Upload fine-tuned checkpoint
Browse files- README.md +202 -0
- adapter_config.json +39 -0
- adapter_model.safetensors +3 -0
- added_tokens.json +19 -0
- merges.txt +0 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +24 -0
- tokenizer.json +0 -0
- tokenizer_config.json +161 -0
- trainer_state.json +2841 -0
- training_args.bin +3 -0
- vocab.json +0 -0
README.md
ADDED
|
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: roneneldan/TinyStories-1M
|
| 3 |
+
library_name: peft
|
| 4 |
+
---
|
| 5 |
+
|
| 6 |
+
# Model Card for Model ID
|
| 7 |
+
|
| 8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 9 |
+
|
| 10 |
+
|
| 11 |
+
|
| 12 |
+
## Model Details
|
| 13 |
+
|
| 14 |
+
### Model Description
|
| 15 |
+
|
| 16 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
- **Developed by:** [More Information Needed]
|
| 21 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 22 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 23 |
+
- **Model type:** [More Information Needed]
|
| 24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 25 |
+
- **License:** [More Information Needed]
|
| 26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 27 |
+
|
| 28 |
+
### Model Sources [optional]
|
| 29 |
+
|
| 30 |
+
<!-- Provide the basic links for the model. -->
|
| 31 |
+
|
| 32 |
+
- **Repository:** [More Information Needed]
|
| 33 |
+
- **Paper [optional]:** [More Information Needed]
|
| 34 |
+
- **Demo [optional]:** [More Information Needed]
|
| 35 |
+
|
| 36 |
+
## Uses
|
| 37 |
+
|
| 38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 39 |
+
|
| 40 |
+
### Direct Use
|
| 41 |
+
|
| 42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 43 |
+
|
| 44 |
+
[More Information Needed]
|
| 45 |
+
|
| 46 |
+
### Downstream Use [optional]
|
| 47 |
+
|
| 48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 49 |
+
|
| 50 |
+
[More Information Needed]
|
| 51 |
+
|
| 52 |
+
### Out-of-Scope Use
|
| 53 |
+
|
| 54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 55 |
+
|
| 56 |
+
[More Information Needed]
|
| 57 |
+
|
| 58 |
+
## Bias, Risks, and Limitations
|
| 59 |
+
|
| 60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 61 |
+
|
| 62 |
+
[More Information Needed]
|
| 63 |
+
|
| 64 |
+
### Recommendations
|
| 65 |
+
|
| 66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 67 |
+
|
| 68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 69 |
+
|
| 70 |
+
## How to Get Started with the Model
|
| 71 |
+
|
| 72 |
+
Use the code below to get started with the model.
|
| 73 |
+
|
| 74 |
+
[More Information Needed]
|
| 75 |
+
|
| 76 |
+
## Training Details
|
| 77 |
+
|
| 78 |
+
### Training Data
|
| 79 |
+
|
| 80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 81 |
+
|
| 82 |
+
[More Information Needed]
|
| 83 |
+
|
| 84 |
+
### Training Procedure
|
| 85 |
+
|
| 86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 87 |
+
|
| 88 |
+
#### Preprocessing [optional]
|
| 89 |
+
|
| 90 |
+
[More Information Needed]
|
| 91 |
+
|
| 92 |
+
|
| 93 |
+
#### Training Hyperparameters
|
| 94 |
+
|
| 95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 96 |
+
|
| 97 |
+
#### Speeds, Sizes, Times [optional]
|
| 98 |
+
|
| 99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 100 |
+
|
| 101 |
+
[More Information Needed]
|
| 102 |
+
|
| 103 |
+
## Evaluation
|
| 104 |
+
|
| 105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 106 |
+
|
| 107 |
+
### Testing Data, Factors & Metrics
|
| 108 |
+
|
| 109 |
+
#### Testing Data
|
| 110 |
+
|
| 111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 112 |
+
|
| 113 |
+
[More Information Needed]
|
| 114 |
+
|
| 115 |
+
#### Factors
|
| 116 |
+
|
| 117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 118 |
+
|
| 119 |
+
[More Information Needed]
|
| 120 |
+
|
| 121 |
+
#### Metrics
|
| 122 |
+
|
| 123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 124 |
+
|
| 125 |
+
[More Information Needed]
|
| 126 |
+
|
| 127 |
+
### Results
|
| 128 |
+
|
| 129 |
+
[More Information Needed]
|
| 130 |
+
|
| 131 |
+
#### Summary
|
| 132 |
+
|
| 133 |
+
|
| 134 |
+
|
| 135 |
+
## Model Examination [optional]
|
| 136 |
+
|
| 137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 138 |
+
|
| 139 |
+
[More Information Needed]
|
| 140 |
+
|
| 141 |
+
## Environmental Impact
|
| 142 |
+
|
| 143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 144 |
+
|
| 145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
| 146 |
+
|
| 147 |
+
- **Hardware Type:** [More Information Needed]
|
| 148 |
+
- **Hours used:** [More Information Needed]
|
| 149 |
+
- **Cloud Provider:** [More Information Needed]
|
| 150 |
+
- **Compute Region:** [More Information Needed]
|
| 151 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 152 |
+
|
| 153 |
+
## Technical Specifications [optional]
|
| 154 |
+
|
| 155 |
+
### Model Architecture and Objective
|
| 156 |
+
|
| 157 |
+
[More Information Needed]
|
| 158 |
+
|
| 159 |
+
### Compute Infrastructure
|
| 160 |
+
|
| 161 |
+
[More Information Needed]
|
| 162 |
+
|
| 163 |
+
#### Hardware
|
| 164 |
+
|
| 165 |
+
[More Information Needed]
|
| 166 |
+
|
| 167 |
+
#### Software
|
| 168 |
+
|
| 169 |
+
[More Information Needed]
|
| 170 |
+
|
| 171 |
+
## Citation [optional]
|
| 172 |
+
|
| 173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 174 |
+
|
| 175 |
+
**BibTeX:**
|
| 176 |
+
|
| 177 |
+
[More Information Needed]
|
| 178 |
+
|
| 179 |
+
**APA:**
|
| 180 |
+
|
| 181 |
+
[More Information Needed]
|
| 182 |
+
|
| 183 |
+
## Glossary [optional]
|
| 184 |
+
|
| 185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 186 |
+
|
| 187 |
+
[More Information Needed]
|
| 188 |
+
|
| 189 |
+
## More Information [optional]
|
| 190 |
+
|
| 191 |
+
[More Information Needed]
|
| 192 |
+
|
| 193 |
+
## Model Card Authors [optional]
|
| 194 |
+
|
| 195 |
+
[More Information Needed]
|
| 196 |
+
|
| 197 |
+
## Model Card Contact
|
| 198 |
+
|
| 199 |
+
[More Information Needed]
|
| 200 |
+
### Framework versions
|
| 201 |
+
|
| 202 |
+
- PEFT 0.14.0
|
adapter_config.json
ADDED
|
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "roneneldan/TinyStories-1M",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"eva_config": null,
|
| 7 |
+
"exclude_modules": null,
|
| 8 |
+
"fan_in_fan_out": false,
|
| 9 |
+
"inference_mode": true,
|
| 10 |
+
"init_lora_weights": true,
|
| 11 |
+
"layer_replication": null,
|
| 12 |
+
"layers_pattern": null,
|
| 13 |
+
"layers_to_transform": null,
|
| 14 |
+
"loftq_config": {},
|
| 15 |
+
"lora_alpha": 32,
|
| 16 |
+
"lora_bias": false,
|
| 17 |
+
"lora_dropout": 0.05,
|
| 18 |
+
"megatron_config": null,
|
| 19 |
+
"megatron_core": "megatron.core",
|
| 20 |
+
"modules_to_save": [
|
| 21 |
+
"wte"
|
| 22 |
+
],
|
| 23 |
+
"peft_type": "LORA",
|
| 24 |
+
"r": 32,
|
| 25 |
+
"rank_pattern": {},
|
| 26 |
+
"revision": null,
|
| 27 |
+
"target_modules": [
|
| 28 |
+
"k_proj",
|
| 29 |
+
"up_proj",
|
| 30 |
+
"v_proj",
|
| 31 |
+
"gate_proj",
|
| 32 |
+
"q_proj",
|
| 33 |
+
"o_proj",
|
| 34 |
+
"down_proj"
|
| 35 |
+
],
|
| 36 |
+
"task_type": "CAUSAL_LM",
|
| 37 |
+
"use_dora": false,
|
| 38 |
+
"use_rslora": true
|
| 39 |
+
}
|
adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bffa9d18e49a345a9b66654a8b379c12896d28ad3d84beb951c5224569da50f1
|
| 3 |
+
size 13269912
|
added_tokens.json
ADDED
|
@@ -0,0 +1,19 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<cluster_0>": 50268,
|
| 3 |
+
"<cluster_10>": 50264,
|
| 4 |
+
"<cluster_11>": 50261,
|
| 5 |
+
"<cluster_12>": 50257,
|
| 6 |
+
"<cluster_13>": 50265,
|
| 7 |
+
"<cluster_14>": 50262,
|
| 8 |
+
"<cluster_15>": 50272,
|
| 9 |
+
"<cluster_16>": 50273,
|
| 10 |
+
"<cluster_1>": 50260,
|
| 11 |
+
"<cluster_2>": 50259,
|
| 12 |
+
"<cluster_3>": 50269,
|
| 13 |
+
"<cluster_4>": 50267,
|
| 14 |
+
"<cluster_5>": 50270,
|
| 15 |
+
"<cluster_6>": 50266,
|
| 16 |
+
"<cluster_7>": 50263,
|
| 17 |
+
"<cluster_8>": 50271,
|
| 18 |
+
"<cluster_9>": 50258
|
| 19 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a94175e53964c6c84a5af9ab8815c4ee3b327e86338e6970e19fe608e3799137
|
| 3 |
+
size 7354554
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1351e3cbde5fba28ca4ac8afda43f48563c490779fc18bffc14596d2ecdfa130
|
| 3 |
+
size 14244
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e055298148c186988a54be766385f194e9e1ed4ff410a4916a76b1dcb1be936e
|
| 3 |
+
size 1064
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<|endoftext|>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": true,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "<|endoftext|>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": true,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": "<|endoftext|>",
|
| 17 |
+
"unk_token": {
|
| 18 |
+
"content": "<|endoftext|>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": true,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
}
|
| 24 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,161 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": true,
|
| 4 |
+
"add_prefix_space": false,
|
| 5 |
+
"added_tokens_decoder": {
|
| 6 |
+
"50256": {
|
| 7 |
+
"content": "<|endoftext|>",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": true,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false,
|
| 12 |
+
"special": true
|
| 13 |
+
},
|
| 14 |
+
"50257": {
|
| 15 |
+
"content": "<cluster_12>",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": false,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false,
|
| 20 |
+
"special": true
|
| 21 |
+
},
|
| 22 |
+
"50258": {
|
| 23 |
+
"content": "<cluster_9>",
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"normalized": false,
|
| 26 |
+
"rstrip": false,
|
| 27 |
+
"single_word": false,
|
| 28 |
+
"special": true
|
| 29 |
+
},
|
| 30 |
+
"50259": {
|
| 31 |
+
"content": "<cluster_2>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false,
|
| 36 |
+
"special": true
|
| 37 |
+
},
|
| 38 |
+
"50260": {
|
| 39 |
+
"content": "<cluster_1>",
|
| 40 |
+
"lstrip": false,
|
| 41 |
+
"normalized": false,
|
| 42 |
+
"rstrip": false,
|
| 43 |
+
"single_word": false,
|
| 44 |
+
"special": true
|
| 45 |
+
},
|
| 46 |
+
"50261": {
|
| 47 |
+
"content": "<cluster_11>",
|
| 48 |
+
"lstrip": false,
|
| 49 |
+
"normalized": false,
|
| 50 |
+
"rstrip": false,
|
| 51 |
+
"single_word": false,
|
| 52 |
+
"special": true
|
| 53 |
+
},
|
| 54 |
+
"50262": {
|
| 55 |
+
"content": "<cluster_14>",
|
| 56 |
+
"lstrip": false,
|
| 57 |
+
"normalized": false,
|
| 58 |
+
"rstrip": false,
|
| 59 |
+
"single_word": false,
|
| 60 |
+
"special": true
|
| 61 |
+
},
|
| 62 |
+
"50263": {
|
| 63 |
+
"content": "<cluster_7>",
|
| 64 |
+
"lstrip": false,
|
| 65 |
+
"normalized": false,
|
| 66 |
+
"rstrip": false,
|
| 67 |
+
"single_word": false,
|
| 68 |
+
"special": true
|
| 69 |
+
},
|
| 70 |
+
"50264": {
|
| 71 |
+
"content": "<cluster_10>",
|
| 72 |
+
"lstrip": false,
|
| 73 |
+
"normalized": false,
|
| 74 |
+
"rstrip": false,
|
| 75 |
+
"single_word": false,
|
| 76 |
+
"special": true
|
| 77 |
+
},
|
| 78 |
+
"50265": {
|
| 79 |
+
"content": "<cluster_13>",
|
| 80 |
+
"lstrip": false,
|
| 81 |
+
"normalized": false,
|
| 82 |
+
"rstrip": false,
|
| 83 |
+
"single_word": false,
|
| 84 |
+
"special": true
|
| 85 |
+
},
|
| 86 |
+
"50266": {
|
| 87 |
+
"content": "<cluster_6>",
|
| 88 |
+
"lstrip": false,
|
| 89 |
+
"normalized": false,
|
| 90 |
+
"rstrip": false,
|
| 91 |
+
"single_word": false,
|
| 92 |
+
"special": true
|
| 93 |
+
},
|
| 94 |
+
"50267": {
|
| 95 |
+
"content": "<cluster_4>",
|
| 96 |
+
"lstrip": false,
|
| 97 |
+
"normalized": false,
|
| 98 |
+
"rstrip": false,
|
| 99 |
+
"single_word": false,
|
| 100 |
+
"special": true
|
| 101 |
+
},
|
| 102 |
+
"50268": {
|
| 103 |
+
"content": "<cluster_0>",
|
| 104 |
+
"lstrip": false,
|
| 105 |
+
"normalized": false,
|
| 106 |
+
"rstrip": false,
|
| 107 |
+
"single_word": false,
|
| 108 |
+
"special": true
|
| 109 |
+
},
|
| 110 |
+
"50269": {
|
| 111 |
+
"content": "<cluster_3>",
|
| 112 |
+
"lstrip": false,
|
| 113 |
+
"normalized": false,
|
| 114 |
+
"rstrip": false,
|
| 115 |
+
"single_word": false,
|
| 116 |
+
"special": true
|
| 117 |
+
},
|
| 118 |
+
"50270": {
|
| 119 |
+
"content": "<cluster_5>",
|
| 120 |
+
"lstrip": false,
|
| 121 |
+
"normalized": false,
|
| 122 |
+
"rstrip": false,
|
| 123 |
+
"single_word": false,
|
| 124 |
+
"special": true
|
| 125 |
+
},
|
| 126 |
+
"50271": {
|
| 127 |
+
"content": "<cluster_8>",
|
| 128 |
+
"lstrip": false,
|
| 129 |
+
"normalized": false,
|
| 130 |
+
"rstrip": false,
|
| 131 |
+
"single_word": false,
|
| 132 |
+
"special": true
|
| 133 |
+
},
|
| 134 |
+
"50272": {
|
| 135 |
+
"content": "<cluster_15>",
|
| 136 |
+
"lstrip": false,
|
| 137 |
+
"normalized": false,
|
| 138 |
+
"rstrip": false,
|
| 139 |
+
"single_word": false,
|
| 140 |
+
"special": true
|
| 141 |
+
},
|
| 142 |
+
"50273": {
|
| 143 |
+
"content": "<cluster_16>",
|
| 144 |
+
"lstrip": false,
|
| 145 |
+
"normalized": false,
|
| 146 |
+
"rstrip": false,
|
| 147 |
+
"single_word": false,
|
| 148 |
+
"special": true
|
| 149 |
+
}
|
| 150 |
+
},
|
| 151 |
+
"bos_token": "<|endoftext|>",
|
| 152 |
+
"clean_up_tokenization_spaces": false,
|
| 153 |
