Commit
•
50d473f
1
Parent(s):
27ae57d
Upload 16 files
Browse files- README.md +202 -0
- adapter_config.json +29 -0
- adapter_model.safetensors +3 -0
- added_tokens.json +13 -0
- optimizer.pt +3 -0
- rng_state_0.pth +3 -0
- rng_state_1.pth +3 -0
- rng_state_2.pth +3 -0
- rng_state_3.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +24 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +131 -0
- trainer_state.json +2600 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: microsoft/Phi-3-mini-4k-instruct
|
| 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 0.8.2
|
adapter_config.json
ADDED
|
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "microsoft/Phi-3-mini-4k-instruct",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": false,
|
| 7 |
+
"inference_mode": true,
|
| 8 |
+
"init_lora_weights": true,
|
| 9 |
+
"layers_pattern": null,
|
| 10 |
+
"layers_to_transform": null,
|
| 11 |
+
"loftq_config": {},
|
| 12 |
+
"lora_alpha": 8,
|
| 13 |
+
"lora_dropout": 0.05,
|
| 14 |
+
"megatron_config": null,
|
| 15 |
+
"megatron_core": "megatron.core",
|
| 16 |
+
"modules_to_save": null,
|
| 17 |
+
"peft_type": "LORA",
|
| 18 |
+
"r": 8,
|
| 19 |
+
"rank_pattern": {},
|
| 20 |
+
"revision": null,
|
| 21 |
+
"target_modules": [
|
| 22 |
+
"gate_up_proj",
|
| 23 |
+
"down_proj",
|
| 24 |
+
"o_proj",
|
| 25 |
+
"qkv_proj"
|
| 26 |
+
],
|
| 27 |
+
"task_type": "CAUSAL_LM",
|
| 28 |
+
"use_rslora": false
|
| 29 |
+
}
|
adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:12bd873dec5242fded3d451bc157ad946daf2a00f9f89da54f846dc40c766de3
|
| 3 |
+
size 25200088
|
added_tokens.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<|assistant|>": 32001,
|
| 3 |
+
"<|endoftext|>": 32000,
|
| 4 |
+
"<|end|>": 32007,
|
| 5 |
+
"<|placeholder1|>": 32002,
|
| 6 |
+
"<|placeholder2|>": 32003,
|
| 7 |
+
"<|placeholder3|>": 32004,
|
| 8 |
+
"<|placeholder4|>": 32005,
|
| 9 |
+
"<|placeholder5|>": 32008,
|
| 10 |
+
"<|placeholder6|>": 32009,
|
| 11 |
+
"<|system|>": 32006,
|
| 12 |
+
"<|user|>": 32010
|
| 13 |
+
}
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:34535e79ae4c60f9b699766dc5ca388a375f49c0b6c8c29d3f6dc221a7a1cc19
|
| 3 |
+
size 50546810
|
rng_state_0.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ff8f54adafa2b0d6aaa8413716b94f80f79fdfbf193adfdcf545c315edff25b2
|
| 3 |
+
size 15024
|
rng_state_1.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:984f0c6ffad882ac487630a6b0fd329627783a6980336bf78d797d3d01642905
|
| 3 |
+
size 15024
|
rng_state_2.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c0b494aea52b34fdd871c516a28f779b36518f239372386345ac43186fdf7005
|
| 3 |
+
size 15024
|
rng_state_3.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:212787cbb3369255a01be3327973959b3535af5a49bfd5060f61299783315502
|
| 3 |
+
size 15024
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:83ee1037dce7bfbeb048eb499f32bf0035fe5e597ef0d869798e0eb7fe22122a
|
| 3 |
+
size 1064
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "<|endoftext|>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": "<unk>",
|
| 17 |
+
"unk_token": {
|
| 18 |
+
"content": "<unk>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
}
|
| 24 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer.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 +1,131 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"add_prefix_space": null,
|
| 5 |
+
"added_tokens_decoder": {
|
| 6 |
+
"0": {
|
| 7 |
+
"content": "<unk>",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": false,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false,
|
| 12 |
+
"special": true
|
| 13 |
+
},
|
| 14 |
+
"1": {
|
| 15 |
+
"content": "<s>",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": false,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false,
|
| 20 |
+
"special": true
|
| 21 |
+
},
|
| 22 |
+
"2": {
|
| 23 |
+
"content": "</s>",
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"normalized": false,
|
| 26 |
+
"rstrip": true,
|
| 27 |
+
"single_word": false,
|
| 28 |
+
"special": false
|
| 29 |
+
},
|
| 30 |
+
"32000": {
|
| 31 |
+
"content": "<|endoftext|>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false,
|
| 36 |
+
"special": true
|
| 37 |
+
},
|
| 38 |
+
"32001": {
|
| 39 |
+
"content": "<|assistant|>",
|
| 40 |
+
"lstrip": false,
|
| 41 |
+
"normalized": false,
|
| 42 |
+
"rstrip": true,
|
| 43 |
+
"single_word": false,
|
| 44 |
+
"special": true
|
| 45 |
+
},
|
| 46 |
+
"32002": {
|
| 47 |
+
"content": "<|placeholder1|>",
|
| 48 |
+
"lstrip": false,
|
| 49 |
+
"normalized": false,
|
| 50 |
+
"rstrip": true,
|
| 51 |
+
"single_word": false,
|
| 52 |
+
"special": true
|
| 53 |
+
},
|
| 54 |
+
"32003": {
|
| 55 |
+
"content": "<|placeholder2|>",
|
| 56 |
+
"lstrip": false,
|
| 57 |
+
"normalized": false,
|
| 58 |
+
"rstrip": true,
|
| 59 |
+
"single_word": false,
|
| 60 |
+
"special": true
|
| 61 |
+
},
|
| 62 |
+
"32004": {
|
| 63 |
+
"content": "<|placeholder3|>",
|
| 64 |
+
"lstrip": false,
|
| 65 |
+
"normalized": false,
|
| 66 |
+
"rstrip": true,
|
| 67 |
+
"single_word": false,
|
| 68 |
+
"special": true
|
| 69 |
+
},
|
| 70 |
+
"32005": {
|
| 71 |
+
"content": "<|placeholder4|>",
|
| 72 |
+
"lstrip": false,
|
| 73 |
+
"normalized": false,
|
| 74 |
+
"rstrip": true,
|
| 75 |
+
"single_word": false,
|
| 76 |
+
"special": true
|
| 77 |
+
},
|
| 78 |
+
"32006": {
|
| 79 |
+
"content": "<|system|>",
|
| 80 |
+
"lstrip": false,
|
| 81 |
+
"normalized": false,
|
| 82 |
+
"rstrip": true,
|
| 83 |
+
"single_word": false,
|
| 84 |
+
"special": true
|
| 85 |
+
},
|
| 86 |
+
"32007": {
|
| 87 |
+
"content": "<|end|>",
|
| 88 |
+
"lstrip": false,
|
| 89 |
+
"normalized": false,
|
| 90 |
+
"rstrip": true,
|
| 91 |
+
"single_word": false,
|
| 92 |
+
"special": true
|
| 93 |
+
},
|
| 94 |
+
"32008": {
|
| 95 |
+
"content": "<|placeholder5|>",
|
| 96 |
+
"lstrip": false,
|
| 97 |
+
"normalized": false,
|
| 98 |
+
"rstrip": true,
|
| 99 |
+
"single_word": false,
|
| 100 |
+
"special": true
|
| 101 |
+
},
|
| 102 |
+
"32009": {
|
| 103 |
+
"content": "<|placeholder6|>",
|
| 104 |
+
"lstrip": false,
|
| 105 |
+
"normalized": false,
|
| 106 |
+
"rstrip": true,
|
| 107 |
+
"single_word": false,
|
| 108 |
+
"special": true
|
| 109 |
+
},
|
| 110 |
+
"32010": {
|
| 111 |
+
"content": "<|user|>",
|
| 112 |
+
"lstrip": false,
|
| 113 |
+
"normalized": false,
|
| 114 |
+
"rstrip": true,
|
| 115 |
+
"single_word": false,
|
| 116 |
+
"special": true
|
| 117 |
+
}
|
| 118 |
+
},
|
| 119 |
+
"bos_token": "<s>",
|
| 120 |
+
"chat_template": "{% for message in messages %}{% if message['role'] == 'system' %}{{'<|system|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'user' %}{{'<|user|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'assistant' %}{{'<|assistant|>\n' + message['content'] + '<|end|>\n'}}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>\n' }}{% else %}{{ eos_token }}{% endif %}",
|
| 121 |
+
"clean_up_tokenization_spaces": false,
|
| 122 |
+
"eos_token": "<|endoftext|>",
|
| 123 |
+
"legacy": false,
|
| 124 |
+
"model_max_length": 2048,
|
| 125 |
+
"pad_token": "<unk>",
|
| 126 |
+
"padding_side": "right",
|
| 127 |
+
"sp_model_kwargs": {},
|
| 128 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 129 |
+
"unk_token": "<unk>",
|
| 130 |
+
"use_default_system_prompt": false
|
| 131 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,2600 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 10.0,
|
| 5 |
+
"eval_steps": 100,
|
| 6 |
+
"global_step": 3860,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.05181347150259067,
|
| 13 |
+
"grad_norm": 0.1298828125,
|
| 14 |
+
"learning_rate": 1.2953367875647668e-07,
|
| 15 |
+
"loss": 1.0187,
|
| 16 |
+
"step": 20
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.10362694300518134,
|
| 20 |
+
"grad_norm": 0.11962890625,
|
| 21 |
+
"learning_rate": 2.5906735751295336e-07,
|
| 22 |
+
"loss": 1.016,
|
| 23 |
+
"step": 40
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.15544041450777202,
|
| 27 |
+
"grad_norm": 0.11962890625,
|
| 28 |
+
"learning_rate": 3.886010362694301e-07,
|
| 29 |
+
"loss": 1.0219,
|
| 30 |
+
"step": 60
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.20725388601036268,
|
| 34 |
+
"grad_norm": 0.11767578125,
|
| 35 |
+
"learning_rate": 5.181347150259067e-07,
|
| 36 |
+
"loss": 1.0164,
|
| 37 |
+
"step": 80
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.25906735751295334,
|
| 41 |
+
"grad_norm": 0.126953125,
|
| 42 |
+
"learning_rate": 6.476683937823834e-07,
|
| 43 |
+
"loss": 1.0119,
|
| 44 |
+
"step": 100
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.25906735751295334,
|
| 48 |
+
"eval_main_loss": 1.0200841426849365,
|
| 49 |
+
"eval_main_runtime": 50.8504,
|
| 50 |
+
"eval_main_samples_per_second": 30.206,
|
| 51 |
+
"eval_main_steps_per_second": 3.776,
|
| 52 |
+
"step": 100
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.25906735751295334,
|
| 56 |
+
"eval_anatomy_loss": 2.9678244590759277,
|
| 57 |
+
"eval_anatomy_runtime": 0.2681,
|
| 58 |
+
"eval_anatomy_samples_per_second": 7.459,
|
| 59 |
+
"eval_anatomy_steps_per_second": 3.729,
|
| 60 |
+
"step": 100
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"epoch": 0.25906735751295334,
|
| 64 |
+
"eval_college_mathematics_loss": 2.1804275512695312,
|
| 65 |
+
"eval_college_mathematics_runtime": 0.2684,
|
| 66 |
+
"eval_college_mathematics_samples_per_second": 7.451,
|
| 67 |
+
"eval_college_mathematics_steps_per_second": 3.726,
|
| 68 |
+
"step": 100
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.25906735751295334,
|
| 72 |
+
"eval_international_law_loss": 3.191988229751587,
|
| 73 |
+
"eval_international_law_runtime": 0.2665,
|
| 74 |
+
"eval_international_law_samples_per_second": 7.505,
|
| 75 |
+
"eval_international_law_steps_per_second": 3.752,
|
| 76 |
+
"step": 100
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"epoch": 0.31088082901554404,
|
| 80 |
+
"grad_norm": 0.12890625,
|
| 81 |
+
"learning_rate": 7.772020725388602e-07,
|
| 82 |
+
"loss": 1.0155,
|
| 83 |
+
"step": 120
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"epoch": 0.3626943005181347,
|
| 87 |
+
"grad_norm": 0.134765625,
|
| 88 |
+
"learning_rate": 9.067357512953369e-07,
|
| 89 |
+
"loss": 1.022,
|
| 90 |
+
"step": 140
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 0.41450777202072536,
|
| 94 |
+
"grad_norm": 0.1328125,
|
| 95 |
+
"learning_rate": 1.0362694300518134e-06,
|
| 96 |
+
"loss": 1.0071,
|
| 97 |
+
"step": 160
|
| 98 |
+
},
|
| 99 |
+
{
|
| 100 |
+
"epoch": 0.46632124352331605,
|
| 101 |
+
"grad_norm": 0.13671875,
|
| 102 |
+
"learning_rate": 1.1658031088082903e-06,
|
| 103 |
+
"loss": 1.0226,
|
| 104 |
+
"step": 180
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.5181347150259067,
|
| 108 |
+
"grad_norm": 0.1494140625,
|
| 109 |
+
"learning_rate": 1.2953367875647669e-06,
|
| 110 |
+
"loss": 1.0175,
|
| 111 |
+
"step": 200
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 0.5181347150259067,
|
| 115 |
+
"eval_main_loss": 1.017417311668396,
|
| 116 |
+
"eval_main_runtime": 50.9406,
|
| 117 |
+
"eval_main_samples_per_second": 30.153,
|
| 118 |
+
"eval_main_steps_per_second": 3.769,
|
| 119 |
+
"step": 200
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 0.5181347150259067,
|
| 123 |
+
"eval_anatomy_loss": 2.9614720344543457,
|
| 124 |
+
"eval_anatomy_runtime": 0.2677,
|
| 125 |
+
"eval_anatomy_samples_per_second": 7.471,
|
| 126 |
+
"eval_anatomy_steps_per_second": 3.735,
|
| 127 |
+
"step": 200
|
| 128 |
+
},
|
| 129 |
+
{
|
| 130 |
+
"epoch": 0.5181347150259067,
|
| 131 |
+
"eval_college_mathematics_loss": 2.1731653213500977,
|
| 132 |
+
"eval_college_mathematics_runtime": 0.2679,
|
| 133 |
+
"eval_college_mathematics_samples_per_second": 7.466,
|
| 134 |
+
"eval_college_mathematics_steps_per_second": 3.733,
|
| 135 |
+
"step": 200
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.5181347150259067,
|
| 139 |
+
"eval_international_law_loss": 3.1835579872131348,
|
| 140 |
+
"eval_international_law_runtime": 0.2687,
|
| 141 |
+
"eval_international_law_samples_per_second": 7.443,
|
| 142 |
+
"eval_international_law_steps_per_second": 3.722,
|
| 143 |
+
"step": 200
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.5699481865284974,
|
| 147 |
+
"grad_norm": 0.1591796875,
|
| 148 |
+
"learning_rate": 1.4248704663212437e-06,
|
| 149 |
+
"loss": 1.0125,
|
| 150 |
+
"step": 220
