Upload 8 files
Browse files- README.md +202 -3
- adapter_config.json +31 -0
- adapter_model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +3021 -0
- training_args.bin +3 -0
README.md
CHANGED
|
@@ -1,3 +1,202 @@
|
|
| 1 |
-
---
|
| 2 |
-
|
| 3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
base_model: microsoft/phi-2
|
| 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 0.10.1.dev0
|
adapter_config.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": null,
|
| 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 |
+
"dense_4h_to_h",
|
| 24 |
+
"query_key_value",
|
| 25 |
+
"dense_h_to_4h",
|
| 26 |
+
"dense"
|
| 27 |
+
],
|
| 28 |
+
"task_type": "CAUSAL_LM",
|
| 29 |
+
"use_dora": false,
|
| 30 |
+
"use_rslora": false
|
| 31 |
+
}
|
adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bddb7168cd62f3b33982233d8a25c2861c656353ebbfa0959837e12ab1ac253b
|
| 3 |
+
size 89185944
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c1d8fcaf43c9e4f2341f79ae4dce9b599897e905f8ccf525e47ac594a388a50e
|
| 3 |
+
size 2698490
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5e48e61c75e8ef4ecbc3c1aacbe366224aec6950f62686870facf776eb5d9b7d
|
| 3 |
+
size 14244
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fdb95164c86164d783e82ee9039d2c512dbb0a4c9278bc83337e1e65eef0bc86
|
| 3 |
+
size 1064
|
trainer_state.json
ADDED
|
@@ -0,0 +1,3021 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 3.510607957839966,
|
| 3 |
+
"best_model_checkpoint": "./Phi-2_PT_QA_1/checkpoint-200",
|
| 4 |
+
"epoch": 0.0022854530910753055,
|
| 5 |
+
"eval_steps": 1,
|
| 6 |
+
"global_step": 200,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 1.1427265455376528e-05,
|
| 13 |
+
"grad_norm": 0.7554183006286621,
|
| 14 |
+
"learning_rate": 2.5e-05,
|
| 15 |
+
"loss": 7.6787,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 1.1427265455376528e-05,
|
| 20 |
+
"eval_loss": 7.217936038970947,
|
| 21 |
+
"eval_runtime": 3184.807,
|
| 22 |
+
"eval_samples_per_second": 1.727,
|
| 23 |
+
"eval_steps_per_second": 1.727,
|
| 24 |
+
"step": 1
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 2.2854530910753055e-05,
|
| 28 |
+
"grad_norm": 0.809639573097229,
|
| 29 |
+
"learning_rate": 2.4874371859296484e-05,
|
| 30 |
+
"loss": 7.5645,
|
| 31 |
+
"step": 2
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 2.2854530910753055e-05,
|
| 35 |
+
"eval_loss": 7.216185569763184,
|
| 36 |
+
"eval_runtime": 3195.682,
|
| 37 |
+
"eval_samples_per_second": 1.721,
|
| 38 |
+
"eval_steps_per_second": 1.721,
|
| 39 |
+
"step": 2
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 3.428179636612959e-05,
|
| 43 |
+
"grad_norm": 0.5419557094573975,
|
| 44 |
+
"learning_rate": 2.4748743718592964e-05,
|
| 45 |
+
"loss": 5.6844,
|
| 46 |
+
"step": 3
|
| 47 |
+
},
|
| 48 |
+
{
|
| 49 |
+
"epoch": 3.428179636612959e-05,
|
| 50 |
+
"eval_loss": 7.211589336395264,
|
| 51 |
+
"eval_runtime": 3196.3014,
|
| 52 |
+
"eval_samples_per_second": 1.721,
|
| 53 |
+
"eval_steps_per_second": 1.721,
|
| 54 |
+
"step": 3
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 4.570906182150611e-05,
|
| 58 |
+
"grad_norm": 0.6964669823646545,
|
| 59 |
+
"learning_rate": 2.462311557788945e-05,
|
| 60 |
+
"loss": 6.8741,
|
| 61 |
+
"step": 4
|
| 62 |
+
},
|
| 63 |
+
{
|
| 64 |
+
"epoch": 4.570906182150611e-05,
|
| 65 |
+
"eval_loss": 7.204798221588135,
|
| 66 |
+
"eval_runtime": 3194.9301,
|
| 67 |
+
"eval_samples_per_second": 1.721,
|
| 68 |
+
"eval_steps_per_second": 1.721,
|
| 69 |
+
"step": 4
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 5.713632727688264e-05,
|
| 73 |
+
"grad_norm": 0.670452356338501,
|
| 74 |
+
"learning_rate": 2.449748743718593e-05,
|
| 75 |
+
"loss": 6.6605,
|
| 76 |
+
"step": 5
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"epoch": 5.713632727688264e-05,
|
| 80 |
+
"eval_loss": 7.197990894317627,
|
| 81 |
+
"eval_runtime": 3194.2197,
|
| 82 |
+
"eval_samples_per_second": 1.722,
|
| 83 |
+
"eval_steps_per_second": 1.722,
|
| 84 |
+
"step": 5
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 6.856359273225918e-05,
|
| 88 |
+
"grad_norm": 0.8575164675712585,
|
| 89 |
+
"learning_rate": 2.4371859296482413e-05,
|
| 90 |
+
"loss": 8.0797,
|
| 91 |
+
"step": 6
|
| 92 |
+
},
|
| 93 |
+
{
|
| 94 |
+
"epoch": 6.856359273225918e-05,
|
| 95 |
+
"eval_loss": 7.1901774406433105,
|
| 96 |
+
"eval_runtime": 3196.5055,
|
| 97 |
+
"eval_samples_per_second": 1.721,
|
| 98 |
+
"eval_steps_per_second": 1.721,
|
| 99 |
+
"step": 6
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 7.99908581876357e-05,
|
| 103 |
+
"grad_norm": 0.46564584970474243,
|
| 104 |
+
"learning_rate": 2.4246231155778896e-05,
|
| 105 |
+
"loss": 4.6497,
|
| 106 |
+
"step": 7
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 7.99908581876357e-05,
|
| 110 |
+
"eval_loss": 7.182745933532715,
|
| 111 |
+
"eval_runtime": 3195.2045,
|
| 112 |
+
"eval_samples_per_second": 1.721,
|
| 113 |
+
"eval_steps_per_second": 1.721,
|
| 114 |
+
"step": 7
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 9.141812364301222e-05,
|
| 118 |
+
"grad_norm": 0.8245170712471008,
|
| 119 |
+
"learning_rate": 2.4120603015075376e-05,
|
| 120 |
+
"loss": 7.1603,
|
| 121 |
+
"step": 8
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 9.141812364301222e-05,
|
| 125 |
+
"eval_loss": 7.173906326293945,
|
| 126 |
+
"eval_runtime": 3196.5564,
|
| 127 |
+
"eval_samples_per_second": 1.721,
|
| 128 |
+
"eval_steps_per_second": 1.721,
|
| 129 |
+
"step": 8
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.00010284538909838876,
|
| 133 |
+
"grad_norm": 0.7266675233840942,
|
| 134 |
+
"learning_rate": 2.3994974874371863e-05,
|
| 135 |
+
"loss": 5.9704,
|
| 136 |
+
"step": 9
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.00010284538909838876,
|
| 140 |
+
"eval_loss": 7.165711879730225,
|
| 141 |
+
"eval_runtime": 3195.6693,
|
| 142 |
+
"eval_samples_per_second": 1.721,
|
| 143 |
+
"eval_steps_per_second": 1.721,
|
| 144 |
+
"step": 9
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 0.00011427265455376528,
|
| 148 |
+
"grad_norm": 0.8064714670181274,
|
| 149 |
+
"learning_rate": 2.3869346733668342e-05,
|
| 150 |
+
"loss": 6.5571,
|
| 151 |
+
"step": 10
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 0.00011427265455376528,
|
| 155 |
+
"eval_loss": 7.157066822052002,
|
| 156 |
+
"eval_runtime": 3196.6621,
|
| 157 |
+
"eval_samples_per_second": 1.721,
|
| 158 |
+
"eval_steps_per_second": 1.721,
|
| 159 |
+
"step": 10
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.00012569992000914182,
|
| 163 |
+
"grad_norm": 1.181254267692566,
|
| 164 |
+
"learning_rate": 2.3743718592964825e-05,
|
| 165 |
+
"loss": 8.2521,
|
| 166 |
+
"step": 11
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 0.00012569992000914182,
|
| 170 |
+
"eval_loss": 7.1473798751831055,
|
| 171 |
+
"eval_runtime": 3195.7223,
|
| 172 |
+
"eval_samples_per_second": 1.721,
|
| 173 |
+
"eval_steps_per_second": 1.721,
|
| 174 |
+
"step": 11
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 0.00013712718546451835,
|
| 178 |
+
"grad_norm": 0.8531734347343445,
|
| 179 |
+
"learning_rate": 2.361809045226131e-05,
|
| 180 |
+
"loss": 6.5084,
|
| 181 |
+
"step": 12
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 0.00013712718546451835,
|
| 185 |
+
"eval_loss": 7.1375651359558105,
|
| 186 |
+
"eval_runtime": 3197.1154,
|
| 187 |
+
"eval_samples_per_second": 1.72,
|
| 188 |
+
"eval_steps_per_second": 1.72,
|
| 189 |
+
"step": 12
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 0.00014855445091989486,
|
| 193 |
+
"grad_norm": 0.8652932643890381,
|
| 194 |
+
"learning_rate": 2.3492462311557788e-05,
|
| 195 |
+
"loss": 6.1662,
|
| 196 |
+
"step": 13
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 0.00014855445091989486,
|
| 200 |
+
"eval_loss": 7.127073287963867,
|
| 201 |
+
"eval_runtime": 3199.1778,
|
| 202 |
+
"eval_samples_per_second": 1.719,
|
| 203 |
+
"eval_steps_per_second": 1.719,
|
| 204 |
+
"step": 13
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 0.0001599817163752714,
|
| 208 |
+
"grad_norm": 1.108816146850586,
|
| 209 |
+
"learning_rate": 2.3366834170854275e-05,
|
| 210 |
+
"loss": 7.9397,
|
| 211 |
+
"step": 14
|
| 212 |
+
},
|
| 213 |
+
{
|
| 214 |
+
"epoch": 0.0001599817163752714,
|
| 215 |
+
"eval_loss": 7.116166114807129,
|
| 216 |
+
"eval_runtime": 3199.5106,
|
| 217 |
+
"eval_samples_per_second": 1.719,
|
| 218 |
+
"eval_steps_per_second": 1.719,
|
| 219 |
+
"step": 14
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.00017140898183064793,
|
| 223 |
+
"grad_norm": 1.090276837348938,
|
| 224 |
+
"learning_rate": 2.3241206030150754e-05,
|
| 225 |
+
"loss": 7.066,
|
| 226 |
+
"step": 15
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.00017140898183064793,
|
| 230 |
+
"eval_loss": 7.104613780975342,
|
| 231 |
+
"eval_runtime": 3197.1218,
|
| 232 |
+
"eval_samples_per_second": 1.72,
|
| 233 |
+
"eval_steps_per_second": 1.72,
|
| 234 |
+
"step": 15
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.00018283624728602444,
|
| 238 |
+
"grad_norm": 1.5131642818450928,
|
| 239 |
+
"learning_rate": 2.3115577889447238e-05,
|
| 240 |
+
"loss": 8.6329,
|
| 241 |
+
"step": 16
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.00018283624728602444,
|
| 245 |
+
"eval_loss": 7.092124938964844,
|
| 246 |
+
"eval_runtime": 3198.3437,
|
| 247 |
+
"eval_samples_per_second": 1.72,
|
| 248 |
+
"eval_steps_per_second": 1.72,
|
| 249 |
+
"step": 16
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 0.00019426351274140098,
|
| 253 |
+
"grad_norm": 1.1908084154129028,
|
| 254 |
+
"learning_rate": 2.298994974874372e-05,
|
| 255 |
+
"loss": 7.2422,
|
| 256 |
+
"step": 17
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 0.00019426351274140098,
|
| 260 |
+
"eval_loss": 7.078921794891357,
|
| 261 |
+
"eval_runtime": 3196.3444,
|
| 262 |
+
"eval_samples_per_second": 1.721,
|
| 263 |
+
"eval_steps_per_second": 1.721,
|
| 264 |
+
"step": 17
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 0.00020569077819677752,
|
| 268 |
+
"grad_norm": 1.157004714012146,
|
| 269 |
+
"learning_rate": 2.28643216080402e-05,
|
| 270 |
+
"loss": 6.7972,
|
| 271 |
+
"step": 18
|
| 272 |
+
},
|
| 273 |
+
{
|
| 274 |
+
"epoch": 0.00020569077819677752,
|
| 275 |
+
"eval_loss": 7.065500736236572,
|
| 276 |
+
"eval_runtime": 3196.895,
|
| 277 |
+
"eval_samples_per_second": 1.72,
|
| 278 |
+
"eval_steps_per_second": 1.72,
|
| 279 |
+
"step": 18
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 0.00021711804365215405,
|
| 283 |
+
"grad_norm": 1.2554625272750854,
|
| 284 |
+
"learning_rate": 2.2738693467336687e-05,
|
| 285 |
+
"loss": 6.9076,
|
| 286 |
+
"step": 19
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 0.00021711804365215405,
|
| 290 |
+
"eval_loss": 7.051235675811768,
|
| 291 |
+
"eval_runtime": 3197.6043,
|
| 292 |
+
"eval_samples_per_second": 1.72,
|
| 293 |
+
"eval_steps_per_second": 1.72,
|
| 294 |
+
"step": 19
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 0.00022854530910753056,
|
| 298 |
+
"grad_norm": 1.1883549690246582,
|
| 299 |
+
"learning_rate": 2.2613065326633167e-05,
|
| 300 |
+
"loss": 6.5687,
|
| 301 |
+
"step": 20
|
| 302 |
+
},
|
| 303 |
+
{
|
| 304 |
+
"epoch": 0.00022854530910753056,
|
| 305 |
+
"eval_loss": 7.036637306213379,
|
| 306 |
+
"eval_runtime": 3196.0972,
|
| 307 |
+
"eval_samples_per_second": 1.721,
|
| 308 |
+
"eval_steps_per_second": 1.721,
|
| 309 |
+
"step": 20
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 0.0002399725745629071,
|
| 313 |
+
"grad_norm": 1.328796148300171,
|
| 314 |
+
"learning_rate": 2.248743718592965e-05,
|
| 315 |
+
"loss": 6.7253,
|
| 316 |
+
"step": 21
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 0.0002399725745629071,
|
| 320 |
+
"eval_loss": 7.021302700042725,
|
| 321 |
+
"eval_runtime": 3197.9644,
|
| 322 |
+
"eval_samples_per_second": 1.72,
|
| 323 |
+
"eval_steps_per_second": 1.72,
|
| 324 |
+
"step": 21
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.00025139984001828363,
|
| 328 |
+
"grad_norm": 1.2712606191635132,
|
| 329 |
+
"learning_rate": 2.2361809045226133e-05,
|
| 330 |
+
"loss": 6.1315,
|
| 331 |
+
"step": 22
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.00025139984001828363,
|
| 335 |
+
"eval_loss": 7.005300521850586,
|
| 336 |
+
"eval_runtime": 3198.4581,
|
| 337 |
+
"eval_samples_per_second": 1.72,
|
| 338 |
+
"eval_steps_per_second": 1.72,
|
| 339 |
+
"step": 22
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.00026282710547366017,
|
| 343 |
+
"grad_norm": 1.5367112159729004,
|
| 344 |
+
"learning_rate": 2.2236180904522613e-05,
|
| 345 |
+
"loss": 7.0915,
|
| 346 |
+
"step": 23
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.00026282710547366017,
|
| 350 |
+
"eval_loss": 6.98922872543335,
|
| 351 |
+
"eval_runtime": 3194.9885,
