Model save
Browse files- README.md +3 -11
- adapter_config.json +3 -3
- adapter_model.safetensors +1 -1
- num_examples=400/llava-v1.5-13b_1.0/README.md +202 -0
- num_examples=400/llava-v1.5-13b_1.0/adapter_config.json +34 -0
- num_examples=400/llava-v1.5-13b_1.0/adapter_model.safetensors +3 -0
- num_examples=400/llava-v1.5-13b_1.0/special_tokens_map.json +24 -0
- num_examples=400/llava-v1.5-13b_1.0/tokenizer.model +3 -0
- num_examples=400/llava-v1.5-13b_1.0/tokenizer_config.json +42 -0
- num_examples=400/llava-v1.5-13b_1.0/training_args.bin +3 -0
- trainer_state.json +784 -2704
- training_args.bin +1 -1
README.md
CHANGED
|
@@ -1,27 +1,19 @@
|
|
| 1 |
---
|
| 2 |
library_name: peft
|
| 3 |
tags:
|
| 4 |
-
- liuhaotian/llava-v1.5-13b_20.0
|
| 5 |
- generated_from_trainer
|
| 6 |
base_model: liuhaotian/llava-v1.5-13b
|
| 7 |
model-index:
|
| 8 |
-
- name:
|
| 9 |
results: []
|
| 10 |
---
|
| 11 |
|
| 12 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 13 |
should probably proofread and complete it, then remove this comment. -->
|
| 14 |
|
| 15 |
-
#
|
| 16 |
|
| 17 |
-
This model is a fine-tuned version of [liuhaotian/llava-v1.5-
|
| 18 |
-
It achieves the following results on the evaluation set:
|
| 19 |
-
- eval_loss: 0.0021
|
| 20 |
-
- eval_runtime: 40.9486
|
| 21 |
-
- eval_samples_per_second: 11.038
|
| 22 |
-
- eval_steps_per_second: 0.366
|
| 23 |
-
- epoch: 19.0
|
| 24 |
-
- step: 285
|
| 25 |
|
| 26 |
## Model description
|
| 27 |
|
|
|
|
| 1 |
---
|
| 2 |
library_name: peft
|
| 3 |
tags:
|
|
|
|
| 4 |
- generated_from_trainer
|
| 5 |
base_model: liuhaotian/llava-v1.5-13b
|
| 6 |
model-index:
|
| 7 |
+
- name: llava_13b_neighborhood_synthetic
|
| 8 |
results: []
|
| 9 |
---
|
| 10 |
|
| 11 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 12 |
should probably proofread and complete it, then remove this comment. -->
|
| 13 |
|
| 14 |
+
# llava_13b_neighborhood_synthetic
|
| 15 |
|
| 16 |
+
This model is a fine-tuned version of [liuhaotian/llava-v1.5-13b](https://huggingface.co/liuhaotian/llava-v1.5-13b) on an unknown dataset.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 17 |
|
| 18 |
## Model description
|
| 19 |
|
adapter_config.json
CHANGED
|
@@ -21,12 +21,12 @@
|
|
| 21 |
"revision": null,
|
| 22 |
"target_modules": [
|
| 23 |
"k_proj",
|
|
|
|
| 24 |
"q_proj",
|
| 25 |
"o_proj",
|
| 26 |
-
"down_proj",
|
| 27 |
-
"up_proj",
|
| 28 |
"v_proj",
|
| 29 |
-
"
|
|
|
|
| 30 |
],
|
| 31 |
"task_type": "CAUSAL_LM",
|
| 32 |
"use_dora": false,
|
|
|
|
| 21 |
"revision": null,
|
| 22 |
"target_modules": [
|
| 23 |
"k_proj",
|
| 24 |
+
"gate_proj",
|
| 25 |
"q_proj",
|
| 26 |
"o_proj",
|
|
|
|
|
|
|
| 27 |
"v_proj",
|
| 28 |
+
"up_proj",
|
| 29 |
+
"down_proj"
|
| 30 |
],
|
| 31 |
"task_type": "CAUSAL_LM",
|
| 32 |
"use_dora": false,
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1001466944
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:09d91d82e712d1030dc46067af174545032cffe35fad81a818839e5716f39ea9
|
| 3 |
size 1001466944
|
num_examples=400/llava-v1.5-13b_1.0/README.md
ADDED
|
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
base_model: liuhaotian/llava-v1.5-13b
|
| 4 |
+
---
|
| 5 |
+
|
| 6 |
+
# Model Card for Model ID
|
| 7 |
+
|
| 8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 9 |
+
|
| 10 |
+
|
| 11 |
+
|
| 12 |
+
## Model Details
|
| 13 |
+
|
| 14 |
+
### Model Description
|
| 15 |
+
|
| 16 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
- **Developed by:** [More Information Needed]
|
| 21 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 22 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 23 |
+
- **Model type:** [More Information Needed]
|
| 24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 25 |
+
- **License:** [More Information Needed]
|
| 26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 27 |
+
|
| 28 |
+
### Model Sources [optional]
|
| 29 |
+
|
| 30 |
+
<!-- Provide the basic links for the model. -->
|
| 31 |
+
|
| 32 |
+
- **Repository:** [More Information Needed]
|
| 33 |
+
- **Paper [optional]:** [More Information Needed]
|
| 34 |
+
- **Demo [optional]:** [More Information Needed]
|
| 35 |
+
|
| 36 |
+
## Uses
|
| 37 |
+
|
| 38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 39 |
+
|
| 40 |
+
### Direct Use
|
| 41 |
+
|
| 42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 43 |
+
|
| 44 |
+
[More Information Needed]
|
| 45 |
+
|
| 46 |
+
### Downstream Use [optional]
|
| 47 |
+
|
| 48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 49 |
+
|
| 50 |
+
[More Information Needed]
|
| 51 |
+
|
| 52 |
+
### Out-of-Scope Use
|
| 53 |
+
|
| 54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 55 |
+
|
| 56 |
+
[More Information Needed]
|
| 57 |
+
|
| 58 |
+
## Bias, Risks, and Limitations
|
| 59 |
+
|
| 60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 61 |
+
|
| 62 |
+
[More Information Needed]
|
| 63 |
+
|
| 64 |
+
### Recommendations
|
| 65 |
+
|
| 66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 67 |
+
|
| 68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 69 |
+
|
| 70 |
+
## How to Get Started with the Model
|
| 71 |
+
|
| 72 |
+
Use the code below to get started with the model.
|
| 73 |
+
|
| 74 |
+
[More Information Needed]
|
| 75 |
+
|
| 76 |
+
## Training Details
|
| 77 |
+
|
| 78 |
+
### Training Data
|
| 79 |
+
|
| 80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 81 |
+
|
| 82 |
+
[More Information Needed]
|
| 83 |
+
|
| 84 |
+
### Training Procedure
|
| 85 |
+
|
| 86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 87 |
+
|
| 88 |
+
#### Preprocessing [optional]
|
| 89 |
+
|
| 90 |
+
[More Information Needed]
|
| 91 |
+
|
| 92 |
+
|
| 93 |
+
#### Training Hyperparameters
|
| 94 |
+
|
| 95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 96 |
+
|
| 97 |
+
#### Speeds, Sizes, Times [optional]
|
| 98 |
+
|
| 99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 100 |
+
|
| 101 |
+
[More Information Needed]
|
| 102 |
+
|
| 103 |
+
## Evaluation
|
| 104 |
+
|
| 105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 106 |
+
|
| 107 |
+
### Testing Data, Factors & Metrics
|
| 108 |
+
|
| 109 |
+
#### Testing Data
|
| 110 |
+
|
| 111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 112 |
+
|
| 113 |
+
[More Information Needed]
|
| 114 |
+
|
| 115 |
+
#### Factors
|
| 116 |
+
|
| 117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 118 |
+
|
| 119 |
+
[More Information Needed]
|
| 120 |
+
|
| 121 |
+
#### Metrics
|
| 122 |
+
|
| 123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 124 |
+
|
| 125 |
+
[More Information Needed]
|
| 126 |
+
|
| 127 |
+
### Results
|
| 128 |
+
|
| 129 |
+
[More Information Needed]
|
| 130 |
+
|
| 131 |
+
#### Summary
|
| 132 |
+
|
| 133 |
+
|
| 134 |
+
|
| 135 |
+
## Model Examination [optional]
|
| 136 |
+
|
| 137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 138 |
+
|
| 139 |
+
[More Information Needed]
|
| 140 |
+
|
| 141 |
+
## Environmental Impact
|
| 142 |
+
|
| 143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 144 |
+
|
| 145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
| 146 |
+
|
| 147 |
+
- **Hardware Type:** [More Information Needed]
|
| 148 |
+
- **Hours used:** [More Information Needed]
|
| 149 |
+
- **Cloud Provider:** [More Information Needed]
|
| 150 |
+
- **Compute Region:** [More Information Needed]
|
| 151 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 152 |
+
|
| 153 |
+
## Technical Specifications [optional]
|
| 154 |
+
|
| 155 |
+
### Model Architecture and Objective
|
| 156 |
+
|
| 157 |
+
[More Information Needed]
|
| 158 |
+
|
| 159 |
+
### Compute Infrastructure
|
| 160 |
+
|
| 161 |
+
[More Information Needed]
|
| 162 |
+
|
| 163 |
+
#### Hardware
|
| 164 |
+
|
| 165 |
+
[More Information Needed]
|
| 166 |
+
|
| 167 |
+
#### Software
|
| 168 |
+
|
| 169 |
+
[More Information Needed]
|
| 170 |
+
|
| 171 |
+
## Citation [optional]
|
| 172 |
+
|
| 173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 174 |
+
|
| 175 |
+
**BibTeX:**
|
| 176 |
+
|
| 177 |
+
[More Information Needed]
|
| 178 |
+
|
| 179 |
+
**APA:**
|
| 180 |
+
|
| 181 |
+
[More Information Needed]
|
| 182 |
+
|
| 183 |
+
## Glossary [optional]
|
| 184 |
+
|
| 185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 186 |
+
|
| 187 |
+
[More Information Needed]
|
| 188 |
+
|
| 189 |
+
## More Information [optional]
|
| 190 |
+
|
| 191 |
+
[More Information Needed]
|
| 192 |
+
|
| 193 |
+
## Model Card Authors [optional]
|
| 194 |
+
|
| 195 |
+
[More Information Needed]
|
| 196 |
+
|
| 197 |
+
## Model Card Contact
|
| 198 |
+
|
| 199 |
+
[More Information Needed]
|
| 200 |
+
### Framework versions
|
| 201 |
+
|
| 202 |
+
- PEFT 0.10.0
|
num_examples=400/llava-v1.5-13b_1.0/adapter_config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "liuhaotian/llava-v1.5-13b",
|
| 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": 256,
|
| 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": 128,
|
| 20 |
+
"rank_pattern": {},
|
| 21 |
+
"revision": null,
|
| 22 |
+
"target_modules": [
|
| 23 |
+
"k_proj",
|
| 24 |
+
"gate_proj",
|
| 25 |
+
"q_proj",
|
| 26 |
+
"o_proj",
|
| 27 |
+
"v_proj",
|
| 28 |
+
"up_proj",
|
| 29 |
+
"down_proj"
|
| 30 |
+
],
|
| 31 |
+
"task_type": "CAUSAL_LM",
|
| 32 |
+
"use_dora": false,
|
| 33 |
+
"use_rslora": false
|
| 34 |
+
}
|
num_examples=400/llava-v1.5-13b_1.0/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:09d91d82e712d1030dc46067af174545032cffe35fad81a818839e5716f39ea9
|
| 3 |
+
size 1001466944
|
num_examples=400/llava-v1.5-13b_1.0/special_tokens_map.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "</s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": "<unk>",
|
| 17 |
+
"unk_token": {
|
| 18 |
+
"content": "<unk>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
}
|
| 24 |
+
}
|
num_examples=400/llava-v1.5-13b_1.0/tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
| 3 |
+
size 499723
|
num_examples=400/llava-v1.5-13b_1.0/tokenizer_config.json
ADDED
|
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"0": {
|
| 6 |
+
"content": "<unk>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"1": {
|
| 14 |
+
"content": "<s>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"2": {
|
| 22 |
+
"content": "</s>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
}
|
| 29 |
+
},
|
| 30 |
+
"bos_token": "<s>",
|
| 31 |
+
"clean_up_tokenization_spaces": false,
|
| 32 |
+
"eos_token": "</s>",
|
| 33 |
+
"legacy": false,
|
| 34 |
+
"model_max_length": 2048,
|
| 35 |
+
"pad_token": "<unk>",
|
| 36 |
+
"padding_side": "right",
|
| 37 |
+
"sp_model_kwargs": {},
|
| 38 |
+
"spaces_between_special_tokens": false,
|
| 39 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 40 |
+
"unk_token": "<unk>",
|
| 41 |
+
"use_default_system_prompt": false
|
| 42 |
+
}
|
num_examples=400/llava-v1.5-13b_1.0/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:13a31b74c0a0e5235f89162d7a85b854f83db99409f5e9e9828384af833b44b4
|
| 3 |
+
size 6840
|
trainer_state.json
CHANGED
|
@@ -3,3907 +3,1987 @@
|
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
"epoch": 20.0,
|
| 5 |
"eval_steps": 500,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
-
"epoch": 0.
|
| 13 |
"learning_rate": 0.0,
|
| 14 |
-
"loss": 1.
|
| 15 |
"step": 1
|
| 16 |
},
|
| 17 |
{
|
| 18 |
-
"epoch": 0.
|
| 19 |
-
"learning_rate":
|
| 20 |
-
"loss": 1.
|
| 21 |
"step": 2
|
| 22 |
},
|
| 23 |
{
|
| 24 |
-
"epoch": 0.
|
| 25 |
-
"learning_rate":
|
| 26 |
-
"loss": 1.
|
| 27 |
"step": 3
|
| 28 |
},
|
| 29 |
{
|
| 30 |
-
"epoch": 0.
|
| 31 |
-
"learning_rate":
|
| 32 |
-
"loss": 1.
|
| 33 |
"step": 4
|
| 34 |
},
|
| 35 |
{
|
| 36 |
-
"epoch": 0.
|
| 37 |
-
"learning_rate": 0.
|
| 38 |
-
"loss": 1.
|
| 39 |
"step": 5
|
| 40 |
},
|
| 41 |
{
|
| 42 |
-
"epoch": 0.
|
| 43 |
-
"learning_rate": 0.
|
| 44 |
-
"loss": 1.
|
| 45 |
"step": 6
|
| 46 |
},
|
| 47 |
{
|
| 48 |
-
"epoch": 0.
|
| 49 |
-
"learning_rate": 0.
|
| 50 |
-
"loss": 1.
|
| 51 |
"step": 7
|
| 52 |
},
|
| 53 |
{
|
| 54 |
-
"epoch": 0.
|
| 55 |
-
"learning_rate": 0.
|
| 56 |
-
"loss":
|
| 57 |
"step": 8
|
| 58 |
},
|
| 59 |
{
|
| 60 |
-
"epoch": 0.
|
| 61 |
-
"learning_rate": 0.
|
| 62 |
-
"loss": 0.
|
| 63 |
"step": 9
|
| 64 |
},
|
| 65 |
{
|
| 66 |
-
"epoch": 0.
|
| 67 |
-
"learning_rate": 0.
|
| 68 |
-
"loss":
|
| 69 |
"step": 10
|
| 70 |
},
|
| 71 |
{
|
| 72 |
-
"epoch": 0.
|
| 73 |
-
"learning_rate": 0.
|
| 74 |
-
"loss":
|
| 75 |
"step": 11
|
| 76 |
},
|
| 77 |
{
|
| 78 |
-
"epoch": 0.
|
| 79 |
-
"learning_rate": 0.
|
| 80 |
-
"loss": 0.
|
| 81 |
"step": 12
|
| 82 |
},
|
| 83 |
{
|
| 84 |
-
"epoch": 0.
|
| 85 |
-
"learning_rate": 0.
|
| 86 |
-
"loss": 0.
|
| 87 |
"step": 13
|
| 88 |
},
|
| 89 |
{
|
| 90 |
-
"epoch": 0.
|
| 91 |
-
"learning_rate": 0.
|
| 92 |
-
"loss": 0.
|
| 93 |
"step": 14
|
| 94 |
},
|
| 95 |
{
|
| 96 |
-
"epoch": 0
|
| 97 |
-
"learning_rate": 0.
|
| 98 |
-
"loss": 0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 99 |
"step": 15
|
| 100 |
},
|
| 101 |
{
|
| 102 |
-
"epoch":
|
| 103 |
-
"learning_rate": 0.
|
| 104 |
-
"loss": 0.
|
| 105 |
"step": 16
|
| 106 |
},
|
| 107 |
{
|
| 108 |
-
"epoch":
|
| 109 |
-
"learning_rate": 0.
|
| 110 |
-
"loss": 0.
|
| 111 |
"step": 17
|
| 112 |
},
|
| 113 |
{
|
| 114 |
-
"epoch":
|
| 115 |
-
"learning_rate": 0.
|
| 116 |
-
"loss": 0.
|
| 117 |
"step": 18
|
| 118 |
},
|
| 119 |
{
|
| 120 |
-
"epoch":
|
| 121 |
"learning_rate": 0.0002,
|
| 122 |
-
"loss": 0.
|
| 123 |
"step": 19
|
| 124 |
},
|
| 125 |
{
|
| 126 |
-
"epoch":
|
| 127 |
"learning_rate": 0.0002,
|
| 128 |
-
"loss": 0.
|
| 129 |
"step": 20
|
| 130 |
},
|
| 131 |
{
|
| 132 |
-
"epoch":
|
| 133 |
"learning_rate": 0.0002,
|
| 134 |
-
"loss": 0.
|
| 135 |
"step": 21
|
| 136 |
},
|
| 137 |
{
|
| 138 |
-
"epoch":
|
| 139 |
"learning_rate": 0.0002,
|
| 140 |
-
"loss": 0.
|
| 141 |
"step": 22
|
| 142 |
},
|
| 143 |
{
|
| 144 |
-
"epoch":
|
| 145 |
"learning_rate": 0.0002,
|
| 146 |
-
"loss": 0.
|
| 147 |
"step": 23
|
| 148 |
},
|
| 149 |
{
|
| 150 |
-
"epoch":
|
| 151 |
"learning_rate": 0.0002,
|
| 152 |
-
"loss": 0.
|
| 153 |
"step": 24
|
| 154 |
},
|
| 155 |
{
|
| 156 |
-
"epoch":
|
| 157 |
"learning_rate": 0.0002,
|
| 158 |
-
"loss": 0.
|
| 159 |
"step": 25
|
| 160 |
},
|
| 161 |
{
|
| 162 |
-
"epoch":
|
| 163 |
"learning_rate": 0.0002,
|
| 164 |
-
"loss": 0.
|
| 165 |
"step": 26
|
| 166 |
},
|
| 167 |
{
|
| 168 |
-
"epoch":
|
| 169 |
"learning_rate": 0.0002,
|
| 170 |
-
"loss": 0.
|
| 171 |
"step": 27
|
| 172 |
},
|
| 173 |
{
|
| 174 |
-
"epoch":
|
| 175 |
"learning_rate": 0.0002,
|
| 176 |
-
"loss": 0.
|
| 177 |
"step": 28
|
| 178 |
},
|
| 179 |
{
|
| 180 |
-
"epoch":
|
| 181 |
"learning_rate": 0.0002,
|
| 182 |
-
"loss": 0.
|
| 183 |
"step": 29
|
| 184 |
},
|
| 185 |
{
|
| 186 |
-
"epoch": 0
|
| 187 |
"learning_rate": 0.0002,
|
| 188 |
-
"loss": 0.
|
| 189 |
"step": 30
|
| 190 |
},
|
| 191 |
{
|
| 192 |
-
"epoch":
|
| 193 |
-
"
|
| 194 |
-
"
|
| 195 |
-
"
|
|
|
|
|
|
|
| 196 |
},
|
| 197 |
{
|
| 198 |
-
"epoch":
|
| 199 |
-
"
|
| 200 |
-
"
|
| 201 |
-
"eval_samples_per_second": 12.288,
|
| 202 |
-
"eval_steps_per_second": 0.392,
|
| 203 |
"step": 31
|
| 204 |
},
|
| 205 |
{
|
| 206 |
-
"epoch":
|
| 207 |
"learning_rate": 0.0002,
|
| 208 |
-
"loss": 0.
|
| 209 |
"step": 32
|
| 210 |
},
|
| 211 |
{
|
| 212 |
-
"epoch":
|
| 213 |
"learning_rate": 0.0002,
|
| 214 |
-
"loss": 0.
|
| 215 |
"step": 33
|
| 216 |
},
|
| 217 |
{
|
| 218 |
-
"epoch":
|
| 219 |
"learning_rate": 0.0002,
|
| 220 |
-
"loss": 0.
|
| 221 |
"step": 34
|
| 222 |
},
|
| 223 |
{
|
| 224 |
-
"epoch":
|
| 225 |
"learning_rate": 0.0002,
|
| 226 |
-
"loss": 0.
|
| 227 |
"step": 35
|
| 228 |
},
|
| 229 |
{
|
| 230 |
-
"epoch":
|
| 231 |
"learning_rate": 0.0002,
|
| 232 |
-
"loss": 0.
|
| 233 |
"step": 36
|
| 234 |
},
|
| 235 |
{
|
| 236 |
-
"epoch":
|
| 237 |
"learning_rate": 0.0002,
|
| 238 |
-
"loss": 0.
|
| 239 |
"step": 37
|
| 240 |
},
|
| 241 |
{
|
| 242 |
-
"epoch":
|
| 243 |
"learning_rate": 0.0002,
|
| 244 |
-
"loss": 0.
|
| 245 |
"step": 38
|
| 246 |
},
|
| 247 |
{
|
| 248 |
-
"epoch":
|
| 249 |
"learning_rate": 0.0002,
|
| 250 |
-
"loss": 0.
|
| 251 |
"step": 39
|
| 252 |
},
|
| 253 |
{
|
| 254 |
-
"epoch":
|
| 255 |
"learning_rate": 0.0002,
|
| 256 |
-
"loss": 0.
|
| 257 |
"step": 40
|
| 258 |
},
|
| 259 |
{
|
| 260 |
-
"epoch":
|
| 261 |
"learning_rate": 0.0002,
|
| 262 |
-
"loss": 0.
|
| 263 |
"step": 41
|
| 264 |
},
|
| 265 |
{
|
| 266 |
-
"epoch":
|
| 267 |
"learning_rate": 0.0002,
|
| 268 |
-
"loss": 0.
|
| 269 |
"step": 42
|
| 270 |
},
|
| 271 |
{
|
| 272 |
-
"epoch":
|
| 273 |
"learning_rate": 0.0002,
|
| 274 |
-
"loss": 0.
|
| 275 |
"step": 43
|
| 276 |
},
|
| 277 |
{
|
| 278 |
-
"epoch":
|
| 279 |
"learning_rate": 0.0002,
|
| 280 |
-
"loss": 0.
|
| 281 |
"step": 44
|
| 282 |
},
|
| 283 |
{
|
| 284 |
-
"epoch":
|
| 285 |
"learning_rate": 0.0002,
|
| 286 |
-
"loss": 0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 287 |
"step": 45
|
| 288 |
},
|
| 289 |
{
|
| 290 |
-
"epoch":
|
| 291 |
"learning_rate": 0.0002,
|
| 292 |
-
"loss": 0.
|
| 293 |
"step": 46
|
| 294 |
},
|
| 295 |
{
|
| 296 |
-
"epoch":
|
| 297 |
"learning_rate": 0.0002,
|
| 298 |
-
"loss": 0.
|
| 299 |
"step": 47
|
| 300 |
},
|
| 301 |
{
|
| 302 |
-
"epoch":
|
| 303 |
"learning_rate": 0.0002,
|
| 304 |
-
"loss": 0.
|
| 305 |
"step": 48
|
| 306 |
},
|
| 307 |
{
|
| 308 |
-
"epoch":
|
| 309 |
"learning_rate": 0.0002,
|
| 310 |
-
"loss": 0.
|
| 311 |
"step": 49
|
| 312 |
},
|
| 313 |
{
|
| 314 |
-
"epoch":
|
| 315 |
"learning_rate": 0.0002,
|
| 316 |
-
"loss": 0.
|
| 317 |
"step": 50
|
| 318 |
},
|
| 319 |
{
|
| 320 |
-
"epoch":
|
| 321 |
"learning_rate": 0.0002,
|
| 322 |
-
"loss": 0.
|
| 323 |
"step": 51
|
| 324 |
},
|
| 325 |
{
|
| 326 |
-
"epoch":
|
| 327 |
"learning_rate": 0.0002,
|
| 328 |
-
"loss": 0.
|
| 329 |
"step": 52
|
| 330 |
},
|
| 331 |
{
|
| 332 |
-
"epoch":
|
| 333 |
"learning_rate": 0.0002,
|
| 334 |
-
"loss": 0.
|
| 335 |
"step": 53
|
| 336 |
},
|
| 337 |
{
|
| 338 |
-
"epoch":
|
| 339 |
"learning_rate": 0.0002,
|
| 340 |
-
"loss": 0.
|
| 341 |
"step": 54
|
| 342 |
},
|
| 343 |
{
|
| 344 |
-
"epoch":
|
| 345 |
"learning_rate": 0.0002,
|
| 346 |
-
"loss": 0.
|
| 347 |
"step": 55
|
| 348 |
},
|
| 349 |
{
|
| 350 |
-
"epoch":
|
| 351 |
"learning_rate": 0.0002,
|
| 352 |
-
"loss": 0.
|
| 353 |
"step": 56
|
| 354 |
},
|
| 355 |
{
|
| 356 |
-
"epoch":
|
| 357 |
"learning_rate": 0.0002,
|
| 358 |
-
"loss": 0.
|
| 359 |
"step": 57
|
| 360 |
},
|
| 361 |
{
|
| 362 |
-
"epoch":
|
| 363 |
"learning_rate": 0.0002,
|
| 364 |
-
"loss": 0.
|
| 365 |
"step": 58
|
| 366 |
},
|
| 367 |
{
|
| 368 |
-
"epoch":
|
| 369 |
"learning_rate": 0.0002,
|
| 370 |
-
"loss": 0.
|
| 371 |
"step": 59
|
| 372 |
},
|
| 373 |
{
|
| 374 |
-
"epoch":
|
| 375 |
"learning_rate": 0.0002,
|
| 376 |
-
"loss": 0.
|
| 377 |
"step": 60
|
| 378 |
},
|
| 379 |
{
|
| 380 |
-
"epoch":
|
| 381 |
-
"
|
| 382 |
-
"
|
| 383 |
-
"
|
|
|
|
|
|
|
| 384 |
},
|
| 385 |
{
|
| 386 |
-
"epoch":
|
| 387 |
"learning_rate": 0.0002,
|
| 388 |
-
"loss": 0.
|
| 389 |
-
"step":
|
| 390 |
},
|
| 391 |
{
|
| 392 |
-
"epoch":
|
| 393 |
-
"
|
| 394 |
-
"
|
| 395 |
-
"eval_samples_per_second": 12.227,
|
| 396 |
-
"eval_steps_per_second": 0.39,
|
| 397 |
"step": 62
|
| 398 |
},
|
| 399 |
{
|
| 400 |
-
"epoch": 2
|
| 401 |
"learning_rate": 0.0002,
|
| 402 |
-
"loss": 0.
|
| 403 |
"step": 63
|
| 404 |
},
|
| 405 |
{
|
| 406 |
-
"epoch":
|
| 407 |
"learning_rate": 0.0002,
|
| 408 |
-
"loss": 0.
|
| 409 |
"step": 64
|
| 410 |
},
|
| 411 |
{
|
| 412 |
-
"epoch":
|
| 413 |
"learning_rate": 0.0002,
|
| 414 |
-
"loss": 0.
|
| 415 |
"step": 65
|
| 416 |
},
|
| 417 |
{
|
| 418 |
-
"epoch":
|
| 419 |
"learning_rate": 0.0002,
|
| 420 |
-
"loss": 0.
|
| 421 |
"step": 66
|
| 422 |
},
|
| 423 |
{
|
| 424 |
-
"epoch":
|
| 425 |
"learning_rate": 0.0002,
|
| 426 |
-
"loss": 0.
|
| 427 |
"step": 67
|
| 428 |
},
|
| 429 |
{
|
| 430 |
-
"epoch":
|
| 431 |
"learning_rate": 0.0002,
|
| 432 |
-
"loss": 0.
|
| 433 |
"step": 68
|
| 434 |
},
|
| 435 |
{
|
| 436 |
-
"epoch":
|
| 437 |
"learning_rate": 0.0002,
|
| 438 |
-
"loss": 0.
|
| 439 |
"step": 69
|
| 440 |
},
|
| 441 |
{
|
| 442 |
-
"epoch":
|
| 443 |
"learning_rate": 0.0002,
|
| 444 |
-
"loss": 0.
|
| 445 |
"step": 70
|
| 446 |
},
|
| 447 |
{
|
| 448 |
-
"epoch":
|
| 449 |
"learning_rate": 0.0002,
|
| 450 |
-
"loss": 0.
|
| 451 |
"step": 71
|
| 452 |
},
|
| 453 |
{
|
| 454 |
-
"epoch":
|
| 455 |
"learning_rate": 0.0002,
|
| 456 |
-
"loss": 0.
|
| 457 |
"step": 72
|
| 458 |
},
|
| 459 |
{
|
| 460 |
-
"epoch":
|
| 461 |
"learning_rate": 0.0002,
|
| 462 |
-
"loss": 0.
|
| 463 |
"step": 73
|
| 464 |
},
|
| 465 |
{
|
| 466 |
-
"epoch":
|
| 467 |
"learning_rate": 0.0002,
|
| 468 |
-
"loss": 0.
|
| 469 |
"step": 74
|
| 470 |
},
|
| 471 |
{
|
| 472 |
-
"epoch":
|
| 473 |
"learning_rate": 0.0002,
|
| 474 |
-
"loss": 0.
|
| 475 |
"step": 75
|
| 476 |
},
|
| 477 |
{
|
| 478 |
-
"epoch":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 479 |
"learning_rate": 0.0002,
|
| 480 |
-
"loss": 0.
|
| 481 |
"step": 76
|
| 482 |
},
|
| 483 |
{
|
| 484 |
-
"epoch":
|
| 485 |
"learning_rate": 0.0002,
|
| 486 |
-
"loss": 0.
|
| 487 |
"step": 77
|
| 488 |
},
|
| 489 |
{
|
| 490 |
-
"epoch": 2
|
| 491 |
"learning_rate": 0.0002,
|
| 492 |
-
"loss": 0.
|
| 493 |
"step": 78
|
| 494 |
},
|
| 495 |
{
|
| 496 |
-
"epoch":
|
| 497 |
"learning_rate": 0.0002,
|
| 498 |
-
"loss": 0.
|
| 499 |
"step": 79
|
| 500 |
},
|
| 501 |
{
|
| 502 |
-
"epoch":
|
| 503 |
"learning_rate": 0.0002,
|
| 504 |
-
"loss": 0.
|
| 505 |
"step": 80
|
| 506 |
},
|
| 507 |
{
|
| 508 |
-
"epoch":
|
| 509 |
"learning_rate": 0.0002,
|
| 510 |
-
"loss": 0.
|
| 511 |
"step": 81
|
| 512 |
},
|
| 513 |
{
|
| 514 |
-
"epoch":
|
| 515 |
"learning_rate": 0.0002,
|
| 516 |
-
"loss": 0.
|
| 517 |
"step": 82
|
| 518 |
},
|
| 519 |
{
|
| 520 |
-
"epoch":
|
| 521 |
"learning_rate": 0.0002,
|
| 522 |
-
"loss": 0.
|
| 523 |
"step": 83
|
| 524 |
},
|
| 525 |
{
|
| 526 |
-
"epoch":
|
| 527 |
"learning_rate": 0.0002,
|
| 528 |
-
"loss": 0.
|
| 529 |
"step": 84
|
| 530 |
},
|
| 531 |
{
|
| 532 |
-
"epoch":
|
| 533 |
"learning_rate": 0.0002,
|
| 534 |
-
"loss": 0.
|
| 535 |
"step": 85
|
| 536 |
},
|
| 537 |
{
|
| 538 |
-
"epoch":
|
| 539 |
"learning_rate": 0.0002,
|
| 540 |
-
"loss": 0.