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.6217616580310881,
|
| 154 |
+
"grad_norm": 0.1767578125,
|
| 155 |
+
"learning_rate": 1.5544041450777204e-06,
|
| 156 |
+
"loss": 1.0142,
|
| 157 |
+
"step": 240
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.6735751295336787,
|
| 161 |
+
"grad_norm": 0.1728515625,
|
| 162 |
+
"learning_rate": 1.683937823834197e-06,
|
| 163 |
+
"loss": 1.0175,
|
| 164 |
+
"step": 260
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.7253886010362695,
|
| 168 |
+
"grad_norm": 0.205078125,
|
| 169 |
+
"learning_rate": 1.8134715025906738e-06,
|
| 170 |
+
"loss": 1.0147,
|
| 171 |
+
"step": 280
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.7772020725388601,
|
| 175 |
+
"grad_norm": 0.2294921875,
|
| 176 |
+
"learning_rate": 1.9430051813471504e-06,
|
| 177 |
+
"loss": 1.0072,
|
| 178 |
+
"step": 300
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.7772020725388601,
|
| 182 |
+
"eval_main_loss": 1.0116238594055176,
|
| 183 |
+
"eval_main_runtime": 50.9159,
|
| 184 |
+
"eval_main_samples_per_second": 30.167,
|
| 185 |
+
"eval_main_steps_per_second": 3.771,
|
| 186 |
+
"step": 300
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 0.7772020725388601,
|
| 190 |
+
"eval_anatomy_loss": 2.944845676422119,
|
| 191 |
+
"eval_anatomy_runtime": 0.2687,
|
| 192 |
+
"eval_anatomy_samples_per_second": 7.443,
|
| 193 |
+
"eval_anatomy_steps_per_second": 3.721,
|
| 194 |
+
"step": 300
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 0.7772020725388601,
|
| 198 |
+
"eval_college_mathematics_loss": 2.1590933799743652,
|
| 199 |
+
"eval_college_mathematics_runtime": 0.2683,
|
| 200 |
+
"eval_college_mathematics_samples_per_second": 7.455,
|
| 201 |
+
"eval_college_mathematics_steps_per_second": 3.727,
|
| 202 |
+
"step": 300
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 0.7772020725388601,
|
| 206 |
+
"eval_international_law_loss": 3.1690821647644043,
|
| 207 |
+
"eval_international_law_runtime": 0.2666,
|
| 208 |
+
"eval_international_law_samples_per_second": 7.501,
|
| 209 |
+
"eval_international_law_steps_per_second": 3.75,
|
| 210 |
+
"step": 300
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 0.8290155440414507,
|
| 214 |
+
"grad_norm": 0.26171875,
|
| 215 |
+
"learning_rate": 2.072538860103627e-06,
|
| 216 |
+
"loss": 1.017,
|
| 217 |
+
"step": 320
|
| 218 |
+
},
|
| 219 |
+
{
|
| 220 |
+
"epoch": 0.8808290155440415,
|
| 221 |
+
"grad_norm": 0.265625,
|
| 222 |
+
"learning_rate": 2.2020725388601037e-06,
|
| 223 |
+
"loss": 1.0084,
|
| 224 |
+
"step": 340
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 0.9326424870466321,
|
| 228 |
+
"grad_norm": 0.283203125,
|
| 229 |
+
"learning_rate": 2.3316062176165805e-06,
|
| 230 |
+
"loss": 1.0008,
|
| 231 |
+
"step": 360
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 0.9844559585492227,
|
| 235 |
+
"grad_norm": 0.283203125,
|
| 236 |
+
"learning_rate": 2.461139896373057e-06,
|
| 237 |
+
"loss": 1.0035,
|
| 238 |
+
"step": 380
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"epoch": 1.0362694300518134,
|
| 242 |
+
"grad_norm": 0.35546875,
|
| 243 |
+
"learning_rate": 2.5906735751295338e-06,
|
| 244 |
+
"loss": 1.0034,
|
| 245 |
+
"step": 400
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 1.0362694300518134,
|
| 249 |
+
"eval_main_loss": 1.0014457702636719,
|
| 250 |
+
"eval_main_runtime": 50.699,
|
| 251 |
+
"eval_main_samples_per_second": 30.296,
|
| 252 |
+
"eval_main_steps_per_second": 3.787,
|
| 253 |
+
"step": 400
|
| 254 |
+
},
|
| 255 |
+
{
|
| 256 |
+
"epoch": 1.0362694300518134,
|
| 257 |
+
"eval_anatomy_loss": 2.91424298286438,
|
| 258 |
+
"eval_anatomy_runtime": 0.2675,
|
| 259 |
+
"eval_anatomy_samples_per_second": 7.475,
|
| 260 |
+
"eval_anatomy_steps_per_second": 3.738,
|
| 261 |
+
"step": 400
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 1.0362694300518134,
|
| 265 |
+
"eval_college_mathematics_loss": 2.136711597442627,
|
| 266 |
+
"eval_college_mathematics_runtime": 0.2681,
|
| 267 |
+
"eval_college_mathematics_samples_per_second": 7.46,
|
| 268 |
+
"eval_college_mathematics_steps_per_second": 3.73,
|
| 269 |
+
"step": 400
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 1.0362694300518134,
|
| 273 |
+
"eval_international_law_loss": 3.133229970932007,
|
| 274 |
+
"eval_international_law_runtime": 0.2663,
|
| 275 |
+
"eval_international_law_samples_per_second": 7.511,
|
| 276 |
+
"eval_international_law_steps_per_second": 3.755,
|
| 277 |
+
"step": 400
|
| 278 |
+
},
|
| 279 |
+
{
|
| 280 |
+
"epoch": 1.0880829015544042,
|
| 281 |
+
"grad_norm": 0.361328125,
|
| 282 |
+
"learning_rate": 2.7202072538860106e-06,
|
| 283 |
+
"loss": 0.9984,
|
| 284 |
+
"step": 420
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 1.1398963730569949,
|
| 288 |
+
"grad_norm": 0.373046875,
|
| 289 |
+
"learning_rate": 2.8497409326424875e-06,
|
| 290 |
+
"loss": 0.9973,
|
| 291 |
+
"step": 440
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 1.1917098445595855,
|
| 295 |
+
"grad_norm": 0.46484375,
|
| 296 |
+
"learning_rate": 2.979274611398964e-06,
|
| 297 |
+
"loss": 0.9898,
|
| 298 |
+
"step": 460
|
| 299 |
+
},
|
| 300 |
+
{
|
| 301 |
+
"epoch": 1.2435233160621761,
|
| 302 |
+
"grad_norm": 0.462890625,
|
| 303 |
+
"learning_rate": 3.1088082901554407e-06,
|
| 304 |
+
"loss": 0.9841,
|
| 305 |
+
"step": 480
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 1.2953367875647668,
|
| 309 |
+
"grad_norm": 0.498046875,
|
| 310 |
+
"learning_rate": 3.238341968911917e-06,
|
| 311 |
+
"loss": 0.9908,
|
| 312 |
+
"step": 500
|
| 313 |
+
},
|
| 314 |
+
{
|
| 315 |
+
"epoch": 1.2953367875647668,
|
| 316 |
+
"eval_main_loss": 0.9807333946228027,
|
| 317 |
+
"eval_main_runtime": 50.6947,
|
| 318 |
+
"eval_main_samples_per_second": 30.299,
|
| 319 |
+
"eval_main_steps_per_second": 3.787,
|
| 320 |
+
"step": 500
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 1.2953367875647668,
|
| 324 |
+
"eval_anatomy_loss": 2.860694408416748,
|
| 325 |
+
"eval_anatomy_runtime": 0.2674,
|
| 326 |
+
"eval_anatomy_samples_per_second": 7.479,
|
| 327 |
+
"eval_anatomy_steps_per_second": 3.739,
|
| 328 |
+
"step": 500
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"epoch": 1.2953367875647668,
|
| 332 |
+
"eval_college_mathematics_loss": 2.0933423042297363,
|
| 333 |
+
"eval_college_mathematics_runtime": 0.2663,
|
| 334 |
+
"eval_college_mathematics_samples_per_second": 7.51,
|
| 335 |
+
"eval_college_mathematics_steps_per_second": 3.755,
|
| 336 |
+
"step": 500
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 1.2953367875647668,
|
| 340 |
+
"eval_international_law_loss": 3.0646896362304688,
|
| 341 |
+
"eval_international_law_runtime": 0.2664,
|
| 342 |
+
"eval_international_law_samples_per_second": 7.506,
|
| 343 |
+
"eval_international_law_steps_per_second": 3.753,
|
| 344 |
+
"step": 500
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 1.3471502590673574,
|
| 348 |
+
"grad_norm": 0.56640625,
|
| 349 |
+
"learning_rate": 3.367875647668394e-06,
|
| 350 |
+
"loss": 0.9792,
|
| 351 |
+
"step": 520
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 1.3989637305699483,
|
| 355 |
+
"grad_norm": 0.56640625,
|
| 356 |
+
"learning_rate": 3.497409326424871e-06,
|
| 357 |
+
"loss": 0.9697,
|
| 358 |
+
"step": 540
|
| 359 |
+
},
|
| 360 |
+
{
|
| 361 |
+
"epoch": 1.450777202072539,
|
| 362 |
+
"grad_norm": 0.5234375,
|
| 363 |
+
"learning_rate": 3.6269430051813476e-06,
|
| 364 |
+
"loss": 0.9604,
|
| 365 |
+
"step": 560
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"epoch": 1.5025906735751295,
|
| 369 |
+
"grad_norm": 0.50390625,
|
| 370 |
+
"learning_rate": 3.756476683937824e-06,
|
| 371 |
+
"loss": 0.9549,
|
| 372 |
+
"step": 580
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"epoch": 1.5544041450777202,
|
| 376 |
+
"grad_norm": 0.59375,
|
| 377 |
+
"learning_rate": 3.886010362694301e-06,
|
| 378 |
+
"loss": 0.9634,
|
| 379 |
+
"step": 600
|
| 380 |
+
},
|
| 381 |
+
{
|
| 382 |
+
"epoch": 1.5544041450777202,
|
| 383 |
+
"eval_main_loss": 0.9588530659675598,
|
| 384 |
+
"eval_main_runtime": 50.8939,
|
| 385 |
+
"eval_main_samples_per_second": 30.18,
|
| 386 |
+
"eval_main_steps_per_second": 3.773,
|
| 387 |
+
"step": 600
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 1.5544041450777202,
|
| 391 |
+
"eval_anatomy_loss": 2.800969123840332,
|
| 392 |
+
"eval_anatomy_runtime": 0.268,
|
| 393 |
+
"eval_anatomy_samples_per_second": 7.464,
|
| 394 |
+
"eval_anatomy_steps_per_second": 3.732,
|
| 395 |
+
"step": 600
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 1.5544041450777202,
|
| 399 |
+
"eval_college_mathematics_loss": 2.0425174236297607,
|
| 400 |
+
"eval_college_mathematics_runtime": 0.2684,
|
| 401 |
+
"eval_college_mathematics_samples_per_second": 7.452,
|
| 402 |
+
"eval_college_mathematics_steps_per_second": 3.726,
|
| 403 |
+
"step": 600
|
| 404 |
+
},
|
| 405 |
+
{
|
| 406 |
+
"epoch": 1.5544041450777202,
|
| 407 |
+
"eval_international_law_loss": 2.9860198497772217,
|
| 408 |
+
"eval_international_law_runtime": 0.2678,
|
| 409 |
+
"eval_international_law_samples_per_second": 7.467,
|
| 410 |
+
"eval_international_law_steps_per_second": 3.734,
|
| 411 |
+
"step": 600
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 1.6062176165803108,
|
| 415 |
+
"grad_norm": 0.59765625,
|
| 416 |
+
"learning_rate": 4.015544041450777e-06,
|
| 417 |
+
"loss": 0.9551,
|
| 418 |
+
"step": 620
|
| 419 |
+
},
|
| 420 |
+
{
|
| 421 |
+
"epoch": 1.6580310880829017,
|
| 422 |
+
"grad_norm": 0.640625,
|
| 423 |
+
"learning_rate": 4.145077720207254e-06,
|
| 424 |
+
"loss": 0.9462,
|
| 425 |
+
"step": 640
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 1.709844559585492,
|
| 429 |
+
"grad_norm": 0.51953125,
|
| 430 |
+
"learning_rate": 4.274611398963731e-06,
|
| 431 |
+
"loss": 0.9398,
|
| 432 |
+
"step": 660
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 1.761658031088083,
|
| 436 |
+
"grad_norm": 0.490234375,
|
| 437 |
+
"learning_rate": 4.404145077720207e-06,
|
| 438 |
+
"loss": 0.9289,
|
| 439 |
+
"step": 680
|
| 440 |
+
},
|
| 441 |
+
{
|
| 442 |
+
"epoch": 1.8134715025906736,
|
| 443 |
+
"grad_norm": 0.4921875,
|
| 444 |
+
"learning_rate": 4.533678756476685e-06,
|
| 445 |
+
"loss": 0.9209,
|
| 446 |
+
"step": 700
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 1.8134715025906736,
|
| 450 |
+
"eval_main_loss": 0.9181744456291199,
|
| 451 |
+
"eval_main_runtime": 50.9128,
|
| 452 |
+
"eval_main_samples_per_second": 30.169,
|
| 453 |
+
"eval_main_steps_per_second": 3.771,
|
| 454 |
+
"step": 700
|
| 455 |
+
},
|
| 456 |
+
{
|
| 457 |
+
"epoch": 1.8134715025906736,
|
| 458 |
+
"eval_anatomy_loss": 2.6760823726654053,
|
| 459 |
+
"eval_anatomy_runtime": 0.2694,
|
| 460 |
+
"eval_anatomy_samples_per_second": 7.423,
|
| 461 |
+
"eval_anatomy_steps_per_second": 3.711,
|
| 462 |
+
"step": 700
|
| 463 |
+
},
|
| 464 |
+
{
|
| 465 |
+
"epoch": 1.8134715025906736,
|
| 466 |
+
"eval_college_mathematics_loss": 1.9530092477798462,
|
| 467 |
+
"eval_college_mathematics_runtime": 0.2669,
|
| 468 |
+
"eval_college_mathematics_samples_per_second": 7.494,
|
| 469 |
+
"eval_college_mathematics_steps_per_second": 3.747,
|
| 470 |
+
"step": 700
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 1.8134715025906736,
|
| 474 |
+
"eval_international_law_loss": 2.8536064624786377,
|
| 475 |
+
"eval_international_law_runtime": 0.268,
|
| 476 |
+
"eval_international_law_samples_per_second": 7.462,
|
| 477 |
+
"eval_international_law_steps_per_second": 3.731,
|
| 478 |
+
"step": 700
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 1.8652849740932642,
|
| 482 |
+
"grad_norm": 0.435546875,
|
| 483 |
+
"learning_rate": 4.663212435233161e-06,
|
| 484 |
+
"loss": 0.9132,
|
| 485 |
+
"step": 720
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 1.917098445595855,
|
| 489 |
+
"grad_norm": 0.45703125,
|
| 490 |
+
"learning_rate": 4.7927461139896375e-06,
|
| 491 |
+
"loss": 0.8982,
|
| 492 |
+
"step": 740
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 1.9689119170984455,
|
| 496 |
+
"grad_norm": 0.42578125,
|
| 497 |
+
"learning_rate": 4.922279792746114e-06,
|
| 498 |
+
"loss": 0.898,
|
| 499 |
+
"step": 760
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 2.0207253886010363,
|
| 503 |
+
"grad_norm": 0.451171875,
|
| 504 |
+
"learning_rate": 4.9999171995395824e-06,
|
| 505 |
+
"loss": 0.8827,
|
| 506 |
+
"step": 780
