Upload folder using huggingface_hub
Browse files- checkpoint-196/README.md +202 -0
- checkpoint-196/adapter_config.json +34 -0
- checkpoint-196/adapter_model.safetensors +3 -0
- checkpoint-196/optimizer.pt +3 -0
- checkpoint-196/rng_state_0.pth +3 -0
- checkpoint-196/rng_state_1.pth +3 -0
- checkpoint-196/rng_state_2.pth +3 -0
- checkpoint-196/rng_state_3.pth +3 -0
- checkpoint-196/scheduler.pt +3 -0
- checkpoint-196/special_tokens_map.json +36 -0
- checkpoint-196/tokenizer.model +3 -0
- checkpoint-196/tokenizer_config.json +85 -0
- checkpoint-196/trainer_state.json +1429 -0
- checkpoint-196/training_args.bin +3 -0
- checkpoint-98/README.md +202 -0
- checkpoint-98/adapter_config.json +34 -0
- checkpoint-98/adapter_model.safetensors +3 -0
- checkpoint-98/optimizer.pt +3 -0
- checkpoint-98/rng_state_0.pth +3 -0
- checkpoint-98/rng_state_1.pth +3 -0
- checkpoint-98/rng_state_2.pth +3 -0
- checkpoint-98/rng_state_3.pth +3 -0
- checkpoint-98/scheduler.pt +3 -0
- checkpoint-98/special_tokens_map.json +36 -0
- checkpoint-98/tokenizer.model +3 -0
- checkpoint-98/tokenizer_config.json +85 -0
- checkpoint-98/trainer_state.json +735 -0
- checkpoint-98/training_args.bin +3 -0
checkpoint-196/README.md
ADDED
|
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
base_model: NousResearch/CodeLlama-7b-hf
|
| 4 |
+
---
|
| 5 |
+
|
| 6 |
+
# Model Card for Model ID
|
| 7 |
+
|
| 8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 9 |
+
|
| 10 |
+
|
| 11 |
+
|
| 12 |
+
## Model Details
|
| 13 |
+
|
| 14 |
+
### Model Description
|
| 15 |
+
|
| 16 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
- **Developed by:** [More Information Needed]
|
| 21 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 22 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 23 |
+
- **Model type:** [More Information Needed]
|
| 24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 25 |
+
- **License:** [More Information Needed]
|
| 26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 27 |
+
|
| 28 |
+
### Model Sources [optional]
|
| 29 |
+
|
| 30 |
+
<!-- Provide the basic links for the model. -->
|
| 31 |
+
|
| 32 |
+
- **Repository:** [More Information Needed]
|
| 33 |
+
- **Paper [optional]:** [More Information Needed]
|
| 34 |
+
- **Demo [optional]:** [More Information Needed]
|
| 35 |
+
|
| 36 |
+
## Uses
|
| 37 |
+
|
| 38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 39 |
+
|
| 40 |
+
### Direct Use
|
| 41 |
+
|
| 42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 43 |
+
|
| 44 |
+
[More Information Needed]
|
| 45 |
+
|
| 46 |
+
### Downstream Use [optional]
|
| 47 |
+
|
| 48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 49 |
+
|
| 50 |
+
[More Information Needed]
|
| 51 |
+
|
| 52 |
+
### Out-of-Scope Use
|
| 53 |
+
|
| 54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 55 |
+
|
| 56 |
+
[More Information Needed]
|
| 57 |
+
|
| 58 |
+
## Bias, Risks, and Limitations
|
| 59 |
+
|
| 60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 61 |
+
|
| 62 |
+
[More Information Needed]
|
| 63 |
+
|
| 64 |
+
### Recommendations
|
| 65 |
+
|
| 66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 67 |
+
|
| 68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 69 |
+
|
| 70 |
+
## How to Get Started with the Model
|
| 71 |
+
|
| 72 |
+
Use the code below to get started with the model.
|
| 73 |
+
|
| 74 |
+
[More Information Needed]
|
| 75 |
+
|
| 76 |
+
## Training Details
|
| 77 |
+
|
| 78 |
+
### Training Data
|
| 79 |
+
|
| 80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 81 |
+
|
| 82 |
+
[More Information Needed]
|
| 83 |
+
|
| 84 |
+
### Training Procedure
|
| 85 |
+
|
| 86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 87 |
+
|
| 88 |
+
#### Preprocessing [optional]
|
| 89 |
+
|
| 90 |
+
[More Information Needed]
|
| 91 |
+
|
| 92 |
+
|
| 93 |
+
#### Training Hyperparameters
|
| 94 |
+
|
| 95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 96 |
+
|
| 97 |
+
#### Speeds, Sizes, Times [optional]
|
| 98 |
+
|
| 99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 100 |
+
|
| 101 |
+
[More Information Needed]
|
| 102 |
+
|
| 103 |
+
## Evaluation
|
| 104 |
+
|
| 105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 106 |
+
|
| 107 |
+
### Testing Data, Factors & Metrics
|
| 108 |
+
|
| 109 |
+
#### Testing Data
|
| 110 |
+
|
| 111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 112 |
+
|
| 113 |
+
[More Information Needed]
|
| 114 |
+
|
| 115 |
+
#### Factors
|
| 116 |
+
|
| 117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 118 |
+
|
| 119 |
+
[More Information Needed]
|
| 120 |
+
|
| 121 |
+
#### Metrics
|
| 122 |
+
|
| 123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 124 |
+
|
| 125 |
+
[More Information Needed]
|
| 126 |
+
|
| 127 |
+
### Results
|
| 128 |
+
|
| 129 |
+
[More Information Needed]
|
| 130 |
+
|
| 131 |
+
#### Summary
|
| 132 |
+
|
| 133 |
+
|
| 134 |
+
|
| 135 |
+
## Model Examination [optional]
|
| 136 |
+
|
| 137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 138 |
+
|
| 139 |
+
[More Information Needed]
|
| 140 |
+
|
| 141 |
+
## Environmental Impact
|
| 142 |
+
|
| 143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 144 |
+
|
| 145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
| 146 |
+
|
| 147 |
+
- **Hardware Type:** [More Information Needed]
|
| 148 |
+
- **Hours used:** [More Information Needed]
|
| 149 |
+
- **Cloud Provider:** [More Information Needed]
|
| 150 |
+
- **Compute Region:** [More Information Needed]
|
| 151 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 152 |
+
|
| 153 |
+
## Technical Specifications [optional]
|
| 154 |
+
|
| 155 |
+
### Model Architecture and Objective
|
| 156 |
+
|
| 157 |
+
[More Information Needed]
|
| 158 |
+
|
| 159 |
+
### Compute Infrastructure
|
| 160 |
+
|
| 161 |
+
[More Information Needed]
|
| 162 |
+
|
| 163 |
+
#### Hardware
|
| 164 |
+
|
| 165 |
+
[More Information Needed]
|
| 166 |
+
|
| 167 |
+
#### Software
|
| 168 |
+
|
| 169 |
+
[More Information Needed]
|
| 170 |
+
|
| 171 |
+
## Citation [optional]
|
| 172 |
+
|
| 173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 174 |
+
|
| 175 |
+
**BibTeX:**
|
| 176 |
+
|
| 177 |
+
[More Information Needed]
|
| 178 |
+
|
| 179 |
+
**APA:**
|
| 180 |
+
|
| 181 |
+
[More Information Needed]
|
| 182 |
+
|
| 183 |
+
## Glossary [optional]
|
| 184 |
+
|
| 185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 186 |
+
|
| 187 |
+
[More Information Needed]
|
| 188 |
+
|
| 189 |
+
## More Information [optional]
|
| 190 |
+
|
| 191 |
+
[More Information Needed]
|
| 192 |
+
|
| 193 |
+
## Model Card Authors [optional]
|
| 194 |
+
|
| 195 |
+
[More Information Needed]
|
| 196 |
+
|
| 197 |
+
## Model Card Contact
|
| 198 |
+
|
| 199 |
+
[More Information Needed]
|
| 200 |
+
### Framework versions
|
| 201 |
+
|
| 202 |
+
- PEFT 0.11.1
|
checkpoint-196/adapter_config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "NousResearch/CodeLlama-7b-hf",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": null,
|
| 7 |
+
"inference_mode": true,
|
| 8 |
+
"init_lora_weights": true,
|
| 9 |
+
"layer_replication": null,
|
| 10 |
+
"layers_pattern": null,
|
| 11 |
+
"layers_to_transform": null,
|
| 12 |
+
"loftq_config": {},
|
| 13 |
+
"lora_alpha": 16,
|
| 14 |
+
"lora_dropout": 0.05,
|
| 15 |
+
"megatron_config": null,
|
| 16 |
+
"megatron_core": "megatron.core",
|
| 17 |
+
"modules_to_save": null,
|
| 18 |
+
"peft_type": "LORA",
|
| 19 |
+
"r": 32,
|
| 20 |
+
"rank_pattern": {},
|
| 21 |
+
"revision": null,
|
| 22 |
+
"target_modules": [
|
| 23 |
+
"gate_proj",
|
| 24 |
+
"v_proj",
|
| 25 |
+
"o_proj",
|
| 26 |
+
"k_proj",
|
| 27 |
+
"up_proj",
|
| 28 |
+
"down_proj",
|
| 29 |
+
"q_proj"
|
| 30 |
+
],
|
| 31 |
+
"task_type": "CAUSAL_LM",
|
| 32 |
+
"use_dora": false,
|
| 33 |
+
"use_rslora": false
|
| 34 |
+
}
|
checkpoint-196/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d864f7c13ddab5d0f3b7278bb1a3d64f11cf60e64194d5ce005452c9d18ed413
|
| 3 |
+
size 319876032
|
checkpoint-196/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e3ce267bd5a7479a2ce0e0b6bb51d5eef84024cb0d2429379c06448b29e21a39
|
| 3 |
+
size 160736084
|
checkpoint-196/rng_state_0.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d107a6144e78522b1d6f429faba280da16f2b609387ac758a998c16f053d803e
|
| 3 |
+
size 14960
|
checkpoint-196/rng_state_1.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:849b02b883c17f420e0f4f92078172b190f770f39a47971c5631de03bb26519f
|
| 3 |
+
size 14960
|
checkpoint-196/rng_state_2.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f656a2486ff1cf688db4ff13ce8dc019fe41d0342657d208668bb9a6cb5c0cd7
|
| 3 |
+
size 14960
|
checkpoint-196/rng_state_3.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4668e970ff90d1e8dea5510be594298fe9c19d655c1578f0ffce328a9f2c1463
|
| 3 |
+
size 14960
|
checkpoint-196/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e22ca0a50bab80d00c8b8910bffb983a348f8762b7cf025e6f8e64a05a938289
|
| 3 |
+
size 1064
|
checkpoint-196/special_tokens_map.json
ADDED
|
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"▁<PRE>",
|
| 4 |
+
"▁<MID>",
|
| 5 |
+
"▁<SUF>",
|
| 6 |
+
"▁<EOT>"
|
| 7 |
+
],
|
| 8 |
+
"bos_token": {
|
| 9 |
+
"content": "<s>",
|
| 10 |
+
"lstrip": false,
|
| 11 |
+
"normalized": false,
|
| 12 |
+
"rstrip": false,
|
| 13 |
+
"single_word": false
|
| 14 |
+
},
|
| 15 |
+
"eos_token": {
|
| 16 |
+
"content": "</s>",
|
| 17 |
+
"lstrip": false,
|
| 18 |
+
"normalized": false,
|
| 19 |
+
"rstrip": false,
|
| 20 |
+
"single_word": false
|
| 21 |
+
},
|
| 22 |
+
"pad_token": {
|
| 23 |
+
"content": "</s>",
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"normalized": false,
|
| 26 |
+
"rstrip": false,
|
| 27 |
+
"single_word": false
|
| 28 |
+
},
|
| 29 |
+
"unk_token": {
|
| 30 |
+
"content": "<unk>",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": false,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false
|
| 35 |
+
}
|
| 36 |
+
}
|
checkpoint-196/tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:45ccb9c8b6b561889acea59191d66986d314e7cbd6a78abc6e49b139ca91c1e6
|
| 3 |
+
size 500058
|
checkpoint-196/tokenizer_config.json
ADDED
|
@@ -0,0 +1,85 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"0": {
|
| 6 |
+
"content": "<unk>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"1": {
|
| 14 |
+
"content": "<s>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"2": {
|
| 22 |
+
"content": "</s>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
},
|
| 29 |
+
"32007": {
|
| 30 |
+
"content": "▁<PRE>",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": false,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false,
|
| 35 |
+
"special": true
|
| 36 |
+
},
|
| 37 |
+
"32008": {
|
| 38 |
+
"content": "▁<SUF>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false,
|
| 43 |
+
"special": true
|
| 44 |
+
},
|
| 45 |
+
"32009": {
|
| 46 |
+
"content": "▁<MID>",
|
| 47 |
+
"lstrip": false,
|
| 48 |
+
"normalized": false,
|
| 49 |
+
"rstrip": false,
|
| 50 |
+
"single_word": false,
|
| 51 |
+
"special": true
|
| 52 |
+
},
|
| 53 |
+
"32010": {
|
| 54 |
+
"content": "▁<EOT>",
|
| 55 |
+
"lstrip": false,
|
| 56 |
+
"normalized": false,
|
| 57 |
+
"rstrip": false,
|
| 58 |
+
"single_word": false,
|
| 59 |
+
"special": true
|
| 60 |
+
}
|
| 61 |
+
},
|
| 62 |
+
"additional_special_tokens": [
|
| 63 |
+
"▁<PRE>",
|
| 64 |
+
"▁<MID>",
|
| 65 |
+
"▁<SUF>",
|
| 66 |
+
