Commit
•
b3efbb1
1
Parent(s):
4b5241b
Training in progress, epoch 1
Browse files- .ipynb_checkpoints/README-checkpoint.md +82 -0
- .ipynb_checkpoints/all_results-checkpoint.json +8 -0
- .ipynb_checkpoints/config-checkpoint.json +74 -0
- .ipynb_checkpoints/train_results-checkpoint.json +8 -0
- .ipynb_checkpoints/trainer_state-checkpoint.json +499 -0
- all_results.json +8 -0
- pytorch_model.bin +1 -1
- runs/Mar13_15-46-49_pop-os/1678722500.0429041/events.out.tfevents.1678722500.pop-os.8344.1 +3 -0
- runs/Mar13_15-46-49_pop-os/events.out.tfevents.1678722499.pop-os.8344.0 +3 -0
- train_results.json +8 -0
- trainer_state.json +499 -0
- training_args.bin +1 -1
.ipynb_checkpoints/README-checkpoint.md
ADDED
|
@@ -0,0 +1,82 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
datasets:
|
| 6 |
+
- imagefolder
|
| 7 |
+
metrics:
|
| 8 |
+
- accuracy
|
| 9 |
+
model-index:
|
| 10 |
+
- name: weather-mod
|
| 11 |
+
results:
|
| 12 |
+
- task:
|
| 13 |
+
name: Image Classification
|
| 14 |
+
type: image-classification
|
| 15 |
+
dataset:
|
| 16 |
+
name: imagefolder
|
| 17 |
+
type: imagefolder
|
| 18 |
+
config: dataset
|
| 19 |
+
split: train
|
| 20 |
+
args: dataset
|
| 21 |
+
metrics:
|
| 22 |
+
- name: Accuracy
|
| 23 |
+
type: accuracy
|
| 24 |
+
value: 0.9426751592356688
|
| 25 |
+
---
|
| 26 |
+
|
| 27 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 28 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 29 |
+
|
| 30 |
+
# weather-mod
|
| 31 |
+
|
| 32 |
+
This model is a fine-tuned version of [microsoft/beit-base-patch16-224-pt22k-ft22k](https://huggingface.co/microsoft/beit-base-patch16-224-pt22k-ft22k) on the imagefolder dataset.
|
| 33 |
+
It achieves the following results on the evaluation set:
|
| 34 |
+
- Loss: 0.2331
|
| 35 |
+
- Accuracy: 0.9427
|
| 36 |
+
|
| 37 |
+
## Model description
|
| 38 |
+
|
| 39 |
+
More information needed
|
| 40 |
+
|
| 41 |
+
## Intended uses & limitations
|
| 42 |
+
|
| 43 |
+
More information needed
|
| 44 |
+
|
| 45 |
+
## Training and evaluation data
|
| 46 |
+
|
| 47 |
+
More information needed
|
| 48 |
+
|
| 49 |
+
## Training procedure
|
| 50 |
+
|
| 51 |
+
### Training hyperparameters
|
| 52 |
+
|
| 53 |
+
The following hyperparameters were used during training:
|
| 54 |
+
- learning_rate: 5e-05
|
| 55 |
+
- train_batch_size: 8
|
| 56 |
+
- eval_batch_size: 8
|
| 57 |
+
- seed: 42
|
| 58 |
+
- gradient_accumulation_steps: 4
|
| 59 |
+
- total_train_batch_size: 32
|
| 60 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 61 |
+
- lr_scheduler_type: linear
|
| 62 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 63 |
+
- num_epochs: 6
|
| 64 |
+
|
| 65 |
+
### Training results
|
| 66 |
+
|
| 67 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 68 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
| 69 |
+
| 0.1517 | 1.0 | 118 | 0.2654 | 0.9151 |
|
| 70 |
+
| 0.1627 | 2.0 | 236 | 0.2255 | 0.9321 |
|
| 71 |
+
| 0.1071 | 3.0 | 354 | 0.2734 | 0.9342 |
|
| 72 |
+
| 0.0757 | 4.0 | 472 | 0.2343 | 0.9448 |
|
| 73 |
+
| 0.059 | 5.0 | 590 | 0.2578 | 0.9384 |
|
| 74 |
+
| 0.0266 | 6.0 | 708 | 0.2331 | 0.9427 |
|
| 75 |
+
|
| 76 |
+
|
| 77 |
+
### Framework versions
|
| 78 |
+
|
| 79 |
+
- Transformers 4.26.1
|
| 80 |
+
- Pytorch 1.13.1+cu116
|
| 81 |
+
- Datasets 2.10.1
|
| 82 |
+
- Tokenizers 0.13.2
|
.ipynb_checkpoints/all_results-checkpoint.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 6.0,
|
| 3 |
+
"total_flos": 1.7589230025365053e+18,
|
| 4 |
+
"train_loss": 0.10344488720941004,
|
| 5 |
+
"train_runtime": 2153.5363,
|
| 6 |
+
"train_samples_per_second": 10.506,
|
| 7 |
+
"train_steps_per_second": 0.329
|
| 8 |
+
}
|
.ipynb_checkpoints/config-checkpoint.json
ADDED
|
@@ -0,0 +1,74 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "microsoft/beit-base-patch16-224-pt22k-ft22k",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"BeitForImageClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.0,
|
| 7 |
+
"auxiliary_channels": 256,
|
| 8 |
+
"auxiliary_concat_input": false,
|
| 9 |
+
"auxiliary_loss_weight": 0.4,
|
| 10 |
+
"auxiliary_num_convs": 1,
|
| 11 |
+
"drop_path_rate": 0.1,
|
| 12 |
+
"hidden_act": "gelu",
|
| 13 |
+
"hidden_dropout_prob": 0.0,
|
| 14 |
+
"hidden_size": 768,
|
| 15 |
+
"id2label": {
|
| 16 |
+
"0": "dew",
|
| 17 |
+
"1": "fogsmog",
|
| 18 |
+
"2": "frost",
|
| 19 |
+
"3": "glaze",
|
| 20 |
+
"4": "hail",
|
| 21 |
+
"5": "lightning",
|
| 22 |
+
"6": "rain",
|
| 23 |
+
"7": "rainbow",