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 2.0725388601036268,
|
| 510 |
+
"grad_norm": 0.41015625,
|
| 511 |
+
"learning_rate": 4.9989857573474595e-06,
|
| 512 |
+
"loss": 0.8667,
|
| 513 |
+
"step": 800
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 2.0725388601036268,
|
| 517 |
+
"eval_main_loss": 0.8773276209831238,
|
| 518 |
+
"eval_main_runtime": 50.6915,
|
| 519 |
+
"eval_main_samples_per_second": 30.301,
|
| 520 |
+
"eval_main_steps_per_second": 3.788,
|
| 521 |
+
"step": 800
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 2.0725388601036268,
|
| 525 |
+
"eval_anatomy_loss": 2.5175046920776367,
|
| 526 |
+
"eval_anatomy_runtime": 0.2667,
|
| 527 |
+
"eval_anatomy_samples_per_second": 7.498,
|
| 528 |
+
"eval_anatomy_steps_per_second": 3.749,
|
| 529 |
+
"step": 800
|
| 530 |
+
},
|
| 531 |
+
{
|
| 532 |
+
"epoch": 2.0725388601036268,
|
| 533 |
+
"eval_college_mathematics_loss": 1.8391788005828857,
|
| 534 |
+
"eval_college_mathematics_runtime": 0.2681,
|
| 535 |
+
"eval_college_mathematics_samples_per_second": 7.459,
|
| 536 |
+
"eval_college_mathematics_steps_per_second": 3.73,
|
| 537 |
+
"step": 800
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 2.0725388601036268,
|
| 541 |
+
"eval_international_law_loss": 2.7238972187042236,
|
| 542 |
+
"eval_international_law_runtime": 0.2657,
|
| 543 |
+
"eval_international_law_samples_per_second": 7.529,
|
| 544 |
+
"eval_international_law_steps_per_second": 3.764,
|
| 545 |
+
"step": 800
|
| 546 |
+
},
|
| 547 |
+
{
|
| 548 |
+
"epoch": 2.1243523316062176,
|
| 549 |
+
"grad_norm": 0.3984375,
|
| 550 |
+
"learning_rate": 4.997019759281217e-06,
|
| 551 |
+
"loss": 0.8706,
|
| 552 |
+
"step": 820
|
| 553 |
+
},
|
| 554 |
+
{
|
| 555 |
+
"epoch": 2.1761658031088085,
|
| 556 |
+
"grad_norm": 0.38671875,
|
| 557 |
+
"learning_rate": 4.9940200192449906e-06,
|
| 558 |
+
"loss": 0.8744,
|
| 559 |
+
"step": 840
|
| 560 |
+
},
|
| 561 |
+
{
|
| 562 |
+
"epoch": 2.227979274611399,
|
| 563 |
+
"grad_norm": 0.349609375,
|
| 564 |
+
"learning_rate": 4.989987779102074e-06,
|
| 565 |
+
"loss": 0.8583,
|
| 566 |
+
"step": 860
|
| 567 |
+
},
|
| 568 |
+
{
|
| 569 |
+
"epoch": 2.2797927461139897,
|
| 570 |
+
"grad_norm": 0.330078125,
|
| 571 |
+
"learning_rate": 4.984924708160789e-06,
|
| 572 |
+
"loss": 0.8637,
|
| 573 |
+
"step": 880
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 2.33160621761658,
|
| 577 |
+
"grad_norm": 0.296875,
|
| 578 |
+
"learning_rate": 4.978832902483415e-06,
|
| 579 |
+
"loss": 0.8592,
|
| 580 |
+
"step": 900
|
| 581 |
+
},
|
| 582 |
+
{
|
| 583 |
+
"epoch": 2.33160621761658,
|
| 584 |
+
"eval_main_loss": 0.8600960373878479,
|
| 585 |
+
"eval_main_runtime": 50.6644,
|
| 586 |
+
"eval_main_samples_per_second": 30.317,
|
| 587 |
+
"eval_main_steps_per_second": 3.79,
|
| 588 |
+
"step": 900
|
| 589 |
+
},
|
| 590 |
+
{
|
| 591 |
+
"epoch": 2.33160621761658,
|
| 592 |
+
"eval_anatomy_loss": 2.4422662258148193,
|
| 593 |
+
"eval_anatomy_runtime": 0.2671,
|
| 594 |
+
"eval_anatomy_samples_per_second": 7.488,
|
| 595 |
+
"eval_anatomy_steps_per_second": 3.744,
|
| 596 |
+
"step": 900
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 2.33160621761658,
|
| 600 |
+
"eval_college_mathematics_loss": 1.7872785329818726,
|
| 601 |
+
"eval_college_mathematics_runtime": 0.267,
|
| 602 |
+
"eval_college_mathematics_samples_per_second": 7.492,
|
| 603 |
+
"eval_college_mathematics_steps_per_second": 3.746,
|
| 604 |
+
"step": 900
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 2.33160621761658,
|
| 608 |
+
"eval_international_law_loss": 2.6731436252593994,
|
| 609 |
+
"eval_international_law_runtime": 0.2664,
|
| 610 |
+
"eval_international_law_samples_per_second": 7.508,
|
| 611 |
+
"eval_international_law_steps_per_second": 3.754,
|
| 612 |
+
"step": 900
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 2.383419689119171,
|
| 616 |
+
"grad_norm": 0.326171875,
|
| 617 |
+
"learning_rate": 4.971714884018439e-06,
|
| 618 |
+
"loss": 0.8623,
|
| 619 |
+
"step": 920
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 2.4352331606217614,
|
| 623 |
+
"grad_norm": 0.291015625,
|
| 624 |
+
"learning_rate": 4.96357359955649e-06,
|
| 625 |
+
"loss": 0.8496,
|
| 626 |
+
"step": 940
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 2.4870466321243523,
|
| 630 |
+
"grad_norm": 0.29296875,
|
| 631 |
+
"learning_rate": 4.9544124195104015e-06,
|
| 632 |
+
"loss": 0.8595,
|
| 633 |
+
"step": 960
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 2.538860103626943,
|
| 637 |
+
"grad_norm": 0.296875,
|
| 638 |
+
"learning_rate": 4.944235136519888e-06,
|
| 639 |
+
"loss": 0.8512,
|
| 640 |
+
"step": 980
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 2.5906735751295336,
|
| 644 |
+
"grad_norm": 0.265625,
|
| 645 |
+
"learning_rate": 4.933045963881431e-06,
|
| 646 |
+
"loss": 0.8522,
|
| 647 |
+
"step": 1000
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 2.5906735751295336,
|
| 651 |
+
"eval_main_loss": 0.8523173928260803,
|
| 652 |
+
"eval_main_runtime": 50.9143,
|
| 653 |
+
"eval_main_samples_per_second": 30.168,
|
| 654 |
+
"eval_main_steps_per_second": 3.771,
|
| 655 |
+
"step": 1000
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 2.5906735751295336,
|
| 659 |
+
"eval_anatomy_loss": 2.420971632003784,
|
| 660 |
+
"eval_anatomy_runtime": 0.2681,
|
| 661 |
+
"eval_anatomy_samples_per_second": 7.459,
|
| 662 |
+
"eval_anatomy_steps_per_second": 3.729,
|
| 663 |
+
"step": 1000
|
| 664 |
+
},
|
| 665 |
+
{
|
| 666 |
+
"epoch": 2.5906735751295336,
|
| 667 |
+
"eval_college_mathematics_loss": 1.7655620574951172,
|
| 668 |
+
"eval_college_mathematics_runtime": 0.2683,
|
| 669 |
+
"eval_college_mathematics_samples_per_second": 7.454,
|
| 670 |
+
"eval_college_mathematics_steps_per_second": 3.727,
|
| 671 |
+
"step": 1000
|
| 672 |
+
},
|
| 673 |
+
{
|
| 674 |
+
"epoch": 2.5906735751295336,
|
| 675 |
+
"eval_international_law_loss": 2.6557209491729736,
|
| 676 |
+
"eval_international_law_runtime": 0.2675,
|
| 677 |
+
"eval_international_law_samples_per_second": 7.475,
|
| 678 |
+
"eval_international_law_steps_per_second": 3.738,
|
| 679 |
+
"step": 1000
|
| 680 |
+
},
|
| 681 |
+
{
|
| 682 |
+
"epoch": 2.6424870466321244,
|
| 683 |
+
"grad_norm": 0.263671875,
|
| 684 |
+
"learning_rate": 4.920849533804017e-06,
|
| 685 |
+
"loss": 0.8525,
|
| 686 |
+
"step": 1020
|
| 687 |
+
},
|
| 688 |
+
{
|
| 689 |
+
"epoch": 2.694300518134715,
|
| 690 |
+
"grad_norm": 0.275390625,
|
| 691 |
+
"learning_rate": 4.907650895491443e-06,
|
| 692 |
+
"loss": 0.8554,
|
| 693 |
+
"step": 1040
|
| 694 |
+
},
|
| 695 |
+
{
|
| 696 |
+
"epoch": 2.7461139896373057,
|
| 697 |
+
"grad_norm": 0.2421875,
|
| 698 |
+
"learning_rate": 4.893455513052003e-06,
|
| 699 |
+
"loss": 0.8489,
|
| 700 |
+
"step": 1060
|
| 701 |
+
},
|
| 702 |
+
{
|
| 703 |
+
"epoch": 2.7979274611398965,
|
| 704 |
+
"grad_norm": 0.25,
|
| 705 |
+
"learning_rate": 4.878269263236391e-06,
|
| 706 |
+
"loss": 0.844,
|
| 707 |
+
"step": 1080
|
| 708 |
+
},
|
| 709 |
+
{
|
| 710 |
+
"epoch": 2.849740932642487,
|
| 711 |
+
"grad_norm": 0.275390625,
|
| 712 |
+
"learning_rate": 4.86209843300479e-06,
|
| 713 |
+
"loss": 0.8456,
|
| 714 |
+
"step": 1100
|
| 715 |
+
},
|
| 716 |
+
{
|
| 717 |
+
"epoch": 2.849740932642487,
|
| 718 |
+
"eval_main_loss": 0.8472149968147278,
|
| 719 |
+
"eval_main_runtime": 50.8752,
|
| 720 |
+
"eval_main_samples_per_second": 30.192,
|
| 721 |
+
"eval_main_steps_per_second": 3.774,
|
| 722 |
+
"step": 1100
|
| 723 |
+
},
|
| 724 |
+
{
|
| 725 |
+
"epoch": 2.849740932642487,
|
| 726 |
+
"eval_anatomy_loss": 2.407443046569824,
|
| 727 |
+
"eval_anatomy_runtime": 0.2673,
|
| 728 |
+
"eval_anatomy_samples_per_second": 7.481,
|
| 729 |
+
"eval_anatomy_steps_per_second": 3.741,
|
| 730 |
+
"step": 1100
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 2.849740932642487,
|
| 734 |
+
"eval_college_mathematics_loss": 1.7581956386566162,
|
| 735 |
+
"eval_college_mathematics_runtime": 0.2664,
|
| 736 |
+
"eval_college_mathematics_samples_per_second": 7.507,
|
| 737 |
+
"eval_college_mathematics_steps_per_second": 3.753,
|
| 738 |
+
"step": 1100
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 2.849740932642487,
|
| 742 |
+
"eval_international_law_loss": 2.643361806869507,
|
| 743 |
+
"eval_international_law_runtime": 0.266,
|
| 744 |
+
"eval_international_law_samples_per_second": 7.518,
|
| 745 |
+
"eval_international_law_steps_per_second": 3.759,
|
| 746 |
+
"step": 1100
|
| 747 |
+
},
|
| 748 |
+
{
|
| 749 |
+
"epoch": 2.901554404145078,
|
| 750 |
+
"grad_norm": 0.2412109375,
|
| 751 |
+
"learning_rate": 4.8449497169241285e-06,
|
| 752 |
+
"loss": 0.847,
|
| 753 |
+
"step": 1120
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 2.9533678756476682,
|
| 757 |
+
"grad_norm": 0.248046875,
|
| 758 |
+
"learning_rate": 4.826830214396594e-06,
|
| 759 |
+
"loss": 0.8444,
|
| 760 |
+
"step": 1140
|
| 761 |
+
},
|
| 762 |
+
{
|
| 763 |
+
"epoch": 3.005181347150259,
|
| 764 |
+
"grad_norm": 0.2490234375,
|
| 765 |
+
"learning_rate": 4.807747426720553e-06,
|
| 766 |
+
"loss": 0.8454,
|
| 767 |
+
"step": 1160
|
| 768 |
+
},
|
| 769 |
+
{
|
| 770 |
+
"epoch": 3.05699481865285,
|
| 771 |
+
"grad_norm": 0.2431640625,
|
| 772 |
+
"learning_rate": 4.78770925398508e-06,
|
| 773 |
+
"loss": 0.8409,
|
| 774 |
+
"step": 1180
|
| 775 |
+
},
|
| 776 |
+
{
|
| 777 |
+
"epoch": 3.1088082901554404,
|
| 778 |
+
"grad_norm": 0.25390625,
|
| 779 |
+
"learning_rate": 4.766723991799407e-06,
|
| 780 |
+
"loss": 0.8392,
|
| 781 |
+
"step": 1200
|
| 782 |
+
},
|
| 783 |
+
{
|
| 784 |
+
"epoch": 3.1088082901554404,
|
| 785 |
+
"eval_main_loss": 0.8436682820320129,
|
| 786 |
+
"eval_main_runtime": 50.6014,
|
| 787 |
+
"eval_main_samples_per_second": 30.355,
|
| 788 |
+
"eval_main_steps_per_second": 3.794,
|
| 789 |
+
"step": 1200
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 3.1088082901554404,
|
| 793 |
+
"eval_anatomy_loss": 2.3988683223724365,
|
| 794 |
+
"eval_anatomy_runtime": 0.2661,
|
| 795 |
+
"eval_anatomy_samples_per_second": 7.517,
|
| 796 |
+
"eval_anatomy_steps_per_second": 3.758,
|
| 797 |
+
"step": 1200
|
| 798 |
+
},
|
| 799 |
+
{
|
| 800 |
+
"epoch": 3.1088082901554404,
|
| 801 |
+
"eval_college_mathematics_loss": 1.7500412464141846,
|
| 802 |
+
"eval_college_mathematics_runtime": 0.2666,
|
| 803 |
+
"eval_college_mathematics_samples_per_second": 7.502,
|
| 804 |
+
"eval_college_mathematics_steps_per_second": 3.751,
|
| 805 |
+
"step": 1200
|
| 806 |
+
},
|
| 807 |
+
{
|
| 808 |
+
"epoch": 3.1088082901554404,
|
| 809 |
+
"eval_international_law_loss": 2.639014482498169,
|
| 810 |
+
"eval_international_law_runtime": 0.2661,
|
| 811 |
+
"eval_international_law_samples_per_second": 7.517,
|
| 812 |
+
"eval_international_law_steps_per_second": 3.759,
|
| 813 |
+
"step": 1200
|
| 814 |
+
},
|
| 815 |
+
{
|
| 816 |
+
"epoch": 3.160621761658031,
|
| 817 |
+
"grad_norm": 0.2109375,
|
| 818 |
+
"learning_rate": 4.744800327858608e-06,
|
| 819 |
+
"loss": 0.8409,
|
| 820 |
+
"step": 1220
|
| 821 |
+
},
|
| 822 |
+
{
|
| 823 |
+
"epoch": 3.2124352331606216,
|
| 824 |
+
"grad_norm": 0.255859375,
|
| 825 |
+
"learning_rate": 4.721947338346993e-06,
|
| 826 |
+
"loss": 0.8413,
|
| 827 |
+
"step": 1240
|
| 828 |
+
},
|
| 829 |
+
{
|
| 830 |
+
"epoch": 3.2642487046632125,
|
| 831 |
+
"grad_norm": 0.2197265625,
|
| 832 |
+
"learning_rate": 4.698174484180641e-06,
|
| 833 |
+
"loss": 0.8364,
|
| 834 |
+
"step": 1260
|
| 835 |
+
},
|
| 836 |
+
{
|
| 837 |
+
"epoch": 3.3160621761658033,
|
| 838 |
+
"grad_norm": 0.236328125,
|
| 839 |
+
"learning_rate": 4.673491607090684e-06,
|
| 840 |
+
"loss": 0.8351,
|
| 841 |
+
"step": 1280
|
| 842 |
+
},
|
| 843 |
+
{
|
| 844 |
+
"epoch": 3.3678756476683938,
|
| 845 |
+
"grad_norm": 0.2158203125,
|
| 846 |
+
"learning_rate": 4.647908925548918e-06,
|
| 847 |
+
"loss": 0.8354,
|
| 848 |
+
"step": 1300
|
| 849 |
+
},
|
| 850 |
+
{
|
| 851 |
+
"epoch": 3.3678756476683938,
|
| 852 |
+
"eval_main_loss": 0.8413074016571045,
|
| 853 |
+
"eval_main_runtime": 50.8355,
|
| 854 |
+
"eval_main_samples_per_second": 30.215,
|
| 855 |
+
"eval_main_steps_per_second": 3.777,
|
| 856 |
+
"step": 1300
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 3.3678756476683938,
|
| 860 |
+
"eval_anatomy_loss": 2.3927080631256104,
|
| 861 |
+
"eval_anatomy_runtime": 0.2684,
|
| 862 |
+
"eval_anatomy_samples_per_second": 7.451,
