End of training
Browse files- README.md +44 -22
- backup_checkpoint-12000/config.json +75 -0
- backup_checkpoint-12000/generation_config.json +13 -0
- backup_checkpoint-12000/model.safetensors +3 -0
- backup_checkpoint-12000/optimizer.pt +3 -0
- backup_checkpoint-12000/rng_state.pth +3 -0
- backup_checkpoint-12000/scheduler.pt +3 -0
- backup_checkpoint-12000/trainer_state.json +939 -0
- backup_checkpoint-12000/training_args.bin +3 -0
- backup_checkpoint/config.json +75 -0
- backup_checkpoint/generation_config.json +13 -0
- backup_checkpoint/model.safetensors +3 -0
- backup_checkpoint/optimizer.pt +3 -0
- backup_checkpoint/rng_state.pth +3 -0
- backup_checkpoint/scheduler.pt +3 -0
- backup_checkpoint/trainer_state.json +749 -0
- backup_checkpoint/training_args.bin +3 -0
- config.json +1 -1
- model.safetensors +1 -1
- training_args.bin +1 -1
README.md
CHANGED
|
@@ -1,6 +1,4 @@
|
|
| 1 |
---
|
| 2 |
-
license: apache-2.0
|
| 3 |
-
base_model: facebook/bart-base
|
| 4 |
tags:
|
| 5 |
- generated_from_trainer
|
| 6 |
model-index:
|
|
@@ -13,9 +11,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 13 |
|
| 14 |
# bart_test_p2
|
| 15 |
|
| 16 |
-
This model
|
| 17 |
It achieves the following results on the evaluation set:
|
| 18 |
-
- Loss: 0.
|
| 19 |
|
| 20 |
## Model description
|
| 21 |
|
|
@@ -34,32 +32,56 @@ More information needed
|
|
| 34 |
### Training hyperparameters
|
| 35 |
|
| 36 |
The following hyperparameters were used during training:
|
| 37 |
-
- learning_rate:
|
| 38 |
- train_batch_size: 8
|
| 39 |
- eval_batch_size: 8
|
| 40 |
- seed: 42
|
| 41 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 42 |
- lr_scheduler_type: linear
|
| 43 |
-
- num_epochs:
|
| 44 |
|
| 45 |
### Training results
|
| 46 |
|
| 47 |
-
| Training Loss | Epoch | Step
|
| 48 |
-
|
| 49 |
-
| 0.
|
| 50 |
-
| 0.
|
| 51 |
-
| 0.
|
| 52 |
-
| 0.
|
| 53 |
-
| 0.
|
| 54 |
-
| 0.
|
| 55 |
-
| 0.
|
| 56 |
-
| 0.
|
| 57 |
-
| 0.
|
| 58 |
-
| 0.
|
| 59 |
-
| 0.
|
| 60 |
-
| 0.
|
| 61 |
-
| 0.
|
| 62 |
-
| 0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 63 |
|
| 64 |
|
| 65 |
### Framework versions
|
|
|
|
| 1 |
---
|
|
|
|
|
|
|
| 2 |
tags:
|
| 3 |
- generated_from_trainer
|
| 4 |
model-index:
|
|
|
|
| 11 |
|
| 12 |
# bart_test_p2
|
| 13 |
|
| 14 |
+
This model was trained from scratch on the None dataset.
|
| 15 |
It achieves the following results on the evaluation set:
|
| 16 |
+
- Loss: 0.0194
|
| 17 |
|
| 18 |
## Model description
|
| 19 |
|
|
|
|
| 32 |
### Training hyperparameters
|
| 33 |
|
| 34 |
The following hyperparameters were used during training:
|
| 35 |
+
- learning_rate: 1e-05
|
| 36 |
- train_batch_size: 8
|
| 37 |
- eval_batch_size: 8
|
| 38 |
- seed: 42
|
| 39 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 40 |
- lr_scheduler_type: linear
|
| 41 |
+
- num_epochs: 3
|
| 42 |
|
| 43 |
### Training results
|
| 44 |
|
| 45 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 46 |
+
|:-------------:|:-----:|:-----:|:---------------:|
|
| 47 |
+
| 0.0273 | 0.08 | 500 | 0.0224 |
|
| 48 |
+
| 0.0255 | 0.16 | 1000 | 0.0215 |
|
| 49 |
+
| 0.0245 | 0.24 | 1500 | 0.0213 |
|
| 50 |
+
| 0.0234 | 0.32 | 2000 | 0.0211 |
|
| 51 |
+
| 0.025 | 0.39 | 2500 | 0.0207 |
|
| 52 |
+
| 0.0243 | 0.47 | 3000 | 0.0208 |
|
| 53 |
+
| 0.0236 | 0.55 | 3500 | 0.0206 |
|
| 54 |
+
| 0.0246 | 0.63 | 4000 | 0.0204 |
|
| 55 |
+
| 0.0235 | 0.71 | 4500 | 0.0202 |
|
| 56 |
+
| 0.0231 | 0.79 | 5000 | 0.0203 |
|
| 57 |
+
| 0.0221 | 0.87 | 5500 | 0.0201 |
|
| 58 |
+
| 0.0239 | 0.95 | 6000 | 0.0199 |
|
| 59 |
+
| 0.0209 | 1.03 | 6500 | 0.0200 |
|
| 60 |
+
| 0.0193 | 1.1 | 7000 | 0.0198 |
|
| 61 |
+
| 0.0207 | 1.18 | 7500 | 0.0199 |
|
| 62 |
+
| 0.0189 | 1.26 | 8000 | 0.0201 |
|
| 63 |
+
| 0.0193 | 1.34 | 8500 | 0.0200 |
|
| 64 |
+
| 0.0186 | 1.42 | 9000 | 0.0197 |
|
| 65 |
+
| 0.0199 | 1.5 | 9500 | 0.0197 |
|
| 66 |
+
| 0.0207 | 1.58 | 10000 | 0.0195 |
|
| 67 |
+
| 0.0199 | 1.66 | 10500 | 0.0196 |
|
| 68 |
+
| 0.0188 | 1.74 | 11000 | 0.0195 |
|
| 69 |
+
| 0.0194 | 1.81 | 11500 | 0.0194 |
|
| 70 |
+
| 0.0201 | 1.89 | 12000 | 0.0195 |
|
| 71 |
+
| 0.0181 | 1.97 | 12500 | 0.0194 |
|
| 72 |
+
| 0.0177 | 2.05 | 13000 | 0.0194 |
|
| 73 |
+
| 0.0161 | 2.13 | 13500 | 0.0196 |
|
| 74 |
+
| 0.0172 | 2.21 | 14000 | 0.0195 |
|
| 75 |
+
| 0.0184 | 2.29 | 14500 | 0.0195 |
|
| 76 |
+
| 0.0168 | 2.37 | 15000 | 0.0195 |
|
| 77 |
+
| 0.0176 | 2.44 | 15500 | 0.0194 |
|
| 78 |
+
| 0.0177 | 2.52 | 16000 | 0.0194 |
|
| 79 |
+
| 0.0158 | 2.6 | 16500 | 0.0194 |
|
| 80 |
+
| 0.0177 | 2.68 | 17000 | 0.0193 |
|
| 81 |
+
| 0.0179 | 2.76 | 17500 | 0.0193 |
|
| 82 |
+
| 0.0167 | 2.84 | 18000 | 0.0194 |
|
| 83 |
+
| 0.0177 | 2.92 | 18500 | 0.0193 |
|
| 84 |
+
| 0.0171 | 3.0 | 19000 | 0.0194 |
|
| 85 |
|
| 86 |
|
| 87 |
### Framework versions
|
backup_checkpoint-12000/config.json
ADDED
|
@@ -0,0 +1,75 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "facebook/bart-base",
|
| 3 |
+
"activation_dropout": 0.1,
|
| 4 |
+
"activation_function": "gelu",
|
| 5 |
+
"add_bias_logits": false,
|
| 6 |
+
"add_final_layer_norm": false,
|
| 7 |
+
"architectures": [
|
| 8 |
+
"BartForConditionalGeneration"
|
| 9 |
+
],
|
| 10 |
+
"attention_dropout": 0.1,
|
| 11 |
+
"bos_token_id": 0,
|
| 12 |
+
"classif_dropout": 0.1,
|
| 13 |
+
"classifier_dropout": 0.0,
|
| 14 |
+
"d_model": 768,
|
| 15 |
+
"decoder_attention_heads": 12,
|
| 16 |
+
"decoder_ffn_dim": 3072,
|
| 17 |
+
"decoder_layerdrop": 0.0,
|
| 18 |
+
"decoder_layers": 6,
|
| 19 |
+
"decoder_start_token_id": 2,
|
| 20 |
+
"dropout": 0.1,
|
| 21 |
+
"early_stopping": true,
|
| 22 |
+
"encoder_attention_heads": 12,
|
| 23 |
+
"encoder_ffn_dim": 3072,
|
| 24 |
+
"encoder_layerdrop": 0.0,
|
| 25 |
+
"encoder_layers": 6,
|
| 26 |
+
"eos_token_id": 2,
|
| 27 |
+
"forced_bos_token_id": 0,
|
| 28 |
+
"forced_eos_token_id": 2,
|
| 29 |
+
"gradient_checkpointing": false,
|
| 30 |
+
"id2label": {
|
| 31 |
+
"0": "LABEL_0",
|
| 32 |
+
"1": "LABEL_1",
|
| 33 |
+
"2": "LABEL_2"
|
| 34 |
+
},
|
| 35 |
+
"init_std": 0.02,
|
| 36 |
+
"is_encoder_decoder": true,
|
| 37 |
+
"label2id": {
|
| 38 |
+
"LABEL_0": 0,
|
| 39 |
+
"LABEL_1": 1,
|
| 40 |
+
"LABEL_2": 2
|
| 41 |
+
},
|
| 42 |
+
"max_position_embeddings": 1024,
|
| 43 |
+
"model_type": "bart",
|
| 44 |
+
"no_repeat_ngram_size": 3,
|
| 45 |
+
"normalize_before": false,
|
| 46 |
+
"normalize_embedding": true,
|
| 47 |
+
"num_beams": 4,
|
| 48 |
+
"num_hidden_layers": 6,
|
| 49 |
+
"pad_token_id": 1,
|
| 50 |
+
"scale_embedding": false,
|
| 51 |
+
"task_specific_params": {
|
| 52 |
+
"summarization": {
|
| 53 |
+
"length_penalty": 1.0,
|
| 54 |
+
"max_length": 128,
|
| 55 |
+
"min_length": 12,
|
| 56 |
+
"num_beams": 4
|
| 57 |
+
},
|
| 58 |
+
"summarization_cnn": {
|
| 59 |
+
"length_penalty": 2.0,
|
| 60 |
+
"max_length": 142,
|
| 61 |
+
"min_length": 56,
|
| 62 |
+
"num_beams": 4
|
| 63 |
+
},
|
| 64 |
+
"summarization_xsum": {
|
| 65 |
+
"length_penalty": 1.0,
|
| 66 |
+
"max_length": 62,
|
| 67 |
+
"min_length": 11,
|
| 68 |
+
"num_beams": 6
|
| 69 |
+
}
|
| 70 |
+
},
|
| 71 |
+
"torch_dtype": "float32",
|
| 72 |
+
"transformers_version": "4.37.0.dev0",
|
| 73 |
+
"use_cache": true,
|
| 74 |
+
"vocab_size": 50265
|
| 75 |
+
}
|
backup_checkpoint-12000/generation_config.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 0,
|
| 4 |
+
"decoder_start_token_id": 2,
|
| 5 |
+
"early_stopping": true,
|
| 6 |
+
"eos_token_id": 2,
|
| 7 |
+
"forced_bos_token_id": 0,
|
| 8 |
+
"forced_eos_token_id": 2,
|
| 9 |
+
"no_repeat_ngram_size": 3,
|
| 10 |
+
"num_beams": 4,
|
| 11 |
+
"pad_token_id": 1,
