Upload folder using huggingface_hub
Browse files- README.md +204 -0
- adapter_config.json +35 -0
- adapter_model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +1566 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,204 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
base_model: SeaLLMs/SeaLLM-7B-v2
|
| 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 |
+
|
| 201 |
+
|
| 202 |
+
### Framework versions
|
| 203 |
+
|
| 204 |
+
- PEFT 0.9.1.dev0
|
adapter_config.json
ADDED
|
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "SeaLLMs/SeaLLM-7B-v2",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": false,
|
| 7 |
+
"inference_mode": true,
|
| 8 |
+
"init_lora_weights": true,
|
| 9 |
+
"layer_replication": null,
|
| 10 |
+
"layers_pattern": null,
|
| 11 |
+
"layers_to_transform": null,
|
| 12 |
+
"loftq_config": {},
|
| 13 |
+
"lora_alpha": 64,
|
| 14 |
+
"lora_dropout": 0.05,
|
| 15 |
+
"megatron_config": null,
|
| 16 |
+
"megatron_core": "megatron.core",
|
| 17 |
+
"modules_to_save": null,
|
| 18 |
+
"peft_type": "LORA",
|
| 19 |
+
"r": 32,
|
| 20 |
+
"rank_pattern": {},
|
| 21 |
+
"revision": null,
|
| 22 |
+
"target_modules": [
|
| 23 |
+
"q_proj",
|
| 24 |
+
"down_proj",
|
| 25 |
+
"gate_proj",
|
| 26 |
+
"k_proj",
|
| 27 |
+
"lm_head",
|
| 28 |
+
"o_proj",
|
| 29 |
+
"v_proj",
|
| 30 |
+
"up_proj"
|
| 31 |
+
],
|
| 32 |
+
"task_type": "CAUSAL_LM",
|
| 33 |
+
"use_dora": false,
|
| 34 |
+
"use_rslora": false
|
| 35 |
+
}
|
adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:881950e6663806a7a1cae84e16806fa4b0c356c7700d75b09e824d5a1038d104
|
| 3 |
+
size 1135046584
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5ee43ea073ea8bfd0122999e3f5401effb661df83831472b7c7613173f45d8e4
|
| 3 |
+
size 172002140
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e1fab63bc4c064521d684a84ba72e6a51341affd3d4ae1cf57dc3dee1786bdeb
|
| 3 |
+
size 14244
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1fca2dbc47f45142fd4d9074083bcceb2bd1672185349ccd98ffcef54047507e
|
| 3 |
+
size 1064
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1566 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.9941125373998648,
|
| 5 |
+
"eval_steps": 100,
|
| 6 |
+
"global_step": 10300,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.01,
|
| 13 |
+
"grad_norm": 5.765194416046143,
|
| 14 |
+
"learning_rate": 2.483498899926662e-05,
|
| 15 |
+
"loss": 1.8358,
|
| 16 |
+
"step": 100
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.01,
|
| 20 |
+
"eval_loss": 1.4509096145629883,
|
| 21 |
+
"eval_runtime": 27.2685,
|
| 22 |
+
"eval_samples_per_second": 18.336,
|
| 23 |
+
"eval_steps_per_second": 2.31,
|
| 24 |
+
"step": 100
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.02,
|
| 28 |
+
"grad_norm": 5.369307041168213,
|
| 29 |
+
"learning_rate": 2.466831122074805e-05,
|
| 30 |
+
"loss": 1.6055,
|
| 31 |
+
"step": 200
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.02,
|
| 35 |
+
"eval_loss": 1.4317318201065063,
|
| 36 |
+
"eval_runtime": 27.2583,
|
| 37 |
+
"eval_samples_per_second": 18.343,
|
| 38 |
+
"eval_steps_per_second": 2.311,
|
| 39 |
+
"step": 200
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.03,
|
| 43 |
+
"grad_norm": 5.935494422912598,
|
| 44 |
+
"learning_rate": 2.450163344222948e-05,
|
| 45 |
+
"loss": 1.7293,
|
| 46 |
+
"step": 300
|
| 47 |
+
},
|
| 48 |
+
{
|
| 49 |
+
"epoch": 0.03,
|
| 50 |
+
"eval_loss": 1.4047609567642212,
|
| 51 |
+
"eval_runtime": 27.2345,
|
| 52 |
+
"eval_samples_per_second": 18.359,
|
| 53 |
+
"eval_steps_per_second": 2.313,
|
| 54 |
+
"step": 300
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 0.04,
|
| 58 |
+
"grad_norm": 3.3592865467071533,
|
| 59 |
+
"learning_rate": 2.4334955663710914e-05,
|
| 60 |
+
"loss": 1.59,
|
| 61 |
+
"step": 400
|
| 62 |
+
},
|
| 63 |
+
{
|
| 64 |
+
"epoch": 0.04,
|
| 65 |
+
"eval_loss": 1.391677975654602,
|
| 66 |
+
"eval_runtime": 27.2416,
|
| 67 |
+
"eval_samples_per_second": 18.354,
|
| 68 |
+
"eval_steps_per_second": 2.313,
|
| 69 |
+
"step": 400
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.05,
|
| 73 |
+
"grad_norm": 5.640110492706299,
|
| 74 |
+
"learning_rate": 2.4168277885192348e-05,
|
| 75 |
+
"loss": 1.6514,
|
| 76 |
+
"step": 500
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"epoch": 0.05,
|
| 80 |
+
"eval_loss": 1.3870183229446411,
|
| 81 |
+
"eval_runtime": 27.2222,
|
| 82 |
+
"eval_samples_per_second": 18.367,
|
| 83 |
+
"eval_steps_per_second": 2.314,
|
| 84 |
+
"step": 500
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 0.06,
|
| 88 |
+
"grad_norm": 4.0497846603393555,
|
| 89 |
+
"learning_rate": 2.400160010667378e-05,
|
| 90 |
+
"loss": 1.5763,
|
| 91 |
+
"step": 600
|
| 92 |
+
},
|
| 93 |
+
{
|
| 94 |
+
"epoch": 0.06,
|
| 95 |
+
"eval_loss": 1.3725069761276245,
|
| 96 |
+
"eval_runtime": 27.2203,
|
| 97 |
+
"eval_samples_per_second": 18.369,
|
| 98 |
+
"eval_steps_per_second": 2.314,
|
| 99 |
+
"step": 600
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.07,
|
| 103 |
+
"grad_norm": 6.3066606521606445,
|
| 104 |
+
"learning_rate": 2.3834922328155212e-05,
|
| 105 |
+
"loss": 1.6176,
|
| 106 |
+
"step": 700
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 0.07,
|
| 110 |
+
"eval_loss": 1.3781300783157349,
|
| 111 |
+
"eval_runtime": 27.2227,
|
| 112 |
+
"eval_samples_per_second": 18.367,
|
| 113 |
+
"eval_steps_per_second": 2.314,
|
| 114 |
+
"step": 700
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.08,
|
| 118 |
+
"grad_norm": 7.34067964553833,
|
| 119 |
+
"learning_rate": 2.3668244549636642e-05,
|
| 120 |
+
"loss": 1.628,
|
| 121 |
+
"step": 800
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.08,
|
| 125 |
+
"eval_loss": 1.3644652366638184,
|
| 126 |
+
"eval_runtime": 27.2246,
|
| 127 |
+
"eval_samples_per_second": 18.366,
|
| 128 |
+
"eval_steps_per_second": 2.314,
|
| 129 |
+
"step": 800
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.09,
|
| 133 |
+
"grad_norm": 4.025296688079834,
|
| 134 |
+
"learning_rate": 2.3501566771118076e-05,
|
| 135 |
+
"loss": 1.5682,
|
| 136 |
+
"step": 900
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.09,
|
| 140 |
+
"eval_loss": 1.3602643013000488,
|
| 141 |
+
"eval_runtime": 27.2245,
|
| 142 |
+
"eval_samples_per_second": 18.366,
|
| 143 |
+
"eval_steps_per_second": 2.314,
|
| 144 |
+
"step": 900