|
| 863 |
+
"eval_anatomy_steps_per_second": 3.725,
|
| 864 |
+
"step": 1300
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 3.3678756476683938,
|
| 868 |
+
"eval_college_mathematics_loss": 1.7482649087905884,
|
| 869 |
+
"eval_college_mathematics_runtime": 0.2673,
|
| 870 |
+
"eval_college_mathematics_samples_per_second": 7.482,
|
| 871 |
+
"eval_college_mathematics_steps_per_second": 3.741,
|
| 872 |
+
"step": 1300
|
| 873 |
+
},
|
| 874 |
+
{
|
| 875 |
+
"epoch": 3.3678756476683938,
|
| 876 |
+
"eval_international_law_loss": 2.6322338581085205,
|
| 877 |
+
"eval_international_law_runtime": 0.2677,
|
| 878 |
+
"eval_international_law_samples_per_second": 7.47,
|
| 879 |
+
"eval_international_law_steps_per_second": 3.735,
|
| 880 |
+
"step": 1300
|
| 881 |
+
},
|
| 882 |
+
{
|
| 883 |
+
"epoch": 3.4196891191709846,
|
| 884 |
+
"grad_norm": 0.236328125,
|
| 885 |
+
"learning_rate": 4.621437030537461e-06,
|
| 886 |
+
"loss": 0.8428,
|
| 887 |
+
"step": 1320
|
| 888 |
+
},
|
| 889 |
+
{
|
| 890 |
+
"epoch": 3.471502590673575,
|
| 891 |
+
"grad_norm": 0.232421875,
|
| 892 |
+
"learning_rate": 4.594086881164184e-06,
|
| 893 |
+
"loss": 0.8495,
|
| 894 |
+
"step": 1340
|
| 895 |
+
},
|
| 896 |
+
{
|
| 897 |
+
"epoch": 3.523316062176166,
|
| 898 |
+
"grad_norm": 0.244140625,
|
| 899 |
+
"learning_rate": 4.565869800125747e-06,
|
| 900 |
+
"loss": 0.8445,
|
| 901 |
+
"step": 1360
|
| 902 |
+
},
|
| 903 |
+
{
|
| 904 |
+
"epoch": 3.5751295336787567,
|
| 905 |
+
"grad_norm": 0.2314453125,
|
| 906 |
+
"learning_rate": 4.536797469020116e-06,
|
| 907 |
+
"loss": 0.8441,
|
| 908 |
+
"step": 1380
|
| 909 |
+
},
|
| 910 |
+
{
|
| 911 |
+
"epoch": 3.626943005181347,
|
| 912 |
+
"grad_norm": 0.220703125,
|
| 913 |
+
"learning_rate": 4.506881923510493e-06,
|
| 914 |
+
"loss": 0.8388,
|
| 915 |
+
"step": 1400
|
| 916 |
+
},
|
| 917 |
+
{
|
| 918 |
+
"epoch": 3.626943005181347,
|
| 919 |
+
"eval_main_loss": 0.8397356867790222,
|
| 920 |
+
"eval_main_runtime": 50.8597,
|
| 921 |
+
"eval_main_samples_per_second": 30.201,
|
| 922 |
+
"eval_main_steps_per_second": 3.775,
|
| 923 |
+
"step": 1400
|
| 924 |
+
},
|
| 925 |
+
{
|
| 926 |
+
"epoch": 3.626943005181347,
|
| 927 |
+
"eval_anatomy_loss": 2.392620325088501,
|
| 928 |
+
"eval_anatomy_runtime": 0.268,
|
| 929 |
+
"eval_anatomy_samples_per_second": 7.464,
|
| 930 |
+
"eval_anatomy_steps_per_second": 3.732,
|
| 931 |
+
"step": 1400
|
| 932 |
+
},
|
| 933 |
+
{
|
| 934 |
+
"epoch": 3.626943005181347,
|
| 935 |
+
"eval_college_mathematics_loss": 1.746407151222229,
|
| 936 |
+
"eval_college_mathematics_runtime": 0.2684,
|
| 937 |
+
"eval_college_mathematics_samples_per_second": 7.451,
|
| 938 |
+
"eval_college_mathematics_steps_per_second": 3.725,
|
| 939 |
+
"step": 1400
|
| 940 |
+
},
|
| 941 |
+
{
|
| 942 |
+
"epoch": 3.626943005181347,
|
| 943 |
+
"eval_international_law_loss": 2.632657527923584,
|
| 944 |
+
"eval_international_law_runtime": 0.2666,
|
| 945 |
+
"eval_international_law_samples_per_second": 7.503,
|
| 946 |
+
"eval_international_law_steps_per_second": 3.751,
|
| 947 |
+
"step": 1400
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 3.6787564766839376,
|
| 951 |
+
"grad_norm": 0.2197265625,
|
| 952 |
+
"learning_rate": 4.476135548342666e-06,
|
| 953 |
+
"loss": 0.8405,
|
| 954 |
+
"step": 1420
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 3.7305699481865284,
|
| 958 |
+
"grad_norm": 0.2119140625,
|
| 959 |
+
"learning_rate": 4.444571072217848e-06,
|
| 960 |
+
"loss": 0.8353,
|
| 961 |
+
"step": 1440
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 3.7823834196891193,
|
| 965 |
+
"grad_norm": 0.2353515625,
|
| 966 |
+
"learning_rate": 4.4122015625231125e-06,
|
| 967 |
+
"loss": 0.838,
|
| 968 |
+
"step": 1460
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 3.8341968911917097,
|
| 972 |
+
"grad_norm": 0.208984375,
|
| 973 |
+
"learning_rate": 4.37904041992163e-06,
|
| 974 |
+
"loss": 0.8339,
|
| 975 |
+
"step": 1480
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 3.8860103626943006,
|
| 979 |
+
"grad_norm": 0.2099609375,
|
| 980 |
+
"learning_rate": 4.345101372804917e-06,
|
| 981 |
+
"loss": 0.8352,
|
| 982 |
+
"step": 1500
|
| 983 |
+
},
|
| 984 |
+
{
|
| 985 |
+
"epoch": 3.8860103626943006,
|
| 986 |
+
"eval_main_loss": 0.8387607932090759,
|
| 987 |
+
"eval_main_runtime": 50.9241,
|
| 988 |
+
"eval_main_samples_per_second": 30.163,
|
| 989 |
+
"eval_main_steps_per_second": 3.77,
|
| 990 |
+
"step": 1500
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 3.8860103626943006,
|
| 994 |
+
"eval_anatomy_loss": 2.3933463096618652,
|
| 995 |
+
"eval_anatomy_runtime": 0.2694,
|
| 996 |
+
"eval_anatomy_samples_per_second": 7.424,
|
| 997 |
+
"eval_anatomy_steps_per_second": 3.712,
|
| 998 |
+
"step": 1500
|
| 999 |
+
},
|
| 1000 |
+
{
|
| 1001 |
+
"epoch": 3.8860103626943006,
|
| 1002 |
+
"eval_college_mathematics_loss": 1.7452200651168823,
|
| 1003 |
+
"eval_college_mathematics_runtime": 0.2686,
|
| 1004 |
+
"eval_college_mathematics_samples_per_second": 7.447,
|
| 1005 |
+
"eval_college_mathematics_steps_per_second": 3.724,
|
| 1006 |
+
"step": 1500
|
| 1007 |
+
},
|
| 1008 |
+
{
|
| 1009 |
+
"epoch": 3.8860103626943006,
|
| 1010 |
+
"eval_international_law_loss": 2.631213903427124,
|
| 1011 |
+
"eval_international_law_runtime": 0.2675,
|
| 1012 |
+
"eval_international_law_samples_per_second": 7.475,
|
| 1013 |
+
"eval_international_law_steps_per_second": 3.738,
|
| 1014 |
+
"step": 1500
|
| 1015 |
+
},
|
| 1016 |
+
{
|
| 1017 |
+
"epoch": 3.937823834196891,
|
| 1018 |
+
"grad_norm": 0.2119140625,
|
| 1019 |
+
"learning_rate": 4.310398471609416e-06,
|
| 1020 |
+
"loss": 0.8379,
|
| 1021 |
+
"step": 1520
|
| 1022 |
+
},
|
| 1023 |
+
{
|
| 1024 |
+
"epoch": 3.989637305699482,
|
| 1025 |
+
"grad_norm": 0.228515625,
|
| 1026 |
+
"learning_rate": 4.274946082999753e-06,
|
| 1027 |
+
"loss": 0.8366,
|
| 1028 |
+
"step": 1540
|
| 1029 |
+
},
|
| 1030 |
+
{
|
| 1031 |
+
"epoch": 4.041450777202073,
|
| 1032 |
+
"grad_norm": 0.240234375,
|
| 1033 |
+
"learning_rate": 4.238758883921077e-06,
|
| 1034 |
+
"loss": 0.8351,
|
| 1035 |
+
"step": 1560
|
| 1036 |
+
},
|
| 1037 |
+
{
|
| 1038 |
+
"epoch": 4.0932642487046635,
|
| 1039 |
+
"grad_norm": 0.244140625,
|
| 1040 |
+
"learning_rate": 4.201851855522946e-06,
|
| 1041 |
+
"loss": 0.8427,
|
| 1042 |
+
"step": 1580
|
| 1043 |
+
},
|
| 1044 |
+
{
|
| 1045 |
+
"epoch": 4.1450777202072535,
|
| 1046 |
+
"grad_norm": 0.2197265625,
|
| 1047 |
+
"learning_rate": 4.1642402769572775e-06,
|
| 1048 |
+
"loss": 0.8375,
|
| 1049 |
+
"step": 1600
|
| 1050 |
+
},
|
| 1051 |
+
{
|
| 1052 |
+
"epoch": 4.1450777202072535,
|
| 1053 |
+
"eval_main_loss": 0.8381660580635071,
|
| 1054 |
+
"eval_main_runtime": 50.8823,
|
| 1055 |
+
"eval_main_samples_per_second": 30.187,
|
| 1056 |
+
"eval_main_steps_per_second": 3.773,
|
| 1057 |
+
"step": 1600
|
| 1058 |
+
},
|
| 1059 |
+
{
|
| 1060 |
+
"epoch": 4.1450777202072535,
|
| 1061 |
+
"eval_anatomy_loss": 2.3937363624572754,
|
| 1062 |
+
"eval_anatomy_runtime": 0.2711,
|
| 1063 |
+
"eval_anatomy_samples_per_second": 7.376,
|
| 1064 |
+
"eval_anatomy_steps_per_second": 3.688,
|
| 1065 |
+
"step": 1600
|
| 1066 |
+
},
|
| 1067 |
+
{
|
| 1068 |
+
"epoch": 4.1450777202072535,
|
| 1069 |
+
"eval_college_mathematics_loss": 1.7459180355072021,
|
| 1070 |
+
"eval_college_mathematics_runtime": 0.2669,
|
| 1071 |
+
"eval_college_mathematics_samples_per_second": 7.493,
|
| 1072 |
+
"eval_college_mathematics_steps_per_second": 3.747,
|
| 1073 |
+
"step": 1600
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 4.1450777202072535,
|
| 1077 |
+
"eval_international_law_loss": 2.6354634761810303,
|
| 1078 |
+
"eval_international_law_runtime": 0.2663,
|
| 1079 |
+
"eval_international_law_samples_per_second": 7.509,
|
| 1080 |
+
"eval_international_law_steps_per_second": 3.755,
|
| 1081 |
+
"step": 1600
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 4.196891191709844,
|
| 1085 |
+
"grad_norm": 0.2431640625,
|
| 1086 |
+
"learning_rate": 4.125939719052927e-06,
|
| 1087 |
+
"loss": 0.8405,
|
| 1088 |
+
"step": 1620
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 4.248704663212435,
|
| 1092 |
+
"grad_norm": 0.193359375,
|
| 1093 |
+
"learning_rate": 4.086966037869515e-06,
|
| 1094 |
+
"loss": 0.8346,
|
| 1095 |
+
"step": 1640
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 4.300518134715026,
|
| 1099 |
+
"grad_norm": 0.244140625,
|
| 1100 |
+
"learning_rate": 4.047335368133176e-06,
|
| 1101 |
+
"loss": 0.8388,
|
| 1102 |
+
"step": 1660
|
| 1103 |
+
},
|
| 1104 |
+
{
|
| 1105 |
+
"epoch": 4.352331606217617,
|
| 1106 |
+
"grad_norm": 0.21484375,
|
| 1107 |
+
"learning_rate": 4.0070641165569335e-06,
|
| 1108 |
+
"loss": 0.8301,
|
| 1109 |
+
"step": 1680
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 4.404145077720207,
|
| 1113 |
+
"grad_norm": 0.2275390625,
|
| 1114 |
+
"learning_rate": 3.96616895504848e-06,
|
| 1115 |
+
"loss": 0.8366,
|
| 1116 |
+
"step": 1700
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 4.404145077720207,
|
| 1120 |
+
"eval_main_loss": 0.8377915024757385,
|
| 1121 |
+
"eval_main_runtime": 50.9147,
|
| 1122 |
+
"eval_main_samples_per_second": 30.168,
|
| 1123 |
+
"eval_main_steps_per_second": 3.771,
|
| 1124 |
+
"step": 1700
|
| 1125 |
+
},
|
| 1126 |
+
{
|
| 1127 |
+
"epoch": 4.404145077720207,
|
| 1128 |
+
"eval_anatomy_loss": 2.394949197769165,
|
| 1129 |
+
"eval_anatomy_runtime": 0.2684,
|
| 1130 |
+
"eval_anatomy_samples_per_second": 7.451,
|
| 1131 |
+
"eval_anatomy_steps_per_second": 3.726,
|
| 1132 |
+
"step": 1700
|
| 1133 |
+
},
|
| 1134 |
+
{
|
| 1135 |
+
"epoch": 4.404145077720207,
|
| 1136 |
+
"eval_college_mathematics_loss": 1.7438111305236816,
|
| 1137 |
+
"eval_college_mathematics_runtime": 0.2676,
|
| 1138 |
+
"eval_college_mathematics_samples_per_second": 7.475,
|
| 1139 |
+
"eval_college_mathematics_steps_per_second": 3.737,
|
| 1140 |
+
"step": 1700
|
| 1141 |
+
},
|
| 1142 |
+
{
|
| 1143 |
+
"epoch": 4.404145077720207,
|
| 1144 |
+
"eval_international_law_loss": 2.6339313983917236,
|
| 1145 |
+
"eval_international_law_runtime": 0.2665,
|
| 1146 |
+
"eval_international_law_samples_per_second": 7.506,
|
| 1147 |
+
"eval_international_law_steps_per_second": 3.753,
|
| 1148 |
+
"step": 1700
|
| 1149 |
+
},
|
| 1150 |
+
{
|
| 1151 |
+
"epoch": 4.455958549222798,
|
| 1152 |
+
"grad_norm": 0.2197265625,
|
| 1153 |
+
"learning_rate": 3.924666813808176e-06,
|
| 1154 |
+
"loss": 0.833,
|
| 1155 |
+
"step": 1720
|
| 1156 |
+
},
|
| 1157 |
+
{
|
| 1158 |
+
"epoch": 4.507772020725389,
|
| 1159 |
+
"grad_norm": 0.234375,
|
| 1160 |
+
"learning_rate": 3.882574874320099e-06,
|
| 1161 |
+
"loss": 0.8381,
|
| 1162 |
+
"step": 1740
|
| 1163 |
+
},
|
| 1164 |
+
{
|
| 1165 |
+
"epoch": 4.5595854922279795,
|
| 1166 |
+
"grad_norm": 0.2177734375,
|
| 1167 |
+
"learning_rate": 3.839910562239088e-06,
|
| 1168 |
+
"loss": 0.8438,
|
| 1169 |
+
"step": 1760
|
| 1170 |
+
},
|
| 1171 |
+
{
|
| 1172 |
+
"epoch": 4.61139896373057,
|
| 1173 |
+
"grad_norm": 0.2138671875,
|
| 1174 |
+
"learning_rate": 3.7966915401766845e-06,
|
| 1175 |
+
"loss": 0.832,
|
| 1176 |
+
"step": 1780
|
| 1177 |
+
},
|
| 1178 |
+
{
|
| 1179 |
+
"epoch": 4.66321243523316,
|
| 1180 |
+
"grad_norm": 0.2177734375,
|
| 1181 |
+
"learning_rate": 3.752935700388982e-06,
|
| 1182 |
+
"loss": 0.843,
|
| 1183 |
+
"step": 1800
|
| 1184 |
+
},
|
| 1185 |
+
{
|
| 1186 |
+
"epoch": 4.66321243523316,
|
| 1187 |
+
"eval_main_loss": 0.8375835418701172,
|
| 1188 |
+
"eval_main_runtime": 50.8717,
|
| 1189 |
+
"eval_main_samples_per_second": 30.194,
|
| 1190 |
+
"eval_main_steps_per_second": 3.774,
|
| 1191 |
+
"step": 1800
|
| 1192 |
+
},
|
| 1193 |
+
{
|
| 1194 |
+
"epoch": 4.66321243523316,
|
| 1195 |
+
"eval_anatomy_loss": 2.3957273960113525,
|
| 1196 |
+
"eval_anatomy_runtime": 0.2674,
|
| 1197 |
+
"eval_anatomy_samples_per_second": 7.479,
|
| 1198 |
+
"eval_anatomy_steps_per_second": 3.74,
|
| 1199 |
+
"step": 1800
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 4.66321243523316,
|
| 1203 |
+
"eval_college_mathematics_loss": 1.745951771736145,
|
| 1204 |
+
"eval_college_mathematics_runtime": 0.2678,
|
| 1205 |
+
"eval_college_mathematics_samples_per_second": 7.468,
|
| 1206 |
+
"eval_college_mathematics_steps_per_second": 3.734,
|
| 1207 |
+
"step": 1800
|
| 1208 |
+
},
|
| 1209 |
+
{
|
| 1210 |
+
"epoch": 4.66321243523316,
|
| 1211 |
+
