Model save
Browse files- README.md +54 -0
- adapter_config.json +43 -0
- adapter_model.safetensors +3 -0
- preprocessor_config.json +15 -0
- trainer_state.json +1957 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
license: apache-2.0
|
| 4 |
+
base_model: openai/whisper-base
|
| 5 |
+
tags:
|
| 6 |
+
- base_model:adapter:openai/whisper-base
|
| 7 |
+
- lora
|
| 8 |
+
- transformers
|
| 9 |
+
model-index:
|
| 10 |
+
- name: whisper_ft
|
| 11 |
+
results: []
|
| 12 |
+
---
|
| 13 |
+
|
| 14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 15 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 16 |
+
|
| 17 |
+
# whisper_ft
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [openai/whisper-base](https://huggingface.co/openai/whisper-base) on an unknown dataset.
|
| 20 |
+
|
| 21 |
+
## Model description
|
| 22 |
+
|
| 23 |
+
More information needed
|
| 24 |
+
|
| 25 |
+
## Intended uses & limitations
|
| 26 |
+
|
| 27 |
+
More information needed
|
| 28 |
+
|
| 29 |
+
## Training and evaluation data
|
| 30 |
+
|
| 31 |
+
More information needed
|
| 32 |
+
|
| 33 |
+
## Training procedure
|
| 34 |
+
|
| 35 |
+
### Training hyperparameters
|
| 36 |
+
|
| 37 |
+
The following hyperparameters were used during training:
|
| 38 |
+
- learning_rate: 0.0002
|
| 39 |
+
- train_batch_size: 8
|
| 40 |
+
- eval_batch_size: 8
|
| 41 |
+
- seed: 42
|
| 42 |
+
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 43 |
+
- lr_scheduler_type: cosine
|
| 44 |
+
- lr_scheduler_warmup_steps: 100
|
| 45 |
+
- num_epochs: 10
|
| 46 |
+
- mixed_precision_training: Native AMP
|
| 47 |
+
|
| 48 |
+
### Framework versions
|
| 49 |
+
|
| 50 |
+
- PEFT 0.17.1
|
| 51 |
+
- Transformers 4.56.1
|
| 52 |
+
- Pytorch 2.8.0+cu128
|
| 53 |
+
- Datasets 3.6.0
|
| 54 |
+
- Tokenizers 0.22.0
|
adapter_config.json
ADDED
|
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": {
|
| 4 |
+
"base_model_class": "WhisperForConditionalGeneration",
|
| 5 |
+
"parent_library": "transformers.models.whisper.modeling_whisper"
|
| 6 |
+
},
|
| 7 |
+
"base_model_name_or_path": "openai/whisper-base",
|
| 8 |
+
"bias": "none",
|
| 9 |
+
"corda_config": null,
|
| 10 |
+
"eva_config": null,
|
| 11 |
+
"exclude_modules": null,
|
| 12 |
+
"fan_in_fan_out": false,
|
| 13 |
+
"inference_mode": true,
|
| 14 |
+
"init_lora_weights": "loftq",
|
| 15 |
+
"layer_replication": null,
|
| 16 |
+
"layers_pattern": null,
|
| 17 |
+
"layers_to_transform": null,
|
| 18 |
+
"loftq_config": {
|
| 19 |
+
"loftq_bits": 8,
|
| 20 |
+
"loftq_iter": 1
|
| 21 |
+
},
|
| 22 |
+
"lora_alpha": 64,
|
| 23 |
+
"lora_bias": false,
|
| 24 |
+
"lora_dropout": 0.05,
|
| 25 |
+
"megatron_config": null,
|
| 26 |
+
"megatron_core": "megatron.core",
|
| 27 |
+
"modules_to_save": null,
|
| 28 |
+
"peft_type": "LORA",
|
| 29 |
+
"qalora_group_size": 16,
|
| 30 |
+
"r": 32,
|
| 31 |
+
"rank_pattern": {},
|
| 32 |
+
"revision": null,
|
| 33 |
+
"target_modules": [
|
| 34 |
+
"q_proj",
|
| 35 |
+
"v_proj"
|
| 36 |
+
],
|
| 37 |
+
"target_parameters": null,
|
| 38 |
+
"task_type": null,
|
| 39 |
+
"trainable_token_indices": null,
|
| 40 |
+
"use_dora": false,
|
| 41 |
+
"use_qalora": false,
|
| 42 |
+
"use_rslora": false
|
| 43 |
+
}
|
adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4be761a32416e20ef24cdf5bfeb8f24db75d129c5c1078e76d3590ec5ddca8b3
|
| 3 |
+
size 4728680
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"chunk_length": 30,
|
| 3 |
+
"dither": 0.0,
|
| 4 |
+
"feature_extractor_type": "WhisperFeatureExtractor",
|
| 5 |
+
"feature_size": 80,
|
| 6 |
+
"hop_length": 160,
|
| 7 |
+
"n_fft": 400,
|
| 8 |
+
"n_samples": 480000,
|
| 9 |
+
"nb_max_frames": 3000,
|
| 10 |
+
"padding_side": "right",
|
| 11 |
+
"padding_value": 0.0,
|
| 12 |
+
"processor_class": "WhisperProcessor",
|
| 13 |
+
"return_attention_mask": false,
|
| 14 |
+
"sampling_rate": 16000
|
| 15 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1957 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": 47000,
|
| 3 |
+
"best_metric": 0.41246128940763466,
|
| 4 |
+
"best_model_checkpoint": "/vol/whisper_ft/checkpoint-47000",
|
| 5 |
+
"epoch": 2.129264073104733,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 48000,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.011089917047420485,
|
| 14 |
+
"grad_norm": 1.1934534311294556,
|
| 15 |
+
"learning_rate": 0.00019999978422352354,
|
| 16 |
+
"loss": 1.6958,
|
| 17 |
+
"step": 250
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.02217983409484097,
|
| 21 |
+
"grad_norm": 1.2334566116333008,
|
| 22 |
+
"learning_rate": 0.00019999845269336546,
|
| 23 |
+
"loss": 1.3806,
|
| 24 |
+
"step": 500
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.02217983409484097,
|
| 28 |
+
"eval_bleu": 0.26383481798460395,
|
| 29 |
+
"step": 500,
|
| 30 |
+
"swisstext21_eval_bleu": 0.24588728491056722
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.03326975114226145,
|
| 34 |
+
"grad_norm": 1.3390406370162964,
|
| 35 |
+
"learning_rate": 0.00019999590627988633,
|
| 36 |
+
"loss": 1.3021,
|
| 37 |
+
"step": 750
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.04435966818968194,
|
| 41 |
+
"grad_norm": 1.4407659769058228,
|
| 42 |
+
"learning_rate": 0.00019999214501402262,
|
| 43 |
+
"loss": 1.2618,
|
| 44 |
+
"step": 1000
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.04435966818968194,
|
| 48 |
+
"eval_bleu": 0.29376917116497847,
|
| 49 |
+
"step": 1000,
|
| 50 |
+
"swisstext21_eval_bleu": 0.2559340674197411
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.055449585237102424,
|
| 54 |
+
"grad_norm": 1.732470154762268,
|
| 55 |
+
"learning_rate": 0.00019998716894147002,
|
| 56 |
+
"loss": 1.2498,
|
| 57 |
+
"step": 1250
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.0665395022845229,
|
| 61 |
+
"grad_norm": 1.6147369146347046,
|
| 62 |
+
"learning_rate": 0.00019998097812268297,
|
| 63 |
+
"loss": 1.2098,
|
| 64 |
+
"step": 1500
|
| 65 |
+
},
|
| 66 |
+
{
|
| 67 |
+
"epoch": 0.0665395022845229,
|
| 68 |
+
"eval_bleu": 0.30711942134345976,
|
| 69 |
+
"step": 1500,
|
| 70 |
+
"swisstext21_eval_bleu": 0.269003899480841
|
| 71 |
+
},
|
| 72 |
+
{
|
| 73 |
+
"epoch": 0.0776294193319434,
|
| 74 |
+
"grad_norm": 2.459263563156128,
|
| 75 |
+
"learning_rate": 0.00019997357263287384,
|
| 76 |
+
"loss": 1.2022,
|
| 77 |
+
"step": 1750
|
| 78 |
+
},
|
| 79 |
+
{
|
| 80 |
+
"epoch": 0.08871933637936388,
|
| 81 |
+
"grad_norm": 2.6925580501556396,
|
| 82 |
+
"learning_rate": 0.00019996495256201206,
|
| 83 |
+
"loss": 1.1799,
|
| 84 |
+
"step": 2000
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 0.08871933637936388,
|
| 88 |
+
"eval_bleu": 0.30569528721761224,
|
| 89 |
+
"step": 2000,
|
| 90 |
+
"swisstext21_eval_bleu": 0.27000582668120887
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 0.09980925342678437,
|
| 94 |
+
"grad_norm": 1.5046218633651733,
|
| 95 |
+
"learning_rate": 0.0001999551180148231,
|
| 96 |
+
"loss": 1.1461,
|
| 97 |
+
"step": 2250
|
| 98 |
+
},
|
| 99 |