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 0.1,
|
| 148 |
+
"grad_norm": 2.649806499481201,
|
| 149 |
+
"learning_rate": 2.3334888992599506e-05,
|
| 150 |
+
"loss": 1.5065,
|
| 151 |
+
"step": 1000
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 0.1,
|
| 155 |
+
"eval_loss": 1.3477470874786377,
|
| 156 |
+
"eval_runtime": 27.271,
|
| 157 |
+
"eval_samples_per_second": 18.334,
|
| 158 |
+
"eval_steps_per_second": 2.31,
|
| 159 |
+
"step": 1000
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.11,
|
| 163 |
+
"grad_norm": 4.1880974769592285,
|
| 164 |
+
"learning_rate": 2.316821121408094e-05,
|
| 165 |
+
"loss": 1.5344,
|
| 166 |
+
"step": 1100
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 0.11,
|
| 170 |
+
"eval_loss": 1.3474398851394653,
|
| 171 |
+
"eval_runtime": 27.2441,
|
| 172 |
+
"eval_samples_per_second": 18.353,
|
| 173 |
+
"eval_steps_per_second": 2.312,
|
| 174 |
+
"step": 1100
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 0.12,
|
| 178 |
+
"grad_norm": 7.770794868469238,
|
| 179 |
+
"learning_rate": 2.3001533435562373e-05,
|
| 180 |
+
"loss": 1.5565,
|
| 181 |
+
"step": 1200
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 0.12,
|
| 185 |
+
"eval_loss": 1.331454873085022,
|
| 186 |
+
"eval_runtime": 27.2308,
|
| 187 |
+
"eval_samples_per_second": 18.362,
|
| 188 |
+
"eval_steps_per_second": 2.314,
|
| 189 |
+
"step": 1200
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 0.13,
|
| 193 |
+
"grad_norm": 17.147653579711914,
|
| 194 |
+
"learning_rate": 2.2834855657043804e-05,
|
| 195 |
+
"loss": 1.564,
|
| 196 |
+
"step": 1300
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 0.13,
|
| 200 |
+
"eval_loss": 1.3280667066574097,
|
| 201 |
+
"eval_runtime": 27.2409,
|
| 202 |
+
"eval_samples_per_second": 18.355,
|
| 203 |
+
"eval_steps_per_second": 2.313,
|
| 204 |
+
"step": 1300
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 0.14,
|
| 208 |
+
"grad_norm": 3.113165855407715,
|
| 209 |
+
"learning_rate": 2.2668177878525237e-05,
|
| 210 |
+
"loss": 1.4985,
|
| 211 |
+
"step": 1400
|
| 212 |
+
},
|
| 213 |
+
{
|
| 214 |
+
"epoch": 0.14,
|
| 215 |
+
"eval_loss": 1.328255295753479,
|
| 216 |
+
"eval_runtime": 27.2314,
|
| 217 |
+
"eval_samples_per_second": 18.361,
|
| 218 |
+
"eval_steps_per_second": 2.314,
|
| 219 |
+
"step": 1400
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.14,
|
| 223 |
+
"grad_norm": 8.325815200805664,
|
| 224 |
+
"learning_rate": 2.2501500100006667e-05,
|
| 225 |
+
"loss": 1.5745,
|
| 226 |
+
"step": 1500
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.14,
|
| 230 |
+
"eval_loss": 1.3225585222244263,
|
| 231 |
+
"eval_runtime": 27.2173,
|
| 232 |
+
"eval_samples_per_second": 18.371,
|
| 233 |
+
"eval_steps_per_second": 2.315,
|
| 234 |
+
"step": 1500
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.15,
|
| 238 |
+
"grad_norm": 2.7448880672454834,
|
| 239 |
+
"learning_rate": 2.23348223214881e-05,
|
| 240 |
+
"loss": 1.4828,
|
| 241 |
+
"step": 1600
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.15,
|
| 245 |
+
"eval_loss": 1.3202852010726929,
|
| 246 |
+
"eval_runtime": 27.2236,
|
| 247 |
+
"eval_samples_per_second": 18.366,
|
| 248 |
+
"eval_steps_per_second": 2.314,
|
| 249 |
+
"step": 1600
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 0.16,
|
| 253 |
+
"grad_norm": 11.465213775634766,
|
| 254 |
+
"learning_rate": 2.216814454296953e-05,
|
| 255 |
+
"loss": 1.5091,
|
| 256 |
+
"step": 1700
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 0.16,
|
| 260 |
+
"eval_loss": 1.3147573471069336,
|
| 261 |
+
"eval_runtime": 27.2355,
|
| 262 |
+
"eval_samples_per_second": 18.358,
|
| 263 |
+
"eval_steps_per_second": 2.313,
|
| 264 |
+
"step": 1700
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 0.17,
|
| 268 |
+
"grad_norm": 6.742743015289307,
|
| 269 |
+
"learning_rate": 2.2001466764450965e-05,
|
| 270 |
+
"loss": 1.5142,
|
| 271 |
+
"step": 1800
|
| 272 |
+
},
|
| 273 |
+
{
|
| 274 |
+
"epoch": 0.17,
|
| 275 |
+
"eval_loss": 1.310064435005188,
|
| 276 |
+
"eval_runtime": 27.2194,
|
| 277 |
+
"eval_samples_per_second": 18.369,
|
| 278 |
+
"eval_steps_per_second": 2.315,
|
| 279 |
+
"step": 1800
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 0.18,
|
| 283 |
+
"grad_norm": 6.905991077423096,
|
| 284 |
+
"learning_rate": 2.18347889859324e-05,
|
| 285 |
+
"loss": 1.4293,
|
| 286 |
+
"step": 1900
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 0.18,
|
| 290 |
+
"eval_loss": 1.303736686706543,
|
| 291 |
+
"eval_runtime": 27.2248,
|
| 292 |
+
"eval_samples_per_second": 18.366,
|
| 293 |
+
"eval_steps_per_second": 2.314,
|
| 294 |
+
"step": 1900
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 0.19,
|
| 298 |
+
"grad_norm": 7.1159162521362305,
|
| 299 |
+
"learning_rate": 2.166811120741383e-05,
|
| 300 |
+
"loss": 1.6055,
|
| 301 |
+
"step": 2000
|
| 302 |
+
},
|
| 303 |
+
{
|
| 304 |
+
"epoch": 0.19,
|
| 305 |
+
"eval_loss": 1.2934476137161255,
|
| 306 |
+
"eval_runtime": 27.2203,
|
| 307 |
+
"eval_samples_per_second": 18.369,
|
| 308 |
+
"eval_steps_per_second": 2.314,
|
| 309 |
+
"step": 2000
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 0.2,
|
| 313 |
+
"grad_norm": 7.020285606384277,
|
| 314 |
+
"learning_rate": 2.150143342889526e-05,
|
| 315 |
+
"loss": 1.526,
|
| 316 |
+
"step": 2100
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 0.2,
|
| 320 |
+
"eval_loss": 1.295276165008545,
|
| 321 |
+
"eval_runtime": 27.2359,
|
| 322 |
+
"eval_samples_per_second": 18.358,
|
| 323 |
+
"eval_steps_per_second": 2.313,
|
| 324 |
+
"step": 2100
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.21,
|
| 328 |
+
"grad_norm": 12.202252388000488,
|
| 329 |
+
"learning_rate": 2.1334755650376693e-05,
|
| 330 |
+
"loss": 1.5421,
|
| 331 |
+
"step": 2200
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.21,
|
| 335 |
+
"eval_loss": 1.2898857593536377,
|
| 336 |
+
"eval_runtime": 27.2174,
|
| 337 |
+
"eval_samples_per_second": 18.371,
|
| 338 |
+
"eval_steps_per_second": 2.315,
|
| 339 |
+
"step": 2200
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.22,
|
| 343 |
+
"grad_norm": 8.110170364379883,
|
| 344 |
+
"learning_rate": 2.1168077871858126e-05,
|
| 345 |
+
"loss": 1.5439,
|
| 346 |
+
"step": 2300
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.22,
|
| 350 |
+
"eval_loss": 1.2835201025009155,
|
| 351 |
+
"eval_runtime": 27.234,
