Upload 13 files
Browse files- README.md +202 -0
- adapter_config.json +37 -0
- adapter_model.safetensors +3 -0
- added_tokens.json +19 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +65 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +194 -0
- trainer_state.json +1723 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: epfl-llm/meditron-7b
|
| 3 |
+
library_name: peft
|
| 4 |
+
---
|
| 5 |
+
|
| 6 |
+
# Model Card for Model ID
|
| 7 |
+
|
| 8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 9 |
+
|
| 10 |
+
|
| 11 |
+
|
| 12 |
+
## Model Details
|
| 13 |
+
|
| 14 |
+
### Model Description
|
| 15 |
+
|
| 16 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
- **Developed by:** [More Information Needed]
|
| 21 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 22 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 23 |
+
- **Model type:** [More Information Needed]
|
| 24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 25 |
+
- **License:** [More Information Needed]
|
| 26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 27 |
+
|
| 28 |
+
### Model Sources [optional]
|
| 29 |
+
|
| 30 |
+
<!-- Provide the basic links for the model. -->
|
| 31 |
+
|
| 32 |
+
- **Repository:** [More Information Needed]
|
| 33 |
+
- **Paper [optional]:** [More Information Needed]
|
| 34 |
+
- **Demo [optional]:** [More Information Needed]
|
| 35 |
+
|
| 36 |
+
## Uses
|
| 37 |
+
|
| 38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 39 |
+
|
| 40 |
+
### Direct Use
|
| 41 |
+
|
| 42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 43 |
+
|
| 44 |
+
[More Information Needed]
|
| 45 |
+
|
| 46 |
+
### Downstream Use [optional]
|
| 47 |
+
|
| 48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 49 |
+
|
| 50 |
+
[More Information Needed]
|
| 51 |
+
|
| 52 |
+
### Out-of-Scope Use
|
| 53 |
+
|
| 54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 55 |
+
|
| 56 |
+
[More Information Needed]
|
| 57 |
+
|
| 58 |
+
## Bias, Risks, and Limitations
|
| 59 |
+
|
| 60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 61 |
+
|
| 62 |
+
[More Information Needed]
|
| 63 |
+
|
| 64 |
+
### Recommendations
|
| 65 |
+
|
| 66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 67 |
+
|
| 68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 69 |
+
|
| 70 |
+
## How to Get Started with the Model
|
| 71 |
+
|
| 72 |
+
Use the code below to get started with the model.
|
| 73 |
+
|
| 74 |
+
[More Information Needed]
|
| 75 |
+
|
| 76 |
+
## Training Details
|
| 77 |
+
|
| 78 |
+
### Training Data
|
| 79 |
+
|
| 80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 81 |
+
|
| 82 |
+
[More Information Needed]
|
| 83 |
+
|
| 84 |
+
### Training Procedure
|
| 85 |
+
|
| 86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 87 |
+
|
| 88 |
+
#### Preprocessing [optional]
|
| 89 |
+
|
| 90 |
+
[More Information Needed]
|
| 91 |
+
|
| 92 |
+
|
| 93 |
+
#### Training Hyperparameters
|
| 94 |
+
|
| 95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 96 |
+
|
| 97 |
+
#### Speeds, Sizes, Times [optional]
|
| 98 |
+
|
| 99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 100 |
+
|
| 101 |
+
[More Information Needed]
|
| 102 |
+
|
| 103 |
+
## Evaluation
|
| 104 |
+
|
| 105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 106 |
+
|
| 107 |
+
### Testing Data, Factors & Metrics
|
| 108 |
+
|
| 109 |
+
#### Testing Data
|
| 110 |
+
|
| 111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 112 |
+
|
| 113 |
+
[More Information Needed]
|
| 114 |
+
|
| 115 |
+
#### Factors
|
| 116 |
+
|
| 117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 118 |
+
|
| 119 |
+
[More Information Needed]
|
| 120 |
+
|
| 121 |
+
#### Metrics
|
| 122 |
+
|
| 123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 124 |
+
|
| 125 |
+
[More Information Needed]
|
| 126 |
+
|
| 127 |
+
### Results
|
| 128 |
+
|
| 129 |
+
[More Information Needed]
|
| 130 |
+
|
| 131 |
+
#### Summary
|
| 132 |
+
|
| 133 |
+
|
| 134 |
+
|
| 135 |
+
## Model Examination [optional]
|
| 136 |
+
|
| 137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 138 |
+
|
| 139 |
+
[More Information Needed]
|
| 140 |
+
|
| 141 |
+
## Environmental Impact
|
| 142 |
+
|
| 143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 144 |
+
|
| 145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
| 146 |
+
|
| 147 |
+
- **Hardware Type:** [More Information Needed]
|
| 148 |
+
- **Hours used:** [More Information Needed]
|
| 149 |
+
- **Cloud Provider:** [More Information Needed]
|
| 150 |
+
- **Compute Region:** [More Information Needed]
|
| 151 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 152 |
+
|
| 153 |
+
## Technical Specifications [optional]
|
| 154 |
+
|
| 155 |
+
### Model Architecture and Objective
|
| 156 |
+
|
| 157 |
+
[More Information Needed]
|
| 158 |
+
|
| 159 |
+
### Compute Infrastructure
|
| 160 |
+
|
| 161 |
+
[More Information Needed]
|
| 162 |
+
|
| 163 |
+
#### Hardware
|
| 164 |
+
|
| 165 |
+
[More Information Needed]
|
| 166 |
+
|
| 167 |
+
#### Software
|
| 168 |
+
|
| 169 |
+
[More Information Needed]
|
| 170 |
+
|
| 171 |
+
## Citation [optional]
|
| 172 |
+
|
| 173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 174 |
+
|
| 175 |
+
**BibTeX:**
|
| 176 |
+
|
| 177 |
+
[More Information Needed]
|
| 178 |
+
|
| 179 |
+
**APA:**
|
| 180 |
+
|
| 181 |
+
[More Information Needed]
|
| 182 |
+
|
| 183 |
+
## Glossary [optional]
|
| 184 |
+
|
| 185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 186 |
+
|
| 187 |
+
[More Information Needed]
|
| 188 |
+
|
| 189 |
+
## More Information [optional]
|
| 190 |
+
|
| 191 |
+
[More Information Needed]
|
| 192 |
+
|
| 193 |
+
## Model Card Authors [optional]
|
| 194 |
+
|
| 195 |
+
[More Information Needed]
|
| 196 |
+
|
| 197 |
+
## Model Card Contact
|
| 198 |
+
|
| 199 |
+
[More Information Needed]
|
| 200 |
+
### Framework versions
|
| 201 |
+
|
| 202 |
+
- PEFT 0.12.0
|
adapter_config.json
ADDED
|
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "epfl-llm/meditron-7b",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": false,
|
| 7 |
+
"inference_mode": true,
|
| 8 |
+
"init_lora_weights": true,
|
| 9 |
+
"layer_replication": null,
|
| 10 |
+
"layers_pattern": null,
|
| 11 |
+
"layers_to_transform": null,
|
| 12 |
+
"loftq_config": {},
|
| 13 |
+
"lora_alpha": 32,
|
| 14 |
+
"lora_dropout": 0.05,
|
| 15 |
+
"megatron_config": null,
|
| 16 |
+
"megatron_core": "megatron.core",
|
| 17 |
+
"modules_to_save": [
|
| 18 |
+
"classifier",
|
| 19 |
+
"score"
|
| 20 |
+
],
|
| 21 |
+
"peft_type": "LORA",
|
| 22 |
+
"r": 64,
|
| 23 |
+
"rank_pattern": {},
|
| 24 |
+
"revision": null,
|
| 25 |
+
"target_modules": [
|
| 26 |
+
"v_proj",
|
| 27 |
+
"gate_proj",
|
| 28 |
+
"up_proj",
|
| 29 |
+
"q_proj",
|
| 30 |
+
"down_proj",
|
| 31 |
+
"o_proj",
|
| 32 |
+
"k_proj"
|
| 33 |
+
],
|
| 34 |
+
"task_type": "SEQ_CLS",
|
| 35 |
+
"use_dora": false,
|
| 36 |
+
"use_rslora": false
|
| 37 |
+
}
|
adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b3ebd93756fc04d1337ab4736705b05cbba9ae8ea698b3d9355e2a57b3070ef2
|
| 3 |
+
size 639724744
|
added_tokens.json
ADDED
|
@@ -0,0 +1,19 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<CLS>": 32000,
|
| 3 |
+
"<EOD>": 32002,
|
| 4 |
+
"<MASK>": 32003,
|
| 5 |
+
"<PAD>": 32004,
|
| 6 |
+
"<SEP>": 32001,
|
| 7 |
+
"[/bib]": 32010,
|
| 8 |
+
"[/bib_ref]": 32006,
|
| 9 |
+
"[/fig]": 32012,
|
| 10 |
+
"[/fig_ref]": 32008,
|
| 11 |
+
"[/formula]": 32016,
|
| 12 |
+
"[/table]": 32014,
|
| 13 |
+
"[bib]": 32009,
|
| 14 |
+
"[bib_ref]": 32005,
|
| 15 |
+
"[fig]": 32011,
|
| 16 |
+
"[fig_ref]": 32007,
|
| 17 |
+
"[formula]": 32015,
|
| 18 |
+
"[table]": 32013
|
| 19 |
+
}
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bc8733332725c8a52c30f4262360e5af5942af62891c1b06352f031fcbc200e0
|
| 3 |
+
size 1279707477
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5337191b069a9044ad096e7ff2dac6ab28e3f47991b36bcdc874c86832e0f63b
|
| 3 |
+
size 14244
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e05f9a8349fff0b24c041eada6afbf1be8506f5e0fe2776c4416d7d8e1183bfa
|
| 3 |
+
size 1064
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,65 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"[bib_ref]",
|
| 4 |
+
"[/bib_ref]",
|
| 5 |
+
"[fig_ref]",
|
| 6 |
+
"[/fig_ref]",
|
| 7 |
+
"[bib]",
|
| 8 |
+
"[/bib]",
|
| 9 |
+
"[fig]",
|
| 10 |
+
"[/fig]",
|
| 11 |
+
"[table]",
|
| 12 |
+
"[/table]",
|
| 13 |
+
"[formula]",
|
| 14 |
+
"[/formula]"
|
| 15 |
+
],
|
| 16 |
+
"bos_token": {
|
| 17 |
+
"content": "<s>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": true,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"cls_token": {
|
| 24 |
+
"content": "<CLS>",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"eos_token": {
|
| 31 |
+