|
| 24 |
+
"8": "rime",
|
| 25 |
+
"9": "sandstorm",
|
| 26 |
+
"10": "snow"
|
| 27 |
+
},
|
| 28 |
+
"image_size": 224,
|
| 29 |
+
"initializer_range": 0.02,
|
| 30 |
+
"intermediate_size": 3072,
|
| 31 |
+
"label2id": {
|
| 32 |
+
"dew": 0,
|
| 33 |
+
"fogsmog": 1,
|
| 34 |
+
"frost": 2,
|
| 35 |
+
"glaze": 3,
|
| 36 |
+
"hail": 4,
|
| 37 |
+
"lightning": 5,
|
| 38 |
+
"rain": 6,
|
| 39 |
+
"rainbow": 7,
|
| 40 |
+
"rime": 8,
|
| 41 |
+
"sandstorm": 9,
|
| 42 |
+
"snow": 10
|
| 43 |
+
},
|
| 44 |
+
"layer_norm_eps": 1e-12,
|
| 45 |
+
"layer_scale_init_value": 0.1,
|
| 46 |
+
"model_type": "beit",
|
| 47 |
+
"num_attention_heads": 12,
|
| 48 |
+
"num_channels": 3,
|
| 49 |
+
"num_hidden_layers": 12,
|
| 50 |
+
"out_indices": [
|
| 51 |
+
3,
|
| 52 |
+
5,
|
| 53 |
+
7,
|
| 54 |
+
11
|
| 55 |
+
],
|
| 56 |
+
"patch_size": 16,
|
| 57 |
+
"pool_scales": [
|
| 58 |
+
1,
|
| 59 |
+
2,
|
| 60 |
+
3,
|
| 61 |
+
6
|
| 62 |
+
],
|
| 63 |
+
"problem_type": "single_label_classification",
|
| 64 |
+
"semantic_loss_ignore_index": 255,
|
| 65 |
+
"torch_dtype": "float32",
|
| 66 |
+
"transformers_version": "4.26.1",
|
| 67 |
+
"use_absolute_position_embeddings": false,
|
| 68 |
+
"use_auxiliary_head": true,
|
| 69 |
+
"use_mask_token": false,
|
| 70 |
+
"use_mean_pooling": true,
|
| 71 |
+
"use_relative_position_bias": true,
|
| 72 |
+
"use_shared_relative_position_bias": false,
|
| 73 |
+
"vocab_size": 8192
|
| 74 |
+
}
|
.ipynb_checkpoints/train_results-checkpoint.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 6.0,
|
| 3 |
+
"total_flos": 1.7589230025365053e+18,
|
| 4 |
+
"train_loss": 0.10344488720941004,
|
| 5 |
+
"train_runtime": 2153.5363,
|
| 6 |
+
"train_samples_per_second": 10.506,
|
| 7 |
+
"train_steps_per_second": 0.329
|
| 8 |
+
}
|
.ipynb_checkpoints/trainer_state-checkpoint.json
ADDED
|
@@ -0,0 +1,499 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.9447983014861996,
|
| 3 |
+
"best_model_checkpoint": "./weather-mod/checkpoint-472",
|
| 4 |
+
"epoch": 6.0,
|
| 5 |
+
"global_step": 708,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.08,
|
| 12 |
+
"learning_rate": 1.5492957746478872e-05,
|
| 13 |
+
"loss": 0.179,
|
| 14 |
+
"step": 10
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.17,
|
| 18 |
+
"learning_rate": 2.2535211267605634e-05,
|
| 19 |
+
"loss": 0.1308,
|
| 20 |
+
"step": 20
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.25,
|
| 24 |
+
"learning_rate": 2.9577464788732395e-05,
|
| 25 |
+
"loss": 0.1013,
|
| 26 |
+
"step": 30
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.34,
|
| 30 |
+
"learning_rate": 3.661971830985916e-05,
|
| 31 |
+
"loss": 0.1276,
|
| 32 |
+
"step": 40
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.42,
|
| 36 |
+
"learning_rate": 4.366197183098591e-05,
|
| 37 |
+
"loss": 0.1344,
|
| 38 |
+
"step": 50
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.51,
|
| 42 |
+
"learning_rate": 4.992150706436421e-05,
|
| 43 |
+
"loss": 0.1502,
|
| 44 |
+
"step": 60
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.59,
|
| 48 |
+
"learning_rate": 4.913657770800628e-05,
|
| 49 |
+
"loss": 0.1448,
|
| 50 |
+
"step": 70
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.68,
|
| 54 |
+
"learning_rate": 4.8351648351648355e-05,
|
| 55 |
+
"loss": 0.1864,
|
| 56 |
+
"step": 80
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.76,
|
| 60 |
+
"learning_rate": 4.756671899529043e-05,
|
| 61 |
+
"loss": 0.2092,
|
| 62 |
+
"step": 90
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.85,
|
| 66 |
+
"learning_rate": 4.67817896389325e-05,
|
| 67 |
+
"loss": 0.2008,
|
| 68 |
+
"step": 100
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.93,
|
| 72 |
+
"learning_rate": 4.599686028257457e-05,
|
| 73 |
+
"loss": 0.1517,
|
| 74 |
+
"step": 110
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 1.0,
|
| 78 |
+
"eval_accuracy": 0.9150743099787686,
|
| 79 |
+
"eval_loss": 0.26539650559425354,
|
| 80 |
+
"eval_runtime": 14.9714,
|
| 81 |
+
"eval_samples_per_second": 31.46,
|
| 82 |
+
"eval_steps_per_second": 3.941,
|
| 83 |
+
"step": 118
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"epoch": 1.02,
|
| 87 |
+
"learning_rate": 4.5211930926216645e-05,
|
| 88 |
+
"loss": 0.145,
|
| 89 |
+
"step": 120
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 1.1,
|
| 93 |
+
"learning_rate": 4.442700156985872e-05,
|
| 94 |
+
"loss": 0.1558,
|
| 95 |
+
"step": 130
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 1.19,