|
| 12 |
+
"transformers_version": "4.37.0.dev0"
|
| 13 |
+
}
|
backup_checkpoint-12000/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b5990d57924b063382afa18e7f1e8a07e2208b81d4c47b82a69b18a27be4f3a0
|
| 3 |
+
size 557912620
|
backup_checkpoint-12000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:01995ea2be2ccd0fa68c02532530506f317d4b6e7c0734555d85d1b276da1a11
|
| 3 |
+
size 1115579898
|
backup_checkpoint-12000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ad3b281e73f1cb93b0cc5cffda813f0a4ed9d78ba586dc62adf279c06a2b7600
|
| 3 |
+
size 14244
|
backup_checkpoint-12000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:439eb315d94372a87edf0a17384904142733c05e44126c626d64f9d13dc8e1a9
|
| 3 |
+
size 1064
|
backup_checkpoint-12000/trainer_state.json
ADDED
|
@@ -0,0 +1,939 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.8927444794952681,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 12000,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.0,
|
| 13 |
+
"learning_rate": 9.999684542586752e-05,
|
| 14 |
+
"loss": 12.4787,
|
| 15 |
+
"step": 1
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.02,
|
| 19 |
+
"learning_rate": 9.96845425867508e-05,
|
| 20 |
+
"loss": 1.3146,
|
| 21 |
+
"step": 100
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.03,
|
| 25 |
+
"learning_rate": 9.936908517350158e-05,
|
| 26 |
+
"loss": 0.0928,
|
| 27 |
+
"step": 200
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.05,
|
| 31 |
+
"learning_rate": 9.905362776025237e-05,
|
| 32 |
+
"loss": 0.0903,
|
| 33 |
+
"step": 300
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.06,
|
| 37 |
+
"learning_rate": 9.873817034700316e-05,
|
| 38 |
+
"loss": 0.0675,
|
| 39 |
+
"step": 400
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.08,
|
| 43 |
+
"learning_rate": 9.842271293375394e-05,
|
| 44 |
+
"loss": 0.0744,
|
| 45 |
+
"step": 500
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.08,
|
| 49 |
+
"eval_loss": 0.06298290193080902,
|
| 50 |
+
"eval_runtime": 191.3725,
|
| 51 |
+
"eval_samples_per_second": 113.574,
|
| 52 |
+
"eval_steps_per_second": 14.197,
|
| 53 |
+
"step": 500
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 0.09,
|
| 57 |
+
"learning_rate": 9.810725552050474e-05,
|
| 58 |
+
"loss": 0.0682,
|
| 59 |
+
"step": 600
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.11,
|
| 63 |
+
"learning_rate": 9.779179810725552e-05,
|
| 64 |
+
"loss": 0.072,
|
| 65 |
+
"step": 700
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.13,
|
| 69 |
+
"learning_rate": 9.747634069400632e-05,
|
| 70 |
+
"loss": 0.0731,
|
| 71 |
+
"step": 800
|
| 72 |
+
},
|
| 73 |
+
{
|
| 74 |
+
"epoch": 0.14,
|
| 75 |
+
"learning_rate": 9.71608832807571e-05,
|
| 76 |
+
"loss": 0.0638,
|
| 77 |
+
"step": 900
|
| 78 |
+
},
|
| 79 |
+
{
|
| 80 |
+
"epoch": 0.16,
|
| 81 |
+
"learning_rate": 9.684542586750788e-05,
|
| 82 |
+
"loss": 0.062,
|
| 83 |
+
"step": 1000
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"epoch": 0.16,
|
| 87 |
+
"eval_loss": 0.056409742683172226,
|
| 88 |
+
"eval_runtime": 191.8919,
|
| 89 |
+
"eval_samples_per_second": 113.267,
|
| 90 |
+
"eval_steps_per_second": 14.159,
|
| 91 |
+
"step": 1000
|
| 92 |
+
},
|
| 93 |
+
{
|
| 94 |
+
"epoch": 0.17,
|
| 95 |
+
"learning_rate": 9.652996845425868e-05,
|
| 96 |
+
"loss": 0.0663,
|
| 97 |
+
"step": 1100
|
| 98 |
+
},
|
| 99 |
+
{
|
| 100 |
+
"epoch": 0.19,
|
| 101 |
+
"learning_rate": 9.621451104100947e-05,
|
| 102 |
+
"loss": 0.0598,
|
| 103 |
+
"step": 1200
|
| 104 |
+
},
|
| 105 |
+
{
|
| 106 |
+
"epoch": 0.21,
|
| 107 |
+
"learning_rate": 9.589905362776026e-05,
|
| 108 |
+
"loss": 0.0625,
|
| 109 |
+
"step": 1300
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 0.22,
|
| 113 |
+
"learning_rate": 9.558359621451105e-05,
|
| 114 |
+
"loss": 0.0673,
|
| 115 |
+
"step": 1400
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.24,
|
| 119 |
+
"learning_rate": 9.526813880126184e-05,
|
| 120 |
+
"loss": 0.0625,
|
| 121 |
+
"step": 1500
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.24,
|
| 125 |
+
"eval_loss": 0.05498537793755531,
|
| 126 |
+
"eval_runtime": 191.898,
|
| 127 |
+
"eval_samples_per_second": 113.263,
|
| 128 |
+
"eval_steps_per_second": 14.159,
|
| 129 |
+
"step": 1500
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.25,
|
| 133 |
+
"learning_rate": 9.495268138801262e-05,
|
| 134 |
+
"loss": 0.0606,
|
| 135 |
+
"step": 1600
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.27,
|
| 139 |
+
"learning_rate": 9.463722397476341e-05,
|
| 140 |
+
"loss": 0.0684,
|
| 141 |
+
"step": 1700
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 0.28,
|
| 145 |
+
"learning_rate": 9.43217665615142e-05,
|
| 146 |
+
"loss": 0.0607,
|
| 147 |
+
"step": 1800
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 0.3,
|
| 151 |
+
"learning_rate": 9.400630914826499e-05,
|
| 152 |
+
"loss": 0.0679,
|
| 153 |
+
"step": 1900
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 0.32,
|
| 157 |
+
"learning_rate": 9.369085173501577e-05,
|
| 158 |
+
"loss": 0.0633,
|
| 159 |
+
"step": 2000
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.32,
|
| 163 |
+
"eval_loss": 0.052233804017305374,
|
| 164 |
+
"eval_runtime": 191.8762,
|
| 165 |
+
"eval_samples_per_second": 113.276,
|
| 166 |
+
"eval_steps_per_second": 14.16,
|
| 167 |
+
"step": 2000
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 0.33,
|
| 171 |
+
"learning_rate": 9.337539432176656e-05,
|
| 172 |
+
"loss": 0.061,
|
| 173 |
+
"step": 2100
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 0.35,
|
| 177 |
+
"learning_rate": 9.305993690851735e-05,
|
| 178 |
+
"loss": 0.0715,
|
| 179 |
+
"step": 2200
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 0.36,
|
| 183 |
+
"learning_rate": 9.274447949526815e-05,
|
| 184 |
+
"loss": 0.0586,
|
| 185 |
+
"step": 2300
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.38,
|
| 189 |
+
"learning_rate": 9.242902208201893e-05,
|
| 190 |
+
"loss": 0.0581,
|
| 191 |
+
"step": 2400
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.39,
|
| 195 |
+
"learning_rate": 9.211356466876973e-05,
|
| 196 |
+
"loss": 0.0588,
|
| 197 |
+
"step": 2500
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 0.39,
|
| 201 |
+
"eval_loss": 0.05040860176086426,
|
| 202 |
+
"eval_runtime": 191.6049,
|
| 203 |
+
"eval_samples_per_second": 113.437,
|
| 204 |
+
"eval_steps_per_second": 14.18,
|
| 205 |
+
"step": 2500
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.41,
|
| 209 |
+
"learning_rate": 9.179810725552051e-05,
|
| 210 |
+
"loss": 0.0572,
|
| 211 |
+
"step": 2600
|
| 212 |
+
},
|
| 213 |
+
{
|
| 214 |
+
"epoch": 0.43,
|
| 215 |
+
"learning_rate": 9.148264984227129e-05,
|
| 216 |
+
"loss": 0.0555,
|
| 217 |
+
"step": 2700
|
| 218 |
+
},
|
| 219 |
+
{
|
| 220 |
+
"epoch": 0.44,
|
| 221 |
+
"learning_rate": 9.116719242902209e-05,
|
| 222 |
+
"loss": 0.0547,
|
| 223 |
+
"step": 2800
|
| 224 |
+
},
|
| 225 |
+
{
|
| 226 |
+
"epoch": 0.46,
|
| 227 |
+
"learning_rate": 9.085173501577287e-05,
|
| 228 |
+
"loss": 0.0596,
|
| 229 |
+
"step": 2900
|
| 230 |
+
},
|
| 231 |
+
{
|
| 232 |
+
"epoch": 0.47,
|
| 233 |
+
"learning_rate": 9.053627760252367e-05,
|
| 234 |
+
"loss": 0.0593,
|
| 235 |
+
"step": 3000
|
| 236 |
+
},
|
| 237 |
+
{
|
| 238 |
+
"epoch": 0.47,
|
| 239 |
+
"eval_loss": 0.04637610912322998,
|
| 240 |
+
"eval_runtime": 192.1829,
|
| 241 |
+
"eval_samples_per_second": 113.095,
|
| 242 |
+
"eval_steps_per_second": 14.138,
|
| 243 |
+
"step": 3000
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 0.49,
|
| 247 |
+