"content": "</s>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": true,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
},
|
| 37 |
+
"mask_token": {
|
| 38 |
+
"content": "<MASK>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false
|
| 43 |
+
},
|
| 44 |
+
"pad_token": {
|
| 45 |
+
"content": "<PAD>",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": false,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false
|
| 50 |
+
},
|
| 51 |
+
"sep_token": {
|
| 52 |
+
"content": "<SEP>",
|
| 53 |
+
"lstrip": false,
|
| 54 |
+
"normalized": false,
|
| 55 |
+
"rstrip": false,
|
| 56 |
+
"single_word": false
|
| 57 |
+
},
|
| 58 |
+
"unk_token": {
|
| 59 |
+
"content": "<unk>",
|
| 60 |
+
"lstrip": false,
|
| 61 |
+
"normalized": true,
|
| 62 |
+
"rstrip": false,
|
| 63 |
+
"single_word": false
|
| 64 |
+
}
|
| 65 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
| 3 |
+
size 499723
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,194 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"add_prefix_space": null,
|
| 5 |
+
"added_tokens_decoder": {
|
| 6 |
+
"0": {
|
| 7 |
+
"content": "<unk>",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": true,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false,
|
| 12 |
+
"special": true
|
| 13 |
+
},
|
| 14 |
+
"1": {
|
| 15 |
+
"content": "<s>",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": true,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false,
|
| 20 |
+
"special": true
|
| 21 |
+
},
|
| 22 |
+
"2": {
|
| 23 |
+
"content": "</s>",
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"normalized": true,
|
| 26 |
+
"rstrip": false,
|
| 27 |
+
"single_word": false,
|
| 28 |
+
"special": true
|
| 29 |
+
},
|
| 30 |
+
"32000": {
|
| 31 |
+
"content": "<CLS>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false,
|
| 36 |
+
"special": true
|
| 37 |
+
},
|
| 38 |
+
"32001": {
|
| 39 |
+
"content": "<SEP>",
|
| 40 |
+
"lstrip": false,
|
| 41 |
+
"normalized": false,
|
| 42 |
+
"rstrip": false,
|
| 43 |
+
"single_word": false,
|
| 44 |
+
"special": true
|
| 45 |
+
},
|
| 46 |
+
"32002": {
|
| 47 |
+
"content": "<EOD>",
|
| 48 |
+
"lstrip": false,
|
| 49 |
+
"normalized": false,
|
| 50 |
+
"rstrip": false,
|
| 51 |
+
"single_word": false,
|
| 52 |
+
"special": true
|
| 53 |
+
},
|
| 54 |
+
"32003": {
|
| 55 |
+
"content": "<MASK>",
|
| 56 |
+
"lstrip": false,
|
| 57 |
+
"normalized": false,
|
| 58 |
+
"rstrip": false,
|
| 59 |
+
"single_word": false,
|
| 60 |
+
"special": true
|
| 61 |
+
},
|
| 62 |
+
"32004": {
|
| 63 |
+
"content": "<PAD>",
|
| 64 |
+
"lstrip": false,
|
| 65 |
+
"normalized": false,
|
| 66 |
+
"rstrip": false,
|
| 67 |
+
"single_word": false,
|
| 68 |
+
"special": true
|
| 69 |
+
},
|
| 70 |
+
"32005": {
|
| 71 |
+
"content": "[bib_ref]",
|
| 72 |
+
"lstrip": false,
|
| 73 |
+
"normalized": false,
|
| 74 |
+
"rstrip": false,
|
| 75 |
+
"single_word": false,
|
| 76 |
+
"special": true
|
| 77 |
+
},
|
| 78 |
+
"32006": {
|
| 79 |
+
"content": "[/bib_ref]",
|
| 80 |
+
"lstrip": false,
|
| 81 |
+
"normalized": false,
|
| 82 |
+
"rstrip": false,
|
| 83 |
+
"single_word": false,
|
| 84 |
+
"special": true
|
| 85 |
+
},
|
| 86 |
+
"32007": {
|
| 87 |
+
"content": "[fig_ref]",
|
| 88 |
+
"lstrip": false,
|
| 89 |
+
"normalized": false,
|
| 90 |
+
"rstrip": false,
|
| 91 |
+
"single_word": false,
|
| 92 |
+
"special": true
|
| 93 |
+
},
|
| 94 |
+
"32008": {
|
| 95 |
+
"content": "[/fig_ref]",
|
| 96 |
+
"lstrip": false,
|
| 97 |
+
"normalized": false,
|
| 98 |
+
"rstrip": false,
|
| 99 |
+
"single_word": false,
|
| 100 |
+
"special": true
|
| 101 |
+
},
|
| 102 |
+
"32009": {
|
| 103 |
+
"content": "[bib]",
|
| 104 |
+
"lstrip": false,
|
| 105 |
+
"normalized": false,
|
| 106 |
+
"rstrip": false,
|
| 107 |
+
"single_word": false,
|
| 108 |
+
"special": true
|
| 109 |
+
},
|
| 110 |
+
"32010": {
|
| 111 |
+
"content": "[/bib]",
|
| 112 |
+
"lstrip": false,
|
| 113 |
+
"normalized": false,
|
| 114 |
+
"rstrip": false,
|
| 115 |
+
"single_word": false,
|
| 116 |
+
"special": true
|
| 117 |
+
},
|
| 118 |
+
"32011": {
|
| 119 |
+
"content": "[fig]",
|
| 120 |
+
"lstrip": false,
|
| 121 |
+
"normalized": false,
|
| 122 |
+
"rstrip": false,
|
| 123 |
+
"single_word": false,
|
| 124 |
+
"special": true
|
| 125 |
+
},
|
| 126 |
+
"32012": {
|
| 127 |
+
"content": "[/fig]",
|
| 128 |
+
"lstrip": false,
|
| 129 |
+
"normalized": false,
|
| 130 |
+
"rstrip": false,
|
| 131 |
+
"single_word": false,
|
| 132 |
+
"special": true
|
| 133 |
+
},
|
| 134 |
+
"32013": {
|
| 135 |
+
"content": "[table]",
|
| 136 |
+
"lstrip": false,
|
| 137 |
+
"normalized": false,
|
| 138 |
+
"rstrip": false,
|
| 139 |
+
"single_word": false,
|
| 140 |
+
"special": true
|
| 141 |
+
},
|
| 142 |
+
"32014": {
|
| 143 |
+
"content": "[/table]",
|
| 144 |
+
"lstrip": false,
|
| 145 |
+
"normalized": false,
|
| 146 |
+
"rstrip": false,
|
| 147 |
+
"single_word": false,
|
| 148 |
+
"special": true
|
| 149 |
+
},
|
| 150 |
+
"32015": {
|
| 151 |
+
"content": "[formula]",
|
| 152 |
+
"lstrip": false,
|
| 153 |
+
"normalized": false,
|
| 154 |
+
"rstrip": false,
|
| 155 |
+
"single_word": false,
|
| 156 |
+
"special": true
|
| 157 |
+
},
|
| 158 |
+
"32016": {
|
| 159 |
+
"content": "[/formula]",
|
| 160 |
+
"lstrip": false,
|
| 161 |
+
"normalized": false,
|
| 162 |
+
"rstrip": false,
|
| 163 |
+
"single_word": false,
|
| 164 |
+
"special": true
|
| 165 |
+
}
|
| 166 |
+
},
|
| 167 |
+
"additional_special_tokens": [
|
| 168 |
+
"[bib_ref]",
|
| 169 |
+
"[/bib_ref]",
|
| 170 |
+
"[fig_ref]",
|
| 171 |
+
"[/fig_ref]",
|
| 172 |
+
"[bib]",
|
| 173 |
+
"[/bib]",
|
| 174 |
+
"[fig]",
|
| 175 |
+
"[/fig]",
|
| 176 |
+
"[table]",
|
| 177 |
+
"[/table]",
|
| 178 |
+
"[formula]",
|
| 179 |
+
"[/formula]"
|
| 180 |
+
],
|
| 181 |
+
"bos_token": "<s>",
|
| 182 |
+
"clean_up_tokenization_spaces": false,
|
| 183 |
+
"cls_token": "<CLS>",
|
| 184 |
+
"eos_token": "</s>",
|
| 185 |
+
"legacy": true,
|
| 186 |
+
"mask_token": "<MASK>",
|
| 187 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 188 |
+
"pad_token": "<PAD>",
|
| 189 |
+
"sep_token": "<SEP>",
|
| 190 |
+
"sp_model_kwargs": {},
|
| 191 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 192 |
+
"unk_token": "<unk>",
|
| 193 |
+
"use_default_system_prompt": false
|
| 194 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1723 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 1.104968547821045,
|
| 3 |
+
"best_model_checkpoint": "epoch_weights/checkpoint-78342",
|
| 4 |
+
"epoch": 3.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 117513,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.01276454519925455,
|
| 13 |
+
"grad_norm": 124.07389068603516,
|
| 14 |
+
"learning_rate": 1.9948941819202982e-05,
|
| 15 |
+
"loss": 1.6279,
|
| 16 |
+
"step": 500
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.0255290903985091,
|
| 20 |
+
"grad_norm": 128.66375732421875,
|
| 21 |
+
"learning_rate": 1.9897883638405966e-05,
|
| 22 |
+
"loss": 1.4381,
|
| 23 |
+
"step": 1000
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.03829363559776365,
|
| 27 |
+
"grad_norm": 0.37872114777565,
|
| 28 |
+
"learning_rate": 1.9846825457608946e-05,
|
| 29 |
+
"loss": 1.2973,
|
| 30 |
+
"step": 1500
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.0510581807970182,
|
| 34 |
+
"grad_norm": 50.04689025878906,
|
| 35 |
+
"learning_rate": 1.9795767276811927e-05,
|
| 36 |
+
"loss": 1.3153,
|
| 37 |
+
"step": 2000
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.06382272599627276,
|
| 41 |
+
"grad_norm": 121.96903991699219,
|
| 42 |
+
"learning_rate": 1.974470909601491e-05,
|
| 43 |
+
"loss": 1.3964,
|
| 44 |
+
"step": 2500
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.0765872711955273,
|
| 48 |
+
"grad_norm": 108.51911163330078,
|
| 49 |
+
"learning_rate": 1.969365091521789e-05,
|
| 50 |
+
"loss": 1.2638,
|
| 51 |
+
"step": 3000
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.08935181639478186,
|
| 55 |
+
"grad_norm": 0.2868095636367798,
|
| 56 |
+
"learning_rate": 1.9642592734420874e-05,
|
| 57 |
+
"loss": 1.223,
|
| 58 |
+
"step": 3500
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.1021163615940364,
|
| 62 |
+
"grad_norm": 0.06836055219173431,
|
| 63 |
+
"learning_rate": 1.9591534553623858e-05,
|
| 64 |
+
"loss": 1.2365,
|
| 65 |
+
"step": 4000
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.11488090679329095,
|
| 69 |
+
"grad_norm": 0.05994059517979622,
|
| 70 |
+
"learning_rate": 1.954047637282684e-05,
|
| 71 |
+
"loss": 1.2321,
|
| 72 |
+
"step": 4500
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.1276454519925455,
|
| 76 |
+
"grad_norm": 2.723158597946167,
|
| 77 |
+
"learning_rate": 1.948941819202982e-05,
|
| 78 |
+
"loss": 1.2502,
|
| 79 |
+
"step": 5000
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.14040999719180006,
|
| 83 |
+
"grad_norm": 0.1803564429283142,
|
| 84 |
+
