Training in progress, epoch 10, checkpoint
Browse files- checkpoint-155690/README.md +207 -0
- checkpoint-155690/adapter_config.json +37 -0
- checkpoint-155690/adapter_model.safetensors +3 -0
- checkpoint-155690/optimizer.pt +3 -0
- checkpoint-155690/rng_state_0.pth +3 -0
- checkpoint-155690/rng_state_1.pth +3 -0
- checkpoint-155690/rng_state_2.pth +3 -0
- checkpoint-155690/rng_state_3.pth +3 -0
- checkpoint-155690/scaler.pt +3 -0
- checkpoint-155690/scheduler.pt +3 -0
- checkpoint-155690/special_tokens_map.json +23 -0
- checkpoint-155690/tokenizer.json +0 -0
- checkpoint-155690/tokenizer_config.json +194 -0
- checkpoint-155690/trainer_state.json +2603 -0
- checkpoint-155690/training_args.bin +3 -0
checkpoint-155690/README.md
ADDED
|
@@ -0,0 +1,207 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: deepseek-ai/deepseek-coder-6.7b-base
|
| 3 |
+
library_name: peft
|
| 4 |
+
pipeline_tag: text-generation
|
| 5 |
+
tags:
|
| 6 |
+
- base_model:adapter:deepseek-ai/deepseek-coder-6.7b-base
|
| 7 |
+
- lora
|
| 8 |
+
- transformers
|
| 9 |
+
---
|
| 10 |
+
|
| 11 |
+
# Model Card for Model ID
|
| 12 |
+
|
| 13 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 14 |
+
|
| 15 |
+
|
| 16 |
+
|
| 17 |
+
## Model Details
|
| 18 |
+
|
| 19 |
+
### Model Description
|
| 20 |
+
|
| 21 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 22 |
+
|
| 23 |
+
|
| 24 |
+
|
| 25 |
+
- **Developed by:** [More Information Needed]
|
| 26 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 27 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 28 |
+
- **Model type:** [More Information Needed]
|
| 29 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 30 |
+
- **License:** [More Information Needed]
|
| 31 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 32 |
+
|
| 33 |
+
### Model Sources [optional]
|
| 34 |
+
|
| 35 |
+
<!-- Provide the basic links for the model. -->
|
| 36 |
+
|
| 37 |
+
- **Repository:** [More Information Needed]
|
| 38 |
+
- **Paper [optional]:** [More Information Needed]
|
| 39 |
+
- **Demo [optional]:** [More Information Needed]
|
| 40 |
+
|
| 41 |
+
## Uses
|
| 42 |
+
|
| 43 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 44 |
+
|
| 45 |
+
### Direct Use
|
| 46 |
+
|
| 47 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 48 |
+
|
| 49 |
+
[More Information Needed]
|
| 50 |
+
|
| 51 |
+
### Downstream Use [optional]
|
| 52 |
+
|
| 53 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 54 |
+
|
| 55 |
+
[More Information Needed]
|
| 56 |
+
|
| 57 |
+
### Out-of-Scope Use
|
| 58 |
+
|
| 59 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 60 |
+
|
| 61 |
+
[More Information Needed]
|
| 62 |
+
|
| 63 |
+
## Bias, Risks, and Limitations
|
| 64 |
+
|
| 65 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 66 |
+
|
| 67 |
+
[More Information Needed]
|
| 68 |
+
|
| 69 |
+
### Recommendations
|
| 70 |
+
|
| 71 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 72 |
+
|
| 73 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 74 |
+
|
| 75 |
+
## How to Get Started with the Model
|
| 76 |
+
|
| 77 |
+
Use the code below to get started with the model.
|
| 78 |
+
|
| 79 |
+
[More Information Needed]
|
| 80 |
+
|
| 81 |
+
## Training Details
|
| 82 |
+
|
| 83 |
+
### Training Data
|
| 84 |
+
|
| 85 |
+
<!-- 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. -->
|
| 86 |
+
|
| 87 |
+
[More Information Needed]
|
| 88 |
+
|
| 89 |
+
### Training Procedure
|
| 90 |
+
|
| 91 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 92 |
+
|
| 93 |
+
#### Preprocessing [optional]
|
| 94 |
+
|
| 95 |
+
[More Information Needed]
|
| 96 |
+
|
| 97 |
+
|
| 98 |
+
#### Training Hyperparameters
|
| 99 |
+
|
| 100 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 101 |
+
|
| 102 |
+
#### Speeds, Sizes, Times [optional]
|
| 103 |
+
|
| 104 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 105 |
+
|
| 106 |
+
[More Information Needed]
|
| 107 |
+
|
| 108 |
+
## Evaluation
|
| 109 |
+
|
| 110 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 111 |
+
|
| 112 |
+
### Testing Data, Factors & Metrics
|
| 113 |
+
|
| 114 |
+
#### Testing Data
|
| 115 |
+
|
| 116 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 117 |
+
|
| 118 |
+
[More Information Needed]
|
| 119 |
+
|
| 120 |
+
#### Factors
|
| 121 |
+
|
| 122 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 123 |
+
|
| 124 |
+
[More Information Needed]
|
| 125 |
+
|
| 126 |
+
#### Metrics
|
| 127 |
+
|
| 128 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 129 |
+
|
| 130 |
+
[More Information Needed]
|
| 131 |
+
|
| 132 |
+
### Results
|
| 133 |
+
|
| 134 |
+
[More Information Needed]
|
| 135 |
+
|
| 136 |
+
#### Summary
|
| 137 |
+
|
| 138 |
+
|
| 139 |
+
|
| 140 |
+
## Model Examination [optional]
|
| 141 |
+
|
| 142 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 143 |
+
|
| 144 |
+
[More Information Needed]
|
| 145 |
+
|
| 146 |
+
## Environmental Impact
|
| 147 |
+
|
| 148 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 149 |
+
|
| 150 |
+
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).
|
| 151 |
+
|
| 152 |
+
- **Hardware Type:** [More Information Needed]
|
| 153 |
+
- **Hours used:** [More Information Needed]
|
| 154 |
+
- **Cloud Provider:** [More Information Needed]
|
| 155 |
+
- **Compute Region:** [More Information Needed]
|
| 156 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 157 |
+
|
| 158 |
+
## Technical Specifications [optional]
|
| 159 |
+
|
| 160 |
+
### Model Architecture and Objective
|
| 161 |
+
|
| 162 |
+
[More Information Needed]
|
| 163 |
+
|
| 164 |
+
### Compute Infrastructure
|
| 165 |
+
|
| 166 |
+
[More Information Needed]
|
| 167 |
+
|
| 168 |
+
#### Hardware
|
| 169 |
+
|
| 170 |
+
[More Information Needed]
|
| 171 |
+
|
| 172 |
+
#### Software
|
| 173 |
+
|
| 174 |
+
[More Information Needed]
|
| 175 |
+
|
| 176 |
+
## Citation [optional]
|
| 177 |
+
|
| 178 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 179 |
+
|
| 180 |
+
**BibTeX:**
|
| 181 |
+
|
| 182 |
+
[More Information Needed]
|
| 183 |
+
|
| 184 |
+
**APA:**
|
| 185 |
+
|
| 186 |
+
[More Information Needed]
|
| 187 |
+
|
| 188 |
+
## Glossary [optional]
|
| 189 |
+
|
| 190 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 191 |
+
|
| 192 |
+
[More Information Needed]
|
| 193 |
+
|
| 194 |
+
## More Information [optional]
|
| 195 |
+
|
| 196 |
+
[More Information Needed]
|
| 197 |
+
|
| 198 |
+
## Model Card Authors [optional]
|
| 199 |
+
|
| 200 |
+
[More Information Needed]
|
| 201 |
+
|
| 202 |
+
## Model Card Contact
|
| 203 |
+
|
| 204 |
+
[More Information Needed]
|
| 205 |
+
### Framework versions
|
| 206 |
+
|
| 207 |
+
- PEFT 0.17.1
|
checkpoint-155690/adapter_config.json
ADDED
|
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "deepseek-ai/deepseek-coder-6.7b-base",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"corda_config": null,
|
| 7 |
+
"eva_config": null,
|
| 8 |
+
"exclude_modules": null,
|
| 9 |
+
"fan_in_fan_out": false,
|
| 10 |
+
"inference_mode": true,
|
| 11 |
+
"init_lora_weights": true,
|
| 12 |
+
"layer_replication": null,
|
| 13 |
+
"layers_pattern": null,
|
| 14 |
+
"layers_to_transform": null,
|
| 15 |
+
"loftq_config": {},
|
| 16 |
+
"lora_alpha": 32,
|
| 17 |
+
"lora_bias": false,
|
| 18 |
+
"lora_dropout": 0.05,
|
| 19 |
+
"megatron_config": null,
|
| 20 |
+
"megatron_core": "megatron.core",
|
| 21 |
+
"modules_to_save": null,
|
| 22 |
+
"peft_type": "LORA",
|
| 23 |
+
"qalora_group_size": 16,
|
| 24 |
+
"r": 8,
|
| 25 |
+
"rank_pattern": {},
|
| 26 |
+
"revision": null,
|
| 27 |
+
"target_modules": [
|
| 28 |
+
"q_proj",
|
| 29 |
+
"v_proj"
|
| 30 |
+
],
|
| 31 |
+
"target_parameters": null,
|
| 32 |
+
"task_type": "CAUSAL_LM",
|
| 33 |
+
"trainable_token_indices": null,
|
| 34 |
+
"use_dora": false,
|
| 35 |
+
"use_qalora": false,
|
| 36 |
+
"use_rslora": false
|
| 37 |
+
}
|
checkpoint-155690/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d43e40e459b2cfa87b4d5f181291d365764486e5d05dd96c491317baf863e0c6
|
| 3 |
+
size 541442872
|
checkpoint-155690/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:53d388d20f91a67cb2f09889cb88b99d4f712e08cf1294fd78db38796254e9f1
|
| 3 |
+
size 33664331
|
checkpoint-155690/rng_state_0.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:90d7013d5fc16d5fd1229460424a7b2fe19b3253d0fd7857c1f4c7bb3ed5672a
|
| 3 |
+
size 15429
|
checkpoint-155690/rng_state_1.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:23eb78fbbb7ceb06a5822ab54331122cfac4883f692478b5f2d8ea16811383da
|
| 3 |
+
size 15429
|
checkpoint-155690/rng_state_2.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5b420c951f4fad80bbcc8fbce0f0133f0104272cbfba9b0534d5dc2faa9a5c28
|
| 3 |
+
size 15429
|
checkpoint-155690/rng_state_3.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:543ea08878f6308f59bbedd61d60dc2c5f2bba7efa7c3769a3847c40767db25e
|
| 3 |
+
size 15429
|
checkpoint-155690/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b1772622b0581d64e798fe55ba23ce81e27cb895e9060ef0933ac35621ac596b
|
| 3 |
+
size 1383
|
checkpoint-155690/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:341f5ec5c09e31e4ea7ae5fe4f439d632feab7f6097b51a8f48071f1ea1c9b84
|
| 3 |
+
size 1465
|
checkpoint-155690/special_tokens_map.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<｜begin▁of▁sentence｜>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": true,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "<｜end▁of▁sentence｜>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": true,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "<｜end▁of▁sentence｜>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": true,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
}
|
| 23 |
+
}
|
checkpoint-155690/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-155690/tokenizer_config.json
ADDED
|
@@ -0,0 +1,194 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"add_prefix_space": null,
|
| 5 |
+
"added_tokens_decoder": {
|
| 6 |
+
"32000": {
|
| 7 |
+
"content": "õ",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": true,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false,
|
| 12 |
+
"special": false
|
| 13 |
+
},
|
| 14 |
+
"32001": {
|
| 15 |
+
"content": "÷",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": true,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false,
|
| 20 |
+
"special": false
|
| 21 |
+
},
|
| 22 |
+
"32002": {
|
| 23 |
+
"content": "Á",
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"normalized": true,
|
| 26 |
+
"rstrip": false,
|
| 27 |
+
"single_word": false,
|
| 28 |
+
"special": false
|
| 29 |
+
},
|
| 30 |
+
"32003": {
|
| 31 |
+
"content": "ý",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": true,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false,
|
| 36 |
+
"special": false
|
| 37 |
+
},
|
| 38 |
+
"32004": {
|
| 39 |
+
"content": "À",
|
| 40 |
+
"lstrip": false,
|
| 41 |
+
"normalized": true,
|
| 42 |
+
"rstrip": false,
|
| 43 |
+
"single_word": false,
|
| 44 |
+
"special": false
|
| 45 |
+
},
|
| 46 |
+
"32005": {
|
| 47 |
+
"content": "ÿ",
|
| 48 |
+
"lstrip": false,
|
| 49 |
+
"normalized": true,
|
| 50 |
+
"rstrip": false,
|
| 51 |
+
"single_word": false,
|
| 52 |
+
"special": false
|
| 53 |
+
},
|
| 54 |
+
"32006": {
|
| 55 |
+
"content": "ø",
|
| 56 |
+
"lstrip": false,
|
| 57 |
+
"normalized": true,
|
| 58 |
+
"rstrip": false,
|
| 59 |
+
"single_word": false,
|
| 60 |
+
"special": false
|
| 61 |
+
},
|
| 62 |
+
"32007": {
|
| 63 |
+
"content": "ú",
|
| 64 |
+
"lstrip": false,
|
| 65 |
+
"normalized": true,
|
| 66 |
+
"rstrip": false,
|
| 67 |
+
"single_word": false,
|
| 68 |
+
"special": false
|
| 69 |
+
},
|
| 70 |
+
"32008": {
|
| 71 |
+
"content": "þ",
|
| 72 |
+
"lstrip": false,
|
| 73 |
+
"normalized": true,
|
| 74 |
+
"rstrip": false,
|
| 75 |
+
"single_word": false,
|
| 76 |
+
"special": false
|
| 77 |
+
},
|
| 78 |
+
"32009": {
|
| 79 |
+
"content": "ü",
|
| 80 |
+
"lstrip": false,
|
| 81 |
+
"normalized": true,
|
| 82 |
+
"rstrip": false,
|
| 83 |
+
"single_word": false,
|
| 84 |
+
"special": false
|
| 85 |
+
},
|
| 86 |
+
"32010": {
|
| 87 |
+
"content": "ù",
|
| 88 |
+
"lstrip": false,
|
| 89 |
+
"normalized": true,
|
| 90 |
+
"rstrip": false,
|
| 91 |
+
"single_word": false,
|
| 92 |
+
"special": false
|
| 93 |
+
},
|
| 94 |
+
"32011": {
|
| 95 |
+
"content": "ö",
|
| 96 |
+
"lstrip": false,
|
| 97 |
+
"normalized": true,
|
| 98 |
+
"rstrip": false,
|
| 99 |
+
"single_word": false,
|
| 100 |
+
"special": false
|
| 101 |
+
},
|