"learning_rate": 9.022082018927446e-05,
|
| 248 |
+
"loss": 0.0536,
|
| 249 |
+
"step": 3100
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 0.5,
|
| 253 |
+
"learning_rate": 8.990536277602523e-05,
|
| 254 |
+
"loss": 0.0506,
|
| 255 |
+
"step": 3200
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.52,
|
| 259 |
+
"learning_rate": 8.958990536277603e-05,
|
| 260 |
+
"loss": 0.0601,
|
| 261 |
+
"step": 3300
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.54,
|
| 265 |
+
"learning_rate": 8.927444794952682e-05,
|
| 266 |
+
"loss": 0.05,
|
| 267 |
+
"step": 3400
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 0.55,
|
| 271 |
+
"learning_rate": 8.89589905362776e-05,
|
| 272 |
+
"loss": 0.0492,
|
| 273 |
+
"step": 3500
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 0.55,
|
| 277 |
+
"eval_loss": 0.0455920547246933,
|
| 278 |
+
"eval_runtime": 192.0796,
|
| 279 |
+
"eval_samples_per_second": 113.156,
|
| 280 |
+
"eval_steps_per_second": 14.145,
|
| 281 |
+
"step": 3500
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 0.57,
|
| 285 |
+
"learning_rate": 8.86435331230284e-05,
|
| 286 |
+
"loss": 0.0547,
|
| 287 |
+
"step": 3600
|
| 288 |
+
},
|
| 289 |
+
{
|
| 290 |
+
"epoch": 0.58,
|
| 291 |
+
"learning_rate": 8.832807570977918e-05,
|
| 292 |
+
"loss": 0.0582,
|
| 293 |
+
"step": 3700
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 0.6,
|
| 297 |
+
"learning_rate": 8.801261829652997e-05,
|
| 298 |
+
"loss": 0.0535,
|
| 299 |
+
"step": 3800
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 0.62,
|
| 303 |
+
"learning_rate": 8.769716088328076e-05,
|
| 304 |
+
"loss": 0.0554,
|
| 305 |
+
"step": 3900
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 0.63,
|
| 309 |
+
"learning_rate": 8.738170347003154e-05,
|
| 310 |
+
"loss": 0.0506,
|
| 311 |
+
"step": 4000
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.63,
|
| 315 |
+
"eval_loss": 0.04419832304120064,
|
| 316 |
+
"eval_runtime": 192.193,
|
| 317 |
+
"eval_samples_per_second": 113.089,
|
| 318 |
+
"eval_steps_per_second": 14.137,
|
| 319 |
+
"step": 4000
|
| 320 |
+
},
|
| 321 |
+
{
|
| 322 |
+
"epoch": 0.65,
|
| 323 |
+
"learning_rate": 8.706624605678234e-05,
|
| 324 |
+
"loss": 0.0508,
|
| 325 |
+
"step": 4100
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.66,
|
| 329 |
+
"learning_rate": 8.675078864353314e-05,
|
| 330 |
+
"loss": 0.0566,
|
| 331 |
+
"step": 4200
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.68,
|
| 335 |
+
"learning_rate": 8.64353312302839e-05,
|
| 336 |
+
"loss": 0.0556,
|
| 337 |
+
"step": 4300
|
| 338 |
+
},
|
| 339 |
+
{
|
| 340 |
+
"epoch": 0.69,
|
| 341 |
+
"learning_rate": 8.61198738170347e-05,
|
| 342 |
+
"loss": 0.0595,
|
| 343 |
+
"step": 4400
|
| 344 |
+
},
|
| 345 |
+
{
|
| 346 |
+
"epoch": 0.71,
|
| 347 |
+
"learning_rate": 8.58044164037855e-05,
|
| 348 |
+
"loss": 0.0584,
|
| 349 |
+
"step": 4500
|
| 350 |
+
},
|
| 351 |
+
{
|
| 352 |
+
"epoch": 0.71,
|
| 353 |
+
"eval_loss": 0.043363627046346664,
|
| 354 |
+
"eval_runtime": 191.6803,
|
| 355 |
+
"eval_samples_per_second": 113.392,
|
| 356 |
+
"eval_steps_per_second": 14.175,
|
| 357 |
+
"step": 4500
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 0.73,
|
| 361 |
+
"learning_rate": 8.548895899053628e-05,
|
| 362 |
+
"loss": 0.0546,
|
| 363 |
+
"step": 4600
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 0.74,
|
| 367 |
+
"learning_rate": 8.517350157728708e-05,
|
| 368 |
+
"loss": 0.0457,
|
| 369 |
+
"step": 4700
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 0.76,
|
| 373 |
+
"learning_rate": 8.485804416403787e-05,
|
| 374 |
+
"loss": 0.0531,
|
| 375 |
+
"step": 4800
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 0.77,
|
| 379 |
+
"learning_rate": 8.454258675078864e-05,
|
| 380 |
+
"loss": 0.0506,
|
| 381 |
+
"step": 4900
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.79,
|
| 385 |
+
"learning_rate": 8.422712933753944e-05,
|
| 386 |
+
"loss": 0.0455,
|
| 387 |
+
"step": 5000
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.79,
|
| 391 |
+
"eval_loss": 0.04175921157002449,
|
| 392 |
+
"eval_runtime": 192.0012,
|
| 393 |
+
"eval_samples_per_second": 113.202,
|
| 394 |
+
"eval_steps_per_second": 14.151,
|
| 395 |
+
"step": 5000
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.8,
|
| 399 |
+
"learning_rate": 8.391167192429022e-05,
|
| 400 |
+
"loss": 0.053,
|
| 401 |
+
"step": 5100
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.82,
|
| 405 |
+
"learning_rate": 8.359621451104101e-05,
|
| 406 |
+
"loss": 0.0499,
|
| 407 |
+
"step": 5200
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 0.84,
|
| 411 |
+
"learning_rate": 8.328075709779181e-05,
|
| 412 |
+
"loss": 0.0407,
|
| 413 |
+
"step": 5300
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 0.85,
|
| 417 |
+
"learning_rate": 8.296529968454258e-05,
|
| 418 |
+
"loss": 0.0559,
|
| 419 |
+
"step": 5400
|
| 420 |
+
},
|
| 421 |
+
{
|
| 422 |
+
"epoch": 0.87,
|
| 423 |
+
"learning_rate": 8.264984227129337e-05,
|
| 424 |
+
"loss": 0.0477,
|
| 425 |
+
"step": 5500
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 0.87,
|
| 429 |
+
"eval_loss": 0.042047169059515,
|
| 430 |
+
"eval_runtime": 192.1,
|
| 431 |
+
"eval_samples_per_second": 113.144,
|
| 432 |
+
"eval_steps_per_second": 14.144,
|
| 433 |
+
"step": 5500
|
| 434 |
+
},
|
| 435 |
+
{
|
| 436 |
+
"epoch": 0.88,
|
| 437 |
+
"learning_rate": 8.233438485804417e-05,
|
| 438 |
+
"loss": 0.0488,
|
| 439 |
+
"step": 5600
|
| 440 |
+
},
|
| 441 |
+
{
|
| 442 |
+
"epoch": 0.9,
|
| 443 |
+
"learning_rate": 8.201892744479495e-05,
|
| 444 |
+
"loss": 0.0537,
|
| 445 |
+
"step": 5700
|
| 446 |
+
},
|
| 447 |
+
{
|
| 448 |
+
"epoch": 0.91,
|
| 449 |
+
"learning_rate": 8.170347003154575e-05,
|
| 450 |
+
"loss": 0.0515,
|
| 451 |
+
"step": 5800
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 0.93,
|
| 455 |
+
"learning_rate": 8.138801261829655e-05,
|
| 456 |
+
"loss": 0.0511,
|
| 457 |
+
"step": 5900
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.95,
|
| 461 |
+
"learning_rate": 8.107255520504731e-05,
|
| 462 |
+
"loss": 0.0548,
|
| 463 |
+
"step": 6000
|
| 464 |
+
},
|
| 465 |
+
{
|
| 466 |
+
"epoch": 0.95,
|
| 467 |
+
"eval_loss": 0.039724551141262054,
|
| 468 |
+
"eval_runtime": 191.9769,
|
| 469 |
+
"eval_samples_per_second": 113.217,
|
| 470 |
+
"eval_steps_per_second": 14.153,
|
| 471 |
+
"step": 6000
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.96,
|
| 475 |
+
"learning_rate": 8.075709779179811e-05,
|
| 476 |
+
"loss": 0.0482,
|
| 477 |
+
"step": 6100
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 0.98,
|
| 481 |
+
"learning_rate": 8.04416403785489e-05,
|
| 482 |
+
"loss": 0.0474,
|
| 483 |
+
"step": 6200
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 0.99,
|
| 487 |
+
"learning_rate": 8.012618296529969e-05,
|
| 488 |
+
"loss": 0.0488,
|
| 489 |
+
"step": 6300
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 1.01,
|
| 493 |
+
"learning_rate": 7.981072555205048e-05,
|
| 494 |
+
"loss": 0.0346,
|
| 495 |
+
"step": 6400
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 1.03,
|
| 499 |
+
"learning_rate": 7.949526813880127e-05,
|
| 500 |
+
"loss": 0.035,
|
| 501 |
+
"step": 6500
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 1.03,
|
| 505 |
+
"eval_loss": 0.039325978606939316,
|
| 506 |
+
"eval_runtime": 191.6608,
|
| 507 |
+
"eval_samples_per_second": 113.403,
|
| 508 |
+
"eval_steps_per_second": 14.176,
|
| 509 |
+
"step": 6500
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 1.04,
|
| 513 |
+
"learning_rate": 7.917981072555205e-05,