"learning_rate": 1.9438360011232803e-05,
|
| 85 |
+
"loss": 1.1791,
|
| 86 |
+
"step": 5500
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.1531745423910546,
|
| 90 |
+
"grad_norm": 0.004028810653835535,
|
| 91 |
+
"learning_rate": 1.9387301830435783e-05,
|
| 92 |
+
"loss": 1.2433,
|
| 93 |
+
"step": 6000
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.16593908759030915,
|
| 97 |
+
"grad_norm": 15.455341339111328,
|
| 98 |
+
"learning_rate": 1.9336243649638764e-05,
|
| 99 |
+
"loss": 1.2551,
|
| 100 |
+
"step": 6500
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.17870363278956372,
|
| 104 |
+
"grad_norm": 92.5711441040039,
|
| 105 |
+
"learning_rate": 1.9285185468841747e-05,
|
| 106 |
+
"loss": 1.2383,
|
| 107 |
+
"step": 7000
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.19146817798881827,
|
| 111 |
+
"grad_norm": 0.015813980251550674,
|
| 112 |
+
"learning_rate": 1.9234127288044728e-05,
|
| 113 |
+
"loss": 1.2028,
|
| 114 |
+
"step": 7500
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.2042327231880728,
|
| 118 |
+
"grad_norm": 0.04976970702409744,
|
| 119 |
+
"learning_rate": 1.9183069107247708e-05,
|
| 120 |
+
"loss": 1.2494,
|
| 121 |
+
"step": 8000
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.21699726838732736,
|
| 125 |
+
"grad_norm": 79.4881820678711,
|
| 126 |
+
"learning_rate": 1.9132010926450692e-05,
|
| 127 |
+
"loss": 1.1732,
|
| 128 |
+
"step": 8500
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.2297618135865819,
|
| 132 |
+
"grad_norm": 0.12827420234680176,
|
| 133 |
+
"learning_rate": 1.9080952745653672e-05,
|
| 134 |
+
"loss": 1.3421,
|
| 135 |
+
"step": 9000
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.24252635878583645,
|
| 139 |
+
"grad_norm": 0.2911496162414551,
|
| 140 |
+
"learning_rate": 1.9029894564856656e-05,
|
| 141 |
+
"loss": 1.2083,
|
| 142 |
+
"step": 9500
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.255290903985091,
|
| 146 |
+
"grad_norm": 0.006654891651123762,
|
| 147 |
+
"learning_rate": 1.8978836384059636e-05,
|
| 148 |
+
"loss": 1.115,
|
| 149 |
+
"step": 10000
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.26805544918434554,
|
| 153 |
+
"grad_norm": 0.04584607109427452,
|
| 154 |
+
"learning_rate": 1.892777820326262e-05,
|
| 155 |
+
"loss": 1.203,
|
| 156 |
+
"step": 10500
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.2808199943836001,
|
| 160 |
+
"grad_norm": 0.026795102283358574,
|
| 161 |
+
"learning_rate": 1.8876720022465604e-05,
|
| 162 |
+
"loss": 1.2735,
|
| 163 |
+
"step": 11000
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.2935845395828547,
|
| 167 |
+
"grad_norm": 82.26731872558594,
|
| 168 |
+
"learning_rate": 1.8825661841668584e-05,
|
| 169 |
+
"loss": 1.3205,
|
| 170 |
+
"step": 11500
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.3063490847821092,
|
| 174 |
+
"grad_norm": 0.02986270561814308,
|
| 175 |
+
"learning_rate": 1.8774603660871565e-05,
|
| 176 |
+
"loss": 1.2024,
|
| 177 |
+
"step": 12000
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.3191136299813638,
|
| 181 |
+
"grad_norm": 0.17114710807800293,
|
| 182 |
+
"learning_rate": 1.872354548007455e-05,
|
| 183 |
+
"loss": 1.273,
|
| 184 |
+
"step": 12500
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.3318781751806183,
|
| 188 |
+
"grad_norm": 0.43191567063331604,
|
| 189 |
+
"learning_rate": 1.867248729927753e-05,
|
| 190 |
+
"loss": 1.2321,
|
| 191 |
+
"step": 13000
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.34464272037987287,
|
| 195 |
+
"grad_norm": 1.2378649711608887,
|
| 196 |
+
"learning_rate": 1.862142911848051e-05,
|
| 197 |
+
"loss": 1.3128,
|
| 198 |
+
"step": 13500
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.35740726557912744,
|
| 202 |
+
"grad_norm": 0.21141913533210754,
|
| 203 |
+
"learning_rate": 1.8570370937683493e-05,
|
| 204 |
+
"loss": 1.2247,
|
| 205 |
+
"step": 14000
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.37017181077838196,
|
| 209 |
+
"grad_norm": 0.11364568769931793,
|
| 210 |
+
"learning_rate": 1.8519312756886473e-05,
|
| 211 |
+
"loss": 1.2406,
|
| 212 |
+
"step": 14500
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.38293635597763653,
|
| 216 |
+
"grad_norm": 1.0514061450958252,
|
| 217 |
+
"learning_rate": 1.8468254576089454e-05,
|
| 218 |
+
"loss": 1.2086,
|
| 219 |
+
"step": 15000
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.39570090117689105,
|
| 223 |
+
"grad_norm": 0.561066210269928,
|
| 224 |
+
"learning_rate": 1.8417196395292437e-05,
|
| 225 |
+
"loss": 1.2823,
|
| 226 |
+
"step": 15500
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.4084654463761456,
|
| 230 |
+
"grad_norm": 0.23838554322719574,
|
| 231 |
+
"learning_rate": 1.8366138214495418e-05,
|
| 232 |
+
"loss": 1.163,
|
| 233 |
+
"step": 16000
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.42122999157540014,
|
| 237 |
+
"grad_norm": 0.18532218039035797,
|
| 238 |
+
"learning_rate": 1.83150800336984e-05,
|
| 239 |
+
"loss": 1.2661,
|
| 240 |
+
"step": 16500
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.4339945367746547,
|
| 244 |
+
"grad_norm": 0.7906472682952881,
|
| 245 |
+
"learning_rate": 1.8264021852901382e-05,
|
| 246 |
+
"loss": 1.1826,
|
| 247 |
+
"step": 17000
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.4467590819739093,
|
| 251 |
+
"grad_norm": 0.15492267906665802,
|
| 252 |
+
"learning_rate": 1.8212963672104366e-05,
|
| 253 |
+
"loss": 1.2583,
|
| 254 |
+
"step": 17500
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.4595236271731638,
|
| 258 |
+
"grad_norm": 66.59947204589844,
|
| 259 |
+
"learning_rate": 1.8161905491307346e-05,
|
| 260 |
+
"loss": 1.0828,
|
| 261 |
+
"step": 18000
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.4722881723724184,
|
| 265 |
+
"grad_norm": 0.062189556658267975,
|
| 266 |
+
"learning_rate": 1.811084731051033e-05,
|
| 267 |
+
"loss": 1.2617,
|
| 268 |
+
"step": 18500
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.4850527175716729,
|
| 272 |
+
"grad_norm": 0.4971618354320526,
|
| 273 |
+
"learning_rate": 1.805978912971331e-05,
|
| 274 |
+
"loss": 1.2473,
|
| 275 |
+
"step": 19000
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.49781726277092747,
|
| 279 |
+
"grad_norm": 0.08685887604951859,
|
| 280 |
+
"learning_rate": 1.800873094891629e-05,
|
| 281 |
+
"loss": 1.274,
|
| 282 |
+
"step": 19500
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.510581807970182,
|
| 286 |
+
"grad_norm": 0.006585211958736181,
|
| 287 |
+
"learning_rate": 1.7957672768119274e-05,
|
| 288 |
+
"loss": 1.1477,
|
| 289 |
+
"step": 20000
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.5233463531694366,
|
| 293 |
+
"grad_norm": 2.229275941848755,
|
| 294 |
+
"learning_rate": 1.7906614587322255e-05,
|
| 295 |
+
"loss": 1.1253,
|
| 296 |
+
"step": 20500
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.5361108983686911,
|
| 300 |
+
"grad_norm": 70.02924346923828,
|
| 301 |
+
"learning_rate": 1.7855556406525235e-05,
|
| 302 |
+
"loss": 1.2017,
|
| 303 |
+
"step": 21000
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.5488754435679457,
|
| 307 |
+
"grad_norm": 66.59735107421875,
|
| 308 |
+
"learning_rate": 1.780449822572822e-05,
|
| 309 |
+
"loss": 1.3485,
|
| 310 |
+
"step": 21500
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.5616399887672002,
|
| 314 |
+
"grad_norm": 0.5093948245048523,
|
| 315 |
+
"learning_rate": 1.77534400449312e-05,
|
| 316 |
+
"loss": 1.2104,
|
| 317 |
+
"step": 22000
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.5744045339664547,
|
| 321 |
+
"grad_norm": 0.16927452385425568,
|
| 322 |
+
"learning_rate": 1.7702381864134183e-05,
|
| 323 |
+
"loss": 1.2675,
|
| 324 |
+
"step": 22500
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.5871690791657094,
|
| 328 |
+
"grad_norm": 0.6897981762886047,
|
| 329 |
+
"learning_rate": 1.7651323683337164e-05,
|
| 330 |
+
"loss": 1.254,
|
| 331 |
+
"step": 23000
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.5999336243649639,
|
| 335 |
+
"grad_norm": 0.104646235704422,
|
| 336 |
+
"learning_rate": 1.7600265502540147e-05,
|
| 337 |
+
"loss": 1.0584,
|
| 338 |
+
"step": 23500
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.6126981695642184,
|
| 342 |
+
"grad_norm": 0.14023582637310028,
|
| 343 |
+
"learning_rate": 1.7549207321743128e-05,
|
| 344 |
+
"loss": 1.1129,
|
| 345 |
+
"step": 24000
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.6254627147634729,
|
| 349 |
+
"grad_norm": 0.023725107312202454,
|
| 350 |
+
"learning_rate": 1.749814914094611e-05,
|
| 351 |
+
"loss": 1.1688,
|
| 352 |
+
"step": 24500
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.6382272599627276,
|
| 356 |
+
"grad_norm": 0.12562257051467896,
|
| 357 |
+
"learning_rate": 1.7447090960149092e-05,
|
| 358 |
+
"loss": 1.3021,
|
| 359 |
+
"step": 25000
