Commit
•
a7f0d68
1
Parent(s):
d9f6f58
Upload 8 files
Browse files- README.md +202 -3
- adapter_config.json +29 -0
- adapter_model.bin +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +3081 -0
- training_args.bin +3 -0
README.md
CHANGED
|
@@ -1,3 +1,202 @@
|
|
| 1 |
-
---
|
| 2 |
-
|
| 3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
base_model: meta-llama/Llama-2-7b-hf
|
| 4 |
+
---
|
| 5 |
+
|
| 6 |
+
# Model Card for Model ID
|
| 7 |
+
|
| 8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 9 |
+
|
| 10 |
+
|
| 11 |
+
|
| 12 |
+
## Model Details
|
| 13 |
+
|
| 14 |
+
### Model Description
|
| 15 |
+
|
| 16 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
- **Developed by:** [More Information Needed]
|
| 21 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 22 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 23 |
+
- **Model type:** [More Information Needed]
|
| 24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 25 |
+
- **License:** [More Information Needed]
|
| 26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 27 |
+
|
| 28 |
+
### Model Sources [optional]
|
| 29 |
+
|
| 30 |
+
<!-- Provide the basic links for the model. -->
|
| 31 |
+
|
| 32 |
+
- **Repository:** [More Information Needed]
|
| 33 |
+
- **Paper [optional]:** [More Information Needed]
|
| 34 |
+
- **Demo [optional]:** [More Information Needed]
|
| 35 |
+
|
| 36 |
+
## Uses
|
| 37 |
+
|
| 38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 39 |
+
|
| 40 |
+
### Direct Use
|
| 41 |
+
|
| 42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 43 |
+
|
| 44 |
+
[More Information Needed]
|
| 45 |
+
|
| 46 |
+
### Downstream Use [optional]
|
| 47 |
+
|
| 48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 49 |
+
|
| 50 |
+
[More Information Needed]
|
| 51 |
+
|
| 52 |
+
### Out-of-Scope Use
|
| 53 |
+
|
| 54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 55 |
+
|
| 56 |
+
[More Information Needed]
|
| 57 |
+
|
| 58 |
+
## Bias, Risks, and Limitations
|
| 59 |
+
|
| 60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 61 |
+
|
| 62 |
+
[More Information Needed]
|
| 63 |
+
|
| 64 |
+
### Recommendations
|
| 65 |
+
|
| 66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 67 |
+
|
| 68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 69 |
+
|
| 70 |
+
## How to Get Started with the Model
|
| 71 |
+
|
| 72 |
+
Use the code below to get started with the model.
|
| 73 |
+
|
| 74 |
+
[More Information Needed]
|
| 75 |
+
|
| 76 |
+
## Training Details
|
| 77 |
+
|
| 78 |
+
### Training Data
|
| 79 |
+
|
| 80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 81 |
+
|
| 82 |
+
[More Information Needed]
|
| 83 |
+
|
| 84 |
+
### Training Procedure
|
| 85 |
+
|
| 86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 87 |
+
|
| 88 |
+
#### Preprocessing [optional]
|
| 89 |
+
|
| 90 |
+
[More Information Needed]
|
| 91 |
+
|
| 92 |
+
|
| 93 |
+
#### Training Hyperparameters
|
| 94 |
+
|
| 95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 96 |
+
|
| 97 |
+
#### Speeds, Sizes, Times [optional]
|
| 98 |
+
|
| 99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 100 |
+
|
| 101 |
+
[More Information Needed]
|
| 102 |
+
|
| 103 |
+
## Evaluation
|
| 104 |
+
|
| 105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 106 |
+
|
| 107 |
+
### Testing Data, Factors & Metrics
|
| 108 |
+
|
| 109 |
+
#### Testing Data
|
| 110 |
+
|
| 111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 112 |
+
|
| 113 |
+
[More Information Needed]
|
| 114 |
+
|
| 115 |
+
#### Factors
|
| 116 |
+
|
| 117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 118 |
+
|
| 119 |
+
[More Information Needed]
|
| 120 |
+
|
| 121 |
+
#### Metrics
|
| 122 |
+
|
| 123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 124 |
+
|
| 125 |
+
[More Information Needed]
|
| 126 |
+
|
| 127 |
+
### Results
|
| 128 |
+
|
| 129 |
+
[More Information Needed]
|
| 130 |
+
|
| 131 |
+
#### Summary
|
| 132 |
+
|
| 133 |
+
|
| 134 |
+
|
| 135 |
+
## Model Examination [optional]
|
| 136 |
+
|
| 137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 138 |
+
|
| 139 |
+
[More Information Needed]
|
| 140 |
+
|
| 141 |
+
## Environmental Impact
|
| 142 |
+
|
| 143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 144 |
+
|
| 145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
| 146 |
+
|
| 147 |
+
- **Hardware Type:** [More Information Needed]
|
| 148 |
+
- **Hours used:** [More Information Needed]
|
| 149 |
+
- **Cloud Provider:** [More Information Needed]
|
| 150 |
+
- **Compute Region:** [More Information Needed]
|
| 151 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 152 |
+
|
| 153 |
+
## Technical Specifications [optional]
|
| 154 |
+
|
| 155 |
+
### Model Architecture and Objective
|
| 156 |
+
|
| 157 |
+
[More Information Needed]
|
| 158 |
+
|
| 159 |
+
### Compute Infrastructure
|
| 160 |
+
|
| 161 |
+
[More Information Needed]
|
| 162 |
+
|
| 163 |
+
#### Hardware
|
| 164 |
+
|
| 165 |
+
[More Information Needed]
|
| 166 |
+
|
| 167 |
+
#### Software
|
| 168 |
+
|
| 169 |
+
[More Information Needed]
|
| 170 |
+
|
| 171 |
+
## Citation [optional]
|
| 172 |
+
|
| 173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 174 |
+
|
| 175 |
+
**BibTeX:**
|
| 176 |
+
|
| 177 |
+
[More Information Needed]
|
| 178 |
+
|
| 179 |
+
**APA:**
|
| 180 |
+
|
| 181 |
+
[More Information Needed]
|
| 182 |
+
|
| 183 |
+
## Glossary [optional]
|
| 184 |
+
|
| 185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 186 |
+
|
| 187 |
+
[More Information Needed]
|
| 188 |
+
|
| 189 |
+
## More Information [optional]
|
| 190 |
+
|
| 191 |
+
[More Information Needed]
|
| 192 |
+
|
| 193 |
+
## Model Card Authors [optional]
|
| 194 |
+
|
| 195 |
+
[More Information Needed]
|
| 196 |
+
|
| 197 |
+
## Model Card Contact
|
| 198 |
+
|
| 199 |
+
[More Information Needed]
|
| 200 |
+
### Framework versions
|
| 201 |
+
|
| 202 |
+
- PEFT 0.10.0
|
adapter_config.json
ADDED
|
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "meta-llama/Llama-2-7b-hf",
|
| 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": 16,
|
| 14 |
+
"lora_dropout": 0.05,
|
| 15 |
+
"megatron_config": null,
|
| 16 |
+
"megatron_core": "megatron.core",
|
| 17 |
+
"modules_to_save": null,
|
| 18 |
+
"peft_type": "LORA",
|
| 19 |
+
"r": 8,
|
| 20 |
+
"rank_pattern": {},
|
| 21 |
+
"revision": null,
|
| 22 |
+
"target_modules": [
|
| 23 |
+
"q_proj",
|
| 24 |
+
"v_proj"
|
| 25 |
+
],
|
| 26 |
+
"task_type": "CAUSAL_LM",
|
| 27 |
+
"use_dora": false,
|
| 28 |
+
"use_rslora": false
|
| 29 |
+
}
|
adapter_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5a29fcefdb344cf1a464af2a5e7ed0d952d39ad2c8b5e0858b0c61b563c88c0d
|
| 3 |
+
size 16823434
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bb762c33b6175cc74c2e5af47e0d080ea8a6fc74e8ee62d11e299aeec8a13d32
|
| 3 |
+
size 33662074
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6a77dab915dbdee4ee2ed70cf9d33b1f4c48feae37e3dac9be1253213135da20
|
| 3 |
+
size 14244
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c39631598c211078c8c06465028f0973c120a65c8abe8de2e11eef0b34560bbd
|
| 3 |
+
size 1064
|
trainer_state.json
ADDED
|
@@ -0,0 +1,3081 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.28078943490982056,
|
| 3 |
+
"best_model_checkpoint": "/scratch/czm5kz/llama2-7b_8_100_0.0003_sg_finetuned_combined_with_output/checkpoint-1680",
|
| 4 |
+
"epoch": 100.0,
|
| 5 |
+
"eval_steps": 20,
|
| 6 |
+
"global_step": 1700,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.29,
|
| 13 |
+
"grad_norm": NaN,
|
| 14 |
+
"learning_rate": 0.0002992941176470588,
|
| 15 |
+
"loss": 5.0998,
|
| 16 |
+
"step": 5
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.59,
|
| 20 |
+
"grad_norm": 1.5051676034927368,
|
| 21 |
+
"learning_rate": 0.00029841176470588233,
|
| 22 |
+
"loss": 4.8032,
|
| 23 |
+
"step": 10
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.88,
|
| 27 |
+
"grad_norm": 4.402914524078369,
|
| 28 |
+
"learning_rate": 0.00029752941176470587,
|
| 29 |
+
"loss": 3.9535,
|
| 30 |
+
"step": 15
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 1.18,
|
| 34 |
+
"grad_norm": 1.9224834442138672,
|
| 35 |
+
"learning_rate": 0.00029664705882352936,
|
| 36 |
+
"loss": 3.4666,
|
| 37 |
+
"step": 20
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 1.18,
|
| 41 |
+
"eval_loss": 3.126023054122925,
|
| 42 |
+
"eval_runtime": 1.9511,
|
| 43 |
+
"eval_samples_per_second": 68.678,
|
| 44 |
+
"eval_steps_per_second": 8.713,
|
| 45 |
+
"step": 20
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 1.47,
|
| 49 |
+
"grad_norm": 2.0780274868011475,
|
| 50 |
+
"learning_rate": 0.0002957647058823529,
|
| 51 |
+
"loss": 2.9757,
|
| 52 |
+
"step": 25
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 1.76,
|
| 56 |
+
"grad_norm": 2.7333483695983887,
|
| 57 |
+
"learning_rate": 0.00029488235294117645,
|
| 58 |
+
"loss": 2.7866,
|
| 59 |
+
"step": 30
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 2.06,
|
| 63 |
+
"grad_norm": 2.3373279571533203,
|
| 64 |
+
"learning_rate": 0.000294,
|
| 65 |
+
"loss": 2.5319,
|
| 66 |
+
"step": 35
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 2.35,
|
| 70 |
+
"grad_norm": 2.571775436401367,
|
| 71 |
+
"learning_rate": 0.0002931176470588235,
|
| 72 |
+
"loss": 2.2629,
|
| 73 |
+
"step": 40
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 2.35,
|
| 77 |
+
"eval_loss": 2.029690980911255,
|
| 78 |
+
"eval_runtime": 1.9448,
|
| 79 |
+
"eval_samples_per_second": 68.902,
|
| 80 |
+
"eval_steps_per_second": 8.741,
|
| 81 |
+
"step": 40
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 2.65,
|
| 85 |
+
"grad_norm": 2.8255844116210938,
|
| 86 |
+
"learning_rate": 0.000292235294117647,
|
| 87 |
+
"loss": 2.0272,
|
| 88 |
+
"step": 45
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 2.94,
|
| 92 |
+
"grad_norm": 3.8026905059814453,
|
| 93 |
+
"learning_rate": 0.00029135294117647057,
|
| 94 |
+
"loss": 1.8851,
|
| 95 |
+
"step": 50
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 3.24,
|
| 99 |
+
"grad_norm": 5.537219524383545,
|
| 100 |
+
"learning_rate": 0.0002904705882352941,
|
| 101 |
+
"loss": 1.6101,
|
| 102 |
+
"step": 55
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 3.53,
|
| 106 |
+
"grad_norm": 3.3063488006591797,
|
| 107 |
+
"learning_rate": 0.00028958823529411765,
|
| 108 |
+
"loss": 1.4105,
|
| 109 |
+
"step": 60
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 3.53,
|
| 113 |
+
"eval_loss": 1.1428149938583374,
|
| 114 |
+
"eval_runtime": 1.9473,
|
| 115 |
+
"eval_samples_per_second": 68.815,
|
| 116 |
+
"eval_steps_per_second": 8.73,
|
| 117 |
+
"step": 60
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 3.82,
|
| 121 |
+
"grad_norm": 4.771293640136719,
|
| 122 |
+
"learning_rate": 0.00028870588235294114,
|
| 123 |
+
"loss": 1.2173,
|
| 124 |
+
"step": 65
|
| 125 |
+
},
|
| 126 |
+
{
|
| 127 |
+
"epoch": 4.12,
|
| 128 |
+
"grad_norm": 3.6649744510650635,
|
| 129 |
+
"learning_rate": 0.0002878235294117647,
|
| 130 |
+
"loss": 0.9633,
|
| 131 |
+
"step": 70
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 4.41,
|
| 135 |
+
"grad_norm": 5.370645046234131,
|
| 136 |
+
"learning_rate": 0.00028694117647058817,
|
| 137 |
+
"loss": 0.8975,
|
| 138 |
+
"step": 75
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 4.71,
|
| 142 |
+
"grad_norm": 4.725810527801514,
|
| 143 |
+
"learning_rate": 0.0002860588235294117,
|
| 144 |
+
"loss": 0.843,
|
| 145 |
+
"step": 80
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 4.71,
|
| 149 |
+
"eval_loss": 0.6662469506263733,
|
| 150 |
+
"eval_runtime": 1.9536,
|
| 151 |
+
"eval_samples_per_second": 68.59,
|
| 152 |
+
"eval_steps_per_second": 8.702,
|
| 153 |
+
"step": 80
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 5.0,
|
| 157 |
+
"grad_norm": 4.064177989959717,
|
| 158 |
+
"learning_rate": 0.00028517647058823526,
|
| 159 |
+
"loss": 0.8561,
|
| 160 |
+
"step": 85
|
| 161 |
+
},
|
| 162 |
+
{
|
| 163 |
+
"epoch": 5.29,
|
| 164 |
+
"grad_norm": 3.2627274990081787,
|
| 165 |
+
"learning_rate": 0.0002842941176470588,
|
| 166 |
+
"loss": 0.5679,
|
| 167 |
+
"step": 90
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 5.59,
|
| 171 |
+
"grad_norm": 3.991358757019043,
|
| 172 |
+
"learning_rate": 0.00028341176470588234,
|
| 173 |
+
"loss": 0.6491,
|
| 174 |
+
"step": 95
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 5.88,
|
| 178 |
+
"grad_norm": 3.3958096504211426,
|
| 179 |
+
"learning_rate": 0.00028252941176470583,
|
| 180 |
+
"loss": 0.594,
|
| 181 |
+
"step": 100
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 5.88,
|
| 185 |
+
"eval_loss": 0.47748813033103943,
|
| 186 |
+
"eval_runtime": 1.9525,
|
| 187 |
+
"eval_samples_per_second": 68.63,
|
| 188 |
+