|
| 514 |
+
"loss": 0.0355,
|
| 515 |
+
"step": 6600
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 1.06,
|
| 519 |
+
"learning_rate": 7.886435331230284e-05,
|
| 520 |
+
"loss": 0.0363,
|
| 521 |
+
"step": 6700
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 1.07,
|
| 525 |
+
"learning_rate": 7.854889589905363e-05,
|
| 526 |
+
"loss": 0.0407,
|
| 527 |
+
"step": 6800
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 1.09,
|
| 531 |
+
"learning_rate": 7.823343848580442e-05,
|
| 532 |
+
"loss": 0.0385,
|
| 533 |
+
"step": 6900
|
| 534 |
+
},
|
| 535 |
+
{
|
| 536 |
+
"epoch": 1.1,
|
| 537 |
+
"learning_rate": 7.791798107255522e-05,
|
| 538 |
+
"loss": 0.0347,
|
| 539 |
+
"step": 7000
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 1.1,
|
| 543 |
+
"eval_loss": 0.03924637660384178,
|
| 544 |
+
"eval_runtime": 192.1827,
|
| 545 |
+
"eval_samples_per_second": 113.096,
|
| 546 |
+
"eval_steps_per_second": 14.138,
|
| 547 |
+
"step": 7000
|
| 548 |
+
},
|
| 549 |
+
{
|
| 550 |
+
"epoch": 1.12,
|
| 551 |
+
"learning_rate": 7.760252365930599e-05,
|
| 552 |
+
"loss": 0.0357,
|
| 553 |
+
"step": 7100
|
| 554 |
+
},
|
| 555 |
+
{
|
| 556 |
+
"epoch": 1.14,
|
| 557 |
+
"learning_rate": 7.728706624605678e-05,
|
| 558 |
+
"loss": 0.041,
|
| 559 |
+
"step": 7200
|
| 560 |
+
},
|
| 561 |
+
{
|
| 562 |
+
"epoch": 1.15,
|
| 563 |
+
"learning_rate": 7.697160883280758e-05,
|
| 564 |
+
"loss": 0.0313,
|
| 565 |
+
"step": 7300
|
| 566 |
+
},
|
| 567 |
+
{
|
| 568 |
+
"epoch": 1.17,
|
| 569 |
+
"learning_rate": 7.665615141955836e-05,
|
| 570 |
+
"loss": 0.0336,
|
| 571 |
+
"step": 7400
|
| 572 |
+
},
|
| 573 |
+
{
|
| 574 |
+
"epoch": 1.18,
|
| 575 |
+
"learning_rate": 7.634069400630916e-05,
|
| 576 |
+
"loss": 0.0303,
|
| 577 |
+
"step": 7500
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 1.18,
|
| 581 |
+
"eval_loss": 0.03979608044028282,
|
| 582 |
+
"eval_runtime": 192.103,
|
| 583 |
+
"eval_samples_per_second": 113.142,
|
| 584 |
+
"eval_steps_per_second": 14.143,
|
| 585 |
+
"step": 7500
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 1.2,
|
| 589 |
+
"learning_rate": 7.602523659305994e-05,
|
| 590 |
+
"loss": 0.0356,
|
| 591 |
+
"step": 7600
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 1.21,
|
| 595 |
+
"learning_rate": 7.570977917981072e-05,
|
| 596 |
+
"loss": 0.0379,
|
| 597 |
+
"step": 7700
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 1.23,
|
| 601 |
+
"learning_rate": 7.539432176656152e-05,
|
| 602 |
+
"loss": 0.0365,
|
| 603 |
+
"step": 7800
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 1.25,
|
| 607 |
+
"learning_rate": 7.50788643533123e-05,
|
| 608 |
+
"loss": 0.0393,
|
| 609 |
+
"step": 7900
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 1.26,
|
| 613 |
+
"learning_rate": 7.47634069400631e-05,
|
| 614 |
+
"loss": 0.0374,
|
| 615 |
+
"step": 8000
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 1.26,
|
| 619 |
+
"eval_loss": 0.038463614881038666,
|
| 620 |
+
"eval_runtime": 192.1601,
|
| 621 |
+
"eval_samples_per_second": 113.109,
|
| 622 |
+
"eval_steps_per_second": 14.139,
|
| 623 |
+
"step": 8000
|
| 624 |
+
},
|
| 625 |
+
{
|
| 626 |
+
"epoch": 1.28,
|
| 627 |
+
"learning_rate": 7.444794952681389e-05,
|
| 628 |
+
"loss": 0.0303,
|
| 629 |
+
"step": 8100
|
| 630 |
+
},
|
| 631 |
+
{
|
| 632 |
+
"epoch": 1.29,
|
| 633 |
+
"learning_rate": 7.413249211356468e-05,
|
| 634 |
+
"loss": 0.0384,
|
| 635 |
+
"step": 8200
|
| 636 |
+
},
|
| 637 |
+
{
|
| 638 |
+
"epoch": 1.31,
|
| 639 |
+
"learning_rate": 7.381703470031546e-05,
|
| 640 |
+
"loss": 0.0383,
|
| 641 |
+
"step": 8300
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 1.32,
|
| 645 |
+
"learning_rate": 7.350157728706625e-05,
|
| 646 |
+
"loss": 0.0378,
|
| 647 |
+
"step": 8400
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 1.34,
|
| 651 |
+
"learning_rate": 7.318611987381704e-05,
|
| 652 |
+
"loss": 0.0343,
|
| 653 |
+
"step": 8500
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 1.34,
|
| 657 |
+
"eval_loss": 0.03961439058184624,
|
| 658 |
+
"eval_runtime": 192.1114,
|
| 659 |
+
"eval_samples_per_second": 113.137,
|
| 660 |
+
"eval_steps_per_second": 14.143,
|
| 661 |
+
"step": 8500
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 1.36,
|
| 665 |
+
"learning_rate": 7.287066246056783e-05,
|
| 666 |
+
"loss": 0.0362,
|
| 667 |
+
"step": 8600
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 1.37,
|
| 671 |
+
"learning_rate": 7.255520504731861e-05,
|
| 672 |
+
"loss": 0.0435,
|
| 673 |
+
"step": 8700
|
| 674 |
+
},
|
| 675 |
+
{
|
| 676 |
+
"epoch": 1.39,
|
| 677 |
+
"learning_rate": 7.22397476340694e-05,
|
| 678 |
+
"loss": 0.0382,
|
| 679 |
+
"step": 8800
|
| 680 |
+
},
|
| 681 |
+
{
|
| 682 |
+
"epoch": 1.4,
|
| 683 |
+
"learning_rate": 7.192429022082019e-05,
|
| 684 |
+
"loss": 0.0439,
|
| 685 |
+
"step": 8900
|
| 686 |
+
},
|
| 687 |
+
{
|
| 688 |
+
"epoch": 1.42,
|
| 689 |
+
"learning_rate": 7.160883280757098e-05,
|
| 690 |
+
"loss": 0.0374,
|
| 691 |
+
"step": 9000
|
| 692 |
+
},
|
| 693 |
+
{
|
| 694 |
+
"epoch": 1.42,
|
| 695 |
+
"eval_loss": 0.037410151213407516,
|
| 696 |
+
"eval_runtime": 192.1572,
|
| 697 |
+
"eval_samples_per_second": 113.111,
|
| 698 |
+
"eval_steps_per_second": 14.139,
|
| 699 |
+
"step": 9000
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 1.44,
|
| 703 |
+
"learning_rate": 7.129337539432177e-05,
|
| 704 |
+
"loss": 0.0342,
|
| 705 |
+
"step": 9100
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 1.45,
|
| 709 |
+
"learning_rate": 7.097791798107257e-05,
|
| 710 |
+
"loss": 0.0337,
|
| 711 |
+
"step": 9200
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 1.47,
|
| 715 |
+
"learning_rate": 7.066246056782335e-05,
|
| 716 |
+
"loss": 0.0358,
|
| 717 |
+
"step": 9300
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 1.48,
|
| 721 |
+
"learning_rate": 7.034700315457413e-05,
|
| 722 |
+
"loss": 0.0301,
|
| 723 |
+
"step": 9400
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 1.5,
|
| 727 |
+
"learning_rate": 7.003154574132493e-05,
|
| 728 |
+
"loss": 0.0362,
|
| 729 |
+
"step": 9500
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 1.5,
|
| 733 |
+
"eval_loss": 0.03637044504284859,
|
| 734 |
+
"eval_runtime": 192.1621,
|
| 735 |
+
"eval_samples_per_second": 113.108,
|
| 736 |
+
"eval_steps_per_second": 14.139,
|
| 737 |
+
"step": 9500
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 1.51,
|
| 741 |
+
"learning_rate": 6.971608832807571e-05,
|
| 742 |
+
"loss": 0.037,
|
| 743 |
+
"step": 9600
|
| 744 |
+
},
|
| 745 |
+
{
|
| 746 |
+
"epoch": 1.53,
|
| 747 |
+
"learning_rate": 6.94006309148265e-05,
|
| 748 |
+
"loss": 0.0374,
|
| 749 |
+
"step": 9700
|
| 750 |
+
},
|
| 751 |
+
{
|
| 752 |
+
"epoch": 1.55,
|
| 753 |
+
"learning_rate": 6.908517350157729e-05,
|
| 754 |
+
"loss": 0.0379,
|
| 755 |
+
"step": 9800
|
| 756 |
+
},
|
| 757 |
+
{
|
| 758 |
+
"epoch": 1.56,
|
| 759 |
+
"learning_rate": 6.876971608832808e-05,
|
| 760 |
+
"loss": 0.0328,
|
| 761 |
+
"step": 9900
|
| 762 |
+
},
|
| 763 |
+
{
|
| 764 |
+
"epoch": 1.58,
|
| 765 |
+
"learning_rate": 6.845425867507887e-05,
|
| 766 |
+
"loss": 0.0315,
|
| 767 |
+
"step": 10000
|
| 768 |
+
},
|
| 769 |
+
{
|
| 770 |
+
"epoch": 1.58,
|
| 771 |
+
"eval_loss": 0.03636159375309944,
|
| 772 |
+
"eval_runtime": 192.0641,
|
| 773 |
+
"eval_samples_per_second": 113.165,
|
| 774 |
+
"eval_steps_per_second": 14.146,
|
| 775 |
+
"step": 10000
|
| 776 |
+
},
|
| 777 |
+
{
|
| 778 |
+
"epoch": 1.59,
|
| 779 |
+
"learning_rate": 6.813880126182965e-05,
|
| 780 |
+
"loss": 0.0328,