|
| 352 |
+
"eval_samples_per_second": 1.721,
|
| 353 |
+
"eval_steps_per_second": 1.721,
|
| 354 |
+
"step": 23
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 0.0002742543709290367,
|
| 358 |
+
"grad_norm": 1.4399423599243164,
|
| 359 |
+
"learning_rate": 2.21105527638191e-05,
|
| 360 |
+
"loss": 6.5237,
|
| 361 |
+
"step": 24
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 0.0002742543709290367,
|
| 365 |
+
"eval_loss": 6.972210884094238,
|
| 366 |
+
"eval_runtime": 3194.7666,
|
| 367 |
+
"eval_samples_per_second": 1.722,
|
| 368 |
+
"eval_steps_per_second": 1.722,
|
| 369 |
+
"step": 24
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 0.0002856816363844132,
|
| 373 |
+
"grad_norm": 0.9845247864723206,
|
| 374 |
+
"learning_rate": 2.198492462311558e-05,
|
| 375 |
+
"loss": 5.0536,
|
| 376 |
+
"step": 25
|
| 377 |
+
},
|
| 378 |
+
{
|
| 379 |
+
"epoch": 0.0002856816363844132,
|
| 380 |
+
"eval_loss": 6.955036163330078,
|
| 381 |
+
"eval_runtime": 3197.7715,
|
| 382 |
+
"eval_samples_per_second": 1.72,
|
| 383 |
+
"eval_steps_per_second": 1.72,
|
| 384 |
+
"step": 25
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 0.0002971089018397897,
|
| 388 |
+
"grad_norm": 1.1501060724258423,
|
| 389 |
+
"learning_rate": 2.1859296482412062e-05,
|
| 390 |
+
"loss": 5.3398,
|
| 391 |
+
"step": 26
|
| 392 |
+
},
|
| 393 |
+
{
|
| 394 |
+
"epoch": 0.0002971089018397897,
|
| 395 |
+
"eval_loss": 6.937135696411133,
|
| 396 |
+
"eval_runtime": 3193.8534,
|
| 397 |
+
"eval_samples_per_second": 1.722,
|
| 398 |
+
"eval_steps_per_second": 1.722,
|
| 399 |
+
"step": 26
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 0.00030853616729516626,
|
| 403 |
+
"grad_norm": 0.6898478865623474,
|
| 404 |
+
"learning_rate": 2.1733668341708545e-05,
|
| 405 |
+
"loss": 4.2246,
|
| 406 |
+
"step": 27
|
| 407 |
+
},
|
| 408 |
+
{
|
| 409 |
+
"epoch": 0.00030853616729516626,
|
| 410 |
+
"eval_loss": 6.919322490692139,
|
| 411 |
+
"eval_runtime": 3194.157,
|
| 412 |
+
"eval_samples_per_second": 1.722,
|
| 413 |
+
"eval_steps_per_second": 1.722,
|
| 414 |
+
"step": 27
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 0.0003199634327505428,
|
| 418 |
+
"grad_norm": 1.9928979873657227,
|
| 419 |
+
"learning_rate": 2.1608040201005025e-05,
|
| 420 |
+
"loss": 8.0199,
|
| 421 |
+
"step": 28
|
| 422 |
+
},
|
| 423 |
+
{
|
| 424 |
+
"epoch": 0.0003199634327505428,
|
| 425 |
+
"eval_loss": 6.901232719421387,
|
| 426 |
+
"eval_runtime": 3194.869,
|
| 427 |
+
"eval_samples_per_second": 1.722,
|
| 428 |
+
"eval_steps_per_second": 1.722,
|
| 429 |
+
"step": 28
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.00033139069820591933,
|
| 433 |
+
"grad_norm": 1.6013647317886353,
|
| 434 |
+
"learning_rate": 2.1482412060301508e-05,
|
| 435 |
+
"loss": 6.4213,
|
| 436 |
+
"step": 29
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.00033139069820591933,
|
| 440 |
+
"eval_loss": 6.882281303405762,
|
| 441 |
+
"eval_runtime": 3196.4271,
|
| 442 |
+
"eval_samples_per_second": 1.721,
|
| 443 |
+
"eval_steps_per_second": 1.721,
|
| 444 |
+
"step": 29
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.00034281796366129587,
|
| 448 |
+
"grad_norm": 0.6780699491500854,
|
| 449 |
+
"learning_rate": 2.135678391959799e-05,
|
| 450 |
+
"loss": 4.0142,
|
| 451 |
+
"step": 30
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 0.00034281796366129587,
|
| 455 |
+
"eval_loss": 6.86350154876709,
|
| 456 |
+
"eval_runtime": 3195.3922,
|
| 457 |
+
"eval_samples_per_second": 1.721,
|
| 458 |
+
"eval_steps_per_second": 1.721,
|
| 459 |
+
"step": 30
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 0.0003542452291166724,
|
| 463 |
+
"grad_norm": 1.243430256843567,
|
| 464 |
+
"learning_rate": 2.1231155778894474e-05,
|
| 465 |
+
"loss": 5.1075,
|
| 466 |
+
"step": 31
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 0.0003542452291166724,
|
| 470 |
+
"eval_loss": 6.844424724578857,
|
| 471 |
+
"eval_runtime": 3194.7916,
|
| 472 |
+
"eval_samples_per_second": 1.722,
|
| 473 |
+
"eval_steps_per_second": 1.722,
|
| 474 |
+
"step": 31
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 0.0003656724945720489,
|
| 478 |
+
"grad_norm": 1.993019700050354,
|
| 479 |
+
"learning_rate": 2.1105527638190957e-05,
|
| 480 |
+
"loss": 6.6294,
|
| 481 |
+
"step": 32
|
| 482 |
+
},
|
| 483 |
+
{
|
| 484 |
+
"epoch": 0.0003656724945720489,
|
| 485 |
+
"eval_loss": 6.824941635131836,
|
| 486 |
+
"eval_runtime": 3194.2906,
|
| 487 |
+
"eval_samples_per_second": 1.722,
|
| 488 |
+
"eval_steps_per_second": 1.722,
|
| 489 |
+
"step": 32
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 0.0003770997600274254,
|
| 493 |
+
"grad_norm": 2.094905138015747,
|
| 494 |
+
"learning_rate": 2.0979899497487437e-05,
|
| 495 |
+
"loss": 7.1042,
|
| 496 |
+
"step": 33
|
| 497 |
+
},
|
| 498 |
+
{
|
| 499 |
+
"epoch": 0.0003770997600274254,
|
| 500 |
+
"eval_loss": 6.804728031158447,
|
| 501 |
+
"eval_runtime": 3194.5706,
|
| 502 |
+
"eval_samples_per_second": 1.722,
|
| 503 |
+
"eval_steps_per_second": 1.722,
|
| 504 |
+
"step": 33
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 0.00038852702548280196,
|
| 508 |
+
"grad_norm": 1.7997703552246094,
|
| 509 |
+
"learning_rate": 2.085427135678392e-05,
|
| 510 |
+
"loss": 6.6241,
|
| 511 |
+
"step": 34
|
| 512 |
+
},
|
| 513 |
+
{
|
| 514 |
+
"epoch": 0.00038852702548280196,
|
| 515 |
+
"eval_loss": 6.784134864807129,
|
| 516 |
+
"eval_runtime": 3194.7504,
|
| 517 |
+
"eval_samples_per_second": 1.722,
|
| 518 |
+
"eval_steps_per_second": 1.722,
|
| 519 |
+
"step": 34
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 0.0003999542909381785,
|
| 523 |
+
"grad_norm": 1.6641287803649902,
|
| 524 |
+
"learning_rate": 2.0728643216080403e-05,
|
| 525 |
+
"loss": 5.6431,
|
| 526 |
+
"step": 35
|
| 527 |
+
},
|
| 528 |
+
{
|
| 529 |
+
"epoch": 0.0003999542909381785,
|
| 530 |
+
"eval_loss": 6.762852191925049,
|
| 531 |
+
"eval_runtime": 3195.8642,
|
| 532 |
+
"eval_samples_per_second": 1.721,
|
| 533 |
+
"eval_steps_per_second": 1.721,
|
| 534 |
+
"step": 35
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.00041138155639355503,
|
| 538 |
+
"grad_norm": 1.9099078178405762,
|
| 539 |
+
"learning_rate": 2.0603015075376886e-05,
|
| 540 |
+
"loss": 6.4051,
|
| 541 |
+
"step": 36
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.00041138155639355503,
|
| 545 |
+
"eval_loss": 6.741316795349121,
|
| 546 |
+
"eval_runtime": 3192.3732,
|
| 547 |
+
"eval_samples_per_second": 1.723,
|
| 548 |
+
"eval_steps_per_second": 1.723,
|
| 549 |
+
"step": 36
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.00042280882184893157,
|
| 553 |
+
"grad_norm": 1.958937406539917,
|
| 554 |
+
"learning_rate": 2.047738693467337e-05,
|
| 555 |
+
"loss": 6.8499,
|
| 556 |
+
"step": 37
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 0.00042280882184893157,
|
| 560 |
+
"eval_loss": 6.719349384307861,
|
| 561 |
+
"eval_runtime": 3195.1382,
|
| 562 |
+
"eval_samples_per_second": 1.721,
|
| 563 |
+
"eval_steps_per_second": 1.721,
|
| 564 |
+
"step": 37
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 0.0004342360873043081,
|
| 568 |
+
"grad_norm": 1.903361201286316,
|
| 569 |
+
"learning_rate": 2.035175879396985e-05,
|
| 570 |
+
"loss": 6.1026,
|
| 571 |
+
"step": 38
|
| 572 |
+
},
|
| 573 |
+
{
|
| 574 |
+
"epoch": 0.0004342360873043081,
|
| 575 |
+
"eval_loss": 6.697410583496094,
|
| 576 |
+
"eval_runtime": 3195.9588,
|
| 577 |
+
"eval_samples_per_second": 1.721,
|
| 578 |
+
"eval_steps_per_second": 1.721,
|
| 579 |
+
"step": 38
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 0.0004456633527596846,
|
| 583 |
+
"grad_norm": 2.3142635822296143,
|
| 584 |
+
"learning_rate": 2.0226130653266332e-05,
|
| 585 |
+
"loss": 6.834,
|
| 586 |
+
"step": 39
|
| 587 |
+
},
|
| 588 |
+
{
|
| 589 |
+
"epoch": 0.0004456633527596846,
|
| 590 |
+
"eval_loss": 6.674659252166748,
|
| 591 |
+
"eval_runtime": 3194.6685,
|
| 592 |
+
"eval_samples_per_second": 1.722,
|
| 593 |
+
"eval_steps_per_second": 1.722,
|
| 594 |
+
"step": 39
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 0.0004570906182150611,
|
| 598 |
+
"grad_norm": 2.355628252029419,
|
| 599 |
+
"learning_rate": 2.0100502512562815e-05,
|
| 600 |
+
"loss": 7.05,
|
| 601 |
+
"step": 40
|
| 602 |
+
},
|
| 603 |
+
{
|
| 604 |
+
"epoch": 0.0004570906182150611,
|
| 605 |
+
"eval_loss": 6.651575088500977,
|
| 606 |
+
"eval_runtime": 3192.9283,
|
| 607 |
+
"eval_samples_per_second": 1.723,
|
| 608 |
+
"eval_steps_per_second": 1.723,
|
| 609 |
+
"step": 40
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 0.00046851788367043766,
|
| 613 |
+
"grad_norm": 2.478034496307373,
|
| 614 |
+
"learning_rate": 1.9974874371859298e-05,
|
| 615 |
+
"loss": 7.203,
|
| 616 |
+
"step": 41
|
| 617 |
+
},
|
| 618 |
+
{
|
| 619 |
+
"epoch": 0.00046851788367043766,
|
| 620 |
+
"eval_loss": 6.6284260749816895,
|
| 621 |
+
"eval_runtime": 3195.3222,
|
| 622 |
+
"eval_samples_per_second": 1.721,
|
| 623 |
+
"eval_steps_per_second": 1.721,
|
| 624 |
+
"step": 41
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 0.0004799451491258142,
|
| 628 |
+
"grad_norm": 1.591928482055664,
|
| 629 |
+
"learning_rate": 1.984924623115578e-05,
|
| 630 |
+
"loss": 4.5537,
|
| 631 |
+
"step": 42
|
| 632 |
+
},
|
| 633 |
+
{
|
| 634 |
+
"epoch": 0.0004799451491258142,
|
| 635 |
+
"eval_loss": 6.604694366455078,
|
| 636 |
+
"eval_runtime": 3196.8557,
|
| 637 |
+
"eval_samples_per_second": 1.72,
|
| 638 |
+
"eval_steps_per_second": 1.72,
|
| 639 |
+
"step": 42
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.0004913724145811907,
|
| 643 |
+
"grad_norm": 2.615412712097168,
|
| 644 |
+
"learning_rate": 1.972361809045226e-05,
|
| 645 |
+
"loss": 6.8927,
|
| 646 |
+
"step": 43
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 0.0004913724145811907,
|
| 650 |
+
"eval_loss": 6.580879211425781,
|
| 651 |
+
"eval_runtime": 3197.1663,
|
| 652 |
+
"eval_samples_per_second": 1.72,
|
| 653 |
+
"eval_steps_per_second": 1.72,
|
| 654 |
+
"step": 43
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 0.0005027996800365673,
|
| 658 |
+
"grad_norm": 2.0230987071990967,
|
| 659 |
+
"learning_rate": 1.9597989949748744e-05,
|
| 660 |
+
"loss": 6.0638,
|
| 661 |
+
"step": 44
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 0.0005027996800365673,
|
| 665 |
+
"eval_loss": 6.556508541107178,
|
| 666 |
+
"eval_runtime": 3196.2452,
|
| 667 |
+
"eval_samples_per_second": 1.721,
|
| 668 |
+
"eval_steps_per_second": 1.721,
|
| 669 |
+
"step": 44
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 0.0005142269454919438,
|
| 673 |
+
"grad_norm": 2.6316287517547607,
|
| 674 |
+
"learning_rate": 1.9472361809045227e-05,
|
| 675 |
+
"loss": 6.8353,
|
| 676 |
+
"step": 45
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 0.0005142269454919438,
|
| 680 |
+
"eval_loss": 6.532052516937256,
|
| 681 |
+
"eval_runtime": 3195.9887,
|
| 682 |
+
"eval_samples_per_second": 1.721,
|
| 683 |
+
"eval_steps_per_second": 1.721,
|
| 684 |
+
"step": 45
|
| 685 |
+
},
|
| 686 |
+
{
|
| 687 |
+
"epoch": 0.0005256542109473203,
|
| 688 |
+
"grad_norm": 1.5371630191802979,
|
| 689 |
+
"learning_rate": 1.934673366834171e-05,
|
| 690 |
+
"loss": 4.5244,
|
| 691 |
+
"step": 46
|
| 692 |
+
},
|
| 693 |
+
{
|
| 694 |
+
"epoch": 0.0005256542109473203,
|
| 695 |
+
"eval_loss": 6.507321834564209,
|
| 696 |
+
"eval_runtime": 3196.0239,
|
| 697 |
+
"eval_samples_per_second": 1.721,
|
| 698 |
+
"eval_steps_per_second": 1.721,
|
| 699 |
+
"step": 46
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 0.0005370814764026968,
|
| 703 |
+
"grad_norm": 1.7422285079956055,
|
| 704 |
+
"learning_rate": 1.9221105527638193e-05,
|
| 705 |
+
"loss": 4.9649,
|
| 706 |
+
"step": 47
|
| 707 |
+
},
|
| 708 |
+
{
|
| 709 |
+
"epoch": 0.0005370814764026968,
|
| 710 |
+
"eval_loss": 6.482240200042725,
|
| 711 |
+
"eval_runtime": 3195.5121,
|
| 712 |
+
"eval_samples_per_second": 1.721,
|
| 713 |
+
"eval_steps_per_second": 1.721,
|
| 714 |
+
"step": 47
|
| 715 |
+
},
|
| 716 |
+
{
|
| 717 |
+
"epoch": 0.0005485087418580734,
|
| 718 |
+
"grad_norm": 1.1683274507522583,
|
| 719 |
+
"learning_rate": 1.9095477386934673e-05,
|
| 720 |
+
"loss": 3.7341,
|
| 721 |
+
"step": 48
|
| 722 |
+
},
|
| 723 |
+
{
|
| 724 |
+
"epoch": 0.0005485087418580734,
|
| 725 |
+
"eval_loss": 6.456914901733398,
|
| 726 |
+
"eval_runtime": 3194.9287,
|
| 727 |
+
"eval_samples_per_second": 1.721,
|
| 728 |
+
"eval_steps_per_second": 1.721,
|
| 729 |
+
"step": 48
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 0.0005599360073134499,
|
| 733 |
+
"grad_norm": 3.5512888431549072,
|
| 734 |
+
"learning_rate": 1.8969849246231156e-05,
|
| 735 |
+
"loss": 8.3966,
|
| 736 |
+
"step": 49
|
| 737 |
+
},
|
| 738 |
+
{
|
| 739 |
+
"epoch": 0.0005599360073134499,
|