"eval_steps_per_second": 8.707,
|
| 189 |
+
"step": 100
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 6.18,
|
| 193 |
+
"grad_norm": 2.515850067138672,
|
| 194 |
+
"learning_rate": 0.0002816470588235294,
|
| 195 |
+
"loss": 0.5506,
|
| 196 |
+
"step": 105
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 6.47,
|
| 200 |
+
"grad_norm": 3.668363571166992,
|
| 201 |
+
"learning_rate": 0.0002807647058823529,
|
| 202 |
+
"loss": 0.5036,
|
| 203 |
+
"step": 110
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 6.76,
|
| 207 |
+
"grad_norm": 2.7981760501861572,
|
| 208 |
+
"learning_rate": 0.00027988235294117646,
|
| 209 |
+
"loss": 0.5038,
|
| 210 |
+
"step": 115
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 7.06,
|
| 214 |
+
"grad_norm": 3.593534469604492,
|
| 215 |
+
"learning_rate": 0.000279,
|
| 216 |
+
"loss": 0.5558,
|
| 217 |
+
"step": 120
|
| 218 |
+
},
|
| 219 |
+
{
|
| 220 |
+
"epoch": 7.06,
|
| 221 |
+
"eval_loss": 0.41368114948272705,
|
| 222 |
+
"eval_runtime": 1.9554,
|
| 223 |
+
"eval_samples_per_second": 68.53,
|
| 224 |
+
"eval_steps_per_second": 8.694,
|
| 225 |
+
"step": 120
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 7.35,
|
| 229 |
+
"grad_norm": 2.759305715560913,
|
| 230 |
+
"learning_rate": 0.0002781176470588235,
|
| 231 |
+
"loss": 0.3992,
|
| 232 |
+
"step": 125
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"epoch": 7.65,
|
| 236 |
+
"grad_norm": 3.9013450145721436,
|
| 237 |
+
"learning_rate": 0.00027723529411764704,
|
| 238 |
+
"loss": 0.483,
|
| 239 |
+
"step": 130
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 7.94,
|
| 243 |
+
"grad_norm": 2.91575288772583,
|
| 244 |
+
"learning_rate": 0.0002763529411764706,
|
| 245 |
+
"loss": 0.5406,
|
| 246 |
+
"step": 135
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 8.24,
|
| 250 |
+
"grad_norm": 2.767667770385742,
|
| 251 |
+
"learning_rate": 0.00027547058823529407,
|
| 252 |
+
"loss": 0.4172,
|
| 253 |
+
"step": 140
|
| 254 |
+
},
|
| 255 |
+
{
|
| 256 |
+
"epoch": 8.24,
|
| 257 |
+
"eval_loss": 0.38757023215293884,
|
| 258 |
+
"eval_runtime": 1.955,
|
| 259 |
+
"eval_samples_per_second": 68.543,
|
| 260 |
+
"eval_steps_per_second": 8.696,
|
| 261 |
+
"step": 140
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 8.53,
|
| 265 |
+
"grad_norm": 3.9081954956054688,
|
| 266 |
+
"learning_rate": 0.0002745882352941176,
|
| 267 |
+
"loss": 0.436,
|
| 268 |
+
"step": 145
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 8.82,
|
| 272 |
+
"grad_norm": 6.408878326416016,
|
| 273 |
+
"learning_rate": 0.00027370588235294116,
|
| 274 |
+
"loss": 0.4897,
|
| 275 |
+
"step": 150
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 9.12,
|
| 279 |
+
"grad_norm": 2.7324299812316895,
|
| 280 |
+
"learning_rate": 0.0002728235294117647,
|
| 281 |
+
"loss": 0.5004,
|
| 282 |
+
"step": 155
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 9.41,
|
| 286 |
+
"grad_norm": 2.421757936477661,
|
| 287 |
+
"learning_rate": 0.00027194117647058824,
|
| 288 |
+
"loss": 0.3975,
|
| 289 |
+
"step": 160
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 9.41,
|
| 293 |
+
"eval_loss": 0.3739613890647888,
|
| 294 |
+
"eval_runtime": 1.956,
|
| 295 |
+
"eval_samples_per_second": 68.509,
|
| 296 |
+
"eval_steps_per_second": 8.691,
|
| 297 |
+
"step": 160
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 9.71,
|
| 301 |
+
"grad_norm": 2.3842573165893555,
|
| 302 |
+
"learning_rate": 0.00027105882352941173,
|
| 303 |
+
"loss": 0.4115,
|
| 304 |
+
"step": 165
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 10.0,
|
| 308 |
+
"grad_norm": 2.133479356765747,
|
| 309 |
+
"learning_rate": 0.0002701764705882353,
|
| 310 |
+
"loss": 0.4631,
|
| 311 |
+
"step": 170
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 10.29,
|
| 315 |
+
"grad_norm": 2.5470354557037354,
|
| 316 |
+
"learning_rate": 0.0002692941176470588,
|
| 317 |
+
"loss": 0.3529,
|
| 318 |
+
"step": 175
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 10.59,
|
| 322 |
+
"grad_norm": 2.089559316635132,
|
| 323 |
+
"learning_rate": 0.0002684117647058823,
|
| 324 |
+
"loss": 0.4345,
|
| 325 |
+
"step": 180
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 10.59,
|
| 329 |
+
"eval_loss": 0.36016595363616943,
|
| 330 |
+
"eval_runtime": 1.9572,
|
| 331 |
+
"eval_samples_per_second": 68.467,
|
| 332 |
+
"eval_steps_per_second": 8.686,
|
| 333 |
+
"step": 180
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 10.88,
|
| 337 |
+
"grad_norm": 1.8793551921844482,
|
| 338 |
+
"learning_rate": 0.00026752941176470585,
|
| 339 |
+
"loss": 0.4174,
|
| 340 |
+
"step": 185
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"epoch": 11.18,
|
| 344 |
+
"grad_norm": 1.600169062614441,
|
| 345 |
+
"learning_rate": 0.0002666470588235294,
|
| 346 |
+
"loss": 0.4024,
|
| 347 |
+
"step": 190
|
| 348 |
+
},
|
| 349 |
+
{
|
| 350 |
+
"epoch": 11.47,
|
| 351 |
+
"grad_norm": 2.6070401668548584,
|
| 352 |
+
"learning_rate": 0.00026576470588235293,
|
| 353 |
+
"loss": 0.3793,
|
| 354 |
+
"step": 195
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 11.76,
|
| 358 |
+
"grad_norm": 1.698486566543579,
|
| 359 |
+
"learning_rate": 0.0002648823529411764,
|
| 360 |
+
"loss": 0.4292,
|
| 361 |
+
"step": 200
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 11.76,
|
| 365 |
+
"eval_loss": 0.34652820229530334,
|
| 366 |
+
"eval_runtime": 1.9608,
|
| 367 |
+
"eval_samples_per_second": 68.339,
|
| 368 |
+
"eval_steps_per_second": 8.67,
|
| 369 |
+
"step": 200
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 12.06,
|
| 373 |
+
"grad_norm": 1.3916856050491333,
|
| 374 |
+
"learning_rate": 0.00026399999999999997,
|
| 375 |
+
"loss": 0.408,
|
| 376 |
+
"step": 205
|
| 377 |
+
},
|
| 378 |
+
{
|
| 379 |
+
"epoch": 12.35,
|
| 380 |
+
"grad_norm": 1.8041679859161377,
|
| 381 |
+
"learning_rate": 0.0002631176470588235,
|
| 382 |
+
"loss": 0.3553,
|
| 383 |
+
"step": 210
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 12.65,
|
| 387 |
+
"grad_norm": 1.9701488018035889,
|
| 388 |
+
"learning_rate": 0.00026223529411764705,
|
| 389 |
+
"loss": 0.4163,
|
| 390 |
+
"step": 215
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 12.94,
|
| 394 |
+
"grad_norm": 4.201530933380127,
|
| 395 |
+
"learning_rate": 0.0002613529411764706,
|
| 396 |
+
"loss": 0.3755,
|
| 397 |
+
"step": 220
|
| 398 |
+
},
|
| 399 |
+
{
|
| 400 |
+
"epoch": 12.94,
|
| 401 |
+
"eval_loss": 0.33055052161216736,
|
| 402 |
+
"eval_runtime": 1.9605,
|
| 403 |
+
"eval_samples_per_second": 68.348,
|
| 404 |
+
"eval_steps_per_second": 8.671,
|
| 405 |
+
"step": 220
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 13.24,
|
| 409 |
+
"grad_norm": 1.1253122091293335,
|
| 410 |
+
"learning_rate": 0.0002604705882352941,
|
| 411 |
+
"loss": 0.3317,
|
| 412 |
+
"step": 225
|
| 413 |
+
},
|
| 414 |
+
{
|
| 415 |
+
"epoch": 13.53,
|
| 416 |
+
"grad_norm": 1.38557767868042,
|
| 417 |
+
"learning_rate": 0.0002595882352941176,
|
| 418 |
+
"loss": 0.3587,
|
| 419 |
+
"step": 230
|
| 420 |
+
},
|
| 421 |
+
{
|
| 422 |
+
"epoch": 13.82,
|
| 423 |
+
"grad_norm": 1.5310808420181274,
|
| 424 |
+
"learning_rate": 0.0002587058823529411,
|
| 425 |
+
"loss": 0.4219,
|
| 426 |
+
"step": 235
|
| 427 |
+
},
|
| 428 |
+
{
|
| 429 |
+
"epoch": 14.12,
|
| 430 |
+
"grad_norm": 2.292116165161133,
|
| 431 |
+
"learning_rate": 0.00025782352941176466,
|
| 432 |
+
"loss": 0.3532,
|
| 433 |
+
"step": 240
|
| 434 |
+
},
|
| 435 |
+
{
|
| 436 |
+
"epoch": 14.12,
|
| 437 |
+
"eval_loss": 0.32043349742889404,
|
| 438 |
+
"eval_runtime": 1.9616,
|
| 439 |
+
"eval_samples_per_second": 68.311,
|
| 440 |
+
"eval_steps_per_second": 8.666,
|
| 441 |
+
"step": 240
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 14.41,
|
| 445 |
+
"grad_norm": 1.8762236833572388,
|
| 446 |
+
"learning_rate": 0.0002569411764705882,
|
| 447 |
+
"loss": 0.3637,
|
| 448 |
+
"step": 245
|
| 449 |
+
},
|
| 450 |
+
{
|
| 451 |
+
"epoch": 14.71,
|
| 452 |
+
"grad_norm": 1.4035817384719849,
|
| 453 |
+
"learning_rate": 0.00025605882352941174,
|
| 454 |
+
"loss": 0.3381,
|
| 455 |
+
"step": 250
|
| 456 |
+
},
|
| 457 |
+
{
|
| 458 |
+
"epoch": 15.0,
|
| 459 |
+
"grad_norm": 1.2829474210739136,
|
| 460 |
+
"learning_rate": 0.0002551764705882353,
|
| 461 |
+
"loss": 0.4141,
|
| 462 |
+
"step": 255
|
| 463 |
+
},
|
| 464 |
+
{
|
| 465 |
+
"epoch": 15.29,
|
| 466 |
+
"grad_norm": 0.9864193797111511,
|
| 467 |
+
"learning_rate": 0.0002542941176470588,
|
| 468 |
+
"loss": 0.3267,
|
| 469 |
+
"step": 260
|
| 470 |
+
},
|
| 471 |
+
{
|
| 472 |
+
"epoch": 15.29,
|
| 473 |
+
"eval_loss": 0.32013770937919617,
|
| 474 |
+
"eval_runtime": 1.9612,
|
| 475 |
+
"eval_samples_per_second": 68.326,
|
| 476 |
+
"eval_steps_per_second": 8.668,
|
| 477 |
+
"step": 260
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 15.59,
|
| 481 |
+
"grad_norm": 1.867457628250122,
|
| 482 |
+
"learning_rate": 0.0002534117647058823,
|
| 483 |
+
"loss": 0.3506,
|
| 484 |
+
"step": 265
|
| 485 |
+
},
|
| 486 |
+
{
|
| 487 |
+
"epoch": 15.88,
|
| 488 |
+
"grad_norm": 3.3703501224517822,
|
| 489 |
+
"learning_rate": 0.00025252941176470586,
|
| 490 |
+
"loss": 0.3671,
|
| 491 |
+
"step": 270
|
| 492 |
+
},
|
| 493 |
+
{
|
| 494 |
+
"epoch": 16.18,
|
| 495 |
+
"grad_norm": 1.0780836343765259,
|
| 496 |
+
"learning_rate": 0.0002516470588235294,
|
| 497 |
+
"loss": 0.3525,
|
| 498 |
+
"step": 275
|
| 499 |
+
},
|
| 500 |
+
{
|
| 501 |
+
"epoch": 16.47,
|
| 502 |
+
"grad_norm": 1.5468271970748901,
|
| 503 |
+
"learning_rate": 0.00025076470588235295,
|
| 504 |
+
"loss": 0.3632,
|
| 505 |
+
"step": 280
|
| 506 |
+
},
|
| 507 |
+
{
|
| 508 |
+
"epoch": 16.47,
|
| 509 |
+
"eval_loss": 0.31823015213012695,
|
| 510 |
+
"eval_runtime": 1.9635,
|
| 511 |
+
"eval_samples_per_second": 68.245,
|
| 512 |
+
"eval_steps_per_second": 8.658,
|
| 513 |
+
"step": 280
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 16.76,
|
| 517 |
+
"grad_norm": 0.9740966558456421,
|
| 518 |
+
"learning_rate": 0.00024988235294117644,
|
| 519 |
+
"loss": 0.3335,
|
| 520 |
+
"step": 285
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 17.06,
|
| 524 |
+
"grad_norm": 0.9535332918167114,
|
| 525 |
+
"learning_rate": 0.000249,
|
| 526 |
+
"loss": 0.3708,
|
| 527 |
+
"step": 290
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 17.35,
|
| 531 |
+
"grad_norm": 1.0746893882751465,
|
| 532 |
+
"learning_rate": 0.0002481176470588235,
|
| 533 |
+
"loss": 0.2916,
|
| 534 |
+
"step": 295
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 17.65,
|
| 538 |
+
"grad_norm": 1.3976492881774902,
|
| 539 |
+
"learning_rate": 0.000247235294117647,
|
| 540 |
+
"loss": 0.3722,
|
| 541 |
+
"step": 300
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 17.65,
|
| 545 |
+
"eval_loss": 0.3323402404785156,
|
| 546 |
+
"eval_runtime": 1.9628,
|
| 547 |
+
"eval_samples_per_second": 68.269,
|
| 548 |
+
"eval_steps_per_second": 8.661,
|
| 549 |
+
"step": 300
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 17.94,
|
| 553 |
+
"grad_norm": 1.7855074405670166,
|
| 554 |
+
"learning_rate": 0.00024635294117647056,
|
| 555 |
+
"loss": 0.3998,
|
| 556 |
+
"step": 305
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 18.24,
|
| 560 |
+
"grad_norm": 1.0271461009979248,
|
| 561 |
+
"learning_rate": 0.0002454705882352941,
|
| 562 |
+
"loss": 0.3371,
|
| 563 |
+
"step": 310
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 18.53,
|
| 567 |
+
"grad_norm": 1.378629207611084,
|
| 568 |
+
"learning_rate": 0.00024458823529411764,
|
| 569 |
+
"loss": 0.3335,
|
| 570 |
+
"step": 315
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 18.82,
|
| 574 |
+
"grad_norm": 1.4561057090759277,
|
| 575 |
+
"learning_rate": 0.00024370588235294116,
|
| 576 |
+
"loss": 0.3682,
|
| 577 |
+
"step": 320
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 18.82,
|
| 581 |
+
"eval_loss": 0.32237428426742554,
|
| 582 |
+
"eval_runtime": 1.9652,
|
| 583 |
+
"eval_samples_per_second": 68.185,
|
| 584 |
+
"eval_steps_per_second": 8.65,
|
| 585 |
+
"step": 320
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 19.12,
|
| 589 |
+
"grad_norm": 1.7702654600143433,
|
| 590 |
+
"learning_rate": 0.0002428235294117647,
|
| 591 |
+
"loss": 0.3449,
|
| 592 |
+
"step": 325
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"epoch": 19.41,
|
| 596 |
+
"grad_norm": 0.7253245711326599,
|
| 597 |
+
"learning_rate": 0.00024194117647058822,
|
| 598 |
+
"loss": 0.3241,
|
| 599 |
+
"step": 330
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 19.71,
|
| 603 |
+
"grad_norm": 1.31587815284729,
|
| 604 |
+
"learning_rate": 0.00024105882352941176,
|
| 605 |
+
"loss": 0.3352,
|
| 606 |
+
"step": 335
|
| 607 |
+
},
|
| 608 |
+
{
|
| 609 |
+
"epoch": 20.0,
|
| 610 |
+