"▁<EOT>"
|
| 67 |
+
],
|
| 68 |
+
"bos_token": "<s>",
|
| 69 |
+
"clean_up_tokenization_spaces": false,
|
| 70 |
+
"eos_token": "</s>",
|
| 71 |
+
"eot_token": "▁<EOT>",
|
| 72 |
+
"fill_token": "<FILL_ME>",
|
| 73 |
+
"legacy": null,
|
| 74 |
+
"middle_token": "▁<MID>",
|
| 75 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 76 |
+
"pad_token": "</s>",
|
| 77 |
+
"prefix_token": "▁<PRE>",
|
| 78 |
+
"sp_model_kwargs": {},
|
| 79 |
+
"suffix_first": false,
|
| 80 |
+
"suffix_token": "▁<SUF>",
|
| 81 |
+
"tokenizer_class": "CodeLlamaTokenizer",
|
| 82 |
+
"unk_token": "<unk>",
|
| 83 |
+
"use_default_system_prompt": false,
|
| 84 |
+
"use_fast": true
|
| 85 |
+
}
|
checkpoint-196/trainer_state.json
ADDED
|
@@ -0,0 +1,1429 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.9644670050761421,
|
| 5 |
+
"eval_steps": 98,
|
| 6 |
+
"global_step": 196,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.01015228426395939,
|
| 13 |
+
"grad_norm": 0.516016960144043,
|
| 14 |
+
"learning_rate": 2e-05,
|
| 15 |
+
"loss": 4.3699,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.01015228426395939,
|
| 20 |
+
"eval_loss": 4.561354637145996,
|
| 21 |
+
"eval_runtime": 58.1653,
|
| 22 |
+
"eval_samples_per_second": 10.144,
|
| 23 |
+
"eval_steps_per_second": 1.272,
|
| 24 |
+
"step": 1
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.02030456852791878,
|
| 28 |
+
"grad_norm": 0.5144633650779724,
|
| 29 |
+
"learning_rate": 4e-05,
|
| 30 |
+
"loss": 4.5708,
|
| 31 |
+
"step": 2
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.030456852791878174,
|
| 35 |
+
"grad_norm": 0.5246109962463379,
|
| 36 |
+
"learning_rate": 6e-05,
|
| 37 |
+
"loss": 4.5871,
|
| 38 |
+
"step": 3
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.04060913705583756,
|
| 42 |
+
"grad_norm": 0.5753014087677002,
|
| 43 |
+
"learning_rate": 8e-05,
|
| 44 |
+
"loss": 4.3818,
|
| 45 |
+
"step": 4
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.050761421319796954,
|
| 49 |
+
"grad_norm": 0.6615588665008545,
|
| 50 |
+
"learning_rate": 0.0001,
|
| 51 |
+
"loss": 4.448,
|
| 52 |
+
"step": 5
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.06091370558375635,
|
| 56 |
+
"grad_norm": 0.751004159450531,
|
| 57 |
+
"learning_rate": 0.00012,
|
| 58 |
+
"loss": 4.4964,
|
| 59 |
+
"step": 6
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.07106598984771574,
|
| 63 |
+
"grad_norm": 0.886650562286377,
|
| 64 |
+
"learning_rate": 0.00014,
|
| 65 |
+
"loss": 4.4011,
|
| 66 |
+
"step": 7
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.08121827411167512,
|
| 70 |
+
"grad_norm": 1.1175657510757446,
|
| 71 |
+
"learning_rate": 0.00016,
|
| 72 |
+
"loss": 3.9849,
|
| 73 |
+
"step": 8
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.09137055837563451,
|
| 77 |
+
"grad_norm": 0.9861809015274048,
|
| 78 |
+
"learning_rate": 0.00018,
|
| 79 |
+
"loss": 3.8218,
|
| 80 |
+
"step": 9
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.10152284263959391,
|
| 84 |
+
"grad_norm": 1.1107577085494995,
|
| 85 |
+
"learning_rate": 0.0002,
|
| 86 |
+
"loss": 3.6451,
|
| 87 |
+
"step": 10
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.1116751269035533,
|
| 91 |
+
"grad_norm": 0.9435870051383972,
|
| 92 |
+
"learning_rate": 0.000199985736255971,
|
| 93 |
+
"loss": 3.5619,
|
| 94 |
+
"step": 11
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.1218274111675127,
|
| 98 |
+
"grad_norm": 0.9529088139533997,
|
| 99 |
+
"learning_rate": 0.0001999429490929718,
|
| 100 |
+
"loss": 3.4561,
|
| 101 |
+
"step": 12
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.1319796954314721,
|
| 105 |
+
"grad_norm": 1.3805211782455444,
|
| 106 |
+
"learning_rate": 0.00019987165071710527,
|
| 107 |
+
"loss": 3.2067,
|
| 108 |
+
"step": 13
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.14213197969543148,
|
| 112 |
+
"grad_norm": 1.319393515586853,
|
| 113 |
+
"learning_rate": 0.00019977186146800707,
|
| 114 |
+
"loss": 3.0656,
|
| 115 |
+
"step": 14
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.15228426395939088,
|
| 119 |
+
"grad_norm": 1.061409592628479,
|
| 120 |
+
"learning_rate": 0.0001996436098130433,
|
| 121 |
+
"loss": 2.7711,
|
| 122 |
+
"step": 15
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.16243654822335024,
|
| 126 |
+
"grad_norm": 1.036845326423645,
|
| 127 |
+
"learning_rate": 0.00019948693233918952,
|
| 128 |
+
"loss": 2.6576,
|
| 129 |
+
"step": 16
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.17258883248730963,
|
| 133 |
+
"grad_norm": 1.0924557447433472,
|
| 134 |
+
"learning_rate": 0.00019930187374259337,
|
| 135 |
+
"loss": 2.4101,
|
| 136 |
+
"step": 17
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.18274111675126903,
|
| 140 |
+
"grad_norm": 1.0557212829589844,
|
| 141 |
+
"learning_rate": 0.00019908848681582391,
|
| 142 |
+
"loss": 2.2991,
|
| 143 |
+
"step": 18
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.19289340101522842,
|
| 147 |
+
"grad_norm": 1.1735273599624634,
|
| 148 |
+
"learning_rate": 0.00019884683243281116,
|
| 149 |
+
"loss": 2.3991,
|
| 150 |
+
"step": 19
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.20304568527918782,
|
| 154 |
+
"grad_norm": 0.8104203343391418,
|
| 155 |
+
"learning_rate": 0.00019857697953148037,
|
| 156 |
+
"loss": 2.107,
|
| 157 |
+
"step": 20
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.2131979695431472,
|
| 161 |
+
"grad_norm": 0.7275764346122742,
|
| 162 |
+
"learning_rate": 0.00019827900509408581,
|
| 163 |
+
"loss": 2.0596,
|
| 164 |
+
"step": 21
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.2233502538071066,
|
| 168 |
+
"grad_norm": 1.0672590732574463,
|
| 169 |
+
"learning_rate": 0.00019795299412524945,
|
| 170 |
+
"loss": 1.9543,
|
| 171 |
+
"step": 22
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.233502538071066,
|
| 175 |
+
"grad_norm": 0.5848283767700195,
|
| 176 |
+
"learning_rate": 0.00019759903962771156,
|
| 177 |
+
"loss": 1.8091,
|
| 178 |
+
"step": 23
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.2436548223350254,
|
| 182 |
+
"grad_norm": 0.9580035209655762,
|
| 183 |
+
"learning_rate": 0.00019721724257579907,
|
| 184 |
+
"loss": 1.7178,
|
| 185 |
+
"step": 24
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.25380710659898476,
|
| 189 |
+
"grad_norm": 0.5362741351127625,
|
| 190 |
+
"learning_rate": 0.00019680771188662044,
|
| 191 |
+
"loss": 1.6739,
|
| 192 |
+
"step": 25
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.2639593908629442,
|
| 196 |
+
"grad_norm": 0.5108774304389954,
|
| 197 |
+
"learning_rate": 0.0001963705643889941,
|
| 198 |
+
"loss": 1.7575,
|
| 199 |
+
"step": 26
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.27411167512690354,
|
| 203 |
+
"grad_norm": 0.5604164004325867,
|
| 204 |
+
"learning_rate": 0.00019590592479012023,
|
| 205 |
+
"loss": 1.6815,
|
| 206 |
+
"step": 27
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.28426395939086296,
|
| 210 |
+
"grad_norm": 0.7223322987556458,
|
| 211 |
+
"learning_rate": 0.00019541392564000488,
|
| 212 |
+
"loss": 1.6213,
|
| 213 |
+
"step": 28
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.29441624365482233,
|
| 217 |
+
"grad_norm": 0.5081471800804138,
|
| 218 |
+
"learning_rate": 0.00019489470729364692,
|
| 219 |
+
"loss": 1.5935,
|
| 220 |
+
"step": 29
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.30456852791878175,
|
| 224 |
+
"grad_norm": 0.5000993013381958,
|
| 225 |
+
"learning_rate": 0.00019434841787099803,
|
| 226 |
+
"loss": 1.6237,
|
| 227 |
+
"step": 30
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.3147208121827411,
|
| 231 |
+
"grad_norm": 0.45925211906433105,
|
| 232 |
+
"learning_rate": 0.00019377521321470805,
|
| 233 |
+
"loss": 1.6201,
|
| 234 |
+
"step": 31
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.3248730964467005,
|
| 238 |
+
"grad_norm": 0.38572826981544495,
|
| 239 |
+
"learning_rate": 0.00019317525684566685,
|
| 240 |
+
"loss": 1.4805,
|
| 241 |
+
"step": 32
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.3350253807106599,
|
| 245 |
+
"grad_norm": 0.28524091839790344,
|
| 246 |
+
"learning_rate": 0.00019254871991635598,
|
| 247 |
+
"loss": 1.5985,
|
| 248 |
+
"step": 33
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.34517766497461927,
|
| 252 |
+
"grad_norm": 0.3277890980243683,
|
| 253 |
+
"learning_rate": 0.00019189578116202307,
|
| 254 |
+
"loss": 1.4994,
|
| 255 |
+
"step": 34
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.3553299492385787,
|
| 259 |
+
"grad_norm": 0.3320370018482208,
|
| 260 |
+
"learning_rate": 0.00019121662684969335,
|
| 261 |
+
"loss": 1.5039,
|
| 262 |
+
"step": 35
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.36548223350253806,
|
| 266 |
+
"grad_norm": 0.2798719108104706,
|
| 267 |
+
"learning_rate": 0.00019051145072503215,
|
| 268 |
+
"loss": 1.4997,
|
| 269 |
+
"step": 36
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.3756345177664975,
|
| 273 |
+
"grad_norm": 1.7497050762176514,
|
| 274 |
+
"learning_rate": 0.00018978045395707418,
|
| 275 |
+
"loss": 1.5465,
|
| 276 |
+
"step": 37
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.38578680203045684,
|
| 280 |
+
"grad_norm": 0.27379170060157776,
|
| 281 |
+
"learning_rate": 0.00018902384508083517,
|
| 282 |
+
"loss": 1.4846,
|
| 283 |
+
"step": 38
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.39593908629441626,
|
| 287 |
+
"grad_norm": 0.36681699752807617,
|
| 288 |
+
"learning_rate": 0.00018824183993782192,
|
| 289 |
+
"loss": 1.4154,
|
| 290 |
+
"step": 39
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.40609137055837563,
|
| 294 |
+
"grad_norm": 0.45136329531669617,
|
| 295 |
+
"learning_rate": 0.00018743466161445823,
|
| 296 |
+
"loss": 1.3928,
|
| 297 |
+
"step": 40
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.41624365482233505,
|
| 301 |
+
"grad_norm": 0.27879664301872253,
|
| 302 |
+
"learning_rate": 0.00018660254037844388,
|
| 303 |
+
"loss": 1.5119,
|
| 304 |
+
"step": 41
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.4263959390862944,
|
| 308 |
+
"grad_norm": 0.29230332374572754,
|
| 309 |
+
"learning_rate": 0.0001857457136130651,
|
| 310 |
+
"loss": 1.5095,
|
| 311 |
+
"step": 42
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.4365482233502538,
|
| 315 |
+
"grad_norm": 0.2731008231639862,
|
| 316 |
+
"learning_rate": 0.00018486442574947511,
|
| 317 |
+
"loss": 1.4672,
|
| 318 |
+
"step": 43
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.4467005076142132,
|
| 322 |
+
"grad_norm": 0.23685932159423828,
|
| 323 |
+
"learning_rate": 0.00018395892819696389,
|
| 324 |
+
"loss": 1.4173,
|
| 325 |
+
"step": 44
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.45685279187817257,
|
| 329 |
+
"grad_norm": 0.2703058421611786,
|
| 330 |
+
"learning_rate": 0.00018302947927123766,
|
| 331 |
+
"loss": 1.4088,
|
| 332 |
+
"step": 45
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.467005076142132,
|
| 336 |
+
"grad_norm": 1.65743887424469,
|
| 337 |
+
"learning_rate": 0.00018207634412072764,
|
| 338 |
+
"loss": 1.4672,
|
| 339 |
+
"step": 46
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.47715736040609136,
|
| 343 |
+
"grad_norm": 0.21287347376346588,
|
| 344 |
+
"learning_rate": 0.00018109979465095013,
|
| 345 |
+
"loss": 1.3975,
|
| 346 |
+
"step": 47
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.4873096446700508,
|
| 350 |
+
"grad_norm": 0.3460160791873932,
|
| 351 |