+
"eos_token": "<|endoftext|>",
|
| 154 |
+
"errors": "replace",
|
| 155 |
+
"extra_special_tokens": {},
|
| 156 |
+
"model_max_length": 2048,
|
| 157 |
+
"pad_token": "<|endoftext|>",
|
| 158 |
+
"padding_side": "left",
|
| 159 |
+
"tokenizer_class": "GPT2Tokenizer",
|
| 160 |
+
"unk_token": "<|endoftext|>"
|
| 161 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,2841 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 3.8681728839874268,
|
| 3 |
+
"best_model_checkpoint": "checkpoints/test_1M_1-2025-02-12-12-32/checkpoint-10000",
|
| 4 |
+
"epoch": 0.7914523149980214,
|
| 5 |
+
"eval_steps": 10000,
|
| 6 |
+
"global_step": 10000,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.0019786307874950534,
|
| 13 |
+
"grad_norm": 254.82342529296875,
|
| 14 |
+
"learning_rate": 2.499208537244918e-07,
|
| 15 |
+
"loss": 5.7705,
|
| 16 |
+
"step": 25
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.003957261574990107,
|
| 20 |
+
"grad_norm": 153.19989013671875,
|
| 21 |
+
"learning_rate": 2.498384096875041e-07,
|
| 22 |
+
"loss": 5.6747,
|
| 23 |
+
"step": 50
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.00593589236248516,
|
| 27 |
+
"grad_norm": 224.5292510986328,
|
| 28 |
+
"learning_rate": 2.4975596565051644e-07,
|
| 29 |
+
"loss": 5.6201,
|
| 30 |
+
"step": 75
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.007914523149980214,
|
| 34 |
+
"grad_norm": 175.854248046875,
|
| 35 |
+
"learning_rate": 2.4967352161352873e-07,
|
| 36 |
+
"loss": 5.6974,
|
| 37 |
+
"step": 100
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.009893153937475268,
|
| 41 |
+
"grad_norm": 163.52769470214844,
|
| 42 |
+
"learning_rate": 2.49591077576541e-07,
|
| 43 |
+
"loss": 5.5417,
|
| 44 |
+
"step": 125
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.01187178472497032,
|
| 48 |
+
"grad_norm": 254.2264862060547,
|
| 49 |
+
"learning_rate": 2.4950863353955335e-07,
|
| 50 |
+
"loss": 5.8201,
|
| 51 |
+
"step": 150
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.013850415512465374,
|
| 55 |
+
"grad_norm": 175.30279541015625,
|
| 56 |
+
"learning_rate": 2.4942618950256564e-07,
|
| 57 |
+
"loss": 5.5302,
|
| 58 |
+
"step": 175
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.015829046299960427,
|
| 62 |
+
"grad_norm": 300.1286315917969,
|
| 63 |
+
"learning_rate": 2.4934374546557797e-07,
|
| 64 |
+
"loss": 5.6572,
|
| 65 |
+
"step": 200
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.01780767708745548,
|
| 69 |
+
"grad_norm": 201.56961059570312,
|
| 70 |
+
"learning_rate": 2.4926130142859026e-07,
|
| 71 |
+
"loss": 5.2914,
|
| 72 |
+
"step": 225
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.019786307874950535,
|
| 76 |
+
"grad_norm": 245.64854431152344,
|
| 77 |
+
"learning_rate": 2.491788573916026e-07,
|
| 78 |
+
"loss": 5.4478,
|
| 79 |
+
"step": 250
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.02176493866244559,
|
| 83 |
+
"grad_norm": 239.78257751464844,
|
| 84 |
+
"learning_rate": 2.490964133546149e-07,
|
| 85 |
+
"loss": 5.4161,
|
| 86 |
+
"step": 275
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.02374356944994064,
|
| 90 |
+
"grad_norm": 150.18310546875,
|
| 91 |
+
"learning_rate": 2.4901396931762717e-07,
|
| 92 |
+
"loss": 5.4978,
|
| 93 |
+
"step": 300
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.025722200237435693,
|
| 97 |
+
"grad_norm": 172.03607177734375,
|
| 98 |
+
"learning_rate": 2.489315252806395e-07,
|
| 99 |
+
"loss": 5.4105,
|
| 100 |
+
"step": 325
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.027700831024930747,
|
| 104 |
+
"grad_norm": 343.2570495605469,
|
| 105 |
+
"learning_rate": 2.488490812436518e-07,
|
| 106 |
+
"loss": 5.5195,
|
| 107 |
+
"step": 350
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.0296794618124258,
|
| 111 |
+
"grad_norm": 329.7228698730469,
|
| 112 |
+
"learning_rate": 2.4876663720666413e-07,
|
| 113 |
+
"loss": 5.4494,
|
| 114 |
+
"step": 375
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.031658092599920855,
|
| 118 |
+
"grad_norm": 174.63136291503906,
|
| 119 |
+
"learning_rate": 2.486841931696764e-07,
|
| 120 |
+
"loss": 5.2864,
|
| 121 |
+
"step": 400
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.033636723387415905,
|
| 125 |
+
"grad_norm": 356.6216125488281,
|
| 126 |
+
"learning_rate": 2.486017491326887e-07,
|
| 127 |
+
"loss": 5.4376,
|
| 128 |
+
"step": 425
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.03561535417491096,
|
| 132 |
+
"grad_norm": 166.16783142089844,
|
| 133 |
+
"learning_rate": 2.4851930509570104e-07,
|
| 134 |
+
"loss": 5.3141,
|
| 135 |
+
"step": 450
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.03759398496240601,
|
| 139 |
+
"grad_norm": 220.06170654296875,
|
| 140 |
+
"learning_rate": 2.484368610587133e-07,
|
| 141 |
+
"loss": 5.5457,
|
| 142 |
+
"step": 475
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.03957261574990107,
|
| 146 |
+
"grad_norm": 154.55517578125,
|
| 147 |
+
"learning_rate": 2.483544170217256e-07,
|
| 148 |
+
"loss": 5.1264,
|
| 149 |
+
"step": 500
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.04155124653739612,
|
| 153 |
+
"grad_norm": 184.18443298339844,
|
| 154 |
+
"learning_rate": 2.4827197298473794e-07,
|
| 155 |
+
"loss": 5.3702,
|
| 156 |
+
"step": 525
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.04352987732489118,
|
| 160 |
+
"grad_norm": 128.84693908691406,
|
| 161 |
+
"learning_rate": 2.4818952894775023e-07,
|
| 162 |
+
"loss": 5.0207,
|
| 163 |
+
"step": 550
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.04550850811238623,
|
| 167 |
+
"grad_norm": 196.2894287109375,
|
| 168 |
+
"learning_rate": 2.4810708491076257e-07,
|
| 169 |
+
"loss": 5.315,
|
| 170 |
+
"step": 575
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.04748713889988128,
|
| 174 |
+
"grad_norm": 200.00257873535156,
|
| 175 |
+
"learning_rate": 2.4802464087377485e-07,
|
| 176 |
+
"loss": 5.2215,
|
| 177 |
+
"step": 600
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.049465769687376336,
|
| 181 |
+
"grad_norm": 271.8963928222656,
|
| 182 |
+
"learning_rate": 2.479421968367872e-07,
|
| 183 |
+
"loss": 5.3286,
|
| 184 |
+
"step": 625
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.051444400474871387,
|
| 188 |
+
"grad_norm": 181.56686401367188,
|
| 189 |
+
"learning_rate": 2.478597527997995e-07,
|
| 190 |
+
"loss": 4.9967,
|
| 191 |
+
"step": 650
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.053423031262366444,
|
| 195 |
+
"grad_norm": 242.8925323486328,
|
| 196 |
+
"learning_rate": 2.477773087628118e-07,
|
| 197 |
+
"loss": 5.1984,
|
| 198 |
+
"step": 675
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.055401662049861494,
|
| 202 |
+
"grad_norm": 210.05746459960938,
|
| 203 |
+
"learning_rate": 2.476948647258241e-07,
|
| 204 |
+
"loss": 5.0975,
|
| 205 |
+
"step": 700
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.05738029283735655,
|
| 209 |
+
"grad_norm": 181.1220245361328,
|
| 210 |
+
"learning_rate": 2.476124206888364e-07,
|
| 211 |
+
"loss": 5.0036,
|
| 212 |
+
"step": 725
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.0593589236248516,
|
| 216 |
+
"grad_norm": 166.00709533691406,
|
| 217 |
+
"learning_rate": 2.475299766518487e-07,
|
| 218 |
+
"loss": 5.3082,
|
| 219 |
+
"step": 750
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.06133755441234666,
|
| 223 |
+
"grad_norm": 151.4649200439453,
|
| 224 |
+
"learning_rate": 2.47447532614861e-07,
|
| 225 |
+
"loss": 5.1391,
|
| 226 |
+
"step": 775
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.06331618519984171,
|
| 230 |
+
"grad_norm": 149.88165283203125,
|
| 231 |
+
"learning_rate": 2.4736508857787335e-07,
|
| 232 |
+
"loss": 5.0783,
|
| 233 |
+
"step": 800
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.06529481598733676,
|
| 237 |
+
"grad_norm": 172.47061157226562,
|
| 238 |
+
"learning_rate": 2.4728264454088563e-07,
|
| 239 |
+
"loss": 4.9624,
|
| 240 |
+
"step": 825
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.06727344677483181,
|
| 244 |
+
"grad_norm": 298.1490478515625,
|
| 245 |
+
"learning_rate": 2.4720020050389797e-07,
|
| 246 |
+
"loss": 5.1937,
|
| 247 |
+
"step": 850
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.06925207756232687,
|
| 251 |
+
"grad_norm": 164.37867736816406,
|
| 252 |
+
"learning_rate": 2.4711775646691025e-07,
|
| 253 |
+
"loss": 5.1792,
|
| 254 |
+
"step": 875
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.07123070834982193,
|
| 258 |
+
"grad_norm": 216.8033905029297,
|
| 259 |
+
"learning_rate": 2.4703531242992254e-07,
|
| 260 |
+
"loss": 5.152,
|
| 261 |
+
"step": 900
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.07320933913731698,
|
| 265 |
+
"grad_norm": 211.95762634277344,
|
| 266 |
+
"learning_rate": 2.469528683929349e-07,
|
| 267 |
+
"loss": 4.9146,
|
| 268 |
+
"step": 925
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.07518796992481203,
|
| 272 |
+
"grad_norm": 257.61968994140625,
|
| 273 |
+
"learning_rate": 2.4687042435594716e-07,
|
| 274 |
+
"loss": 5.095,
|
| 275 |
+
"step": 950
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.07716660071230709,
|
| 279 |
+
"grad_norm": 179.43719482421875,
|
| 280 |
+
"learning_rate": 2.467879803189595e-07,
|
| 281 |
+
"loss": 5.0316,
|
| 282 |
+
"step": 975
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.07914523149980214,
|
| 286 |
+
"grad_norm": 180.3157958984375,
|
| 287 |
+
"learning_rate": 2.467055362819718e-07,
|
| 288 |
+
"loss": 4.9441,
|
| 289 |
+
"step": 1000
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.08112386228729719,
|
| 293 |
+
"grad_norm": 162.77447509765625,
|
| 294 |
+
"learning_rate": 2.4662309224498407e-07,
|
| 295 |
+
"loss": 4.9724,
|
| 296 |
+
"step": 1025
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.08310249307479224,
|
| 300 |
+
"grad_norm": 123.65939331054688,
|
| 301 |
+
"learning_rate": 2.465406482079964e-07,
|
| 302 |
+
"loss": 5.2271,
|
| 303 |
+
"step": 1050
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.08508112386228729,
|
| 307 |
+
"grad_norm": 163.114990234375,
|
| 308 |
+
"learning_rate": 2.464582041710087e-07,
|
| 309 |
+
"loss": 4.9724,
|
| 310 |
+
"step": 1075
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.08705975464978236,
|
| 314 |
+
"grad_norm": 204.76400756835938,
|
| 315 |
+
"learning_rate": 2.46375760134021e-07,
|
| 316 |
+
"loss": 4.8724,
|
| 317 |
+
"step": 1100
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.0890383854372774,
|
| 321 |
+
"grad_norm": 307.8963623046875,
|
| 322 |
+
"learning_rate": 2.462933160970333e-07,
|
| 323 |
+
"loss": 4.9256,
|
| 324 |
+
"step": 1125
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.09101701622477246,
|
| 328 |
+
"grad_norm": 133.03707885742188,
|
| 329 |
+
"learning_rate": 2.462108720600456e-07,
|
| 330 |
+
"loss": 4.8792,
|
| 331 |
+
"step": 1150
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.09299564701226751,
|
| 335 |
+
"grad_norm": 161.41697692871094,
|
| 336 |
+
"learning_rate": 2.4612842802305794e-07,
|
| 337 |
+
"loss": 5.054,
|
| 338 |
+
"step": 1175
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.09497427779976256,
|
| 342 |
+
"grad_norm": 135.36228942871094,
|
| 343 |
+
"learning_rate": 2.460459839860702e-07,
|
| 344 |
+
"loss": 4.8655,
|
| 345 |
+
"step": 1200
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.09695290858725762,
|
| 349 |
+
"grad_norm": 179.60646057128906,
|
| 350 |
+
"learning_rate": 2.4596353994908256e-07,
|
| 351 |
+
"loss": 4.7832,
|
| 352 |
+
"step": 1225
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.09893153937475267,
|
| 356 |
+
"grad_norm": 335.71380615234375,
|
| 357 |
+
"learning_rate": 2.4588109591209485e-07,
|
| 358 |
+
"loss": 4.9979,
|
| 359 |
+
"step": 1250
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.10091017016224772,
|
| 363 |
+
"grad_norm": 149.5147247314453,
|
| 364 |
+
"learning_rate": 2.457986518751072e-07,
|
| 365 |
+
"loss": 4.714,
|
| 366 |
+
"step": 1275
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.10288880094974277,
|
| 370 |
+
"grad_norm": 154.0236358642578,
|
| 371 |
+
"learning_rate": 2.4571620783811947e-07,
|
| 372 |
+
"loss": 4.8015,
|
| 373 |
+
"step": 1300
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.10486743173723784,
|
| 377 |
+
"grad_norm": 450.5319519042969,
|
| 378 |
+
"learning_rate": 2.456337638011318e-07,
|
| 379 |
+
"loss": 4.6914,
|
| 380 |
+
"step": 1325
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.10684606252473289,
|
| 384 |
+
"grad_norm": 195.87863159179688,
|
| 385 |
+
"learning_rate": 2.455513197641441e-07,
|
| 386 |
+
"loss": 5.0124,
|
| 387 |
+
"step": 1350
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.10882469331222794,
|
| 391 |
+
"grad_norm": 198.12225341796875,
|
| 392 |
+
"learning_rate": 2.454688757271564e-07,
|
| 393 |
+
"loss": 4.5305,
|
| 394 |
+
"step": 1375
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.11080332409972299,
|
| 398 |
+
"grad_norm": 161.57623291015625,
|
| 399 |
+
"learning_rate": 2.453864316901687e-07,
|
| 400 |
+
"loss": 4.7806,
|
| 401 |
+
"step": 1400
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.11278195488721804,
|
| 405 |
+
"grad_norm": 187.8081817626953,
|
| 406 |
+