| 740 |
+
"eval_loss": 6.431957244873047,
|
| 741 |
+
"eval_runtime": 3193.8838,
|
| 742 |
+
"eval_samples_per_second": 1.722,
|
| 743 |
+
"eval_steps_per_second": 1.722,
|
| 744 |
+
"step": 49
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 0.0005713632727688264,
|
| 748 |
+
"grad_norm": 1.8522059917449951,
|
| 749 |
+
"learning_rate": 1.884422110552764e-05,
|
| 750 |
+
"loss": 4.837,
|
| 751 |
+
"step": 50
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 0.0005713632727688264,
|
| 755 |
+
"eval_loss": 6.406413555145264,
|
| 756 |
+
"eval_runtime": 3195.7335,
|
| 757 |
+
"eval_samples_per_second": 1.721,
|
| 758 |
+
"eval_steps_per_second": 1.721,
|
| 759 |
+
"step": 50
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 0.000582790538224203,
|
| 763 |
+
"grad_norm": 2.5635313987731934,
|
| 764 |
+
"learning_rate": 1.8718592964824123e-05,
|
| 765 |
+
"loss": 6.2677,
|
| 766 |
+
"step": 51
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 0.000582790538224203,
|
| 770 |
+
"eval_loss": 6.380771160125732,
|
| 771 |
+
"eval_runtime": 3193.483,
|
| 772 |
+
"eval_samples_per_second": 1.722,
|
| 773 |
+
"eval_steps_per_second": 1.722,
|
| 774 |
+
"step": 51
|
| 775 |
+
},
|
| 776 |
+
{
|
| 777 |
+
"epoch": 0.0005942178036795794,
|
| 778 |
+
"grad_norm": 3.0012006759643555,
|
| 779 |
+
"learning_rate": 1.8592964824120602e-05,
|
| 780 |
+
"loss": 6.3779,
|
| 781 |
+
"step": 52
|
| 782 |
+
},
|
| 783 |
+
{
|
| 784 |
+
"epoch": 0.0005942178036795794,
|
| 785 |
+
"eval_loss": 6.354803085327148,
|
| 786 |
+
"eval_runtime": 3191.7709,
|
| 787 |
+
"eval_samples_per_second": 1.723,
|
| 788 |
+
"eval_steps_per_second": 1.723,
|
| 789 |
+
"step": 52
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 0.000605645069134956,
|
| 793 |
+
"grad_norm": 2.9274518489837646,
|
| 794 |
+
"learning_rate": 1.8467336683417085e-05,
|
| 795 |
+
"loss": 6.4349,
|
| 796 |
+
"step": 53
|
| 797 |
+
},
|
| 798 |
+
{
|
| 799 |
+
"epoch": 0.000605645069134956,
|
| 800 |
+
"eval_loss": 6.329031467437744,
|
| 801 |
+
"eval_runtime": 3194.6961,
|
| 802 |
+
"eval_samples_per_second": 1.722,
|
| 803 |
+
"eval_steps_per_second": 1.722,
|
| 804 |
+
"step": 53
|
| 805 |
+
},
|
| 806 |
+
{
|
| 807 |
+
"epoch": 0.0006170723345903325,
|
| 808 |
+
"grad_norm": 3.2986245155334473,
|
| 809 |
+
"learning_rate": 1.834170854271357e-05,
|
| 810 |
+
"loss": 7.2301,
|
| 811 |
+
"step": 54
|
| 812 |
+
},
|
| 813 |
+
{
|
| 814 |
+
"epoch": 0.0006170723345903325,
|
| 815 |
+
"eval_loss": 6.30263090133667,
|
| 816 |
+
"eval_runtime": 3193.3906,
|
| 817 |
+
"eval_samples_per_second": 1.722,
|
| 818 |
+
"eval_steps_per_second": 1.722,
|
| 819 |
+
"step": 54
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"epoch": 0.0006284996000457091,
|
| 823 |
+
"grad_norm": 2.258892297744751,
|
| 824 |
+
"learning_rate": 1.821608040201005e-05,
|
| 825 |
+
"loss": 5.288,
|
| 826 |
+
"step": 55
|
| 827 |
+
},
|
| 828 |
+
{
|
| 829 |
+
"epoch": 0.0006284996000457091,
|
| 830 |
+
"eval_loss": 6.27651834487915,
|
| 831 |
+
"eval_runtime": 3193.9175,
|
| 832 |
+
"eval_samples_per_second": 1.722,
|
| 833 |
+
"eval_steps_per_second": 1.722,
|
| 834 |
+
"step": 55
|
| 835 |
+
},
|
| 836 |
+
{
|
| 837 |
+
"epoch": 0.0006399268655010856,
|
| 838 |
+
"grad_norm": 3.4918830394744873,
|
| 839 |
+
"learning_rate": 1.8090452261306535e-05,
|
| 840 |
+
"loss": 7.0831,
|
| 841 |
+
"step": 56
|
| 842 |
+
},
|
| 843 |
+
{
|
| 844 |
+
"epoch": 0.0006399268655010856,
|
| 845 |
+
"eval_loss": 6.249880790710449,
|
| 846 |
+
"eval_runtime": 3195.1438,
|
| 847 |
+
"eval_samples_per_second": 1.721,
|
| 848 |
+
"eval_steps_per_second": 1.721,
|
| 849 |
+
"step": 56
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 0.0006513541309564621,
|
| 853 |
+
"grad_norm": 3.48417592048645,
|
| 854 |
+
"learning_rate": 1.7964824120603014e-05,
|
| 855 |
+
"loss": 7.1039,
|
| 856 |
+
"step": 57
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 0.0006513541309564621,
|
| 860 |
+
"eval_loss": 6.223054885864258,
|
| 861 |
+
"eval_runtime": 3193.8782,
|
| 862 |
+
"eval_samples_per_second": 1.722,
|
| 863 |
+
"eval_steps_per_second": 1.722,
|
| 864 |
+
"step": 57
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 0.0006627813964118387,
|
| 868 |
+
"grad_norm": 2.575576066970825,
|
| 869 |
+
"learning_rate": 1.7839195979899497e-05,
|
| 870 |
+
"loss": 5.38,
|
| 871 |
+
"step": 58
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 0.0006627813964118387,
|
| 875 |
+
"eval_loss": 6.195952892303467,
|
| 876 |
+
"eval_runtime": 3193.8956,
|
| 877 |
+
"eval_samples_per_second": 1.722,
|
| 878 |
+
"eval_steps_per_second": 1.722,
|
| 879 |
+
"step": 58
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 0.0006742086618672151,
|
| 883 |
+
"grad_norm": 3.869877815246582,
|
| 884 |
+
"learning_rate": 1.771356783919598e-05,
|
| 885 |
+
"loss": 7.1632,
|
| 886 |
+
"step": 59
|
| 887 |
+
},
|
| 888 |
+
{
|
| 889 |
+
"epoch": 0.0006742086618672151,
|
| 890 |
+
"eval_loss": 6.1690497398376465,
|
| 891 |
+
"eval_runtime": 3195.4516,
|
| 892 |
+
"eval_samples_per_second": 1.721,
|
| 893 |
+
"eval_steps_per_second": 1.721,
|
| 894 |
+
"step": 59
|
| 895 |
+
},
|
| 896 |
+
{
|
| 897 |
+
"epoch": 0.0006856359273225917,
|
| 898 |
+
"grad_norm": 2.590207815170288,
|
| 899 |
+
"learning_rate": 1.7587939698492464e-05,
|
| 900 |
+
"loss": 5.6661,
|
| 901 |
+
"step": 60
|
| 902 |
+
},
|
| 903 |
+
{
|
| 904 |
+
"epoch": 0.0006856359273225917,
|
| 905 |
+
"eval_loss": 6.141936779022217,
|
| 906 |
+
"eval_runtime": 3196.1077,
|
| 907 |
+
"eval_samples_per_second": 1.721,
|
| 908 |
+
"eval_steps_per_second": 1.721,
|
| 909 |
+
"step": 60
|
| 910 |
+
},
|
| 911 |
+
{
|
| 912 |
+
"epoch": 0.0006970631927779682,
|
| 913 |
+
"grad_norm": 3.316432237625122,
|
| 914 |
+
"learning_rate": 1.7462311557788947e-05,
|
| 915 |
+
"loss": 6.4535,
|
| 916 |
+
"step": 61
|
| 917 |
+
},
|
| 918 |
+
{
|
| 919 |
+
"epoch": 0.0006970631927779682,
|
| 920 |
+
"eval_loss": 6.114187717437744,
|
| 921 |
+
"eval_runtime": 3196.6866,
|
| 922 |
+
"eval_samples_per_second": 1.721,
|
| 923 |
+
"eval_steps_per_second": 1.721,
|
| 924 |
+
"step": 61
|
| 925 |
+
},
|
| 926 |
+
{
|
| 927 |
+
"epoch": 0.0007084904582333448,
|
| 928 |
+
"grad_norm": 3.1938068866729736,
|
| 929 |
+
"learning_rate": 1.7336683417085427e-05,
|
| 930 |
+
"loss": 6.0447,
|
| 931 |
+
"step": 62
|
| 932 |
+
},
|
| 933 |
+
{
|
| 934 |
+
"epoch": 0.0007084904582333448,
|
| 935 |
+
"eval_loss": 6.08643913269043,
|
| 936 |
+
"eval_runtime": 3195.265,
|
| 937 |
+
"eval_samples_per_second": 1.721,
|
| 938 |
+
"eval_steps_per_second": 1.721,
|
| 939 |
+
"step": 62
|
| 940 |
+
},
|
| 941 |
+
{
|
| 942 |
+
"epoch": 0.0007199177236887213,
|
| 943 |
+
"grad_norm": 3.078531265258789,
|
| 944 |
+
"learning_rate": 1.721105527638191e-05,
|
| 945 |
+
"loss": 5.802,
|
| 946 |
+
"step": 63
|
| 947 |
+
},
|
| 948 |
+
{
|
| 949 |
+
"epoch": 0.0007199177236887213,
|
| 950 |
+
"eval_loss": 6.058650016784668,
|
| 951 |
+
"eval_runtime": 3193.9302,
|
| 952 |
+
"eval_samples_per_second": 1.722,
|
| 953 |
+
"eval_steps_per_second": 1.722,
|
| 954 |
+
"step": 63
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 0.0007313449891440978,
|
| 958 |
+
"grad_norm": 3.1577515602111816,
|
| 959 |
+
"learning_rate": 1.7085427135678393e-05,
|
| 960 |
+
"loss": 5.8267,
|
| 961 |
+
"step": 64
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 0.0007313449891440978,
|
| 965 |
+
"eval_loss": 6.030569553375244,
|
| 966 |
+
"eval_runtime": 3193.2589,
|
| 967 |
+
"eval_samples_per_second": 1.722,
|
| 968 |
+
"eval_steps_per_second": 1.722,
|
| 969 |
+
"step": 64
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 0.0007427722545994744,
|
| 973 |
+
"grad_norm": 3.361140012741089,
|
| 974 |
+
"learning_rate": 1.6959798994974876e-05,
|
| 975 |
+
"loss": 6.1471,
|
| 976 |
+
"step": 65
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 0.0007427722545994744,
|
| 980 |
+
"eval_loss": 6.002427577972412,
|
| 981 |
+
"eval_runtime": 3194.7411,
|
| 982 |
+
"eval_samples_per_second": 1.722,
|
| 983 |
+
"eval_steps_per_second": 1.722,
|
| 984 |
+
"step": 65
|
| 985 |
+
},
|
| 986 |
+
{
|
| 987 |
+
"epoch": 0.0007541995200548508,
|
| 988 |
+
"grad_norm": 1.4381821155548096,
|
| 989 |
+
"learning_rate": 1.683417085427136e-05,
|
| 990 |
+
"loss": 3.696,
|
| 991 |
+
"step": 66
|
| 992 |
+
},
|
| 993 |
+
{
|
| 994 |
+
"epoch": 0.0007541995200548508,
|
| 995 |
+
"eval_loss": 5.974757671356201,
|
| 996 |
+
"eval_runtime": 3195.246,
|
| 997 |
+
"eval_samples_per_second": 1.721,
|
| 998 |
+
"eval_steps_per_second": 1.721,
|
| 999 |
+
"step": 66
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 0.0007656267855102274,
|
| 1003 |
+
"grad_norm": 3.1451377868652344,
|
| 1004 |
+
"learning_rate": 1.670854271356784e-05,
|
| 1005 |
+
"loss": 5.9335,
|
| 1006 |
+
"step": 67
|
| 1007 |
+
},
|
| 1008 |
+
{
|
| 1009 |
+
"epoch": 0.0007656267855102274,
|
| 1010 |
+
"eval_loss": 5.946895599365234,
|
| 1011 |
+
"eval_runtime": 3195.4763,
|
| 1012 |
+
"eval_samples_per_second": 1.721,
|
| 1013 |
+
"eval_steps_per_second": 1.721,
|
| 1014 |
+
"step": 67
|
| 1015 |
+
},
|
| 1016 |
+
{
|
| 1017 |
+
"epoch": 0.0007770540509656039,
|
| 1018 |
+
"grad_norm": 2.85153865814209,
|
| 1019 |
+
"learning_rate": 1.6582914572864322e-05,
|
| 1020 |
+
"loss": 5.5253,
|
| 1021 |
+
"step": 68
|
| 1022 |
+
},
|
| 1023 |
+
{
|
| 1024 |
+
"epoch": 0.0007770540509656039,
|
| 1025 |
+
"eval_loss": 5.918909072875977,
|
| 1026 |
+
"eval_runtime": 3194.2966,
|
| 1027 |
+
"eval_samples_per_second": 1.722,
|
| 1028 |
+
"eval_steps_per_second": 1.722,
|
| 1029 |
+
"step": 68
|
| 1030 |
+
},
|
| 1031 |
+
{
|
| 1032 |
+
"epoch": 0.0007884813164209805,
|
| 1033 |
+
"grad_norm": 0.18748074769973755,
|
| 1034 |
+
"learning_rate": 1.6457286432160805e-05,
|
| 1035 |
+
"loss": 2.4955,
|
| 1036 |
+
"step": 69
|
| 1037 |
+
},
|
| 1038 |
+
{
|
| 1039 |
+
"epoch": 0.0007884813164209805,
|
| 1040 |
+
"eval_loss": 5.893527507781982,
|
| 1041 |
+
"eval_runtime": 3192.8875,
|
| 1042 |
+
"eval_samples_per_second": 1.723,
|
| 1043 |
+
"eval_steps_per_second": 1.723,
|
| 1044 |
+
"step": 69
|
| 1045 |
+
},
|
| 1046 |
+
{
|
| 1047 |
+
"epoch": 0.000799908581876357,
|
| 1048 |
+
"grad_norm": 3.377441167831421,
|
| 1049 |
+
"learning_rate": 1.6331658291457288e-05,
|
| 1050 |
+
"loss": 6.0589,
|
| 1051 |
+
"step": 70
|
| 1052 |
+
},
|
| 1053 |
+
{
|
| 1054 |
+
"epoch": 0.000799908581876357,
|
| 1055 |
+
"eval_loss": 5.8677473068237305,
|
| 1056 |
+
"eval_runtime": 3192.1113,
|
| 1057 |
+
"eval_samples_per_second": 1.723,
|
| 1058 |
+
"eval_steps_per_second": 1.723,
|
| 1059 |
+
"step": 70
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 0.0008113358473317335,
|
| 1063 |
+
"grad_norm": 3.5671401023864746,
|
| 1064 |
+
"learning_rate": 1.620603015075377e-05,
|
| 1065 |
+
"loss": 6.1037,
|
| 1066 |
+
"step": 71
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 0.0008113358473317335,
|
| 1070 |
+
"eval_loss": 5.841763019561768,
|
| 1071 |
+
"eval_runtime": 3193.951,
|
| 1072 |
+
"eval_samples_per_second": 1.722,
|
| 1073 |
+
"eval_steps_per_second": 1.722,
|
| 1074 |
+
"step": 71
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 0.0008227631127871101,
|
| 1078 |
+
"grad_norm": 1.8638324737548828,
|
| 1079 |
+
"learning_rate": 1.608040201005025e-05,
|
| 1080 |
+
"loss": 3.9179,
|
| 1081 |
+
"step": 72
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 0.0008227631127871101,
|
| 1085 |
+
"eval_loss": 5.815106391906738,
|
| 1086 |
+
"eval_runtime": 3193.2648,
|
| 1087 |
+
"eval_samples_per_second": 1.722,
|
| 1088 |
+
"eval_steps_per_second": 1.722,
|
| 1089 |
+
"step": 72
|
| 1090 |
+
},
|
| 1091 |
+
{
|
| 1092 |
+
"epoch": 0.0008341903782424865,
|
| 1093 |
+
"grad_norm": 3.3266711235046387,
|
| 1094 |
+
"learning_rate": 1.5954773869346734e-05,
|
| 1095 |
+
"loss": 5.3457,
|
| 1096 |
+
"step": 73
|
| 1097 |
+
},
|
| 1098 |
+
{
|
| 1099 |
+
"epoch": 0.0008341903782424865,
|
| 1100 |
+
"eval_loss": 5.788687229156494,
|
| 1101 |
+
"eval_runtime": 3194.6212,
|
| 1102 |
+
"eval_samples_per_second": 1.722,
|
| 1103 |
+
"eval_steps_per_second": 1.722,
|
| 1104 |
+
"step": 73
|
| 1105 |
+
},
|
| 1106 |
+
{
|
| 1107 |
+
"epoch": 0.0008456176436978631,
|
| 1108 |
+
"grad_norm": 4.605172157287598,
|
| 1109 |
+
"learning_rate": 1.5829145728643217e-05,
|
| 1110 |
+
"loss": 7.0032,
|
| 1111 |
+
"step": 74
|
| 1112 |
+
},
|
| 1113 |
+
{
|
| 1114 |
+
"epoch": 0.0008456176436978631,
|
| 1115 |
+
"eval_loss": 5.761895656585693,
|
| 1116 |
+
"eval_runtime": 3191.5309,
|
| 1117 |
+
"eval_samples_per_second": 1.723,
|
| 1118 |
+
"eval_steps_per_second": 1.723,
|
| 1119 |
+
"step": 74
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 0.0008570449091532396,
|
| 1123 |
+
"grad_norm": 3.4830474853515625,
|
| 1124 |
+
"learning_rate": 1.57035175879397e-05,
|
| 1125 |