"grad_norm": 1.0167505741119385,
|
| 611 |
+
"learning_rate": 0.00024017647058823525,
|
| 612 |
+
"loss": 0.3823,
|
| 613 |
+
"step": 340
|
| 614 |
+
},
|
| 615 |
+
{
|
| 616 |
+
"epoch": 20.0,
|
| 617 |
+
"eval_loss": 0.30231013894081116,
|
| 618 |
+
"eval_runtime": 1.9647,
|
| 619 |
+
"eval_samples_per_second": 68.205,
|
| 620 |
+
"eval_steps_per_second": 8.653,
|
| 621 |
+
"step": 340
|
| 622 |
+
},
|
| 623 |
+
{
|
| 624 |
+
"epoch": 20.29,
|
| 625 |
+
"grad_norm": 1.0506433248519897,
|
| 626 |
+
"learning_rate": 0.0002392941176470588,
|
| 627 |
+
"loss": 0.3026,
|
| 628 |
+
"step": 345
|
| 629 |
+
},
|
| 630 |
+
{
|
| 631 |
+
"epoch": 20.59,
|
| 632 |
+
"grad_norm": 0.7938820719718933,
|
| 633 |
+
"learning_rate": 0.00023841176470588233,
|
| 634 |
+
"loss": 0.3523,
|
| 635 |
+
"step": 350
|
| 636 |
+
},
|
| 637 |
+
{
|
| 638 |
+
"epoch": 20.88,
|
| 639 |
+
"grad_norm": 0.8134554028511047,
|
| 640 |
+
"learning_rate": 0.00023752941176470585,
|
| 641 |
+
"loss": 0.3466,
|
| 642 |
+
"step": 355
|
| 643 |
+
},
|
| 644 |
+
{
|
| 645 |
+
"epoch": 21.18,
|
| 646 |
+
"grad_norm": 0.6556082963943481,
|
| 647 |
+
"learning_rate": 0.0002366470588235294,
|
| 648 |
+
"loss": 0.3347,
|
| 649 |
+
"step": 360
|
| 650 |
+
},
|
| 651 |
+
{
|
| 652 |
+
"epoch": 21.18,
|
| 653 |
+
"eval_loss": 0.3018949627876282,
|
| 654 |
+
"eval_runtime": 1.9624,
|
| 655 |
+
"eval_samples_per_second": 68.284,
|
| 656 |
+
"eval_steps_per_second": 8.663,
|
| 657 |
+
"step": 360
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"epoch": 21.47,
|
| 661 |
+
"grad_norm": 0.8881806135177612,
|
| 662 |
+
"learning_rate": 0.0002357647058823529,
|
| 663 |
+
"loss": 0.3187,
|
| 664 |
+
"step": 365
|
| 665 |
+
},
|
| 666 |
+
{
|
| 667 |
+
"epoch": 21.76,
|
| 668 |
+
"grad_norm": 1.0280077457427979,
|
| 669 |
+
"learning_rate": 0.00023488235294117645,
|
| 670 |
+
"loss": 0.3513,
|
| 671 |
+
"step": 370
|
| 672 |
+
},
|
| 673 |
+
{
|
| 674 |
+
"epoch": 22.06,
|
| 675 |
+
"grad_norm": 0.874485433101654,
|
| 676 |
+
"learning_rate": 0.000234,
|
| 677 |
+
"loss": 0.3472,
|
| 678 |
+
"step": 375
|
| 679 |
+
},
|
| 680 |
+
{
|
| 681 |
+
"epoch": 22.35,
|
| 682 |
+
"grad_norm": 0.8063223958015442,
|
| 683 |
+
"learning_rate": 0.0002331176470588235,
|
| 684 |
+
"loss": 0.3199,
|
| 685 |
+
"step": 380
|
| 686 |
+
},
|
| 687 |
+
{
|
| 688 |
+
"epoch": 22.35,
|
| 689 |
+
"eval_loss": 0.3000001907348633,
|
| 690 |
+
"eval_runtime": 1.9831,
|
| 691 |
+
"eval_samples_per_second": 67.57,
|
| 692 |
+
"eval_steps_per_second": 8.572,
|
| 693 |
+
"step": 380
|
| 694 |
+
},
|
| 695 |
+
{
|
| 696 |
+
"epoch": 22.65,
|
| 697 |
+
"grad_norm": 1.3876217603683472,
|
| 698 |
+
"learning_rate": 0.00023223529411764705,
|
| 699 |
+
"loss": 0.342,
|
| 700 |
+
"step": 385
|
| 701 |
+
},
|
| 702 |
+
{
|
| 703 |
+
"epoch": 22.94,
|
| 704 |
+
"grad_norm": 0.9147685766220093,
|
| 705 |
+
"learning_rate": 0.00023135294117647054,
|
| 706 |
+
"loss": 0.3275,
|
| 707 |
+
"step": 390
|
| 708 |
+
},
|
| 709 |
+
{
|
| 710 |
+
"epoch": 23.24,
|
| 711 |
+
"grad_norm": 1.1167635917663574,
|
| 712 |
+
"learning_rate": 0.0002304705882352941,
|
| 713 |
+
"loss": 0.3417,
|
| 714 |
+
"step": 395
|
| 715 |
+
},
|
| 716 |
+
{
|
| 717 |
+
"epoch": 23.53,
|
| 718 |
+
"grad_norm": 0.8822980523109436,
|
| 719 |
+
"learning_rate": 0.00022958823529411763,
|
| 720 |
+
"loss": 0.3526,
|
| 721 |
+
"step": 400
|
| 722 |
+
},
|
| 723 |
+
{
|
| 724 |
+
"epoch": 23.53,
|
| 725 |
+
"eval_loss": 0.30671894550323486,
|
| 726 |
+
"eval_runtime": 1.9623,
|
| 727 |
+
"eval_samples_per_second": 68.287,
|
| 728 |
+
"eval_steps_per_second": 8.663,
|
| 729 |
+
"step": 400
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 23.82,
|
| 733 |
+
"grad_norm": 0.911723792552948,
|
| 734 |
+
"learning_rate": 0.00022870588235294115,
|
| 735 |
+
"loss": 0.3223,
|
| 736 |
+
"step": 405
|
| 737 |
+
},
|
| 738 |
+
{
|
| 739 |
+
"epoch": 24.12,
|
| 740 |
+
"grad_norm": 0.9427434802055359,
|
| 741 |
+
"learning_rate": 0.0002278235294117647,
|
| 742 |
+
"loss": 0.3258,
|
| 743 |
+
"step": 410
|
| 744 |
+
},
|
| 745 |
+
{
|
| 746 |
+
"epoch": 24.41,
|
| 747 |
+
"grad_norm": 0.643779456615448,
|
| 748 |
+
"learning_rate": 0.0002269411764705882,
|
| 749 |
+
"loss": 0.3062,
|
| 750 |
+
"step": 415
|
| 751 |
+
},
|
| 752 |
+
{
|
| 753 |
+
"epoch": 24.71,
|
| 754 |
+
"grad_norm": 0.8616035580635071,
|
| 755 |
+
"learning_rate": 0.00022605882352941175,
|
| 756 |
+
"loss": 0.3282,
|
| 757 |
+
"step": 420
|
| 758 |
+
},
|
| 759 |
+
{
|
| 760 |
+
"epoch": 24.71,
|
| 761 |
+
"eval_loss": 0.3003075420856476,
|
| 762 |
+
"eval_runtime": 1.9662,
|
| 763 |
+
"eval_samples_per_second": 68.151,
|
| 764 |
+
"eval_steps_per_second": 8.646,
|
| 765 |
+
"step": 420
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 25.0,
|
| 769 |
+
"grad_norm": 1.039482831954956,
|
| 770 |
+
"learning_rate": 0.0002251764705882353,
|
| 771 |
+
"loss": 0.3482,
|
| 772 |
+
"step": 425
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 25.29,
|
| 776 |
+
"grad_norm": 0.866456151008606,
|
| 777 |
+
"learning_rate": 0.0002242941176470588,
|
| 778 |
+
"loss": 0.2953,
|
| 779 |
+
"step": 430
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 25.59,
|
| 783 |
+
"grad_norm": 0.7293558716773987,
|
| 784 |
+
"learning_rate": 0.00022341176470588235,
|
| 785 |
+
"loss": 0.3024,
|
| 786 |
+
"step": 435
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 25.88,
|
| 790 |
+
"grad_norm": 0.8793621063232422,
|
| 791 |
+
"learning_rate": 0.00022252941176470587,
|
| 792 |
+
"loss": 0.3514,
|
| 793 |
+
"step": 440
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 25.88,
|
| 797 |
+
"eval_loss": 0.2972111999988556,
|
| 798 |
+
"eval_runtime": 1.963,
|
| 799 |
+
"eval_samples_per_second": 68.262,
|
| 800 |
+
"eval_steps_per_second": 8.66,
|
| 801 |
+
"step": 440
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 26.18,
|
| 805 |
+
"grad_norm": 0.7020326256752014,
|
| 806 |
+
"learning_rate": 0.00022164705882352938,
|
| 807 |
+
"loss": 0.3474,
|
| 808 |
+
"step": 445
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 26.47,
|
| 812 |
+
"grad_norm": 0.6527474522590637,
|
| 813 |
+
"learning_rate": 0.0002207647058823529,
|
| 814 |
+
"loss": 0.2785,
|
| 815 |
+
"step": 450
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 26.76,
|
| 819 |
+
"grad_norm": 0.7786436676979065,
|
| 820 |
+
"learning_rate": 0.00021988235294117644,
|
| 821 |
+
"loss": 0.3178,
|
| 822 |
+
"step": 455
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 27.06,
|
| 826 |
+
"grad_norm": 0.8497650623321533,
|
| 827 |
+
"learning_rate": 0.00021899999999999998,
|
| 828 |
+
"loss": 0.3504,
|
| 829 |
+
"step": 460
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 27.06,
|
| 833 |
+
"eval_loss": 0.2919369041919708,
|
| 834 |
+
"eval_runtime": 1.9847,
|
| 835 |
+
"eval_samples_per_second": 67.516,
|
| 836 |
+
"eval_steps_per_second": 8.565,
|
| 837 |
+
"step": 460
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 27.35,
|
| 841 |
+
"grad_norm": 0.5582404732704163,
|
| 842 |
+
"learning_rate": 0.0002181176470588235,
|
| 843 |
+
"loss": 0.2934,
|
| 844 |
+
"step": 465
|
| 845 |
+
},
|
| 846 |
+
{
|
| 847 |
+
"epoch": 27.65,
|
| 848 |
+
"grad_norm": 0.863581120967865,
|
| 849 |
+
"learning_rate": 0.00021723529411764704,
|
| 850 |
+
"loss": 0.339,
|
| 851 |
+
"step": 470
|
| 852 |
+
},
|
| 853 |
+
{
|
| 854 |
+
"epoch": 27.94,
|
| 855 |
+
"grad_norm": 0.5909052491188049,
|
| 856 |
+
"learning_rate": 0.00021635294117647059,
|
| 857 |
+
"loss": 0.337,
|
| 858 |
+
"step": 475
|
| 859 |
+
},
|
| 860 |
+
{
|
| 861 |
+
"epoch": 28.24,
|
| 862 |
+
"grad_norm": 0.7073140144348145,
|
| 863 |
+
"learning_rate": 0.0002154705882352941,
|
| 864 |
+
"loss": 0.3107,
|
| 865 |
+
"step": 480
|
| 866 |
+
},
|
| 867 |
+
{
|
| 868 |
+
"epoch": 28.24,
|
| 869 |
+
"eval_loss": 0.29314759373664856,
|
| 870 |
+
"eval_runtime": 1.965,
|
| 871 |
+
"eval_samples_per_second": 68.193,
|
| 872 |
+
"eval_steps_per_second": 8.651,
|
| 873 |
+
"step": 480
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 28.53,
|
| 877 |
+
"grad_norm": 0.6535521745681763,
|
| 878 |
+
"learning_rate": 0.00021458823529411764,
|
| 879 |
+
"loss": 0.3035,
|
| 880 |
+
"step": 485
|
| 881 |
+
},
|
| 882 |
+
{
|
| 883 |
+
"epoch": 28.82,
|
| 884 |
+
"grad_norm": 0.7834466695785522,
|
| 885 |
+
"learning_rate": 0.00021370588235294116,
|
| 886 |
+
"loss": 0.3289,
|
| 887 |
+
"step": 490
|
| 888 |
+
},
|
| 889 |
+
{
|
| 890 |
+
"epoch": 29.12,
|
| 891 |
+
"grad_norm": 0.6114407181739807,
|
| 892 |
+
"learning_rate": 0.0002128235294117647,
|
| 893 |
+
"loss": 0.2927,
|
| 894 |
+
"step": 495
|
| 895 |
+
},
|
| 896 |
+
{
|
| 897 |
+
"epoch": 29.41,
|
| 898 |
+
"grad_norm": 0.8664116859436035,
|
| 899 |
+
"learning_rate": 0.0002119411764705882,
|
| 900 |
+
"loss": 0.3149,
|
| 901 |
+
"step": 500
|
| 902 |
+
},
|
| 903 |
+
{
|
| 904 |
+
"epoch": 29.41,
|
| 905 |
+
"eval_loss": 0.2926511764526367,
|
| 906 |
+
"eval_runtime": 1.9627,
|
| 907 |
+
"eval_samples_per_second": 68.272,
|
| 908 |
+
"eval_steps_per_second": 8.661,
|
| 909 |
+
"step": 500
|
| 910 |
+
},
|
| 911 |
+
{
|
| 912 |
+
"epoch": 29.71,
|
| 913 |
+
"grad_norm": 0.6796421408653259,
|
| 914 |
+
"learning_rate": 0.00021105882352941174,
|
| 915 |
+
"loss": 0.3222,
|
| 916 |
+
"step": 505
|
| 917 |
+
},
|
| 918 |
+
{
|
| 919 |
+
"epoch": 30.0,
|
| 920 |
+
"grad_norm": 1.039330244064331,
|
| 921 |
+
"learning_rate": 0.00021017647058823528,
|
| 922 |
+
"loss": 0.3117,
|
| 923 |
+
"step": 510
|
| 924 |
+
},
|
| 925 |
+
{
|
| 926 |
+
"epoch": 30.29,
|
| 927 |
+
"grad_norm": 0.6566951274871826,
|
| 928 |
+
"learning_rate": 0.0002092941176470588,
|
| 929 |
+
"loss": 0.3103,
|
| 930 |
+
"step": 515
|
| 931 |
+
},
|
| 932 |
+
{
|
| 933 |
+
"epoch": 30.59,
|
| 934 |
+
"grad_norm": 0.8899269104003906,
|
| 935 |
+
"learning_rate": 0.00020841176470588234,
|
| 936 |
+
"loss": 0.2923,
|
| 937 |
+
"step": 520
|
| 938 |
+
},
|
| 939 |
+
{
|
| 940 |
+
"epoch": 30.59,
|
| 941 |
+
"eval_loss": 0.29460230469703674,
|
| 942 |
+
"eval_runtime": 1.9627,
|
| 943 |
+
"eval_samples_per_second": 68.274,
|
| 944 |
+
"eval_steps_per_second": 8.662,
|
| 945 |
+
"step": 520
|
| 946 |
+
},
|
| 947 |
+
{
|
| 948 |
+
"epoch": 30.88,
|
| 949 |
+
"grad_norm": 0.8392385244369507,
|
| 950 |
+
"learning_rate": 0.00020752941176470585,
|
| 951 |
+
"loss": 0.3178,
|
| 952 |
+
"step": 525
|
| 953 |
+
},
|
| 954 |
+
{
|
| 955 |
+
"epoch": 31.18,
|
| 956 |
+
"grad_norm": 0.6451537013053894,
|
| 957 |
+
"learning_rate": 0.0002066470588235294,
|
| 958 |
+
"loss": 0.3217,
|
| 959 |
+
"step": 530
|
| 960 |
+
},
|
| 961 |
+
{
|
| 962 |
+
"epoch": 31.47,
|
| 963 |
+
"grad_norm": 0.7242605686187744,
|
| 964 |
+
"learning_rate": 0.00020576470588235294,
|
| 965 |
+
"loss": 0.2926,
|
| 966 |
+
"step": 535
|
| 967 |
+
},
|
| 968 |
+
{
|
| 969 |
+
"epoch": 31.76,
|
| 970 |
+
"grad_norm": 0.8665878772735596,
|
| 971 |
+
"learning_rate": 0.00020488235294117646,
|
| 972 |
+
"loss": 0.3193,
|
| 973 |
+
"step": 540
|
| 974 |
+
},
|
| 975 |
+
{
|
| 976 |
+
"epoch": 31.76,
|
| 977 |
+
"eval_loss": 0.2924383282661438,
|
| 978 |
+
"eval_runtime": 1.9651,
|
| 979 |
+
"eval_samples_per_second": 68.191,
|
| 980 |
+
"eval_steps_per_second": 8.651,
|
| 981 |
+
"step": 540
|
| 982 |
+
},
|
| 983 |
+
{
|
| 984 |
+
"epoch": 32.06,
|
| 985 |
+
"grad_norm": 0.560516357421875,
|
| 986 |
+
"learning_rate": 0.000204,
|
| 987 |
+
"loss": 0.3127,
|
| 988 |
+
"step": 545
|
| 989 |
+
},
|
| 990 |
+
{
|
| 991 |
+
"epoch": 32.35,
|
| 992 |
+
"grad_norm": 0.6437721848487854,
|
| 993 |
+
"learning_rate": 0.0002031176470588235,
|
| 994 |
+
"loss": 0.3065,
|
| 995 |
+
"step": 550
|
| 996 |
+
},
|
| 997 |
+
{
|
| 998 |
+
"epoch": 32.65,
|
| 999 |
+
"grad_norm": 1.002756118774414,
|
| 1000 |
+
"learning_rate": 0.00020223529411764703,
|
| 1001 |
+
"loss": 0.3134,
|
| 1002 |
+
"step": 555
|
| 1003 |
+
},
|
| 1004 |
+
{
|
| 1005 |
+
"epoch": 32.94,
|
| 1006 |
+
"grad_norm": 0.7988303303718567,
|
| 1007 |
+
"learning_rate": 0.00020135294117647057,
|
| 1008 |
+
"loss": 0.3163,
|
| 1009 |
+
"step": 560
|
| 1010 |
+
},
|
| 1011 |
+
{
|
| 1012 |
+
"epoch": 32.94,
|
| 1013 |
+
"eval_loss": 0.2888733446598053,
|
| 1014 |
+
"eval_runtime": 1.9651,
|
| 1015 |
+
"eval_samples_per_second": 68.19,
|
| 1016 |
+
"eval_steps_per_second": 8.651,
|
| 1017 |
+
"step": 560
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 33.24,
|
| 1021 |
+
"grad_norm": 0.5882442593574524,
|
| 1022 |
+
"learning_rate": 0.0002004705882352941,
|
| 1023 |
+
"loss": 0.2773,
|
| 1024 |
+
"step": 565
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 33.53,
|
| 1028 |
+
"grad_norm": 0.7490789294242859,
|
| 1029 |
+
"learning_rate": 0.00019958823529411763,
|
| 1030 |
+
"loss": 0.3246,
|
| 1031 |
+
"step": 570