+
{
|
| 100 |
+
"epoch": 0.11089917047420485,
|
| 101 |
+
"grad_norm": 1.556638479232788,
|
| 102 |
+
"learning_rate": 0.00019994406911078705,
|
| 103 |
+
"loss": 1.1438,
|
| 104 |
+
"step": 2500
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.11089917047420485,
|
| 108 |
+
"eval_bleu": 0.3315598406945841,
|
| 109 |
+
"step": 2500,
|
| 110 |
+
"swisstext21_eval_bleu": 0.2808034890747164
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 0.12198908752162534,
|
| 114 |
+
"grad_norm": 1.793188452720642,
|
| 115 |
+
"learning_rate": 0.00019993180598413727,
|
| 116 |
+
"loss": 1.1377,
|
| 117 |
+
"step": 2750
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 0.1330790045690458,
|
| 121 |
+
"grad_norm": 1.8901283740997314,
|
| 122 |
+
"learning_rate": 0.00019991832878385877,
|
| 123 |
+
"loss": 1.1102,
|
| 124 |
+
"step": 3000
|
| 125 |
+
},
|
| 126 |
+
{
|
| 127 |
+
"epoch": 0.1330790045690458,
|
| 128 |
+
"eval_bleu": 0.3286964300064891,
|
| 129 |
+
"step": 3000,
|
| 130 |
+
"swisstext21_eval_bleu": 0.2869587788387092
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 0.1441689216164663,
|
| 134 |
+
"grad_norm": 2.159233808517456,
|
| 135 |
+
"learning_rate": 0.00019990363767368634,
|
| 136 |
+
"loss": 1.0988,
|
| 137 |
+
"step": 3250
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 0.1552588386638868,
|
| 141 |
+
"grad_norm": 2.3724594116210938,
|
| 142 |
+
"learning_rate": 0.00019988773283210258,
|
| 143 |
+
"loss": 1.1046,
|
| 144 |
+
"step": 3500
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 0.1552588386638868,
|
| 148 |
+
"eval_bleu": 0.33459475803966965,
|
| 149 |
+
"step": 3500,
|
| 150 |
+
"swisstext21_eval_bleu": 0.29295814557090094
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.16634875571130728,
|
| 154 |
+
"grad_norm": 1.7678097486495972,
|
| 155 |
+
"learning_rate": 0.00019987061445233577,
|
| 156 |
+
"loss": 1.1092,
|
| 157 |
+
"step": 3750
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.17743867275872777,
|
| 161 |
+
"grad_norm": 2.1687381267547607,
|
| 162 |
+
"learning_rate": 0.00019985228274235742,
|
| 163 |
+
"loss": 1.0759,
|
| 164 |
+
"step": 4000
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.17743867275872777,
|
| 168 |
+
"eval_bleu": 0.34760286238068167,
|
| 169 |
+
"step": 4000,
|
| 170 |
+
"swisstext21_eval_bleu": 0.2908780491365115
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.18852858980614826,
|
| 174 |
+
"grad_norm": 1.9985744953155518,
|
| 175 |
+
"learning_rate": 0.00019983273792487989,
|
| 176 |
+
"loss": 1.0808,
|
| 177 |
+
"step": 4250
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.19961850685356874,
|
| 181 |
+
"grad_norm": 1.8689627647399902,
|
| 182 |
+
"learning_rate": 0.0001998119802373536,
|
| 183 |
+
"loss": 1.0705,
|
| 184 |
+
"step": 4500
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.19961850685356874,
|
| 188 |
+
"eval_bleu": 0.34319683823977476,
|
| 189 |
+
"step": 4500,
|
| 190 |
+
"swisstext21_eval_bleu": 0.28856541001986674
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 0.21070842390098923,
|
| 194 |
+
"grad_norm": 2.0760931968688965,
|
| 195 |
+
"learning_rate": 0.00019979000993196412,
|
| 196 |
+
"loss": 1.0473,
|
| 197 |
+
"step": 4750
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 0.2217983409484097,
|
| 201 |
+
"grad_norm": 1.9144140481948853,
|
| 202 |
+
"learning_rate": 0.00019976682727562914,
|
| 203 |
+
"loss": 1.0731,
|
| 204 |
+
"step": 5000
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 0.2217983409484097,
|
| 208 |
+
"eval_bleu": 0.3442873001843364,
|
| 209 |
+
"step": 5000,
|
| 210 |
+
"swisstext21_eval_bleu": 0.28945781960876255
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 0.23288825799583018,
|
| 214 |
+
"grad_norm": 2.0428848266601562,
|
| 215 |
+
"learning_rate": 0.00019974243254999524,
|
| 216 |
+
"loss": 1.0473,
|
| 217 |
+
"step": 5250
|
| 218 |
+
},
|
| 219 |
+
{
|
| 220 |
+
"epoch": 0.24397817504325067,
|
| 221 |
+
"grad_norm": 2.340768814086914,
|
| 222 |
+
"learning_rate": 0.0001997168260514345,
|
| 223 |
+
"loss": 1.0434,
|
| 224 |
+
"step": 5500
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 0.24397817504325067,
|
| 228 |
+
"eval_bleu": 0.3553012116107563,
|
| 229 |
+
"step": 5500,
|
| 230 |
+
"swisstext21_eval_bleu": 0.2917851023260039
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 0.25506809209067116,
|
| 234 |
+
"grad_norm": 2.007636785507202,
|
| 235 |
+
"learning_rate": 0.00019969000809104078,
|
| 236 |
+
"loss": 1.0606,
|
| 237 |
+
"step": 5750
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 0.2661580091380916,
|
| 241 |
+
"grad_norm": 1.9096291065216064,
|
| 242 |
+
"learning_rate": 0.00019966197899462607,
|
| 243 |
+
"loss": 1.0455,
|
| 244 |
+
"step": 6000
|
| 245 |
+
},
|
| 246 |
+
{
|
| 247 |
+
"epoch": 0.2661580091380916,
|
| 248 |
+
"eval_bleu": 0.35127993097271876,
|
| 249 |
+
"step": 6000,
|
| 250 |
+
"swisstext21_eval_bleu": 0.2929261661819239
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 0.27724792618551214,
|
| 254 |
+
"grad_norm": 1.8328126668930054,
|
| 255 |
+
"learning_rate": 0.00019963273910271644,
|
| 256 |
+
"loss": 1.0379,
|
| 257 |
+
"step": 6250
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 0.2883378432329326,
|
| 261 |
+
"grad_norm": 2.2776389122009277,
|
| 262 |
+
"learning_rate": 0.00019960228877054798,
|
| 263 |
+
"loss": 1.0634,
|
| 264 |
+
"step": 6500
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 0.2883378432329326,
|
| 268 |
+
"eval_bleu": 0.3593740208185027,
|
| 269 |
+
"step": 6500,
|
| 270 |
+
"swisstext21_eval_bleu": 0.2988206584421688
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 0.2994277602803531,
|
| 274 |
+
"grad_norm": 2.0759193897247314,
|
| 275 |
+
"learning_rate": 0.0001995706283680624,
|
| 276 |
+
"loss": 1.0503,
|
| 277 |
+
"step": 6750
|
| 278 |
+
},
|
| 279 |
+
{
|
| 280 |
+
"epoch": 0.3105176773277736,
|
| 281 |
+
"grad_norm": 2.1185827255249023,
|
| 282 |
+
"learning_rate": 0.0001995377582799026,
|
| 283 |
+
"loss": 1.034,
|
| 284 |
+
"step": 7000
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 0.3105176773277736,
|
| 288 |
+
"eval_bleu": 0.3624353947369105,
|
| 289 |
+
"step": 7000,
|
| 290 |
+
"swisstext21_eval_bleu": 0.3041434672016612
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.3216075943751941,
|
| 294 |
+
"grad_norm": 2.1475605964660645,
|
| 295 |
+
"learning_rate": 0.00019950367890540798,
|
| 296 |
+
"loss": 0.9958,
|
| 297 |
+
"step": 7250
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.33269751142261456,
|
| 301 |
+
"grad_norm": 2.6123814582824707,
|
| 302 |
+
"learning_rate": 0.00019946839065860956,
|
| 303 |
+
"loss": 0.999,
|
| 304 |
+
"step": 7500
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.33269751142261456,
|
| 308 |
+
"eval_bleu": 0.36432220231953555,
|
| 309 |
+
"step": 7500,
|
| 310 |
+
"swisstext21_eval_bleu": 0.30350836299630507
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.343787428470035,
|
| 314 |
+