+
"loss": 5.9244,
|
| 1126 |
+
"step": 75
|
| 1127 |
+
},
|
| 1128 |
+
{
|
| 1129 |
+
"epoch": 0.0008570449091532396,
|
| 1130 |
+
"eval_loss": 5.734696388244629,
|
| 1131 |
+
"eval_runtime": 3191.7239,
|
| 1132 |
+
"eval_samples_per_second": 1.723,
|
| 1133 |
+
"eval_steps_per_second": 1.723,
|
| 1134 |
+
"step": 75
|
| 1135 |
+
},
|
| 1136 |
+
{
|
| 1137 |
+
"epoch": 0.0008684721746086162,
|
| 1138 |
+
"grad_norm": 3.59964919090271,
|
| 1139 |
+
"learning_rate": 1.5577889447236183e-05,
|
| 1140 |
+
"loss": 5.4847,
|
| 1141 |
+
"step": 76
|
| 1142 |
+
},
|
| 1143 |
+
{
|
| 1144 |
+
"epoch": 0.0008684721746086162,
|
| 1145 |
+
"eval_loss": 5.707438945770264,
|
| 1146 |
+
"eval_runtime": 3191.9511,
|
| 1147 |
+
"eval_samples_per_second": 1.723,
|
| 1148 |
+
"eval_steps_per_second": 1.723,
|
| 1149 |
+
"step": 76
|
| 1150 |
+
},
|
| 1151 |
+
{
|
| 1152 |
+
"epoch": 0.0008798994400639927,
|
| 1153 |
+
"grad_norm": 4.7916412353515625,
|
| 1154 |
+
"learning_rate": 1.5452261306532663e-05,
|
| 1155 |
+
"loss": 7.0196,
|
| 1156 |
+
"step": 77
|
| 1157 |
+
},
|
| 1158 |
+
{
|
| 1159 |
+
"epoch": 0.0008798994400639927,
|
| 1160 |
+
"eval_loss": 5.680092811584473,
|
| 1161 |
+
"eval_runtime": 3192.5862,
|
| 1162 |
+
"eval_samples_per_second": 1.723,
|
| 1163 |
+
"eval_steps_per_second": 1.723,
|
| 1164 |
+
"step": 77
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 0.0008913267055193692,
|
| 1168 |
+
"grad_norm": 3.67484450340271,
|
| 1169 |
+
"learning_rate": 1.5326633165829146e-05,
|
| 1170 |
+
"loss": 5.7853,
|
| 1171 |
+
"step": 78
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 0.0008913267055193692,
|
| 1175 |
+
"eval_loss": 5.652522087097168,
|
| 1176 |
+
"eval_runtime": 3191.0964,
|
| 1177 |
+
"eval_samples_per_second": 1.724,
|
| 1178 |
+
"eval_steps_per_second": 1.724,
|
| 1179 |
+
"step": 78
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 0.0009027539709747458,
|
| 1183 |
+
"grad_norm": 3.265822410583496,
|
| 1184 |
+
"learning_rate": 1.5201005025125627e-05,
|
| 1185 |
+
"loss": 5.3229,
|
| 1186 |
+
"step": 79
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 0.0009027539709747458,
|
| 1190 |
+
"eval_loss": 5.624815940856934,
|
| 1191 |
+
"eval_runtime": 3191.2862,
|
| 1192 |
+
"eval_samples_per_second": 1.723,
|
| 1193 |
+
"eval_steps_per_second": 1.723,
|
| 1194 |
+
"step": 79
|
| 1195 |
+
},
|
| 1196 |
+
{
|
| 1197 |
+
"epoch": 0.0009141812364301222,
|
| 1198 |
+
"grad_norm": 3.9072275161743164,
|
| 1199 |
+
"learning_rate": 1.507537688442211e-05,
|
| 1200 |
+
"loss": 5.6212,
|
| 1201 |
+
"step": 80
|
| 1202 |
+
},
|
| 1203 |
+
{
|
| 1204 |
+
"epoch": 0.0009141812364301222,
|
| 1205 |
+
"eval_loss": 5.597079753875732,
|
| 1206 |
+
"eval_runtime": 3190.1642,
|
| 1207 |
+
"eval_samples_per_second": 1.724,
|
| 1208 |
+
"eval_steps_per_second": 1.724,
|
| 1209 |
+
"step": 80
|
| 1210 |
+
},
|
| 1211 |
+
{
|
| 1212 |
+
"epoch": 0.0009256085018854988,
|
| 1213 |
+
"grad_norm": 3.1518900394439697,
|
| 1214 |
+
"learning_rate": 1.4949748743718595e-05,
|
| 1215 |
+
"loss": 5.0651,
|
| 1216 |
+
"step": 81
|
| 1217 |
+
},
|
| 1218 |
+
{
|
| 1219 |
+
"epoch": 0.0009256085018854988,
|
| 1220 |
+
"eval_loss": 5.56900691986084,
|
| 1221 |
+
"eval_runtime": 3189.2121,
|
| 1222 |
+
"eval_samples_per_second": 1.725,
|
| 1223 |
+
"eval_steps_per_second": 1.725,
|
| 1224 |
+
"step": 81
|
| 1225 |
+
},
|
| 1226 |
+
{
|
| 1227 |
+
"epoch": 0.0009370357673408753,
|
| 1228 |
+
"grad_norm": 2.539473295211792,
|
| 1229 |
+
"learning_rate": 1.4824120603015077e-05,
|
| 1230 |
+
"loss": 4.0285,
|
| 1231 |
+
"step": 82
|
| 1232 |
+
},
|
| 1233 |
+
{
|
| 1234 |
+
"epoch": 0.0009370357673408753,
|
| 1235 |
+
"eval_loss": 5.540792942047119,
|
| 1236 |
+
"eval_runtime": 3188.8344,
|
| 1237 |
+
"eval_samples_per_second": 1.725,
|
| 1238 |
+
"eval_steps_per_second": 1.725,
|
| 1239 |
+
"step": 82
|
| 1240 |
+
},
|
| 1241 |
+
{
|
| 1242 |
+
"epoch": 0.0009484630327962519,
|
| 1243 |
+
"grad_norm": 4.24508810043335,
|
| 1244 |
+
"learning_rate": 1.4698492462311558e-05,
|
| 1245 |
+
"loss": 6.0955,
|
| 1246 |
+
"step": 83
|
| 1247 |
+
},
|
| 1248 |
+
{
|
| 1249 |
+
"epoch": 0.0009484630327962519,
|
| 1250 |
+
"eval_loss": 5.512935638427734,
|
| 1251 |
+
"eval_runtime": 3191.1876,
|
| 1252 |
+
"eval_samples_per_second": 1.723,
|
| 1253 |
+
"eval_steps_per_second": 1.723,
|
| 1254 |
+
"step": 83
|
| 1255 |
+
},
|
| 1256 |
+
{
|
| 1257 |
+
"epoch": 0.0009598902982516284,
|
| 1258 |
+
"grad_norm": 3.5962705612182617,
|
| 1259 |
+
"learning_rate": 1.457286432160804e-05,
|
| 1260 |
+
"loss": 5.3177,
|
| 1261 |
+
"step": 84
|
| 1262 |
+
},
|
| 1263 |
+
{
|
| 1264 |
+
"epoch": 0.0009598902982516284,
|
| 1265 |
+
"eval_loss": 5.484694004058838,
|
| 1266 |
+
"eval_runtime": 3191.2979,
|
| 1267 |
+
"eval_samples_per_second": 1.723,
|
| 1268 |
+
"eval_steps_per_second": 1.723,
|
| 1269 |
+
"step": 84
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 0.0009713175637070049,
|
| 1273 |
+
"grad_norm": 4.158171653747559,
|
| 1274 |
+
"learning_rate": 1.4447236180904523e-05,
|
| 1275 |
+
"loss": 5.8912,
|
| 1276 |
+
"step": 85
|
| 1277 |
+
},
|
| 1278 |
+
{
|
| 1279 |
+
"epoch": 0.0009713175637070049,
|
| 1280 |
+
"eval_loss": 5.456665515899658,
|
| 1281 |
+
"eval_runtime": 3192.0268,
|
| 1282 |
+
"eval_samples_per_second": 1.723,
|
| 1283 |
+
"eval_steps_per_second": 1.723,
|
| 1284 |
+
"step": 85
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 0.0009827448291623814,
|
| 1288 |
+
"grad_norm": 4.112974643707275,
|
| 1289 |
+
"learning_rate": 1.4321608040201007e-05,
|
| 1290 |
+
"loss": 5.9361,
|
| 1291 |
+
"step": 86
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 0.0009827448291623814,
|
| 1295 |
+
"eval_loss": 5.428305149078369,
|
| 1296 |
+
"eval_runtime": 3189.75,
|
| 1297 |
+
"eval_samples_per_second": 1.724,
|
| 1298 |
+
"eval_steps_per_second": 1.724,
|
| 1299 |
+
"step": 86
|
| 1300 |
+
},
|
| 1301 |
+
{
|
| 1302 |
+
"epoch": 0.000994172094617758,
|
| 1303 |
+
"grad_norm": 3.924593925476074,
|
| 1304 |
+
"learning_rate": 1.4195979899497489e-05,
|
| 1305 |
+
"loss": 5.4892,
|
| 1306 |
+
"step": 87
|
| 1307 |
+
},
|
| 1308 |
+
{
|
| 1309 |
+
"epoch": 0.000994172094617758,
|
| 1310 |
+
"eval_loss": 5.400221824645996,
|
| 1311 |
+
"eval_runtime": 3191.2904,
|
| 1312 |
+
"eval_samples_per_second": 1.723,
|
| 1313 |
+
"eval_steps_per_second": 1.723,
|
| 1314 |
+
"step": 87
|
| 1315 |
+
},
|
| 1316 |
+
{
|
| 1317 |
+
"epoch": 0.0010055993600731345,
|
| 1318 |
+
"grad_norm": 5.291077613830566,
|
| 1319 |
+
"learning_rate": 1.407035175879397e-05,
|
| 1320 |
+
"loss": 6.7912,
|
| 1321 |
+
"step": 88
|
| 1322 |
+
},
|
| 1323 |
+
{
|
| 1324 |
+
"epoch": 0.0010055993600731345,
|
| 1325 |
+
"eval_loss": 5.371959686279297,
|
| 1326 |
+
"eval_runtime": 3188.0583,
|
| 1327 |
+
"eval_samples_per_second": 1.725,
|
| 1328 |
+
"eval_steps_per_second": 1.725,
|
| 1329 |
+
"step": 88
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 0.001017026625528511,
|
| 1333 |
+
"grad_norm": 3.935314893722534,
|
| 1334 |
+
"learning_rate": 1.3944723618090452e-05,
|
| 1335 |
+
"loss": 5.2535,
|
| 1336 |
+
"step": 89
|
| 1337 |
+
},
|
| 1338 |
+
{
|
| 1339 |
+
"epoch": 0.001017026625528511,
|
| 1340 |
+
"eval_loss": 5.343928337097168,
|
| 1341 |
+
"eval_runtime": 3186.5407,
|
| 1342 |
+
"eval_samples_per_second": 1.726,
|
| 1343 |
+
"eval_steps_per_second": 1.726,
|
| 1344 |
+
"step": 89
|
| 1345 |
+
},
|
| 1346 |
+
{
|
| 1347 |
+
"epoch": 0.0010284538909838875,
|
| 1348 |
+
"grad_norm": 4.988033771514893,
|
| 1349 |
+
"learning_rate": 1.3819095477386935e-05,
|
| 1350 |
+
"loss": 6.5576,
|
| 1351 |
+
"step": 90
|
| 1352 |
+
},
|
| 1353 |
+
{
|
| 1354 |
+
"epoch": 0.0010284538909838875,
|
| 1355 |
+
"eval_loss": 5.315735816955566,
|
| 1356 |
+
"eval_runtime": 3190.1379,
|
| 1357 |
+
"eval_samples_per_second": 1.724,
|
| 1358 |
+
"eval_steps_per_second": 1.724,
|
| 1359 |
+
"step": 90
|
| 1360 |
+
},
|
| 1361 |
+
{
|
| 1362 |
+
"epoch": 0.001039881156439264,
|
| 1363 |
+
"grad_norm": 3.571462631225586,
|
| 1364 |
+
"learning_rate": 1.369346733668342e-05,
|
| 1365 |
+
"loss": 5.0059,
|
| 1366 |
+
"step": 91
|
| 1367 |
+
},
|
| 1368 |
+
{
|
| 1369 |
+
"epoch": 0.001039881156439264,
|
| 1370 |
+
"eval_loss": 5.287474632263184,
|
| 1371 |
+
"eval_runtime": 3183.8947,
|
| 1372 |
+
"eval_samples_per_second": 1.727,
|
| 1373 |
+
"eval_steps_per_second": 1.727,
|
| 1374 |
+
"step": 91
|
| 1375 |
+
},
|
| 1376 |
+
{
|
| 1377 |
+
"epoch": 0.0010513084218946407,
|
| 1378 |
+
"grad_norm": 3.0511598587036133,
|
| 1379 |
+
"learning_rate": 1.3567839195979901e-05,
|
| 1380 |
+
"loss": 4.255,
|
| 1381 |
+
"step": 92
|
| 1382 |
+
},
|
| 1383 |
+
{
|
| 1384 |
+
"epoch": 0.0010513084218946407,
|
| 1385 |
+
"eval_loss": 5.25911283493042,
|
| 1386 |
+
"eval_runtime": 3188.1641,
|
| 1387 |
+
"eval_samples_per_second": 1.725,
|
| 1388 |
+
"eval_steps_per_second": 1.725,
|
| 1389 |
+
"step": 92
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 0.0010627356873500172,
|
| 1393 |
+
"grad_norm": 3.8936984539031982,
|
| 1394 |
+
"learning_rate": 1.3442211055276382e-05,
|
| 1395 |
+
"loss": 5.0144,
|
| 1396 |
+
"step": 93
|
| 1397 |
+
},
|
| 1398 |
+
{
|
| 1399 |
+
"epoch": 0.0010627356873500172,
|
| 1400 |
+
"eval_loss": 5.231190204620361,
|
| 1401 |
+
"eval_runtime": 3178.9927,
|
| 1402 |
+
"eval_samples_per_second": 1.73,
|
| 1403 |
+
"eval_steps_per_second": 1.73,
|
| 1404 |
+
"step": 93
|
| 1405 |
+
},
|
| 1406 |
+
{
|
| 1407 |
+
"epoch": 0.0010741629528053936,
|
| 1408 |
+
"grad_norm": 3.204448699951172,
|
| 1409 |
+
"learning_rate": 1.3316582914572864e-05,
|
| 1410 |
+
"loss": 4.539,
|
| 1411 |
+
"step": 94
|
| 1412 |
+
},
|
| 1413 |
+
{
|
| 1414 |
+
"epoch": 0.0010741629528053936,
|
| 1415 |
+
"eval_loss": 5.203569412231445,
|
| 1416 |
+
"eval_runtime": 3181.9254,
|
| 1417 |
+
"eval_samples_per_second": 1.729,
|
| 1418 |
+
"eval_steps_per_second": 1.729,
|
| 1419 |
+
"step": 94
|
| 1420 |
+
},
|
| 1421 |
+
{
|
| 1422 |
+
"epoch": 0.0010855902182607701,
|
| 1423 |
+
"grad_norm": 5.711158752441406,
|
| 1424 |
+
"learning_rate": 1.3190954773869347e-05,
|
| 1425 |
+
"loss": 7.1367,
|
| 1426 |
+
"step": 95
|
| 1427 |
+
},
|
| 1428 |
+
{
|
| 1429 |
+
"epoch": 0.0010855902182607701,
|
| 1430 |
+
"eval_loss": 5.176050662994385,
|
| 1431 |
+
"eval_runtime": 3182.616,
|
| 1432 |
+
"eval_samples_per_second": 1.728,
|
| 1433 |
+
"eval_steps_per_second": 1.728,
|
| 1434 |
+
"step": 95
|
| 1435 |
+
},
|
| 1436 |
+
{
|
| 1437 |
+
"epoch": 0.0010970174837161468,
|
| 1438 |
+
"grad_norm": 4.6051435470581055,
|
| 1439 |
+
"learning_rate": 1.306532663316583e-05,
|
| 1440 |
+
"loss": 5.5839,
|
| 1441 |
+
"step": 96
|
| 1442 |
+
},
|
| 1443 |
+
{
|
| 1444 |
+
"epoch": 0.0010970174837161468,
|
| 1445 |
+
"eval_loss": 5.148005962371826,
|
| 1446 |
+
"eval_runtime": 3185.2573,
|
| 1447 |
+
"eval_samples_per_second": 1.727,
|
| 1448 |
+
"eval_steps_per_second": 1.727,
|
| 1449 |
+
"step": 96
|
| 1450 |
+
},
|
| 1451 |
+
{
|
| 1452 |
+
"epoch": 0.0011084447491715233,
|
| 1453 |
+
"grad_norm": 2.9833264350891113,
|
| 1454 |
+
"learning_rate": 1.2939698492462313e-05,
|
| 1455 |
+
"loss": 4.1461,
|
| 1456 |
+
"step": 97
|
| 1457 |
+
},
|
| 1458 |
+
{
|
| 1459 |
+
"epoch": 0.0011084447491715233,
|
| 1460 |
+
"eval_loss": 5.120667934417725,
|
| 1461 |
+
"eval_runtime": 3188.7644,
|
| 1462 |
+
"eval_samples_per_second": 1.725,
|
| 1463 |
+
"eval_steps_per_second": 1.725,
|
| 1464 |
+
"step": 97
|
| 1465 |
+
},
|
| 1466 |
+
{
|
| 1467 |
+
"epoch": 0.0011198720146268998,
|
| 1468 |
+
"grad_norm": 3.4609251022338867,
|
| 1469 |
+
"learning_rate": 1.2814070351758795e-05,
|
| 1470 |
+
"loss": 4.3763,
|
| 1471 |
+
"step": 98
|
| 1472 |
+
},
|
| 1473 |
+
{
|
| 1474 |
+
"epoch": 0.0011198720146268998,
|
| 1475 |
+
"eval_loss": 5.093635559082031,
|
| 1476 |
+
"eval_runtime": 3186.9357,
|
| 1477 |
+
"eval_samples_per_second": 1.726,
|
| 1478 |
+
"eval_steps_per_second": 1.726,
|
| 1479 |
+
"step": 98
|
| 1480 |
+
},
|
| 1481 |
+
{
|
| 1482 |
+
"epoch": 0.0011312992800822763,
|
| 1483 |
+
"grad_norm": 3.9000020027160645,
|
| 1484 |
+
"learning_rate": 1.2688442211055276e-05,
|
| 1485 |
+
"loss": 4.8055,
|
| 1486 |
+
"step": 99
|
| 1487 |
+
},
|
| 1488 |
+
{
|
| 1489 |
+
"epoch": 0.0011312992800822763,
|
| 1490 |
+
"eval_loss": 5.06650447845459,
|
| 1491 |
+
"eval_runtime": 3189.8792,
|
| 1492 |
+
"eval_samples_per_second": 1.724,
|
| 1493 |
+
"eval_steps_per_second": 1.724,
|
| 1494 |
+
"step": 99
|
| 1495 |
+
},
|
| 1496 |
+
{
|
| 1497 |
+
"epoch": 0.0011427265455376528,
|
| 1498 |
+
"grad_norm": 4.556962966918945,
|
| 1499 |
+
"learning_rate": 1.2562814070351759e-05,
|
| 1500 |
+
"loss": 5.1023,
|
| 1501 |
+
"step": 100
|
| 1502 |
+
},
|
| 1503 |
+
{
|
| 1504 |
+
"epoch": 0.0011427265455376528,
|
| 1505 |
+
"eval_loss": 5.03890323638916,
|
| 1506 |
+