|
| 99 |
+
"learning_rate": 4.364207221350079e-05,
|
| 100 |
+
"loss": 0.1556,
|
| 101 |
+
"step": 140
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 1.27,
|
| 105 |
+
"learning_rate": 4.2857142857142856e-05,
|
| 106 |
+
"loss": 0.1194,
|
| 107 |
+
"step": 150
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 1.36,
|
| 111 |
+
"learning_rate": 4.207221350078493e-05,
|
| 112 |
+
"loss": 0.1738,
|
| 113 |
+
"step": 160
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 1.44,
|
| 117 |
+
"learning_rate": 4.1287284144427e-05,
|
| 118 |
+
"loss": 0.1495,
|
| 119 |
+
"step": 170
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 1.53,
|
| 123 |
+
"learning_rate": 4.0502354788069074e-05,
|
| 124 |
+
"loss": 0.1603,
|
| 125 |
+
"step": 180
|
| 126 |
+
},
|
| 127 |
+
{
|
| 128 |
+
"epoch": 1.61,
|
| 129 |
+
"learning_rate": 3.971742543171115e-05,
|
| 130 |
+
"loss": 0.1494,
|
| 131 |
+
"step": 190
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 1.69,
|
| 135 |
+
"learning_rate": 3.893249607535322e-05,
|
| 136 |
+
"loss": 0.1469,
|
| 137 |
+
"step": 200
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 1.78,
|
| 141 |
+
"learning_rate": 3.814756671899529e-05,
|
| 142 |
+
"loss": 0.1922,
|
| 143 |
+
"step": 210
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 1.86,
|
| 147 |
+
"learning_rate": 3.7362637362637365e-05,
|
| 148 |
+
"loss": 0.1371,
|
| 149 |
+
"step": 220
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 1.95,
|
| 153 |
+
"learning_rate": 3.657770800627944e-05,
|
| 154 |
+
"loss": 0.1627,
|
| 155 |
+
"step": 230
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 2.0,
|
| 159 |
+
"eval_accuracy": 0.9320594479830149,
|
| 160 |
+
"eval_loss": 0.2255283147096634,
|
| 161 |
+
"eval_runtime": 34.5035,
|
| 162 |
+
"eval_samples_per_second": 13.651,
|
| 163 |
+
"eval_steps_per_second": 1.71,
|
| 164 |
+
"step": 236
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 2.03,
|
| 168 |
+
"learning_rate": 3.579277864992151e-05,
|
| 169 |
+
"loss": 0.2128,
|
| 170 |
+
"step": 240
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 2.12,
|
| 174 |
+
"learning_rate": 3.500784929356358e-05,
|
| 175 |
+
"loss": 0.0869,
|
| 176 |
+
"step": 250
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 2.2,
|
| 180 |
+
"learning_rate": 3.4222919937205655e-05,
|
| 181 |
+
"loss": 0.1261,
|
| 182 |
+
"step": 260
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 2.29,
|
| 186 |
+
"learning_rate": 3.343799058084773e-05,
|
| 187 |
+
"loss": 0.1104,
|
| 188 |
+
"step": 270
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 2.37,
|
| 192 |
+
"learning_rate": 3.265306122448979e-05,
|
| 193 |
+
"loss": 0.1111,
|
| 194 |
+
"step": 280
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 2.46,
|
| 198 |
+
"learning_rate": 3.1868131868131866e-05,
|
| 199 |
+
"loss": 0.0662,
|
| 200 |
+
"step": 290
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 2.54,
|
| 204 |
+
"learning_rate": 3.108320251177394e-05,
|
| 205 |
+
"loss": 0.1436,
|
| 206 |
+
"step": 300
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 2.63,
|
| 210 |
+
"learning_rate": 3.029827315541601e-05,
|
| 211 |
+
"loss": 0.1594,
|
| 212 |
+
"step": 310
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 2.71,
|
| 216 |
+
"learning_rate": 2.9513343799058084e-05,
|
| 217 |
+
"loss": 0.105,
|
| 218 |
+
"step": 320
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 2.8,
|
| 222 |
+
"learning_rate": 2.8728414442700156e-05,
|
| 223 |
+
"loss": 0.063,
|
| 224 |
+
"step": 330
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 2.88,
|
| 228 |
+
"learning_rate": 2.794348508634223e-05,
|
| 229 |
+
"loss": 0.104,
|
| 230 |
+
"step": 340
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 2.97,
|
| 234 |
+
"learning_rate": 2.71585557299843e-05,
|
| 235 |
+
"loss": 0.1071,
|
| 236 |
+
"step": 350
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 3.0,
|
| 240 |
+
"eval_accuracy": 0.9341825902335457,
|
| 241 |
+
"eval_loss": 0.2734454274177551,
|
| 242 |
+
"eval_runtime": 34.3105,
|
| 243 |
+
"eval_samples_per_second": 13.728,
|
| 244 |
+
"eval_steps_per_second": 1.72,
|
| 245 |
+
"step": 354
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 3.05,
|
| 249 |
+
"learning_rate": 2.6373626373626374e-05,
|
| 250 |
+
"loss": 0.0874,
|
| 251 |
+
"step": 360
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 3.14,
|
| 255 |
+
"learning_rate": 2.5588697017268447e-05,
|
| 256 |
+
"loss": 0.1084,