|
| 352 |
+
"eval_samples_per_second": 18.359,
|
| 353 |
+
"eval_steps_per_second": 2.313,
|
| 354 |
+
"step": 2300
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 0.23,
|
| 358 |
+
"grad_norm": 9.563570022583008,
|
| 359 |
+
"learning_rate": 2.1001400093339556e-05,
|
| 360 |
+
"loss": 1.4597,
|
| 361 |
+
"step": 2400
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 0.23,
|
| 365 |
+
"eval_loss": 1.2785178422927856,
|
| 366 |
+
"eval_runtime": 27.2163,
|
| 367 |
+
"eval_samples_per_second": 18.371,
|
| 368 |
+
"eval_steps_per_second": 2.315,
|
| 369 |
+
"step": 2400
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 0.24,
|
| 373 |
+
"grad_norm": 14.292014122009277,
|
| 374 |
+
"learning_rate": 2.083472231482099e-05,
|
| 375 |
+
"loss": 1.4039,
|
| 376 |
+
"step": 2500
|
| 377 |
+
},
|
| 378 |
+
{
|
| 379 |
+
"epoch": 0.24,
|
| 380 |
+
"eval_loss": 1.2762665748596191,
|
| 381 |
+
"eval_runtime": 27.2214,
|
| 382 |
+
"eval_samples_per_second": 18.368,
|
| 383 |
+
"eval_steps_per_second": 2.314,
|
| 384 |
+
"step": 2500
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 0.25,
|
| 388 |
+
"grad_norm": 4.076394081115723,
|
| 389 |
+
"learning_rate": 2.0668044536302424e-05,
|
| 390 |
+
"loss": 1.5642,
|
| 391 |
+
"step": 2600
|
| 392 |
+
},
|
| 393 |
+
{
|
| 394 |
+
"epoch": 0.25,
|
| 395 |
+
"eval_loss": 1.2759555578231812,
|
| 396 |
+
"eval_runtime": 27.2363,
|
| 397 |
+
"eval_samples_per_second": 18.358,
|
| 398 |
+
"eval_steps_per_second": 2.313,
|
| 399 |
+
"step": 2600
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 0.26,
|
| 403 |
+
"grad_norm": 10.41948413848877,
|
| 404 |
+
"learning_rate": 2.050136675778385e-05,
|
| 405 |
+
"loss": 1.3917,
|
| 406 |
+
"step": 2700
|
| 407 |
+
},
|
| 408 |
+
{
|
| 409 |
+
"epoch": 0.26,
|
| 410 |
+
"eval_loss": 1.2696521282196045,
|
| 411 |
+
"eval_runtime": 27.2277,
|
| 412 |
+
"eval_samples_per_second": 18.364,
|
| 413 |
+
"eval_steps_per_second": 2.314,
|
| 414 |
+
"step": 2700
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 0.27,
|
| 418 |
+
"grad_norm": 8.529683113098145,
|
| 419 |
+
"learning_rate": 2.0334688979265284e-05,
|
| 420 |
+
"loss": 1.5147,
|
| 421 |
+
"step": 2800
|
| 422 |
+
},
|
| 423 |
+
{
|
| 424 |
+
"epoch": 0.27,
|
| 425 |
+
"eval_loss": 1.2705649137496948,
|
| 426 |
+
"eval_runtime": 27.2409,
|
| 427 |
+
"eval_samples_per_second": 18.355,
|
| 428 |
+
"eval_steps_per_second": 2.313,
|
| 429 |
+
"step": 2800
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.28,
|
| 433 |
+
"grad_norm": 4.257082939147949,
|
| 434 |
+
"learning_rate": 2.0168011200746718e-05,
|
| 435 |
+
"loss": 1.4392,
|
| 436 |
+
"step": 2900
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.28,
|
| 440 |
+
"eval_loss": 1.2686102390289307,
|
| 441 |
+
"eval_runtime": 27.2394,
|
| 442 |
+
"eval_samples_per_second": 18.356,
|
| 443 |
+
"eval_steps_per_second": 2.313,
|
| 444 |
+
"step": 2900
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.29,
|
| 448 |
+
"grad_norm": 9.243705749511719,
|
| 449 |
+
"learning_rate": 2.0001333422228148e-05,
|
| 450 |
+
"loss": 1.42,
|
| 451 |
+
"step": 3000
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 0.29,
|
| 455 |
+
"eval_loss": 1.2711559534072876,
|
| 456 |
+
"eval_runtime": 27.2345,
|
| 457 |
+
"eval_samples_per_second": 18.359,
|
| 458 |
+
"eval_steps_per_second": 2.313,
|
| 459 |
+
"step": 3000
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 0.3,
|
| 463 |
+
"grad_norm": 3.96095609664917,
|
| 464 |
+
"learning_rate": 1.983465564370958e-05,
|
| 465 |
+
"loss": 1.4526,
|
| 466 |
+
"step": 3100
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 0.3,
|
| 470 |
+
"eval_loss": 1.2658092975616455,
|
| 471 |
+
"eval_runtime": 27.251,
|
| 472 |
+
"eval_samples_per_second": 18.348,
|
| 473 |
+
"eval_steps_per_second": 2.312,
|
| 474 |
+
"step": 3100
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 0.31,
|
| 478 |
+
"grad_norm": 7.505685329437256,
|
| 479 |
+
"learning_rate": 1.9667977865191015e-05,
|
| 480 |
+
"loss": 1.464,
|
| 481 |
+
"step": 3200
|
| 482 |
+
},
|
| 483 |
+
{
|
| 484 |
+
"epoch": 0.31,
|
| 485 |
+
"eval_loss": 1.2660542726516724,
|
| 486 |
+
"eval_runtime": 27.2428,
|
| 487 |
+
"eval_samples_per_second": 18.354,
|
| 488 |
+
"eval_steps_per_second": 2.313,
|
| 489 |
+
"step": 3200
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 0.32,
|
| 493 |
+
"grad_norm": 2.5489604473114014,
|
| 494 |
+
"learning_rate": 1.9501300086672446e-05,
|
| 495 |
+
"loss": 1.4093,
|
| 496 |
+
"step": 3300
|
| 497 |
+
},
|
| 498 |
+
{
|
| 499 |
+
"epoch": 0.32,
|
| 500 |
+
"eval_loss": 1.2600222826004028,
|
| 501 |
+
"eval_runtime": 27.2413,
|
| 502 |
+
"eval_samples_per_second": 18.355,
|
| 503 |
+
"eval_steps_per_second": 2.313,
|
| 504 |
+
"step": 3300
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 0.33,
|
| 508 |
+
"grad_norm": 5.240612506866455,
|
| 509 |
+
"learning_rate": 1.9334622308153876e-05,
|
| 510 |
+
"loss": 1.4735,
|
| 511 |
+
"step": 3400
|
| 512 |
+
},
|
| 513 |
+
{
|
| 514 |
+
"epoch": 0.33,
|
| 515 |
+
"eval_loss": 1.2596392631530762,
|
| 516 |
+
"eval_runtime": 27.2353,
|
| 517 |
+
"eval_samples_per_second": 18.359,
|
| 518 |
+
"eval_steps_per_second": 2.313,
|
| 519 |
+
"step": 3400
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 0.34,
|
| 523 |
+
"grad_norm": 7.678092002868652,
|
| 524 |
+
"learning_rate": 1.916794452963531e-05,
|
| 525 |
+
"loss": 1.377,
|
| 526 |
+
"step": 3500
|
| 527 |
+
},
|
| 528 |
+
{
|
| 529 |
+
"epoch": 0.34,
|
| 530 |
+
"eval_loss": 1.2602125406265259,
|
| 531 |
+
"eval_runtime": 27.2377,
|
| 532 |
+
"eval_samples_per_second": 18.357,
|
| 533 |
+
"eval_steps_per_second": 2.313,
|
| 534 |
+
"step": 3500
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.35,
|
| 538 |
+
"grad_norm": 5.745735168457031,
|
| 539 |
+
"learning_rate": 1.9001266751116743e-05,
|
| 540 |
+
"loss": 1.4398,
|
| 541 |
+
"step": 3600
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.35,
|
| 545 |
+
"eval_loss": 1.2613269090652466,
|
| 546 |
+
"eval_runtime": 27.2388,
|
| 547 |
+
"eval_samples_per_second": 18.356,
|
| 548 |
+
"eval_steps_per_second": 2.313,
|
| 549 |
+
"step": 3600
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.36,
|
| 553 |
+
"grad_norm": 6.888312816619873,
|
| 554 |
+
"learning_rate": 1.8834588972598173e-05,
|
| 555 |
+
"loss": 1.4953,
|
| 556 |
+