| 102 |
+
"32012": {
|
| 103 |
+
"content": "û",
|
| 104 |
+
"lstrip": false,
|
| 105 |
+
"normalized": true,
|
| 106 |
+
"rstrip": false,
|
| 107 |
+
"single_word": false,
|
| 108 |
+
"special": false
|
| 109 |
+
},
|
| 110 |
+
"32013": {
|
| 111 |
+
"content": "<｜begin▁of▁sentence｜>",
|
| 112 |
+
"lstrip": false,
|
| 113 |
+
"normalized": true,
|
| 114 |
+
"rstrip": false,
|
| 115 |
+
"single_word": false,
|
| 116 |
+
"special": true
|
| 117 |
+
},
|
| 118 |
+
"32014": {
|
| 119 |
+
"content": "<｜end▁of▁sentence｜>",
|
| 120 |
+
"lstrip": false,
|
| 121 |
+
"normalized": true,
|
| 122 |
+
"rstrip": false,
|
| 123 |
+
"single_word": false,
|
| 124 |
+
"special": true
|
| 125 |
+
},
|
| 126 |
+
"32015": {
|
| 127 |
+
"content": "<｜fim▁hole｜>",
|
| 128 |
+
"lstrip": false,
|
| 129 |
+
"normalized": true,
|
| 130 |
+
"rstrip": false,
|
| 131 |
+
"single_word": false,
|
| 132 |
+
"special": false
|
| 133 |
+
},
|
| 134 |
+
"32016": {
|
| 135 |
+
"content": "<｜fim▁begin｜>",
|
| 136 |
+
"lstrip": false,
|
| 137 |
+
"normalized": true,
|
| 138 |
+
"rstrip": false,
|
| 139 |
+
"single_word": false,
|
| 140 |
+
"special": false
|
| 141 |
+
},
|
| 142 |
+
"32017": {
|
| 143 |
+
"content": "<｜fim▁end｜>",
|
| 144 |
+
"lstrip": false,
|
| 145 |
+
"normalized": true,
|
| 146 |
+
"rstrip": false,
|
| 147 |
+
"single_word": false,
|
| 148 |
+
"special": false
|
| 149 |
+
},
|
| 150 |
+
"32018": {
|
| 151 |
+
"content": "<pad>",
|
| 152 |
+
"lstrip": false,
|
| 153 |
+
"normalized": true,
|
| 154 |
+
"rstrip": false,
|
| 155 |
+
"single_word": false,
|
| 156 |
+
"special": false
|
| 157 |
+
},
|
| 158 |
+
"32019": {
|
| 159 |
+
"content": "<|User|>",
|
| 160 |
+
"lstrip": false,
|
| 161 |
+
"normalized": true,
|
| 162 |
+
"rstrip": false,
|
| 163 |
+
"single_word": false,
|
| 164 |
+
"special": false
|
| 165 |
+
},
|
| 166 |
+
"32020": {
|
| 167 |
+
"content": "<|Assistant|>",
|
| 168 |
+
"lstrip": false,
|
| 169 |
+
"normalized": true,
|
| 170 |
+
"rstrip": false,
|
| 171 |
+
"single_word": false,
|
| 172 |
+
"special": false
|
| 173 |
+
},
|
| 174 |
+
"32021": {
|
| 175 |
+
"content": "<|EOT|>",
|
| 176 |
+
"lstrip": false,
|
| 177 |
+
"normalized": true,
|
| 178 |
+
"rstrip": false,
|
| 179 |
+
"single_word": false,
|
| 180 |
+
"special": false
|
| 181 |
+
}
|
| 182 |
+
},
|
| 183 |
+
"bos_token": "<｜begin▁of▁sentence｜>",
|
| 184 |
+
"clean_up_tokenization_spaces": false,
|
| 185 |
+
"eos_token": "<｜end▁of▁sentence｜>",
|
| 186 |
+
"extra_special_tokens": {},
|
| 187 |
+
"legacy": true,
|
| 188 |
+
"model_max_length": 16384,
|
| 189 |
+
"pad_token": "<｜end▁of▁sentence｜>",
|
| 190 |
+
"sp_model_kwargs": {},
|
| 191 |
+
"tokenizer_class": "LlamaTokenizerFast",
|
| 192 |
+
"unk_token": null,
|
| 193 |
+
"use_default_system_prompt": false
|
| 194 |
+
}
|
checkpoint-155690/trainer_state.json
ADDED
|
@@ -0,0 +1,2603 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 10.0,
|
| 6 |
+
"eval_steps": 3114,
|
| 7 |
+
"global_step": 155690,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.03211510052026463,
|
| 14 |
+
"grad_norm": 0.59400475025177,
|
| 15 |
+
"learning_rate": 0.0003989316376560259,
|
| 16 |
+
"loss": 0.4657,
|
| 17 |
+
"step": 500
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.06423020104052926,
|
| 21 |
+
"grad_norm": 0.6175355315208435,
|
| 22 |
+
"learning_rate": 0.0003978611343053504,
|
| 23 |
+
"loss": 0.3896,
|
| 24 |
+
"step": 1000
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.09634530156079389,
|
| 28 |
+
"grad_norm": 0.6760411858558655,
|
| 29 |
+
"learning_rate": 0.0003967906309546749,
|
| 30 |
+
"loss": 0.3524,
|
| 31 |
+
"step": 1500
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.12846040208105852,
|
| 35 |
+
"grad_norm": 0.610696017742157,
|
| 36 |
+
"learning_rate": 0.00039572012760399943,
|
| 37 |
+
"loss": 0.3337,
|
| 38 |
+
"step": 2000
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.16057550260132314,
|
| 42 |
+
"grad_norm": 0.6075437664985657,
|
| 43 |
+
"learning_rate": 0.0003946496242533239,
|
| 44 |
+
"loss": 0.3212,
|
| 45 |
+
"step": 2500
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.19269060312158778,
|
| 49 |
+
"grad_norm": 0.47634950280189514,
|
| 50 |
+
"learning_rate": 0.00039357912090264843,
|
| 51 |
+
"loss": 0.3108,
|
| 52 |
+
"step": 3000
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.2000128460402081,
|
| 56 |
+
"eval_loss": 0.3016771972179413,
|
| 57 |
+
"eval_runtime": 15.733,
|
| 58 |
+
"eval_samples_per_second": 31.78,
|
| 59 |
+
"eval_steps_per_second": 4.004,
|
| 60 |
+
"step": 3114
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"epoch": 0.2248057036418524,
|
| 64 |
+
"grad_norm": 0.5005037784576416,
|
| 65 |
+
"learning_rate": 0.00039250861755197295,
|
| 66 |
+
"loss": 0.304,
|
| 67 |
+
"step": 3500
|
| 68 |
+
},
|
| 69 |
+
{
|
| 70 |
+
"epoch": 0.25692080416211704,
|
| 71 |
+
"grad_norm": 0.4508284628391266,
|
| 72 |
+
"learning_rate": 0.0003914381142012975,
|
| 73 |
+
"loss": 0.2931,
|
| 74 |
+
"step": 4000
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.28903590468238166,
|
| 78 |
+
"grad_norm": 0.5151750445365906,
|
| 79 |
+
"learning_rate": 0.00039036761085062195,
|
| 80 |
+
"loss": 0.2856,
|
| 81 |
+
"step": 4500
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.3211510052026463,
|
| 85 |
+
"grad_norm": 0.4935036301612854,
|
| 86 |
+
"learning_rate": 0.0003892971074999465,
|
| 87 |
+
"loss": 0.2757,
|
| 88 |
+
"step": 5000
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 0.3532661057229109,
|
| 92 |
+
"grad_norm": 0.5727084279060364,
|
| 93 |
+
"learning_rate": 0.000388226604149271,
|
| 94 |
+
"loss": 0.2773,
|
| 95 |
+
"step": 5500
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 0.38538120624317557,
|
| 99 |
+
"grad_norm": 0.5073119401931763,
|
| 100 |
+
"learning_rate": 0.0003871561007985955,
|
| 101 |
+
"loss": 0.2685,
|
| 102 |
+
"step": 6000
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 0.4000256920804162,
|
| 106 |
+
"eval_loss": 0.25506290793418884,
|
| 107 |
+
"eval_runtime": 15.8313,
|
| 108 |
+
"eval_samples_per_second": 31.583,
|
| 109 |
+
"eval_steps_per_second": 3.979,
|
| 110 |
+
"step": 6228
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 0.4174963067634402,
|
| 114 |
+
"grad_norm": 0.7391453981399536,
|
| 115 |
+
"learning_rate": 0.00038608559744792,
|
| 116 |
+
"loss": 0.2662,
|
| 117 |
+
"step": 6500
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 0.4496114072837048,
|
| 121 |
+
"grad_norm": 0.8289486169815063,
|
| 122 |
+
"learning_rate": 0.00038501509409724454,
|
| 123 |
+
"loss": 0.2577,
|
| 124 |
+
"step": 7000
|
| 125 |
+
},
|
| 126 |
+
{
|
| 127 |
+
"epoch": 0.4817265078039694,
|
| 128 |
+
"grad_norm": 0.9032345414161682,
|
| 129 |
+
"learning_rate": 0.00038394459074656906,
|
| 130 |
+
"loss": 0.2567,
|
| 131 |
+
"step": 7500
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 0.5138416083242341,
|
| 135 |
+
"grad_norm": 0.6563591957092285,
|
| 136 |
+
"learning_rate": 0.0003828740873958936,
|
| 137 |
+
"loss": 0.251,
|
| 138 |
+
"step": 8000
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 0.5459567088444987,
|
| 142 |
+
"grad_norm": 0.8996277451515198,
|
| 143 |
+
"learning_rate": 0.0003818035840452181,
|
| 144 |
+
"loss": 0.2519,
|
| 145 |
+
"step": 8500
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 0.5780718093647633,
|
| 149 |
+
"grad_norm": 0.6761796474456787,
|
| 150 |
+
"learning_rate": 0.0003807330806945426,
|
| 151 |
+
"loss": 0.2493,
|
| 152 |
+
"step": 9000
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 0.6000385381206244,
|
| 156 |
+
"eval_loss": 0.2313319444656372,
|
| 157 |
+
"eval_runtime": 15.6731,
|
| 158 |
+
"eval_samples_per_second": 31.902,
|
| 159 |
+
"eval_steps_per_second": 4.02,
|
| 160 |
+
"step": 9342
|
| 161 |
+
},
|
| 162 |
+
{
|
| 163 |
+
"epoch": 0.610186909885028,
|
| 164 |
+
"grad_norm": 0.6171412467956543,
|
| 165 |
+
"learning_rate": 0.0003796625773438671,
|
| 166 |
+
"loss": 0.2461,
|
| 167 |
+
"step": 9500
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 0.6423020104052926,
|
| 171 |
+
"grad_norm": 0.5448698401451111,
|
| 172 |
+
"learning_rate": 0.00037859207399319164,
|
| 173 |
+
"loss": 0.241,
|
| 174 |
+
"step": 10000
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 0.6744171109255572,
|
| 178 |
+
"grad_norm": 0.5607863068580627,
|
| 179 |
+
"learning_rate": 0.0003775215706425161,
|
| 180 |
+
"loss": 0.2452,
|
| 181 |
+
"step": 10500
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 0.7065322114458218,
|
| 185 |
+
"grad_norm": 0.5820897817611694,
|
| 186 |
+
"learning_rate": 0.00037645106729184064,
|
| 187 |
+
"loss": 0.2381,
|
| 188 |
+
"step": 11000
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 0.7386473119660865,
|
| 192 |
+
"grad_norm": 0.47285422682762146,
|
| 193 |
+
"learning_rate": 0.00037538056394116517,
|
| 194 |
+
"loss": 0.2398,
|
| 195 |
+
"step": 11500
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 0.7707624124863511,
|
| 199 |
+
"grad_norm": 0.6115566492080688,
|
| 200 |
+
"learning_rate": 0.0003743100605904897,
|
| 201 |
+
"loss": 0.2335,
|
| 202 |
+
"step": 12000
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 0.8000513841608324,
|
| 206 |
+
"eval_loss": 0.22419464588165283,
|
| 207 |
+
"eval_runtime": 15.6555,
|
| 208 |
+
"eval_samples_per_second": 31.938,
|
| 209 |
+
"eval_steps_per_second": 4.024,
|
| 210 |
+
"step": 12456
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 0.8028775130066157,
|
| 214 |
+
"grad_norm": 0.6582175493240356,
|
| 215 |
+
"learning_rate": 0.00037323955723981417,
|
| 216 |
+
"loss": 0.2306,
|
| 217 |
+
"step": 12500
|
| 218 |
+
},
|
| 219 |
+
{
|
| 220 |
+
"epoch": 0.8349926135268804,
|
| 221 |
+
"grad_norm": 0.6073306798934937,
|
| 222 |
+
"learning_rate": 0.0003721690538891387,
|
| 223 |
+
"loss": 0.2284,
|
| 224 |
+
"step": 13000
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 0.8671077140471449,
|
| 228 |
+
"grad_norm": 0.8297299146652222,
|
| 229 |
+
"learning_rate": 0.0003710985505384632,
|
| 230 |
+
"loss": 0.2284,
|
| 231 |
+
"step": 13500
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 0.8992228145674096,
|
| 235 |
+
"grad_norm": 0.7792572975158691,
|
| 236 |
+
"learning_rate": 0.0003700280471877877,
|
| 237 |
+
"loss": 0.2284,
|
| 238 |
+
"step": 14000
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"epoch": 0.9313379150876743,
|
| 242 |
+
"grad_norm": 0.6355712413787842,
|
| 243 |
+
"learning_rate": 0.0003689575438371122,
|
| 244 |
+
"loss": 0.2278,
|
| 245 |
+
"step": 14500
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 0.9634530156079388,
|
| 249 |
+
"grad_norm": 0.8210628628730774,
|
| 250 |
+
"learning_rate": 0.00036788704048643675,
|
| 251 |
+
"loss": 0.223,
|
| 252 |
+
"step": 15000
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 0.9955681161282035,
|
| 256 |
+
"grad_norm": 0.5225551128387451,
|
| 257 |
+
"learning_rate": 0.0003668165371357613,
|
| 258 |
+
"loss": 0.2223,
|
| 259 |
+
"step": 15500
|
| 260 |
+
},
|
| 261 |
+
{
|
| 262 |
+
"epoch": 1.0000642302010405,
|
| 263 |
+
"eval_loss": 0.2162015736103058,
|
| 264 |
+
"eval_runtime": 15.7328,
|
| 265 |
+
"eval_samples_per_second": 31.781,
|
| 266 |
+
"eval_steps_per_second": 4.004,
|
| 267 |
+
"step": 15570
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 1.0276832166484682,
|
| 271 |
+
"grad_norm": 0.6531597971916199,
|
| 272 |
+
"learning_rate": 0.00036574603378508575,
|
| 273 |
+
"loss": 0.2036,
|
| 274 |
+
"step": 16000
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 1.0597983171687329,
|
| 278 |
+
"grad_norm": 0.7152116298675537,
|
| 279 |
+
"learning_rate": 0.0003646755304344103,
|
| 280 |
+
"loss": 0.2036,
|
| 281 |
+
"step": 16500
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 1.0919134176889973,
|
| 285 |
+
"grad_norm": 0.6521881818771362,
|
| 286 |
+
"learning_rate": 0.0003636050270837348,
|
| 287 |
+
"loss": 0.2006,
|
| 288 |
+
"step": 17000
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 1.124028518209262,
|
| 292 |
+
"grad_norm": 0.7996369004249573,
|
| 293 |
+
"learning_rate": 0.0003625345237330593,
|
| 294 |
+
"loss": 0.2046,
|
| 295 |
+
"step": 17500
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 1.1561436187295266,
|
| 299 |
+
"grad_norm": 0.5365395545959473,
|
| 300 |
+
"learning_rate": 0.0003614640203823838,
|
| 301 |
+
"loss": 0.2019,
|
| 302 |
+
"step": 18000
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 1.1882587192497913,
|
| 306 |
+
"grad_norm": 0.8401092886924744,
|
| 307 |
+
"learning_rate": 0.00036039351703170833,