|
| 257 |
+
"step": 370
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 3.22,
|
| 261 |
+
"learning_rate": 2.480376766091052e-05,
|
| 262 |
+
"loss": 0.0758,
|
| 263 |
+
"step": 380
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 3.31,
|
| 267 |
+
"learning_rate": 2.4018838304552592e-05,
|
| 268 |
+
"loss": 0.0895,
|
| 269 |
+
"step": 390
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 3.39,
|
| 273 |
+
"learning_rate": 2.3233908948194665e-05,
|
| 274 |
+
"loss": 0.0998,
|
| 275 |
+
"step": 400
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 3.47,
|
| 279 |
+
"learning_rate": 2.2448979591836737e-05,
|
| 280 |
+
"loss": 0.0797,
|
| 281 |
+
"step": 410
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 3.56,
|
| 285 |
+
"learning_rate": 2.166405023547881e-05,
|
| 286 |
+
"loss": 0.0318,
|
| 287 |
+
"step": 420
|
| 288 |
+
},
|
| 289 |
+
{
|
| 290 |
+
"epoch": 3.64,
|
| 291 |
+
"learning_rate": 2.0879120879120882e-05,
|
| 292 |
+
"loss": 0.0744,
|
| 293 |
+
"step": 430
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 3.73,
|
| 297 |
+
"learning_rate": 2.0094191522762955e-05,
|
| 298 |
+
"loss": 0.0453,
|
| 299 |
+
"step": 440
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 3.81,
|
| 303 |
+
"learning_rate": 1.9309262166405024e-05,
|
| 304 |
+
"loss": 0.1569,
|
| 305 |
+
"step": 450
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 3.9,
|
| 309 |
+
"learning_rate": 1.8524332810047097e-05,
|
| 310 |
+
"loss": 0.0866,
|
| 311 |
+
"step": 460
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 3.98,
|
| 315 |
+
"learning_rate": 1.773940345368917e-05,
|
| 316 |
+
"loss": 0.0757,
|
| 317 |
+
"step": 470
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 4.0,
|
| 321 |
+
"eval_accuracy": 0.9447983014861996,
|
| 322 |
+
"eval_loss": 0.23432743549346924,
|
| 323 |
+
"eval_runtime": 35.6046,
|
| 324 |
+
"eval_samples_per_second": 13.229,
|
| 325 |
+
"eval_steps_per_second": 1.657,
|
| 326 |
+
"step": 472
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 4.07,
|
| 330 |
+
"learning_rate": 1.6954474097331242e-05,
|
| 331 |
+
"loss": 0.0881,
|
| 332 |
+
"step": 480
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 4.15,
|
| 336 |
+
"learning_rate": 1.6169544740973315e-05,
|
| 337 |
+
"loss": 0.0385,
|
| 338 |
+
"step": 490
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 4.24,
|
| 342 |
+
"learning_rate": 1.5384615384615387e-05,
|
| 343 |
+
"loss": 0.0238,
|
| 344 |
+
"step": 500
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 4.32,
|
| 348 |
+
"learning_rate": 1.4599686028257458e-05,
|
| 349 |
+
"loss": 0.0733,
|
| 350 |
+
"step": 510
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 4.41,
|
| 354 |
+
"learning_rate": 1.3814756671899529e-05,
|
| 355 |
+
"loss": 0.1086,
|
| 356 |
+
"step": 520
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 4.49,
|
| 360 |
+
"learning_rate": 1.3029827315541602e-05,
|
| 361 |
+
"loss": 0.0896,
|
| 362 |
+
"step": 530
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 4.58,
|
| 366 |
+
"learning_rate": 1.2244897959183674e-05,
|
| 367 |
+
"loss": 0.0461,
|
| 368 |
+
"step": 540
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 4.66,
|
| 372 |
+
"learning_rate": 1.1459968602825747e-05,
|
| 373 |
+
"loss": 0.0427,
|
| 374 |
+
"step": 550
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 4.75,
|
| 378 |
+
"learning_rate": 1.067503924646782e-05,
|
| 379 |
+
"loss": 0.0634,
|
| 380 |
+
"step": 560
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 4.83,
|
| 384 |
+
"learning_rate": 9.89010989010989e-06,
|
| 385 |
+
"loss": 0.0591,
|
| 386 |
+
"step": 570
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 4.92,
|
| 390 |
+
"learning_rate": 9.105180533751963e-06,
|
| 391 |
+
"loss": 0.0816,
|
| 392 |
+
"step": 580
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 5.0,
|
| 396 |
+
"learning_rate": 8.320251177394036e-06,
|
| 397 |
+
"loss": 0.059,
|
| 398 |
+
"step": 590
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 5.0,
|
| 402 |
+
"eval_accuracy": 0.9384288747346072,
|
| 403 |
+
"eval_loss": 0.2577723562717438,
|
| 404 |
+
"eval_runtime": 13.3966,
|
| 405 |
+
"eval_samples_per_second": 35.158,
|
| 406 |
+
"eval_steps_per_second": 4.404,
|
| 407 |
+
"step": 590
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 5.08,
|
| 411 |
+
"learning_rate": 7.535321821036106e-06,
|
| 412 |
+
"loss": 0.0398,
|
| 413 |
+
"step": 600
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 5.17,