"learning_rate": 2.45303987653181e-07,
|
| 407 |
+
"loss": 4.9401,
|
| 408 |
+
"step": 1425
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.1147605856747131,
|
| 412 |
+
"grad_norm": 160.1893768310547,
|
| 413 |
+
"learning_rate": 2.4522154361619334e-07,
|
| 414 |
+
"loss": 4.8119,
|
| 415 |
+
"step": 1450
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.11673921646220815,
|
| 419 |
+
"grad_norm": 181.8563995361328,
|
| 420 |
+
"learning_rate": 2.4513909957920563e-07,
|
| 421 |
+
"loss": 4.7979,
|
| 422 |
+
"step": 1475
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.1187178472497032,
|
| 426 |
+
"grad_norm": 184.80641174316406,
|
| 427 |
+
"learning_rate": 2.4505665554221796e-07,
|
| 428 |
+
"loss": 4.8448,
|
| 429 |
+
"step": 1500
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.12069647803719825,
|
| 433 |
+
"grad_norm": 151.4502410888672,
|
| 434 |
+
"learning_rate": 2.4497421150523025e-07,
|
| 435 |
+
"loss": 4.7101,
|
| 436 |
+
"step": 1525
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.12267510882469332,
|
| 440 |
+
"grad_norm": 163.2119598388672,
|
| 441 |
+
"learning_rate": 2.4489176746824253e-07,
|
| 442 |
+
"loss": 4.8802,
|
| 443 |
+
"step": 1550
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.12465373961218837,
|
| 447 |
+
"grad_norm": 147.33741760253906,
|
| 448 |
+
"learning_rate": 2.4480932343125487e-07,
|
| 449 |
+
"loss": 4.6433,
|
| 450 |
+
"step": 1575
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.12663237039968342,
|
| 454 |
+
"grad_norm": 145.84716796875,
|
| 455 |
+
"learning_rate": 2.4472687939426716e-07,
|
| 456 |
+
"loss": 4.4118,
|
| 457 |
+
"step": 1600
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.12861100118717847,
|
| 461 |
+
"grad_norm": 111.55641174316406,
|
| 462 |
+
"learning_rate": 2.4464443535727944e-07,
|
| 463 |
+
"loss": 4.819,
|
| 464 |
+
"step": 1625
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.13058963197467352,
|
| 468 |
+
"grad_norm": 145.68092346191406,
|
| 469 |
+
"learning_rate": 2.445619913202918e-07,
|
| 470 |
+
"loss": 4.7752,
|
| 471 |
+
"step": 1650
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.13256826276216857,
|
| 475 |
+
"grad_norm": 274.0830078125,
|
| 476 |
+
"learning_rate": 2.4447954728330407e-07,
|
| 477 |
+
"loss": 4.8566,
|
| 478 |
+
"step": 1675
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 0.13454689354966362,
|
| 482 |
+
"grad_norm": 141.83982849121094,
|
| 483 |
+
"learning_rate": 2.4439710324631635e-07,
|
| 484 |
+
"loss": 4.6643,
|
| 485 |
+
"step": 1700
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.1365255243371587,
|
| 489 |
+
"grad_norm": 182.46160888671875,
|
| 490 |
+
"learning_rate": 2.443146592093287e-07,
|
| 491 |
+
"loss": 4.731,
|
| 492 |
+
"step": 1725
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 0.13850415512465375,
|
| 496 |
+
"grad_norm": 200.28773498535156,
|
| 497 |
+
"learning_rate": 2.44232215172341e-07,
|
| 498 |
+
"loss": 4.5525,
|
| 499 |
+
"step": 1750
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.1404827859121488,
|
| 503 |
+
"grad_norm": 163.7792510986328,
|
| 504 |
+
"learning_rate": 2.441497711353533e-07,
|
| 505 |
+
"loss": 4.8076,
|
| 506 |
+
"step": 1775
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.14246141669964385,
|
| 510 |
+
"grad_norm": 422.9642639160156,
|
| 511 |
+
"learning_rate": 2.440673270983656e-07,
|
| 512 |
+
"loss": 4.7045,
|
| 513 |
+
"step": 1800
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.1444400474871389,
|
| 517 |
+
"grad_norm": 187.99957275390625,
|
| 518 |
+
"learning_rate": 2.4398488306137794e-07,
|
| 519 |
+
"loss": 4.6615,
|
| 520 |
+
"step": 1825
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 0.14641867827463395,
|
| 524 |
+
"grad_norm": 144.52732849121094,
|
| 525 |
+
"learning_rate": 2.439024390243902e-07,
|
| 526 |
+
"loss": 4.7912,
|
| 527 |
+
"step": 1850
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.148397309062129,
|
| 531 |
+
"grad_norm": 192.0771026611328,
|
| 532 |
+
"learning_rate": 2.4381999498740256e-07,
|
| 533 |
+
"loss": 4.7916,
|
| 534 |
+
"step": 1875
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.15037593984962405,
|
| 538 |
+
"grad_norm": 148.06878662109375,
|
| 539 |
+
"learning_rate": 2.4373755095041484e-07,
|
| 540 |
+
"loss": 4.7782,
|
| 541 |
+
"step": 1900
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.1523545706371191,
|
| 545 |
+
"grad_norm": 131.4456329345703,
|
| 546 |
+
"learning_rate": 2.436551069134272e-07,
|
| 547 |
+
"loss": 4.579,
|
| 548 |
+
"step": 1925
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 0.15433320142461418,
|
| 552 |
+
"grad_norm": 141.84681701660156,
|
| 553 |
+
"learning_rate": 2.4357266287643947e-07,
|
| 554 |
+
"loss": 4.5776,
|
| 555 |
+
"step": 1950
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.15631183221210923,
|
| 559 |
+
"grad_norm": 122.31990051269531,
|
| 560 |
+
"learning_rate": 2.4349021883945175e-07,
|
| 561 |
+
"loss": 4.5185,
|
| 562 |
+
"step": 1975
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 0.15829046299960428,
|
| 566 |
+
"grad_norm": 229.08372497558594,
|
| 567 |
+
"learning_rate": 2.434077748024641e-07,
|
| 568 |
+
"loss": 4.6352,
|
| 569 |
+
"step": 2000
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.16026909378709933,
|
| 573 |
+
"grad_norm": 136.54153442382812,
|
| 574 |
+
"learning_rate": 2.433253307654764e-07,
|
| 575 |
+
"loss": 4.5512,
|
| 576 |
+
"step": 2025
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 0.16224772457459438,
|
| 580 |
+
"grad_norm": 237.05514526367188,
|
| 581 |
+
"learning_rate": 2.432428867284887e-07,
|
| 582 |
+
"loss": 4.7146,
|
| 583 |
+
"step": 2050
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.16422635536208943,
|
| 587 |
+
"grad_norm": 149.2750244140625,
|
| 588 |
+
"learning_rate": 2.43160442691501e-07,
|
| 589 |
+
"loss": 4.6935,
|
| 590 |
+
"step": 2075
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 0.16620498614958448,
|
| 594 |
+
"grad_norm": 149.77297973632812,
|
| 595 |
+
"learning_rate": 2.4307799865451334e-07,
|
| 596 |
+
"loss": 4.8223,
|
| 597 |
+
"step": 2100
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.16818361693707953,
|
| 601 |
+
"grad_norm": 235.3883056640625,
|
| 602 |
+
"learning_rate": 2.429955546175256e-07,
|
| 603 |
+
"loss": 4.6266,
|
| 604 |
+
"step": 2125
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 0.17016224772457458,
|
| 608 |
+
"grad_norm": 137.77316284179688,
|
| 609 |
+
"learning_rate": 2.429131105805379e-07,
|
| 610 |
+
"loss": 4.8543,
|
| 611 |
+
"step": 2150
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.17214087851206966,
|
| 615 |
+
"grad_norm": 143.8935089111328,
|
| 616 |
+
"learning_rate": 2.4283066654355025e-07,
|
| 617 |
+
"loss": 4.651,
|
| 618 |
+
"step": 2175
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 0.1741195092995647,
|
| 622 |
+
"grad_norm": 191.43856811523438,
|
| 623 |
+
"learning_rate": 2.4274822250656253e-07,
|
| 624 |
+
"loss": 4.4166,
|
| 625 |
+
"step": 2200
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.17609814008705976,
|
| 629 |
+
"grad_norm": 135.82838439941406,
|
| 630 |
+
"learning_rate": 2.426657784695748e-07,
|
| 631 |
+
"loss": 4.7078,
|
| 632 |
+
"step": 2225
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 0.1780767708745548,
|
| 636 |
+
"grad_norm": 114.28646087646484,
|
| 637 |
+
"learning_rate": 2.4258333443258715e-07,
|
| 638 |
+
"loss": 4.5316,
|
| 639 |
+
"step": 2250
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.18005540166204986,
|
| 643 |
+
"grad_norm": 237.41001892089844,
|
| 644 |
+
"learning_rate": 2.4250089039559944e-07,
|
| 645 |
+
"loss": 4.4699,
|
| 646 |
+
"step": 2275
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 0.1820340324495449,
|
| 650 |
+
"grad_norm": 124.57892608642578,
|
| 651 |
+
"learning_rate": 2.424184463586117e-07,
|
| 652 |
+
"loss": 4.5101,
|
| 653 |
+
"step": 2300
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 0.18401266323703996,
|
| 657 |
+
"grad_norm": 147.15554809570312,
|
| 658 |
+
"learning_rate": 2.4233600232162406e-07,
|
| 659 |
+
"loss": 4.5974,
|
| 660 |
+
"step": 2325
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 0.18599129402453501,
|
| 664 |
+
"grad_norm": 166.0609588623047,
|
| 665 |
+
"learning_rate": 2.4225355828463635e-07,
|
| 666 |
+
"loss": 4.5105,
|
| 667 |
+
"step": 2350
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 0.18796992481203006,
|
| 671 |
+
"grad_norm": 188.97705078125,
|
| 672 |
+
"learning_rate": 2.421711142476487e-07,
|
| 673 |
+
"loss": 4.587,
|
| 674 |
+
"step": 2375
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 0.18994855559952512,
|
| 678 |
+
"grad_norm": 243.09271240234375,
|
| 679 |
+
"learning_rate": 2.4208867021066097e-07,
|
| 680 |
+
"loss": 4.7686,
|
| 681 |
+
"step": 2400
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.1919271863870202,
|
| 685 |
+
"grad_norm": 127.40078735351562,
|
| 686 |
+
"learning_rate": 2.420062261736733e-07,
|
| 687 |
+
"loss": 4.4476,
|
| 688 |
+
"step": 2425
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 0.19390581717451524,
|
| 692 |
+
"grad_norm": 253.8776092529297,
|
| 693 |
+
"learning_rate": 2.419237821366856e-07,
|
| 694 |
+
"loss": 4.5478,
|
| 695 |
+
"step": 2450
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 0.1958844479620103,
|
| 699 |
+
"grad_norm": 123.27115631103516,
|
| 700 |
+
"learning_rate": 2.4184133809969793e-07,
|
| 701 |
+
"loss": 4.3502,
|
| 702 |
+
"step": 2475
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 0.19786307874950534,
|
| 706 |
+
"grad_norm": 138.00375366210938,
|
| 707 |
+
"learning_rate": 2.417588940627102e-07,
|
| 708 |
+
"loss": 4.3534,
|
| 709 |
+
"step": 2500
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 0.1998417095370004,
|
| 713 |
+
"grad_norm": 115.53954315185547,
|
| 714 |
+
"learning_rate": 2.4167645002572256e-07,
|
| 715 |
+
"loss": 4.7066,
|
| 716 |
+
"step": 2525
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 0.20182034032449545,
|
| 720 |
+
"grad_norm": 180.38809204101562,
|
| 721 |
+
"learning_rate": 2.4159400598873484e-07,
|
| 722 |
+
"loss": 4.6605,
|
| 723 |
+
"step": 2550
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 0.2037989711119905,
|
| 727 |
+
"grad_norm": 129.8457489013672,
|
| 728 |
+
"learning_rate": 2.415115619517472e-07,
|
| 729 |
+
"loss": 4.3849,
|
| 730 |
+
"step": 2575
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 0.20577760189948555,
|
| 734 |
+
"grad_norm": 156.64404296875,
|
| 735 |
+
"learning_rate": 2.4142911791475946e-07,
|
| 736 |
+
"loss": 4.3434,
|
| 737 |
+
"step": 2600
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 0.2077562326869806,
|
| 741 |
+
"grad_norm": 162.81320190429688,
|
| 742 |
+
"learning_rate": 2.4134667387777175e-07,
|
| 743 |
+
"loss": 4.5466,
|
| 744 |
+
"step": 2625
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 0.20973486347447567,
|
| 748 |
+
"grad_norm": 128.7244873046875,
|
| 749 |
+
"learning_rate": 2.412642298407841e-07,
|
| 750 |
+
"loss": 4.5358,
|
| 751 |
+
"step": 2650
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 0.21171349426197072,
|
| 755 |
+
"grad_norm": 217.59042358398438,
|
| 756 |
+
"learning_rate": 2.4118178580379637e-07,
|
| 757 |
+
"loss": 4.5235,
|
| 758 |
+
"step": 2675
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 0.21369212504946578,
|
| 762 |
+
"grad_norm": 144.84365844726562,
|
| 763 |
+
"learning_rate": 2.410993417668087e-07,
|
| 764 |
+
"loss": 4.3811,
|
| 765 |
+
"step": 2700
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 0.21567075583696083,
|
| 769 |
+
"grad_norm": 146.22451782226562,
|
| 770 |
+
"learning_rate": 2.41016897729821e-07,
|
| 771 |
+
"loss": 4.3797,
|
| 772 |
+
"step": 2725
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 0.21764938662445588,
|
| 776 |
+
"grad_norm": 198.39772033691406,
|
| 777 |
+
"learning_rate": 2.409344536928333e-07,
|
| 778 |
+
"loss": 4.4303,
|
| 779 |
+
"step": 2750
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 0.21962801741195093,
|
| 783 |
+
"grad_norm": 158.10592651367188,
|
| 784 |
+
"learning_rate": 2.408520096558456e-07,
|
| 785 |
+
"loss": 4.3633,
|
| 786 |
+
"step": 2775
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 0.22160664819944598,
|
| 790 |
+
"grad_norm": 166.79954528808594,
|
| 791 |
+
"learning_rate": 2.407695656188579e-07,
|
| 792 |
+
"loss": 4.5392,
|
| 793 |
+
"step": 2800
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 0.22358527898694103,
|
| 797 |
+
"grad_norm": 207.30593872070312,
|
| 798 |
+
"learning_rate": 2.406871215818702e-07,
|
| 799 |
+
"loss": 4.5003,
|
| 800 |
+
"step": 2825
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 0.22556390977443608,
|
| 804 |
+
"grad_norm": 128.81883239746094,
|
| 805 |
+
"learning_rate": 2.4060467754488253e-07,
|
| 806 |
+
"loss": 4.5416,
|
| 807 |
+
"step": 2850
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 0.22754254056193116,
|
| 811 |
+
"grad_norm": 181.48960876464844,
|
| 812 |
+
"learning_rate": 2.405222335078948e-07,
|
| 813 |
+
"loss": 4.1725,
|
| 814 |
+
"step": 2875
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 0.2295211713494262,
|
| 818 |
+
"grad_norm": 179.47384643554688,