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 33.82,
|
| 1035 |
+
"grad_norm": 0.7290482521057129,
|
| 1036 |
+
"learning_rate": 0.00019870588235294115,
|
| 1037 |
+
"loss": 0.309,
|
| 1038 |
+
"step": 575
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"epoch": 34.12,
|
| 1042 |
+
"grad_norm": 0.6329946517944336,
|
| 1043 |
+
"learning_rate": 0.0001978235294117647,
|
| 1044 |
+
"loss": 0.3415,
|
| 1045 |
+
"step": 580
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 34.12,
|
| 1049 |
+
"eval_loss": 0.2882162630558014,
|
| 1050 |
+
"eval_runtime": 1.964,
|
| 1051 |
+
"eval_samples_per_second": 68.229,
|
| 1052 |
+
"eval_steps_per_second": 8.656,
|
| 1053 |
+
"step": 580
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 34.41,
|
| 1057 |
+
"grad_norm": 0.5783909559249878,
|
| 1058 |
+
"learning_rate": 0.00019694117647058823,
|
| 1059 |
+
"loss": 0.2792,
|
| 1060 |
+
"step": 585
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"epoch": 34.71,
|
| 1064 |
+
"grad_norm": 0.6922691464424133,
|
| 1065 |
+
"learning_rate": 0.00019605882352941175,
|
| 1066 |
+
"loss": 0.3279,
|
| 1067 |
+
"step": 590
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"epoch": 35.0,
|
| 1071 |
+
"grad_norm": 0.8705866932868958,
|
| 1072 |
+
"learning_rate": 0.0001951764705882353,
|
| 1073 |
+
"loss": 0.3127,
|
| 1074 |
+
"step": 595
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 35.29,
|
| 1078 |
+
"grad_norm": 0.6629935503005981,
|
| 1079 |
+
"learning_rate": 0.0001942941176470588,
|
| 1080 |
+
"loss": 0.3003,
|
| 1081 |
+
"step": 600
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 35.29,
|
| 1085 |
+
"eval_loss": 0.2893199622631073,
|
| 1086 |
+
"eval_runtime": 1.9629,
|
| 1087 |
+
"eval_samples_per_second": 68.266,
|
| 1088 |
+
"eval_steps_per_second": 8.661,
|
| 1089 |
+
"step": 600
|
| 1090 |
+
},
|
| 1091 |
+
{
|
| 1092 |
+
"epoch": 35.59,
|
| 1093 |
+
"grad_norm": 0.6237422227859497,
|
| 1094 |
+
"learning_rate": 0.00019341176470588233,
|
| 1095 |
+
"loss": 0.2999,
|
| 1096 |
+
"step": 605
|
| 1097 |
+
},
|
| 1098 |
+
{
|
| 1099 |
+
"epoch": 35.88,
|
| 1100 |
+
"grad_norm": 0.9606088995933533,
|
| 1101 |
+
"learning_rate": 0.00019252941176470584,
|
| 1102 |
+
"loss": 0.3227,
|
| 1103 |
+
"step": 610
|
| 1104 |
+
},
|
| 1105 |
+
{
|
| 1106 |
+
"epoch": 36.18,
|
| 1107 |
+
"grad_norm": 0.5493776202201843,
|
| 1108 |
+
"learning_rate": 0.00019164705882352938,
|
| 1109 |
+
"loss": 0.3145,
|
| 1110 |
+
"step": 615
|
| 1111 |
+
},
|
| 1112 |
+
{
|
| 1113 |
+
"epoch": 36.47,
|
| 1114 |
+
"grad_norm": 0.7220461964607239,
|
| 1115 |
+
"learning_rate": 0.00019076470588235293,
|
| 1116 |
+
"loss": 0.2865,
|
| 1117 |
+
"step": 620
|
| 1118 |
+
},
|
| 1119 |
+
{
|
| 1120 |
+
"epoch": 36.47,
|
| 1121 |
+
"eval_loss": 0.2936779856681824,
|
| 1122 |
+
"eval_runtime": 1.9642,
|
| 1123 |
+
"eval_samples_per_second": 68.221,
|
| 1124 |
+
"eval_steps_per_second": 8.655,
|
| 1125 |
+
"step": 620
|
| 1126 |
+
},
|
| 1127 |
+
{
|
| 1128 |
+
"epoch": 36.76,
|
| 1129 |
+
"grad_norm": 0.6160561442375183,
|
| 1130 |
+
"learning_rate": 0.00018988235294117644,
|
| 1131 |
+
"loss": 0.3216,
|
| 1132 |
+
"step": 625
|
| 1133 |
+
},
|
| 1134 |
+
{
|
| 1135 |
+
"epoch": 37.06,
|
| 1136 |
+
"grad_norm": 0.6289909482002258,
|
| 1137 |
+
"learning_rate": 0.00018899999999999999,
|
| 1138 |
+
"loss": 0.3189,
|
| 1139 |
+
"step": 630
|
| 1140 |
+
},
|
| 1141 |
+
{
|
| 1142 |
+
"epoch": 37.35,
|
| 1143 |
+
"grad_norm": 0.6761196851730347,
|
| 1144 |
+
"learning_rate": 0.00018811764705882353,
|
| 1145 |
+
"loss": 0.3087,
|
| 1146 |
+
"step": 635
|
| 1147 |
+
},
|
| 1148 |
+
{
|
| 1149 |
+
"epoch": 37.65,
|
| 1150 |
+
"grad_norm": 0.5623531341552734,
|
| 1151 |
+
"learning_rate": 0.00018723529411764705,
|
| 1152 |
+
"loss": 0.2807,
|
| 1153 |
+
"step": 640
|
| 1154 |
+
},
|
| 1155 |
+
{
|
| 1156 |
+
"epoch": 37.65,
|
| 1157 |
+
"eval_loss": 0.2888528108596802,
|
| 1158 |
+
"eval_runtime": 1.9653,
|
| 1159 |
+
"eval_samples_per_second": 68.184,
|
| 1160 |
+
"eval_steps_per_second": 8.65,
|
| 1161 |
+
"step": 640
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 37.94,
|
| 1165 |
+
"grad_norm": 0.7031363248825073,
|
| 1166 |
+
"learning_rate": 0.0001863529411764706,
|
| 1167 |
+
"loss": 0.3148,
|
| 1168 |
+
"step": 645
|
| 1169 |
+
},
|
| 1170 |
+
{
|
| 1171 |
+
"epoch": 38.24,
|
| 1172 |
+
"grad_norm": 0.6560050249099731,
|
| 1173 |
+
"learning_rate": 0.0001854705882352941,
|
| 1174 |
+
"loss": 0.2879,
|
| 1175 |
+
"step": 650
|
| 1176 |
+
},
|
| 1177 |
+
{
|
| 1178 |
+
"epoch": 38.53,
|
| 1179 |
+
"grad_norm": 0.6954489350318909,
|
| 1180 |
+
"learning_rate": 0.00018458823529411762,
|
| 1181 |
+
"loss": 0.2893,
|
| 1182 |
+
"step": 655
|
| 1183 |
+
},
|
| 1184 |
+
{
|
| 1185 |
+
"epoch": 38.82,
|
| 1186 |
+
"grad_norm": 0.547197163105011,
|
| 1187 |
+
"learning_rate": 0.00018370588235294114,
|
| 1188 |
+
"loss": 0.3119,
|
| 1189 |
+
"step": 660
|
| 1190 |
+
},
|
| 1191 |
+
{
|
| 1192 |
+
"epoch": 38.82,
|
| 1193 |
+
"eval_loss": 0.28801044821739197,
|
| 1194 |
+
"eval_runtime": 1.9633,
|
| 1195 |
+
"eval_samples_per_second": 68.252,
|
| 1196 |
+
"eval_steps_per_second": 8.659,
|
| 1197 |
+
"step": 660
|
| 1198 |
+
},
|
| 1199 |
+
{
|
| 1200 |
+
"epoch": 39.12,
|
| 1201 |
+
"grad_norm": 0.635062575340271,
|
| 1202 |
+
"learning_rate": 0.00018282352941176468,
|
| 1203 |
+
"loss": 0.3068,
|
| 1204 |
+
"step": 665
|
| 1205 |
+
},
|
| 1206 |
+
{
|
| 1207 |
+
"epoch": 39.41,
|
| 1208 |
+
"grad_norm": 0.7098654508590698,
|
| 1209 |
+
"learning_rate": 0.00018194117647058822,
|
| 1210 |
+
"loss": 0.3022,
|
| 1211 |
+
"step": 670
|
| 1212 |
+
},
|
| 1213 |
+
{
|
| 1214 |
+
"epoch": 39.71,
|
| 1215 |
+
"grad_norm": 0.8924707770347595,
|
| 1216 |
+
"learning_rate": 0.00018105882352941174,
|
| 1217 |
+
"loss": 0.3173,
|
| 1218 |
+
"step": 675
|
| 1219 |
+
},
|
| 1220 |
+
{
|
| 1221 |
+
"epoch": 40.0,
|
| 1222 |
+
"grad_norm": 0.7111414670944214,
|
| 1223 |
+
"learning_rate": 0.00018017647058823528,
|
| 1224 |
+
"loss": 0.3181,
|
| 1225 |
+
"step": 680
|
| 1226 |
+
},
|
| 1227 |
+
{
|
| 1228 |
+
"epoch": 40.0,
|
| 1229 |
+
"eval_loss": 0.2859283983707428,
|
| 1230 |
+
"eval_runtime": 1.9638,
|
| 1231 |
+
"eval_samples_per_second": 68.234,
|
| 1232 |
+
"eval_steps_per_second": 8.657,
|
| 1233 |
+
"step": 680
|
| 1234 |
+
},
|
| 1235 |
+
{
|
| 1236 |
+
"epoch": 40.29,
|
| 1237 |
+
"grad_norm": 0.6105594635009766,
|
| 1238 |
+
"learning_rate": 0.0001792941176470588,
|
| 1239 |
+
"loss": 0.281,
|
| 1240 |
+
"step": 685
|
| 1241 |
+
},
|
| 1242 |
+
{
|
| 1243 |
+
"epoch": 40.59,
|
| 1244 |
+
"grad_norm": 0.5732124447822571,
|
| 1245 |
+
"learning_rate": 0.00017841176470588234,
|
| 1246 |
+
"loss": 0.2991,
|
| 1247 |
+
"step": 690
|
| 1248 |
+
},
|
| 1249 |
+
{
|
| 1250 |
+
"epoch": 40.88,
|
| 1251 |
+
"grad_norm": 0.48427799344062805,
|
| 1252 |
+
"learning_rate": 0.00017752941176470588,
|
| 1253 |
+
"loss": 0.3271,
|
| 1254 |
+
"step": 695
|
| 1255 |
+
},
|
| 1256 |
+
{
|
| 1257 |
+
"epoch": 41.18,
|
| 1258 |
+
"grad_norm": 0.6201653480529785,
|
| 1259 |
+
"learning_rate": 0.0001766470588235294,
|
| 1260 |
+
"loss": 0.3132,
|
| 1261 |
+
"step": 700
|
| 1262 |
+
},
|
| 1263 |
+
{
|
| 1264 |
+
"epoch": 41.18,
|
| 1265 |
+
"eval_loss": 0.2859351336956024,
|
| 1266 |
+
"eval_runtime": 1.9655,
|
| 1267 |
+
"eval_samples_per_second": 68.176,
|
| 1268 |
+
"eval_steps_per_second": 8.649,
|
| 1269 |
+
"step": 700
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 41.47,
|
| 1273 |
+
"grad_norm": 0.618773341178894,
|
| 1274 |
+
"learning_rate": 0.00017576470588235294,
|
| 1275 |
+
"loss": 0.3043,
|
| 1276 |
+
"step": 705
|
| 1277 |
+
},
|
| 1278 |
+
{
|
| 1279 |
+
"epoch": 41.76,
|
| 1280 |
+
"grad_norm": 0.4781729280948639,
|
| 1281 |
+
"learning_rate": 0.00017488235294117643,
|
| 1282 |
+
"loss": 0.3199,
|
| 1283 |
+
"step": 710
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 42.06,
|
| 1287 |
+
"grad_norm": 0.7103304266929626,
|
| 1288 |
+
"learning_rate": 0.00017399999999999997,
|
| 1289 |
+
"loss": 0.3058,
|
| 1290 |
+
"step": 715
|
| 1291 |
+
},
|
| 1292 |
+
{
|
| 1293 |
+
"epoch": 42.35,
|
| 1294 |
+
"grad_norm": 0.8100818395614624,
|
| 1295 |
+
"learning_rate": 0.00017311764705882352,
|
| 1296 |
+
"loss": 0.2913,
|
| 1297 |
+
"step": 720
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 42.35,
|
| 1301 |
+
"eval_loss": 0.28682219982147217,
|
| 1302 |
+
"eval_runtime": 1.9662,
|
| 1303 |
+
"eval_samples_per_second": 68.151,
|
| 1304 |
+
"eval_steps_per_second": 8.646,
|
| 1305 |
+
"step": 720
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 42.65,
|
| 1309 |
+
"grad_norm": 0.7974515557289124,
|
| 1310 |
+
"learning_rate": 0.00017223529411764703,
|
| 1311 |
+
"loss": 0.3184,
|
| 1312 |
+
"step": 725
|
| 1313 |
+
},
|
| 1314 |
+
{
|
| 1315 |
+
"epoch": 42.94,
|
| 1316 |
+
"grad_norm": 0.6758606433868408,
|
| 1317 |
+
"learning_rate": 0.00017135294117647058,
|
| 1318 |
+
"loss": 0.3011,
|
| 1319 |
+
"step": 730
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 43.24,
|
| 1323 |
+
"grad_norm": 0.6599326133728027,
|
| 1324 |
+
"learning_rate": 0.0001704705882352941,
|
| 1325 |
+
"loss": 0.284,
|
| 1326 |
+
"step": 735
|
| 1327 |
+
},
|
| 1328 |
+
{
|
| 1329 |
+
"epoch": 43.53,
|
| 1330 |
+
"grad_norm": 0.676020085811615,
|
| 1331 |
+
"learning_rate": 0.00016958823529411763,
|
| 1332 |
+
"loss": 0.3029,
|
| 1333 |
+
"step": 740
|
| 1334 |
+
},
|
| 1335 |
+
{
|
| 1336 |
+
"epoch": 43.53,
|
| 1337 |
+
"eval_loss": 0.28783947229385376,
|
| 1338 |
+
"eval_runtime": 1.9653,
|
| 1339 |
+
"eval_samples_per_second": 68.184,
|
| 1340 |
+
"eval_steps_per_second": 8.65,
|
| 1341 |
+
"step": 740
|
| 1342 |
+
},
|
| 1343 |
+
{
|
| 1344 |
+
"epoch": 43.82,
|
| 1345 |
+
"grad_norm": 0.6323675513267517,
|
| 1346 |
+
"learning_rate": 0.00016870588235294118,
|
| 1347 |
+
"loss": 0.3023,
|
| 1348 |
+
"step": 745
|
| 1349 |
+
},
|
| 1350 |
+
{
|
| 1351 |
+
"epoch": 44.12,
|
| 1352 |
+
"grad_norm": 0.6845364570617676,
|
| 1353 |
+
"learning_rate": 0.0001678235294117647,
|
| 1354 |
+
"loss": 0.3328,
|
| 1355 |
+
"step": 750
|
| 1356 |
+
},
|
| 1357 |
+
{
|
| 1358 |
+
"epoch": 44.41,
|
| 1359 |
+
"grad_norm": 0.7217048406600952,
|
| 1360 |
+
"learning_rate": 0.00016694117647058824,
|
| 1361 |
+
"loss": 0.3118,
|
| 1362 |
+
"step": 755
|
| 1363 |
+
},
|
| 1364 |
+
{
|
| 1365 |
+
"epoch": 44.71,
|
| 1366 |
+
"grad_norm": 0.5953862071037292,
|
| 1367 |
+
"learning_rate": 0.00016605882352941175,
|
| 1368 |
+
"loss": 0.2855,
|
| 1369 |
+
"step": 760
|
| 1370 |
+
},
|
| 1371 |
+
{
|
| 1372 |
+
"epoch": 44.71,
|
| 1373 |
+
"eval_loss": 0.28705352544784546,
|
| 1374 |
+
"eval_runtime": 1.9663,
|
| 1375 |
+
"eval_samples_per_second": 68.147,
|
| 1376 |
+
"eval_steps_per_second": 8.645,
|
| 1377 |
+
"step": 760
|
| 1378 |
+
},
|
| 1379 |
+
{
|
| 1380 |
+
"epoch": 45.0,
|
| 1381 |
+
"grad_norm": 1.210176944732666,
|
| 1382 |
+
"learning_rate": 0.00016517647058823527,
|
| 1383 |
+
"loss": 0.3186,
|
| 1384 |
+
"step": 765
|
| 1385 |
+
},
|
| 1386 |
+
{
|
| 1387 |
+
"epoch": 45.29,
|
| 1388 |
+
"grad_norm": 0.45849332213401794,
|
| 1389 |
+
"learning_rate": 0.0001642941176470588,
|
| 1390 |
+
"loss": 0.2951,
|
| 1391 |
+
"step": 770
|
| 1392 |
+
},
|
| 1393 |
+
{
|
| 1394 |
+
"epoch": 45.59,
|
| 1395 |
+
"grad_norm": 0.6013903617858887,
|
| 1396 |
+
"learning_rate": 0.00016341176470588233,
|
| 1397 |
+
"loss": 0.3077,
|
| 1398 |
+
"step": 775
|
| 1399 |
+
},
|
| 1400 |
+
{
|
| 1401 |
+
"epoch": 45.88,
|
| 1402 |
+
"grad_norm": 0.6650539040565491,
|
| 1403 |
+
"learning_rate": 0.00016252941176470587,
|
| 1404 |
+
"loss": 0.3067,
|
| 1405 |
+
"step": 780
|
| 1406 |
+
},
|
| 1407 |
+
{
|
| 1408 |
+
"epoch": 45.88,
|
| 1409 |
+
"eval_loss": 0.28653430938720703,
|
| 1410 |
+
"eval_runtime": 1.9662,
|
| 1411 |
+
"eval_samples_per_second": 68.152,
|
| 1412 |
+
"eval_steps_per_second": 8.646,
|
| 1413 |
+
"step": 780
|
| 1414 |
+
},
|
| 1415 |
+
{
|
| 1416 |
+
"epoch": 46.18,
|
| 1417 |
+
"grad_norm": 0.6908199191093445,
|
| 1418 |
+
"learning_rate": 0.0001616470588235294,
|
| 1419 |
+
"loss": 0.3092,
|
| 1420 |
+
"step": 785
|
| 1421 |
+
},
|
| 1422 |
+
{
|
| 1423 |
+
"epoch": 46.47,
|
| 1424 |
+
"grad_norm": 0.6603782176971436,
|
| 1425 |
+
"learning_rate": 0.00016076470588235293,
|
| 1426 |
+
"loss": 0.2849,
|
| 1427 |
+
"step": 790
|
| 1428 |
+
},
|
| 1429 |
+
{
|
| 1430 |
+
"epoch": 46.76,
|
| 1431 |
+
"grad_norm": 0.5460072159767151,
|
| 1432 |
+
"learning_rate": 0.00015988235294117647,
|
| 1433 |
+
"loss": 0.3238,
|
| 1434 |
+
"step": 795
|
| 1435 |
+
},
|
| 1436 |
+
{
|
| 1437 |
+
"epoch": 47.06,
|
| 1438 |
+
"grad_norm": 0.5787355899810791,
|
| 1439 |
+
"learning_rate": 0.000159,
|
| 1440 |
+
"loss": 0.3097,
|
| 1441 |
+
"step": 800
|
| 1442 |
+
},
|
| 1443 |
+
{
|
| 1444 |