|
| 417 |
+
"learning_rate": 6.750392464678179e-06,
|
| 418 |
+
"loss": 0.0226,
|
| 419 |
+
"step": 610
|
| 420 |
+
},
|
| 421 |
+
{
|
| 422 |
+
"epoch": 5.25,
|
| 423 |
+
"learning_rate": 5.965463108320252e-06,
|
| 424 |
+
"loss": 0.0777,
|
| 425 |
+
"step": 620
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 5.34,
|
| 429 |
+
"learning_rate": 5.180533751962323e-06,
|
| 430 |
+
"loss": 0.1017,
|
| 431 |
+
"step": 630
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 5.42,
|
| 435 |
+
"learning_rate": 4.395604395604396e-06,
|
| 436 |
+
"loss": 0.0144,
|
| 437 |
+
"step": 640
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 5.51,
|
| 441 |
+
"learning_rate": 3.610675039246468e-06,
|
| 442 |
+
"loss": 0.0738,
|
| 443 |
+
"step": 650
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 5.59,
|
| 447 |
+
"learning_rate": 2.8257456828885403e-06,
|
| 448 |
+
"loss": 0.0168,
|
| 449 |
+
"step": 660
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 5.68,
|
| 453 |
+
"learning_rate": 2.040816326530612e-06,
|
| 454 |
+
"loss": 0.029,
|
| 455 |
+
"step": 670
|
| 456 |
+
},
|
| 457 |
+
{
|
| 458 |
+
"epoch": 5.76,
|
| 459 |
+
"learning_rate": 1.2558869701726847e-06,
|
| 460 |
+
"loss": 0.0407,
|
| 461 |
+
"step": 680
|
| 462 |
+
},
|
| 463 |
+
{
|
| 464 |
+
"epoch": 5.85,
|
| 465 |
+
"learning_rate": 4.7095761381475665e-07,
|
| 466 |
+
"loss": 0.1009,
|
| 467 |
+
"step": 690
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 5.93,
|
| 471 |
+
"learning_rate": 0.0,
|
| 472 |
+
"loss": 0.0266,
|
| 473 |
+
"step": 700
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 6.0,
|
| 477 |
+
"eval_accuracy": 0.9426751592356688,
|
| 478 |
+
"eval_loss": 0.23305891454219818,
|
| 479 |
+
"eval_runtime": 33.4701,
|
| 480 |
+
"eval_samples_per_second": 14.072,
|
| 481 |
+
"eval_steps_per_second": 1.763,
|
| 482 |
+
"step": 708
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 6.0,
|
| 486 |
+
"step": 708,
|
| 487 |
+
"total_flos": 1.7589230025365053e+18,
|
| 488 |
+
"train_loss": 0.10344488720941004,
|
| 489 |
+
"train_runtime": 2153.5363,
|
| 490 |
+
"train_samples_per_second": 10.506,
|
| 491 |
+
"train_steps_per_second": 0.329
|
| 492 |
+
}
|
| 493 |
+
],
|
| 494 |
+
"max_steps": 708,
|
| 495 |
+
"num_train_epochs": 6,
|
| 496 |
+
"total_flos": 1.7589230025365053e+18,
|
| 497 |
+
"trial_name": null,
|
| 498 |
+
"trial_params": null
|
| 499 |
+
}
|
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 6.0,
|
| 3 |
+
"total_flos": 1.7589230025365053e+18,
|
| 4 |
+
"train_loss": 0.10344488720941004,
|
| 5 |
+
"train_runtime": 2153.5363,
|
| 6 |
+
"train_samples_per_second": 10.506,
|
| 7 |
+
"train_steps_per_second": 0.329
|
| 8 |
+
}
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 346888057
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dad74a455081d04a37b78dcb7ce50f5386723243dffbedf397c041b3a1e3e8ad
|
| 3 |
size 346888057
|
runs/Mar13_15-46-49_pop-os/1678722500.0429041/events.out.tfevents.1678722500.pop-os.8344.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0295b1f35698ccaf1f3b3853365e14c4ae8f4c589173add56893ff052c42e73d
|
| 3 |
+
size 5701
|
runs/Mar13_15-46-49_pop-os/events.out.tfevents.1678722499.pop-os.8344.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4e7e13dd6ff2fa483c43e701f61fa39e3f249143dfc672afcea02ed36a6752f3
|
| 3 |
+
size 6732
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 6.0,
|
| 3 |
+
"total_flos": 1.7589230025365053e+18,
|
| 4 |
+
"train_loss": 0.10344488720941004,
|
| 5 |
+
"train_runtime": 2153.5363,
|
| 6 |
+
"train_samples_per_second": 10.506,
|
| 7 |
+
"train_steps_per_second": 0.329
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,499 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.9447983014861996,
|
| 3 |
+
"best_model_checkpoint": "./weather-mod/checkpoint-472",
|
| 4 |
+
"epoch": 6.0,
|
| 5 |
+
"global_step": 708,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.08,
|
| 12 |
+
"learning_rate": 1.5492957746478872e-05,
|
| 13 |
+
"loss": 0.179,
|
| 14 |
+
"step": 10
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.17,
|
| 18 |
+
"learning_rate": 2.2535211267605634e-05,
|
| 19 |
+
"loss": 0.1308,
|
| 20 |
+
"step": 20
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.25,
|
| 24 |
+
"learning_rate": 2.9577464788732395e-05,
|
| 25 |
+
"loss": 0.1013,
|
| 26 |
+
"step": 30
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.34,
|
| 30 |
+
"learning_rate": 3.661971830985916e-05,