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.6509918051619821,
|
| 363 |
+
"grad_norm": 0.3559040129184723,
|
| 364 |
+
"learning_rate": 1.7396032779352072e-05,
|
| 365 |
+
"loss": 1.3639,
|
| 366 |
+
"step": 25500
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.6637563503612366,
|
| 370 |
+
"grad_norm": 0.40778619050979614,
|
| 371 |
+
"learning_rate": 1.7344974598555056e-05,
|
| 372 |
+
"loss": 1.2725,
|
| 373 |
+
"step": 26000
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.6765208955604912,
|
| 377 |
+
"grad_norm": 0.1941840797662735,
|
| 378 |
+
"learning_rate": 1.7293916417758036e-05,
|
| 379 |
+
"loss": 1.1994,
|
| 380 |
+
"step": 26500
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.6892854407597457,
|
| 384 |
+
"grad_norm": 97.33511352539062,
|
| 385 |
+
"learning_rate": 1.7242858236961017e-05,
|
| 386 |
+
"loss": 1.195,
|
| 387 |
+
"step": 27000
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.7020499859590003,
|
| 391 |
+
"grad_norm": 99.68802642822266,
|
| 392 |
+
"learning_rate": 1.7191800056164e-05,
|
| 393 |
+
"loss": 1.0833,
|
| 394 |
+
"step": 27500
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.7148145311582549,
|
| 398 |
+
"grad_norm": 96.7743148803711,
|
| 399 |
+
"learning_rate": 1.714074187536698e-05,
|
| 400 |
+
"loss": 1.1637,
|
| 401 |
+
"step": 28000
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.7275790763575094,
|
| 405 |
+
"grad_norm": 99.62881469726562,
|
| 406 |
+
"learning_rate": 1.708968369456996e-05,
|
| 407 |
+
"loss": 1.2237,
|
| 408 |
+
"step": 28500
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.7403436215567639,
|
| 412 |
+
"grad_norm": 0.7065278887748718,
|
| 413 |
+
"learning_rate": 1.7038625513772945e-05,
|
| 414 |
+
"loss": 1.1587,
|
| 415 |
+
"step": 29000
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.7531081667560184,
|
| 419 |
+
"grad_norm": 0.3432465195655823,
|
| 420 |
+
"learning_rate": 1.698756733297593e-05,
|
| 421 |
+
"loss": 1.2863,
|
| 422 |
+
"step": 29500
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.7658727119552731,
|
| 426 |
+
"grad_norm": 0.04037034511566162,
|
| 427 |
+
"learning_rate": 1.693650915217891e-05,
|
| 428 |
+
"loss": 1.1613,
|
| 429 |
+
"step": 30000
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.7786372571545276,
|
| 433 |
+
"grad_norm": 0.012942465953528881,
|
| 434 |
+
"learning_rate": 1.6885450971381893e-05,
|
| 435 |
+
"loss": 1.1705,
|
| 436 |
+
"step": 30500
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.7914018023537821,
|
| 440 |
+
"grad_norm": 0.06133579462766647,
|
| 441 |
+
"learning_rate": 1.6834392790584873e-05,
|
| 442 |
+
"loss": 1.1006,
|
| 443 |
+
"step": 31000
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.8041663475530367,
|
| 447 |
+
"grad_norm": 0.040928054600954056,
|
| 448 |
+
"learning_rate": 1.6783334609787854e-05,
|
| 449 |
+
"loss": 1.1462,
|
| 450 |
+
"step": 31500
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.8169308927522912,
|
| 454 |
+
"grad_norm": 0.5418524742126465,
|
| 455 |
+
"learning_rate": 1.6732276428990837e-05,
|
| 456 |
+
"loss": 1.121,
|
| 457 |
+
"step": 32000
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.8296954379515458,
|
| 461 |
+
"grad_norm": 0.5459625124931335,
|
| 462 |
+
"learning_rate": 1.6681218248193818e-05,
|
| 463 |
+
"loss": 1.1391,
|
| 464 |
+
"step": 32500
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.8424599831508003,
|
| 468 |
+
"grad_norm": 0.11072584986686707,
|
| 469 |
+
"learning_rate": 1.66301600673968e-05,
|
| 470 |
+
"loss": 1.0201,
|
| 471 |
+
"step": 33000
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.8552245283500549,
|
| 475 |
+
"grad_norm": 83.50057220458984,
|
| 476 |
+
"learning_rate": 1.6579101886599782e-05,
|
| 477 |
+
"loss": 1.2236,
|
| 478 |
+
"step": 33500
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 0.8679890735493094,
|
| 482 |
+
"grad_norm": 0.05394850671291351,
|
| 483 |
+
"learning_rate": 1.6528043705802762e-05,
|
| 484 |
+
"loss": 1.1969,
|
| 485 |
+
"step": 34000
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.880753618748564,
|
| 489 |
+
"grad_norm": 0.10764531046152115,
|
| 490 |
+
"learning_rate": 1.6476985525005746e-05,
|
| 491 |
+
"loss": 1.2367,
|
| 492 |
+
"step": 34500
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 0.8935181639478186,
|
| 496 |
+
"grad_norm": 0.4855539798736572,
|
| 497 |
+
"learning_rate": 1.6425927344208727e-05,
|
| 498 |
+
"loss": 1.1557,
|
| 499 |
+
"step": 35000
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.9062827091470731,
|
| 503 |
+
"grad_norm": 84.196533203125,
|
| 504 |
+
"learning_rate": 1.6374869163411707e-05,
|
| 505 |
+
"loss": 1.1508,
|
| 506 |
+
"step": 35500
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.9190472543463276,
|
| 510 |
+
"grad_norm": 0.011251543648540974,
|
| 511 |
+
"learning_rate": 1.632381098261469e-05,
|
| 512 |
+
"loss": 1.1501,
|
| 513 |
+
"step": 36000
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.9318117995455822,
|
| 517 |
+
"grad_norm": 0.34031379222869873,
|
| 518 |
+
"learning_rate": 1.6272752801817674e-05,
|
| 519 |
+
"loss": 1.0097,
|
| 520 |
+
"step": 36500
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 0.9445763447448368,
|
| 524 |
+
"grad_norm": 0.1333027482032776,
|
| 525 |
+
"learning_rate": 1.6221694621020655e-05,
|
| 526 |
+
"loss": 1.3426,
|
| 527 |
+
"step": 37000
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.9573408899440913,
|
| 531 |
+
"grad_norm": 45.01104736328125,
|
| 532 |
+
"learning_rate": 1.617063644022364e-05,
|
| 533 |
+
"loss": 1.0867,
|
| 534 |
+
"step": 37500
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.9701054351433458,
|
| 538 |
+
"grad_norm": 1.5684014558792114,
|
| 539 |
+
"learning_rate": 1.611957825942662e-05,
|
| 540 |
+
"loss": 1.2435,
|
| 541 |
+
"step": 38000
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.9828699803426004,
|
| 545 |
+
"grad_norm": 0.47411900758743286,
|
| 546 |
+
"learning_rate": 1.60685200786296e-05,
|
| 547 |
+
"loss": 1.1407,
|
| 548 |
+
"step": 38500
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 0.9956345255418549,
|
| 552 |
+
"grad_norm": 45.75678634643555,
|
| 553 |
+
"learning_rate": 1.6017461897832583e-05,
|
| 554 |
+
"loss": 1.1986,
|
| 555 |
+
"step": 39000
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 1.0,
|
| 559 |
+
"eval_accuracy": 0.7540599990639771,
|
| 560 |
+
"eval_f1": 0.7600566184192502,
|
| 561 |
+
"eval_loss": 1.1569325923919678,
|
| 562 |
+
"eval_precision": 0.743722634259673,
|
| 563 |
+
"eval_recall": 0.777124183006536,
|
| 564 |
+
"eval_runtime": 157732.0331,
|
| 565 |
+
"eval_samples_per_second": 0.135,
|
| 566 |
+
"eval_steps_per_second": 0.135,
|
| 567 |
+
"step": 39171
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 1.0083990707411095,
|
| 571 |
+
"grad_norm": 0.0804721936583519,
|
| 572 |
+
"learning_rate": 1.5966403717035563e-05,
|
| 573 |
+
"loss": 1.046,
|
| 574 |
+
"step": 39500
|
| 575 |
+
},
|
| 576 |
+
{
|
| 577 |
+
"epoch": 1.021163615940364,
|
| 578 |
+
"grad_norm": 17.048269271850586,
|
| 579 |
+
"learning_rate": 1.5915345536238544e-05,
|
| 580 |
+
"loss": 1.202,
|
| 581 |
+
"step": 40000
|
| 582 |
+
},
|
| 583 |
+
{
|
| 584 |
+
"epoch": 1.0339281611396185,
|
| 585 |
+
"grad_norm": 43.9289436340332,
|
| 586 |
+
"learning_rate": 1.5864287355441528e-05,
|
| 587 |
+
"loss": 1.107,
|
| 588 |
+
"step": 40500
|
| 589 |
+
},
|
| 590 |
+
{
|
| 591 |
+
"epoch": 1.0466927063388731,
|
| 592 |
+
"grad_norm": 43.42015075683594,
|
| 593 |
+
"learning_rate": 1.5813229174644508e-05,
|
| 594 |
+
"loss": 1.2023,
|
| 595 |
+
"step": 41000
|
| 596 |
+
},
|
| 597 |
+
{
|
| 598 |
+
"epoch": 1.0594572515381278,
|
| 599 |
+
"grad_norm": 0.013399166986346245,
|
| 600 |
+
"learning_rate": 1.576217099384749e-05,
|
| 601 |
+
"loss": 1.0662,
|
| 602 |
+
"step": 41500
|
| 603 |
+
},
|
| 604 |
+
{
|
| 605 |
+
"epoch": 1.0722217967373822,
|
| 606 |
+
"grad_norm": 0.06720153987407684,
|
| 607 |
+
"learning_rate": 1.5711112813050472e-05,
|
| 608 |
+
"loss": 1.1996,
|
| 609 |
+
"step": 42000
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 1.0849863419366368,
|
| 613 |
+
"grad_norm": 47.7587890625,
|
| 614 |
+
"learning_rate": 1.5660054632253453e-05,
|
| 615 |
+
"loss": 1.2023,
|
| 616 |
+
"step": 42500
|
| 617 |
+
},
|
| 618 |
+
{
|
| 619 |
+
"epoch": 1.0977508871358914,
|
| 620 |
+
"grad_norm": 0.09353866428136826,
|
| 621 |
+
"learning_rate": 1.5608996451456436e-05,
|
| 622 |
+
"loss": 1.1306,
|
| 623 |
+
"step": 43000
|
| 624 |
+
},
|
| 625 |
+
{
|
| 626 |
+
"epoch": 1.1105154323351458,
|
| 627 |
+
"grad_norm": 0.07377411425113678,
|
| 628 |
+
"learning_rate": 1.555793827065942e-05,
|
| 629 |
+
"loss": 1.0741,
|
| 630 |
+
"step": 43500
|
| 631 |
+
},
|
| 632 |
+
{
|
| 633 |
+
"epoch": 1.1232799775344005,
|
| 634 |
+
"grad_norm": 91.8946762084961,
|
| 635 |
+
"learning_rate": 1.55068800898624e-05,