|
| 781 |
+
"step": 10100
|
| 782 |
+
},
|
| 783 |
+
{
|
| 784 |
+
"epoch": 1.61,
|
| 785 |
+
"learning_rate": 6.782334384858045e-05,
|
| 786 |
+
"loss": 0.0355,
|
| 787 |
+
"step": 10200
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 1.62,
|
| 791 |
+
"learning_rate": 6.750788643533124e-05,
|
| 792 |
+
"loss": 0.0398,
|
| 793 |
+
"step": 10300
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 1.64,
|
| 797 |
+
"learning_rate": 6.719242902208202e-05,
|
| 798 |
+
"loss": 0.0372,
|
| 799 |
+
"step": 10400
|
| 800 |
+
},
|
| 801 |
+
{
|
| 802 |
+
"epoch": 1.66,
|
| 803 |
+
"learning_rate": 6.68769716088328e-05,
|
| 804 |
+
"loss": 0.0399,
|
| 805 |
+
"step": 10500
|
| 806 |
+
},
|
| 807 |
+
{
|
| 808 |
+
"epoch": 1.66,
|
| 809 |
+
"eval_loss": 0.03677404299378395,
|
| 810 |
+
"eval_runtime": 191.6576,
|
| 811 |
+
"eval_samples_per_second": 113.405,
|
| 812 |
+
"eval_steps_per_second": 14.176,
|
| 813 |
+
"step": 10500
|
| 814 |
+
},
|
| 815 |
+
{
|
| 816 |
+
"epoch": 1.67,
|
| 817 |
+
"learning_rate": 6.65615141955836e-05,
|
| 818 |
+
"loss": 0.0394,
|
| 819 |
+
"step": 10600
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"epoch": 1.69,
|
| 823 |
+
"learning_rate": 6.624605678233438e-05,
|
| 824 |
+
"loss": 0.0355,
|
| 825 |
+
"step": 10700
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 1.7,
|
| 829 |
+
"learning_rate": 6.593059936908518e-05,
|
| 830 |
+
"loss": 0.0326,
|
| 831 |
+
"step": 10800
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 1.72,
|
| 835 |
+
"learning_rate": 6.561514195583596e-05,
|
| 836 |
+
"loss": 0.0307,
|
| 837 |
+
"step": 10900
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 1.74,
|
| 841 |
+
"learning_rate": 6.529968454258676e-05,
|
| 842 |
+
"loss": 0.0372,
|
| 843 |
+
"step": 11000
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 1.74,
|
| 847 |
+
"eval_loss": 0.03506915271282196,
|
| 848 |
+
"eval_runtime": 192.4202,
|
| 849 |
+
"eval_samples_per_second": 112.956,
|
| 850 |
+
"eval_steps_per_second": 14.12,
|
| 851 |
+
"step": 11000
|
| 852 |
+
},
|
| 853 |
+
{
|
| 854 |
+
"epoch": 1.75,
|
| 855 |
+
"learning_rate": 6.498422712933754e-05,
|
| 856 |
+
"loss": 0.0321,
|
| 857 |
+
"step": 11100
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 1.77,
|
| 861 |
+
"learning_rate": 6.466876971608832e-05,
|
| 862 |
+
"loss": 0.0272,
|
| 863 |
+
"step": 11200
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 1.78,
|
| 867 |
+
"learning_rate": 6.435331230283912e-05,
|
| 868 |
+
"loss": 0.0322,
|
| 869 |
+
"step": 11300
|
| 870 |
+
},
|
| 871 |
+
{
|
| 872 |
+
"epoch": 1.8,
|
| 873 |
+
"learning_rate": 6.403785488958992e-05,
|
| 874 |
+
"loss": 0.0355,
|
| 875 |
+
"step": 11400
|
| 876 |
+
},
|
| 877 |
+
{
|
| 878 |
+
"epoch": 1.81,
|
| 879 |
+
"learning_rate": 6.37223974763407e-05,
|
| 880 |
+
"loss": 0.0324,
|
| 881 |
+
"step": 11500
|
| 882 |
+
},
|
| 883 |
+
{
|
| 884 |
+
"epoch": 1.81,
|
| 885 |
+
"eval_loss": 0.034638404846191406,
|
| 886 |
+
"eval_runtime": 192.5205,
|
| 887 |
+
"eval_samples_per_second": 112.897,
|
| 888 |
+
"eval_steps_per_second": 14.113,
|
| 889 |
+
"step": 11500
|
| 890 |
+
},
|
| 891 |
+
{
|
| 892 |
+
"epoch": 1.83,
|
| 893 |
+
"learning_rate": 6.34069400630915e-05,
|
| 894 |
+
"loss": 0.0362,
|
| 895 |
+
"step": 11600
|
| 896 |
+
},
|
| 897 |
+
{
|
| 898 |
+
"epoch": 1.85,
|
| 899 |
+
"learning_rate": 6.309148264984228e-05,
|
| 900 |
+
"loss": 0.03,
|
| 901 |
+
"step": 11700
|
| 902 |
+
},
|
| 903 |
+
{
|
| 904 |
+
"epoch": 1.86,
|
| 905 |
+
"learning_rate": 6.277602523659306e-05,
|
| 906 |
+
"loss": 0.0313,
|
| 907 |
+
"step": 11800
|
| 908 |
+
},
|
| 909 |
+
{
|
| 910 |
+
"epoch": 1.88,
|
| 911 |
+
"learning_rate": 6.246056782334385e-05,
|
| 912 |
+
"loss": 0.0348,
|
| 913 |
+
"step": 11900
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 1.89,
|
| 917 |
+
"learning_rate": 6.214511041009464e-05,
|
| 918 |
+
"loss": 0.0351,
|
| 919 |
+
"step": 12000
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 1.89,
|
| 923 |
+
"eval_loss": 0.03646688908338547,
|
| 924 |
+
"eval_runtime": 192.2872,
|
| 925 |
+
"eval_samples_per_second": 113.034,
|
| 926 |
+
"eval_steps_per_second": 14.13,
|
| 927 |
+
"step": 12000
|
| 928 |
+
}
|
| 929 |
+
],
|
| 930 |
+
"logging_steps": 100,
|
| 931 |
+
"max_steps": 31700,
|
| 932 |
+
"num_input_tokens_seen": 0,
|
| 933 |
+
"num_train_epochs": 5,
|
| 934 |
+
"save_steps": 500,
|
| 935 |
+
"total_flos": 4226972988026880.0,
|
| 936 |
+
"train_batch_size": 8,
|
| 937 |
+
"trial_name": null,
|
| 938 |
+
"trial_params": null
|
| 939 |
+
}
|
backup_checkpoint-12000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:266031b962f594171a699a315d204ad9c02913dc636256066f9f3f3625b85451
|
| 3 |
+
size 4664
|
backup_checkpoint/config.json
ADDED
|
@@ -0,0 +1,75 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "facebook/bart-base",
|
| 3 |
+
"activation_dropout": 0.1,
|
| 4 |
+
"activation_function": "gelu",
|
| 5 |
+
"add_bias_logits": false,
|
| 6 |
+
"add_final_layer_norm": false,
|
| 7 |
+
"architectures": [
|
| 8 |
+
"BartForConditionalGeneration"
|
| 9 |
+
],
|
| 10 |
+
"attention_dropout": 0.1,
|
| 11 |
+
"bos_token_id": 0,
|
| 12 |
+
"classif_dropout": 0.1,
|
| 13 |
+
"classifier_dropout": 0.0,
|
| 14 |
+
"d_model": 768,
|
| 15 |
+
"decoder_attention_heads": 12,
|
| 16 |
+
"decoder_ffn_dim": 3072,
|
| 17 |
+
"decoder_layerdrop": 0.0,
|
| 18 |
+
"decoder_layers": 6,
|
| 19 |
+
"decoder_start_token_id": 2,
|
| 20 |
+
"dropout": 0.1,
|
| 21 |
+
"early_stopping": true,
|
| 22 |
+
"encoder_attention_heads": 12,
|
| 23 |
+
"encoder_ffn_dim": 3072,
|
| 24 |
+
"encoder_layerdrop": 0.0,
|
| 25 |
+
"encoder_layers": 6,
|
| 26 |
+
"eos_token_id": 2,
|
| 27 |
+
"forced_bos_token_id": 0,
|
| 28 |
+
"forced_eos_token_id": 2,
|
| 29 |
+
"gradient_checkpointing": false,
|
| 30 |
+
"id2label": {
|
| 31 |
+
"0": "LABEL_0",
|
| 32 |
+
"1": "LABEL_1",
|
| 33 |
+
"2": "LABEL_2"
|
| 34 |
+
},
|
| 35 |
+
"init_std": 0.02,
|
| 36 |
+
"is_encoder_decoder": true,
|
| 37 |
+
"label2id": {
|
| 38 |
+
"LABEL_0": 0,
|
| 39 |
+
"LABEL_1": 1,
|
| 40 |
+
"LABEL_2": 2
|
| 41 |
+
},
|
| 42 |
+
"max_position_embeddings": 1024,
|
| 43 |
+
"model_type": "bart",
|
| 44 |
+
"no_repeat_ngram_size": 3,
|
| 45 |
+
"normalize_before": false,
|
| 46 |
+
"normalize_embedding": true,
|
| 47 |
+
"num_beams": 4,
|
| 48 |
+
"num_hidden_layers": 6,
|
| 49 |
+
"pad_token_id": 1,
|
| 50 |
+
"scale_embedding": false,
|
| 51 |
+
"task_specific_params": {
|
| 52 |
+
"summarization": {
|
| 53 |
+
"length_penalty": 1.0,
|
| 54 |
+
"max_length": 128,
|
| 55 |
+
"min_length": 12,
|
| 56 |
+
"num_beams": 4
|
| 57 |
+
},
|
| 58 |
+
"summarization_cnn": {
|
| 59 |
+
"length_penalty": 2.0,
|
| 60 |
+
"max_length": 142,
|
| 61 |
+
"min_length": 56,
|
| 62 |
+
"num_beams": 4
|
| 63 |
+
},
|
| 64 |
+
"summarization_xsum": {
|
| 65 |
+
"length_penalty": 1.0,
|
| 66 |
+
"max_length": 62,
|
| 67 |
+
"min_length": 11,
|
| 68 |
+
"num_beams": 6
|
| 69 |
+
}
|
| 70 |
+
},
|
| 71 |
+
"torch_dtype": "float32",
|
| 72 |
+
"transformers_version": "4.37.0.dev0",
|
| 73 |
+
"use_cache": true,
|
| 74 |
+
"vocab_size": 50265
|
| 75 |
+
}
|
backup_checkpoint/generation_config.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 0,
|
| 4 |
+
"decoder_start_token_id": 2,
|
| 5 |
+
"early_stopping": true,
|
| 6 |
+
"eos_token_id": 2,
|
| 7 |
+
"forced_bos_token_id": 0,
|
| 8 |
+
"forced_eos_token_id": 2,
|
| 9 |
+
"no_repeat_ngram_size": 3,
|
| 10 |
+
"num_beams": 4,
|
| 11 |
+
"pad_token_id": 1,
|
| 12 |
+
"transformers_version": "4.37.0.dev0"
|
| 13 |
+
}
|