|
| 31 |
+
"loss": 0.1276,
|
| 32 |
+
"step": 40
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.42,
|
| 36 |
+
"learning_rate": 4.366197183098591e-05,
|
| 37 |
+
"loss": 0.1344,
|
| 38 |
+
"step": 50
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.51,
|
| 42 |
+
"learning_rate": 4.992150706436421e-05,
|
| 43 |
+
"loss": 0.1502,
|
| 44 |
+
"step": 60
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.59,
|
| 48 |
+
"learning_rate": 4.913657770800628e-05,
|
| 49 |
+
"loss": 0.1448,
|
| 50 |
+
"step": 70
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.68,
|
| 54 |
+
"learning_rate": 4.8351648351648355e-05,
|
| 55 |
+
"loss": 0.1864,
|
| 56 |
+
"step": 80
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.76,
|
| 60 |
+
"learning_rate": 4.756671899529043e-05,
|
| 61 |
+
"loss": 0.2092,
|
| 62 |
+
"step": 90
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.85,
|
| 66 |
+
"learning_rate": 4.67817896389325e-05,
|
| 67 |
+
"loss": 0.2008,
|
| 68 |
+
"step": 100
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.93,
|
| 72 |
+
"learning_rate": 4.599686028257457e-05,
|
| 73 |
+
"loss": 0.1517,
|
| 74 |
+
"step": 110
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 1.0,
|
| 78 |
+
"eval_accuracy": 0.9150743099787686,
|
| 79 |
+
"eval_loss": 0.26539650559425354,
|
| 80 |
+
"eval_runtime": 14.9714,
|
| 81 |
+
"eval_samples_per_second": 31.46,
|
| 82 |
+
"eval_steps_per_second": 3.941,
|
| 83 |
+
"step": 118
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"epoch": 1.02,
|
| 87 |
+
"learning_rate": 4.5211930926216645e-05,
|
| 88 |
+
"loss": 0.145,
|
| 89 |
+
"step": 120
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 1.1,
|
| 93 |
+
"learning_rate": 4.442700156985872e-05,
|
| 94 |
+
"loss": 0.1558,
|
| 95 |
+
"step": 130
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 1.19,
|
| 99 |
+
"learning_rate": 4.364207221350079e-05,
|
| 100 |
+
"loss": 0.1556,
|
| 101 |
+
"step": 140
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 1.27,
|
| 105 |
+
"learning_rate": 4.2857142857142856e-05,
|
| 106 |
+
"loss": 0.1194,
|
| 107 |
+
"step": 150
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 1.36,
|
| 111 |
+
"learning_rate": 4.207221350078493e-05,
|
| 112 |
+
"loss": 0.1738,
|
| 113 |
+
"step": 160
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 1.44,
|
| 117 |
+
"learning_rate": 4.1287284144427e-05,
|
| 118 |
+
"loss": 0.1495,
|
| 119 |
+
"step": 170
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 1.53,
|
| 123 |
+
"learning_rate": 4.0502354788069074e-05,
|
| 124 |
+
"loss": 0.1603,
|
| 125 |
+
"step": 180
|
| 126 |
+
},
|
| 127 |
+
{
|
| 128 |
+
"epoch": 1.61,
|
| 129 |
+
"learning_rate": 3.971742543171115e-05,
|
| 130 |
+
"loss": 0.1494,
|
| 131 |
+
"step": 190
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 1.69,
|
| 135 |
+
"learning_rate": 3.893249607535322e-05,
|
| 136 |
+
"loss": 0.1469,
|
| 137 |
+
"step": 200
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 1.78,
|
| 141 |
+
"learning_rate": 3.814756671899529e-05,
|
| 142 |
+
"loss": 0.1922,
|
| 143 |
+
"step": 210
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 1.86,
|
| 147 |
+
"learning_rate": 3.7362637362637365e-05,
|
| 148 |
+
"loss": 0.1371,
|
| 149 |
+
"step": 220
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 1.95,
|
| 153 |
+
"learning_rate": 3.657770800627944e-05,
|
| 154 |
+
"loss": 0.1627,
|
| 155 |
+
"step": 230
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 2.0,
|
| 159 |
+
"eval_accuracy": 0.9320594479830149,
|
| 160 |
+
"eval_loss": 0.2255283147096634,
|
| 161 |
+
"eval_runtime": 34.5035,
|
| 162 |
+
"eval_samples_per_second": 13.651,
|
| 163 |
+
"eval_steps_per_second": 1.71,
|
| 164 |
+
"step": 236
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 2.03,
|
| 168 |
+
"learning_rate": 3.579277864992151e-05,
|
| 169 |
+
"loss": 0.2128,
|
| 170 |
+
"step": 240
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 2.12,
|
| 174 |
+
"learning_rate": 3.500784929356358e-05,
|
| 175 |
+
"loss": 0.0869,
|
| 176 |
+
"step": 250
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 2.2,
|
| 180 |
+
"learning_rate": 3.4222919937205655e-05,
|
| 181 |
+
"loss": 0.1261,
|
| 182 |
+
"step": 260
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 2.29,
|
| 186 |
+
"learning_rate": 3.343799058084773e-05,
|
| 187 |
+
"loss": 0.1104,
|
| 188 |
+
"step": 270
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 2.37,
|
| 192 |