|
| 819 |
+
"learning_rate": 2.4043978947090715e-07,
|
| 820 |
+
"loss": 4.5229,
|
| 821 |
+
"step": 2900
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 0.23149980213692126,
|
| 825 |
+
"grad_norm": 144.242919921875,
|
| 826 |
+
"learning_rate": 2.4035734543391943e-07,
|
| 827 |
+
"loss": 4.3295,
|
| 828 |
+
"step": 2925
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 0.2334784329244163,
|
| 832 |
+
"grad_norm": 177.61968994140625,
|
| 833 |
+
"learning_rate": 2.402749013969317e-07,
|
| 834 |
+
"loss": 4.4266,
|
| 835 |
+
"step": 2950
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 0.23545706371191136,
|
| 839 |
+
"grad_norm": 143.8682861328125,
|
| 840 |
+
"learning_rate": 2.4019245735994406e-07,
|
| 841 |
+
"loss": 4.2341,
|
| 842 |
+
"step": 2975
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 0.2374356944994064,
|
| 846 |
+
"grad_norm": 128.8461151123047,
|
| 847 |
+
"learning_rate": 2.4011001332295634e-07,
|
| 848 |
+
"loss": 4.3676,
|
| 849 |
+
"step": 3000
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 0.23941432528690146,
|
| 853 |
+
"grad_norm": 160.70687866210938,
|
| 854 |
+
"learning_rate": 2.400275692859687e-07,
|
| 855 |
+
"loss": 4.3945,
|
| 856 |
+
"step": 3025
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 0.2413929560743965,
|
| 860 |
+
"grad_norm": 157.65855407714844,
|
| 861 |
+
"learning_rate": 2.3994512524898097e-07,
|
| 862 |
+
"loss": 4.4967,
|
| 863 |
+
"step": 3050
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 0.24337158686189156,
|
| 867 |
+
"grad_norm": 125.79988861083984,
|
| 868 |
+
"learning_rate": 2.398626812119933e-07,
|
| 869 |
+
"loss": 4.279,
|
| 870 |
+
"step": 3075
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 0.24535021764938664,
|
| 874 |
+
"grad_norm": 168.8534698486328,
|
| 875 |
+
"learning_rate": 2.397802371750056e-07,
|
| 876 |
+
"loss": 4.4813,
|
| 877 |
+
"step": 3100
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 0.2473288484368817,
|
| 881 |
+
"grad_norm": 120.4126968383789,
|
| 882 |
+
"learning_rate": 2.3969779313801793e-07,
|
| 883 |
+
"loss": 4.1997,
|
| 884 |
+
"step": 3125
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 0.24930747922437674,
|
| 888 |
+
"grad_norm": 115.56365203857422,
|
| 889 |
+
"learning_rate": 2.396153491010302e-07,
|
| 890 |
+
"loss": 4.4076,
|
| 891 |
+
"step": 3150
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 0.2512861100118718,
|
| 895 |
+
"grad_norm": 152.89859008789062,
|
| 896 |
+
"learning_rate": 2.3953290506404255e-07,
|
| 897 |
+
"loss": 4.2893,
|
| 898 |
+
"step": 3175
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 0.25326474079936684,
|
| 902 |
+
"grad_norm": 177.6272735595703,
|
| 903 |
+
"learning_rate": 2.3945046102705484e-07,
|
| 904 |
+
"loss": 4.4892,
|
| 905 |
+
"step": 3200
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 0.2552433715868619,
|
| 909 |
+
"grad_norm": 131.46661376953125,
|
| 910 |
+
"learning_rate": 2.393680169900671e-07,
|
| 911 |
+
"loss": 4.2702,
|
| 912 |
+
"step": 3225
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 0.25722200237435694,
|
| 916 |
+
"grad_norm": 101.60210418701172,
|
| 917 |
+
"learning_rate": 2.3928557295307946e-07,
|
| 918 |
+
"loss": 4.2209,
|
| 919 |
+
"step": 3250
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 0.259200633161852,
|
| 923 |
+
"grad_norm": 199.7799835205078,
|
| 924 |
+
"learning_rate": 2.3920312891609174e-07,
|
| 925 |
+
"loss": 4.1502,
|
| 926 |
+
"step": 3275
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 0.26117926394934704,
|
| 930 |
+
"grad_norm": 163.44424438476562,
|
| 931 |
+
"learning_rate": 2.391206848791041e-07,
|
| 932 |
+
"loss": 4.3423,
|
| 933 |
+
"step": 3300
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 0.2631578947368421,
|
| 937 |
+
"grad_norm": 148.59519958496094,
|
| 938 |
+
"learning_rate": 2.3903824084211637e-07,
|
| 939 |
+
"loss": 4.4833,
|
| 940 |
+
"step": 3325
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 0.26513652552433714,
|
| 944 |
+
"grad_norm": 129.75927734375,
|
| 945 |
+
"learning_rate": 2.3895579680512865e-07,
|
| 946 |
+
"loss": 4.4745,
|
| 947 |
+
"step": 3350
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 0.2671151563118322,
|
| 951 |
+
"grad_norm": 126.6795654296875,
|
| 952 |
+
"learning_rate": 2.38873352768141e-07,
|
| 953 |
+
"loss": 4.3964,
|
| 954 |
+
"step": 3375
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 0.26909378709932724,
|
| 958 |
+
"grad_norm": 157.1032257080078,
|
| 959 |
+
"learning_rate": 2.387909087311533e-07,
|
| 960 |
+
"loss": 4.3419,
|
| 961 |
+
"step": 3400
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 0.2710724178868223,
|
| 965 |
+
"grad_norm": 142.79139709472656,
|
| 966 |
+
"learning_rate": 2.3870846469416556e-07,
|
| 967 |
+
"loss": 4.2243,
|
| 968 |
+
"step": 3425
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 0.2730510486743174,
|
| 972 |
+
"grad_norm": 137.3797607421875,
|
| 973 |
+
"learning_rate": 2.386260206571779e-07,
|
| 974 |
+
"loss": 4.1661,
|
| 975 |
+
"step": 3450
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 0.27502967946181245,
|
| 979 |
+
"grad_norm": 148.77401733398438,
|
| 980 |
+
"learning_rate": 2.385435766201902e-07,
|
| 981 |
+
"loss": 4.483,
|
| 982 |
+
"step": 3475
|
| 983 |
+
},
|
| 984 |
+
{
|
| 985 |
+
"epoch": 0.2770083102493075,
|
| 986 |
+
"grad_norm": 124.54267120361328,
|
| 987 |
+
"learning_rate": 2.384611325832025e-07,
|
| 988 |
+
"loss": 4.369,
|
| 989 |
+
"step": 3500
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 0.27898694103680255,
|
| 993 |
+
"grad_norm": 113.43370056152344,
|
| 994 |
+
"learning_rate": 2.383786885462148e-07,
|
| 995 |
+
"loss": 4.1491,
|
| 996 |
+
"step": 3525
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 0.2809655718242976,
|
| 1000 |
+
"grad_norm": 155.67677307128906,
|
| 1001 |
+
"learning_rate": 2.3829624450922712e-07,
|
| 1002 |
+
"loss": 4.3403,
|
| 1003 |
+
"step": 3550
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 0.28294420261179265,
|
| 1007 |
+
"grad_norm": 201.27784729003906,
|
| 1008 |
+
"learning_rate": 2.3821380047223943e-07,
|
| 1009 |
+
"loss": 4.3563,
|
| 1010 |
+
"step": 3575
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 0.2849228333992877,
|
| 1014 |
+
"grad_norm": 104.74275970458984,
|
| 1015 |
+
"learning_rate": 2.3813135643525174e-07,
|
| 1016 |
+
"loss": 4.2706,
|
| 1017 |
+
"step": 3600
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 0.28690146418678275,
|
| 1021 |
+
"grad_norm": 133.6251678466797,
|
| 1022 |
+
"learning_rate": 2.3804891239826405e-07,
|
| 1023 |
+
"loss": 4.3637,
|
| 1024 |
+
"step": 3625
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 0.2888800949742778,
|
| 1028 |
+
"grad_norm": 102.35352325439453,
|
| 1029 |
+
"learning_rate": 2.3796646836127634e-07,
|
| 1030 |
+
"loss": 4.2585,
|
| 1031 |
+
"step": 3650
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 0.29085872576177285,
|
| 1035 |
+
"grad_norm": 156.72654724121094,
|
| 1036 |
+
"learning_rate": 2.3788402432428868e-07,
|
| 1037 |
+
"loss": 4.3448,
|
| 1038 |
+
"step": 3675
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"epoch": 0.2928373565492679,
|
| 1042 |
+
"grad_norm": 121.19142150878906,
|
| 1043 |
+
"learning_rate": 2.3780158028730096e-07,
|
| 1044 |
+
"loss": 4.1475,
|
| 1045 |
+
"step": 3700
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 0.29481598733676295,
|
| 1049 |
+
"grad_norm": 138.72952270507812,
|
| 1050 |
+
"learning_rate": 2.3771913625031327e-07,
|
| 1051 |
+
"loss": 4.2475,
|
| 1052 |
+
"step": 3725
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 0.296794618124258,
|
| 1056 |
+
"grad_norm": 314.35113525390625,
|
| 1057 |
+
"learning_rate": 2.3763669221332559e-07,
|
| 1058 |
+
"loss": 4.2643,
|
| 1059 |
+
"step": 3750
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 0.29877324891175305,
|
| 1063 |
+
"grad_norm": 131.71240234375,
|
| 1064 |
+
"learning_rate": 2.375542481763379e-07,
|
| 1065 |
+
"loss": 4.2741,
|
| 1066 |
+
"step": 3775
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 0.3007518796992481,
|
| 1070 |
+
"grad_norm": 193.2744598388672,
|
| 1071 |
+
"learning_rate": 2.374718041393502e-07,
|
| 1072 |
+
"loss": 4.2314,
|
| 1073 |
+
"step": 3800
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 0.30273051048674315,
|
| 1077 |
+
"grad_norm": 146.98760986328125,
|
| 1078 |
+
"learning_rate": 2.3738936010236252e-07,
|
| 1079 |
+
"loss": 4.5421,
|
| 1080 |
+
"step": 3825
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 0.3047091412742382,
|
| 1084 |
+
"grad_norm": 106.49159240722656,
|
| 1085 |
+
"learning_rate": 2.373069160653748e-07,
|
| 1086 |
+
"loss": 4.0922,
|
| 1087 |
+
"step": 3850
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 0.30668777206173325,
|
| 1091 |
+
"grad_norm": 128.12686157226562,
|
| 1092 |
+
"learning_rate": 2.3722447202838712e-07,
|
| 1093 |
+
"loss": 4.3171,
|
| 1094 |
+
"step": 3875
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 0.30866640284922836,
|
| 1098 |
+
"grad_norm": 165.8458251953125,
|
| 1099 |
+
"learning_rate": 2.3714202799139943e-07,
|
| 1100 |
+
"loss": 4.1937,
|
| 1101 |
+
"step": 3900
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 0.3106450336367234,
|
| 1105 |
+
"grad_norm": 129.49652099609375,
|
| 1106 |
+
"learning_rate": 2.3705958395441171e-07,
|
| 1107 |
+
"loss": 4.2486,
|
| 1108 |
+
"step": 3925
|
| 1109 |
+
},
|
| 1110 |
+
{
|
| 1111 |
+
"epoch": 0.31262366442421846,
|
| 1112 |
+
"grad_norm": 113.08882141113281,
|
| 1113 |
+
"learning_rate": 2.3697713991742405e-07,
|
| 1114 |
+
"loss": 3.9533,
|
| 1115 |
+
"step": 3950
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 0.3146022952117135,
|
| 1119 |
+
"grad_norm": 116.51021575927734,
|
| 1120 |
+
"learning_rate": 2.3689469588043634e-07,
|
| 1121 |
+
"loss": 4.2525,
|
| 1122 |
+
"step": 3975
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 0.31658092599920856,
|
| 1126 |
+
"grad_norm": 95.54279327392578,
|
| 1127 |
+
"learning_rate": 2.3681225184344867e-07,
|
| 1128 |
+
"loss": 4.1355,
|
| 1129 |
+
"step": 4000
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 0.3185595567867036,
|
| 1133 |
+
"grad_norm": 123.10621643066406,
|
| 1134 |
+
"learning_rate": 2.3672980780646096e-07,
|
| 1135 |
+
"loss": 4.3705,
|
| 1136 |
+
"step": 4025
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 0.32053818757419866,
|
| 1140 |
+
"grad_norm": 142.11273193359375,
|
| 1141 |
+
"learning_rate": 2.3664736376947327e-07,
|
| 1142 |
+
"loss": 4.2712,
|
| 1143 |
+
"step": 4050
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 0.3225168183616937,
|
| 1147 |
+
"grad_norm": 162.17141723632812,
|
| 1148 |
+
"learning_rate": 2.3656491973248558e-07,
|
| 1149 |
+
"loss": 4.1127,
|
| 1150 |
+
"step": 4075
|
| 1151 |
+
},
|
| 1152 |
+
{
|
| 1153 |
+
"epoch": 0.32449544914918876,
|
| 1154 |
+
"grad_norm": 160.26893615722656,
|
| 1155 |
+
"learning_rate": 2.364824756954979e-07,
|
| 1156 |
+
"loss": 4.2687,
|
| 1157 |
+
"step": 4100
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 0.3264740799366838,
|
| 1161 |
+
"grad_norm": 134.65093994140625,
|
| 1162 |
+
"learning_rate": 2.3640003165851018e-07,
|
| 1163 |
+
"loss": 4.3567,
|
| 1164 |
+
"step": 4125
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 0.32845271072417886,
|
| 1168 |
+
"grad_norm": 178.23516845703125,
|
| 1169 |
+
"learning_rate": 2.3631758762152252e-07,
|
| 1170 |
+
"loss": 4.097,
|
| 1171 |
+
"step": 4150
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 0.3304313415116739,
|
| 1175 |
+
"grad_norm": 151.1556396484375,
|
| 1176 |
+
"learning_rate": 2.362351435845348e-07,
|
| 1177 |
+
"loss": 4.1602,
|
| 1178 |
+
"step": 4175
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 0.33240997229916897,
|
| 1182 |
+
"grad_norm": 154.64442443847656,
|
| 1183 |
+
"learning_rate": 2.3615269954754711e-07,
|
| 1184 |
+
"loss": 4.2365,
|
| 1185 |
+
"step": 4200
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 0.334388603086664,
|
| 1189 |
+
"grad_norm": 226.6827850341797,
|
| 1190 |
+
"learning_rate": 2.3607025551055943e-07,
|
| 1191 |
+
"loss": 4.3196,
|
| 1192 |
+
"step": 4225
|
| 1193 |
+
},
|
| 1194 |
+
{
|
| 1195 |
+
"epoch": 0.33636723387415907,
|
| 1196 |
+
"grad_norm": 172.67916870117188,
|
| 1197 |
+
"learning_rate": 2.359878114735717e-07,
|
| 1198 |
+
"loss": 4.4476,
|
| 1199 |
+
"step": 4250
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 0.3383458646616541,
|
| 1203 |
+
"grad_norm": 124.78984069824219,
|
| 1204 |
+
"learning_rate": 2.3590536743658405e-07,
|
| 1205 |
+
"loss": 4.4006,
|
| 1206 |
+
"step": 4275
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"epoch": 0.34032449544914917,
|
| 1210 |
+
"grad_norm": 156.81365966796875,
|
| 1211 |
+
"learning_rate": 2.3582292339959633e-07,
|
| 1212 |
+
"loss": 4.3914,
|
| 1213 |
+
"step": 4300
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 0.3423031262366442,
|
| 1217 |
+
"grad_norm": 116.53181457519531,
|
| 1218 |
+
"learning_rate": 2.3574047936260865e-07,
|
| 1219 |
+
"loss": 4.2846,
|
| 1220 |
+
"step": 4325
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 0.3442817570241393,
|
| 1224 |
+
"grad_norm": 146.16543579101562,