|
| 541 |
"step": 86
|
| 542 |
},
|
| 543 |
{
|
| 544 |
-
"epoch":
|
| 545 |
"learning_rate": 0.0002,
|
| 546 |
-
"loss": 0.
|
| 547 |
"step": 87
|
| 548 |
},
|
| 549 |
{
|
| 550 |
-
"epoch":
|
| 551 |
"learning_rate": 0.0002,
|
| 552 |
-
"loss": 0.
|
| 553 |
"step": 88
|
| 554 |
},
|
| 555 |
{
|
| 556 |
-
"epoch":
|
| 557 |
"learning_rate": 0.0002,
|
| 558 |
-
"loss": 0.
|
| 559 |
"step": 89
|
| 560 |
},
|
| 561 |
{
|
| 562 |
-
"epoch":
|
| 563 |
"learning_rate": 0.0002,
|
| 564 |
-
"loss": 0.
|
| 565 |
"step": 90
|
| 566 |
},
|
| 567 |
{
|
| 568 |
-
"epoch":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 569 |
"learning_rate": 0.0002,
|
| 570 |
-
"loss": 0.
|
| 571 |
"step": 91
|
| 572 |
},
|
| 573 |
{
|
| 574 |
-
"epoch":
|
| 575 |
"learning_rate": 0.0002,
|
| 576 |
-
"loss": 0.
|
| 577 |
"step": 92
|
| 578 |
},
|
| 579 |
{
|
| 580 |
-
"epoch":
|
| 581 |
"learning_rate": 0.0002,
|
| 582 |
-
"loss": 0.
|
| 583 |
-
"step": 93
|
| 584 |
-
},
|
| 585 |
-
{
|
| 586 |
-
"epoch": 3.0,
|
| 587 |
-
"eval_loss": 0.014188293367624283,
|
| 588 |
-
"eval_runtime": 79.3578,
|
| 589 |
-
"eval_samples_per_second": 12.236,
|
| 590 |
-
"eval_steps_per_second": 0.391,
|
| 591 |
"step": 93
|
| 592 |
},
|
| 593 |
{
|
| 594 |
-
"epoch":
|
| 595 |
"learning_rate": 0.0002,
|
| 596 |
-
"loss": 0.
|
| 597 |
"step": 94
|
| 598 |
},
|
| 599 |
{
|
| 600 |
-
"epoch":
|
| 601 |
"learning_rate": 0.0002,
|
| 602 |
-
"loss": 0.
|
| 603 |
"step": 95
|
| 604 |
},
|
| 605 |
{
|
| 606 |
-
"epoch":
|
| 607 |
"learning_rate": 0.0002,
|
| 608 |
-
"loss": 0.
|
| 609 |
"step": 96
|
| 610 |
},
|
| 611 |
{
|
| 612 |
-
"epoch":
|
| 613 |
"learning_rate": 0.0002,
|
| 614 |
-
"loss": 0.
|
| 615 |
"step": 97
|
| 616 |
},
|
| 617 |
{
|
| 618 |
-
"epoch":
|
| 619 |
"learning_rate": 0.0002,
|
| 620 |
-
"loss": 0.
|
| 621 |
"step": 98
|
| 622 |
},
|
| 623 |
{
|
| 624 |
-
"epoch":
|
| 625 |
"learning_rate": 0.0002,
|
| 626 |
-
"loss": 0.
|
| 627 |
"step": 99
|
| 628 |
},
|
| 629 |
{
|
| 630 |
-
"epoch":
|
| 631 |
"learning_rate": 0.0002,
|
| 632 |
-
"loss": 0.
|
| 633 |
"step": 100
|
| 634 |
},
|
| 635 |
{
|
| 636 |
-
"epoch":
|
| 637 |
"learning_rate": 0.0002,
|
| 638 |
-
"loss": 0.
|
| 639 |
"step": 101
|
| 640 |
},
|
| 641 |
{
|
| 642 |
-
"epoch":
|
| 643 |
"learning_rate": 0.0002,
|
| 644 |
-
"loss": 0.
|
| 645 |
"step": 102
|
| 646 |
},
|
| 647 |
{
|
| 648 |
-
"epoch":
|
| 649 |
"learning_rate": 0.0002,
|
| 650 |
-
"loss": 0.
|
| 651 |
"step": 103
|
| 652 |
},
|
| 653 |
{
|
| 654 |
-
"epoch":
|
| 655 |
"learning_rate": 0.0002,
|
| 656 |
-
"loss": 0.
|
| 657 |
"step": 104
|
| 658 |
},
|
| 659 |
{
|
| 660 |
-
"epoch":
|
| 661 |
"learning_rate": 0.0002,
|
| 662 |
-
"loss": 0.
|
| 663 |
"step": 105
|
| 664 |
},
|
| 665 |
{
|
| 666 |
-
"epoch":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 667 |
"learning_rate": 0.0002,
|
| 668 |
-
"loss": 0.
|
| 669 |
"step": 106
|
| 670 |
},
|
| 671 |
{
|
| 672 |
-
"epoch":
|
| 673 |
"learning_rate": 0.0002,
|
| 674 |
-
"loss": 0.
|
| 675 |
"step": 107
|
| 676 |
},
|
| 677 |
{
|
| 678 |
-
"epoch":
|
| 679 |
"learning_rate": 0.0002,
|
| 680 |
-
"loss": 0.
|
| 681 |
"step": 108
|
| 682 |
},
|
| 683 |
{
|
| 684 |
-
"epoch":
|
| 685 |
"learning_rate": 0.0002,
|
| 686 |
-
"loss": 0.
|
| 687 |
"step": 109
|
| 688 |
},
|
| 689 |
{
|
| 690 |
-
"epoch":
|
| 691 |
"learning_rate": 0.0002,
|
| 692 |
-
"loss": 0.
|
| 693 |
"step": 110
|
| 694 |
},
|
| 695 |
{
|
| 696 |
-
"epoch":
|
| 697 |
"learning_rate": 0.0002,
|
| 698 |
-
"loss": 0.
|
| 699 |
"step": 111
|
| 700 |
},
|
| 701 |
{
|
| 702 |
-
"epoch":
|
| 703 |
"learning_rate": 0.0002,
|
| 704 |
-
"loss": 0.
|
| 705 |
"step": 112
|
| 706 |
},
|
| 707 |
{
|
| 708 |
-
"epoch":
|
| 709 |
"learning_rate": 0.0002,
|
| 710 |
-
"loss": 0.
|
| 711 |
"step": 113
|
| 712 |
},
|
| 713 |
{
|
| 714 |
-
"epoch":
|
| 715 |
"learning_rate": 0.0002,
|
| 716 |
-
"loss": 0.
|
| 717 |
"step": 114
|
| 718 |
},
|
| 719 |
{
|
| 720 |
-
"epoch":
|
| 721 |
"learning_rate": 0.0002,
|
| 722 |
-
"loss": 0.
|
| 723 |
"step": 115
|
| 724 |
},
|
| 725 |
{
|
| 726 |
-
"epoch":
|
| 727 |
"learning_rate": 0.0002,
|
| 728 |
-
"loss": 0.
|
| 729 |
"step": 116
|
| 730 |
},
|
| 731 |
{
|
| 732 |
-
"epoch":
|
| 733 |
"learning_rate": 0.0002,
|
| 734 |
-
"loss": 0.
|
| 735 |
"step": 117
|
| 736 |
},
|
| 737 |
{
|
| 738 |
-
"epoch":
|
| 739 |
"learning_rate": 0.0002,
|
| 740 |
-
"loss": 0.
|
| 741 |
"step": 118
|
| 742 |
},
|
| 743 |
{
|
| 744 |
-
"epoch":
|
| 745 |
"learning_rate": 0.0002,
|
| 746 |
-
"loss": 0.
|
| 747 |
"step": 119
|
| 748 |
},
|
| 749 |
{
|
| 750 |
-
"epoch":
|
| 751 |
"learning_rate": 0.0002,
|
| 752 |
-
"loss": 0.
|
| 753 |
"step": 120
|
| 754 |
},
|
| 755 |
{
|
| 756 |
-
"epoch":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 757 |
"learning_rate": 0.0002,
|
| 758 |
-
"loss": 0.
|
| 759 |
"step": 121
|
| 760 |
},
|
| 761 |
{
|
| 762 |
-
"epoch":
|
| 763 |
"learning_rate": 0.0002,
|
| 764 |
-
"loss": 0.
|
| 765 |
"step": 122
|
| 766 |
},
|
| 767 |
{
|
| 768 |
-
"epoch":
|
| 769 |
"learning_rate": 0.0002,
|
| 770 |
-
"loss": 0.
|
| 771 |
"step": 123
|
| 772 |
},
|
| 773 |
{
|
| 774 |
-
"epoch":
|
| 775 |
"learning_rate": 0.0002,
|
| 776 |
-
"loss": 0.
|
| 777 |
-
"step": 124
|
| 778 |
-
},
|
| 779 |
-
{
|
| 780 |
-
"epoch": 4.0,
|
| 781 |
-
"eval_loss": 0.00705763790756464,
|
| 782 |
-
"eval_runtime": 79.4948,
|
| 783 |
-
"eval_samples_per_second": 12.215,
|
| 784 |
-
"eval_steps_per_second": 0.39,
|
| 785 |
"step": 124
|
| 786 |
},
|
| 787 |
{
|
| 788 |
-
"epoch":
|
| 789 |
"learning_rate": 0.0002,
|
| 790 |
-
"loss": 0.
|
| 791 |
"step": 125
|
| 792 |
},
|
| 793 |
{
|
| 794 |
-
"epoch": 4
|
| 795 |
"learning_rate": 0.0002,
|
| 796 |
-
"loss": 0.
|
| 797 |
"step": 126
|
| 798 |
},
|
| 799 |
{
|
| 800 |
-
"epoch":
|
| 801 |
"learning_rate": 0.0002,
|
| 802 |
-
"loss": 0.
|
| 803 |
"step": 127
|
| 804 |
},
|
| 805 |
{
|
| 806 |
-
"epoch":
|
| 807 |
"learning_rate": 0.0002,
|
| 808 |
-
"loss": 0.
|
| 809 |
"step": 128
|
| 810 |
},
|
| 811 |
{
|
| 812 |
-
"epoch":
|
| 813 |
"learning_rate": 0.0002,
|
| 814 |
-
"loss": 0.
|
| 815 |
"step": 129
|
| 816 |
},
|
| 817 |
{
|
| 818 |
-
"epoch":
|
| 819 |
"learning_rate": 0.0002,
|
| 820 |
-
"loss": 0.
|
| 821 |
"step": 130
|
| 822 |
},
|
| 823 |
{
|
| 824 |
-
"epoch":
|
| 825 |
"learning_rate": 0.0002,
|
| 826 |
-
"loss": 0.
|
| 827 |
"step": 131
|
| 828 |
},
|
| 829 |
{
|
| 830 |
-
"epoch":
|
| 831 |
"learning_rate": 0.0002,
|
| 832 |
-
"loss": 0.
|
| 833 |
"step": 132
|
| 834 |
},
|
| 835 |
{
|
| 836 |
-
"epoch":
|
| 837 |
"learning_rate": 0.0002,
|
| 838 |
-
"loss": 0.
|
| 839 |
"step": 133
|
| 840 |
},
|
| 841 |
{
|
| 842 |
-
"epoch":
|
| 843 |
"learning_rate": 0.0002,
|
| 844 |
-
"loss": 0.
|
| 845 |
"step": 134
|
| 846 |
},
|
| 847 |
{
|
| 848 |
-
"epoch":
|
| 849 |
"learning_rate": 0.0002,
|
| 850 |
-
"loss": 0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 851 |
"step": 135
|
| 852 |
},
|
| 853 |
{
|
| 854 |
-
"epoch":
|
| 855 |
"learning_rate": 0.0002,
|
| 856 |
-
"loss": 0.
|
| 857 |
"step": 136
|
| 858 |
},
|
| 859 |
{
|
| 860 |
-
"epoch":
|
| 861 |
"learning_rate": 0.0002,
|
| 862 |
-
"loss": 0.
|
| 863 |
"step": 137
|
| 864 |
},
|
| 865 |
{
|
| 866 |
-
"epoch":
|
| 867 |
"learning_rate": 0.0002,
|
| 868 |
-
"loss": 0.
|
| 869 |
"step": 138
|
| 870 |
},
|
| 871 |
{
|
| 872 |
-
"epoch":
|
| 873 |
"learning_rate": 0.0002,
|
| 874 |
-
"loss": 0.
|
| 875 |
"step": 139
|
| 876 |
},
|
| 877 |
{
|
| 878 |
-
"epoch":
|
| 879 |
"learning_rate": 0.0002,
|
| 880 |
-
"loss": 0.
|
| 881 |
"step": 140
|
| 882 |
},
|
| 883 |
{
|
| 884 |
-
"epoch": 4
|
| 885 |
"learning_rate": 0.0002,
|
| 886 |
-
"loss": 0.
|
| 887 |
"step": 141
|
| 888 |
},
|
| 889 |
{
|
| 890 |
-
"epoch":
|
| 891 |
"learning_rate": 0.0002,
|
| 892 |
-
"loss": 0.
|
| 893 |
"step": 142
|
| 894 |
},
|
| 895 |
{
|
| 896 |
-
"epoch":
|
| 897 |
"learning_rate": 0.0002,
|
| 898 |
-
"loss": 0.
|
| 899 |
"step": 143
|
| 900 |
},
|
| 901 |
{
|
| 902 |
-
"epoch":
|
| 903 |
"learning_rate": 0.0002,
|
| 904 |
-
"loss": 0.
|
| 905 |
"step": 144
|
| 906 |
},
|
| 907 |
{
|
| 908 |
-
"epoch":
|
| 909 |
"learning_rate": 0.0002,
|
| 910 |
-
"loss": 0.
|
| 911 |
"step": 145
|
| 912 |
},
|
| 913 |
{
|
| 914 |
-
"epoch":
|
| 915 |
"learning_rate": 0.0002,
|
| 916 |
-
"loss": 0.
|
| 917 |
"step": 146
|
| 918 |
},
|
| 919 |
{
|
| 920 |
-
"epoch":
|
| 921 |
"learning_rate": 0.0002,
|
| 922 |
-
"loss": 0.
|
| 923 |
"step": 147
|
| 924 |
},
|
| 925 |
{
|
| 926 |
-
"epoch":
|
| 927 |
"learning_rate": 0.0002,
|
| 928 |
-
"loss": 0.
|
| 929 |
"step": 148
|
| 930 |
},
|
| 931 |
{
|
| 932 |
-
"epoch":
|
| 933 |
"learning_rate": 0.0002,
|
| 934 |
-
"loss": 0.
|
| 935 |
"step": 149
|
| 936 |
},
|
| 937 |
{
|
| 938 |
-
"epoch":
|
| 939 |
"learning_rate": 0.0002,
|
| 940 |
-
"loss": 0.
|
| 941 |
"step": 150
|
| 942 |
},
|
| 943 |
{
|
| 944 |
-
"epoch":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 945 |
"learning_rate": 0.0002,
|
| 946 |
-
"loss": 0.
|
| 947 |
"step": 151
|
| 948 |
},
|
| 949 |
{
|
| 950 |
-
"epoch":
|
| 951 |
"learning_rate": 0.0002,
|
| 952 |
-
"loss": 0.
|
| 953 |
"step": 152
|
| 954 |
},
|
| 955 |
{
|
| 956 |
-
"epoch":
|
| 957 |
"learning_rate": 0.0002,
|
| 958 |
-
"loss": 0.
|
| 959 |
"step": 153
|
| 960 |
},
|
| 961 |
{
|
| 962 |
-
"epoch":
|
| 963 |
"learning_rate": 0.0002,
|
| 964 |
-
"loss": 0.
|
| 965 |
"step": 154
|
| 966 |
},
|
| 967 |
{
|
| 968 |
-
"epoch":
|
| 969 |
"learning_rate": 0.0002,
|
| 970 |
-
"loss": 0.
|
| 971 |
-
"step": 155
|
| 972 |
-
},
|
| 973 |
-
{
|
| 974 |
-
"epoch": 5.0,
|
| 975 |
-
"eval_loss": 0.006716921925544739,
|
| 976 |
-
"eval_runtime": 78.8305,
|
| 977 |
-
"eval_samples_per_second": 12.318,
|
| 978 |
-
"eval_steps_per_second": 0.393,
|
| 979 |
"step": 155
|
| 980 |
},
|
| 981 |
{
|
| 982 |
-
"epoch":
|
| 983 |
"learning_rate": 0.0002,
|
| 984 |
-
"loss": 0.
|
| 985 |
"step": 156
|
| 986 |
},
|
| 987 |
{
|
| 988 |
-
"epoch":
|
| 989 |
"learning_rate": 0.0002,
|
| 990 |
-
"loss": 0.
|
| 991 |
"step": 157
|
| 992 |
},
|
| 993 |
{
|
| 994 |
-
"epoch":
|
| 995 |
"learning_rate": 0.0002,
|
| 996 |
-
"loss": 0.
|
| 997 |
"step": 158
|
| 998 |
},
|
| 999 |
{
|
| 1000 |
-
"epoch":
|
| 1001 |
"learning_rate": 0.0002,
|
| 1002 |
-
"loss": 0.
|
| 1003 |
"step": 159
|
| 1004 |
},
|
| 1005 |
{
|
| 1006 |
-
"epoch":
|
| 1007 |
"learning_rate": 0.0002,
|
| 1008 |
-
"loss": 0.
|
| 1009 |
"step": 160
|
| 1010 |
},
|
| 1011 |
{
|
| 1012 |
-
"epoch":
|
| 1013 |
"learning_rate": 0.0002,
|
| 1014 |
-
"loss": 0.
|
| 1015 |
"step": 161
|
| 1016 |
},
|
| 1017 |
{
|
| 1018 |
-
"epoch":
|
| 1019 |
"learning_rate": 0.0002,
|
| 1020 |
-
"loss": 0.
|
| 1021 |
"step": 162
|
| 1022 |
},
|
| 1023 |
{
|
| 1024 |
-
"epoch":
|
| 1025 |
"learning_rate": 0.0002,
|
| 1026 |
-
"loss": 0.
|
| 1027 |
"step": 163
|
| 1028 |
},
|
| 1029 |
{
|
| 1030 |
-
"epoch":
|
| 1031 |
"learning_rate": 0.0002,
|
| 1032 |
-
"loss": 0.
|
| 1033 |
"step": 164
|
| 1034 |
},
|
| 1035 |
{
|
| 1036 |
-
"epoch":
|
| 1037 |
"learning_rate": 0.0002,
|
| 1038 |
-
"loss": 0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1039 |
"step": 165
|
| 1040 |
},
|
| 1041 |
{
|
| 1042 |
-
"epoch":
|
| 1043 |
"learning_rate": 0.0002,
|
| 1044 |
-
"loss": 0.
|
| 1045 |
"step": 166
|
| 1046 |
},
|
| 1047 |
{
|
| 1048 |
-
"epoch":
|
| 1049 |
"learning_rate": 0.0002,
|
| 1050 |
-
"loss": 0.
|
| 1051 |
"step": 167
|
| 1052 |
},
|
| 1053 |
{
|
| 1054 |
-
"epoch":
|
| 1055 |
"learning_rate": 0.0002,
|
| 1056 |
-
"loss": 0.
|
| 1057 |
"step": 168
|
| 1058 |
},
|
| 1059 |
{
|
| 1060 |
-
"epoch":
|
| 1061 |
"learning_rate": 0.0002,
|
| 1062 |
-
"loss": 0.
|
| 1063 |
"step": 169
|
| 1064 |
},
|
| 1065 |
{
|
| 1066 |
-
"epoch":
|
| 1067 |
"learning_rate": 0.0002,
|
| 1068 |
-
"loss": 0.
|
| 1069 |
"step": 170
|
| 1070 |
},
|
| 1071 |
{
|
| 1072 |
-
"epoch":
|
| 1073 |
"learning_rate": 0.0002,
|
| 1074 |
-
"loss": 0.
|
| 1075 |
"step": 171
|
| 1076 |
},
|
| 1077 |
{
|
| 1078 |
-
"epoch":
|
| 1079 |
"learning_rate": 0.0002,
|
| 1080 |
-
"loss": 0.
|
| 1081 |
"step": 172
|
| 1082 |
},
|
| 1083 |
{
|
| 1084 |
-
"epoch":
|
| 1085 |
"learning_rate": 0.0002,
|
| 1086 |
-
"loss": 0.
|
| 1087 |
"step": 173
|
| 1088 |
},
|
| 1089 |
{
|
| 1090 |
-
"epoch":
|
| 1091 |
"learning_rate": 0.0002,
|
| 1092 |
-
"loss": 0.
|
| 1093 |
"step": 174
|
| 1094 |
},
|
| 1095 |
{
|
| 1096 |
-
"epoch":
|
| 1097 |
"learning_rate": 0.0002,
|
| 1098 |
-
"loss": 0.
|
| 1099 |
"step": 175
|
| 1100 |
},
|
| 1101 |
{
|
| 1102 |
-
"epoch":
|
| 1103 |
"learning_rate": 0.0002,
|
| 1104 |
-
"loss": 0.
|
| 1105 |
"step": 176
|
| 1106 |
},
|
| 1107 |
{
|
| 1108 |
-
"epoch":
|
| 1109 |
"learning_rate": 0.0002,
|
| 1110 |
-
"loss": 0.
|
| 1111 |
"step": 177
|
| 1112 |
},
|
| 1113 |
{
|
| 1114 |
-
"epoch":
|
| 1115 |
"learning_rate": 0.0002,
|
| 1116 |
-
"loss": 0.
|
| 1117 |
"step": 178
|
| 1118 |
},
|
| 1119 |
{
|
| 1120 |
-
"epoch":
|
| 1121 |
"learning_rate": 0.0002,
|
| 1122 |
-
"loss": 0.
|
| 1123 |
"step": 179
|
| 1124 |
},
|
| 1125 |
{
|
| 1126 |
-
"epoch":
|
| 1127 |
"learning_rate": 0.0002,
|
| 1128 |
-
"loss": 0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1129 |
"step": 180
|
| 1130 |
},
|
| 1131 |
{
|
| 1132 |
-
"epoch":
|
| 1133 |
"learning_rate": 0.0002,
|
| 1134 |
-
"loss": 0.
|
| 1135 |
"step": 181
|
| 1136 |
},
|
| 1137 |
{
|
| 1138 |
-
"epoch":
|
| 1139 |
"learning_rate": 0.0002,
|
| 1140 |
-
"loss": 0.
|
| 1141 |
"step": 182
|
| 1142 |
},
|
| 1143 |
{
|
| 1144 |
-
"epoch":
|
| 1145 |
"learning_rate": 0.0002,
|
| 1146 |
-
"loss": 0.
|
| 1147 |
"step": 183
|
| 1148 |
},
|
| 1149 |
{
|
| 1150 |
-
"epoch":
|
| 1151 |
"learning_rate": 0.0002,
|
| 1152 |
-
"loss": 0.
|
| 1153 |
"step": 184
|
| 1154 |
},
|
| 1155 |
{
|
| 1156 |
-
"epoch":
|
| 1157 |
"learning_rate": 0.0002,
|
| 1158 |
-
"loss": 0.
|
| 1159 |
"step": 185
|
| 1160 |
},
|
| 1161 |
{
|
| 1162 |
-
"epoch":
|
| 1163 |
"learning_rate": 0.0002,
|
| 1164 |
-
"loss": 0.
|
| 1165 |
-
"step": 186
|
| 1166 |
-
},
|
| 1167 |
-
{
|
| 1168 |
-
"epoch": 6.0,
|
| 1169 |
-
"eval_loss": 0.004568978678435087,
|
| 1170 |
-
"eval_runtime": 79.3401,
|
| 1171 |
-
"eval_samples_per_second": 12.238,
|
| 1172 |
-
"eval_steps_per_second": 0.391,
|
| 1173 |
"step": 186
|
| 1174 |
},
|
| 1175 |
{
|
| 1176 |
-
"epoch":
|
| 1177 |
"learning_rate": 0.0002,
|
| 1178 |
-
"loss": 0.
|
| 1179 |
"step": 187
|
| 1180 |
},
|
| 1181 |
{
|
| 1182 |
-
"epoch":
|
| 1183 |
"learning_rate": 0.0002,
|
| 1184 |
-
"loss": 0.
|
| 1185 |
"step": 188
|
| 1186 |
},
|
| 1187 |
{
|
| 1188 |
-
"epoch": 6
|
| 1189 |
"learning_rate": 0.0002,
|
| 1190 |
-
"loss": 0.
|
| 1191 |
"step": 189
|
| 1192 |
},
|
| 1193 |
{
|
| 1194 |
-
"epoch":
|
| 1195 |
"learning_rate": 0.0002,
|
| 1196 |
-
"loss": 0.
|
| 1197 |
"step": 190
|
| 1198 |
},
|
| 1199 |
{
|
| 1200 |
-
"epoch":
|
| 1201 |
"learning_rate": 0.0002,
|
| 1202 |
-
"loss": 0.
|
| 1203 |
"step": 191
|
| 1204 |
},
|
| 1205 |
{
|
| 1206 |
-
"epoch":
|
| 1207 |
"learning_rate": 0.0002,
|
| 1208 |
-
"loss": 0.
|
| 1209 |
"step": 192
|
| 1210 |
},
|
| 1211 |
{
|
| 1212 |
-
"epoch":
|
| 1213 |
"learning_rate": 0.0002,
|
| 1214 |
-
"loss": 0.
|
| 1215 |
"step": 193
|
| 1216 |
},
|
| 1217 |
{
|
| 1218 |
-
"epoch":
|
| 1219 |
"learning_rate": 0.0002,
|
| 1220 |
-
"loss": 0.
|
| 1221 |
"step": 194
|
| 1222 |
},
|
| 1223 |
{
|
| 1224 |
-
"epoch":
|
| 1225 |
"learning_rate": 0.0002,
|
| 1226 |
-
"loss": 0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1227 |
"step": 195
|
| 1228 |
},
|
| 1229 |
{
|
| 1230 |
-
"epoch":
|
| 1231 |
"learning_rate": 0.0002,
|
| 1232 |
-
"loss": 0.
|
| 1233 |
"step": 196
|
| 1234 |
},
|
| 1235 |
{
|
| 1236 |
-
"epoch":
|
| 1237 |
"learning_rate": 0.0002,
|
| 1238 |
-
"loss": 0.
|
| 1239 |
"step": 197
|
| 1240 |
},
|
| 1241 |
{
|
| 1242 |
-
"epoch":
|
| 1243 |
"learning_rate": 0.0002,
|
| 1244 |
-
"loss": 0.
|
| 1245 |
"step": 198
|
| 1246 |
},
|
| 1247 |
{
|
| 1248 |
-
"epoch":
|
| 1249 |
"learning_rate": 0.0002,
|
| 1250 |
-
"loss": 0.
|
| 1251 |
"step": 199
|
| 1252 |
},
|
| 1253 |
{
|
| 1254 |
-
"epoch":
|
| 1255 |
"learning_rate": 0.0002,
|
| 1256 |
-
"loss": 0.
|
| 1257 |
"step": 200
|
| 1258 |
},
|
| 1259 |
{
|
| 1260 |
-
"epoch":
|
| 1261 |
"learning_rate": 0.0002,
|
| 1262 |
-
"loss": 0.
|
| 1263 |
"step": 201
|
| 1264 |
},
|
| 1265 |
{
|
| 1266 |
-
"epoch":
|
| 1267 |
"learning_rate": 0.0002,
|
| 1268 |
-
"loss": 0.
|
| 1269 |
"step": 202
|
| 1270 |
},
|
| 1271 |
{
|
| 1272 |
-
"epoch":
|
| 1273 |
"learning_rate": 0.0002,
|
| 1274 |
-
"loss": 0.
|
| 1275 |
"step": 203
|
| 1276 |
},
|
| 1277 |
{
|
| 1278 |
-
"epoch": 6
|
| 1279 |
"learning_rate": 0.0002,
|
| 1280 |
-
"loss": 0.
|
| 1281 |
"step": 204
|
| 1282 |
},
|
| 1283 |
{
|
| 1284 |
-
"epoch":
|
| 1285 |
"learning_rate": 0.0002,
|
| 1286 |
-
"loss": 0.
|
| 1287 |
"step": 205
|
| 1288 |
},
|
| 1289 |
{
|
| 1290 |
-
"epoch":
|
| 1291 |
"learning_rate": 0.0002,
|
| 1292 |
-
"loss": 0.
|
| 1293 |
"step": 206
|
| 1294 |
},
|
| 1295 |
{
|
| 1296 |
-
"epoch":
|
| 1297 |
"learning_rate": 0.0002,
|
| 1298 |
-
"loss": 0.
|
| 1299 |
"step": 207
|
| 1300 |
},
|
| 1301 |
{
|
| 1302 |
-
"epoch":
|
| 1303 |
"learning_rate": 0.0002,
|
| 1304 |
-
"loss": 0.
|
| 1305 |
"step": 208
|
| 1306 |
},
|
| 1307 |
{
|
| 1308 |
-
"epoch":
|
| 1309 |
"learning_rate": 0.0002,
|
| 1310 |
-
"loss": 0.
|
| 1311 |
"step": 209
|
| 1312 |
},
|
| 1313 |
{
|
| 1314 |
-
"epoch":
|
| 1315 |
"learning_rate": 0.0002,
|
| 1316 |
-
"loss": 0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1317 |
"step": 210
|
| 1318 |
},
|
| 1319 |
{
|
| 1320 |
-
"epoch":
|
| 1321 |
"learning_rate": 0.0002,
|
| 1322 |
-
"loss": 0.
|
| 1323 |
"step": 211
|
| 1324 |
},
|
| 1325 |
{
|
| 1326 |
-
"epoch":
|
| 1327 |
"learning_rate": 0.0002,
|
| 1328 |
-
"loss": 0.
|
| 1329 |
"step": 212
|
| 1330 |
},
|
| 1331 |
{
|
| 1332 |
-
"epoch":
|
| 1333 |
"learning_rate": 0.0002,
|
| 1334 |
-
"loss": 0.
|
| 1335 |
"step": 213
|
| 1336 |
},
|
| 1337 |
{
|
| 1338 |
-
"epoch":
|
| 1339 |
"learning_rate": 0.0002,
|
| 1340 |
-
"loss": 0.
|
| 1341 |
"step": 214
|
| 1342 |
},
|
| 1343 |
{
|
| 1344 |
-
"epoch":
|
| 1345 |
"learning_rate": 0.0002,
|
| 1346 |
-
"loss": 0.
|
| 1347 |
"step": 215
|
| 1348 |
},
|
| 1349 |
{
|
| 1350 |
-
"epoch":
|
| 1351 |
"learning_rate": 0.0002,
|
| 1352 |
-
"loss": 0.
|
| 1353 |
"step": 216
|
| 1354 |
},
|
| 1355 |
{
|
| 1356 |
-
"epoch":
|
| 1357 |
"learning_rate": 0.0002,
|
| 1358 |
-
"loss": 0.
|
| 1359 |
-
"step": 217
|
| 1360 |
-
},
|
| 1361 |
-
{
|
| 1362 |
-
"epoch": 7.0,
|
| 1363 |
-
"eval_loss": 0.002206017728894949,
|
| 1364 |
-
"eval_runtime": 79.3964,
|
| 1365 |
-
"eval_samples_per_second": 12.23,
|
| 1366 |
-
"eval_steps_per_second": 0.39,
|
| 1367 |
"step": 217
|
| 1368 |
},
|
| 1369 |
{
|
| 1370 |
-
"epoch":
|
| 1371 |
"learning_rate": 0.0002,
|
| 1372 |
-
"loss": 0.
|
| 1373 |
"step": 218
|
| 1374 |
},
|
| 1375 |
{
|
| 1376 |
-
"epoch":
|
| 1377 |
"learning_rate": 0.0002,
|
| 1378 |
-
"loss": 0.
|
| 1379 |
"step": 219
|
| 1380 |
},
|
| 1381 |
{
|
| 1382 |
-
"epoch":
|
| 1383 |
"learning_rate": 0.0002,
|
| 1384 |
-
"loss": 0.
|
| 1385 |
"step": 220
|
| 1386 |
},
|
| 1387 |
{
|
| 1388 |
-
"epoch":
|
| 1389 |
"learning_rate": 0.0002,
|
| 1390 |
-
"loss": 0.