+
"learning_rate": 3.265306122448979e-05,
|
| 193 |
+
"loss": 0.1111,
|
| 194 |
+
"step": 280
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 2.46,
|
| 198 |
+
"learning_rate": 3.1868131868131866e-05,
|
| 199 |
+
"loss": 0.0662,
|
| 200 |
+
"step": 290
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 2.54,
|
| 204 |
+
"learning_rate": 3.108320251177394e-05,
|
| 205 |
+
"loss": 0.1436,
|
| 206 |
+
"step": 300
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 2.63,
|
| 210 |
+
"learning_rate": 3.029827315541601e-05,
|
| 211 |
+
"loss": 0.1594,
|
| 212 |
+
"step": 310
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 2.71,
|
| 216 |
+
"learning_rate": 2.9513343799058084e-05,
|
| 217 |
+
"loss": 0.105,
|
| 218 |
+
"step": 320
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 2.8,
|
| 222 |
+
"learning_rate": 2.8728414442700156e-05,
|
| 223 |
+
"loss": 0.063,
|
| 224 |
+
"step": 330
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 2.88,
|
| 228 |
+
"learning_rate": 2.794348508634223e-05,
|
| 229 |
+
"loss": 0.104,
|
| 230 |
+
"step": 340
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 2.97,
|
| 234 |
+
"learning_rate": 2.71585557299843e-05,
|
| 235 |
+
"loss": 0.1071,
|
| 236 |
+
"step": 350
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 3.0,
|
| 240 |
+
"eval_accuracy": 0.9341825902335457,
|
| 241 |
+
"eval_loss": 0.2734454274177551,
|
| 242 |
+
"eval_runtime": 34.3105,
|
| 243 |
+
"eval_samples_per_second": 13.728,
|
| 244 |
+
"eval_steps_per_second": 1.72,
|
| 245 |
+
"step": 354
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 3.05,
|
| 249 |
+
"learning_rate": 2.6373626373626374e-05,
|
| 250 |
+
"loss": 0.0874,
|
| 251 |
+
"step": 360
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 3.14,
|
| 255 |
+
"learning_rate": 2.5588697017268447e-05,
|
| 256 |
+
"loss": 0.1084,
|
| 257 |
+
"step": 370
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 3.22,
|
| 261 |
+
"learning_rate": 2.480376766091052e-05,
|
| 262 |
+
"loss": 0.0758,
|
| 263 |
+
"step": 380
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 3.31,
|
| 267 |
+
"learning_rate": 2.4018838304552592e-05,
|
| 268 |
+
"loss": 0.0895,
|
| 269 |
+
"step": 390
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 3.39,
|
| 273 |
+
"learning_rate": 2.3233908948194665e-05,
|
| 274 |
+
"loss": 0.0998,
|
| 275 |
+
"step": 400
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 3.47,
|
| 279 |
+
"learning_rate": 2.2448979591836737e-05,
|
| 280 |
+
"loss": 0.0797,
|
| 281 |
+
"step": 410
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 3.56,
|
| 285 |
+
"learning_rate": 2.166405023547881e-05,
|
| 286 |
+
"loss": 0.0318,
|
| 287 |
+
"step": 420
|
| 288 |
+
},
|
| 289 |
+
{
|
| 290 |
+
"epoch": 3.64,
|
| 291 |
+
"learning_rate": 2.0879120879120882e-05,
|
| 292 |
+
"loss": 0.0744,
|
| 293 |
+
"step": 430
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 3.73,
|
| 297 |
+
"learning_rate": 2.0094191522762955e-05,
|
| 298 |
+
"loss": 0.0453,
|
| 299 |
+
"step": 440
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 3.81,
|
| 303 |
+
"learning_rate": 1.9309262166405024e-05,
|
| 304 |
+
"loss": 0.1569,
|
| 305 |
+
"step": 450
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 3.9,
|
| 309 |
+
"learning_rate": 1.8524332810047097e-05,
|
| 310 |
+
"loss": 0.0866,
|
| 311 |
+
"step": 460
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 3.98,
|
| 315 |
+
"learning_rate": 1.773940345368917e-05,
|
| 316 |
+
"loss": 0.0757,
|
| 317 |
+
"step": 470
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 4.0,
|
| 321 |
+
"eval_accuracy": 0.9447983014861996,
|
| 322 |
+
"eval_loss": 0.23432743549346924,
|
| 323 |
+
"eval_runtime": 35.6046,
|
| 324 |
+
"eval_samples_per_second": 13.229,
|
| 325 |
+
"eval_steps_per_second": 1.657,
|
| 326 |
+
"step": 472
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 4.07,
|
| 330 |
+
"learning_rate": 1.6954474097331242e-05,
|
| 331 |
+
"loss": 0.0881,
|
| 332 |
+
"step": 480
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 4.15,
|
| 336 |
+
"learning_rate": 1.6169544740973315e-05,
|
| 337 |
+
"loss": 0.0385,
|
| 338 |
+
"step": 490
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 4.24,
|
| 342 |
+
"learning_rate": 1.5384615384615387e-05,
|
| 343 |
+
"loss": 0.0238,
|
| 344 |
+
"step": 500
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 4.32,
|
| 348 |
+
"learning_rate": 1.4599686028257458e-05,
|
| 349 |
+
"loss": 0.0733,