|
| 636 |
+
"loss": 1.321,
|
| 637 |
+
"step": 44000
|
| 638 |
+
},
|
| 639 |
+
{
|
| 640 |
+
"epoch": 1.136044522733655,
|
| 641 |
+
"grad_norm": 0.09886912256479263,
|
| 642 |
+
"learning_rate": 1.545582190906538e-05,
|
| 643 |
+
"loss": 1.0535,
|
| 644 |
+
"step": 44500
|
| 645 |
+
},
|
| 646 |
+
{
|
| 647 |
+
"epoch": 1.1488090679329095,
|
| 648 |
+
"grad_norm": 0.30927518010139465,
|
| 649 |
+
"learning_rate": 1.5404763728268365e-05,
|
| 650 |
+
"loss": 1.1857,
|
| 651 |
+
"step": 45000
|
| 652 |
+
},
|
| 653 |
+
{
|
| 654 |
+
"epoch": 1.1615736131321641,
|
| 655 |
+
"grad_norm": 89.31499481201172,
|
| 656 |
+
"learning_rate": 1.5353705547471345e-05,
|
| 657 |
+
"loss": 1.1391,
|
| 658 |
+
"step": 45500
|
| 659 |
+
},
|
| 660 |
+
{
|
| 661 |
+
"epoch": 1.1743381583314187,
|
| 662 |
+
"grad_norm": 1.457594394683838,
|
| 663 |
+
"learning_rate": 1.5302647366674325e-05,
|
| 664 |
+
"loss": 1.0623,
|
| 665 |
+
"step": 46000
|
| 666 |
+
},
|
| 667 |
+
{
|
| 668 |
+
"epoch": 1.1871027035306732,
|
| 669 |
+
"grad_norm": 0.7686181664466858,
|
| 670 |
+
"learning_rate": 1.5251589185877309e-05,
|
| 671 |
+
"loss": 1.1916,
|
| 672 |
+
"step": 46500
|
| 673 |
+
},
|
| 674 |
+
{
|
| 675 |
+
"epoch": 1.1998672487299278,
|
| 676 |
+
"grad_norm": 0.17544373869895935,
|
| 677 |
+
"learning_rate": 1.520053100508029e-05,
|
| 678 |
+
"loss": 1.1964,
|
| 679 |
+
"step": 47000
|
| 680 |
+
},
|
| 681 |
+
{
|
| 682 |
+
"epoch": 1.2126317939291824,
|
| 683 |
+
"grad_norm": 42.57478713989258,
|
| 684 |
+
"learning_rate": 1.5149472824283272e-05,
|
| 685 |
+
"loss": 1.2117,
|
| 686 |
+
"step": 47500
|
| 687 |
+
},
|
| 688 |
+
{
|
| 689 |
+
"epoch": 1.2253963391284368,
|
| 690 |
+
"grad_norm": 0.03184300288558006,
|
| 691 |
+
"learning_rate": 1.5098414643486254e-05,
|
| 692 |
+
"loss": 1.1183,
|
| 693 |
+
"step": 48000
|
| 694 |
+
},
|
| 695 |
+
{
|
| 696 |
+
"epoch": 1.2381608843276914,
|
| 697 |
+
"grad_norm": 0.10931099206209183,
|
| 698 |
+
"learning_rate": 1.5047356462689236e-05,
|
| 699 |
+
"loss": 1.1356,
|
| 700 |
+
"step": 48500
|
| 701 |
+
},
|
| 702 |
+
{
|
| 703 |
+
"epoch": 1.250925429526946,
|
| 704 |
+
"grad_norm": 0.317095547914505,
|
| 705 |
+
"learning_rate": 1.4996298281892216e-05,
|
| 706 |
+
"loss": 1.2026,
|
| 707 |
+
"step": 49000
|
| 708 |
+
},
|
| 709 |
+
{
|
| 710 |
+
"epoch": 1.2636899747262005,
|
| 711 |
+
"grad_norm": 0.04404517263174057,
|
| 712 |
+
"learning_rate": 1.49452401010952e-05,
|
| 713 |
+
"loss": 1.1131,
|
| 714 |
+
"step": 49500
|
| 715 |
+
},
|
| 716 |
+
{
|
| 717 |
+
"epoch": 1.2764545199254551,
|
| 718 |
+
"grad_norm": 0.10865862667560577,
|
| 719 |
+
"learning_rate": 1.489418192029818e-05,
|
| 720 |
+
"loss": 1.0374,
|
| 721 |
+
"step": 50000
|
| 722 |
+
},
|
| 723 |
+
{
|
| 724 |
+
"epoch": 1.2892190651247097,
|
| 725 |
+
"grad_norm": 2.7427468299865723,
|
| 726 |
+
"learning_rate": 1.4843123739501162e-05,
|
| 727 |
+
"loss": 1.0323,
|
| 728 |
+
"step": 50500
|
| 729 |
+
},
|
| 730 |
+
{
|
| 731 |
+
"epoch": 1.3019836103239641,
|
| 732 |
+
"grad_norm": 0.09404811263084412,
|
| 733 |
+
"learning_rate": 1.4792065558704144e-05,
|
| 734 |
+
"loss": 1.2665,
|
| 735 |
+
"step": 51000
|
| 736 |
+
},
|
| 737 |
+
{
|
| 738 |
+
"epoch": 1.3147481555232188,
|
| 739 |
+
"grad_norm": 0.2893916964530945,
|
| 740 |
+
"learning_rate": 1.4741007377907126e-05,
|
| 741 |
+
"loss": 0.9735,
|
| 742 |
+
"step": 51500
|
| 743 |
+
},
|
| 744 |
+
{
|
| 745 |
+
"epoch": 1.3275127007224732,
|
| 746 |
+
"grad_norm": 0.07920054346323013,
|
| 747 |
+
"learning_rate": 1.4689949197110107e-05,
|
| 748 |
+
"loss": 1.0051,
|
| 749 |
+
"step": 52000
|
| 750 |
+
},
|
| 751 |
+
{
|
| 752 |
+
"epoch": 1.3402772459217278,
|
| 753 |
+
"grad_norm": 0.1930513083934784,
|
| 754 |
+
"learning_rate": 1.463889101631309e-05,
|
| 755 |
+
"loss": 1.1209,
|
| 756 |
+
"step": 52500
|
| 757 |
+
},
|
| 758 |
+
{
|
| 759 |
+
"epoch": 1.3530417911209824,
|
| 760 |
+
"grad_norm": 0.07992220669984818,
|
| 761 |
+
"learning_rate": 1.4587832835516071e-05,
|
| 762 |
+
"loss": 1.158,
|
| 763 |
+
"step": 53000
|
| 764 |
+
},
|
| 765 |
+
{
|
| 766 |
+
"epoch": 1.3658063363202368,
|
| 767 |
+
"grad_norm": 0.3551184833049774,
|
| 768 |
+
"learning_rate": 1.4536774654719053e-05,
|
| 769 |
+
"loss": 1.1188,
|
| 770 |
+
"step": 53500
|
| 771 |
+
},
|
| 772 |
+
{
|
| 773 |
+
"epoch": 1.3785708815194915,
|
| 774 |
+
"grad_norm": 39.360172271728516,
|
| 775 |
+
"learning_rate": 1.4485716473922035e-05,
|
| 776 |
+
"loss": 1.2785,
|
| 777 |
+
"step": 54000
|
| 778 |
+
},
|
| 779 |
+
{
|
| 780 |
+
"epoch": 1.3913354267187459,
|
| 781 |
+
"grad_norm": 0.04260186478495598,
|
| 782 |
+
"learning_rate": 1.4434658293125017e-05,
|
| 783 |
+
"loss": 1.1566,
|
| 784 |
+
"step": 54500
|
| 785 |
+
},
|
| 786 |
+
{
|
| 787 |
+
"epoch": 1.4040999719180005,
|
| 788 |
+
"grad_norm": 41.94396209716797,
|
| 789 |
+
"learning_rate": 1.4383600112328e-05,
|
| 790 |
+
"loss": 1.193,
|
| 791 |
+
"step": 55000
|
| 792 |
+
},
|
| 793 |
+
{
|
| 794 |
+
"epoch": 1.4168645171172551,
|
| 795 |
+
"grad_norm": 0.06002192199230194,
|
| 796 |
+
"learning_rate": 1.4332541931530981e-05,
|
| 797 |
+
"loss": 1.0656,
|
| 798 |
+
"step": 55500
|
| 799 |
+
},
|
| 800 |
+
{
|
| 801 |
+
"epoch": 1.4296290623165095,
|
| 802 |
+
"grad_norm": 1.0684689283370972,
|
| 803 |
+
"learning_rate": 1.4281483750733962e-05,
|
| 804 |
+
"loss": 1.1563,
|
| 805 |
+
"step": 56000
|
| 806 |
+
},
|
| 807 |
+
{
|
| 808 |
+
"epoch": 1.4423936075157642,
|
| 809 |
+
"grad_norm": 0.048284854739904404,
|
| 810 |
+
"learning_rate": 1.4230425569936946e-05,
|
| 811 |
+
"loss": 1.0954,
|
| 812 |
+
"step": 56500
|
| 813 |
+
},
|
| 814 |
+
{
|
| 815 |
+
"epoch": 1.4551581527150188,
|
| 816 |
+
"grad_norm": 0.2408294975757599,
|
| 817 |
+
"learning_rate": 1.4179367389139926e-05,
|
| 818 |
+
"loss": 1.0068,
|
| 819 |
+
"step": 57000
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"epoch": 1.4679226979142732,
|
| 823 |
+
"grad_norm": 0.06633832305669785,
|
| 824 |
+
"learning_rate": 1.4128309208342908e-05,
|
| 825 |
+
"loss": 1.1817,
|
| 826 |
+
"step": 57500
|
| 827 |
+
},
|
| 828 |
+
{
|
| 829 |
+
"epoch": 1.4806872431135278,
|
| 830 |
+
"grad_norm": 0.21509085595607758,
|
| 831 |
+
"learning_rate": 1.407725102754589e-05,
|
| 832 |
+
"loss": 1.2413,
|
| 833 |
+
"step": 58000
|
| 834 |
+
},
|
| 835 |
+
{
|
| 836 |
+
"epoch": 1.4934517883127825,
|
| 837 |
+
"grad_norm": 83.50659942626953,
|
| 838 |
+
"learning_rate": 1.4026192846748872e-05,
|
| 839 |
+
"loss": 1.1976,
|
| 840 |
+
"step": 58500
|
| 841 |
+
},
|
| 842 |
+
{
|
| 843 |
+
"epoch": 1.5062163335120369,
|
| 844 |
+
"grad_norm": 0.11434028297662735,
|
| 845 |
+
"learning_rate": 1.3975134665951853e-05,
|
| 846 |
+
"loss": 1.1473,
|
| 847 |
+
"step": 59000
|
| 848 |
+
},
|
| 849 |
+
{
|
| 850 |
+
"epoch": 1.5189808787112915,
|
| 851 |
+
"grad_norm": 92.45787811279297,
|
| 852 |
+
"learning_rate": 1.3924076485154836e-05,
|
| 853 |
+
"loss": 1.1364,
|
| 854 |
+
"step": 59500
|
| 855 |
+
},
|
| 856 |
+
{
|
| 857 |
+
"epoch": 1.5317454239105461,
|
| 858 |
+
"grad_norm": 0.1601213961839676,
|
| 859 |
+
"learning_rate": 1.3873018304357817e-05,
|
| 860 |
+
"loss": 1.0498,
|
| 861 |
+
"step": 60000
|
| 862 |
+
},
|
| 863 |
+
{
|
| 864 |
+
"epoch": 1.5445099691098005,
|
| 865 |
+
"grad_norm": 0.047536320984363556,
|
| 866 |
+
"learning_rate": 1.3821960123560799e-05,
|
| 867 |
+
"loss": 1.2807,
|
| 868 |
+
"step": 60500
|
| 869 |
+
},
|
| 870 |
+
{
|
| 871 |
+
"epoch": 1.5572745143090552,
|
| 872 |
+
"grad_norm": 78.99024963378906,
|
| 873 |
+
"learning_rate": 1.377090194276378e-05,
|
| 874 |
+
"loss": 1.1829,
|
| 875 |
+
"step": 61000
|
| 876 |
+
},
|
| 877 |
+
{
|
| 878 |
+
"epoch": 1.5700390595083098,
|
| 879 |
+
"grad_norm": 2.0312910079956055,
|
| 880 |
+
"learning_rate": 1.3719843761966763e-05,
|
| 881 |
+
"loss": 1.1205,
|
| 882 |
+
"step": 61500
|
| 883 |
+
},
|
| 884 |
+
{
|
| 885 |
+
"epoch": 1.5828036047075642,
|
| 886 |
+
"grad_norm": 0.025315482169389725,
|
| 887 |
+
"learning_rate": 1.3668785581169743e-05,
|
| 888 |
+
"loss": 1.2491,
|
| 889 |
+
"step": 62000
|
| 890 |
+
},
|
| 891 |
+
{
|
| 892 |
+
"epoch": 1.5955681499068188,
|
| 893 |
+
"grad_norm": 0.11782744526863098,
|
| 894 |
+
"learning_rate": 1.3617727400372727e-05,
|
| 895 |
+
"loss": 1.1396,
|
| 896 |
+
"step": 62500
|
| 897 |
+
},
|
| 898 |
+
{
|
| 899 |
+
"epoch": 1.6083326951060735,
|
| 900 |
+
"grad_norm": 76.90337371826172,
|
| 901 |
+
"learning_rate": 1.3566669219575707e-05,
|
| 902 |
+
"loss": 1.0816,
|
| 903 |
+
"step": 63000
|
| 904 |
+
},
|
| 905 |
+
{
|
| 906 |
+
"epoch": 1.6210972403053279,
|
| 907 |
+
"grad_norm": 0.4952268600463867,
|
| 908 |
+
"learning_rate": 1.351561103877869e-05,
|
| 909 |
+
"loss": 1.1147,
|
| 910 |
+
"step": 63500
|
| 911 |
+
},
|
| 912 |
+
{
|
| 913 |
+
"epoch": 1.6338617855045825,
|
| 914 |
+
"grad_norm": 0.3075408339500427,