"step": 3700
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 0.36,
|
| 560 |
+
"eval_loss": 1.2581281661987305,
|
| 561 |
+
"eval_runtime": 27.2396,
|
| 562 |
+
"eval_samples_per_second": 18.356,
|
| 563 |
+
"eval_steps_per_second": 2.313,
|
| 564 |
+
"step": 3700
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 0.37,
|
| 568 |
+
"grad_norm": 6.642201900482178,
|
| 569 |
+
"learning_rate": 1.8667911194079607e-05,
|
| 570 |
+
"loss": 1.3507,
|
| 571 |
+
"step": 3800
|
| 572 |
+
},
|
| 573 |
+
{
|
| 574 |
+
"epoch": 0.37,
|
| 575 |
+
"eval_loss": 1.2513525485992432,
|
| 576 |
+
"eval_runtime": 27.2312,
|
| 577 |
+
"eval_samples_per_second": 18.361,
|
| 578 |
+
"eval_steps_per_second": 2.314,
|
| 579 |
+
"step": 3800
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 0.38,
|
| 583 |
+
"grad_norm": 8.896329879760742,
|
| 584 |
+
"learning_rate": 1.850123341556104e-05,
|
| 585 |
+
"loss": 1.4659,
|
| 586 |
+
"step": 3900
|
| 587 |
+
},
|
| 588 |
+
{
|
| 589 |
+
"epoch": 0.38,
|
| 590 |
+
"eval_loss": 1.252593994140625,
|
| 591 |
+
"eval_runtime": 27.2402,
|
| 592 |
+
"eval_samples_per_second": 18.355,
|
| 593 |
+
"eval_steps_per_second": 2.313,
|
| 594 |
+
"step": 3900
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 0.39,
|
| 598 |
+
"grad_norm": 6.306306838989258,
|
| 599 |
+
"learning_rate": 1.833455563704247e-05,
|
| 600 |
+
"loss": 1.3839,
|
| 601 |
+
"step": 4000
|
| 602 |
+
},
|
| 603 |
+
{
|
| 604 |
+
"epoch": 0.39,
|
| 605 |
+
"eval_loss": 1.2493339776992798,
|
| 606 |
+
"eval_runtime": 27.2431,
|
| 607 |
+
"eval_samples_per_second": 18.353,
|
| 608 |
+
"eval_steps_per_second": 2.313,
|
| 609 |
+
"step": 4000
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 0.4,
|
| 613 |
+
"grad_norm": 9.476497650146484,
|
| 614 |
+
"learning_rate": 1.81678778585239e-05,
|
| 615 |
+
"loss": 1.4575,
|
| 616 |
+
"step": 4100
|
| 617 |
+
},
|
| 618 |
+
{
|
| 619 |
+
"epoch": 0.4,
|
| 620 |
+
"eval_loss": 1.2447402477264404,
|
| 621 |
+
"eval_runtime": 27.2408,
|
| 622 |
+
"eval_samples_per_second": 18.355,
|
| 623 |
+
"eval_steps_per_second": 2.313,
|
| 624 |
+
"step": 4100
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 0.41,
|
| 628 |
+
"grad_norm": 8.788684844970703,
|
| 629 |
+
"learning_rate": 1.8001200080005335e-05,
|
| 630 |
+
"loss": 1.4355,
|
| 631 |
+
"step": 4200
|
| 632 |
+
},
|
| 633 |
+
{
|
| 634 |
+
"epoch": 0.41,
|
| 635 |
+
"eval_loss": 1.2466756105422974,
|
| 636 |
+
"eval_runtime": 27.2362,
|
| 637 |
+
"eval_samples_per_second": 18.358,
|
| 638 |
+
"eval_steps_per_second": 2.313,
|
| 639 |
+
"step": 4200
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.42,
|
| 643 |
+
"grad_norm": 7.325284004211426,
|
| 644 |
+
"learning_rate": 1.7834522301486768e-05,
|
| 645 |
+
"loss": 1.4325,
|
| 646 |
+
"step": 4300
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 0.42,
|
| 650 |
+
"eval_loss": 1.2401726245880127,
|
| 651 |
+
"eval_runtime": 27.2408,
|
| 652 |
+
"eval_samples_per_second": 18.355,
|
| 653 |
+
"eval_steps_per_second": 2.313,
|
| 654 |
+
"step": 4300
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 0.42,
|
| 658 |
+
"grad_norm": 5.760813236236572,
|
| 659 |
+
"learning_rate": 1.76678445229682e-05,
|
| 660 |
+
"loss": 1.444,
|
| 661 |
+
"step": 4400
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 0.42,
|
| 665 |
+
"eval_loss": 1.237419843673706,
|
| 666 |
+
"eval_runtime": 27.235,
|
| 667 |
+
"eval_samples_per_second": 18.359,
|
| 668 |
+
"eval_steps_per_second": 2.313,
|
| 669 |
+
"step": 4400
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 0.43,
|
| 673 |
+
"grad_norm": 5.730567932128906,
|
| 674 |
+
"learning_rate": 1.7501166744449632e-05,
|
| 675 |
+
"loss": 1.3808,
|
| 676 |
+
"step": 4500
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 0.43,
|
| 680 |
+
"eval_loss": 1.233359932899475,
|
| 681 |
+
"eval_runtime": 27.2413,
|
| 682 |
+
"eval_samples_per_second": 18.355,
|
| 683 |
+
"eval_steps_per_second": 2.313,
|
| 684 |
+
"step": 4500
|
| 685 |
+
},
|
| 686 |
+
{
|
| 687 |
+
"epoch": 0.44,
|
| 688 |
+
"grad_norm": 5.33050537109375,
|
| 689 |
+
"learning_rate": 1.7334488965931062e-05,
|
| 690 |
+
"loss": 1.4183,
|
| 691 |
+
"step": 4600
|
| 692 |
+
},
|
| 693 |
+
{
|
| 694 |
+
"epoch": 0.44,
|
| 695 |
+
"eval_loss": 1.2271193265914917,
|
| 696 |
+
"eval_runtime": 27.2354,
|
| 697 |
+
"eval_samples_per_second": 18.358,
|
| 698 |
+
"eval_steps_per_second": 2.313,
|
| 699 |
+
"step": 4600
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 0.45,
|
| 703 |
+
"grad_norm": 5.542807102203369,
|
| 704 |
+
"learning_rate": 1.7167811187412493e-05,
|
| 705 |
+
"loss": 1.4737,
|
| 706 |
+
"step": 4700
|
| 707 |
+
},
|
| 708 |
+
{
|
| 709 |
+
"epoch": 0.45,
|
| 710 |
+
"eval_loss": 1.2270761728286743,
|
| 711 |
+
"eval_runtime": 27.2428,
|
| 712 |
+
"eval_samples_per_second": 18.353,
|
| 713 |
+
"eval_steps_per_second": 2.313,
|
| 714 |
+
"step": 4700
|
| 715 |
+
},
|
| 716 |
+
{
|
| 717 |
+
"epoch": 0.46,
|
| 718 |
+
"grad_norm": 5.02695369720459,
|
| 719 |
+
"learning_rate": 1.7001133408893926e-05,
|
| 720 |
+
"loss": 1.3564,
|
| 721 |
+
"step": 4800
|
| 722 |
+
},
|
| 723 |
+
{
|
| 724 |
+
"epoch": 0.46,
|
| 725 |
+
"eval_loss": 1.2189486026763916,
|
| 726 |
+
"eval_runtime": 27.2289,
|
| 727 |
+
"eval_samples_per_second": 18.363,
|
| 728 |
+
"eval_steps_per_second": 2.314,
|
| 729 |
+
"step": 4800
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 0.47,
|
| 733 |
+
"grad_norm": 9.54018783569336,
|
| 734 |
+
"learning_rate": 1.683445563037536e-05,
|
| 735 |
+
"loss": 1.3615,
|
| 736 |
+
"step": 4900
|
| 737 |
+
},
|
| 738 |
+
{
|
| 739 |
+
"epoch": 0.47,
|
| 740 |
+
"eval_loss": 1.2135944366455078,
|
| 741 |
+
"eval_runtime": 27.2481,
|
| 742 |
+
"eval_samples_per_second": 18.35,
|
| 743 |
+
"eval_steps_per_second": 2.312,
|
| 744 |
+
"step": 4900
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 0.48,
|
| 748 |
+
"grad_norm": 4.637027740478516,
|
| 749 |
+
"learning_rate": 1.6667777851856793e-05,
|
| 750 |
+
"loss": 1.4264,
|
| 751 |
+
"step": 5000
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 0.48,
|
| 755 |
+
"eval_loss": 1.2105356454849243,
|
| 756 |
+
"eval_runtime": 27.2429,
|
| 757 |
+
"eval_samples_per_second": 18.353,
|
| 758 |
+
"eval_steps_per_second": 2.313,
|
| 759 |
+
"step": 5000
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 0.49,
|