+
"epoch": 47.06,
|
| 1445 |
+
"eval_loss": 0.2853982746601105,
|
| 1446 |
+
"eval_runtime": 1.9644,
|
| 1447 |
+
"eval_samples_per_second": 68.213,
|
| 1448 |
+
"eval_steps_per_second": 8.654,
|
| 1449 |
+
"step": 800
|
| 1450 |
+
},
|
| 1451 |
+
{
|
| 1452 |
+
"epoch": 47.35,
|
| 1453 |
+
"grad_norm": 0.6943737268447876,
|
| 1454 |
+
"learning_rate": 0.00015811764705882353,
|
| 1455 |
+
"loss": 0.2873,
|
| 1456 |
+
"step": 805
|
| 1457 |
+
},
|
| 1458 |
+
{
|
| 1459 |
+
"epoch": 47.65,
|
| 1460 |
+
"grad_norm": 0.48888710141181946,
|
| 1461 |
+
"learning_rate": 0.00015723529411764705,
|
| 1462 |
+
"loss": 0.2863,
|
| 1463 |
+
"step": 810
|
| 1464 |
+
},
|
| 1465 |
+
{
|
| 1466 |
+
"epoch": 47.94,
|
| 1467 |
+
"grad_norm": 0.7545343041419983,
|
| 1468 |
+
"learning_rate": 0.00015635294117647056,
|
| 1469 |
+
"loss": 0.314,
|
| 1470 |
+
"step": 815
|
| 1471 |
+
},
|
| 1472 |
+
{
|
| 1473 |
+
"epoch": 48.24,
|
| 1474 |
+
"grad_norm": 0.6604719161987305,
|
| 1475 |
+
"learning_rate": 0.00015547058823529408,
|
| 1476 |
+
"loss": 0.3013,
|
| 1477 |
+
"step": 820
|
| 1478 |
+
},
|
| 1479 |
+
{
|
| 1480 |
+
"epoch": 48.24,
|
| 1481 |
+
"eval_loss": 0.28414490818977356,
|
| 1482 |
+
"eval_runtime": 1.9648,
|
| 1483 |
+
"eval_samples_per_second": 68.2,
|
| 1484 |
+
"eval_steps_per_second": 8.652,
|
| 1485 |
+
"step": 820
|
| 1486 |
+
},
|
| 1487 |
+
{
|
| 1488 |
+
"epoch": 48.53,
|
| 1489 |
+
"grad_norm": 0.6394490599632263,
|
| 1490 |
+
"learning_rate": 0.00015458823529411762,
|
| 1491 |
+
"loss": 0.2728,
|
| 1492 |
+
"step": 825
|
| 1493 |
+
},
|
| 1494 |
+
{
|
| 1495 |
+
"epoch": 48.82,
|
| 1496 |
+
"grad_norm": 0.7762249708175659,
|
| 1497 |
+
"learning_rate": 0.00015370588235294117,
|
| 1498 |
+
"loss": 0.3195,
|
| 1499 |
+
"step": 830
|
| 1500 |
+
},
|
| 1501 |
+
{
|
| 1502 |
+
"epoch": 49.12,
|
| 1503 |
+
"grad_norm": 0.4706575274467468,
|
| 1504 |
+
"learning_rate": 0.00015282352941176468,
|
| 1505 |
+
"loss": 0.3057,
|
| 1506 |
+
"step": 835
|
| 1507 |
+
},
|
| 1508 |
+
{
|
| 1509 |
+
"epoch": 49.41,
|
| 1510 |
+
"grad_norm": 0.5505021214485168,
|
| 1511 |
+
"learning_rate": 0.00015194117647058822,
|
| 1512 |
+
"loss": 0.3117,
|
| 1513 |
+
"step": 840
|
| 1514 |
+
},
|
| 1515 |
+
{
|
| 1516 |
+
"epoch": 49.41,
|
| 1517 |
+
"eval_loss": 0.2862291634082794,
|
| 1518 |
+
"eval_runtime": 1.9664,
|
| 1519 |
+
"eval_samples_per_second": 68.145,
|
| 1520 |
+
"eval_steps_per_second": 8.645,
|
| 1521 |
+
"step": 840
|
| 1522 |
+
},
|
| 1523 |
+
{
|
| 1524 |
+
"epoch": 49.71,
|
| 1525 |
+
"grad_norm": 0.7223942279815674,
|
| 1526 |
+
"learning_rate": 0.00015105882352941177,
|
| 1527 |
+
"loss": 0.3031,
|
| 1528 |
+
"step": 845
|
| 1529 |
+
},
|
| 1530 |
+
{
|
| 1531 |
+
"epoch": 50.0,
|
| 1532 |
+
"grad_norm": 0.8495947122573853,
|
| 1533 |
+
"learning_rate": 0.00015017647058823528,
|
| 1534 |
+
"loss": 0.307,
|
| 1535 |
+
"step": 850
|
| 1536 |
+
},
|
| 1537 |
+
{
|
| 1538 |
+
"epoch": 50.29,
|
| 1539 |
+
"grad_norm": 0.5779330730438232,
|
| 1540 |
+
"learning_rate": 0.0001492941176470588,
|
| 1541 |
+
"loss": 0.2962,
|
| 1542 |
+
"step": 855
|
| 1543 |
+
},
|
| 1544 |
+
{
|
| 1545 |
+
"epoch": 50.59,
|
| 1546 |
+
"grad_norm": 0.753194272518158,
|
| 1547 |
+
"learning_rate": 0.00014841176470588234,
|
| 1548 |
+
"loss": 0.3005,
|
| 1549 |
+
"step": 860
|
| 1550 |
+
},
|
| 1551 |
+
{
|
| 1552 |
+
"epoch": 50.59,
|
| 1553 |
+
"eval_loss": 0.28647956252098083,
|
| 1554 |
+
"eval_runtime": 1.9639,
|
| 1555 |
+
"eval_samples_per_second": 68.233,
|
| 1556 |
+
"eval_steps_per_second": 8.656,
|
| 1557 |
+
"step": 860
|
| 1558 |
+
},
|
| 1559 |
+
{
|
| 1560 |
+
"epoch": 50.88,
|
| 1561 |
+
"grad_norm": 0.6464411616325378,
|
| 1562 |
+
"learning_rate": 0.00014752941176470586,
|
| 1563 |
+
"loss": 0.3068,
|
| 1564 |
+
"step": 865
|
| 1565 |
+
},
|
| 1566 |
+
{
|
| 1567 |
+
"epoch": 51.18,
|
| 1568 |
+
"grad_norm": 0.7173861861228943,
|
| 1569 |
+
"learning_rate": 0.0001466470588235294,
|
| 1570 |
+
"loss": 0.3133,
|
| 1571 |
+
"step": 870
|
| 1572 |
+
},
|
| 1573 |
+
{
|
| 1574 |
+
"epoch": 51.47,
|
| 1575 |
+
"grad_norm": 0.7621653079986572,
|
| 1576 |
+
"learning_rate": 0.00014576470588235294,
|
| 1577 |
+
"loss": 0.2931,
|
| 1578 |
+
"step": 875
|
| 1579 |
+
},
|
| 1580 |
+
{
|
| 1581 |
+
"epoch": 51.76,
|
| 1582 |
+
"grad_norm": 0.6334201097488403,
|
| 1583 |
+
"learning_rate": 0.00014488235294117646,
|
| 1584 |
+
"loss": 0.2795,
|
| 1585 |
+
"step": 880
|
| 1586 |
+
},
|
| 1587 |
+
{
|
| 1588 |
+
"epoch": 51.76,
|
| 1589 |
+
"eval_loss": 0.2854805588722229,
|
| 1590 |
+
"eval_runtime": 1.9654,
|
| 1591 |
+
"eval_samples_per_second": 68.179,
|
| 1592 |
+
"eval_steps_per_second": 8.65,
|
| 1593 |
+
"step": 880
|
| 1594 |
+
},
|
| 1595 |
+
{
|
| 1596 |
+
"epoch": 52.06,
|
| 1597 |
+
"grad_norm": 0.6040038466453552,
|
| 1598 |
+
"learning_rate": 0.00014399999999999998,
|
| 1599 |
+
"loss": 0.3078,
|
| 1600 |
+
"step": 885
|
| 1601 |
+
},
|
| 1602 |
+
{
|
| 1603 |
+
"epoch": 52.35,
|
| 1604 |
+
"grad_norm": 0.620993971824646,
|
| 1605 |
+
"learning_rate": 0.00014311764705882352,
|
| 1606 |
+
"loss": 0.2844,
|
| 1607 |
+
"step": 890
|
| 1608 |
+
},
|
| 1609 |
+
{
|
| 1610 |
+
"epoch": 52.65,
|
| 1611 |
+
"grad_norm": 0.6360505223274231,
|
| 1612 |
+
"learning_rate": 0.00014223529411764704,
|
| 1613 |
+
"loss": 0.3051,
|
| 1614 |
+
"step": 895
|
| 1615 |
+
},
|
| 1616 |
+
{
|
| 1617 |
+
"epoch": 52.94,
|
| 1618 |
+
"grad_norm": 0.6702447533607483,
|
| 1619 |
+
"learning_rate": 0.00014135294117647058,
|
| 1620 |
+
"loss": 0.3078,
|
| 1621 |
+
"step": 900
|
| 1622 |
+
},
|
| 1623 |
+
{
|
| 1624 |
+
"epoch": 52.94,
|
| 1625 |
+
"eval_loss": 0.28418096899986267,
|
| 1626 |
+
"eval_runtime": 1.9664,
|
| 1627 |
+
"eval_samples_per_second": 68.143,
|
| 1628 |
+
"eval_steps_per_second": 8.645,
|
| 1629 |
+
"step": 900
|
| 1630 |
+
},
|
| 1631 |
+
{
|
| 1632 |
+
"epoch": 53.24,
|
| 1633 |
+
"grad_norm": 0.6132071614265442,
|
| 1634 |
+
"learning_rate": 0.00014047058823529412,
|
| 1635 |
+
"loss": 0.2888,
|
| 1636 |
+
"step": 905
|
| 1637 |
+
},
|
| 1638 |
+
{
|
| 1639 |
+
"epoch": 53.53,
|
| 1640 |
+
"grad_norm": 0.6795573830604553,
|
| 1641 |
+
"learning_rate": 0.00013958823529411764,
|
| 1642 |
+
"loss": 0.2887,
|
| 1643 |
+
"step": 910
|
| 1644 |
+
},
|
| 1645 |
+
{
|
| 1646 |
+
"epoch": 53.82,
|
| 1647 |
+
"grad_norm": 0.5238967537879944,
|
| 1648 |
+
"learning_rate": 0.00013870588235294115,
|
| 1649 |
+
"loss": 0.2998,
|
| 1650 |
+
"step": 915
|
| 1651 |
+
},
|
| 1652 |
+
{
|
| 1653 |
+
"epoch": 54.12,
|
| 1654 |
+
"grad_norm": 0.4750180244445801,
|
| 1655 |
+
"learning_rate": 0.0001378235294117647,
|
| 1656 |
+
"loss": 0.3205,
|
| 1657 |
+
"step": 920
|
| 1658 |
+
},
|
| 1659 |
+
{
|
| 1660 |
+
"epoch": 54.12,
|
| 1661 |
+
"eval_loss": 0.28351739048957825,
|
| 1662 |
+
"eval_runtime": 1.9639,
|
| 1663 |
+
"eval_samples_per_second": 68.232,
|
| 1664 |
+
"eval_steps_per_second": 8.656,
|
| 1665 |
+
"step": 920
|
| 1666 |
+
},
|
| 1667 |
+
{
|
| 1668 |
+
"epoch": 54.41,
|
| 1669 |
+
"grad_norm": 0.5777810215950012,
|
| 1670 |
+
"learning_rate": 0.00013694117647058824,
|
| 1671 |
+
"loss": 0.3021,
|
| 1672 |
+
"step": 925
|
| 1673 |
+
},
|
| 1674 |
+
{
|
| 1675 |
+
"epoch": 54.71,
|
| 1676 |
+
"grad_norm": 0.7304868698120117,
|
| 1677 |
+
"learning_rate": 0.00013605882352941176,
|
| 1678 |
+
"loss": 0.3076,
|
| 1679 |
+
"step": 930
|
| 1680 |
+
},
|
| 1681 |
+
{
|
| 1682 |
+
"epoch": 55.0,
|
| 1683 |
+
"grad_norm": 0.7278028130531311,
|
| 1684 |
+
"learning_rate": 0.00013517647058823527,
|
| 1685 |
+
"loss": 0.3034,
|
| 1686 |
+
"step": 935
|
| 1687 |
+
},
|
| 1688 |
+
{
|
| 1689 |
+
"epoch": 55.29,
|
| 1690 |
+
"grad_norm": 0.8247731328010559,
|
| 1691 |
+
"learning_rate": 0.00013429411764705881,
|
| 1692 |
+
"loss": 0.3041,
|
| 1693 |
+
"step": 940
|
| 1694 |
+
},
|
| 1695 |
+
{
|
| 1696 |
+
"epoch": 55.29,
|
| 1697 |
+
"eval_loss": 0.28424587845802307,
|
| 1698 |
+
"eval_runtime": 1.9641,
|
| 1699 |
+
"eval_samples_per_second": 68.225,
|
| 1700 |
+
"eval_steps_per_second": 8.655,
|
| 1701 |
+
"step": 940
|
| 1702 |
+
},
|
| 1703 |
+
{
|
| 1704 |
+
"epoch": 55.59,
|
| 1705 |
+
"grad_norm": 0.636499285697937,
|
| 1706 |
+
"learning_rate": 0.00013341176470588233,
|
| 1707 |
+
"loss": 0.2901,
|
| 1708 |
+
"step": 945
|
| 1709 |
+
},
|
| 1710 |
+
{
|
| 1711 |
+
"epoch": 55.88,
|
| 1712 |
+
"grad_norm": 0.6638462543487549,
|
| 1713 |
+
"learning_rate": 0.00013252941176470587,
|
| 1714 |
+
"loss": 0.3016,
|
| 1715 |
+
"step": 950
|
| 1716 |
+
},
|
| 1717 |
+
{
|
| 1718 |
+
"epoch": 56.18,
|
| 1719 |
+
"grad_norm": 0.6350640654563904,
|
| 1720 |
+
"learning_rate": 0.00013164705882352942,
|
| 1721 |
+
"loss": 0.3017,
|
| 1722 |
+
"step": 955
|
| 1723 |
+
},
|
| 1724 |
+
{
|
| 1725 |
+
"epoch": 56.47,
|
| 1726 |
+
"grad_norm": 0.47436249256134033,
|
| 1727 |
+
"learning_rate": 0.00013076470588235293,
|
| 1728 |
+
"loss": 0.3002,
|
| 1729 |
+
"step": 960
|
| 1730 |
+
},
|
| 1731 |
+
{
|
| 1732 |
+
"epoch": 56.47,
|
| 1733 |
+
"eval_loss": 0.28626057505607605,
|
| 1734 |
+
"eval_runtime": 1.9665,
|
| 1735 |
+
"eval_samples_per_second": 68.14,
|
| 1736 |
+
"eval_steps_per_second": 8.645,
|
| 1737 |
+
"step": 960
|
| 1738 |
+
},
|
| 1739 |
+
{
|
| 1740 |
+
"epoch": 56.76,
|
| 1741 |
+
"grad_norm": 0.74443119764328,
|
| 1742 |
+
"learning_rate": 0.00012988235294117645,
|
| 1743 |
+
"loss": 0.3048,
|
| 1744 |
+
"step": 965
|
| 1745 |
+
},
|
| 1746 |
+
{
|
| 1747 |
+
"epoch": 57.06,
|
| 1748 |
+
"grad_norm": 0.5560376048088074,
|
| 1749 |
+
"learning_rate": 0.000129,
|
| 1750 |
+
"loss": 0.2866,
|
| 1751 |
+
"step": 970
|
| 1752 |
+
},
|
| 1753 |
+
{
|
| 1754 |
+
"epoch": 57.35,
|
| 1755 |
+
"grad_norm": 0.4963874816894531,
|
| 1756 |
+
"learning_rate": 0.0001281176470588235,
|
| 1757 |
+
"loss": 0.2959,
|
| 1758 |
+
"step": 975
|
| 1759 |
+
},
|
| 1760 |
+
{
|
| 1761 |
+
"epoch": 57.65,
|
| 1762 |
+
"grad_norm": 0.6134093999862671,
|
| 1763 |
+
"learning_rate": 0.00012723529411764705,
|
| 1764 |
+
"loss": 0.2818,
|
| 1765 |
+
"step": 980
|
| 1766 |
+
},
|
| 1767 |
+
{
|
| 1768 |
+
"epoch": 57.65,
|
| 1769 |
+
"eval_loss": 0.2846217751502991,
|
| 1770 |
+
"eval_runtime": 1.963,
|
| 1771 |
+
"eval_samples_per_second": 68.264,
|
| 1772 |
+
"eval_steps_per_second": 8.66,
|
| 1773 |
+
"step": 980
|
| 1774 |
+
},
|
| 1775 |
+
{
|
| 1776 |
+
"epoch": 57.94,
|
| 1777 |
+
"grad_norm": 0.5762036442756653,
|
| 1778 |
+
"learning_rate": 0.0001263529411764706,
|
| 1779 |
+
"loss": 0.3253,
|
| 1780 |
+
"step": 985
|
| 1781 |
+
},
|
| 1782 |
+
{
|
| 1783 |
+
"epoch": 58.24,
|
| 1784 |
+
"grad_norm": 0.4365149438381195,
|
| 1785 |
+
"learning_rate": 0.0001254705882352941,
|
| 1786 |
+
"loss": 0.2786,
|
| 1787 |
+
"step": 990
|
| 1788 |
+
},
|
| 1789 |
+
{
|
| 1790 |
+
"epoch": 58.53,
|
| 1791 |
+
"grad_norm": 0.6106890439987183,
|
| 1792 |
+
"learning_rate": 0.00012458823529411763,
|
| 1793 |
+
"loss": 0.3185,
|
| 1794 |
+
"step": 995
|
| 1795 |
+
},
|
| 1796 |
+
{
|
| 1797 |
+
"epoch": 58.82,
|
| 1798 |
+
"grad_norm": 0.5440130829811096,
|
| 1799 |
+
"learning_rate": 0.00012370588235294117,
|
| 1800 |
+
"loss": 0.2836,
|
| 1801 |
+
"step": 1000
|
| 1802 |
+
},
|
| 1803 |
+
{
|
| 1804 |
+
"epoch": 58.82,
|
| 1805 |
+
"eval_loss": 0.28373199701309204,
|
| 1806 |
+
"eval_runtime": 1.986,
|
| 1807 |
+
"eval_samples_per_second": 67.471,
|
| 1808 |
+
"eval_steps_per_second": 8.56,
|
| 1809 |
+
"step": 1000
|
| 1810 |
+
},
|
| 1811 |
+
{
|
| 1812 |
+
"epoch": 59.12,
|
| 1813 |
+
"grad_norm": 0.6012306213378906,
|
| 1814 |
+
"learning_rate": 0.0001228235294117647,
|
| 1815 |
+
"loss": 0.3082,
|
| 1816 |
+
"step": 1005
|
| 1817 |
+
},
|
| 1818 |
+
{
|
| 1819 |
+
"epoch": 59.41,
|
| 1820 |
+
"grad_norm": 0.6317033171653748,
|
| 1821 |
+
"learning_rate": 0.00012194117647058823,
|
| 1822 |
+
"loss": 0.2873,
|
| 1823 |
+
"step": 1010
|
| 1824 |
+
},
|
| 1825 |
+
{
|
| 1826 |
+
"epoch": 59.71,
|
| 1827 |
+
"grad_norm": 0.6505876779556274,
|
| 1828 |
+
"learning_rate": 0.00012105882352941174,
|
| 1829 |
+
"loss": 0.3002,
|
| 1830 |
+
"step": 1015
|
| 1831 |
+
},
|
| 1832 |
+
{
|
| 1833 |
+
"epoch": 60.0,
|
| 1834 |
+
"grad_norm": 0.7005593180656433,
|
| 1835 |
+
"learning_rate": 0.00012017647058823529,
|
| 1836 |
+
"loss": 0.287,
|
| 1837 |
+
"step": 1020
|
| 1838 |
+
},
|
| 1839 |
+
{
|
| 1840 |
+
"epoch": 60.0,
|
| 1841 |
+
"eval_loss": 0.2828787565231323,
|
| 1842 |
+
"eval_runtime": 1.9719,
|
| 1843 |
+
"eval_samples_per_second": 67.954,
|
| 1844 |
+
"eval_steps_per_second": 8.621,
|
| 1845 |
+
"step": 1020
|
| 1846 |
+
},
|
| 1847 |
+
{
|
| 1848 |
+
"epoch": 60.29,
|
| 1849 |
+
"grad_norm": 0.7630228400230408,
|
| 1850 |
+
"learning_rate": 0.00011929411764705882,
|
| 1851 |
+
"loss": 0.3082,
|
| 1852 |
+
"step": 1025
|
| 1853 |
+
},
|
| 1854 |
+
{
|
| 1855 |