+
"learning_rate": 0.00018010010944693848,
|
| 352 |
+
"loss": 1.4501,
|
| 353 |
+
"step": 48
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.49746192893401014,
|
| 357 |
+
"grad_norm": 0.4228818714618683,
|
| 358 |
+
"learning_rate": 0.00017907757369376985,
|
| 359 |
+
"loss": 1.4632,
|
| 360 |
+
"step": 49
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.5076142131979695,
|
| 364 |
+
"grad_norm": 0.46471402049064636,
|
| 365 |
+
"learning_rate": 0.0001780324790952092,
|
| 366 |
+
"loss": 1.3696,
|
| 367 |
+
"step": 50
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.5177664974619289,
|
| 371 |
+
"grad_norm": 0.35602033138275146,
|
| 372 |
+
"learning_rate": 0.00017696512379049325,
|
| 373 |
+
"loss": 1.4096,
|
| 374 |
+
"step": 51
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.5279187817258884,
|
| 378 |
+
"grad_norm": 0.2879682779312134,
|
| 379 |
+
"learning_rate": 0.0001758758122692791,
|
| 380 |
+
"loss": 1.337,
|
| 381 |
+
"step": 52
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.5380710659898477,
|
| 385 |
+
"grad_norm": 0.1947374939918518,
|
| 386 |
+
"learning_rate": 0.00017476485528478093,
|
| 387 |
+
"loss": 1.3815,
|
| 388 |
+
"step": 53
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.5482233502538071,
|
| 392 |
+
"grad_norm": 0.22819018363952637,
|
| 393 |
+
"learning_rate": 0.00017363256976511972,
|
| 394 |
+
"loss": 1.4021,
|
| 395 |
+
"step": 54
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.5583756345177665,
|
| 399 |
+
"grad_norm": 0.19164641201496124,
|
| 400 |
+
"learning_rate": 0.000172479278722912,
|
| 401 |
+
"loss": 1.3899,
|
| 402 |
+
"step": 55
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.5685279187817259,
|
| 406 |
+
"grad_norm": 0.5477288961410522,
|
| 407 |
+
"learning_rate": 0.00017130531116312203,
|
| 408 |
+
"loss": 1.4089,
|
| 409 |
+
"step": 56
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.5786802030456852,
|
| 413 |
+
"grad_norm": 0.6282036900520325,
|
| 414 |
+
"learning_rate": 0.0001701110019892053,
|
| 415 |
+
"loss": 1.3983,
|
| 416 |
+
"step": 57
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.5888324873096447,
|
| 420 |
+
"grad_norm": 0.5962779521942139,
|
| 421 |
+
"learning_rate": 0.00016889669190756868,
|
| 422 |
+
"loss": 1.3126,
|
| 423 |
+
"step": 58
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.5989847715736041,
|
| 427 |
+
"grad_norm": 0.39695534110069275,
|
| 428 |
+
"learning_rate": 0.00016766272733037576,
|
| 429 |
+
"loss": 1.3693,
|
| 430 |
+
"step": 59
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.6091370558375635,
|
| 434 |
+
"grad_norm": 0.2737330198287964,
|
| 435 |
+
"learning_rate": 0.00016640946027672392,
|
| 436 |
+
"loss": 1.4286,
|
| 437 |
+
"step": 60
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 0.6192893401015228,
|
| 441 |
+
"grad_norm": 0.34324145317077637,
|
| 442 |
+
"learning_rate": 0.00016513724827222227,
|
| 443 |
+
"loss": 1.3363,
|
| 444 |
+
"step": 61
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.6294416243654822,
|
| 448 |
+
"grad_norm": 0.4945085942745209,
|
| 449 |
+
"learning_rate": 0.00016384645424699835,
|
| 450 |
+
"loss": 1.4388,
|
| 451 |
+
"step": 62
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 0.6395939086294417,
|
| 455 |
+
"grad_norm": 0.3939533829689026,
|
| 456 |
+
"learning_rate": 0.00016253744643216368,
|
| 457 |
+
"loss": 1.325,
|
| 458 |
+
"step": 63
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.649746192893401,
|
| 462 |
+
"grad_norm": 0.3593675196170807,
|
| 463 |
+
"learning_rate": 0.0001612105982547663,
|
| 464 |
+
"loss": 1.353,
|
| 465 |
+
"step": 64
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.6598984771573604,
|
| 469 |
+
"grad_norm": 0.3457062244415283,
|
| 470 |
+
"learning_rate": 0.0001598662882312615,
|
| 471 |
+
"loss": 1.3119,
|
| 472 |
+
"step": 65
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 0.6700507614213198,
|
| 476 |
+
"grad_norm": 0.22607868909835815,
|
| 477 |
+
"learning_rate": 0.00015850489985953076,
|
| 478 |
+
"loss": 1.3281,
|
| 479 |
+
"step": 66
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 0.6802030456852792,
|
| 483 |
+
"grad_norm": 0.1937730461359024,
|
| 484 |
+
"learning_rate": 0.00015712682150947923,
|
| 485 |
+
"loss": 1.3061,
|
| 486 |
+
"step": 67
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 0.6903553299492385,
|
| 490 |
+
"grad_norm": 0.19334916770458221,
|
| 491 |
+
"learning_rate": 0.00015573244631224365,
|
| 492 |
+
"loss": 1.2995,
|
| 493 |
+
"step": 68
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 0.700507614213198,
|
| 497 |
+
"grad_norm": 0.43978920578956604,
|
| 498 |
+
"learning_rate": 0.0001543221720480419,
|
| 499 |
+
"loss": 1.3196,
|
| 500 |
+
"step": 69
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 0.7106598984771574,
|
| 504 |
+
"grad_norm": 0.20429864525794983,
|
| 505 |
+
"learning_rate": 0.00015289640103269625,
|
| 506 |
+
"loss": 1.3428,
|
| 507 |
+
"step": 70
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.7208121827411168,
|
| 511 |
+
"grad_norm": 0.2042793482542038,
|
| 512 |
+
"learning_rate": 0.0001514555400028629,
|
| 513 |
+
"loss": 1.2717,
|
| 514 |
+
"step": 71
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 0.7309644670050761,
|
| 518 |
+
"grad_norm": 0.2089298814535141,
|
| 519 |
+
"learning_rate": 0.00015000000000000001,
|
| 520 |
+
"loss": 1.2823,
|
| 521 |
+
"step": 72
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 0.7411167512690355,
|
| 525 |
+
"grad_norm": 0.29447218775749207,
|
| 526 |
+
"learning_rate": 0.00014853019625310813,
|
| 527 |
+
"loss": 1.2596,
|
| 528 |
+
"step": 73
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 0.751269035532995,
|
| 532 |
+
"grad_norm": 0.20766524970531464,
|
| 533 |
+
"learning_rate": 0.0001470465480602756,
|
| 534 |
+
"loss": 1.3421,
|
| 535 |
+
"step": 74
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 0.7614213197969543,
|
| 539 |
+
"grad_norm": 0.19240014255046844,
|
| 540 |
+
"learning_rate": 0.0001455494786690634,
|
| 541 |
+
"loss": 1.3871,
|
| 542 |
+
"step": 75
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 0.7715736040609137,
|
| 546 |
+
"grad_norm": 0.16677537560462952,
|
| 547 |
+
"learning_rate": 0.00014403941515576344,
|
| 548 |
+
"loss": 1.2507,
|
| 549 |
+
"step": 76
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.7817258883248731,
|
| 553 |
+
"grad_norm": 0.1933940052986145,
|
| 554 |
+
"learning_rate": 0.00014251678830356408,
|
| 555 |
+
"loss": 1.2792,
|
| 556 |
+
"step": 77
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 0.7918781725888325,
|
| 560 |
+
"grad_norm": 0.19050206243991852,
|
| 561 |
+
"learning_rate": 0.00014098203247965875,
|
| 562 |
+
"loss": 1.3017,
|
| 563 |
+
"step": 78
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 0.8020304568527918,
|
| 567 |
+
"grad_norm": 0.25748810172080994,
|
| 568 |
+
"learning_rate": 0.00013943558551133186,
|
| 569 |
+
"loss": 1.2879,
|
| 570 |
+
"step": 79
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 0.8121827411167513,
|
| 574 |
+
"grad_norm": 0.2314893752336502,
|
| 575 |
+
"learning_rate": 0.0001378778885610576,
|
| 576 |
+
"loss": 1.3692,
|
| 577 |
+
"step": 80
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 0.8223350253807107,
|
| 581 |
+
"grad_norm": 0.20771433413028717,
|
| 582 |
+
"learning_rate": 0.00013630938600064747,
|
| 583 |
+
"loss": 1.3268,
|
| 584 |
+
"step": 81
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 0.8324873096446701,
|
| 588 |
+
"grad_norm": 0.18968452513217926,
|
| 589 |
+
"learning_rate": 0.00013473052528448201,
|
| 590 |
+
"loss": 1.2663,
|
| 591 |
+
"step": 82
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 0.8426395939086294,
|
| 595 |
+
"grad_norm": 0.1978602409362793,
|
| 596 |
+
"learning_rate": 0.0001331417568218636,
|
| 597 |
+
"loss": 1.2968,
|
| 598 |
+
"step": 83
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 0.8527918781725888,
|
| 602 |
+
"grad_norm": 0.9941853284835815,
|
| 603 |
+
"learning_rate": 0.00013154353384852558,
|
| 604 |
+
"loss": 1.3187,
|
| 605 |
+
"step": 84
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 0.8629441624365483,
|
| 609 |
+
"grad_norm": 0.18706466257572174,
|
| 610 |
+
"learning_rate": 0.00012993631229733582,
|
| 611 |
+
"loss": 1.2808,
|
| 612 |
+
"step": 85
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 0.8730964467005076,
|
| 616 |
+
"grad_norm": 0.18098409473896027,
|
| 617 |
+
"learning_rate": 0.00012832055066823038,
|
| 618 |
+
"loss": 1.2246,
|
| 619 |
+
"step": 86
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 0.883248730964467,
|
| 623 |
+
"grad_norm": 0.22270160913467407,
|
| 624 |
+
"learning_rate": 0.00012669670989741517,
|
| 625 |
+
"loss": 1.3028,
|
| 626 |
+
"step": 87
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 0.8934010152284264,
|
| 630 |
+
"grad_norm": 0.25465860962867737,
|
| 631 |
+
"learning_rate": 0.00012506525322587207,
|
| 632 |
+
"loss": 1.347,
|
| 633 |
+
"step": 88
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 0.9035532994923858,
|
| 637 |
+
"grad_norm": 0.23076751828193665,
|
| 638 |
+
"learning_rate": 0.00012342664606720822,
|
| 639 |
+
"loss": 1.3099,
|
| 640 |
+
"step": 89
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 0.9137055837563451,
|
| 644 |
+
"grad_norm": 0.19831228256225586,
|
| 645 |
+
"learning_rate": 0.00012178135587488515,
|
| 646 |
+
"loss": 1.278,
|
| 647 |
+
"step": 90
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 0.9238578680203046,
|
| 651 |
+
"grad_norm": 0.22052858769893646,
|
| 652 |
+
"learning_rate": 0.00012012985200886602,
|
| 653 |
+
"loss": 1.2165,
|
| 654 |
+
"step": 91
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 0.934010152284264,
|
| 658 |
+
"grad_norm": 0.18730390071868896,
|
| 659 |
+
"learning_rate": 0.00011847260560171896,
|
| 660 |
+
"loss": 1.2814,
|
| 661 |
+
"step": 92
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 0.9441624365482234,
|
| 665 |
+
"grad_norm": 0.16983264684677124,
|
| 666 |
+
"learning_rate": 0.00011681008942421483,
|
| 667 |
+
"loss": 1.2235,
|
| 668 |
+
"step": 93
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 0.9543147208121827,
|
| 672 |
+
"grad_norm": 0.17806044220924377,
|
| 673 |
+
"learning_rate": 0.00011514277775045768,
|
| 674 |
+
"loss": 1.1867,
|
| 675 |
+
"step": 94
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 0.9644670050761421,
|
| 679 |
+
"grad_norm": 0.1574580818414688,
|
| 680 |
+
"learning_rate": 0.00011347114622258612,
|
| 681 |
+
"loss": 1.2718,
|
| 682 |
+
"step": 95
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 0.9746192893401016,
|
| 686 |
+
"grad_norm": 0.15895454585552216,
|
| 687 |
+
"learning_rate": 0.00011179567171508463,
|
| 688 |
+
"loss": 1.245,
|
| 689 |
+
"step": 96
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 0.9847715736040609,
|
| 693 |
+
"grad_norm": 0.22224721312522888,
|
| 694 |
+
"learning_rate": 0.00011011683219874323,
|
| 695 |
+
"loss": 1.2945,
|
| 696 |
+
"step": 97
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 0.9949238578680203,
|
| 700 |
+
"grad_norm": 0.16613103449344635,
|
| 701 |
+
"learning_rate": 0.00010843510660430447,
|
| 702 |
+
"loss": 1.3054,
|
| 703 |
+
"step": 98
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 0.9949238578680203,
|
| 707 |
+
"eval_loss": 1.249497413635254,
|
| 708 |
+
"eval_runtime": 58.5386,
|
| 709 |
+
"eval_samples_per_second": 10.079,
|