"eval_international_law_loss": 2.635204315185547,
|
| 1212 |
+
"eval_international_law_runtime": 0.2682,
|
| 1213 |
+
"eval_international_law_samples_per_second": 7.458,
|
| 1214 |
+
"eval_international_law_steps_per_second": 3.729,
|
| 1215 |
+
"step": 1800
|
| 1216 |
+
},
|
| 1217 |
+
{
|
| 1218 |
+
"epoch": 4.715025906735751,
|
| 1219 |
+
"grad_norm": 0.22265625,
|
| 1220 |
+
"learning_rate": 3.7086611573694107e-06,
|
| 1221 |
+
"loss": 0.8254,
|
| 1222 |
+
"step": 1820
|
| 1223 |
+
},
|
| 1224 |
+
{
|
| 1225 |
+
"epoch": 4.766839378238342,
|
| 1226 |
+
"grad_norm": 0.232421875,
|
| 1227 |
+
"learning_rate": 3.663886240349507e-06,
|
| 1228 |
+
"loss": 0.8342,
|
| 1229 |
+
"step": 1840
|
| 1230 |
+
},
|
| 1231 |
+
{
|
| 1232 |
+
"epoch": 4.818652849740933,
|
| 1233 |
+
"grad_norm": 0.228515625,
|
| 1234 |
+
"learning_rate": 3.6186294857107933e-06,
|
| 1235 |
+
"loss": 0.8368,
|
| 1236 |
+
"step": 1860
|
| 1237 |
+
},
|
| 1238 |
+
{
|
| 1239 |
+
"epoch": 4.870466321243523,
|
| 1240 |
+
"grad_norm": 0.2255859375,
|
| 1241 |
+
"learning_rate": 3.5729096293108935e-06,
|
| 1242 |
+
"loss": 0.8406,
|
| 1243 |
+
"step": 1880
|
| 1244 |
+
},
|
| 1245 |
+
{
|
| 1246 |
+
"epoch": 4.922279792746114,
|
| 1247 |
+
"grad_norm": 0.23828125,
|
| 1248 |
+
"learning_rate": 3.526745598727071e-06,
|
| 1249 |
+
"loss": 0.8317,
|
| 1250 |
+
"step": 1900
|
| 1251 |
+
},
|
| 1252 |
+
{
|
| 1253 |
+
"epoch": 4.922279792746114,
|
| 1254 |
+
"eval_main_loss": 0.8374476432800293,
|
| 1255 |
+
"eval_main_runtime": 50.8861,
|
| 1256 |
+
"eval_main_samples_per_second": 30.185,
|
| 1257 |
+
"eval_main_steps_per_second": 3.773,
|
| 1258 |
+
"step": 1900
|
| 1259 |
+
},
|
| 1260 |
+
{
|
| 1261 |
+
"epoch": 4.922279792746114,
|
| 1262 |
+
"eval_anatomy_loss": 2.3970742225646973,
|
| 1263 |
+
"eval_anatomy_runtime": 0.268,
|
| 1264 |
+
"eval_anatomy_samples_per_second": 7.462,
|
| 1265 |
+
"eval_anatomy_steps_per_second": 3.731,
|
| 1266 |
+
"step": 1900
|
| 1267 |
+
},
|
| 1268 |
+
{
|
| 1269 |
+
"epoch": 4.922279792746114,
|
| 1270 |
+
"eval_college_mathematics_loss": 1.7456122636795044,
|
| 1271 |
+
"eval_college_mathematics_runtime": 0.2683,
|
| 1272 |
+
"eval_college_mathematics_samples_per_second": 7.454,
|
| 1273 |
+
"eval_college_mathematics_steps_per_second": 3.727,
|
| 1274 |
+
"step": 1900
|
| 1275 |
+
},
|
| 1276 |
+
{
|
| 1277 |
+
"epoch": 4.922279792746114,
|
| 1278 |
+
"eval_international_law_loss": 2.6364247798919678,
|
| 1279 |
+
"eval_international_law_runtime": 0.267,
|
| 1280 |
+
"eval_international_law_samples_per_second": 7.49,
|
| 1281 |
+
"eval_international_law_steps_per_second": 3.745,
|
| 1282 |
+
"step": 1900
|
| 1283 |
+
},
|
| 1284 |
+
{
|
| 1285 |
+
"epoch": 4.974093264248705,
|
| 1286 |
+
"grad_norm": 0.232421875,
|
| 1287 |
+
"learning_rate": 3.4801565054203962e-06,
|
| 1288 |
+
"loss": 0.834,
|
| 1289 |
+
"step": 1920
|
| 1290 |
+
},
|
| 1291 |
+
{
|
| 1292 |
+
"epoch": 5.025906735751295,
|
| 1293 |
+
"grad_norm": 0.228515625,
|
| 1294 |
+
"learning_rate": 3.433161636823782e-06,
|
| 1295 |
+
"loss": 0.8409,
|
| 1296 |
+
"step": 1940
|
| 1297 |
+
},
|
| 1298 |
+
{
|
| 1299 |
+
"epoch": 5.077720207253886,
|
| 1300 |
+
"grad_norm": 0.2099609375,
|
| 1301 |
+
"learning_rate": 3.3857804483571803e-06,
|
| 1302 |
+
"loss": 0.8324,
|
| 1303 |
+
"step": 1960
|
| 1304 |
+
},
|
| 1305 |
+
{
|
| 1306 |
+
"epoch": 5.129533678756476,
|
| 1307 |
+
"grad_norm": 0.236328125,
|
| 1308 |
+
"learning_rate": 3.3380325553732223e-06,
|
| 1309 |
+
"loss": 0.8433,
|
| 1310 |
+
"step": 1980
|
| 1311 |
+
},
|
| 1312 |
+
{
|
| 1313 |
+
"epoch": 5.181347150259067,
|
| 1314 |
+
"grad_norm": 0.21484375,
|
| 1315 |
+
"learning_rate": 3.2899377250366536e-06,
|
| 1316 |
+
"loss": 0.8307,
|
| 1317 |
+
"step": 2000
|
| 1318 |
+
},
|
| 1319 |
+
{
|
| 1320 |
+
"epoch": 5.181347150259067,
|
| 1321 |
+
"eval_main_loss": 0.8373920321464539,
|
| 1322 |
+
"eval_main_runtime": 50.7102,
|
| 1323 |
+
"eval_main_samples_per_second": 30.29,
|
| 1324 |
+
"eval_main_steps_per_second": 3.786,
|
| 1325 |
+
"step": 2000
|
| 1326 |
+
},
|
| 1327 |
+
{
|
| 1328 |
+
"epoch": 5.181347150259067,
|
| 1329 |
+
"eval_anatomy_loss": 2.3975374698638916,
|
| 1330 |
+
"eval_anatomy_runtime": 0.2673,
|
| 1331 |
+
"eval_anatomy_samples_per_second": 7.483,
|
| 1332 |
+
"eval_anatomy_steps_per_second": 3.741,
|
| 1333 |
+
"step": 2000
|
| 1334 |
+
},
|
| 1335 |
+
{
|
| 1336 |
+
"epoch": 5.181347150259067,
|
| 1337 |
+
"eval_college_mathematics_loss": 1.746949315071106,
|
| 1338 |
+
"eval_college_mathematics_runtime": 0.2679,
|
| 1339 |
+
"eval_college_mathematics_samples_per_second": 7.465,
|
| 1340 |
+
"eval_college_mathematics_steps_per_second": 3.732,
|
| 1341 |
+
"step": 2000
|
| 1342 |
+
},
|
| 1343 |
+
{
|
| 1344 |
+
"epoch": 5.181347150259067,
|
| 1345 |
+
"eval_international_law_loss": 2.637000799179077,
|
| 1346 |
+
"eval_international_law_runtime": 0.267,
|
| 1347 |
+
"eval_international_law_samples_per_second": 7.49,
|
| 1348 |
+
"eval_international_law_steps_per_second": 3.745,
|
| 1349 |
+
"step": 2000
|
| 1350 |
+
},
|
| 1351 |
+
{
|
| 1352 |
+
"epoch": 5.233160621761658,
|
| 1353 |
+
"grad_norm": 0.2138671875,
|
| 1354 |
+
"learning_rate": 3.2415158681409215e-06,
|
| 1355 |
+
"loss": 0.836,
|
| 1356 |
+
"step": 2020
|
| 1357 |
+
},
|
| 1358 |
+
{
|
| 1359 |
+
"epoch": 5.284974093264249,
|
| 1360 |
+
"grad_norm": 0.2099609375,
|
| 1361 |
+
"learning_rate": 3.1927870308652953e-06,
|
| 1362 |
+
"loss": 0.8447,
|
| 1363 |
+
"step": 2040
|
| 1364 |
+
},
|
| 1365 |
+
{
|
| 1366 |
+
"epoch": 5.33678756476684,
|
| 1367 |
+
"grad_norm": 0.220703125,
|
| 1368 |
+
"learning_rate": 3.1437713864759483e-06,
|
| 1369 |
+
"loss": 0.8383,
|
| 1370 |
+
"step": 2060
|
| 1371 |
+
},
|
| 1372 |
+
{
|
| 1373 |
+
"epoch": 5.38860103626943,
|
| 1374 |
+
"grad_norm": 0.2451171875,
|
| 1375 |
+
"learning_rate": 3.0944892269744155e-06,
|
| 1376 |
+
"loss": 0.8412,
|
| 1377 |
+
"step": 2080
|
| 1378 |
+
},
|
| 1379 |
+
{
|
| 1380 |
+
"epoch": 5.4404145077720205,
|
| 1381 |
+
"grad_norm": 0.23828125,
|
| 1382 |
+
"learning_rate": 3.044960954696906e-06,
|
| 1383 |
+
"loss": 0.837,
|
| 1384 |
+
"step": 2100
|
| 1385 |
+
},
|
| 1386 |
+
{
|
| 1387 |
+
"epoch": 5.4404145077720205,
|
| 1388 |
+
"eval_main_loss": 0.837336003780365,
|
| 1389 |
+
"eval_main_runtime": 50.8778,
|
| 1390 |
+
"eval_main_samples_per_second": 30.19,
|
| 1391 |
+
"eval_main_steps_per_second": 3.774,
|
| 1392 |
+
"step": 2100
|
| 1393 |
+
},
|
| 1394 |
+
{
|
| 1395 |
+
"epoch": 5.4404145077720205,
|
| 1396 |
+
"eval_anatomy_loss": 2.39707350730896,
|
| 1397 |
+
"eval_anatomy_runtime": 0.264,
|
| 1398 |
+
"eval_anatomy_samples_per_second": 7.575,
|
| 1399 |
+
"eval_anatomy_steps_per_second": 3.787,
|
| 1400 |
+
"step": 2100
|
| 1401 |
+
},
|
| 1402 |
+
{
|
| 1403 |
+
"epoch": 5.4404145077720205,
|
| 1404 |
+
"eval_college_mathematics_loss": 1.746044397354126,
|
| 1405 |
+
"eval_college_mathematics_runtime": 0.2668,
|
| 1406 |
+
"eval_college_mathematics_samples_per_second": 7.497,
|
| 1407 |
+
"eval_college_mathematics_steps_per_second": 3.748,
|
| 1408 |
+
"step": 2100
|
| 1409 |
+
},
|
| 1410 |
+
{
|
| 1411 |
+
"epoch": 5.4404145077720205,
|
| 1412 |
+
"eval_international_law_loss": 2.639299154281616,
|
| 1413 |
+
"eval_international_law_runtime": 0.2686,
|
| 1414 |
+
"eval_international_law_samples_per_second": 7.446,
|
| 1415 |
+
"eval_international_law_steps_per_second": 3.723,
|
| 1416 |
+
"step": 2100
|
| 1417 |
+
},
|
| 1418 |
+
{
|
| 1419 |
+
"epoch": 5.492227979274611,
|
| 1420 |
+
"grad_norm": 0.244140625,
|
| 1421 |
+
"learning_rate": 2.9952070738679312e-06,
|
| 1422 |
+
"loss": 0.8349,
|
| 1423 |
+
"step": 2120
|
| 1424 |
+
},
|
| 1425 |
+
{
|
| 1426 |
+
"epoch": 5.544041450777202,
|
| 1427 |
+
"grad_norm": 0.2421875,
|
| 1428 |
+
"learning_rate": 2.9452481821117544e-06,
|
| 1429 |
+
"loss": 0.8261,
|
| 1430 |
+
"step": 2140
|
| 1431 |
+
},
|
| 1432 |
+
{
|
| 1433 |
+
"epoch": 5.595854922279793,
|
| 1434 |
+
"grad_norm": 0.193359375,
|
| 1435 |
+
"learning_rate": 2.895104961925179e-06,
|
| 1436 |
+
"loss": 0.8305,
|
| 1437 |
+
"step": 2160
|
| 1438 |
+
},
|
| 1439 |
+
{
|
| 1440 |
+
"epoch": 5.647668393782383,
|
| 1441 |
+
"grad_norm": 0.2177734375,
|
| 1442 |
+
"learning_rate": 2.844798172115185e-06,
|
| 1443 |
+
"loss": 0.8316,
|
| 1444 |
+
"step": 2180
|
| 1445 |
+
},
|
| 1446 |
+
{
|
| 1447 |
+
"epoch": 5.699481865284974,
|
| 1448 |
+
"grad_norm": 0.220703125,
|
| 1449 |
+
"learning_rate": 2.7943486392049972e-06,
|
| 1450 |
+
"loss": 0.8334,
|
| 1451 |
+
"step": 2200
|
| 1452 |
+
},
|
| 1453 |
+
{
|
| 1454 |
+
"epoch": 5.699481865284974,
|
| 1455 |
+
"eval_main_loss": 0.8372721076011658,
|
| 1456 |
+
"eval_main_runtime": 50.8569,
|
| 1457 |
+
"eval_main_samples_per_second": 30.202,
|
| 1458 |
+
"eval_main_steps_per_second": 3.775,
|
| 1459 |
+
"step": 2200
|
| 1460 |
+
},
|
| 1461 |
+
{
|
| 1462 |
+
"epoch": 5.699481865284974,
|
| 1463 |
+
"eval_anatomy_loss": 2.3966822624206543,
|
| 1464 |
+
"eval_anatomy_runtime": 0.2669,
|
| 1465 |
+
"eval_anatomy_samples_per_second": 7.494,
|
| 1466 |
+
"eval_anatomy_steps_per_second": 3.747,
|
| 1467 |
+
"step": 2200
|
| 1468 |
+
},
|
| 1469 |
+
{
|
| 1470 |
+
"epoch": 5.699481865284974,
|
| 1471 |
+
"eval_college_mathematics_loss": 1.7497589588165283,
|
| 1472 |
+
"eval_college_mathematics_runtime": 0.2678,
|
| 1473 |
+
"eval_college_mathematics_samples_per_second": 7.468,
|
| 1474 |
+
"eval_college_mathematics_steps_per_second": 3.734,
|
| 1475 |
+
"step": 2200
|
| 1476 |
+
},
|
| 1477 |
+
{
|
| 1478 |
+
"epoch": 5.699481865284974,
|
| 1479 |
+
"eval_international_law_loss": 2.634140968322754,
|
| 1480 |
+
"eval_international_law_runtime": 0.267,
|
| 1481 |
+
"eval_international_law_samples_per_second": 7.492,
|
| 1482 |
+
"eval_international_law_steps_per_second": 3.746,
|
| 1483 |
+
"step": 2200
|
| 1484 |
+
},
|
| 1485 |
+
{
|
| 1486 |
+
"epoch": 5.751295336787565,
|
| 1487 |
+
"grad_norm": 0.212890625,
|
| 1488 |
+
"learning_rate": 2.7437772488120945e-06,
|
| 1489 |
+
"loss": 0.8305,
|
| 1490 |
+
"step": 2220
|
| 1491 |
+
},
|
| 1492 |
+
{
|
| 1493 |
+
"epoch": 5.803108808290156,
|
| 1494 |
+
"grad_norm": 0.2109375,
|
| 1495 |
+
"learning_rate": 2.6931049370017755e-06,
|
| 1496 |
+
"loss": 0.8383,
|
| 1497 |
+
"step": 2240
|
| 1498 |
+
},
|
| 1499 |
+
{
|
| 1500 |
+
"epoch": 5.8549222797927465,
|
| 1501 |
+
"grad_norm": 0.2333984375,
|
| 1502 |
+
"learning_rate": 2.6423526816198253e-06,
|
| 1503 |
+
"loss": 0.8445,
|
| 1504 |
+
"step": 2260
|
| 1505 |
+
},
|
| 1506 |
+
{
|
| 1507 |
+
"epoch": 5.9067357512953365,
|
| 1508 |
+
"grad_norm": 0.2236328125,
|
| 1509 |
+
"learning_rate": 2.5915414936078933e-06,
|
| 1510 |
+
"loss": 0.8385,
|
| 1511 |
+
"step": 2280
|
| 1512 |
+
},
|
| 1513 |
+
{
|
| 1514 |
+
"epoch": 5.958549222797927,
|
| 1515 |
+
"grad_norm": 0.2294921875,
|
| 1516 |
+
"learning_rate": 2.5406924083051683e-06,
|
| 1517 |
+
"loss": 0.8359,
|
| 1518 |
+
"step": 2300
|
| 1519 |
+
},
|
| 1520 |
+
{
|
| 1521 |
+
"epoch": 5.958549222797927,
|
| 1522 |
+
"eval_main_loss": 0.8372599482536316,
|
| 1523 |
+
"eval_main_runtime": 50.7835,
|
| 1524 |
+
"eval_main_samples_per_second": 30.246,
|
| 1525 |
+
"eval_main_steps_per_second": 3.781,
|
| 1526 |
+
"step": 2300
|
| 1527 |
+
},
|
| 1528 |
+
{
|
| 1529 |
+
"epoch": 5.958549222797927,
|
| 1530 |
+
"eval_anatomy_loss": 2.3953776359558105,
|
| 1531 |
+
"eval_anatomy_runtime": 0.2668,
|
| 1532 |
+
"eval_anatomy_samples_per_second": 7.496,
|
| 1533 |
+
"eval_anatomy_steps_per_second": 3.748,
|
| 1534 |
+
"step": 2300
|
| 1535 |
+
},
|
| 1536 |
+
{
|
| 1537 |
+
"epoch": 5.958549222797927,
|
| 1538 |
+
"eval_college_mathematics_loss": 1.7478266954421997,
|
| 1539 |
+
"eval_college_mathematics_runtime": 0.2698,
|
| 1540 |
+
"eval_college_mathematics_samples_per_second": 7.413,
|
| 1541 |
+
"eval_college_mathematics_steps_per_second": 3.707,
|
| 1542 |
+
"step": 2300
|
| 1543 |
+
},
|
| 1544 |
+
{
|
| 1545 |
+
"epoch": 5.958549222797927,
|
| 1546 |
+
"eval_international_law_loss": 2.6391143798828125,
|
| 1547 |
+
"eval_international_law_runtime": 0.2663,
|
| 1548 |
+
"eval_international_law_samples_per_second": 7.509,
|
| 1549 |
+
"eval_international_law_steps_per_second": 3.755,
|
| 1550 |
+
"step": 2300
|
| 1551 |
+
},
|
| 1552 |
+
{
|
| 1553 |
+
"epoch": 6.010362694300518,
|
| 1554 |
+
"grad_norm": 0.2392578125,
|
| 1555 |
+
"learning_rate": 2.4898264767399445e-06,
|
| 1556 |