+
"epoch": 60.59,
|
| 1856 |
+
"grad_norm": 0.605331301689148,
|
| 1857 |
+
"learning_rate": 0.00011841176470588235,
|
| 1858 |
+
"loss": 0.265,
|
| 1859 |
+
"step": 1030
|
| 1860 |
+
},
|
| 1861 |
+
{
|
| 1862 |
+
"epoch": 60.88,
|
| 1863 |
+
"grad_norm": 0.6675235629081726,
|
| 1864 |
+
"learning_rate": 0.00011752941176470587,
|
| 1865 |
+
"loss": 0.3104,
|
| 1866 |
+
"step": 1035
|
| 1867 |
+
},
|
| 1868 |
+
{
|
| 1869 |
+
"epoch": 61.18,
|
| 1870 |
+
"grad_norm": 0.5875442028045654,
|
| 1871 |
+
"learning_rate": 0.00011664705882352939,
|
| 1872 |
+
"loss": 0.3008,
|
| 1873 |
+
"step": 1040
|
| 1874 |
+
},
|
| 1875 |
+
{
|
| 1876 |
+
"epoch": 61.18,
|
| 1877 |
+
"eval_loss": 0.282687246799469,
|
| 1878 |
+
"eval_runtime": 1.9686,
|
| 1879 |
+
"eval_samples_per_second": 68.069,
|
| 1880 |
+
"eval_steps_per_second": 8.636,
|
| 1881 |
+
"step": 1040
|
| 1882 |
+
},
|
| 1883 |
+
{
|
| 1884 |
+
"epoch": 61.47,
|
| 1885 |
+
"grad_norm": 0.5393230319023132,
|
| 1886 |
+
"learning_rate": 0.00011576470588235292,
|
| 1887 |
+
"loss": 0.3023,
|
| 1888 |
+
"step": 1045
|
| 1889 |
+
},
|
| 1890 |
+
{
|
| 1891 |
+
"epoch": 61.76,
|
| 1892 |
+
"grad_norm": 0.6968395113945007,
|
| 1893 |
+
"learning_rate": 0.00011488235294117646,
|
| 1894 |
+
"loss": 0.2992,
|
| 1895 |
+
"step": 1050
|
| 1896 |
+
},
|
| 1897 |
+
{
|
| 1898 |
+
"epoch": 62.06,
|
| 1899 |
+
"grad_norm": 0.454150915145874,
|
| 1900 |
+
"learning_rate": 0.00011399999999999999,
|
| 1901 |
+
"loss": 0.2766,
|
| 1902 |
+
"step": 1055
|
| 1903 |
+
},
|
| 1904 |
+
{
|
| 1905 |
+
"epoch": 62.35,
|
| 1906 |
+
"grad_norm": 0.9340410232543945,
|
| 1907 |
+
"learning_rate": 0.00011311764705882352,
|
| 1908 |
+
"loss": 0.2947,
|
| 1909 |
+
"step": 1060
|
| 1910 |
+
},
|
| 1911 |
+
{
|
| 1912 |
+
"epoch": 62.35,
|
| 1913 |
+
"eval_loss": 0.28353533148765564,
|
| 1914 |
+
"eval_runtime": 1.964,
|
| 1915 |
+
"eval_samples_per_second": 68.229,
|
| 1916 |
+
"eval_steps_per_second": 8.656,
|
| 1917 |
+
"step": 1060
|
| 1918 |
+
},
|
| 1919 |
+
{
|
| 1920 |
+
"epoch": 62.65,
|
| 1921 |
+
"grad_norm": 0.7134456038475037,
|
| 1922 |
+
"learning_rate": 0.00011223529411764705,
|
| 1923 |
+
"loss": 0.3003,
|
| 1924 |
+
"step": 1065
|
| 1925 |
+
},
|
| 1926 |
+
{
|
| 1927 |
+
"epoch": 62.94,
|
| 1928 |
+
"grad_norm": 0.617602527141571,
|
| 1929 |
+
"learning_rate": 0.00011135294117647057,
|
| 1930 |
+
"loss": 0.3215,
|
| 1931 |
+
"step": 1070
|
| 1932 |
+
},
|
| 1933 |
+
{
|
| 1934 |
+
"epoch": 63.24,
|
| 1935 |
+
"grad_norm": 0.5604396462440491,
|
| 1936 |
+
"learning_rate": 0.00011047058823529411,
|
| 1937 |
+
"loss": 0.2912,
|
| 1938 |
+
"step": 1075
|
| 1939 |
+
},
|
| 1940 |
+
{
|
| 1941 |
+
"epoch": 63.53,
|
| 1942 |
+
"grad_norm": 0.5035967230796814,
|
| 1943 |
+
"learning_rate": 0.00010958823529411764,
|
| 1944 |
+
"loss": 0.2913,
|
| 1945 |
+
"step": 1080
|
| 1946 |
+
},
|
| 1947 |
+
{
|
| 1948 |
+
"epoch": 63.53,
|
| 1949 |
+
"eval_loss": 0.2838851511478424,
|
| 1950 |
+
"eval_runtime": 1.9641,
|
| 1951 |
+
"eval_samples_per_second": 68.224,
|
| 1952 |
+
"eval_steps_per_second": 8.655,
|
| 1953 |
+
"step": 1080
|
| 1954 |
+
},
|
| 1955 |
+
{
|
| 1956 |
+
"epoch": 63.82,
|
| 1957 |
+
"grad_norm": 0.7588418126106262,
|
| 1958 |
+
"learning_rate": 0.00010870588235294117,
|
| 1959 |
+
"loss": 0.2989,
|
| 1960 |
+
"step": 1085
|
| 1961 |
+
},
|
| 1962 |
+
{
|
| 1963 |
+
"epoch": 64.12,
|
| 1964 |
+
"grad_norm": 0.5613157749176025,
|
| 1965 |
+
"learning_rate": 0.0001078235294117647,
|
| 1966 |
+
"loss": 0.2946,
|
| 1967 |
+
"step": 1090
|
| 1968 |
+
},
|
| 1969 |
+
{
|
| 1970 |
+
"epoch": 64.41,
|
| 1971 |
+
"grad_norm": 0.5209499597549438,
|
| 1972 |
+
"learning_rate": 0.00010694117647058822,
|
| 1973 |
+
"loss": 0.2699,
|
| 1974 |
+
"step": 1095
|
| 1975 |
+
},
|
| 1976 |
+
{
|
| 1977 |
+
"epoch": 64.71,
|
| 1978 |
+
"grad_norm": 0.5548143982887268,
|
| 1979 |
+
"learning_rate": 0.00010605882352941176,
|
| 1980 |
+
"loss": 0.294,
|
| 1981 |
+
"step": 1100
|
| 1982 |
+
},
|
| 1983 |
+
{
|
| 1984 |
+
"epoch": 64.71,
|
| 1985 |
+
"eval_loss": 0.2836940586566925,
|
| 1986 |
+
"eval_runtime": 1.964,
|
| 1987 |
+
"eval_samples_per_second": 68.227,
|
| 1988 |
+
"eval_steps_per_second": 8.656,
|
| 1989 |
+
"step": 1100
|
| 1990 |
+
},
|
| 1991 |
+
{
|
| 1992 |
+
"epoch": 65.0,
|
| 1993 |
+
"grad_norm": 0.7083863615989685,
|
| 1994 |
+
"learning_rate": 0.00010517647058823529,
|
| 1995 |
+
"loss": 0.3139,
|
| 1996 |
+
"step": 1105
|
| 1997 |
+
},
|
| 1998 |
+
{
|
| 1999 |
+
"epoch": 65.29,
|
| 2000 |
+
"grad_norm": 0.6682425737380981,
|
| 2001 |
+
"learning_rate": 0.00010429411764705882,
|
| 2002 |
+
"loss": 0.2792,
|
| 2003 |
+
"step": 1110
|
| 2004 |
+
},
|
| 2005 |
+
{
|
| 2006 |
+
"epoch": 65.59,
|
| 2007 |
+
"grad_norm": 0.6851276159286499,
|
| 2008 |
+
"learning_rate": 0.00010341176470588235,
|
| 2009 |
+
"loss": 0.3267,
|
| 2010 |
+
"step": 1115
|
| 2011 |
+
},
|
| 2012 |
+
{
|
| 2013 |
+
"epoch": 65.88,
|
| 2014 |
+
"grad_norm": 0.5307226181030273,
|
| 2015 |
+
"learning_rate": 0.00010252941176470586,
|
| 2016 |
+
"loss": 0.2846,
|
| 2017 |
+
"step": 1120
|
| 2018 |
+
},
|
| 2019 |
+
{
|
| 2020 |
+
"epoch": 65.88,
|
| 2021 |
+
"eval_loss": 0.2831686735153198,
|
| 2022 |
+
"eval_runtime": 1.9628,
|
| 2023 |
+
"eval_samples_per_second": 68.271,
|
| 2024 |
+
"eval_steps_per_second": 8.661,
|
| 2025 |
+
"step": 1120
|
| 2026 |
+
},
|
| 2027 |
+
{
|
| 2028 |
+
"epoch": 66.18,
|
| 2029 |
+
"grad_norm": 0.7149540781974792,
|
| 2030 |
+
"learning_rate": 0.00010164705882352939,
|
| 2031 |
+
"loss": 0.2943,
|
| 2032 |
+
"step": 1125
|
| 2033 |
+
},
|
| 2034 |
+
{
|
| 2035 |
+
"epoch": 66.47,
|
| 2036 |
+
"grad_norm": 0.4598942697048187,
|
| 2037 |
+
"learning_rate": 0.00010076470588235294,
|
| 2038 |
+
"loss": 0.2945,
|
| 2039 |
+
"step": 1130
|
| 2040 |
+
},
|
| 2041 |
+
{
|
| 2042 |
+
"epoch": 66.76,
|
| 2043 |
+
"grad_norm": 0.6665242910385132,
|
| 2044 |
+
"learning_rate": 9.988235294117646e-05,
|
| 2045 |
+
"loss": 0.2942,
|
| 2046 |
+
"step": 1135
|
| 2047 |
+
},
|
| 2048 |
+
{
|
| 2049 |
+
"epoch": 67.06,
|
| 2050 |
+
"grad_norm": 0.6449436545372009,
|
| 2051 |
+
"learning_rate": 9.9e-05,
|
| 2052 |
+
"loss": 0.3038,
|
| 2053 |
+
"step": 1140
|
| 2054 |
+
},
|
| 2055 |
+
{
|
| 2056 |
+
"epoch": 67.06,
|
| 2057 |
+
"eval_loss": 0.2825150191783905,
|
| 2058 |
+
"eval_runtime": 1.971,
|
| 2059 |
+
"eval_samples_per_second": 67.985,
|
| 2060 |
+
"eval_steps_per_second": 8.625,
|
| 2061 |
+
"step": 1140
|
| 2062 |
+
},
|
| 2063 |
+
{
|
| 2064 |
+
"epoch": 67.35,
|
| 2065 |
+
"grad_norm": 0.618532121181488,
|
| 2066 |
+
"learning_rate": 9.811764705882352e-05,
|
| 2067 |
+
"loss": 0.2772,
|
| 2068 |
+
"step": 1145
|
| 2069 |
+
},
|
| 2070 |
+
{
|
| 2071 |
+
"epoch": 67.65,
|
| 2072 |
+
"grad_norm": 0.6807150840759277,
|
| 2073 |
+
"learning_rate": 9.723529411764704e-05,
|
| 2074 |
+
"loss": 0.2987,
|
| 2075 |
+
"step": 1150
|
| 2076 |
+
},
|
| 2077 |
+
{
|
| 2078 |
+
"epoch": 67.94,
|
| 2079 |
+
"grad_norm": 0.6171286106109619,
|
| 2080 |
+
"learning_rate": 9.635294117647058e-05,
|
| 2081 |
+
"loss": 0.2987,
|
| 2082 |
+
"step": 1155
|
| 2083 |
+
},
|
| 2084 |
+
{
|
| 2085 |
+
"epoch": 68.24,
|
| 2086 |
+
"grad_norm": 0.6873087882995605,
|
| 2087 |
+
"learning_rate": 9.547058823529411e-05,
|
| 2088 |
+
"loss": 0.2806,
|
| 2089 |
+
"step": 1160
|
| 2090 |
+
},
|
| 2091 |
+
{
|
| 2092 |
+
"epoch": 68.24,
|
| 2093 |
+
"eval_loss": 0.2823193073272705,
|
| 2094 |
+
"eval_runtime": 1.9639,
|
| 2095 |
+
"eval_samples_per_second": 68.232,
|
| 2096 |
+
"eval_steps_per_second": 8.656,
|
| 2097 |
+
"step": 1160
|
| 2098 |
+
},
|
| 2099 |
+
{
|
| 2100 |
+
"epoch": 68.53,
|
| 2101 |
+
"grad_norm": 0.5284867882728577,
|
| 2102 |
+
"learning_rate": 9.458823529411764e-05,
|
| 2103 |
+
"loss": 0.3118,
|
| 2104 |
+
"step": 1165
|
| 2105 |
+
},
|
| 2106 |
+
{
|
| 2107 |
+
"epoch": 68.82,
|
| 2108 |
+
"grad_norm": 0.7557244896888733,
|
| 2109 |
+
"learning_rate": 9.370588235294117e-05,
|
| 2110 |
+
"loss": 0.3047,
|
| 2111 |
+
"step": 1170
|
| 2112 |
+
},
|
| 2113 |
+
{
|
| 2114 |
+
"epoch": 69.12,
|
| 2115 |
+
"grad_norm": 0.5363481640815735,
|
| 2116 |
+
"learning_rate": 9.282352941176469e-05,
|
| 2117 |
+
"loss": 0.2778,
|
| 2118 |
+
"step": 1175
|
| 2119 |
+
},
|
| 2120 |
+
{
|
| 2121 |
+
"epoch": 69.41,
|
| 2122 |
+
"grad_norm": 0.5491881966590881,
|
| 2123 |
+
"learning_rate": 9.194117647058823e-05,
|
| 2124 |
+
"loss": 0.3196,
|
| 2125 |
+
"step": 1180
|
| 2126 |
+
},
|
| 2127 |
+
{
|
| 2128 |
+
"epoch": 69.41,
|
| 2129 |
+
"eval_loss": 0.28297773003578186,
|
| 2130 |
+
"eval_runtime": 1.9632,
|
| 2131 |
+
"eval_samples_per_second": 68.255,
|
| 2132 |
+
"eval_steps_per_second": 8.659,
|
| 2133 |
+
"step": 1180
|
| 2134 |
+
},
|
| 2135 |
+
{
|
| 2136 |
+
"epoch": 69.71,
|
| 2137 |
+
"grad_norm": 0.5784395933151245,
|
| 2138 |
+
"learning_rate": 9.105882352941176e-05,
|
| 2139 |
+
"loss": 0.2852,
|
| 2140 |
+
"step": 1185
|
| 2141 |
+
},
|
| 2142 |
+
{
|
| 2143 |
+
"epoch": 70.0,
|
| 2144 |
+
"grad_norm": 0.8285568356513977,
|
| 2145 |
+
"learning_rate": 9.017647058823529e-05,
|
| 2146 |
+
"loss": 0.2917,
|
| 2147 |
+
"step": 1190
|
| 2148 |
+
},
|
| 2149 |
+
{
|
| 2150 |
+
"epoch": 70.29,
|
| 2151 |
+
"grad_norm": 0.5826485753059387,
|
| 2152 |
+
"learning_rate": 8.929411764705882e-05,
|
| 2153 |
+
"loss": 0.2881,
|
| 2154 |
+
"step": 1195
|
| 2155 |
+
},
|
| 2156 |
+
{
|
| 2157 |
+
"epoch": 70.59,
|
| 2158 |
+
"grad_norm": 0.5593310594558716,
|
| 2159 |
+
"learning_rate": 8.841176470588233e-05,
|
| 2160 |
+
"loss": 0.2846,
|
| 2161 |
+
"step": 1200
|
| 2162 |
+
},
|
| 2163 |
+
{
|
| 2164 |
+
"epoch": 70.59,
|
| 2165 |
+
"eval_loss": 0.28390002250671387,
|
| 2166 |
+
"eval_runtime": 1.963,
|
| 2167 |
+
"eval_samples_per_second": 68.263,
|
| 2168 |
+
"eval_steps_per_second": 8.66,
|
| 2169 |
+
"step": 1200
|
| 2170 |
+
},
|
| 2171 |
+
{
|
| 2172 |
+
"epoch": 70.88,
|
| 2173 |
+
"grad_norm": 0.5749803185462952,
|
| 2174 |
+
"learning_rate": 8.752941176470586e-05,
|
| 2175 |
+
"loss": 0.2979,
|
| 2176 |
+
"step": 1205
|
| 2177 |
+
},
|
| 2178 |
+
{
|
| 2179 |
+
"epoch": 71.18,
|
| 2180 |
+
"grad_norm": 0.6317547559738159,
|
| 2181 |
+
"learning_rate": 8.664705882352941e-05,
|
| 2182 |
+
"loss": 0.3125,
|
| 2183 |
+
"step": 1210
|
| 2184 |
+
},
|
| 2185 |
+
{
|
| 2186 |
+
"epoch": 71.47,
|
| 2187 |
+
"grad_norm": 0.5578967928886414,
|
| 2188 |
+
"learning_rate": 8.576470588235294e-05,
|
| 2189 |
+
"loss": 0.2938,
|
| 2190 |
+
"step": 1215
|
| 2191 |
+
},
|
| 2192 |
+
{
|
| 2193 |
+
"epoch": 71.76,
|
| 2194 |
+
"grad_norm": 0.6607205271720886,
|
| 2195 |
+
"learning_rate": 8.488235294117647e-05,
|
| 2196 |
+
"loss": 0.2843,
|
| 2197 |
+
"step": 1220
|
| 2198 |
+
},
|
| 2199 |
+
{
|
| 2200 |
+
"epoch": 71.76,
|
| 2201 |
+
"eval_loss": 0.28264713287353516,
|
| 2202 |
+
"eval_runtime": 1.963,
|
| 2203 |
+
"eval_samples_per_second": 68.264,
|
| 2204 |
+
"eval_steps_per_second": 8.66,
|
| 2205 |
+
"step": 1220
|
| 2206 |
+
},
|
| 2207 |
+
{
|
| 2208 |
+
"epoch": 72.06,
|
| 2209 |
+
"grad_norm": 0.5545605421066284,
|
| 2210 |
+
"learning_rate": 8.4e-05,
|
| 2211 |
+
"loss": 0.3011,
|
| 2212 |
+
"step": 1225
|
| 2213 |
+
},
|
| 2214 |
+
{
|
| 2215 |
+
"epoch": 72.35,
|
| 2216 |
+
"grad_norm": 0.6020538210868835,
|
| 2217 |
+
"learning_rate": 8.311764705882351e-05,
|
| 2218 |
+
"loss": 0.2816,
|
| 2219 |
+
"step": 1230
|
| 2220 |
+
},
|
| 2221 |
+
{
|
| 2222 |
+
"epoch": 72.65,
|
| 2223 |
+
"grad_norm": 0.6859305500984192,
|
| 2224 |
+
"learning_rate": 8.223529411764705e-05,
|
| 2225 |
+
"loss": 0.3075,
|
| 2226 |
+
"step": 1235
|
| 2227 |
+
},
|
| 2228 |
+
{
|
| 2229 |
+
"epoch": 72.94,
|
| 2230 |
+
"grad_norm": 0.6900057196617126,
|
| 2231 |
+
"learning_rate": 8.135294117647058e-05,
|
| 2232 |
+
"loss": 0.2948,
|
| 2233 |
+
"step": 1240
|
| 2234 |
+
},
|
| 2235 |
+
{
|
| 2236 |
+
"epoch": 72.94,
|
| 2237 |
+
"eval_loss": 0.2825179994106293,
|
| 2238 |
+
"eval_runtime": 1.9651,
|
| 2239 |
+
"eval_samples_per_second": 68.188,
|
| 2240 |
+
"eval_steps_per_second": 8.651,
|
| 2241 |
+
"step": 1240
|
| 2242 |
+
},
|
| 2243 |
+
{
|
| 2244 |
+
"epoch": 73.24,
|
| 2245 |
+
"grad_norm": 0.6471824645996094,
|
| 2246 |
+
"learning_rate": 8.047058823529411e-05,
|
| 2247 |
+
"loss": 0.2848,
|
| 2248 |
+
"step": 1245
|
| 2249 |
+
},
|
| 2250 |
+
{
|
| 2251 |
+
"epoch": 73.53,
|
| 2252 |
+
"grad_norm": 0.47918254137039185,
|
| 2253 |
+
"learning_rate": 7.958823529411764e-05,
|
| 2254 |
+
"loss": 0.293,
|
| 2255 |
+
"step": 1250
|
| 2256 |
+
},
|
| 2257 |
+
{
|
| 2258 |
+
"epoch": 73.82,
|
| 2259 |
+
"grad_norm": 0.8730375170707703,
|
| 2260 |
+
"learning_rate": 7.870588235294116e-05,
|
| 2261 |
+
"loss": 0.3072,
|
| 2262 |
+
"step": 1255
|
| 2263 |
+
},
|
| 2264 |
+
{
|
| 2265 |
+
"epoch": 74.12,
|
| 2266 |
+