| 710 |
+
"eval_steps_per_second": 1.264,
|
| 711 |
+
"step": 98
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 1.0050761421319796,
|
| 715 |
+
"grad_norm": 0.18297390639781952,
|
| 716 |
+
"learning_rate": 0.00010675097468583652,
|
| 717 |
+
"loss": 1.2749,
|
| 718 |
+
"step": 99
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 1.015228426395939,
|
| 722 |
+
"grad_norm": 0.1834397166967392,
|
| 723 |
+
"learning_rate": 0.00010506491688387127,
|
| 724 |
+
"loss": 1.3218,
|
| 725 |
+
"step": 100
|
| 726 |
+
},
|
| 727 |
+
{
|
| 728 |
+
"epoch": 1.0253807106598984,
|
| 729 |
+
"grad_norm": 0.37363290786743164,
|
| 730 |
+
"learning_rate": 0.00010337741418834684,
|
| 731 |
+
"loss": 1.2591,
|
| 732 |
+
"step": 101
|
| 733 |
+
},
|
| 734 |
+
{
|
| 735 |
+
"epoch": 1.0101522842639594,
|
| 736 |
+
"grad_norm": 0.14738723635673523,
|
| 737 |
+
"learning_rate": 0.0001016889480013931,
|
| 738 |
+
"loss": 1.2353,
|
| 739 |
+
"step": 102
|
| 740 |
+
},
|
| 741 |
+
{
|
| 742 |
+
"epoch": 1.0203045685279188,
|
| 743 |
+
"grad_norm": 0.17808881402015686,
|
| 744 |
+
"learning_rate": 0.0001,
|
| 745 |
+
"loss": 1.2708,
|
| 746 |
+
"step": 103
|
| 747 |
+
},
|
| 748 |
+
{
|
| 749 |
+
"epoch": 1.0304568527918783,
|
| 750 |
+
"grad_norm": 0.1652560830116272,
|
| 751 |
+
"learning_rate": 9.83110519986069e-05,
|
| 752 |
+
"loss": 1.2261,
|
| 753 |
+
"step": 104
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 1.0406091370558375,
|
| 757 |
+
"grad_norm": 0.1601293385028839,
|
| 758 |
+
"learning_rate": 9.662258581165319e-05,
|
| 759 |
+
"loss": 1.2336,
|
| 760 |
+
"step": 105
|
| 761 |
+
},
|
| 762 |
+
{
|
| 763 |
+
"epoch": 1.0507614213197969,
|
| 764 |
+
"grad_norm": 0.18094658851623535,
|
| 765 |
+
"learning_rate": 9.493508311612874e-05,
|
| 766 |
+
"loss": 1.2165,
|
| 767 |
+
"step": 106
|
| 768 |
+
},
|
| 769 |
+
{
|
| 770 |
+
"epoch": 1.0609137055837563,
|
| 771 |
+
"grad_norm": 0.17732879519462585,
|
| 772 |
+
"learning_rate": 9.324902531416349e-05,
|
| 773 |
+
"loss": 1.2647,
|
| 774 |
+
"step": 107
|
| 775 |
+
},
|
| 776 |
+
{
|
| 777 |
+
"epoch": 1.0710659898477157,
|
| 778 |
+
"grad_norm": 0.16203966736793518,
|
| 779 |
+
"learning_rate": 9.156489339569554e-05,
|
| 780 |
+
"loss": 1.2343,
|
| 781 |
+
"step": 108
|
| 782 |
+
},
|
| 783 |
+
{
|
| 784 |
+
"epoch": 1.0812182741116751,
|
| 785 |
+
"grad_norm": 0.21242284774780273,
|
| 786 |
+
"learning_rate": 8.98831678012568e-05,
|
| 787 |
+
"loss": 1.2335,
|
| 788 |
+
"step": 109
|
| 789 |
+
},
|
| 790 |
+
{
|
| 791 |
+
"epoch": 1.0913705583756346,
|
| 792 |
+
"grad_norm": 0.1700202375650406,
|
| 793 |
+
"learning_rate": 8.820432828491542e-05,
|
| 794 |
+
"loss": 1.175,
|
| 795 |
+
"step": 110
|
| 796 |
+
},
|
| 797 |
+
{
|
| 798 |
+
"epoch": 1.101522842639594,
|
| 799 |
+
"grad_norm": 0.1947324275970459,
|
| 800 |
+
"learning_rate": 8.652885377741393e-05,
|
| 801 |
+
"loss": 1.2354,
|
| 802 |
+
"step": 111
|
| 803 |
+
},
|
| 804 |
+
{
|
| 805 |
+
"epoch": 1.1116751269035534,
|
| 806 |
+
"grad_norm": 0.15965348482131958,
|
| 807 |
+
"learning_rate": 8.485722224954237e-05,
|
| 808 |
+
"loss": 1.1937,
|
| 809 |
+
"step": 112
|
| 810 |
+
},
|
| 811 |
+
{
|
| 812 |
+
"epoch": 1.1218274111675126,
|
| 813 |
+
"grad_norm": 0.1767743080854416,
|
| 814 |
+
"learning_rate": 8.31899105757852e-05,
|
| 815 |
+
"loss": 1.2075,
|
| 816 |
+
"step": 113
|
| 817 |
+
},
|
| 818 |
+
{
|
| 819 |
+
"epoch": 1.131979695431472,
|
| 820 |
+
"grad_norm": 0.1793358474969864,
|
| 821 |
+
"learning_rate": 8.15273943982811e-05,
|
| 822 |
+
"loss": 1.2963,
|
| 823 |
+
"step": 114
|
| 824 |
+
},
|
| 825 |
+
{
|
| 826 |
+
"epoch": 1.1421319796954315,
|
| 827 |
+
"grad_norm": 0.17889666557312012,
|
| 828 |
+
"learning_rate": 7.987014799113397e-05,
|
| 829 |
+
"loss": 1.208,
|
| 830 |
+
"step": 115
|
| 831 |
+
},
|
| 832 |
+
{
|
| 833 |
+
"epoch": 1.1522842639593909,
|
| 834 |
+
"grad_norm": 0.16769151389598846,
|
| 835 |
+
"learning_rate": 7.821864412511485e-05,
|
| 836 |
+
"loss": 1.2279,
|
| 837 |
+
"step": 116
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 1.1624365482233503,
|
| 841 |
+
"grad_norm": 0.1788126677274704,
|
| 842 |
+
"learning_rate": 7.65733539327918e-05,
|
| 843 |
+
"loss": 1.2341,
|
| 844 |
+
"step": 117
|
| 845 |
+
},
|
| 846 |
+
{
|
| 847 |
+
"epoch": 1.1725888324873097,
|
| 848 |
+
"grad_norm": 0.17543092370033264,
|
| 849 |
+
"learning_rate": 7.493474677412794e-05,
|
| 850 |
+
"loss": 1.3065,
|
| 851 |
+
"step": 118
|
| 852 |
+
},
|
| 853 |
+
{
|
| 854 |
+
"epoch": 1.1827411167512691,
|
| 855 |
+
"grad_norm": 0.18606220185756683,
|
| 856 |
+
"learning_rate": 7.330329010258483e-05,
|
| 857 |
+
"loss": 1.2233,
|
| 858 |
+
"step": 119
|
| 859 |
+
},
|
| 860 |
+
{
|
| 861 |
+
"epoch": 1.1928934010152283,
|
| 862 |
+
"grad_norm": 0.23003295063972473,
|
| 863 |
+
"learning_rate": 7.16794493317696e-05,
|
| 864 |
+
"loss": 1.2107,
|
| 865 |
+
"step": 120
|
| 866 |
+
},
|
| 867 |
+
{
|
| 868 |
+
"epoch": 1.2030456852791878,
|
| 869 |
+
"grad_norm": 0.15619252622127533,
|
| 870 |
+
"learning_rate": 7.006368770266421e-05,
|
| 871 |
+
"loss": 1.1885,
|
| 872 |
+
"step": 121
|
| 873 |
+
},
|
| 874 |
+
{
|
| 875 |
+
"epoch": 1.2131979695431472,
|
| 876 |
+
"grad_norm": 0.22341646254062653,
|
| 877 |
+
"learning_rate": 6.845646615147445e-05,
|
| 878 |
+
"loss": 1.2421,
|
| 879 |
+
"step": 122
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 1.2233502538071066,
|
| 883 |
+
"grad_norm": 0.1528923660516739,
|
| 884 |
+
"learning_rate": 6.685824317813643e-05,
|
| 885 |
+
"loss": 1.207,
|
| 886 |
+
"step": 123
|
| 887 |
+
},
|
| 888 |
+
{
|
| 889 |
+
"epoch": 1.233502538071066,
|
| 890 |
+
"grad_norm": 0.15776072442531586,
|
| 891 |
+
"learning_rate": 6.526947471551798e-05,
|
| 892 |
+
"loss": 1.278,
|
| 893 |
+
"step": 124
|
| 894 |
+
},
|
| 895 |
+
{
|
| 896 |
+
"epoch": 1.2436548223350254,
|
| 897 |
+
"grad_norm": 0.1788446009159088,
|
| 898 |
+
"learning_rate": 6.369061399935255e-05,
|
| 899 |
+
"loss": 1.2107,
|
| 900 |
+
"step": 125
|
| 901 |
+
},
|
| 902 |
+
{
|
| 903 |
+
"epoch": 1.2538071065989849,
|
| 904 |
+
"grad_norm": 0.17271803319454193,
|
| 905 |
+
"learning_rate": 6.21221114389424e-05,
|
| 906 |
+
"loss": 1.2333,
|
| 907 |
+
"step": 126
|
| 908 |
+
},
|
| 909 |
+
{
|
| 910 |
+
"epoch": 1.263959390862944,
|
| 911 |
+
"grad_norm": 0.15987545251846313,
|
| 912 |
+
"learning_rate": 6.0564414488668165e-05,
|
| 913 |
+
"loss": 1.238,
|
| 914 |
+
"step": 127
|
| 915 |
+
},
|
| 916 |
+
{
|
| 917 |
+
"epoch": 1.2741116751269035,
|
| 918 |
+
"grad_norm": 0.16485555469989777,
|
| 919 |
+
"learning_rate": 5.901796752034128e-05,
|
| 920 |
+
"loss": 1.2471,
|
| 921 |
+
"step": 128
|
| 922 |
+
},
|
| 923 |
+
{
|
| 924 |
+
"epoch": 1.284263959390863,
|
| 925 |
+
"grad_norm": 0.18228358030319214,
|
| 926 |
+
"learning_rate": 5.748321169643596e-05,
|
| 927 |
+
"loss": 1.1761,
|
| 928 |
+
"step": 129
|
| 929 |
+
},
|
| 930 |
+
{
|
| 931 |
+
"epoch": 1.2944162436548223,
|
| 932 |
+
"grad_norm": 0.1641974151134491,
|
| 933 |
+
"learning_rate": 5.596058484423656e-05,
|
| 934 |
+
"loss": 1.2469,
|
| 935 |
+
"step": 130
|
| 936 |
+
},
|
| 937 |
+
{
|
| 938 |
+
"epoch": 1.3045685279187818,
|
| 939 |
+
"grad_norm": 0.20411786437034607,
|
| 940 |
+
"learning_rate": 5.44505213309366e-05,
|
| 941 |
+
"loss": 1.212,
|
| 942 |
+
"step": 131
|
| 943 |
+
},
|
| 944 |
+
{
|
| 945 |
+
"epoch": 1.3147208121827412,
|
| 946 |
+
"grad_norm": 0.16920053958892822,
|
| 947 |
+
"learning_rate": 5.2953451939724454e-05,
|
| 948 |
+
"loss": 1.254,
|
| 949 |
+
"step": 132
|
| 950 |
+
},
|
| 951 |
+
{
|
| 952 |
+
"epoch": 1.3248730964467006,
|
| 953 |
+
"grad_norm": 0.19527798891067505,
|
| 954 |
+
"learning_rate": 5.146980374689192e-05,
|
| 955 |
+
"loss": 1.2187,
|
| 956 |
+
"step": 133
|
| 957 |
+
},
|
| 958 |
+
{
|
| 959 |
+
"epoch": 1.3350253807106598,
|
| 960 |
+
"grad_norm": 0.19046878814697266,
|
| 961 |
+
"learning_rate": 5.000000000000002e-05,
|
| 962 |
+
"loss": 1.2035,
|
| 963 |
+
"step": 134
|
| 964 |
+
},
|
| 965 |
+
{
|
| 966 |
+
"epoch": 1.3451776649746192,
|
| 967 |
+
"grad_norm": 0.1827058643102646,
|
| 968 |
+
"learning_rate": 4.854445999713715e-05,
|
| 969 |
+
"loss": 1.1891,
|
| 970 |
+
"step": 135
|
| 971 |
+
},
|
| 972 |
+
{
|
| 973 |
+
"epoch": 1.3553299492385786,
|
| 974 |
+
"grad_norm": 0.16475000977516174,
|
| 975 |
+
"learning_rate": 4.710359896730379e-05,
|
| 976 |
+
"loss": 1.2263,
|
| 977 |
+
"step": 136
|
| 978 |
+
},
|
| 979 |
+
{
|
| 980 |
+
"epoch": 1.365482233502538,
|
| 981 |
+
"grad_norm": 0.15977239608764648,
|
| 982 |
+
"learning_rate": 4.567782795195816e-05,
|
| 983 |
+
"loss": 1.2006,
|
| 984 |
+
"step": 137
|
| 985 |
+
},
|
| 986 |
+
{
|
| 987 |
+
"epoch": 1.3756345177664975,
|
| 988 |
+
"grad_norm": 0.16366241872310638,
|
| 989 |
+
"learning_rate": 4.426755368775637e-05,
|
| 990 |
+
"loss": 1.1572,
|
| 991 |
+
"step": 138
|
| 992 |
+
},
|
| 993 |
+
{
|
| 994 |
+
"epoch": 1.385786802030457,
|
| 995 |
+
"grad_norm": 0.16748002171516418,
|
| 996 |
+
"learning_rate": 4.287317849052075e-05,
|
| 997 |
+
"loss": 1.1932,
|
| 998 |
+
"step": 139
|
| 999 |
+
},
|
| 1000 |
+
{
|
| 1001 |
+
"epoch": 1.3959390862944163,
|
| 1002 |
+
"grad_norm": 0.17944949865341187,
|
| 1003 |
+
"learning_rate": 4.149510014046922e-05,
|
| 1004 |
+
"loss": 1.1635,
|
| 1005 |
+
"step": 140
|
| 1006 |
+
},
|
| 1007 |
+
{
|
| 1008 |
+
"epoch": 1.4060913705583755,
|
| 1009 |
+
"grad_norm": 0.15999887883663177,
|
| 1010 |
+
"learning_rate": 4.013371176873849e-05,
|
| 1011 |
+
"loss": 1.1987,
|
| 1012 |
+
"step": 141
|
| 1013 |
+
},
|
| 1014 |
+
{
|
| 1015 |
+
"epoch": 1.4162436548223352,
|
| 1016 |
+
"grad_norm": 0.17952662706375122,
|
| 1017 |
+
"learning_rate": 3.878940174523371e-05,
|
| 1018 |
+
"loss": 1.2722,
|
| 1019 |
+
"step": 142
|
| 1020 |
+
},
|
| 1021 |
+
{
|
| 1022 |
+
"epoch": 1.4263959390862944,
|
| 1023 |
+
"grad_norm": 0.16714362800121307,
|
| 1024 |
+
"learning_rate": 3.746255356783632e-05,
|
| 1025 |
+
"loss": 1.2027,
|
| 1026 |
+
"step": 143
|
| 1027 |
+
},
|
| 1028 |
+
{
|
| 1029 |
+
"epoch": 1.4365482233502538,
|
| 1030 |
+
"grad_norm": 0.21137690544128418,
|
| 1031 |
+
"learning_rate": 3.615354575300166e-05,
|
| 1032 |
+
"loss": 1.2099,
|
| 1033 |
+
"step": 144
|
| 1034 |
+
},
|
| 1035 |
+
{
|
| 1036 |
+
"epoch": 1.4467005076142132,
|
| 1037 |
+
"grad_norm": 0.16340382397174835,
|
| 1038 |
+
"learning_rate": 3.4862751727777797e-05,
|
| 1039 |
+
"loss": 1.2476,
|
| 1040 |
+
"step": 145
|
| 1041 |
+
},
|
| 1042 |
+
{
|
| 1043 |
+
"epoch": 1.4568527918781726,
|
| 1044 |
+
"grad_norm": 0.33795541524887085,
|
| 1045 |
+
"learning_rate": 3.3590539723276083e-05,
|
| 1046 |
+
"loss": 1.1955,
|
| 1047 |
+
"step": 146
|
| 1048 |
+
},
|
| 1049 |
+
{
|
| 1050 |
+
"epoch": 1.467005076142132,
|
| 1051 |
+
"grad_norm": 0.1949048787355423,
|
| 1052 |
+
"learning_rate": 3.233727266962425e-05,
|
| 1053 |
+
"loss": 1.2588,
|
| 1054 |
+
"step": 147
|
| 1055 |
+
},
|
| 1056 |
+
{
|
| 1057 |
+
"epoch": 1.4771573604060912,
|
| 1058 |
+
"grad_norm": 0.15895332396030426,
|
| 1059 |
+
"learning_rate": 3.110330809243134e-05,
|
| 1060 |
+
"loss": 1.1895,
|
| 1061 |
+
"step": 148
|
| 1062 |
+
},
|
| 1063 |
+
{
|
| 1064 |
+
"epoch": 1.487309644670051,
|
| 1065 |
+
"grad_norm": 0.17805150151252747,
|
| 1066 |
+
"learning_rate": 2.9888998010794743e-05,
|
| 1067 |
+
"loss": 1.2412,
|
| 1068 |
+
"step": 149
|
| 1069 |
+
},
|
| 1070 |
+
{
|
| 1071 |
+
"epoch": 1.49746192893401,
|
| 1072 |
+