|
| 1225 |
+
"learning_rate": 2.3565803532562096e-07,
|
| 1226 |
+
"loss": 4.1371,
|
| 1227 |
+
"step": 4350
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 0.3462603878116344,
|
| 1231 |
+
"grad_norm": 213.07974243164062,
|
| 1232 |
+
"learning_rate": 2.3557559128863327e-07,
|
| 1233 |
+
"loss": 4.2294,
|
| 1234 |
+
"step": 4375
|
| 1235 |
+
},
|
| 1236 |
+
{
|
| 1237 |
+
"epoch": 0.3482390185991294,
|
| 1238 |
+
"grad_norm": 99.38206481933594,
|
| 1239 |
+
"learning_rate": 2.3549314725164558e-07,
|
| 1240 |
+
"loss": 4.1726,
|
| 1241 |
+
"step": 4400
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 0.3502176493866245,
|
| 1245 |
+
"grad_norm": 162.97059631347656,
|
| 1246 |
+
"learning_rate": 2.354107032146579e-07,
|
| 1247 |
+
"loss": 4.0507,
|
| 1248 |
+
"step": 4425
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 0.3521962801741195,
|
| 1252 |
+
"grad_norm": 132.77474975585938,
|
| 1253 |
+
"learning_rate": 2.3532825917767018e-07,
|
| 1254 |
+
"loss": 4.0016,
|
| 1255 |
+
"step": 4450
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 0.3541749109616146,
|
| 1259 |
+
"grad_norm": 126.9658203125,
|
| 1260 |
+
"learning_rate": 2.3524581514068252e-07,
|
| 1261 |
+
"loss": 4.2731,
|
| 1262 |
+
"step": 4475
|
| 1263 |
+
},
|
| 1264 |
+
{
|
| 1265 |
+
"epoch": 0.3561535417491096,
|
| 1266 |
+
"grad_norm": 194.47755432128906,
|
| 1267 |
+
"learning_rate": 2.351633711036948e-07,
|
| 1268 |
+
"loss": 4.1119,
|
| 1269 |
+
"step": 4500
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 0.3581321725366047,
|
| 1273 |
+
"grad_norm": 153.6606903076172,
|
| 1274 |
+
"learning_rate": 2.3508092706670709e-07,
|
| 1275 |
+
"loss": 4.4556,
|
| 1276 |
+
"step": 4525
|
| 1277 |
+
},
|
| 1278 |
+
{
|
| 1279 |
+
"epoch": 0.3601108033240997,
|
| 1280 |
+
"grad_norm": 146.66709899902344,
|
| 1281 |
+
"learning_rate": 2.3499848302971942e-07,
|
| 1282 |
+
"loss": 4.3314,
|
| 1283 |
+
"step": 4550
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 0.3620894341115948,
|
| 1287 |
+
"grad_norm": 111.01129913330078,
|
| 1288 |
+
"learning_rate": 2.349160389927317e-07,
|
| 1289 |
+
"loss": 4.2929,
|
| 1290 |
+
"step": 4575
|
| 1291 |
+
},
|
| 1292 |
+
{
|
| 1293 |
+
"epoch": 0.3640680648990898,
|
| 1294 |
+
"grad_norm": 137.40582275390625,
|
| 1295 |
+
"learning_rate": 2.3483359495574405e-07,
|
| 1296 |
+
"loss": 4.2198,
|
| 1297 |
+
"step": 4600
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 0.3660466956865849,
|
| 1301 |
+
"grad_norm": 142.0623779296875,
|
| 1302 |
+
"learning_rate": 2.3475115091875633e-07,
|
| 1303 |
+
"loss": 4.2013,
|
| 1304 |
+
"step": 4625
|
| 1305 |
+
},
|
| 1306 |
+
{
|
| 1307 |
+
"epoch": 0.36802532647407993,
|
| 1308 |
+
"grad_norm": 135.2795867919922,
|
| 1309 |
+
"learning_rate": 2.3466870688176864e-07,
|
| 1310 |
+
"loss": 4.231,
|
| 1311 |
+
"step": 4650
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 0.370003957261575,
|
| 1315 |
+
"grad_norm": 127.59281158447266,
|
| 1316 |
+
"learning_rate": 2.3458626284478096e-07,
|
| 1317 |
+
"loss": 3.9613,
|
| 1318 |
+
"step": 4675
|
| 1319 |
+
},
|
| 1320 |
+
{
|
| 1321 |
+
"epoch": 0.37198258804907003,
|
| 1322 |
+
"grad_norm": 132.48663330078125,
|
| 1323 |
+
"learning_rate": 2.3450381880779327e-07,
|
| 1324 |
+
"loss": 4.1925,
|
| 1325 |
+
"step": 4700
|
| 1326 |
+
},
|
| 1327 |
+
{
|
| 1328 |
+
"epoch": 0.3739612188365651,
|
| 1329 |
+
"grad_norm": 135.35409545898438,
|
| 1330 |
+
"learning_rate": 2.3442137477080555e-07,
|
| 1331 |
+
"loss": 4.1828,
|
| 1332 |
+
"step": 4725
|
| 1333 |
+
},
|
| 1334 |
+
{
|
| 1335 |
+
"epoch": 0.37593984962406013,
|
| 1336 |
+
"grad_norm": 107.55503845214844,
|
| 1337 |
+
"learning_rate": 2.343389307338179e-07,
|
| 1338 |
+
"loss": 4.2578,
|
| 1339 |
+
"step": 4750
|
| 1340 |
+
},
|
| 1341 |
+
{
|
| 1342 |
+
"epoch": 0.3779184804115552,
|
| 1343 |
+
"grad_norm": 132.79620361328125,
|
| 1344 |
+
"learning_rate": 2.3425648669683018e-07,
|
| 1345 |
+
"loss": 4.0254,
|
| 1346 |
+
"step": 4775
|
| 1347 |
+
},
|
| 1348 |
+
{
|
| 1349 |
+
"epoch": 0.37989711119905023,
|
| 1350 |
+
"grad_norm": 123.6044692993164,
|
| 1351 |
+
"learning_rate": 2.341740426598425e-07,
|
| 1352 |
+
"loss": 3.9981,
|
| 1353 |
+
"step": 4800
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"epoch": 0.38187574198654534,
|
| 1357 |
+
"grad_norm": 149.656005859375,
|
| 1358 |
+
"learning_rate": 2.340915986228548e-07,
|
| 1359 |
+
"loss": 4.1067,
|
| 1360 |
+
"step": 4825
|
| 1361 |
+
},
|
| 1362 |
+
{
|
| 1363 |
+
"epoch": 0.3838543727740404,
|
| 1364 |
+
"grad_norm": 122.97380065917969,
|
| 1365 |
+
"learning_rate": 2.3400915458586708e-07,
|
| 1366 |
+
"loss": 4.2396,
|
| 1367 |
+
"step": 4850
|
| 1368 |
+
},
|
| 1369 |
+
{
|
| 1370 |
+
"epoch": 0.38583300356153544,
|
| 1371 |
+
"grad_norm": 140.10183715820312,
|
| 1372 |
+
"learning_rate": 2.3392671054887942e-07,
|
| 1373 |
+
"loss": 4.1309,
|
| 1374 |
+
"step": 4875
|
| 1375 |
+
},
|
| 1376 |
+
{
|
| 1377 |
+
"epoch": 0.3878116343490305,
|
| 1378 |
+
"grad_norm": 137.91583251953125,
|
| 1379 |
+
"learning_rate": 2.338442665118917e-07,
|
| 1380 |
+
"loss": 4.0575,
|
| 1381 |
+
"step": 4900
|
| 1382 |
+
},
|
| 1383 |
+
{
|
| 1384 |
+
"epoch": 0.38979026513652554,
|
| 1385 |
+
"grad_norm": 137.72152709960938,
|
| 1386 |
+
"learning_rate": 2.3376182247490402e-07,
|
| 1387 |
+
"loss": 4.159,
|
| 1388 |
+
"step": 4925
|
| 1389 |
+
},
|
| 1390 |
+
{
|
| 1391 |
+
"epoch": 0.3917688959240206,
|
| 1392 |
+
"grad_norm": 84.3819808959961,
|
| 1393 |
+
"learning_rate": 2.3367937843791633e-07,
|
| 1394 |
+
"loss": 4.2611,
|
| 1395 |
+
"step": 4950
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"epoch": 0.39374752671151564,
|
| 1399 |
+
"grad_norm": 200.3111114501953,
|
| 1400 |
+
"learning_rate": 2.3359693440092864e-07,
|
| 1401 |
+
"loss": 4.167,
|
| 1402 |
+
"step": 4975
|
| 1403 |
+
},
|
| 1404 |
+
{
|
| 1405 |
+
"epoch": 0.3957261574990107,
|
| 1406 |
+
"grad_norm": 123.27460479736328,
|
| 1407 |
+
"learning_rate": 2.3351449036394095e-07,
|
| 1408 |
+
"loss": 4.2918,
|
| 1409 |
+
"step": 5000
|
| 1410 |
+
},
|
| 1411 |
+
{
|
| 1412 |
+
"epoch": 0.39770478828650574,
|
| 1413 |
+
"grad_norm": 111.70620727539062,
|
| 1414 |
+
"learning_rate": 2.3343204632695327e-07,
|
| 1415 |
+
"loss": 4.2242,
|
| 1416 |
+
"step": 5025
|
| 1417 |
+
},
|
| 1418 |
+
{
|
| 1419 |
+
"epoch": 0.3996834190740008,
|
| 1420 |
+
"grad_norm": 107.74165344238281,
|
| 1421 |
+
"learning_rate": 2.3334960228996555e-07,
|
| 1422 |
+
"loss": 4.3572,
|
| 1423 |
+
"step": 5050
|
| 1424 |
+
},
|
| 1425 |
+
{
|
| 1426 |
+
"epoch": 0.40166204986149584,
|
| 1427 |
+
"grad_norm": 138.31423950195312,
|
| 1428 |
+
"learning_rate": 2.332671582529779e-07,
|
| 1429 |
+
"loss": 4.1759,
|
| 1430 |
+
"step": 5075
|
| 1431 |
+
},
|
| 1432 |
+
{
|
| 1433 |
+
"epoch": 0.4036406806489909,
|
| 1434 |
+
"grad_norm": 104.73587799072266,
|
| 1435 |
+
"learning_rate": 2.3318471421599017e-07,
|
| 1436 |
+
"loss": 4.1695,
|
| 1437 |
+
"step": 5100
|
| 1438 |
+
},
|
| 1439 |
+
{
|
| 1440 |
+
"epoch": 0.40561931143648594,
|
| 1441 |
+
"grad_norm": 138.1061553955078,
|
| 1442 |
+
"learning_rate": 2.3310227017900246e-07,
|
| 1443 |
+
"loss": 4.0986,
|
| 1444 |
+
"step": 5125
|
| 1445 |
+
},
|
| 1446 |
+
{
|
| 1447 |
+
"epoch": 0.407597942223981,
|
| 1448 |
+
"grad_norm": 148.92279052734375,
|
| 1449 |
+
"learning_rate": 2.330198261420148e-07,
|
| 1450 |
+
"loss": 4.3455,
|
| 1451 |
+
"step": 5150
|
| 1452 |
+
},
|
| 1453 |
+
{
|
| 1454 |
+
"epoch": 0.40957657301147604,
|
| 1455 |
+
"grad_norm": 321.29852294921875,
|
| 1456 |
+
"learning_rate": 2.3293738210502708e-07,
|
| 1457 |
+
"loss": 4.1285,
|
| 1458 |
+
"step": 5175
|
| 1459 |
+
},
|
| 1460 |
+
{
|
| 1461 |
+
"epoch": 0.4115552037989711,
|
| 1462 |
+
"grad_norm": 114.85989379882812,
|
| 1463 |
+
"learning_rate": 2.3285493806803942e-07,
|
| 1464 |
+
"loss": 3.9628,
|
| 1465 |
+
"step": 5200
|
| 1466 |
+
},
|
| 1467 |
+
{
|
| 1468 |
+
"epoch": 0.41353383458646614,
|
| 1469 |
+
"grad_norm": 137.27610778808594,
|
| 1470 |
+
"learning_rate": 2.327724940310517e-07,
|
| 1471 |
+
"loss": 4.1521,
|
| 1472 |
+
"step": 5225
|
| 1473 |
+
},
|
| 1474 |
+
{
|
| 1475 |
+
"epoch": 0.4155124653739612,
|
| 1476 |
+
"grad_norm": 96.02686309814453,
|
| 1477 |
+
"learning_rate": 2.3269004999406402e-07,
|
| 1478 |
+
"loss": 4.027,
|
| 1479 |
+
"step": 5250
|
| 1480 |
+
},
|
| 1481 |
+
{
|
| 1482 |
+
"epoch": 0.4174910961614563,
|
| 1483 |
+
"grad_norm": 213.81649780273438,
|
| 1484 |
+
"learning_rate": 2.3260760595707633e-07,
|
| 1485 |
+
"loss": 4.0522,
|
| 1486 |
+
"step": 5275
|
| 1487 |
+
},
|
| 1488 |
+
{
|
| 1489 |
+
"epoch": 0.41946972694895135,
|
| 1490 |
+
"grad_norm": 160.4125518798828,
|
| 1491 |
+
"learning_rate": 2.3252516192008864e-07,
|
| 1492 |
+
"loss": 4.09,
|
| 1493 |
+
"step": 5300
|
| 1494 |
+
},
|
| 1495 |
+
{
|
| 1496 |
+
"epoch": 0.4214483577364464,
|
| 1497 |
+
"grad_norm": 167.58741760253906,
|
| 1498 |
+
"learning_rate": 2.3244271788310093e-07,
|
| 1499 |
+
"loss": 4.1128,
|
| 1500 |
+
"step": 5325
|
| 1501 |
+
},
|
| 1502 |
+
{
|
| 1503 |
+
"epoch": 0.42342698852394145,
|
| 1504 |
+
"grad_norm": 159.55303955078125,
|
| 1505 |
+
"learning_rate": 2.3236027384611326e-07,
|
| 1506 |
+
"loss": 4.0867,
|
| 1507 |
+
"step": 5350
|
| 1508 |
+
},
|
| 1509 |
+
{
|
| 1510 |
+
"epoch": 0.4254056193114365,
|
| 1511 |
+
"grad_norm": 122.51324462890625,
|
| 1512 |
+
"learning_rate": 2.3227782980912555e-07,
|
| 1513 |
+
"loss": 4.2261,
|
| 1514 |
+
"step": 5375
|
| 1515 |
+
},
|
| 1516 |
+
{
|
| 1517 |
+
"epoch": 0.42738425009893155,
|
| 1518 |
+
"grad_norm": 185.9108428955078,
|
| 1519 |
+
"learning_rate": 2.3219538577213789e-07,
|
| 1520 |
+
"loss": 3.9684,
|
| 1521 |
+
"step": 5400
|
| 1522 |
+
},
|
| 1523 |
+
{
|
| 1524 |
+
"epoch": 0.4293628808864266,
|
| 1525 |
+
"grad_norm": 195.37579345703125,
|
| 1526 |
+
"learning_rate": 2.3211294173515017e-07,
|
| 1527 |
+
"loss": 4.0779,
|
| 1528 |
+
"step": 5425
|
| 1529 |
+
},
|
| 1530 |
+
{
|
| 1531 |
+
"epoch": 0.43134151167392165,
|
| 1532 |
+
"grad_norm": 157.84371948242188,
|
| 1533 |
+
"learning_rate": 2.3203049769816246e-07,
|
| 1534 |
+
"loss": 4.1991,
|
| 1535 |
+
"step": 5450
|
| 1536 |
+
},
|
| 1537 |
+
{
|
| 1538 |
+
"epoch": 0.4333201424614167,
|
| 1539 |
+
"grad_norm": 111.01512908935547,
|
| 1540 |
+
"learning_rate": 2.319480536611748e-07,
|
| 1541 |
+
"loss": 3.9962,
|
| 1542 |
+
"step": 5475
|
| 1543 |
+
},
|
| 1544 |
+
{
|
| 1545 |
+
"epoch": 0.43529877324891175,
|
| 1546 |
+
"grad_norm": 114.49053955078125,
|
| 1547 |
+
"learning_rate": 2.3186560962418708e-07,
|
| 1548 |
+
"loss": 3.8972,
|
| 1549 |
+
"step": 5500
|
| 1550 |
+
},
|
| 1551 |
+
{
|
| 1552 |
+
"epoch": 0.4372774040364068,
|
| 1553 |
+
"grad_norm": 168.17874145507812,
|
| 1554 |
+
"learning_rate": 2.317831655871994e-07,
|
| 1555 |
+
"loss": 4.1913,
|
| 1556 |
+
"step": 5525
|
| 1557 |
+
},
|
| 1558 |
+
{
|
| 1559 |
+
"epoch": 0.43925603482390185,
|
| 1560 |
+
"grad_norm": 140.61912536621094,
|
| 1561 |
+
"learning_rate": 2.317007215502117e-07,
|
| 1562 |
+
"loss": 4.1396,
|
| 1563 |
+
"step": 5550
|
| 1564 |
+
},
|
| 1565 |
+
{
|
| 1566 |
+
"epoch": 0.4412346656113969,
|
| 1567 |
+
"grad_norm": 138.01805114746094,
|
| 1568 |
+
"learning_rate": 2.3161827751322401e-07,
|
| 1569 |
+
"loss": 4.1399,
|
| 1570 |
+
"step": 5575
|
| 1571 |
+
},
|
| 1572 |
+
{
|
| 1573 |
+
"epoch": 0.44321329639889195,
|
| 1574 |
+
"grad_norm": 188.0181427001953,
|
| 1575 |
+
"learning_rate": 2.3153583347623633e-07,
|
| 1576 |
+
"loss": 4.0329,
|
| 1577 |
+
"step": 5600
|
| 1578 |
+
},
|
| 1579 |
+
{
|
| 1580 |
+
"epoch": 0.445191927186387,
|
| 1581 |
+
"grad_norm": 170.8402099609375,
|
| 1582 |
+
"learning_rate": 2.3145338943924864e-07,
|
| 1583 |
+
"loss": 4.3414,
|
| 1584 |
+
"step": 5625
|
| 1585 |
+
},
|
| 1586 |
+
{
|
| 1587 |
+
"epoch": 0.44717055797388205,
|
| 1588 |
+
"grad_norm": 200.65077209472656,
|
| 1589 |
+
"learning_rate": 2.3137094540226092e-07,
|
| 1590 |
+
"loss": 4.2154,
|
| 1591 |
+
"step": 5650
|
| 1592 |
+
},
|
| 1593 |
+
{
|
| 1594 |
+
"epoch": 0.4491491887613771,
|
| 1595 |
+
"grad_norm": 120.18091583251953,
|
| 1596 |
+
"learning_rate": 2.3128850136527326e-07,
|
| 1597 |
+
"loss": 4.0372,
|
| 1598 |
+
"step": 5675
|
| 1599 |
+
},
|
| 1600 |
+
{
|
| 1601 |
+
"epoch": 0.45112781954887216,
|
| 1602 |
+
"grad_norm": 89.9730224609375,
|
| 1603 |
+
"learning_rate": 2.3120605732828555e-07,
|
| 1604 |
+
"loss": 4.1059,
|
| 1605 |
+
"step": 5700
|
| 1606 |
+
},
|
| 1607 |
+
{
|
| 1608 |
+
"epoch": 0.45310645033636726,
|
| 1609 |
+
"grad_norm": 133.7999267578125,
|
| 1610 |
+
"learning_rate": 2.3112361329129786e-07,
|
| 1611 |
+
"loss": 4.2035,
|
| 1612 |
+
"step": 5725
|
| 1613 |
+
},
|
| 1614 |
+
{
|
| 1615 |
+
"epoch": 0.4550850811238623,
|
| 1616 |
+
"grad_norm": 88.3386459350586,
|
| 1617 |
+
"learning_rate": 2.3104116925431017e-07,
|
| 1618 |
+
"loss": 4.0566,
|
| 1619 |
+
"step": 5750
|
| 1620 |
+
},
|
| 1621 |
+
{
|
| 1622 |
+
"epoch": 0.45706371191135736,
|
| 1623 |
+
"grad_norm": 130.95127868652344,
|
| 1624 |
+
"learning_rate": 2.3095872521732245e-07,
|
| 1625 |
+
"loss": 4.3084,
|
| 1626 |
+
"step": 5775
|
| 1627 |
+
},
|
| 1628 |
+
{
|
| 1629 |
+