| 763 |
+
"grad_norm": 7.059263706207275,
|
| 764 |
+
"learning_rate": 1.6501100073338224e-05,
|
| 765 |
+
"loss": 1.281,
|
| 766 |
+
"step": 5100
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 0.49,
|
| 770 |
+
"eval_loss": 1.2117621898651123,
|
| 771 |
+
"eval_runtime": 27.2335,
|
| 772 |
+
"eval_samples_per_second": 18.36,
|
| 773 |
+
"eval_steps_per_second": 2.313,
|
| 774 |
+
"step": 5100
|
| 775 |
+
},
|
| 776 |
+
{
|
| 777 |
+
"epoch": 0.5,
|
| 778 |
+
"grad_norm": 4.905197620391846,
|
| 779 |
+
"learning_rate": 1.6334422294819657e-05,
|
| 780 |
+
"loss": 1.4319,
|
| 781 |
+
"step": 5200
|
| 782 |
+
},
|
| 783 |
+
{
|
| 784 |
+
"epoch": 0.5,
|
| 785 |
+
"eval_loss": 1.2079901695251465,
|
| 786 |
+
"eval_runtime": 27.2435,
|
| 787 |
+
"eval_samples_per_second": 18.353,
|
| 788 |
+
"eval_steps_per_second": 2.312,
|
| 789 |
+
"step": 5200
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 0.51,
|
| 793 |
+
"grad_norm": 11.458580017089844,
|
| 794 |
+
"learning_rate": 1.6167744516301088e-05,
|
| 795 |
+
"loss": 1.346,
|
| 796 |
+
"step": 5300
|
| 797 |
+
},
|
| 798 |
+
{
|
| 799 |
+
"epoch": 0.51,
|
| 800 |
+
"eval_loss": 1.2106558084487915,
|
| 801 |
+
"eval_runtime": 27.2322,
|
| 802 |
+
"eval_samples_per_second": 18.361,
|
| 803 |
+
"eval_steps_per_second": 2.313,
|
| 804 |
+
"step": 5300
|
| 805 |
+
},
|
| 806 |
+
{
|
| 807 |
+
"epoch": 0.52,
|
| 808 |
+
"grad_norm": 5.2320146560668945,
|
| 809 |
+
"learning_rate": 1.6001066737782518e-05,
|
| 810 |
+
"loss": 1.396,
|
| 811 |
+
"step": 5400
|
| 812 |
+
},
|
| 813 |
+
{
|
| 814 |
+
"epoch": 0.52,
|
| 815 |
+
"eval_loss": 1.208406925201416,
|
| 816 |
+
"eval_runtime": 27.2304,
|
| 817 |
+
"eval_samples_per_second": 18.362,
|
| 818 |
+
"eval_steps_per_second": 2.314,
|
| 819 |
+
"step": 5400
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"epoch": 0.53,
|
| 823 |
+
"grad_norm": 7.270910739898682,
|
| 824 |
+
"learning_rate": 1.583438895926395e-05,
|
| 825 |
+
"loss": 1.3313,
|
| 826 |
+
"step": 5500
|
| 827 |
+
},
|
| 828 |
+
{
|
| 829 |
+
"epoch": 0.53,
|
| 830 |
+
"eval_loss": 1.2069458961486816,
|
| 831 |
+
"eval_runtime": 27.2355,
|
| 832 |
+
"eval_samples_per_second": 18.358,
|
| 833 |
+
"eval_steps_per_second": 2.313,
|
| 834 |
+
"step": 5500
|
| 835 |
+
},
|
| 836 |
+
{
|
| 837 |
+
"epoch": 0.54,
|
| 838 |
+
"grad_norm": 8.65515422821045,
|
| 839 |
+
"learning_rate": 1.5667711180745385e-05,
|
| 840 |
+
"loss": 1.3069,
|
| 841 |
+
"step": 5600
|
| 842 |
+
},
|
| 843 |
+
{
|
| 844 |
+
"epoch": 0.54,
|
| 845 |
+
"eval_loss": 1.2003055810928345,
|
| 846 |
+
"eval_runtime": 27.2389,
|
| 847 |
+
"eval_samples_per_second": 18.356,
|
| 848 |
+
"eval_steps_per_second": 2.313,
|
| 849 |
+
"step": 5600
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 0.55,
|
| 853 |
+
"grad_norm": 7.7110724449157715,
|
| 854 |
+
"learning_rate": 1.5501033402226815e-05,
|
| 855 |
+
"loss": 1.2984,
|
| 856 |
+
"step": 5700
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 0.55,
|
| 860 |
+
"eval_loss": 1.20066499710083,
|
| 861 |
+
"eval_runtime": 27.2419,
|
| 862 |
+
"eval_samples_per_second": 18.354,
|
| 863 |
+
"eval_steps_per_second": 2.313,
|
| 864 |
+
"step": 5700
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 0.56,
|
| 868 |
+
"grad_norm": 7.086616516113281,
|
| 869 |
+
"learning_rate": 1.533435562370825e-05,
|
| 870 |
+
"loss": 1.3998,
|
| 871 |
+
"step": 5800
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 0.56,
|
| 875 |
+
"eval_loss": 1.1993930339813232,
|
| 876 |
+
"eval_runtime": 27.2542,
|
| 877 |
+
"eval_samples_per_second": 18.346,
|
| 878 |
+
"eval_steps_per_second": 2.312,
|
| 879 |
+
"step": 5800
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 0.57,
|
| 883 |
+
"grad_norm": 8.898906707763672,
|
| 884 |
+
"learning_rate": 1.5167677845189679e-05,
|
| 885 |
+
"loss": 1.4083,
|
| 886 |
+
"step": 5900
|
| 887 |
+
},
|
| 888 |
+
{
|
| 889 |
+
"epoch": 0.57,
|
| 890 |
+
"eval_loss": 1.2009773254394531,
|
| 891 |
+
"eval_runtime": 27.2476,
|
| 892 |
+
"eval_samples_per_second": 18.35,
|
| 893 |
+
"eval_steps_per_second": 2.312,
|
| 894 |
+
"step": 5900
|
| 895 |
+
},
|
| 896 |
+
{
|
| 897 |
+
"epoch": 0.58,
|
| 898 |
+
"grad_norm": 6.958111763000488,
|
| 899 |
+
"learning_rate": 1.5001000066671111e-05,
|
| 900 |
+
"loss": 1.3425,
|
| 901 |
+
"step": 6000
|
| 902 |
+
},
|
| 903 |
+
{
|
| 904 |
+
"epoch": 0.58,
|
| 905 |
+
"eval_loss": 1.1988615989685059,
|
| 906 |
+
"eval_runtime": 27.2347,
|
| 907 |
+
"eval_samples_per_second": 18.359,
|
| 908 |
+
"eval_steps_per_second": 2.313,
|
| 909 |
+
"step": 6000
|
| 910 |
+
},
|
| 911 |
+
{
|
| 912 |
+
"epoch": 0.59,
|
| 913 |
+
"grad_norm": 5.355065822601318,
|
| 914 |
+
"learning_rate": 1.4834322288152545e-05,
|
| 915 |
+
"loss": 1.3308,
|
| 916 |
+
"step": 6100
|
| 917 |
+
},
|
| 918 |
+
{
|
| 919 |
+
"epoch": 0.59,
|
| 920 |
+
"eval_loss": 1.1959185600280762,
|
| 921 |
+
"eval_runtime": 27.2351,
|
| 922 |
+
"eval_samples_per_second": 18.359,
|
| 923 |
+
"eval_steps_per_second": 2.313,
|
| 924 |
+
"step": 6100
|
| 925 |
+
},
|
| 926 |
+
{
|
| 927 |
+
"epoch": 0.6,
|
| 928 |
+
"grad_norm": 6.108639240264893,
|
| 929 |
+
"learning_rate": 1.4667644509633977e-05,
|
| 930 |
+
"loss": 1.3496,
|
| 931 |
+
"step": 6200
|
| 932 |
+
},
|
| 933 |
+
{
|
| 934 |
+
"epoch": 0.6,
|
| 935 |
+
"eval_loss": 1.1931555271148682,
|
| 936 |
+
"eval_runtime": 27.2299,
|
| 937 |
+
"eval_samples_per_second": 18.362,
|
| 938 |
+
"eval_steps_per_second": 2.314,
|
| 939 |
+
"step": 6200
|
| 940 |
+
},
|
| 941 |
+
{
|
| 942 |
+
"epoch": 0.61,
|
| 943 |
+
"grad_norm": 5.120665550231934,
|
| 944 |
+
"learning_rate": 1.4500966731115409e-05,
|
| 945 |
+
"loss": 1.2974,
|
| 946 |
+
"step": 6300
|
| 947 |
+
},
|
| 948 |
+
{
|
| 949 |
+
"epoch": 0.61,
|
| 950 |
+
"eval_loss": 1.189644455909729,
|
| 951 |
+
"eval_runtime": 27.2414,
|
| 952 |
+
"eval_samples_per_second": 18.354,
|
| 953 |
+
"eval_steps_per_second": 2.313,
|
| 954 |
+
"step": 6300
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 0.62,
|
| 958 |
+
"grad_norm": 9.152058601379395,
|
| 959 |
+
"learning_rate": 1.4334288952596842e-05,
|
| 960 |
+
"loss": 1.3366,
|
| 961 |
+
"step": 6400
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 0.62,
|
| 965 |
+
"eval_loss": 1.1901721954345703,
|
| 966 |
+
"eval_runtime": 27.2454,
|
| 967 |
+
"eval_samples_per_second": 18.352,
|
| 968 |