"grad_norm": 1.8161005973815918,
|
| 315 |
+
"learning_rate": 0.00019943189396822507,
|
| 316 |
+
"loss": 0.9979,
|
| 317 |
+
"step": 7750
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.35487734551745553,
|
| 321 |
+
"grad_norm": 2.436647653579712,
|
| 322 |
+
"learning_rate": 0.00019939418927765348,
|
| 323 |
+
"loss": 1.0018,
|
| 324 |
+
"step": 8000
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.35487734551745553,
|
| 328 |
+
"eval_bleu": 0.35839847923496915,
|
| 329 |
+
"step": 8000,
|
| 330 |
+
"swisstext21_eval_bleu": 0.3043209488144041
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 0.365967262564876,
|
| 334 |
+
"grad_norm": 2.308076858520508,
|
| 335 |
+
"learning_rate": 0.00019935527704496994,
|
| 336 |
+
"loss": 0.9902,
|
| 337 |
+
"step": 8250
|
| 338 |
+
},
|
| 339 |
+
{
|
| 340 |
+
"epoch": 0.3770571796122965,
|
| 341 |
+
"grad_norm": 2.606699228286743,
|
| 342 |
+
"learning_rate": 0.00019931515774291998,
|
| 343 |
+
"loss": 0.9822,
|
| 344 |
+
"step": 8500
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 0.3770571796122965,
|
| 348 |
+
"eval_bleu": 0.36044795502424115,
|
| 349 |
+
"step": 8500,
|
| 350 |
+
"swisstext21_eval_bleu": 0.3064253970521744
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 0.388147096659717,
|
| 354 |
+
"grad_norm": 2.556300163269043,
|
| 355 |
+
"learning_rate": 0.0001992738318589138,
|
| 356 |
+
"loss": 1.0149,
|
| 357 |
+
"step": 8750
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 0.3992370137071375,
|
| 361 |
+
"grad_norm": 2.8726866245269775,
|
| 362 |
+
"learning_rate": 0.00019923129989502054,
|
| 363 |
+
"loss": 0.9838,
|
| 364 |
+
"step": 9000
|
| 365 |
+
},
|
| 366 |
+
{
|
| 367 |
+
"epoch": 0.3992370137071375,
|
| 368 |
+
"eval_bleu": 0.37244848523119756,
|
| 369 |
+
"step": 9000,
|
| 370 |
+
"swisstext21_eval_bleu": 0.3129379937656933
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 0.41032693075455795,
|
| 374 |
+
"grad_norm": 2.598942279815674,
|
| 375 |
+
"learning_rate": 0.00019918756236796185,
|
| 376 |
+
"loss": 0.9566,
|
| 377 |
+
"step": 9250
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 0.42141684780197847,
|
| 381 |
+
"grad_norm": 2.4860658645629883,
|
| 382 |
+
"learning_rate": 0.0001991426198091059,
|
| 383 |
+
"loss": 0.9935,
|
| 384 |
+
"step": 9500
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 0.42141684780197847,
|
| 388 |
+
"eval_bleu": 0.3737906725916547,
|
| 389 |
+
"step": 9500,
|
| 390 |
+
"swisstext21_eval_bleu": 0.3083854991004289
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 0.43250676484939893,
|
| 394 |
+
"grad_norm": 2.1095190048217773,
|
| 395 |
+
"learning_rate": 0.00019909647276446078,
|
| 396 |
+
"loss": 0.9678,
|
| 397 |
+
"step": 9750
|
| 398 |
+
},
|
| 399 |
+
{
|
| 400 |
+
"epoch": 0.4435966818968194,
|
| 401 |
+
"grad_norm": 2.4634251594543457,
|
| 402 |
+
"learning_rate": 0.00019904912179466794,
|
| 403 |
+
"loss": 0.9953,
|
| 404 |
+
"step": 10000
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 0.4435966818968194,
|
| 408 |
+
"eval_bleu": 0.3665470193277728,
|
| 409 |
+
"step": 10000,
|
| 410 |
+
"swisstext21_eval_bleu": 0.3026636658490007
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 0.4546865989442399,
|
| 414 |
+
"grad_norm": 2.3925271034240723,
|
| 415 |
+
"learning_rate": 0.00019900056747499528,
|
| 416 |
+
"loss": 0.9665,
|
| 417 |
+
"step": 10250
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 0.46577651599166037,
|
| 421 |
+
"grad_norm": 2.091660261154175,
|
| 422 |
+
"learning_rate": 0.00019895081039533028,
|
| 423 |
+
"loss": 0.9742,
|
| 424 |
+
"step": 10500
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"epoch": 0.46577651599166037,
|
| 428 |
+
"eval_bleu": 0.36861395481685405,
|
| 429 |
+
"step": 10500,
|
| 430 |
+
"swisstext21_eval_bleu": 0.3054061636591619
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.4768664330390809,
|
| 434 |
+
"grad_norm": 2.4169013500213623,
|
| 435 |
+
"learning_rate": 0.00019889985116017275,
|
| 436 |
+
"loss": 0.9737,
|
| 437 |
+
"step": 10750
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 0.48795635008650134,
|
| 441 |
+
"grad_norm": 2.641219139099121,
|
| 442 |
+
"learning_rate": 0.00019884769038862752,
|
| 443 |
+
"loss": 0.9644,
|
| 444 |
+
"step": 11000
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.48795635008650134,
|
| 448 |
+
"eval_bleu": 0.36434503459432904,
|
| 449 |
+
"step": 11000,
|
| 450 |
+
"swisstext21_eval_bleu": 0.29839491482098374
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.49904626713392186,
|
| 454 |
+
"grad_norm": 2.1267800331115723,
|
| 455 |
+
"learning_rate": 0.0001987943287143969,
|
| 456 |
+
"loss": 0.9495,
|
| 457 |
+
"step": 11250
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.5101361841813423,
|
| 461 |
+
"grad_norm": 2.882136344909668,
|
| 462 |
+
"learning_rate": 0.00019873976678577303,
|
| 463 |
+
"loss": 0.9463,
|
| 464 |
+
"step": 11500
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.5101361841813423,
|
| 468 |
+
"eval_bleu": 0.3740910429878766,
|
| 469 |
+
"step": 11500,
|
| 470 |
+
"swisstext21_eval_bleu": 0.3090743441007289
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 0.5212261012287628,
|
| 474 |
+
"grad_norm": 3.2668380737304688,
|
| 475 |
+
"learning_rate": 0.00019868400526562986,
|
| 476 |
+
"loss": 0.9392,
|
| 477 |
+
"step": 11750
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 0.5323160182761832,
|
| 481 |
+
"grad_norm": 2.5321474075317383,
|
| 482 |
+
"learning_rate": 0.00019862704483141538,
|
| 483 |
+
"loss": 0.9619,
|
| 484 |
+
"step": 12000
|
| 485 |
+
},
|
| 486 |
+
{
|
| 487 |
+
"epoch": 0.5323160182761832,
|
| 488 |
+
"eval_bleu": 0.36756283810138785,
|
| 489 |
+
"step": 12000,
|
| 490 |
+
"swisstext21_eval_bleu": 0.3048907871619846
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 0.5434059353236038,
|
| 494 |
+
"grad_norm": 2.021146535873413,
|
| 495 |
+
"learning_rate": 0.00019856888617514305,
|
| 496 |
+
"loss": 0.971,
|
| 497 |
+
"step": 12250
|
| 498 |
+
},
|
| 499 |
+
{
|
| 500 |
+
"epoch": 0.5544958523710243,
|
| 501 |
+
"grad_norm": 2.465663194656372,
|
| 502 |
+
"learning_rate": 0.00019850953000338364,
|
| 503 |
+
"loss": 0.9584,
|
| 504 |
+
"step": 12500
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 0.5544958523710243,
|
| 508 |
+
"eval_bleu": 0.3669124274171023,
|
| 509 |
+
"step": 12500,
|
| 510 |
+
"swisstext21_eval_bleu": 0.3044579034347087
|
| 511 |
+
},
|
| 512 |
+
{
|
| 513 |
+
"epoch": 0.5655857694184447,
|
| 514 |
+
"grad_norm": 2.527566432952881,
|
| 515 |
+
"learning_rate": 0.00019844897703725657,
|
| 516 |
+
"loss": 0.9479,
|
| 517 |
+
"step": 12750
|
| 518 |
+
},
|
| 519 |
+
{
|
| 520 |
+
"epoch": 0.5766756864658652,
|
| 521 |
+
"grad_norm": 2.43293833732605,
|
| 522 |
+
"learning_rate": 0.00019838722801242102,
|
| 523 |
+
"loss": 0.9627,
|
| 524 |
+
"step": 13000
|
| 525 |
+
},
|
| 526 |
+
{
|
| 527 |
+
"epoch": 0.5766756864658652,
|
| 528 |
+
"eval_bleu": 0.3896419547996463,
|