"epoch": 0.4590423426988524,
|
| 1630 |
+
"grad_norm": 162.55679321289062,
|
| 1631 |
+
"learning_rate": 2.308762811803348e-07,
|
| 1632 |
+
"loss": 4.0288,
|
| 1633 |
+
"step": 5800
|
| 1634 |
+
},
|
| 1635 |
+
{
|
| 1636 |
+
"epoch": 0.46102097348634746,
|
| 1637 |
+
"grad_norm": 104.4178695678711,
|
| 1638 |
+
"learning_rate": 2.3079383714334708e-07,
|
| 1639 |
+
"loss": 3.9244,
|
| 1640 |
+
"step": 5825
|
| 1641 |
+
},
|
| 1642 |
+
{
|
| 1643 |
+
"epoch": 0.4629996042738425,
|
| 1644 |
+
"grad_norm": 235.28123474121094,
|
| 1645 |
+
"learning_rate": 2.307113931063594e-07,
|
| 1646 |
+
"loss": 4.1106,
|
| 1647 |
+
"step": 5850
|
| 1648 |
+
},
|
| 1649 |
+
{
|
| 1650 |
+
"epoch": 0.46497823506133756,
|
| 1651 |
+
"grad_norm": 289.6645812988281,
|
| 1652 |
+
"learning_rate": 2.306289490693717e-07,
|
| 1653 |
+
"loss": 4.0457,
|
| 1654 |
+
"step": 5875
|
| 1655 |
+
},
|
| 1656 |
+
{
|
| 1657 |
+
"epoch": 0.4669568658488326,
|
| 1658 |
+
"grad_norm": 99.97111511230469,
|
| 1659 |
+
"learning_rate": 2.30546505032384e-07,
|
| 1660 |
+
"loss": 4.2542,
|
| 1661 |
+
"step": 5900
|
| 1662 |
+
},
|
| 1663 |
+
{
|
| 1664 |
+
"epoch": 0.46893549663632766,
|
| 1665 |
+
"grad_norm": 260.0950622558594,
|
| 1666 |
+
"learning_rate": 2.304640609953963e-07,
|
| 1667 |
+
"loss": 4.1564,
|
| 1668 |
+
"step": 5925
|
| 1669 |
+
},
|
| 1670 |
+
{
|
| 1671 |
+
"epoch": 0.4709141274238227,
|
| 1672 |
+
"grad_norm": 113.74392700195312,
|
| 1673 |
+
"learning_rate": 2.3038161695840864e-07,
|
| 1674 |
+
"loss": 4.0403,
|
| 1675 |
+
"step": 5950
|
| 1676 |
+
},
|
| 1677 |
+
{
|
| 1678 |
+
"epoch": 0.47289275821131777,
|
| 1679 |
+
"grad_norm": 79.32340240478516,
|
| 1680 |
+
"learning_rate": 2.3029917292142092e-07,
|
| 1681 |
+
"loss": 4.0408,
|
| 1682 |
+
"step": 5975
|
| 1683 |
+
},
|
| 1684 |
+
{
|
| 1685 |
+
"epoch": 0.4748713889988128,
|
| 1686 |
+
"grad_norm": 95.92308807373047,
|
| 1687 |
+
"learning_rate": 2.3021672888443326e-07,
|
| 1688 |
+
"loss": 3.9811,
|
| 1689 |
+
"step": 6000
|
| 1690 |
+
},
|
| 1691 |
+
{
|
| 1692 |
+
"epoch": 0.47685001978630787,
|
| 1693 |
+
"grad_norm": 94.5758285522461,
|
| 1694 |
+
"learning_rate": 2.3013428484744554e-07,
|
| 1695 |
+
"loss": 4.1102,
|
| 1696 |
+
"step": 6025
|
| 1697 |
+
},
|
| 1698 |
+
{
|
| 1699 |
+
"epoch": 0.4788286505738029,
|
| 1700 |
+
"grad_norm": 142.32131958007812,
|
| 1701 |
+
"learning_rate": 2.3005184081045786e-07,
|
| 1702 |
+
"loss": 3.989,
|
| 1703 |
+
"step": 6050
|
| 1704 |
+
},
|
| 1705 |
+
{
|
| 1706 |
+
"epoch": 0.48080728136129797,
|
| 1707 |
+
"grad_norm": 97.84469604492188,
|
| 1708 |
+
"learning_rate": 2.2996939677347017e-07,
|
| 1709 |
+
"loss": 3.9512,
|
| 1710 |
+
"step": 6075
|
| 1711 |
+
},
|
| 1712 |
+
{
|
| 1713 |
+
"epoch": 0.482785912148793,
|
| 1714 |
+
"grad_norm": 94.38491821289062,
|
| 1715 |
+
"learning_rate": 2.2988695273648245e-07,
|
| 1716 |
+
"loss": 3.9475,
|
| 1717 |
+
"step": 6100
|
| 1718 |
+
},
|
| 1719 |
+
{
|
| 1720 |
+
"epoch": 0.48476454293628807,
|
| 1721 |
+
"grad_norm": 124.32872772216797,
|
| 1722 |
+
"learning_rate": 2.2980450869949476e-07,
|
| 1723 |
+
"loss": 4.1352,
|
| 1724 |
+
"step": 6125
|
| 1725 |
+
},
|
| 1726 |
+
{
|
| 1727 |
+
"epoch": 0.4867431737237831,
|
| 1728 |
+
"grad_norm": 196.1511993408203,
|
| 1729 |
+
"learning_rate": 2.2972206466250708e-07,
|
| 1730 |
+
"loss": 4.2956,
|
| 1731 |
+
"step": 6150
|
| 1732 |
+
},
|
| 1733 |
+
{
|
| 1734 |
+
"epoch": 0.48872180451127817,
|
| 1735 |
+
"grad_norm": 144.1227264404297,
|
| 1736 |
+
"learning_rate": 2.296396206255194e-07,
|
| 1737 |
+
"loss": 3.9718,
|
| 1738 |
+
"step": 6175
|
| 1739 |
+
},
|
| 1740 |
+
{
|
| 1741 |
+
"epoch": 0.4907004352987733,
|
| 1742 |
+
"grad_norm": 115.52275085449219,
|
| 1743 |
+
"learning_rate": 2.295571765885317e-07,
|
| 1744 |
+
"loss": 3.9135,
|
| 1745 |
+
"step": 6200
|
| 1746 |
+
},
|
| 1747 |
+
{
|
| 1748 |
+
"epoch": 0.4926790660862683,
|
| 1749 |
+
"grad_norm": 117.71548461914062,
|
| 1750 |
+
"learning_rate": 2.29474732551544e-07,
|
| 1751 |
+
"loss": 3.9026,
|
| 1752 |
+
"step": 6225
|
| 1753 |
+
},
|
| 1754 |
+
{
|
| 1755 |
+
"epoch": 0.4946576968737634,
|
| 1756 |
+
"grad_norm": 135.42698669433594,
|
| 1757 |
+
"learning_rate": 2.293922885145563e-07,
|
| 1758 |
+
"loss": 4.0369,
|
| 1759 |
+
"step": 6250
|
| 1760 |
+
},
|
| 1761 |
+
{
|
| 1762 |
+
"epoch": 0.4966363276612584,
|
| 1763 |
+
"grad_norm": 142.4741973876953,
|
| 1764 |
+
"learning_rate": 2.2930984447756863e-07,
|
| 1765 |
+
"loss": 4.3588,
|
| 1766 |
+
"step": 6275
|
| 1767 |
+
},
|
| 1768 |
+
{
|
| 1769 |
+
"epoch": 0.4986149584487535,
|
| 1770 |
+
"grad_norm": 128.56195068359375,
|
| 1771 |
+
"learning_rate": 2.2922740044058092e-07,
|
| 1772 |
+
"loss": 3.9089,
|
| 1773 |
+
"step": 6300
|
| 1774 |
+
},
|
| 1775 |
+
{
|
| 1776 |
+
"epoch": 0.5005935892362485,
|
| 1777 |
+
"grad_norm": 96.84894561767578,
|
| 1778 |
+
"learning_rate": 2.2914495640359323e-07,
|
| 1779 |
+
"loss": 4.1722,
|
| 1780 |
+
"step": 6325
|
| 1781 |
+
},
|
| 1782 |
+
{
|
| 1783 |
+
"epoch": 0.5025722200237436,
|
| 1784 |
+
"grad_norm": 236.92965698242188,
|
| 1785 |
+
"learning_rate": 2.2906251236660554e-07,
|
| 1786 |
+
"loss": 3.9729,
|
| 1787 |
+
"step": 6350
|
| 1788 |
+
},
|
| 1789 |
+
{
|
| 1790 |
+
"epoch": 0.5045508508112386,
|
| 1791 |
+
"grad_norm": 135.83609008789062,
|
| 1792 |
+
"learning_rate": 2.2898006832961783e-07,
|
| 1793 |
+
"loss": 4.0322,
|
| 1794 |
+
"step": 6375
|
| 1795 |
+
},
|
| 1796 |
+
{
|
| 1797 |
+
"epoch": 0.5065294815987337,
|
| 1798 |
+
"grad_norm": 123.36375427246094,
|
| 1799 |
+
"learning_rate": 2.2889762429263017e-07,
|
| 1800 |
+
"loss": 4.0042,
|
| 1801 |
+
"step": 6400
|
| 1802 |
+
},
|
| 1803 |
+
{
|
| 1804 |
+
"epoch": 0.5085081123862287,
|
| 1805 |
+
"grad_norm": 118.30574035644531,
|
| 1806 |
+
"learning_rate": 2.2881518025564245e-07,
|
| 1807 |
+
"loss": 4.1079,
|
| 1808 |
+
"step": 6425
|
| 1809 |
+
},
|
| 1810 |
+
{
|
| 1811 |
+
"epoch": 0.5104867431737238,
|
| 1812 |
+
"grad_norm": 107.81358337402344,
|
| 1813 |
+
"learning_rate": 2.2873273621865476e-07,
|
| 1814 |
+
"loss": 4.1198,
|
| 1815 |
+
"step": 6450
|
| 1816 |
+
},
|
| 1817 |
+
{
|
| 1818 |
+
"epoch": 0.5124653739612188,
|
| 1819 |
+
"grad_norm": 146.2493438720703,
|
| 1820 |
+
"learning_rate": 2.2865029218166707e-07,
|
| 1821 |
+
"loss": 4.0814,
|
| 1822 |
+
"step": 6475
|
| 1823 |
+
},
|
| 1824 |
+
{
|
| 1825 |
+
"epoch": 0.5144440047487139,
|
| 1826 |
+
"grad_norm": 136.8212890625,
|
| 1827 |
+
"learning_rate": 2.2856784814467939e-07,
|
| 1828 |
+
"loss": 4.0562,
|
| 1829 |
+
"step": 6500
|
| 1830 |
+
},
|
| 1831 |
+
{
|
| 1832 |
+
"epoch": 0.5164226355362089,
|
| 1833 |
+
"grad_norm": 139.30670166015625,
|
| 1834 |
+
"learning_rate": 2.2848540410769167e-07,
|
| 1835 |
+
"loss": 4.1199,
|
| 1836 |
+
"step": 6525
|
| 1837 |
+
},
|
| 1838 |
+
{
|
| 1839 |
+
"epoch": 0.518401266323704,
|
| 1840 |
+
"grad_norm": 194.90414428710938,
|
| 1841 |
+
"learning_rate": 2.28402960070704e-07,
|
| 1842 |
+
"loss": 4.0562,
|
| 1843 |
+
"step": 6550
|
| 1844 |
+
},
|
| 1845 |
+
{
|
| 1846 |
+
"epoch": 0.520379897111199,
|
| 1847 |
+
"grad_norm": 103.54257202148438,
|
| 1848 |
+
"learning_rate": 2.283205160337163e-07,
|
| 1849 |
+
"loss": 4.0797,
|
| 1850 |
+
"step": 6575
|
| 1851 |
+
},
|
| 1852 |
+
{
|
| 1853 |
+
"epoch": 0.5223585278986941,
|
| 1854 |
+
"grad_norm": 101.63102722167969,
|
| 1855 |
+
"learning_rate": 2.2823807199672863e-07,
|
| 1856 |
+
"loss": 4.0591,
|
| 1857 |
+
"step": 6600
|
| 1858 |
+
},
|
| 1859 |
+
{
|
| 1860 |
+
"epoch": 0.5243371586861891,
|
| 1861 |
+
"grad_norm": 104.28479766845703,
|
| 1862 |
+
"learning_rate": 2.2815562795974092e-07,
|
| 1863 |
+
"loss": 3.8991,
|
| 1864 |
+
"step": 6625
|
| 1865 |
+
},
|
| 1866 |
+
{
|
| 1867 |
+
"epoch": 0.5263157894736842,
|
| 1868 |
+
"grad_norm": 166.01107788085938,
|
| 1869 |
+
"learning_rate": 2.2807318392275323e-07,
|
| 1870 |
+
"loss": 4.1011,
|
| 1871 |
+
"step": 6650
|
| 1872 |
+
},
|
| 1873 |
+
{
|
| 1874 |
+
"epoch": 0.5282944202611792,
|
| 1875 |
+
"grad_norm": 154.64959716796875,
|
| 1876 |
+
"learning_rate": 2.2799073988576554e-07,
|
| 1877 |
+
"loss": 3.9283,
|
| 1878 |
+
"step": 6675
|
| 1879 |
+
},
|
| 1880 |
+
{
|
| 1881 |
+
"epoch": 0.5302730510486743,
|
| 1882 |
+
"grad_norm": 96.0099868774414,
|
| 1883 |
+
"learning_rate": 2.2790829584877782e-07,
|
| 1884 |
+
"loss": 3.8247,
|
| 1885 |
+
"step": 6700
|
| 1886 |
+
},
|
| 1887 |
+
{
|
| 1888 |
+
"epoch": 0.5322516818361693,
|
| 1889 |
+
"grad_norm": 120.90514373779297,
|
| 1890 |
+
"learning_rate": 2.2782585181179014e-07,
|
| 1891 |
+
"loss": 4.0629,
|
| 1892 |
+
"step": 6725
|
| 1893 |
+
},
|
| 1894 |
+
{
|
| 1895 |
+
"epoch": 0.5342303126236644,
|
| 1896 |
+
"grad_norm": 106.48863983154297,
|
| 1897 |
+
"learning_rate": 2.2774340777480245e-07,
|
| 1898 |
+
"loss": 4.0127,
|
| 1899 |
+
"step": 6750
|
| 1900 |
+
},
|
| 1901 |
+
{
|
| 1902 |
+
"epoch": 0.5362089434111594,
|
| 1903 |
+
"grad_norm": 113.17047882080078,
|
| 1904 |
+
"learning_rate": 2.2766096373781476e-07,
|
| 1905 |
+
"loss": 4.03,
|
| 1906 |
+
"step": 6775
|
| 1907 |
+
},
|
| 1908 |
+
{
|
| 1909 |
+
"epoch": 0.5381875741986545,
|
| 1910 |
+
"grad_norm": 130.6500701904297,
|
| 1911 |
+
"learning_rate": 2.2757851970082707e-07,
|
| 1912 |
+
"loss": 4.0192,
|
| 1913 |
+
"step": 6800
|
| 1914 |
+
},
|
| 1915 |
+
{
|
| 1916 |
+
"epoch": 0.5401662049861495,
|
| 1917 |
+
"grad_norm": 142.3747100830078,
|
| 1918 |
+
"learning_rate": 2.2749607566383938e-07,
|
| 1919 |
+
"loss": 4.1507,
|
| 1920 |
+
"step": 6825
|
| 1921 |
+
},
|
| 1922 |
+
{
|
| 1923 |
+
"epoch": 0.5421448357736446,
|
| 1924 |
+
"grad_norm": 125.88548278808594,
|
| 1925 |
+
"learning_rate": 2.2741363162685167e-07,
|
| 1926 |
+
"loss": 4.2026,
|
| 1927 |
+
"step": 6850
|
| 1928 |
+
},
|
| 1929 |
+
{
|
| 1930 |
+
"epoch": 0.5441234665611397,
|
| 1931 |
+
"grad_norm": 156.44570922851562,
|
| 1932 |
+
"learning_rate": 2.27331187589864e-07,
|
| 1933 |
+
"loss": 4.1063,
|
| 1934 |
+
"step": 6875
|
| 1935 |
+
},
|
| 1936 |
+
{
|
| 1937 |
+
"epoch": 0.5461020973486348,
|
| 1938 |
+
"grad_norm": 150.82635498046875,
|
| 1939 |
+
"learning_rate": 2.272487435528763e-07,
|
| 1940 |
+
"loss": 4.0477,
|
| 1941 |
+
"step": 6900
|
| 1942 |
+
},
|
| 1943 |
+
{
|
| 1944 |
+
"epoch": 0.5480807281361298,
|
| 1945 |
+
"grad_norm": 170.67994689941406,
|
| 1946 |
+
"learning_rate": 2.271662995158886e-07,
|
| 1947 |
+
"loss": 4.1398,
|
| 1948 |
+
"step": 6925
|
| 1949 |
+
},
|
| 1950 |
+
{
|
| 1951 |
+
"epoch": 0.5500593589236249,
|
| 1952 |
+
"grad_norm": 114.224609375,
|
| 1953 |
+
"learning_rate": 2.2708385547890091e-07,
|
| 1954 |
+
"loss": 4.0906,
|
| 1955 |
+
"step": 6950
|
| 1956 |
+
},
|
| 1957 |
+
{
|
| 1958 |
+
"epoch": 0.55203798971112,
|
| 1959 |
+
"grad_norm": 135.5966033935547,
|
| 1960 |
+
"learning_rate": 2.2700141144191323e-07,
|
| 1961 |
+
"loss": 3.872,
|
| 1962 |
+
"step": 6975
|
| 1963 |
+
},
|
| 1964 |
+
{
|
| 1965 |
+
"epoch": 0.554016620498615,
|
| 1966 |
+
"grad_norm": 120.73974609375,
|
| 1967 |
+
"learning_rate": 2.2691896740492554e-07,
|
| 1968 |
+
"loss": 3.9762,
|
| 1969 |
+
"step": 7000
|
| 1970 |
+
},
|
| 1971 |
+
{
|
| 1972 |
+
"epoch": 0.55599525128611,
|
| 1973 |
+
"grad_norm": 107.66891479492188,
|
| 1974 |
+
"learning_rate": 2.2683652336793782e-07,
|
| 1975 |
+
"loss": 4.0551,
|
| 1976 |
+
"step": 7025
|
| 1977 |
+
},
|
| 1978 |
+
{
|
| 1979 |
+
"epoch": 0.5579738820736051,
|
| 1980 |
+
"grad_norm": 107.60162353515625,
|
| 1981 |
+
"learning_rate": 2.2675407933095013e-07,
|
| 1982 |
+
"loss": 3.973,
|
| 1983 |
+
"step": 7050
|
| 1984 |
+
},
|
| 1985 |
+
{
|
| 1986 |
+
"epoch": 0.5599525128611001,
|
| 1987 |
+
"grad_norm": 118.88258361816406,
|
| 1988 |
+
"learning_rate": 2.2667163529396245e-07,
|
| 1989 |
+
"loss": 3.9864,
|
| 1990 |
+
"step": 7075
|
| 1991 |
+
},
|
| 1992 |
+
{
|
| 1993 |
+
"epoch": 0.5619311436485952,
|
| 1994 |
+
"grad_norm": 148.85667419433594,
|
| 1995 |
+
"learning_rate": 2.2658919125697476e-07,
|
| 1996 |
+
"loss": 3.9409,
|
| 1997 |
+
"step": 7100
|
| 1998 |
+
},
|
| 1999 |
+
{
|
| 2000 |
+
"epoch": 0.5639097744360902,
|
| 2001 |
+
"grad_norm": 148.57321166992188,
|
| 2002 |
+
"learning_rate": 2.2650674721998704e-07,
|
| 2003 |
+
"loss": 3.9611,
|
| 2004 |
+
"step": 7125
|
| 2005 |
+
},
|
| 2006 |
+
{
|
| 2007 |
+
"epoch": 0.5658884052235853,
|
| 2008 |
+
"grad_norm": 172.39999389648438,
|
| 2009 |
+
"learning_rate": 2.2642430318299938e-07,
|
| 2010 |
+
"loss": 3.97,
|
| 2011 |
+
"step": 7150
|
| 2012 |
+
},
|
| 2013 |
+
{
|
| 2014 |
+
"epoch": 0.5678670360110804,
|
| 2015 |
+
"grad_norm": 120.57051086425781,
|
| 2016 |
+
"learning_rate": 2.2634185914601167e-07,
|
| 2017 |
+
"loss": 3.9352,
|
| 2018 |
+
"step": 7175
|
| 2019 |
+
},
|
| 2020 |
+
{
|
| 2021 |
+
"epoch": 0.5698456667985754,
|
| 2022 |
+
"grad_norm": 143.2531280517578,
|
| 2023 |
+
"learning_rate": 2.26259415109024e-07,
|
| 2024 |
+
"loss": 3.9686,
|
| 2025 |
+
"step": 7200
|
| 2026 |
+
},
|
| 2027 |
+
{
|
| 2028 |
+
"epoch": 0.5718242975860705,
|
| 2029 |
+
"grad_norm": 123.57396697998047,
|
| 2030 |
+
"learning_rate": 2.261769710720363e-07,
|
| 2031 |
+
"loss": 4.0855,
|
| 2032 |
+
"step": 7225
|
| 2033 |
+
},
|
| 2034 |
+
{
|
| 2035 |
+
"epoch": 0.5738029283735655,