"grad_norm": 0.16068041324615479,
|
| 1073 |
+
"learning_rate": 2.869468883687798e-05,
|
| 1074 |
+
"loss": 1.1935,
|
| 1075 |
+
"step": 150
|
| 1076 |
+
},
|
| 1077 |
+
{
|
| 1078 |
+
"epoch": 1.5076142131979695,
|
| 1079 |
+
"grad_norm": 0.16954682767391205,
|
| 1080 |
+
"learning_rate": 2.7520721277088024e-05,
|
| 1081 |
+
"loss": 1.2139,
|
| 1082 |
+
"step": 151
|
| 1083 |
+
},
|
| 1084 |
+
{
|
| 1085 |
+
"epoch": 1.517766497461929,
|
| 1086 |
+
"grad_norm": 0.17811493575572968,
|
| 1087 |
+
"learning_rate": 2.6367430234880284e-05,
|
| 1088 |
+
"loss": 1.2791,
|
| 1089 |
+
"step": 152
|
| 1090 |
+
},
|
| 1091 |
+
{
|
| 1092 |
+
"epoch": 1.5279187817258884,
|
| 1093 |
+
"grad_norm": 0.1642419546842575,
|
| 1094 |
+
"learning_rate": 2.523514471521913e-05,
|
| 1095 |
+
"loss": 1.2178,
|
| 1096 |
+
"step": 153
|
| 1097 |
+
},
|
| 1098 |
+
{
|
| 1099 |
+
"epoch": 1.5380710659898478,
|
| 1100 |
+
"grad_norm": 0.16778188943862915,
|
| 1101 |
+
"learning_rate": 2.4124187730720917e-05,
|
| 1102 |
+
"loss": 1.2735,
|
| 1103 |
+
"step": 154
|
| 1104 |
+
},
|
| 1105 |
+
{
|
| 1106 |
+
"epoch": 1.548223350253807,
|
| 1107 |
+
"grad_norm": 0.17863012850284576,
|
| 1108 |
+
"learning_rate": 2.3034876209506772e-05,
|
| 1109 |
+
"loss": 1.1632,
|
| 1110 |
+
"step": 155
|
| 1111 |
+
},
|
| 1112 |
+
{
|
| 1113 |
+
"epoch": 1.5583756345177666,
|
| 1114 |
+
"grad_norm": 0.15400968492031097,
|
| 1115 |
+
"learning_rate": 2.1967520904790827e-05,
|
| 1116 |
+
"loss": 1.2465,
|
| 1117 |
+
"step": 156
|
| 1118 |
+
},
|
| 1119 |
+
{
|
| 1120 |
+
"epoch": 1.5685279187817258,
|
| 1121 |
+
"grad_norm": 0.1574324369430542,
|
| 1122 |
+
"learning_rate": 2.092242630623016e-05,
|
| 1123 |
+
"loss": 1.2346,
|
| 1124 |
+
"step": 157
|
| 1125 |
+
},
|
| 1126 |
+
{
|
| 1127 |
+
"epoch": 1.5786802030456852,
|
| 1128 |
+
"grad_norm": 0.15566711127758026,
|
| 1129 |
+
"learning_rate": 1.9899890553061562e-05,
|
| 1130 |
+
"loss": 1.188,
|
| 1131 |
+
"step": 158
|
| 1132 |
+
},
|
| 1133 |
+
{
|
| 1134 |
+
"epoch": 1.5888324873096447,
|
| 1135 |
+
"grad_norm": 0.1699032336473465,
|
| 1136 |
+
"learning_rate": 1.8900205349049904e-05,
|
| 1137 |
+
"loss": 1.2062,
|
| 1138 |
+
"step": 159
|
| 1139 |
+
},
|
| 1140 |
+
{
|
| 1141 |
+
"epoch": 1.598984771573604,
|
| 1142 |
+
"grad_norm": 0.20871774852275848,
|
| 1143 |
+
"learning_rate": 1.7923655879272393e-05,
|
| 1144 |
+
"loss": 1.2349,
|
| 1145 |
+
"step": 160
|
| 1146 |
+
},
|
| 1147 |
+
{
|
| 1148 |
+
"epoch": 1.6091370558375635,
|
| 1149 |
+
"grad_norm": 0.19627781212329865,
|
| 1150 |
+
"learning_rate": 1.6970520728762375e-05,
|
| 1151 |
+
"loss": 1.193,
|
| 1152 |
+
"step": 161
|
| 1153 |
+
},
|
| 1154 |
+
{
|
| 1155 |
+
"epoch": 1.6192893401015227,
|
| 1156 |
+
"grad_norm": 0.1803133487701416,
|
| 1157 |
+
"learning_rate": 1.60410718030361e-05,
|
| 1158 |
+
"loss": 1.28,
|
| 1159 |
+
"step": 162
|
| 1160 |
+
},
|
| 1161 |
+
{
|
| 1162 |
+
"epoch": 1.6294416243654823,
|
| 1163 |
+
"grad_norm": 0.17840127646923065,
|
| 1164 |
+
"learning_rate": 1.5135574250524897e-05,
|
| 1165 |
+
"loss": 1.285,
|
| 1166 |
+
"step": 163
|
| 1167 |
+
},
|
| 1168 |
+
{
|
| 1169 |
+
"epoch": 1.6395939086294415,
|
| 1170 |
+
"grad_norm": 0.1523265242576599,
|
| 1171 |
+
"learning_rate": 1.425428638693489e-05,
|
| 1172 |
+
"loss": 1.2491,
|
| 1173 |
+
"step": 164
|
| 1174 |
+
},
|
| 1175 |
+
{
|
| 1176 |
+
"epoch": 1.649746192893401,
|
| 1177 |
+
"grad_norm": 0.17296157777309418,
|
| 1178 |
+
"learning_rate": 1.339745962155613e-05,
|
| 1179 |
+
"loss": 1.231,
|
| 1180 |
+
"step": 165
|
| 1181 |
+
},
|
| 1182 |
+
{
|
| 1183 |
+
"epoch": 1.6598984771573604,
|
| 1184 |
+
"grad_norm": 0.17164817452430725,
|
| 1185 |
+
"learning_rate": 1.2565338385541792e-05,
|
| 1186 |
+
"loss": 1.2217,
|
| 1187 |
+
"step": 166
|
| 1188 |
+
},
|
| 1189 |
+
{
|
| 1190 |
+
"epoch": 1.6700507614213198,
|
| 1191 |
+
"grad_norm": 0.17271456122398376,
|
| 1192 |
+
"learning_rate": 1.1758160062178093e-05,
|
| 1193 |
+
"loss": 1.285,
|
| 1194 |
+
"step": 167
|
| 1195 |
+
},
|
| 1196 |
+
{
|
| 1197 |
+
"epoch": 1.6802030456852792,
|
| 1198 |
+
"grad_norm": 0.16020996868610382,
|
| 1199 |
+
"learning_rate": 1.097615491916485e-05,
|
| 1200 |
+
"loss": 1.1259,
|
| 1201 |
+
"step": 168
|
| 1202 |
+
},
|
| 1203 |
+
{
|
| 1204 |
+
"epoch": 1.6903553299492384,
|
| 1205 |
+
"grad_norm": 0.17722178995609283,
|
| 1206 |
+
"learning_rate": 1.0219546042925843e-05,
|
| 1207 |
+
"loss": 1.2601,
|
| 1208 |
+
"step": 169
|
| 1209 |
+
},
|
| 1210 |
+
{
|
| 1211 |
+
"epoch": 1.700507614213198,
|
| 1212 |
+
"grad_norm": 0.1641930788755417,
|
| 1213 |
+
"learning_rate": 9.488549274967872e-06,
|
| 1214 |
+
"loss": 1.1552,
|
| 1215 |
+
"step": 170
|
| 1216 |
+
},
|
| 1217 |
+
{
|
| 1218 |
+
"epoch": 1.7106598984771573,
|
| 1219 |
+
"grad_norm": 0.17400699853897095,
|
| 1220 |
+
"learning_rate": 8.783373150306661e-06,
|
| 1221 |
+
"loss": 1.2226,
|
| 1222 |
+
"step": 171
|
| 1223 |
+
},
|
| 1224 |
+
{
|
| 1225 |
+
"epoch": 1.720812182741117,
|
| 1226 |
+
"grad_norm": 0.16899757087230682,
|
| 1227 |
+
"learning_rate": 8.10421883797694e-06,
|
| 1228 |
+
"loss": 1.3269,
|
| 1229 |
+
"step": 172
|
| 1230 |
+
},
|
| 1231 |
+
{
|
| 1232 |
+
"epoch": 1.7309644670050761,
|
| 1233 |
+
"grad_norm": 0.20650531351566315,
|
| 1234 |
+
"learning_rate": 7.4512800836440525e-06,
|
| 1235 |
+
"loss": 1.1627,
|
| 1236 |
+
"step": 173
|
| 1237 |
+
},
|
| 1238 |
+
{
|
| 1239 |
+
"epoch": 1.7411167512690355,
|
| 1240 |
+
"grad_norm": 0.15405453741550446,
|
| 1241 |
+
"learning_rate": 6.824743154333157e-06,
|
| 1242 |
+
"loss": 1.1767,
|
| 1243 |
+
"step": 174
|
| 1244 |
+
},
|
| 1245 |
+
{
|
| 1246 |
+
"epoch": 1.751269035532995,
|
| 1247 |
+
"grad_norm": 0.16714583337306976,
|
| 1248 |
+
"learning_rate": 6.22478678529197e-06,
|
| 1249 |
+
"loss": 1.2332,
|
| 1250 |
+
"step": 175
|
| 1251 |
+
},
|
| 1252 |
+
{
|
| 1253 |
+
"epoch": 1.7614213197969542,
|
| 1254 |
+
"grad_norm": 0.16613709926605225,
|
| 1255 |
+
"learning_rate": 5.651582129001986e-06,
|
| 1256 |
+
"loss": 1.2306,
|
| 1257 |
+
"step": 176
|
| 1258 |
+
},
|
| 1259 |
+
{
|
| 1260 |
+
"epoch": 1.7715736040609138,
|
| 1261 |
+
"grad_norm": 0.22227272391319275,
|
| 1262 |
+
"learning_rate": 5.105292706353093e-06,
|
| 1263 |
+
"loss": 1.1969,
|
| 1264 |
+
"step": 177
|
| 1265 |
+
},
|
| 1266 |
+
{
|
| 1267 |
+
"epoch": 1.781725888324873,
|
| 1268 |
+
"grad_norm": 0.18371812999248505,
|
| 1269 |
+
"learning_rate": 4.586074359995119e-06,
|
| 1270 |
+
"loss": 1.2643,
|
| 1271 |
+
"step": 178
|
| 1272 |
+
},
|
| 1273 |
+
{
|
| 1274 |
+
"epoch": 1.7918781725888326,
|
| 1275 |
+
"grad_norm": 0.1571132242679596,
|
| 1276 |
+
"learning_rate": 4.094075209879788e-06,
|
| 1277 |
+
"loss": 1.208,
|
| 1278 |
+
"step": 179
|
| 1279 |
+
},
|
| 1280 |
+
{
|
| 1281 |
+
"epoch": 1.8020304568527918,
|
| 1282 |
+
"grad_norm": 0.16985946893692017,
|
| 1283 |
+
"learning_rate": 3.6294356110059157e-06,
|
| 1284 |
+
"loss": 1.2069,
|
| 1285 |
+
"step": 180
|
| 1286 |
+
},
|
| 1287 |
+
{
|
| 1288 |
+
"epoch": 1.8121827411167513,
|
| 1289 |
+
"grad_norm": 0.16651304066181183,
|
| 1290 |
+
"learning_rate": 3.1922881133795825e-06,
|
| 1291 |
+
"loss": 1.2017,
|
| 1292 |
+
"step": 181
|
| 1293 |
+
},
|
| 1294 |
+
{
|
| 1295 |
+
"epoch": 1.8223350253807107,
|
| 1296 |
+
"grad_norm": 0.16982710361480713,
|
| 1297 |
+
"learning_rate": 2.7827574242009437e-06,
|
| 1298 |
+
"loss": 1.1706,
|
| 1299 |
+
"step": 182
|
| 1300 |
+
},
|
| 1301 |
+
{
|
| 1302 |
+
"epoch": 1.83248730964467,
|
| 1303 |
+
"grad_norm": 0.16492588818073273,
|
| 1304 |
+
"learning_rate": 2.4009603722884742e-06,
|
| 1305 |
+
"loss": 1.2733,
|
| 1306 |
+
"step": 183
|
| 1307 |
+
},
|
| 1308 |
+
{
|
| 1309 |
+
"epoch": 1.8426395939086295,
|
| 1310 |
+
"grad_norm": 0.165365532040596,
|
| 1311 |
+
"learning_rate": 2.0470058747505516e-06,
|
| 1312 |
+
"loss": 1.1843,
|
| 1313 |
+
"step": 184
|
| 1314 |
+
},
|
| 1315 |
+
{
|
| 1316 |
+
"epoch": 1.8527918781725887,
|
| 1317 |
+
"grad_norm": 0.15770269930362701,
|
| 1318 |
+
"learning_rate": 1.7209949059142083e-06,
|
| 1319 |
+
"loss": 1.2168,
|
| 1320 |
+
"step": 185
|
| 1321 |
+
},
|
| 1322 |
+
{
|
| 1323 |
+
"epoch": 1.8629441624365484,
|
| 1324 |
+
"grad_norm": 0.16646115481853485,
|
| 1325 |
+
"learning_rate": 1.4230204685196203e-06,
|
| 1326 |
+
"loss": 1.1774,
|
| 1327 |
+
"step": 186
|
| 1328 |
+
},
|
| 1329 |
+
{
|
| 1330 |
+
"epoch": 1.8730964467005076,
|
| 1331 |
+
"grad_norm": 0.17410410940647125,
|
| 1332 |
+
"learning_rate": 1.1531675671888619e-06,
|
| 1333 |
+
"loss": 1.2268,
|
| 1334 |
+
"step": 187
|
| 1335 |
+
},
|
| 1336 |
+
{
|
| 1337 |
+
"epoch": 1.883248730964467,
|
| 1338 |
+
"grad_norm": 0.17677107453346252,
|
| 1339 |
+
"learning_rate": 9.11513184176116e-07,
|
| 1340 |
+
"loss": 1.1485,
|
| 1341 |
+
"step": 188
|
| 1342 |
+
},
|
| 1343 |
+
{
|
| 1344 |
+
"epoch": 1.8934010152284264,
|
| 1345 |
+
"grad_norm": 0.15033933520317078,
|
| 1346 |
+
"learning_rate": 6.981262574066394e-07,
|
| 1347 |
+
"loss": 1.2125,
|
| 1348 |
+
"step": 189
|
| 1349 |
+
},
|
| 1350 |
+
{
|
| 1351 |
+
"epoch": 1.9035532994923858,
|
| 1352 |
+
"grad_norm": 0.1645897626876831,
|
| 1353 |
+
"learning_rate": 5.130676608104845e-07,
|
| 1354 |
+
"loss": 1.2151,
|
| 1355 |
+
"step": 190
|
| 1356 |
+
},
|
| 1357 |
+
{
|
| 1358 |
+
"epoch": 1.9137055837563453,
|
| 1359 |
+
"grad_norm": 0.17260093986988068,
|
| 1360 |
+
"learning_rate": 3.56390186956701e-07,
|
| 1361 |
+
"loss": 1.2509,
|
| 1362 |
+
"step": 191
|
| 1363 |
+
},
|
| 1364 |
+
{
|
| 1365 |
+
"epoch": 1.9238578680203045,
|
| 1366 |
+
"grad_norm": 0.16453680396080017,
|
| 1367 |
+
"learning_rate": 2.2813853199292746e-07,
|
| 1368 |
+
"loss": 1.264,
|
| 1369 |
+
"step": 192
|
| 1370 |
+
},
|
| 1371 |
+
{
|
| 1372 |
+
"epoch": 1.934010152284264,
|
| 1373 |
+
"grad_norm": 0.1580802947282791,
|
| 1374 |
+
"learning_rate": 1.2834928289472416e-07,
|
| 1375 |
+
"loss": 1.193,
|
| 1376 |
+
"step": 193
|
| 1377 |
+
},
|
| 1378 |
+
{
|
| 1379 |
+
"epoch": 1.9441624365482233,
|
| 1380 |
+
"grad_norm": 0.18191225826740265,
|
| 1381 |
+
"learning_rate": 5.705090702819993e-08,
|
| 1382 |
+
"loss": 1.2404,
|
| 1383 |
+
"step": 194
|
| 1384 |
+
},
|
| 1385 |
+
{
|
| 1386 |
+
"epoch": 1.9543147208121827,
|
| 1387 |
+
"grad_norm": 0.19886773824691772,
|
| 1388 |
+
"learning_rate": 1.426374402901942e-08,
|
| 1389 |
+
"loss": 1.1602,
|
| 1390 |
+
"step": 195
|
| 1391 |
+
},
|
| 1392 |
+
{
|
| 1393 |
+
"epoch": 1.9644670050761421,
|
| 1394 |
+
"grad_norm": 0.19592063128948212,
|
| 1395 |
+
"learning_rate": 0.0,
|
| 1396 |
+
"loss": 1.1879,
|
| 1397 |
+
"step": 196
|
| 1398 |
+
},
|
| 1399 |
+
{
|
| 1400 |
+
"epoch": 1.9644670050761421,
|
| 1401 |
+
"eval_loss": 1.2216618061065674,
|
| 1402 |
+
"eval_runtime": 58.8162,
|
| 1403 |
+
"eval_samples_per_second": 10.031,
|
| 1404 |
+
"eval_steps_per_second": 1.258,
|
| 1405 |
+
"step": 196
|
| 1406 |
+
}
|
| 1407 |
+
],
|
| 1408 |
+
"logging_steps": 1,
|
| 1409 |
+
"max_steps": 196,
|
| 1410 |
+
"num_input_tokens_seen": 0,
|
| 1411 |
+
"num_train_epochs": 2,
|
| 1412 |
+
"save_steps": 98,
|
| 1413 |
+
"stateful_callbacks": {
|
| 1414 |
+
"TrainerControl": {
|
| 1415 |
+
"args": {
|
| 1416 |
+
"should_epoch_stop": false,
|
| 1417 |
+
"should_evaluate": false,
|
| 1418 |
+
"should_log": false,
|
| 1419 |
+
"should_save": true,
|
| 1420 |
+
"should_training_stop": true
|
| 1421 |
+
},
|
| 1422 |
+
"attributes": {}
|
| 1423 |
+
}
|
| 1424 |
+
},
|
| 1425 |
+
"total_flos": 1.0307946378260644e+18,
|