| 529 |
+
"step": 13000,
|
| 530 |
+
"swisstext21_eval_bleu": 0.3107247914347159
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 0.5877656035132858,
|
| 534 |
+
"grad_norm": 2.9251341819763184,
|
| 535 |
+
"learning_rate": 0.00019832428367906726,
|
| 536 |
+
"loss": 0.9336,
|
| 537 |
+
"step": 13250
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 0.5988555205607062,
|
| 541 |
+
"grad_norm": 1.883135199546814,
|
| 542 |
+
"learning_rate": 0.00019826014480190735,
|
| 543 |
+
"loss": 0.9602,
|
| 544 |
+
"step": 13500
|
| 545 |
+
},
|
| 546 |
+
{
|
| 547 |
+
"epoch": 0.5988555205607062,
|
| 548 |
+
"eval_bleu": 0.38262014029410524,
|
| 549 |
+
"step": 13500,
|
| 550 |
+
"swisstext21_eval_bleu": 0.3081525753078253
|
| 551 |
+
},
|
| 552 |
+
{
|
| 553 |
+
"epoch": 0.6099454376081267,
|
| 554 |
+
"grad_norm": 2.635322332382202,
|
| 555 |
+
"learning_rate": 0.00019819481216016581,
|
| 556 |
+
"loss": 0.9449,
|
| 557 |
+
"step": 13750
|
| 558 |
+
},
|
| 559 |
+
{
|
| 560 |
+
"epoch": 0.6210353546555472,
|
| 561 |
+
"grad_norm": 2.1079013347625732,
|
| 562 |
+
"learning_rate": 0.00019812828654757036,
|
| 563 |
+
"loss": 0.9389,
|
| 564 |
+
"step": 14000
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 0.6210353546555472,
|
| 568 |
+
"eval_bleu": 0.3855927266497669,
|
| 569 |
+
"step": 14000,
|
| 570 |
+
"swisstext21_eval_bleu": 0.30831521418263236
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 0.6321252717029676,
|
| 574 |
+
"grad_norm": 2.3937461376190186,
|
| 575 |
+
"learning_rate": 0.00019806056877234203,
|
| 576 |
+
"loss": 0.9186,
|
| 577 |
+
"step": 14250
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 0.6432151887503882,
|
| 581 |
+
"grad_norm": 2.3645012378692627,
|
| 582 |
+
"learning_rate": 0.0001979916596571855,
|
| 583 |
+
"loss": 0.9262,
|
| 584 |
+
"step": 14500
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 0.6432151887503882,
|
| 588 |
+
"eval_bleu": 0.38679790640795114,
|
| 589 |
+
"step": 14500,
|
| 590 |
+
"swisstext21_eval_bleu": 0.30320803115793465
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 0.6543051057978087,
|
| 594 |
+
"grad_norm": 2.6536011695861816,
|
| 595 |
+
"learning_rate": 0.00019792156003927908,
|
| 596 |
+
"loss": 0.9367,
|
| 597 |
+
"step": 14750
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.6653950228452291,
|
| 601 |
+
"grad_norm": 2.554568290710449,
|
| 602 |
+
"learning_rate": 0.0001978502707702645,
|
| 603 |
+
"loss": 0.9376,
|
| 604 |
+
"step": 15000
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 0.6653950228452291,
|
| 608 |
+
"eval_bleu": 0.38779759574648714,
|
| 609 |
+
"step": 15000,
|
| 610 |
+
"swisstext21_eval_bleu": 0.31106129606447
|
| 611 |
+
},
|
| 612 |
+
{
|
| 613 |
+
"epoch": 0.6764849398926496,
|
| 614 |
+
"grad_norm": 2.6350646018981934,
|
| 615 |
+
"learning_rate": 0.00019777779271623667,
|
| 616 |
+
"loss": 0.9491,
|
| 617 |
+
"step": 15250
|
| 618 |
+
},
|
| 619 |
+
{
|
| 620 |
+
"epoch": 0.68757485694007,
|
| 621 |
+
"grad_norm": 2.5811619758605957,
|
| 622 |
+
"learning_rate": 0.0001977041267577329,
|
| 623 |
+
"loss": 0.9336,
|
| 624 |
+
"step": 15500
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 0.68757485694007,
|
| 628 |
+
"eval_bleu": 0.3875376232865486,
|
| 629 |
+
"step": 15500,
|
| 630 |
+
"swisstext21_eval_bleu": 0.31103764077844936
|
| 631 |
+
},
|
| 632 |
+
{
|
| 633 |
+
"epoch": 0.6986647739874906,
|
| 634 |
+
"grad_norm": 2.780806064605713,
|
| 635 |
+
"learning_rate": 0.00019762927378972258,
|
| 636 |
+
"loss": 0.8984,
|
| 637 |
+
"step": 15750
|
| 638 |
+
},
|
| 639 |
+
{
|
| 640 |
+
"epoch": 0.7097546910349111,
|
| 641 |
+
"grad_norm": 2.4621236324310303,
|
| 642 |
+
"learning_rate": 0.00019755323472159594,
|
| 643 |
+
"loss": 0.9099,
|
| 644 |
+
"step": 16000
|
| 645 |
+
},
|
| 646 |
+
{
|
| 647 |
+
"epoch": 0.7097546910349111,
|
| 648 |
+
"eval_bleu": 0.38610772811380073,
|
| 649 |
+
"step": 16000,
|
| 650 |
+
"swisstext21_eval_bleu": 0.3148091200691657
|
| 651 |
+
},
|
| 652 |
+
{
|
| 653 |
+
"epoch": 0.7208446080823315,
|
| 654 |
+
"grad_norm": 2.343982219696045,
|
| 655 |
+
"learning_rate": 0.00019747601047715325,
|
| 656 |
+
"loss": 0.9183,
|
| 657 |
+
"step": 16250
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"epoch": 0.731934525129752,
|
| 661 |
+
"grad_norm": 2.3189568519592285,
|
| 662 |
+
"learning_rate": 0.00019739760199459348,
|
| 663 |
+
"loss": 0.9384,
|
| 664 |
+
"step": 16500
|
| 665 |
+
},
|
| 666 |
+
{
|
| 667 |
+
"epoch": 0.731934525129752,
|
| 668 |
+
"eval_bleu": 0.39072795790688153,
|
| 669 |
+
"step": 16500,
|
| 670 |
+
"swisstext21_eval_bleu": 0.3164304311232893
|
| 671 |
+
},
|
| 672 |
+
{
|
| 673 |
+
"epoch": 0.7430244421771726,
|
| 674 |
+
"grad_norm": 3.279153823852539,
|
| 675 |
+
"learning_rate": 0.00019731801022650295,
|
| 676 |
+
"loss": 0.9353,
|
| 677 |
+
"step": 16750
|
| 678 |
+
},
|
| 679 |
+
{
|
| 680 |
+
"epoch": 0.754114359224593,
|
| 681 |
+
"grad_norm": 2.482011079788208,
|
| 682 |
+
"learning_rate": 0.0001972372361398438,
|
| 683 |
+
"loss": 0.8947,
|
| 684 |
+
"step": 17000
|
| 685 |
+
},
|
| 686 |
+
{
|
| 687 |
+
"epoch": 0.754114359224593,
|
| 688 |
+
"eval_bleu": 0.39613006097078557,
|
| 689 |
+
"step": 17000,
|
| 690 |
+
"swisstext21_eval_bleu": 0.3207937159426819
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 0.7652042762720135,
|
| 694 |
+
"grad_norm": 2.11147403717041,
|
| 695 |
+
"learning_rate": 0.000197155280715942,
|
| 696 |
+
"loss": 0.9199,
|
| 697 |
+
"step": 17250
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 0.776294193319434,
|
| 701 |
+
"grad_norm": 2.464308977127075,
|
| 702 |
+
"learning_rate": 0.00019707214495047584,
|
| 703 |
+
"loss": 0.9243,
|
| 704 |
+
"step": 17500
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 0.776294193319434,
|
| 708 |
+
"eval_bleu": 0.38742231043625974,
|
| 709 |
+
"step": 17500,
|
| 710 |
+
"swisstext21_eval_bleu": 0.30187657356550057
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 0.7873841103668544,
|
| 714 |
+
"grad_norm": 2.7994627952575684,
|
| 715 |
+
"learning_rate": 0.00019698782985346343,
|
| 716 |
+
"loss": 0.9019,
|
| 717 |
+
"step": 17750
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 0.798474027414275,
|
| 721 |
+
"grad_norm": 2.315702438354492,
|
| 722 |
+
"learning_rate": 0.0001969023364492507,
|
| 723 |
+
"loss": 0.9211,
|
| 724 |
+
"step": 18000
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 0.798474027414275,
|
| 728 |
+
"eval_bleu": 0.385437022847082,
|
| 729 |
+
"step": 18000,
|
| 730 |
+
"swisstext21_eval_bleu": 0.30319223545431473
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 0.8095639444616954,
|
| 734 |
+
"grad_norm": 2.745156764984131,
|
| 735 |
+
"learning_rate": 0.00019681566577649882,
|
| 736 |
+
"loss": 0.9317,
|
| 737 |
+
"step": 18250
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 0.8206538615091159,
|
| 741 |
+
"grad_norm": 2.8551061153411865,
|
| 742 |
+
"learning_rate": 0.00019672781888817166,
|
| 743 |
+
"loss": 0.913,