|
| 1391 |
"step": 221
|
| 1392 |
},
|
| 1393 |
{
|
| 1394 |
-
"epoch":
|
| 1395 |
"learning_rate": 0.0002,
|
| 1396 |
-
"loss": 0.
|
| 1397 |
"step": 222
|
| 1398 |
},
|
| 1399 |
{
|
| 1400 |
-
"epoch":
|
| 1401 |
"learning_rate": 0.0002,
|
| 1402 |
-
"loss": 0.
|
| 1403 |
"step": 223
|
| 1404 |
},
|
| 1405 |
{
|
| 1406 |
-
"epoch":
|
| 1407 |
"learning_rate": 0.0002,
|
| 1408 |
-
"loss": 0.
|
| 1409 |
"step": 224
|
| 1410 |
},
|
| 1411 |
{
|
| 1412 |
-
"epoch":
|
| 1413 |
"learning_rate": 0.0002,
|
| 1414 |
-
"loss": 0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1415 |
"step": 225
|
| 1416 |
},
|
| 1417 |
{
|
| 1418 |
-
"epoch":
|
| 1419 |
"learning_rate": 0.0002,
|
| 1420 |
-
"loss": 0.
|
| 1421 |
"step": 226
|
| 1422 |
},
|
| 1423 |
{
|
| 1424 |
-
"epoch":
|
| 1425 |
"learning_rate": 0.0002,
|
| 1426 |
-
"loss": 0.
|
| 1427 |
"step": 227
|
| 1428 |
},
|
| 1429 |
{
|
| 1430 |
-
"epoch":
|
| 1431 |
"learning_rate": 0.0002,
|
| 1432 |
-
"loss": 0.
|
| 1433 |
"step": 228
|
| 1434 |
},
|
| 1435 |
{
|
| 1436 |
-
"epoch":
|
| 1437 |
"learning_rate": 0.0002,
|
| 1438 |
-
"loss": 0.
|
| 1439 |
"step": 229
|
| 1440 |
},
|
| 1441 |
{
|
| 1442 |
-
"epoch":
|
| 1443 |
"learning_rate": 0.0002,
|
| 1444 |
-
"loss": 0.
|
| 1445 |
"step": 230
|
| 1446 |
},
|
| 1447 |
{
|
| 1448 |
-
"epoch":
|
| 1449 |
"learning_rate": 0.0002,
|
| 1450 |
-
"loss": 0.
|
| 1451 |
"step": 231
|
| 1452 |
},
|
| 1453 |
{
|
| 1454 |
-
"epoch":
|
| 1455 |
"learning_rate": 0.0002,
|
| 1456 |
-
"loss": 0.
|
| 1457 |
"step": 232
|
| 1458 |
},
|
| 1459 |
{
|
| 1460 |
-
"epoch":
|
| 1461 |
"learning_rate": 0.0002,
|
| 1462 |
-
"loss": 0.
|
| 1463 |
"step": 233
|
| 1464 |
},
|
| 1465 |
{
|
| 1466 |
-
"epoch":
|
| 1467 |
"learning_rate": 0.0002,
|
| 1468 |
-
"loss": 0.
|
| 1469 |
"step": 234
|
| 1470 |
},
|
| 1471 |
{
|
| 1472 |
-
"epoch":
|
| 1473 |
"learning_rate": 0.0002,
|
| 1474 |
-
"loss": 0.
|
| 1475 |
"step": 235
|
| 1476 |
},
|
| 1477 |
{
|
| 1478 |
-
"epoch":
|
| 1479 |
"learning_rate": 0.0002,
|
| 1480 |
-
"loss": 0.
|
| 1481 |
"step": 236
|
| 1482 |
},
|
| 1483 |
{
|
| 1484 |
-
"epoch":
|
| 1485 |
"learning_rate": 0.0002,
|
| 1486 |
-
"loss": 0.
|
| 1487 |
"step": 237
|
| 1488 |
},
|
| 1489 |
{
|
| 1490 |
-
"epoch":
|
| 1491 |
"learning_rate": 0.0002,
|
| 1492 |
-
"loss": 0.
|
| 1493 |
"step": 238
|
| 1494 |
},
|
| 1495 |
{
|
| 1496 |
-
"epoch":
|
| 1497 |
"learning_rate": 0.0002,
|
| 1498 |
-
"loss": 0.
|
| 1499 |
"step": 239
|
| 1500 |
},
|
| 1501 |
{
|
| 1502 |
-
"epoch":
|
| 1503 |
"learning_rate": 0.0002,
|
| 1504 |
-
"loss": 0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1505 |
"step": 240
|
| 1506 |
},
|
| 1507 |
{
|
| 1508 |
-
"epoch":
|
| 1509 |
"learning_rate": 0.0002,
|
| 1510 |
-
"loss": 0.
|
| 1511 |
"step": 241
|
| 1512 |
},
|
| 1513 |
{
|
| 1514 |
-
"epoch":
|
| 1515 |
"learning_rate": 0.0002,
|
| 1516 |
-
"loss": 0.
|
| 1517 |
"step": 242
|
| 1518 |
},
|
| 1519 |
{
|
| 1520 |
-
"epoch":
|
| 1521 |
"learning_rate": 0.0002,
|
| 1522 |
-
"loss": 0.
|
| 1523 |
"step": 243
|
| 1524 |
},
|
| 1525 |
{
|
| 1526 |
-
"epoch":
|
| 1527 |
"learning_rate": 0.0002,
|
| 1528 |
-
"loss": 0.
|
| 1529 |
"step": 244
|
| 1530 |
},
|
| 1531 |
{
|
| 1532 |
-
"epoch":
|
| 1533 |
"learning_rate": 0.0002,
|
| 1534 |
-
"loss": 0.
|
| 1535 |
"step": 245
|
| 1536 |
},
|
| 1537 |
{
|
| 1538 |
-
"epoch":
|
| 1539 |
"learning_rate": 0.0002,
|
| 1540 |
-
"loss": 0.
|
| 1541 |
"step": 246
|
| 1542 |
},
|
| 1543 |
{
|
| 1544 |
-
"epoch":
|
| 1545 |
"learning_rate": 0.0002,
|
| 1546 |
-
"loss": 0.
|
| 1547 |
"step": 247
|
| 1548 |
},
|
| 1549 |
{
|
| 1550 |
-
"epoch":
|
| 1551 |
"learning_rate": 0.0002,
|
| 1552 |
-
"loss": 0.
|
| 1553 |
-
"step": 248
|
| 1554 |
-
},
|
| 1555 |
-
{
|
| 1556 |
-
"epoch": 8.0,
|
| 1557 |
-
"eval_loss": 0.0019320615101605654,
|
| 1558 |
-
"eval_runtime": 79.4036,
|
| 1559 |
-
"eval_samples_per_second": 12.229,
|
| 1560 |
-
"eval_steps_per_second": 0.39,
|
| 1561 |
"step": 248
|
| 1562 |
},
|
| 1563 |
{
|
| 1564 |
-
"epoch":
|
| 1565 |
"learning_rate": 0.0002,
|
| 1566 |
-
"loss": 0.
|
| 1567 |
"step": 249
|
| 1568 |
},
|
| 1569 |
{
|
| 1570 |
-
"epoch":
|
| 1571 |
"learning_rate": 0.0002,
|
| 1572 |
-
"loss": 0.
|
| 1573 |
"step": 250
|
| 1574 |
},
|
| 1575 |
{
|
| 1576 |
-
"epoch":
|
| 1577 |
"learning_rate": 0.0002,
|
| 1578 |
-
"loss": 0.
|
| 1579 |
"step": 251
|
| 1580 |
},
|
| 1581 |
{
|
| 1582 |
-
"epoch": 8
|
| 1583 |
"learning_rate": 0.0002,
|
| 1584 |
-
"loss": 0.
|
| 1585 |
"step": 252
|
| 1586 |
},
|
| 1587 |
{
|
| 1588 |
-
"epoch":
|
| 1589 |
"learning_rate": 0.0002,
|
| 1590 |
-
"loss": 0.
|
| 1591 |
"step": 253
|
| 1592 |
},
|
| 1593 |
{
|
| 1594 |
-
"epoch":
|
| 1595 |
"learning_rate": 0.0002,
|
| 1596 |
-
"loss": 0.
|
| 1597 |
"step": 254
|
| 1598 |
},
|
| 1599 |
{
|
| 1600 |
-
"epoch":
|
| 1601 |
"learning_rate": 0.0002,
|
| 1602 |
-
"loss": 0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1603 |
"step": 255
|
| 1604 |
},
|
| 1605 |
{
|
| 1606 |
-
"epoch":
|
| 1607 |
"learning_rate": 0.0002,
|
| 1608 |
-
"loss": 0.
|
| 1609 |
"step": 256
|
| 1610 |
},
|
| 1611 |
{
|
| 1612 |
-
"epoch":
|
| 1613 |
"learning_rate": 0.0002,
|
| 1614 |
-
"loss": 0.
|
| 1615 |
"step": 257
|
| 1616 |
},
|
| 1617 |
{
|
| 1618 |
-
"epoch":
|
| 1619 |
"learning_rate": 0.0002,
|
| 1620 |
-
"loss": 0.
|
| 1621 |
"step": 258
|
| 1622 |
},
|
| 1623 |
{
|
| 1624 |
-
"epoch":
|
| 1625 |
"learning_rate": 0.0002,
|
| 1626 |
-
"loss": 0.
|
| 1627 |
"step": 259
|
| 1628 |
},
|
| 1629 |
{
|
| 1630 |
-
"epoch":
|
| 1631 |
"learning_rate": 0.0002,
|
| 1632 |
-
"loss": 0.
|
| 1633 |
"step": 260
|
| 1634 |
},
|
| 1635 |
{
|
| 1636 |
-
"epoch":
|
| 1637 |
"learning_rate": 0.0002,
|
| 1638 |
-
"loss": 0.
|
| 1639 |
"step": 261
|
| 1640 |
},
|
| 1641 |
{
|
| 1642 |
-
"epoch":
|
| 1643 |
"learning_rate": 0.0002,
|
| 1644 |
-
"loss": 0.
|
| 1645 |
"step": 262
|
| 1646 |
},
|
| 1647 |
{
|
| 1648 |
-
"epoch":
|
| 1649 |
"learning_rate": 0.0002,
|
| 1650 |
-
"loss": 0.
|
| 1651 |
"step": 263
|
| 1652 |
},
|
| 1653 |
{
|
| 1654 |
-
"epoch":
|
| 1655 |
"learning_rate": 0.0002,
|
| 1656 |
-
"loss": 0.
|
| 1657 |
"step": 264
|
| 1658 |
},
|
| 1659 |
{
|
| 1660 |
-
"epoch":
|
| 1661 |
"learning_rate": 0.0002,
|
| 1662 |
-
"loss": 0.
|
| 1663 |
"step": 265
|
| 1664 |
},
|
| 1665 |
{
|
| 1666 |
-
"epoch":
|
| 1667 |
"learning_rate": 0.0002,
|
| 1668 |
-
"loss": 0.
|
| 1669 |
"step": 266
|
| 1670 |
},
|
| 1671 |
{
|
| 1672 |
-
"epoch": 8
|
| 1673 |
"learning_rate": 0.0002,
|
| 1674 |
-
"loss": 0.
|
| 1675 |
"step": 267
|
| 1676 |
},
|
| 1677 |
{
|
| 1678 |
-
"epoch":
|
| 1679 |
"learning_rate": 0.0002,
|
| 1680 |
-
"loss": 0.
|
| 1681 |
"step": 268
|
| 1682 |
},
|
| 1683 |
{
|
| 1684 |
-
"epoch":
|
| 1685 |
"learning_rate": 0.0002,
|
| 1686 |
-
"loss": 0.
|
| 1687 |
"step": 269
|
| 1688 |
},
|
| 1689 |
{
|
| 1690 |
-
"epoch":
|
| 1691 |
"learning_rate": 0.0002,
|
| 1692 |
-
"loss": 0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1693 |
"step": 270
|
| 1694 |
},
|
| 1695 |
{
|
| 1696 |
-
"epoch":
|
| 1697 |
"learning_rate": 0.0002,
|
| 1698 |
-
"loss": 0.
|
| 1699 |
"step": 271
|
| 1700 |
},
|
| 1701 |
{
|
| 1702 |
-
"epoch":
|
| 1703 |
"learning_rate": 0.0002,
|
| 1704 |
-
"loss": 0.
|
| 1705 |
"step": 272
|
| 1706 |
},
|
| 1707 |
{
|
| 1708 |
-
"epoch":
|
| 1709 |
"learning_rate": 0.0002,
|
| 1710 |
-
"loss": 0.
|
| 1711 |
"step": 273
|
| 1712 |
},
|
| 1713 |
{
|
| 1714 |
-
"epoch":
|
| 1715 |
"learning_rate": 0.0002,
|
| 1716 |
-
"loss": 0.
|
| 1717 |
"step": 274
|
| 1718 |
},
|
| 1719 |
{
|
| 1720 |
-
"epoch":
|
| 1721 |
"learning_rate": 0.0002,
|
| 1722 |
-
"loss": 0.
|
| 1723 |
"step": 275
|
| 1724 |
},
|
| 1725 |
{
|
| 1726 |
-
"epoch":
|
| 1727 |
"learning_rate": 0.0002,
|
| 1728 |
-
"loss": 0.
|
| 1729 |
"step": 276
|
| 1730 |
},
|
| 1731 |
{
|
| 1732 |
-
"epoch":
|
| 1733 |
"learning_rate": 0.0002,
|
| 1734 |
-
"loss": 0.
|
| 1735 |
"step": 277
|
| 1736 |
},
|
| 1737 |
{
|
| 1738 |
-
"epoch":
|
| 1739 |
"learning_rate": 0.0002,
|
| 1740 |
-
"loss": 0.
|
| 1741 |
"step": 278
|
| 1742 |
},
|
| 1743 |
{
|
| 1744 |
-
"epoch":
|
| 1745 |
"learning_rate": 0.0002,
|
| 1746 |
-
"loss": 0.
|
| 1747 |
"step": 279
|
| 1748 |
},
|
| 1749 |
{
|
| 1750 |
-
"epoch":
|
| 1751 |
-
"
|
| 1752 |
-
"
|
| 1753 |
-
"
|
| 1754 |
-
"eval_steps_per_second": 0.391,
|
| 1755 |
-
"step": 279
|
| 1756 |
},
|
| 1757 |
{
|
| 1758 |
-
"epoch":
|
| 1759 |
"learning_rate": 0.0002,
|
| 1760 |
-
"loss": 0.
|
| 1761 |
-
"step": 280
|
| 1762 |
-
},
|
| 1763 |
-
{
|
| 1764 |
-
"epoch": 9.06,
|
| 1765 |
-
"learning_rate": 0.0002,
|
| 1766 |
-
"loss": 0.0024,
|
| 1767 |
"step": 281
|
| 1768 |
},
|
| 1769 |
{
|
| 1770 |
-
"epoch":
|
| 1771 |
"learning_rate": 0.0002,
|
| 1772 |
-
"loss": 0.
|
| 1773 |
"step": 282
|
| 1774 |
},
|
| 1775 |
{
|
| 1776 |
-
"epoch":
|
| 1777 |
"learning_rate": 0.0002,
|
| 1778 |
-
"loss": 0.
|
| 1779 |
"step": 283
|
| 1780 |
},
|
| 1781 |
{
|
| 1782 |
-
"epoch":
|
| 1783 |
"learning_rate": 0.0002,
|
| 1784 |
-
"loss": 0.
|
| 1785 |
"step": 284
|
| 1786 |
},
|
| 1787 |
{
|
| 1788 |
-
"epoch":
|
| 1789 |
"learning_rate": 0.0002,
|
| 1790 |
-
"loss": 0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1791 |
"step": 285
|
| 1792 |
},
|
| 1793 |
{
|
| 1794 |
-
"epoch":
|
| 1795 |
"learning_rate": 0.0002,
|
| 1796 |
-
"loss": 0.
|
| 1797 |
"step": 286
|
| 1798 |
},
|
| 1799 |
{
|
| 1800 |
-
"epoch":
|
| 1801 |
"learning_rate": 0.0002,
|
| 1802 |
-
"loss": 0.
|
| 1803 |
"step": 287
|
| 1804 |
},
|
| 1805 |
{
|
| 1806 |
-
"epoch":
|
| 1807 |
"learning_rate": 0.0002,
|
| 1808 |
-
"loss": 0.
|
| 1809 |
"step": 288
|
| 1810 |
},
|
| 1811 |
{
|
| 1812 |
-
"epoch":
|
| 1813 |
"learning_rate": 0.0002,
|
| 1814 |
-
"loss": 0.
|
| 1815 |
"step": 289
|
| 1816 |
},
|
| 1817 |
{
|
| 1818 |
-
"epoch":
|
| 1819 |
"learning_rate": 0.0002,
|
| 1820 |
-
"loss": 0.
|
| 1821 |
"step": 290
|
| 1822 |
},
|
| 1823 |
{
|
| 1824 |
-
"epoch":
|
| 1825 |
"learning_rate": 0.0002,
|
| 1826 |
-
"loss": 0.
|
| 1827 |
"step": 291
|
| 1828 |
},
|
| 1829 |
{
|
| 1830 |
-
"epoch":
|
| 1831 |
"learning_rate": 0.0002,
|
| 1832 |
-
"loss": 0.
|
| 1833 |
"step": 292
|
| 1834 |
},
|
| 1835 |
{
|
| 1836 |
-
"epoch":
|
| 1837 |
"learning_rate": 0.0002,
|
| 1838 |
-
"loss": 0.
|
| 1839 |
"step": 293
|
| 1840 |
},
|
| 1841 |
{
|
| 1842 |
-
"epoch":
|
| 1843 |
"learning_rate": 0.0002,
|
| 1844 |
-
"loss": 0.
|
| 1845 |
"step": 294
|
| 1846 |
},
|
| 1847 |
{
|
| 1848 |
-
"epoch":
|
| 1849 |
"learning_rate": 0.0002,
|
| 1850 |
-
"loss": 0.
|
| 1851 |
"step": 295
|
| 1852 |
},
|
| 1853 |
{
|
| 1854 |
-
"epoch":
|
| 1855 |
"learning_rate": 0.0002,
|
| 1856 |
-
"loss": 0.
|
| 1857 |
"step": 296
|
| 1858 |
},
|
| 1859 |
{
|
| 1860 |
-
"epoch":
|
| 1861 |
"learning_rate": 0.0002,
|
| 1862 |
-
"loss": 0.
|
| 1863 |
"step": 297
|
| 1864 |
},
|
| 1865 |
{
|
| 1866 |
-
"epoch":
|
| 1867 |
"learning_rate": 0.0002,
|
| 1868 |
-
"loss": 0.
|
| 1869 |
"step": 298
|
| 1870 |
},
|
| 1871 |
{
|
| 1872 |
-
"epoch":
|
| 1873 |
"learning_rate": 0.0002,
|
| 1874 |
-
"loss": 0.
|
| 1875 |
"step": 299
|
| 1876 |
},
|
| 1877 |
{
|
| 1878 |
-
"epoch":
|
| 1879 |
-
"learning_rate": 0.0002,
|
| 1880 |
-
"loss": 0.0035,
|
| 1881 |
-
"step": 300
|
| 1882 |
-
},
|
| 1883 |
-
{
|
| 1884 |
-
"epoch": 9.71,
|
| 1885 |
-
"learning_rate": 0.0002,
|
| 1886 |
-
"loss": 0.0027,
|
| 1887 |
-
"step": 301
|
| 1888 |
-
},
|
| 1889 |
-
{
|
| 1890 |
-
"epoch": 9.74,
|
| 1891 |
-
"learning_rate": 0.0002,
|
| 1892 |
-
"loss": 0.0021,
|
| 1893 |
-
"step": 302
|
| 1894 |
-
},
|
| 1895 |
-
{
|
| 1896 |
-
"epoch": 9.77,
|
| 1897 |
-
"learning_rate": 0.0002,
|
| 1898 |
-
"loss": 0.0057,
|
| 1899 |
-
"step": 303
|
| 1900 |
-
},
|
| 1901 |
-
{
|
| 1902 |
-
"epoch": 9.81,
|
| 1903 |
-
"learning_rate": 0.0002,
|
| 1904 |
-
"loss": 0.0015,
|
| 1905 |
-
"step": 304
|
| 1906 |
-
},
|
| 1907 |
-
{
|
| 1908 |
-
"epoch": 9.84,
|
| 1909 |
-
"learning_rate": 0.0002,
|
| 1910 |
-
"loss": 0.0031,
|
| 1911 |
-
"step": 305
|
| 1912 |
-
},
|
| 1913 |
-
{
|
| 1914 |
-
"epoch": 9.87,
|
| 1915 |
-
"learning_rate": 0.0002,
|
| 1916 |
-
"loss": 0.0015,
|
| 1917 |
-
"step": 306
|
| 1918 |
-
},
|
| 1919 |
-
{
|
| 1920 |
-
"epoch": 9.9,
|
| 1921 |
-
"learning_rate": 0.0002,
|
| 1922 |
-
"loss": 0.0029,
|
| 1923 |
-
"step": 307
|
| 1924 |
-
},
|
| 1925 |
-
{
|
| 1926 |
-
"epoch": 9.94,
|
| 1927 |
-
"learning_rate": 0.0002,
|
| 1928 |
-
"loss": 0.0068,
|
| 1929 |
-
"step": 308
|
| 1930 |
-
},
|
| 1931 |
-
{
|
| 1932 |
-
"epoch": 9.97,
|
| 1933 |
-
"learning_rate": 0.0002,
|
| 1934 |
-
"loss": 0.0021,
|
| 1935 |
-
"step": 309
|
| 1936 |
-
},
|
| 1937 |
-
{
|
| 1938 |
-
"epoch": 10.0,
|
| 1939 |
-
"learning_rate": 0.0002,
|
| 1940 |
-
"loss": 0.0021,
|
| 1941 |
-
"step": 310
|
| 1942 |
-
},
|
| 1943 |
-
{
|
| 1944 |
-
"epoch": 10.0,
|
| 1945 |
-
"eval_loss": 0.0029947422444820404,
|
| 1946 |
-
"eval_runtime": 79.3749,
|
| 1947 |
-
"eval_samples_per_second": 12.233,
|
| 1948 |
-
"eval_steps_per_second": 0.391,
|
| 1949 |
-
"step": 310
|
| 1950 |
-
},
|
| 1951 |
-
{
|
| 1952 |
-
"epoch": 10.03,
|
| 1953 |
-
"learning_rate": 0.0002,
|
| 1954 |
-
"loss": 0.0037,
|
| 1955 |
-
"step": 311
|
| 1956 |
-
},
|
| 1957 |
-
{
|
| 1958 |
-
"epoch": 10.06,
|
| 1959 |
"learning_rate": 0.0002,
|
| 1960 |
"loss": 0.0018,
|
| 1961 |
-
"step":
|
| 1962 |
-
},
|
| 1963 |
-
{
|
| 1964 |
-
"epoch": 10.1,
|
| 1965 |
-
"learning_rate": 0.0002,
|
| 1966 |
-
"loss": 0.0041,
|
| 1967 |
-
"step": 313
|
| 1968 |
-
},
|
| 1969 |
-
{
|
| 1970 |
-
"epoch": 10.13,
|
| 1971 |
-
"learning_rate": 0.0002,
|
| 1972 |
-
"loss": 0.0009,
|
| 1973 |
-
"step": 314
|
| 1974 |
-
},
|
| 1975 |
-
{
|
| 1976 |
-
"epoch": 10.16,
|
| 1977 |
-
"learning_rate": 0.0002,
|
| 1978 |
-
"loss": 0.002,
|
| 1979 |
-
"step": 315
|
| 1980 |
-
},
|
| 1981 |
-
{
|
| 1982 |
-
"epoch": 10.19,
|
| 1983 |
-
"learning_rate": 0.0002,
|
| 1984 |
-
"loss": 0.0037,
|
| 1985 |
-
"step": 316
|
| 1986 |
-
},
|
| 1987 |
-
{
|
| 1988 |
-
"epoch": 10.23,
|
| 1989 |
-
"learning_rate": 0.0002,
|
| 1990 |
-
"loss": 0.0041,
|
| 1991 |
-
"step": 317
|
| 1992 |
-
},
|
| 1993 |
-
{
|
| 1994 |
-
"epoch": 10.26,
|
| 1995 |
-
"learning_rate": 0.0002,
|
| 1996 |
-
"loss": 0.0026,
|
| 1997 |
-
"step": 318
|
| 1998 |
-
},
|
| 1999 |
-
{
|
| 2000 |
-
"epoch": 10.29,
|
| 2001 |
-
"learning_rate": 0.0002,
|
| 2002 |
-
"loss": 0.0017,
|
| 2003 |
-
"step": 319
|
| 2004 |
-
},
|
| 2005 |
-
{
|
| 2006 |
-
"epoch": 10.32,
|
| 2007 |
-
"learning_rate": 0.0002,
|
| 2008 |
-
"loss": 0.0027,
|
| 2009 |
-
"step": 320
|
| 2010 |
-
},
|
| 2011 |
-
{
|
| 2012 |
-
"epoch": 10.35,
|
| 2013 |
-
"learning_rate": 0.0002,
|
| 2014 |
-
"loss": 0.002,
|
| 2015 |
-
"step": 321
|
| 2016 |
-
},
|
| 2017 |
-
{
|
| 2018 |
-
"epoch": 10.39,
|
| 2019 |
-
"learning_rate": 0.0002,
|
| 2020 |
-
"loss": 0.0012,
|
| 2021 |
-
"step": 322
|
| 2022 |
-
},
|
| 2023 |
-
{
|
| 2024 |
-
"epoch": 10.42,
|
| 2025 |
-
"learning_rate": 0.0002,
|
| 2026 |
-
"loss": 0.0036,
|
| 2027 |
-
"step": 323
|
| 2028 |
-
},
|
| 2029 |
-
{
|
| 2030 |
-
"epoch": 10.45,
|
| 2031 |
-
"learning_rate": 0.0002,
|
| 2032 |
-
"loss": 0.0036,
|
| 2033 |
-
"step": 324
|
| 2034 |
-
},
|
| 2035 |
-
{
|
| 2036 |
-
"epoch": 10.48,
|
| 2037 |
-
"learning_rate": 0.0002,
|
| 2038 |
-
"loss": 0.008,
|
| 2039 |
-
"step": 325
|
| 2040 |
-
},
|
| 2041 |
-
{
|
| 2042 |
-
"epoch": 10.52,
|
| 2043 |
-
"learning_rate": 0.0002,
|
| 2044 |
-
"loss": 0.0077,
|
| 2045 |
-
"step": 326
|
| 2046 |
-
},
|
| 2047 |
-
{
|
| 2048 |
-
"epoch": 10.55,
|
| 2049 |
-
"learning_rate": 0.0002,
|
| 2050 |
-
"loss": 0.0082,
|
| 2051 |
-
"step": 327
|
| 2052 |
-
},
|
| 2053 |
-
{
|
| 2054 |
-
"epoch": 10.58,
|
| 2055 |
-
"learning_rate": 0.0002,
|
| 2056 |
-
"loss": 0.0047,
|
| 2057 |
-
"step": 328
|
| 2058 |
-
},
|
| 2059 |
-
{
|
| 2060 |
-
"epoch": 10.61,
|
| 2061 |
-
"learning_rate": 0.0002,
|
| 2062 |
-
"loss": 0.0042,
|
| 2063 |
-
"step": 329
|
| 2064 |
-
},
|
| 2065 |
-
{
|
| 2066 |
-
"epoch": 10.65,
|
| 2067 |
-
"learning_rate": 0.0002,
|
| 2068 |
-
"loss": 0.0036,
|
| 2069 |
-
"step": 330
|
| 2070 |
-
},
|
| 2071 |
-
{
|
| 2072 |
-
"epoch": 10.68,
|
| 2073 |
-
"learning_rate": 0.0002,
|
| 2074 |
-
"loss": 0.0121,
|
| 2075 |
-
"step": 331
|
| 2076 |
-
},
|
| 2077 |
-
{
|
| 2078 |
-
"epoch": 10.71,
|
| 2079 |
-
"learning_rate": 0.0002,
|
| 2080 |
-
"loss": 0.0105,
|
| 2081 |
-
"step": 332
|
| 2082 |
-
},
|
| 2083 |
-
{
|
| 2084 |
-
"epoch": 10.74,
|
| 2085 |
-
"learning_rate": 0.0002,
|
| 2086 |
-
"loss": 0.0047,
|
| 2087 |
-
"step": 333
|
| 2088 |
-
},
|
| 2089 |
-
{
|
| 2090 |
-
"epoch": 10.77,
|
| 2091 |
-
"learning_rate": 0.0002,
|
| 2092 |
-
"loss": 0.0036,
|
| 2093 |
-
"step": 334
|
| 2094 |
-
},
|
| 2095 |
-
{
|
| 2096 |
-
"epoch": 10.81,
|
| 2097 |
-
"learning_rate": 0.0002,
|
| 2098 |
-
"loss": 0.0058,
|
| 2099 |
-
"step": 335
|
| 2100 |
-
},
|
| 2101 |
-
{
|
| 2102 |
-
"epoch": 10.84,
|
| 2103 |
-
"learning_rate": 0.0002,
|
| 2104 |
-
"loss": 0.0051,
|
| 2105 |
-
"step": 336
|
| 2106 |
-
},
|
| 2107 |
-
{
|
| 2108 |
-
"epoch": 10.87,
|
| 2109 |
-
"learning_rate": 0.0002,
|
| 2110 |
-
"loss": 0.0072,
|
| 2111 |
-
"step": 337
|
| 2112 |
-
},
|
| 2113 |
-
{
|
| 2114 |
-
"epoch": 10.9,
|
| 2115 |
-
"learning_rate": 0.0002,
|
| 2116 |
-
"loss": 0.0078,
|
| 2117 |
-
"step": 338
|
| 2118 |
-
},
|
| 2119 |
-
{
|
| 2120 |
-
"epoch": 10.94,
|
| 2121 |
-
"learning_rate": 0.0002,
|
| 2122 |
-
"loss": 0.0102,
|
| 2123 |
-
"step": 339
|
| 2124 |
-
},
|
| 2125 |
-
{
|
| 2126 |
-
"epoch": 10.97,
|
| 2127 |
-
"learning_rate": 0.0002,
|
| 2128 |
-
"loss": 0.0069,
|
| 2129 |
-
"step": 340
|
| 2130 |
-
},
|
| 2131 |
-
{
|
| 2132 |
-
"epoch": 11.0,
|
| 2133 |
-
"learning_rate": 0.0002,
|
| 2134 |
-
"loss": 0.0074,
|
| 2135 |
-
"step": 341
|
| 2136 |
-
},
|
| 2137 |
-
{
|
| 2138 |
-
"epoch": 11.0,
|
| 2139 |
-
"eval_loss": 0.0036581410095095634,
|
| 2140 |
-
"eval_runtime": 79.3104,
|
| 2141 |
-
"eval_samples_per_second": 12.243,
|
| 2142 |
-
"eval_steps_per_second": 0.391,
|
| 2143 |
-
"step": 341
|
| 2144 |
-
},
|
| 2145 |
-
{
|
| 2146 |
-
"epoch": 11.03,
|
| 2147 |
-
"learning_rate": 0.0002,
|
| 2148 |
-
"loss": 0.0009,
|
| 2149 |
-
"step": 342
|
| 2150 |
-
},
|
| 2151 |
-
{
|
| 2152 |
-
"epoch": 11.06,
|
| 2153 |
-
"learning_rate": 0.0002,
|
| 2154 |
-
"loss": 0.0028,
|
| 2155 |
-
"step": 343
|
| 2156 |
-
},
|
| 2157 |
-
{
|
| 2158 |
-
"epoch": 11.1,
|
| 2159 |
-
"learning_rate": 0.0002,
|
| 2160 |
-
"loss": 0.0062,
|
| 2161 |
-
"step": 344
|
| 2162 |
-
},
|
| 2163 |
-
{
|
| 2164 |
-
"epoch": 11.13,
|
| 2165 |
-
"learning_rate": 0.0002,
|
| 2166 |
-
"loss": 0.0053,
|
| 2167 |
-
"step": 345
|
| 2168 |
-
},
|
| 2169 |
-
{
|
| 2170 |
-
"epoch": 11.16,
|
| 2171 |
-
"learning_rate": 0.0002,
|
| 2172 |
-
"loss": 0.0045,
|
| 2173 |