"eval_runtime": 3185.537,
|
| 1507 |
+
"eval_samples_per_second": 1.727,
|
| 1508 |
+
"eval_steps_per_second": 1.727,
|
| 1509 |
+
"step": 100
|
| 1510 |
+
},
|
| 1511 |
+
{
|
| 1512 |
+
"epoch": 0.0011541538109930295,
|
| 1513 |
+
"grad_norm": 3.0480575561523438,
|
| 1514 |
+
"learning_rate": 1.2437185929648242e-05,
|
| 1515 |
+
"loss": 3.8963,
|
| 1516 |
+
"step": 101
|
| 1517 |
+
},
|
| 1518 |
+
{
|
| 1519 |
+
"epoch": 0.0011541538109930295,
|
| 1520 |
+
"eval_loss": 5.011804580688477,
|
| 1521 |
+
"eval_runtime": 3186.5554,
|
| 1522 |
+
"eval_samples_per_second": 1.726,
|
| 1523 |
+
"eval_steps_per_second": 1.726,
|
| 1524 |
+
"step": 101
|
| 1525 |
+
},
|
| 1526 |
+
{
|
| 1527 |
+
"epoch": 0.001165581076448406,
|
| 1528 |
+
"grad_norm": 4.384181499481201,
|
| 1529 |
+
"learning_rate": 1.2311557788944725e-05,
|
| 1530 |
+
"loss": 5.3644,
|
| 1531 |
+
"step": 102
|
| 1532 |
+
},
|
| 1533 |
+
{
|
| 1534 |
+
"epoch": 0.001165581076448406,
|
| 1535 |
+
"eval_loss": 4.984678745269775,
|
| 1536 |
+
"eval_runtime": 3185.3238,
|
| 1537 |
+
"eval_samples_per_second": 1.727,
|
| 1538 |
+
"eval_steps_per_second": 1.727,
|
| 1539 |
+
"step": 102
|
| 1540 |
+
},
|
| 1541 |
+
{
|
| 1542 |
+
"epoch": 0.0011770083419037824,
|
| 1543 |
+
"grad_norm": 3.9702224731445312,
|
| 1544 |
+
"learning_rate": 1.2185929648241207e-05,
|
| 1545 |
+
"loss": 4.6785,
|
| 1546 |
+
"step": 103
|
| 1547 |
+
},
|
| 1548 |
+
{
|
| 1549 |
+
"epoch": 0.0011770083419037824,
|
| 1550 |
+
"eval_loss": 4.957573890686035,
|
| 1551 |
+
"eval_runtime": 3183.6056,
|
| 1552 |
+
"eval_samples_per_second": 1.728,
|
| 1553 |
+
"eval_steps_per_second": 1.728,
|
| 1554 |
+
"step": 103
|
| 1555 |
+
},
|
| 1556 |
+
{
|
| 1557 |
+
"epoch": 0.001188435607359159,
|
| 1558 |
+
"grad_norm": 2.205033540725708,
|
| 1559 |
+
"learning_rate": 1.2060301507537688e-05,
|
| 1560 |
+
"loss": 3.2692,
|
| 1561 |
+
"step": 104
|
| 1562 |
+
},
|
| 1563 |
+
{
|
| 1564 |
+
"epoch": 0.001188435607359159,
|
| 1565 |
+
"eval_loss": 4.930599212646484,
|
| 1566 |
+
"eval_runtime": 3187.0691,
|
| 1567 |
+
"eval_samples_per_second": 1.726,
|
| 1568 |
+
"eval_steps_per_second": 1.726,
|
| 1569 |
+
"step": 104
|
| 1570 |
+
},
|
| 1571 |
+
{
|
| 1572 |
+
"epoch": 0.0011998628728145354,
|
| 1573 |
+
"grad_norm": 5.425383567810059,
|
| 1574 |
+
"learning_rate": 1.1934673366834171e-05,
|
| 1575 |
+
"loss": 5.8127,
|
| 1576 |
+
"step": 105
|
| 1577 |
+
},
|
| 1578 |
+
{
|
| 1579 |
+
"epoch": 0.0011998628728145354,
|
| 1580 |
+
"eval_loss": 4.903759002685547,
|
| 1581 |
+
"eval_runtime": 3191.0573,
|
| 1582 |
+
"eval_samples_per_second": 1.724,
|
| 1583 |
+
"eval_steps_per_second": 1.724,
|
| 1584 |
+
"step": 105
|
| 1585 |
+
},
|
| 1586 |
+
{
|
| 1587 |
+
"epoch": 0.001211290138269912,
|
| 1588 |
+
"grad_norm": 2.0843021869659424,
|
| 1589 |
+
"learning_rate": 1.1809045226130654e-05,
|
| 1590 |
+
"loss": 3.2769,
|
| 1591 |
+
"step": 106
|
| 1592 |
+
},
|
| 1593 |
+
{
|
| 1594 |
+
"epoch": 0.001211290138269912,
|
| 1595 |
+
"eval_loss": 4.877487659454346,
|
| 1596 |
+
"eval_runtime": 3192.0095,
|
| 1597 |
+
"eval_samples_per_second": 1.723,
|
| 1598 |
+
"eval_steps_per_second": 1.723,
|
| 1599 |
+
"step": 106
|
| 1600 |
+
},
|
| 1601 |
+
{
|
| 1602 |
+
"epoch": 0.0012227174037252886,
|
| 1603 |
+
"grad_norm": 5.174865245819092,
|
| 1604 |
+
"learning_rate": 1.1683417085427137e-05,
|
| 1605 |
+
"loss": 5.5865,
|
| 1606 |
+
"step": 107
|
| 1607 |
+
},
|
| 1608 |
+
{
|
| 1609 |
+
"epoch": 0.0012227174037252886,
|
| 1610 |
+
"eval_loss": 4.85078763961792,
|
| 1611 |
+
"eval_runtime": 3181.3647,
|
| 1612 |
+
"eval_samples_per_second": 1.729,
|
| 1613 |
+
"eval_steps_per_second": 1.729,
|
| 1614 |
+
"step": 107
|
| 1615 |
+
},
|
| 1616 |
+
{
|
| 1617 |
+
"epoch": 0.001234144669180665,
|
| 1618 |
+
"grad_norm": 4.530418395996094,
|
| 1619 |
+
"learning_rate": 1.1557788944723619e-05,
|
| 1620 |
+
"loss": 4.9615,
|
| 1621 |
+
"step": 108
|
| 1622 |
+
},
|
| 1623 |
+
{
|
| 1624 |
+
"epoch": 0.001234144669180665,
|
| 1625 |
+
"eval_loss": 4.824298858642578,
|
| 1626 |
+
"eval_runtime": 3188.1147,
|
| 1627 |
+
"eval_samples_per_second": 1.725,
|
| 1628 |
+
"eval_steps_per_second": 1.725,
|
| 1629 |
+
"step": 108
|
| 1630 |
+
},
|
| 1631 |
+
{
|
| 1632 |
+
"epoch": 0.0012455719346360415,
|
| 1633 |
+
"grad_norm": 4.7975172996521,
|
| 1634 |
+
"learning_rate": 1.14321608040201e-05,
|
| 1635 |
+
"loss": 5.4098,
|
| 1636 |
+
"step": 109
|
| 1637 |
+
},
|
| 1638 |
+
{
|
| 1639 |
+
"epoch": 0.0012455719346360415,
|
| 1640 |
+
"eval_loss": 4.7980499267578125,
|
| 1641 |
+
"eval_runtime": 3187.1944,
|
| 1642 |
+
"eval_samples_per_second": 1.726,
|
| 1643 |
+
"eval_steps_per_second": 1.726,
|
| 1644 |
+
"step": 109
|
| 1645 |
+
},
|
| 1646 |
+
{
|
| 1647 |
+
"epoch": 0.0012569992000914182,
|
| 1648 |
+
"grad_norm": 4.517176151275635,
|
| 1649 |
+
"learning_rate": 1.1306532663316583e-05,
|
| 1650 |
+
"loss": 5.0089,
|
| 1651 |
+
"step": 110
|
| 1652 |
+
},
|
| 1653 |
+
{
|
| 1654 |
+
"epoch": 0.0012569992000914182,
|
| 1655 |
+
"eval_loss": 4.771963596343994,
|
| 1656 |
+
"eval_runtime": 3195.7844,
|
| 1657 |
+
"eval_samples_per_second": 1.721,
|
| 1658 |
+
"eval_steps_per_second": 1.721,
|
| 1659 |
+
"step": 110
|
| 1660 |
+
},
|
| 1661 |
+
{
|
| 1662 |
+
"epoch": 0.0012684264655467947,
|
| 1663 |
+
"grad_norm": 4.071757793426514,
|
| 1664 |
+
"learning_rate": 1.1180904522613066e-05,
|
| 1665 |
+
"loss": 4.3814,
|
| 1666 |
+
"step": 111
|
| 1667 |
+
},
|
| 1668 |
+
{
|
| 1669 |
+
"epoch": 0.0012684264655467947,
|
| 1670 |
+
"eval_loss": 4.745976448059082,
|
| 1671 |
+
"eval_runtime": 3197.3702,
|
| 1672 |
+
"eval_samples_per_second": 1.72,
|
| 1673 |
+
"eval_steps_per_second": 1.72,
|
| 1674 |
+
"step": 111
|
| 1675 |
+
},
|
| 1676 |
+
{
|
| 1677 |
+
"epoch": 0.0012798537310021712,
|
| 1678 |
+
"grad_norm": 3.3903536796569824,
|
| 1679 |
+
"learning_rate": 1.105527638190955e-05,
|
| 1680 |
+
"loss": 4.0058,
|
| 1681 |
+
"step": 112
|
| 1682 |
+
},
|
| 1683 |
+
{
|
| 1684 |
+
"epoch": 0.0012798537310021712,
|
| 1685 |
+
"eval_loss": 4.720351696014404,
|
| 1686 |
+
"eval_runtime": 3192.7959,
|
| 1687 |
+
"eval_samples_per_second": 1.723,
|
| 1688 |
+
"eval_steps_per_second": 1.723,
|
| 1689 |
+
"step": 112
|
| 1690 |
+
},
|
| 1691 |
+
{
|
| 1692 |
+
"epoch": 0.0012912809964575477,
|
| 1693 |
+
"grad_norm": 3.1727375984191895,
|
| 1694 |
+
"learning_rate": 1.0929648241206031e-05,
|
| 1695 |
+
"loss": 3.7689,
|
| 1696 |
+
"step": 113
|
| 1697 |
+
},
|
| 1698 |
+
{
|
| 1699 |
+
"epoch": 0.0012912809964575477,
|
| 1700 |
+
"eval_loss": 4.694741249084473,
|
| 1701 |
+
"eval_runtime": 3189.1299,
|
| 1702 |
+
"eval_samples_per_second": 1.725,
|
| 1703 |
+
"eval_steps_per_second": 1.725,
|
| 1704 |
+
"step": 113
|
| 1705 |
+
},
|
| 1706 |
+
{
|
| 1707 |
+
"epoch": 0.0013027082619129242,
|
| 1708 |
+
"grad_norm": 2.47040057182312,
|
| 1709 |
+
"learning_rate": 1.0804020100502512e-05,
|
| 1710 |
+
"loss": 3.3884,
|
| 1711 |
+
"step": 114
|
| 1712 |
+
},
|
| 1713 |
+
{
|
| 1714 |
+
"epoch": 0.0013027082619129242,
|
| 1715 |
+
"eval_loss": 4.6697916984558105,
|
| 1716 |
+
"eval_runtime": 3190.5928,
|
| 1717 |
+
"eval_samples_per_second": 1.724,
|
| 1718 |
+
"eval_steps_per_second": 1.724,
|
| 1719 |
+
"step": 114
|
| 1720 |
+
},
|
| 1721 |
+
{
|
| 1722 |
+
"epoch": 0.0013141355273683009,
|
| 1723 |
+
"grad_norm": 3.910038471221924,
|
| 1724 |
+
"learning_rate": 1.0678391959798995e-05,
|
| 1725 |
+
"loss": 4.1467,
|
| 1726 |
+
"step": 115
|
| 1727 |
+
},
|
| 1728 |
+
{
|
| 1729 |
+
"epoch": 0.0013141355273683009,
|
| 1730 |
+
"eval_loss": 4.645045280456543,
|
| 1731 |
+
"eval_runtime": 3188.0361,
|
| 1732 |
+
"eval_samples_per_second": 1.725,
|
| 1733 |
+
"eval_steps_per_second": 1.725,
|
| 1734 |
+
"step": 115
|
| 1735 |
+
},
|
| 1736 |
+
{
|
| 1737 |
+
"epoch": 0.0013255627928236773,
|
| 1738 |
+
"grad_norm": 5.768658638000488,
|
| 1739 |
+
"learning_rate": 1.0552763819095479e-05,
|
| 1740 |
+
"loss": 5.5406,
|
| 1741 |
+
"step": 116
|
| 1742 |
+
},
|
| 1743 |
+
{
|
| 1744 |
+
"epoch": 0.0013255627928236773,
|
| 1745 |
+
"eval_loss": 4.620331764221191,
|
| 1746 |
+
"eval_runtime": 3188.8345,
|
| 1747 |
+
"eval_samples_per_second": 1.725,
|
| 1748 |
+
"eval_steps_per_second": 1.725,
|
| 1749 |
+
"step": 116
|
| 1750 |
+
},
|
| 1751 |
+
{
|
| 1752 |
+
"epoch": 0.0013369900582790538,
|
| 1753 |
+
"grad_norm": 4.449304580688477,
|
| 1754 |
+
"learning_rate": 1.042713567839196e-05,
|
| 1755 |
+
"loss": 4.4227,
|
| 1756 |
+
"step": 117
|
| 1757 |
+
},
|
| 1758 |
+
{
|
| 1759 |
+
"epoch": 0.0013369900582790538,
|
| 1760 |
+
"eval_loss": 4.595801830291748,
|
| 1761 |
+
"eval_runtime": 3189.9885,
|
| 1762 |
+
"eval_samples_per_second": 1.724,
|
| 1763 |
+
"eval_steps_per_second": 1.724,
|
| 1764 |
+
"step": 117
|
| 1765 |
+
},
|
| 1766 |
+
{
|
| 1767 |
+
"epoch": 0.0013484173237344303,
|
| 1768 |
+
"grad_norm": 5.598243236541748,
|
| 1769 |
+
"learning_rate": 1.0301507537688443e-05,
|
| 1770 |
+
"loss": 5.0256,
|
| 1771 |
+
"step": 118
|
| 1772 |
+
},
|
| 1773 |
+
{
|
| 1774 |
+
"epoch": 0.0013484173237344303,
|
| 1775 |
+
"eval_loss": 4.571651458740234,
|
| 1776 |
+
"eval_runtime": 3184.1254,
|
| 1777 |
+
"eval_samples_per_second": 1.727,
|
| 1778 |
+
"eval_steps_per_second": 1.727,
|
| 1779 |
+
"step": 118
|
| 1780 |
+
},
|
| 1781 |
+
{
|
| 1782 |
+
"epoch": 0.0013598445891898068,
|
| 1783 |
+
"grad_norm": 2.351072311401367,
|
| 1784 |
+
"learning_rate": 1.0175879396984924e-05,
|
| 1785 |
+
"loss": 3.3235,
|
| 1786 |
+
"step": 119
|
| 1787 |
+
},
|
| 1788 |
+
{
|
| 1789 |
+
"epoch": 0.0013598445891898068,
|
| 1790 |
+
"eval_loss": 4.5476908683776855,
|
| 1791 |
+
"eval_runtime": 3195.9101,
|
| 1792 |
+
"eval_samples_per_second": 1.721,
|
| 1793 |
+
"eval_steps_per_second": 1.721,
|
| 1794 |
+
"step": 119
|
| 1795 |
+
},
|
| 1796 |
+
{
|
| 1797 |
+
"epoch": 0.0013712718546451835,
|
| 1798 |
+
"grad_norm": 4.657642364501953,
|
| 1799 |
+
"learning_rate": 1.0050251256281408e-05,
|
| 1800 |
+
"loss": 4.6996,
|
| 1801 |
+
"step": 120
|
| 1802 |
+
},
|
| 1803 |
+
{
|
| 1804 |
+
"epoch": 0.0013712718546451835,
|
| 1805 |
+
"eval_loss": 4.524058818817139,
|
| 1806 |
+
"eval_runtime": 3187.7906,
|
| 1807 |
+
"eval_samples_per_second": 1.725,
|
| 1808 |
+
"eval_steps_per_second": 1.725,
|
| 1809 |
+
"step": 120
|
| 1810 |
+
},
|
| 1811 |
+
{
|
| 1812 |
+
"epoch": 0.00138269912010056,
|
| 1813 |
+
"grad_norm": 4.85261344909668,
|
| 1814 |
+
"learning_rate": 9.92462311557789e-06,
|
| 1815 |
+
"loss": 4.9033,
|
| 1816 |
+
"step": 121
|
| 1817 |
+
},
|
| 1818 |
+
{
|
| 1819 |
+
"epoch": 0.00138269912010056,
|
| 1820 |
+
"eval_loss": 4.500573635101318,
|
| 1821 |
+
"eval_runtime": 3191.7978,
|
| 1822 |
+
"eval_samples_per_second": 1.723,
|
| 1823 |
+
"eval_steps_per_second": 1.723,
|
| 1824 |
+
"step": 121
|
| 1825 |
+
},
|
| 1826 |
+
{
|
| 1827 |
+
"epoch": 0.0013941263855559364,
|
| 1828 |
+
"grad_norm": 2.878826379776001,
|
| 1829 |
+
"learning_rate": 9.798994974874372e-06,
|
| 1830 |
+
"loss": 3.7129,
|
| 1831 |
+
"step": 122
|
| 1832 |
+
},
|
| 1833 |
+
{
|
| 1834 |
+
"epoch": 0.0013941263855559364,
|
| 1835 |
+
"eval_loss": 4.477457046508789,
|
| 1836 |
+
"eval_runtime": 3188.7301,
|
| 1837 |
+
"eval_samples_per_second": 1.725,
|
| 1838 |
+
"eval_steps_per_second": 1.725,
|
| 1839 |
+
"step": 122
|
| 1840 |
+
},
|
| 1841 |
+
{
|
| 1842 |
+
"epoch": 0.001405553651011313,
|
| 1843 |
+
"grad_norm": 4.454727649688721,
|
| 1844 |
+
"learning_rate": 9.673366834170855e-06,
|
| 1845 |
+
"loss": 4.4705,
|
| 1846 |
+
"step": 123
|
| 1847 |
+
},
|
| 1848 |
+
{
|
| 1849 |
+
"epoch": 0.001405553651011313,
|
| 1850 |
+
"eval_loss": 4.454273223876953,
|
| 1851 |
+
"eval_runtime": 3193.5195,
|
| 1852 |
+
"eval_samples_per_second": 1.722,
|
| 1853 |
+
"eval_steps_per_second": 1.722,
|
| 1854 |
+
"step": 123
|
| 1855 |
+
},
|
| 1856 |
+
{
|
| 1857 |
+
"epoch": 0.0014169809164666896,
|
| 1858 |
+
"grad_norm": 5.7791547775268555,
|
| 1859 |
+
"learning_rate": 9.547738693467337e-06,
|
| 1860 |
+
"loss": 5.1999,
|
| 1861 |
+
"step": 124
|
| 1862 |
+
},
|
| 1863 |
+
{
|
| 1864 |
+
"epoch": 0.0014169809164666896,
|
| 1865 |
+
"eval_loss": 4.431214332580566,
|
| 1866 |
+
"eval_runtime": 3197.3551,
|
| 1867 |
+
"eval_samples_per_second": 1.72,
|
| 1868 |
+
"eval_steps_per_second": 1.72,
|
| 1869 |
+
"step": 124
|
| 1870 |
+
},
|
| 1871 |
+
{
|
| 1872 |
+
"epoch": 0.001428408181922066,
|
| 1873 |
+
"grad_norm": 4.197294235229492,
|
| 1874 |
+
"learning_rate": 9.42211055276382e-06,
|
| 1875 |
+
"loss": 4.0018,
|
| 1876 |
+
"step": 125
|
| 1877 |
+
},
|
| 1878 |
+
{
|
| 1879 |
+
"epoch": 0.001428408181922066,
|
| 1880 |
+
"eval_loss": 4.408187389373779,
|
| 1881 |
+
"eval_runtime": 3199.7906,
|
| 1882 |
+
"eval_samples_per_second": 1.719,
|
| 1883 |
+
"eval_steps_per_second": 1.719,
|
| 1884 |
+
"step": 125
|
| 1885 |
+