|
| 2036 |
+
"grad_norm": 115.12631225585938,
|
| 2037 |
+
"learning_rate": 2.260945270350486e-07,
|
| 2038 |
+
"loss": 3.9754,
|
| 2039 |
+
"step": 7250
|
| 2040 |
+
},
|
| 2041 |
+
{
|
| 2042 |
+
"epoch": 0.5757815591610606,
|
| 2043 |
+
"grad_norm": 114.95091247558594,
|
| 2044 |
+
"learning_rate": 2.260120829980609e-07,
|
| 2045 |
+
"loss": 3.8981,
|
| 2046 |
+
"step": 7275
|
| 2047 |
+
},
|
| 2048 |
+
{
|
| 2049 |
+
"epoch": 0.5777601899485556,
|
| 2050 |
+
"grad_norm": 105.46833038330078,
|
| 2051 |
+
"learning_rate": 2.2592963896107322e-07,
|
| 2052 |
+
"loss": 3.9452,
|
| 2053 |
+
"step": 7300
|
| 2054 |
+
},
|
| 2055 |
+
{
|
| 2056 |
+
"epoch": 0.5797388207360507,
|
| 2057 |
+
"grad_norm": 132.89012145996094,
|
| 2058 |
+
"learning_rate": 2.258471949240855e-07,
|
| 2059 |
+
"loss": 4.0808,
|
| 2060 |
+
"step": 7325
|
| 2061 |
+
},
|
| 2062 |
+
{
|
| 2063 |
+
"epoch": 0.5817174515235457,
|
| 2064 |
+
"grad_norm": 143.6460418701172,
|
| 2065 |
+
"learning_rate": 2.2576475088709782e-07,
|
| 2066 |
+
"loss": 4.0108,
|
| 2067 |
+
"step": 7350
|
| 2068 |
+
},
|
| 2069 |
+
{
|
| 2070 |
+
"epoch": 0.5836960823110408,
|
| 2071 |
+
"grad_norm": 130.83352661132812,
|
| 2072 |
+
"learning_rate": 2.2568230685011013e-07,
|
| 2073 |
+
"loss": 3.9701,
|
| 2074 |
+
"step": 7375
|
| 2075 |
+
},
|
| 2076 |
+
{
|
| 2077 |
+
"epoch": 0.5856747130985358,
|
| 2078 |
+
"grad_norm": 111.10405731201172,
|
| 2079 |
+
"learning_rate": 2.2559986281312244e-07,
|
| 2080 |
+
"loss": 4.3162,
|
| 2081 |
+
"step": 7400
|
| 2082 |
+
},
|
| 2083 |
+
{
|
| 2084 |
+
"epoch": 0.5876533438860309,
|
| 2085 |
+
"grad_norm": 163.31959533691406,
|
| 2086 |
+
"learning_rate": 2.2551741877613476e-07,
|
| 2087 |
+
"loss": 3.9096,
|
| 2088 |
+
"step": 7425
|
| 2089 |
+
},
|
| 2090 |
+
{
|
| 2091 |
+
"epoch": 0.5896319746735259,
|
| 2092 |
+
"grad_norm": 134.72927856445312,
|
| 2093 |
+
"learning_rate": 2.2543497473914704e-07,
|
| 2094 |
+
"loss": 3.8888,
|
| 2095 |
+
"step": 7450
|
| 2096 |
+
},
|
| 2097 |
+
{
|
| 2098 |
+
"epoch": 0.591610605461021,
|
| 2099 |
+
"grad_norm": 124.26619720458984,
|
| 2100 |
+
"learning_rate": 2.2535253070215938e-07,
|
| 2101 |
+
"loss": 4.0683,
|
| 2102 |
+
"step": 7475
|
| 2103 |
+
},
|
| 2104 |
+
{
|
| 2105 |
+
"epoch": 0.593589236248516,
|
| 2106 |
+
"grad_norm": 106.8174057006836,
|
| 2107 |
+
"learning_rate": 2.2527008666517166e-07,
|
| 2108 |
+
"loss": 4.0547,
|
| 2109 |
+
"step": 7500
|
| 2110 |
+
},
|
| 2111 |
+
{
|
| 2112 |
+
"epoch": 0.5955678670360111,
|
| 2113 |
+
"grad_norm": 108.11019897460938,
|
| 2114 |
+
"learning_rate": 2.2518764262818398e-07,
|
| 2115 |
+
"loss": 3.9728,
|
| 2116 |
+
"step": 7525
|
| 2117 |
+
},
|
| 2118 |
+
{
|
| 2119 |
+
"epoch": 0.5975464978235061,
|
| 2120 |
+
"grad_norm": 117.44151306152344,
|
| 2121 |
+
"learning_rate": 2.251051985911963e-07,
|
| 2122 |
+
"loss": 4.0569,
|
| 2123 |
+
"step": 7550
|
| 2124 |
+
},
|
| 2125 |
+
{
|
| 2126 |
+
"epoch": 0.5995251286110012,
|
| 2127 |
+
"grad_norm": 106.18008422851562,
|
| 2128 |
+
"learning_rate": 2.250227545542086e-07,
|
| 2129 |
+
"loss": 3.9042,
|
| 2130 |
+
"step": 7575
|
| 2131 |
+
},
|
| 2132 |
+
{
|
| 2133 |
+
"epoch": 0.6015037593984962,
|
| 2134 |
+
"grad_norm": 88.67406463623047,
|
| 2135 |
+
"learning_rate": 2.249403105172209e-07,
|
| 2136 |
+
"loss": 4.0719,
|
| 2137 |
+
"step": 7600
|
| 2138 |
+
},
|
| 2139 |
+
{
|
| 2140 |
+
"epoch": 0.6034823901859913,
|
| 2141 |
+
"grad_norm": 111.12770080566406,
|
| 2142 |
+
"learning_rate": 2.248578664802332e-07,
|
| 2143 |
+
"loss": 3.9749,
|
| 2144 |
+
"step": 7625
|
| 2145 |
+
},
|
| 2146 |
+
{
|
| 2147 |
+
"epoch": 0.6054610209734863,
|
| 2148 |
+
"grad_norm": 119.26530456542969,
|
| 2149 |
+
"learning_rate": 2.247754224432455e-07,
|
| 2150 |
+
"loss": 3.9832,
|
| 2151 |
+
"step": 7650
|
| 2152 |
+
},
|
| 2153 |
+
{
|
| 2154 |
+
"epoch": 0.6074396517609814,
|
| 2155 |
+
"grad_norm": 157.9289093017578,
|
| 2156 |
+
"learning_rate": 2.2469297840625782e-07,
|
| 2157 |
+
"loss": 3.9538,
|
| 2158 |
+
"step": 7675
|
| 2159 |
+
},
|
| 2160 |
+
{
|
| 2161 |
+
"epoch": 0.6094182825484764,
|
| 2162 |
+
"grad_norm": 122.70995330810547,
|
| 2163 |
+
"learning_rate": 2.2461053436927013e-07,
|
| 2164 |
+
"loss": 3.8497,
|
| 2165 |
+
"step": 7700
|
| 2166 |
+
},
|
| 2167 |
+
{
|
| 2168 |
+
"epoch": 0.6113969133359715,
|
| 2169 |
+
"grad_norm": 142.41835021972656,
|
| 2170 |
+
"learning_rate": 2.2452809033228242e-07,
|
| 2171 |
+
"loss": 3.9172,
|
| 2172 |
+
"step": 7725
|
| 2173 |
+
},
|
| 2174 |
+
{
|
| 2175 |
+
"epoch": 0.6133755441234665,
|
| 2176 |
+
"grad_norm": 128.31825256347656,
|
| 2177 |
+
"learning_rate": 2.2444564629529475e-07,
|
| 2178 |
+
"loss": 3.7326,
|
| 2179 |
+
"step": 7750
|
| 2180 |
+
},
|
| 2181 |
+
{
|
| 2182 |
+
"epoch": 0.6153541749109616,
|
| 2183 |
+
"grad_norm": 142.67408752441406,
|
| 2184 |
+
"learning_rate": 2.2436320225830704e-07,
|
| 2185 |
+
"loss": 3.8782,
|
| 2186 |
+
"step": 7775
|
| 2187 |
+
},
|
| 2188 |
+
{
|
| 2189 |
+
"epoch": 0.6173328056984567,
|
| 2190 |
+
"grad_norm": 145.0731658935547,
|
| 2191 |
+
"learning_rate": 2.2428075822131938e-07,
|
| 2192 |
+
"loss": 4.024,
|
| 2193 |
+
"step": 7800
|
| 2194 |
+
},
|
| 2195 |
+
{
|
| 2196 |
+
"epoch": 0.6193114364859518,
|
| 2197 |
+
"grad_norm": 187.09068298339844,
|
| 2198 |
+
"learning_rate": 2.2419831418433166e-07,
|
| 2199 |
+
"loss": 3.8939,
|
| 2200 |
+
"step": 7825
|
| 2201 |
+
},
|
| 2202 |
+
{
|
| 2203 |
+
"epoch": 0.6212900672734468,
|
| 2204 |
+
"grad_norm": 122.93965148925781,
|
| 2205 |
+
"learning_rate": 2.2411587014734397e-07,
|
| 2206 |
+
"loss": 4.0373,
|
| 2207 |
+
"step": 7850
|
| 2208 |
+
},
|
| 2209 |
+
{
|
| 2210 |
+
"epoch": 0.6232686980609419,
|
| 2211 |
+
"grad_norm": 152.1845245361328,
|
| 2212 |
+
"learning_rate": 2.2403342611035628e-07,
|
| 2213 |
+
"loss": 4.1168,
|
| 2214 |
+
"step": 7875
|
| 2215 |
+
},
|
| 2216 |
+
{
|
| 2217 |
+
"epoch": 0.6252473288484369,
|
| 2218 |
+
"grad_norm": 100.07666778564453,
|
| 2219 |
+
"learning_rate": 2.239509820733686e-07,
|
| 2220 |
+
"loss": 3.9718,
|
| 2221 |
+
"step": 7900
|
| 2222 |
+
},
|
| 2223 |
+
{
|
| 2224 |
+
"epoch": 0.627225959635932,
|
| 2225 |
+
"grad_norm": 130.85479736328125,
|
| 2226 |
+
"learning_rate": 2.2386853803638088e-07,
|
| 2227 |
+
"loss": 4.0301,
|
| 2228 |
+
"step": 7925
|
| 2229 |
+
},
|
| 2230 |
+
{
|
| 2231 |
+
"epoch": 0.629204590423427,
|
| 2232 |
+
"grad_norm": 123.073974609375,
|
| 2233 |
+
"learning_rate": 2.237860939993932e-07,
|
| 2234 |
+
"loss": 4.0104,
|
| 2235 |
+
"step": 7950
|
| 2236 |
+
},
|
| 2237 |
+
{
|
| 2238 |
+
"epoch": 0.6311832212109221,
|
| 2239 |
+
"grad_norm": 168.19808959960938,
|
| 2240 |
+
"learning_rate": 2.237036499624055e-07,
|
| 2241 |
+
"loss": 3.9421,
|
| 2242 |
+
"step": 7975
|
| 2243 |
+
},
|
| 2244 |
+
{
|
| 2245 |
+
"epoch": 0.6331618519984171,
|
| 2246 |
+
"grad_norm": 118.69593811035156,
|
| 2247 |
+
"learning_rate": 2.2362120592541782e-07,
|
| 2248 |
+
"loss": 3.8238,
|
| 2249 |
+
"step": 8000
|
| 2250 |
+
},
|
| 2251 |
+
{
|
| 2252 |
+
"epoch": 0.6351404827859122,
|
| 2253 |
+
"grad_norm": 192.9334259033203,
|
| 2254 |
+
"learning_rate": 2.2353876188843013e-07,
|
| 2255 |
+
"loss": 3.8227,
|
| 2256 |
+
"step": 8025
|
| 2257 |
+
},
|
| 2258 |
+
{
|
| 2259 |
+
"epoch": 0.6371191135734072,
|
| 2260 |
+
"grad_norm": 103.11824035644531,
|
| 2261 |
+
"learning_rate": 2.2345631785144241e-07,
|
| 2262 |
+
"loss": 3.9359,
|
| 2263 |
+
"step": 8050
|
| 2264 |
+
},
|
| 2265 |
+
{
|
| 2266 |
+
"epoch": 0.6390977443609023,
|
| 2267 |
+
"grad_norm": 129.3599090576172,
|
| 2268 |
+
"learning_rate": 2.2337387381445475e-07,
|
| 2269 |
+
"loss": 4.0562,
|
| 2270 |
+
"step": 8075
|
| 2271 |
+
},
|
| 2272 |
+
{
|
| 2273 |
+
"epoch": 0.6410763751483973,
|
| 2274 |
+
"grad_norm": 124.06795501708984,
|
| 2275 |
+
"learning_rate": 2.2329142977746704e-07,
|
| 2276 |
+
"loss": 4.1502,
|
| 2277 |
+
"step": 8100
|
| 2278 |
+
},
|
| 2279 |
+
{
|
| 2280 |
+
"epoch": 0.6430550059358924,
|
| 2281 |
+
"grad_norm": 113.18289184570312,
|
| 2282 |
+
"learning_rate": 2.2320898574047935e-07,
|
| 2283 |
+
"loss": 4.0059,
|
| 2284 |
+
"step": 8125
|
| 2285 |
+
},
|
| 2286 |
+
{
|
| 2287 |
+
"epoch": 0.6450336367233874,
|
| 2288 |
+
"grad_norm": 117.89970397949219,
|
| 2289 |
+
"learning_rate": 2.2312654170349166e-07,
|
| 2290 |
+
"loss": 4.0162,
|
| 2291 |
+
"step": 8150
|
| 2292 |
+
},
|
| 2293 |
+
{
|
| 2294 |
+
"epoch": 0.6470122675108825,
|
| 2295 |
+
"grad_norm": 109.6517105102539,
|
| 2296 |
+
"learning_rate": 2.2304409766650397e-07,
|
| 2297 |
+
"loss": 3.9979,
|
| 2298 |
+
"step": 8175
|
| 2299 |
+
},
|
| 2300 |
+
{
|
| 2301 |
+
"epoch": 0.6489908982983775,
|
| 2302 |
+
"grad_norm": 123.35499572753906,
|
| 2303 |
+
"learning_rate": 2.2296165362951628e-07,
|
| 2304 |
+
"loss": 3.9273,
|
| 2305 |
+
"step": 8200
|
| 2306 |
+
},
|
| 2307 |
+
{
|
| 2308 |
+
"epoch": 0.6509695290858726,
|
| 2309 |
+
"grad_norm": 141.97459411621094,
|
| 2310 |
+
"learning_rate": 2.228792095925286e-07,
|
| 2311 |
+
"loss": 4.0558,
|
| 2312 |
+
"step": 8225
|
| 2313 |
+
},
|
| 2314 |
+
{
|
| 2315 |
+
"epoch": 0.6529481598733676,
|
| 2316 |
+
"grad_norm": 159.06973266601562,
|
| 2317 |
+
"learning_rate": 2.2279676555554088e-07,
|
| 2318 |
+
"loss": 3.8374,
|
| 2319 |
+
"step": 8250
|
| 2320 |
+
},
|
| 2321 |
+
{
|
| 2322 |
+
"epoch": 0.6549267906608627,
|
| 2323 |
+
"grad_norm": 120.933837890625,
|
| 2324 |
+
"learning_rate": 2.227143215185532e-07,
|
| 2325 |
+
"loss": 3.8412,
|
| 2326 |
+
"step": 8275
|
| 2327 |
+
},
|
| 2328 |
+
{
|
| 2329 |
+
"epoch": 0.6569054214483577,
|
| 2330 |
+
"grad_norm": 106.266357421875,
|
| 2331 |
+
"learning_rate": 2.226318774815655e-07,
|
| 2332 |
+
"loss": 3.8757,
|
| 2333 |
+
"step": 8300
|
| 2334 |
+
},
|
| 2335 |
+
{
|
| 2336 |
+
"epoch": 0.6588840522358528,
|
| 2337 |
+
"grad_norm": 138.7765655517578,
|
| 2338 |
+
"learning_rate": 2.225494334445778e-07,
|
| 2339 |
+
"loss": 4.2284,
|
| 2340 |
+
"step": 8325
|
| 2341 |
+
},
|
| 2342 |
+
{
|
| 2343 |
+
"epoch": 0.6608626830233478,
|
| 2344 |
+
"grad_norm": 120.76045989990234,
|
| 2345 |
+
"learning_rate": 2.2246698940759013e-07,
|
| 2346 |
+
"loss": 3.9127,
|
| 2347 |
+
"step": 8350
|
| 2348 |
+
},
|
| 2349 |
+
{
|
| 2350 |
+
"epoch": 0.6628413138108429,
|
| 2351 |
+
"grad_norm": 117.31808471679688,
|
| 2352 |
+
"learning_rate": 2.223845453706024e-07,
|
| 2353 |
+
"loss": 3.7577,
|
| 2354 |
+
"step": 8375
|
| 2355 |
+
},
|
| 2356 |
+
{
|
| 2357 |
+
"epoch": 0.6648199445983379,
|
| 2358 |
+
"grad_norm": 108.21405029296875,
|
| 2359 |
+
"learning_rate": 2.2230210133361475e-07,
|
| 2360 |
+
"loss": 4.1095,
|
| 2361 |
+
"step": 8400
|
| 2362 |
+
},
|
| 2363 |
+
{
|
| 2364 |
+
"epoch": 0.666798575385833,
|
| 2365 |
+
"grad_norm": 126.65251159667969,
|
| 2366 |
+
"learning_rate": 2.2221965729662703e-07,
|
| 2367 |
+
"loss": 3.9047,
|
| 2368 |
+
"step": 8425
|
| 2369 |
+
},
|
| 2370 |
+
{
|
| 2371 |
+
"epoch": 0.668777206173328,
|
| 2372 |
+
"grad_norm": 135.06512451171875,
|
| 2373 |
+
"learning_rate": 2.2213721325963935e-07,
|
| 2374 |
+
"loss": 3.9267,
|
| 2375 |
+
"step": 8450
|
| 2376 |
+
},
|
| 2377 |
+
{
|
| 2378 |
+
"epoch": 0.6707558369608231,
|
| 2379 |
+
"grad_norm": 150.37025451660156,
|
| 2380 |
+
"learning_rate": 2.2205476922265166e-07,
|
| 2381 |
+
"loss": 3.9662,
|
| 2382 |
+
"step": 8475
|
| 2383 |
+
},
|
| 2384 |
+
{
|
| 2385 |
+
"epoch": 0.6727344677483181,
|
| 2386 |
+
"grad_norm": 138.01531982421875,
|
| 2387 |
+
"learning_rate": 2.2197232518566397e-07,
|
| 2388 |
+
"loss": 3.8107,
|
| 2389 |
+
"step": 8500
|
| 2390 |
+
},
|
| 2391 |
+
{
|
| 2392 |
+
"epoch": 0.6747130985358132,
|
| 2393 |
+
"grad_norm": 130.35153198242188,
|
| 2394 |
+
"learning_rate": 2.2188988114867625e-07,
|
| 2395 |
+
"loss": 3.8068,
|
| 2396 |
+
"step": 8525
|
| 2397 |
+
},
|
| 2398 |
+
{
|
| 2399 |
+
"epoch": 0.6766917293233082,
|
| 2400 |
+
"grad_norm": 161.9180145263672,
|
| 2401 |
+
"learning_rate": 2.218074371116886e-07,
|
| 2402 |
+
"loss": 4.0893,
|
| 2403 |
+
"step": 8550
|
| 2404 |
+
},
|
| 2405 |
+
{
|
| 2406 |
+
"epoch": 0.6786703601108033,
|
| 2407 |
+
"grad_norm": 165.08409118652344,
|
| 2408 |
+
"learning_rate": 2.2172499307470088e-07,
|
| 2409 |
+
"loss": 3.8419,
|
| 2410 |
+
"step": 8575
|
| 2411 |
+
},
|
| 2412 |
+
{
|
| 2413 |
+
"epoch": 0.6806489908982983,
|
| 2414 |
+
"grad_norm": 153.2915496826172,
|
| 2415 |
+
"learning_rate": 2.216425490377132e-07,
|
| 2416 |
+
"loss": 3.9302,
|
| 2417 |
+
"step": 8600
|
| 2418 |
+
},
|
| 2419 |
+
{
|
| 2420 |
+
"epoch": 0.6826276216857934,
|
| 2421 |
+
"grad_norm": 153.20138549804688,
|
| 2422 |
+
"learning_rate": 2.215601050007255e-07,
|
| 2423 |
+
"loss": 3.9947,
|
| 2424 |
+
"step": 8625
|
| 2425 |
+
},
|
| 2426 |
+
{
|
| 2427 |
+
"epoch": 0.6846062524732884,
|
| 2428 |
+
"grad_norm": 124.32341003417969,
|
| 2429 |
+
"learning_rate": 2.2147766096373779e-07,
|
| 2430 |
+
"loss": 3.8241,
|
| 2431 |
+
"step": 8650
|
| 2432 |
+
},
|
| 2433 |
+
{
|
| 2434 |
+
"epoch": 0.6865848832607835,
|
| 2435 |
+
"grad_norm": 209.813232421875,
|
| 2436 |
+
"learning_rate": 2.2139521692675012e-07,
|
| 2437 |
+
"loss": 3.917,
|
| 2438 |
+
"step": 8675
|
| 2439 |
+
},
|
| 2440 |
+
{
|
| 2441 |
+
"epoch": 0.6885635140482786,
