
|
| 1288 |
+
"learning_rate": 8.252525252525253e-06,
|
| 1289 |
+
"loss": 0.4576,
|
| 1290 |
+
"step": 1830
|
| 1291 |
+
},
|
| 1292 |
+
{
|
| 1293 |
+
"epoch": 0.66,
|
| 1294 |
+
"grad_norm": 0.611566960811615,
|
| 1295 |
+
"learning_rate": 8.242424242424243e-06,
|
| 1296 |
+
"loss": 0.496,
|
| 1297 |
+
"step": 1840
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 0.66,
|
| 1301 |
+
"grad_norm": 0.6482832431793213,
|
| 1302 |
+
"learning_rate": 8.232323232323233e-06,
|
| 1303 |
+
"loss": 0.4601,
|
| 1304 |
+
"step": 1850
|
| 1305 |
+
},
|
| 1306 |
+
{
|
| 1307 |
+
"epoch": 0.67,
|
| 1308 |
+
"grad_norm": 0.7550622820854187,
|
| 1309 |
+
"learning_rate": 8.222222222222222e-06,
|
| 1310 |
+
"loss": 0.5036,
|
| 1311 |
+
"step": 1860
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 0.67,
|
| 1315 |
+
"grad_norm": 0.7835694551467896,
|
| 1316 |
+
"learning_rate": 8.212121212121212e-06,
|
| 1317 |
+
"loss": 0.5617,
|
| 1318 |
+
"step": 1870
|
| 1319 |
+
},
|
| 1320 |
+
{
|
| 1321 |
+
"epoch": 0.67,
|
| 1322 |
+
"grad_norm": 0.7926068305969238,
|
| 1323 |
+
"learning_rate": 8.202020202020202e-06,
|
| 1324 |
+
"loss": 0.4327,
|
| 1325 |
+
"step": 1880
|
| 1326 |
+
},
|
| 1327 |
+
{
|
| 1328 |
+
"epoch": 0.68,
|
| 1329 |
+
"grad_norm": 0.786851167678833,
|
| 1330 |
+
"learning_rate": 8.191919191919193e-06,
|
| 1331 |
+
"loss": 0.4654,
|
| 1332 |
+
"step": 1890
|
| 1333 |
+
},
|
| 1334 |
+
{
|
| 1335 |
+
"epoch": 0.68,
|
| 1336 |
+
"grad_norm": 0.9023171663284302,
|
| 1337 |
+
"learning_rate": 8.181818181818183e-06,
|
| 1338 |
+
"loss": 0.5426,
|
| 1339 |
+
"step": 1900
|
| 1340 |
+
},
|
| 1341 |
+
{
|
| 1342 |
+
"epoch": 0.68,
|
| 1343 |
+
"grad_norm": 1.0345401763916016,
|
| 1344 |
+
"learning_rate": 8.171717171717173e-06,
|
| 1345 |
+
"loss": 0.52,
|
| 1346 |
+
"step": 1910
|
| 1347 |
+
},
|
| 1348 |
+
{
|
| 1349 |
+
"epoch": 0.69,
|
| 1350 |
+
"grad_norm": 0.945004940032959,
|
| 1351 |
+
"learning_rate": 8.161616161616162e-06,
|
| 1352 |
+
"loss": 0.5512,
|
| 1353 |
+
"step": 1920
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"epoch": 0.69,
|
| 1357 |
+
"grad_norm": 0.658362090587616,
|
| 1358 |
+
"learning_rate": 8.151515151515152e-06,
|
| 1359 |
+
"loss": 0.513,
|
| 1360 |
+
"step": 1930
|
| 1361 |
+
},
|
| 1362 |
+
{
|
| 1363 |
+
"epoch": 0.7,
|
| 1364 |
+
"grad_norm": 0.6390058398246765,
|
| 1365 |
+
"learning_rate": 8.141414141414142e-06,
|
| 1366 |
+
"loss": 0.5652,
|
| 1367 |
+
"step": 1940
|
| 1368 |
+
},
|
| 1369 |
+
{
|
| 1370 |
+
"epoch": 0.7,
|
| 1371 |
+
"grad_norm": 0.7705880403518677,
|
| 1372 |
+
"learning_rate": 8.131313131313133e-06,
|
| 1373 |
+
"loss": 0.4929,
|
| 1374 |
+
"step": 1950
|
| 1375 |
+
},
|
| 1376 |
+
{
|
| 1377 |
+
"epoch": 0.7,
|
| 1378 |
+
"grad_norm": 0.5400047302246094,
|
| 1379 |
+
"learning_rate": 8.121212121212121e-06,
|
| 1380 |
+
"loss": 0.4932,
|
| 1381 |
+
"step": 1960
|
| 1382 |
+
},
|
| 1383 |
+
{
|
| 1384 |
+
"epoch": 0.71,
|
| 1385 |
+
"grad_norm": 0.9128320217132568,
|
| 1386 |
+
"learning_rate": 8.111111111111112e-06,
|
| 1387 |
+
"loss": 0.5085,
|
| 1388 |
+
"step": 1970
|
| 1389 |
+
},
|
| 1390 |
+
{
|
| 1391 |
+
"epoch": 0.71,
|
| 1392 |
+
"grad_norm": 1.0019017457962036,
|
| 1393 |
+
"learning_rate": 8.101010101010102e-06,
|
| 1394 |
+
"loss": 0.4552,
|
| 1395 |
+
"step": 1980
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"epoch": 0.71,
|
| 1399 |
+
"grad_norm": 0.818148136138916,
|
| 1400 |
+
"learning_rate": 8.090909090909092e-06,
|
| 1401 |
+
"loss": 0.5517,
|
| 1402 |
+
"step": 1990
|
| 1403 |
+
},
|
| 1404 |
+
{
|
| 1405 |
+
"epoch": 0.72,
|
| 1406 |
+
"grad_norm": 0.8848174810409546,
|
| 1407 |
+
"learning_rate": 8.08080808080808e-06,
|
| 1408 |
+
"loss": 0.5094,
|
| 1409 |
+
"step": 2000
|
| 1410 |
+
},
|
| 1411 |
+
{
|
| 1412 |
+
"epoch": 0.72,
|
| 1413 |
+
"eval_loss": 0.6485620141029358,
|
| 1414 |
+
"eval_runtime": 340.5095,
|
| 1415 |
+
"eval_samples_per_second": 2.937,
|
| 1416 |
+
"eval_steps_per_second": 2.937,
|
| 1417 |
+
"step": 2000
|
| 1418 |
+
}
|
| 1419 |
+
],
|
| 1420 |
+
"logging_steps": 10,
|
| 1421 |
+
"max_steps": 10000,
|
| 1422 |
+
"num_input_tokens_seen": 0,
|
| 1423 |
+
"num_train_epochs": 4,
|
| 1424 |
+
"save_steps": 2000,
|
| 1425 |
+
"total_flos": 1.63205502468096e+17,
|
| 1426 |
+
"train_batch_size": 1,
|
| 1427 |
+
"trial_name": null,
|
| 1428 |
+
"trial_params": null
|
| 1429 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5b7d24b2588c9cc7f5b00158042ea7d4bff93ddd70bd49ab7701d433ce1fc925
|
| 3 |
+
size 4920
|