backup_checkpoint/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:acc561d99f17d9573b5d2c97086c82ccd1e57e20c82f54bfb6c055c5dae1a3cb
|
| 3 |
+
size 557912620
|
backup_checkpoint/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c0d53e4853b78131aa2fd3dba9e24dcfc369ab8bb95af928a52af89426571012
|
| 3 |
+
size 1115579898
|
backup_checkpoint/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a73c6f1e1eb77013e5ab142cf4e8d03715ff991905e41d762946a7eb2154ef3f
|
| 3 |
+
size 14244
|
backup_checkpoint/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:51c6bfad6b9ed7f7b64c27c27fdb69168a5257375021c87f904bde03904fc246
|
| 3 |
+
size 1064
|
backup_checkpoint/trainer_state.json
ADDED
|
@@ -0,0 +1,749 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.498422712933754,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 9500,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.0,
|
| 13 |
+
"learning_rate": 9.999684542586752e-05,
|
| 14 |
+
"loss": 12.4787,
|
| 15 |
+
"step": 1
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.02,
|
| 19 |
+
"learning_rate": 9.96845425867508e-05,
|
| 20 |
+
"loss": 1.3146,
|
| 21 |
+
"step": 100
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.03,
|
| 25 |
+
"learning_rate": 9.936908517350158e-05,
|
| 26 |
+
"loss": 0.0928,
|
| 27 |
+
"step": 200
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.05,
|
| 31 |
+
"learning_rate": 9.905362776025237e-05,
|
| 32 |
+
"loss": 0.0903,
|
| 33 |
+
"step": 300
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.06,
|
| 37 |
+
"learning_rate": 9.873817034700316e-05,
|
| 38 |
+
"loss": 0.0675,
|
| 39 |
+
"step": 400
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.08,
|
| 43 |
+
"learning_rate": 9.842271293375394e-05,
|
| 44 |
+
"loss": 0.0744,
|
| 45 |
+
"step": 500
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.08,
|
| 49 |
+
"eval_loss": 0.06298290193080902,
|
| 50 |
+
"eval_runtime": 191.3725,
|
| 51 |
+
"eval_samples_per_second": 113.574,
|
| 52 |
+
"eval_steps_per_second": 14.197,
|
| 53 |
+
"step": 500
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 0.09,
|
| 57 |
+
"learning_rate": 9.810725552050474e-05,
|
| 58 |
+
"loss": 0.0682,
|
| 59 |
+
"step": 600
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.11,
|
| 63 |
+
"learning_rate": 9.779179810725552e-05,
|
| 64 |
+
"loss": 0.072,
|
| 65 |
+
"step": 700
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.13,
|
| 69 |
+
"learning_rate": 9.747634069400632e-05,
|
| 70 |
+
"loss": 0.0731,
|
| 71 |
+
"step": 800
|
| 72 |
+
},
|
| 73 |
+
{
|
| 74 |
+
"epoch": 0.14,
|
| 75 |
+
"learning_rate": 9.71608832807571e-05,
|
| 76 |
+
"loss": 0.0638,
|
| 77 |
+
"step": 900
|
| 78 |
+
},
|
| 79 |
+
{
|
| 80 |
+
"epoch": 0.16,
|
| 81 |
+
"learning_rate": 9.684542586750788e-05,
|
| 82 |
+
"loss": 0.062,
|
| 83 |
+
"step": 1000
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"epoch": 0.16,
|
| 87 |
+
"eval_loss": 0.056409742683172226,
|
| 88 |
+
"eval_runtime": 191.8919,
|
| 89 |
+
"eval_samples_per_second": 113.267,
|
| 90 |
+
"eval_steps_per_second": 14.159,
|
| 91 |
+
"step": 1000
|
| 92 |
+
},
|
| 93 |
+
{
|
| 94 |
+
"epoch": 0.17,
|
| 95 |
+
"learning_rate": 9.652996845425868e-05,
|
| 96 |
+
"loss": 0.0663,
|
| 97 |
+
"step": 1100
|
| 98 |
+
},
|
| 99 |
+
{
|
| 100 |
+
"epoch": 0.19,
|
| 101 |
+
"learning_rate": 9.621451104100947e-05,
|
| 102 |
+
"loss": 0.0598,
|
| 103 |
+
"step": 1200
|
| 104 |
+
},
|
| 105 |
+
{
|
| 106 |
+
"epoch": 0.21,
|
| 107 |
+
"learning_rate": 9.589905362776026e-05,
|
| 108 |
+
"loss": 0.0625,
|
| 109 |
+
"step": 1300
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 0.22,
|
| 113 |
+
"learning_rate": 9.558359621451105e-05,
|
| 114 |
+
"loss": 0.0673,
|
| 115 |
+
"step": 1400
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.24,
|
| 119 |
+
"learning_rate": 9.526813880126184e-05,
|
| 120 |
+
"loss": 0.0625,
|
| 121 |
+
"step": 1500
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.24,
|
| 125 |
+
"eval_loss": 0.05498537793755531,
|
| 126 |
+
"eval_runtime": 191.898,
|
| 127 |
+
"eval_samples_per_second": 113.263,
|
| 128 |
+
"eval_steps_per_second": 14.159,
|
| 129 |
+
"step": 1500
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.25,
|
| 133 |
+
"learning_rate": 9.495268138801262e-05,
|
| 134 |
+
"loss": 0.0606,
|
| 135 |
+
"step": 1600
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.27,
|
| 139 |
+
"learning_rate": 9.463722397476341e-05,
|
| 140 |
+
"loss": 0.0684,
|
| 141 |
+
"step": 1700
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 0.28,
|
| 145 |
+
"learning_rate": 9.43217665615142e-05,
|
| 146 |
+
"loss": 0.0607,
|
| 147 |
+
"step": 1800
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 0.3,
|
| 151 |
+
"learning_rate": 9.400630914826499e-05,
|
| 152 |
+
"loss": 0.0679,
|
| 153 |
+
"step": 1900
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 0.32,
|
| 157 |
+
"learning_rate": 9.369085173501577e-05,
|
| 158 |
+
"loss": 0.0633,
|
| 159 |
+
"step": 2000
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.32,
|
| 163 |
+
"eval_loss": 0.052233804017305374,
|
| 164 |
+
"eval_runtime": 191.8762,
|
| 165 |
+
"eval_samples_per_second": 113.276,
|
| 166 |
+
"eval_steps_per_second": 14.16,
|
| 167 |
+
"step": 2000
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 0.33,
|
| 171 |
+
"learning_rate": 9.337539432176656e-05,
|
| 172 |
+
"loss": 0.061,
|
| 173 |
+
"step": 2100
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 0.35,
|
| 177 |
+
"learning_rate": 9.305993690851735e-05,
|
| 178 |
+
"loss": 0.0715,
|
| 179 |
+
"step": 2200
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 0.36,
|
| 183 |
+
"learning_rate": 9.274447949526815e-05,
|
| 184 |
+
"loss": 0.0586,
|
| 185 |
+
"step": 2300
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.38,
|
| 189 |
+
"learning_rate": 9.242902208201893e-05,
|
| 190 |
+
"loss": 0.0581,
|
| 191 |
+
"step": 2400
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.39,
|
| 195 |
+
"learning_rate": 9.211356466876973e-05,
|
| 196 |
+
"loss": 0.0588,
|
| 197 |
+
"step": 2500
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 0.39,
|
| 201 |
+
"eval_loss": 0.05040860176086426,
|
| 202 |
+
"eval_runtime": 191.6049,
|
| 203 |
+
"eval_samples_per_second": 113.437,
|
| 204 |
+
"eval_steps_per_second": 14.18,
|
| 205 |
+
"step": 2500
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.41,
|
| 209 |
+
"learning_rate": 9.179810725552051e-05,
|
| 210 |
+
"loss": 0.0572,
|
| 211 |
+
"step": 2600
|
| 212 |
+
},
|
| 213 |
+
{
|
| 214 |
+
"epoch": 0.43,
|
| 215 |
+
"learning_rate": 9.148264984227129e-05,
|
| 216 |
+
"loss": 0.0555,
|
| 217 |
+
"step": 2700
|
| 218 |
+
},
|
| 219 |
+
{
|
| 220 |
+
"epoch": 0.44,
|
| 221 |
+
"learning_rate": 9.116719242902209e-05,
|
| 222 |
+
"loss": 0.0547,
|
| 223 |
+
"step": 2800
|
| 224 |
+
},
|
| 225 |
+
{
|
| 226 |
+
"epoch": 0.46,
|
| 227 |
+
"learning_rate": 9.085173501577287e-05,
|
| 228 |
+
"loss": 0.0596,
|
| 229 |
+
"step": 2900
|
| 230 |
+
},
|
| 231 |
+
{
|
| 232 |
+
"epoch": 0.47,
|
| 233 |
+
"learning_rate": 9.053627760252367e-05,
|
| 234 |
+
"loss": 0.0593,
|
| 235 |
+
"step": 3000
|
| 236 |
+
},
|
| 237 |
+
{
|
| 238 |
+
"epoch": 0.47,
|
| 239 |
+
"eval_loss": 0.04637610912322998,
|
| 240 |
+
"eval_runtime": 192.1829,
|
| 241 |
+
"eval_samples_per_second": 113.095,
|
| 242 |
+
"eval_steps_per_second": 14.138,
|
| 243 |
+
"step": 3000
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 0.49,
|
| 247 |
+
"learning_rate": 9.022082018927446e-05,
|
| 248 |
+
"loss": 0.0536,
|
| 249 |
+
"step": 3100