},
|
| 1886 |
+
{
|
| 1887 |
+
"epoch": 0.0014398354473774426,
|
| 1888 |
+
"grad_norm": 4.467915058135986,
|
| 1889 |
+
"learning_rate": 9.296482412060301e-06,
|
| 1890 |
+
"loss": 4.3018,
|
| 1891 |
+
"step": 126
|
| 1892 |
+
},
|
| 1893 |
+
{
|
| 1894 |
+
"epoch": 0.0014398354473774426,
|
| 1895 |
+
"eval_loss": 4.386054515838623,
|
| 1896 |
+
"eval_runtime": 3193.7722,
|
| 1897 |
+
"eval_samples_per_second": 1.722,
|
| 1898 |
+
"eval_steps_per_second": 1.722,
|
| 1899 |
+
"step": 126
|
| 1900 |
+
},
|
| 1901 |
+
{
|
| 1902 |
+
"epoch": 0.001451262712832819,
|
| 1903 |
+
"grad_norm": 5.470479488372803,
|
| 1904 |
+
"learning_rate": 9.170854271356784e-06,
|
| 1905 |
+
"loss": 4.8658,
|
| 1906 |
+
"step": 127
|
| 1907 |
+
},
|
| 1908 |
+
{
|
| 1909 |
+
"epoch": 0.001451262712832819,
|
| 1910 |
+
"eval_loss": 4.363833427429199,
|
| 1911 |
+
"eval_runtime": 3195.1881,
|
| 1912 |
+
"eval_samples_per_second": 1.721,
|
| 1913 |
+
"eval_steps_per_second": 1.721,
|
| 1914 |
+
"step": 127
|
| 1915 |
+
},
|
| 1916 |
+
{
|
| 1917 |
+
"epoch": 0.0014626899782881956,
|
| 1918 |
+
"grad_norm": 4.576855182647705,
|
| 1919 |
+
"learning_rate": 9.045226130653267e-06,
|
| 1920 |
+
"loss": 4.5801,
|
| 1921 |
+
"step": 128
|
| 1922 |
+
},
|
| 1923 |
+
{
|
| 1924 |
+
"epoch": 0.0014626899782881956,
|
| 1925 |
+
"eval_loss": 4.341481685638428,
|
| 1926 |
+
"eval_runtime": 3196.2749,
|
| 1927 |
+
"eval_samples_per_second": 1.721,
|
| 1928 |
+
"eval_steps_per_second": 1.721,
|
| 1929 |
+
"step": 128
|
| 1930 |
+
},
|
| 1931 |
+
{
|
| 1932 |
+
"epoch": 0.0014741172437435722,
|
| 1933 |
+
"grad_norm": 3.8720321655273438,
|
| 1934 |
+
"learning_rate": 8.919597989949749e-06,
|
| 1935 |
+
"loss": 3.9047,
|
| 1936 |
+
"step": 129
|
| 1937 |
+
},
|
| 1938 |
+
{
|
| 1939 |
+
"epoch": 0.0014741172437435722,
|
| 1940 |
+
"eval_loss": 4.319530010223389,
|
| 1941 |
+
"eval_runtime": 3192.3427,
|
| 1942 |
+
"eval_samples_per_second": 1.723,
|
| 1943 |
+
"eval_steps_per_second": 1.723,
|
| 1944 |
+
"step": 129
|
| 1945 |
+
},
|
| 1946 |
+
{
|
| 1947 |
+
"epoch": 0.0014855445091989487,
|
| 1948 |
+
"grad_norm": 5.404055595397949,
|
| 1949 |
+
"learning_rate": 8.793969849246232e-06,
|
| 1950 |
+
"loss": 4.5479,
|
| 1951 |
+
"step": 130
|
| 1952 |
+
},
|
| 1953 |
+
{
|
| 1954 |
+
"epoch": 0.0014855445091989487,
|
| 1955 |
+
"eval_loss": 4.298058032989502,
|
| 1956 |
+
"eval_runtime": 3192.0239,
|
| 1957 |
+
"eval_samples_per_second": 1.723,
|
| 1958 |
+
"eval_steps_per_second": 1.723,
|
| 1959 |
+
"step": 130
|
| 1960 |
+
},
|
| 1961 |
+
{
|
| 1962 |
+
"epoch": 0.0014969717746543252,
|
| 1963 |
+
"grad_norm": 5.212480068206787,
|
| 1964 |
+
"learning_rate": 8.668341708542713e-06,
|
| 1965 |
+
"loss": 4.6837,
|
| 1966 |
+
"step": 131
|
| 1967 |
+
},
|
| 1968 |
+
{
|
| 1969 |
+
"epoch": 0.0014969717746543252,
|
| 1970 |
+
"eval_loss": 4.276992321014404,
|
| 1971 |
+
"eval_runtime": 3190.8662,
|
| 1972 |
+
"eval_samples_per_second": 1.724,
|
| 1973 |
+
"eval_steps_per_second": 1.724,
|
| 1974 |
+
"step": 131
|
| 1975 |
+
},
|
| 1976 |
+
{
|
| 1977 |
+
"epoch": 0.0015083990401097017,
|
| 1978 |
+
"grad_norm": 5.532873153686523,
|
| 1979 |
+
"learning_rate": 8.542713567839196e-06,
|
| 1980 |
+
"loss": 4.5492,
|
| 1981 |
+
"step": 132
|
| 1982 |
+
},
|
| 1983 |
+
{
|
| 1984 |
+
"epoch": 0.0015083990401097017,
|
| 1985 |
+
"eval_loss": 4.256262302398682,
|
| 1986 |
+
"eval_runtime": 3195.153,
|
| 1987 |
+
"eval_samples_per_second": 1.721,
|
| 1988 |
+
"eval_steps_per_second": 1.721,
|
| 1989 |
+
"step": 132
|
| 1990 |
+
},
|
| 1991 |
+
{
|
| 1992 |
+
"epoch": 0.0015198263055650782,
|
| 1993 |
+
"grad_norm": 5.229096412658691,
|
| 1994 |
+
"learning_rate": 8.41708542713568e-06,
|
| 1995 |
+
"loss": 4.6645,
|
| 1996 |
+
"step": 133
|
| 1997 |
+
},
|
| 1998 |
+
{
|
| 1999 |
+
"epoch": 0.0015198263055650782,
|
| 2000 |
+
"eval_loss": 4.235621452331543,
|
| 2001 |
+
"eval_runtime": 3193.1225,
|
| 2002 |
+
"eval_samples_per_second": 1.722,
|
| 2003 |
+
"eval_steps_per_second": 1.722,
|
| 2004 |
+
"step": 133
|
| 2005 |
+
},
|
| 2006 |
+
{
|
| 2007 |
+
"epoch": 0.0015312535710204549,
|
| 2008 |
+
"grad_norm": 6.112283229827881,
|
| 2009 |
+
"learning_rate": 8.291457286432161e-06,
|
| 2010 |
+
"loss": 5.1063,
|
| 2011 |
+
"step": 134
|
| 2012 |
+
},
|
| 2013 |
+
{
|
| 2014 |
+
"epoch": 0.0015312535710204549,
|
| 2015 |
+
"eval_loss": 4.215306282043457,
|
| 2016 |
+
"eval_runtime": 3190.5362,
|
| 2017 |
+
"eval_samples_per_second": 1.724,
|
| 2018 |
+
"eval_steps_per_second": 1.724,
|
| 2019 |
+
"step": 134
|
| 2020 |
+
},
|
| 2021 |
+
{
|
| 2022 |
+
"epoch": 0.0015426808364758314,
|
| 2023 |
+
"grad_norm": 5.098965644836426,
|
| 2024 |
+
"learning_rate": 8.165829145728644e-06,
|
| 2025 |
+
"loss": 4.3275,
|
| 2026 |
+
"step": 135
|
| 2027 |
+
},
|
| 2028 |
+
{
|
| 2029 |
+
"epoch": 0.0015426808364758314,
|
| 2030 |
+
"eval_loss": 4.195265769958496,
|
| 2031 |
+
"eval_runtime": 3197.2965,
|
| 2032 |
+
"eval_samples_per_second": 1.72,
|
| 2033 |
+
"eval_steps_per_second": 1.72,
|
| 2034 |
+
"step": 135
|
| 2035 |
+
},
|
| 2036 |
+
{
|
| 2037 |
+
"epoch": 0.0015541081019312078,
|
| 2038 |
+
"grad_norm": 4.572518825531006,
|
| 2039 |
+
"learning_rate": 8.040201005025125e-06,
|
| 2040 |
+
"loss": 4.1709,
|
| 2041 |
+
"step": 136
|
| 2042 |
+
},
|
| 2043 |
+
{
|
| 2044 |
+
"epoch": 0.0015541081019312078,
|
| 2045 |
+
"eval_loss": 4.174986362457275,
|
| 2046 |
+
"eval_runtime": 3195.4093,
|
| 2047 |
+
"eval_samples_per_second": 1.721,
|
| 2048 |
+
"eval_steps_per_second": 1.721,
|
| 2049 |
+
"step": 136
|
| 2050 |
+
},
|
| 2051 |
+
{
|
| 2052 |
+
"epoch": 0.0015655353673865843,
|
| 2053 |
+
"grad_norm": 4.504931926727295,
|
| 2054 |
+
"learning_rate": 7.914572864321608e-06,
|
| 2055 |
+
"loss": 4.1334,
|
| 2056 |
+
"step": 137
|
| 2057 |
+
},
|
| 2058 |
+
{
|
| 2059 |
+
"epoch": 0.0015655353673865843,
|
| 2060 |
+
"eval_loss": 4.155473232269287,
|
| 2061 |
+
"eval_runtime": 3196.5363,
|
| 2062 |
+
"eval_samples_per_second": 1.721,
|
| 2063 |
+
"eval_steps_per_second": 1.721,
|
| 2064 |
+
"step": 137
|
| 2065 |
+
},
|
| 2066 |
+
{
|
| 2067 |
+
"epoch": 0.001576962632841961,
|
| 2068 |
+
"grad_norm": 4.817331790924072,
|
| 2069 |
+
"learning_rate": 7.788944723618092e-06,
|
| 2070 |
+
"loss": 4.0312,
|
| 2071 |
+
"step": 138
|
| 2072 |
+
},
|
| 2073 |
+
{
|
| 2074 |
+
"epoch": 0.001576962632841961,
|
| 2075 |
+
"eval_loss": 4.136098861694336,
|
| 2076 |
+
"eval_runtime": 3192.698,
|
| 2077 |
+
"eval_samples_per_second": 1.723,
|
| 2078 |
+
"eval_steps_per_second": 1.723,
|
| 2079 |
+
"step": 138
|
| 2080 |
+
},
|
| 2081 |
+
{
|
| 2082 |
+
"epoch": 0.0015883898982973375,
|
| 2083 |
+
"grad_norm": 5.8819146156311035,
|
| 2084 |
+
"learning_rate": 7.663316582914573e-06,
|
| 2085 |
+
"loss": 4.8895,
|
| 2086 |
+
"step": 139
|
| 2087 |
+
},
|
| 2088 |
+
{
|
| 2089 |
+
"epoch": 0.0015883898982973375,
|
| 2090 |
+
"eval_loss": 4.116922378540039,
|
| 2091 |
+
"eval_runtime": 3194.9621,
|
| 2092 |
+
"eval_samples_per_second": 1.721,
|
| 2093 |
+
"eval_steps_per_second": 1.721,
|
| 2094 |
+
"step": 139
|
| 2095 |
+
},
|
| 2096 |
+
{
|
| 2097 |
+
"epoch": 0.001599817163752714,
|
| 2098 |
+
"grad_norm": 4.634926795959473,
|
| 2099 |
+
"learning_rate": 7.537688442211055e-06,
|
| 2100 |
+
"loss": 4.1536,
|
| 2101 |
+
"step": 140
|
| 2102 |
+
},
|
| 2103 |
+
{
|
| 2104 |
+
"epoch": 0.001599817163752714,
|
| 2105 |
+
"eval_loss": 4.097559452056885,
|
| 2106 |
+
"eval_runtime": 3190.2406,
|
| 2107 |
+
"eval_samples_per_second": 1.724,
|
| 2108 |
+
"eval_steps_per_second": 1.724,
|
| 2109 |
+
"step": 140
|
| 2110 |
+
},
|
| 2111 |
+
{
|
| 2112 |
+
"epoch": 0.0016112444292080905,
|
| 2113 |
+
"grad_norm": 4.497166156768799,
|
| 2114 |
+
"learning_rate": 7.412060301507538e-06,
|
| 2115 |
+
"loss": 4.1384,
|
| 2116 |
+
"step": 141
|
| 2117 |
+
},
|
| 2118 |
+
{
|
| 2119 |
+
"epoch": 0.0016112444292080905,
|
| 2120 |
+
"eval_loss": 4.079128742218018,
|
| 2121 |
+
"eval_runtime": 3192.3172,
|
| 2122 |
+
"eval_samples_per_second": 1.723,
|
| 2123 |
+
"eval_steps_per_second": 1.723,
|
| 2124 |
+
"step": 141
|
| 2125 |
+
},
|
| 2126 |
+
{
|
| 2127 |
+
"epoch": 0.001622671694663467,
|
| 2128 |
+
"grad_norm": 5.713669300079346,
|
| 2129 |
+
"learning_rate": 7.28643216080402e-06,
|
| 2130 |
+
"loss": 4.7611,
|
| 2131 |
+
"step": 142
|
| 2132 |
+
},
|
| 2133 |
+
{
|
| 2134 |
+
"epoch": 0.001622671694663467,
|
| 2135 |
+
"eval_loss": 4.0609354972839355,
|
| 2136 |
+
"eval_runtime": 3191.9262,
|
| 2137 |
+
"eval_samples_per_second": 1.723,
|
| 2138 |
+
"eval_steps_per_second": 1.723,
|
| 2139 |
+
"step": 142
|
| 2140 |
+
},
|
| 2141 |
+
{
|
| 2142 |
+
"epoch": 0.0016340989601188436,
|
| 2143 |
+
"grad_norm": 4.149837017059326,
|
| 2144 |
+
"learning_rate": 7.160804020100504e-06,
|
| 2145 |
+
"loss": 3.8286,
|
| 2146 |
+
"step": 143
|
| 2147 |
+
},
|
| 2148 |
+
{
|
| 2149 |
+
"epoch": 0.0016340989601188436,
|
| 2150 |
+
"eval_loss": 4.042760372161865,
|
| 2151 |
+
"eval_runtime": 3188.8273,
|
| 2152 |
+
"eval_samples_per_second": 1.725,
|
| 2153 |
+
"eval_steps_per_second": 1.725,
|
| 2154 |
+
"step": 143
|
| 2155 |
+
},
|
| 2156 |
+
{
|
| 2157 |
+
"epoch": 0.0016455262255742201,
|
| 2158 |
+
"grad_norm": 6.028262138366699,
|
| 2159 |
+
"learning_rate": 7.035175879396985e-06,
|
| 2160 |
+
"loss": 4.6085,
|
| 2161 |
+
"step": 144
|
| 2162 |
+
},
|
| 2163 |
+
{
|
| 2164 |
+
"epoch": 0.0016455262255742201,
|
| 2165 |
+
"eval_loss": 4.024686336517334,
|
| 2166 |
+
"eval_runtime": 3191.547,
|
| 2167 |
+
"eval_samples_per_second": 1.723,
|
| 2168 |
+
"eval_steps_per_second": 1.723,
|
| 2169 |
+
"step": 144
|
| 2170 |
+
},
|
| 2171 |
+
{
|
| 2172 |
+
"epoch": 0.0016569534910295966,
|
| 2173 |
+
"grad_norm": 5.114198207855225,
|
| 2174 |
+
"learning_rate": 6.909547738693467e-06,
|
| 2175 |
+
"loss": 4.2915,
|
| 2176 |
+
"step": 145
|
| 2177 |
+
},
|
| 2178 |
+
{
|
| 2179 |
+
"epoch": 0.0016569534910295966,
|
| 2180 |
+
"eval_loss": 4.007183074951172,
|
| 2181 |
+
"eval_runtime": 3193.0349,
|
| 2182 |
+
"eval_samples_per_second": 1.722,
|
| 2183 |
+
"eval_steps_per_second": 1.722,
|
| 2184 |
+
"step": 145
|
| 2185 |
+
},
|
| 2186 |
+
{
|
| 2187 |
+
"epoch": 0.001668380756484973,
|
| 2188 |
+
"grad_norm": 5.462469100952148,
|
| 2189 |
+
"learning_rate": 6.7839195979899505e-06,
|
| 2190 |
+
"loss": 4.1471,
|
| 2191 |
+
"step": 146
|
| 2192 |
+
},
|
| 2193 |
+
{
|
| 2194 |
+
"epoch": 0.001668380756484973,
|
| 2195 |
+
"eval_loss": 3.9897186756134033,
|
| 2196 |
+
"eval_runtime": 3190.8896,
|
| 2197 |
+
"eval_samples_per_second": 1.724,
|
| 2198 |
+
"eval_steps_per_second": 1.724,
|
| 2199 |
+
"step": 146
|
| 2200 |
+
},
|
| 2201 |
+
{
|
| 2202 |
+
"epoch": 0.0016798080219403496,
|
| 2203 |
+
"grad_norm": 0.8918362855911255,
|
| 2204 |
+
"learning_rate": 6.658291457286432e-06,
|
| 2205 |
+
"loss": 2.468,
|
| 2206 |
+
"step": 147
|
| 2207 |
+
},
|
| 2208 |
+
{
|
| 2209 |
+
"epoch": 0.0016798080219403496,
|
| 2210 |
+
"eval_loss": 3.9733145236968994,
|
| 2211 |
+
"eval_runtime": 3186.1248,
|
| 2212 |
+
"eval_samples_per_second": 1.726,
|
| 2213 |
+
"eval_steps_per_second": 1.726,
|
| 2214 |
+
"step": 147
|
| 2215 |
+
},
|
| 2216 |
+
{
|
| 2217 |
+
"epoch": 0.0016912352873957263,
|
| 2218 |
+
"grad_norm": 4.393204689025879,
|
| 2219 |
+
"learning_rate": 6.532663316582915e-06,
|
| 2220 |
+
"loss": 3.9712,
|
| 2221 |
+
"step": 148
|
| 2222 |
+
},
|
| 2223 |
+
{
|
| 2224 |
+
"epoch": 0.0016912352873957263,
|
| 2225 |
+
"eval_loss": 3.956583023071289,
|
| 2226 |
+
"eval_runtime": 3187.8674,
|
| 2227 |
+
"eval_samples_per_second": 1.725,
|
| 2228 |
+
"eval_steps_per_second": 1.725,
|
| 2229 |
+
"step": 148
|
| 2230 |
+
},
|
| 2231 |
+
{
|
| 2232 |
+
"epoch": 0.0017026625528511028,
|
| 2233 |
+
"grad_norm": 6.782311916351318,
|
| 2234 |
+
"learning_rate": 6.407035175879397e-06,
|
| 2235 |
+
"loss": 5.212,
|
| 2236 |
+
"step": 149
|
| 2237 |
+
},
|
| 2238 |
+
{
|
| 2239 |
+
"epoch": 0.0017026625528511028,
|
| 2240 |
+
"eval_loss": 3.9407119750976562,
|
| 2241 |
+
"eval_runtime": 3189.4481,
|
| 2242 |
+
"eval_samples_per_second": 1.724,
|
| 2243 |
+
"eval_steps_per_second": 1.724,
|
| 2244 |
+
"step": 149
|
| 2245 |
+
},
|
| 2246 |
+
{
|
| 2247 |
+
"epoch": 0.0017140898183064792,
|
| 2248 |
+
"grad_norm": 3.583444356918335,
|
| 2249 |
+
"learning_rate": 6.2814070351758795e-06,
|
| 2250 |
+
"loss": 3.5865,
|
| 2251 |
+
"step": 150
|
| 2252 |
+
},
|
| 2253 |
+
{
|
| 2254 |
+
"epoch": 0.0017140898183064792,
|
| 2255 |
+
"eval_loss": 3.9249038696289062,
|
| 2256 |
+
"eval_runtime": 3193.1787,
|
| 2257 |
+
"eval_samples_per_second": 1.722,
|
| 2258 |
+
"eval_steps_per_second": 1.722,
|
| 2259 |
+
"step": 150
|
| 2260 |
+
},
|
| 2261 |
+
{
|
| 2262 |
+
"epoch": 0.0017255170837618557,
|
| 2263 |
+
"grad_norm": 4.707357406616211,
|
| 2264 |
+
"learning_rate": 6.155778894472363e-06,
|