|
| 308 |
+
"loss": 0.2042,
|
| 309 |
+
"step": 18500
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 1.2000770762412487,
|
| 313 |
+
"eval_loss": 0.20440329611301422,
|
| 314 |
+
"eval_runtime": 15.9564,
|
| 315 |
+
"eval_samples_per_second": 31.335,
|
| 316 |
+
"eval_steps_per_second": 3.948,
|
| 317 |
+
"step": 18684
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 1.2203738197700558,
|
| 321 |
+
"grad_norm": 0.7515975832939148,
|
| 322 |
+
"learning_rate": 0.0003593230136810328,
|
| 323 |
+
"loss": 0.2027,
|
| 324 |
+
"step": 19000
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 1.2524889202903204,
|
| 328 |
+
"grad_norm": 0.5627322196960449,
|
| 329 |
+
"learning_rate": 0.00035825251033035733,
|
| 330 |
+
"loss": 0.205,
|
| 331 |
+
"step": 19500
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 1.2846040208105851,
|
| 335 |
+
"grad_norm": 0.6319966912269592,
|
| 336 |
+
"learning_rate": 0.00035718200697968186,
|
| 337 |
+
"loss": 0.2048,
|
| 338 |
+
"step": 20000
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 1.3167191213308498,
|
| 342 |
+
"grad_norm": 0.5528004765510559,
|
| 343 |
+
"learning_rate": 0.0003561115036290064,
|
| 344 |
+
"loss": 0.1999,
|
| 345 |
+
"step": 20500
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 1.3488342218511145,
|
| 349 |
+
"grad_norm": 0.5572360157966614,
|
| 350 |
+
"learning_rate": 0.00035504100027833086,
|
| 351 |
+
"loss": 0.1957,
|
| 352 |
+
"step": 21000
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 1.3809493223713791,
|
| 356 |
+
"grad_norm": 0.7685332298278809,
|
| 357 |
+
"learning_rate": 0.0003539704969276554,
|
| 358 |
+
"loss": 0.1984,
|
| 359 |
+
"step": 21500
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 1.4000899222814567,
|
| 363 |
+
"eval_loss": 0.19859124720096588,
|
| 364 |
+
"eval_runtime": 15.7983,
|
| 365 |
+
"eval_samples_per_second": 31.649,
|
| 366 |
+
"eval_steps_per_second": 3.988,
|
| 367 |
+
"step": 21798
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 1.4130644228916436,
|
| 371 |
+
"grad_norm": 0.529292643070221,
|
| 372 |
+
"learning_rate": 0.0003528999935769799,
|
| 373 |
+
"loss": 0.2009,
|
| 374 |
+
"step": 22000
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 1.4451795234119083,
|
| 378 |
+
"grad_norm": 0.5322939157485962,
|
| 379 |
+
"learning_rate": 0.0003518294902263044,
|
| 380 |
+
"loss": 0.1986,
|
| 381 |
+
"step": 22500
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 1.477294623932173,
|
| 385 |
+
"grad_norm": 0.6415036916732788,
|
| 386 |
+
"learning_rate": 0.00035075898687562896,
|
| 387 |
+
"loss": 0.1983,
|
| 388 |
+
"step": 23000
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 1.5094097244524374,
|
| 392 |
+
"grad_norm": 0.8364657759666443,
|
| 393 |
+
"learning_rate": 0.0003496884835249535,
|
| 394 |
+
"loss": 0.1948,
|
| 395 |
+
"step": 23500
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 1.541524824972702,
|
| 399 |
+
"grad_norm": 1.2917670011520386,
|
| 400 |
+
"learning_rate": 0.00034861798017427796,
|
| 401 |
+
"loss": 0.1967,
|
| 402 |
+
"step": 24000
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 1.5736399254929667,
|
| 406 |
+
"grad_norm": 0.6391225457191467,
|
| 407 |
+
"learning_rate": 0.0003475474768236025,
|
| 408 |
+
"loss": 0.1993,
|
| 409 |
+
"step": 24500
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 1.6001027683216649,
|
| 413 |
+
"eval_loss": 0.1940152645111084,
|
| 414 |
+
"eval_runtime": 15.6866,
|
| 415 |
+
"eval_samples_per_second": 31.874,
|
| 416 |
+
"eval_steps_per_second": 4.016,
|
| 417 |
+
"step": 24912
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 1.6057550260132314,
|
| 421 |
+
"grad_norm": 0.7363100051879883,
|
| 422 |
+
"learning_rate": 0.000346476973472927,
|
| 423 |
+
"loss": 0.1979,
|
| 424 |
+
"step": 25000
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"epoch": 1.637870126533496,
|
| 428 |
+
"grad_norm": 0.7358267903327942,
|
| 429 |
+
"learning_rate": 0.0003454064701222515,
|
| 430 |
+
"loss": 0.1991,
|
| 431 |
+
"step": 25500
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 1.6699852270537607,
|
| 435 |
+
"grad_norm": 0.6543652415275574,
|
| 436 |
+
"learning_rate": 0.000344335966771576,
|
| 437 |
+
"loss": 0.1934,
|
| 438 |
+
"step": 26000
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 1.7021003275740254,
|
| 442 |
+
"grad_norm": 0.5435949563980103,
|
| 443 |
+
"learning_rate": 0.00034326546342090055,
|
| 444 |
+
"loss": 0.1937,
|
| 445 |
+
"step": 26500
|
| 446 |
+
},
|
| 447 |
+
{
|
| 448 |
+
"epoch": 1.73421542809429,
|
| 449 |
+
"grad_norm": 0.6814190745353699,
|
| 450 |
+
"learning_rate": 0.00034219496007022507,
|
| 451 |
+
"loss": 0.1921,
|
| 452 |
+
"step": 27000
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 1.7663305286145545,
|
| 456 |
+
"grad_norm": 0.611840546131134,
|
| 457 |
+
"learning_rate": 0.00034112445671954954,
|
| 458 |
+
"loss": 0.1889,
|
| 459 |
+
"step": 27500
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 1.7984456291348192,
|
| 463 |
+
"grad_norm": 0.4577610492706299,
|
| 464 |
+
"learning_rate": 0.00034005395336887407,
|
| 465 |
+
"loss": 0.1931,
|
| 466 |
+
"step": 28000
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 1.8001156143618728,
|
| 470 |
+
"eval_loss": 0.18858034908771515,
|
| 471 |
+
"eval_runtime": 15.6877,
|
| 472 |
+
"eval_samples_per_second": 31.872,
|
| 473 |
+
"eval_steps_per_second": 4.016,
|
| 474 |
+
"step": 28026
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 1.8305607296550839,
|
| 478 |
+
"grad_norm": 0.5208987593650818,
|
| 479 |
+
"learning_rate": 0.0003389834500181986,
|
| 480 |
+
"loss": 0.1971,
|
| 481 |
+
"step": 28500
|
| 482 |
+
},
|
| 483 |
+
{
|
| 484 |
+
"epoch": 1.8626758301753483,
|
| 485 |
+
"grad_norm": 0.7604556083679199,
|
| 486 |
+
"learning_rate": 0.00033791294666752307,
|
| 487 |
+
"loss": 0.194,
|
| 488 |
+
"step": 29000
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 1.894790930695613,
|
| 492 |
+
"grad_norm": 0.5700426697731018,
|
| 493 |
+
"learning_rate": 0.0003368424433168476,
|
| 494 |
+
"loss": 0.1939,
|
| 495 |
+
"step": 29500
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 1.9269060312158777,
|
| 499 |
+
"grad_norm": 0.6078197956085205,
|
| 500 |
+
"learning_rate": 0.0003357719399661721,
|
| 501 |
+
"loss": 0.1904,
|
| 502 |
+
"step": 30000
|
| 503 |
+
},
|
| 504 |
+
{
|
| 505 |
+
"epoch": 1.9590211317361423,
|
| 506 |
+
"grad_norm": 0.5726480484008789,
|
| 507 |
+
"learning_rate": 0.0003347014366154966,
|
| 508 |
+
"loss": 0.19,
|
| 509 |
+
"step": 30500
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 1.991136232256407,
|
| 513 |
+
"grad_norm": 0.6116159558296204,
|
| 514 |
+
"learning_rate": 0.0003336309332648211,
|
| 515 |
+
"loss": 0.1887,
|
| 516 |
+
"step": 31000
|
| 517 |
+
},
|
| 518 |
+
{
|
| 519 |
+
"epoch": 2.000128460402081,
|
| 520 |
+
"eval_loss": 0.18762615323066711,
|
| 521 |
+
"eval_runtime": 15.7012,
|
| 522 |
+
"eval_samples_per_second": 31.845,
|
| 523 |
+
"eval_steps_per_second": 4.012,
|
| 524 |
+
"step": 31140
|
| 525 |
+
},
|
| 526 |
+
{
|
| 527 |
+
"epoch": 2.0232513327766717,
|
| 528 |
+
"grad_norm": 0.7668157815933228,
|
| 529 |
+
"learning_rate": 0.00033256042991414565,
|
| 530 |
+
"loss": 0.1784,
|
| 531 |
+
"step": 31500
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 2.0553664332969364,
|
| 535 |
+
"grad_norm": 0.7431900501251221,
|
| 536 |
+
"learning_rate": 0.0003314899265634702,
|
| 537 |
+
"loss": 0.1754,
|
| 538 |
+
"step": 32000
|
| 539 |
+
},
|
| 540 |
+
{
|
| 541 |
+
"epoch": 2.087481533817201,
|
| 542 |
+
"grad_norm": 0.9105784893035889,
|
| 543 |
+
"learning_rate": 0.00033041942321279465,
|
| 544 |
+
"loss": 0.1697,
|
| 545 |
+
"step": 32500
|
| 546 |
+
},
|
| 547 |
+
{
|
| 548 |
+
"epoch": 2.1195966343374657,
|
| 549 |
+
"grad_norm": 0.7251182794570923,
|
| 550 |
+
"learning_rate": 0.0003293489198621192,
|
| 551 |
+
"loss": 0.1739,
|
| 552 |
+
"step": 33000
|
| 553 |
+
},
|
| 554 |
+
{
|
| 555 |
+
"epoch": 2.15171173485773,
|
| 556 |
+
"grad_norm": 0.87636798620224,
|
| 557 |
+
"learning_rate": 0.0003282784165114437,
|
| 558 |
+
"loss": 0.1722,
|
| 559 |
+
"step": 33500
|
| 560 |
+
},
|
| 561 |
+
{
|
| 562 |
+
"epoch": 2.1838268353779946,
|
| 563 |
+
"grad_norm": 0.817030668258667,
|
| 564 |
+
"learning_rate": 0.0003272079131607682,
|
| 565 |
+
"loss": 0.1712,
|
| 566 |
+
"step": 34000
|
| 567 |
+
},
|
| 568 |
+
{
|
| 569 |
+
"epoch": 2.2001413064422892,
|
| 570 |
+
"eval_loss": 0.18303386867046356,
|
| 571 |
+
"eval_runtime": 15.9057,
|
| 572 |
+
"eval_samples_per_second": 31.435,
|
| 573 |
+
"eval_steps_per_second": 3.961,
|
| 574 |
+
"step": 34254
|
| 575 |
+
},
|
| 576 |
+
{
|
| 577 |
+
"epoch": 2.2159419358982593,
|
| 578 |
+
"grad_norm": 0.8336374759674072,
|
| 579 |
+
"learning_rate": 0.0003261374098100927,
|
| 580 |
+
"loss": 0.1757,
|
| 581 |
+
"step": 34500
|
| 582 |
+
},
|
| 583 |
+
{
|
| 584 |
+
"epoch": 2.248057036418524,
|
| 585 |
+
"grad_norm": 0.49993234872817993,
|
| 586 |
+
"learning_rate": 0.00032506690645941723,
|
| 587 |
+
"loss": 0.1777,
|
| 588 |
+
"step": 35000
|
| 589 |
+
},
|
| 590 |
+
{
|
| 591 |
+
"epoch": 2.2801721369387886,
|
| 592 |
+
"grad_norm": 0.6853183507919312,
|
| 593 |
+
"learning_rate": 0.0003239964031087417,
|
| 594 |
+
"loss": 0.173,
|
| 595 |
+
"step": 35500
|
| 596 |
+
},
|
| 597 |
+
{
|
| 598 |
+
"epoch": 2.3122872374590533,
|
| 599 |
+
"grad_norm": 0.7537247538566589,
|
| 600 |
+
"learning_rate": 0.00032292589975806623,
|
| 601 |
+
"loss": 0.1728,
|
| 602 |
+
"step": 36000
|
| 603 |
+
},
|
| 604 |
+
{
|
| 605 |
+
"epoch": 2.344402337979318,
|
| 606 |
+
"grad_norm": 0.6860816478729248,
|
| 607 |
+
"learning_rate": 0.00032185539640739076,
|
| 608 |
+
"loss": 0.174,
|
| 609 |
+
"step": 36500
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 2.3765174384995826,
|
| 613 |
+
"grad_norm": 0.5592321753501892,
|
| 614 |
+
"learning_rate": 0.0003207848930567153,
|
| 615 |
+
"loss": 0.1751,
|
| 616 |
+
"step": 37000
|
| 617 |
+
},
|
| 618 |
+
{
|
| 619 |
+
"epoch": 2.4001541524824974,
|
| 620 |
+
"eval_loss": 0.17932510375976562,
|
| 621 |
+
"eval_runtime": 15.7992,
|
| 622 |
+
"eval_samples_per_second": 31.647,
|
| 623 |
+
"eval_steps_per_second": 3.988,
|
| 624 |
+
"step": 37368
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 2.4086325390198473,
|
| 628 |
+
"grad_norm": 0.6483610272407532,
|
| 629 |
+
"learning_rate": 0.00031971438970603976,
|
| 630 |
+
"loss": 0.1741,
|
| 631 |
+
"step": 37500
|
| 632 |
+
},
|
| 633 |
+
{
|
| 634 |
+
"epoch": 2.4407476395401115,
|
| 635 |
+
"grad_norm": 0.8754846453666687,
|
| 636 |
+
"learning_rate": 0.00031864388635536434,
|
| 637 |
+
"loss": 0.1736,
|
| 638 |
+
"step": 38000
|
| 639 |
+
},
|
| 640 |
+
{
|
| 641 |
+
"epoch": 2.472862740060376,
|
| 642 |
+
"grad_norm": 0.5679237842559814,
|
| 643 |
+
"learning_rate": 0.00031757338300468887,
|
| 644 |
+
"loss": 0.1735,
|
| 645 |
+
"step": 38500
|
| 646 |
+
},
|
| 647 |
+
{
|
| 648 |
+
"epoch": 2.504977840580641,
|
| 649 |
+
"grad_norm": 0.7428104877471924,
|
| 650 |
+
"learning_rate": 0.00031650287965401334,
|
| 651 |
+
"loss": 0.1703,
|
| 652 |
+
"step": 39000
|
| 653 |
+
},
|
| 654 |
+
{
|
| 655 |
+
"epoch": 2.5370929411009056,
|
| 656 |
+
"grad_norm": 0.7946887612342834,
|
| 657 |
+
"learning_rate": 0.00031543237630333787,
|
| 658 |
+
"loss": 0.1717,
|
| 659 |
+
"step": 39500
|
| 660 |
+
},
|
| 661 |
+
{
|
| 662 |
+
"epoch": 2.5692080416211702,
|
| 663 |
+
"grad_norm": 0.4965314269065857,
|
| 664 |
+
"learning_rate": 0.0003143618729526624,
|
| 665 |
+
"loss": 0.1714,
|
| 666 |
+
"step": 40000
|
| 667 |
+
},
|
| 668 |
+
{
|
| 669 |
+
"epoch": 2.600166998522705,
|
| 670 |
+
"eval_loss": 0.17936299741268158,
|
| 671 |
+
"eval_runtime": 15.8296,
|
| 672 |
+
"eval_samples_per_second": 31.586,
|
| 673 |
+
"eval_steps_per_second": 3.98,
|
| 674 |
+
"step": 40482
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 2.601323142141435,
|
| 678 |
+
"grad_norm": 0.9659818410873413,
|
| 679 |
+
"learning_rate": 0.00031329136960198687,
|
| 680 |
+
"loss": 0.1729,
|
| 681 |
+
"step": 40500
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 2.6334382426616996,
|
| 685 |
+
"grad_norm": 0.5570570230484009,
|
| 686 |
+
"learning_rate": 0.0003122208662513114,
|
| 687 |
+
"loss": 0.1726,
|
| 688 |
+
"step": 41000
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 2.6655533431819642,
|
| 692 |
+
"grad_norm": 0.7049115300178528,
|
| 693 |
+
"learning_rate": 0.0003111503629006359,
|
| 694 |
+
"loss": 0.1708,
|
| 695 |
+
"step": 41500