|
| 915 |
+
"learning_rate": 1.3464552857981672e-05,
|
| 916 |
+
"loss": 1.1859,
|
| 917 |
+
"step": 64000
|
| 918 |
+
},
|
| 919 |
+
{
|
| 920 |
+
"epoch": 1.6466263307038371,
|
| 921 |
+
"grad_norm": 0.16973990201950073,
|
| 922 |
+
"learning_rate": 1.3413494677184654e-05,
|
| 923 |
+
"loss": 1.1367,
|
| 924 |
+
"step": 64500
|
| 925 |
+
},
|
| 926 |
+
{
|
| 927 |
+
"epoch": 1.6593908759030915,
|
| 928 |
+
"grad_norm": 0.1379852145910263,
|
| 929 |
+
"learning_rate": 1.3362436496387634e-05,
|
| 930 |
+
"loss": 1.0859,
|
| 931 |
+
"step": 65000
|
| 932 |
+
},
|
| 933 |
+
{
|
| 934 |
+
"epoch": 1.6721554211023462,
|
| 935 |
+
"grad_norm": 0.4755842089653015,
|
| 936 |
+
"learning_rate": 1.3311378315590618e-05,
|
| 937 |
+
"loss": 1.0848,
|
| 938 |
+
"step": 65500
|
| 939 |
+
},
|
| 940 |
+
{
|
| 941 |
+
"epoch": 1.6849199663016008,
|
| 942 |
+
"grad_norm": 0.5476590394973755,
|
| 943 |
+
"learning_rate": 1.3260320134793598e-05,
|
| 944 |
+
"loss": 1.0839,
|
| 945 |
+
"step": 66000
|
| 946 |
+
},
|
| 947 |
+
{
|
| 948 |
+
"epoch": 1.6976845115008552,
|
| 949 |
+
"grad_norm": 0.21435514092445374,
|
| 950 |
+
"learning_rate": 1.3209261953996579e-05,
|
| 951 |
+
"loss": 1.1667,
|
| 952 |
+
"step": 66500
|
| 953 |
+
},
|
| 954 |
+
{
|
| 955 |
+
"epoch": 1.7104490567001098,
|
| 956 |
+
"grad_norm": 83.75049591064453,
|
| 957 |
+
"learning_rate": 1.3158203773199562e-05,
|
| 958 |
+
"loss": 1.0872,
|
| 959 |
+
"step": 67000
|
| 960 |
+
},
|
| 961 |
+
{
|
| 962 |
+
"epoch": 1.7232136018993645,
|
| 963 |
+
"grad_norm": 0.07525191456079483,
|
| 964 |
+
"learning_rate": 1.3107145592402544e-05,
|
| 965 |
+
"loss": 1.0386,
|
| 966 |
+
"step": 67500
|
| 967 |
+
},
|
| 968 |
+
{
|
| 969 |
+
"epoch": 1.7359781470986189,
|
| 970 |
+
"grad_norm": 80.56642150878906,
|
| 971 |
+
"learning_rate": 1.3056087411605525e-05,
|
| 972 |
+
"loss": 1.0914,
|
| 973 |
+
"step": 68000
|
| 974 |
+
},
|
| 975 |
+
{
|
| 976 |
+
"epoch": 1.7487426922978733,
|
| 977 |
+
"grad_norm": 0.03004269115626812,
|
| 978 |
+
"learning_rate": 1.3005029230808509e-05,
|
| 979 |
+
"loss": 1.0951,
|
| 980 |
+
"step": 68500
|
| 981 |
+
},
|
| 982 |
+
{
|
| 983 |
+
"epoch": 1.7615072374971281,
|
| 984 |
+
"grad_norm": 40.985191345214844,
|
| 985 |
+
"learning_rate": 1.2953971050011489e-05,
|
| 986 |
+
"loss": 1.0683,
|
| 987 |
+
"step": 69000
|
| 988 |
+
},
|
| 989 |
+
{
|
| 990 |
+
"epoch": 1.7742717826963825,
|
| 991 |
+
"grad_norm": 0.20058491826057434,
|
| 992 |
+
"learning_rate": 1.290291286921447e-05,
|
| 993 |
+
"loss": 1.0831,
|
| 994 |
+
"step": 69500
|
| 995 |
+
},
|
| 996 |
+
{
|
| 997 |
+
"epoch": 1.787036327895637,
|
| 998 |
+
"grad_norm": 0.052201852202415466,
|
| 999 |
+
"learning_rate": 1.2851854688417453e-05,
|
| 1000 |
+
"loss": 1.0696,
|
| 1001 |
+
"step": 70000
|
| 1002 |
+
},
|
| 1003 |
+
{
|
| 1004 |
+
"epoch": 1.7998008730948918,
|
| 1005 |
+
"grad_norm": 0.6036315560340881,
|
| 1006 |
+
"learning_rate": 1.2800796507620435e-05,
|
| 1007 |
+
"loss": 1.1347,
|
| 1008 |
+
"step": 70500
|
| 1009 |
+
},
|
| 1010 |
+
{
|
| 1011 |
+
"epoch": 1.8125654182941462,
|
| 1012 |
+
"grad_norm": 0.22676169872283936,
|
| 1013 |
+
"learning_rate": 1.2749738326823416e-05,
|
| 1014 |
+
"loss": 1.2593,
|
| 1015 |
+
"step": 71000
|
| 1016 |
+
},
|
| 1017 |
+
{
|
| 1018 |
+
"epoch": 1.8253299634934006,
|
| 1019 |
+
"grad_norm": 0.10824225842952728,
|
| 1020 |
+
"learning_rate": 1.26986801460264e-05,
|
| 1021 |
+
"loss": 0.9807,
|
| 1022 |
+
"step": 71500
|
| 1023 |
+
},
|
| 1024 |
+
{
|
| 1025 |
+
"epoch": 1.8380945086926552,
|
| 1026 |
+
"grad_norm": 41.9105224609375,
|
| 1027 |
+
"learning_rate": 1.264762196522938e-05,
|
| 1028 |
+
"loss": 1.0355,
|
| 1029 |
+
"step": 72000
|
| 1030 |
+
},
|
| 1031 |
+
{
|
| 1032 |
+
"epoch": 1.8508590538919099,
|
| 1033 |
+
"grad_norm": 0.5162324905395508,
|
| 1034 |
+
"learning_rate": 1.259656378443236e-05,
|
| 1035 |
+
"loss": 1.0889,
|
| 1036 |
+
"step": 72500
|
| 1037 |
+
},
|
| 1038 |
+
{
|
| 1039 |
+
"epoch": 1.8636235990911643,
|
| 1040 |
+
"grad_norm": 38.32647705078125,
|
| 1041 |
+
"learning_rate": 1.2545505603635344e-05,
|
| 1042 |
+
"loss": 1.2899,
|
| 1043 |
+
"step": 73000
|
| 1044 |
+
},
|
| 1045 |
+
{
|
| 1046 |
+
"epoch": 1.876388144290419,
|
| 1047 |
+
"grad_norm": 0.2805481255054474,
|
| 1048 |
+
"learning_rate": 1.2494447422838324e-05,
|
| 1049 |
+
"loss": 1.2102,
|
| 1050 |
+
"step": 73500
|
| 1051 |
+
},
|
| 1052 |
+
{
|
| 1053 |
+
"epoch": 1.8891526894896735,
|
| 1054 |
+
"grad_norm": 0.35390621423721313,
|
| 1055 |
+
"learning_rate": 1.2443389242041306e-05,
|
| 1056 |
+
"loss": 1.1915,
|
| 1057 |
+
"step": 74000
|
| 1058 |
+
},
|
| 1059 |
+
{
|
| 1060 |
+
"epoch": 1.901917234688928,
|
| 1061 |
+
"grad_norm": 0.05271849408745766,
|
| 1062 |
+
"learning_rate": 1.239233106124429e-05,
|
| 1063 |
+
"loss": 1.1858,
|
| 1064 |
+
"step": 74500
|
| 1065 |
+
},
|
| 1066 |
+
{
|
| 1067 |
+
"epoch": 1.9146817798881826,
|
| 1068 |
+
"grad_norm": 0.789485514163971,
|
| 1069 |
+
"learning_rate": 1.234127288044727e-05,
|
| 1070 |
+
"loss": 1.1919,
|
| 1071 |
+
"step": 75000
|
| 1072 |
+
},
|
| 1073 |
+
{
|
| 1074 |
+
"epoch": 1.9274463250874372,
|
| 1075 |
+
"grad_norm": 0.1899205893278122,
|
| 1076 |
+
"learning_rate": 1.229021469965025e-05,
|
| 1077 |
+
"loss": 1.0587,
|
| 1078 |
+
"step": 75500
|
| 1079 |
+
},
|
| 1080 |
+
{
|
| 1081 |
+
"epoch": 1.9402108702866916,
|
| 1082 |
+
"grad_norm": 0.10818950086832047,
|
| 1083 |
+
"learning_rate": 1.2239156518853235e-05,
|
| 1084 |
+
"loss": 1.1135,
|
| 1085 |
+
"step": 76000
|
| 1086 |
+
},
|
| 1087 |
+
{
|
| 1088 |
+
"epoch": 1.9529754154859462,
|
| 1089 |
+
"grad_norm": 0.8333826661109924,
|
| 1090 |
+
"learning_rate": 1.2188098338056215e-05,
|
| 1091 |
+
"loss": 1.1456,
|
| 1092 |
+
"step": 76500
|
| 1093 |
+
},
|
| 1094 |
+
{
|
| 1095 |
+
"epoch": 1.9657399606852008,
|
| 1096 |
+
"grad_norm": 81.41983795166016,
|
| 1097 |
+
"learning_rate": 1.2137040157259199e-05,
|
| 1098 |
+
"loss": 1.1834,
|
| 1099 |
+
"step": 77000
|
| 1100 |
+
},
|
| 1101 |
+
{
|
| 1102 |
+
"epoch": 1.9785045058844553,
|
| 1103 |
+
"grad_norm": 0.12772557139396667,
|
| 1104 |
+
"learning_rate": 1.2085981976462179e-05,
|
| 1105 |
+
"loss": 1.0672,
|
| 1106 |
+
"step": 77500
|
| 1107 |
+
},
|
| 1108 |
+
{
|
| 1109 |
+
"epoch": 1.9912690510837099,
|
| 1110 |
+
"grad_norm": 0.28256455063819885,
|
| 1111 |
+
"learning_rate": 1.2034923795665161e-05,
|
| 1112 |
+
"loss": 1.1685,
|
| 1113 |
+
"step": 78000
|
| 1114 |
+
},
|
| 1115 |
+
{
|
| 1116 |
+
"epoch": 2.0,
|
| 1117 |
+
"eval_accuracy": 0.7559788458838396,
|
| 1118 |
+
"eval_f1": 0.7781654186521443,
|
| 1119 |
+
"eval_loss": 1.104968547821045,
|
| 1120 |
+
"eval_precision": 0.7147881819602939,
|
| 1121 |
+
"eval_recall": 0.853874883286648,
|
| 1122 |
+
"eval_runtime": 7009.9686,
|
| 1123 |
+
"eval_samples_per_second": 3.048,
|
| 1124 |
+
"eval_steps_per_second": 3.048,
|
| 1125 |
+
"step": 78342
|
| 1126 |
+
},
|
| 1127 |
+
{
|
| 1128 |
+
"epoch": 2.0040335962829645,
|
| 1129 |
+
"grad_norm": 0.10416727513074875,
|
| 1130 |
+
"learning_rate": 1.1983865614868145e-05,
|
| 1131 |
+
"loss": 1.1774,
|
| 1132 |
+
"step": 78500
|
| 1133 |
+
},
|
| 1134 |
+
{
|
| 1135 |
+
"epoch": 2.016798141482219,
|
| 1136 |
+
"grad_norm": 0.24586385488510132,
|
| 1137 |
+
"learning_rate": 1.1932807434071125e-05,
|
| 1138 |
+
"loss": 1.152,
|
| 1139 |
+
"step": 79000
|
| 1140 |
+
},
|
| 1141 |
+
{
|
| 1142 |
+
"epoch": 2.0295626866814733,
|
| 1143 |
+
"grad_norm": 81.22022247314453,
|
| 1144 |
+
"learning_rate": 1.1881749253274106e-05,
|
| 1145 |
+
"loss": 1.1793,
|
| 1146 |
+
"step": 79500
|
| 1147 |
+
},
|
| 1148 |
+
{
|
| 1149 |
+
"epoch": 2.042327231880728,
|
| 1150 |
+
"grad_norm": 0.14370392262935638,
|
| 1151 |
+
"learning_rate": 1.183069107247709e-05,
|
| 1152 |
+
"loss": 1.0436,
|
| 1153 |
+
"step": 80000
|
| 1154 |
+
},
|
| 1155 |
+
{
|
| 1156 |
+
"epoch": 2.0550917770799826,
|
| 1157 |
+
"grad_norm": 0.6635909080505371,
|
| 1158 |
+
"learning_rate": 1.177963289168007e-05,
|
| 1159 |
+
"loss": 1.2154,
|
| 1160 |
+
"step": 80500
|
| 1161 |
+
},
|
| 1162 |
+
{
|
| 1163 |
+
"epoch": 2.067856322279237,
|
| 1164 |
+
"grad_norm": 0.21300217509269714,
|
| 1165 |
+
"learning_rate": 1.1728574710883052e-05,
|
| 1166 |
+
"loss": 1.1494,
|
| 1167 |
+
"step": 81000
|
| 1168 |
+
},
|
| 1169 |
+
{
|
| 1170 |
+
"epoch": 2.080620867478492,
|
| 1171 |
+
"grad_norm": 0.0938217043876648,
|
| 1172 |
+
"learning_rate": 1.1677516530086036e-05,
|
| 1173 |
+
"loss": 0.9968,
|
| 1174 |
+
"step": 81500
|
| 1175 |
+
},
|
| 1176 |
+
{
|
| 1177 |
+
"epoch": 2.0933854126777462,
|
| 1178 |
+
"grad_norm": 0.2714625298976898,
|
| 1179 |
+
"learning_rate": 1.1626458349289016e-05,
|
| 1180 |
+
"loss": 1.0973,
|
| 1181 |
+
"step": 82000
|
| 1182 |
+
},
|
| 1183 |
+
{
|
| 1184 |
+
"epoch": 2.1061499578770007,
|
| 1185 |
+
"grad_norm": 0.21016670763492584,
|