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 0.5,
|
| 253 |
+
"learning_rate": 8.990536277602523e-05,
|
| 254 |
+
"loss": 0.0506,
|
| 255 |
+
"step": 3200
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.52,
|
| 259 |
+
"learning_rate": 8.958990536277603e-05,
|
| 260 |
+
"loss": 0.0601,
|
| 261 |
+
"step": 3300
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.54,
|
| 265 |
+
"learning_rate": 8.927444794952682e-05,
|
| 266 |
+
"loss": 0.05,
|
| 267 |
+
"step": 3400
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 0.55,
|
| 271 |
+
"learning_rate": 8.89589905362776e-05,
|
| 272 |
+
"loss": 0.0492,
|
| 273 |
+
"step": 3500
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 0.55,
|
| 277 |
+
"eval_loss": 0.0455920547246933,
|
| 278 |
+
"eval_runtime": 192.0796,
|
| 279 |
+
"eval_samples_per_second": 113.156,
|
| 280 |
+
"eval_steps_per_second": 14.145,
|
| 281 |
+
"step": 3500
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 0.57,
|
| 285 |
+
"learning_rate": 8.86435331230284e-05,
|
| 286 |
+
"loss": 0.0547,
|
| 287 |
+
"step": 3600
|
| 288 |
+
},
|
| 289 |
+
{
|
| 290 |
+
"epoch": 0.58,
|
| 291 |
+
"learning_rate": 8.832807570977918e-05,
|
| 292 |
+
"loss": 0.0582,
|
| 293 |
+
"step": 3700
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 0.6,
|
| 297 |
+
"learning_rate": 8.801261829652997e-05,
|
| 298 |
+
"loss": 0.0535,
|
| 299 |
+
"step": 3800
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 0.62,
|
| 303 |
+
"learning_rate": 8.769716088328076e-05,
|
| 304 |
+
"loss": 0.0554,
|
| 305 |
+
"step": 3900
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 0.63,
|
| 309 |
+
"learning_rate": 8.738170347003154e-05,
|
| 310 |
+
"loss": 0.0506,
|
| 311 |
+
"step": 4000
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.63,
|
| 315 |
+
"eval_loss": 0.04419832304120064,
|
| 316 |
+
"eval_runtime": 192.193,
|
| 317 |
+
"eval_samples_per_second": 113.089,
|
| 318 |
+
"eval_steps_per_second": 14.137,
|
| 319 |
+
"step": 4000
|
| 320 |
+
},
|
| 321 |
+
{
|
| 322 |
+
"epoch": 0.65,
|
| 323 |
+
"learning_rate": 8.706624605678234e-05,
|
| 324 |
+
"loss": 0.0508,
|
| 325 |
+
"step": 4100
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.66,
|
| 329 |
+
"learning_rate": 8.675078864353314e-05,
|
| 330 |
+
"loss": 0.0566,
|
| 331 |
+
"step": 4200
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.68,
|
| 335 |
+
"learning_rate": 8.64353312302839e-05,
|
| 336 |
+
"loss": 0.0556,
|
| 337 |
+
"step": 4300
|
| 338 |
+
},
|
| 339 |
+
{
|
| 340 |
+
"epoch": 0.69,
|
| 341 |
+
"learning_rate": 8.61198738170347e-05,
|
| 342 |
+
"loss": 0.0595,
|
| 343 |
+
"step": 4400
|
| 344 |
+
},
|
| 345 |
+
{
|
| 346 |
+
"epoch": 0.71,
|
| 347 |
+
"learning_rate": 8.58044164037855e-05,
|
| 348 |
+
"loss": 0.0584,
|
| 349 |
+
"step": 4500
|
| 350 |
+
},
|
| 351 |
+
{
|
| 352 |
+
"epoch": 0.71,
|
| 353 |
+
"eval_loss": 0.043363627046346664,
|
| 354 |
+
"eval_runtime": 191.6803,
|
| 355 |
+
"eval_samples_per_second": 113.392,
|
| 356 |
+
"eval_steps_per_second": 14.175,
|
| 357 |
+
"step": 4500
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 0.73,
|
| 361 |
+
"learning_rate": 8.548895899053628e-05,
|
| 362 |
+
"loss": 0.0546,
|
| 363 |
+
"step": 4600
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 0.74,
|
| 367 |
+
"learning_rate": 8.517350157728708e-05,
|
| 368 |
+
"loss": 0.0457,
|
| 369 |
+
"step": 4700
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 0.76,
|
| 373 |
+
"learning_rate": 8.485804416403787e-05,
|
| 374 |
+
"loss": 0.0531,
|
| 375 |
+
"step": 4800
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 0.77,
|
| 379 |
+
"learning_rate": 8.454258675078864e-05,
|
| 380 |
+
"loss": 0.0506,
|
| 381 |
+
"step": 4900
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.79,
|
| 385 |
+
"learning_rate": 8.422712933753944e-05,
|
| 386 |
+
"loss": 0.0455,
|
| 387 |
+
"step": 5000
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.79,
|
| 391 |
+
"eval_loss": 0.04175921157002449,
|
| 392 |
+
"eval_runtime": 192.0012,
|
| 393 |
+
"eval_samples_per_second": 113.202,
|
| 394 |
+
"eval_steps_per_second": 14.151,
|
| 395 |
+
"step": 5000
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.8,
|
| 399 |
+
"learning_rate": 8.391167192429022e-05,
|
| 400 |
+
"loss": 0.053,
|
| 401 |
+
"step": 5100
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.82,
|
| 405 |
+
"learning_rate": 8.359621451104101e-05,
|
| 406 |
+
"loss": 0.0499,
|
| 407 |
+
"step": 5200
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 0.84,
|
| 411 |
+
"learning_rate": 8.328075709779181e-05,
|
| 412 |
+
"loss": 0.0407,
|
| 413 |
+
"step": 5300
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 0.85,
|
| 417 |
+
"learning_rate": 8.296529968454258e-05,
|
| 418 |
+
"loss": 0.0559,
|
| 419 |
+
"step": 5400
|
| 420 |
+
},
|
| 421 |
+
{
|
| 422 |
+
"epoch": 0.87,
|
| 423 |
+
"learning_rate": 8.264984227129337e-05,
|
| 424 |
+
"loss": 0.0477,
|
| 425 |
+
"step": 5500
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 0.87,
|
| 429 |
+
"eval_loss": 0.042047169059515,
|
| 430 |
+
"eval_runtime": 192.1,
|
| 431 |
+
"eval_samples_per_second": 113.144,
|
| 432 |
+
"eval_steps_per_second": 14.144,
|
| 433 |
+
"step": 5500
|
| 434 |
+
},
|
| 435 |
+
{
|
| 436 |
+
"epoch": 0.88,
|
| 437 |
+
"learning_rate": 8.233438485804417e-05,
|
| 438 |
+
"loss": 0.0488,
|
| 439 |
+
"step": 5600
|
| 440 |
+
},
|
| 441 |
+
{
|
| 442 |
+
"epoch": 0.9,
|
| 443 |
+
"learning_rate": 8.201892744479495e-05,
|
| 444 |
+
"loss": 0.0537,
|
| 445 |
+
"step": 5700
|
| 446 |
+
},
|
| 447 |
+
{
|
| 448 |
+
"epoch": 0.91,
|
| 449 |
+
"learning_rate": 8.170347003154575e-05,
|
| 450 |
+
"loss": 0.0515,
|
| 451 |
+
"step": 5800
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 0.93,
|
| 455 |
+
"learning_rate": 8.138801261829655e-05,
|
| 456 |
+
"loss": 0.0511,
|
| 457 |
+
"step": 5900
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.95,
|
| 461 |
+
"learning_rate": 8.107255520504731e-05,
|
| 462 |
+
"loss": 0.0548,
|
| 463 |
+
"step": 6000
|
| 464 |
+
},
|
| 465 |
+
{
|
| 466 |
+
"epoch": 0.95,
|
| 467 |
+
"eval_loss": 0.039724551141262054,
|
| 468 |
+
"eval_runtime": 191.9769,
|
| 469 |
+
"eval_samples_per_second": 113.217,
|
| 470 |
+
"eval_steps_per_second": 14.153,
|
| 471 |
+
"step": 6000
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.96,
|
| 475 |
+
"learning_rate": 8.075709779179811e-05,
|
| 476 |
+
"loss": 0.0482,
|
| 477 |
+
"step": 6100
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 0.98,
|
| 481 |
+
"learning_rate": 8.04416403785489e-05,
|
| 482 |
+
"loss": 0.0474,
|
| 483 |
+
"step": 6200
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 0.99,
|
| 487 |
+
"learning_rate": 8.012618296529969e-05,
|
| 488 |
+
"loss": 0.0488,
|
| 489 |
+
"step": 6300
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 1.01,
|
| 493 |
+
"learning_rate": 7.981072555205048e-05,
|
| 494 |
+
"loss": 0.0346,
|
| 495 |
+
"step": 6400
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 1.03,
|
| 499 |
+
"learning_rate": 7.949526813880127e-05,
|
| 500 |
+
"loss": 0.035,
|
| 501 |
+
"step": 6500
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 1.03,
|
| 505 |
+
"eval_loss": 0.039325978606939316,
|
| 506 |
+
"eval_runtime": 191.6608,
|
| 507 |
+
"eval_samples_per_second": 113.403,
|
| 508 |
+
"eval_steps_per_second": 14.176,
|
| 509 |
+
"step": 6500
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 1.04,
|
| 513 |
+
"learning_rate": 7.917981072555205e-05,
|
| 514 |
+
"loss": 0.0355,
|
| 515 |
+
"step": 6600
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 1.06,