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 2.697668443702229,
|
| 699 |
+
"grad_norm": 0.5560699701309204,
|
| 700 |
+
"learning_rate": 0.0003100798595499604,
|
| 701 |
+
"loss": 0.1706,
|
| 702 |
+
"step": 42000
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 2.729783544222493,
|
| 706 |
+
"grad_norm": 0.6901995539665222,
|
| 707 |
+
"learning_rate": 0.0003090093561992849,
|
| 708 |
+
"loss": 0.168,
|
| 709 |
+
"step": 42500
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 2.7618986447427583,
|
| 713 |
+
"grad_norm": 0.8500509262084961,
|
| 714 |
+
"learning_rate": 0.00030793885284860945,
|
| 715 |
+
"loss": 0.1708,
|
| 716 |
+
"step": 43000
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 2.7940137452630225,
|
| 720 |
+
"grad_norm": 0.6205178499221802,
|
| 721 |
+
"learning_rate": 0.000306868349497934,
|
| 722 |
+
"loss": 0.1736,
|
| 723 |
+
"step": 43500
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 2.8001798445629134,
|
| 727 |
+
"eval_loss": 0.17952795326709747,
|
| 728 |
+
"eval_runtime": 15.7935,
|
| 729 |
+
"eval_samples_per_second": 31.659,
|
| 730 |
+
"eval_steps_per_second": 3.989,
|
| 731 |
+
"step": 43596
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 2.826128845783287,
|
| 735 |
+
"grad_norm": 0.76055508852005,
|
| 736 |
+
"learning_rate": 0.00030579784614725845,
|
| 737 |
+
"loss": 0.1712,
|
| 738 |
+
"step": 44000
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 2.858243946303552,
|
| 742 |
+
"grad_norm": 1.136112093925476,
|
| 743 |
+
"learning_rate": 0.000304727342796583,
|
| 744 |
+
"loss": 0.1708,
|
| 745 |
+
"step": 44500
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 2.8903590468238165,
|
| 749 |
+
"grad_norm": 0.6640391945838928,
|
| 750 |
+
"learning_rate": 0.0003036568394459075,
|
| 751 |
+
"loss": 0.1693,
|
| 752 |
+
"step": 45000
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 2.922474147344081,
|
| 756 |
+
"grad_norm": 0.7601767182350159,
|
| 757 |
+
"learning_rate": 0.000302586336095232,
|
| 758 |
+
"loss": 0.1711,
|
| 759 |
+
"step": 45500
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 2.954589247864346,
|
| 763 |
+
"grad_norm": 0.652157723903656,
|
| 764 |
+
"learning_rate": 0.0003015158327445565,
|
| 765 |
+
"loss": 0.1698,
|
| 766 |
+
"step": 46000
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 2.9867043483846105,
|
| 770 |
+
"grad_norm": 0.8606679439544678,
|
| 771 |
+
"learning_rate": 0.00030044532939388103,
|
| 772 |
+
"loss": 0.168,
|
| 773 |
+
"step": 46500
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 3.0001926906031215,
|
| 777 |
+
"eval_loss": 0.17218953371047974,
|
| 778 |
+
"eval_runtime": 16.1357,
|
| 779 |
+
"eval_samples_per_second": 30.987,
|
| 780 |
+
"eval_steps_per_second": 3.904,
|
| 781 |
+
"step": 46710
|
| 782 |
+
},
|
| 783 |
+
{
|
| 784 |
+
"epoch": 3.018819448904875,
|
| 785 |
+
"grad_norm": 0.5109479427337646,
|
| 786 |
+
"learning_rate": 0.0002993748260432055,
|
| 787 |
+
"loss": 0.1477,
|
| 788 |
+
"step": 47000
|
| 789 |
+
},
|
| 790 |
+
{
|
| 791 |
+
"epoch": 3.05093454942514,
|
| 792 |
+
"grad_norm": 0.9119648337364197,
|
| 793 |
+
"learning_rate": 0.00029830432269253003,
|
| 794 |
+
"loss": 0.1498,
|
| 795 |
+
"step": 47500
|
| 796 |
+
},
|
| 797 |
+
{
|
| 798 |
+
"epoch": 3.0830496499454045,
|
| 799 |
+
"grad_norm": 0.5713444948196411,
|
| 800 |
+
"learning_rate": 0.00029723381934185455,
|
| 801 |
+
"loss": 0.1465,
|
| 802 |
+
"step": 48000
|
| 803 |
+
},
|
| 804 |
+
{
|
| 805 |
+
"epoch": 3.1151647504656688,
|
| 806 |
+
"grad_norm": 0.8740578293800354,
|
| 807 |
+
"learning_rate": 0.0002961633159911791,
|
| 808 |
+
"loss": 0.1487,
|
| 809 |
+
"step": 48500
|
| 810 |
+
},
|
| 811 |
+
{
|
| 812 |
+
"epoch": 3.1472798509859334,
|
| 813 |
+
"grad_norm": 0.7460174560546875,
|
| 814 |
+
"learning_rate": 0.00029509281264050355,
|
| 815 |
+
"loss": 0.1533,
|
| 816 |
+
"step": 49000
|
| 817 |
+
},
|
| 818 |
+
{
|
| 819 |
+
"epoch": 3.179394951506198,
|
| 820 |
+
"grad_norm": 0.6636391878128052,
|
| 821 |
+
"learning_rate": 0.0002940223092898281,
|
| 822 |
+
"loss": 0.1564,
|
| 823 |
+
"step": 49500
|
| 824 |
+
},
|
| 825 |
+
{
|
| 826 |
+
"epoch": 3.2002055366433297,
|
| 827 |
+
"eval_loss": 0.1716606765985489,
|
| 828 |
+
"eval_runtime": 16.0717,
|
| 829 |
+
"eval_samples_per_second": 31.111,
|
| 830 |
+
"eval_steps_per_second": 3.92,
|
| 831 |
+
"step": 49824
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 3.211510052026463,
|
| 835 |
+
"grad_norm": 0.7573930621147156,
|
| 836 |
+
"learning_rate": 0.0002929518059391526,
|
| 837 |
+
"loss": 0.1528,
|
| 838 |
+
"step": 50000
|
| 839 |
+
},
|
| 840 |
+
{
|
| 841 |
+
"epoch": 3.2436251525467275,
|
| 842 |
+
"grad_norm": 0.7488681077957153,
|
| 843 |
+
"learning_rate": 0.0002918813025884771,
|
| 844 |
+
"loss": 0.1522,
|
| 845 |
+
"step": 50500
|
| 846 |
+
},
|
| 847 |
+
{
|
| 848 |
+
"epoch": 3.275740253066992,
|
| 849 |
+
"grad_norm": 0.7012600302696228,
|
| 850 |
+
"learning_rate": 0.0002908107992378016,
|
| 851 |
+
"loss": 0.155,
|
| 852 |
+
"step": 51000
|
| 853 |
+
},
|
| 854 |
+
{
|
| 855 |
+
"epoch": 3.307855353587257,
|
| 856 |
+
"grad_norm": 1.240614891052246,
|
| 857 |
+
"learning_rate": 0.00028974029588712613,
|
| 858 |
+
"loss": 0.1567,
|
| 859 |
+
"step": 51500
|
| 860 |
+
},
|
| 861 |
+
{
|
| 862 |
+
"epoch": 3.3399704541075215,
|
| 863 |
+
"grad_norm": 1.2059004306793213,
|
| 864 |
+
"learning_rate": 0.0002886697925364506,
|
| 865 |
+
"loss": 0.1544,
|
| 866 |
+
"step": 52000
|
| 867 |
+
},
|
| 868 |
+
{
|
| 869 |
+
"epoch": 3.372085554627786,
|
| 870 |
+
"grad_norm": 0.9451314806938171,
|
| 871 |
+
"learning_rate": 0.00028759928918577513,
|
| 872 |
+
"loss": 0.156,
|
| 873 |
+
"step": 52500
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 3.400218382683538,
|
| 877 |
+
"eval_loss": 0.16954921185970306,
|
| 878 |
+
"eval_runtime": 15.8327,
|
| 879 |
+
"eval_samples_per_second": 31.58,
|
| 880 |
+
"eval_steps_per_second": 3.979,
|
| 881 |
+
"step": 52938
|
| 882 |
+
},
|
| 883 |
+
{
|
| 884 |
+
"epoch": 3.404200655148051,
|
| 885 |
+
"grad_norm": 0.8606504797935486,
|
| 886 |
+
"learning_rate": 0.00028652878583509966,
|
| 887 |
+
"loss": 0.1577,
|
| 888 |
+
"step": 53000
|
| 889 |
+
},
|
| 890 |
+
{
|
| 891 |
+
"epoch": 3.436315755668315,
|
| 892 |
+
"grad_norm": 0.8004255294799805,
|
| 893 |
+
"learning_rate": 0.0002854582824844242,
|
| 894 |
+
"loss": 0.1568,
|
| 895 |
+
"step": 53500
|
| 896 |
+
},
|
| 897 |
+
{
|
| 898 |
+
"epoch": 3.4684308561885797,
|
| 899 |
+
"grad_norm": 1.1171952486038208,
|
| 900 |
+
"learning_rate": 0.0002843877791337487,
|
| 901 |
+
"loss": 0.1583,
|
| 902 |
+
"step": 54000
|
| 903 |
+
},
|
| 904 |
+
{
|
| 905 |
+
"epoch": 3.5005459567088444,
|
| 906 |
+
"grad_norm": 0.7299367785453796,
|
| 907 |
+
"learning_rate": 0.00028331727578307324,
|
| 908 |
+
"loss": 0.1594,
|
| 909 |
+
"step": 54500
|
| 910 |
+
},
|
| 911 |
+
{
|
| 912 |
+
"epoch": 3.532661057229109,
|
| 913 |
+
"grad_norm": 1.0551788806915283,
|
| 914 |
+
"learning_rate": 0.00028224677243239777,
|
| 915 |
+
"loss": 0.1578,
|
| 916 |
+
"step": 55000
|
| 917 |
+
},
|
| 918 |
+
{
|
| 919 |
+
"epoch": 3.5647761577493737,
|
| 920 |
+
"grad_norm": 0.7545414566993713,
|
| 921 |
+
"learning_rate": 0.00028117626908172224,
|
| 922 |
+
"loss": 0.1571,
|
| 923 |
+
"step": 55500
|
| 924 |
+
},
|
| 925 |
+
{
|
| 926 |
+
"epoch": 3.5968912582696384,
|
| 927 |
+
"grad_norm": 0.9115778803825378,
|
| 928 |
+
"learning_rate": 0.00028010576573104677,
|
| 929 |
+
"loss": 0.154,
|
| 930 |
+
"step": 56000
|
| 931 |
+
},
|
| 932 |
+
{
|
| 933 |
+
"epoch": 3.6002312287237457,
|
| 934 |
+
"eval_loss": 0.16733905673027039,
|
| 935 |
+
"eval_runtime": 15.7815,
|
| 936 |
+
"eval_samples_per_second": 31.683,
|
| 937 |
+
"eval_steps_per_second": 3.992,
|
| 938 |
+
"step": 56052
|
| 939 |
+
},
|
| 940 |
+
{
|
| 941 |
+
"epoch": 3.629006358789903,
|
| 942 |
+
"grad_norm": 0.6606740951538086,
|
| 943 |
+
"learning_rate": 0.0002790352623803713,
|
| 944 |
+
"loss": 0.1564,
|
| 945 |
+
"step": 56500
|
| 946 |
+
},
|
| 947 |
+
{
|
| 948 |
+
"epoch": 3.6611214593101677,
|
| 949 |
+
"grad_norm": 0.8278652429580688,
|
| 950 |
+
"learning_rate": 0.00027796475902969577,
|
| 951 |
+
"loss": 0.1551,
|
| 952 |
+
"step": 57000
|
| 953 |
+
},
|
| 954 |
+
{
|
| 955 |
+
"epoch": 3.6932365598304324,
|
| 956 |
+
"grad_norm": 0.7000519633293152,
|
| 957 |
+
"learning_rate": 0.0002768942556790203,
|
| 958 |
+
"loss": 0.1552,
|
| 959 |
+
"step": 57500
|
| 960 |
+
},
|
| 961 |
+
{
|
| 962 |
+
"epoch": 3.7253516603506966,
|
| 963 |
+
"grad_norm": 0.7368202805519104,
|
| 964 |
+
"learning_rate": 0.0002758237523283448,
|
| 965 |
+
"loss": 0.157,
|
| 966 |
+
"step": 58000
|
| 967 |
+
},
|
| 968 |
+
{
|
| 969 |
+
"epoch": 3.7574667608709618,
|
| 970 |
+
"grad_norm": 0.7182698845863342,
|
| 971 |
+
"learning_rate": 0.0002747532489776693,
|
| 972 |
+
"loss": 0.1535,
|
| 973 |
+
"step": 58500
|
| 974 |
+
},
|
| 975 |
+
{
|
| 976 |
+
"epoch": 3.789581861391226,
|
| 977 |
+
"grad_norm": 0.9096634387969971,
|
| 978 |
+
"learning_rate": 0.0002736827456269938,
|
| 979 |
+
"loss": 0.1538,
|
| 980 |
+
"step": 59000
|
| 981 |
+
},
|
| 982 |
+
{
|
| 983 |
+
"epoch": 3.800244074763954,
|
| 984 |
+
"eval_loss": 0.16655243933200836,
|
| 985 |
+
"eval_runtime": 15.8093,
|
| 986 |
+
"eval_samples_per_second": 31.627,
|
| 987 |
+
"eval_steps_per_second": 3.985,
|
| 988 |
+
"step": 59166
|
| 989 |
+
},
|
| 990 |
+
{
|
| 991 |
+
"epoch": 3.8216969619114907,
|
| 992 |
+
"grad_norm": 0.7491119503974915,
|
| 993 |
+
"learning_rate": 0.00027261224227631835,
|
| 994 |
+
"loss": 0.1563,
|
| 995 |
+
"step": 59500
|
| 996 |
+
},
|
| 997 |
+
{
|
| 998 |
+
"epoch": 3.8538120624317553,
|
| 999 |
+
"grad_norm": 0.6401111483573914,
|
| 1000 |
+
"learning_rate": 0.0002715417389256429,
|
| 1001 |
+
"loss": 0.152,
|
| 1002 |
+
"step": 60000
|
| 1003 |
+
},
|
| 1004 |
+
{
|
| 1005 |
+
"epoch": 3.88592716295202,
|
| 1006 |
+
"grad_norm": 0.6719266772270203,
|
| 1007 |
+
"learning_rate": 0.00027047123557496735,
|
| 1008 |
+
"loss": 0.1551,
|
| 1009 |
+
"step": 60500
|
| 1010 |
+
},
|
| 1011 |
+
{
|
| 1012 |
+
"epoch": 3.9180422634722847,
|
| 1013 |
+
"grad_norm": 0.5323716402053833,
|
| 1014 |
+
"learning_rate": 0.0002694007322242919,
|
| 1015 |
+
"loss": 0.1545,
|
| 1016 |
+
"step": 61000
|
| 1017 |
+
},
|
| 1018 |
+
{
|
| 1019 |
+
"epoch": 3.9501573639925494,
|
| 1020 |
+
"grad_norm": 0.4854276180267334,
|
| 1021 |
+
"learning_rate": 0.0002683302288736164,
|
| 1022 |
+
"loss": 0.1572,
|
| 1023 |
+
"step": 61500
|
| 1024 |
+
},
|
| 1025 |
+
{
|
| 1026 |
+
"epoch": 3.982272464512814,
|
| 1027 |
+
"grad_norm": 0.5417631268501282,
|
| 1028 |
+
"learning_rate": 0.0002672597255229409,
|
| 1029 |
+
"loss": 0.1539,
|
| 1030 |
+
"step": 62000
|
| 1031 |
+
},
|
| 1032 |
+
{
|
| 1033 |
+
"epoch": 4.000256920804162,
|
| 1034 |
+
"eval_loss": 0.165705144405365,
|
| 1035 |
+
"eval_runtime": 15.8383,
|
| 1036 |
+
"eval_samples_per_second": 31.569,
|
| 1037 |
+
"eval_steps_per_second": 3.978,
|
| 1038 |
+
"step": 62280
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"epoch": 4.014387565033078,
|
| 1042 |
+
"grad_norm": 0.7811856269836426,
|
| 1043 |
+
"learning_rate": 0.0002661892221722654,
|
| 1044 |
+
"loss": 0.1475,
|
| 1045 |
+
"step": 62500
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 4.046502665553343,
|
| 1049 |
+
"grad_norm": 0.7467861175537109,
|
| 1050 |
+
"learning_rate": 0.00026511871882158993,
|
| 1051 |
+
"loss": 0.1333,
|
| 1052 |
+
"step": 63000
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 4.078617766073608,
|
| 1056 |
+
"grad_norm": 1.106714129447937,
|
| 1057 |
+
"learning_rate": 0.0002640482154709144,
|
| 1058 |
+
"loss": 0.1361,
|
| 1059 |
+
"step": 63500
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 4.110732866593873,
|
| 1063 |
+
"grad_norm": 0.7650594115257263,
|
| 1064 |
+
"learning_rate": 0.00026297771212023893,
|
| 1065 |
+
"loss": 0.1437,
|
| 1066 |
+
"step": 64000
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 4.142847967114137,
|
| 1070 |
+
"grad_norm": 0.5561996698379517,
|
| 1071 |
+
"learning_rate": 0.00026190720876956346,
|
| 1072 |
+
"loss": 0.1385,
|
| 1073 |
+
"step": 64500
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 4.174963067634402,
|
| 1077 |
+
"grad_norm": 0.8409940004348755,
|
| 1078 |
+
"learning_rate": 0.000260836705418888,
|
| 1079 |
+
"loss": 0.1388,
|
| 1080 |
+
"step": 65000
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 4.20026976684437,
|
| 1084 |
+
"eval_loss": 0.16242507100105286,
|
| 1085 |