"grad_norm": 0.8796351552009583,
|
| 2267 |
+
"learning_rate": 7.78235294117647e-05,
|
| 2268 |
+
"loss": 0.2961,
|
| 2269 |
+
"step": 1260
|
| 2270 |
+
},
|
| 2271 |
+
{
|
| 2272 |
+
"epoch": 74.12,
|
| 2273 |
+
"eval_loss": 0.2819651663303375,
|
| 2274 |
+
"eval_runtime": 1.965,
|
| 2275 |
+
"eval_samples_per_second": 68.195,
|
| 2276 |
+
"eval_steps_per_second": 8.652,
|
| 2277 |
+
"step": 1260
|
| 2278 |
+
},
|
| 2279 |
+
{
|
| 2280 |
+
"epoch": 74.41,
|
| 2281 |
+
"grad_norm": 0.5722956657409668,
|
| 2282 |
+
"learning_rate": 7.694117647058823e-05,
|
| 2283 |
+
"loss": 0.2972,
|
| 2284 |
+
"step": 1265
|
| 2285 |
+
},
|
| 2286 |
+
{
|
| 2287 |
+
"epoch": 74.71,
|
| 2288 |
+
"grad_norm": 0.6367900967597961,
|
| 2289 |
+
"learning_rate": 7.605882352941176e-05,
|
| 2290 |
+
"loss": 0.2796,
|
| 2291 |
+
"step": 1270
|
| 2292 |
+
},
|
| 2293 |
+
{
|
| 2294 |
+
"epoch": 75.0,
|
| 2295 |
+
"grad_norm": 0.7407358288764954,
|
| 2296 |
+
"learning_rate": 7.517647058823529e-05,
|
| 2297 |
+
"loss": 0.2941,
|
| 2298 |
+
"step": 1275
|
| 2299 |
+
},
|
| 2300 |
+
{
|
| 2301 |
+
"epoch": 75.29,
|
| 2302 |
+
"grad_norm": 0.7088748812675476,
|
| 2303 |
+
"learning_rate": 7.429411764705882e-05,
|
| 2304 |
+
"loss": 0.3188,
|
| 2305 |
+
"step": 1280
|
| 2306 |
+
},
|
| 2307 |
+
{
|
| 2308 |
+
"epoch": 75.29,
|
| 2309 |
+
"eval_loss": 0.282102108001709,
|
| 2310 |
+
"eval_runtime": 1.9653,
|
| 2311 |
+
"eval_samples_per_second": 68.182,
|
| 2312 |
+
"eval_steps_per_second": 8.65,
|
| 2313 |
+
"step": 1280
|
| 2314 |
+
},
|
| 2315 |
+
{
|
| 2316 |
+
"epoch": 75.59,
|
| 2317 |
+
"grad_norm": 0.5513805150985718,
|
| 2318 |
+
"learning_rate": 7.341176470588235e-05,
|
| 2319 |
+
"loss": 0.2985,
|
| 2320 |
+
"step": 1285
|
| 2321 |
+
},
|
| 2322 |
+
{
|
| 2323 |
+
"epoch": 75.88,
|
| 2324 |
+
"grad_norm": 0.44790807366371155,
|
| 2325 |
+
"learning_rate": 7.252941176470588e-05,
|
| 2326 |
+
"loss": 0.2574,
|
| 2327 |
+
"step": 1290
|
| 2328 |
+
},
|
| 2329 |
+
{
|
| 2330 |
+
"epoch": 76.18,
|
| 2331 |
+
"grad_norm": 0.6300696134567261,
|
| 2332 |
+
"learning_rate": 7.164705882352941e-05,
|
| 2333 |
+
"loss": 0.2881,
|
| 2334 |
+
"step": 1295
|
| 2335 |
+
},
|
| 2336 |
+
{
|
| 2337 |
+
"epoch": 76.47,
|
| 2338 |
+
"grad_norm": 0.6399747729301453,
|
| 2339 |
+
"learning_rate": 7.076470588235294e-05,
|
| 2340 |
+
"loss": 0.2913,
|
| 2341 |
+
"step": 1300
|
| 2342 |
+
},
|
| 2343 |
+
{
|
| 2344 |
+
"epoch": 76.47,
|
| 2345 |
+
"eval_loss": 0.2819598317146301,
|
| 2346 |
+
"eval_runtime": 1.9635,
|
| 2347 |
+
"eval_samples_per_second": 68.247,
|
| 2348 |
+
"eval_steps_per_second": 8.658,
|
| 2349 |
+
"step": 1300
|
| 2350 |
+
},
|
| 2351 |
+
{
|
| 2352 |
+
"epoch": 76.76,
|
| 2353 |
+
"grad_norm": 0.6456499695777893,
|
| 2354 |
+
"learning_rate": 6.988235294117647e-05,
|
| 2355 |
+
"loss": 0.2862,
|
| 2356 |
+
"step": 1305
|
| 2357 |
+
},
|
| 2358 |
+
{
|
| 2359 |
+
"epoch": 77.06,
|
| 2360 |
+
"grad_norm": 0.48646461963653564,
|
| 2361 |
+
"learning_rate": 6.9e-05,
|
| 2362 |
+
"loss": 0.2938,
|
| 2363 |
+
"step": 1310
|
| 2364 |
+
},
|
| 2365 |
+
{
|
| 2366 |
+
"epoch": 77.35,
|
| 2367 |
+
"grad_norm": 0.5514676570892334,
|
| 2368 |
+
"learning_rate": 6.811764705882353e-05,
|
| 2369 |
+
"loss": 0.2729,
|
| 2370 |
+
"step": 1315
|
| 2371 |
+
},
|
| 2372 |
+
{
|
| 2373 |
+
"epoch": 77.65,
|
| 2374 |
+
"grad_norm": 0.605254054069519,
|
| 2375 |
+
"learning_rate": 6.723529411764706e-05,
|
| 2376 |
+
"loss": 0.3185,
|
| 2377 |
+
"step": 1320
|
| 2378 |
+
},
|
| 2379 |
+
{
|
| 2380 |
+
"epoch": 77.65,
|
| 2381 |
+
"eval_loss": 0.28241264820098877,
|
| 2382 |
+
"eval_runtime": 1.9624,
|
| 2383 |
+
"eval_samples_per_second": 68.285,
|
| 2384 |
+
"eval_steps_per_second": 8.663,
|
| 2385 |
+
"step": 1320
|
| 2386 |
+
},
|
| 2387 |
+
{
|
| 2388 |
+
"epoch": 77.94,
|
| 2389 |
+
"grad_norm": 0.5630979537963867,
|
| 2390 |
+
"learning_rate": 6.635294117647059e-05,
|
| 2391 |
+
"loss": 0.3031,
|
| 2392 |
+
"step": 1325
|
| 2393 |
+
},
|
| 2394 |
+
{
|
| 2395 |
+
"epoch": 78.24,
|
| 2396 |
+
"grad_norm": 0.6344974637031555,
|
| 2397 |
+
"learning_rate": 6.547058823529411e-05,
|
| 2398 |
+
"loss": 0.2751,
|
| 2399 |
+
"step": 1330
|
| 2400 |
+
},
|
| 2401 |
+
{
|
| 2402 |
+
"epoch": 78.53,
|
| 2403 |
+
"grad_norm": 0.6511242985725403,
|
| 2404 |
+
"learning_rate": 6.458823529411764e-05,
|
| 2405 |
+
"loss": 0.2912,
|
| 2406 |
+
"step": 1335
|
| 2407 |
+
},
|
| 2408 |
+
{
|
| 2409 |
+
"epoch": 78.82,
|
| 2410 |
+
"grad_norm": 0.6341962814331055,
|
| 2411 |
+
"learning_rate": 6.370588235294117e-05,
|
| 2412 |
+
"loss": 0.3045,
|
| 2413 |
+
"step": 1340
|
| 2414 |
+
},
|
| 2415 |
+
{
|
| 2416 |
+
"epoch": 78.82,
|
| 2417 |
+
"eval_loss": 0.2820163369178772,
|
| 2418 |
+
"eval_runtime": 1.9645,
|
| 2419 |
+
"eval_samples_per_second": 68.21,
|
| 2420 |
+
"eval_steps_per_second": 8.653,
|
| 2421 |
+
"step": 1340
|
| 2422 |
+
},
|
| 2423 |
+
{
|
| 2424 |
+
"epoch": 79.12,
|
| 2425 |
+
"grad_norm": 0.4710829257965088,
|
| 2426 |
+
"learning_rate": 6.28235294117647e-05,
|
| 2427 |
+
"loss": 0.2864,
|
| 2428 |
+
"step": 1345
|
| 2429 |
+
},
|
| 2430 |
+
{
|
| 2431 |
+
"epoch": 79.41,
|
| 2432 |
+
"grad_norm": 0.5435501933097839,
|
| 2433 |
+
"learning_rate": 6.194117647058823e-05,
|
| 2434 |
+
"loss": 0.2911,
|
| 2435 |
+
"step": 1350
|
| 2436 |
+
},
|
| 2437 |
+
{
|
| 2438 |
+
"epoch": 79.71,
|
| 2439 |
+
"grad_norm": 0.6263275146484375,
|
| 2440 |
+
"learning_rate": 6.105882352941176e-05,
|
| 2441 |
+
"loss": 0.2754,
|
| 2442 |
+
"step": 1355
|
| 2443 |
+
},
|
| 2444 |
+
{
|
| 2445 |
+
"epoch": 80.0,
|
| 2446 |
+
"grad_norm": 0.9273045659065247,
|
| 2447 |
+
"learning_rate": 6.017647058823529e-05,
|
| 2448 |
+
"loss": 0.3234,
|
| 2449 |
+
"step": 1360
|
| 2450 |
+
},
|
| 2451 |
+
{
|
| 2452 |
+
"epoch": 80.0,
|
| 2453 |
+
"eval_loss": 0.2816248834133148,
|
| 2454 |
+
"eval_runtime": 1.9628,
|
| 2455 |
+
"eval_samples_per_second": 68.269,
|
| 2456 |
+
"eval_steps_per_second": 8.661,
|
| 2457 |
+
"step": 1360
|
| 2458 |
+
},
|
| 2459 |
+
{
|
| 2460 |
+
"epoch": 80.29,
|
| 2461 |
+
"grad_norm": 0.5134958624839783,
|
| 2462 |
+
"learning_rate": 5.9294117647058814e-05,
|
| 2463 |
+
"loss": 0.2779,
|
| 2464 |
+
"step": 1365
|
| 2465 |
+
},
|
| 2466 |
+
{
|
| 2467 |
+
"epoch": 80.59,
|
| 2468 |
+
"grad_norm": 0.5631394982337952,
|
| 2469 |
+
"learning_rate": 5.8411764705882344e-05,
|
| 2470 |
+
"loss": 0.292,
|
| 2471 |
+
"step": 1370
|
| 2472 |
+
},
|
| 2473 |
+
{
|
| 2474 |
+
"epoch": 80.88,
|
| 2475 |
+
"grad_norm": 0.670920729637146,
|
| 2476 |
+
"learning_rate": 5.752941176470588e-05,
|
| 2477 |
+
"loss": 0.286,
|
| 2478 |
+
"step": 1375
|
| 2479 |
+
},
|
| 2480 |
+
{
|
| 2481 |
+
"epoch": 81.18,
|
| 2482 |
+
"grad_norm": 0.5817293524742126,
|
| 2483 |
+
"learning_rate": 5.66470588235294e-05,
|
| 2484 |
+
"loss": 0.307,
|
| 2485 |
+
"step": 1380
|
| 2486 |
+
},
|
| 2487 |
+
{
|
| 2488 |
+
"epoch": 81.18,
|
| 2489 |
+
"eval_loss": 0.2816360890865326,
|
| 2490 |
+
"eval_runtime": 1.9645,
|
| 2491 |
+
"eval_samples_per_second": 68.21,
|
| 2492 |
+
"eval_steps_per_second": 8.654,
|
| 2493 |
+
"step": 1380
|
| 2494 |
+
},
|
| 2495 |
+
{
|
| 2496 |
+
"epoch": 81.47,
|
| 2497 |
+
"grad_norm": 0.6460394859313965,
|
| 2498 |
+
"learning_rate": 5.576470588235294e-05,
|
| 2499 |
+
"loss": 0.2795,
|
| 2500 |
+
"step": 1385
|
| 2501 |
+
},
|
| 2502 |
+
{
|
| 2503 |
+
"epoch": 81.76,
|
| 2504 |
+
"grad_norm": 0.6339797377586365,
|
| 2505 |
+
"learning_rate": 5.488235294117647e-05,
|
| 2506 |
+
"loss": 0.2908,
|
| 2507 |
+
"step": 1390
|
| 2508 |
+
},
|
| 2509 |
+
{
|
| 2510 |
+
"epoch": 82.06,
|
| 2511 |
+
"grad_norm": 0.5646565556526184,
|
| 2512 |
+
"learning_rate": 5.399999999999999e-05,
|
| 2513 |
+
"loss": 0.2969,
|
| 2514 |
+
"step": 1395
|
| 2515 |
+
},
|
| 2516 |
+
{
|
| 2517 |
+
"epoch": 82.35,
|
| 2518 |
+
"grad_norm": 0.6593837738037109,
|
| 2519 |
+
"learning_rate": 5.311764705882353e-05,
|
| 2520 |
+
"loss": 0.285,
|
| 2521 |
+
"step": 1400
|
| 2522 |
+
},
|
| 2523 |
+
{
|
| 2524 |
+
"epoch": 82.35,
|
| 2525 |
+
"eval_loss": 0.2816665470600128,
|
| 2526 |
+
"eval_runtime": 1.963,
|
| 2527 |
+
"eval_samples_per_second": 68.264,
|
| 2528 |
+
"eval_steps_per_second": 8.66,
|
| 2529 |
+
"step": 1400
|
| 2530 |
+
},
|
| 2531 |
+
{
|
| 2532 |
+
"epoch": 82.65,
|
| 2533 |
+
"grad_norm": 0.5819811820983887,
|
| 2534 |
+
"learning_rate": 5.223529411764705e-05,
|
| 2535 |
+
"loss": 0.2993,
|
| 2536 |
+
"step": 1405
|
| 2537 |
+
},
|
| 2538 |
+
{
|
| 2539 |
+
"epoch": 82.94,
|
| 2540 |
+
"grad_norm": 0.7297362089157104,
|
| 2541 |
+
"learning_rate": 5.135294117647058e-05,
|
| 2542 |
+
"loss": 0.2933,
|
| 2543 |
+
"step": 1410
|
| 2544 |
+
},
|
| 2545 |
+
{
|
| 2546 |
+
"epoch": 83.24,
|
| 2547 |
+
"grad_norm": 0.5894657969474792,
|
| 2548 |
+
"learning_rate": 5.0470588235294116e-05,
|
| 2549 |
+
"loss": 0.2741,
|
| 2550 |
+
"step": 1415
|
| 2551 |
+
},
|
| 2552 |
+
{
|
| 2553 |
+
"epoch": 83.53,
|
| 2554 |
+
"grad_norm": 0.6407579183578491,
|
| 2555 |
+
"learning_rate": 4.958823529411764e-05,
|
| 2556 |
+
"loss": 0.284,
|
| 2557 |
+
"step": 1420
|
| 2558 |
+
},
|
| 2559 |
+
{
|
| 2560 |
+
"epoch": 83.53,
|
| 2561 |
+
"eval_loss": 0.2816457152366638,
|
| 2562 |
+
"eval_runtime": 1.9634,
|
| 2563 |
+
"eval_samples_per_second": 68.249,
|
| 2564 |
+
"eval_steps_per_second": 8.658,
|
| 2565 |
+
"step": 1420
|
| 2566 |
+
},
|
| 2567 |
+
{
|
| 2568 |
+
"epoch": 83.82,
|
| 2569 |
+
"grad_norm": 0.6652833223342896,
|
| 2570 |
+
"learning_rate": 4.8705882352941175e-05,
|
| 2571 |
+
"loss": 0.2956,
|
| 2572 |
+
"step": 1425
|
| 2573 |
+
},
|
| 2574 |
+
{
|
| 2575 |
+
"epoch": 84.12,
|
| 2576 |
+
"grad_norm": 0.6132673025131226,
|
| 2577 |
+
"learning_rate": 4.7823529411764704e-05,
|
| 2578 |
+
"loss": 0.3118,
|
| 2579 |
+
"step": 1430
|
| 2580 |
+
},
|
| 2581 |
+
{
|
| 2582 |
+
"epoch": 84.41,
|
| 2583 |
+
"grad_norm": 0.6194684505462646,
|
| 2584 |
+
"learning_rate": 4.694117647058823e-05,
|
| 2585 |
+
"loss": 0.2974,
|
| 2586 |
+
"step": 1435
|
| 2587 |
+
},
|
| 2588 |
+
{
|
| 2589 |
+
"epoch": 84.71,
|
| 2590 |
+
"grad_norm": 0.6432455778121948,
|
| 2591 |
+
"learning_rate": 4.605882352941176e-05,
|
| 2592 |
+
"loss": 0.284,
|
| 2593 |
+
"step": 1440
|
| 2594 |
+
},
|
| 2595 |
+
{
|
| 2596 |
+
"epoch": 84.71,
|
| 2597 |
+
"eval_loss": 0.2816688120365143,
|
| 2598 |
+
"eval_runtime": 1.9635,
|
| 2599 |
+
"eval_samples_per_second": 68.245,
|
| 2600 |
+
"eval_steps_per_second": 8.658,
|
| 2601 |
+
"step": 1440
|
| 2602 |
+
},
|
| 2603 |
+
{
|
| 2604 |
+
"epoch": 85.0,
|
| 2605 |
+
"grad_norm": 0.6287035942077637,
|
| 2606 |
+
"learning_rate": 4.5176470588235286e-05,
|
| 2607 |
+
"loss": 0.2954,
|
| 2608 |
+
"step": 1445
|
| 2609 |
+
},
|
| 2610 |
+
{
|
| 2611 |
+
"epoch": 85.29,
|
| 2612 |
+
"grad_norm": 0.6195583939552307,
|
| 2613 |
+
"learning_rate": 4.4294117647058816e-05,
|
| 2614 |
+
"loss": 0.2924,
|
| 2615 |
+
"step": 1450
|
| 2616 |
+
},
|
| 2617 |
+
{
|
| 2618 |
+
"epoch": 85.59,
|
| 2619 |
+
"grad_norm": 0.4889207184314728,
|
| 2620 |
+
"learning_rate": 4.341176470588235e-05,
|
| 2621 |
+
"loss": 0.2876,
|
| 2622 |
+
"step": 1455
|
| 2623 |
+
},
|
| 2624 |
+
{
|
| 2625 |
+
"epoch": 85.88,
|
| 2626 |
+
"grad_norm": 0.5067662596702576,
|
| 2627 |
+
"learning_rate": 4.2529411764705875e-05,
|
| 2628 |
+
"loss": 0.2907,
|
| 2629 |
+
"step": 1460
|
| 2630 |
+
},
|
| 2631 |
+
{
|
| 2632 |
+
"epoch": 85.88,
|
| 2633 |
+
"eval_loss": 0.28165140748023987,
|
| 2634 |
+
"eval_runtime": 1.9945,
|
| 2635 |
+
"eval_samples_per_second": 67.184,
|
| 2636 |
+
"eval_steps_per_second": 8.523,
|
| 2637 |
+
"step": 1460
|
| 2638 |
+
},
|
| 2639 |
+
{
|
| 2640 |
+
"epoch": 86.18,
|
| 2641 |
+
"grad_norm": 0.585261881351471,
|
| 2642 |
+
"learning_rate": 4.164705882352941e-05,
|
| 2643 |
+
"loss": 0.2819,
|
| 2644 |
+
"step": 1465
|
| 2645 |
+
},
|
| 2646 |
+
{
|
| 2647 |
+
"epoch": 86.47,
|
| 2648 |
+
"grad_norm": 0.6940666437149048,
|
| 2649 |
+
"learning_rate": 4.076470588235294e-05,
|
| 2650 |
+
"loss": 0.2871,
|
| 2651 |
+
"step": 1470
|
| 2652 |
+
},
|
| 2653 |
+
{
|
| 2654 |
+
"epoch": 86.76,
|
| 2655 |
+
"grad_norm": 0.6339988112449646,
|
| 2656 |
+
"learning_rate": 3.988235294117646e-05,
|
| 2657 |
+
"loss": 0.3024,
|
| 2658 |
+
"step": 1475
|
| 2659 |
+
},
|
| 2660 |
+
{
|
| 2661 |
+
"epoch": 87.06,
|
| 2662 |
+
"grad_norm": 0.6392388343811035,
|
| 2663 |
+
"learning_rate": 3.9e-05,
|
| 2664 |
+
"loss": 0.2772,
|
| 2665 |
+
"step": 1480
|
| 2666 |
+
},
|
| 2667 |
+
{
|
| 2668 |
+
"epoch": 87.06,
|
| 2669 |
+
"eval_loss": 0.2811833918094635,
|
| 2670 |
+
"eval_runtime": 1.9644,
|
| 2671 |
+
"eval_samples_per_second": 68.214,
|
| 2672 |
+
"eval_steps_per_second": 8.654,
|
| 2673 |
+
"step": 1480
|
| 2674 |
+
},
|
| 2675 |
+
{
|
| 2676 |
+
"epoch": 87.35,
|
| 2677 |
+