+
"loss": 0.8316,
|
| 1557 |
+
"step": 2320
|
| 1558 |
+
},
|
| 1559 |
+
{
|
| 1560 |
+
"epoch": 6.062176165803109,
|
| 1561 |
+
"grad_norm": 0.2255859375,
|
| 1562 |
+
"learning_rate": 2.438964756914712e-06,
|
| 1563 |
+
"loss": 0.8412,
|
| 1564 |
+
"step": 2340
|
| 1565 |
+
},
|
| 1566 |
+
{
|
| 1567 |
+
"epoch": 6.1139896373057,
|
| 1568 |
+
"grad_norm": 0.2236328125,
|
| 1569 |
+
"learning_rate": 2.3881283050883368e-06,
|
| 1570 |
+
"loss": 0.8368,
|
| 1571 |
+
"step": 2360
|
| 1572 |
+
},
|
| 1573 |
+
{
|
| 1574 |
+
"epoch": 6.16580310880829,
|
| 1575 |
+
"grad_norm": 0.234375,
|
| 1576 |
+
"learning_rate": 2.337338167058981e-06,
|
| 1577 |
+
"loss": 0.8392,
|
| 1578 |
+
"step": 2380
|
| 1579 |
+
},
|
| 1580 |
+
{
|
| 1581 |
+
"epoch": 6.217616580310881,
|
| 1582 |
+
"grad_norm": 0.212890625,
|
| 1583 |
+
"learning_rate": 2.286615369451342e-06,
|
| 1584 |
+
"loss": 0.834,
|
| 1585 |
+
"step": 2400
|
| 1586 |
+
},
|
| 1587 |
+
{
|
| 1588 |
+
"epoch": 6.217616580310881,
|
| 1589 |
+
"eval_main_loss": 0.8373088836669922,
|
| 1590 |
+
"eval_main_runtime": 50.8482,
|
| 1591 |
+
"eval_main_samples_per_second": 30.208,
|
| 1592 |
+
"eval_main_steps_per_second": 3.776,
|
| 1593 |
+
"step": 2400
|
| 1594 |
+
},
|
| 1595 |
+
{
|
| 1596 |
+
"epoch": 6.217616580310881,
|
| 1597 |
+
"eval_anatomy_loss": 2.3978271484375,
|
| 1598 |
+
"eval_anatomy_runtime": 0.2671,
|
| 1599 |
+
"eval_anatomy_samples_per_second": 7.487,
|
| 1600 |
+
"eval_anatomy_steps_per_second": 3.744,
|
| 1601 |
+
"step": 2400
|
| 1602 |
+
},
|
| 1603 |
+
{
|
| 1604 |
+
"epoch": 6.217616580310881,
|
| 1605 |
+
"eval_college_mathematics_loss": 1.7477797269821167,
|
| 1606 |
+
"eval_college_mathematics_runtime": 0.2685,
|
| 1607 |
+
"eval_college_mathematics_samples_per_second": 7.449,
|
| 1608 |
+
"eval_college_mathematics_steps_per_second": 3.724,
|
| 1609 |
+
"step": 2400
|
| 1610 |
+
},
|
| 1611 |
+
{
|
| 1612 |
+
"epoch": 6.217616580310881,
|
| 1613 |
+
"eval_international_law_loss": 2.638612985610962,
|
| 1614 |
+
"eval_international_law_runtime": 0.2668,
|
| 1615 |
+
"eval_international_law_samples_per_second": 7.495,
|
| 1616 |
+
"eval_international_law_steps_per_second": 3.748,
|
| 1617 |
+
"step": 2400
|
| 1618 |
+
},
|
| 1619 |
+
{
|
| 1620 |
+
"epoch": 6.269430051813472,
|
| 1621 |
+
"grad_norm": 0.2275390625,
|
| 1622 |
+
"learning_rate": 2.2359809110118358e-06,
|
| 1623 |
+
"loss": 0.8391,
|
| 1624 |
+
"step": 2420
|
| 1625 |
+
},
|
| 1626 |
+
{
|
| 1627 |
+
"epoch": 6.321243523316062,
|
| 1628 |
+
"grad_norm": 0.2431640625,
|
| 1629 |
+
"learning_rate": 2.1854557539153203e-06,
|
| 1630 |
+
"loss": 0.8368,
|
| 1631 |
+
"step": 2440
|
| 1632 |
+
},
|
| 1633 |
+
{
|
| 1634 |
+
"epoch": 6.373056994818652,
|
| 1635 |
+
"grad_norm": 0.2294921875,
|
| 1636 |
+
"learning_rate": 2.1350608150869563e-06,
|
| 1637 |
+
"loss": 0.8321,
|
| 1638 |
+
"step": 2460
|
| 1639 |
+
},
|
| 1640 |
+
{
|
| 1641 |
+
"epoch": 6.424870466321243,
|
| 1642 |
+
"grad_norm": 0.23828125,
|
| 1643 |
+
"learning_rate": 2.0848169575428057e-06,
|
| 1644 |
+
"loss": 0.8375,
|
| 1645 |
+
"step": 2480
|
| 1646 |
+
},
|
| 1647 |
+
{
|
| 1648 |
+
"epoch": 6.476683937823834,
|
| 1649 |
+
"grad_norm": 0.232421875,
|
| 1650 |
+
"learning_rate": 2.034744981752741e-06,
|
| 1651 |
+
"loss": 0.835,
|
| 1652 |
+
"step": 2500
|
| 1653 |
+
},
|
| 1654 |
+
{
|
| 1655 |
+
"epoch": 6.476683937823834,
|
| 1656 |
+
"eval_main_loss": 0.8372688889503479,
|
| 1657 |
+
"eval_main_runtime": 50.7481,
|
| 1658 |
+
"eval_main_samples_per_second": 30.267,
|
| 1659 |
+
"eval_main_steps_per_second": 3.783,
|
| 1660 |
+
"step": 2500
|
| 1661 |
+
},
|
| 1662 |
+
{
|
| 1663 |
+
"epoch": 6.476683937823834,
|
| 1664 |
+
"eval_anatomy_loss": 2.397125244140625,
|
| 1665 |
+
"eval_anatomy_runtime": 0.2662,
|
| 1666 |
+
"eval_anatomy_samples_per_second": 7.513,
|
| 1667 |
+
"eval_anatomy_steps_per_second": 3.757,
|
| 1668 |
+
"step": 2500
|
| 1669 |
+
},
|
| 1670 |
+
{
|
| 1671 |
+
"epoch": 6.476683937823834,
|
| 1672 |
+
"eval_college_mathematics_loss": 1.7471617460250854,
|
| 1673 |
+
"eval_college_mathematics_runtime": 0.2671,
|
| 1674 |
+
"eval_college_mathematics_samples_per_second": 7.487,
|
| 1675 |
+
"eval_college_mathematics_steps_per_second": 3.744,
|
| 1676 |
+
"step": 2500
|
| 1677 |
+
},
|
| 1678 |
+
{
|
| 1679 |
+
"epoch": 6.476683937823834,
|
| 1680 |
+
"eval_international_law_loss": 2.6356821060180664,
|
| 1681 |
+
"eval_international_law_runtime": 0.2665,
|
| 1682 |
+
"eval_international_law_samples_per_second": 7.504,
|
| 1683 |
+
"eval_international_law_steps_per_second": 3.752,
|
| 1684 |
+
"step": 2500
|
| 1685 |
+
},
|
| 1686 |
+
{
|
| 1687 |
+
"epoch": 6.528497409326425,
|
| 1688 |
+
"grad_norm": 0.2490234375,
|
| 1689 |
+
"learning_rate": 1.9848656170292556e-06,
|
| 1690 |
+
"loss": 0.8291,
|
| 1691 |
+
"step": 2520
|
| 1692 |
+
},
|
| 1693 |
+
{
|
| 1694 |
+
"epoch": 6.580310880829016,
|
| 1695 |
+
"grad_norm": 0.2314453125,
|
| 1696 |
+
"learning_rate": 1.9351995129457305e-06,
|
| 1697 |
+
"loss": 0.8325,
|
| 1698 |
+
"step": 2540
|
| 1699 |
+
},
|
| 1700 |
+
{
|
| 1701 |
+
"epoch": 6.632124352331607,
|
| 1702 |
+
"grad_norm": 0.2294921875,
|
| 1703 |
+
"learning_rate": 1.88576723078771e-06,
|
| 1704 |
+
"loss": 0.8345,
|
| 1705 |
+
"step": 2560
|
| 1706 |
+
},
|
| 1707 |
+
{
|
| 1708 |
+
"epoch": 6.683937823834197,
|
| 1709 |
+
"grad_norm": 0.2412109375,
|
| 1710 |
+
"learning_rate": 1.8365892350407238e-06,
|
| 1711 |
+
"loss": 0.8387,
|
| 1712 |
+
"step": 2580
|
| 1713 |
+
},
|
| 1714 |
+
{
|
| 1715 |
+
"epoch": 6.7357512953367875,
|
| 1716 |
+
"grad_norm": 0.212890625,
|
| 1717 |
+
"learning_rate": 1.7876858849181982e-06,
|
| 1718 |
+
"loss": 0.8311,
|
| 1719 |
+
"step": 2600
|
| 1720 |
+
},
|
| 1721 |
+
{
|
| 1722 |
+
"epoch": 6.7357512953367875,
|
| 1723 |
+
"eval_main_loss": 0.8372130393981934,
|
| 1724 |
+
"eval_main_runtime": 50.6463,
|
| 1725 |
+
"eval_main_samples_per_second": 30.328,
|
| 1726 |
+
"eval_main_steps_per_second": 3.791,
|
| 1727 |
+
"step": 2600
|
| 1728 |
+
},
|
| 1729 |
+
{
|
| 1730 |
+
"epoch": 6.7357512953367875,
|
| 1731 |
+
"eval_anatomy_loss": 2.393521308898926,
|
| 1732 |
+
"eval_anatomy_runtime": 0.267,
|
| 1733 |
+
"eval_anatomy_samples_per_second": 7.49,
|
| 1734 |
+
"eval_anatomy_steps_per_second": 3.745,
|
| 1735 |
+
"step": 2600
|
| 1736 |
+
},
|
| 1737 |
+
{
|
| 1738 |
+
"epoch": 6.7357512953367875,
|
| 1739 |
+
"eval_college_mathematics_loss": 1.748924970626831,
|
| 1740 |
+
"eval_college_mathematics_runtime": 0.2664,
|
| 1741 |
+
"eval_college_mathematics_samples_per_second": 7.509,
|
| 1742 |
+
"eval_college_mathematics_steps_per_second": 3.754,
|
| 1743 |
+
"step": 2600
|
| 1744 |
+
},
|
| 1745 |
+
{
|
| 1746 |
+
"epoch": 6.7357512953367875,
|
| 1747 |
+
"eval_international_law_loss": 2.637521505355835,
|
| 1748 |
+
"eval_international_law_runtime": 0.2667,
|
| 1749 |
+
"eval_international_law_samples_per_second": 7.499,
|
| 1750 |
+
"eval_international_law_steps_per_second": 3.749,
|
| 1751 |
+
"step": 2600
|
| 1752 |
+
},
|
| 1753 |
+
{
|
| 1754 |
+
"epoch": 6.787564766839378,
|
| 1755 |
+
"grad_norm": 0.2421875,
|
| 1756 |
+
"learning_rate": 1.73907742593293e-06,
|
| 1757 |
+
"loss": 0.8395,
|
| 1758 |
+
"step": 2620
|
| 1759 |
+
},
|
| 1760 |
+
{
|
| 1761 |
+
"epoch": 6.839378238341969,
|
| 1762 |
+
"grad_norm": 0.220703125,
|
| 1763 |
+
"learning_rate": 1.690783981515648e-06,
|
| 1764 |
+
"loss": 0.8399,
|
| 1765 |
+
"step": 2640
|
| 1766 |
+
},
|
| 1767 |
+
{
|
| 1768 |
+
"epoch": 6.891191709844559,
|
| 1769 |
+
"grad_norm": 0.2470703125,
|
| 1770 |
+
"learning_rate": 1.642825544684101e-06,
|
| 1771 |
+
"loss": 0.8302,
|
| 1772 |
+
"step": 2660
|
| 1773 |
+
},
|
| 1774 |
+
{
|
| 1775 |
+
"epoch": 6.94300518134715,
|
| 1776 |
+
"grad_norm": 0.201171875,
|
| 1777 |
+
"learning_rate": 1.5952219697661455e-06,
|
| 1778 |
+
"loss": 0.8338,
|
| 1779 |
+
"step": 2680
|
| 1780 |
+
},
|
| 1781 |
+
{
|
| 1782 |
+
"epoch": 6.994818652849741,
|
| 1783 |
+
"grad_norm": 0.224609375,
|
| 1784 |
+
"learning_rate": 1.5479929641802492e-06,
|
| 1785 |
+
"loss": 0.837,
|
| 1786 |
+
"step": 2700
|
| 1787 |
+
},
|
| 1788 |
+
{
|
| 1789 |
+
"epoch": 6.994818652849741,
|
| 1790 |
+
"eval_main_loss": 0.8372467160224915,
|
| 1791 |
+
"eval_main_runtime": 50.6632,
|
| 1792 |
+
"eval_main_samples_per_second": 30.318,
|
| 1793 |
+
"eval_main_steps_per_second": 3.79,
|
| 1794 |
+
"step": 2700
|
| 1795 |
+
},
|
| 1796 |
+
{
|
| 1797 |
+
"epoch": 6.994818652849741,
|
| 1798 |
+
"eval_anatomy_loss": 2.399848222732544,
|
| 1799 |
+
"eval_anatomy_runtime": 0.2663,
|
| 1800 |
+
"eval_anatomy_samples_per_second": 7.512,
|
| 1801 |
+
"eval_anatomy_steps_per_second": 3.756,
|
| 1802 |
+
"step": 2700
|
| 1803 |
+
},
|
| 1804 |
+
{
|
| 1805 |
+
"epoch": 6.994818652849741,
|
| 1806 |
+
"eval_college_mathematics_loss": 1.7486381530761719,
|
| 1807 |
+
"eval_college_mathematics_runtime": 0.268,
|
| 1808 |
+
"eval_college_mathematics_samples_per_second": 7.464,
|
| 1809 |
+
"eval_college_mathematics_steps_per_second": 3.732,
|
| 1810 |
+
"step": 2700
|
| 1811 |
+
},
|
| 1812 |
+
{
|
| 1813 |
+
"epoch": 6.994818652849741,
|
| 1814 |
+
"eval_international_law_loss": 2.637385845184326,
|
| 1815 |
+
"eval_international_law_runtime": 0.2665,
|
| 1816 |
+
"eval_international_law_samples_per_second": 7.504,
|
| 1817 |
+
"eval_international_law_steps_per_second": 3.752,
|
| 1818 |
+
"step": 2700
|
| 1819 |
+
},
|
| 1820 |
+
{
|
| 1821 |
+
"epoch": 7.046632124352332,
|
| 1822 |
+
"grad_norm": 0.2431640625,
|
| 1823 |
+
"learning_rate": 1.5011580802768048e-06,
|
| 1824 |
+
"loss": 0.8392,
|
| 1825 |
+
"step": 2720
|
| 1826 |
+
},
|
| 1827 |
+
{
|
| 1828 |
+
"epoch": 7.098445595854923,
|
| 1829 |
+
"grad_norm": 0.2333984375,
|
| 1830 |
+
"learning_rate": 1.4547367072436519e-06,
|
| 1831 |
+
"loss": 0.8326,
|
| 1832 |
+
"step": 2740
|
| 1833 |
+
},
|
| 1834 |
+
{
|
| 1835 |
+
"epoch": 7.150259067357513,
|
| 1836 |
+
"grad_norm": 0.2275390625,
|
| 1837 |
+
"learning_rate": 1.4087480630791405e-06,
|
| 1838 |
+
"loss": 0.8324,
|
| 1839 |
+
"step": 2760
|
| 1840 |
+
},
|
| 1841 |
+
{
|
| 1842 |
+
"epoch": 7.2020725388601035,
|
| 1843 |
+
"grad_norm": 0.2333984375,
|
| 1844 |
+
"learning_rate": 1.3632111866360585e-06,
|
| 1845 |
+
"loss": 0.8309,
|
| 1846 |
+
"step": 2780
|
| 1847 |
+
},
|
| 1848 |
+
{
|
| 1849 |
+
"epoch": 7.253886010362694,
|
| 1850 |
+
"grad_norm": 0.2265625,
|
| 1851 |
+
"learning_rate": 1.318144929739743e-06,
|
| 1852 |
+
"loss": 0.8292,
|
| 1853 |
+
"step": 2800
|
| 1854 |
+
},
|
| 1855 |
+
{
|
| 1856 |
+
"epoch": 7.253886010362694,
|
| 1857 |
+
"eval_main_loss": 0.8372478485107422,
|
| 1858 |
+
"eval_main_runtime": 50.677,
|
| 1859 |
+
"eval_main_samples_per_second": 30.31,
|
| 1860 |
+
"eval_main_steps_per_second": 3.789,
|
| 1861 |
+
"step": 2800
|
| 1862 |
+
},
|
| 1863 |
+
{
|
| 1864 |
+
"epoch": 7.253886010362694,
|
| 1865 |
+
"eval_anatomy_loss": 2.3977112770080566,
|
| 1866 |
+
"eval_anatomy_runtime": 0.2672,
|
| 1867 |
+
"eval_anatomy_samples_per_second": 7.484,
|
| 1868 |
+
"eval_anatomy_steps_per_second": 3.742,
|
| 1869 |
+
"step": 2800
|
| 1870 |
+
},
|
| 1871 |
+
{
|
| 1872 |
+
"epoch": 7.253886010362694,
|
| 1873 |
+
"eval_college_mathematics_loss": 1.745300531387329,
|
| 1874 |
+
"eval_college_mathematics_runtime": 0.2659,
|
| 1875 |
+
"eval_college_mathematics_samples_per_second": 7.523,
|
| 1876 |
+
"eval_college_mathematics_steps_per_second": 3.761,
|
| 1877 |
+
"step": 2800
|
| 1878 |
+
},
|
| 1879 |
+
{
|
| 1880 |
+
"epoch": 7.253886010362694,
|
| 1881 |
+
"eval_international_law_loss": 2.6362087726593018,
|
| 1882 |
+
"eval_international_law_runtime": 0.2666,
|
| 1883 |
+
"eval_international_law_samples_per_second": 7.502,
|
| 1884 |
+
"eval_international_law_steps_per_second": 3.751,
|
| 1885 |
+
"step": 2800
|
| 1886 |
+
},
|
| 1887 |
+
{
|
| 1888 |
+
"epoch": 7.305699481865285,
|
| 1889 |
+
"grad_norm": 0.2451171875,
|
| 1890 |
+
"learning_rate": 1.273567949383601e-06,
|
| 1891 |
+
"loss": 0.8384,
|
| 1892 |
+
"step": 2820
|
| 1893 |
+
},
|
| 1894 |
+
{
|
| 1895 |
+
"epoch": 7.357512953367876,
|
| 1896 |
+
"grad_norm": 0.21875,
|
| 1897 |
+
"learning_rate": 1.229498700005295e-06,
|
| 1898 |
+
"loss": 0.8375,
|
| 1899 |
+
"step": 2840
|
| 1900 |
+
},
|
| 1901 |
+
{
|
| 1902 |
+
"epoch": 7.409326424870466,
|
| 1903 |
+
"grad_norm": 0.2314453125,
|
| 1904 |
+
"learning_rate": 1.1859554258467843e-06,
|