+
"eval_runtime": 15.9549,
|
| 1086 |
+
"eval_samples_per_second": 31.338,
|
| 1087 |
+
"eval_steps_per_second": 3.949,
|
| 1088 |
+
"step": 65394
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 4.207078168154666,
|
| 1092 |
+
"grad_norm": 0.6058255434036255,
|
| 1093 |
+
"learning_rate": 0.00025976620206821246,
|
| 1094 |
+
"loss": 0.1402,
|
| 1095 |
+
"step": 65500
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 4.239193268674931,
|
| 1099 |
+
"grad_norm": 0.8761014938354492,
|
| 1100 |
+
"learning_rate": 0.000258695698717537,
|
| 1101 |
+
"loss": 0.1381,
|
| 1102 |
+
"step": 66000
|
| 1103 |
+
},
|
| 1104 |
+
{
|
| 1105 |
+
"epoch": 4.271308369195196,
|
| 1106 |
+
"grad_norm": 0.6440082788467407,
|
| 1107 |
+
"learning_rate": 0.0002576251953668615,
|
| 1108 |
+
"loss": 0.1405,
|
| 1109 |
+
"step": 66500
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 4.30342346971546,
|
| 1113 |
+
"grad_norm": 0.8914796710014343,
|
| 1114 |
+
"learning_rate": 0.000256554692016186,
|
| 1115 |
+
"loss": 0.1395,
|
| 1116 |
+
"step": 67000
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 4.335538570235725,
|
| 1120 |
+
"grad_norm": 0.7656377553939819,
|
| 1121 |
+
"learning_rate": 0.0002554841886655105,
|
| 1122 |
+
"loss": 0.1361,
|
| 1123 |
+
"step": 67500
|
| 1124 |
+
},
|
| 1125 |
+
{
|
| 1126 |
+
"epoch": 4.367653670755989,
|
| 1127 |
+
"grad_norm": 0.7148778438568115,
|
| 1128 |
+
"learning_rate": 0.00025441368531483504,
|
| 1129 |
+
"loss": 0.1448,
|
| 1130 |
+
"step": 68000
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 4.399768771276254,
|
| 1134 |
+
"grad_norm": 1.0374408960342407,
|
| 1135 |
+
"learning_rate": 0.00025334318196415956,
|
| 1136 |
+
"loss": 0.1406,
|
| 1137 |
+
"step": 68500
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 4.4002826128845784,
|
| 1141 |
+
"eval_loss": 0.16343337297439575,
|
| 1142 |
+
"eval_runtime": 15.842,
|
| 1143 |
+
"eval_samples_per_second": 31.562,
|
| 1144 |
+
"eval_steps_per_second": 3.977,
|
| 1145 |
+
"step": 68508
|
| 1146 |
+
},
|
| 1147 |
+
{
|
| 1148 |
+
"epoch": 4.4318838717965185,
|
| 1149 |
+
"grad_norm": 0.6319938898086548,
|
| 1150 |
+
"learning_rate": 0.0002522726786134841,
|
| 1151 |
+
"loss": 0.1419,
|
| 1152 |
+
"step": 69000
|
| 1153 |
+
},
|
| 1154 |
+
{
|
| 1155 |
+
"epoch": 4.463998972316784,
|
| 1156 |
+
"grad_norm": 0.6749518513679504,
|
| 1157 |
+
"learning_rate": 0.0002512021752628086,
|
| 1158 |
+
"loss": 0.1418,
|
| 1159 |
+
"step": 69500
|
| 1160 |
+
},
|
| 1161 |
+
{
|
| 1162 |
+
"epoch": 4.496114072837048,
|
| 1163 |
+
"grad_norm": 1.1089214086532593,
|
| 1164 |
+
"learning_rate": 0.0002501316719121331,
|
| 1165 |
+
"loss": 0.1403,
|
| 1166 |
+
"step": 70000
|
| 1167 |
+
},
|
| 1168 |
+
{
|
| 1169 |
+
"epoch": 4.528229173357312,
|
| 1170 |
+
"grad_norm": 0.8678436279296875,
|
| 1171 |
+
"learning_rate": 0.0002490611685614576,
|
| 1172 |
+
"loss": 0.1416,
|
| 1173 |
+
"step": 70500
|
| 1174 |
+
},
|
| 1175 |
+
{
|
| 1176 |
+
"epoch": 4.560344273877577,
|
| 1177 |
+
"grad_norm": 0.80596923828125,
|
| 1178 |
+
"learning_rate": 0.00024799066521078214,
|
| 1179 |
+
"loss": 0.1404,
|
| 1180 |
+
"step": 71000
|
| 1181 |
+
},
|
| 1182 |
+
{
|
| 1183 |
+
"epoch": 4.592459374397842,
|
| 1184 |
+
"grad_norm": 0.6812764406204224,
|
| 1185 |
+
"learning_rate": 0.00024692016186010667,
|
| 1186 |
+
"loss": 0.1379,
|
| 1187 |
+
"step": 71500
|
| 1188 |
+
},
|
| 1189 |
+
{
|
| 1190 |
+
"epoch": 4.600295458924786,
|
| 1191 |
+
"eval_loss": 0.15734289586544037,
|
| 1192 |
+
"eval_runtime": 15.806,
|
| 1193 |
+
"eval_samples_per_second": 31.634,
|
| 1194 |
+
"eval_steps_per_second": 3.986,
|
| 1195 |
+
"step": 71622
|
| 1196 |
+
},
|
| 1197 |
+
{
|
| 1198 |
+
"epoch": 4.624574474918107,
|
| 1199 |
+
"grad_norm": 0.6708959341049194,
|
| 1200 |
+
"learning_rate": 0.00024584965850943114,
|
| 1201 |
+
"loss": 0.1421,
|
| 1202 |
+
"step": 72000
|
| 1203 |
+
},
|
| 1204 |
+
{
|
| 1205 |
+
"epoch": 4.656689575438371,
|
| 1206 |
+
"grad_norm": 0.5451516509056091,
|
| 1207 |
+
"learning_rate": 0.00024477915515875567,
|
| 1208 |
+
"loss": 0.1409,
|
| 1209 |
+
"step": 72500
|
| 1210 |
+
},
|
| 1211 |
+
{
|
| 1212 |
+
"epoch": 4.688804675958636,
|
| 1213 |
+
"grad_norm": 0.7876731753349304,
|
| 1214 |
+
"learning_rate": 0.00024370865180808017,
|
| 1215 |
+
"loss": 0.14,
|
| 1216 |
+
"step": 73000
|
| 1217 |
+
},
|
| 1218 |
+
{
|
| 1219 |
+
"epoch": 4.7209197764789,
|
| 1220 |
+
"grad_norm": 0.6321316361427307,
|
| 1221 |
+
"learning_rate": 0.0002426381484574047,
|
| 1222 |
+
"loss": 0.138,
|
| 1223 |
+
"step": 73500
|
| 1224 |
+
},
|
| 1225 |
+
{
|
| 1226 |
+
"epoch": 4.753034876999165,
|
| 1227 |
+
"grad_norm": 0.813981294631958,
|
| 1228 |
+
"learning_rate": 0.0002415676451067292,
|
| 1229 |
+
"loss": 0.1405,
|
| 1230 |
+
"step": 74000
|
| 1231 |
+
},
|
| 1232 |
+
{
|
| 1233 |
+
"epoch": 4.7851499775194295,
|
| 1234 |
+
"grad_norm": 0.8753657341003418,
|
| 1235 |
+
"learning_rate": 0.00024049714175605373,
|
| 1236 |
+
"loss": 0.1407,
|
| 1237 |
+
"step": 74500
|
| 1238 |
+
},
|
| 1239 |
+
{
|
| 1240 |
+
"epoch": 4.800308304964995,
|
| 1241 |
+
"eval_loss": 0.15800152719020844,
|
| 1242 |
+
"eval_runtime": 15.8284,
|
| 1243 |
+
"eval_samples_per_second": 31.589,
|
| 1244 |
+
"eval_steps_per_second": 3.98,
|
| 1245 |
+
"step": 74736
|
| 1246 |
+
},
|
| 1247 |
+
{
|
| 1248 |
+
"epoch": 4.817265078039695,
|
| 1249 |
+
"grad_norm": 0.784956693649292,
|
| 1250 |
+
"learning_rate": 0.00023942663840537822,
|
| 1251 |
+
"loss": 0.1398,
|
| 1252 |
+
"step": 75000
|
| 1253 |
+
},
|
| 1254 |
+
{
|
| 1255 |
+
"epoch": 4.849380178559959,
|
| 1256 |
+
"grad_norm": 0.6395303010940552,
|
| 1257 |
+
"learning_rate": 0.00023835613505470272,
|
| 1258 |
+
"loss": 0.1368,
|
| 1259 |
+
"step": 75500
|
| 1260 |
+
},
|
| 1261 |
+
{
|
| 1262 |
+
"epoch": 4.881495279080223,
|
| 1263 |
+
"grad_norm": 0.9165125489234924,
|
| 1264 |
+
"learning_rate": 0.00023728563170402725,
|
| 1265 |
+
"loss": 0.1398,
|
| 1266 |
+
"step": 76000
|
| 1267 |
+
},
|
| 1268 |
+
{
|
| 1269 |
+
"epoch": 4.913610379600488,
|
| 1270 |
+
"grad_norm": 0.5325254797935486,
|
| 1271 |
+
"learning_rate": 0.00023621512835335175,
|
| 1272 |
+
"loss": 0.1432,
|
| 1273 |
+
"step": 76500
|
| 1274 |
+
},
|
| 1275 |
+
{
|
| 1276 |
+
"epoch": 4.945725480120752,
|
| 1277 |
+
"grad_norm": 0.7633726000785828,
|
| 1278 |
+
"learning_rate": 0.00023514462500267628,
|
| 1279 |
+
"loss": 0.1412,
|
| 1280 |
+
"step": 77000
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 4.9778405806410175,
|
| 1284 |
+
"grad_norm": 0.8984594345092773,
|
| 1285 |
+
"learning_rate": 0.00023407412165200078,
|
| 1286 |
+
"loss": 0.1395,
|
| 1287 |
+
"step": 77500
|
| 1288 |
+
},
|
| 1289 |
+
{
|
| 1290 |
+
"epoch": 5.000321151005203,
|
| 1291 |
+
"eval_loss": 0.15773242712020874,
|
| 1292 |
+
"eval_runtime": 15.867,
|
| 1293 |
+
"eval_samples_per_second": 31.512,
|
| 1294 |
+
"eval_steps_per_second": 3.97,
|
| 1295 |
+
"step": 77850
|
| 1296 |
+
},
|
| 1297 |
+
{
|
| 1298 |
+
"epoch": 5.009955681161282,
|
| 1299 |
+
"grad_norm": 0.7705770134925842,
|
| 1300 |
+
"learning_rate": 0.00023300361830132528,
|
| 1301 |
+
"loss": 0.1357,
|
| 1302 |
+
"step": 78000
|
| 1303 |
+
},
|
| 1304 |
+
{
|
| 1305 |
+
"epoch": 5.042070781681547,
|
| 1306 |
+
"grad_norm": 0.5788760781288147,
|
| 1307 |
+
"learning_rate": 0.0002319331149506498,
|
| 1308 |
+
"loss": 0.1237,
|
| 1309 |
+
"step": 78500
|
| 1310 |
+
},
|
| 1311 |
+
{
|
| 1312 |
+
"epoch": 5.074185882201811,
|
| 1313 |
+
"grad_norm": 1.1300725936889648,
|
| 1314 |
+
"learning_rate": 0.0002308626115999743,
|
| 1315 |
+
"loss": 0.1228,
|
| 1316 |
+
"step": 79000
|
| 1317 |
+
},
|
| 1318 |
+
{
|
| 1319 |
+
"epoch": 5.106300982722076,
|
| 1320 |
+
"grad_norm": 0.787729024887085,
|
| 1321 |
+
"learning_rate": 0.00022979210824929883,
|
| 1322 |
+
"loss": 0.1235,
|
| 1323 |
+
"step": 79500
|
| 1324 |
+
},
|
| 1325 |
+
{
|
| 1326 |
+
"epoch": 5.1384160832423404,
|
| 1327 |
+
"grad_norm": 0.8614232540130615,
|
| 1328 |
+
"learning_rate": 0.00022872160489862333,
|
| 1329 |
+
"loss": 0.1268,
|
| 1330 |
+
"step": 80000
|
| 1331 |
+
},
|
| 1332 |
+
{
|
| 1333 |
+
"epoch": 5.170531183762606,
|
| 1334 |
+
"grad_norm": 0.9982044696807861,
|
| 1335 |
+
"learning_rate": 0.00022765110154794783,
|
| 1336 |
+
"loss": 0.1245,
|
| 1337 |
+
"step": 80500
|
| 1338 |
+
},
|
| 1339 |
+
{
|
| 1340 |
+
"epoch": 5.20033399704541,
|
| 1341 |
+
"eval_loss": 0.1549646407365799,
|
| 1342 |
+
"eval_runtime": 15.9532,
|
| 1343 |
+
"eval_samples_per_second": 31.342,
|
| 1344 |
+
"eval_steps_per_second": 3.949,
|
| 1345 |
+
"step": 80964
|
| 1346 |
+
},
|
| 1347 |
+
{
|
| 1348 |
+
"epoch": 5.20264628428287,
|
| 1349 |
+
"grad_norm": 0.5808855295181274,
|
| 1350 |
+
"learning_rate": 0.00022658059819727236,
|
| 1351 |
+
"loss": 0.1239,
|
| 1352 |
+
"step": 81000
|
| 1353 |
+
},
|
| 1354 |
+
{
|
| 1355 |
+
"epoch": 5.234761384803134,
|
| 1356 |
+
"grad_norm": 0.8479210138320923,
|
| 1357 |
+
"learning_rate": 0.00022551009484659686,
|
| 1358 |
+
"loss": 0.1257,
|
| 1359 |
+
"step": 81500
|
| 1360 |
+
},
|
| 1361 |
+
{
|
| 1362 |
+
"epoch": 5.266876485323399,
|
| 1363 |
+
"grad_norm": 0.7510769963264465,
|
| 1364 |
+
"learning_rate": 0.00022443959149592139,
|
| 1365 |
+
"loss": 0.1265,
|
| 1366 |
+
"step": 82000
|
| 1367 |
+
},
|
| 1368 |
+
{
|
| 1369 |
+
"epoch": 5.298991585843663,
|
| 1370 |
+
"grad_norm": 0.7535855770111084,
|
| 1371 |
+
"learning_rate": 0.00022336908814524589,
|
| 1372 |
+
"loss": 0.126,
|
| 1373 |
+
"step": 82500
|
| 1374 |
+
},
|
| 1375 |
+
{
|
| 1376 |
+
"epoch": 5.3311066863639285,
|
| 1377 |
+
"grad_norm": 1.0075010061264038,
|
| 1378 |
+
"learning_rate": 0.00022229858479457039,
|
| 1379 |
+
"loss": 0.1239,
|
| 1380 |
+
"step": 83000
|
| 1381 |
+
},
|
| 1382 |
+
{
|
| 1383 |
+
"epoch": 5.363221786884193,
|
| 1384 |
+
"grad_norm": 0.5806704163551331,
|
| 1385 |
+
"learning_rate": 0.0002212280814438949,
|
| 1386 |
+
"loss": 0.1287,
|
| 1387 |
+
"step": 83500
|
| 1388 |
+
},
|
| 1389 |
+
{
|
| 1390 |
+
"epoch": 5.395336887404458,
|
| 1391 |
+
"grad_norm": 0.7302008867263794,
|
| 1392 |
+
"learning_rate": 0.00022015757809321947,
|
| 1393 |
+
"loss": 0.1286,
|
| 1394 |
+
"step": 84000
|
| 1395 |
+
},
|
| 1396 |
+
{
|
| 1397 |
+
"epoch": 5.400346843085619,
|
| 1398 |
+
"eval_loss": 0.15586435794830322,
|
| 1399 |
+
"eval_runtime": 15.8878,
|
| 1400 |
+
"eval_samples_per_second": 31.471,
|
| 1401 |
+
"eval_steps_per_second": 3.965,
|
| 1402 |
+
"step": 84078
|
| 1403 |
+
},
|
| 1404 |
+
{
|
| 1405 |
+
"epoch": 5.427451987924722,
|
| 1406 |
+
"grad_norm": 0.7109474539756775,
|
| 1407 |
+
"learning_rate": 0.00021908707474254397,
|
| 1408 |
+
"loss": 0.1306,
|
| 1409 |
+
"step": 84500
|
| 1410 |
+
},
|
| 1411 |
+
{
|
| 1412 |
+
"epoch": 5.459567088444987,
|
| 1413 |
+
"grad_norm": 0.7373353838920593,
|
| 1414 |
+
"learning_rate": 0.0002180165713918685,
|
| 1415 |
+
"loss": 0.1293,
|
| 1416 |
+
"step": 85000
|
| 1417 |
+
},
|
| 1418 |
+
{
|
| 1419 |
+
"epoch": 5.491682188965251,
|
| 1420 |
+
"grad_norm": 0.804830014705658,
|
| 1421 |
+
"learning_rate": 0.000216946068041193,
|
| 1422 |
+
"loss": 0.1292,
|
| 1423 |
+
"step": 85500
|
| 1424 |
+
},
|
| 1425 |
+
{
|
| 1426 |
+
"epoch": 5.5237972894855165,
|
| 1427 |
+
"grad_norm": 0.8162550330162048,
|
| 1428 |
+
"learning_rate": 0.00021587556469051752,
|
| 1429 |
+
"loss": 0.1282,
|
| 1430 |
+
"step": 86000
|
| 1431 |
+
},
|
| 1432 |
+
{
|
| 1433 |
+
"epoch": 5.555912390005781,
|
| 1434 |
+
"grad_norm": 0.7299586534500122,
|
| 1435 |
+
"learning_rate": 0.00021480506133984202,
|
| 1436 |
+
"loss": 0.1223,
|
| 1437 |
+
"step": 86500
|
| 1438 |
+
},
|
| 1439 |
+
{
|
| 1440 |
+
"epoch": 5.588027490526045,
|
| 1441 |
+
"grad_norm": 0.8338757157325745,
|
| 1442 |
+
"learning_rate": 0.00021373455798916652,
|
| 1443 |
+
"loss": 0.1283,
|
| 1444 |
+
"step": 87000
|
| 1445 |
+
},
|
| 1446 |
+
{
|
| 1447 |
+
"epoch": 5.600359689125827,
|
| 1448 |
+
"eval_loss": 0.15210534632205963,
|
| 1449 |
+
"eval_runtime": 16.0632,
|
| 1450 |
+
"eval_samples_per_second": 31.127,
|
| 1451 |
+
"eval_steps_per_second": 3.922,
|
| 1452 |
+
"step": 87192
|
| 1453 |
+
},
|
| 1454 |
+
{
|
| 1455 |
+
"epoch": 5.62014259104631,
|
| 1456 |
+
"grad_norm": 0.6446358561515808,
|
| 1457 |
+
"learning_rate": 0.00021266405463849105,
|
| 1458 |
+
"loss": 0.1242,
|
| 1459 |
+
"step": 87500
|
| 1460 |
+
},
|
| 1461 |
+
{
|
| 1462 |
+
"epoch": 5.652257691566574,
|
| 1463 |
+
"grad_norm": 1.3578524589538574,
|
| 1464 |
+
"learning_rate": 0.00021159355128781555,
|
| 1465 |
+
"loss": 0.1269,