"grad_norm": 0.7161315083503723,
|
| 2678 |
+
"learning_rate": 3.811764705882352e-05,
|
| 2679 |
+
"loss": 0.2638,
|
| 2680 |
+
"step": 1485
|
| 2681 |
+
},
|
| 2682 |
+
{
|
| 2683 |
+
"epoch": 87.65,
|
| 2684 |
+
"grad_norm": 0.7191869020462036,
|
| 2685 |
+
"learning_rate": 3.723529411764705e-05,
|
| 2686 |
+
"loss": 0.3073,
|
| 2687 |
+
"step": 1490
|
| 2688 |
+
},
|
| 2689 |
+
{
|
| 2690 |
+
"epoch": 87.94,
|
| 2691 |
+
"grad_norm": 0.5518560409545898,
|
| 2692 |
+
"learning_rate": 3.635294117647058e-05,
|
| 2693 |
+
"loss": 0.3008,
|
| 2694 |
+
"step": 1495
|
| 2695 |
+
},
|
| 2696 |
+
{
|
| 2697 |
+
"epoch": 88.24,
|
| 2698 |
+
"grad_norm": 0.5638569593429565,
|
| 2699 |
+
"learning_rate": 3.547058823529412e-05,
|
| 2700 |
+
"loss": 0.2835,
|
| 2701 |
+
"step": 1500
|
| 2702 |
+
},
|
| 2703 |
+
{
|
| 2704 |
+
"epoch": 88.24,
|
| 2705 |
+
"eval_loss": 0.281184583902359,
|
| 2706 |
+
"eval_runtime": 1.9648,
|
| 2707 |
+
"eval_samples_per_second": 68.199,
|
| 2708 |
+
"eval_steps_per_second": 8.652,
|
| 2709 |
+
"step": 1500
|
| 2710 |
+
},
|
| 2711 |
+
{
|
| 2712 |
+
"epoch": 88.53,
|
| 2713 |
+
"grad_norm": 0.6046936511993408,
|
| 2714 |
+
"learning_rate": 3.458823529411765e-05,
|
| 2715 |
+
"loss": 0.3009,
|
| 2716 |
+
"step": 1505
|
| 2717 |
+
},
|
| 2718 |
+
{
|
| 2719 |
+
"epoch": 88.82,
|
| 2720 |
+
"grad_norm": 0.6414223313331604,
|
| 2721 |
+
"learning_rate": 3.3705882352941176e-05,
|
| 2722 |
+
"loss": 0.2982,
|
| 2723 |
+
"step": 1510
|
| 2724 |
+
},
|
| 2725 |
+
{
|
| 2726 |
+
"epoch": 89.12,
|
| 2727 |
+
"grad_norm": 0.6182020306587219,
|
| 2728 |
+
"learning_rate": 3.28235294117647e-05,
|
| 2729 |
+
"loss": 0.2785,
|
| 2730 |
+
"step": 1515
|
| 2731 |
+
},
|
| 2732 |
+
{
|
| 2733 |
+
"epoch": 89.41,
|
| 2734 |
+
"grad_norm": 0.5438305139541626,
|
| 2735 |
+
"learning_rate": 3.1941176470588235e-05,
|
| 2736 |
+
"loss": 0.2851,
|
| 2737 |
+
"step": 1520
|
| 2738 |
+
},
|
| 2739 |
+
{
|
| 2740 |
+
"epoch": 89.41,
|
| 2741 |
+
"eval_loss": 0.28117018938064575,
|
| 2742 |
+
"eval_runtime": 1.9627,
|
| 2743 |
+
"eval_samples_per_second": 68.272,
|
| 2744 |
+
"eval_steps_per_second": 8.661,
|
| 2745 |
+
"step": 1520
|
| 2746 |
+
},
|
| 2747 |
+
{
|
| 2748 |
+
"epoch": 89.71,
|
| 2749 |
+
"grad_norm": 0.7188280820846558,
|
| 2750 |
+
"learning_rate": 3.1058823529411765e-05,
|
| 2751 |
+
"loss": 0.3077,
|
| 2752 |
+
"step": 1525
|
| 2753 |
+
},
|
| 2754 |
+
{
|
| 2755 |
+
"epoch": 90.0,
|
| 2756 |
+
"grad_norm": 1.365729570388794,
|
| 2757 |
+
"learning_rate": 3.017647058823529e-05,
|
| 2758 |
+
"loss": 0.281,
|
| 2759 |
+
"step": 1530
|
| 2760 |
+
},
|
| 2761 |
+
{
|
| 2762 |
+
"epoch": 90.29,
|
| 2763 |
+
"grad_norm": 0.5949041843414307,
|
| 2764 |
+
"learning_rate": 2.929411764705882e-05,
|
| 2765 |
+
"loss": 0.2812,
|
| 2766 |
+
"step": 1535
|
| 2767 |
+
},
|
| 2768 |
+
{
|
| 2769 |
+
"epoch": 90.59,
|
| 2770 |
+
"grad_norm": 0.6256306767463684,
|
| 2771 |
+
"learning_rate": 2.8411764705882353e-05,
|
| 2772 |
+
"loss": 0.2894,
|
| 2773 |
+
"step": 1540
|
| 2774 |
+
},
|
| 2775 |
+
{
|
| 2776 |
+
"epoch": 90.59,
|
| 2777 |
+
"eval_loss": 0.28130242228507996,
|
| 2778 |
+
"eval_runtime": 1.9709,
|
| 2779 |
+
"eval_samples_per_second": 67.99,
|
| 2780 |
+
"eval_steps_per_second": 8.626,
|
| 2781 |
+
"step": 1540
|
| 2782 |
+
},
|
| 2783 |
+
{
|
| 2784 |
+
"epoch": 90.88,
|
| 2785 |
+
"grad_norm": 0.6415876150131226,
|
| 2786 |
+
"learning_rate": 2.752941176470588e-05,
|
| 2787 |
+
"loss": 0.2947,
|
| 2788 |
+
"step": 1545
|
| 2789 |
+
},
|
| 2790 |
+
{
|
| 2791 |
+
"epoch": 91.18,
|
| 2792 |
+
"grad_norm": 0.6539847254753113,
|
| 2793 |
+
"learning_rate": 2.664705882352941e-05,
|
| 2794 |
+
"loss": 0.3072,
|
| 2795 |
+
"step": 1550
|
| 2796 |
+
},
|
| 2797 |
+
{
|
| 2798 |
+
"epoch": 91.47,
|
| 2799 |
+
"grad_norm": 0.5993030071258545,
|
| 2800 |
+
"learning_rate": 2.5764705882352938e-05,
|
| 2801 |
+
"loss": 0.2862,
|
| 2802 |
+
"step": 1555
|
| 2803 |
+
},
|
| 2804 |
+
{
|
| 2805 |
+
"epoch": 91.76,
|
| 2806 |
+
"grad_norm": 0.8233740329742432,
|
| 2807 |
+
"learning_rate": 2.488235294117647e-05,
|
| 2808 |
+
"loss": 0.2866,
|
| 2809 |
+
"step": 1560
|
| 2810 |
+
},
|
| 2811 |
+
{
|
| 2812 |
+
"epoch": 91.76,
|
| 2813 |
+
"eval_loss": 0.2810344398021698,
|
| 2814 |
+
"eval_runtime": 1.9637,
|
| 2815 |
+
"eval_samples_per_second": 68.24,
|
| 2816 |
+
"eval_steps_per_second": 8.657,
|
| 2817 |
+
"step": 1560
|
| 2818 |
+
},
|
| 2819 |
+
{
|
| 2820 |
+
"epoch": 92.06,
|
| 2821 |
+
"grad_norm": 0.7091302871704102,
|
| 2822 |
+
"learning_rate": 2.3999999999999997e-05,
|
| 2823 |
+
"loss": 0.2725,
|
| 2824 |
+
"step": 1565
|
| 2825 |
+
},
|
| 2826 |
+
{
|
| 2827 |
+
"epoch": 92.35,
|
| 2828 |
+
"grad_norm": 0.6882550120353699,
|
| 2829 |
+
"learning_rate": 2.3117647058823527e-05,
|
| 2830 |
+
"loss": 0.2637,
|
| 2831 |
+
"step": 1570
|
| 2832 |
+
},
|
| 2833 |
+
{
|
| 2834 |
+
"epoch": 92.65,
|
| 2835 |
+
"grad_norm": 0.7456904649734497,
|
| 2836 |
+
"learning_rate": 2.2235294117647056e-05,
|
| 2837 |
+
"loss": 0.3136,
|
| 2838 |
+
"step": 1575
|
| 2839 |
+
},
|
| 2840 |
+
{
|
| 2841 |
+
"epoch": 92.94,
|
| 2842 |
+
"grad_norm": 0.7350043058395386,
|
| 2843 |
+
"learning_rate": 2.135294117647059e-05,
|
| 2844 |
+
"loss": 0.2989,
|
| 2845 |
+
"step": 1580
|
| 2846 |
+
},
|
| 2847 |
+
{
|
| 2848 |
+
"epoch": 92.94,
|
| 2849 |
+
"eval_loss": 0.2810307443141937,
|
| 2850 |
+
"eval_runtime": 1.9647,
|
| 2851 |
+
"eval_samples_per_second": 68.205,
|
| 2852 |
+
"eval_steps_per_second": 8.653,
|
| 2853 |
+
"step": 1580
|
| 2854 |
+
},
|
| 2855 |
+
{
|
| 2856 |
+
"epoch": 93.24,
|
| 2857 |
+
"grad_norm": 0.6609780192375183,
|
| 2858 |
+
"learning_rate": 2.0470588235294115e-05,
|
| 2859 |
+
"loss": 0.2661,
|
| 2860 |
+
"step": 1585
|
| 2861 |
+
},
|
| 2862 |
+
{
|
| 2863 |
+
"epoch": 93.53,
|
| 2864 |
+
"grad_norm": 0.5839440822601318,
|
| 2865 |
+
"learning_rate": 1.9588235294117645e-05,
|
| 2866 |
+
"loss": 0.2879,
|
| 2867 |
+
"step": 1590
|
| 2868 |
+
},
|
| 2869 |
+
{
|
| 2870 |
+
"epoch": 93.82,
|
| 2871 |
+
"grad_norm": 0.7363938689231873,
|
| 2872 |
+
"learning_rate": 1.8705882352941174e-05,
|
| 2873 |
+
"loss": 0.2768,
|
| 2874 |
+
"step": 1595
|
| 2875 |
+
},
|
| 2876 |
+
{
|
| 2877 |
+
"epoch": 94.12,
|
| 2878 |
+
"grad_norm": 0.6621124148368835,
|
| 2879 |
+
"learning_rate": 1.7823529411764704e-05,
|
| 2880 |
+
"loss": 0.2824,
|
| 2881 |
+
"step": 1600
|
| 2882 |
+
},
|
| 2883 |
+
{
|
| 2884 |
+
"epoch": 94.12,
|
| 2885 |
+
"eval_loss": 0.28088855743408203,
|
| 2886 |
+
"eval_runtime": 1.9626,
|
| 2887 |
+
"eval_samples_per_second": 68.278,
|
| 2888 |
+
"eval_steps_per_second": 8.662,
|
| 2889 |
+
"step": 1600
|
| 2890 |
+
},
|
| 2891 |
+
{
|
| 2892 |
+
"epoch": 94.41,
|
| 2893 |
+
"grad_norm": 0.6326584219932556,
|
| 2894 |
+
"learning_rate": 1.6941176470588233e-05,
|
| 2895 |
+
"loss": 0.2847,
|
| 2896 |
+
"step": 1605
|
| 2897 |
+
},
|
| 2898 |
+
{
|
| 2899 |
+
"epoch": 94.71,
|
| 2900 |
+
"grad_norm": 0.5328549742698669,
|
| 2901 |
+
"learning_rate": 1.6058823529411763e-05,
|
| 2902 |
+
"loss": 0.2957,
|
| 2903 |
+
"step": 1610
|
| 2904 |
+
},
|
| 2905 |
+
{
|
| 2906 |
+
"epoch": 95.0,
|
| 2907 |
+
"grad_norm": 0.6264612078666687,
|
| 2908 |
+
"learning_rate": 1.5176470588235294e-05,
|
| 2909 |
+
"loss": 0.2832,
|
| 2910 |
+
"step": 1615
|
| 2911 |
+
},
|
| 2912 |
+
{
|
| 2913 |
+
"epoch": 95.29,
|
| 2914 |
+
"grad_norm": 0.5468940734863281,
|
| 2915 |
+
"learning_rate": 1.4294117647058822e-05,
|
| 2916 |
+
"loss": 0.2884,
|
| 2917 |
+
"step": 1620
|
| 2918 |
+
},
|
| 2919 |
+
{
|
| 2920 |
+
"epoch": 95.29,
|
| 2921 |
+
"eval_loss": 0.28081610798835754,
|
| 2922 |
+
"eval_runtime": 1.9624,
|
| 2923 |
+
"eval_samples_per_second": 68.284,
|
| 2924 |
+
"eval_steps_per_second": 8.663,
|
| 2925 |
+
"step": 1620
|
| 2926 |
+
},
|
| 2927 |
+
{
|
| 2928 |
+
"epoch": 95.59,
|
| 2929 |
+
"grad_norm": 0.6490024924278259,
|
| 2930 |
+
"learning_rate": 1.3411764705882353e-05,
|
| 2931 |
+
"loss": 0.2933,
|
| 2932 |
+
"step": 1625
|
| 2933 |
+
},
|
| 2934 |
+
{
|
| 2935 |
+
"epoch": 95.88,
|
| 2936 |
+
"grad_norm": 0.6643602252006531,
|
| 2937 |
+
"learning_rate": 1.252941176470588e-05,
|
| 2938 |
+
"loss": 0.2778,
|
| 2939 |
+
"step": 1630
|
| 2940 |
+
},
|
| 2941 |
+
{
|
| 2942 |
+
"epoch": 96.18,
|
| 2943 |
+
"grad_norm": 0.6024314761161804,
|
| 2944 |
+
"learning_rate": 1.1647058823529412e-05,
|
| 2945 |
+
"loss": 0.2764,
|
| 2946 |
+
"step": 1635
|
| 2947 |
+
},
|
| 2948 |
+
{
|
| 2949 |
+
"epoch": 96.47,
|
| 2950 |
+
"grad_norm": 0.765645444393158,
|
| 2951 |
+
"learning_rate": 1.076470588235294e-05,
|
| 2952 |
+
"loss": 0.2793,
|
| 2953 |
+
"step": 1640
|
| 2954 |
+
},
|
| 2955 |
+
{
|
| 2956 |
+
"epoch": 96.47,
|
| 2957 |
+
"eval_loss": 0.2808389365673065,
|
| 2958 |
+
"eval_runtime": 1.9615,
|
| 2959 |
+
"eval_samples_per_second": 68.314,
|
| 2960 |
+
"eval_steps_per_second": 8.667,
|
| 2961 |
+
"step": 1640
|
| 2962 |
+
},
|
| 2963 |
+
{
|
| 2964 |
+
"epoch": 96.76,
|
| 2965 |
+
"grad_norm": 0.572972297668457,
|
| 2966 |
+
"learning_rate": 9.88235294117647e-06,
|
| 2967 |
+
"loss": 0.2921,
|
| 2968 |
+
"step": 1645
|
| 2969 |
+
},
|
| 2970 |
+
{
|
| 2971 |
+
"epoch": 97.06,
|
| 2972 |
+
"grad_norm": 0.5067675113677979,
|
| 2973 |
+
"learning_rate": 8.999999999999999e-06,
|
| 2974 |
+
"loss": 0.2803,
|
| 2975 |
+
"step": 1650
|
| 2976 |
+
},
|
| 2977 |
+
{
|
| 2978 |
+
"epoch": 97.35,
|
| 2979 |
+
"grad_norm": 0.5740128755569458,
|
| 2980 |
+
"learning_rate": 8.117647058823528e-06,
|
| 2981 |
+
"loss": 0.2788,
|
| 2982 |
+
"step": 1655
|
| 2983 |
+
},
|
| 2984 |
+
{
|
| 2985 |
+
"epoch": 97.65,
|
| 2986 |
+
"grad_norm": 0.8507512211799622,
|
| 2987 |
+
"learning_rate": 7.2352941176470575e-06,
|
| 2988 |
+
"loss": 0.2935,
|
| 2989 |
+
"step": 1660
|
| 2990 |
+
},
|
| 2991 |
+
{
|
| 2992 |
+
"epoch": 97.65,
|
| 2993 |
+
"eval_loss": 0.28082287311553955,
|
| 2994 |
+
"eval_runtime": 1.9624,
|
| 2995 |
+
"eval_samples_per_second": 68.284,
|
| 2996 |
+
"eval_steps_per_second": 8.663,
|
| 2997 |
+
"step": 1660
|
| 2998 |
+
},
|
| 2999 |
+
{
|
| 3000 |
+
"epoch": 97.94,
|
| 3001 |
+
"grad_norm": 0.6840553879737854,
|
| 3002 |
+
"learning_rate": 6.352941176470587e-06,
|
| 3003 |
+
"loss": 0.2907,
|
| 3004 |
+
"step": 1665
|
| 3005 |
+
},
|
| 3006 |
+
{
|
| 3007 |
+
"epoch": 98.24,
|
| 3008 |
+
"grad_norm": 0.6912717819213867,
|
| 3009 |
+
"learning_rate": 5.4705882352941165e-06,
|
| 3010 |
+
"loss": 0.3077,
|
| 3011 |
+
"step": 1670
|
| 3012 |
+
},
|
| 3013 |
+
{
|
| 3014 |
+
"epoch": 98.53,
|
| 3015 |
+
"grad_norm": 0.684217631816864,
|
| 3016 |
+
"learning_rate": 4.588235294117647e-06,
|
| 3017 |
+
"loss": 0.2764,
|
| 3018 |
+
"step": 1675
|
| 3019 |
+
},
|
| 3020 |
+
{
|
| 3021 |
+
"epoch": 98.82,
|
| 3022 |
+
"grad_norm": 0.5906203985214233,
|
| 3023 |
+
"learning_rate": 3.705882352941176e-06,
|
| 3024 |
+
"loss": 0.2838,
|
| 3025 |
+
"step": 1680
|
| 3026 |
+
},
|
| 3027 |
+
{
|
| 3028 |
+
"epoch": 98.82,
|
| 3029 |
+
"eval_loss": 0.28078943490982056,
|
| 3030 |
+
"eval_runtime": 1.9629,
|
| 3031 |
+
"eval_samples_per_second": 68.268,
|
| 3032 |
+
"eval_steps_per_second": 8.661,
|
| 3033 |
+
"step": 1680
|
| 3034 |
+
},
|
| 3035 |
+
{
|
| 3036 |
+
"epoch": 99.12,
|
| 3037 |
+
"grad_norm": 0.506241500377655,
|
| 3038 |
+
"learning_rate": 2.8235294117647054e-06,
|
| 3039 |
+
"loss": 0.2696,
|
| 3040 |
+
"step": 1685
|
| 3041 |
+
},
|
| 3042 |
+
{
|
| 3043 |
+
"epoch": 99.41,
|
| 3044 |
+
"grad_norm": 0.689836859703064,
|
| 3045 |
+
"learning_rate": 1.9411764705882353e-06,
|
| 3046 |
+
"loss": 0.2888,
|
| 3047 |
+
"step": 1690
|
| 3048 |
+
},
|
| 3049 |
+
{
|
| 3050 |
+
"epoch": 99.71,
|
| 3051 |
+
"grad_norm": 0.5296027064323425,
|
| 3052 |
+
"learning_rate": 1.0588235294117646e-06,
|
| 3053 |
+
"loss": 0.2806,
|
| 3054 |
+
"step": 1695
|
| 3055 |
+
},
|
| 3056 |
+
{
|
| 3057 |
+
"epoch": 100.0,
|
| 3058 |
+
"grad_norm": 1.283803105354309,
|
| 3059 |
+
"learning_rate": 1.7647058823529409e-07,
|
| 3060 |
+
"loss": 0.2969,
|
| 3061 |
+
"step": 1700
|
| 3062 |
+
},
|
| 3063 |
+
{
|
| 3064 |
+
"epoch": 100.0,
|
| 3065 |
+
"eval_loss": 0.28079184889793396,
|
| 3066 |
+
"eval_runtime": 1.9638,
|
| 3067 |
+
"eval_samples_per_second": 68.236,
|
| 3068 |
+
"eval_steps_per_second": 8.657,
|
| 3069 |
+
"step": 1700
|
| 3070 |
+
}
|
| 3071 |
+
],
|
| 3072 |
+
"logging_steps": 5,
|
| 3073 |
+
"max_steps": 1700,
|
| 3074 |
+
"num_input_tokens_seen": 0,
|
| 3075 |
+
"num_train_epochs": 100,
|
| 3076 |
+
"save_steps": 20,
|
| 3077 |
+
"total_flos": 1.445927475412992e+16,
|
| 3078 |
+
"train_batch_size": 4,
|
| 3079 |
+
"trial_name": null,
|
| 3080 |
+
"trial_params": null
|
| 3081 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c83a51d9ec2ec085c2aa7cd8cbf648b98ae0bc6533f6d5798bcc49476c0360e3
|
| 3 |
+
size 5048
|