| 2265 |
+
"loss": 3.508,
|
| 2266 |
+
"step": 151
|
| 2267 |
+
},
|
| 2268 |
+
{
|
| 2269 |
+
"epoch": 0.0017255170837618557,
|
| 2270 |
+
"eval_loss": 3.9093074798583984,
|
| 2271 |
+
"eval_runtime": 3187.8945,
|
| 2272 |
+
"eval_samples_per_second": 1.725,
|
| 2273 |
+
"eval_steps_per_second": 1.725,
|
| 2274 |
+
"step": 151
|
| 2275 |
+
},
|
| 2276 |
+
{
|
| 2277 |
+
"epoch": 0.0017369443492172324,
|
| 2278 |
+
"grad_norm": 4.769847393035889,
|
| 2279 |
+
"learning_rate": 6.030150753768844e-06,
|
| 2280 |
+
"loss": 3.8634,
|
| 2281 |
+
"step": 152
|
| 2282 |
+
},
|
| 2283 |
+
{
|
| 2284 |
+
"epoch": 0.0017369443492172324,
|
| 2285 |
+
"eval_loss": 3.894160270690918,
|
| 2286 |
+
"eval_runtime": 3191.7342,
|
| 2287 |
+
"eval_samples_per_second": 1.723,
|
| 2288 |
+
"eval_steps_per_second": 1.723,
|
| 2289 |
+
"step": 152
|
| 2290 |
+
},
|
| 2291 |
+
{
|
| 2292 |
+
"epoch": 0.001748371614672609,
|
| 2293 |
+
"grad_norm": 2.5702831745147705,
|
| 2294 |
+
"learning_rate": 5.904522613065327e-06,
|
| 2295 |
+
"loss": 2.8717,
|
| 2296 |
+
"step": 153
|
| 2297 |
+
},
|
| 2298 |
+
{
|
| 2299 |
+
"epoch": 0.001748371614672609,
|
| 2300 |
+
"eval_loss": 3.879079818725586,
|
| 2301 |
+
"eval_runtime": 3192.0831,
|
| 2302 |
+
"eval_samples_per_second": 1.723,
|
| 2303 |
+
"eval_steps_per_second": 1.723,
|
| 2304 |
+
"step": 153
|
| 2305 |
+
},
|
| 2306 |
+
{
|
| 2307 |
+
"epoch": 0.0017597988801279854,
|
| 2308 |
+
"grad_norm": 6.417558670043945,
|
| 2309 |
+
"learning_rate": 5.778894472361809e-06,
|
| 2310 |
+
"loss": 4.4295,
|
| 2311 |
+
"step": 154
|
| 2312 |
+
},
|
| 2313 |
+
{
|
| 2314 |
+
"epoch": 0.0017597988801279854,
|
| 2315 |
+
"eval_loss": 3.8640522956848145,
|
| 2316 |
+
"eval_runtime": 3194.0863,
|
| 2317 |
+
"eval_samples_per_second": 1.722,
|
| 2318 |
+
"eval_steps_per_second": 1.722,
|
| 2319 |
+
"step": 154
|
| 2320 |
+
},
|
| 2321 |
+
{
|
| 2322 |
+
"epoch": 0.0017712261455833619,
|
| 2323 |
+
"grad_norm": 4.981814861297607,
|
| 2324 |
+
"learning_rate": 5.653266331658292e-06,
|
| 2325 |
+
"loss": 3.6863,
|
| 2326 |
+
"step": 155
|
| 2327 |
+
},
|
| 2328 |
+
{
|
| 2329 |
+
"epoch": 0.0017712261455833619,
|
| 2330 |
+
"eval_loss": 3.849724769592285,
|
| 2331 |
+
"eval_runtime": 3192.4569,
|
| 2332 |
+
"eval_samples_per_second": 1.723,
|
| 2333 |
+
"eval_steps_per_second": 1.723,
|
| 2334 |
+
"step": 155
|
| 2335 |
+
},
|
| 2336 |
+
{
|
| 2337 |
+
"epoch": 0.0017826534110387383,
|
| 2338 |
+
"grad_norm": 3.5112829208374023,
|
| 2339 |
+
"learning_rate": 5.527638190954775e-06,
|
| 2340 |
+
"loss": 3.5074,
|
| 2341 |
+
"step": 156
|
| 2342 |
+
},
|
| 2343 |
+
{
|
| 2344 |
+
"epoch": 0.0017826534110387383,
|
| 2345 |
+
"eval_loss": 3.835315704345703,
|
| 2346 |
+
"eval_runtime": 3195.7661,
|
| 2347 |
+
"eval_samples_per_second": 1.721,
|
| 2348 |
+
"eval_steps_per_second": 1.721,
|
| 2349 |
+
"step": 156
|
| 2350 |
+
},
|
| 2351 |
+
{
|
| 2352 |
+
"epoch": 0.001794080676494115,
|
| 2353 |
+
"grad_norm": 4.1393513679504395,
|
| 2354 |
+
"learning_rate": 5.402010050251256e-06,
|
| 2355 |
+
"loss": 3.6329,
|
| 2356 |
+
"step": 157
|
| 2357 |
+
},
|
| 2358 |
+
{
|
| 2359 |
+
"epoch": 0.001794080676494115,
|
| 2360 |
+
"eval_loss": 3.820890188217163,
|
| 2361 |
+
"eval_runtime": 3191.7062,
|
| 2362 |
+
"eval_samples_per_second": 1.723,
|
| 2363 |
+
"eval_steps_per_second": 1.723,
|
| 2364 |
+
"step": 157
|
| 2365 |
+
},
|
| 2366 |
+
{
|
| 2367 |
+
"epoch": 0.0018055079419494915,
|
| 2368 |
+
"grad_norm": 5.644866943359375,
|
| 2369 |
+
"learning_rate": 5.276381909547739e-06,
|
| 2370 |
+
"loss": 3.8676,
|
| 2371 |
+
"step": 158
|
| 2372 |
+
},
|
| 2373 |
+
{
|
| 2374 |
+
"epoch": 0.0018055079419494915,
|
| 2375 |
+
"eval_loss": 3.8074545860290527,
|
| 2376 |
+
"eval_runtime": 3189.2491,
|
| 2377 |
+
"eval_samples_per_second": 1.725,
|
| 2378 |
+
"eval_steps_per_second": 1.725,
|
| 2379 |
+
"step": 158
|
| 2380 |
+
},
|
| 2381 |
+
{
|
| 2382 |
+
"epoch": 0.001816935207404868,
|
| 2383 |
+
"grad_norm": 5.790183067321777,
|
| 2384 |
+
"learning_rate": 5.1507537688442215e-06,
|
| 2385 |
+
"loss": 4.4173,
|
| 2386 |
+
"step": 159
|
| 2387 |
+
},
|
| 2388 |
+
{
|
| 2389 |
+
"epoch": 0.001816935207404868,
|
| 2390 |
+
"eval_loss": 3.7939019203186035,
|
| 2391 |
+
"eval_runtime": 3184.9276,
|
| 2392 |
+
"eval_samples_per_second": 1.727,
|
| 2393 |
+
"eval_steps_per_second": 1.727,
|
| 2394 |
+
"step": 159
|
| 2395 |
+
},
|
| 2396 |
+
{
|
| 2397 |
+
"epoch": 0.0018283624728602445,
|
| 2398 |
+
"grad_norm": 4.434901237487793,
|
| 2399 |
+
"learning_rate": 5.025125628140704e-06,
|
| 2400 |
+
"loss": 3.561,
|
| 2401 |
+
"step": 160
|
| 2402 |
+
},
|
| 2403 |
+
{
|
| 2404 |
+
"epoch": 0.0018283624728602445,
|
| 2405 |
+
"eval_loss": 3.7808175086975098,
|
| 2406 |
+
"eval_runtime": 3191.4708,
|
| 2407 |
+
"eval_samples_per_second": 1.723,
|
| 2408 |
+
"eval_steps_per_second": 1.723,
|
| 2409 |
+
"step": 160
|
| 2410 |
+
},
|
| 2411 |
+
{
|
| 2412 |
+
"epoch": 0.001839789738315621,
|
| 2413 |
+
"grad_norm": 5.6928606033325195,
|
| 2414 |
+
"learning_rate": 4.899497487437186e-06,
|
| 2415 |
+
"loss": 4.0468,
|
| 2416 |
+
"step": 161
|
| 2417 |
+
},
|
| 2418 |
+
{
|
| 2419 |
+
"epoch": 0.001839789738315621,
|
| 2420 |
+
"eval_loss": 3.7684166431427,
|
| 2421 |
+
"eval_runtime": 3189.152,
|
| 2422 |
+
"eval_samples_per_second": 1.725,
|
| 2423 |
+
"eval_steps_per_second": 1.725,
|
| 2424 |
+
"step": 161
|
| 2425 |
+
},
|
| 2426 |
+
{
|
| 2427 |
+
"epoch": 0.0018512170037709977,
|
| 2428 |
+
"grad_norm": 5.777411937713623,
|
| 2429 |
+
"learning_rate": 4.773869346733668e-06,
|
| 2430 |
+
"loss": 4.046,
|
| 2431 |
+
"step": 162
|
| 2432 |
+
},
|
| 2433 |
+
{
|
| 2434 |
+
"epoch": 0.0018512170037709977,
|
| 2435 |
+
"eval_loss": 3.755950927734375,
|
| 2436 |
+
"eval_runtime": 3194.3133,
|
| 2437 |
+
"eval_samples_per_second": 1.722,
|
| 2438 |
+
"eval_steps_per_second": 1.722,
|
| 2439 |
+
"step": 162
|
| 2440 |
+
},
|
| 2441 |
+
{
|
| 2442 |
+
"epoch": 0.0018626442692263742,
|
| 2443 |
+
"grad_norm": 4.234452247619629,
|
| 2444 |
+
"learning_rate": 4.6482412060301506e-06,
|
| 2445 |
+
"loss": 3.4605,
|
| 2446 |
+
"step": 163
|
| 2447 |
+
},
|
| 2448 |
+
{
|
| 2449 |
+
"epoch": 0.0018626442692263742,
|
| 2450 |
+
"eval_loss": 3.743618965148926,
|
| 2451 |
+
"eval_runtime": 3190.5794,
|
| 2452 |
+
"eval_samples_per_second": 1.724,
|
| 2453 |
+
"eval_steps_per_second": 1.724,
|
| 2454 |
+
"step": 163
|
| 2455 |
+
},
|
| 2456 |
+
{
|
| 2457 |
+
"epoch": 0.0018740715346817506,
|
| 2458 |
+
"grad_norm": 4.58046817779541,
|
| 2459 |
+
"learning_rate": 4.522613065326634e-06,
|
| 2460 |
+
"loss": 3.8547,
|
| 2461 |
+
"step": 164
|
| 2462 |
+
},
|
| 2463 |
+
{
|
| 2464 |
+
"epoch": 0.0018740715346817506,
|
| 2465 |
+
"eval_loss": 3.731459856033325,
|
| 2466 |
+
"eval_runtime": 3195.1963,
|
| 2467 |
+
"eval_samples_per_second": 1.721,
|
| 2468 |
+
"eval_steps_per_second": 1.721,
|
| 2469 |
+
"step": 164
|
| 2470 |
+
},
|
| 2471 |
+
{
|
| 2472 |
+
"epoch": 0.0018854988001371271,
|
| 2473 |
+
"grad_norm": 4.460115909576416,
|
| 2474 |
+
"learning_rate": 4.396984924623116e-06,
|
| 2475 |
+
"loss": 3.4863,
|
| 2476 |
+
"step": 165
|
| 2477 |
+
},
|
| 2478 |
+
{
|
| 2479 |
+
"epoch": 0.0018854988001371271,
|
| 2480 |
+
"eval_loss": 3.7194907665252686,
|
| 2481 |
+
"eval_runtime": 3192.9919,
|
| 2482 |
+
"eval_samples_per_second": 1.723,
|
| 2483 |
+
"eval_steps_per_second": 1.723,
|
| 2484 |
+
"step": 165
|
| 2485 |
+
},
|
| 2486 |
+
{
|
| 2487 |
+
"epoch": 0.0018969260655925038,
|
| 2488 |
+
"grad_norm": 3.752925395965576,
|
| 2489 |
+
"learning_rate": 4.271356783919598e-06,
|
| 2490 |
+
"loss": 3.1784,
|
| 2491 |
+
"step": 166
|
| 2492 |
+
},
|
| 2493 |
+
{
|
| 2494 |
+
"epoch": 0.0018969260655925038,
|
| 2495 |
+
"eval_loss": 3.708251476287842,
|
| 2496 |
+
"eval_runtime": 3191.38,
|
| 2497 |
+
"eval_samples_per_second": 1.723,
|
| 2498 |
+
"eval_steps_per_second": 1.723,
|
| 2499 |
+
"step": 166
|
| 2500 |
+
},
|
| 2501 |
+
{
|
| 2502 |
+
"epoch": 0.0019083533310478803,
|
| 2503 |
+
"grad_norm": 5.099639415740967,
|
| 2504 |
+
"learning_rate": 4.1457286432160804e-06,
|
| 2505 |
+
"loss": 3.9205,
|
| 2506 |
+
"step": 167
|
| 2507 |
+
},
|
| 2508 |
+
{
|
| 2509 |
+
"epoch": 0.0019083533310478803,
|
| 2510 |
+
"eval_loss": 3.6969456672668457,
|
| 2511 |
+
"eval_runtime": 3184.4302,
|
| 2512 |
+
"eval_samples_per_second": 1.727,
|
| 2513 |
+
"eval_steps_per_second": 1.727,
|
| 2514 |
+
"step": 167
|
| 2515 |
+
},
|
| 2516 |
+
{
|
| 2517 |
+
"epoch": 0.0019197805965032568,
|
| 2518 |
+
"grad_norm": 2.3207623958587646,
|
| 2519 |
+
"learning_rate": 4.020100502512563e-06,
|
| 2520 |
+
"loss": 2.687,
|
| 2521 |
+
"step": 168
|
| 2522 |
+
},
|
| 2523 |
+
{
|
| 2524 |
+
"epoch": 0.0019197805965032568,
|
| 2525 |
+
"eval_loss": 3.686185359954834,
|
| 2526 |
+
"eval_runtime": 3190.1367,
|
| 2527 |
+
"eval_samples_per_second": 1.724,
|
| 2528 |
+
"eval_steps_per_second": 1.724,
|
| 2529 |
+
"step": 168
|
| 2530 |
+
},
|
| 2531 |
+
{
|
| 2532 |
+
"epoch": 0.0019312078619586333,
|
| 2533 |
+
"grad_norm": 5.285946846008301,
|
| 2534 |
+
"learning_rate": 3.894472361809046e-06,
|
| 2535 |
+
"loss": 3.916,
|
| 2536 |
+
"step": 169
|
| 2537 |
+
},
|
| 2538 |
+
{
|
| 2539 |
+
"epoch": 0.0019312078619586333,
|
| 2540 |
+
"eval_loss": 3.675804615020752,
|
| 2541 |
+
"eval_runtime": 3187.8804,
|
| 2542 |
+
"eval_samples_per_second": 1.725,
|
| 2543 |
+
"eval_steps_per_second": 1.725,
|
| 2544 |
+
"step": 169
|
| 2545 |
+
},
|
| 2546 |
+
{
|
| 2547 |
+
"epoch": 0.0019426351274140097,
|
| 2548 |
+
"grad_norm": 4.83530855178833,
|
| 2549 |
+
"learning_rate": 3.7688442211055276e-06,
|
| 2550 |
+
"loss": 3.7806,
|
| 2551 |
+
"step": 170
|
| 2552 |
+
},
|
| 2553 |
+
{
|
| 2554 |
+
"epoch": 0.0019426351274140097,
|
| 2555 |
+
"eval_loss": 3.6655375957489014,
|
| 2556 |
+
"eval_runtime": 3183.8288,
|
| 2557 |
+
"eval_samples_per_second": 1.727,
|
| 2558 |
+
"eval_steps_per_second": 1.727,
|
| 2559 |
+
"step": 170
|
| 2560 |
+
},
|
| 2561 |
+
{
|
| 2562 |
+
"epoch": 0.0019540623928693862,
|
| 2563 |
+
"grad_norm": 5.306794166564941,
|
| 2564 |
+
"learning_rate": 3.64321608040201e-06,
|
| 2565 |
+
"loss": 3.6463,
|
| 2566 |
+
"step": 171
|
| 2567 |
+
},
|
| 2568 |
+
{
|
| 2569 |
+
"epoch": 0.0019540623928693862,
|
| 2570 |
+
"eval_loss": 3.6555092334747314,
|
| 2571 |
+
"eval_runtime": 3189.4936,
|
| 2572 |
+
"eval_samples_per_second": 1.724,
|
| 2573 |
+
"eval_steps_per_second": 1.724,
|
| 2574 |
+
"step": 171
|
| 2575 |
+
},
|
| 2576 |
+
{
|
| 2577 |
+
"epoch": 0.0019654896583247627,
|
| 2578 |
+
"grad_norm": 7.400163173675537,
|
| 2579 |
+
"learning_rate": 3.5175879396984926e-06,
|
| 2580 |
+
"loss": 4.8809,
|
| 2581 |
+
"step": 172
|
| 2582 |
+
},
|
| 2583 |
+
{
|
| 2584 |
+
"epoch": 0.0019654896583247627,
|
| 2585 |
+
"eval_loss": 3.645655632019043,
|
| 2586 |
+
"eval_runtime": 3189.5993,
|
| 2587 |
+
"eval_samples_per_second": 1.724,
|
| 2588 |
+
"eval_steps_per_second": 1.724,
|
| 2589 |
+
"step": 172
|
| 2590 |
+
},
|
| 2591 |
+
{
|
| 2592 |
+
"epoch": 0.0019769169237801396,
|
| 2593 |
+
"grad_norm": 5.281580448150635,
|
| 2594 |
+
"learning_rate": 3.3919597989949752e-06,
|
| 2595 |
+
"loss": 3.7168,
|
| 2596 |
+
"step": 173
|
| 2597 |
+
},
|
| 2598 |
+
{
|
| 2599 |
+
"epoch": 0.0019769169237801396,
|
| 2600 |
+
"eval_loss": 3.6365396976470947,
|
| 2601 |
+
"eval_runtime": 3191.3086,
|
| 2602 |
+
"eval_samples_per_second": 1.723,
|
| 2603 |
+
"eval_steps_per_second": 1.723,
|
| 2604 |
+
"step": 173
|
| 2605 |
+
},
|
| 2606 |
+
{
|
| 2607 |
+
"epoch": 0.001988344189235516,
|
| 2608 |
+
"grad_norm": 5.500361919403076,
|
| 2609 |
+
"learning_rate": 3.2663316582914575e-06,
|
| 2610 |
+
"loss": 3.5465,
|
| 2611 |
+
"step": 174
|
| 2612 |
+
},
|
| 2613 |
+
{
|
| 2614 |
+
"epoch": 0.001988344189235516,
|
| 2615 |
+
"eval_loss": 3.627671957015991,
|
| 2616 |
+
"eval_runtime": 3191.166,
|
| 2617 |
+
"eval_samples_per_second": 1.724,
|
| 2618 |
+
"eval_steps_per_second": 1.724,
|
| 2619 |
+
"step": 174
|
| 2620 |
+
},
|
| 2621 |
+
{
|
| 2622 |
+
"epoch": 0.0019997714546908926,
|
| 2623 |
+
"grad_norm": 5.550091743469238,
|
| 2624 |
+
"learning_rate": 3.1407035175879398e-06,
|
| 2625 |
+
"loss": 3.7022,
|
| 2626 |
+
"step": 175
|
| 2627 |
+
},
|
| 2628 |
+
{
|
| 2629 |
+
"epoch": 0.0019997714546908926,
|
| 2630 |
+
"eval_loss": 3.6191136837005615,
|
| 2631 |
+
"eval_runtime": 3190.3196,
|
| 2632 |
+
"eval_samples_per_second": 1.724,
|
| 2633 |
+
"eval_steps_per_second": 1.724,
|
| 2634 |
+
"step": 175
|
| 2635 |
+
},
|
| 2636 |
+
{
|
| 2637 |
+
"epoch": 0.002011198720146269,
|
| 2638 |
+
"grad_norm": 4.048425197601318,
|
| 2639 |
+
"learning_rate": 3.015075376884422e-06,
|
| 2640 |
+
"loss": 3.5034,
|
| 2641 |
+
"step": 176
|
| 2642 |
+
},
|
| 2643 |
+
{
|
| 2644 |
+
"epoch": 0.002011198720146269,
|
| 2645 |
+