|
| 2442 |
+
"grad_norm": 116.88125610351562,
|
| 2443 |
+
"learning_rate": 2.213127728897624e-07,
|
| 2444 |
+
"loss": 3.9474,
|
| 2445 |
+
"step": 8700
|
| 2446 |
+
},
|
| 2447 |
+
{
|
| 2448 |
+
"epoch": 0.6905421448357737,
|
| 2449 |
+
"grad_norm": 178.58721923828125,
|
| 2450 |
+
"learning_rate": 2.2123032885277472e-07,
|
| 2451 |
+
"loss": 3.9247,
|
| 2452 |
+
"step": 8725
|
| 2453 |
+
},
|
| 2454 |
+
{
|
| 2455 |
+
"epoch": 0.6925207756232687,
|
| 2456 |
+
"grad_norm": 123.67437744140625,
|
| 2457 |
+
"learning_rate": 2.2114788481578703e-07,
|
| 2458 |
+
"loss": 3.9548,
|
| 2459 |
+
"step": 8750
|
| 2460 |
+
},
|
| 2461 |
+
{
|
| 2462 |
+
"epoch": 0.6944994064107638,
|
| 2463 |
+
"grad_norm": 154.60626220703125,
|
| 2464 |
+
"learning_rate": 2.2106544077879934e-07,
|
| 2465 |
+
"loss": 3.8239,
|
| 2466 |
+
"step": 8775
|
| 2467 |
+
},
|
| 2468 |
+
{
|
| 2469 |
+
"epoch": 0.6964780371982588,
|
| 2470 |
+
"grad_norm": 141.65699768066406,
|
| 2471 |
+
"learning_rate": 2.2098299674181166e-07,
|
| 2472 |
+
"loss": 3.8458,
|
| 2473 |
+
"step": 8800
|
| 2474 |
+
},
|
| 2475 |
+
{
|
| 2476 |
+
"epoch": 0.6984566679857539,
|
| 2477 |
+
"grad_norm": 112.9280776977539,
|
| 2478 |
+
"learning_rate": 2.2090055270482397e-07,
|
| 2479 |
+
"loss": 3.9648,
|
| 2480 |
+
"step": 8825
|
| 2481 |
+
},
|
| 2482 |
+
{
|
| 2483 |
+
"epoch": 0.700435298773249,
|
| 2484 |
+
"grad_norm": 154.57643127441406,
|
| 2485 |
+
"learning_rate": 2.2081810866783625e-07,
|
| 2486 |
+
"loss": 4.0078,
|
| 2487 |
+
"step": 8850
|
| 2488 |
+
},
|
| 2489 |
+
{
|
| 2490 |
+
"epoch": 0.702413929560744,
|
| 2491 |
+
"grad_norm": 129.07418823242188,
|
| 2492 |
+
"learning_rate": 2.207356646308486e-07,
|
| 2493 |
+
"loss": 4.0276,
|
| 2494 |
+
"step": 8875
|
| 2495 |
+
},
|
| 2496 |
+
{
|
| 2497 |
+
"epoch": 0.704392560348239,
|
| 2498 |
+
"grad_norm": 113.59859466552734,
|
| 2499 |
+
"learning_rate": 2.2065322059386088e-07,
|
| 2500 |
+
"loss": 4.1596,
|
| 2501 |
+
"step": 8900
|
| 2502 |
+
},
|
| 2503 |
+
{
|
| 2504 |
+
"epoch": 0.7063711911357341,
|
| 2505 |
+
"grad_norm": 136.26283264160156,
|
| 2506 |
+
"learning_rate": 2.2057077655687316e-07,
|
| 2507 |
+
"loss": 3.948,
|
| 2508 |
+
"step": 8925
|
| 2509 |
+
},
|
| 2510 |
+
{
|
| 2511 |
+
"epoch": 0.7083498219232292,
|
| 2512 |
+
"grad_norm": 118.27870178222656,
|
| 2513 |
+
"learning_rate": 2.204883325198855e-07,
|
| 2514 |
+
"loss": 3.7611,
|
| 2515 |
+
"step": 8950
|
| 2516 |
+
},
|
| 2517 |
+
{
|
| 2518 |
+
"epoch": 0.7103284527107242,
|
| 2519 |
+
"grad_norm": 159.56643676757812,
|
| 2520 |
+
"learning_rate": 2.2040588848289778e-07,
|
| 2521 |
+
"loss": 4.0215,
|
| 2522 |
+
"step": 8975
|
| 2523 |
+
},
|
| 2524 |
+
{
|
| 2525 |
+
"epoch": 0.7123070834982193,
|
| 2526 |
+
"grad_norm": 125.84573364257812,
|
| 2527 |
+
"learning_rate": 2.2032344444591012e-07,
|
| 2528 |
+
"loss": 4.0046,
|
| 2529 |
+
"step": 9000
|
| 2530 |
+
},
|
| 2531 |
+
{
|
| 2532 |
+
"epoch": 0.7142857142857143,
|
| 2533 |
+
"grad_norm": 148.7548065185547,
|
| 2534 |
+
"learning_rate": 2.202410004089224e-07,
|
| 2535 |
+
"loss": 4.0033,
|
| 2536 |
+
"step": 9025
|
| 2537 |
+
},
|
| 2538 |
+
{
|
| 2539 |
+
"epoch": 0.7162643450732094,
|
| 2540 |
+
"grad_norm": 109.41517639160156,
|
| 2541 |
+
"learning_rate": 2.2015855637193472e-07,
|
| 2542 |
+
"loss": 3.9298,
|
| 2543 |
+
"step": 9050
|
| 2544 |
+
},
|
| 2545 |
+
{
|
| 2546 |
+
"epoch": 0.7182429758607044,
|
| 2547 |
+
"grad_norm": 112.52848815917969,
|
| 2548 |
+
"learning_rate": 2.2007611233494703e-07,
|
| 2549 |
+
"loss": 4.1003,
|
| 2550 |
+
"step": 9075
|
| 2551 |
+
},
|
| 2552 |
+
{
|
| 2553 |
+
"epoch": 0.7202216066481995,
|
| 2554 |
+
"grad_norm": 114.72808074951172,
|
| 2555 |
+
"learning_rate": 2.1999366829795934e-07,
|
| 2556 |
+
"loss": 4.1112,
|
| 2557 |
+
"step": 9100
|
| 2558 |
+
},
|
| 2559 |
+
{
|
| 2560 |
+
"epoch": 0.7222002374356945,
|
| 2561 |
+
"grad_norm": 144.11619567871094,
|
| 2562 |
+
"learning_rate": 2.1991122426097163e-07,
|
| 2563 |
+
"loss": 3.764,
|
| 2564 |
+
"step": 9125
|
| 2565 |
+
},
|
| 2566 |
+
{
|
| 2567 |
+
"epoch": 0.7241788682231896,
|
| 2568 |
+
"grad_norm": 118.64055633544922,
|
| 2569 |
+
"learning_rate": 2.1982878022398396e-07,
|
| 2570 |
+
"loss": 3.9262,
|
| 2571 |
+
"step": 9150
|
| 2572 |
+
},
|
| 2573 |
+
{
|
| 2574 |
+
"epoch": 0.7261574990106846,
|
| 2575 |
+
"grad_norm": 166.79525756835938,
|
| 2576 |
+
"learning_rate": 2.1974633618699625e-07,
|
| 2577 |
+
"loss": 4.0518,
|
| 2578 |
+
"step": 9175
|
| 2579 |
+
},
|
| 2580 |
+
{
|
| 2581 |
+
"epoch": 0.7281361297981797,
|
| 2582 |
+
"grad_norm": 128.2512969970703,
|
| 2583 |
+
"learning_rate": 2.1966389215000856e-07,
|
| 2584 |
+
"loss": 3.952,
|
| 2585 |
+
"step": 9200
|
| 2586 |
+
},
|
| 2587 |
+
{
|
| 2588 |
+
"epoch": 0.7301147605856747,
|
| 2589 |
+
"grad_norm": 143.56414794921875,
|
| 2590 |
+
"learning_rate": 2.1958144811302087e-07,
|
| 2591 |
+
"loss": 3.7034,
|
| 2592 |
+
"step": 9225
|
| 2593 |
+
},
|
| 2594 |
+
{
|
| 2595 |
+
"epoch": 0.7320933913731698,
|
| 2596 |
+
"grad_norm": 120.13394165039062,
|
| 2597 |
+
"learning_rate": 2.1949900407603316e-07,
|
| 2598 |
+
"loss": 3.7839,
|
| 2599 |
+
"step": 9250
|
| 2600 |
+
},
|
| 2601 |
+
{
|
| 2602 |
+
"epoch": 0.7340720221606648,
|
| 2603 |
+
"grad_norm": 148.74070739746094,
|
| 2604 |
+
"learning_rate": 2.194165600390455e-07,
|
| 2605 |
+
"loss": 3.8871,
|
| 2606 |
+
"step": 9275
|
| 2607 |
+
},
|
| 2608 |
+
{
|
| 2609 |
+
"epoch": 0.7360506529481599,
|
| 2610 |
+
"grad_norm": 148.17022705078125,
|
| 2611 |
+
"learning_rate": 2.1933411600205778e-07,
|
| 2612 |
+
"loss": 3.7486,
|
| 2613 |
+
"step": 9300
|
| 2614 |
+
},
|
| 2615 |
+
{
|
| 2616 |
+
"epoch": 0.7380292837356549,
|
| 2617 |
+
"grad_norm": 112.7260513305664,
|
| 2618 |
+
"learning_rate": 2.192516719650701e-07,
|
| 2619 |
+
"loss": 3.9436,
|
| 2620 |
+
"step": 9325
|
| 2621 |
+
},
|
| 2622 |
+
{
|
| 2623 |
+
"epoch": 0.74000791452315,
|
| 2624 |
+
"grad_norm": 131.4718780517578,
|
| 2625 |
+
"learning_rate": 2.191692279280824e-07,
|
| 2626 |
+
"loss": 4.1101,
|
| 2627 |
+
"step": 9350
|
| 2628 |
+
},
|
| 2629 |
+
{
|
| 2630 |
+
"epoch": 0.741986545310645,
|
| 2631 |
+
"grad_norm": 106.73101043701172,
|
| 2632 |
+
"learning_rate": 2.1908678389109472e-07,
|
| 2633 |
+
"loss": 3.9285,
|
| 2634 |
+
"step": 9375
|
| 2635 |
+
},
|
| 2636 |
+
{
|
| 2637 |
+
"epoch": 0.7439651760981401,
|
| 2638 |
+
"grad_norm": 120.58040618896484,
|
| 2639 |
+
"learning_rate": 2.1900433985410703e-07,
|
| 2640 |
+
"loss": 3.8471,
|
| 2641 |
+
"step": 9400
|
| 2642 |
+
},
|
| 2643 |
+
{
|
| 2644 |
+
"epoch": 0.7459438068856351,
|
| 2645 |
+
"grad_norm": 135.69512939453125,
|
| 2646 |
+
"learning_rate": 2.1892189581711934e-07,
|
| 2647 |
+
"loss": 3.7629,
|
| 2648 |
+
"step": 9425
|
| 2649 |
+
},
|
| 2650 |
+
{
|
| 2651 |
+
"epoch": 0.7479224376731302,
|
| 2652 |
+
"grad_norm": 125.78627014160156,
|
| 2653 |
+
"learning_rate": 2.1883945178013162e-07,
|
| 2654 |
+
"loss": 4.0646,
|
| 2655 |
+
"step": 9450
|
| 2656 |
+
},
|
| 2657 |
+
{
|
| 2658 |
+
"epoch": 0.7499010684606252,
|
| 2659 |
+
"grad_norm": 150.2305145263672,
|
| 2660 |
+
"learning_rate": 2.1875700774314396e-07,
|
| 2661 |
+
"loss": 3.9361,
|
| 2662 |
+
"step": 9475
|
| 2663 |
+
},
|
| 2664 |
+
{
|
| 2665 |
+
"epoch": 0.7518796992481203,
|
| 2666 |
+
"grad_norm": 95.4436264038086,
|
| 2667 |
+
"learning_rate": 2.1867456370615625e-07,
|
| 2668 |
+
"loss": 3.7688,
|
| 2669 |
+
"step": 9500
|
| 2670 |
+
},
|
| 2671 |
+
{
|
| 2672 |
+
"epoch": 0.7538583300356153,
|
| 2673 |
+
"grad_norm": 141.27809143066406,
|
| 2674 |
+
"learning_rate": 2.1859211966916853e-07,
|
| 2675 |
+
"loss": 4.0217,
|
| 2676 |
+
"step": 9525
|
| 2677 |
+
},
|
| 2678 |
+
{
|
| 2679 |
+
"epoch": 0.7558369608231104,
|
| 2680 |
+
"grad_norm": 133.8254852294922,
|
| 2681 |
+
"learning_rate": 2.1850967563218087e-07,
|
| 2682 |
+
"loss": 4.0683,
|
| 2683 |
+
"step": 9550
|
| 2684 |
+
},
|
| 2685 |
+
{
|
| 2686 |
+
"epoch": 0.7578155916106054,
|
| 2687 |
+
"grad_norm": 139.919189453125,
|
| 2688 |
+
"learning_rate": 2.1842723159519316e-07,
|
| 2689 |
+
"loss": 3.9958,
|
| 2690 |
+
"step": 9575
|
| 2691 |
+
},
|
| 2692 |
+
{
|
| 2693 |
+
"epoch": 0.7597942223981005,
|
| 2694 |
+
"grad_norm": 173.58946228027344,
|
| 2695 |
+
"learning_rate": 2.183447875582055e-07,
|
| 2696 |
+
"loss": 3.9474,
|
| 2697 |
+
"step": 9600
|
| 2698 |
+
},
|
| 2699 |
+
{
|
| 2700 |
+
"epoch": 0.7617728531855956,
|
| 2701 |
+
"grad_norm": 107.07398223876953,
|
| 2702 |
+
"learning_rate": 2.1826234352121778e-07,
|
| 2703 |
+
"loss": 3.8308,
|
| 2704 |
+
"step": 9625
|
| 2705 |
+
},
|
| 2706 |
+
{
|
| 2707 |
+
"epoch": 0.7637514839730907,
|
| 2708 |
+
"grad_norm": 124.00753784179688,
|
| 2709 |
+
"learning_rate": 2.181798994842301e-07,
|
| 2710 |
+
"loss": 3.8218,
|
| 2711 |
+
"step": 9650
|
| 2712 |
+
},
|
| 2713 |
+
{
|
| 2714 |
+
"epoch": 0.7657301147605857,
|
| 2715 |
+
"grad_norm": 138.23736572265625,
|
| 2716 |
+
"learning_rate": 2.180974554472424e-07,
|
| 2717 |
+
"loss": 3.7296,
|
| 2718 |
+
"step": 9675
|
| 2719 |
+
},
|
| 2720 |
+
{
|
| 2721 |
+
"epoch": 0.7677087455480808,
|
| 2722 |
+
"grad_norm": 128.9496612548828,
|
| 2723 |
+
"learning_rate": 2.1801501141025471e-07,
|
| 2724 |
+
"loss": 3.9163,
|
| 2725 |
+
"step": 9700
|
| 2726 |
+
},
|
| 2727 |
+
{
|
| 2728 |
+
"epoch": 0.7696873763355758,
|
| 2729 |
+
"grad_norm": 108.07875061035156,
|
| 2730 |
+
"learning_rate": 2.17932567373267e-07,
|
| 2731 |
+
"loss": 3.9408,
|
| 2732 |
+
"step": 9725
|
| 2733 |
+
},
|
| 2734 |
+
{
|
| 2735 |
+
"epoch": 0.7716660071230709,
|
| 2736 |
+
"grad_norm": 126.18501281738281,
|
| 2737 |
+
"learning_rate": 2.1785012333627934e-07,
|
| 2738 |
+
"loss": 4.1993,
|
| 2739 |
+
"step": 9750
|
| 2740 |
+
},
|
| 2741 |
+
{
|
| 2742 |
+
"epoch": 0.7736446379105659,
|
| 2743 |
+
"grad_norm": 144.8102264404297,
|
| 2744 |
+
"learning_rate": 2.1776767929929162e-07,
|
| 2745 |
+
"loss": 3.877,
|
| 2746 |
+
"step": 9775
|
| 2747 |
+
},
|
| 2748 |
+
{
|
| 2749 |
+
"epoch": 0.775623268698061,
|
| 2750 |
+
"grad_norm": 118.8504638671875,
|
| 2751 |
+
"learning_rate": 2.1768523526230396e-07,
|
| 2752 |
+
"loss": 3.9788,
|
| 2753 |
+
"step": 9800
|
| 2754 |
+
},
|
| 2755 |
+
{
|
| 2756 |
+
"epoch": 0.777601899485556,
|
| 2757 |
+
"grad_norm": 127.45133209228516,
|
| 2758 |
+
"learning_rate": 2.1760279122531625e-07,
|
| 2759 |
+
"loss": 3.8987,
|
| 2760 |
+
"step": 9825
|
| 2761 |
+
},
|
| 2762 |
+
{
|
| 2763 |
+
"epoch": 0.7795805302730511,
|
| 2764 |
+
"grad_norm": 134.95892333984375,
|
| 2765 |
+
"learning_rate": 2.1752034718832853e-07,
|
| 2766 |
+
"loss": 3.8251,
|
| 2767 |
+
"step": 9850
|
| 2768 |
+
},
|
| 2769 |
+
{
|
| 2770 |
+
"epoch": 0.7815591610605461,
|
| 2771 |
+
"grad_norm": 124.00614929199219,
|
| 2772 |
+
"learning_rate": 2.1743790315134087e-07,
|
| 2773 |
+
"loss": 3.6875,
|
| 2774 |
+
"step": 9875
|
| 2775 |
+
},
|
| 2776 |
+
{
|
| 2777 |
+
"epoch": 0.7835377918480412,
|
| 2778 |
+
"grad_norm": 126.81105041503906,
|
| 2779 |
+
"learning_rate": 2.1735545911435315e-07,
|
| 2780 |
+
"loss": 3.7447,
|
| 2781 |
+
"step": 9900
|
| 2782 |
+
},
|
| 2783 |
+
{
|
| 2784 |
+
"epoch": 0.7855164226355362,
|
| 2785 |
+
"grad_norm": 106.54443359375,
|
| 2786 |
+
"learning_rate": 2.172730150773655e-07,
|
| 2787 |
+
"loss": 3.9051,
|
| 2788 |
+
"step": 9925
|
| 2789 |
+
},
|
| 2790 |
+
{
|
| 2791 |
+
"epoch": 0.7874950534230313,
|
| 2792 |
+
"grad_norm": 156.5098876953125,
|
| 2793 |
+
"learning_rate": 2.1719057104037778e-07,
|
| 2794 |
+
"loss": 3.9587,
|
| 2795 |
+
"step": 9950
|
| 2796 |
+
},
|
| 2797 |
+
{
|
| 2798 |
+
"epoch": 0.7894736842105263,
|
| 2799 |
+
"grad_norm": 128.83648681640625,
|
| 2800 |
+
"learning_rate": 2.171081270033901e-07,
|
| 2801 |
+
"loss": 4.0755,
|
| 2802 |
+
"step": 9975
|
| 2803 |
+
},
|
| 2804 |
+
{
|
| 2805 |
+
"epoch": 0.7914523149980214,
|
| 2806 |
+
"grad_norm": 131.54664611816406,
|
| 2807 |
+
"learning_rate": 2.170256829664024e-07,
|
| 2808 |
+
"loss": 4.0072,
|
| 2809 |
+
"step": 10000
|
| 2810 |
+
},
|
| 2811 |
+
{
|
| 2812 |
+
"epoch": 0.7914523149980214,
|
| 2813 |
+
"eval_loss": 3.8681728839874268,
|
| 2814 |
+
"eval_runtime": 9.5698,
|
| 2815 |
+
"eval_samples_per_second": 264.165,
|
| 2816 |
+
"eval_steps_per_second": 33.021,
|
| 2817 |
+
"step": 10000
|
| 2818 |
+
}
|
| 2819 |
+
],
|
| 2820 |
+
"logging_steps": 25,
|
| 2821 |
+
"max_steps": 75810,
|
| 2822 |
+
"num_input_tokens_seen": 0,
|
| 2823 |
+
"num_train_epochs": 6,
|
| 2824 |
+
"save_steps": 10000,
|
| 2825 |
+
"stateful_callbacks": {
|
| 2826 |
+
"TrainerControl": {
|
| 2827 |
+
"args": {
|
| 2828 |
+
"should_epoch_stop": false,
|
| 2829 |
+
"should_evaluate": false,
|
| 2830 |
+
"should_log": false,
|
| 2831 |
+
"should_save": true,
|
| 2832 |
+
"should_training_stop": false
|
| 2833 |
+
},
|
| 2834 |
+
"attributes": {}
|
| 2835 |
+
}
|
| 2836 |
+
},
|
| 2837 |
+
"total_flos": 35767296000000.0,
|
| 2838 |
+
"train_batch_size": 2,
|
| 2839 |
+
"trial_name": null,
|
| 2840 |
+
"trial_params": null
|
| 2841 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5f0750642d2d827a5e19e0680b08bccba3bfafb1b441cc175ce68cad186375e5
|
| 3 |
+
size 5368
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|