-
"step": 346
|
| 2174 |
-
},
|
| 2175 |
-
{
|
| 2176 |
-
"epoch": 11.19,
|
| 2177 |
-
"learning_rate": 0.0002,
|
| 2178 |
-
"loss": 0.0091,
|
| 2179 |
-
"step": 347
|
| 2180 |
-
},
|
| 2181 |
-
{
|
| 2182 |
-
"epoch": 11.23,
|
| 2183 |
-
"learning_rate": 0.0002,
|
| 2184 |
-
"loss": 0.0104,
|
| 2185 |
-
"step": 348
|
| 2186 |
-
},
|
| 2187 |
-
{
|
| 2188 |
-
"epoch": 11.26,
|
| 2189 |
-
"learning_rate": 0.0002,
|
| 2190 |
-
"loss": 0.0038,
|
| 2191 |
-
"step": 349
|
| 2192 |
-
},
|
| 2193 |
-
{
|
| 2194 |
-
"epoch": 11.29,
|
| 2195 |
-
"learning_rate": 0.0002,
|
| 2196 |
-
"loss": 0.0075,
|
| 2197 |
-
"step": 350
|
| 2198 |
-
},
|
| 2199 |
-
{
|
| 2200 |
-
"epoch": 11.32,
|
| 2201 |
-
"learning_rate": 0.0002,
|
| 2202 |
-
"loss": 0.0062,
|
| 2203 |
-
"step": 351
|
| 2204 |
-
},
|
| 2205 |
-
{
|
| 2206 |
-
"epoch": 11.35,
|
| 2207 |
-
"learning_rate": 0.0002,
|
| 2208 |
-
"loss": 0.0078,
|
| 2209 |
-
"step": 352
|
| 2210 |
-
},
|
| 2211 |
-
{
|
| 2212 |
-
"epoch": 11.39,
|
| 2213 |
-
"learning_rate": 0.0002,
|
| 2214 |
-
"loss": 0.0032,
|
| 2215 |
-
"step": 353
|
| 2216 |
-
},
|
| 2217 |
-
{
|
| 2218 |
-
"epoch": 11.42,
|
| 2219 |
-
"learning_rate": 0.0002,
|
| 2220 |
-
"loss": 0.0121,
|
| 2221 |
-
"step": 354
|
| 2222 |
-
},
|
| 2223 |
-
{
|
| 2224 |
-
"epoch": 11.45,
|
| 2225 |
-
"learning_rate": 0.0002,
|
| 2226 |
-
"loss": 0.0084,
|
| 2227 |
-
"step": 355
|
| 2228 |
-
},
|
| 2229 |
-
{
|
| 2230 |
-
"epoch": 11.48,
|
| 2231 |
-
"learning_rate": 0.0002,
|
| 2232 |
-
"loss": 0.005,
|
| 2233 |
-
"step": 356
|
| 2234 |
-
},
|
| 2235 |
-
{
|
| 2236 |
-
"epoch": 11.52,
|
| 2237 |
-
"learning_rate": 0.0002,
|
| 2238 |
-
"loss": 0.0064,
|
| 2239 |
-
"step": 357
|
| 2240 |
-
},
|
| 2241 |
-
{
|
| 2242 |
-
"epoch": 11.55,
|
| 2243 |
-
"learning_rate": 0.0002,
|
| 2244 |
-
"loss": 0.0023,
|
| 2245 |
-
"step": 358
|
| 2246 |
-
},
|
| 2247 |
-
{
|
| 2248 |
-
"epoch": 11.58,
|
| 2249 |
-
"learning_rate": 0.0002,
|
| 2250 |
-
"loss": 0.0062,
|
| 2251 |
-
"step": 359
|
| 2252 |
-
},
|
| 2253 |
-
{
|
| 2254 |
-
"epoch": 11.61,
|
| 2255 |
-
"learning_rate": 0.0002,
|
| 2256 |
-
"loss": 0.002,
|
| 2257 |
-
"step": 360
|
| 2258 |
-
},
|
| 2259 |
-
{
|
| 2260 |
-
"epoch": 11.65,
|
| 2261 |
-
"learning_rate": 0.0002,
|
| 2262 |
-
"loss": 0.0043,
|
| 2263 |
-
"step": 361
|
| 2264 |
-
},
|
| 2265 |
-
{
|
| 2266 |
-
"epoch": 11.68,
|
| 2267 |
-
"learning_rate": 0.0002,
|
| 2268 |
-
"loss": 0.005,
|
| 2269 |
-
"step": 362
|
| 2270 |
-
},
|
| 2271 |
-
{
|
| 2272 |
-
"epoch": 11.71,
|
| 2273 |
-
"learning_rate": 0.0002,
|
| 2274 |
-
"loss": 0.006,
|
| 2275 |
-
"step": 363
|
| 2276 |
-
},
|
| 2277 |
-
{
|
| 2278 |
-
"epoch": 11.74,
|
| 2279 |
-
"learning_rate": 0.0002,
|
| 2280 |
-
"loss": 0.0025,
|
| 2281 |
-
"step": 364
|
| 2282 |
-
},
|
| 2283 |
-
{
|
| 2284 |
-
"epoch": 11.77,
|
| 2285 |
-
"learning_rate": 0.0002,
|
| 2286 |
-
"loss": 0.0057,
|
| 2287 |
-
"step": 365
|
| 2288 |
-
},
|
| 2289 |
-
{
|
| 2290 |
-
"epoch": 11.81,
|
| 2291 |
-
"learning_rate": 0.0002,
|
| 2292 |
-
"loss": 0.0081,
|
| 2293 |
-
"step": 366
|
| 2294 |
-
},
|
| 2295 |
-
{
|
| 2296 |
-
"epoch": 11.84,
|
| 2297 |
-
"learning_rate": 0.0002,
|
| 2298 |
-
"loss": 0.0067,
|
| 2299 |
-
"step": 367
|
| 2300 |
-
},
|
| 2301 |
-
{
|
| 2302 |
-
"epoch": 11.87,
|
| 2303 |
-
"learning_rate": 0.0002,
|
| 2304 |
-
"loss": 0.0046,
|
| 2305 |
-
"step": 368
|
| 2306 |
-
},
|
| 2307 |
-
{
|
| 2308 |
-
"epoch": 11.9,
|
| 2309 |
-
"learning_rate": 0.0002,
|
| 2310 |
-
"loss": 0.0017,
|
| 2311 |
-
"step": 369
|
| 2312 |
-
},
|
| 2313 |
-
{
|
| 2314 |
-
"epoch": 11.94,
|
| 2315 |
-
"learning_rate": 0.0002,
|
| 2316 |
-
"loss": 0.004,
|
| 2317 |
-
"step": 370
|
| 2318 |
-
},
|
| 2319 |
-
{
|
| 2320 |
-
"epoch": 11.97,
|
| 2321 |
-
"learning_rate": 0.0002,
|
| 2322 |
-
"loss": 0.0059,
|
| 2323 |
-
"step": 371
|
| 2324 |
-
},
|
| 2325 |
-
{
|
| 2326 |
-
"epoch": 12.0,
|
| 2327 |
-
"learning_rate": 0.0002,
|
| 2328 |
-
"loss": 0.0029,
|
| 2329 |
-
"step": 372
|
| 2330 |
-
},
|
| 2331 |
-
{
|
| 2332 |
-
"epoch": 12.0,
|
| 2333 |
-
"eval_loss": 0.003008361207321286,
|
| 2334 |
-
"eval_runtime": 79.3511,
|
| 2335 |
-
"eval_samples_per_second": 12.237,
|
| 2336 |
-
"eval_steps_per_second": 0.391,
|
| 2337 |
-
"step": 372
|
| 2338 |
-
},
|
| 2339 |
-
{
|
| 2340 |
-
"epoch": 12.03,
|
| 2341 |
-
"learning_rate": 0.0002,
|
| 2342 |
-
"loss": 0.0031,
|
| 2343 |
-
"step": 373
|
| 2344 |
-
},
|
| 2345 |
-
{
|
| 2346 |
-
"epoch": 12.06,
|
| 2347 |
-
"learning_rate": 0.0002,
|
| 2348 |
-
"loss": 0.0052,
|
| 2349 |
-
"step": 374
|
| 2350 |
-
},
|
| 2351 |
-
{
|
| 2352 |
-
"epoch": 12.1,
|
| 2353 |
-
"learning_rate": 0.0002,
|
| 2354 |
-
"loss": 0.0014,
|
| 2355 |
-
"step": 375
|
| 2356 |
-
},
|
| 2357 |
-
{
|
| 2358 |
-
"epoch": 12.13,
|
| 2359 |
-
"learning_rate": 0.0002,
|
| 2360 |
-
"loss": 0.0048,
|
| 2361 |
-
"step": 376
|
| 2362 |
-
},
|
| 2363 |
-
{
|
| 2364 |
-
"epoch": 12.16,
|
| 2365 |
-
"learning_rate": 0.0002,
|
| 2366 |
-
"loss": 0.0061,
|
| 2367 |
-
"step": 377
|
| 2368 |
-
},
|
| 2369 |
-
{
|
| 2370 |
-
"epoch": 12.19,
|
| 2371 |
-
"learning_rate": 0.0002,
|
| 2372 |
-
"loss": 0.0047,
|
| 2373 |
-
"step": 378
|
| 2374 |
-
},
|
| 2375 |
-
{
|
| 2376 |
-
"epoch": 12.23,
|
| 2377 |
-
"learning_rate": 0.0002,
|
| 2378 |
-
"loss": 0.0068,
|
| 2379 |
-
"step": 379
|
| 2380 |
-
},
|
| 2381 |
-
{
|
| 2382 |
-
"epoch": 12.26,
|
| 2383 |
-
"learning_rate": 0.0002,
|
| 2384 |
-
"loss": 0.0027,
|
| 2385 |
-
"step": 380
|
| 2386 |
-
},
|
| 2387 |
-
{
|
| 2388 |
-
"epoch": 12.29,
|
| 2389 |
-
"learning_rate": 0.0002,
|
| 2390 |
-
"loss": 0.0071,
|
| 2391 |
-
"step": 381
|
| 2392 |
-
},
|
| 2393 |
-
{
|
| 2394 |
-
"epoch": 12.32,
|
| 2395 |
-
"learning_rate": 0.0002,
|
| 2396 |
-
"loss": 0.0062,
|
| 2397 |
-
"step": 382
|
| 2398 |
-
},
|
| 2399 |
-
{
|
| 2400 |
-
"epoch": 12.35,
|
| 2401 |
-
"learning_rate": 0.0002,
|
| 2402 |
-
"loss": 0.0043,
|
| 2403 |
-
"step": 383
|
| 2404 |
-
},
|
| 2405 |
-
{
|
| 2406 |
-
"epoch": 12.39,
|
| 2407 |
-
"learning_rate": 0.0002,
|
| 2408 |
-
"loss": 0.0061,
|
| 2409 |
-
"step": 384
|
| 2410 |
-
},
|
| 2411 |
-
{
|
| 2412 |
-
"epoch": 12.42,
|
| 2413 |
-
"learning_rate": 0.0002,
|
| 2414 |
-
"loss": 0.0024,
|
| 2415 |
-
"step": 385
|
| 2416 |
-
},
|
| 2417 |
-
{
|
| 2418 |
-
"epoch": 12.45,
|
| 2419 |
-
"learning_rate": 0.0002,
|
| 2420 |
-
"loss": 0.0038,
|
| 2421 |
-
"step": 386
|
| 2422 |
-
},
|
| 2423 |
-
{
|
| 2424 |
-
"epoch": 12.48,
|
| 2425 |
-
"learning_rate": 0.0002,
|
| 2426 |
-
"loss": 0.0033,
|
| 2427 |
-
"step": 387
|
| 2428 |
-
},
|
| 2429 |
-
{
|
| 2430 |
-
"epoch": 12.52,
|
| 2431 |
-
"learning_rate": 0.0002,
|
| 2432 |
-
"loss": 0.0071,
|
| 2433 |
-
"step": 388
|
| 2434 |
-
},
|
| 2435 |
-
{
|
| 2436 |
-
"epoch": 12.55,
|
| 2437 |
-
"learning_rate": 0.0002,
|
| 2438 |
-
"loss": 0.0046,
|
| 2439 |
-
"step": 389
|
| 2440 |
-
},
|
| 2441 |
-
{
|
| 2442 |
-
"epoch": 12.58,
|
| 2443 |
-
"learning_rate": 0.0002,
|
| 2444 |
-
"loss": 0.0041,
|
| 2445 |
-
"step": 390
|
| 2446 |
-
},
|
| 2447 |
-
{
|
| 2448 |
-
"epoch": 12.61,
|
| 2449 |
-
"learning_rate": 0.0002,
|
| 2450 |
-
"loss": 0.0033,
|
| 2451 |
-
"step": 391
|
| 2452 |
-
},
|
| 2453 |
-
{
|
| 2454 |
-
"epoch": 12.65,
|
| 2455 |
-
"learning_rate": 0.0002,
|
| 2456 |
-
"loss": 0.0055,
|
| 2457 |
-
"step": 392
|
| 2458 |
-
},
|
| 2459 |
-
{
|
| 2460 |
-
"epoch": 12.68,
|
| 2461 |
-
"learning_rate": 0.0002,
|
| 2462 |
-
"loss": 0.0046,
|
| 2463 |
-
"step": 393
|
| 2464 |
-
},
|
| 2465 |
-
{
|
| 2466 |
-
"epoch": 12.71,
|
| 2467 |
-
"learning_rate": 0.0002,
|
| 2468 |
-
"loss": 0.0051,
|
| 2469 |
-
"step": 394
|
| 2470 |
-
},
|
| 2471 |
-
{
|
| 2472 |
-
"epoch": 12.74,
|
| 2473 |
-
"learning_rate": 0.0002,
|
| 2474 |
-
"loss": 0.0024,
|
| 2475 |
-
"step": 395
|
| 2476 |
-
},
|
| 2477 |
-
{
|
| 2478 |
-
"epoch": 12.77,
|
| 2479 |
-
"learning_rate": 0.0002,
|
| 2480 |
-
"loss": 0.0062,
|
| 2481 |
-
"step": 396
|
| 2482 |
-
},
|
| 2483 |
-
{
|
| 2484 |
-
"epoch": 12.81,
|
| 2485 |
-
"learning_rate": 0.0002,
|
| 2486 |
-
"loss": 0.0032,
|
| 2487 |
-
"step": 397
|
| 2488 |
-
},
|
| 2489 |
-
{
|
| 2490 |
-
"epoch": 12.84,
|
| 2491 |
-
"learning_rate": 0.0002,
|
| 2492 |
-
"loss": 0.0046,
|
| 2493 |
-
"step": 398
|
| 2494 |
-
},
|
| 2495 |
-
{
|
| 2496 |
-
"epoch": 12.87,
|
| 2497 |
-
"learning_rate": 0.0002,
|
| 2498 |
-
"loss": 0.0025,
|
| 2499 |
-
"step": 399
|
| 2500 |
-
},
|
| 2501 |
-
{
|
| 2502 |
-
"epoch": 12.9,
|
| 2503 |
-
"learning_rate": 0.0002,
|
| 2504 |
-
"loss": 0.0051,
|
| 2505 |
-
"step": 400
|
| 2506 |
-
},
|
| 2507 |
-
{
|
| 2508 |
-
"epoch": 12.94,
|
| 2509 |
-
"learning_rate": 0.0002,
|
| 2510 |
-
"loss": 0.005,
|
| 2511 |
-
"step": 401
|
| 2512 |
-
},
|
| 2513 |
-
{
|
| 2514 |
-
"epoch": 12.97,
|
| 2515 |
-
"learning_rate": 0.0002,
|
| 2516 |
-
"loss": 0.0021,
|
| 2517 |
-
"step": 402
|
| 2518 |
-
},
|
| 2519 |
-
{
|
| 2520 |
-
"epoch": 13.0,
|
| 2521 |
-
"learning_rate": 0.0002,
|
| 2522 |
-
"loss": 0.0025,
|
| 2523 |
-
"step": 403
|
| 2524 |
-
},
|
| 2525 |
-
{
|
| 2526 |
-
"epoch": 13.0,
|
| 2527 |
-
"eval_loss": 0.004574234131723642,
|
| 2528 |
-
"eval_runtime": 79.3371,
|
| 2529 |
-
"eval_samples_per_second": 12.239,
|
| 2530 |
-
"eval_steps_per_second": 0.391,
|
| 2531 |
-
"step": 403
|
| 2532 |
-
},
|
| 2533 |
-
{
|
| 2534 |
-
"epoch": 13.03,
|
| 2535 |
-
"learning_rate": 0.0002,
|
| 2536 |
-
"loss": 0.0023,
|
| 2537 |
-
"step": 404
|
| 2538 |
-
},
|
| 2539 |
-
{
|
| 2540 |
-
"epoch": 13.06,
|
| 2541 |
-
"learning_rate": 0.0002,
|
| 2542 |
-
"loss": 0.0038,
|
| 2543 |
-
"step": 405
|
| 2544 |
-
},
|
| 2545 |
-
{
|
| 2546 |
-
"epoch": 13.1,
|
| 2547 |
-
"learning_rate": 0.0002,
|
| 2548 |
-
"loss": 0.0045,
|
| 2549 |
-
"step": 406
|
| 2550 |
-
},
|
| 2551 |
-
{
|
| 2552 |
-
"epoch": 13.13,
|
| 2553 |
-
"learning_rate": 0.0002,
|
| 2554 |
-
"loss": 0.0034,
|
| 2555 |
-
"step": 407
|
| 2556 |
-
},
|
| 2557 |
-
{
|
| 2558 |
-
"epoch": 13.16,
|
| 2559 |
-
"learning_rate": 0.0002,
|
| 2560 |
-
"loss": 0.0134,
|
| 2561 |
-
"step": 408
|
| 2562 |
-
},
|
| 2563 |
-
{
|
| 2564 |
-
"epoch": 13.19,
|
| 2565 |
-
"learning_rate": 0.0002,
|
| 2566 |
-
"loss": 0.0054,
|
| 2567 |
-
"step": 409
|
| 2568 |
-
},
|
| 2569 |
-
{
|
| 2570 |
-
"epoch": 13.23,
|
| 2571 |
-
"learning_rate": 0.0002,
|
| 2572 |
-
"loss": 0.0042,
|
| 2573 |
-
"step": 410
|
| 2574 |
-
},
|
| 2575 |
-
{
|
| 2576 |
-
"epoch": 13.26,
|
| 2577 |
-
"learning_rate": 0.0002,
|
| 2578 |
-
"loss": 0.0097,
|
| 2579 |
-
"step": 411
|
| 2580 |
-
},
|
| 2581 |
-
{
|
| 2582 |
-
"epoch": 13.29,
|
| 2583 |
-
"learning_rate": 0.0002,
|
| 2584 |
-
"loss": 0.0063,
|
| 2585 |
-
"step": 412
|
| 2586 |
-
},
|
| 2587 |
-
{
|
| 2588 |
-
"epoch": 13.32,
|
| 2589 |
-
"learning_rate": 0.0002,
|
| 2590 |
-
"loss": 0.0034,
|
| 2591 |
-
"step": 413
|
| 2592 |
-
},
|
| 2593 |
-
{
|
| 2594 |
-
"epoch": 13.35,
|
| 2595 |
-
"learning_rate": 0.0002,
|
| 2596 |
-
"loss": 0.0027,
|
| 2597 |
-
"step": 414
|
| 2598 |
-
},
|
| 2599 |
-
{
|
| 2600 |
-
"epoch": 13.39,
|
| 2601 |
-
"learning_rate": 0.0002,
|
| 2602 |
-
"loss": 0.0032,
|
| 2603 |
-
"step": 415
|
| 2604 |
-
},
|
| 2605 |
-
{
|
| 2606 |
-
"epoch": 13.42,
|
| 2607 |
-
"learning_rate": 0.0002,
|
| 2608 |
-
"loss": 0.0035,
|
| 2609 |
-
"step": 416
|
| 2610 |
-
},
|
| 2611 |
-
{
|
| 2612 |
-
"epoch": 13.45,
|
| 2613 |
-
"learning_rate": 0.0002,
|
| 2614 |
-
"loss": 0.0029,
|
| 2615 |
-
"step": 417
|
| 2616 |
-
},
|
| 2617 |
-
{
|
| 2618 |
-
"epoch": 13.48,
|
| 2619 |
-
"learning_rate": 0.0002,
|
| 2620 |
-
"loss": 0.0061,
|
| 2621 |
-
"step": 418
|
| 2622 |
-
},
|
| 2623 |
-
{
|
| 2624 |
-
"epoch": 13.52,
|
| 2625 |
-
"learning_rate": 0.0002,
|
| 2626 |
-
"loss": 0.0055,
|
| 2627 |
-
"step": 419
|
| 2628 |
-
},
|
| 2629 |
-
{
|
| 2630 |
-
"epoch": 13.55,
|
| 2631 |
-
"learning_rate": 0.0002,
|
| 2632 |
-
"loss": 0.0094,
|
| 2633 |
-
"step": 420
|
| 2634 |
-
},
|
| 2635 |
-
{
|
| 2636 |
-
"epoch": 13.58,
|
| 2637 |
-
"learning_rate": 0.0002,
|
| 2638 |
-
"loss": 0.0029,
|
| 2639 |
-
"step": 421
|
| 2640 |
-
},
|
| 2641 |
-
{
|
| 2642 |
-
"epoch": 13.61,
|
| 2643 |
-
"learning_rate": 0.0002,
|
| 2644 |
-
"loss": 0.0058,
|
| 2645 |
-
"step": 422
|
| 2646 |
-
},
|
| 2647 |
-
{
|
| 2648 |
-
"epoch": 13.65,
|
| 2649 |
-
"learning_rate": 0.0002,
|
| 2650 |
-
"loss": 0.0098,
|
| 2651 |
-
"step": 423
|
| 2652 |
-
},
|
| 2653 |
-
{
|
| 2654 |
-
"epoch": 13.68,
|
| 2655 |
-
"learning_rate": 0.0002,
|
| 2656 |
-
"loss": 0.0044,
|
| 2657 |
-
"step": 424
|
| 2658 |
-
},
|
| 2659 |
-
{
|
| 2660 |
-
"epoch": 13.71,
|
| 2661 |
-
"learning_rate": 0.0002,
|
| 2662 |
-
"loss": 0.005,
|
| 2663 |
-
"step": 425
|
| 2664 |
-
},
|
| 2665 |
-
{
|
| 2666 |
-
"epoch": 13.74,
|
| 2667 |
-
"learning_rate": 0.0002,
|
| 2668 |
-
"loss": 0.0061,
|
| 2669 |
-
"step": 426
|
| 2670 |
-
},
|
| 2671 |
-
{
|
| 2672 |
-
"epoch": 13.77,
|
| 2673 |
-
"learning_rate": 0.0002,
|
| 2674 |
-
"loss": 0.0047,
|
| 2675 |
-
"step": 427
|
| 2676 |
-
},
|
| 2677 |
-
{
|
| 2678 |
-
"epoch": 13.81,
|
| 2679 |
-
"learning_rate": 0.0002,
|
| 2680 |
-
"loss": 0.0044,
|
| 2681 |
-
"step": 428
|
| 2682 |
-
},
|
| 2683 |
-
{
|
| 2684 |
-
"epoch": 13.84,
|
| 2685 |
-
"learning_rate": 0.0002,
|
| 2686 |
-
"loss": 0.0051,
|
| 2687 |
-
"step": 429
|
| 2688 |
-
},
|
| 2689 |
-
{
|
| 2690 |
-
"epoch": 13.87,
|
| 2691 |
-
"learning_rate": 0.0002,
|
| 2692 |
-
"loss": 0.0051,
|
| 2693 |
-
"step": 430
|
| 2694 |
-
},
|
| 2695 |
-
{
|
| 2696 |
-
"epoch": 13.9,
|
| 2697 |
-
"learning_rate": 0.0002,
|
| 2698 |
-
"loss": 0.0064,
|
| 2699 |
-
"step": 431
|
| 2700 |
-
},
|
| 2701 |
-
{
|
| 2702 |
-
"epoch": 13.94,
|
| 2703 |
-
"learning_rate": 0.0002,
|
| 2704 |
-
"loss": 0.0028,
|
| 2705 |
-
"step": 432
|
| 2706 |
-
},
|
| 2707 |
-
{
|
| 2708 |
-
"epoch": 13.97,
|
| 2709 |
-
"learning_rate": 0.0002,
|
| 2710 |
-
"loss": 0.0045,
|
| 2711 |
-
"step": 433
|
| 2712 |
-
},
|
| 2713 |
-
{
|
| 2714 |
-
"epoch": 14.0,
|
| 2715 |
-
"learning_rate": 0.0002,
|
| 2716 |
-
"loss": 0.0106,
|
| 2717 |
-
"step": 434
|
| 2718 |
-
},
|
| 2719 |
-
{
|
| 2720 |
-
"epoch": 14.0,
|
| 2721 |
-
"eval_loss": 0.0039254180155694485,
|
| 2722 |
-
"eval_runtime": 79.3661,
|
| 2723 |
-
"eval_samples_per_second": 12.234,
|
| 2724 |
-
"eval_steps_per_second": 0.391,
|
| 2725 |
-
"step": 434
|
| 2726 |
-
},
|
| 2727 |
-
{
|
| 2728 |
-
"epoch": 14.03,
|
| 2729 |
-
"learning_rate": 0.0002,
|
| 2730 |
-
"loss": 0.0043,
|
| 2731 |
-
"step": 435
|
| 2732 |
-
},
|
| 2733 |
-
{
|
| 2734 |
-
"epoch": 14.06,
|
| 2735 |
-
"learning_rate": 0.0002,
|
| 2736 |
-
"loss": 0.0104,
|
| 2737 |
-
"step": 436
|
| 2738 |
-
},
|
| 2739 |
-
{
|
| 2740 |
-
"epoch": 14.1,
|
| 2741 |
-
"learning_rate": 0.0002,
|
| 2742 |
-
"loss": 0.0047,
|
| 2743 |
-
"step": 437
|
| 2744 |
-
},
|
| 2745 |
-
{
|
| 2746 |
-
"epoch": 14.13,
|
| 2747 |
-
"learning_rate": 0.0002,
|
| 2748 |
-
"loss": 0.0036,
|
| 2749 |
-
"step": 438
|
| 2750 |
-
},
|
| 2751 |
-
{
|
| 2752 |
-
"epoch": 14.16,
|
| 2753 |
-
"learning_rate": 0.0002,
|
| 2754 |
-
"loss": 0.0054,
|
| 2755 |
-
"step": 439
|
| 2756 |
-
},
|
| 2757 |
-
{
|
| 2758 |
-
"epoch": 14.19,
|
| 2759 |
-
"learning_rate": 0.0002,
|
| 2760 |
-
"loss": 0.0024,
|
| 2761 |
-
"step": 440
|
| 2762 |
-
},
|
| 2763 |
-
{
|
| 2764 |
-
"epoch": 14.23,
|
| 2765 |
-
"learning_rate": 0.0002,
|
| 2766 |
-
"loss": 0.0052,
|
| 2767 |
-
"step": 441
|
| 2768 |
-
},
|
| 2769 |
-
{
|
| 2770 |
-
"epoch": 14.26,
|
| 2771 |
-
"learning_rate": 0.0002,
|
| 2772 |
-
"loss": 0.0025,
|
| 2773 |
-
"step": 442
|
| 2774 |
-
},
|
| 2775 |
-
{
|
| 2776 |
-
"epoch": 14.29,
|
| 2777 |
-
"learning_rate": 0.0002,
|
| 2778 |
-
"loss": 0.0046,
|
| 2779 |
-
"step": 443
|
| 2780 |
-
},
|
| 2781 |
-
{
|
| 2782 |
-
"epoch": 14.32,
|
| 2783 |
-
"learning_rate": 0.0002,
|
| 2784 |
-
"loss": 0.0097,
|
| 2785 |
-
"step": 444
|
| 2786 |
-
},
|
| 2787 |
-
{
|
| 2788 |
-
"epoch": 14.35,
|
| 2789 |
-
"learning_rate": 0.0002,
|
| 2790 |
-
"loss": 0.0034,
|
| 2791 |
-
"step": 445
|
| 2792 |
-
},
|
| 2793 |
-
{
|
| 2794 |
-
"epoch": 14.39,
|
| 2795 |
-
"learning_rate": 0.0002,
|
| 2796 |
-
"loss": 0.009,
|
| 2797 |
-
"step": 446
|
| 2798 |
-
},
|
| 2799 |
-
{
|
| 2800 |
-
"epoch": 14.42,
|
| 2801 |
-
"learning_rate": 0.0002,
|
| 2802 |
-
"loss": 0.0055,
|
| 2803 |
-
"step": 447
|
| 2804 |
-
},
|
| 2805 |
-
{
|
| 2806 |
-
"epoch": 14.45,
|
| 2807 |
-
"learning_rate": 0.0002,
|
| 2808 |
-
"loss": 0.0078,
|
| 2809 |
-
"step": 448
|
| 2810 |
-
},
|
| 2811 |
-
{
|
| 2812 |
-
"epoch": 14.48,
|
| 2813 |
-
"learning_rate": 0.0002,
|
| 2814 |
-
"loss": 0.0034,
|
| 2815 |
-
"step": 449
|
| 2816 |
-
},
|
| 2817 |
-
{
|
| 2818 |
-
"epoch": 14.52,
|
| 2819 |
-
"learning_rate": 0.0002,
|
| 2820 |
-
"loss": 0.005,
|
| 2821 |
-
"step": 450
|
| 2822 |
-
},
|
| 2823 |
-
{
|
| 2824 |
-
"epoch": 14.55,
|
| 2825 |
-
"learning_rate": 0.0002,
|
| 2826 |
-
"loss": 0.0033,
|
| 2827 |
-
"step": 451
|
| 2828 |
-
},
|
| 2829 |
-
{
|
| 2830 |
-
"epoch": 14.58,
|
| 2831 |
-
"learning_rate": 0.0002,
|
| 2832 |
-
"loss": 0.0013,
|
| 2833 |
-
"step": 452
|
| 2834 |
-
},
|
| 2835 |
-
{
|
| 2836 |
-
"epoch": 14.61,
|
| 2837 |
-
"learning_rate": 0.0002,
|
| 2838 |
-
"loss": 0.0086,
|
| 2839 |
-
"step": 453
|
| 2840 |
-
},
|
| 2841 |
-
{
|
| 2842 |
-
"epoch": 14.65,
|
| 2843 |
-
"learning_rate": 0.0002,
|
| 2844 |
-
"loss": 0.0046,
|
| 2845 |
-
"step": 454
|
| 2846 |
-
},
|
| 2847 |
-
{
|
| 2848 |
-
"epoch": 14.68,
|
| 2849 |
-
"learning_rate": 0.0002,
|
| 2850 |
-
"loss": 0.0037,
|
| 2851 |
-
"step": 455
|
| 2852 |
-
},
|
| 2853 |
-
{
|
| 2854 |
-
"epoch": 14.71,
|
| 2855 |
-
"learning_rate": 0.0002,
|
| 2856 |
-
"loss": 0.0021,
|
| 2857 |
-
"step": 456
|
| 2858 |
-
},
|
| 2859 |
-
{
|
| 2860 |
-
"epoch": 14.74,
|
| 2861 |
-
"learning_rate": 0.0002,
|
| 2862 |
-
"loss": 0.0059,
|
| 2863 |
-
"step": 457
|
| 2864 |
-
},
|
| 2865 |
-
{
|
| 2866 |
-
"epoch": 14.77,
|
| 2867 |
-
"learning_rate": 0.0002,
|
| 2868 |
-
"loss": 0.0075,
|
| 2869 |
-
"step": 458
|
| 2870 |
-
},
|
| 2871 |
-
{
|
| 2872 |
-
"epoch": 14.81,
|
| 2873 |
-
"learning_rate": 0.0002,
|
| 2874 |
-
"loss": 0.004,
|
| 2875 |
-
"step": 459
|
| 2876 |
-
},
|
| 2877 |
-
{
|
| 2878 |
-
"epoch": 14.84,
|
| 2879 |
-
"learning_rate": 0.0002,
|
| 2880 |
-
"loss": 0.0068,
|
| 2881 |
-
"step": 460
|
| 2882 |
-
},
|
| 2883 |
-
{
|
| 2884 |
-
"epoch": 14.87,
|
| 2885 |
-
"learning_rate": 0.0002,
|
| 2886 |
-
"loss": 0.0068,
|
| 2887 |
-
"step": 461
|
| 2888 |
-
},
|
| 2889 |
-
{
|
| 2890 |
-
"epoch": 14.9,
|
| 2891 |
-
"learning_rate": 0.0002,
|
| 2892 |
-
"loss": 0.0058,
|
| 2893 |
-
"step": 462
|
| 2894 |
-
},
|
| 2895 |
-
{
|
| 2896 |
-
"epoch": 14.94,
|
| 2897 |
-
"learning_rate": 0.0002,
|
| 2898 |
-
"loss": 0.0031,
|
| 2899 |
-
"step": 463
|
| 2900 |
-
},
|
| 2901 |
-
{
|
| 2902 |
-
"epoch": 14.97,