|
| 1466 |
+
"step": 88000
|
| 1467 |
+
},
|
| 1468 |
+
{
|
| 1469 |
+
"epoch": 5.684372792086839,
|
| 1470 |
+
"grad_norm": 0.8587378263473511,
|
| 1471 |
+
"learning_rate": 0.00021052304793714007,
|
| 1472 |
+
"loss": 0.1266,
|
| 1473 |
+
"step": 88500
|
| 1474 |
+
},
|
| 1475 |
+
{
|
| 1476 |
+
"epoch": 5.716487892607104,
|
| 1477 |
+
"grad_norm": 0.6348199248313904,
|
| 1478 |
+
"learning_rate": 0.00020945254458646457,
|
| 1479 |
+
"loss": 0.1269,
|
| 1480 |
+
"step": 89000
|
| 1481 |
+
},
|
| 1482 |
+
{
|
| 1483 |
+
"epoch": 5.748602993127369,
|
| 1484 |
+
"grad_norm": 0.7587723135948181,
|
| 1485 |
+
"learning_rate": 0.00020838204123578907,
|
| 1486 |
+
"loss": 0.1293,
|
| 1487 |
+
"step": 89500
|
| 1488 |
+
},
|
| 1489 |
+
{
|
| 1490 |
+
"epoch": 5.780718093647633,
|
| 1491 |
+
"grad_norm": 0.7418575286865234,
|
| 1492 |
+
"learning_rate": 0.0002073115378851136,
|
| 1493 |
+
"loss": 0.1254,
|
| 1494 |
+
"step": 90000
|
| 1495 |
+
},
|
| 1496 |
+
{
|
| 1497 |
+
"epoch": 5.800372535166035,
|
| 1498 |
+
"eval_loss": 0.14803029596805573,
|
| 1499 |
+
"eval_runtime": 15.7485,
|
| 1500 |
+
"eval_samples_per_second": 31.749,
|
| 1501 |
+
"eval_steps_per_second": 4.0,
|
| 1502 |
+
"step": 90306
|
| 1503 |
+
},
|
| 1504 |
+
{
|
| 1505 |
+
"epoch": 5.812833194167898,
|
| 1506 |
+
"grad_norm": 0.6490494012832642,
|
| 1507 |
+
"learning_rate": 0.0002062410345344381,
|
| 1508 |
+
"loss": 0.1255,
|
| 1509 |
+
"step": 90500
|
| 1510 |
+
},
|
| 1511 |
+
{
|
| 1512 |
+
"epoch": 5.844948294688162,
|
| 1513 |
+
"grad_norm": 0.644496500492096,
|
| 1514 |
+
"learning_rate": 0.00020517053118376263,
|
| 1515 |
+
"loss": 0.125,
|
| 1516 |
+
"step": 91000
|
| 1517 |
+
},
|
| 1518 |
+
{
|
| 1519 |
+
"epoch": 5.8770633952084275,
|
| 1520 |
+
"grad_norm": 0.8341867327690125,
|
| 1521 |
+
"learning_rate": 0.00020410002783308713,
|
| 1522 |
+
"loss": 0.1278,
|
| 1523 |
+
"step": 91500
|
| 1524 |
+
},
|
| 1525 |
+
{
|
| 1526 |
+
"epoch": 5.909178495728692,
|
| 1527 |
+
"grad_norm": 0.49528875946998596,
|
| 1528 |
+
"learning_rate": 0.00020302952448241163,
|
| 1529 |
+
"loss": 0.1295,
|
| 1530 |
+
"step": 92000
|
| 1531 |
+
},
|
| 1532 |
+
{
|
| 1533 |
+
"epoch": 5.941293596248956,
|
| 1534 |
+
"grad_norm": 0.6712813973426819,
|
| 1535 |
+
"learning_rate": 0.00020195902113173615,
|
| 1536 |
+
"loss": 0.1278,
|
| 1537 |
+
"step": 92500
|
| 1538 |
+
},
|
| 1539 |
+
{
|
| 1540 |
+
"epoch": 5.973408696769221,
|
| 1541 |
+
"grad_norm": 0.866651713848114,
|
| 1542 |
+
"learning_rate": 0.00020088851778106065,
|
| 1543 |
+
"loss": 0.1254,
|
| 1544 |
+
"step": 93000
|
| 1545 |
+
},
|
| 1546 |
+
{
|
| 1547 |
+
"epoch": 6.000385381206243,
|
| 1548 |
+
"eval_loss": 0.14452539384365082,
|
| 1549 |
+
"eval_runtime": 15.7786,
|
| 1550 |
+
"eval_samples_per_second": 31.689,
|
| 1551 |
+
"eval_steps_per_second": 3.993,
|
| 1552 |
+
"step": 93420
|
| 1553 |
+
},
|
| 1554 |
+
{
|
| 1555 |
+
"epoch": 6.005523797289485,
|
| 1556 |
+
"grad_norm": 0.5858412384986877,
|
| 1557 |
+
"learning_rate": 0.00019981801443038518,
|
| 1558 |
+
"loss": 0.1246,
|
| 1559 |
+
"step": 93500
|
| 1560 |
+
},
|
| 1561 |
+
{
|
| 1562 |
+
"epoch": 6.03763889780975,
|
| 1563 |
+
"grad_norm": 0.8819634318351746,
|
| 1564 |
+
"learning_rate": 0.00019874751107970968,
|
| 1565 |
+
"loss": 0.1079,
|
| 1566 |
+
"step": 94000
|
| 1567 |
+
},
|
| 1568 |
+
{
|
| 1569 |
+
"epoch": 6.069753998330015,
|
| 1570 |
+
"grad_norm": 0.705180823802948,
|
| 1571 |
+
"learning_rate": 0.00019767700772903418,
|
| 1572 |
+
"loss": 0.1116,
|
| 1573 |
+
"step": 94500
|
| 1574 |
+
},
|
| 1575 |
+
{
|
| 1576 |
+
"epoch": 6.10186909885028,
|
| 1577 |
+
"grad_norm": 0.8040666580200195,
|
| 1578 |
+
"learning_rate": 0.00019660650437835873,
|
| 1579 |
+
"loss": 0.1105,
|
| 1580 |
+
"step": 95000
|
| 1581 |
+
},
|
| 1582 |
+
{
|
| 1583 |
+
"epoch": 6.133984199370544,
|
| 1584 |
+
"grad_norm": 0.9658277630805969,
|
| 1585 |
+
"learning_rate": 0.00019553600102768323,
|
| 1586 |
+
"loss": 0.111,
|
| 1587 |
+
"step": 95500
|
| 1588 |
+
},
|
| 1589 |
+
{
|
| 1590 |
+
"epoch": 6.166099299890809,
|
| 1591 |
+
"grad_norm": 0.656114399433136,
|
| 1592 |
+
"learning_rate": 0.00019446549767700773,
|
| 1593 |
+
"loss": 0.1134,
|
| 1594 |
+
"step": 96000
|
| 1595 |
+
},
|
| 1596 |
+
{
|
| 1597 |
+
"epoch": 6.198214400411073,
|
| 1598 |
+
"grad_norm": 0.7085436582565308,
|
| 1599 |
+
"learning_rate": 0.00019339499432633226,
|
| 1600 |
+
"loss": 0.1129,
|
| 1601 |
+
"step": 96500
|
| 1602 |
+
},
|
| 1603 |
+
{
|
| 1604 |
+
"epoch": 6.200398227246451,
|
| 1605 |
+
"eval_loss": 0.144108846783638,
|
| 1606 |
+
"eval_runtime": 15.7766,
|
| 1607 |
+
"eval_samples_per_second": 31.693,
|
| 1608 |
+
"eval_steps_per_second": 3.993,
|
| 1609 |
+
"step": 96534
|
| 1610 |
+
},
|
| 1611 |
+
{
|
| 1612 |
+
"epoch": 6.2303295009313375,
|
| 1613 |
+
"grad_norm": 0.7406576871871948,
|
| 1614 |
+
"learning_rate": 0.00019232449097565676,
|
| 1615 |
+
"loss": 0.1152,
|
| 1616 |
+
"step": 97000
|
| 1617 |
+
},
|
| 1618 |
+
{
|
| 1619 |
+
"epoch": 6.262444601451603,
|
| 1620 |
+
"grad_norm": 0.9315550327301025,
|
| 1621 |
+
"learning_rate": 0.0001912539876249813,
|
| 1622 |
+
"loss": 0.1109,
|
| 1623 |
+
"step": 97500
|
| 1624 |
+
},
|
| 1625 |
+
{
|
| 1626 |
+
"epoch": 6.294559701971867,
|
| 1627 |
+
"grad_norm": 0.5328162908554077,
|
| 1628 |
+
"learning_rate": 0.0001901834842743058,
|
| 1629 |
+
"loss": 0.1103,
|
| 1630 |
+
"step": 98000
|
| 1631 |
+
},
|
| 1632 |
+
{
|
| 1633 |
+
"epoch": 6.326674802492132,
|
| 1634 |
+
"grad_norm": 0.9557679295539856,
|
| 1635 |
+
"learning_rate": 0.0001891129809236303,
|
| 1636 |
+
"loss": 0.1148,
|
| 1637 |
+
"step": 98500
|
| 1638 |
+
},
|
| 1639 |
+
{
|
| 1640 |
+
"epoch": 6.358789903012396,
|
| 1641 |
+
"grad_norm": 0.7726024985313416,
|
| 1642 |
+
"learning_rate": 0.00018804247757295481,
|
| 1643 |
+
"loss": 0.1142,
|
| 1644 |
+
"step": 99000
|
| 1645 |
+
},
|
| 1646 |
+
{
|
| 1647 |
+
"epoch": 6.390905003532661,
|
| 1648 |
+
"grad_norm": 1.0211020708084106,
|
| 1649 |
+
"learning_rate": 0.00018697197422227931,
|
| 1650 |
+
"loss": 0.1146,
|
| 1651 |
+
"step": 99500
|
| 1652 |
+
},
|
| 1653 |
+
{
|
| 1654 |
+
"epoch": 6.4004110732866595,
|
| 1655 |
+
"eval_loss": 0.14410270750522614,
|
| 1656 |
+
"eval_runtime": 16.0794,
|
| 1657 |
+
"eval_samples_per_second": 31.096,
|
| 1658 |
+
"eval_steps_per_second": 3.918,
|
| 1659 |
+
"step": 99648
|
| 1660 |
+
},
|
| 1661 |
+
{
|
| 1662 |
+
"epoch": 6.423020104052926,
|
| 1663 |
+
"grad_norm": 0.896350085735321,
|
| 1664 |
+
"learning_rate": 0.00018590147087160384,
|
| 1665 |
+
"loss": 0.1161,
|
| 1666 |
+
"step": 100000
|
| 1667 |
+
},
|
| 1668 |
+
{
|
| 1669 |
+
"epoch": 6.455135204573191,
|
| 1670 |
+
"grad_norm": 0.7463588714599609,
|
| 1671 |
+
"learning_rate": 0.00018483096752092834,
|
| 1672 |
+
"loss": 0.1143,
|
| 1673 |
+
"step": 100500
|
| 1674 |
+
},
|
| 1675 |
+
{
|
| 1676 |
+
"epoch": 6.487250305093455,
|
| 1677 |
+
"grad_norm": 0.8884052038192749,
|
| 1678 |
+
"learning_rate": 0.00018376046417025287,
|
| 1679 |
+
"loss": 0.1152,
|
| 1680 |
+
"step": 101000
|
| 1681 |
+
},
|
| 1682 |
+
{
|
| 1683 |
+
"epoch": 6.519365405613719,
|
| 1684 |
+
"grad_norm": 0.529490053653717,
|
| 1685 |
+
"learning_rate": 0.00018268996081957737,
|
| 1686 |
+
"loss": 0.1132,
|
| 1687 |
+
"step": 101500
|
| 1688 |
+
},
|
| 1689 |
+
{
|
| 1690 |
+
"epoch": 6.551480506133984,
|
| 1691 |
+
"grad_norm": 1.0092920064926147,
|
| 1692 |
+
"learning_rate": 0.00018161945746890187,
|
| 1693 |
+
"loss": 0.1126,
|
| 1694 |
+
"step": 102000
|
| 1695 |
+
},
|
| 1696 |
+
{
|
| 1697 |
+
"epoch": 6.5835956066542485,
|
| 1698 |
+
"grad_norm": 0.6666002869606018,
|
| 1699 |
+
"learning_rate": 0.0001805489541182264,
|
| 1700 |
+
"loss": 0.1166,
|
| 1701 |
+
"step": 102500
|
| 1702 |
+
},
|
| 1703 |
+
{
|
| 1704 |
+
"epoch": 6.600423919326867,
|
| 1705 |
+
"eval_loss": 0.14196071028709412,
|
| 1706 |
+
"eval_runtime": 15.9418,
|
| 1707 |
+
"eval_samples_per_second": 31.364,
|
| 1708 |
+
"eval_steps_per_second": 3.952,
|
| 1709 |
+
"step": 102762
|
| 1710 |
+
},
|
| 1711 |
+
{
|
| 1712 |
+
"epoch": 6.615710707174514,
|
| 1713 |
+
"grad_norm": 0.6810824871063232,
|
| 1714 |
+
"learning_rate": 0.00017947845076755092,
|
| 1715 |
+
"loss": 0.1116,
|
| 1716 |
+
"step": 103000
|
| 1717 |
+
},
|
| 1718 |
+
{
|
| 1719 |
+
"epoch": 6.647825807694778,
|
| 1720 |
+
"grad_norm": 0.6888949275016785,
|
| 1721 |
+
"learning_rate": 0.00017840794741687542,
|
| 1722 |
+
"loss": 0.1163,
|
| 1723 |
+
"step": 103500
|
| 1724 |
+
},
|
| 1725 |
+
{
|
| 1726 |
+
"epoch": 6.679940908215043,
|
| 1727 |
+
"grad_norm": 0.6990634799003601,
|
| 1728 |
+
"learning_rate": 0.00017733744406619995,
|
| 1729 |
+
"loss": 0.1161,
|
| 1730 |
+
"step": 104000
|
| 1731 |
+
},
|
| 1732 |
+
{
|
| 1733 |
+
"epoch": 6.712056008735307,
|
| 1734 |
+
"grad_norm": 1.3494635820388794,
|
| 1735 |
+
"learning_rate": 0.00017626694071552445,
|
| 1736 |
+
"loss": 0.1118,
|
| 1737 |
+
"step": 104500
|
| 1738 |
+
},
|
| 1739 |
+
{
|
| 1740 |
+
"epoch": 6.744171109255572,
|
| 1741 |
+
"grad_norm": 0.7329450249671936,
|
| 1742 |
+
"learning_rate": 0.00017519643736484898,
|
| 1743 |
+
"loss": 0.1142,
|
| 1744 |
+
"step": 105000
|
| 1745 |
+
},
|
| 1746 |
+
{
|
| 1747 |
+
"epoch": 6.7762862097758365,
|
| 1748 |
+
"grad_norm": 0.7146152257919312,
|
| 1749 |
+
"learning_rate": 0.00017412593401417348,
|
| 1750 |
+
"loss": 0.1159,
|
| 1751 |
+
"step": 105500
|
| 1752 |
+
},
|
| 1753 |
+
{
|
| 1754 |
+
"epoch": 6.800436765367076,
|
| 1755 |
+
"eval_loss": 0.14355608820915222,
|
| 1756 |
+
"eval_runtime": 15.7995,
|
| 1757 |
+
"eval_samples_per_second": 31.647,
|
| 1758 |
+
"eval_steps_per_second": 3.987,
|
| 1759 |
+
"step": 105876
|
| 1760 |
+
},
|
| 1761 |
+
{
|
| 1762 |
+
"epoch": 6.808401310296102,
|
| 1763 |
+
"grad_norm": 0.6309993267059326,
|
| 1764 |
+
"learning_rate": 0.00017305543066349798,
|
| 1765 |
+
"loss": 0.1149,
|
| 1766 |
+
"step": 106000
|
| 1767 |
+
},
|
| 1768 |
+
{
|
| 1769 |
+
"epoch": 6.840516410816366,
|
| 1770 |
+
"grad_norm": 0.9224129915237427,
|
| 1771 |
+
"learning_rate": 0.0001719849273128225,
|
| 1772 |
+
"loss": 0.1124,
|
| 1773 |
+
"step": 106500
|
| 1774 |
+
},
|
| 1775 |
+
{
|
| 1776 |
+
"epoch": 6.87263151133663,
|
| 1777 |
+
"grad_norm": 0.6489787697792053,
|
| 1778 |
+
"learning_rate": 0.000170914423962147,
|
| 1779 |
+
"loss": 0.117,
|
| 1780 |
+
"step": 107000
|
| 1781 |
+
},
|
| 1782 |
+
{
|
| 1783 |
+
"epoch": 6.904746611856895,
|
| 1784 |
+
"grad_norm": 0.8559143543243408,
|
| 1785 |
+
"learning_rate": 0.00016984392061147153,
|
| 1786 |
+
"loss": 0.1159,
|
| 1787 |
+
"step": 107500
|
| 1788 |
+
},
|
| 1789 |
+
{
|
| 1790 |
+
"epoch": 6.936861712377159,
|
| 1791 |
+
"grad_norm": 0.6018438339233398,
|
| 1792 |
+
"learning_rate": 0.00016877341726079603,
|
| 1793 |
+
"loss": 0.1125,
|
| 1794 |
+
"step": 108000
|
| 1795 |
+
},
|
| 1796 |
+
{
|
| 1797 |
+
"epoch": 6.9689768128974245,
|
| 1798 |
+
"grad_norm": 0.4429938793182373,
|
| 1799 |
+
"learning_rate": 0.00016770291391012053,
|
| 1800 |
+
"loss": 0.1155,
|
| 1801 |
+
"step": 108500
|
| 1802 |
+
},
|
| 1803 |
+
{
|
| 1804 |
+
"epoch": 7.000449611407284,
|
| 1805 |
+
"eval_loss": 0.1406981498003006,
|
| 1806 |
+
"eval_runtime": 15.8026,
|
| 1807 |
+
"eval_samples_per_second": 31.64,
|
| 1808 |
+
"eval_steps_per_second": 3.987,
|
| 1809 |
+
"step": 108990
|
| 1810 |
+
},
|
| 1811 |
+
{
|
| 1812 |
+
"epoch": 7.001091913417689,
|
| 1813 |
+
"grad_norm": 0.6586825847625732,
|
| 1814 |
+
"learning_rate": 0.00016663241055944506,
|
| 1815 |
+
"loss": 0.1134,
|
| 1816 |
+
"step": 109000
|
| 1817 |
+
},
|
| 1818 |
+
{
|
| 1819 |
+
"epoch": 7.033207013937954,
|
| 1820 |
+
"grad_norm": 0.708396315574646,
|
| 1821 |
+
"learning_rate": 0.00016556190720876956,
|
| 1822 |
+
"loss": 0.096,
|
| 1823 |
+
"step": 109500
|
| 1824 |
+
},
|
| 1825 |
+
{
|
| 1826 |
+
"epoch": 7.065322114458218,
|
| 1827 |
+
"grad_norm": 0.5787486433982849,
|
| 1828 |
+
"learning_rate": 0.00016449140385809408,
|
| 1829 |
+
"loss": 0.097,
|
| 1830 |
+
"step": 110000
|
| 1831 |
+
},
|
| 1832 |
+
{
|
| 1833 |
+
"epoch": 7.097437214978483,
|
| 1834 |
+
"grad_norm": 0.5055108666419983,
|
| 1835 |
+
"learning_rate": 0.0001634209005074186,
|
| 1836 |
+
"loss": 0.0978,
|
| 1837 |
+
"step": 110500
|
| 1838 |
+
},
|
| 1839 |
+
{
|
| 1840 |
+
"epoch": 7.1295523154987475,
|
| 1841 |
+
"grad_norm": 0.6582817435264587,
|
| 1842 |
+
"learning_rate": 0.0001623503971567431,
|
| 1843 |
+
"loss": 0.1009,
|
| 1844 |
+
"step": 111000
|
| 1845 |
+
},
|
| 1846 |
+
{
|
| 1847 |
+