| 1905 |
+
"loss": 0.8416,
|
| 1906 |
+
"step": 2860
|
| 1907 |
+
},
|
| 1908 |
+
{
|
| 1909 |
+
"epoch": 7.461139896373057,
|
| 1910 |
+
"grad_norm": 0.2265625,
|
| 1911 |
+
"learning_rate": 1.1429561534013869e-06,
|
| 1912 |
+
"loss": 0.8367,
|
| 1913 |
+
"step": 2880
|
| 1914 |
+
},
|
| 1915 |
+
{
|
| 1916 |
+
"epoch": 7.512953367875648,
|
| 1917 |
+
"grad_norm": 0.2412109375,
|
| 1918 |
+
"learning_rate": 1.1005186839509887e-06,
|
| 1919 |
+
"loss": 0.8372,
|
| 1920 |
+
"step": 2900
|
| 1921 |
+
},
|
| 1922 |
+
{
|
| 1923 |
+
"epoch": 7.512953367875648,
|
| 1924 |
+
"eval_main_loss": 0.8372209668159485,
|
| 1925 |
+
"eval_main_runtime": 50.6545,
|
| 1926 |
+
"eval_main_samples_per_second": 30.323,
|
| 1927 |
+
"eval_main_steps_per_second": 3.79,
|
| 1928 |
+
"step": 2900
|
| 1929 |
+
},
|
| 1930 |
+
{
|
| 1931 |
+
"epoch": 7.512953367875648,
|
| 1932 |
+
"eval_anatomy_loss": 2.3963139057159424,
|
| 1933 |
+
"eval_anatomy_runtime": 0.2679,
|
| 1934 |
+
"eval_anatomy_samples_per_second": 7.464,
|
| 1935 |
+
"eval_anatomy_steps_per_second": 3.732,
|
| 1936 |
+
"step": 2900
|
| 1937 |
+
},
|
| 1938 |
+
{
|
| 1939 |
+
"epoch": 7.512953367875648,
|
| 1940 |
+
"eval_college_mathematics_loss": 1.7459056377410889,
|
| 1941 |
+
"eval_college_mathematics_runtime": 0.2655,
|
| 1942 |
+
"eval_college_mathematics_samples_per_second": 7.534,
|
| 1943 |
+
"eval_college_mathematics_steps_per_second": 3.767,
|
| 1944 |
+
"step": 2900
|
| 1945 |
+
},
|
| 1946 |
+
{
|
| 1947 |
+
"epoch": 7.512953367875648,
|
| 1948 |
+
"eval_international_law_loss": 2.6337826251983643,
|
| 1949 |
+
"eval_international_law_runtime": 0.2662,
|
| 1950 |
+
"eval_international_law_samples_per_second": 7.512,
|
| 1951 |
+
"eval_international_law_steps_per_second": 3.756,
|
| 1952 |
+
"step": 2900
|
| 1953 |
+
},
|
| 1954 |
+
{
|
| 1955 |
+
"epoch": 7.564766839378239,
|
| 1956 |
+
"grad_norm": 0.2138671875,
|
| 1957 |
+
"learning_rate": 1.0586605861964804e-06,
|
| 1958 |
+
"loss": 0.8313,
|
| 1959 |
+
"step": 2920
|
| 1960 |
+
},
|
| 1961 |
+
{
|
| 1962 |
+
"epoch": 7.616580310880829,
|
| 1963 |
+
"grad_norm": 0.2431640625,
|
| 1964 |
+
"learning_rate": 1.01739918898449e-06,
|
| 1965 |
+
"loss": 0.8346,
|
| 1966 |
+
"step": 2940
|
| 1967 |
+
},
|
| 1968 |
+
{
|
| 1969 |
+
"epoch": 7.668393782383419,
|
| 1970 |
+
"grad_norm": 0.21875,
|
| 1971 |
+
"learning_rate": 9.767515741334039e-07,
|
| 1972 |
+
"loss": 0.8372,
|
| 1973 |
+
"step": 2960
|
| 1974 |
+
},
|
| 1975 |
+
{
|
| 1976 |
+
"epoch": 7.72020725388601,
|
| 1977 |
+
"grad_norm": 0.2177734375,
|
| 1978 |
+
"learning_rate": 9.367345693616625e-07,
|
| 1979 |
+
"loss": 0.8343,
|
| 1980 |
+
"step": 2980
|
| 1981 |
+
},
|
| 1982 |
+
{
|
| 1983 |
+
"epoch": 7.772020725388601,
|
| 1984 |
+
"grad_norm": 0.24609375,
|
| 1985 |
+
"learning_rate": 8.973647413212494e-07,
|
| 1986 |
+
"loss": 0.8441,
|
| 1987 |
+
"step": 3000
|
| 1988 |
+
},
|
| 1989 |
+
{
|
| 1990 |
+
"epoch": 7.772020725388601,
|
| 1991 |
+
"eval_main_loss": 0.8372817039489746,
|
| 1992 |
+
"eval_main_runtime": 50.6245,
|
| 1993 |
+
"eval_main_samples_per_second": 30.341,
|
| 1994 |
+
"eval_main_steps_per_second": 3.793,
|
| 1995 |
+
"step": 3000
|
| 1996 |
+
},
|
| 1997 |
+
{
|
| 1998 |
+
"epoch": 7.772020725388601,
|
| 1999 |
+
"eval_anatomy_loss": 2.3954248428344727,
|
| 2000 |
+
"eval_anatomy_runtime": 0.2651,
|
| 2001 |
+
"eval_anatomy_samples_per_second": 7.545,
|
| 2002 |
+
"eval_anatomy_steps_per_second": 3.773,
|
| 2003 |
+
"step": 3000
|
| 2004 |
+
},
|
| 2005 |
+
{
|
| 2006 |
+
"epoch": 7.772020725388601,
|
| 2007 |
+
"eval_college_mathematics_loss": 1.744511365890503,
|
| 2008 |
+
"eval_college_mathematics_runtime": 0.2656,
|
| 2009 |
+
"eval_college_mathematics_samples_per_second": 7.53,
|
| 2010 |
+
"eval_college_mathematics_steps_per_second": 3.765,
|
| 2011 |
+
"step": 3000
|
| 2012 |
+
},
|
| 2013 |
+
{
|
| 2014 |
+
"epoch": 7.772020725388601,
|
| 2015 |
+
"eval_international_law_loss": 2.635951280593872,
|
| 2016 |
+
"eval_international_law_runtime": 0.2679,
|
| 2017 |
+
"eval_international_law_samples_per_second": 7.464,
|
| 2018 |
+
"eval_international_law_steps_per_second": 3.732,
|
| 2019 |
+
"step": 3000
|
| 2020 |
+
},
|
| 2021 |
+
{
|
| 2022 |
+
"epoch": 7.823834196891192,
|
| 2023 |
+
"grad_norm": 0.22265625,
|
| 2024 |
+
"learning_rate": 8.586583887392546e-07,
|
| 2025 |
+
"loss": 0.8383,
|
| 2026 |
+
"step": 3020
|
| 2027 |
+
},
|
| 2028 |
+
{
|
| 2029 |
+
"epoch": 7.875647668393782,
|
| 2030 |
+
"grad_norm": 0.2177734375,
|
| 2031 |
+
"learning_rate": 8.206315356703634e-07,
|
| 2032 |
+
"loss": 0.8312,
|
| 2033 |
+
"step": 3040
|
| 2034 |
+
},
|
| 2035 |
+
{
|
| 2036 |
+
"epoch": 7.927461139896373,
|
| 2037 |
+
"grad_norm": 0.2265625,
|
| 2038 |
+
"learning_rate": 7.832999248630479e-07,
|
| 2039 |
+
"loss": 0.8401,
|
| 2040 |
+
"step": 3060
|
| 2041 |
+
},
|
| 2042 |
+
{
|
| 2043 |
+
"epoch": 7.979274611398964,
|
| 2044 |
+
"grad_norm": 0.2490234375,
|
| 2045 |
+
"learning_rate": 7.466790112422257e-07,
|
| 2046 |
+
"loss": 0.8283,
|
| 2047 |
+
"step": 3080
|
| 2048 |
+
},
|
| 2049 |
+
{
|
| 2050 |
+
"epoch": 8.031088082901555,
|
| 2051 |
+
"grad_norm": 0.2216796875,
|
| 2052 |
+
"learning_rate": 7.107839555110707e-07,
|
| 2053 |
+
"loss": 0.8378,
|
| 2054 |
+
"step": 3100
|
| 2055 |
+
},
|
| 2056 |
+
{
|
| 2057 |
+
"epoch": 8.031088082901555,
|
| 2058 |
+
"eval_main_loss": 0.8372604846954346,
|
| 2059 |
+
"eval_main_runtime": 50.6329,
|
| 2060 |
+
"eval_main_samples_per_second": 30.336,
|
| 2061 |
+
"eval_main_steps_per_second": 3.792,
|
| 2062 |
+
"step": 3100
|
| 2063 |
+
},
|
| 2064 |
+
{
|
| 2065 |
+
"epoch": 8.031088082901555,
|
| 2066 |
+
"eval_anatomy_loss": 2.397829532623291,
|
| 2067 |
+
"eval_anatomy_runtime": 0.2664,
|
| 2068 |
+
"eval_anatomy_samples_per_second": 7.509,
|
| 2069 |
+
"eval_anatomy_steps_per_second": 3.754,
|
| 2070 |
+
"step": 3100
|
| 2071 |
+
},
|
| 2072 |
+
{
|
| 2073 |
+
"epoch": 8.031088082901555,
|
| 2074 |
+
"eval_college_mathematics_loss": 1.745050311088562,
|
| 2075 |
+
"eval_college_mathematics_runtime": 0.2662,
|
| 2076 |
+
"eval_college_mathematics_samples_per_second": 7.512,
|
| 2077 |
+
"eval_college_mathematics_steps_per_second": 3.756,
|
| 2078 |
+
"step": 3100
|
| 2079 |
+
},
|
| 2080 |
+
{
|
| 2081 |
+
"epoch": 8.031088082901555,
|
| 2082 |
+
"eval_international_law_loss": 2.635841131210327,
|
| 2083 |
+
"eval_international_law_runtime": 0.2664,
|
| 2084 |
+
"eval_international_law_samples_per_second": 7.508,
|
| 2085 |
+
"eval_international_law_steps_per_second": 3.754,
|
| 2086 |
+
"step": 3100
|
| 2087 |
+
},
|
| 2088 |
+
{
|
| 2089 |
+
"epoch": 8.082901554404145,
|
| 2090 |
+
"grad_norm": 0.20703125,
|
| 2091 |
+
"learning_rate": 6.756296178746282e-07,
|
| 2092 |
+
"loss": 0.8382,
|
| 2093 |
+
"step": 3120
|
| 2094 |
+
},
|
| 2095 |
+
{
|
| 2096 |
+
"epoch": 8.134715025906736,
|
| 2097 |
+
"grad_norm": 0.23828125,
|
| 2098 |
+
"learning_rate": 6.412305518878343e-07,
|
| 2099 |
+
"loss": 0.8411,
|
| 2100 |
+
"step": 3140
|
| 2101 |
+
},
|
| 2102 |
+
{
|
| 2103 |
+
"epoch": 8.186528497409327,
|
| 2104 |
+
"grad_norm": 0.2294921875,
|
| 2105 |
+
"learning_rate": 6.076009984304837e-07,
|
| 2106 |
+
"loss": 0.8411,
|
| 2107 |
+
"step": 3160
|
| 2108 |
+
},
|
| 2109 |
+
{
|
| 2110 |
+
"epoch": 8.238341968911918,
|
| 2111 |
+
"grad_norm": 0.2216796875,
|
| 2112 |
+
"learning_rate": 5.747548798116451e-07,
|
| 2113 |
+
"loss": 0.8384,
|
| 2114 |
+
"step": 3180
|
| 2115 |
+
},
|
| 2116 |
+
{
|
| 2117 |
+
"epoch": 8.290155440414507,
|
| 2118 |
+
"grad_norm": 0.2119140625,
|
| 2119 |
+
"learning_rate": 5.427057940059607e-07,
|
| 2120 |
+
"loss": 0.8304,
|
| 2121 |
+
"step": 3200
|
| 2122 |
+
},
|
| 2123 |
+
{
|
| 2124 |
+
"epoch": 8.290155440414507,
|
| 2125 |
+
"eval_main_loss": 0.8372419476509094,
|
| 2126 |
+
"eval_main_runtime": 50.616,
|
| 2127 |
+
"eval_main_samples_per_second": 30.346,
|
| 2128 |
+
"eval_main_steps_per_second": 3.793,
|
| 2129 |
+
"step": 3200
|
| 2130 |
+
},
|
| 2131 |
+
{
|
| 2132 |
+
"epoch": 8.290155440414507,
|
| 2133 |
+
"eval_anatomy_loss": 2.398320436477661,
|
| 2134 |
+
"eval_anatomy_runtime": 0.2666,
|
| 2135 |
+
"eval_anatomy_samples_per_second": 7.501,
|
| 2136 |
+
"eval_anatomy_steps_per_second": 3.751,
|
| 2137 |
+
"step": 3200
|
| 2138 |
+
},
|
| 2139 |
+
{
|
| 2140 |
+
"epoch": 8.290155440414507,
|
| 2141 |
+
"eval_college_mathematics_loss": 1.7492754459381104,
|
| 2142 |
+
"eval_college_mathematics_runtime": 0.2666,
|
| 2143 |
+
"eval_college_mathematics_samples_per_second": 7.501,
|
| 2144 |
+
"eval_college_mathematics_steps_per_second": 3.75,
|
| 2145 |
+
"step": 3200
|
| 2146 |
+
},
|
| 2147 |
+
{
|
| 2148 |
+
"epoch": 8.290155440414507,
|
| 2149 |
+
"eval_international_law_loss": 2.6363821029663086,
|
| 2150 |
+
"eval_international_law_runtime": 0.266,
|
| 2151 |
+
"eval_international_law_samples_per_second": 7.519,
|
| 2152 |
+
"eval_international_law_steps_per_second": 3.76,
|
| 2153 |
+
"step": 3200
|
| 2154 |
+
},
|
| 2155 |
+
{
|
| 2156 |
+
"epoch": 8.341968911917098,
|
| 2157 |
+
"grad_norm": 0.2255859375,
|
| 2158 |
+
"learning_rate": 5.11467009024216e-07,
|
| 2159 |
+
"loss": 0.8361,
|
| 2160 |
+
"step": 3220
|
| 2161 |
+
},
|
| 2162 |
+
{
|
| 2163 |
+
"epoch": 8.393782383419689,
|
| 2164 |
+
"grad_norm": 0.2294921875,
|
| 2165 |
+
"learning_rate": 4.810514574205125e-07,
|
| 2166 |
+
"loss": 0.8339,
|
| 2167 |
+
"step": 3240
|
| 2168 |
+
},
|
| 2169 |
+
{
|
| 2170 |
+
"epoch": 8.44559585492228,
|
| 2171 |
+
"grad_norm": 0.2294921875,
|
| 2172 |
+
"learning_rate": 4.5147173093831264e-07,
|
| 2173 |
+
"loss": 0.8345,
|
| 2174 |
+
"step": 3260
|
| 2175 |
+
},
|
| 2176 |
+
{
|
| 2177 |
+
"epoch": 8.49740932642487,
|
| 2178 |
+
"grad_norm": 0.2265625,
|
| 2179 |
+
"learning_rate": 4.227400752975835e-07,
|
| 2180 |
+
"loss": 0.8374,
|
| 2181 |
+
"step": 3280
|
| 2182 |
+
},
|
| 2183 |
+
{
|
| 2184 |
+
"epoch": 8.549222797927461,
|
| 2185 |
+
"grad_norm": 0.2294921875,
|
| 2186 |
+
"learning_rate": 3.9486838512518777e-07,
|
| 2187 |
+
"loss": 0.8374,
|
| 2188 |
+
"step": 3300
|
| 2189 |
+
},
|
| 2190 |
+
{
|
| 2191 |
+
"epoch": 8.549222797927461,
|
| 2192 |
+
"eval_main_loss": 0.8372399806976318,
|
| 2193 |
+
"eval_main_runtime": 50.5872,
|
| 2194 |
+
"eval_main_samples_per_second": 30.363,
|
| 2195 |
+
"eval_main_steps_per_second": 3.795,
|
| 2196 |
+
"step": 3300
|
| 2197 |
+
},
|
| 2198 |
+
{
|
| 2199 |
+
"epoch": 8.549222797927461,
|
| 2200 |
+
"eval_anatomy_loss": 2.3960189819335938,
|
| 2201 |
+
"eval_anatomy_runtime": 0.2667,
|
| 2202 |
+
"eval_anatomy_samples_per_second": 7.498,
|
| 2203 |
+
"eval_anatomy_steps_per_second": 3.749,
|
| 2204 |
+
"step": 3300
|
| 2205 |
+
},
|
| 2206 |
+
{
|
| 2207 |
+
"epoch": 8.549222797927461,
|
| 2208 |
+
"eval_college_mathematics_loss": 1.7492492198944092,
|
| 2209 |
+
"eval_college_mathematics_runtime": 0.2676,
|
| 2210 |
+
"eval_college_mathematics_samples_per_second": 7.475,
|
| 2211 |
+
"eval_college_mathematics_steps_per_second": 3.738,
|
| 2212 |
+
"step": 3300
|
| 2213 |
+
},
|
| 2214 |
+
{
|
| 2215 |
+
"epoch": 8.549222797927461,
|
| 2216 |
+
"eval_international_law_loss": 2.6380083560943604,
|
| 2217 |
+
"eval_international_law_runtime": 0.2658,
|
| 2218 |
+
"eval_international_law_samples_per_second": 7.525,
|
| 2219 |
+
"eval_international_law_steps_per_second": 3.762,
|
| 2220 |
+
"step": 3300
|
| 2221 |
+
},
|
| 2222 |
+
{
|
| 2223 |
+
"epoch": 8.601036269430052,
|
| 2224 |
+
"grad_norm": 0.255859375,
|
| 2225 |
+
"learning_rate": 3.678681990306207e-07,
|
| 2226 |
+
"loss": 0.8359,
|
| 2227 |
+
"step": 3320
|
| 2228 |
+
},
|
| 2229 |
+
{
|
| 2230 |
+
"epoch": 8.652849740932643,
|
| 2231 |
+
"grad_norm": 0.2412109375,
|
| 2232 |
+
"learning_rate": 3.4175069482914105e-07,
|
| 2233 |
+
"loss": 0.8284,
|
| 2234 |
+
"step": 3340
|
| 2235 |
+
},
|
| 2236 |
+
{
|
| 2237 |
+
"epoch": 8.704663212435234,
|
| 2238 |
+
"grad_norm": 0.2138671875,
|
| 2239 |
+
"learning_rate": 3.165266849142581e-07,
|
| 2240 |
+
"loss": 0.8334,
|
| 2241 |
+
"step": 3360
|
| 2242 |
+
},
|
| 2243 |
+
{
|
| 2244 |
+
"epoch": 8.756476683937823,
|
| 2245 |
+
"grad_norm": 0.232421875,
|
| 2246 |
+
"learning_rate": 2.9220661178151366e-07,
|
| 2247 |
+
"loss": 0.8337,
|
| 2248 |
+
"step": 3380
|
| 2249 |
+
},
|
| 2250 |
+
{
|
| 2251 |
+
"epoch": 8.808290155440414,
|
| 2252 |
+
"grad_norm": 0.20703125,
|
| 2253 |
+
"learning_rate": 2.688005437053845e-07,
|
| 2254 |