|
| 2903 |
-
"learning_rate": 0.0002,
|
| 2904 |
-
"loss": 0.0061,
|
| 2905 |
-
"step": 464
|
| 2906 |
-
},
|
| 2907 |
-
{
|
| 2908 |
-
"epoch": 15.0,
|
| 2909 |
-
"learning_rate": 0.0002,
|
| 2910 |
-
"loss": 0.0029,
|
| 2911 |
-
"step": 465
|
| 2912 |
-
},
|
| 2913 |
-
{
|
| 2914 |
-
"epoch": 15.0,
|
| 2915 |
-
"eval_loss": 0.005505946930497885,
|
| 2916 |
-
"eval_runtime": 79.3727,
|
| 2917 |
-
"eval_samples_per_second": 12.233,
|
| 2918 |
-
"eval_steps_per_second": 0.391,
|
| 2919 |
-
"step": 465
|
| 2920 |
-
},
|
| 2921 |
-
{
|
| 2922 |
-
"epoch": 15.03,
|
| 2923 |
-
"learning_rate": 0.0002,
|
| 2924 |
-
"loss": 0.0074,
|
| 2925 |
-
"step": 466
|
| 2926 |
-
},
|
| 2927 |
-
{
|
| 2928 |
-
"epoch": 15.06,
|
| 2929 |
-
"learning_rate": 0.0002,
|
| 2930 |
-
"loss": 0.0069,
|
| 2931 |
-
"step": 467
|
| 2932 |
-
},
|
| 2933 |
-
{
|
| 2934 |
-
"epoch": 15.1,
|
| 2935 |
-
"learning_rate": 0.0002,
|
| 2936 |
-
"loss": 0.0067,
|
| 2937 |
-
"step": 468
|
| 2938 |
-
},
|
| 2939 |
-
{
|
| 2940 |
-
"epoch": 15.13,
|
| 2941 |
-
"learning_rate": 0.0002,
|
| 2942 |
-
"loss": 0.0055,
|
| 2943 |
-
"step": 469
|
| 2944 |
-
},
|
| 2945 |
-
{
|
| 2946 |
-
"epoch": 15.16,
|
| 2947 |
-
"learning_rate": 0.0002,
|
| 2948 |
-
"loss": 0.0108,
|
| 2949 |
-
"step": 470
|
| 2950 |
-
},
|
| 2951 |
-
{
|
| 2952 |
-
"epoch": 15.19,
|
| 2953 |
-
"learning_rate": 0.0002,
|
| 2954 |
-
"loss": 0.0061,
|
| 2955 |
-
"step": 471
|
| 2956 |
-
},
|
| 2957 |
-
{
|
| 2958 |
-
"epoch": 15.23,
|
| 2959 |
-
"learning_rate": 0.0002,
|
| 2960 |
-
"loss": 0.0041,
|
| 2961 |
-
"step": 472
|
| 2962 |
-
},
|
| 2963 |
-
{
|
| 2964 |
-
"epoch": 15.26,
|
| 2965 |
-
"learning_rate": 0.0002,
|
| 2966 |
-
"loss": 0.0062,
|
| 2967 |
-
"step": 473
|
| 2968 |
-
},
|
| 2969 |
-
{
|
| 2970 |
-
"epoch": 15.29,
|
| 2971 |
-
"learning_rate": 0.0002,
|
| 2972 |
-
"loss": 0.0032,
|
| 2973 |
-
"step": 474
|
| 2974 |
-
},
|
| 2975 |
-
{
|
| 2976 |
-
"epoch": 15.32,
|
| 2977 |
-
"learning_rate": 0.0002,
|
| 2978 |
-
"loss": 0.0022,
|
| 2979 |
-
"step": 475
|
| 2980 |
-
},
|
| 2981 |
-
{
|
| 2982 |
-
"epoch": 15.35,
|
| 2983 |
-
"learning_rate": 0.0002,
|
| 2984 |
-
"loss": 0.0083,
|
| 2985 |
-
"step": 476
|
| 2986 |
-
},
|
| 2987 |
-
{
|
| 2988 |
-
"epoch": 15.39,
|
| 2989 |
-
"learning_rate": 0.0002,
|
| 2990 |
-
"loss": 0.0036,
|
| 2991 |
-
"step": 477
|
| 2992 |
-
},
|
| 2993 |
-
{
|
| 2994 |
-
"epoch": 15.42,
|
| 2995 |
-
"learning_rate": 0.0002,
|
| 2996 |
-
"loss": 0.0054,
|
| 2997 |
-
"step": 478
|
| 2998 |
-
},
|
| 2999 |
-
{
|
| 3000 |
-
"epoch": 15.45,
|
| 3001 |
-
"learning_rate": 0.0002,
|
| 3002 |
-
"loss": 0.0089,
|
| 3003 |
-
"step": 479
|
| 3004 |
-
},
|
| 3005 |
-
{
|
| 3006 |
-
"epoch": 15.48,
|
| 3007 |
-
"learning_rate": 0.0002,
|
| 3008 |
-
"loss": 0.0044,
|
| 3009 |
-
"step": 480
|
| 3010 |
-
},
|
| 3011 |
-
{
|
| 3012 |
-
"epoch": 15.52,
|
| 3013 |
-
"learning_rate": 0.0002,
|
| 3014 |
-
"loss": 0.0191,
|
| 3015 |
-
"step": 481
|
| 3016 |
-
},
|
| 3017 |
-
{
|
| 3018 |
-
"epoch": 15.55,
|
| 3019 |
-
"learning_rate": 0.0002,
|
| 3020 |
-
"loss": 0.0055,
|
| 3021 |
-
"step": 482
|
| 3022 |
-
},
|
| 3023 |
-
{
|
| 3024 |
-
"epoch": 15.58,
|
| 3025 |
-
"learning_rate": 0.0002,
|
| 3026 |
-
"loss": 0.008,
|
| 3027 |
-
"step": 483
|
| 3028 |
-
},
|
| 3029 |
-
{
|
| 3030 |
-
"epoch": 15.61,
|
| 3031 |
-
"learning_rate": 0.0002,
|
| 3032 |
-
"loss": 0.0071,
|
| 3033 |
-
"step": 484
|
| 3034 |
-
},
|
| 3035 |
-
{
|
| 3036 |
-
"epoch": 15.65,
|
| 3037 |
-
"learning_rate": 0.0002,
|
| 3038 |
-
"loss": 0.0038,
|
| 3039 |
-
"step": 485
|
| 3040 |
-
},
|
| 3041 |
-
{
|
| 3042 |
-
"epoch": 15.68,
|
| 3043 |
-
"learning_rate": 0.0002,
|
| 3044 |
-
"loss": 0.0083,
|
| 3045 |
-
"step": 486
|
| 3046 |
-
},
|
| 3047 |
-
{
|
| 3048 |
-
"epoch": 15.71,
|
| 3049 |
-
"learning_rate": 0.0002,
|
| 3050 |
-
"loss": 0.005,
|
| 3051 |
-
"step": 487
|
| 3052 |
-
},
|
| 3053 |
-
{
|
| 3054 |
-
"epoch": 15.74,
|
| 3055 |
-
"learning_rate": 0.0002,
|
| 3056 |
-
"loss": 0.0075,
|
| 3057 |
-
"step": 488
|
| 3058 |
-
},
|
| 3059 |
-
{
|
| 3060 |
-
"epoch": 15.77,
|
| 3061 |
-
"learning_rate": 0.0002,
|
| 3062 |
-
"loss": 0.0074,
|
| 3063 |
-
"step": 489
|
| 3064 |
-
},
|
| 3065 |
-
{
|
| 3066 |
-
"epoch": 15.81,
|
| 3067 |
-
"learning_rate": 0.0002,
|
| 3068 |
-
"loss": 0.01,
|
| 3069 |
-
"step": 490
|
| 3070 |
-
},
|
| 3071 |
-
{
|
| 3072 |
-
"epoch": 15.84,
|
| 3073 |
-
"learning_rate": 0.0002,
|
| 3074 |
-
"loss": 0.0073,
|
| 3075 |
-
"step": 491
|
| 3076 |
-
},
|
| 3077 |
-
{
|
| 3078 |
-
"epoch": 15.87,
|
| 3079 |
-
"learning_rate": 0.0002,
|
| 3080 |
-
"loss": 0.0086,
|
| 3081 |
-
"step": 492
|
| 3082 |
-
},
|
| 3083 |
-
{
|
| 3084 |
-
"epoch": 15.9,
|
| 3085 |
-
"learning_rate": 0.0002,
|
| 3086 |
-
"loss": 0.0042,
|
| 3087 |
-
"step": 493
|
| 3088 |
-
},
|
| 3089 |
-
{
|
| 3090 |
-
"epoch": 15.94,
|
| 3091 |
-
"learning_rate": 0.0002,
|
| 3092 |
-
"loss": 0.0078,
|
| 3093 |
-
"step": 494
|
| 3094 |
-
},
|
| 3095 |
-
{
|
| 3096 |
-
"epoch": 15.97,
|
| 3097 |
-
"learning_rate": 0.0002,
|
| 3098 |
-
"loss": 0.0024,
|
| 3099 |
-
"step": 495
|
| 3100 |
-
},
|
| 3101 |
-
{
|
| 3102 |
-
"epoch": 16.0,
|
| 3103 |
-
"learning_rate": 0.0002,
|
| 3104 |
-
"loss": 0.0043,
|
| 3105 |
-
"step": 496
|
| 3106 |
-
},
|
| 3107 |
-
{
|
| 3108 |
-
"epoch": 16.0,
|
| 3109 |
-
"eval_loss": 0.003584536025300622,
|
| 3110 |
-
"eval_runtime": 79.3118,
|
| 3111 |
-
"eval_samples_per_second": 12.243,
|
| 3112 |
-
"eval_steps_per_second": 0.391,
|
| 3113 |
-
"step": 496
|
| 3114 |
-
},
|
| 3115 |
-
{
|
| 3116 |
-
"epoch": 16.03,
|
| 3117 |
-
"learning_rate": 0.0002,
|
| 3118 |
-
"loss": 0.0021,
|
| 3119 |
-
"step": 497
|
| 3120 |
-
},
|
| 3121 |
-
{
|
| 3122 |
-
"epoch": 16.06,
|
| 3123 |
-
"learning_rate": 0.0002,
|
| 3124 |
-
"loss": 0.0028,
|
| 3125 |
-
"step": 498
|
| 3126 |
-
},
|
| 3127 |
-
{
|
| 3128 |
-
"epoch": 16.1,
|
| 3129 |
-
"learning_rate": 0.0002,
|
| 3130 |
-
"loss": 0.0039,
|
| 3131 |
-
"step": 499
|
| 3132 |
-
},
|
| 3133 |
-
{
|
| 3134 |
-
"epoch": 16.13,
|
| 3135 |
-
"learning_rate": 0.0002,
|
| 3136 |
-
"loss": 0.0042,
|
| 3137 |
-
"step": 500
|
| 3138 |
-
},
|
| 3139 |
-
{
|
| 3140 |
-
"epoch": 16.16,
|
| 3141 |
-
"learning_rate": 0.0002,
|
| 3142 |
-
"loss": 0.0054,
|
| 3143 |
-
"step": 501
|
| 3144 |
-
},
|
| 3145 |
-
{
|
| 3146 |
-
"epoch": 16.19,
|
| 3147 |
-
"learning_rate": 0.0002,
|
| 3148 |
-
"loss": 0.004,
|
| 3149 |
-
"step": 502
|
| 3150 |
-
},
|
| 3151 |
-
{
|
| 3152 |
-
"epoch": 16.23,
|
| 3153 |
-
"learning_rate": 0.0002,
|
| 3154 |
-
"loss": 0.0046,
|
| 3155 |
-
"step": 503
|
| 3156 |
-
},
|
| 3157 |
-
{
|
| 3158 |
-
"epoch": 16.26,
|
| 3159 |
-
"learning_rate": 0.0002,
|
| 3160 |
-
"loss": 0.0069,
|
| 3161 |
-
"step": 504
|
| 3162 |
-
},
|
| 3163 |
-
{
|
| 3164 |
-
"epoch": 16.29,
|
| 3165 |
-
"learning_rate": 0.0002,
|
| 3166 |
-
"loss": 0.0054,
|
| 3167 |
-
"step": 505
|
| 3168 |
-
},
|
| 3169 |
-
{
|
| 3170 |
-
"epoch": 16.32,
|
| 3171 |
-
"learning_rate": 0.0002,
|
| 3172 |
-
"loss": 0.0036,
|
| 3173 |
-
"step": 506
|
| 3174 |
-
},
|
| 3175 |
-
{
|
| 3176 |
-
"epoch": 16.35,
|
| 3177 |
-
"learning_rate": 0.0002,
|
| 3178 |
-
"loss": 0.0044,
|
| 3179 |
-
"step": 507
|
| 3180 |
-
},
|
| 3181 |
-
{
|
| 3182 |
-
"epoch": 16.39,
|
| 3183 |
-
"learning_rate": 0.0002,
|
| 3184 |
-
"loss": 0.004,
|
| 3185 |
-
"step": 508
|
| 3186 |
-
},
|
| 3187 |
-
{
|
| 3188 |
-
"epoch": 16.42,
|
| 3189 |
-
"learning_rate": 0.0002,
|
| 3190 |
-
"loss": 0.0028,
|
| 3191 |
-
"step": 509
|
| 3192 |
-
},
|
| 3193 |
-
{
|
| 3194 |
-
"epoch": 16.45,
|
| 3195 |
-
"learning_rate": 0.0002,
|
| 3196 |
-
"loss": 0.0019,
|
| 3197 |
-
"step": 510
|
| 3198 |
-
},
|
| 3199 |
-
{
|
| 3200 |
-
"epoch": 16.48,
|
| 3201 |
-
"learning_rate": 0.0002,
|
| 3202 |
-
"loss": 0.0075,
|
| 3203 |
-
"step": 511
|
| 3204 |
-
},
|
| 3205 |
-
{
|
| 3206 |
-
"epoch": 16.52,
|
| 3207 |
-
"learning_rate": 0.0002,
|
| 3208 |
-
"loss": 0.013,
|
| 3209 |
-
"step": 512
|
| 3210 |
-
},
|
| 3211 |
-
{
|
| 3212 |
-
"epoch": 16.55,
|
| 3213 |
-
"learning_rate": 0.0002,
|
| 3214 |
-
"loss": 0.002,
|
| 3215 |
-
"step": 513
|
| 3216 |
-
},
|
| 3217 |
-
{
|
| 3218 |
-
"epoch": 16.58,
|
| 3219 |
-
"learning_rate": 0.0002,
|
| 3220 |
-
"loss": 0.0067,
|
| 3221 |
-
"step": 514
|
| 3222 |
-
},
|
| 3223 |
-
{
|
| 3224 |
-
"epoch": 16.61,
|
| 3225 |
-
"learning_rate": 0.0002,
|
| 3226 |
-
"loss": 0.0044,
|
| 3227 |
-
"step": 515
|
| 3228 |
-
},
|
| 3229 |
-
{
|
| 3230 |
-
"epoch": 16.65,
|
| 3231 |
-
"learning_rate": 0.0002,
|
| 3232 |
-
"loss": 0.0068,
|
| 3233 |
-
"step": 516
|
| 3234 |
-
},
|
| 3235 |
-
{
|
| 3236 |
-
"epoch": 16.68,
|
| 3237 |
-
"learning_rate": 0.0002,
|
| 3238 |
-
"loss": 0.0068,
|
| 3239 |
-
"step": 517
|
| 3240 |
-
},
|
| 3241 |
-
{
|
| 3242 |
-
"epoch": 16.71,
|
| 3243 |
-
"learning_rate": 0.0002,
|
| 3244 |
-
"loss": 0.0121,
|
| 3245 |
-
"step": 518
|
| 3246 |
-
},
|
| 3247 |
-
{
|
| 3248 |
-
"epoch": 16.74,
|
| 3249 |
-
"learning_rate": 0.0002,
|
| 3250 |
-
"loss": 0.0049,
|
| 3251 |
-
"step": 519
|
| 3252 |
-
},
|
| 3253 |
-
{
|
| 3254 |
-
"epoch": 16.77,
|
| 3255 |
-
"learning_rate": 0.0002,
|
| 3256 |
-
"loss": 0.0074,
|
| 3257 |
-
"step": 520
|
| 3258 |
-
},
|
| 3259 |
-
{
|
| 3260 |
-
"epoch": 16.81,
|
| 3261 |
-
"learning_rate": 0.0002,
|
| 3262 |
-
"loss": 0.0051,
|
| 3263 |
-
"step": 521
|
| 3264 |
-
},
|
| 3265 |
-
{
|
| 3266 |
-
"epoch": 16.84,
|
| 3267 |
-
"learning_rate": 0.0002,
|
| 3268 |
-
"loss": 0.0053,
|
| 3269 |
-
"step": 522
|
| 3270 |
-
},
|
| 3271 |
-
{
|
| 3272 |
-
"epoch": 16.87,
|
| 3273 |
-
"learning_rate": 0.0002,
|
| 3274 |
-
"loss": 0.0056,
|
| 3275 |
-
"step": 523
|
| 3276 |
-
},
|
| 3277 |
-
{
|
| 3278 |
-
"epoch": 16.9,
|
| 3279 |
-
"learning_rate": 0.0002,
|
| 3280 |
-
"loss": 0.0035,
|
| 3281 |
-
"step": 524
|
| 3282 |
-
},
|
| 3283 |
-
{
|
| 3284 |
-
"epoch": 16.94,
|
| 3285 |
-
"learning_rate": 0.0002,
|
| 3286 |
-
"loss": 0.0077,
|
| 3287 |
-
"step": 525
|
| 3288 |
-
},
|
| 3289 |
-
{
|
| 3290 |
-
"epoch": 16.97,
|
| 3291 |
-
"learning_rate": 0.0002,
|
| 3292 |
-
"loss": 0.0057,
|
| 3293 |
-
"step": 526
|
| 3294 |
-
},
|
| 3295 |
-
{
|
| 3296 |
-
"epoch": 17.0,
|
| 3297 |
-
"learning_rate": 0.0002,
|
| 3298 |
-
"loss": 0.0054,
|
| 3299 |
-
"step": 527
|
| 3300 |
-
},
|
| 3301 |
-
{
|
| 3302 |
-
"epoch": 17.0,
|
| 3303 |
-
"eval_loss": 0.003963674884289503,
|
| 3304 |
-
"eval_runtime": 79.4143,
|
| 3305 |
-
"eval_samples_per_second": 12.227,
|
| 3306 |
-
"eval_steps_per_second": 0.39,
|
| 3307 |
-
"step": 527
|
| 3308 |
-
},
|
| 3309 |
-
{
|
| 3310 |
-
"epoch": 17.03,
|
| 3311 |
-
"learning_rate": 0.0002,
|
| 3312 |
-
"loss": 0.0035,
|
| 3313 |
-
"step": 528
|
| 3314 |
-
},
|
| 3315 |
-
{
|
| 3316 |
-
"epoch": 17.06,
|
| 3317 |
-
"learning_rate": 0.0002,
|
| 3318 |
-
"loss": 0.0039,
|
| 3319 |
-
"step": 529
|
| 3320 |
-
},
|
| 3321 |
-
{
|
| 3322 |
-
"epoch": 17.1,
|
| 3323 |
-
"learning_rate": 0.0002,
|
| 3324 |
-
"loss": 0.0018,
|
| 3325 |
-
"step": 530
|
| 3326 |
-
},
|
| 3327 |
-
{
|
| 3328 |
-
"epoch": 17.13,
|
| 3329 |
-
"learning_rate": 0.0002,
|
| 3330 |
-
"loss": 0.0054,
|
| 3331 |
-
"step": 531
|
| 3332 |
-
},
|
| 3333 |
-
{
|
| 3334 |
-
"epoch": 17.16,
|
| 3335 |
-
"learning_rate": 0.0002,
|
| 3336 |
-
"loss": 0.0035,
|
| 3337 |
-
"step": 532
|
| 3338 |
-
},
|
| 3339 |
-
{
|
| 3340 |
-
"epoch": 17.19,
|
| 3341 |
-
"learning_rate": 0.0002,
|
| 3342 |
-
"loss": 0.0049,
|
| 3343 |
-
"step": 533
|
| 3344 |
-
},
|
| 3345 |
-
{
|
| 3346 |
-
"epoch": 17.23,
|
| 3347 |
-
"learning_rate": 0.0002,
|
| 3348 |
-
"loss": 0.0065,
|
| 3349 |
-
"step": 534
|
| 3350 |
-
},
|
| 3351 |
-
{
|
| 3352 |
-
"epoch": 17.26,
|
| 3353 |
-
"learning_rate": 0.0002,
|
| 3354 |
-
"loss": 0.0062,
|
| 3355 |
-
"step": 535
|
| 3356 |
-
},
|
| 3357 |
-
{
|
| 3358 |
-
"epoch": 17.29,
|
| 3359 |
-
"learning_rate": 0.0002,
|
| 3360 |
-
"loss": 0.0093,
|
| 3361 |
-
"step": 536
|
| 3362 |
-
},
|
| 3363 |
-
{
|
| 3364 |
-
"epoch": 17.32,
|
| 3365 |
-
"learning_rate": 0.0002,
|
| 3366 |
-
"loss": 0.0047,
|
| 3367 |
-
"step": 537
|
| 3368 |
-
},
|
| 3369 |
-
{
|
| 3370 |
-
"epoch": 17.35,
|
| 3371 |
-
"learning_rate": 0.0002,
|
| 3372 |
-
"loss": 0.0046,
|
| 3373 |
-
"step": 538
|
| 3374 |
-
},
|
| 3375 |
-
{
|
| 3376 |
-
"epoch": 17.39,
|
| 3377 |
-
"learning_rate": 0.0002,
|
| 3378 |
-
"loss": 0.0041,
|
| 3379 |
-
"step": 539
|
| 3380 |
-
},
|
| 3381 |
-
{
|
| 3382 |
-
"epoch": 17.42,
|
| 3383 |
-
"learning_rate": 0.0002,
|
| 3384 |
-
"loss": 0.005,
|
| 3385 |
-
"step": 540
|
| 3386 |
-
},
|
| 3387 |
-
{
|
| 3388 |
-
"epoch": 17.45,
|
| 3389 |
-
"learning_rate": 0.0002,
|
| 3390 |
-
"loss": 0.0095,
|
| 3391 |
-
"step": 541
|
| 3392 |
-
},
|
| 3393 |
-
{
|
| 3394 |
-
"epoch": 17.48,
|
| 3395 |
-
"learning_rate": 0.0002,
|
| 3396 |
-
"loss": 0.0068,
|
| 3397 |
-
"step": 542
|
| 3398 |
-
},
|
| 3399 |
-
{
|
| 3400 |
-
"epoch": 17.52,
|
| 3401 |
-
"learning_rate": 0.0002,
|
| 3402 |
-
"loss": 0.0084,
|
| 3403 |
-
"step": 543
|
| 3404 |
-
},
|
| 3405 |
-
{
|
| 3406 |
-
"epoch": 17.55,
|
| 3407 |
-
"learning_rate": 0.0002,
|
| 3408 |
-
"loss": 0.0044,
|
| 3409 |
-
"step": 544
|
| 3410 |
-
},
|
| 3411 |
-
{
|
| 3412 |
-
"epoch": 17.58,
|
| 3413 |
-
"learning_rate": 0.0002,
|
| 3414 |
-
"loss": 0.0063,
|
| 3415 |
-
"step": 545
|
| 3416 |
-
},
|
| 3417 |
-
{
|
| 3418 |
-
"epoch": 17.61,
|
| 3419 |
-
"learning_rate": 0.0002,
|
| 3420 |
-
"loss": 0.0083,
|
| 3421 |
-
"step": 546
|
| 3422 |
-
},
|
| 3423 |
-
{
|
| 3424 |
-
"epoch": 17.65,
|
| 3425 |
-
"learning_rate": 0.0002,
|
| 3426 |
-
"loss": 0.0059,
|
| 3427 |
-
"step": 547
|
| 3428 |
-
},
|
| 3429 |
-
{
|
| 3430 |
-
"epoch": 17.68,
|
| 3431 |
-
"learning_rate": 0.0002,
|
| 3432 |
-
"loss": 0.0065,
|
| 3433 |
-
"step": 548
|
| 3434 |
-
},
|
| 3435 |
-
{
|
| 3436 |
-
"epoch": 17.71,
|
| 3437 |
-
"learning_rate": 0.0002,
|
| 3438 |
-
"loss": 0.0071,
|
| 3439 |
-
"step": 549
|
| 3440 |
-
},
|
| 3441 |
-
{
|
| 3442 |
-
"epoch": 17.74,
|
| 3443 |
-
"learning_rate": 0.0002,
|
| 3444 |
-
"loss": 0.0049,
|
| 3445 |
-
"step": 550
|
| 3446 |
-
},
|
| 3447 |
-
{
|
| 3448 |
-
"epoch": 17.77,
|
| 3449 |
-
"learning_rate": 0.0002,
|
| 3450 |
-
"loss": 0.0085,
|
| 3451 |
-
"step": 551
|
| 3452 |
-
},
|
| 3453 |
-
{
|
| 3454 |
-
"epoch": 17.81,
|
| 3455 |
-
"learning_rate": 0.0002,
|
| 3456 |
-
"loss": 0.0106,
|
| 3457 |
-
"step": 552
|
| 3458 |
-
},
|
| 3459 |
-
{
|
| 3460 |
-
"epoch": 17.84,
|
| 3461 |
-
"learning_rate": 0.0002,
|
| 3462 |
-
"loss": 0.0037,
|
| 3463 |
-
"step": 553
|
| 3464 |
-
},
|
| 3465 |
-
{
|
| 3466 |
-
"epoch": 17.87,
|
| 3467 |
-
"learning_rate": 0.0002,
|
| 3468 |
-
"loss": 0.0032,
|
| 3469 |
-
"step": 554
|
| 3470 |
-
},
|
| 3471 |
-
{
|
| 3472 |
-
"epoch": 17.9,
|
| 3473 |
-
"learning_rate": 0.0002,
|
| 3474 |
-
"loss": 0.0027,
|
| 3475 |
-
"step": 555
|
| 3476 |
-
},
|
| 3477 |
-
{
|
| 3478 |
-
"epoch": 17.94,
|
| 3479 |
-
"learning_rate": 0.0002,
|
| 3480 |
-
"loss": 0.0051,
|
| 3481 |
-
"step": 556
|
| 3482 |
-
},
|
| 3483 |
-
{
|
| 3484 |
-
"epoch": 17.97,
|
| 3485 |
-
"learning_rate": 0.0002,
|
| 3486 |
-
"loss": 0.0065,
|
| 3487 |
-
"step": 557
|
| 3488 |
-
},
|
| 3489 |
-
{
|
| 3490 |
-
"epoch": 18.0,
|
| 3491 |
-
"learning_rate": 0.0002,
|
| 3492 |
-
"loss": 0.0091,
|
| 3493 |
-
"step": 558
|
| 3494 |
-
},
|
| 3495 |
-
{
|
| 3496 |
-
"epoch": 18.0,
|
| 3497 |
-
"eval_loss": 0.004831564612686634,
|
| 3498 |
-
"eval_runtime": 79.3778,
|
| 3499 |
-
"eval_samples_per_second": 12.233,
|
| 3500 |
-
"eval_steps_per_second": 0.391,
|
| 3501 |
-
"step": 558
|
| 3502 |
-
},
|
| 3503 |
-
{
|
| 3504 |
-
"epoch": 18.03,
|
| 3505 |
-
"learning_rate": 0.0002,
|
| 3506 |
-
"loss": 0.008,
|
| 3507 |
-
"step": 559
|
| 3508 |
-
},
|
| 3509 |
-
{
|
| 3510 |
-
"epoch": 18.06,
|
| 3511 |
-
"learning_rate": 0.0002,
|
| 3512 |
-
"loss": 0.0053,
|
| 3513 |
-
"step": 560
|
| 3514 |
-
},
|
| 3515 |
-
{
|
| 3516 |
-
"epoch": 18.1,
|
| 3517 |
-
"learning_rate": 0.0002,
|
| 3518 |
-
"loss": 0.0057,
|
| 3519 |
-
"step": 561
|
| 3520 |
-
},
|
| 3521 |
-
{
|
| 3522 |
-
"epoch": 18.13,
|
| 3523 |
-
"learning_rate": 0.0002,
|
| 3524 |
-
"loss": 0.0037,
|
| 3525 |
-
"step": 562
|
| 3526 |
-
},
|
| 3527 |
-
{
|
| 3528 |
-
"epoch": 18.16,
|
| 3529 |
-
"learning_rate": 0.0002,
|
| 3530 |
-
"loss": 0.0077,
|
| 3531 |
-
"step": 563
|
| 3532 |
-
},
|
| 3533 |
-
{
|
| 3534 |
-
"epoch": 18.19,
|
| 3535 |
-
"learning_rate": 0.0002,
|
| 3536 |
-
"loss": 0.0061,
|
| 3537 |
-
"step": 564
|
| 3538 |
-
},
|
| 3539 |
-
{
|
| 3540 |
-
"epoch": 18.23,
|
| 3541 |
-
"learning_rate": 0.0002,
|
| 3542 |
-
"loss": 0.0093,
|
| 3543 |
-
"step": 565
|
| 3544 |
-
},
|
| 3545 |
-
{
|
| 3546 |
-
"epoch": 18.26,
|
| 3547 |
-
"learning_rate": 0.0002,
|
| 3548 |
-
"loss": 0.0051,
|
| 3549 |
-
"step": 566
|
| 3550 |
-
},
|
| 3551 |
-
{
|
| 3552 |
-
"epoch": 18.29,
|
| 3553 |
-
"learning_rate": 0.0002,
|
| 3554 |
-
"loss": 0.004,
|
| 3555 |
-
"step": 567
|
| 3556 |
-
},
|
| 3557 |
-
{
|
| 3558 |
-
"epoch": 18.32,
|
| 3559 |
-
"learning_rate": 0.0002,
|
| 3560 |
-
"loss": 0.0049,
|
| 3561 |
-
"step": 568
|
| 3562 |
-
},
|
| 3563 |
-
{
|
| 3564 |
-
"epoch": 18.35,
|
| 3565 |
-
"learning_rate": 0.0002,
|
| 3566 |
-
"loss": 0.0077,
|
| 3567 |
-
"step": 569
|
| 3568 |
-
},
|
| 3569 |
-
{
|
| 3570 |
-
"epoch": 18.39,
|
| 3571 |
-
"learning_rate": 0.0002,
|
| 3572 |
-
"loss": 0.0032,
|
| 3573 |
-
"step": 570
|
| 3574 |
-
},
|
| 3575 |
-
{
|
| 3576 |
-
"epoch": 18.42,
|
| 3577 |
-
"learning_rate": 0.0002,
|
| 3578 |
-
"loss": 0.0084,
|
| 3579 |
-
"step": 571
|
| 3580 |
-
},
|
| 3581 |
-
{
|
| 3582 |
-
"epoch": 18.45,
|
| 3583 |
-
"learning_rate": 0.0002,
|
| 3584 |
-
"loss": 0.0074,
|
| 3585 |
-
"step": 572
|
| 3586 |
-
},
|
| 3587 |
-
{
|
| 3588 |
-
"epoch": 18.48,
|
| 3589 |
-
"learning_rate": 0.0002,
|
| 3590 |
-
"loss": 0.0059,
|
| 3591 |
-
"step": 573
|
| 3592 |
-
},
|
| 3593 |
-
{
|
| 3594 |
-
"epoch": 18.52,
|
| 3595 |
-
"learning_rate": 0.0002,
|
| 3596 |
-
"loss": 0.0083,
|
| 3597 |
-
"step": 574
|
| 3598 |
-
},
|
| 3599 |
-
{
|
| 3600 |
-
"epoch": 18.55,
|
| 3601 |
-
"learning_rate": 0.0002,
|
| 3602 |
-
"loss": 0.0084,
|
| 3603 |
-
"step": 575
|
| 3604 |
-
},
|
| 3605 |
-
{
|
| 3606 |
-
"epoch": 18.58,
|
| 3607 |
-
"learning_rate": 0.0002,
|
| 3608 |
-
"loss": 0.0041,
|
| 3609 |
-
"step": 576
|
| 3610 |
-
},
|
| 3611 |
-
{
|
| 3612 |
-
"epoch": 18.61,
|
| 3613 |
-
"learning_rate": 0.0002,
|
| 3614 |
-
"loss": 0.0116,
|
| 3615 |
-
"step": 577
|
| 3616 |
-
},
|
| 3617 |
-
{
|
| 3618 |
-
"epoch": 18.65,
|
| 3619 |
-
"learning_rate": 0.0002,
|
| 3620 |
-
"loss": 0.0047,
|
| 3621 |
-
"step": 578
|
| 3622 |
-
},
|
| 3623 |
-
{
|
| 3624 |
-
"epoch": 18.68,
|
| 3625 |
-
"learning_rate": 0.0002,
|
| 3626 |
-
"loss": 0.0069,
|
| 3627 |
-
"step": 579
|
| 3628 |
-
},