|
| 744 |
+
"step": 18500
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 0.8206538615091159,
|
| 748 |
+
"eval_bleu": 0.3928160809300483,
|
| 749 |
+
"step": 18500,
|
| 750 |
+
"swisstext21_eval_bleu": 0.3170691369085918
|
| 751 |
+
},
|
| 752 |
+
{
|
| 753 |
+
"epoch": 0.8317437785565364,
|
| 754 |
+
"grad_norm": 2.358586072921753,
|
| 755 |
+
"learning_rate": 0.00019663879685152287,
|
| 756 |
+
"loss": 0.8985,
|
| 757 |
+
"step": 18750
|
| 758 |
+
},
|
| 759 |
+
{
|
| 760 |
+
"epoch": 0.8428336956039569,
|
| 761 |
+
"grad_norm": 2.516564130783081,
|
| 762 |
+
"learning_rate": 0.0001965486007480831,
|
| 763 |
+
"loss": 0.9167,
|
| 764 |
+
"step": 19000
|
| 765 |
+
},
|
| 766 |
+
{
|
| 767 |
+
"epoch": 0.8428336956039569,
|
| 768 |
+
"eval_bleu": 0.4001014194326336,
|
| 769 |
+
"step": 19000,
|
| 770 |
+
"swisstext21_eval_bleu": 0.3163929503602198
|
| 771 |
+
},
|
| 772 |
+
{
|
| 773 |
+
"epoch": 0.8539236126513774,
|
| 774 |
+
"grad_norm": 3.280510902404785,
|
| 775 |
+
"learning_rate": 0.0001964572316736467,
|
| 776 |
+
"loss": 0.887,
|
| 777 |
+
"step": 19250
|
| 778 |
+
},
|
| 779 |
+
{
|
| 780 |
+
"epoch": 0.8650135296987979,
|
| 781 |
+
"grad_norm": 2.5148253440856934,
|
| 782 |
+
"learning_rate": 0.00019636469073825853,
|
| 783 |
+
"loss": 0.8978,
|
| 784 |
+
"step": 19500
|
| 785 |
+
},
|
| 786 |
+
{
|
| 787 |
+
"epoch": 0.8650135296987979,
|
| 788 |
+
"eval_bleu": 0.3898774974713507,
|
| 789 |
+
"step": 19500,
|
| 790 |
+
"swisstext21_eval_bleu": 0.30876470114528226
|
| 791 |
+
},
|
| 792 |
+
{
|
| 793 |
+
"epoch": 0.8761034467462183,
|
| 794 |
+
"grad_norm": 2.336972951889038,
|
| 795 |
+
"learning_rate": 0.00019627097906620034,
|
| 796 |
+
"loss": 0.9011,
|
| 797 |
+
"step": 19750
|
| 798 |
+
},
|
| 799 |
+
{
|
| 800 |
+
"epoch": 0.8871933637936388,
|
| 801 |
+
"grad_norm": 2.353951930999756,
|
| 802 |
+
"learning_rate": 0.00019617609779597724,
|
| 803 |
+
"loss": 0.8937,
|
| 804 |
+
"step": 20000
|
| 805 |
+
},
|
| 806 |
+
{
|
| 807 |
+
"epoch": 0.8871933637936388,
|
| 808 |
+
"eval_bleu": 0.3855965532285254,
|
| 809 |
+
"step": 20000,
|
| 810 |
+
"swisstext21_eval_bleu": 0.3116831772809819
|
| 811 |
+
},
|
| 812 |
+
{
|
| 813 |
+
"epoch": 0.8982832808410594,
|
| 814 |
+
"grad_norm": 2.4216506481170654,
|
| 815 |
+
"learning_rate": 0.00019608004808030377,
|
| 816 |
+
"loss": 0.9127,
|
| 817 |
+
"step": 20250
|
| 818 |
+
},
|
| 819 |
+
{
|
| 820 |
+
"epoch": 0.9093731978884798,
|
| 821 |
+
"grad_norm": 2.7430005073547363,
|
| 822 |
+
"learning_rate": 0.00019598283108608996,
|
| 823 |
+
"loss": 0.8907,
|
| 824 |
+
"step": 20500
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 0.9093731978884798,
|
| 828 |
+
"eval_bleu": 0.38969433786646573,
|
| 829 |
+
"step": 20500,
|
| 830 |
+
"swisstext21_eval_bleu": 0.30565766059011035
|
| 831 |
+
},
|
| 832 |
+
{
|
| 833 |
+
"epoch": 0.9204631149359003,
|
| 834 |
+
"grad_norm": 2.8106558322906494,
|
| 835 |
+
"learning_rate": 0.00019588444799442718,
|
| 836 |
+
"loss": 0.8992,
|
| 837 |
+
"step": 20750
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 0.9315530319833207,
|
| 841 |
+
"grad_norm": 3.0954487323760986,
|
| 842 |
+
"learning_rate": 0.00019578490000057364,
|
| 843 |
+
"loss": 0.8886,
|
| 844 |
+
"step": 21000
|
| 845 |
+
},
|
| 846 |
+
{
|
| 847 |
+
"epoch": 0.9315530319833207,
|
| 848 |
+
"eval_bleu": 0.39285462338175686,
|
| 849 |
+
"step": 21000,
|
| 850 |
+
"swisstext21_eval_bleu": 0.30451958390372663
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 0.9426429490307412,
|
| 854 |
+
"grad_norm": 3.1268038749694824,
|
| 855 |
+
"learning_rate": 0.00019568418831394008,
|
| 856 |
+
"loss": 0.8599,
|
| 857 |
+
"step": 21250
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 0.9537328660781618,
|
| 861 |
+
"grad_norm": 3.3307135105133057,
|
| 862 |
+
"learning_rate": 0.00019558231415807485,
|
| 863 |
+
"loss": 0.8636,
|
| 864 |
+
"step": 21500
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 0.9537328660781618,
|
| 868 |
+
"eval_bleu": 0.3950705551480444,
|
| 869 |
+
"step": 21500,
|
| 870 |
+
"swisstext21_eval_bleu": 0.31237385318867816
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 0.9648227831255822,
|
| 874 |
+
"grad_norm": 2.284541606903076,
|
| 875 |
+
"learning_rate": 0.00019547927877064928,
|
| 876 |
+
"loss": 0.8719,
|
| 877 |
+
"step": 21750
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 0.9759127001730027,
|
| 881 |
+
"grad_norm": 2.83581805229187,
|
| 882 |
+
"learning_rate": 0.00019537508340344246,
|
| 883 |
+
"loss": 0.9002,
|
| 884 |
+
"step": 22000
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 0.9759127001730027,
|
| 888 |
+
"eval_bleu": 0.3921707237395287,
|
| 889 |
+
"step": 22000,
|
| 890 |
+
"swisstext21_eval_bleu": 0.3145926745569422
|
| 891 |
+
},
|
| 892 |
+
{
|
| 893 |
+
"epoch": 0.9870026172204232,
|
| 894 |
+
"grad_norm": 2.0217525959014893,
|
| 895 |
+
"learning_rate": 0.00019526972932232611,
|
| 896 |
+
"loss": 0.8814,
|
| 897 |
+
"step": 22250
|
| 898 |
+
},
|
| 899 |
+
{
|
| 900 |
+
"epoch": 0.9980925342678437,
|
| 901 |
+
"grad_norm": 2.3832855224609375,
|
| 902 |
+
"learning_rate": 0.0001951632178072492,
|
| 903 |
+
"loss": 0.889,
|
| 904 |
+
"step": 22500
|
| 905 |
+
},
|
| 906 |
+
{
|
| 907 |
+
"epoch": 0.9980925342678437,
|
| 908 |
+
"eval_bleu": 0.38714935228629954,
|
| 909 |
+
"step": 22500,
|
| 910 |
+
"swisstext21_eval_bleu": 0.30922215825464777
|
| 911 |
+
},
|
| 912 |
+
{
|
| 913 |
+
"epoch": 1.009182451315264,
|
| 914 |
+
"grad_norm": 2.6860873699188232,
|
| 915 |
+
"learning_rate": 0.00019505555015222238,
|
| 916 |
+
"loss": 0.8236,
|
| 917 |
+
"step": 22750
|
| 918 |
+
},
|
| 919 |
+
{
|
| 920 |
+
"epoch": 1.0202723683626846,
|
| 921 |
+
"grad_norm": 2.8335115909576416,
|
| 922 |
+
"learning_rate": 0.0001949467276653023,
|
| 923 |
+
"loss": 0.8179,
|
| 924 |
+
"step": 23000
|
| 925 |
+
},
|
| 926 |
+
{
|
| 927 |
+
"epoch": 1.0202723683626846,
|
| 928 |
+
"eval_bleu": 0.38838724982256007,
|
| 929 |
+
"step": 23000,
|
| 930 |
+
"swisstext21_eval_bleu": 0.31582029041010873
|
| 931 |
+
},
|
| 932 |
+
{
|
| 933 |
+
"epoch": 1.0313622854101052,
|
| 934 |
+
"grad_norm": 3.070591449737549,
|
| 935 |
+
"learning_rate": 0.0001948367516685756,
|
| 936 |
+
"loss": 0.859,
|
| 937 |
+
"step": 23250
|
| 938 |
+
},
|
| 939 |
+
{
|
| 940 |
+
"epoch": 1.0424522024575256,
|
| 941 |
+
"grad_norm": 2.3931617736816406,
|
| 942 |
+
"learning_rate": 0.00019472562349814304,
|
| 943 |
+
"loss": 0.8491,
|
| 944 |
+
"step": 23500
|
| 945 |
+
},
|
| 946 |
+
{
|
| 947 |
+
"epoch": 1.0424522024575256,
|
| 948 |
+
"eval_bleu": 0.38063312076817646,
|
| 949 |
+
"step": 23500,
|
| 950 |
+
"swisstext21_eval_bleu": 0.3102516351199856
|
| 951 |
+
},
|
| 952 |
+
{
|
| 953 |
+
"epoch": 1.0535421195049461,
|
| 954 |
+
"grad_norm": 2.414862632751465,
|
| 955 |
+
"learning_rate": 0.00019461334450410314,
|
| 956 |
+
"loss": 0.8583,
|
| 957 |
+
"step": 23750
|
| 958 |
+
},
|
| 959 |
+
{
|
| 960 |
+
"epoch": 1.0646320365523665,
|
| 961 |