+
"eval_steps_per_second": 2.312,
|
| 969 |
+
"step": 6400
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 0.63,
|
| 973 |
+
"grad_norm": 4.623256683349609,
|
| 974 |
+
"learning_rate": 1.416761117407827e-05,
|
| 975 |
+
"loss": 1.4328,
|
| 976 |
+
"step": 6500
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 0.63,
|
| 980 |
+
"eval_loss": 1.1861129999160767,
|
| 981 |
+
"eval_runtime": 27.2464,
|
| 982 |
+
"eval_samples_per_second": 18.351,
|
| 983 |
+
"eval_steps_per_second": 2.312,
|
| 984 |
+
"step": 6500
|
| 985 |
+
},
|
| 986 |
+
{
|
| 987 |
+
"epoch": 0.64,
|
| 988 |
+
"grad_norm": 5.927731037139893,
|
| 989 |
+
"learning_rate": 1.4000933395559704e-05,
|
| 990 |
+
"loss": 1.2727,
|
| 991 |
+
"step": 6600
|
| 992 |
+
},
|
| 993 |
+
{
|
| 994 |
+
"epoch": 0.64,
|
| 995 |
+
"eval_loss": 1.1859809160232544,
|
| 996 |
+
"eval_runtime": 27.2453,
|
| 997 |
+
"eval_samples_per_second": 18.352,
|
| 998 |
+
"eval_steps_per_second": 2.312,
|
| 999 |
+
"step": 6600
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 0.65,
|
| 1003 |
+
"grad_norm": 4.167983055114746,
|
| 1004 |
+
"learning_rate": 1.3834255617041136e-05,
|
| 1005 |
+
"loss": 1.405,
|
| 1006 |
+
"step": 6700
|
| 1007 |
+
},
|
| 1008 |
+
{
|
| 1009 |
+
"epoch": 0.65,
|
| 1010 |
+
"eval_loss": 1.1869107484817505,
|
| 1011 |
+
"eval_runtime": 27.2415,
|
| 1012 |
+
"eval_samples_per_second": 18.354,
|
| 1013 |
+
"eval_steps_per_second": 2.313,
|
| 1014 |
+
"step": 6700
|
| 1015 |
+
},
|
| 1016 |
+
{
|
| 1017 |
+
"epoch": 0.66,
|
| 1018 |
+
"grad_norm": 11.508980751037598,
|
| 1019 |
+
"learning_rate": 1.3667577838522568e-05,
|
| 1020 |
+
"loss": 1.3313,
|
| 1021 |
+
"step": 6800
|
| 1022 |
+
},
|
| 1023 |
+
{
|
| 1024 |
+
"epoch": 0.66,
|
| 1025 |
+
"eval_loss": 1.1844249963760376,
|
| 1026 |
+
"eval_runtime": 27.2335,
|
| 1027 |
+
"eval_samples_per_second": 18.36,
|
| 1028 |
+
"eval_steps_per_second": 2.313,
|
| 1029 |
+
"step": 6800
|
| 1030 |
+
},
|
| 1031 |
+
{
|
| 1032 |
+
"epoch": 0.67,
|
| 1033 |
+
"grad_norm": 5.97917366027832,
|
| 1034 |
+
"learning_rate": 1.3500900060004002e-05,
|
| 1035 |
+
"loss": 1.3411,
|
| 1036 |
+
"step": 6900
|
| 1037 |
+
},
|
| 1038 |
+
{
|
| 1039 |
+
"epoch": 0.67,
|
| 1040 |
+
"eval_loss": 1.1828359365463257,
|
| 1041 |
+
"eval_runtime": 27.2322,
|
| 1042 |
+
"eval_samples_per_second": 18.361,
|
| 1043 |
+
"eval_steps_per_second": 2.313,
|
| 1044 |
+
"step": 6900
|
| 1045 |
+
},
|
| 1046 |
+
{
|
| 1047 |
+
"epoch": 0.68,
|
| 1048 |
+
"grad_norm": 7.086197376251221,
|
| 1049 |
+
"learning_rate": 1.3334222281485434e-05,
|
| 1050 |
+
"loss": 1.3896,
|
| 1051 |
+
"step": 7000
|
| 1052 |
+
},
|
| 1053 |
+
{
|
| 1054 |
+
"epoch": 0.68,
|
| 1055 |
+
"eval_loss": 1.1808134317398071,
|
| 1056 |
+
"eval_runtime": 27.2433,
|
| 1057 |
+
"eval_samples_per_second": 18.353,
|
| 1058 |
+
"eval_steps_per_second": 2.312,
|
| 1059 |
+
"step": 7000
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 0.69,
|
| 1063 |
+
"grad_norm": 7.553659439086914,
|
| 1064 |
+
"learning_rate": 1.3167544502966864e-05,
|
| 1065 |
+
"loss": 1.3611,
|
| 1066 |
+
"step": 7100
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 0.69,
|
| 1070 |
+
"eval_loss": 1.1791377067565918,
|
| 1071 |
+
"eval_runtime": 27.2454,
|
| 1072 |
+
"eval_samples_per_second": 18.352,
|
| 1073 |
+
"eval_steps_per_second": 2.312,
|
| 1074 |
+
"step": 7100
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 0.69,
|
| 1078 |
+
"grad_norm": 8.123412132263184,
|
| 1079 |
+
"learning_rate": 1.3000866724448296e-05,
|
| 1080 |
+
"loss": 1.3083,
|
| 1081 |
+
"step": 7200
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 0.69,
|
| 1085 |
+
"eval_loss": 1.177075982093811,
|
| 1086 |
+
"eval_runtime": 27.2307,
|
| 1087 |
+
"eval_samples_per_second": 18.362,
|
| 1088 |
+
"eval_steps_per_second": 2.314,
|
| 1089 |
+
"step": 7200
|
| 1090 |
+
},
|
| 1091 |
+
{
|
| 1092 |
+
"epoch": 0.7,
|
| 1093 |
+
"grad_norm": 9.786763191223145,
|
| 1094 |
+
"learning_rate": 1.283418894592973e-05,
|
| 1095 |
+
"loss": 1.2965,
|
| 1096 |
+
"step": 7300
|
| 1097 |
+
},
|
| 1098 |
+
{
|
| 1099 |
+
"epoch": 0.7,
|
| 1100 |
+
"eval_loss": 1.1764291524887085,
|
| 1101 |
+
"eval_runtime": 27.2358,
|
| 1102 |
+
"eval_samples_per_second": 18.358,
|
| 1103 |
+
"eval_steps_per_second": 2.313,
|
| 1104 |
+
"step": 7300
|
| 1105 |
+
},
|
| 1106 |
+
{
|
| 1107 |
+
"epoch": 0.71,
|
| 1108 |
+
"grad_norm": 6.950915336608887,
|
| 1109 |
+
"learning_rate": 1.2667511167411161e-05,
|
| 1110 |
+
"loss": 1.3109,
|
| 1111 |
+
"step": 7400
|
| 1112 |
+
},
|
| 1113 |
+
{
|
| 1114 |
+
"epoch": 0.71,
|
| 1115 |
+
"eval_loss": 1.1759792566299438,
|
| 1116 |
+
"eval_runtime": 27.2377,
|
| 1117 |
+
"eval_samples_per_second": 18.357,
|
| 1118 |
+
"eval_steps_per_second": 2.313,
|
| 1119 |
+
"step": 7400
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 0.72,
|
| 1123 |
+
"grad_norm": 6.95255184173584,
|
| 1124 |
+
"learning_rate": 1.2500833388892593e-05,
|
| 1125 |
+
"loss": 1.317,
|
| 1126 |
+
"step": 7500
|
| 1127 |
+
},
|
| 1128 |
+
{
|
| 1129 |
+
"epoch": 0.72,
|
| 1130 |
+
"eval_loss": 1.1741067171096802,
|
| 1131 |
+
"eval_runtime": 27.2348,
|
| 1132 |
+
"eval_samples_per_second": 18.359,
|
| 1133 |
+
"eval_steps_per_second": 2.313,
|
| 1134 |
+
"step": 7500
|
| 1135 |
+
},
|
| 1136 |
+
{
|
| 1137 |
+
"epoch": 0.73,
|
| 1138 |
+
"grad_norm": 4.61511754989624,
|
| 1139 |
+
"learning_rate": 1.2334155610374025e-05,
|
| 1140 |
+
"loss": 1.3408,
|
| 1141 |
+
"step": 7600
|
| 1142 |
+
},
|
| 1143 |
+
{
|
| 1144 |
+
"epoch": 0.73,
|
| 1145 |
+
"eval_loss": 1.1740319728851318,
|
| 1146 |
+
"eval_runtime": 27.2347,
|
| 1147 |
+
"eval_samples_per_second": 18.359,
|
| 1148 |
+
"eval_steps_per_second": 2.313,
|
| 1149 |
+
"step": 7600
|
| 1150 |
+
},
|
| 1151 |
+
{
|
| 1152 |
+
"epoch": 0.74,
|
| 1153 |
+
"grad_norm": 4.9650750160217285,
|
| 1154 |
+
"learning_rate": 1.2167477831855457e-05,
|
| 1155 |
+
"loss": 1.2952,
|
| 1156 |
+
"step": 7700
|
| 1157 |
+
},
|
| 1158 |
+
{
|
| 1159 |
+
"epoch": 0.74,
|
| 1160 |
+
"eval_loss": 1.1764243841171265,
|
| 1161 |
+
"eval_runtime": 27.2348,
|
| 1162 |
+
"eval_samples_per_second": 18.359,
|
| 1163 |
+
"eval_steps_per_second": 2.313,
|
| 1164 |
+
"step": 7700
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 0.75,
|
| 1168 |
+
"grad_norm": 7.219305515289307,
|
| 1169 |
+
"learning_rate": 1.200080005333689e-05,