|
| 3629 |
-
{
|
| 3630 |
-
"epoch": 18.71,
|
| 3631 |
-
"learning_rate": 0.0002,
|
| 3632 |
-
"loss": 0.0045,
|
| 3633 |
-
"step": 580
|
| 3634 |
-
},
|
| 3635 |
-
{
|
| 3636 |
-
"epoch": 18.74,
|
| 3637 |
-
"learning_rate": 0.0002,
|
| 3638 |
-
"loss": 0.0035,
|
| 3639 |
-
"step": 581
|
| 3640 |
-
},
|
| 3641 |
-
{
|
| 3642 |
-
"epoch": 18.77,
|
| 3643 |
-
"learning_rate": 0.0002,
|
| 3644 |
-
"loss": 0.0061,
|
| 3645 |
-
"step": 582
|
| 3646 |
-
},
|
| 3647 |
-
{
|
| 3648 |
-
"epoch": 18.81,
|
| 3649 |
-
"learning_rate": 0.0002,
|
| 3650 |
-
"loss": 0.0077,
|
| 3651 |
-
"step": 583
|
| 3652 |
-
},
|
| 3653 |
-
{
|
| 3654 |
-
"epoch": 18.84,
|
| 3655 |
-
"learning_rate": 0.0002,
|
| 3656 |
-
"loss": 0.0086,
|
| 3657 |
-
"step": 584
|
| 3658 |
-
},
|
| 3659 |
-
{
|
| 3660 |
-
"epoch": 18.87,
|
| 3661 |
-
"learning_rate": 0.0002,
|
| 3662 |
-
"loss": 0.0036,
|
| 3663 |
-
"step": 585
|
| 3664 |
-
},
|
| 3665 |
-
{
|
| 3666 |
-
"epoch": 18.9,
|
| 3667 |
-
"learning_rate": 0.0002,
|
| 3668 |
-
"loss": 0.0057,
|
| 3669 |
-
"step": 586
|
| 3670 |
-
},
|
| 3671 |
-
{
|
| 3672 |
-
"epoch": 18.94,
|
| 3673 |
-
"learning_rate": 0.0002,
|
| 3674 |
-
"loss": 0.0044,
|
| 3675 |
-
"step": 587
|
| 3676 |
-
},
|
| 3677 |
-
{
|
| 3678 |
-
"epoch": 18.97,
|
| 3679 |
-
"learning_rate": 0.0002,
|
| 3680 |
-
"loss": 0.0057,
|
| 3681 |
-
"step": 588
|
| 3682 |
-
},
|
| 3683 |
-
{
|
| 3684 |
-
"epoch": 19.0,
|
| 3685 |
-
"learning_rate": 0.0002,
|
| 3686 |
-
"loss": 0.0091,
|
| 3687 |
-
"step": 589
|
| 3688 |
-
},
|
| 3689 |
-
{
|
| 3690 |
-
"epoch": 19.0,
|
| 3691 |
-
"eval_loss": 0.005370205733925104,
|
| 3692 |
-
"eval_runtime": 79.4082,
|
| 3693 |
-
"eval_samples_per_second": 12.228,
|
| 3694 |
-
"eval_steps_per_second": 0.39,
|
| 3695 |
-
"step": 589
|
| 3696 |
-
},
|
| 3697 |
-
{
|
| 3698 |
-
"epoch": 19.03,
|
| 3699 |
-
"learning_rate": 0.0002,
|
| 3700 |
-
"loss": 0.0045,
|
| 3701 |
-
"step": 590
|
| 3702 |
-
},
|
| 3703 |
-
{
|
| 3704 |
-
"epoch": 19.06,
|
| 3705 |
-
"learning_rate": 0.0002,
|
| 3706 |
-
"loss": 0.0052,
|
| 3707 |
-
"step": 591
|
| 3708 |
-
},
|
| 3709 |
-
{
|
| 3710 |
-
"epoch": 19.1,
|
| 3711 |
-
"learning_rate": 0.0002,
|
| 3712 |
-
"loss": 0.0042,
|
| 3713 |
-
"step": 592
|
| 3714 |
-
},
|
| 3715 |
-
{
|
| 3716 |
-
"epoch": 19.13,
|
| 3717 |
-
"learning_rate": 0.0002,
|
| 3718 |
-
"loss": 0.0106,
|
| 3719 |
-
"step": 593
|
| 3720 |
-
},
|
| 3721 |
-
{
|
| 3722 |
-
"epoch": 19.16,
|
| 3723 |
-
"learning_rate": 0.0002,
|
| 3724 |
-
"loss": 0.0057,
|
| 3725 |
-
"step": 594
|
| 3726 |
-
},
|
| 3727 |
-
{
|
| 3728 |
-
"epoch": 19.19,
|
| 3729 |
-
"learning_rate": 0.0002,
|
| 3730 |
-
"loss": 0.0036,
|
| 3731 |
-
"step": 595
|
| 3732 |
-
},
|
| 3733 |
-
{
|
| 3734 |
-
"epoch": 19.23,
|
| 3735 |
-
"learning_rate": 0.0002,
|
| 3736 |
-
"loss": 0.0141,
|
| 3737 |
-
"step": 596
|
| 3738 |
-
},
|
| 3739 |
-
{
|
| 3740 |
-
"epoch": 19.26,
|
| 3741 |
-
"learning_rate": 0.0002,
|
| 3742 |
-
"loss": 0.0062,
|
| 3743 |
-
"step": 597
|
| 3744 |
-
},
|
| 3745 |
-
{
|
| 3746 |
-
"epoch": 19.29,
|
| 3747 |
-
"learning_rate": 0.0002,
|
| 3748 |
-
"loss": 0.0029,
|
| 3749 |
-
"step": 598
|
| 3750 |
-
},
|
| 3751 |
-
{
|
| 3752 |
-
"epoch": 19.32,
|
| 3753 |
-
"learning_rate": 0.0002,
|
| 3754 |
-
"loss": 0.0058,
|
| 3755 |
-
"step": 599
|
| 3756 |
-
},
|
| 3757 |
-
{
|
| 3758 |
-
"epoch": 19.35,
|
| 3759 |
-
"learning_rate": 0.0002,
|
| 3760 |
-
"loss": 0.0044,
|
| 3761 |
-
"step": 600
|
| 3762 |
-
},
|
| 3763 |
-
{
|
| 3764 |
-
"epoch": 19.39,
|
| 3765 |
-
"learning_rate": 0.0002,
|
| 3766 |
-
"loss": 0.0054,
|
| 3767 |
-
"step": 601
|
| 3768 |
-
},
|
| 3769 |
-
{
|
| 3770 |
-
"epoch": 19.42,
|
| 3771 |
-
"learning_rate": 0.0002,
|
| 3772 |
-
"loss": 0.0045,
|
| 3773 |
-
"step": 602
|
| 3774 |
-
},
|
| 3775 |
-
{
|
| 3776 |
-
"epoch": 19.45,
|
| 3777 |
-
"learning_rate": 0.0002,
|
| 3778 |
-
"loss": 0.0055,
|
| 3779 |
-
"step": 603
|
| 3780 |
-
},
|
| 3781 |
-
{
|
| 3782 |
-
"epoch": 19.48,
|
| 3783 |
-
"learning_rate": 0.0002,
|
| 3784 |
-
"loss": 0.0045,
|
| 3785 |
-
"step": 604
|
| 3786 |
-
},
|
| 3787 |
-
{
|
| 3788 |
-
"epoch": 19.52,
|
| 3789 |
-
"learning_rate": 0.0002,
|
| 3790 |
-
"loss": 0.0031,
|
| 3791 |
-
"step": 605
|
| 3792 |
-
},
|
| 3793 |
-
{
|
| 3794 |
-
"epoch": 19.55,
|
| 3795 |
-
"learning_rate": 0.0002,
|
| 3796 |
-
"loss": 0.0071,
|
| 3797 |
-
"step": 606
|
| 3798 |
-
},
|
| 3799 |
-
{
|
| 3800 |
-
"epoch": 19.58,
|
| 3801 |
-
"learning_rate": 0.0002,
|
| 3802 |
-
"loss": 0.0061,
|
| 3803 |
-
"step": 607
|
| 3804 |
-
},
|
| 3805 |
-
{
|
| 3806 |
-
"epoch": 19.61,
|
| 3807 |
-
"learning_rate": 0.0002,
|
| 3808 |
-
"loss": 0.004,
|
| 3809 |
-
"step": 608
|
| 3810 |
-
},
|
| 3811 |
-
{
|
| 3812 |
-
"epoch": 19.65,
|
| 3813 |
-
"learning_rate": 0.0002,
|
| 3814 |
-
"loss": 0.0077,
|
| 3815 |
-
"step": 609
|
| 3816 |
-
},
|
| 3817 |
-
{
|
| 3818 |
-
"epoch": 19.68,
|
| 3819 |
-
"learning_rate": 0.0002,
|
| 3820 |
-
"loss": 0.0061,
|
| 3821 |
-
"step": 610
|
| 3822 |
-
},
|
| 3823 |
-
{
|
| 3824 |
-
"epoch": 19.71,
|
| 3825 |
-
"learning_rate": 0.0002,
|
| 3826 |
-
"loss": 0.0045,
|
| 3827 |
-
"step": 611
|
| 3828 |
-
},
|
| 3829 |
-
{
|
| 3830 |
-
"epoch": 19.74,
|
| 3831 |
-
"learning_rate": 0.0002,
|
| 3832 |
-
"loss": 0.0034,
|
| 3833 |
-
"step": 612
|
| 3834 |
-
},
|
| 3835 |
-
{
|
| 3836 |
-
"epoch": 19.77,
|
| 3837 |
-
"learning_rate": 0.0002,
|
| 3838 |
-
"loss": 0.0049,
|
| 3839 |
-
"step": 613
|
| 3840 |
-
},
|
| 3841 |
-
{
|
| 3842 |
-
"epoch": 19.81,
|
| 3843 |
-
"learning_rate": 0.0002,
|
| 3844 |
-
"loss": 0.0048,
|
| 3845 |
-
"step": 614
|
| 3846 |
-
},
|
| 3847 |
-
{
|
| 3848 |
-
"epoch": 19.84,
|
| 3849 |
-
"learning_rate": 0.0002,
|
| 3850 |
-
"loss": 0.0048,
|
| 3851 |
-
"step": 615
|
| 3852 |
-
},
|
| 3853 |
-
{
|
| 3854 |
-
"epoch": 19.87,
|
| 3855 |
-
"learning_rate": 0.0002,
|
| 3856 |
-
"loss": 0.0077,
|
| 3857 |
-
"step": 616
|
| 3858 |
-
},
|
| 3859 |
-
{
|
| 3860 |
-
"epoch": 19.9,
|
| 3861 |
-
"learning_rate": 0.0002,
|
| 3862 |
-
"loss": 0.0051,
|
| 3863 |
-
"step": 617
|
| 3864 |
-
},
|
| 3865 |
-
{
|
| 3866 |
-
"epoch": 19.94,
|
| 3867 |
-
"learning_rate": 0.0002,
|
| 3868 |
-
"loss": 0.0063,
|
| 3869 |
-
"step": 618
|
| 3870 |
-
},
|
| 3871 |
-
{
|
| 3872 |
-
"epoch": 19.97,
|
| 3873 |
-
"learning_rate": 0.0002,
|
| 3874 |
-
"loss": 0.0037,
|
| 3875 |
-
"step": 619
|
| 3876 |
-
},
|
| 3877 |
-
{
|
| 3878 |
-
"epoch": 20.0,
|
| 3879 |
-
"learning_rate": 0.0002,
|
| 3880 |
-
"loss": 0.0028,
|
| 3881 |
-
"step": 620
|
| 3882 |
},
|
| 3883 |
{
|
| 3884 |
"epoch": 20.0,
|
| 3885 |
-
"eval_loss": 0.
|
| 3886 |
-
"eval_runtime":
|
| 3887 |
-
"eval_samples_per_second":
|
| 3888 |
-
"eval_steps_per_second": 0.
|
| 3889 |
-
"step":
|
| 3890 |
},
|
| 3891 |
{
|
| 3892 |
"epoch": 20.0,
|
| 3893 |
-
"step":
|
| 3894 |
-
"total_flos":
|
| 3895 |
-
"train_loss": 0.
|
| 3896 |
-
"train_runtime":
|
| 3897 |
-
"train_samples_per_second": 1.
|
| 3898 |
-
"train_steps_per_second": 0.
|
| 3899 |
}
|
| 3900 |
],
|
| 3901 |
"logging_steps": 1.0,
|
| 3902 |
-
"max_steps":
|
| 3903 |
"num_input_tokens_seen": 0,
|
| 3904 |
"num_train_epochs": 20,
|
| 3905 |
"save_steps": 50000,
|
| 3906 |
-
"total_flos":
|
| 3907 |
"train_batch_size": 4,
|
| 3908 |
"trial_name": null,
|
| 3909 |
"trial_params": null
|
|
|
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
"epoch": 20.0,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 300,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
+
"epoch": 0.07,
|
| 13 |
"learning_rate": 0.0,
|
| 14 |
+
"loss": 1.4796,
|
| 15 |
"step": 1
|
| 16 |
},
|
| 17 |
{
|
| 18 |
+
"epoch": 0.13,
|
| 19 |
+
"learning_rate": 6.309297535714573e-05,
|
| 20 |
+
"loss": 1.2109,
|
| 21 |
"step": 2
|
| 22 |
},
|
| 23 |
{
|
| 24 |
+
"epoch": 0.2,
|
| 25 |
+
"learning_rate": 0.0001,
|
| 26 |
+
"loss": 1.1526,
|
| 27 |
"step": 3
|
| 28 |
},
|
| 29 |
{
|
| 30 |
+
"epoch": 0.27,
|
| 31 |
+
"learning_rate": 0.00012618595071429146,
|
| 32 |
+
"loss": 1.0989,
|
| 33 |
"step": 4
|
| 34 |
},
|
| 35 |
{
|
| 36 |
+
"epoch": 0.33,
|
| 37 |
+
"learning_rate": 0.0001464973520717927,
|
| 38 |
+
"loss": 1.0838,
|
| 39 |
"step": 5
|
| 40 |
},
|
| 41 |
{
|
| 42 |
+
"epoch": 0.4,
|
| 43 |
+
"learning_rate": 0.00016309297535714573,
|
| 44 |
+
"loss": 1.0372,
|
| 45 |
"step": 6
|
| 46 |
},
|
| 47 |
{
|
| 48 |
+
"epoch": 0.47,
|
| 49 |
+
"learning_rate": 0.00017712437491614223,
|
| 50 |
+
"loss": 1.0054,
|
| 51 |
"step": 7
|
| 52 |
},
|
| 53 |
{
|
| 54 |
+
"epoch": 0.53,
|
| 55 |
+
"learning_rate": 0.0001892789260714372,
|
| 56 |
+
"loss": 0.8918,
|
| 57 |
"step": 8
|
| 58 |
},
|
| 59 |
{
|
| 60 |
+
"epoch": 0.6,
|
| 61 |
+
"learning_rate": 0.0002,
|
| 62 |
+
"loss": 0.8802,
|
| 63 |
"step": 9
|
| 64 |
},
|
| 65 |
{
|
| 66 |
+
"epoch": 0.67,
|
| 67 |
+
"learning_rate": 0.0002,
|
| 68 |
+
"loss": 0.8623,
|
| 69 |
"step": 10
|
| 70 |
},
|
| 71 |
{
|
| 72 |
+
"epoch": 0.73,
|
| 73 |
+
"learning_rate": 0.0002,
|
| 74 |
+
"loss": 0.843,
|
| 75 |
"step": 11
|
| 76 |
},
|
| 77 |
{
|
| 78 |
+
"epoch": 0.8,
|
| 79 |
+
"learning_rate": 0.0002,
|
| 80 |
+
"loss": 0.7631,
|
| 81 |
"step": 12
|
| 82 |
},
|
| 83 |
{
|
| 84 |
+
"epoch": 0.87,
|
| 85 |
+
"learning_rate": 0.0002,
|
| 86 |
+
"loss": 0.7026,
|
| 87 |
"step": 13
|
| 88 |
},
|
| 89 |
{
|
| 90 |
+
"epoch": 0.93,
|
| 91 |
+
"learning_rate": 0.0002,
|
| 92 |
+
"loss": 0.5867,
|
| 93 |
"step": 14
|
| 94 |
},
|
| 95 |
{
|
| 96 |
+
"epoch": 1.0,
|
| 97 |
+
"learning_rate": 0.0002,
|
| 98 |
+
"loss": 0.4927,
|
| 99 |
+
"step": 15
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 1.0,
|
| 103 |
+
"eval_loss": 0.41193127632141113,
|
| 104 |
+
"eval_runtime": 40.6398,
|
| 105 |
+
"eval_samples_per_second": 11.122,
|
| 106 |
+
"eval_steps_per_second": 0.369,
|
| 107 |
"step": 15
|
| 108 |
},
|
| 109 |
{
|
| 110 |
+
"epoch": 1.07,
|
| 111 |
+
"learning_rate": 0.0002,
|
| 112 |
+
"loss": 0.3884,
|
| 113 |
"step": 16
|
| 114 |
},
|
| 115 |
{
|
| 116 |
+
"epoch": 1.13,
|
| 117 |
+
"learning_rate": 0.0002,
|
| 118 |
+
"loss": 0.3835,
|
| 119 |
"step": 17
|
| 120 |
},
|
| 121 |
{
|
| 122 |
+
"epoch": 1.2,
|
| 123 |
+
"learning_rate": 0.0002,
|
| 124 |
+
"loss": 0.2859,
|
| 125 |
"step": 18
|
| 126 |
},
|
| 127 |
{
|
| 128 |
+
"epoch": 1.27,
|
| 129 |
"learning_rate": 0.0002,
|
| 130 |
+
"loss": 0.3468,
|
| 131 |
"step": 19
|
| 132 |
},
|
| 133 |
{
|
| 134 |
+
"epoch": 1.33,
|
| 135 |
"learning_rate": 0.0002,
|
| 136 |
+
"loss": 0.2269,
|
| 137 |
"step": 20
|
| 138 |
},
|
| 139 |
{
|
| 140 |
+
"epoch": 1.4,
|
| 141 |
"learning_rate": 0.0002,
|
| 142 |
+
"loss": 0.2044,
|
| 143 |
"step": 21
|
| 144 |
},
|
| 145 |
{
|
| 146 |
+
"epoch": 1.47,
|
| 147 |
"learning_rate": 0.0002,
|
| 148 |
+
"loss": 0.1668,
|
| 149 |
"step": 22
|
| 150 |
},
|
| 151 |
{
|
| 152 |
+
"epoch": 1.53,
|
| 153 |
"learning_rate": 0.0002,
|
| 154 |
+
"loss": 0.1678,
|
| 155 |
"step": 23
|
| 156 |
},
|
| 157 |
{
|
| 158 |
+
"epoch": 1.6,
|
| 159 |
"learning_rate": 0.0002,
|
| 160 |
+
"loss": 0.1654,
|
| 161 |
"step": 24
|
| 162 |
},
|
| 163 |
{
|
| 164 |
+
"epoch": 1.67,
|
| 165 |
"learning_rate": 0.0002,
|
| 166 |
+
"loss": 0.1121,
|
| 167 |
"step": 25
|
| 168 |
},
|
| 169 |
{
|
| 170 |
+
"epoch": 1.73,
|
| 171 |
"learning_rate": 0.0002,
|
| 172 |
+
"loss": 0.223,
|
| 173 |
"step": 26
|
| 174 |
},
|
| 175 |
{
|
| 176 |
+
"epoch": 1.8,
|
| 177 |
"learning_rate": 0.0002,
|
| 178 |
+
"loss": 0.1855,
|
| 179 |
"step": 27
|
| 180 |
},
|
| 181 |
{
|
| 182 |
+
"epoch": 1.87,
|
| 183 |
"learning_rate": 0.0002,
|
| 184 |
+
"loss": 0.1488,
|
| 185 |
"step": 28
|
| 186 |
},
|
| 187 |
{
|
| 188 |
+
"epoch": 1.93,
|
| 189 |
"learning_rate": 0.0002,
|
| 190 |
+
"loss": 0.1586,
|
| 191 |
"step": 29
|
| 192 |
},
|
| 193 |
{
|
| 194 |
+
"epoch": 2.0,
|
| 195 |
"learning_rate": 0.0002,
|
| 196 |
+
"loss": 0.068,
|
| 197 |
"step": 30
|
| 198 |
},
|
| 199 |
{
|
| 200 |
+
"epoch": 2.0,
|
| 201 |
+
"eval_loss": 0.06925466656684875,
|
| 202 |
+
"eval_runtime": 40.9545,
|
| 203 |
+
"eval_samples_per_second": 11.037,
|
| 204 |
+
"eval_steps_per_second": 0.366,
|
| 205 |
+
"step": 30
|
| 206 |
},
|
| 207 |
{
|
| 208 |
+
"epoch": 2.07,
|
| 209 |
+
"learning_rate": 0.0002,
|
| 210 |
+
"loss": 0.0837,
|
|
|
|
|
|
|
| 211 |
"step": 31
|
| 212 |
},
|
| 213 |
{
|
| 214 |
+
"epoch": 2.13,
|
| 215 |
"learning_rate": 0.0002,
|
| 216 |
+
"loss": 0.0331,
|
| 217 |
"step": 32
|
| 218 |
},
|
| 219 |
{
|
| 220 |
+
"epoch": 2.2,
|
| 221 |
"learning_rate": 0.0002,
|
| 222 |
+
"loss": 0.062,
|
| 223 |
"step": 33
|
| 224 |
},
|
| 225 |
{
|
| 226 |
+
"epoch": 2.27,
|
| 227 |
"learning_rate": 0.0002,
|
| 228 |
+
"loss": 0.0236,
|
| 229 |
"step": 34
|
| 230 |
},
|
| 231 |
{
|
| 232 |
+
"epoch": 2.33,
|
| 233 |
"learning_rate": 0.0002,
|
| 234 |
+
"loss": 0.0335,
|
| 235 |
"step": 35
|
| 236 |
},
|
| 237 |
{
|
| 238 |
+
"epoch": 2.4,
|
| 239 |
"learning_rate": 0.0002,
|
| 240 |
+
"loss": 0.0187,
|
| 241 |
"step": 36
|
| 242 |
},
|
| 243 |
{
|
| 244 |
+
"epoch": 2.47,
|
| 245 |
"learning_rate": 0.0002,
|
| 246 |
+
"loss": 0.0626,
|
| 247 |
"step": 37
|
| 248 |
},
|
| 249 |
{
|
| 250 |
+
"epoch": 2.53,
|
| 251 |
"learning_rate": 0.0002,
|
| 252 |
+
"loss": 0.0624,
|
| 253 |
"step": 38
|
| 254 |
},
|
| 255 |
{
|
| 256 |
+
"epoch": 2.6,
|
| 257 |
"learning_rate": 0.0002,
|
| 258 |
+
"loss": 0.0307,
|
| 259 |
"step": 39
|
| 260 |
},
|
| 261 |
{
|
| 262 |
+
"epoch": 2.67,
|
| 263 |
"learning_rate": 0.0002,
|
| 264 |
+
"loss": 0.049,
|
| 265 |
"step": 40
|
| 266 |
},
|
| 267 |
{
|
| 268 |
+
"epoch": 2.73,
|
| 269 |
"learning_rate": 0.0002,
|
| 270 |
+
"loss": 0.0188,
|
| 271 |
"step": 41
|
| 272 |
},
|
| 273 |
{
|
| 274 |
+
"epoch": 2.8,
|
| 275 |
"learning_rate": 0.0002,
|
| 276 |
+
"loss": 0.0246,
|
| 277 |
"step": 42
|
| 278 |
},
|
| 279 |
{
|
| 280 |
+
"epoch": 2.87,
|
| 281 |
"learning_rate": 0.0002,
|
| 282 |
+
"loss": 0.0305,
|
| 283 |
"step": 43
|
| 284 |
},
|
| 285 |
{
|
| 286 |
+
"epoch": 2.93,
|
| 287 |
"learning_rate": 0.0002,
|
| 288 |
+
"loss": 0.0344,
|
| 289 |
"step": 44
|
| 290 |
},
|
| 291 |
{
|
| 292 |
+
"epoch": 3.0,
|
| 293 |
"learning_rate": 0.0002,
|
| 294 |
+
"loss": 0.0299,
|
| 295 |
+
"step": 45
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 3.0,
|
| 299 |
+
"eval_loss": 0.015882715582847595,
|
| 300 |
+
"eval_runtime": 40.9377,
|
| 301 |
+
"eval_samples_per_second": 11.041,
|
| 302 |
+
"eval_steps_per_second": 0.366,
|
| 303 |
"step": 45
|
| 304 |
},
|
| 305 |
{
|
| 306 |
+
"epoch": 3.07,
|
| 307 |
"learning_rate": 0.0002,
|
| 308 |
+
"loss": 0.0084,
|
| 309 |
"step": 46
|
| 310 |
},
|
| 311 |
{
|
| 312 |
+
"epoch": 3.13,
|
| 313 |
"learning_rate": 0.0002,
|
| 314 |
+
"loss": 0.0127,
|
| 315 |
"step": 47
|
| 316 |
},
|
| 317 |
{
|
| 318 |
+
"epoch": 3.2,
|
| 319 |
"learning_rate": 0.0002,
|
| 320 |
+
"loss": 0.0118,
|
| 321 |
"step": 48
|
| 322 |
},
|
| 323 |
{
|
| 324 |
+
"epoch": 3.27,
|
| 325 |
"learning_rate": 0.0002,
|
| 326 |
+
"loss": 0.0121,
|
| 327 |
"step": 49
|
| 328 |
},
|
| 329 |
{
|
| 330 |
+
"epoch": 3.33,
|
| 331 |
"learning_rate": 0.0002,
|
| 332 |
+
"loss": 0.0065,
|
| 333 |
"step": 50
|
| 334 |
},
|
| 335 |
{
|
| 336 |
+
"epoch": 3.4,
|
| 337 |
"learning_rate": 0.0002,
|
| 338 |
+
"loss": 0.0104,
|
| 339 |
"step": 51
|
| 340 |
},
|
| 341 |
{
|
| 342 |
+
"epoch": 3.47,
|
| 343 |
"learning_rate": 0.0002,
|
| 344 |
+
"loss": 0.0212,
|
| 345 |
"step": 52
|
| 346 |
},
|
| 347 |
{
|
| 348 |
+
"epoch": 3.53,
|
| 349 |
"learning_rate": 0.0002,
|
| 350 |
+
"loss": 0.0125,
|
| 351 |
"step": 53
|
| 352 |
},
|
| 353 |
{
|
| 354 |
+
"epoch": 3.6,
|
| 355 |
"learning_rate": 0.0002,
|
| 356 |
+
"loss": 0.0061,
|
| 357 |
"step": 54
|
| 358 |
},
|
| 359 |
{
|
| 360 |
+
"epoch": 3.67,
|
| 361 |
"learning_rate": 0.0002,
|
| 362 |
+
"loss": 0.0065,
|
| 363 |
"step": 55
|
| 364 |
},
|
| 365 |
{
|
| 366 |
+
"epoch": 3.73,
|
| 367 |
"learning_rate": 0.0002,
|
| 368 |
+
"loss": 0.0128,
|
| 369 |
"step": 56
|
| 370 |
},
|
| 371 |
{
|
| 372 |
+
"epoch": 3.8,
|
| 373 |
"learning_rate": 0.0002,
|
| 374 |
+
"loss": 0.0116,
|
| 375 |
"step": 57
|
| 376 |
},
|
| 377 |
{
|
| 378 |
+
"epoch": 3.87,
|
| 379 |
"learning_rate": 0.0002,
|
| 380 |
+
"loss": 0.011,
|
| 381 |
"step": 58
|
| 382 |
},
|
| 383 |
{
|
| 384 |
+
"epoch": 3.93,
|
| 385 |
"learning_rate": 0.0002,
|
| 386 |
+
"loss": 0.0039,
|
| 387 |
"step": 59
|
| 388 |
},
|
| 389 |
{
|
| 390 |
+
"epoch": 4.0,
|
| 391 |
"learning_rate": 0.0002,
|
| 392 |
+
"loss": 0.0086,
|
| 393 |
"step": 60
|
| 394 |
},
|
| 395 |
{
|
| 396 |
+
"epoch": 4.0,
|
| 397 |
+
"eval_loss": 0.007012286223471165,
|
| 398 |
+
"eval_runtime": 40.8411,
|
| 399 |
+
"eval_samples_per_second": 11.067,
|
| 400 |
+
"eval_steps_per_second": 0.367,
|
| 401 |
+
"step": 60
|
| 402 |
},
|
| 403 |
{
|
| 404 |
+
"epoch": 4.07,
|
| 405 |
"learning_rate": 0.0002,
|
| 406 |
+
"loss": 0.0076,
|
| 407 |
+
"step": 61
|
| 408 |
},
|
| 409 |
{
|
| 410 |
+
"epoch": 4.13,
|
| 411 |
+
"learning_rate": 0.0002,
|
| 412 |
+
"loss": 0.0089,
|
|
|
|
|
|
|
| 413 |
"step": 62
|
| 414 |
},
|
| 415 |
{
|
| 416 |
+
"epoch": 4.2,
|
| 417 |
"learning_rate": 0.0002,
|
| 418 |
+
"loss": 0.0038,
|
| 419 |
"step": 63
|
| 420 |
},
|
| 421 |
{
|
| 422 |
+
"epoch": 4.27,
|
| 423 |
"learning_rate": 0.0002,
|
| 424 |
+
"loss": 0.0053,
|
| 425 |
"step": 64
|
| 426 |
},
|
| 427 |
{
|
| 428 |
+
"epoch": 4.33,
|
| 429 |
"learning_rate": 0.0002,
|
| 430 |
+
"loss": 0.0095,
|
| 431 |
"step": 65
|
| 432 |
},
|
| 433 |
{
|
| 434 |
+
"epoch": 4.4,
|
| 435 |
"learning_rate": 0.0002,
|
| 436 |
+
"loss": 0.0063,
|
| 437 |
"step": 66
|
| 438 |
},
|
| 439 |
{
|
| 440 |
+
"epoch": 4.47,
|
| 441 |
"learning_rate": 0.0002,
|
| 442 |
+
"loss": 0.0063,
|
| 443 |
"step": 67
|
| 444 |
},
|
| 445 |
{
|
| 446 |
+
"epoch": 4.53,
|
| 447 |
"learning_rate": 0.0002,
|
| 448 |
+
"loss": 0.0026,
|
| 449 |
"step": 68
|
| 450 |
},
|
| 451 |
{
|
| 452 |
+
"epoch": 4.6,
|
| 453 |
"learning_rate": 0.0002,
|
| 454 |
+
"loss": 0.0088,
|
| 455 |
"step": 69
|
| 456 |
},
|
| 457 |
{
|
| 458 |
+
"epoch": 4.67,
|
| 459 |
"learning_rate": 0.0002,
|
| 460 |
+
"loss": 0.0041,
|
| 461 |
"step": 70
|
| 462 |
},
|
| 463 |
{
|
| 464 |
+
"epoch": 4.73,
|
| 465 |
"learning_rate": 0.0002,
|
| 466 |
+
"loss": 0.0048,
|
| 467 |
"step": 71
|
| 468 |
},
|
| 469 |
{
|
| 470 |
+
"epoch": 4.8,
|
| 471 |
"learning_rate": 0.0002,
|
| 472 |
+
"loss": 0.0046,
|
| 473 |
"step": 72
|
| 474 |
},
|
| 475 |
{
|
| 476 |
+
"epoch": 4.87,
|
| 477 |
"learning_rate": 0.0002,
|
| 478 |
+
"loss": 0.0028,
|
| 479 |
"step": 73
|
| 480 |
},
|
| 481 |
{
|
| 482 |
+
"epoch": 4.93,
|
| 483 |
"learning_rate": 0.0002,
|
| 484 |
+
"loss": 0.0111,
|
| 485 |
"step": 74
|
| 486 |
},
|
| 487 |
{
|
| 488 |
+
"epoch": 5.0,
|
| 489 |
"learning_rate": 0.0002,
|
| 490 |
+
"loss": 0.004,
|
| 491 |