"epoch": 7.161667416019013,
|
| 1848 |
+
"grad_norm": 0.6636567711830139,
|
| 1849 |
+
"learning_rate": 0.00016127989380606764,
|
| 1850 |
+
"loss": 0.1006,
|
| 1851 |
+
"step": 111500
|
| 1852 |
+
},
|
| 1853 |
+
{
|
| 1854 |
+
"epoch": 7.193782516539277,
|
| 1855 |
+
"grad_norm": 0.5881006121635437,
|
| 1856 |
+
"learning_rate": 0.00016020939045539214,
|
| 1857 |
+
"loss": 0.1012,
|
| 1858 |
+
"step": 112000
|
| 1859 |
+
},
|
| 1860 |
+
{
|
| 1861 |
+
"epoch": 7.200462457447491,
|
| 1862 |
+
"eval_loss": 0.14193466305732727,
|
| 1863 |
+
"eval_runtime": 15.7762,
|
| 1864 |
+
"eval_samples_per_second": 31.693,
|
| 1865 |
+
"eval_steps_per_second": 3.993,
|
| 1866 |
+
"step": 112104
|
| 1867 |
+
},
|
| 1868 |
+
{
|
| 1869 |
+
"epoch": 7.225897617059541,
|
| 1870 |
+
"grad_norm": 0.740288496017456,
|
| 1871 |
+
"learning_rate": 0.00015913888710471664,
|
| 1872 |
+
"loss": 0.0994,
|
| 1873 |
+
"step": 112500
|
| 1874 |
+
},
|
| 1875 |
+
{
|
| 1876 |
+
"epoch": 7.258012717579806,
|
| 1877 |
+
"grad_norm": 0.7913209199905396,
|
| 1878 |
+
"learning_rate": 0.00015806838375404116,
|
| 1879 |
+
"loss": 0.099,
|
| 1880 |
+
"step": 113000
|
| 1881 |
+
},
|
| 1882 |
+
{
|
| 1883 |
+
"epoch": 7.29012781810007,
|
| 1884 |
+
"grad_norm": 1.0897345542907715,
|
| 1885 |
+
"learning_rate": 0.00015699788040336566,
|
| 1886 |
+
"loss": 0.1003,
|
| 1887 |
+
"step": 113500
|
| 1888 |
+
},
|
| 1889 |
+
{
|
| 1890 |
+
"epoch": 7.3222429186203355,
|
| 1891 |
+
"grad_norm": 0.47759073972702026,
|
| 1892 |
+
"learning_rate": 0.0001559273770526902,
|
| 1893 |
+
"loss": 0.1028,
|
| 1894 |
+
"step": 114000
|
| 1895 |
+
},
|
| 1896 |
+
{
|
| 1897 |
+
"epoch": 7.3543580191406,
|
| 1898 |
+
"grad_norm": 1.589148998260498,
|
| 1899 |
+
"learning_rate": 0.0001548568737020147,
|
| 1900 |
+
"loss": 0.1009,
|
| 1901 |
+
"step": 114500
|
| 1902 |
+
},
|
| 1903 |
+
{
|
| 1904 |
+
"epoch": 7.386473119660865,
|
| 1905 |
+
"grad_norm": 0.8265223503112793,
|
| 1906 |
+
"learning_rate": 0.00015378637035133922,
|
| 1907 |
+
"loss": 0.0994,
|
| 1908 |
+
"step": 115000
|
| 1909 |
+
},
|
| 1910 |
+
{
|
| 1911 |
+
"epoch": 7.4004753034877,
|
| 1912 |
+
"eval_loss": 0.1418759822845459,
|
| 1913 |
+
"eval_runtime": 15.7405,
|
| 1914 |
+
"eval_samples_per_second": 31.765,
|
| 1915 |
+
"eval_steps_per_second": 4.002,
|
| 1916 |
+
"step": 115218
|
| 1917 |
+
},
|
| 1918 |
+
{
|
| 1919 |
+
"epoch": 7.418588220181129,
|
| 1920 |
+
"grad_norm": 0.7189416289329529,
|
| 1921 |
+
"learning_rate": 0.00015271586700066372,
|
| 1922 |
+
"loss": 0.1032,
|
| 1923 |
+
"step": 115500
|
| 1924 |
+
},
|
| 1925 |
+
{
|
| 1926 |
+
"epoch": 7.450703320701394,
|
| 1927 |
+
"grad_norm": 0.6635364890098572,
|
| 1928 |
+
"learning_rate": 0.00015164536364998822,
|
| 1929 |
+
"loss": 0.0996,
|
| 1930 |
+
"step": 116000
|
| 1931 |
+
},
|
| 1932 |
+
{
|
| 1933 |
+
"epoch": 7.482818421221658,
|
| 1934 |
+
"grad_norm": 1.0325865745544434,
|
| 1935 |
+
"learning_rate": 0.00015057486029931274,
|
| 1936 |
+
"loss": 0.1035,
|
| 1937 |
+
"step": 116500
|
| 1938 |
+
},
|
| 1939 |
+
{
|
| 1940 |
+
"epoch": 7.5149335217419235,
|
| 1941 |
+
"grad_norm": 0.5383486747741699,
|
| 1942 |
+
"learning_rate": 0.00014950435694863724,
|
| 1943 |
+
"loss": 0.1011,
|
| 1944 |
+
"step": 117000
|
| 1945 |
+
},
|
| 1946 |
+
{
|
| 1947 |
+
"epoch": 7.547048622262188,
|
| 1948 |
+
"grad_norm": 0.8052467107772827,
|
| 1949 |
+
"learning_rate": 0.00014843385359796177,
|
| 1950 |
+
"loss": 0.1007,
|
| 1951 |
+
"step": 117500
|
| 1952 |
+
},
|
| 1953 |
+
{
|
| 1954 |
+
"epoch": 7.579163722782452,
|
| 1955 |
+
"grad_norm": 0.6362063884735107,
|
| 1956 |
+
"learning_rate": 0.0001473633502472863,
|
| 1957 |
+
"loss": 0.1012,
|
| 1958 |
+
"step": 118000
|
| 1959 |
+
},
|
| 1960 |
+
{
|
| 1961 |
+
"epoch": 7.600488149527908,
|
| 1962 |
+
"eval_loss": 0.13827957212924957,
|
| 1963 |
+
"eval_runtime": 16.1381,
|
| 1964 |
+
"eval_samples_per_second": 30.983,
|
| 1965 |
+
"eval_steps_per_second": 3.904,
|
| 1966 |
+
"step": 118332
|
| 1967 |
+
},
|
| 1968 |
+
{
|
| 1969 |
+
"epoch": 7.611278823302717,
|
| 1970 |
+
"grad_norm": 0.7652459740638733,
|
| 1971 |
+
"learning_rate": 0.0001462928468966108,
|
| 1972 |
+
"loss": 0.1037,
|
| 1973 |
+
"step": 118500
|
| 1974 |
+
},
|
| 1975 |
+
{
|
| 1976 |
+
"epoch": 7.643393923822981,
|
| 1977 |
+
"grad_norm": 0.9176694750785828,
|
| 1978 |
+
"learning_rate": 0.00014522234354593532,
|
| 1979 |
+
"loss": 0.1025,
|
| 1980 |
+
"step": 119000
|
| 1981 |
+
},
|
| 1982 |
+
{
|
| 1983 |
+
"epoch": 7.6755090243432464,
|
| 1984 |
+
"grad_norm": 0.6579234004020691,
|
| 1985 |
+
"learning_rate": 0.00014415184019525982,
|
| 1986 |
+
"loss": 0.1021,
|
| 1987 |
+
"step": 119500
|
| 1988 |
+
},
|
| 1989 |
+
{
|
| 1990 |
+
"epoch": 7.707624124863511,
|
| 1991 |
+
"grad_norm": 1.048262119293213,
|
| 1992 |
+
"learning_rate": 0.00014308133684458432,
|
| 1993 |
+
"loss": 0.0997,
|
| 1994 |
+
"step": 120000
|
| 1995 |
+
},
|
| 1996 |
+
{
|
| 1997 |
+
"epoch": 7.739739225383776,
|
| 1998 |
+
"grad_norm": 0.42218828201293945,
|
| 1999 |
+
"learning_rate": 0.00014201083349390885,
|
| 2000 |
+
"loss": 0.0995,
|
| 2001 |
+
"step": 120500
|
| 2002 |
+
},
|
| 2003 |
+
{
|
| 2004 |
+
"epoch": 7.77185432590404,
|
| 2005 |
+
"grad_norm": 0.8940654397010803,
|
| 2006 |
+
"learning_rate": 0.00014094033014323335,
|
| 2007 |
+
"loss": 0.1027,
|
| 2008 |
+
"step": 121000
|
| 2009 |
+
},
|
| 2010 |
+
{
|
| 2011 |
+
"epoch": 7.800500995568116,
|
| 2012 |
+
"eval_loss": 0.13814687728881836,
|
| 2013 |
+
"eval_runtime": 15.7443,
|
| 2014 |
+
"eval_samples_per_second": 31.758,
|
| 2015 |
+
"eval_steps_per_second": 4.001,
|
| 2016 |
+
"step": 121446
|
| 2017 |
+
},
|
| 2018 |
+
{
|
| 2019 |
+
"epoch": 7.803969426424304,
|
| 2020 |
+
"grad_norm": 0.6933867931365967,
|
| 2021 |
+
"learning_rate": 0.00013986982679255788,
|
| 2022 |
+
"loss": 0.1028,
|
| 2023 |
+
"step": 121500
|
| 2024 |
+
},
|
| 2025 |
+
{
|
| 2026 |
+
"epoch": 7.836084526944569,
|
| 2027 |
+
"grad_norm": 0.40795835852622986,
|
| 2028 |
+
"learning_rate": 0.00013879932344188238,
|
| 2029 |
+
"loss": 0.1028,
|
| 2030 |
+
"step": 122000
|
| 2031 |
+
},
|
| 2032 |
+
{
|
| 2033 |
+
"epoch": 7.868199627464834,
|
| 2034 |
+
"grad_norm": 1.0124913454055786,
|
| 2035 |
+
"learning_rate": 0.00013772882009120688,
|
| 2036 |
+
"loss": 0.1031,
|
| 2037 |
+
"step": 122500
|
| 2038 |
+
},
|
| 2039 |
+
{
|
| 2040 |
+
"epoch": 7.900314727985099,
|
| 2041 |
+
"grad_norm": 0.5193241238594055,
|
| 2042 |
+
"learning_rate": 0.0001366583167405314,
|
| 2043 |
+
"loss": 0.1038,
|
| 2044 |
+
"step": 123000
|
| 2045 |
+
},
|
| 2046 |
+
{
|
| 2047 |
+
"epoch": 7.932429828505363,
|
| 2048 |
+
"grad_norm": 0.5106309652328491,
|
| 2049 |
+
"learning_rate": 0.0001355878133898559,
|
| 2050 |
+
"loss": 0.1012,
|
| 2051 |
+
"step": 123500
|
| 2052 |
+
},
|
| 2053 |
+
{
|
| 2054 |
+
"epoch": 7.964544929025628,
|
| 2055 |
+
"grad_norm": 0.7035395503044128,
|
| 2056 |
+
"learning_rate": 0.00013451731003918043,
|
| 2057 |
+
"loss": 0.1023,
|
| 2058 |
+
"step": 124000
|
| 2059 |
+
},
|
| 2060 |
+
{
|
| 2061 |
+
"epoch": 7.996660029545892,
|
| 2062 |
+
"grad_norm": 1.0288721323013306,
|
| 2063 |
+
"learning_rate": 0.00013344680668850493,
|
| 2064 |
+
"loss": 0.1014,
|
| 2065 |
+
"step": 124500
|
| 2066 |
+
},
|
| 2067 |
+
{
|
| 2068 |
+
"epoch": 8.000513841608324,
|
| 2069 |
+
"eval_loss": 0.1353892832994461,
|
| 2070 |
+
"eval_runtime": 15.8158,
|
| 2071 |
+
"eval_samples_per_second": 31.614,
|
| 2072 |
+
"eval_steps_per_second": 3.983,
|
| 2073 |
+
"step": 124560
|
| 2074 |
+
},
|
| 2075 |
+
{
|
| 2076 |
+
"epoch": 8.028775130066157,
|
| 2077 |
+
"grad_norm": 0.5636913180351257,
|
| 2078 |
+
"learning_rate": 0.00013237630333782943,
|
| 2079 |
+
"loss": 0.087,
|
| 2080 |
+
"step": 125000
|
| 2081 |
+
},
|
| 2082 |
+
{
|
| 2083 |
+
"epoch": 8.060890230586422,
|
| 2084 |
+
"grad_norm": 0.7191582322120667,
|
| 2085 |
+
"learning_rate": 0.00013130579998715399,
|
| 2086 |
+
"loss": 0.0856,
|
| 2087 |
+
"step": 125500
|
| 2088 |
+
},
|
| 2089 |
+
{
|
| 2090 |
+
"epoch": 8.093005331106687,
|
| 2091 |
+
"grad_norm": 0.7674673199653625,
|
| 2092 |
+
"learning_rate": 0.00013023529663647849,
|
| 2093 |
+
"loss": 0.0868,
|
| 2094 |
+
"step": 126000
|
| 2095 |
+
},
|
| 2096 |
+
{
|
| 2097 |
+
"epoch": 8.125120431626952,
|
| 2098 |
+
"grad_norm": 0.775837779045105,
|
| 2099 |
+
"learning_rate": 0.00012916479328580299,
|
| 2100 |
+
"loss": 0.0869,
|
| 2101 |
+
"step": 126500
|
| 2102 |
+
},
|
| 2103 |
+
{
|
| 2104 |
+
"epoch": 8.157235532147215,
|
| 2105 |
+
"grad_norm": 0.6873489618301392,
|
| 2106 |
+
"learning_rate": 0.0001280942899351275,
|
| 2107 |
+
"loss": 0.0878,
|
| 2108 |
+
"step": 127000
|
| 2109 |
+
},
|
| 2110 |
+
{
|
| 2111 |
+
"epoch": 8.18935063266748,
|
| 2112 |
+
"grad_norm": 0.5567529201507568,
|
| 2113 |
+
"learning_rate": 0.000127023786584452,
|
| 2114 |
+
"loss": 0.0896,
|
| 2115 |
+
"step": 127500
|
| 2116 |
+
},
|
| 2117 |
+
{
|
| 2118 |
+
"epoch": 8.200526687648532,
|
| 2119 |
+
"eval_loss": 0.13849689066410065,
|
| 2120 |
+
"eval_runtime": 15.7325,
|
| 2121 |
+
"eval_samples_per_second": 31.781,
|
| 2122 |
+
"eval_steps_per_second": 4.004,
|
| 2123 |
+
"step": 127674
|
| 2124 |
+
},
|
| 2125 |
+
{
|
| 2126 |
+
"epoch": 8.221465733187745,
|
| 2127 |
+
"grad_norm": 0.6884915828704834,
|
| 2128 |
+
"learning_rate": 0.00012595328323377654,
|
| 2129 |
+
"loss": 0.0879,
|
| 2130 |
+
"step": 128000
|
| 2131 |
+
},
|
| 2132 |
+
{
|
| 2133 |
+
"epoch": 8.253580833708009,
|
| 2134 |
+
"grad_norm": 0.7230240702629089,
|
| 2135 |
+
"learning_rate": 0.00012488277988310104,
|
| 2136 |
+
"loss": 0.0893,
|
| 2137 |
+
"step": 128500
|
| 2138 |
+
},
|
| 2139 |
+
{
|
| 2140 |
+
"epoch": 8.285695934228274,
|
| 2141 |
+
"grad_norm": 0.7840784192085266,
|
| 2142 |
+
"learning_rate": 0.00012381227653242557,
|
| 2143 |
+
"loss": 0.0897,
|
| 2144 |
+
"step": 129000
|
| 2145 |
+
},
|
| 2146 |
+
{
|
| 2147 |
+
"epoch": 8.317811034748539,
|
| 2148 |
+
"grad_norm": 0.9472082257270813,
|
| 2149 |
+
"learning_rate": 0.00012274177318175007,
|
| 2150 |
+
"loss": 0.0876,
|
| 2151 |
+
"step": 129500
|
| 2152 |
+
},
|
| 2153 |
+
{
|
| 2154 |
+
"epoch": 8.349926135268804,
|
| 2155 |
+
"grad_norm": 0.7563714981079102,
|
| 2156 |
+
"learning_rate": 0.00012167126983107458,
|
| 2157 |
+
"loss": 0.0885,
|
| 2158 |
+
"step": 130000
|
| 2159 |
+
},
|
| 2160 |
+
{
|
| 2161 |
+
"epoch": 8.382041235789067,
|
| 2162 |
+
"grad_norm": 0.7382881045341492,
|
| 2163 |
+
"learning_rate": 0.00012060076648039908,
|
| 2164 |
+
"loss": 0.0893,
|
| 2165 |
+
"step": 130500
|
| 2166 |
+
},
|
| 2167 |
+
{
|
| 2168 |
+
"epoch": 8.40053953368874,
|
| 2169 |
+
"eval_loss": 0.13768891990184784,
|
| 2170 |
+
"eval_runtime": 15.732,
|
| 2171 |
+
"eval_samples_per_second": 31.782,
|
| 2172 |
+
"eval_steps_per_second": 4.005,
|
| 2173 |
+
"step": 130788
|
| 2174 |
+
},
|
| 2175 |
+
{
|
| 2176 |
+
"epoch": 8.414156336309333,
|
| 2177 |
+
"grad_norm": 0.6169273257255554,
|
| 2178 |
+
"learning_rate": 0.00011953026312972359,
|
| 2179 |
+
"loss": 0.0895,
|
| 2180 |
+
"step": 131000
|
| 2181 |
+
},
|
| 2182 |
+
{
|
| 2183 |
+
"epoch": 8.446271436829598,
|
| 2184 |
+
"grad_norm": 0.7610024213790894,
|
| 2185 |
+
"learning_rate": 0.0001184597597790481,
|
| 2186 |
+
"loss": 0.0884,
|
| 2187 |
+
"step": 131500
|
| 2188 |
+
},
|
| 2189 |
+
{
|
| 2190 |
+
"epoch": 8.478386537349863,
|
| 2191 |
+
"grad_norm": 0.7594485878944397,
|
| 2192 |
+
"learning_rate": 0.00011738925642837262,
|
| 2193 |
+
"loss": 0.0895,
|
| 2194 |
+
"step": 132000
|
| 2195 |
+
},
|
| 2196 |
+
{
|
| 2197 |
+
"epoch": 8.510501637870126,
|
| 2198 |
+
"grad_norm": 0.7947688102722168,
|
| 2199 |
+
"learning_rate": 0.00011631875307769713,
|
| 2200 |
+
"loss": 0.0876,
|
| 2201 |
+
"step": 132500
|
| 2202 |
+
},
|
| 2203 |
+
{
|
| 2204 |
+
"epoch": 8.542616738390391,
|
| 2205 |
+
"grad_norm": 0.7548133134841919,
|
| 2206 |
+
"learning_rate": 0.00011524824972702166,
|
| 2207 |
+
"loss": 0.0893,
|
| 2208 |
+
"step": 133000
|
| 2209 |
+
},
|
| 2210 |
+
{
|
| 2211 |
+
"epoch": 8.574731838910656,
|
| 2212 |
+
"grad_norm": 0.8032704591751099,
|
| 2213 |
+
"learning_rate": 0.00011417774637634617,
|
| 2214 |
+
"loss": 0.0918,
|
| 2215 |
+
"step": 133500
|
| 2216 |
+
},
|
| 2217 |
+
{
|
| 2218 |
+
"epoch": 8.60055237972895,
|
| 2219 |
+
"eval_loss": 0.13488411903381348,
|
| 2220 |
+
"eval_runtime": 15.7227,
|
| 2221 |
+
"eval_samples_per_second": 31.801,
|
| 2222 |
+
"eval_steps_per_second": 4.007,
|
| 2223 |
+
"step": 133902
|
| 2224 |
+
},
|
| 2225 |
+
{
|
| 2226 |
+
"epoch": 8.60684693943092,