|
| 1170 |
+
"loss": 1.302,
|
| 1171 |
+
"step": 7800
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 0.75,
|
| 1175 |
+
"eval_loss": 1.1715896129608154,
|
| 1176 |
+
"eval_runtime": 27.2301,
|
| 1177 |
+
"eval_samples_per_second": 18.362,
|
| 1178 |
+
"eval_steps_per_second": 2.314,
|
| 1179 |
+
"step": 7800
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 0.76,
|
| 1183 |
+
"grad_norm": 3.7380006313323975,
|
| 1184 |
+
"learning_rate": 1.1834122274818321e-05,
|
| 1185 |
+
"loss": 1.2608,
|
| 1186 |
+
"step": 7900
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 0.76,
|
| 1190 |
+
"eval_loss": 1.1713016033172607,
|
| 1191 |
+
"eval_runtime": 27.2356,
|
| 1192 |
+
"eval_samples_per_second": 18.358,
|
| 1193 |
+
"eval_steps_per_second": 2.313,
|
| 1194 |
+
"step": 7900
|
| 1195 |
+
},
|
| 1196 |
+
{
|
| 1197 |
+
"epoch": 0.77,
|
| 1198 |
+
"grad_norm": 5.135042190551758,
|
| 1199 |
+
"learning_rate": 1.1667444496299753e-05,
|
| 1200 |
+
"loss": 1.3132,
|
| 1201 |
+
"step": 8000
|
| 1202 |
+
},
|
| 1203 |
+
{
|
| 1204 |
+
"epoch": 0.77,
|
| 1205 |
+
"eval_loss": 1.1695390939712524,
|
| 1206 |
+
"eval_runtime": 27.2322,
|
| 1207 |
+
"eval_samples_per_second": 18.361,
|
| 1208 |
+
"eval_steps_per_second": 2.313,
|
| 1209 |
+
"step": 8000
|
| 1210 |
+
},
|
| 1211 |
+
{
|
| 1212 |
+
"epoch": 0.78,
|
| 1213 |
+
"grad_norm": 3.053743600845337,
|
| 1214 |
+
"learning_rate": 1.1500766717781187e-05,
|
| 1215 |
+
"loss": 1.312,
|
| 1216 |
+
"step": 8100
|
| 1217 |
+
},
|
| 1218 |
+
{
|
| 1219 |
+
"epoch": 0.78,
|
| 1220 |
+
"eval_loss": 1.1722323894500732,
|
| 1221 |
+
"eval_runtime": 27.2386,
|
| 1222 |
+
"eval_samples_per_second": 18.356,
|
| 1223 |
+
"eval_steps_per_second": 2.313,
|
| 1224 |
+
"step": 8100
|
| 1225 |
+
},
|
| 1226 |
+
{
|
| 1227 |
+
"epoch": 0.79,
|
| 1228 |
+
"grad_norm": 11.018885612487793,
|
| 1229 |
+
"learning_rate": 1.1334088939262619e-05,
|
| 1230 |
+
"loss": 1.3056,
|
| 1231 |
+
"step": 8200
|
| 1232 |
+
},
|
| 1233 |
+
{
|
| 1234 |
+
"epoch": 0.79,
|
| 1235 |
+
"eval_loss": 1.1667100191116333,
|
| 1236 |
+
"eval_runtime": 27.2417,
|
| 1237 |
+
"eval_samples_per_second": 18.354,
|
| 1238 |
+
"eval_steps_per_second": 2.313,
|
| 1239 |
+
"step": 8200
|
| 1240 |
+
},
|
| 1241 |
+
{
|
| 1242 |
+
"epoch": 0.8,
|
| 1243 |
+
"grad_norm": 6.420007228851318,
|
| 1244 |
+
"learning_rate": 1.116741116074405e-05,
|
| 1245 |
+
"loss": 1.2606,
|
| 1246 |
+
"step": 8300
|
| 1247 |
+
},
|
| 1248 |
+
{
|
| 1249 |
+
"epoch": 0.8,
|
| 1250 |
+
"eval_loss": 1.167235016822815,
|
| 1251 |
+
"eval_runtime": 27.2335,
|
| 1252 |
+
"eval_samples_per_second": 18.36,
|
| 1253 |
+
"eval_steps_per_second": 2.313,
|
| 1254 |
+
"step": 8300
|
| 1255 |
+
},
|
| 1256 |
+
{
|
| 1257 |
+
"epoch": 0.81,
|
| 1258 |
+
"grad_norm": 5.9483842849731445,
|
| 1259 |
+
"learning_rate": 1.1000733382225482e-05,
|
| 1260 |
+
"loss": 1.3797,
|
| 1261 |
+
"step": 8400
|
| 1262 |
+
},
|
| 1263 |
+
{
|
| 1264 |
+
"epoch": 0.81,
|
| 1265 |
+
"eval_loss": 1.1669018268585205,
|
| 1266 |
+
"eval_runtime": 27.2379,
|
| 1267 |
+
"eval_samples_per_second": 18.357,
|
| 1268 |
+
"eval_steps_per_second": 2.313,
|
| 1269 |
+
"step": 8400
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 0.82,
|
| 1273 |
+
"grad_norm": 6.5559892654418945,
|
| 1274 |
+
"learning_rate": 1.0834055603706914e-05,
|
| 1275 |
+
"loss": 1.2377,
|
| 1276 |
+
"step": 8500
|
| 1277 |
+
},
|
| 1278 |
+
{
|
| 1279 |
+
"epoch": 0.82,
|
| 1280 |
+
"eval_loss": 1.1625422239303589,
|
| 1281 |
+
"eval_runtime": 27.2397,
|
| 1282 |
+
"eval_samples_per_second": 18.356,
|
| 1283 |
+
"eval_steps_per_second": 2.313,
|
| 1284 |
+
"step": 8500
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 0.83,
|
| 1288 |
+
"grad_norm": 6.560941219329834,
|
| 1289 |
+
"learning_rate": 1.0667377825188346e-05,
|
| 1290 |
+
"loss": 1.3798,
|
| 1291 |
+
"step": 8600
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 0.83,
|
| 1295 |
+
"eval_loss": 1.162017822265625,
|
| 1296 |
+
"eval_runtime": 27.2403,
|
| 1297 |
+
"eval_samples_per_second": 18.355,
|
| 1298 |
+
"eval_steps_per_second": 2.313,
|
| 1299 |
+
"step": 8600
|
| 1300 |
+
},
|
| 1301 |
+
{
|
| 1302 |
+
"epoch": 0.84,
|
| 1303 |
+
"grad_norm": 10.945527076721191,
|
| 1304 |
+
"learning_rate": 1.0500700046669778e-05,
|
| 1305 |
+
"loss": 1.2488,
|
| 1306 |
+
"step": 8700
|
| 1307 |
+
},
|
| 1308 |
+
{
|
| 1309 |
+
"epoch": 0.84,
|
| 1310 |
+
"eval_loss": 1.15947425365448,
|
| 1311 |
+
"eval_runtime": 27.2348,
|
| 1312 |
+
"eval_samples_per_second": 18.359,
|
| 1313 |
+
"eval_steps_per_second": 2.313,
|
| 1314 |
+
"step": 8700
|
| 1315 |
+
},
|
| 1316 |
+
{
|
| 1317 |
+
"epoch": 0.85,
|
| 1318 |
+
"grad_norm": 3.0299010276794434,
|
| 1319 |
+
"learning_rate": 1.0334022268151212e-05,
|
| 1320 |
+
"loss": 1.2707,
|
| 1321 |
+
"step": 8800
|
| 1322 |
+
},
|
| 1323 |
+
{
|
| 1324 |
+
"epoch": 0.85,
|
| 1325 |
+
"eval_loss": 1.1578799486160278,
|
| 1326 |
+
"eval_runtime": 27.2313,
|
| 1327 |
+
"eval_samples_per_second": 18.361,
|
| 1328 |
+
"eval_steps_per_second": 2.314,
|
| 1329 |
+
"step": 8800
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 0.86,
|
| 1333 |
+
"grad_norm": 2.693074941635132,
|
| 1334 |
+
"learning_rate": 1.0167344489632642e-05,
|
| 1335 |
+
"loss": 1.163,
|
| 1336 |
+
"step": 8900
|
| 1337 |
+
},
|
| 1338 |
+
{
|
| 1339 |
+
"epoch": 0.86,
|
| 1340 |
+
"eval_loss": 1.156869649887085,
|
| 1341 |
+
"eval_runtime": 27.2425,
|
| 1342 |
+
"eval_samples_per_second": 18.354,
|
| 1343 |
+
"eval_steps_per_second": 2.313,
|
| 1344 |
+
"step": 8900
|
| 1345 |
+
},
|
| 1346 |
+
{
|
| 1347 |
+
"epoch": 0.87,
|
| 1348 |
+
"grad_norm": 10.922174453735352,
|
| 1349 |
+
"learning_rate": 1.0000666711114074e-05,
|
| 1350 |
+
"loss": 1.2786,
|
| 1351 |
+
"step": 9000
|
| 1352 |
+
},
|
| 1353 |
+
{
|
| 1354 |
+
"epoch": 0.87,
|
| 1355 |
+
"eval_loss": 1.154771089553833,
|
| 1356 |
+
"eval_runtime": 27.2049,
|
| 1357 |
+
"eval_samples_per_second": 18.379,
|
| 1358 |
+
"eval_steps_per_second": 2.316,
|
| 1359 |
+
"step": 9000
|
| 1360 |
+
},
|
| 1361 |
+
{
|
| 1362 |
+
"epoch": 0.88,
|
| 1363 |
+
"grad_norm": 12.848760604858398,
|
| 1364 |
+
"learning_rate": 9.833988932595508e-06,
|
| 1365 |
+
"loss": 1.2738,
|
| 1366 |
+
"step": 9100
|
| 1367 |
+
},
|
| 1368 |
+
{
|
| 1369 |
+
"epoch": 0.88,
|
| 1370 |
+
"eval_loss": 1.1499338150024414,
|