"step": 75
|
| 492 |
},
|
| 493 |
{
|
| 494 |
+
"epoch": 5.0,
|
| 495 |
+
"eval_loss": 0.0035899323411285877,
|
| 496 |
+
"eval_runtime": 40.7854,
|
| 497 |
+
"eval_samples_per_second": 11.082,
|
| 498 |
+
"eval_steps_per_second": 0.368,
|
| 499 |
+
"step": 75
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 5.07,
|
| 503 |
"learning_rate": 0.0002,
|
| 504 |
+
"loss": 0.0018,
|
| 505 |
"step": 76
|
| 506 |
},
|
| 507 |
{
|
| 508 |
+
"epoch": 5.13,
|
| 509 |
"learning_rate": 0.0002,
|
| 510 |
+
"loss": 0.002,
|
| 511 |
"step": 77
|
| 512 |
},
|
| 513 |
{
|
| 514 |
+
"epoch": 5.2,
|
| 515 |
"learning_rate": 0.0002,
|
| 516 |
+
"loss": 0.0016,
|
| 517 |
"step": 78
|
| 518 |
},
|
| 519 |
{
|
| 520 |
+
"epoch": 5.27,
|
| 521 |
"learning_rate": 0.0002,
|
| 522 |
+
"loss": 0.0019,
|
| 523 |
"step": 79
|
| 524 |
},
|
| 525 |
{
|
| 526 |
+
"epoch": 5.33,
|
| 527 |
"learning_rate": 0.0002,
|
| 528 |
+
"loss": 0.0045,
|
| 529 |
"step": 80
|
| 530 |
},
|
| 531 |
{
|
| 532 |
+
"epoch": 5.4,
|
| 533 |
"learning_rate": 0.0002,
|
| 534 |
+
"loss": 0.0059,
|
| 535 |
"step": 81
|
| 536 |
},
|
| 537 |
{
|
| 538 |
+
"epoch": 5.47,
|
| 539 |
"learning_rate": 0.0002,
|
| 540 |
+
"loss": 0.0034,
|
| 541 |
"step": 82
|
| 542 |
},
|
| 543 |
{
|
| 544 |
+
"epoch": 5.53,
|
| 545 |
"learning_rate": 0.0002,
|
| 546 |
+
"loss": 0.0026,
|
| 547 |
"step": 83
|
| 548 |
},
|
| 549 |
{
|
| 550 |
+
"epoch": 5.6,
|
| 551 |
"learning_rate": 0.0002,
|
| 552 |
+
"loss": 0.0043,
|
| 553 |
"step": 84
|
| 554 |
},
|
| 555 |
{
|
| 556 |
+
"epoch": 5.67,
|
| 557 |
"learning_rate": 0.0002,
|
| 558 |
+
"loss": 0.002,
|
| 559 |
"step": 85
|
| 560 |
},
|
| 561 |
{
|
| 562 |
+
"epoch": 5.73,
|
| 563 |
"learning_rate": 0.0002,
|
| 564 |
+
"loss": 0.0069,
|
| 565 |
"step": 86
|
| 566 |
},
|
| 567 |
{
|
| 568 |
+
"epoch": 5.8,
|
| 569 |
"learning_rate": 0.0002,
|
| 570 |
+
"loss": 0.0082,
|
| 571 |
"step": 87
|
| 572 |
},
|
| 573 |
{
|
| 574 |
+
"epoch": 5.87,
|
| 575 |
"learning_rate": 0.0002,
|
| 576 |
+
"loss": 0.0036,
|
| 577 |
"step": 88
|
| 578 |
},
|
| 579 |
{
|
| 580 |
+
"epoch": 5.93,
|
| 581 |
"learning_rate": 0.0002,
|
| 582 |
+
"loss": 0.0029,
|
| 583 |
"step": 89
|
| 584 |
},
|
| 585 |
{
|
| 586 |
+
"epoch": 6.0,
|
| 587 |
"learning_rate": 0.0002,
|
| 588 |
+
"loss": 0.0025,
|
| 589 |
"step": 90
|
| 590 |
},
|
| 591 |
{
|
| 592 |
+
"epoch": 6.0,
|
| 593 |
+
"eval_loss": 0.0018588710809126496,
|
| 594 |
+
"eval_runtime": 40.8365,
|
| 595 |
+
"eval_samples_per_second": 11.069,
|
| 596 |
+
"eval_steps_per_second": 0.367,
|
| 597 |
+
"step": 90
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 6.07,
|
| 601 |
"learning_rate": 0.0002,
|
| 602 |
+
"loss": 0.0012,
|
| 603 |
"step": 91
|
| 604 |
},
|
| 605 |
{
|
| 606 |
+
"epoch": 6.13,
|
| 607 |
"learning_rate": 0.0002,
|
| 608 |
+
"loss": 0.0019,
|
| 609 |
"step": 92
|
| 610 |
},
|
| 611 |
{
|
| 612 |
+
"epoch": 6.2,
|
| 613 |
"learning_rate": 0.0002,
|
| 614 |
+
"loss": 0.0036,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 615 |
"step": 93
|
| 616 |
},
|
| 617 |
{
|
| 618 |
+
"epoch": 6.27,
|
| 619 |
"learning_rate": 0.0002,
|
| 620 |
+
"loss": 0.0007,
|
| 621 |
"step": 94
|
| 622 |
},
|
| 623 |
{
|
| 624 |
+
"epoch": 6.33,
|
| 625 |
"learning_rate": 0.0002,
|
| 626 |
+
"loss": 0.0019,
|
| 627 |
"step": 95
|
| 628 |
},
|
| 629 |
{
|
| 630 |
+
"epoch": 6.4,
|
| 631 |
"learning_rate": 0.0002,
|
| 632 |
+
"loss": 0.0017,
|
| 633 |
"step": 96
|
| 634 |
},
|
| 635 |
{
|
| 636 |
+
"epoch": 6.47,
|
| 637 |
"learning_rate": 0.0002,
|
| 638 |
+
"loss": 0.001,
|
| 639 |
"step": 97
|
| 640 |
},
|
| 641 |
{
|
| 642 |
+
"epoch": 6.53,
|
| 643 |
"learning_rate": 0.0002,
|
| 644 |
+
"loss": 0.0027,
|
| 645 |
"step": 98
|
| 646 |
},
|
| 647 |
{
|
| 648 |
+
"epoch": 6.6,
|
| 649 |
"learning_rate": 0.0002,
|
| 650 |
+
"loss": 0.001,
|
| 651 |
"step": 99
|
| 652 |
},
|
| 653 |
{
|
| 654 |
+
"epoch": 6.67,
|
| 655 |
"learning_rate": 0.0002,
|
| 656 |
+
"loss": 0.0017,
|
| 657 |
"step": 100
|
| 658 |
},
|
| 659 |
{
|
| 660 |
+
"epoch": 6.73,
|
| 661 |
"learning_rate": 0.0002,
|
| 662 |
+
"loss": 0.0014,
|
| 663 |
"step": 101
|
| 664 |
},
|
| 665 |
{
|
| 666 |
+
"epoch": 6.8,
|
| 667 |
"learning_rate": 0.0002,
|
| 668 |
+
"loss": 0.0021,
|
| 669 |
"step": 102
|
| 670 |
},
|
| 671 |
{
|
| 672 |
+
"epoch": 6.87,
|
| 673 |
"learning_rate": 0.0002,
|
| 674 |
+
"loss": 0.0024,
|
| 675 |
"step": 103
|
| 676 |
},
|
| 677 |
{
|
| 678 |
+
"epoch": 6.93,
|
| 679 |
"learning_rate": 0.0002,
|
| 680 |
+
"loss": 0.0025,
|
| 681 |
"step": 104
|
| 682 |
},
|
| 683 |
{
|
| 684 |
+
"epoch": 7.0,
|
| 685 |
"learning_rate": 0.0002,
|
| 686 |
+
"loss": 0.001,
|
| 687 |
"step": 105
|
| 688 |
},
|
| 689 |
{
|
| 690 |
+
"epoch": 7.0,
|
| 691 |
+
"eval_loss": 0.0018638158217072487,
|
| 692 |
+
"eval_runtime": 40.908,
|
| 693 |
+
"eval_samples_per_second": 11.049,
|
| 694 |
+
"eval_steps_per_second": 0.367,
|
| 695 |
+
"step": 105
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 7.07,
|
| 699 |
"learning_rate": 0.0002,
|
| 700 |
+
"loss": 0.0014,
|
| 701 |
"step": 106
|
| 702 |
},
|
| 703 |
{
|
| 704 |
+
"epoch": 7.13,
|
| 705 |
"learning_rate": 0.0002,
|
| 706 |
+
"loss": 0.0049,
|
| 707 |
"step": 107
|
| 708 |
},
|
| 709 |
{
|
| 710 |
+
"epoch": 7.2,
|
| 711 |
"learning_rate": 0.0002,
|
| 712 |
+
"loss": 0.0015,
|
| 713 |
"step": 108
|
| 714 |
},
|
| 715 |
{
|
| 716 |
+
"epoch": 7.27,
|
| 717 |
"learning_rate": 0.0002,
|
| 718 |
+
"loss": 0.0032,
|
| 719 |
"step": 109
|
| 720 |
},
|
| 721 |
{
|
| 722 |
+
"epoch": 7.33,
|
| 723 |
"learning_rate": 0.0002,
|
| 724 |
+
"loss": 0.0011,
|
| 725 |
"step": 110
|
| 726 |
},
|
| 727 |
{
|
| 728 |
+
"epoch": 7.4,
|
| 729 |
"learning_rate": 0.0002,
|
| 730 |
+
"loss": 0.0023,
|
| 731 |
"step": 111
|
| 732 |
},
|
| 733 |
{
|
| 734 |
+
"epoch": 7.47,
|
| 735 |
"learning_rate": 0.0002,
|
| 736 |
+
"loss": 0.0017,
|
| 737 |
"step": 112
|
| 738 |
},
|
| 739 |
{
|
| 740 |
+
"epoch": 7.53,
|
| 741 |
"learning_rate": 0.0002,
|
| 742 |
+
"loss": 0.0025,
|
| 743 |
"step": 113
|
| 744 |
},
|
| 745 |
{
|
| 746 |
+
"epoch": 7.6,
|
| 747 |
"learning_rate": 0.0002,
|
| 748 |
+
"loss": 0.0028,
|
| 749 |
"step": 114
|
| 750 |
},
|
| 751 |
{
|
| 752 |
+
"epoch": 7.67,
|
| 753 |
"learning_rate": 0.0002,
|
| 754 |
+
"loss": 0.0013,
|
| 755 |
"step": 115
|
| 756 |
},
|
| 757 |
{
|
| 758 |
+
"epoch": 7.73,
|
| 759 |
"learning_rate": 0.0002,
|
| 760 |
+
"loss": 0.0029,
|
| 761 |
"step": 116
|
| 762 |
},
|
| 763 |
{
|
| 764 |
+
"epoch": 7.8,
|
| 765 |
"learning_rate": 0.0002,
|
| 766 |
+
"loss": 0.0019,
|
| 767 |
"step": 117
|
| 768 |
},
|
| 769 |
{
|
| 770 |
+
"epoch": 7.87,
|
| 771 |
"learning_rate": 0.0002,
|
| 772 |
+
"loss": 0.001,
|
| 773 |
"step": 118
|
| 774 |
},
|
| 775 |
{
|
| 776 |
+
"epoch": 7.93,
|
| 777 |
"learning_rate": 0.0002,
|
| 778 |
+
"loss": 0.0018,
|
| 779 |
"step": 119
|
| 780 |
},
|
| 781 |
{
|
| 782 |
+
"epoch": 8.0,
|
| 783 |
"learning_rate": 0.0002,
|
| 784 |
+
"loss": 0.0006,
|
| 785 |
"step": 120
|
| 786 |
},
|
| 787 |
{
|
| 788 |
+
"epoch": 8.0,
|
| 789 |
+
"eval_loss": 0.0013907084940001369,
|
| 790 |
+
"eval_runtime": 40.8865,
|
| 791 |
+
"eval_samples_per_second": 11.055,
|
| 792 |
+
"eval_steps_per_second": 0.367,
|
| 793 |
+
"step": 120
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 8.07,
|
| 797 |
"learning_rate": 0.0002,
|
| 798 |
+
"loss": 0.0004,
|
| 799 |
"step": 121
|
| 800 |
},
|
| 801 |
{
|
| 802 |
+
"epoch": 8.13,
|
| 803 |
"learning_rate": 0.0002,
|
| 804 |
+
"loss": 0.0016,
|
| 805 |
"step": 122
|
| 806 |
},
|
| 807 |
{
|
| 808 |
+
"epoch": 8.2,
|
| 809 |
"learning_rate": 0.0002,
|
| 810 |
+
"loss": 0.0024,
|
| 811 |
"step": 123
|
| 812 |
},
|
| 813 |
{
|
| 814 |
+
"epoch": 8.27,
|
| 815 |
"learning_rate": 0.0002,
|
| 816 |
+
"loss": 0.0006,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 817 |
"step": 124
|
| 818 |
},
|
| 819 |
{
|
| 820 |
+
"epoch": 8.33,
|
| 821 |
"learning_rate": 0.0002,
|
| 822 |
+
"loss": 0.001,
|
| 823 |
"step": 125
|
| 824 |
},
|
| 825 |
{
|
| 826 |
+
"epoch": 8.4,
|
| 827 |
"learning_rate": 0.0002,
|
| 828 |
+
"loss": 0.0011,
|
| 829 |
"step": 126
|
| 830 |
},
|
| 831 |
{
|
| 832 |
+
"epoch": 8.47,
|
| 833 |
"learning_rate": 0.0002,
|
| 834 |
+
"loss": 0.0035,
|
| 835 |
"step": 127
|
| 836 |
},
|
| 837 |
{
|
| 838 |
+
"epoch": 8.53,
|
| 839 |
"learning_rate": 0.0002,
|
| 840 |
+
"loss": 0.0019,
|
| 841 |
"step": 128
|
| 842 |
},
|
| 843 |
{
|
| 844 |
+
"epoch": 8.6,
|
| 845 |
"learning_rate": 0.0002,
|
| 846 |
+
"loss": 0.0018,
|
| 847 |
"step": 129
|
| 848 |
},
|
| 849 |
{
|
| 850 |
+
"epoch": 8.67,
|
| 851 |
"learning_rate": 0.0002,
|
| 852 |
+
"loss": 0.0052,
|
| 853 |
"step": 130
|
| 854 |
},
|
| 855 |
{
|
| 856 |
+
"epoch": 8.73,
|
| 857 |
"learning_rate": 0.0002,
|
| 858 |
+
"loss": 0.0007,
|
| 859 |
"step": 131
|
| 860 |
},
|
| 861 |
{
|
| 862 |
+
"epoch": 8.8,
|
| 863 |
"learning_rate": 0.0002,
|
| 864 |
+
"loss": 0.0012,
|
| 865 |
"step": 132
|
| 866 |
},
|
| 867 |
{
|
| 868 |
+
"epoch": 8.87,
|
| 869 |
"learning_rate": 0.0002,
|
| 870 |
+
"loss": 0.0011,
|
| 871 |
"step": 133
|
| 872 |
},
|
| 873 |
{
|
| 874 |
+
"epoch": 8.93,
|
| 875 |
"learning_rate": 0.0002,
|
| 876 |
+
"loss": 0.0009,
|
| 877 |
"step": 134
|
| 878 |
},
|
| 879 |
{
|
| 880 |
+
"epoch": 9.0,
|
| 881 |
"learning_rate": 0.0002,
|
| 882 |
+
"loss": 0.0004,
|
| 883 |
+
"step": 135
|
| 884 |
+
},
|
| 885 |
+
{
|
| 886 |
+
"epoch": 9.0,
|
| 887 |
+
"eval_loss": 0.0007831940311007202,
|
| 888 |
+
"eval_runtime": 40.9221,
|
| 889 |
+
"eval_samples_per_second": 11.045,
|
| 890 |
+
"eval_steps_per_second": 0.367,
|
| 891 |
"step": 135
|
| 892 |
},
|
| 893 |
{
|
| 894 |
+
"epoch": 9.07,
|
| 895 |
"learning_rate": 0.0002,
|
| 896 |
+
"loss": 0.0014,
|
| 897 |
"step": 136
|
| 898 |
},
|
| 899 |
{
|
| 900 |
+
"epoch": 9.13,
|
| 901 |
"learning_rate": 0.0002,
|
| 902 |
+
"loss": 0.0008,
|
| 903 |
"step": 137
|
| 904 |
},
|
| 905 |
{
|
| 906 |
+
"epoch": 9.2,
|
| 907 |
"learning_rate": 0.0002,
|
| 908 |
+
"loss": 0.0006,
|
| 909 |
"step": 138
|
| 910 |
},
|
| 911 |
{
|
| 912 |
+
"epoch": 9.27,
|
| 913 |
"learning_rate": 0.0002,
|
| 914 |
+
"loss": 0.0004,
|
| 915 |
"step": 139
|
| 916 |
},
|
| 917 |
{
|
| 918 |
+
"epoch": 9.33,
|
| 919 |
"learning_rate": 0.0002,
|
| 920 |
+
"loss": 0.0005,
|
| 921 |
"step": 140
|
| 922 |
},
|
| 923 |
{
|
| 924 |
+
"epoch": 9.4,
|
| 925 |
"learning_rate": 0.0002,
|
| 926 |
+
"loss": 0.0009,
|
| 927 |
"step": 141
|
| 928 |
},
|
| 929 |
{
|
| 930 |
+
"epoch": 9.47,
|
| 931 |
"learning_rate": 0.0002,
|
| 932 |
+
"loss": 0.0004,
|
| 933 |
"step": 142
|
| 934 |
},
|
| 935 |
{
|
| 936 |
+
"epoch": 9.53,
|
| 937 |
"learning_rate": 0.0002,
|
| 938 |
+
"loss": 0.0014,
|
| 939 |
"step": 143
|
| 940 |
},
|
| 941 |
{
|
| 942 |
+
"epoch": 9.6,
|
| 943 |
"learning_rate": 0.0002,
|
| 944 |
+
"loss": 0.0005,
|
| 945 |
"step": 144
|
| 946 |
},
|
| 947 |
{
|
| 948 |
+
"epoch": 9.67,
|
| 949 |
"learning_rate": 0.0002,
|
| 950 |
+
"loss": 0.0002,
|
| 951 |
"step": 145
|
| 952 |
},
|
| 953 |
{
|
| 954 |
+
"epoch": 9.73,
|
| 955 |
"learning_rate": 0.0002,
|
| 956 |
+
"loss": 0.0016,
|
| 957 |
"step": 146
|
| 958 |
},
|
| 959 |
{
|
| 960 |
+
"epoch": 9.8,
|
| 961 |
"learning_rate": 0.0002,
|
| 962 |
+
"loss": 0.0005,
|
| 963 |
"step": 147
|
| 964 |
},
|
| 965 |
{
|
| 966 |
+
"epoch": 9.87,
|
| 967 |
"learning_rate": 0.0002,
|
| 968 |
+
"loss": 0.001,
|
| 969 |
"step": 148
|
| 970 |
},
|
| 971 |
{
|
| 972 |
+
"epoch": 9.93,
|
| 973 |
"learning_rate": 0.0002,
|
| 974 |
+
"loss": 0.0003,
|
| 975 |
"step": 149
|
| 976 |
},
|
| 977 |
{
|
| 978 |
+
"epoch": 10.0,
|
| 979 |
"learning_rate": 0.0002,
|
| 980 |
+
"loss": 0.0003,
|
| 981 |
"step": 150
|
| 982 |
},
|
| 983 |
{
|
| 984 |
+
"epoch": 10.0,
|
| 985 |
+
"eval_loss": 0.00036743757664225996,
|
| 986 |
+
"eval_runtime": 41.0504,
|
| 987 |
+
"eval_samples_per_second": 11.011,
|
| 988 |
+
"eval_steps_per_second": 0.365,
|
| 989 |
+
"step": 150
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 10.07,
|
| 993 |
"learning_rate": 0.0002,
|
| 994 |
+
"loss": 0.0001,
|
| 995 |
"step": 151
|
| 996 |
},
|
| 997 |
{
|
| 998 |
+
"epoch": 10.13,
|
| 999 |
"learning_rate": 0.0002,
|
| 1000 |
+
"loss": 0.0021,
|
| 1001 |
"step": 152
|
| 1002 |
},
|
| 1003 |
{
|
| 1004 |
+
"epoch": 10.2,
|
| 1005 |
"learning_rate": 0.0002,
|
| 1006 |
+
"loss": 0.0003,
|
| 1007 |
"step": 153
|
| 1008 |
},
|
| 1009 |
{
|
| 1010 |
+
"epoch": 10.27,
|
| 1011 |
"learning_rate": 0.0002,
|
| 1012 |
+
"loss": 0.0005,
|
| 1013 |
"step": 154
|
| 1014 |
},
|
| 1015 |
{
|
| 1016 |
+
"epoch": 10.33,
|
| 1017 |
"learning_rate": 0.0002,
|
| 1018 |
+
"loss": 0.0007,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1019 |
"step": 155
|
| 1020 |
},
|
| 1021 |
{
|
| 1022 |
+
"epoch": 10.4,
|
| 1023 |
"learning_rate": 0.0002,
|
| 1024 |
+
"loss": 0.0009,
|
| 1025 |
"step": 156
|
| 1026 |
},
|
| 1027 |
{
|
| 1028 |
+
"epoch": 10.47,
|
| 1029 |
"learning_rate": 0.0002,
|
| 1030 |
+
"loss": 0.0001,
|
| 1031 |
"step": 157
|
| 1032 |
},
|
| 1033 |
{
|
| 1034 |
+
"epoch": 10.53,
|
| 1035 |
"learning_rate": 0.0002,
|
| 1036 |
+
"loss": 0.0007,
|
| 1037 |
"step": 158
|
| 1038 |
},
|
| 1039 |
{
|
| 1040 |
+
"epoch": 10.6,
|
| 1041 |
"learning_rate": 0.0002,
|
| 1042 |
+
"loss": 0.0001,
|
| 1043 |
"step": 159
|
| 1044 |
},
|
| 1045 |
{
|
| 1046 |
+
"epoch": 10.67,
|
| 1047 |
"learning_rate": 0.0002,
|
| 1048 |
+
"loss": 0.0004,
|
| 1049 |
"step": 160
|
| 1050 |
},
|
| 1051 |
{
|
| 1052 |
+
"epoch": 10.73,
|
| 1053 |
"learning_rate": 0.0002,
|
| 1054 |
+
"loss": 0.0002,
|
| 1055 |
"step": 161
|
| 1056 |
},
|
| 1057 |
{
|
| 1058 |
+
"epoch": 10.8,
|
| 1059 |
"learning_rate": 0.0002,
|
| 1060 |
+
"loss": 0.0002,
|
| 1061 |
"step": 162
|
| 1062 |
},
|
| 1063 |
{
|
| 1064 |
+
"epoch": 10.87,
|
| 1065 |
"learning_rate": 0.0002,
|
| 1066 |
+
"loss": 0.0001,
|
| 1067 |
"step": 163
|
| 1068 |
},
|
| 1069 |
{
|
| 1070 |
+
"epoch": 10.93,
|
| 1071 |
"learning_rate": 0.0002,
|
| 1072 |
+
"loss": 0.0007,
|
| 1073 |
"step": 164
|
| 1074 |
},
|
| 1075 |
{
|
| 1076 |
+
"epoch": 11.0,
|
| 1077 |
"learning_rate": 0.0002,
|
| 1078 |
+
"loss": 0.0007,
|
| 1079 |
+
"step": 165
|
| 1080 |
+
},
|
| 1081 |
+
{
|
| 1082 |
+
"epoch": 11.0,
|
| 1083 |
+
"eval_loss": 0.0005829737638123333,
|
| 1084 |
+
"eval_runtime": 40.8774,
|
| 1085 |
+
"eval_samples_per_second": 11.057,
|
| 1086 |
+
"eval_steps_per_second": 0.367,
|
| 1087 |
"step": 165
|
| 1088 |
},
|
| 1089 |
{
|
| 1090 |
+
"epoch": 11.07,
|
| 1091 |
"learning_rate": 0.0002,
|
| 1092 |
+
"loss": 0.0003,
|
| 1093 |
"step": 166
|
| 1094 |
},
|
| 1095 |
{
|
| 1096 |
+
"epoch": 11.13,
|
| 1097 |
"learning_rate": 0.0002,
|
| 1098 |
+
"loss": 0.0002,
|
| 1099 |
"step": 167
|
| 1100 |
},
|
| 1101 |
{
|
| 1102 |
+
"epoch": 11.2,
|
| 1103 |
"learning_rate": 0.0002,
|
| 1104 |
+
"loss": 0.0003,
|
| 1105 |
"step": 168
|
| 1106 |
},
|
| 1107 |
{
|
| 1108 |
+
"epoch": 11.27,
|
| 1109 |
"learning_rate": 0.0002,
|
| 1110 |
+
"loss": 0.0004,
|
| 1111 |
"step": 169
|
| 1112 |
},
|
| 1113 |
{
|
| 1114 |
+
"epoch": 11.33,
|
| 1115 |
"learning_rate": 0.0002,
|
| 1116 |
+
"loss": 0.0007,
|
| 1117 |
"step": 170
|
| 1118 |
},
|
| 1119 |
{
|
| 1120 |
+
"epoch": 11.4,
|
| 1121 |
"learning_rate": 0.0002,
|
| 1122 |
+
"loss": 0.0003,
|
| 1123 |
"step": 171
|
| 1124 |
},
|
| 1125 |
{
|
| 1126 |
+
"epoch": 11.47,
|
| 1127 |
"learning_rate": 0.0002,
|
| 1128 |
+
"loss": 0.0003,
|
| 1129 |
"step": 172
|
| 1130 |
},
|
| 1131 |
{
|
| 1132 |
+
"epoch": 11.53,
|
| 1133 |
"learning_rate": 0.0002,
|
| 1134 |
+
"loss": 0.0015,
|
| 1135 |
"step": 173
|
| 1136 |
},
|
| 1137 |
{
|
| 1138 |
+
"epoch": 11.6,
|
| 1139 |
"learning_rate": 0.0002,
|
| 1140 |
+
"loss": 0.0006,
|
| 1141 |
"step": 174
|
| 1142 |
},
|
| 1143 |
{
|
| 1144 |
+
"epoch": 11.67,
|
| 1145 |
"learning_rate": 0.0002,
|
| 1146 |
+
"loss": 0.0021,
|
| 1147 |
"step": 175
|
| 1148 |
},
|
| 1149 |
{
|
| 1150 |
+
"epoch": 11.73,
|
| 1151 |
"learning_rate": 0.0002,
|
| 1152 |
+
"loss": 0.0003,
|
| 1153 |
"step": 176
|
| 1154 |
},
|
| 1155 |
{
|
| 1156 |
+
"epoch": 11.8,
|
| 1157 |
"learning_rate": 0.0002,
|
| 1158 |
+
"loss": 0.0007,
|
| 1159 |
"step": 177
|
| 1160 |
},
|
| 1161 |
{
|
| 1162 |
+
"epoch": 11.87,
|
| 1163 |
"learning_rate": 0.0002,
|
| 1164 |
+
"loss": 0.0009,
|
| 1165 |
"step": 178
|
| 1166 |
},
|
| 1167 |
{
|
| 1168 |
+
"epoch": 11.93,
|
| 1169 |
"learning_rate": 0.0002,
|
| 1170 |
+
"loss": 0.0018,
|
| 1171 |
"step": 179
|
| 1172 |
},
|
| 1173 |
{
|
| 1174 |
+
"epoch": 12.0,
|
| 1175 |
"learning_rate": 0.0002,
|
| 1176 |
+
"loss": 0.0012,
|
| 1177 |
+
"step": 180
|
| 1178 |
+
},
|
| 1179 |
+
{
|
| 1180 |
+
"epoch": 12.0,
|
| 1181 |
+
"eval_loss": 0.0007969831931404769,
|
| 1182 |
+
"eval_runtime": 40.8593,
|
| 1183 |
+
"eval_samples_per_second": 11.062,
|
| 1184 |
+
"eval_steps_per_second": 0.367,
|
| 1185 |
"step": 180
|
| 1186 |
},
|
| 1187 |
{
|
| 1188 |
+
"epoch": 12.07,
|
| 1189 |
"learning_rate": 0.0002,
|
| 1190 |
+
"loss": 0.0001,
|
| 1191 |
"step": 181
|
| 1192 |
},
|
| 1193 |
{
|
| 1194 |
+
"epoch": 12.13,
|
| 1195 |
"learning_rate": 0.0002,
|
| 1196 |
+
"loss": 0.0019,
|
| 1197 |
"step": 182
|
| 1198 |
},
|
| 1199 |
{
|
| 1200 |
+
"epoch": 12.2,
|
| 1201 |
"learning_rate": 0.0002,
|
| 1202 |
+
"loss": 0.0018,
|
| 1203 |
"step": 183
|
| 1204 |
},
|
| 1205 |
{
|
| 1206 |
+
"epoch": 12.27,
|
| 1207 |
"learning_rate": 0.0002,
|
| 1208 |
+
"loss": 0.0014,
|
| 1209 |
"step": 184
|
| 1210 |
},
|
| 1211 |
{
|
| 1212 |
+
"epoch": 12.33,
|
| 1213 |
"learning_rate": 0.0002,
|
| 1214 |
+
"loss": 0.0007,
|
| 1215 |
"step": 185
|
| 1216 |
},
|
| 1217 |
{
|
| 1218 |
+
"epoch": 12.4,
|
| 1219 |
"learning_rate": 0.0002,
|
| 1220 |
+
"loss": 0.009,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1221 |
"step": 186
|
| 1222 |
},
|
| 1223 |
{
|
| 1224 |
+
"epoch": 12.47,
|
| 1225 |
"learning_rate": 0.0002,
|
| 1226 |
+
"loss": 0.0082,
|
| 1227 |
"step": 187
|
| 1228 |
},
|
| 1229 |
{
|
| 1230 |
+
"epoch": 12.53,
|
| 1231 |
"learning_rate": 0.0002,
|
| 1232 |
+
"loss": 0.0048,
|
| 1233 |
"step": 188
|
| 1234 |
},
|
| 1235 |
{
|
| 1236 |
+
"epoch": 12.6,
|
| 1237 |
"learning_rate": 0.0002,
|
| 1238 |
+
"loss": 0.0029,
|
| 1239 |
"step": 189
|
| 1240 |
},
|
| 1241 |
{
|
| 1242 |
+
"epoch": 12.67,
|
| 1243 |
"learning_rate": 0.0002,
|
| 1244 |
+
"loss": 0.0017,
|
| 1245 |
"step": 190
|
| 1246 |
},
|
| 1247 |
{
|
| 1248 |
+
"epoch": 12.73,
|
| 1249 |
"learning_rate": 0.0002,
|
| 1250 |
+
"loss": 0.002,
|
| 1251 |
"step": 191
|
| 1252 |
},
|
| 1253 |
{
|
| 1254 |
+
"epoch": 12.8,
|
| 1255 |
"learning_rate": 0.0002,
|
| 1256 |
+
"loss": 0.0023,
|
| 1257 |
"step": 192
|
| 1258 |
},
|
| 1259 |
{
|
| 1260 |
+
"epoch": 12.87,
|
| 1261 |
"learning_rate": 0.0002,
|
| 1262 |