| 1426 |
+
"train_batch_size": 2,
|
| 1427 |
+
"trial_name": null,
|
| 1428 |
+
"trial_params": null
|
| 1429 |
+
}
|
checkpoint-196/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ebabd7fe1a216aadf93e2b9106041cfaee52bf0b7322ca74f94d144ee0af1908
|
| 3 |
+
size 6200
|
checkpoint-98/README.md
ADDED
|
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
base_model: NousResearch/CodeLlama-7b-hf
|
| 4 |
+
---
|
| 5 |
+
|
| 6 |
+
# Model Card for Model ID
|
| 7 |
+
|
| 8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 9 |
+
|
| 10 |
+
|
| 11 |
+
|
| 12 |
+
## Model Details
|
| 13 |
+
|
| 14 |
+
### Model Description
|
| 15 |
+
|
| 16 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
- **Developed by:** [More Information Needed]
|
| 21 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 22 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 23 |
+
- **Model type:** [More Information Needed]
|
| 24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 25 |
+
- **License:** [More Information Needed]
|
| 26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 27 |
+
|
| 28 |
+
### Model Sources [optional]
|
| 29 |
+
|
| 30 |
+
<!-- Provide the basic links for the model. -->
|
| 31 |
+
|
| 32 |
+
- **Repository:** [More Information Needed]
|
| 33 |
+
- **Paper [optional]:** [More Information Needed]
|
| 34 |
+
- **Demo [optional]:** [More Information Needed]
|
| 35 |
+
|
| 36 |
+
## Uses
|
| 37 |
+
|
| 38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 39 |
+
|
| 40 |
+
### Direct Use
|
| 41 |
+
|
| 42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 43 |
+
|
| 44 |
+
[More Information Needed]
|
| 45 |
+
|
| 46 |
+
### Downstream Use [optional]
|
| 47 |
+
|
| 48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 49 |
+
|
| 50 |
+
[More Information Needed]
|
| 51 |
+
|
| 52 |
+
### Out-of-Scope Use
|
| 53 |
+
|
| 54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 55 |
+
|
| 56 |
+
[More Information Needed]
|
| 57 |
+
|
| 58 |
+
## Bias, Risks, and Limitations
|
| 59 |
+
|
| 60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 61 |
+
|
| 62 |
+
[More Information Needed]
|
| 63 |
+
|
| 64 |
+
### Recommendations
|
| 65 |
+
|
| 66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 67 |
+
|
| 68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 69 |
+
|
| 70 |
+
## How to Get Started with the Model
|
| 71 |
+
|
| 72 |
+
Use the code below to get started with the model.
|
| 73 |
+
|
| 74 |
+
[More Information Needed]
|
| 75 |
+
|
| 76 |
+
## Training Details
|
| 77 |
+
|
| 78 |
+
### Training Data
|
| 79 |
+
|
| 80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 81 |
+
|
| 82 |
+
[More Information Needed]
|
| 83 |
+
|
| 84 |
+
### Training Procedure
|
| 85 |
+
|
| 86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 87 |
+
|
| 88 |
+
#### Preprocessing [optional]
|
| 89 |
+
|
| 90 |
+
[More Information Needed]
|
| 91 |
+
|
| 92 |
+
|
| 93 |
+
#### Training Hyperparameters
|
| 94 |
+
|
| 95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 96 |
+
|
| 97 |
+
#### Speeds, Sizes, Times [optional]
|
| 98 |
+
|
| 99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 100 |
+
|
| 101 |
+
[More Information Needed]
|
| 102 |
+
|
| 103 |
+
## Evaluation
|
| 104 |
+
|
| 105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 106 |
+
|
| 107 |
+
### Testing Data, Factors & Metrics
|
| 108 |
+
|
| 109 |
+
#### Testing Data
|
| 110 |
+
|
| 111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 112 |
+
|
| 113 |
+
[More Information Needed]
|
| 114 |
+
|
| 115 |
+
#### Factors
|
| 116 |
+
|
| 117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 118 |
+
|
| 119 |
+
[More Information Needed]
|
| 120 |
+
|
| 121 |
+
#### Metrics
|
| 122 |
+
|
| 123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 124 |
+
|
| 125 |
+
[More Information Needed]
|
| 126 |
+
|
| 127 |
+
### Results
|
| 128 |
+
|
| 129 |
+
[More Information Needed]
|
| 130 |
+
|
| 131 |
+
#### Summary
|
| 132 |
+
|
| 133 |
+
|
| 134 |
+
|
| 135 |
+
## Model Examination [optional]
|
| 136 |
+
|
| 137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 138 |
+
|
| 139 |
+
[More Information Needed]
|
| 140 |
+
|
| 141 |
+
## Environmental Impact
|
| 142 |
+
|
| 143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 144 |
+
|
| 145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
| 146 |
+
|
| 147 |
+
- **Hardware Type:** [More Information Needed]
|
| 148 |
+
- **Hours used:** [More Information Needed]
|
| 149 |
+
- **Cloud Provider:** [More Information Needed]
|
| 150 |
+
- **Compute Region:** [More Information Needed]
|
| 151 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 152 |
+
|
| 153 |
+
## Technical Specifications [optional]
|
| 154 |
+
|
| 155 |
+
### Model Architecture and Objective
|
| 156 |
+
|
| 157 |
+
[More Information Needed]
|
| 158 |
+
|
| 159 |
+
### Compute Infrastructure
|
| 160 |
+
|
| 161 |
+
[More Information Needed]
|
| 162 |
+
|
| 163 |
+
#### Hardware
|
| 164 |
+
|
| 165 |
+
[More Information Needed]
|
| 166 |
+
|
| 167 |
+
#### Software
|
| 168 |
+
|
| 169 |
+
[More Information Needed]
|
| 170 |
+
|
| 171 |
+
## Citation [optional]
|
| 172 |
+
|
| 173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 174 |
+
|
| 175 |
+
**BibTeX:**
|
| 176 |
+
|
| 177 |
+
[More Information Needed]
|
| 178 |
+
|
| 179 |
+
**APA:**
|
| 180 |
+
|
| 181 |
+
[More Information Needed]
|
| 182 |
+
|
| 183 |
+
## Glossary [optional]
|
| 184 |
+
|
| 185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 186 |
+
|
| 187 |
+
[More Information Needed]
|
| 188 |
+
|
| 189 |
+
## More Information [optional]
|
| 190 |
+
|
| 191 |
+
[More Information Needed]
|
| 192 |
+
|
| 193 |
+
## Model Card Authors [optional]
|
| 194 |
+
|
| 195 |
+
[More Information Needed]
|
| 196 |
+
|
| 197 |
+
## Model Card Contact
|
| 198 |
+
|
| 199 |
+
[More Information Needed]
|
| 200 |
+
### Framework versions
|
| 201 |
+
|
| 202 |
+
- PEFT 0.11.1
|
checkpoint-98/adapter_config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "NousResearch/CodeLlama-7b-hf",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": null,
|
| 7 |
+
"inference_mode": true,
|
| 8 |
+
"init_lora_weights": true,
|
| 9 |
+
"layer_replication": null,
|
| 10 |
+
"layers_pattern": null,
|
| 11 |
+
"layers_to_transform": null,
|
| 12 |
+
"loftq_config": {},
|
| 13 |
+
"lora_alpha": 16,
|
| 14 |
+
"lora_dropout": 0.05,
|
| 15 |
+
"megatron_config": null,
|
| 16 |
+
"megatron_core": "megatron.core",
|
| 17 |
+
"modules_to_save": null,
|
| 18 |
+
"peft_type": "LORA",
|
| 19 |
+
"r": 32,
|
| 20 |
+
"rank_pattern": {},
|
| 21 |
+
"revision": null,
|
| 22 |
+
"target_modules": [
|
| 23 |
+
"gate_proj",
|
| 24 |
+
"v_proj",
|
| 25 |
+
"o_proj",
|
| 26 |
+
"k_proj",
|
| 27 |
+
"up_proj",
|
| 28 |
+
"down_proj",
|
| 29 |
+
"q_proj"
|
| 30 |
+
],
|
| 31 |
+
"task_type": "CAUSAL_LM",
|
| 32 |
+
"use_dora": false,
|
| 33 |
+
"use_rslora": false
|
| 34 |
+
}
|
checkpoint-98/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7623e73aef3de3718899aa3aa183d3f484023dc9aba3a976dc48b74150154f1f
|
| 3 |
+
size 319876032
|
checkpoint-98/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f41e42e7d1fd08636825f491201a9c3b6ad7064668c2ba27fca2af9a41b5e215
|
| 3 |
+
size 160736084
|
checkpoint-98/rng_state_0.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:31480aca1cfcb18a53878f9e571c2f7e052a77342f7129586689d6757dc10495
|
| 3 |
+
size 14960
|
checkpoint-98/rng_state_1.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:78340106548d9645ba07ebe8b0c7d7b24803ee6b95373c25a757b5a3e8f2b593
|
| 3 |
+
size 14960
|
checkpoint-98/rng_state_2.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fe05cbbb9360e58c7bc54a5c9641cc225f2b526ad6ead9ce2168689bbbae65b7
|
| 3 |
+
size 14960
|
checkpoint-98/rng_state_3.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e1746434fcc316cc4a0038fc698d124320b6b3f0dc2aced172b66fb465b4e103
|
| 3 |
+
size 14960
|
checkpoint-98/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5e31465eabc96d2c0b0dc68386782c8ea3a5771edcba13d0d620c4297cd31957
|
| 3 |
+
size 1064
|
checkpoint-98/special_tokens_map.json
ADDED
|
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"▁<PRE>",
|
| 4 |
+
"▁<MID>",
|
| 5 |
+
"▁<SUF>",
|
| 6 |
+
"▁<EOT>"
|
| 7 |
+
],
|
| 8 |
+
"bos_token": {
|
| 9 |
+
"content": "<s>",
|
| 10 |
+
"lstrip": false,
|
| 11 |
+
"normalized": false,
|
| 12 |
+
"rstrip": false,
|
| 13 |
+
"single_word": false
|
| 14 |
+
},
|
| 15 |
+
"eos_token": {
|
| 16 |
+
"content": "</s>",
|
| 17 |
+
"lstrip": false,
|
| 18 |
+
"normalized": false,
|
| 19 |
+
"rstrip": false,
|
| 20 |
+
"single_word": false
|
| 21 |
+
},
|
| 22 |
+
"pad_token": {
|
| 23 |
+
"content": "</s>",
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"normalized": false,
|
| 26 |
+
"rstrip": false,
|
| 27 |
+
"single_word": false
|
| 28 |
+
},
|
| 29 |
+
"unk_token": {
|
| 30 |
+
"content": "<unk>",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": false,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false
|
| 35 |
+
}
|
| 36 |
+
}
|
checkpoint-98/tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:45ccb9c8b6b561889acea59191d66986d314e7cbd6a78abc6e49b139ca91c1e6
|
| 3 |
+
size 500058
|
checkpoint-98/tokenizer_config.json
ADDED
|
@@ -0,0 +1,85 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"0": {
|
| 6 |
+
"content": "<unk>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"1": {
|
| 14 |
+
"content": "<s>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"2": {
|
| 22 |
+
"content": "</s>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
},
|
| 29 |
+
"32007": {
|
| 30 |
+
"content": "▁<PRE>",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": false,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false,
|
| 35 |
+
"special": true
|
| 36 |
+
},
|
| 37 |
+
"32008": {
|
| 38 |
+
"content": "▁<SUF>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false,
|
| 43 |
+
"special": true
|
| 44 |
+
},
|
| 45 |
+
"32009": {
|
| 46 |
+
"content": "▁<MID>",
|
| 47 |
+
"lstrip": false,
|
| 48 |
+
"normalized": false,
|
| 49 |
+
"rstrip": false,
|
| 50 |
+
"single_word": false,
|
| 51 |
+
"special": true
|
| 52 |
+
},
|
| 53 |
+
"32010": {
|
| 54 |
+
"content": "▁<EOT>",
|
| 55 |
+
"lstrip": false,
|
| 56 |
+
"normalized": false,
|
| 57 |
+
"rstrip": false,
|
| 58 |
+
"single_word": false,
|
| 59 |
+
"special": true
|
| 60 |
+
}
|
| 61 |
+
},
|
| 62 |
+
"additional_special_tokens": [
|
| 63 |
+
"▁<PRE>",
|
| 64 |
+
"▁<MID>",
|
| 65 |
+
"▁<SUF>",
|
| 66 |
+
"▁<EOT>"
|
| 67 |
+
],
|
| 68 |
+
"bos_token": "<s>",
|
| 69 |
+
"clean_up_tokenization_spaces": false,
|
| 70 |
+
"eos_token": "</s>",
|
| 71 |
+
"eot_token": "▁<EOT>",
|
| 72 |
+
"fill_token": "<FILL_ME>",
|
| 73 |
+
"legacy": null,
|
| 74 |
+
"middle_token": "▁<MID>",
|
| 75 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 76 |
+
"pad_token": "</s>",
|
| 77 |
+
"prefix_token": "▁<PRE>",
|
| 78 |
+
"sp_model_kwargs": {},
|
| 79 |
+
"suffix_first": false,
|
| 80 |
+
"suffix_token": "▁<SUF>",
|
| 81 |
+
"tokenizer_class": "CodeLlamaTokenizer",
|
| 82 |
+
"unk_token": "<unk>",
|
| 83 |
+
"use_default_system_prompt": false,
|
| 84 |
+
"use_fast": true
|
| 85 |
+
}
|
checkpoint-98/trainer_state.json
ADDED
|
@@ -0,0 +1,735 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.9949238578680203,
|
| 5 |
+
"eval_steps": 98,
|
| 6 |
+
"global_step": 98,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.01015228426395939,