| 1371 |
+
"eval_runtime": 27.2148,
|
| 1372 |
+
"eval_samples_per_second": 18.372,
|
| 1373 |
+
"eval_steps_per_second": 2.315,
|
| 1374 |
+
"step": 9100
|
| 1375 |
+
},
|
| 1376 |
+
{
|
| 1377 |
+
"epoch": 0.89,
|
| 1378 |
+
"grad_norm": 5.136310577392578,
|
| 1379 |
+
"learning_rate": 9.667311154076938e-06,
|
| 1380 |
+
"loss": 1.3132,
|
| 1381 |
+
"step": 9200
|
| 1382 |
+
},
|
| 1383 |
+
{
|
| 1384 |
+
"epoch": 0.89,
|
| 1385 |
+
"eval_loss": 1.1506128311157227,
|
| 1386 |
+
"eval_runtime": 27.2118,
|
| 1387 |
+
"eval_samples_per_second": 18.374,
|
| 1388 |
+
"eval_steps_per_second": 2.315,
|
| 1389 |
+
"step": 9200
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 0.9,
|
| 1393 |
+
"grad_norm": 6.445253372192383,
|
| 1394 |
+
"learning_rate": 9.500633375558372e-06,
|
| 1395 |
+
"loss": 1.292,
|
| 1396 |
+
"step": 9300
|
| 1397 |
+
},
|
| 1398 |
+
{
|
| 1399 |
+
"epoch": 0.9,
|
| 1400 |
+
"eval_loss": 1.1501805782318115,
|
| 1401 |
+
"eval_runtime": 27.2291,
|
| 1402 |
+
"eval_samples_per_second": 18.363,
|
| 1403 |
+
"eval_steps_per_second": 2.314,
|
| 1404 |
+
"step": 9300
|
| 1405 |
+
},
|
| 1406 |
+
{
|
| 1407 |
+
"epoch": 0.91,
|
| 1408 |
+
"grad_norm": 7.888484477996826,
|
| 1409 |
+
"learning_rate": 9.333955597039803e-06,
|
| 1410 |
+
"loss": 1.3091,
|
| 1411 |
+
"step": 9400
|
| 1412 |
+
},
|
| 1413 |
+
{
|
| 1414 |
+
"epoch": 0.91,
|
| 1415 |
+
"eval_loss": 1.1491880416870117,
|
| 1416 |
+
"eval_runtime": 27.1957,
|
| 1417 |
+
"eval_samples_per_second": 18.385,
|
| 1418 |
+
"eval_steps_per_second": 2.317,
|
| 1419 |
+
"step": 9400
|
| 1420 |
+
},
|
| 1421 |
+
{
|
| 1422 |
+
"epoch": 0.92,
|
| 1423 |
+
"grad_norm": 6.232168674468994,
|
| 1424 |
+
"learning_rate": 9.167277818521235e-06,
|
| 1425 |
+
"loss": 1.2423,
|
| 1426 |
+
"step": 9500
|
| 1427 |
+
},
|
| 1428 |
+
{
|
| 1429 |
+
"epoch": 0.92,
|
| 1430 |
+
"eval_loss": 1.1463291645050049,
|
| 1431 |
+
"eval_runtime": 27.194,
|
| 1432 |
+
"eval_samples_per_second": 18.386,
|
| 1433 |
+
"eval_steps_per_second": 2.317,
|
| 1434 |
+
"step": 9500
|
| 1435 |
+
},
|
| 1436 |
+
{
|
| 1437 |
+
"epoch": 0.93,
|
| 1438 |
+
"grad_norm": 8.130847930908203,
|
| 1439 |
+
"learning_rate": 9.000600040002667e-06,
|
| 1440 |
+
"loss": 1.2448,
|
| 1441 |
+
"step": 9600
|
| 1442 |
+
},
|
| 1443 |
+
{
|
| 1444 |
+
"epoch": 0.93,
|
| 1445 |
+
"eval_loss": 1.1413744688034058,
|
| 1446 |
+
"eval_runtime": 27.1976,
|
| 1447 |
+
"eval_samples_per_second": 18.384,
|
| 1448 |
+
"eval_steps_per_second": 2.316,
|
| 1449 |
+
"step": 9600
|
| 1450 |
+
},
|
| 1451 |
+
{
|
| 1452 |
+
"epoch": 0.94,
|
| 1453 |
+
"grad_norm": 6.337840557098389,
|
| 1454 |
+
"learning_rate": 8.8339222614841e-06,
|
| 1455 |
+
"loss": 1.2572,
|
| 1456 |
+
"step": 9700
|
| 1457 |
+
},
|
| 1458 |
+
{
|
| 1459 |
+
"epoch": 0.94,
|
| 1460 |
+
"eval_loss": 1.1409308910369873,
|
| 1461 |
+
"eval_runtime": 27.2205,
|
| 1462 |
+
"eval_samples_per_second": 18.369,
|
| 1463 |
+
"eval_steps_per_second": 2.314,
|
| 1464 |
+
"step": 9700
|
| 1465 |
+
},
|
| 1466 |
+
{
|
| 1467 |
+
"epoch": 0.95,
|
| 1468 |
+
"grad_norm": 5.349727153778076,
|
| 1469 |
+
"learning_rate": 8.667244482965531e-06,
|
| 1470 |
+
"loss": 1.2629,
|
| 1471 |
+
"step": 9800
|
| 1472 |
+
},
|
| 1473 |
+
{
|
| 1474 |
+
"epoch": 0.95,
|
| 1475 |
+
"eval_loss": 1.1383512020111084,
|
| 1476 |
+
"eval_runtime": 27.2233,
|
| 1477 |
+
"eval_samples_per_second": 18.367,
|
| 1478 |
+
"eval_steps_per_second": 2.314,
|
| 1479 |
+
"step": 9800
|
| 1480 |
+
},
|
| 1481 |
+
{
|
| 1482 |
+
"epoch": 0.96,
|
| 1483 |
+
"grad_norm": 13.291428565979004,
|
| 1484 |
+
"learning_rate": 8.500566704446963e-06,
|
| 1485 |
+
"loss": 1.3713,
|
| 1486 |
+
"step": 9900
|
| 1487 |
+
},
|
| 1488 |
+
{
|
| 1489 |
+
"epoch": 0.96,
|
| 1490 |
+
"eval_loss": 1.1351414918899536,
|
| 1491 |
+
"eval_runtime": 27.226,
|
| 1492 |
+
"eval_samples_per_second": 18.365,
|
| 1493 |
+
"eval_steps_per_second": 2.314,
|
| 1494 |
+
"step": 9900
|
| 1495 |
+
},
|
| 1496 |
+
{
|
| 1497 |
+
"epoch": 0.97,
|
| 1498 |
+
"grad_norm": 7.407767295837402,
|
| 1499 |
+
"learning_rate": 8.333888925928397e-06,
|
| 1500 |
+
"loss": 1.2711,
|
| 1501 |
+
"step": 10000
|
| 1502 |
+
},
|
| 1503 |
+
{
|
| 1504 |
+
"epoch": 0.97,
|
| 1505 |
+
"eval_loss": 1.134214162826538,
|
| 1506 |
+
"eval_runtime": 27.214,
|
| 1507 |
+
"eval_samples_per_second": 18.373,
|
| 1508 |
+
"eval_steps_per_second": 2.315,
|
| 1509 |
+
"step": 10000
|
| 1510 |
+
},
|
| 1511 |
+
{
|
| 1512 |
+
"epoch": 0.97,
|
| 1513 |
+
"grad_norm": 6.4951348304748535,
|
| 1514 |
+
"learning_rate": 8.167211147409829e-06,
|
| 1515 |
+
"loss": 1.2371,
|
| 1516 |
+
"step": 10100
|
| 1517 |
+
},
|
| 1518 |
+
{
|
| 1519 |
+
"epoch": 0.97,
|
| 1520 |
+
"eval_loss": 1.1317152976989746,
|
| 1521 |
+
"eval_runtime": 27.2127,
|
| 1522 |
+
"eval_samples_per_second": 18.374,
|
| 1523 |
+
"eval_steps_per_second": 2.315,
|
| 1524 |
+
"step": 10100
|
| 1525 |
+
},
|
| 1526 |
+
{
|
| 1527 |
+
"epoch": 0.98,
|
| 1528 |
+
"grad_norm": 5.784173488616943,
|
| 1529 |
+
"learning_rate": 8.000533368891259e-06,
|
| 1530 |
+
"loss": 1.2729,
|
| 1531 |
+
"step": 10200
|
| 1532 |
+
},
|
| 1533 |
+
{
|
| 1534 |
+
"epoch": 0.98,
|
| 1535 |
+
"eval_loss": 1.1299734115600586,
|
| 1536 |
+
"eval_runtime": 27.228,
|
| 1537 |
+
"eval_samples_per_second": 18.363,
|
| 1538 |
+
"eval_steps_per_second": 2.314,
|
| 1539 |
+
"step": 10200
|
| 1540 |
+
},
|
| 1541 |
+
{
|
| 1542 |
+
"epoch": 0.99,
|
| 1543 |
+
"grad_norm": 5.597267150878906,
|
| 1544 |
+
"learning_rate": 7.833855590372693e-06,
|
| 1545 |
+
"loss": 1.2332,
|
| 1546 |
+
"step": 10300
|
| 1547 |
+
},
|
| 1548 |
+
{
|
| 1549 |
+
"epoch": 0.99,
|
| 1550 |
+
"eval_loss": 1.1279923915863037,
|
| 1551 |
+
"eval_runtime": 27.2092,
|
| 1552 |
+
"eval_samples_per_second": 18.376,
|
| 1553 |
+
"eval_steps_per_second": 2.315,
|
| 1554 |
+
"step": 10300
|
| 1555 |
+
}
|
| 1556 |
+
],
|
| 1557 |
+
"logging_steps": 100,
|
| 1558 |
+
"max_steps": 15000,
|
| 1559 |
+
"num_input_tokens_seen": 0,
|
| 1560 |
+
"num_train_epochs": 2,
|
| 1561 |
+
"save_steps": 100,
|
| 1562 |
+
"total_flos": 3.888476623847424e+17,
|
| 1563 |
+
"train_batch_size": 2,
|
| 1564 |
+
"trial_name": null,
|
| 1565 |
+
"trial_params": null
|
| 1566 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1e274454bab8db82ffc2eb95b83319df0a257ebd888203fc0f1437e4638ddb59
|
| 3 |
+
size 4920
|