+
"loss": 0.0038,
|
| 1263 |
"step": 193
|
| 1264 |
},
|
| 1265 |
{
|
| 1266 |
+
"epoch": 12.93,
|
| 1267 |
"learning_rate": 0.0002,
|
| 1268 |
+
"loss": 0.0012,
|
| 1269 |
"step": 194
|
| 1270 |
},
|
| 1271 |
{
|
| 1272 |
+
"epoch": 13.0,
|
| 1273 |
"learning_rate": 0.0002,
|
| 1274 |
+
"loss": 0.0006,
|
| 1275 |
+
"step": 195
|
| 1276 |
+
},
|
| 1277 |
+
{
|
| 1278 |
+
"epoch": 13.0,
|
| 1279 |
+
"eval_loss": 0.001564782578498125,
|
| 1280 |
+
"eval_runtime": 41.0115,
|
| 1281 |
+
"eval_samples_per_second": 11.021,
|
| 1282 |
+
"eval_steps_per_second": 0.366,
|
| 1283 |
"step": 195
|
| 1284 |
},
|
| 1285 |
{
|
| 1286 |
+
"epoch": 13.07,
|
| 1287 |
"learning_rate": 0.0002,
|
| 1288 |
+
"loss": 0.0035,
|
| 1289 |
"step": 196
|
| 1290 |
},
|
| 1291 |
{
|
| 1292 |
+
"epoch": 13.13,
|
| 1293 |
"learning_rate": 0.0002,
|
| 1294 |
+
"loss": 0.0017,
|
| 1295 |
"step": 197
|
| 1296 |
},
|
| 1297 |
{
|
| 1298 |
+
"epoch": 13.2,
|
| 1299 |
"learning_rate": 0.0002,
|
| 1300 |
+
"loss": 0.0034,
|
| 1301 |
"step": 198
|
| 1302 |
},
|
| 1303 |
{
|
| 1304 |
+
"epoch": 13.27,
|
| 1305 |
"learning_rate": 0.0002,
|
| 1306 |
+
"loss": 0.0007,
|
| 1307 |
"step": 199
|
| 1308 |
},
|
| 1309 |
{
|
| 1310 |
+
"epoch": 13.33,
|
| 1311 |
"learning_rate": 0.0002,
|
| 1312 |
+
"loss": 0.0008,
|
| 1313 |
"step": 200
|
| 1314 |
},
|
| 1315 |
{
|
| 1316 |
+
"epoch": 13.4,
|
| 1317 |
"learning_rate": 0.0002,
|
| 1318 |
+
"loss": 0.0011,
|
| 1319 |
"step": 201
|
| 1320 |
},
|
| 1321 |
{
|
| 1322 |
+
"epoch": 13.47,
|
| 1323 |
"learning_rate": 0.0002,
|
| 1324 |
+
"loss": 0.0024,
|
| 1325 |
"step": 202
|
| 1326 |
},
|
| 1327 |
{
|
| 1328 |
+
"epoch": 13.53,
|
| 1329 |
"learning_rate": 0.0002,
|
| 1330 |
+
"loss": 0.0012,
|
| 1331 |
"step": 203
|
| 1332 |
},
|
| 1333 |
{
|
| 1334 |
+
"epoch": 13.6,
|
| 1335 |
"learning_rate": 0.0002,
|
| 1336 |
+
"loss": 0.0004,
|
| 1337 |
"step": 204
|
| 1338 |
},
|
| 1339 |
{
|
| 1340 |
+
"epoch": 13.67,
|
| 1341 |
"learning_rate": 0.0002,
|
| 1342 |
+
"loss": 0.0008,
|
| 1343 |
"step": 205
|
| 1344 |
},
|
| 1345 |
{
|
| 1346 |
+
"epoch": 13.73,
|
| 1347 |
"learning_rate": 0.0002,
|
| 1348 |
+
"loss": 0.0004,
|
| 1349 |
"step": 206
|
| 1350 |
},
|
| 1351 |
{
|
| 1352 |
+
"epoch": 13.8,
|
| 1353 |
"learning_rate": 0.0002,
|
| 1354 |
+
"loss": 0.0007,
|
| 1355 |
"step": 207
|
| 1356 |
},
|
| 1357 |
{
|
| 1358 |
+
"epoch": 13.87,
|
| 1359 |
"learning_rate": 0.0002,
|
| 1360 |
+
"loss": 0.0003,
|
| 1361 |
"step": 208
|
| 1362 |
},
|
| 1363 |
{
|
| 1364 |
+
"epoch": 13.93,
|
| 1365 |
"learning_rate": 0.0002,
|
| 1366 |
+
"loss": 0.0026,
|
| 1367 |
"step": 209
|
| 1368 |
},
|
| 1369 |
{
|
| 1370 |
+
"epoch": 14.0,
|
| 1371 |
"learning_rate": 0.0002,
|
| 1372 |
+
"loss": 0.0004,
|
| 1373 |
+
"step": 210
|
| 1374 |
+
},
|
| 1375 |
+
{
|
| 1376 |
+
"epoch": 14.0,
|
| 1377 |
+
"eval_loss": 0.0006033072713762522,
|
| 1378 |
+
"eval_runtime": 40.9789,
|
| 1379 |
+
"eval_samples_per_second": 11.03,
|
| 1380 |
+
"eval_steps_per_second": 0.366,
|
| 1381 |
"step": 210
|
| 1382 |
},
|
| 1383 |
{
|
| 1384 |
+
"epoch": 14.07,
|
| 1385 |
"learning_rate": 0.0002,
|
| 1386 |
+
"loss": 0.0008,
|
| 1387 |
"step": 211
|
| 1388 |
},
|
| 1389 |
{
|
| 1390 |
+
"epoch": 14.13,
|
| 1391 |
"learning_rate": 0.0002,
|
| 1392 |
+
"loss": 0.0005,
|
| 1393 |
"step": 212
|
| 1394 |
},
|
| 1395 |
{
|
| 1396 |
+
"epoch": 14.2,
|
| 1397 |
"learning_rate": 0.0002,
|
| 1398 |
+
"loss": 0.0002,
|
| 1399 |
"step": 213
|
| 1400 |
},
|
| 1401 |
{
|
| 1402 |
+
"epoch": 14.27,
|
| 1403 |
"learning_rate": 0.0002,
|
| 1404 |
+
"loss": 0.0001,
|
| 1405 |
"step": 214
|
| 1406 |
},
|
| 1407 |
{
|
| 1408 |
+
"epoch": 14.33,
|
| 1409 |
"learning_rate": 0.0002,
|
| 1410 |
+
"loss": 0.0002,
|
| 1411 |
"step": 215
|
| 1412 |
},
|
| 1413 |
{
|
| 1414 |
+
"epoch": 14.4,
|
| 1415 |
"learning_rate": 0.0002,
|
| 1416 |
+
"loss": 0.0011,
|
| 1417 |
"step": 216
|
| 1418 |
},
|
| 1419 |
{
|
| 1420 |
+
"epoch": 14.47,
|
| 1421 |
"learning_rate": 0.0002,
|
| 1422 |
+
"loss": 0.0009,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1423 |
"step": 217
|
| 1424 |
},
|
| 1425 |
{
|
| 1426 |
+
"epoch": 14.53,
|
| 1427 |
"learning_rate": 0.0002,
|
| 1428 |
+
"loss": 0.0017,
|
| 1429 |
"step": 218
|
| 1430 |
},
|
| 1431 |
{
|
| 1432 |
+
"epoch": 14.6,
|
| 1433 |
"learning_rate": 0.0002,
|
| 1434 |
+
"loss": 0.0008,
|
| 1435 |
"step": 219
|
| 1436 |
},
|
| 1437 |
{
|
| 1438 |
+
"epoch": 14.67,
|
| 1439 |
"learning_rate": 0.0002,
|
| 1440 |
+
"loss": 0.0016,
|
| 1441 |
"step": 220
|
| 1442 |
},
|
| 1443 |
{
|
| 1444 |
+
"epoch": 14.73,
|
| 1445 |
"learning_rate": 0.0002,
|
| 1446 |
+
"loss": 0.0011,
|
| 1447 |
"step": 221
|
| 1448 |
},
|
| 1449 |
{
|
| 1450 |
+
"epoch": 14.8,
|
| 1451 |
"learning_rate": 0.0002,
|
| 1452 |
+
"loss": 0.0031,
|
| 1453 |
"step": 222
|
| 1454 |
},
|
| 1455 |
{
|
| 1456 |
+
"epoch": 14.87,
|
| 1457 |
"learning_rate": 0.0002,
|
| 1458 |
+
"loss": 0.0016,
|
| 1459 |
"step": 223
|
| 1460 |
},
|
| 1461 |
{
|
| 1462 |
+
"epoch": 14.93,
|
| 1463 |
"learning_rate": 0.0002,
|
| 1464 |
+
"loss": 0.0006,
|
| 1465 |
"step": 224
|
| 1466 |
},
|
| 1467 |
{
|
| 1468 |
+
"epoch": 15.0,
|
| 1469 |
"learning_rate": 0.0002,
|
| 1470 |
+
"loss": 0.0026,
|
| 1471 |
+
"step": 225
|
| 1472 |
+
},
|
| 1473 |
+
{
|
| 1474 |
+
"epoch": 15.0,
|
| 1475 |
+
"eval_loss": 0.0017931672045961022,
|
| 1476 |
+
"eval_runtime": 40.8742,
|
| 1477 |
+
"eval_samples_per_second": 11.058,
|
| 1478 |
+
"eval_steps_per_second": 0.367,
|
| 1479 |
"step": 225
|
| 1480 |
},
|
| 1481 |
{
|
| 1482 |
+
"epoch": 15.07,
|
| 1483 |
"learning_rate": 0.0002,
|
| 1484 |
+
"loss": 0.0012,
|
| 1485 |
"step": 226
|
| 1486 |
},
|
| 1487 |
{
|
| 1488 |
+
"epoch": 15.13,
|
| 1489 |
"learning_rate": 0.0002,
|
| 1490 |
+
"loss": 0.0037,
|
| 1491 |
"step": 227
|
| 1492 |
},
|
| 1493 |
{
|
| 1494 |
+
"epoch": 15.2,
|
| 1495 |
"learning_rate": 0.0002,
|
| 1496 |
+
"loss": 0.0012,
|
| 1497 |
"step": 228
|
| 1498 |
},
|
| 1499 |
{
|
| 1500 |
+
"epoch": 15.27,
|
| 1501 |
"learning_rate": 0.0002,
|
| 1502 |
+
"loss": 0.0011,
|
| 1503 |
"step": 229
|
| 1504 |
},
|
| 1505 |
{
|
| 1506 |
+
"epoch": 15.33,
|
| 1507 |
"learning_rate": 0.0002,
|
| 1508 |
+
"loss": 0.0011,
|
| 1509 |
"step": 230
|
| 1510 |
},
|
| 1511 |
{
|
| 1512 |
+
"epoch": 15.4,
|
| 1513 |
"learning_rate": 0.0002,
|
| 1514 |
+
"loss": 0.0046,
|
| 1515 |
"step": 231
|
| 1516 |
},
|
| 1517 |
{
|
| 1518 |
+
"epoch": 15.47,
|
| 1519 |
"learning_rate": 0.0002,
|
| 1520 |
+
"loss": 0.004,
|
| 1521 |
"step": 232
|
| 1522 |
},
|
| 1523 |
{
|
| 1524 |
+
"epoch": 15.53,
|
| 1525 |
"learning_rate": 0.0002,
|
| 1526 |
+
"loss": 0.0035,
|
| 1527 |
"step": 233
|
| 1528 |
},
|
| 1529 |
{
|
| 1530 |
+
"epoch": 15.6,
|
| 1531 |
"learning_rate": 0.0002,
|
| 1532 |
+
"loss": 0.0034,
|
| 1533 |
"step": 234
|
| 1534 |
},
|
| 1535 |
{
|
| 1536 |
+
"epoch": 15.67,
|
| 1537 |
"learning_rate": 0.0002,
|
| 1538 |
+
"loss": 0.0081,
|
| 1539 |
"step": 235
|
| 1540 |
},
|
| 1541 |
{
|
| 1542 |
+
"epoch": 15.73,
|
| 1543 |
"learning_rate": 0.0002,
|
| 1544 |
+
"loss": 0.0062,
|
| 1545 |
"step": 236
|
| 1546 |
},
|
| 1547 |
{
|
| 1548 |
+
"epoch": 15.8,
|
| 1549 |
"learning_rate": 0.0002,
|
| 1550 |
+
"loss": 0.0022,
|
| 1551 |
"step": 237
|
| 1552 |
},
|
| 1553 |
{
|
| 1554 |
+
"epoch": 15.87,
|
| 1555 |
"learning_rate": 0.0002,
|
| 1556 |
+
"loss": 0.0087,
|
| 1557 |
"step": 238
|
| 1558 |
},
|
| 1559 |
{
|
| 1560 |
+
"epoch": 15.93,
|
| 1561 |
"learning_rate": 0.0002,
|
| 1562 |
+
"loss": 0.0063,
|
| 1563 |
"step": 239
|
| 1564 |
},
|
| 1565 |
{
|
| 1566 |
+
"epoch": 16.0,
|
| 1567 |
"learning_rate": 0.0002,
|
| 1568 |
+
"loss": 0.0013,
|
| 1569 |
+
"step": 240
|
| 1570 |
+
},
|
| 1571 |
+
{
|
| 1572 |
+
"epoch": 16.0,
|
| 1573 |
+
"eval_loss": 0.0023235378321260214,
|
| 1574 |
+
"eval_runtime": 41.291,
|
| 1575 |
+
"eval_samples_per_second": 10.947,
|
| 1576 |
+
"eval_steps_per_second": 0.363,
|
| 1577 |
"step": 240
|
| 1578 |
},
|
| 1579 |
{
|
| 1580 |
+
"epoch": 16.07,
|
| 1581 |
"learning_rate": 0.0002,
|
| 1582 |
+
"loss": 0.0019,
|
| 1583 |
"step": 241
|
| 1584 |
},
|
| 1585 |
{
|
| 1586 |
+
"epoch": 16.13,
|
| 1587 |
"learning_rate": 0.0002,
|
| 1588 |
+
"loss": 0.0019,
|
| 1589 |
"step": 242
|
| 1590 |
},
|
| 1591 |
{
|
| 1592 |
+
"epoch": 16.2,
|
| 1593 |
"learning_rate": 0.0002,
|
| 1594 |
+
"loss": 0.0006,
|
| 1595 |
"step": 243
|
| 1596 |
},
|
| 1597 |
{
|
| 1598 |
+
"epoch": 16.27,
|
| 1599 |
"learning_rate": 0.0002,
|
| 1600 |
+
"loss": 0.0021,
|
| 1601 |
"step": 244
|
| 1602 |
},
|
| 1603 |
{
|
| 1604 |
+
"epoch": 16.33,
|
| 1605 |
"learning_rate": 0.0002,
|
| 1606 |
+
"loss": 0.0043,
|
| 1607 |
"step": 245
|
| 1608 |
},
|
| 1609 |
{
|
| 1610 |
+
"epoch": 16.4,
|
| 1611 |
"learning_rate": 0.0002,
|
| 1612 |
+
"loss": 0.0015,
|
| 1613 |
"step": 246
|
| 1614 |
},
|
| 1615 |
{
|
| 1616 |
+
"epoch": 16.47,
|
| 1617 |
"learning_rate": 0.0002,
|
| 1618 |
+
"loss": 0.0027,
|
| 1619 |
"step": 247
|
| 1620 |
},
|
| 1621 |
{
|
| 1622 |
+
"epoch": 16.53,
|
| 1623 |
"learning_rate": 0.0002,
|
| 1624 |
+
"loss": 0.0012,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1625 |
"step": 248
|
| 1626 |
},
|
| 1627 |
{
|
| 1628 |
+
"epoch": 16.6,
|
| 1629 |
"learning_rate": 0.0002,
|
| 1630 |
+
"loss": 0.0025,
|
| 1631 |
"step": 249
|
| 1632 |
},
|
| 1633 |
{
|
| 1634 |
+
"epoch": 16.67,
|
| 1635 |
"learning_rate": 0.0002,
|
| 1636 |
+
"loss": 0.0016,
|
| 1637 |
"step": 250
|
| 1638 |
},
|
| 1639 |
{
|
| 1640 |
+
"epoch": 16.73,
|
| 1641 |
"learning_rate": 0.0002,
|
| 1642 |
+
"loss": 0.0039,
|
| 1643 |
"step": 251
|
| 1644 |
},
|
| 1645 |
{
|
| 1646 |
+
"epoch": 16.8,
|
| 1647 |
"learning_rate": 0.0002,
|
| 1648 |
+
"loss": 0.0034,
|
| 1649 |
"step": 252
|
| 1650 |
},
|
| 1651 |
{
|
| 1652 |
+
"epoch": 16.87,
|
| 1653 |
"learning_rate": 0.0002,
|
| 1654 |
+
"loss": 0.0046,
|
| 1655 |
"step": 253
|
| 1656 |
},
|
| 1657 |
{
|
| 1658 |
+
"epoch": 16.93,
|
| 1659 |
"learning_rate": 0.0002,
|
| 1660 |
+
"loss": 0.0036,
|
| 1661 |
"step": 254
|
| 1662 |
},
|
| 1663 |
{
|
| 1664 |
+
"epoch": 17.0,
|
| 1665 |
"learning_rate": 0.0002,
|
| 1666 |
+
"loss": 0.0024,
|
| 1667 |
+
"step": 255
|
| 1668 |
+
},
|
| 1669 |
+
{
|
| 1670 |
+
"epoch": 17.0,
|
| 1671 |
+
"eval_loss": 0.002285911003127694,
|
| 1672 |
+
"eval_runtime": 40.9147,
|
| 1673 |
+
"eval_samples_per_second": 11.047,
|
| 1674 |
+
"eval_steps_per_second": 0.367,
|
| 1675 |
"step": 255
|
| 1676 |
},
|
| 1677 |
{
|
| 1678 |
+
"epoch": 17.07,
|
| 1679 |
"learning_rate": 0.0002,
|
| 1680 |
+
"loss": 0.0007,
|
| 1681 |
"step": 256
|
| 1682 |
},
|
| 1683 |
{
|
| 1684 |
+
"epoch": 17.13,
|
| 1685 |
"learning_rate": 0.0002,
|
| 1686 |
+
"loss": 0.0025,
|
| 1687 |
"step": 257
|
| 1688 |
},
|
| 1689 |
{
|
| 1690 |
+
"epoch": 17.2,
|
| 1691 |
"learning_rate": 0.0002,
|
| 1692 |
+
"loss": 0.0026,
|
| 1693 |
"step": 258
|
| 1694 |
},
|
| 1695 |
{
|
| 1696 |
+
"epoch": 17.27,
|
| 1697 |
"learning_rate": 0.0002,
|
| 1698 |
+
"loss": 0.0036,
|
| 1699 |
"step": 259
|
| 1700 |
},
|
| 1701 |
{
|
| 1702 |
+
"epoch": 17.33,
|
| 1703 |
"learning_rate": 0.0002,
|
| 1704 |
+
"loss": 0.0031,
|
| 1705 |
"step": 260
|
| 1706 |
},
|
| 1707 |
{
|
| 1708 |
+
"epoch": 17.4,
|
| 1709 |
"learning_rate": 0.0002,
|
| 1710 |
+
"loss": 0.0021,
|
| 1711 |
"step": 261
|
| 1712 |
},
|
| 1713 |
{
|
| 1714 |
+
"epoch": 17.47,
|
| 1715 |
"learning_rate": 0.0002,
|
| 1716 |
+
"loss": 0.0019,
|
| 1717 |
"step": 262
|
| 1718 |
},
|
| 1719 |
{
|
| 1720 |
+
"epoch": 17.53,
|
| 1721 |
"learning_rate": 0.0002,
|
| 1722 |
+
"loss": 0.0028,
|
| 1723 |
"step": 263
|
| 1724 |
},
|
| 1725 |
{
|
| 1726 |
+
"epoch": 17.6,
|
| 1727 |
"learning_rate": 0.0002,
|
| 1728 |
+
"loss": 0.0051,
|
| 1729 |
"step": 264
|
| 1730 |
},
|
| 1731 |
{
|
| 1732 |
+
"epoch": 17.67,
|
| 1733 |
"learning_rate": 0.0002,
|
| 1734 |
+
"loss": 0.0033,
|
| 1735 |
"step": 265
|
| 1736 |
},
|
| 1737 |
{
|
| 1738 |
+
"epoch": 17.73,
|
| 1739 |
"learning_rate": 0.0002,
|
| 1740 |
+
"loss": 0.0033,
|
| 1741 |
"step": 266
|
| 1742 |
},
|
| 1743 |
{
|
| 1744 |
+
"epoch": 17.8,
|
| 1745 |
"learning_rate": 0.0002,
|
| 1746 |
+
"loss": 0.002,
|
| 1747 |
"step": 267
|
| 1748 |
},
|
| 1749 |
{
|
| 1750 |
+
"epoch": 17.87,
|
| 1751 |
"learning_rate": 0.0002,
|
| 1752 |
+
"loss": 0.0023,
|
| 1753 |
"step": 268
|
| 1754 |
},
|
| 1755 |
{
|
| 1756 |
+
"epoch": 17.93,
|
| 1757 |
"learning_rate": 0.0002,
|
| 1758 |
+
"loss": 0.001,
|
| 1759 |
"step": 269
|
| 1760 |
},
|
| 1761 |
{
|
| 1762 |
+
"epoch": 18.0,
|
| 1763 |
"learning_rate": 0.0002,
|
| 1764 |
+
"loss": 0.0008,
|
| 1765 |
+
"step": 270
|
| 1766 |
+
},
|
| 1767 |
+
{
|
| 1768 |
+
"epoch": 18.0,
|
| 1769 |
+
"eval_loss": 0.0021159963216632605,
|
| 1770 |
+
"eval_runtime": 41.0332,
|
| 1771 |
+
"eval_samples_per_second": 11.015,
|
| 1772 |
+
"eval_steps_per_second": 0.366,
|
| 1773 |
"step": 270
|
| 1774 |
},
|
| 1775 |
{
|
| 1776 |
+
"epoch": 18.07,
|
| 1777 |
"learning_rate": 0.0002,
|
| 1778 |
+
"loss": 0.0016,
|
| 1779 |
"step": 271
|
| 1780 |
},
|
| 1781 |
{
|
| 1782 |
+
"epoch": 18.13,
|
| 1783 |
"learning_rate": 0.0002,
|
| 1784 |
+
"loss": 0.0016,
|
| 1785 |
"step": 272
|
| 1786 |
},
|
| 1787 |
{
|
| 1788 |
+
"epoch": 18.2,
|
| 1789 |
"learning_rate": 0.0002,
|
| 1790 |
+
"loss": 0.0015,
|
| 1791 |
"step": 273
|
| 1792 |
},
|
| 1793 |
{
|
| 1794 |
+
"epoch": 18.27,
|
| 1795 |
"learning_rate": 0.0002,
|
| 1796 |
+
"loss": 0.0006,
|
| 1797 |
"step": 274
|
| 1798 |
},
|
| 1799 |
{
|
| 1800 |
+
"epoch": 18.33,
|
| 1801 |
"learning_rate": 0.0002,
|
| 1802 |
+
"loss": 0.0029,
|
| 1803 |
"step": 275
|
| 1804 |
},
|
| 1805 |
{
|
| 1806 |
+
"epoch": 18.4,
|
| 1807 |
"learning_rate": 0.0002,
|
| 1808 |
+
"loss": 0.0018,
|
| 1809 |
"step": 276
|
| 1810 |
},
|
| 1811 |
{
|
| 1812 |
+
"epoch": 18.47,
|
| 1813 |
"learning_rate": 0.0002,
|
| 1814 |
+
"loss": 0.0007,
|
| 1815 |
"step": 277
|
| 1816 |
},
|
| 1817 |
{
|
| 1818 |
+
"epoch": 18.53,
|
| 1819 |
"learning_rate": 0.0002,
|
| 1820 |
+
"loss": 0.0032,
|
| 1821 |
"step": 278
|
| 1822 |
},
|
| 1823 |
{
|
| 1824 |
+
"epoch": 18.6,
|
| 1825 |
"learning_rate": 0.0002,
|
| 1826 |
+
"loss": 0.0011,
|
| 1827 |
"step": 279
|
| 1828 |
},
|
| 1829 |
{
|
| 1830 |
+
"epoch": 18.67,
|
| 1831 |
+
"learning_rate": 0.0002,
|
| 1832 |
+
"loss": 0.0008,
|
| 1833 |
+
"step": 280
|
|
|
|
|
|
|
| 1834 |
},
|
| 1835 |
{
|
| 1836 |
+
"epoch": 18.73,
|
| 1837 |
"learning_rate": 0.0002,
|
| 1838 |
+
"loss": 0.0011,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1839 |
"step": 281
|
| 1840 |
},
|
| 1841 |
{
|
| 1842 |
+
"epoch": 18.8,
|
| 1843 |
"learning_rate": 0.0002,
|
| 1844 |
+
"loss": 0.0026,
|
| 1845 |
"step": 282
|
| 1846 |
},
|
| 1847 |
{
|
| 1848 |
+
"epoch": 18.87,
|
| 1849 |
"learning_rate": 0.0002,
|
| 1850 |
+
"loss": 0.0028,
|
| 1851 |
"step": 283
|
| 1852 |
},
|
| 1853 |
{
|
| 1854 |
+
"epoch": 18.93,
|
| 1855 |
"learning_rate": 0.0002,
|
| 1856 |
+
"loss": 0.002,
|
| 1857 |
"step": 284
|
| 1858 |
},
|
| 1859 |
{
|
| 1860 |
+
"epoch": 19.0,
|
| 1861 |
"learning_rate": 0.0002,
|
| 1862 |
+
"loss": 0.0025,
|
| 1863 |
+
"step": 285
|
| 1864 |
+
},
|
| 1865 |
+
{
|
| 1866 |
+
"epoch": 19.0,
|
| 1867 |
+
"eval_loss": 0.002144865458831191,
|
| 1868 |
+
"eval_runtime": 40.9486,
|
| 1869 |
+
"eval_samples_per_second": 11.038,
|
| 1870 |
+
"eval_steps_per_second": 0.366,
|
| 1871 |
"step": 285
|
| 1872 |
},
|
| 1873 |
{
|
| 1874 |
+
"epoch": 19.07,
|
| 1875 |
"learning_rate": 0.0002,
|
| 1876 |
+
"loss": 0.0005,
|
| 1877 |
"step": 286
|
| 1878 |
},
|
| 1879 |
{
|
| 1880 |
+
"epoch": 19.13,
|
| 1881 |
"learning_rate": 0.0002,
|
| 1882 |
+
"loss": 0.0028,
|
| 1883 |
"step": 287
|
| 1884 |
},
|
| 1885 |
{
|
| 1886 |
+
"epoch": 19.2,
|
| 1887 |
"learning_rate": 0.0002,
|
| 1888 |
+
"loss": 0.0022,
|
| 1889 |
"step": 288
|
| 1890 |
},
|
| 1891 |
{
|
| 1892 |
+
"epoch": 19.27,
|
| 1893 |
"learning_rate": 0.0002,
|
| 1894 |
+
"loss": 0.0007,
|
| 1895 |
"step": 289
|
| 1896 |
},
|
| 1897 |
{
|
| 1898 |
+
"epoch": 19.33,
|
| 1899 |
"learning_rate": 0.0002,
|
| 1900 |
+
"loss": 0.002,
|
| 1901 |
"step": 290
|
| 1902 |
},
|
| 1903 |
{
|
| 1904 |
+
"epoch": 19.4,
|
| 1905 |
"learning_rate": 0.0002,
|
| 1906 |
+
"loss": 0.0019,
|
| 1907 |
"step": 291
|
| 1908 |
},
|
| 1909 |
{
|
| 1910 |
+
"epoch": 19.47,
|
| 1911 |
"learning_rate": 0.0002,
|
| 1912 |
+
"loss": 0.0031,
|
| 1913 |
"step": 292
|
| 1914 |
},
|
| 1915 |
{
|
| 1916 |
+
"epoch": 19.53,
|
| 1917 |
"learning_rate": 0.0002,
|
| 1918 |
+
"loss": 0.0013,
|
| 1919 |
"step": 293
|
| 1920 |
},
|
| 1921 |
{
|
| 1922 |
+
"epoch": 19.6,
|
| 1923 |
"learning_rate": 0.0002,
|
| 1924 |
+
"loss": 0.0016,
|
| 1925 |
"step": 294
|
| 1926 |
},
|
| 1927 |
{
|
| 1928 |
+
"epoch": 19.67,
|
| 1929 |
"learning_rate": 0.0002,
|
| 1930 |
+
"loss": 0.0076,
|
| 1931 |
"step": 295
|
| 1932 |
},
|
| 1933 |
{
|
| 1934 |
+
"epoch": 19.73,
|
| 1935 |
"learning_rate": 0.0002,
|
| 1936 |
+
"loss": 0.0009,
|
| 1937 |
"step": 296
|
| 1938 |
},
|
| 1939 |
{
|
| 1940 |
+
"epoch": 19.8,
|
| 1941 |
"learning_rate": 0.0002,
|
| 1942 |
+
"loss": 0.0004,
|
| 1943 |
"step": 297
|
| 1944 |
},
|
| 1945 |
{
|
| 1946 |
+
"epoch": 19.87,
|
| 1947 |
"learning_rate": 0.0002,
|
| 1948 |
+
"loss": 0.0039,
|
| 1949 |
"step": 298
|
| 1950 |
},
|
| 1951 |
{
|
| 1952 |
+
"epoch": 19.93,
|
| 1953 |
"learning_rate": 0.0002,
|
| 1954 |
+
"loss": 0.0017,
|
| 1955 |
"step": 299
|
| 1956 |
},
|
| 1957 |
{
|
| 1958 |
+
"epoch": 20.0,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1959 |
"learning_rate": 0.0002,
|
| 1960 |
"loss": 0.0018,
|
| 1961 |
+
"step": 300
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1962 |
},
|
| 1963 |
{
|
| 1964 |
"epoch": 20.0,
|
| 1965 |
+
"eval_loss": 0.0014153169468045235,
|
| 1966 |
+
"eval_runtime": 41.0838,
|
| 1967 |
+
"eval_samples_per_second": 11.002,
|
| 1968 |
+
"eval_steps_per_second": 0.365,
|
| 1969 |
+
"step": 300
|
| 1970 |
},
|
| 1971 |
{
|
| 1972 |
"epoch": 20.0,
|
| 1973 |
+
"step": 300,
|
| 1974 |
+
"total_flos": 1.1369758627263939e+18,
|
| 1975 |
+
"train_loss": 0.062011325372974775,
|
| 1976 |
+
"train_runtime": 6370.9367,
|
| 1977 |
+
"train_samples_per_second": 1.419,
|
| 1978 |
+
"train_steps_per_second": 0.047
|
| 1979 |
}
|
| 1980 |
],
|
| 1981 |
"logging_steps": 1.0,
|
| 1982 |
+
"max_steps": 300,
|
| 1983 |
"num_input_tokens_seen": 0,
|
| 1984 |
"num_train_epochs": 20,
|
| 1985 |
"save_steps": 50000,
|
| 1986 |
+
"total_flos": 1.1369758627263939e+18,
|
| 1987 |
"train_batch_size": 4,
|
| 1988 |
"trial_name": null,
|
| 1989 |
"trial_params": null
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 6840
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:13a31b74c0a0e5235f89162d7a85b854f83db99409f5e9e9828384af833b44b4
|
| 3 |
size 6840
|