"eval_loss": 3.6107609272003174,
|
| 2646 |
+
"eval_runtime": 3196.3566,
|
| 2647 |
+
"eval_samples_per_second": 1.721,
|
| 2648 |
+
"eval_steps_per_second": 1.721,
|
| 2649 |
+
"step": 176
|
| 2650 |
+
},
|
| 2651 |
+
{
|
| 2652 |
+
"epoch": 0.0020226259856016456,
|
| 2653 |
+
"grad_norm": 4.696182727813721,
|
| 2654 |
+
"learning_rate": 2.8894472361809047e-06,
|
| 2655 |
+
"loss": 3.5201,
|
| 2656 |
+
"step": 177
|
| 2657 |
+
},
|
| 2658 |
+
{
|
| 2659 |
+
"epoch": 0.0020226259856016456,
|
| 2660 |
+
"eval_loss": 3.602489948272705,
|
| 2661 |
+
"eval_runtime": 3191.1045,
|
| 2662 |
+
"eval_samples_per_second": 1.724,
|
| 2663 |
+
"eval_steps_per_second": 1.724,
|
| 2664 |
+
"step": 177
|
| 2665 |
+
},
|
| 2666 |
+
{
|
| 2667 |
+
"epoch": 0.002034053251057022,
|
| 2668 |
+
"grad_norm": 4.840107440948486,
|
| 2669 |
+
"learning_rate": 2.7638190954773874e-06,
|
| 2670 |
+
"loss": 3.8883,
|
| 2671 |
+
"step": 178
|
| 2672 |
+
},
|
| 2673 |
+
{
|
| 2674 |
+
"epoch": 0.002034053251057022,
|
| 2675 |
+
"eval_loss": 3.5948402881622314,
|
| 2676 |
+
"eval_runtime": 3181.8951,
|
| 2677 |
+
"eval_samples_per_second": 1.729,
|
| 2678 |
+
"eval_steps_per_second": 1.729,
|
| 2679 |
+
"step": 178
|
| 2680 |
+
},
|
| 2681 |
+
{
|
| 2682 |
+
"epoch": 0.0020454805165123985,
|
| 2683 |
+
"grad_norm": 3.1070148944854736,
|
| 2684 |
+
"learning_rate": 2.6381909547738696e-06,
|
| 2685 |
+
"loss": 2.8413,
|
| 2686 |
+
"step": 179
|
| 2687 |
+
},
|
| 2688 |
+
{
|
| 2689 |
+
"epoch": 0.0020454805165123985,
|
| 2690 |
+
"eval_loss": 3.587570905685425,
|
| 2691 |
+
"eval_runtime": 3187.9084,
|
| 2692 |
+
"eval_samples_per_second": 1.725,
|
| 2693 |
+
"eval_steps_per_second": 1.725,
|
| 2694 |
+
"step": 179
|
| 2695 |
+
},
|
| 2696 |
+
{
|
| 2697 |
+
"epoch": 0.002056907781967775,
|
| 2698 |
+
"grad_norm": 4.61260986328125,
|
| 2699 |
+
"learning_rate": 2.512562814070352e-06,
|
| 2700 |
+
"loss": 3.704,
|
| 2701 |
+
"step": 180
|
| 2702 |
+
},
|
| 2703 |
+
{
|
| 2704 |
+
"epoch": 0.002056907781967775,
|
| 2705 |
+
"eval_loss": 3.5807385444641113,
|
| 2706 |
+
"eval_runtime": 3193.1025,
|
| 2707 |
+
"eval_samples_per_second": 1.722,
|
| 2708 |
+
"eval_steps_per_second": 1.722,
|
| 2709 |
+
"step": 180
|
| 2710 |
+
},
|
| 2711 |
+
{
|
| 2712 |
+
"epoch": 0.0020683350474231515,
|
| 2713 |
+
"grad_norm": 5.774682998657227,
|
| 2714 |
+
"learning_rate": 2.386934673366834e-06,
|
| 2715 |
+
"loss": 4.1228,
|
| 2716 |
+
"step": 181
|
| 2717 |
+
},
|
| 2718 |
+
{
|
| 2719 |
+
"epoch": 0.0020683350474231515,
|
| 2720 |
+
"eval_loss": 3.5740838050842285,
|
| 2721 |
+
"eval_runtime": 3188.6673,
|
| 2722 |
+
"eval_samples_per_second": 1.725,
|
| 2723 |
+
"eval_steps_per_second": 1.725,
|
| 2724 |
+
"step": 181
|
| 2725 |
+
},
|
| 2726 |
+
{
|
| 2727 |
+
"epoch": 0.002079762312878528,
|
| 2728 |
+
"grad_norm": 6.585142612457275,
|
| 2729 |
+
"learning_rate": 2.261306532663317e-06,
|
| 2730 |
+
"loss": 4.1375,
|
| 2731 |
+
"step": 182
|
| 2732 |
+
},
|
| 2733 |
+
{
|
| 2734 |
+
"epoch": 0.002079762312878528,
|
| 2735 |
+
"eval_loss": 3.5675177574157715,
|
| 2736 |
+
"eval_runtime": 3187.9902,
|
| 2737 |
+
"eval_samples_per_second": 1.725,
|
| 2738 |
+
"eval_steps_per_second": 1.725,
|
| 2739 |
+
"step": 182
|
| 2740 |
+
},
|
| 2741 |
+
{
|
| 2742 |
+
"epoch": 0.002091189578333905,
|
| 2743 |
+
"grad_norm": 4.422517776489258,
|
| 2744 |
+
"learning_rate": 2.135678391959799e-06,
|
| 2745 |
+
"loss": 3.2458,
|
| 2746 |
+
"step": 183
|
| 2747 |
+
},
|
| 2748 |
+
{
|
| 2749 |
+
"epoch": 0.002091189578333905,
|
| 2750 |
+
"eval_loss": 3.5616683959960938,
|
| 2751 |
+
"eval_runtime": 3189.6985,
|
| 2752 |
+
"eval_samples_per_second": 1.724,
|
| 2753 |
+
"eval_steps_per_second": 1.724,
|
| 2754 |
+
"step": 183
|
| 2755 |
+
},
|
| 2756 |
+
{
|
| 2757 |
+
"epoch": 0.0021026168437892814,
|
| 2758 |
+
"grad_norm": 5.40252685546875,
|
| 2759 |
+
"learning_rate": 2.0100502512562813e-06,
|
| 2760 |
+
"loss": 3.7518,
|
| 2761 |
+
"step": 184
|
| 2762 |
+
},
|
| 2763 |
+
{
|
| 2764 |
+
"epoch": 0.0021026168437892814,
|
| 2765 |
+
"eval_loss": 3.556403398513794,
|
| 2766 |
+
"eval_runtime": 3188.5075,
|
| 2767 |
+
"eval_samples_per_second": 1.725,
|
| 2768 |
+
"eval_steps_per_second": 1.725,
|
| 2769 |
+
"step": 184
|
| 2770 |
+
},
|
| 2771 |
+
{
|
| 2772 |
+
"epoch": 0.002114044109244658,
|
| 2773 |
+
"grad_norm": 3.357342004776001,
|
| 2774 |
+
"learning_rate": 1.8844221105527638e-06,
|
| 2775 |
+
"loss": 2.8388,
|
| 2776 |
+
"step": 185
|
| 2777 |
+
},
|
| 2778 |
+
{
|
| 2779 |
+
"epoch": 0.002114044109244658,
|
| 2780 |
+
"eval_loss": 3.551210880279541,
|
| 2781 |
+
"eval_runtime": 3198.6279,
|
| 2782 |
+
"eval_samples_per_second": 1.719,
|
| 2783 |
+
"eval_steps_per_second": 1.719,
|
| 2784 |
+
"step": 185
|
| 2785 |
+
},
|
| 2786 |
+
{
|
| 2787 |
+
"epoch": 0.0021254713747000343,
|
| 2788 |
+
"grad_norm": 5.60300350189209,
|
| 2789 |
+
"learning_rate": 1.7587939698492463e-06,
|
| 2790 |
+
"loss": 3.6586,
|
| 2791 |
+
"step": 186
|
| 2792 |
+
},
|
| 2793 |
+
{
|
| 2794 |
+
"epoch": 0.0021254713747000343,
|
| 2795 |
+
"eval_loss": 3.5462591648101807,
|
| 2796 |
+
"eval_runtime": 3194.9645,
|
| 2797 |
+
"eval_samples_per_second": 1.721,
|
| 2798 |
+
"eval_steps_per_second": 1.721,
|
| 2799 |
+
"step": 186
|
| 2800 |
+
},
|
| 2801 |
+
{
|
| 2802 |
+
"epoch": 0.002136898640155411,
|
| 2803 |
+
"grad_norm": 4.910702228546143,
|
| 2804 |
+
"learning_rate": 1.6331658291457288e-06,
|
| 2805 |
+
"loss": 3.6408,
|
| 2806 |
+
"step": 187
|
| 2807 |
+
},
|
| 2808 |
+
{
|
| 2809 |
+
"epoch": 0.002136898640155411,
|
| 2810 |
+
"eval_loss": 3.5415446758270264,
|
| 2811 |
+
"eval_runtime": 3185.4074,
|
| 2812 |
+
"eval_samples_per_second": 1.727,
|
| 2813 |
+
"eval_steps_per_second": 1.727,
|
| 2814 |
+
"step": 187
|
| 2815 |
+
},
|
| 2816 |
+
{
|
| 2817 |
+
"epoch": 0.0021483259056107873,
|
| 2818 |
+
"grad_norm": 5.6200737953186035,
|
| 2819 |
+
"learning_rate": 1.507537688442211e-06,
|
| 2820 |
+
"loss": 3.5742,
|
| 2821 |
+
"step": 188
|
| 2822 |
+
},
|
| 2823 |
+
{
|
| 2824 |
+
"epoch": 0.0021483259056107873,
|
| 2825 |
+
"eval_loss": 3.537212371826172,
|
| 2826 |
+
"eval_runtime": 3182.681,
|
| 2827 |
+
"eval_samples_per_second": 1.728,
|
| 2828 |
+
"eval_steps_per_second": 1.728,
|
| 2829 |
+
"step": 188
|
| 2830 |
+
},
|
| 2831 |
+
{
|
| 2832 |
+
"epoch": 0.0021597531710661638,
|
| 2833 |
+
"grad_norm": 5.1306986808776855,
|
| 2834 |
+
"learning_rate": 1.3819095477386937e-06,
|
| 2835 |
+
"loss": 3.5693,
|
| 2836 |
+
"step": 189
|
| 2837 |
+
},
|
| 2838 |
+
{
|
| 2839 |
+
"epoch": 0.0021597531710661638,
|
| 2840 |
+
"eval_loss": 3.5330007076263428,
|
| 2841 |
+
"eval_runtime": 3185.4993,
|
| 2842 |
+
"eval_samples_per_second": 1.727,
|
| 2843 |
+
"eval_steps_per_second": 1.727,
|
| 2844 |
+
"step": 189
|
| 2845 |
+
},
|
| 2846 |
+
{
|
| 2847 |
+
"epoch": 0.0021711804365215403,
|
| 2848 |
+
"grad_norm": 5.107001781463623,
|
| 2849 |
+
"learning_rate": 1.256281407035176e-06,
|
| 2850 |
+
"loss": 3.6025,
|
| 2851 |
+
"step": 190
|
| 2852 |
+
},
|
| 2853 |
+
{
|
| 2854 |
+
"epoch": 0.0021711804365215403,
|
| 2855 |
+
"eval_loss": 3.529104471206665,
|
| 2856 |
+
"eval_runtime": 3180.9702,
|
| 2857 |
+
"eval_samples_per_second": 1.729,
|
| 2858 |
+
"eval_steps_per_second": 1.729,
|
| 2859 |
+
"step": 190
|
| 2860 |
+
},
|
| 2861 |
+
{
|
| 2862 |
+
"epoch": 0.0021826077019769167,
|
| 2863 |
+
"grad_norm": 5.954830646514893,
|
| 2864 |
+
"learning_rate": 1.1306532663316584e-06,
|
| 2865 |
+
"loss": 3.5938,
|
| 2866 |
+
"step": 191
|
| 2867 |
+
},
|
| 2868 |
+
{
|
| 2869 |
+
"epoch": 0.0021826077019769167,
|
| 2870 |
+
"eval_loss": 3.525881052017212,
|
| 2871 |
+
"eval_runtime": 3184.2834,
|
| 2872 |
+
"eval_samples_per_second": 1.727,
|
| 2873 |
+
"eval_steps_per_second": 1.727,
|
| 2874 |
+
"step": 191
|
| 2875 |
+
},
|
| 2876 |
+
{
|
| 2877 |
+
"epoch": 0.0021940349674322937,
|
| 2878 |
+
"grad_norm": 4.140493392944336,
|
| 2879 |
+
"learning_rate": 1.0050251256281407e-06,
|
| 2880 |
+
"loss": 3.3742,
|
| 2881 |
+
"step": 192
|
| 2882 |
+
},
|
| 2883 |
+
{
|
| 2884 |
+
"epoch": 0.0021940349674322937,
|
| 2885 |
+
"eval_loss": 3.5228757858276367,
|
| 2886 |
+
"eval_runtime": 3193.6231,
|
| 2887 |
+
"eval_samples_per_second": 1.722,
|
| 2888 |
+
"eval_steps_per_second": 1.722,
|
| 2889 |
+
"step": 192
|
| 2890 |
+
},
|
| 2891 |
+
{
|
| 2892 |
+
"epoch": 0.00220546223288767,
|
| 2893 |
+
"grad_norm": 6.1048665046691895,
|
| 2894 |
+
"learning_rate": 8.793969849246231e-07,
|
| 2895 |
+
"loss": 3.9661,
|
| 2896 |
+
"step": 193
|
| 2897 |
+
},
|
| 2898 |
+
{
|
| 2899 |
+
"epoch": 0.00220546223288767,
|
| 2900 |
+
"eval_loss": 3.519984722137451,
|
| 2901 |
+
"eval_runtime": 3190.529,
|
| 2902 |
+
"eval_samples_per_second": 1.724,
|
| 2903 |
+
"eval_steps_per_second": 1.724,
|
| 2904 |
+
"step": 193
|
| 2905 |
+
},
|
| 2906 |
+
{
|
| 2907 |
+
"epoch": 0.0022168894983430466,
|
| 2908 |
+
"grad_norm": 4.738156318664551,
|
| 2909 |
+
"learning_rate": 7.537688442211055e-07,
|
| 2910 |
+
"loss": 3.1686,
|
| 2911 |
+
"step": 194
|
| 2912 |
+
},
|
| 2913 |
+
{
|
| 2914 |
+
"epoch": 0.0022168894983430466,
|
| 2915 |
+
"eval_loss": 3.517745018005371,
|
| 2916 |
+
"eval_runtime": 3189.2139,
|
| 2917 |
+
"eval_samples_per_second": 1.725,
|
| 2918 |
+
"eval_steps_per_second": 1.725,
|
| 2919 |
+
"step": 194
|
| 2920 |
+
},
|
| 2921 |
+
{
|
| 2922 |
+
"epoch": 0.002228316763798423,
|
| 2923 |
+
"grad_norm": 6.101266860961914,
|
| 2924 |
+
"learning_rate": 6.28140703517588e-07,
|
| 2925 |
+
"loss": 3.5854,
|
| 2926 |
+
"step": 195
|
| 2927 |
+
},
|
| 2928 |
+
{
|
| 2929 |
+
"epoch": 0.002228316763798423,
|
| 2930 |
+
"eval_loss": 3.515723705291748,
|
| 2931 |
+
"eval_runtime": 3190.1764,
|
| 2932 |
+
"eval_samples_per_second": 1.724,
|
| 2933 |
+
"eval_steps_per_second": 1.724,
|
| 2934 |
+
"step": 195
|
| 2935 |
+
},
|
| 2936 |
+
{
|
| 2937 |
+
"epoch": 0.0022397440292537996,
|
| 2938 |
+
"grad_norm": 3.0352277755737305,
|
| 2939 |
+
"learning_rate": 5.025125628140703e-07,
|
| 2940 |
+
"loss": 2.9543,
|
| 2941 |
+
"step": 196
|
| 2942 |
+
},
|
| 2943 |
+
{
|
| 2944 |
+
"epoch": 0.0022397440292537996,
|
| 2945 |
+
"eval_loss": 3.5141751766204834,
|
| 2946 |
+
"eval_runtime": 3188.4018,
|
| 2947 |
+
"eval_samples_per_second": 1.725,
|
| 2948 |
+
"eval_steps_per_second": 1.725,
|
| 2949 |
+
"step": 196
|
| 2950 |
+
},
|
| 2951 |
+
{
|
| 2952 |
+
"epoch": 0.002251171294709176,
|
| 2953 |
+
"grad_norm": 3.8082351684570312,
|
| 2954 |
+
"learning_rate": 3.7688442211055275e-07,
|
| 2955 |
+
"loss": 3.3165,
|
| 2956 |
+
"step": 197
|
| 2957 |
+
},
|
| 2958 |
+
{
|
| 2959 |
+
"epoch": 0.002251171294709176,
|
| 2960 |
+
"eval_loss": 3.512690305709839,
|
| 2961 |
+
"eval_runtime": 3190.2684,
|
| 2962 |
+
"eval_samples_per_second": 1.724,
|
| 2963 |
+
"eval_steps_per_second": 1.724,
|
| 2964 |
+
"step": 197
|
| 2965 |
+
},
|
| 2966 |
+
{
|
| 2967 |
+
"epoch": 0.0022625985601645525,
|
| 2968 |
+
"grad_norm": 3.919834613800049,
|
| 2969 |
+
"learning_rate": 2.5125628140703517e-07,
|
| 2970 |
+
"loss": 2.769,
|
| 2971 |
+
"step": 198
|
| 2972 |
+
},
|
| 2973 |
+
{
|
| 2974 |
+
"epoch": 0.0022625985601645525,
|
| 2975 |
+
"eval_loss": 3.5116732120513916,
|
| 2976 |
+
"eval_runtime": 3190.4709,
|
| 2977 |
+
"eval_samples_per_second": 1.724,
|
| 2978 |
+
"eval_steps_per_second": 1.724,
|
| 2979 |
+
"step": 198
|
| 2980 |
+
},
|
| 2981 |
+
{
|
| 2982 |
+
"epoch": 0.002274025825619929,
|
| 2983 |
+
"grad_norm": 5.8951334953308105,
|
| 2984 |
+
"learning_rate": 1.2562814070351758e-07,
|
| 2985 |
+
"loss": 3.999,
|
| 2986 |
+
"step": 199
|
| 2987 |
+
},
|
| 2988 |
+
{
|
| 2989 |
+
"epoch": 0.002274025825619929,
|
| 2990 |
+
"eval_loss": 3.511035442352295,
|
| 2991 |
+
"eval_runtime": 3199.1703,
|
| 2992 |
+
"eval_samples_per_second": 1.719,
|
| 2993 |
+
"eval_steps_per_second": 1.719,
|
| 2994 |
+
"step": 199
|
| 2995 |
+
},
|
| 2996 |
+
{
|
| 2997 |
+
"epoch": 0.0022854530910753055,
|
| 2998 |
+
"grad_norm": 5.609264850616455,
|
| 2999 |
+
"learning_rate": 0.0,
|
| 3000 |
+
"loss": 3.8117,
|
| 3001 |
+
"step": 200
|
| 3002 |
+
},
|
| 3003 |
+
{
|
| 3004 |
+
"epoch": 0.0022854530910753055,
|
| 3005 |
+
"eval_loss": 3.510607957839966,
|
| 3006 |
+
"eval_runtime": 3196.7225,
|
| 3007 |
+
"eval_samples_per_second": 1.721,
|
| 3008 |
+
"eval_steps_per_second": 1.721,
|
| 3009 |
+
"step": 200
|
| 3010 |
+
}
|
| 3011 |
+
],
|
| 3012 |
+
"logging_steps": 1,
|
| 3013 |
+
"max_steps": 200,
|
| 3014 |
+
"num_input_tokens_seen": 0,
|
| 3015 |
+
"num_train_epochs": 1,
|
| 3016 |
+
"save_steps": 1,
|
| 3017 |
+
"total_flos": 2564058316800000.0,
|
| 3018 |
+
"train_batch_size": 1,
|
| 3019 |
+
"trial_name": null,
|
| 3020 |
+
"trial_params": null
|
| 3021 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8616cad9ad2e1e4bfe4475f96537807ac28788048f0757be8c0029f9df96aceb
|
| 3 |
+
size 4984
|