+
"grad_norm": 2.6890299320220947,
|
| 962 |
+
"learning_rate": 0.0001944999160505357,
|
| 963 |
+
"loss": 0.8407,
|
| 964 |
+
"step": 24000
|
| 965 |
+
},
|
| 966 |
+
{
|
| 967 |
+
"epoch": 1.0646320365523665,
|
| 968 |
+
"eval_bleu": 0.3982753114306131,
|
| 969 |
+
"step": 24000,
|
| 970 |
+
"swisstext21_eval_bleu": 0.3128261642735386
|
| 971 |
+
},
|
| 972 |
+
{
|
| 973 |
+
"epoch": 1.075721953599787,
|
| 974 |
+
"grad_norm": 2.8066024780273438,
|
| 975 |
+
"learning_rate": 0.00019438533951548546,
|
| 976 |
+
"loss": 0.8521,
|
| 977 |
+
"step": 24250
|
| 978 |
+
},
|
| 979 |
+
{
|
| 980 |
+
"epoch": 1.0868118706472076,
|
| 981 |
+
"grad_norm": 2.857349157333374,
|
| 982 |
+
"learning_rate": 0.00019426961629094515,
|
| 983 |
+
"loss": 0.8455,
|
| 984 |
+
"step": 24500
|
| 985 |
+
},
|
| 986 |
+
{
|
| 987 |
+
"epoch": 1.0868118706472076,
|
| 988 |
+
"eval_bleu": 0.38830354801904543,
|
| 989 |
+
"step": 24500,
|
| 990 |
+
"swisstext21_eval_bleu": 0.3040715120580202
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 1.097901787694628,
|
| 994 |
+
"grad_norm": 2.4639742374420166,
|
| 995 |
+
"learning_rate": 0.00019415274778283875,
|
| 996 |
+
"loss": 0.834,
|
| 997 |
+
"step": 24750
|
| 998 |
+
},
|
| 999 |
+
{
|
| 1000 |
+
"epoch": 1.1089917047420486,
|
| 1001 |
+
"grad_norm": 2.9022200107574463,
|
| 1002 |
+
"learning_rate": 0.00019403473541100414,
|
| 1003 |
+
"loss": 0.8401,
|
| 1004 |
+
"step": 25000
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 1.1089917047420486,
|
| 1008 |
+
"eval_bleu": 0.3936498808339177,
|
| 1009 |
+
"step": 25000,
|
| 1010 |
+
"swisstext21_eval_bleu": 0.30703476528382184
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 1.1200816217894691,
|
| 1014 |
+
"grad_norm": 2.418813943862915,
|
| 1015 |
+
"learning_rate": 0.00019391558060917615,
|
| 1016 |
+
"loss": 0.8549,
|
| 1017 |
+
"step": 25250
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 1.1311715388368895,
|
| 1021 |
+
"grad_norm": 3.5514161586761475,
|
| 1022 |
+
"learning_rate": 0.00019379528482496905,
|
| 1023 |
+
"loss": 0.8373,
|
| 1024 |
+
"step": 25500
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 1.1311715388368895,
|
| 1028 |
+
"eval_bleu": 0.3949608777582217,
|
| 1029 |
+
"step": 25500,
|
| 1030 |
+
"swisstext21_eval_bleu": 0.2991127273200187
|
| 1031 |
+
},
|
| 1032 |
+
{
|
| 1033 |
+
"epoch": 1.14226145588431,
|
| 1034 |
+
"grad_norm": 2.8393402099609375,
|
| 1035 |
+
"learning_rate": 0.0001936738495198588,
|
| 1036 |
+
"loss": 0.8305,
|
| 1037 |
+
"step": 25750
|
| 1038 |
+
},
|
| 1039 |
+
{
|
| 1040 |
+
"epoch": 1.1533513729317304,
|
| 1041 |
+
"grad_norm": 2.3504981994628906,
|
| 1042 |
+
"learning_rate": 0.00019355127616916558,
|
| 1043 |
+
"loss": 0.8391,
|
| 1044 |
+
"step": 26000
|
| 1045 |
+
},
|
| 1046 |
+
{
|
| 1047 |
+
"epoch": 1.1533513729317304,
|
| 1048 |
+
"eval_bleu": 0.39885045498118465,
|
| 1049 |
+
"step": 26000,
|
| 1050 |
+
"swisstext21_eval_bleu": 0.3008743660411916
|
| 1051 |
+
},
|
| 1052 |
+
{
|
| 1053 |
+
"epoch": 1.164441289979151,
|
| 1054 |
+
"grad_norm": 3.1513872146606445,
|
| 1055 |
+
"learning_rate": 0.00019342756626203553,
|
| 1056 |
+
"loss": 0.8151,
|
| 1057 |
+
"step": 26250
|
| 1058 |
+
},
|
| 1059 |
+
{
|
| 1060 |
+
"epoch": 1.1755312070265713,
|
| 1061 |
+
"grad_norm": 3.1882948875427246,
|
| 1062 |
+
"learning_rate": 0.00019330272130142298,
|
| 1063 |
+
"loss": 0.8451,
|
| 1064 |
+
"step": 26500
|
| 1065 |
+
},
|
| 1066 |
+
{
|
| 1067 |
+
"epoch": 1.1755312070265713,
|
| 1068 |
+
"eval_bleu": 0.39897615108571005,
|
| 1069 |
+
"step": 26500,
|
| 1070 |
+
"swisstext21_eval_bleu": 0.30551010767982617
|
| 1071 |
+
},
|
| 1072 |
+
{
|
| 1073 |
+
"epoch": 1.186621124073992,
|
| 1074 |
+
"grad_norm": 2.0949442386627197,
|
| 1075 |
+
"learning_rate": 0.00019317674280407203,
|
| 1076 |
+
"loss": 0.8558,
|
| 1077 |
+
"step": 26750
|
| 1078 |
+
},
|
| 1079 |
+
{
|
| 1080 |
+
"epoch": 1.1977110411214125,
|
| 1081 |
+
"grad_norm": 2.0875446796417236,
|
| 1082 |
+
"learning_rate": 0.00019304963230049808,
|
| 1083 |
+
"loss": 0.8596,
|
| 1084 |
+
"step": 27000
|
| 1085 |
+
},
|
| 1086 |
+
{
|
| 1087 |
+
"epoch": 1.1977110411214125,
|
| 1088 |
+
"eval_bleu": 0.3997092911184819,
|
| 1089 |
+
"step": 27000,
|
| 1090 |
+
"swisstext21_eval_bleu": 0.31326727973416657
|
| 1091 |
+
},
|
| 1092 |
+
{
|
| 1093 |
+
"epoch": 1.2088009581688328,
|
| 1094 |
+
"grad_norm": 2.8534743785858154,
|
| 1095 |
+
"learning_rate": 0.00019292139133496932,
|
| 1096 |
+
"loss": 0.8365,
|
| 1097 |
+
"step": 27250
|
| 1098 |
+
},
|
| 1099 |
+
{
|
| 1100 |
+
"epoch": 1.2198908752162534,
|
| 1101 |
+
"grad_norm": 3.247786521911621,
|
| 1102 |
+
"learning_rate": 0.00019279202146548795,
|
| 1103 |
+
"loss": 0.848,
|
| 1104 |
+
"step": 27500
|
| 1105 |
+
},
|
| 1106 |
+
{
|
| 1107 |
+
"epoch": 1.2198908752162534,
|
| 1108 |
+
"eval_bleu": 0.3939229666106703,
|
| 1109 |
+
"step": 27500,
|
| 1110 |
+
"swisstext21_eval_bleu": 0.31058011025928695
|
| 1111 |
+
},
|
| 1112 |
+
{
|
| 1113 |
+
"epoch": 1.230980792263674,
|
| 1114 |
+
"grad_norm": 2.812893867492676,
|
| 1115 |
+
"learning_rate": 0.00019266152426377134,
|
| 1116 |
+
"loss": 0.8296,
|
| 1117 |
+
"step": 27750
|
| 1118 |
+
},
|
| 1119 |
+
{
|
| 1120 |
+
"epoch": 1.2420707093110943,
|
| 1121 |
+
"grad_norm": 3.173842430114746,
|
| 1122 |
+
"learning_rate": 0.00019252990131523264,
|
| 1123 |
+
"loss": 0.843,
|
| 1124 |
+
"step": 28000
|
| 1125 |
+
},
|
| 1126 |
+
{
|
| 1127 |
+
"epoch": 1.2420707093110943,
|
| 1128 |
+
"eval_bleu": 0.39727487714618787,
|
| 1129 |
+
"step": 28000,
|
| 1130 |
+
"swisstext21_eval_bleu": 0.30997666108081895
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 1.2531606263585149,
|
| 1134 |
+
"grad_norm": 2.501375436782837,
|
| 1135 |
+
"learning_rate": 0.00019239715421896195,
|
| 1136 |
+
"loss": 0.8296,
|
| 1137 |
+
"step": 28250
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 1.2642505434059355,
|
| 1141 |
+
"grad_norm": 2.394441843032837,
|
| 1142 |
+
"learning_rate": 0.00019226328458770648,
|
| 1143 |
+
"loss": 0.8259,
|
| 1144 |
+
"step": 28500
|
| 1145 |
+
},
|
| 1146 |
+
{
|
| 1147 |
+
"epoch": 1.2642505434059355,
|
| 1148 |
+
"eval_bleu": 0.3951440149567978,
|
| 1149 |
+
"step": 28500,
|
| 1150 |
+
"swisstext21_eval_bleu": 0.3082165747905684
|
| 1151 |
+
},
|
| 1152 |
+
{
|
| 1153 |
+
"epoch": 1.2753404604533558,
|
| 1154 |
+
"grad_norm": 2.3463571071624756,
|
| 1155 |
+
"learning_rate": 0.00019212829404785127,
|
| 1156 |
+
"loss": 0.8372,
|
| 1157 |
+
"step": 28750
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 1.2864303775007762,
|
| 1161 |
+
"grad_norm": 2.619544744491577,
|
| 1162 |
+
"learning_rate": 0.0001919921842393992,
|
| 1163 |
+
"loss": 0.8499,
|
| 1164 |
+
"step": 29000
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 1.2864303775007762,
|
| 1168 |
+
"eval_bleu": 0.3997716708387876,
|
| 1169 |
+
"step": 29000,
|
| 1170 |
+
"swisstext21_eval_bleu": 0.31001057617223277
|
| 1171 |
+
},
|
| 1172 |
+
{
|
| 1173 |