| 1186 |
+
"learning_rate": 1.1575400168491996e-05,
|
| 1187 |
+
"loss": 1.1714,
|
| 1188 |
+
"step": 82500
|
| 1189 |
+
},
|
| 1190 |
+
{
|
| 1191 |
+
"epoch": 2.1189145030762555,
|
| 1192 |
+
"grad_norm": 0.023590411990880966,
|
| 1193 |
+
"learning_rate": 1.152434198769498e-05,
|
| 1194 |
+
"loss": 1.1484,
|
| 1195 |
+
"step": 83000
|
| 1196 |
+
},
|
| 1197 |
+
{
|
| 1198 |
+
"epoch": 2.13167904827551,
|
| 1199 |
+
"grad_norm": 1.0143898725509644,
|
| 1200 |
+
"learning_rate": 1.147328380689796e-05,
|
| 1201 |
+
"loss": 1.1458,
|
| 1202 |
+
"step": 83500
|
| 1203 |
+
},
|
| 1204 |
+
{
|
| 1205 |
+
"epoch": 2.1444435934747643,
|
| 1206 |
+
"grad_norm": 0.3051891326904297,
|
| 1207 |
+
"learning_rate": 1.1422225626100943e-05,
|
| 1208 |
+
"loss": 1.1325,
|
| 1209 |
+
"step": 84000
|
| 1210 |
+
},
|
| 1211 |
+
{
|
| 1212 |
+
"epoch": 2.157208138674019,
|
| 1213 |
+
"grad_norm": 0.19862498342990875,
|
| 1214 |
+
"learning_rate": 1.1371167445303925e-05,
|
| 1215 |
+
"loss": 1.0592,
|
| 1216 |
+
"step": 84500
|
| 1217 |
+
},
|
| 1218 |
+
{
|
| 1219 |
+
"epoch": 2.1699726838732736,
|
| 1220 |
+
"grad_norm": 39.33951950073242,
|
| 1221 |
+
"learning_rate": 1.1320109264506907e-05,
|
| 1222 |
+
"loss": 1.1159,
|
| 1223 |
+
"step": 85000
|
| 1224 |
+
},
|
| 1225 |
+
{
|
| 1226 |
+
"epoch": 2.182737229072528,
|
| 1227 |
+
"grad_norm": 38.398826599121094,
|
| 1228 |
+
"learning_rate": 1.1269051083709887e-05,
|
| 1229 |
+
"loss": 1.0162,
|
| 1230 |
+
"step": 85500
|
| 1231 |
+
},
|
| 1232 |
+
{
|
| 1233 |
+
"epoch": 2.195501774271783,
|
| 1234 |
+
"grad_norm": 0.5094022750854492,
|
| 1235 |
+
"learning_rate": 1.1217992902912871e-05,
|
| 1236 |
+
"loss": 1.2129,
|
| 1237 |
+
"step": 86000
|
| 1238 |
+
},
|
| 1239 |
+
{
|
| 1240 |
+
"epoch": 2.2082663194710372,
|
| 1241 |
+
"grad_norm": 80.10652160644531,
|
| 1242 |
+
"learning_rate": 1.1166934722115851e-05,
|
| 1243 |
+
"loss": 1.0327,
|
| 1244 |
+
"step": 86500
|
| 1245 |
+
},
|
| 1246 |
+
{
|
| 1247 |
+
"epoch": 2.2210308646702916,
|
| 1248 |
+
"grad_norm": 3.5941567420959473,
|
| 1249 |
+
"learning_rate": 1.1115876541318833e-05,
|
| 1250 |
+
"loss": 1.1216,
|
| 1251 |
+
"step": 87000
|
| 1252 |
+
},
|
| 1253 |
+
{
|
| 1254 |
+
"epoch": 2.2337954098695465,
|
| 1255 |
+
"grad_norm": 0.037905264645814896,
|
| 1256 |
+
"learning_rate": 1.1064818360521816e-05,
|
| 1257 |
+
"loss": 1.1096,
|
| 1258 |
+
"step": 87500
|
| 1259 |
+
},
|
| 1260 |
+
{
|
| 1261 |
+
"epoch": 2.246559955068801,
|
| 1262 |
+
"grad_norm": 0.1159309670329094,
|
| 1263 |
+
"learning_rate": 1.1013760179724798e-05,
|
| 1264 |
+
"loss": 1.1862,
|
| 1265 |
+
"step": 88000
|
| 1266 |
+
},
|
| 1267 |
+
{
|
| 1268 |
+
"epoch": 2.2593245002680553,
|
| 1269 |
+
"grad_norm": 1.1286303997039795,
|
| 1270 |
+
"learning_rate": 1.0962701998927778e-05,
|
| 1271 |
+
"loss": 1.3032,
|
| 1272 |
+
"step": 88500
|
| 1273 |
+
},
|
| 1274 |
+
{
|
| 1275 |
+
"epoch": 2.27208904546731,
|
| 1276 |
+
"grad_norm": 0.1710648089647293,
|
| 1277 |
+
"learning_rate": 1.0911643818130762e-05,
|
| 1278 |
+
"loss": 1.054,
|
| 1279 |
+
"step": 89000
|
| 1280 |
+
},
|
| 1281 |
+
{
|
| 1282 |
+
"epoch": 2.2848535906665646,
|
| 1283 |
+
"grad_norm": 0.36557528376579285,
|
| 1284 |
+
"learning_rate": 1.0860585637333742e-05,
|
| 1285 |
+
"loss": 1.226,
|
| 1286 |
+
"step": 89500
|
| 1287 |
+
},
|
| 1288 |
+
{
|
| 1289 |
+
"epoch": 2.297618135865819,
|
| 1290 |
+
"grad_norm": 1.4391981363296509,
|
| 1291 |
+
"learning_rate": 1.0809527456536724e-05,
|
| 1292 |
+
"loss": 1.2126,
|
| 1293 |
+
"step": 90000
|
| 1294 |
+
},
|
| 1295 |
+
{
|
| 1296 |
+
"epoch": 2.310382681065074,
|
| 1297 |
+
"grad_norm": 82.89622497558594,
|
| 1298 |
+
"learning_rate": 1.0758469275739706e-05,
|
| 1299 |
+
"loss": 1.016,
|
| 1300 |
+
"step": 90500
|
| 1301 |
+
},
|
| 1302 |
+
{
|
| 1303 |
+
"epoch": 2.3231472262643282,
|
| 1304 |
+
"grad_norm": 83.06659698486328,
|
| 1305 |
+
"learning_rate": 1.0707411094942688e-05,
|
| 1306 |
+
"loss": 0.9663,
|
| 1307 |
+
"step": 91000
|
| 1308 |
+
},
|
| 1309 |
+
{
|
| 1310 |
+
"epoch": 2.3359117714635826,
|
| 1311 |
+
"grad_norm": 39.086429595947266,
|
| 1312 |
+
"learning_rate": 1.0656352914145669e-05,
|
| 1313 |
+
"loss": 1.0661,
|
| 1314 |
+
"step": 91500
|
| 1315 |
+
},
|
| 1316 |
+
{
|
| 1317 |
+
"epoch": 2.3486763166628375,
|
| 1318 |
+
"grad_norm": 80.77433776855469,
|
| 1319 |
+
"learning_rate": 1.0605294733348653e-05,
|
| 1320 |
+
"loss": 1.0967,
|
| 1321 |
+
"step": 92000
|
| 1322 |
+
},
|
| 1323 |
+
{
|
| 1324 |
+
"epoch": 2.361440861862092,
|
| 1325 |
+
"grad_norm": 0.10435591638088226,
|
| 1326 |
+
"learning_rate": 1.0554236552551633e-05,
|
| 1327 |
+
"loss": 1.0076,
|
| 1328 |
+
"step": 92500
|
| 1329 |
+
},
|
| 1330 |
+
{
|
| 1331 |
+
"epoch": 2.3742054070613463,
|
| 1332 |
+
"grad_norm": 37.59447479248047,
|
| 1333 |
+
"learning_rate": 1.0503178371754615e-05,
|
| 1334 |
+
"loss": 1.0618,
|
| 1335 |
+
"step": 93000
|
| 1336 |
+
},
|
| 1337 |
+
{
|
| 1338 |
+
"epoch": 2.3869699522606007,
|
| 1339 |
+
"grad_norm": 0.1259271204471588,
|
| 1340 |
+
"learning_rate": 1.0452120190957597e-05,
|
| 1341 |
+
"loss": 1.1426,
|
| 1342 |
+
"step": 93500
|
| 1343 |
+
},
|
| 1344 |
+
{
|
| 1345 |
+
"epoch": 2.3997344974598556,
|
| 1346 |
+
"grad_norm": 39.37663269042969,
|
| 1347 |
+
"learning_rate": 1.0401062010160579e-05,
|
| 1348 |
+
"loss": 1.1597,
|
| 1349 |
+
"step": 94000
|
| 1350 |
+
},
|
| 1351 |
+
{
|
| 1352 |
+
"epoch": 2.41249904265911,
|
| 1353 |
+
"grad_norm": 38.08433151245117,
|
| 1354 |
+
"learning_rate": 1.035000382936356e-05,
|
| 1355 |
+
"loss": 1.2757,
|
| 1356 |
+
"step": 94500
|
| 1357 |
+
},
|
| 1358 |
+
{
|
| 1359 |
+
"epoch": 2.425263587858365,
|
| 1360 |
+
"grad_norm": 36.52158737182617,
|
| 1361 |
+
"learning_rate": 1.0298945648566543e-05,
|
| 1362 |
+
"loss": 1.0682,
|
| 1363 |
+
"step": 95000
|
| 1364 |
+
},
|
| 1365 |
+
{
|
| 1366 |
+
"epoch": 2.4380281330576192,
|
| 1367 |
+
"grad_norm": 0.9045330882072449,
|
| 1368 |
+
"learning_rate": 1.0247887467769524e-05,
|
| 1369 |
+
"loss": 1.1287,
|
| 1370 |
+
"step": 95500
|
| 1371 |
+
},
|
| 1372 |
+
{
|
| 1373 |
+
"epoch": 2.4507926782568736,
|
| 1374 |
+
"grad_norm": 0.0985599160194397,
|
| 1375 |
+
"learning_rate": 1.0196829286972506e-05,
|
| 1376 |
+
"loss": 1.074,
|
| 1377 |
+
"step": 96000
|
| 1378 |
+
},
|
| 1379 |
+
{
|
| 1380 |
+
"epoch": 2.463557223456128,
|
| 1381 |
+
"grad_norm": 77.95613098144531,
|
| 1382 |
+
"learning_rate": 1.0145771106175488e-05,
|
| 1383 |
+
"loss": 1.2524,
|
| 1384 |
+
"step": 96500
|
| 1385 |
+
},
|
| 1386 |
+
{
|
| 1387 |
+
"epoch": 2.476321768655383,
|
| 1388 |
+
"grad_norm": 36.22038269042969,
|
| 1389 |
+
"learning_rate": 1.009471292537847e-05,
|
| 1390 |
+
"loss": 1.1292,
|
| 1391 |
+
"step": 97000
|
| 1392 |
+
},
|
| 1393 |
+
{
|
| 1394 |
+
"epoch": 2.4890863138546373,
|
| 1395 |
+
"grad_norm": 0.7746332883834839,
|
| 1396 |
+
"learning_rate": 1.004365474458145e-05,
|
| 1397 |
+
"loss": 1.1763,
|
| 1398 |
+
"step": 97500
|
| 1399 |
+
},
|
| 1400 |
+
{
|
| 1401 |
+
"epoch": 2.501850859053892,
|
| 1402 |
+
"grad_norm": 38.16327667236328,
|
| 1403 |
+
"learning_rate": 9.992596563784434e-06,
|
| 1404 |
+
"loss": 1.0789,
|
| 1405 |
+
"step": 98000
|
| 1406 |
+
},
|
| 1407 |
+
{
|
| 1408 |
+
"epoch": 2.5146154042531466,
|
| 1409 |
+
"grad_norm": 0.16657011210918427,
|
| 1410 |
+
"learning_rate": 9.941538382987414e-06,
|
| 1411 |
+
"loss": 1.097,
|
| 1412 |
+
"step": 98500
|
| 1413 |
+
},
|
| 1414 |
+
{
|
| 1415 |
+
"epoch": 2.527379949452401,
|
| 1416 |
+
"grad_norm": 0.12218489497900009,
|
| 1417 |
+
"learning_rate": 9.890480202190396e-06,
|
| 1418 |
+
"loss": 1.0325,
|
| 1419 |
+
"step": 99000
|
| 1420 |
+
},
|
| 1421 |
+
{
|
| 1422 |
+
"epoch": 2.5401444946516554,
|
| 1423 |
+
"grad_norm": 74.8918685913086,
|
| 1424 |
+
"learning_rate": 9.839422021393379e-06,
|
| 1425 |
+
"loss": 1.113,
|
| 1426 |
+
"step": 99500
|
| 1427 |
+
},
|
| 1428 |
+
{
|
| 1429 |
+
"epoch": 2.5529090398509102,
|
| 1430 |
+
"grad_norm": 77.3615493774414,
|
| 1431 |
+
"learning_rate": 9.78836384059636e-06,
|
| 1432 |
+
"loss": 1.0551,
|
| 1433 |
+
"step": 100000
|
| 1434 |
+
},
|
| 1435 |
+
{
|
| 1436 |
+
"epoch": 2.5656735850501646,
|
| 1437 |
+
"grad_norm": 0.39637118577957153,
|
| 1438 |
+
"learning_rate": 9.737305659799343e-06,
|
| 1439 |
+
"loss": 1.0923,
|
| 1440 |
+
"step": 100500
|
| 1441 |
+
},
|
| 1442 |
+
{
|
| 1443 |
+
"epoch": 2.5784381302494195,
|
| 1444 |
+
"grad_norm": 0.25890830159187317,
|
| 1445 |
+
"learning_rate": 9.686247479002325e-06,
|
| 1446 |
+
"loss": 1.2625,
|
| 1447 |
+
"step": 101000
|
| 1448 |
+
},
|
| 1449 |
+
{
|
| 1450 |
+
"epoch": 2.591202675448674,
|
| 1451 |
+
"grad_norm": 0.06774591654539108,
|
| 1452 |
+
"learning_rate": 9.635189298205305e-06,
|
| 1453 |
+
"loss": 1.0399,
|
| 1454 |
+
"step": 101500
|
| 1455 |
+
},
|
| 1456 |
+
{
|
| 1457 |
+
"epoch": 2.6039672206479283,