|
| 350 |
+
"step": 510
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 4.41,
|
| 354 |
+
"learning_rate": 1.3814756671899529e-05,
|
| 355 |
+
"loss": 0.1086,
|
| 356 |
+
"step": 520
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 4.49,
|
| 360 |
+
"learning_rate": 1.3029827315541602e-05,
|
| 361 |
+
"loss": 0.0896,
|
| 362 |
+
"step": 530
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 4.58,
|
| 366 |
+
"learning_rate": 1.2244897959183674e-05,
|
| 367 |
+
"loss": 0.0461,
|
| 368 |
+
"step": 540
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 4.66,
|
| 372 |
+
"learning_rate": 1.1459968602825747e-05,
|
| 373 |
+
"loss": 0.0427,
|
| 374 |
+
"step": 550
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 4.75,
|
| 378 |
+
"learning_rate": 1.067503924646782e-05,
|
| 379 |
+
"loss": 0.0634,
|
| 380 |
+
"step": 560
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 4.83,
|
| 384 |
+
"learning_rate": 9.89010989010989e-06,
|
| 385 |
+
"loss": 0.0591,
|
| 386 |
+
"step": 570
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 4.92,
|
| 390 |
+
"learning_rate": 9.105180533751963e-06,
|
| 391 |
+
"loss": 0.0816,
|
| 392 |
+
"step": 580
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 5.0,
|
| 396 |
+
"learning_rate": 8.320251177394036e-06,
|
| 397 |
+
"loss": 0.059,
|
| 398 |
+
"step": 590
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 5.0,
|
| 402 |
+
"eval_accuracy": 0.9384288747346072,
|
| 403 |
+
"eval_loss": 0.2577723562717438,
|
| 404 |
+
"eval_runtime": 13.3966,
|
| 405 |
+
"eval_samples_per_second": 35.158,
|
| 406 |
+
"eval_steps_per_second": 4.404,
|
| 407 |
+
"step": 590
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 5.08,
|
| 411 |
+
"learning_rate": 7.535321821036106e-06,
|
| 412 |
+
"loss": 0.0398,
|
| 413 |
+
"step": 600
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 5.17,
|
| 417 |
+
"learning_rate": 6.750392464678179e-06,
|
| 418 |
+
"loss": 0.0226,
|
| 419 |
+
"step": 610
|
| 420 |
+
},
|
| 421 |
+
{
|
| 422 |
+
"epoch": 5.25,
|
| 423 |
+
"learning_rate": 5.965463108320252e-06,
|
| 424 |
+
"loss": 0.0777,
|
| 425 |
+
"step": 620
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 5.34,
|
| 429 |
+
"learning_rate": 5.180533751962323e-06,
|
| 430 |
+
"loss": 0.1017,
|
| 431 |
+
"step": 630
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 5.42,
|
| 435 |
+
"learning_rate": 4.395604395604396e-06,
|
| 436 |
+
"loss": 0.0144,
|
| 437 |
+
"step": 640
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 5.51,
|
| 441 |
+
"learning_rate": 3.610675039246468e-06,
|
| 442 |
+
"loss": 0.0738,
|
| 443 |
+
"step": 650
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 5.59,
|
| 447 |
+
"learning_rate": 2.8257456828885403e-06,
|
| 448 |
+
"loss": 0.0168,
|
| 449 |
+
"step": 660
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 5.68,
|
| 453 |
+
"learning_rate": 2.040816326530612e-06,
|
| 454 |
+
"loss": 0.029,
|
| 455 |
+
"step": 670
|
| 456 |
+
},
|
| 457 |
+
{
|
| 458 |
+
"epoch": 5.76,
|
| 459 |
+
"learning_rate": 1.2558869701726847e-06,
|
| 460 |
+
"loss": 0.0407,
|
| 461 |
+
"step": 680
|
| 462 |
+
},
|
| 463 |
+
{
|
| 464 |
+
"epoch": 5.85,
|
| 465 |
+
"learning_rate": 4.7095761381475665e-07,
|
| 466 |
+
"loss": 0.1009,
|
| 467 |
+
"step": 690
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 5.93,
|
| 471 |
+
"learning_rate": 0.0,
|
| 472 |
+
"loss": 0.0266,
|
| 473 |
+
"step": 700
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 6.0,
|
| 477 |
+
"eval_accuracy": 0.9426751592356688,
|
| 478 |
+
"eval_loss": 0.23305891454219818,
|
| 479 |
+
"eval_runtime": 33.4701,
|
| 480 |
+
"eval_samples_per_second": 14.072,
|
| 481 |
+
"eval_steps_per_second": 1.763,
|
| 482 |
+
"step": 708
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 6.0,
|
| 486 |
+
"step": 708,
|
| 487 |
+
"total_flos": 1.7589230025365053e+18,
|
| 488 |
+
"train_loss": 0.10344488720941004,
|
| 489 |
+
"train_runtime": 2153.5363,
|
| 490 |
+
"train_samples_per_second": 10.506,
|
| 491 |
+
"train_steps_per_second": 0.329
|
| 492 |
+
}
|
| 493 |
+
],
|
| 494 |
+
"max_steps": 708,
|
| 495 |
+
"num_train_epochs": 6,
|
| 496 |
+
"total_flos": 1.7589230025365053e+18,
|
| 497 |
+
"trial_name": null,
|
| 498 |
+
"trial_params": null
|
| 499 |
+
}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3515
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:08da4e18c479ad36fc4203e76ba6c0d1465c8208176b534a260353a8e82a76b4
|
| 3 |
size 3515
|