|
| 2227 |
+
"grad_norm": 0.6742900013923645,
|
| 2228 |
+
"learning_rate": 0.00011310724302567069,
|
| 2229 |
+
"loss": 0.0908,
|
| 2230 |
+
"step": 134000
|
| 2231 |
+
},
|
| 2232 |
+
{
|
| 2233 |
+
"epoch": 8.638962039951185,
|
| 2234 |
+
"grad_norm": 0.7972450852394104,
|
| 2235 |
+
"learning_rate": 0.0001120367396749952,
|
| 2236 |
+
"loss": 0.0884,
|
| 2237 |
+
"step": 134500
|
| 2238 |
+
},
|
| 2239 |
+
{
|
| 2240 |
+
"epoch": 8.67107714047145,
|
| 2241 |
+
"grad_norm": 0.9247697591781616,
|
| 2242 |
+
"learning_rate": 0.0001109662363243197,
|
| 2243 |
+
"loss": 0.0907,
|
| 2244 |
+
"step": 135000
|
| 2245 |
+
},
|
| 2246 |
+
{
|
| 2247 |
+
"epoch": 8.703192240991715,
|
| 2248 |
+
"grad_norm": 0.5495902895927429,
|
| 2249 |
+
"learning_rate": 0.00010989573297364421,
|
| 2250 |
+
"loss": 0.089,
|
| 2251 |
+
"step": 135500
|
| 2252 |
+
},
|
| 2253 |
+
{
|
| 2254 |
+
"epoch": 8.735307341511978,
|
| 2255 |
+
"grad_norm": 0.554291307926178,
|
| 2256 |
+
"learning_rate": 0.00010882522962296873,
|
| 2257 |
+
"loss": 0.092,
|
| 2258 |
+
"step": 136000
|
| 2259 |
+
},
|
| 2260 |
+
{
|
| 2261 |
+
"epoch": 8.767422442032244,
|
| 2262 |
+
"grad_norm": 0.7461488842964172,
|
| 2263 |
+
"learning_rate": 0.00010775472627229324,
|
| 2264 |
+
"loss": 0.0903,
|
| 2265 |
+
"step": 136500
|
| 2266 |
+
},
|
| 2267 |
+
{
|
| 2268 |
+
"epoch": 8.799537542552509,
|
| 2269 |
+
"grad_norm": 0.7722447514533997,
|
| 2270 |
+
"learning_rate": 0.00010668422292161775,
|
| 2271 |
+
"loss": 0.0915,
|
| 2272 |
+
"step": 137000
|
| 2273 |
+
},
|
| 2274 |
+
{
|
| 2275 |
+
"epoch": 8.800565225769157,
|
| 2276 |
+
"eval_loss": 0.13115008175373077,
|
| 2277 |
+
"eval_runtime": 15.7476,
|
| 2278 |
+
"eval_samples_per_second": 31.751,
|
| 2279 |
+
"eval_steps_per_second": 4.001,
|
| 2280 |
+
"step": 137016
|
| 2281 |
+
},
|
| 2282 |
+
{
|
| 2283 |
+
"epoch": 8.831652643072772,
|
| 2284 |
+
"grad_norm": 0.5133621096611023,
|
| 2285 |
+
"learning_rate": 0.00010561371957094225,
|
| 2286 |
+
"loss": 0.0898,
|
| 2287 |
+
"step": 137500
|
| 2288 |
+
},
|
| 2289 |
+
{
|
| 2290 |
+
"epoch": 8.863767743593037,
|
| 2291 |
+
"grad_norm": 0.49867868423461914,
|
| 2292 |
+
"learning_rate": 0.00010454321622026677,
|
| 2293 |
+
"loss": 0.089,
|
| 2294 |
+
"step": 138000
|
| 2295 |
+
},
|
| 2296 |
+
{
|
| 2297 |
+
"epoch": 8.895882844113302,
|
| 2298 |
+
"grad_norm": 0.6413715481758118,
|
| 2299 |
+
"learning_rate": 0.00010347271286959128,
|
| 2300 |
+
"loss": 0.0888,
|
| 2301 |
+
"step": 138500
|
| 2302 |
+
},
|
| 2303 |
+
{
|
| 2304 |
+
"epoch": 8.927997944633567,
|
| 2305 |
+
"grad_norm": 0.869588315486908,
|
| 2306 |
+
"learning_rate": 0.0001024022095189158,
|
| 2307 |
+
"loss": 0.0902,
|
| 2308 |
+
"step": 139000
|
| 2309 |
+
},
|
| 2310 |
+
{
|
| 2311 |
+
"epoch": 8.96011304515383,
|
| 2312 |
+
"grad_norm": 0.6298141479492188,
|
| 2313 |
+
"learning_rate": 0.00010133170616824031,
|
| 2314 |
+
"loss": 0.0906,
|
| 2315 |
+
"step": 139500
|
| 2316 |
+
},
|
| 2317 |
+
{
|
| 2318 |
+
"epoch": 8.992228145674096,
|
| 2319 |
+
"grad_norm": 0.8133781552314758,
|
| 2320 |
+
"learning_rate": 0.00010026120281756482,
|
| 2321 |
+
"loss": 0.0878,
|
| 2322 |
+
"step": 140000
|
| 2323 |
+
},
|
| 2324 |
+
{
|
| 2325 |
+
"epoch": 9.000578071809365,
|
| 2326 |
+
"eval_loss": 0.13225188851356506,
|
| 2327 |
+
"eval_runtime": 15.7719,
|
| 2328 |
+
"eval_samples_per_second": 31.702,
|
| 2329 |
+
"eval_steps_per_second": 3.994,
|
| 2330 |
+
"step": 140130
|
| 2331 |
+
},
|
| 2332 |
+
{
|
| 2333 |
+
"epoch": 9.024343246194361,
|
| 2334 |
+
"grad_norm": 0.7959352135658264,
|
| 2335 |
+
"learning_rate": 9.919069946688933e-05,
|
| 2336 |
+
"loss": 0.0774,
|
| 2337 |
+
"step": 140500
|
| 2338 |
+
},
|
| 2339 |
+
{
|
| 2340 |
+
"epoch": 9.056458346714626,
|
| 2341 |
+
"grad_norm": 0.7019794583320618,
|
| 2342 |
+
"learning_rate": 9.812019611621385e-05,
|
| 2343 |
+
"loss": 0.0746,
|
| 2344 |
+
"step": 141000
|
| 2345 |
+
},
|
| 2346 |
+
{
|
| 2347 |
+
"epoch": 9.08857344723489,
|
| 2348 |
+
"grad_norm": 0.936621904373169,
|
| 2349 |
+
"learning_rate": 9.704969276553836e-05,
|
| 2350 |
+
"loss": 0.0751,
|
| 2351 |
+
"step": 141500
|
| 2352 |
+
},
|
| 2353 |
+
{
|
| 2354 |
+
"epoch": 9.120688547755154,
|
| 2355 |
+
"grad_norm": 0.5780510306358337,
|
| 2356 |
+
"learning_rate": 9.597918941486287e-05,
|
| 2357 |
+
"loss": 0.0728,
|
| 2358 |
+
"step": 142000
|
| 2359 |
+
},
|
| 2360 |
+
{
|
| 2361 |
+
"epoch": 9.15280364827542,
|
| 2362 |
+
"grad_norm": 0.9320997595787048,
|
| 2363 |
+
"learning_rate": 9.490868606418739e-05,
|
| 2364 |
+
"loss": 0.0763,
|
| 2365 |
+
"step": 142500
|
| 2366 |
+
},
|
| 2367 |
+
{
|
| 2368 |
+
"epoch": 9.184918748795683,
|
| 2369 |
+
"grad_norm": 0.6630645394325256,
|
| 2370 |
+
"learning_rate": 9.38381827135119e-05,
|
| 2371 |
+
"loss": 0.0757,
|
| 2372 |
+
"step": 143000
|
| 2373 |
+
},
|
| 2374 |
+
{
|
| 2375 |
+
"epoch": 9.200590917849572,
|
| 2376 |
+
"eval_loss": 0.1348526030778885,
|
| 2377 |
+
"eval_runtime": 15.7516,
|
| 2378 |
+
"eval_samples_per_second": 31.743,
|
| 2379 |
+
"eval_steps_per_second": 4.0,
|
| 2380 |
+
"step": 143244
|
| 2381 |
+
},
|
| 2382 |
+
{
|
| 2383 |
+
"epoch": 9.217033849315948,
|
| 2384 |
+
"grad_norm": 0.7334017157554626,
|
| 2385 |
+
"learning_rate": 9.276767936283641e-05,
|
| 2386 |
+
"loss": 0.0758,
|
| 2387 |
+
"step": 143500
|
| 2388 |
+
},
|
| 2389 |
+
{
|
| 2390 |
+
"epoch": 9.249148949836213,
|
| 2391 |
+
"grad_norm": 0.7668980360031128,
|
| 2392 |
+
"learning_rate": 9.169717601216093e-05,
|
| 2393 |
+
"loss": 0.0778,
|
| 2394 |
+
"step": 144000
|
| 2395 |
+
},
|
| 2396 |
+
{
|
| 2397 |
+
"epoch": 9.281264050356478,
|
| 2398 |
+
"grad_norm": 0.902825653553009,
|
| 2399 |
+
"learning_rate": 9.062667266148544e-05,
|
| 2400 |
+
"loss": 0.076,
|
| 2401 |
+
"step": 144500
|
| 2402 |
+
},
|
| 2403 |
+
{
|
| 2404 |
+
"epoch": 9.313379150876742,
|
| 2405 |
+
"grad_norm": 0.9291773438453674,
|
| 2406 |
+
"learning_rate": 8.955616931080994e-05,
|
| 2407 |
+
"loss": 0.0775,
|
| 2408 |
+
"step": 145000
|
| 2409 |
+
},
|
| 2410 |
+
{
|
| 2411 |
+
"epoch": 9.345494251397007,
|
| 2412 |
+
"grad_norm": 0.49062594771385193,
|
| 2413 |
+
"learning_rate": 8.848566596013445e-05,
|
| 2414 |
+
"loss": 0.0766,
|
| 2415 |
+
"step": 145500
|
| 2416 |
+
},
|
| 2417 |
+
{
|
| 2418 |
+
"epoch": 9.377609351917272,
|
| 2419 |
+
"grad_norm": 0.6508079767227173,
|
| 2420 |
+
"learning_rate": 8.741516260945897e-05,
|
| 2421 |
+
"loss": 0.0772,
|
| 2422 |
+
"step": 146000
|
| 2423 |
+
},
|
| 2424 |
+
{
|
| 2425 |
+
"epoch": 9.40060376388978,
|
| 2426 |
+
"eval_loss": 0.13261519372463226,
|
| 2427 |
+
"eval_runtime": 15.7635,
|
| 2428 |
+
"eval_samples_per_second": 31.719,
|
| 2429 |
+
"eval_steps_per_second": 3.997,
|
| 2430 |
+
"step": 146358
|
| 2431 |
+
},
|
| 2432 |
+
{
|
| 2433 |
+
"epoch": 9.409724452437537,
|
| 2434 |
+
"grad_norm": 0.990882933139801,
|
| 2435 |
+
"learning_rate": 8.63446592587835e-05,
|
| 2436 |
+
"loss": 0.0784,
|
| 2437 |
+
"step": 146500
|
| 2438 |
+
},
|
| 2439 |
+
{
|
| 2440 |
+
"epoch": 9.4418395529578,
|
| 2441 |
+
"grad_norm": 0.688853919506073,
|
| 2442 |
+
"learning_rate": 8.5274155908108e-05,
|
| 2443 |
+
"loss": 0.0752,
|
| 2444 |
+
"step": 147000
|
| 2445 |
+
},
|
| 2446 |
+
{
|
| 2447 |
+
"epoch": 9.473954653478065,
|
| 2448 |
+
"grad_norm": 0.6473709940910339,
|
| 2449 |
+
"learning_rate": 8.420365255743251e-05,
|
| 2450 |
+
"loss": 0.0775,
|
| 2451 |
+
"step": 147500
|
| 2452 |
+
},
|
| 2453 |
+
{
|
| 2454 |
+
"epoch": 9.50606975399833,
|
| 2455 |
+
"grad_norm": 0.4077664017677307,
|
| 2456 |
+
"learning_rate": 8.313314920675702e-05,
|
| 2457 |
+
"loss": 0.0785,
|
| 2458 |
+
"step": 148000
|
| 2459 |
+
},
|
| 2460 |
+
{
|
| 2461 |
+
"epoch": 9.538184854518594,
|
| 2462 |
+
"grad_norm": 0.46778786182403564,
|
| 2463 |
+
"learning_rate": 8.206264585608154e-05,
|
| 2464 |
+
"loss": 0.0798,
|
| 2465 |
+
"step": 148500
|
| 2466 |
+
},
|
| 2467 |
+
{
|
| 2468 |
+
"epoch": 9.570299955038859,
|
| 2469 |
+
"grad_norm": 1.3767471313476562,
|
| 2470 |
+
"learning_rate": 8.099214250540605e-05,
|
| 2471 |
+
"loss": 0.0779,
|
| 2472 |
+
"step": 149000
|
| 2473 |
+
},
|
| 2474 |
+
{
|
| 2475 |
+
"epoch": 9.60061660992999,
|
| 2476 |
+
"eval_loss": 0.13076962530612946,
|
| 2477 |
+
"eval_runtime": 15.7454,
|
| 2478 |
+
"eval_samples_per_second": 31.755,
|
| 2479 |
+
"eval_steps_per_second": 4.001,
|
| 2480 |
+
"step": 149472
|
| 2481 |
+
},
|
| 2482 |
+
{
|
| 2483 |
+
"epoch": 9.602415055559124,
|
| 2484 |
+
"grad_norm": 0.7387043237686157,
|
| 2485 |
+
"learning_rate": 7.992163915473055e-05,
|
| 2486 |
+
"loss": 0.0769,
|
| 2487 |
+
"step": 149500
|
| 2488 |
+
},
|
| 2489 |
+
{
|
| 2490 |
+
"epoch": 9.63453015607939,
|
| 2491 |
+
"grad_norm": 0.677444338798523,
|
| 2492 |
+
"learning_rate": 7.885113580405506e-05,
|
| 2493 |
+
"loss": 0.0778,
|
| 2494 |
+
"step": 150000
|
| 2495 |
+
},
|
| 2496 |
+
{
|
| 2497 |
+
"epoch": 9.666645256599653,
|
| 2498 |
+
"grad_norm": 0.6619726419448853,
|
| 2499 |
+
"learning_rate": 7.778063245337959e-05,
|
| 2500 |
+
"loss": 0.0787,
|
| 2501 |
+
"step": 150500
|
| 2502 |
+
},
|
| 2503 |
+
{
|
| 2504 |
+
"epoch": 9.698760357119918,
|
| 2505 |
+
"grad_norm": 0.868894100189209,
|
| 2506 |
+
"learning_rate": 7.67101291027041e-05,
|
| 2507 |
+
"loss": 0.0773,
|
| 2508 |
+
"step": 151000
|
| 2509 |
+
},
|
| 2510 |
+
{
|
| 2511 |
+
"epoch": 9.730875457640183,
|
| 2512 |
+
"grad_norm": 0.7369173765182495,
|
| 2513 |
+
"learning_rate": 7.563962575202862e-05,
|
| 2514 |
+
"loss": 0.0776,
|
| 2515 |
+
"step": 151500
|
| 2516 |
+
},
|
| 2517 |
+
{
|
| 2518 |
+
"epoch": 9.762990558160446,
|
| 2519 |
+
"grad_norm": 0.8018321990966797,
|
| 2520 |
+
"learning_rate": 7.456912240135312e-05,
|
| 2521 |
+
"loss": 0.0773,
|
| 2522 |
+
"step": 152000
|
| 2523 |
+
},
|
| 2524 |
+
{
|
| 2525 |
+
"epoch": 9.795105658680711,
|
| 2526 |
+
"grad_norm": 0.8573314547538757,
|
| 2527 |
+
"learning_rate": 7.349861905067763e-05,
|
| 2528 |
+
"loss": 0.0757,
|
| 2529 |
+
"step": 152500
|
| 2530 |
+
},
|
| 2531 |
+
{
|
| 2532 |
+
"epoch": 9.800629455970197,
|
| 2533 |
+
"eval_loss": 0.12927444279193878,
|
| 2534 |
+
"eval_runtime": 15.7238,
|
| 2535 |
+
"eval_samples_per_second": 31.799,
|
| 2536 |
+
"eval_steps_per_second": 4.007,
|
| 2537 |
+
"step": 152586
|
| 2538 |
+
},
|
| 2539 |
+
{
|
| 2540 |
+
"epoch": 9.827220759200976,
|
| 2541 |
+
"grad_norm": 0.8061776757240295,
|
| 2542 |
+
"learning_rate": 7.242811570000214e-05,
|
| 2543 |
+
"loss": 0.0791,
|
| 2544 |
+
"step": 153000
|
| 2545 |
+
},
|
| 2546 |
+
{
|
| 2547 |
+
"epoch": 9.859335859721241,
|
| 2548 |
+
"grad_norm": 0.7286409139633179,
|
| 2549 |
+
"learning_rate": 7.135761234932666e-05,
|
| 2550 |
+
"loss": 0.076,
|
| 2551 |
+
"step": 153500
|
| 2552 |
+
},
|
| 2553 |
+
{
|
| 2554 |
+
"epoch": 9.891450960241505,
|
| 2555 |
+
"grad_norm": 0.7510332465171814,
|
| 2556 |
+
"learning_rate": 7.028710899865117e-05,
|
| 2557 |
+
"loss": 0.0792,
|
| 2558 |
+
"step": 154000
|
| 2559 |
+
},
|
| 2560 |
+
{
|
| 2561 |
+
"epoch": 9.92356606076177,
|
| 2562 |
+
"grad_norm": 0.960188627243042,
|
| 2563 |
+
"learning_rate": 6.921660564797568e-05,
|
| 2564 |
+
"loss": 0.0783,
|
| 2565 |
+
"step": 154500
|
| 2566 |
+
},
|
| 2567 |
+
{
|
| 2568 |
+
"epoch": 9.955681161282035,
|
| 2569 |
+
"grad_norm": 0.8785921931266785,
|
| 2570 |
+
"learning_rate": 6.81461022973002e-05,
|
| 2571 |
+
"loss": 0.0786,
|
| 2572 |
+
"step": 155000
|
| 2573 |
+
},
|
| 2574 |
+
{
|
| 2575 |
+
"epoch": 9.9877962618023,
|
| 2576 |
+
"grad_norm": 0.6422717571258545,
|
| 2577 |
+
"learning_rate": 6.707559894662471e-05,
|
| 2578 |
+
"loss": 0.0768,
|
| 2579 |
+
"step": 155500
|
| 2580 |
+
}
|
| 2581 |
+
],
|
| 2582 |
+
"logging_steps": 500,
|
| 2583 |
+
"max_steps": 186828,
|
| 2584 |
+
"num_input_tokens_seen": 0,
|
| 2585 |
+
"num_train_epochs": 12,
|
| 2586 |
+
"save_steps": 500,
|
| 2587 |
+
"stateful_callbacks": {
|
| 2588 |
+
"TrainerControl": {
|
| 2589 |
+
"args": {
|
| 2590 |
+
"should_epoch_stop": false,
|
| 2591 |
+
"should_evaluate": false,
|
| 2592 |
+
"should_log": false,
|
| 2593 |
+
"should_save": true,
|
| 2594 |
+
"should_training_stop": false
|
| 2595 |
+
},
|
| 2596 |
+
"attributes": {}
|
| 2597 |
+
}
|
| 2598 |
+
},
|
| 2599 |
+
"total_flos": 3.5820527394360394e+19,
|
| 2600 |
+
"train_batch_size": 4,
|
| 2601 |
+
"trial_name": null,
|
| 2602 |
+
"trial_params": null
|
| 2603 |
+
}
|
checkpoint-155690/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:73088d518ee530775134be6328391a2166a39681fc7ec212f67176c071d6067e
|
| 3 |
+
size 5969
|