+
"epoch": 1.2975202945481967,
|
| 1174 |
+
"grad_norm": 2.7703518867492676,
|
| 1175 |
+
"learning_rate": 0.00019185495681595121,
|
| 1176 |
+
"loss": 0.8255,
|
| 1177 |
+
"step": 29250
|
| 1178 |
+
},
|
| 1179 |
+
{
|
| 1180 |
+
"epoch": 1.3086102115956173,
|
| 1181 |
+
"grad_norm": 2.2880280017852783,
|
| 1182 |
+
"learning_rate": 0.00019171661344468625,
|
| 1183 |
+
"loss": 0.843,
|
| 1184 |
+
"step": 29500
|
| 1185 |
+
},
|
| 1186 |
+
{
|
| 1187 |
+
"epoch": 1.3086102115956173,
|
| 1188 |
+
"eval_bleu": 0.3990674495806238,
|
| 1189 |
+
"step": 29500,
|
| 1190 |
+
"swisstext21_eval_bleu": 0.3045854425199765
|
| 1191 |
+
},
|
| 1192 |
+
{
|
| 1193 |
+
"epoch": 1.3197001286430377,
|
| 1194 |
+
"grad_norm": 2.427645206451416,
|
| 1195 |
+
"learning_rate": 0.00019157715580634082,
|
| 1196 |
+
"loss": 0.8331,
|
| 1197 |
+
"step": 29750
|
| 1198 |
+
},
|
| 1199 |
+
{
|
| 1200 |
+
"epoch": 1.3307900456904582,
|
| 1201 |
+
"grad_norm": 2.514282703399658,
|
| 1202 |
+
"learning_rate": 0.00019143658559518873,
|
| 1203 |
+
"loss": 0.8303,
|
| 1204 |
+
"step": 30000
|
| 1205 |
+
},
|
| 1206 |
+
{
|
| 1207 |
+
"epoch": 1.3307900456904582,
|
| 1208 |
+
"eval_bleu": 0.39857650020404584,
|
| 1209 |
+
"step": 30000,
|
| 1210 |
+
"swisstext21_eval_bleu": 0.30778486046472064
|
| 1211 |
+
},
|
| 1212 |
+
{
|
| 1213 |
+
"epoch": 1.3418799627378788,
|
| 1214 |
+
"grad_norm": 2.3313047885894775,
|
| 1215 |
+
"learning_rate": 0.00019129490451902042,
|
| 1216 |
+
"loss": 0.7886,
|
| 1217 |
+
"step": 30250
|
| 1218 |
+
},
|
| 1219 |
+
{
|
| 1220 |
+
"epoch": 1.3529698797852991,
|
| 1221 |
+
"grad_norm": 2.250128746032715,
|
| 1222 |
+
"learning_rate": 0.00019115211429912237,
|
| 1223 |
+
"loss": 0.802,
|
| 1224 |
+
"step": 30500
|
| 1225 |
+
},
|
| 1226 |
+
{
|
| 1227 |
+
"epoch": 1.3529698797852991,
|
| 1228 |
+
"eval_bleu": 0.40068405768800824,
|
| 1229 |
+
"step": 30500,
|
| 1230 |
+
"swisstext21_eval_bleu": 0.3109150438405035
|
| 1231 |
+
},
|
| 1232 |
+
{
|
| 1233 |
+
"epoch": 1.3640597968327197,
|
| 1234 |
+
"grad_norm": 4.564970016479492,
|
| 1235 |
+
"learning_rate": 0.0001910082166702559,
|
| 1236 |
+
"loss": 0.7921,
|
| 1237 |
+
"step": 30750
|
| 1238 |
+
},
|
| 1239 |
+
{
|
| 1240 |
+
"epoch": 1.3751497138801403,
|
| 1241 |
+
"grad_norm": 3.340827703475952,
|
| 1242 |
+
"learning_rate": 0.00019086321338063642,
|
| 1243 |
+
"loss": 0.8016,
|
| 1244 |
+
"step": 31000
|
| 1245 |
+
},
|
| 1246 |
+
{
|
| 1247 |
+
"epoch": 1.3751497138801403,
|
| 1248 |
+
"eval_bleu": 0.3907764612746887,
|
| 1249 |
+
"step": 31000,
|
| 1250 |
+
"swisstext21_eval_bleu": 0.307514371169132
|
| 1251 |
+
},
|
| 1252 |
+
{
|
| 1253 |
+
"epoch": 1.3862396309275606,
|
| 1254 |
+
"grad_norm": 3.442969560623169,
|
| 1255 |
+
"learning_rate": 0.00019071710619191192,
|
| 1256 |
+
"loss": 0.8281,
|
| 1257 |
+
"step": 31250
|
| 1258 |
+
},
|
| 1259 |
+
{
|
| 1260 |
+
"epoch": 1.3973295479749812,
|
| 1261 |
+
"grad_norm": 3.0045955181121826,
|
| 1262 |
+
"learning_rate": 0.00019056989687914178,
|
| 1263 |
+
"loss": 0.82,
|
| 1264 |
+
"step": 31500
|
| 1265 |
+
},
|
| 1266 |
+
{
|
| 1267 |
+
"epoch": 1.3973295479749812,
|
| 1268 |
+
"eval_bleu": 0.4070777777979427,
|
| 1269 |
+
"step": 31500,
|
| 1270 |
+
"swisstext21_eval_bleu": 0.3133119978708261
|
| 1271 |
+
},
|
| 1272 |
+
{
|
| 1273 |
+
"epoch": 1.4084194650224016,
|
| 1274 |
+
"grad_norm": 2.9076082706451416,
|
| 1275 |
+
"learning_rate": 0.000190421587230775,
|
| 1276 |
+
"loss": 0.7708,
|
| 1277 |
+
"step": 31750
|
| 1278 |
+
},
|
| 1279 |
+
{
|
| 1280 |
+
"epoch": 1.4195093820698221,
|
| 1281 |
+
"grad_norm": 2.446475028991699,
|
| 1282 |
+
"learning_rate": 0.0001902721790486287,
|
| 1283 |
+
"loss": 0.8103,
|
| 1284 |
+
"step": 32000
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 1.4195093820698221,
|
| 1288 |
+
"eval_bleu": 0.40894432730315045,
|
| 1289 |
+
"step": 32000,
|
| 1290 |
+
"swisstext21_eval_bleu": 0.31024336675207975
|
| 1291 |
+
},
|
| 1292 |
+
{
|
| 1293 |
+
"epoch": 1.4305992991172425,
|
| 1294 |
+
"grad_norm": 2.476989507675171,
|
| 1295 |
+
"learning_rate": 0.00019012167414786602,
|
| 1296 |
+
"loss": 0.8046,
|
| 1297 |
+
"step": 32250
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 1.441689216164663,
|
| 1301 |
+
"grad_norm": 2.7591421604156494,
|
| 1302 |
+
"learning_rate": 0.00018997007435697416,
|
| 1303 |
+
"loss": 0.8286,
|
| 1304 |
+
"step": 32500
|
| 1305 |
+
},
|
| 1306 |
+
{
|
| 1307 |
+
"epoch": 1.441689216164663,
|
| 1308 |
+
"eval_bleu": 0.4030474309836763,
|
| 1309 |
+
"step": 32500,
|
| 1310 |
+
"swisstext21_eval_bleu": 0.3089112511767638
|
| 1311 |
+
},
|
| 1312 |
+
{
|
| 1313 |
+
"epoch": 1.4527791332120836,
|
| 1314 |
+
"grad_norm": 3.6329638957977295,
|
| 1315 |
+
"learning_rate": 0.00018981738151774223,
|
| 1316 |
+
"loss": 0.8007,
|
| 1317 |
+
"step": 32750
|
| 1318 |
+
},
|
| 1319 |
+
{
|
| 1320 |
+
"epoch": 1.463869050259504,
|
| 1321 |
+
"grad_norm": 3.2174901962280273,
|
| 1322 |
+
"learning_rate": 0.00018966359748523882,
|
| 1323 |
+
"loss": 0.8132,
|
| 1324 |
+
"step": 33000
|
| 1325 |
+
},
|
| 1326 |
+
{
|
| 1327 |
+
"epoch": 1.463869050259504,
|
| 1328 |
+
"eval_bleu": 0.40291037790441286,
|
| 1329 |
+
"step": 33000,
|
| 1330 |
+
"swisstext21_eval_bleu": 0.30738722055101736
|
| 1331 |
+
},
|
| 1332 |
+
{
|
| 1333 |
+
"epoch": 1.4749589673069246,
|
| 1334 |
+
"grad_norm": 3.520242929458618,
|
| 1335 |
+
"learning_rate": 0.0001895087241277893,
|
| 1336 |
+
"loss": 0.8109,
|
| 1337 |
+
"step": 33250
|
| 1338 |
+
},
|
| 1339 |
+
{
|
| 1340 |
+
"epoch": 1.4860488843543451,
|
| 1341 |
+
"grad_norm": 2.2728867530822754,
|
| 1342 |
+
"learning_rate": 0.00018935276332695343,
|
| 1343 |
+
"loss": 0.7985,
|
| 1344 |
+
"step": 33500
|
| 1345 |
+
},
|
| 1346 |
+
{
|
| 1347 |
+
"epoch": 1.4860488843543451,
|
| 1348 |
+
"eval_bleu": 0.40080037575712874,
|
| 1349 |
+
"step": 33500,
|
| 1350 |
+
"swisstext21_eval_bleu": 0.30433362941606407
|
| 1351 |
+
},
|
| 1352 |
+
{
|
| 1353 |
+
"epoch": 1.4971388014017655,
|
| 1354 |
+
"grad_norm": 2.971421718597412,
|
| 1355 |
+
"learning_rate": 0.0001891957169775023,
|
| 1356 |
+
"loss": 0.7932,
|
| 1357 |
+
"step": 33750
|
| 1358 |
+
},
|
| 1359 |
+
{
|
| 1360 |
+
"epoch": 1.508228718449186,
|
| 1361 |
+
"grad_norm": 2.5034966468811035,
|
| 1362 |
+
"learning_rate": 0.00018903758698739527,
|
| 1363 |
+
"loss": 0.7919,
|
| 1364 |
+
"step": 34000
|
| 1365 |
+
},
|
| 1366 |
+
{
|
| 1367 |
+
"epoch": 1.508228718449186,
|
| 1368 |
+
"eval_bleu": 0.40767117955379845,
|
| 1369 |
+
"step": 34000,
|
| 1370 |
+
"swisstext21_eval_bleu": 0.30671494308688607
|
| 1371 |
+
},
|
| 1372 |
+
{
|
| 1373 |
+
"epoch": 1.5193186354966066,
|
| 1374 |
+
"grad_norm": 2.4627349376678467,
|
| 1375 |
+
"learning_rate": 0.000188878375277757,
|
| 1376 |
+
"loss": 0.783,
|
| 1377 |
+
"step": 34250
|
| 1378 |
+
},
|
| 1379 |
+
{
|
| 1380 |
+
"epoch": 1.530408552544027,
|
| 1381 |
+
"grad_norm": 2.71600604057312,
|
| 1382 |
+
"learning_rate": 0.00018871808378285388,
|
| 1383 |