+
"loss": 0.8382,
|
| 2255 |
+
"step": 3400
|
| 2256 |
+
},
|
| 2257 |
+
{
|
| 2258 |
+
"epoch": 8.808290155440414,
|
| 2259 |
+
"eval_main_loss": 0.8372331261634827,
|
| 2260 |
+
"eval_main_runtime": 50.6285,
|
| 2261 |
+
"eval_main_samples_per_second": 30.339,
|
| 2262 |
+
"eval_main_steps_per_second": 3.792,
|
| 2263 |
+
"step": 3400
|
| 2264 |
+
},
|
| 2265 |
+
{
|
| 2266 |
+
"epoch": 8.808290155440414,
|
| 2267 |
+
"eval_anatomy_loss": 2.39411997795105,
|
| 2268 |
+
"eval_anatomy_runtime": 0.2664,
|
| 2269 |
+
"eval_anatomy_samples_per_second": 7.507,
|
| 2270 |
+
"eval_anatomy_steps_per_second": 3.753,
|
| 2271 |
+
"step": 3400
|
| 2272 |
+
},
|
| 2273 |
+
{
|
| 2274 |
+
"epoch": 8.808290155440414,
|
| 2275 |
+
"eval_college_mathematics_loss": 1.7451952695846558,
|
| 2276 |
+
"eval_college_mathematics_runtime": 0.2673,
|
| 2277 |
+
"eval_college_mathematics_samples_per_second": 7.482,
|
| 2278 |
+
"eval_college_mathematics_steps_per_second": 3.741,
|
| 2279 |
+
"step": 3400
|
| 2280 |
+
},
|
| 2281 |
+
{
|
| 2282 |
+
"epoch": 8.808290155440414,
|
| 2283 |
+
"eval_international_law_loss": 2.6384801864624023,
|
| 2284 |
+
"eval_international_law_runtime": 0.2666,
|
| 2285 |
+
"eval_international_law_samples_per_second": 7.502,
|
| 2286 |
+
"eval_international_law_steps_per_second": 3.751,
|
| 2287 |
+
"step": 3400
|
| 2288 |
+
},
|
| 2289 |
+
{
|
| 2290 |
+
"epoch": 8.860103626943005,
|
| 2291 |
+
"grad_norm": 0.21875,
|
| 2292 |
+
"learning_rate": 2.4631817057111597e-07,
|
| 2293 |
+
"loss": 0.8363,
|
| 2294 |
+
"step": 3420
|
| 2295 |
+
},
|
| 2296 |
+
{
|
| 2297 |
+
"epoch": 8.911917098445596,
|
| 2298 |
+
"grad_norm": 0.2255859375,
|
| 2299 |
+
"learning_rate": 2.247687998632031e-07,
|
| 2300 |
+
"loss": 0.8389,
|
| 2301 |
+
"step": 3440
|
| 2302 |
+
},
|
| 2303 |
+
{
|
| 2304 |
+
"epoch": 8.963730569948186,
|
| 2305 |
+
"grad_norm": 0.21875,
|
| 2306 |
+
"learning_rate": 2.0416135281218218e-07,
|
| 2307 |
+
"loss": 0.8336,
|
| 2308 |
+
"step": 3460
|
| 2309 |
+
},
|
| 2310 |
+
{
|
| 2311 |
+
"epoch": 9.015544041450777,
|
| 2312 |
+
"grad_norm": 0.236328125,
|
| 2313 |
+
"learning_rate": 1.8450436070132889e-07,
|
| 2314 |
+
"loss": 0.8333,
|
| 2315 |
+
"step": 3480
|
| 2316 |
+
},
|
| 2317 |
+
{
|
| 2318 |
+
"epoch": 9.067357512953368,
|
| 2319 |
+
"grad_norm": 0.23828125,
|
| 2320 |
+
"learning_rate": 1.6580596133478926e-07,
|
| 2321 |
+
"loss": 0.8373,
|
| 2322 |
+
"step": 3500
|
| 2323 |
+
},
|
| 2324 |
+
{
|
| 2325 |
+
"epoch": 9.067357512953368,
|
| 2326 |
+
"eval_main_loss": 0.837254524230957,
|
| 2327 |
+
"eval_main_runtime": 50.6558,
|
| 2328 |
+
"eval_main_samples_per_second": 30.322,
|
| 2329 |
+
"eval_main_steps_per_second": 3.79,
|
| 2330 |
+
"step": 3500
|
| 2331 |
+
},
|
| 2332 |
+
{
|
| 2333 |
+
"epoch": 9.067357512953368,
|
| 2334 |
+
"eval_anatomy_loss": 2.395867347717285,
|
| 2335 |
+
"eval_anatomy_runtime": 0.2665,
|
| 2336 |
+
"eval_anatomy_samples_per_second": 7.506,
|
| 2337 |
+
"eval_anatomy_steps_per_second": 3.753,
|
| 2338 |
+
"step": 3500
|
| 2339 |
+
},
|
| 2340 |
+
{
|
| 2341 |
+
"epoch": 9.067357512953368,
|
| 2342 |
+
"eval_college_mathematics_loss": 1.7460345029830933,
|
| 2343 |
+
"eval_college_mathematics_runtime": 0.267,
|
| 2344 |
+
"eval_college_mathematics_samples_per_second": 7.491,
|
| 2345 |
+
"eval_college_mathematics_steps_per_second": 3.746,
|
| 2346 |
+
"step": 3500
|
| 2347 |
+
},
|
| 2348 |
+
{
|
| 2349 |
+
"epoch": 9.067357512953368,
|
| 2350 |
+
"eval_international_law_loss": 2.6364336013793945,
|
| 2351 |
+
"eval_international_law_runtime": 0.2659,
|
| 2352 |
+
"eval_international_law_samples_per_second": 7.522,
|
| 2353 |
+
"eval_international_law_steps_per_second": 3.761,
|
| 2354 |
+
"step": 3500
|
| 2355 |
+
},
|
| 2356 |
+
{
|
| 2357 |
+
"epoch": 9.119170984455959,
|
| 2358 |
+
"grad_norm": 0.2431640625,
|
| 2359 |
+
"learning_rate": 1.4807389566860675e-07,
|
| 2360 |
+
"loss": 0.838,
|
| 2361 |
+
"step": 3520
|
| 2362 |
+
},
|
| 2363 |
+
{
|
| 2364 |
+
"epoch": 9.17098445595855,
|
| 2365 |
+
"grad_norm": 0.2158203125,
|
| 2366 |
+
"learning_rate": 1.3131550460604242e-07,
|
| 2367 |
+
"loss": 0.8266,
|
| 2368 |
+
"step": 3540
|
| 2369 |
+
},
|
| 2370 |
+
{
|
| 2371 |
+
"epoch": 9.22279792746114,
|
| 2372 |
+
"grad_norm": 0.224609375,
|
| 2373 |
+
"learning_rate": 1.1553772595851109e-07,
|
| 2374 |
+
"loss": 0.8412,
|
| 2375 |
+
"step": 3560
|
| 2376 |
+
},
|
| 2377 |
+
{
|
| 2378 |
+
"epoch": 9.27461139896373,
|
| 2379 |
+
"grad_norm": 0.2412109375,
|
| 2380 |
+
"learning_rate": 1.0074709157339657e-07,
|
| 2381 |
+
"loss": 0.8361,
|
| 2382 |
+
"step": 3580
|
| 2383 |
+
},
|
| 2384 |
+
{
|
| 2385 |
+
"epoch": 9.32642487046632,
|
| 2386 |
+
"grad_norm": 0.2197265625,
|
| 2387 |
+
"learning_rate": 8.694972462992918e-08,
|
| 2388 |
+
"loss": 0.8373,
|
| 2389 |
+
"step": 3600
|
| 2390 |
+
},
|
| 2391 |
+
{
|
| 2392 |
+
"epoch": 9.32642487046632,
|
| 2393 |
+
"eval_main_loss": 0.8372175693511963,
|
| 2394 |
+
"eval_main_runtime": 50.62,
|
| 2395 |
+
"eval_main_samples_per_second": 30.344,
|
| 2396 |
+
"eval_main_steps_per_second": 3.793,
|
| 2397 |
+
"step": 3600
|
| 2398 |
+
},
|
| 2399 |
+
{
|
| 2400 |
+
"epoch": 9.32642487046632,
|
| 2401 |
+
"eval_anatomy_loss": 2.394951105117798,
|
| 2402 |
+
"eval_anatomy_runtime": 0.2668,
|
| 2403 |
+
"eval_anatomy_samples_per_second": 7.496,
|
| 2404 |
+
"eval_anatomy_steps_per_second": 3.748,
|
| 2405 |
+
"step": 3600
|
| 2406 |
+
},
|
| 2407 |
+
{
|
| 2408 |
+
"epoch": 9.32642487046632,
|
| 2409 |
+
"eval_college_mathematics_loss": 1.7458065748214722,
|
| 2410 |
+
"eval_college_mathematics_runtime": 0.2669,
|
| 2411 |
+
"eval_college_mathematics_samples_per_second": 7.494,
|
| 2412 |
+
"eval_college_mathematics_steps_per_second": 3.747,
|
| 2413 |
+
"step": 3600
|
| 2414 |
+
},
|
| 2415 |
+
{
|
| 2416 |
+
"epoch": 9.32642487046632,
|
| 2417 |
+
"eval_international_law_loss": 2.639335870742798,
|
| 2418 |
+
"eval_international_law_runtime": 0.2665,
|
| 2419 |
+
"eval_international_law_samples_per_second": 7.505,
|
| 2420 |
+
"eval_international_law_steps_per_second": 3.752,
|
| 2421 |
+
"step": 3600
|
| 2422 |
+
},
|
| 2423 |
+
{
|
| 2424 |
+
"epoch": 9.378238341968911,
|
| 2425 |
+
"grad_norm": 0.2431640625,
|
| 2426 |
+
"learning_rate": 7.415133710424794e-08,
|
| 2427 |
+
"loss": 0.8335,
|
| 2428 |
+
"step": 3620
|
| 2429 |
+
},
|
| 2430 |
+
{
|
| 2431 |
+
"epoch": 9.430051813471502,
|
| 2432 |
+
"grad_norm": 0.248046875,
|
| 2433 |
+
"learning_rate": 6.235722740469936e-08,
|
| 2434 |
+
"loss": 0.8379,
|
| 2435 |
+
"step": 3640
|
| 2436 |
+
},
|
| 2437 |
+
{
|
| 2438 |
+
"epoch": 9.481865284974093,
|
| 2439 |
+
"grad_norm": 0.23046875,
|
| 2440 |
+
"learning_rate": 5.157227817834648e-08,
|
| 2441 |
+
"loss": 0.831,
|
| 2442 |
+
"step": 3660
|
| 2443 |
+
},
|
| 2444 |
+
{
|
| 2445 |
+
"epoch": 9.533678756476684,
|
| 2446 |
+
"grad_norm": 0.2138671875,
|
| 2447 |
+
"learning_rate": 4.180095428960168e-08,
|
| 2448 |
+
"loss": 0.8399,
|
| 2449 |
+
"step": 3680
|
| 2450 |
+
},
|
| 2451 |
+
{
|
| 2452 |
+
"epoch": 9.585492227979275,
|
| 2453 |
+
"grad_norm": 0.2216796875,
|
| 2454 |
+
"learning_rate": 3.304730097181463e-08,
|
| 2455 |
+
"loss": 0.8428,
|
| 2456 |
+
"step": 3700
|
| 2457 |
+
},
|
| 2458 |
+
{
|
| 2459 |
+
"epoch": 9.585492227979275,
|
| 2460 |
+
"eval_main_loss": 0.8372709155082703,
|
| 2461 |
+
"eval_main_runtime": 50.6434,
|
| 2462 |
+
"eval_main_samples_per_second": 30.33,
|
| 2463 |
+
"eval_main_steps_per_second": 3.791,
|
| 2464 |
+
"step": 3700
|
| 2465 |
+
},
|
| 2466 |
+
{
|
| 2467 |
+
"epoch": 9.585492227979275,
|
| 2468 |
+
"eval_anatomy_loss": 2.3959925174713135,
|
| 2469 |
+
"eval_anatomy_runtime": 0.2686,
|
| 2470 |
+
"eval_anatomy_samples_per_second": 7.447,
|
| 2471 |
+
"eval_anatomy_steps_per_second": 3.723,
|
| 2472 |
+
"step": 3700
|
| 2473 |
+
},
|
| 2474 |
+
{
|
| 2475 |
+
"epoch": 9.585492227979275,
|
| 2476 |
+
"eval_college_mathematics_loss": 1.7489873170852661,
|
| 2477 |
+
"eval_college_mathematics_runtime": 0.2656,
|
| 2478 |
+
"eval_college_mathematics_samples_per_second": 7.529,
|
| 2479 |
+
"eval_college_mathematics_steps_per_second": 3.765,
|
| 2480 |
+
"step": 3700
|
| 2481 |
+
},
|
| 2482 |
+
{
|
| 2483 |
+
"epoch": 9.585492227979275,
|
| 2484 |
+
"eval_international_law_loss": 2.6358718872070312,
|
| 2485 |
+
"eval_international_law_runtime": 0.2658,
|
| 2486 |
+
"eval_international_law_samples_per_second": 7.525,
|
| 2487 |
+
"eval_international_law_steps_per_second": 3.763,
|
| 2488 |
+
"step": 3700
|
| 2489 |
+
},
|
| 2490 |
+
{
|
| 2491 |
+
"epoch": 9.637305699481866,
|
| 2492 |
+
"grad_norm": 0.2373046875,
|
| 2493 |
+
"learning_rate": 2.5314942152586954e-08,
|
| 2494 |
+
"loss": 0.8366,
|
| 2495 |
+
"step": 3720
|
| 2496 |
+
},
|
| 2497 |
+
{
|
| 2498 |
+
"epoch": 9.689119170984457,
|
| 2499 |
+
"grad_norm": 0.208984375,
|
| 2500 |
+
"learning_rate": 1.8607078953498392e-08,
|
| 2501 |
+
"loss": 0.8386,
|
| 2502 |
+
"step": 3740
|
| 2503 |
+
},
|
| 2504 |
+
{
|
| 2505 |
+
"epoch": 9.740932642487046,
|
| 2506 |
+
"grad_norm": 0.2421875,
|
| 2507 |
+
"learning_rate": 1.292648836487609e-08,
|
| 2508 |
+
"loss": 0.8321,
|
| 2509 |
+
"step": 3760
|
| 2510 |
+
},
|
| 2511 |
+
{
|
| 2512 |
+
"epoch": 9.792746113989637,
|
| 2513 |
+
"grad_norm": 0.2412109375,
|
| 2514 |
+
"learning_rate": 8.275522096146404e-09,
|
| 2515 |
+
"loss": 0.8342,
|
| 2516 |
+
"step": 3780
|
| 2517 |
+
},
|
| 2518 |
+
{
|
| 2519 |
+
"epoch": 9.844559585492227,
|
| 2520 |
+
"grad_norm": 0.2275390625,
|
| 2521 |
+
"learning_rate": 4.656105602250382e-09,
|
| 2522 |
+
"loss": 0.8404,
|
| 2523 |
+
"step": 3800
|
| 2524 |
+
},
|
| 2525 |
+
{
|
| 2526 |
+
"epoch": 9.844559585492227,
|
| 2527 |
+
"eval_main_loss": 0.8372488021850586,
|
| 2528 |
+
"eval_main_runtime": 50.6539,
|
| 2529 |
+
"eval_main_samples_per_second": 30.323,
|
| 2530 |
+
"eval_main_steps_per_second": 3.79,
|
| 2531 |
+
"step": 3800
|
| 2532 |
+
},
|
| 2533 |
+
{
|
| 2534 |
+
"epoch": 9.844559585492227,
|
| 2535 |
+
"eval_anatomy_loss": 2.3990156650543213,
|
| 2536 |
+
"eval_anatomy_runtime": 0.2664,
|
| 2537 |
+
"eval_anatomy_samples_per_second": 7.508,
|
| 2538 |
+
"eval_anatomy_steps_per_second": 3.754,
|
| 2539 |
+
"step": 3800
|
| 2540 |
+
},
|
| 2541 |
+
{
|
| 2542 |
+
"epoch": 9.844559585492227,
|
| 2543 |
+
"eval_college_mathematics_loss": 1.7470096349716187,
|
| 2544 |
+
"eval_college_mathematics_runtime": 0.2654,
|
| 2545 |
+
"eval_college_mathematics_samples_per_second": 7.535,
|
| 2546 |
+
"eval_college_mathematics_steps_per_second": 3.767,
|
| 2547 |
+
"step": 3800
|
| 2548 |
+
},
|
| 2549 |
+
{
|
| 2550 |
+
"epoch": 9.844559585492227,
|
| 2551 |
+
"eval_international_law_loss": 2.6360206604003906,
|
| 2552 |
+
"eval_international_law_runtime": 0.2672,
|
| 2553 |
+
"eval_international_law_samples_per_second": 7.485,
|
| 2554 |
+
"eval_international_law_steps_per_second": 3.743,
|
| 2555 |
+
"step": 3800
|
| 2556 |
+
},
|
| 2557 |
+
{
|
| 2558 |
+
"epoch": 9.896373056994818,
|
| 2559 |
+
"grad_norm": 0.2138671875,
|
| 2560 |
+
"learning_rate": 2.0697372865235986e-09,
|
| 2561 |
+
"loss": 0.8301,
|
| 2562 |
+
"step": 3820
|
| 2563 |
+
},
|
| 2564 |
+
{
|
| 2565 |
+
"epoch": 9.94818652849741,
|
| 2566 |
+
"grad_norm": 0.2265625,
|
| 2567 |
+
"learning_rate": 5.174878803720917e-10,
|
| 2568 |
+
"loss": 0.8299,
|
| 2569 |
+
"step": 3840
|
| 2570 |
+
},
|
| 2571 |
+
{
|
| 2572 |
+
"epoch": 10.0,
|
| 2573 |
+
"grad_norm": 0.201171875,
|
| 2574 |
+
"learning_rate": 0.0,
|
| 2575 |
+
"loss": 0.832,
|
| 2576 |
+
"step": 3860
|
| 2577 |
+
}
|
| 2578 |
+
],
|
| 2579 |
+
"logging_steps": 20,
|
| 2580 |
+
"max_steps": 3860,
|
| 2581 |
+
"num_input_tokens_seen": 0,
|
| 2582 |
+
"num_train_epochs": 10,
|
| 2583 |
+
"save_steps": 100,
|
| 2584 |
+
"stateful_callbacks": {
|
| 2585 |
+
"TrainerControl": {
|
| 2586 |
+
"args": {
|
| 2587 |
+
"should_epoch_stop": false,
|
| 2588 |
+
"should_evaluate": false,
|
| 2589 |
+
"should_log": false,
|
| 2590 |
+
"should_save": true,
|
| 2591 |
+
"should_training_stop": true
|
| 2592 |
+
},
|
| 2593 |
+
"attributes": {}
|
| 2594 |
+
}
|
| 2595 |
+
},
|
| 2596 |
+
"total_flos": 2.8346399786239263e+18,
|
| 2597 |
+
"train_batch_size": 4,
|
| 2598 |
+
"trial_name": null,
|
| 2599 |
+
"trial_params": null
|
| 2600 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:52f3ef97f3ab9418f885aaf4c8963ad7ac821d1da63c87fba4946899f606b035
|
| 3 |
+
size 5112
|