|
| 1458 |
+
"grad_norm": 0.5836966037750244,
|
| 1459 |
+
"learning_rate": 9.584131117408287e-06,
|
| 1460 |
+
"loss": 1.1528,
|
| 1461 |
+
"step": 102000
|
| 1462 |
+
},
|
| 1463 |
+
{
|
| 1464 |
+
"epoch": 2.6167317658471827,
|
| 1465 |
+
"grad_norm": 0.41435518860816956,
|
| 1466 |
+
"learning_rate": 9.53307293661127e-06,
|
| 1467 |
+
"loss": 1.184,
|
| 1468 |
+
"step": 102500
|
| 1469 |
+
},
|
| 1470 |
+
{
|
| 1471 |
+
"epoch": 2.6294963110464376,
|
| 1472 |
+
"grad_norm": 0.37088045477867126,
|
| 1473 |
+
"learning_rate": 9.482014755814251e-06,
|
| 1474 |
+
"loss": 1.0628,
|
| 1475 |
+
"step": 103000
|
| 1476 |
+
},
|
| 1477 |
+
{
|
| 1478 |
+
"epoch": 2.642260856245692,
|
| 1479 |
+
"grad_norm": 0.8684372901916504,
|
| 1480 |
+
"learning_rate": 9.430956575017233e-06,
|
| 1481 |
+
"loss": 1.1543,
|
| 1482 |
+
"step": 103500
|
| 1483 |
+
},
|
| 1484 |
+
{
|
| 1485 |
+
"epoch": 2.6550254014449464,
|
| 1486 |
+
"grad_norm": 1.3211474418640137,
|
| 1487 |
+
"learning_rate": 9.379898394220216e-06,
|
| 1488 |
+
"loss": 1.2299,
|
| 1489 |
+
"step": 104000
|
| 1490 |
+
},
|
| 1491 |
+
{
|
| 1492 |
+
"epoch": 2.667789946644201,
|
| 1493 |
+
"grad_norm": 2.8510055541992188,
|
| 1494 |
+
"learning_rate": 9.328840213423198e-06,
|
| 1495 |
+
"loss": 1.1187,
|
| 1496 |
+
"step": 104500
|
| 1497 |
+
},
|
| 1498 |
+
{
|
| 1499 |
+
"epoch": 2.6805544918434556,
|
| 1500 |
+
"grad_norm": 46.20832824707031,
|
| 1501 |
+
"learning_rate": 9.277782032626178e-06,
|
| 1502 |
+
"loss": 1.0977,
|
| 1503 |
+
"step": 105000
|
| 1504 |
+
},
|
| 1505 |
+
{
|
| 1506 |
+
"epoch": 2.69331903704271,
|
| 1507 |
+
"grad_norm": 0.22926129400730133,
|
| 1508 |
+
"learning_rate": 9.22672385182916e-06,
|
| 1509 |
+
"loss": 1.2026,
|
| 1510 |
+
"step": 105500
|
| 1511 |
+
},
|
| 1512 |
+
{
|
| 1513 |
+
"epoch": 2.706083582241965,
|
| 1514 |
+
"grad_norm": 0.3897280693054199,
|
| 1515 |
+
"learning_rate": 9.175665671032142e-06,
|
| 1516 |
+
"loss": 0.9847,
|
| 1517 |
+
"step": 106000
|
| 1518 |
+
},
|
| 1519 |
+
{
|
| 1520 |
+
"epoch": 2.7188481274412193,
|
| 1521 |
+
"grad_norm": 1.3292169570922852,
|
| 1522 |
+
"learning_rate": 9.124607490235124e-06,
|
| 1523 |
+
"loss": 1.2152,
|
| 1524 |
+
"step": 106500
|
| 1525 |
+
},
|
| 1526 |
+
{
|
| 1527 |
+
"epoch": 2.7316126726404737,
|
| 1528 |
+
"grad_norm": 0.04647594690322876,
|
| 1529 |
+
"learning_rate": 9.073549309438106e-06,
|
| 1530 |
+
"loss": 1.1028,
|
| 1531 |
+
"step": 107000
|
| 1532 |
+
},
|
| 1533 |
+
{
|
| 1534 |
+
"epoch": 2.7443772178397285,
|
| 1535 |
+
"grad_norm": 77.241943359375,
|
| 1536 |
+
"learning_rate": 9.022491128641088e-06,
|
| 1537 |
+
"loss": 1.0194,
|
| 1538 |
+
"step": 107500
|
| 1539 |
+
},
|
| 1540 |
+
{
|
| 1541 |
+
"epoch": 2.757141763038983,
|
| 1542 |
+
"grad_norm": 0.11248348653316498,
|
| 1543 |
+
"learning_rate": 8.971432947844069e-06,
|
| 1544 |
+
"loss": 1.1805,
|
| 1545 |
+
"step": 108000
|
| 1546 |
+
},
|
| 1547 |
+
{
|
| 1548 |
+
"epoch": 2.7699063082382374,
|
| 1549 |
+
"grad_norm": 1.2412781715393066,
|
| 1550 |
+
"learning_rate": 8.92037476704705e-06,
|
| 1551 |
+
"loss": 1.2305,
|
| 1552 |
+
"step": 108500
|
| 1553 |
+
},
|
| 1554 |
+
{
|
| 1555 |
+
"epoch": 2.7826708534374918,
|
| 1556 |
+
"grad_norm": 0.030775465071201324,
|
| 1557 |
+
"learning_rate": 8.869316586250033e-06,
|
| 1558 |
+
"loss": 1.0447,
|
| 1559 |
+
"step": 109000
|
| 1560 |
+
},
|
| 1561 |
+
{
|
| 1562 |
+
"epoch": 2.7954353986367466,
|
| 1563 |
+
"grad_norm": 35.25270462036133,
|
| 1564 |
+
"learning_rate": 8.818258405453013e-06,
|
| 1565 |
+
"loss": 1.1336,
|
| 1566 |
+
"step": 109500
|
| 1567 |
+
},
|
| 1568 |
+
{
|
| 1569 |
+
"epoch": 2.808199943836001,
|
| 1570 |
+
"grad_norm": 0.07410182058811188,
|
| 1571 |
+
"learning_rate": 8.767200224655997e-06,
|
| 1572 |
+
"loss": 1.0045,
|
| 1573 |
+
"step": 110000
|
| 1574 |
+
},
|
| 1575 |
+
{
|
| 1576 |
+
"epoch": 2.820964489035256,
|
| 1577 |
+
"grad_norm": 0.0769825130701065,
|
| 1578 |
+
"learning_rate": 8.716142043858979e-06,
|
| 1579 |
+
"loss": 1.0757,
|
| 1580 |
+
"step": 110500
|
| 1581 |
+
},
|
| 1582 |
+
{
|
| 1583 |
+
"epoch": 2.8337290342345103,
|
| 1584 |
+
"grad_norm": 40.211849212646484,
|
| 1585 |
+
"learning_rate": 8.66508386306196e-06,
|
| 1586 |
+
"loss": 1.049,
|
| 1587 |
+
"step": 111000
|
| 1588 |
+
},
|
| 1589 |
+
{
|
| 1590 |
+
"epoch": 2.8464935794337647,
|
| 1591 |
+
"grad_norm": 34.911705017089844,
|
| 1592 |
+
"learning_rate": 8.614025682264942e-06,
|
| 1593 |
+
"loss": 1.1969,
|
| 1594 |
+
"step": 111500
|
| 1595 |
+
},
|
| 1596 |
+
{
|
| 1597 |
+
"epoch": 2.859258124633019,
|
| 1598 |
+
"grad_norm": 0.2742353081703186,
|
| 1599 |
+
"learning_rate": 8.562967501467924e-06,
|
| 1600 |
+
"loss": 1.0186,
|
| 1601 |
+
"step": 112000
|
| 1602 |
+
},
|
| 1603 |
+
{
|
| 1604 |
+
"epoch": 2.872022669832274,
|
| 1605 |
+
"grad_norm": 74.05638122558594,
|
| 1606 |
+
"learning_rate": 8.511909320670904e-06,
|
| 1607 |
+
"loss": 1.2728,
|
| 1608 |
+
"step": 112500
|
| 1609 |
+
},
|
| 1610 |
+
{
|
| 1611 |
+
"epoch": 2.8847872150315284,
|
| 1612 |
+
"grad_norm": 0.575434148311615,
|
| 1613 |
+
"learning_rate": 8.460851139873886e-06,
|
| 1614 |
+
"loss": 1.1119,
|
| 1615 |
+
"step": 113000
|
| 1616 |
+
},
|
| 1617 |
+
{
|
| 1618 |
+
"epoch": 2.897551760230783,
|
| 1619 |
+
"grad_norm": 71.94573211669922,
|
| 1620 |
+
"learning_rate": 8.409792959076868e-06,
|
| 1621 |
+
"loss": 0.9989,
|
| 1622 |
+
"step": 113500
|
| 1623 |
+
},
|
| 1624 |
+
{
|
| 1625 |
+
"epoch": 2.9103163054300376,
|
| 1626 |
+
"grad_norm": 0.1596802920103073,
|
| 1627 |
+
"learning_rate": 8.35873477827985e-06,
|
| 1628 |
+
"loss": 1.235,
|
| 1629 |
+
"step": 114000
|
| 1630 |
+
},
|
| 1631 |
+
{
|
| 1632 |
+
"epoch": 2.923080850629292,
|
| 1633 |
+
"grad_norm": 0.1986386477947235,
|
| 1634 |
+
"learning_rate": 8.307676597482832e-06,
|
| 1635 |
+
"loss": 1.1226,
|
| 1636 |
+
"step": 114500
|
| 1637 |
+
},
|
| 1638 |
+
{
|
| 1639 |
+
"epoch": 2.9358453958285464,
|
| 1640 |
+
"grad_norm": 1.1152982711791992,
|
| 1641 |
+
"learning_rate": 8.256618416685814e-06,
|
| 1642 |
+
"loss": 1.1076,
|
| 1643 |
+
"step": 115000
|
| 1644 |
+
},
|
| 1645 |
+
{
|
| 1646 |
+
"epoch": 2.9486099410278013,
|
| 1647 |
+
"grad_norm": 0.05366308614611626,
|
| 1648 |
+
"learning_rate": 8.205560235888796e-06,
|
| 1649 |
+
"loss": 1.0893,
|
| 1650 |
+
"step": 115500
|
| 1651 |
+
},
|
| 1652 |
+
{
|
| 1653 |
+
"epoch": 2.9613744862270557,
|
| 1654 |
+
"grad_norm": 76.19720458984375,
|
| 1655 |
+
"learning_rate": 8.154502055091777e-06,
|
| 1656 |
+
"loss": 0.9395,
|
| 1657 |
+
"step": 116000
|
| 1658 |
+
},
|
| 1659 |
+
{
|
| 1660 |
+
"epoch": 2.9741390314263105,
|
| 1661 |
+
"grad_norm": 34.510494232177734,
|
| 1662 |
+
"learning_rate": 8.103443874294759e-06,
|
| 1663 |
+
"loss": 1.1488,
|
| 1664 |
+
"step": 116500
|
| 1665 |
+
},
|
| 1666 |
+
{
|
| 1667 |
+
"epoch": 2.986903576625565,
|
| 1668 |
+
"grad_norm": 33.559600830078125,
|
| 1669 |
+
"learning_rate": 8.052385693497741e-06,
|
| 1670 |
+
"loss": 1.0944,
|
| 1671 |
+
"step": 117000
|
| 1672 |
+
},
|
| 1673 |
+
{
|
| 1674 |
+
"epoch": 2.9996681218248193,
|
| 1675 |
+
"grad_norm": 0.10646886378526688,
|
| 1676 |
+
"learning_rate": 8.001327512700723e-06,
|
| 1677 |
+
"loss": 0.9763,
|
| 1678 |
+
"step": 117500
|
| 1679 |
+
},
|
| 1680 |
+
{
|
| 1681 |
+
"epoch": 3.0,
|
| 1682 |
+
"eval_accuracy": 0.7562128515935789,
|
| 1683 |
+
"eval_f1": 0.7631949811337909,
|
| 1684 |
+
"eval_loss": 1.1332379579544067,
|
| 1685 |
+
"eval_precision": 0.74368742801453,
|
| 1686 |
+
"eval_recall": 0.7837535014005602,
|
| 1687 |
+
"eval_runtime": 6972.3798,
|
| 1688 |
+
"eval_samples_per_second": 3.065,
|
| 1689 |
+
"eval_steps_per_second": 3.065,
|
| 1690 |
+
"step": 117513
|
| 1691 |
+
}
|
| 1692 |
+
],
|
| 1693 |
+
"logging_steps": 500,
|
| 1694 |
+
"max_steps": 195855,
|
| 1695 |
+
"num_input_tokens_seen": 0,
|
| 1696 |
+
"num_train_epochs": 5,
|
| 1697 |
+
"save_steps": 500,
|
| 1698 |
+
"stateful_callbacks": {
|
| 1699 |
+
"EarlyStoppingCallback": {
|
| 1700 |
+
"args": {
|
| 1701 |
+
"early_stopping_patience": 1,
|
| 1702 |
+
"early_stopping_threshold": 0.0
|
| 1703 |
+
},
|
| 1704 |
+
"attributes": {
|
| 1705 |
+
"early_stopping_patience_counter": 0
|
| 1706 |
+
}
|
| 1707 |
+
},
|
| 1708 |
+
"TrainerControl": {
|
| 1709 |
+
"args": {
|
| 1710 |
+
"should_epoch_stop": false,
|
| 1711 |
+
"should_evaluate": false,
|
| 1712 |
+
"should_log": false,
|
| 1713 |
+
"should_save": true,
|
| 1714 |
+
"should_training_stop": true
|
| 1715 |
+
},
|
| 1716 |
+
"attributes": {}
|
| 1717 |
+
}
|
| 1718 |
+
},
|
| 1719 |
+
"total_flos": 7.696606978389197e+17,
|
| 1720 |
+
"train_batch_size": 1,
|
| 1721 |
+
"trial_name": null,
|
| 1722 |
+
"trial_params": null
|
| 1723 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:599eaa9a5d9427b0bdf196b30976561863bbc55a63c2d148c7e26ebe1efca945
|
| 3 |
+
size 5176
|