|
| 13 |
+
"grad_norm": 0.516016960144043,
|
| 14 |
+
"learning_rate": 2e-05,
|
| 15 |
+
"loss": 4.3699,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.01015228426395939,
|
| 20 |
+
"eval_loss": 4.561354637145996,
|
| 21 |
+
"eval_runtime": 58.1653,
|
| 22 |
+
"eval_samples_per_second": 10.144,
|
| 23 |
+
"eval_steps_per_second": 1.272,
|
| 24 |
+
"step": 1
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.02030456852791878,
|
| 28 |
+
"grad_norm": 0.5144633650779724,
|
| 29 |
+
"learning_rate": 4e-05,
|
| 30 |
+
"loss": 4.5708,
|
| 31 |
+
"step": 2
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.030456852791878174,
|
| 35 |
+
"grad_norm": 0.5246109962463379,
|
| 36 |
+
"learning_rate": 6e-05,
|
| 37 |
+
"loss": 4.5871,
|
| 38 |
+
"step": 3
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.04060913705583756,
|
| 42 |
+
"grad_norm": 0.5753014087677002,
|
| 43 |
+
"learning_rate": 8e-05,
|
| 44 |
+
"loss": 4.3818,
|
| 45 |
+
"step": 4
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.050761421319796954,
|
| 49 |
+
"grad_norm": 0.6615588665008545,
|
| 50 |
+
"learning_rate": 0.0001,
|
| 51 |
+
"loss": 4.448,
|
| 52 |
+
"step": 5
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.06091370558375635,
|
| 56 |
+
"grad_norm": 0.751004159450531,
|
| 57 |
+
"learning_rate": 0.00012,
|
| 58 |
+
"loss": 4.4964,
|
| 59 |
+
"step": 6
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.07106598984771574,
|
| 63 |
+
"grad_norm": 0.886650562286377,
|
| 64 |
+
"learning_rate": 0.00014,
|
| 65 |
+
"loss": 4.4011,
|
| 66 |
+
"step": 7
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.08121827411167512,
|
| 70 |
+
"grad_norm": 1.1175657510757446,
|
| 71 |
+
"learning_rate": 0.00016,
|
| 72 |
+
"loss": 3.9849,
|
| 73 |
+
"step": 8
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.09137055837563451,
|
| 77 |
+
"grad_norm": 0.9861809015274048,
|
| 78 |
+
"learning_rate": 0.00018,
|
| 79 |
+
"loss": 3.8218,
|
| 80 |
+
"step": 9
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.10152284263959391,
|
| 84 |
+
"grad_norm": 1.1107577085494995,
|
| 85 |
+
"learning_rate": 0.0002,
|
| 86 |
+
"loss": 3.6451,
|
| 87 |
+
"step": 10
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.1116751269035533,
|
| 91 |
+
"grad_norm": 0.9435870051383972,
|
| 92 |
+
"learning_rate": 0.000199985736255971,
|
| 93 |
+
"loss": 3.5619,
|
| 94 |
+
"step": 11
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.1218274111675127,
|
| 98 |
+
"grad_norm": 0.9529088139533997,
|
| 99 |
+
"learning_rate": 0.0001999429490929718,
|
| 100 |
+
"loss": 3.4561,
|
| 101 |
+
"step": 12
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.1319796954314721,
|
| 105 |
+
"grad_norm": 1.3805211782455444,
|
| 106 |
+
"learning_rate": 0.00019987165071710527,
|
| 107 |
+
"loss": 3.2067,
|
| 108 |
+
"step": 13
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.14213197969543148,
|
| 112 |
+
"grad_norm": 1.319393515586853,
|
| 113 |
+
"learning_rate": 0.00019977186146800707,
|
| 114 |
+
"loss": 3.0656,
|
| 115 |
+
"step": 14
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.15228426395939088,
|
| 119 |
+
"grad_norm": 1.061409592628479,
|
| 120 |
+
"learning_rate": 0.0001996436098130433,
|
| 121 |
+
"loss": 2.7711,
|
| 122 |
+
"step": 15
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.16243654822335024,
|
| 126 |
+
"grad_norm": 1.036845326423645,
|
| 127 |
+
"learning_rate": 0.00019948693233918952,
|
| 128 |
+
"loss": 2.6576,
|
| 129 |
+
"step": 16
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.17258883248730963,
|
| 133 |
+
"grad_norm": 1.0924557447433472,
|
| 134 |
+
"learning_rate": 0.00019930187374259337,
|
| 135 |
+
"loss": 2.4101,
|
| 136 |
+
"step": 17
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.18274111675126903,
|
| 140 |
+
"grad_norm": 1.0557212829589844,
|
| 141 |
+
"learning_rate": 0.00019908848681582391,
|
| 142 |
+
"loss": 2.2991,
|
| 143 |
+
"step": 18
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.19289340101522842,
|
| 147 |
+
"grad_norm": 1.1735273599624634,
|
| 148 |
+
"learning_rate": 0.00019884683243281116,
|
| 149 |
+
"loss": 2.3991,
|
| 150 |
+
"step": 19
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.20304568527918782,
|
| 154 |
+
"grad_norm": 0.8104203343391418,
|
| 155 |
+
"learning_rate": 0.00019857697953148037,
|
| 156 |
+
"loss": 2.107,
|
| 157 |
+
"step": 20
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.2131979695431472,
|
| 161 |
+
"grad_norm": 0.7275764346122742,
|
| 162 |
+
"learning_rate": 0.00019827900509408581,
|
| 163 |
+
"loss": 2.0596,
|
| 164 |
+
"step": 21
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.2233502538071066,
|
| 168 |
+
"grad_norm": 1.0672590732574463,
|
| 169 |
+
"learning_rate": 0.00019795299412524945,
|
| 170 |
+
"loss": 1.9543,
|
| 171 |
+
"step": 22
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.233502538071066,
|
| 175 |
+
"grad_norm": 0.5848283767700195,
|
| 176 |
+
"learning_rate": 0.00019759903962771156,
|
| 177 |
+
"loss": 1.8091,
|
| 178 |
+
"step": 23
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.2436548223350254,
|
| 182 |
+
"grad_norm": 0.9580035209655762,
|
| 183 |
+
"learning_rate": 0.00019721724257579907,
|
| 184 |
+
"loss": 1.7178,
|
| 185 |
+
"step": 24
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.25380710659898476,
|
| 189 |
+
"grad_norm": 0.5362741351127625,
|
| 190 |
+
"learning_rate": 0.00019680771188662044,
|
| 191 |
+
"loss": 1.6739,
|
| 192 |
+
"step": 25
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.2639593908629442,
|
| 196 |
+
"grad_norm": 0.5108774304389954,
|
| 197 |
+
"learning_rate": 0.0001963705643889941,
|
| 198 |
+
"loss": 1.7575,
|
| 199 |
+
"step": 26
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.27411167512690354,
|
| 203 |
+
"grad_norm": 0.5604164004325867,
|
| 204 |
+
"learning_rate": 0.00019590592479012023,
|
| 205 |
+
"loss": 1.6815,
|
| 206 |
+
"step": 27
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.28426395939086296,
|
| 210 |
+
"grad_norm": 0.7223322987556458,
|
| 211 |
+
"learning_rate": 0.00019541392564000488,
|
| 212 |
+
"loss": 1.6213,
|
| 213 |
+
"step": 28
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.29441624365482233,
|
| 217 |
+
"grad_norm": 0.5081471800804138,
|
| 218 |
+
"learning_rate": 0.00019489470729364692,
|
| 219 |
+
"loss": 1.5935,
|
| 220 |
+
"step": 29
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.30456852791878175,
|
| 224 |
+
"grad_norm": 0.5000993013381958,
|
| 225 |
+
"learning_rate": 0.00019434841787099803,
|
| 226 |
+
"loss": 1.6237,
|
| 227 |
+
"step": 30
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.3147208121827411,
|
| 231 |
+
"grad_norm": 0.45925211906433105,
|
| 232 |
+
"learning_rate": 0.00019377521321470805,
|
| 233 |
+
"loss": 1.6201,
|
| 234 |
+
"step": 31
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.3248730964467005,
|
| 238 |
+
"grad_norm": 0.38572826981544495,
|
| 239 |
+
"learning_rate": 0.00019317525684566685,
|
| 240 |
+
"loss": 1.4805,
|
| 241 |
+
"step": 32
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.3350253807106599,
|
| 245 |
+
"grad_norm": 0.28524091839790344,
|
| 246 |
+
"learning_rate": 0.00019254871991635598,
|
| 247 |
+
"loss": 1.5985,
|
| 248 |
+
"step": 33
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.34517766497461927,
|
| 252 |
+
"grad_norm": 0.3277890980243683,
|
| 253 |
+
"learning_rate": 0.00019189578116202307,
|
| 254 |
+
"loss": 1.4994,
|
| 255 |
+
"step": 34
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.3553299492385787,
|
| 259 |
+
"grad_norm": 0.3320370018482208,
|
| 260 |
+
"learning_rate": 0.00019121662684969335,
|
| 261 |
+
"loss": 1.5039,
|
| 262 |
+
"step": 35
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.36548223350253806,
|
| 266 |
+
"grad_norm": 0.2798719108104706,
|
| 267 |
+
"learning_rate": 0.00019051145072503215,
|
| 268 |
+
"loss": 1.4997,
|
| 269 |
+
"step": 36
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.3756345177664975,
|
| 273 |
+
"grad_norm": 1.7497050762176514,
|
| 274 |
+
"learning_rate": 0.00018978045395707418,
|
| 275 |
+
"loss": 1.5465,
|
| 276 |
+
"step": 37
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.38578680203045684,
|
| 280 |
+
"grad_norm": 0.27379170060157776,
|
| 281 |
+
"learning_rate": 0.00018902384508083517,
|
| 282 |
+
"loss": 1.4846,
|
| 283 |
+
"step": 38
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.39593908629441626,
|
| 287 |
+
"grad_norm": 0.36681699752807617,
|
| 288 |
+
"learning_rate": 0.00018824183993782192,
|
| 289 |
+
"loss": 1.4154,
|
| 290 |
+
"step": 39
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.40609137055837563,
|
| 294 |
+
"grad_norm": 0.45136329531669617,
|
| 295 |
+
"learning_rate": 0.00018743466161445823,
|
| 296 |
+
"loss": 1.3928,
|
| 297 |
+
"step": 40
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.41624365482233505,
|
| 301 |
+
"grad_norm": 0.27879664301872253,
|
| 302 |
+
"learning_rate": 0.00018660254037844388,
|
| 303 |
+
"loss": 1.5119,
|
| 304 |
+
"step": 41
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.4263959390862944,
|
| 308 |
+
"grad_norm": 0.29230332374572754,
|
| 309 |
+
"learning_rate": 0.0001857457136130651,
|
| 310 |
+
"loss": 1.5095,
|
| 311 |
+
"step": 42
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.4365482233502538,
|
| 315 |
+
"grad_norm": 0.2731008231639862,
|
| 316 |
+
"learning_rate": 0.00018486442574947511,
|
| 317 |
+
"loss": 1.4672,
|
| 318 |
+
"step": 43
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.4467005076142132,
|
| 322 |
+
"grad_norm": 0.23685932159423828,
|
| 323 |
+
"learning_rate": 0.00018395892819696389,
|
| 324 |
+
"loss": 1.4173,
|
| 325 |
+
"step": 44
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.45685279187817257,
|
| 329 |
+
"grad_norm": 0.2703058421611786,
|
| 330 |
+
"learning_rate": 0.00018302947927123766,
|
| 331 |
+
"loss": 1.4088,
|
| 332 |
+
"step": 45
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.467005076142132,
|
| 336 |
+
"grad_norm": 1.65743887424469,
|
| 337 |
+
"learning_rate": 0.00018207634412072764,
|
| 338 |
+
"loss": 1.4672,
|
| 339 |
+
"step": 46
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.47715736040609136,
|
| 343 |
+
"grad_norm": 0.21287347376346588,
|
| 344 |
+
"learning_rate": 0.00018109979465095013,
|
| 345 |
+
"loss": 1.3975,
|
| 346 |
+
"step": 47
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.4873096446700508,
|
| 350 |
+
"grad_norm": 0.3460160791873932,
|
| 351 |
+
"learning_rate": 0.00018010010944693848,
|
| 352 |
+
"loss": 1.4501,
|
| 353 |
+
"step": 48
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.49746192893401014,
|
| 357 |
+
"grad_norm": 0.4228818714618683,
|
| 358 |
+
"learning_rate": 0.00017907757369376985,
|
| 359 |
+
"loss": 1.4632,
|
| 360 |
+
"step": 49
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.5076142131979695,
|
| 364 |
+
"grad_norm": 0.46471402049064636,
|
| 365 |
+
"learning_rate": 0.0001780324790952092,
|
| 366 |
+
"loss": 1.3696,
|
| 367 |
+
"step": 50
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.5177664974619289,
|
| 371 |
+
"grad_norm": 0.35602033138275146,
|
| 372 |
+
"learning_rate": 0.00017696512379049325,
|
| 373 |
+
"loss": 1.4096,
|
| 374 |
+
"step": 51
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.5279187817258884,
|
| 378 |
+
"grad_norm": 0.2879682779312134,
|
| 379 |
+
"learning_rate": 0.0001758758122692791,