|
| 519 |
+
"learning_rate": 7.886435331230284e-05,
|
| 520 |
+
"loss": 0.0363,
|
| 521 |
+
"step": 6700
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 1.07,
|
| 525 |
+
"learning_rate": 7.854889589905363e-05,
|
| 526 |
+
"loss": 0.0407,
|
| 527 |
+
"step": 6800
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 1.09,
|
| 531 |
+
"learning_rate": 7.823343848580442e-05,
|
| 532 |
+
"loss": 0.0385,
|
| 533 |
+
"step": 6900
|
| 534 |
+
},
|
| 535 |
+
{
|
| 536 |
+
"epoch": 1.1,
|
| 537 |
+
"learning_rate": 7.791798107255522e-05,
|
| 538 |
+
"loss": 0.0347,
|
| 539 |
+
"step": 7000
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 1.1,
|
| 543 |
+
"eval_loss": 0.03924637660384178,
|
| 544 |
+
"eval_runtime": 192.1827,
|
| 545 |
+
"eval_samples_per_second": 113.096,
|
| 546 |
+
"eval_steps_per_second": 14.138,
|
| 547 |
+
"step": 7000
|
| 548 |
+
},
|
| 549 |
+
{
|
| 550 |
+
"epoch": 1.12,
|
| 551 |
+
"learning_rate": 7.760252365930599e-05,
|
| 552 |
+
"loss": 0.0357,
|
| 553 |
+
"step": 7100
|
| 554 |
+
},
|
| 555 |
+
{
|
| 556 |
+
"epoch": 1.14,
|
| 557 |
+
"learning_rate": 7.728706624605678e-05,
|
| 558 |
+
"loss": 0.041,
|
| 559 |
+
"step": 7200
|
| 560 |
+
},
|
| 561 |
+
{
|
| 562 |
+
"epoch": 1.15,
|
| 563 |
+
"learning_rate": 7.697160883280758e-05,
|
| 564 |
+
"loss": 0.0313,
|
| 565 |
+
"step": 7300
|
| 566 |
+
},
|
| 567 |
+
{
|
| 568 |
+
"epoch": 1.17,
|
| 569 |
+
"learning_rate": 7.665615141955836e-05,
|
| 570 |
+
"loss": 0.0336,
|
| 571 |
+
"step": 7400
|
| 572 |
+
},
|
| 573 |
+
{
|
| 574 |
+
"epoch": 1.18,
|
| 575 |
+
"learning_rate": 7.634069400630916e-05,
|
| 576 |
+
"loss": 0.0303,
|
| 577 |
+
"step": 7500
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 1.18,
|
| 581 |
+
"eval_loss": 0.03979608044028282,
|
| 582 |
+
"eval_runtime": 192.103,
|
| 583 |
+
"eval_samples_per_second": 113.142,
|
| 584 |
+
"eval_steps_per_second": 14.143,
|
| 585 |
+
"step": 7500
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 1.2,
|
| 589 |
+
"learning_rate": 7.602523659305994e-05,
|
| 590 |
+
"loss": 0.0356,
|
| 591 |
+
"step": 7600
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 1.21,
|
| 595 |
+
"learning_rate": 7.570977917981072e-05,
|
| 596 |
+
"loss": 0.0379,
|
| 597 |
+
"step": 7700
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 1.23,
|
| 601 |
+
"learning_rate": 7.539432176656152e-05,
|
| 602 |
+
"loss": 0.0365,
|
| 603 |
+
"step": 7800
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 1.25,
|
| 607 |
+
"learning_rate": 7.50788643533123e-05,
|
| 608 |
+
"loss": 0.0393,
|
| 609 |
+
"step": 7900
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 1.26,
|
| 613 |
+
"learning_rate": 7.47634069400631e-05,
|
| 614 |
+
"loss": 0.0374,
|
| 615 |
+
"step": 8000
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 1.26,
|
| 619 |
+
"eval_loss": 0.038463614881038666,
|
| 620 |
+
"eval_runtime": 192.1601,
|
| 621 |
+
"eval_samples_per_second": 113.109,
|
| 622 |
+
"eval_steps_per_second": 14.139,
|
| 623 |
+
"step": 8000
|
| 624 |
+
},
|
| 625 |
+
{
|
| 626 |
+
"epoch": 1.28,
|
| 627 |
+
"learning_rate": 7.444794952681389e-05,
|
| 628 |
+
"loss": 0.0303,
|
| 629 |
+
"step": 8100
|
| 630 |
+
},
|
| 631 |
+
{
|
| 632 |
+
"epoch": 1.29,
|
| 633 |
+
"learning_rate": 7.413249211356468e-05,
|
| 634 |
+
"loss": 0.0384,
|
| 635 |
+
"step": 8200
|
| 636 |
+
},
|
| 637 |
+
{
|
| 638 |
+
"epoch": 1.31,
|
| 639 |
+
"learning_rate": 7.381703470031546e-05,
|
| 640 |
+
"loss": 0.0383,
|
| 641 |
+
"step": 8300
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 1.32,
|
| 645 |
+
"learning_rate": 7.350157728706625e-05,
|
| 646 |
+
"loss": 0.0378,
|
| 647 |
+
"step": 8400
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 1.34,
|
| 651 |
+
"learning_rate": 7.318611987381704e-05,
|
| 652 |
+
"loss": 0.0343,
|
| 653 |
+
"step": 8500
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 1.34,
|
| 657 |
+
"eval_loss": 0.03961439058184624,
|
| 658 |
+
"eval_runtime": 192.1114,
|
| 659 |
+
"eval_samples_per_second": 113.137,
|
| 660 |
+
"eval_steps_per_second": 14.143,
|
| 661 |
+
"step": 8500
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 1.36,
|
| 665 |
+
"learning_rate": 7.287066246056783e-05,
|
| 666 |
+
"loss": 0.0362,
|
| 667 |
+
"step": 8600
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 1.37,
|
| 671 |
+
"learning_rate": 7.255520504731861e-05,
|
| 672 |
+
"loss": 0.0435,
|
| 673 |
+
"step": 8700
|
| 674 |
+
},
|
| 675 |
+
{
|
| 676 |
+
"epoch": 1.39,
|
| 677 |
+
"learning_rate": 7.22397476340694e-05,
|
| 678 |
+
"loss": 0.0382,
|
| 679 |
+
"step": 8800
|
| 680 |
+
},
|
| 681 |
+
{
|
| 682 |
+
"epoch": 1.4,
|
| 683 |
+
"learning_rate": 7.192429022082019e-05,
|
| 684 |
+
"loss": 0.0439,
|
| 685 |
+
"step": 8900
|
| 686 |
+
},
|
| 687 |
+
{
|
| 688 |
+
"epoch": 1.42,
|
| 689 |
+
"learning_rate": 7.160883280757098e-05,
|
| 690 |
+
"loss": 0.0374,
|
| 691 |
+
"step": 9000
|
| 692 |
+
},
|
| 693 |
+
{
|
| 694 |
+
"epoch": 1.42,
|
| 695 |
+
"eval_loss": 0.037410151213407516,
|
| 696 |
+
"eval_runtime": 192.1572,
|
| 697 |
+
"eval_samples_per_second": 113.111,
|
| 698 |
+
"eval_steps_per_second": 14.139,
|
| 699 |
+
"step": 9000
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 1.44,
|
| 703 |
+
"learning_rate": 7.129337539432177e-05,
|
| 704 |
+
"loss": 0.0342,
|
| 705 |
+
"step": 9100
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 1.45,
|
| 709 |
+
"learning_rate": 7.097791798107257e-05,
|
| 710 |
+
"loss": 0.0337,
|
| 711 |
+
"step": 9200
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 1.47,
|
| 715 |
+
"learning_rate": 7.066246056782335e-05,
|
| 716 |
+
"loss": 0.0358,
|
| 717 |
+
"step": 9300
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 1.48,
|
| 721 |
+
"learning_rate": 7.034700315457413e-05,
|
| 722 |
+
"loss": 0.0301,
|
| 723 |
+
"step": 9400
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 1.5,
|
| 727 |
+
"learning_rate": 7.003154574132493e-05,
|
| 728 |
+
"loss": 0.0362,
|
| 729 |
+
"step": 9500
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 1.5,
|
| 733 |
+
"eval_loss": 0.03637044504284859,
|
| 734 |
+
"eval_runtime": 192.1621,
|
| 735 |
+
"eval_samples_per_second": 113.108,
|
| 736 |
+
"eval_steps_per_second": 14.139,
|
| 737 |
+
"step": 9500
|
| 738 |
+
}
|
| 739 |
+
],
|
| 740 |
+
"logging_steps": 100,
|
| 741 |
+
"max_steps": 31700,
|
| 742 |
+
"num_input_tokens_seen": 0,
|
| 743 |
+
"num_train_epochs": 5,
|
| 744 |
+
"save_steps": 500,
|
| 745 |
+
"total_flos": 3348871507537920.0,
|
| 746 |
+
"train_batch_size": 8,
|
| 747 |
+
"trial_name": null,
|
| 748 |
+
"trial_params": null
|
| 749 |
+
}
|
backup_checkpoint/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:266031b962f594171a699a315d204ad9c02913dc636256066f9f3f3625b85451
|
| 3 |
+
size 4664
|
config.json
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "
|
| 3 |
"activation_dropout": 0.1,
|
| 4 |
"activation_function": "gelu",
|
| 5 |
"add_bias_logits": false,
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "./bart_test_p2/backup_checkpoint-12000",
|
| 3 |
"activation_dropout": 0.1,
|
| 4 |
"activation_function": "gelu",
|
| 5 |
"add_bias_logits": false,
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 557912620
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bd2d4cc6d9060405892bbe3e531d4520c68bd9a3a2fbf019f9e89cb820504c2f
|
| 3 |
size 557912620
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4664
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:da19c72832637aa9b262dfd4f56dcc1ff2faa4b4d65254eee1a7a257ba33f327
|
| 3 |
size 4664
|