|
| 380 |
+
"loss": 1.337,
|
| 381 |
+
"step": 52
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.5380710659898477,
|
| 385 |
+
"grad_norm": 0.1947374939918518,
|
| 386 |
+
"learning_rate": 0.00017476485528478093,
|
| 387 |
+
"loss": 1.3815,
|
| 388 |
+
"step": 53
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.5482233502538071,
|
| 392 |
+
"grad_norm": 0.22819018363952637,
|
| 393 |
+
"learning_rate": 0.00017363256976511972,
|
| 394 |
+
"loss": 1.4021,
|
| 395 |
+
"step": 54
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.5583756345177665,
|
| 399 |
+
"grad_norm": 0.19164641201496124,
|
| 400 |
+
"learning_rate": 0.000172479278722912,
|
| 401 |
+
"loss": 1.3899,
|
| 402 |
+
"step": 55
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.5685279187817259,
|
| 406 |
+
"grad_norm": 0.5477288961410522,
|
| 407 |
+
"learning_rate": 0.00017130531116312203,
|
| 408 |
+
"loss": 1.4089,
|
| 409 |
+
"step": 56
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.5786802030456852,
|
| 413 |
+
"grad_norm": 0.6282036900520325,
|
| 414 |
+
"learning_rate": 0.0001701110019892053,
|
| 415 |
+
"loss": 1.3983,
|
| 416 |
+
"step": 57
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.5888324873096447,
|
| 420 |
+
"grad_norm": 0.5962779521942139,
|
| 421 |
+
"learning_rate": 0.00016889669190756868,
|
| 422 |
+
"loss": 1.3126,
|
| 423 |
+
"step": 58
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.5989847715736041,
|
| 427 |
+
"grad_norm": 0.39695534110069275,
|
| 428 |
+
"learning_rate": 0.00016766272733037576,
|
| 429 |
+
"loss": 1.3693,
|
| 430 |
+
"step": 59
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.6091370558375635,
|
| 434 |
+
"grad_norm": 0.2737330198287964,
|
| 435 |
+
"learning_rate": 0.00016640946027672392,
|
| 436 |
+
"loss": 1.4286,
|
| 437 |
+
"step": 60
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 0.6192893401015228,
|
| 441 |
+
"grad_norm": 0.34324145317077637,
|
| 442 |
+
"learning_rate": 0.00016513724827222227,
|
| 443 |
+
"loss": 1.3363,
|
| 444 |
+
"step": 61
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.6294416243654822,
|
| 448 |
+
"grad_norm": 0.4945085942745209,
|
| 449 |
+
"learning_rate": 0.00016384645424699835,
|
| 450 |
+
"loss": 1.4388,
|
| 451 |
+
"step": 62
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 0.6395939086294417,
|
| 455 |
+
"grad_norm": 0.3939533829689026,
|
| 456 |
+
"learning_rate": 0.00016253744643216368,
|
| 457 |
+
"loss": 1.325,
|
| 458 |
+
"step": 63
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.649746192893401,
|
| 462 |
+
"grad_norm": 0.3593675196170807,
|
| 463 |
+
"learning_rate": 0.0001612105982547663,
|
| 464 |
+
"loss": 1.353,
|
| 465 |
+
"step": 64
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.6598984771573604,
|
| 469 |
+
"grad_norm": 0.3457062244415283,
|
| 470 |
+
"learning_rate": 0.0001598662882312615,
|
| 471 |
+
"loss": 1.3119,
|
| 472 |
+
"step": 65
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 0.6700507614213198,
|
| 476 |
+
"grad_norm": 0.22607868909835815,
|
| 477 |
+
"learning_rate": 0.00015850489985953076,
|
| 478 |
+
"loss": 1.3281,
|
| 479 |
+
"step": 66
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 0.6802030456852792,
|
| 483 |
+
"grad_norm": 0.1937730461359024,
|
| 484 |
+
"learning_rate": 0.00015712682150947923,
|
| 485 |
+
"loss": 1.3061,
|
| 486 |
+
"step": 67
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 0.6903553299492385,
|
| 490 |
+
"grad_norm": 0.19334916770458221,
|
| 491 |
+
"learning_rate": 0.00015573244631224365,
|
| 492 |
+
"loss": 1.2995,
|
| 493 |
+
"step": 68
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 0.700507614213198,
|
| 497 |
+
"grad_norm": 0.43978920578956604,
|
| 498 |
+
"learning_rate": 0.0001543221720480419,
|
| 499 |
+
"loss": 1.3196,
|
| 500 |
+
"step": 69
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 0.7106598984771574,
|
| 504 |
+
"grad_norm": 0.20429864525794983,
|
| 505 |
+
"learning_rate": 0.00015289640103269625,
|
| 506 |
+
"loss": 1.3428,
|
| 507 |
+
"step": 70
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.7208121827411168,
|
| 511 |
+
"grad_norm": 0.2042793482542038,
|
| 512 |
+
"learning_rate": 0.0001514555400028629,
|
| 513 |
+
"loss": 1.2717,
|
| 514 |
+
"step": 71
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 0.7309644670050761,
|
| 518 |
+
"grad_norm": 0.2089298814535141,
|
| 519 |
+
"learning_rate": 0.00015000000000000001,
|
| 520 |
+
"loss": 1.2823,
|
| 521 |
+
"step": 72
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 0.7411167512690355,
|
| 525 |
+
"grad_norm": 0.29447218775749207,
|
| 526 |
+
"learning_rate": 0.00014853019625310813,
|
| 527 |
+
"loss": 1.2596,
|
| 528 |
+
"step": 73
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 0.751269035532995,
|
| 532 |
+
"grad_norm": 0.20766524970531464,
|
| 533 |
+
"learning_rate": 0.0001470465480602756,
|
| 534 |
+
"loss": 1.3421,
|
| 535 |
+
"step": 74
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 0.7614213197969543,
|
| 539 |
+
"grad_norm": 0.19240014255046844,
|
| 540 |
+
"learning_rate": 0.0001455494786690634,
|
| 541 |
+
"loss": 1.3871,
|
| 542 |
+
"step": 75
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 0.7715736040609137,
|
| 546 |
+
"grad_norm": 0.16677537560462952,
|
| 547 |
+
"learning_rate": 0.00014403941515576344,
|
| 548 |
+
"loss": 1.2507,
|
| 549 |
+
"step": 76
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.7817258883248731,
|
| 553 |
+
"grad_norm": 0.1933940052986145,
|
| 554 |
+
"learning_rate": 0.00014251678830356408,
|
| 555 |
+
"loss": 1.2792,
|
| 556 |
+
"step": 77
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 0.7918781725888325,
|
| 560 |
+
"grad_norm": 0.19050206243991852,
|
| 561 |
+
"learning_rate": 0.00014098203247965875,
|
| 562 |
+
"loss": 1.3017,
|
| 563 |
+
"step": 78
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 0.8020304568527918,
|
| 567 |
+
"grad_norm": 0.25748810172080994,
|
| 568 |
+
"learning_rate": 0.00013943558551133186,
|
| 569 |
+
"loss": 1.2879,
|
| 570 |
+
"step": 79
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 0.8121827411167513,
|
| 574 |
+
"grad_norm": 0.2314893752336502,
|
| 575 |
+
"learning_rate": 0.0001378778885610576,
|
| 576 |
+
"loss": 1.3692,
|
| 577 |
+
"step": 80
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 0.8223350253807107,
|
| 581 |
+
"grad_norm": 0.20771433413028717,
|
| 582 |
+
"learning_rate": 0.00013630938600064747,
|
| 583 |
+
"loss": 1.3268,
|
| 584 |
+
"step": 81
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 0.8324873096446701,
|
| 588 |
+
"grad_norm": 0.18968452513217926,
|
| 589 |
+
"learning_rate": 0.00013473052528448201,
|
| 590 |
+
"loss": 1.2663,
|
| 591 |
+
"step": 82
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 0.8426395939086294,
|
| 595 |
+
"grad_norm": 0.1978602409362793,
|
| 596 |
+
"learning_rate": 0.0001331417568218636,
|
| 597 |
+
"loss": 1.2968,
|
| 598 |
+
"step": 83
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 0.8527918781725888,
|
| 602 |
+
"grad_norm": 0.9941853284835815,
|
| 603 |
+
"learning_rate": 0.00013154353384852558,
|
| 604 |
+
"loss": 1.3187,
|
| 605 |
+
"step": 84
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 0.8629441624365483,
|
| 609 |
+
"grad_norm": 0.18706466257572174,
|
| 610 |
+
"learning_rate": 0.00012993631229733582,
|
| 611 |
+
"loss": 1.2808,
|
| 612 |
+
"step": 85
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 0.8730964467005076,
|
| 616 |
+
"grad_norm": 0.18098409473896027,
|
| 617 |
+
"learning_rate": 0.00012832055066823038,
|
| 618 |
+
"loss": 1.2246,
|
| 619 |
+
"step": 86
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 0.883248730964467,
|
| 623 |
+
"grad_norm": 0.22270160913467407,
|
| 624 |
+
"learning_rate": 0.00012669670989741517,
|
| 625 |
+
"loss": 1.3028,
|
| 626 |
+
"step": 87
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 0.8934010152284264,
|
| 630 |
+
"grad_norm": 0.25465860962867737,
|
| 631 |
+
"learning_rate": 0.00012506525322587207,
|
| 632 |
+
"loss": 1.347,
|
| 633 |
+
"step": 88
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 0.9035532994923858,
|
| 637 |
+
"grad_norm": 0.23076751828193665,
|
| 638 |
+
"learning_rate": 0.00012342664606720822,
|
| 639 |
+
"loss": 1.3099,
|
| 640 |
+
"step": 89
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 0.9137055837563451,
|
| 644 |
+
"grad_norm": 0.19831228256225586,
|
| 645 |
+
"learning_rate": 0.00012178135587488515,
|
| 646 |
+
"loss": 1.278,
|
| 647 |
+
"step": 90
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 0.9238578680203046,
|
| 651 |
+
"grad_norm": 0.22052858769893646,
|
| 652 |
+
"learning_rate": 0.00012012985200886602,
|
| 653 |
+
"loss": 1.2165,
|
| 654 |
+
"step": 91
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 0.934010152284264,
|
| 658 |
+
"grad_norm": 0.18730390071868896,
|
| 659 |
+
"learning_rate": 0.00011847260560171896,
|
| 660 |
+
"loss": 1.2814,
|
| 661 |
+
"step": 92
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 0.9441624365482234,
|
| 665 |
+
"grad_norm": 0.16983264684677124,
|
| 666 |
+
"learning_rate": 0.00011681008942421483,
|
| 667 |
+
"loss": 1.2235,
|
| 668 |
+
"step": 93
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 0.9543147208121827,
|
| 672 |
+
"grad_norm": 0.17806044220924377,
|
| 673 |
+
"learning_rate": 0.00011514277775045768,
|
| 674 |
+
"loss": 1.1867,
|
| 675 |
+
"step": 94
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 0.9644670050761421,
|
| 679 |
+
"grad_norm": 0.1574580818414688,
|
| 680 |
+
"learning_rate": 0.00011347114622258612,
|
| 681 |
+
"loss": 1.2718,
|
| 682 |
+
"step": 95
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 0.9746192893401016,
|
| 686 |
+
"grad_norm": 0.15895454585552216,
|
| 687 |
+
"learning_rate": 0.00011179567171508463,
|
| 688 |
+
"loss": 1.245,
|
| 689 |
+
"step": 96
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 0.9847715736040609,
|
| 693 |
+
"grad_norm": 0.22224721312522888,
|
| 694 |
+
"learning_rate": 0.00011011683219874323,
|
| 695 |
+
"loss": 1.2945,
|
| 696 |
+
"step": 97
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 0.9949238578680203,
|
| 700 |
+
"grad_norm": 0.16613103449344635,
|
| 701 |
+
"learning_rate": 0.00010843510660430447,
|
| 702 |
+
"loss": 1.3054,
|
| 703 |
+
"step": 98
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 0.9949238578680203,
|
| 707 |
+
"eval_loss": 1.249497413635254,
|
| 708 |
+
"eval_runtime": 58.5386,
|
| 709 |
+
"eval_samples_per_second": 10.079,
|
| 710 |
+
"eval_steps_per_second": 1.264,
|
| 711 |
+
"step": 98
|
| 712 |
+
}
|
| 713 |
+
],
|
| 714 |
+
"logging_steps": 1,
|
| 715 |
+
"max_steps": 196,
|
| 716 |
+
"num_input_tokens_seen": 0,
|
| 717 |
+
"num_train_epochs": 2,
|
| 718 |
+
"save_steps": 98,
|
| 719 |
+
"stateful_callbacks": {
|
| 720 |
+
"TrainerControl": {
|
| 721 |
+
"args": {
|
| 722 |
+
"should_epoch_stop": false,
|
| 723 |
+
"should_evaluate": false,
|
| 724 |
+
"should_log": false,
|
| 725 |
+
"should_save": true,
|
| 726 |
+
"should_training_stop": false
|
| 727 |
+
},
|
| 728 |
+
"attributes": {}
|
| 729 |
+
}
|
| 730 |
+
},
|
| 731 |
+
"total_flos": 5.153973189130322e+17,
|
| 732 |
+
"train_batch_size": 2,
|
| 733 |
+
"trial_name": null,
|
| 734 |
+
"trial_params": null
|
| 735 |
+
}
|
checkpoint-98/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ebabd7fe1a216aadf93e2b9106041cfaee52bf0b7322ca74f94d144ee0af1908
|
| 3 |
+
size 6200
|