+
"loss": 0.8108,
|
| 1384 |
+
"step": 34500
|
| 1385 |
+
},
|
| 1386 |
+
{
|
| 1387 |
+
"epoch": 1.530408552544027,
|
| 1388 |
+
"eval_bleu": 0.394797486057362,
|
| 1389 |
+
"step": 34500,
|
| 1390 |
+
"swisstext21_eval_bleu": 0.3087865162589988
|
| 1391 |
+
},
|
| 1392 |
+
{
|
| 1393 |
+
"epoch": 1.5414984695914473,
|
| 1394 |
+
"grad_norm": 3.0158140659332275,
|
| 1395 |
+
"learning_rate": 0.00018855671445007076,
|
| 1396 |
+
"loss": 0.8127,
|
| 1397 |
+
"step": 34750
|
| 1398 |
+
},
|
| 1399 |
+
{
|
| 1400 |
+
"epoch": 1.552588386638868,
|
| 1401 |
+
"grad_norm": 2.9670796394348145,
|
| 1402 |
+
"learning_rate": 0.00018839426923988696,
|
| 1403 |
+
"loss": 0.8098,
|
| 1404 |
+
"step": 35000
|
| 1405 |
+
},
|
| 1406 |
+
{
|
| 1407 |
+
"epoch": 1.552588386638868,
|
| 1408 |
+
"eval_bleu": 0.3992581934406838,
|
| 1409 |
+
"step": 35000,
|
| 1410 |
+
"swisstext21_eval_bleu": 0.3025072689523983
|
| 1411 |
+
},
|
| 1412 |
+
{
|
| 1413 |
+
"epoch": 1.5636783036862885,
|
| 1414 |
+
"grad_norm": 2.3080224990844727,
|
| 1415 |
+
"learning_rate": 0.0001882307501258529,
|
| 1416 |
+
"loss": 0.7835,
|
| 1417 |
+
"step": 35250
|
| 1418 |
+
},
|
| 1419 |
+
{
|
| 1420 |
+
"epoch": 1.5747682207337088,
|
| 1421 |
+
"grad_norm": 3.082775831222534,
|
| 1422 |
+
"learning_rate": 0.0001880661590945657,
|
| 1423 |
+
"loss": 0.8369,
|
| 1424 |
+
"step": 35500
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 1.5747682207337088,
|
| 1428 |
+
"eval_bleu": 0.4048045366265125,
|
| 1429 |
+
"step": 35500,
|
| 1430 |
+
"swisstext21_eval_bleu": 0.3005292082411897
|
| 1431 |
+
},
|
| 1432 |
+
{
|
| 1433 |
+
"epoch": 1.5858581377811294,
|
| 1434 |
+
"grad_norm": 2.1708056926727295,
|
| 1435 |
+
"learning_rate": 0.00018790049814564527,
|
| 1436 |
+
"loss": 0.7855,
|
| 1437 |
+
"step": 35750
|
| 1438 |
+
},
|
| 1439 |
+
{
|
| 1440 |
+
"epoch": 1.59694805482855,
|
| 1441 |
+
"grad_norm": 3.3110837936401367,
|
| 1442 |
+
"learning_rate": 0.00018773376929171005,
|
| 1443 |
+
"loss": 0.8195,
|
| 1444 |
+
"step": 36000
|
| 1445 |
+
},
|
| 1446 |
+
{
|
| 1447 |
+
"epoch": 1.59694805482855,
|
| 1448 |
+
"eval_bleu": 0.40120545805677965,
|
| 1449 |
+
"step": 36000,
|
| 1450 |
+
"swisstext21_eval_bleu": 0.30819612905632277
|
| 1451 |
+
},
|
| 1452 |
+
{
|
| 1453 |
+
"epoch": 1.6080379718759703,
|
| 1454 |
+
"grad_norm": 4.1916632652282715,
|
| 1455 |
+
"learning_rate": 0.0001875659745583524,
|
| 1456 |
+
"loss": 0.8054,
|
| 1457 |
+
"step": 36250
|
| 1458 |
+
},
|
| 1459 |
+
{
|
| 1460 |
+
"epoch": 1.6191278889233909,
|
| 1461 |
+
"grad_norm": 3.0245726108551025,
|
| 1462 |
+
"learning_rate": 0.00018739711598411406,
|
| 1463 |
+
"loss": 0.794,
|
| 1464 |
+
"step": 36500
|
| 1465 |
+
},
|
| 1466 |
+
{
|
| 1467 |
+
"epoch": 1.6191278889233909,
|
| 1468 |
+
"eval_bleu": 0.3979401149463107,
|
| 1469 |
+
"step": 36500,
|
| 1470 |
+
"swisstext21_eval_bleu": 0.3101184244616529
|
| 1471 |
+
},
|
| 1472 |
+
{
|
| 1473 |
+
"epoch": 1.6302178059708115,
|
| 1474 |
+
"grad_norm": 2.3407862186431885,
|
| 1475 |
+
"learning_rate": 0.00018722719562046141,
|
| 1476 |
+
"loss": 0.7961,
|
| 1477 |
+
"step": 36750
|
| 1478 |
+
},
|
| 1479 |
+
{
|
| 1480 |
+
"epoch": 1.6413077230182318,
|
| 1481 |
+
"grad_norm": 2.649019956588745,
|
| 1482 |
+
"learning_rate": 0.00018705621553176066,
|
| 1483 |
+
"loss": 0.787,
|
| 1484 |
+
"step": 37000
|
| 1485 |
+
},
|
| 1486 |
+
{
|
| 1487 |
+
"epoch": 1.6413077230182318,
|
| 1488 |
+
"eval_bleu": 0.4092604945594542,
|
| 1489 |
+
"step": 37000,
|
| 1490 |
+
"swisstext21_eval_bleu": 0.3129861922910357
|
| 1491 |
+
},
|
| 1492 |
+
{
|
| 1493 |
+
"epoch": 1.6523976400656522,
|
| 1494 |
+
"grad_norm": 3.1469483375549316,
|
| 1495 |
+
"learning_rate": 0.0001868841777952524,
|
| 1496 |
+
"loss": 0.8151,
|
| 1497 |
+
"step": 37250
|
| 1498 |
+
},
|
| 1499 |
+
{
|
| 1500 |
+
"epoch": 1.663487557113073,
|
| 1501 |
+
"grad_norm": 4.49592924118042,
|
| 1502 |
+
"learning_rate": 0.00018671108450102678,
|
| 1503 |
+
"loss": 0.7961,
|
| 1504 |
+
"step": 37500
|
| 1505 |
+
},
|
| 1506 |
+
{
|
| 1507 |
+
"epoch": 1.663487557113073,
|
| 1508 |
+
"eval_bleu": 0.40106080170968306,
|
| 1509 |
+
"step": 37500,
|
| 1510 |
+
"swisstext21_eval_bleu": 0.31557875920893397
|
| 1511 |
+
},
|
| 1512 |
+
{
|
| 1513 |
+
"epoch": 1.6745774741604933,
|
| 1514 |
+
"grad_norm": 2.7781357765197754,
|
| 1515 |
+
"learning_rate": 0.00018653693775199797,
|
| 1516 |
+
"loss": 0.8111,
|
| 1517 |
+
"step": 37750
|
| 1518 |
+
},
|
| 1519 |
+
{
|
| 1520 |
+
"epoch": 1.6856673912079136,
|
| 1521 |
+
"grad_norm": 3.807218313217163,
|
| 1522 |
+
"learning_rate": 0.00018636173966387842,
|
| 1523 |
+
"loss": 0.8126,
|
| 1524 |
+
"step": 38000
|
| 1525 |
+
},
|
| 1526 |
+
{
|
| 1527 |
+
"epoch": 1.6856673912079136,
|
| 1528 |
+
"eval_bleu": 0.4042668150834047,
|
| 1529 |
+
"step": 38000,
|
| 1530 |
+
"swisstext21_eval_bleu": 0.3078849028439319
|
| 1531 |
+
},
|
| 1532 |
+
{
|
| 1533 |
+
"epoch": 1.6967573082553342,
|
| 1534 |
+
"grad_norm": 3.1599435806274414,
|
| 1535 |
+
"learning_rate": 0.00018618549236515346,
|
| 1536 |
+
"loss": 0.7728,
|
| 1537 |
+
"step": 38250
|
| 1538 |
+
},
|
| 1539 |
+
{
|
| 1540 |
+
"epoch": 1.7078472253027548,
|
| 1541 |
+
"grad_norm": 2.7357876300811768,
|
| 1542 |
+
"learning_rate": 0.00018600819799705523,
|
| 1543 |
+
"loss": 0.7825,
|
| 1544 |
+
"step": 38500
|
| 1545 |
+
},
|
| 1546 |
+
{
|
| 1547 |
+
"epoch": 1.7078472253027548,
|
| 1548 |
+
"eval_bleu": 0.40671098856376503,
|
| 1549 |
+
"step": 38500,
|
| 1550 |
+
"swisstext21_eval_bleu": 0.30567470776676137
|
| 1551 |
+
},
|
| 1552 |
+
{
|
| 1553 |
+
"epoch": 1.7189371423501751,
|
| 1554 |
+
"grad_norm": 2.384441375732422,
|
| 1555 |
+
"learning_rate": 0.00018582985871353684,
|
| 1556 |
+
"loss": 0.7965,
|
| 1557 |
+
"step": 38750
|
| 1558 |
+
},
|
| 1559 |
+
{
|
| 1560 |
+
"epoch": 1.7300270593975957,
|
| 1561 |
+
"grad_norm": 2.4744198322296143,
|
| 1562 |
+
"learning_rate": 0.00018565047668124592,
|
| 1563 |
+
"loss": 0.8038,
|
| 1564 |
+
"step": 39000
|
| 1565 |
+
},
|
| 1566 |
+
{
|
| 1567 |
+
"epoch": 1.7300270593975957,
|
| 1568 |
+
"eval_bleu": 0.4112997039832828,
|
| 1569 |
+
"step": 39000,
|
| 1570 |
+
"swisstext21_eval_bleu": 0.31252497596244544
|
| 1571 |
+
},
|
| 1572 |
+
{
|
| 1573 |
+
"epoch": 1.7411169764450163,
|
| 1574 |
+
"grad_norm": 3.300543785095215,
|
| 1575 |
+
"learning_rate": 0.00018547005407949866,
|
| 1576 |
+
"loss": 0.8184,
|
| 1577 |
+
"step": 39250
|
| 1578 |
+
},
|
| 1579 |
+
{
|
| 1580 |
+
"epoch": 1.7522068934924366,
|
| 1581 |
+
"grad_norm": 3.401453733444214,
|
| 1582 |
+
"learning_rate": 0.00018528859310025305,
|
| 1583 |
+
"loss": 0.7883,
|
| 1584 |
+
"step": 39500
|
| 1585 |
+
},
|
| 1586 |
+
{
|
| 1587 |
+
"epoch": 1.7522068934924366,
|
| 1588 |
+
"eval_bleu": 0.403520670403573,
|
| 1589 |
+
"step": 39500,
|
| 1590 |
+
"swisstext21_eval_bleu": 0.31147494554557736
|
| 1591 |
+
},
|
| 1592 |
+
{
|
| 1593 |
+
"epoch": 1.7632968105398572,
|
| 1594 |
+
"grad_norm": 2.518880844116211,
|
| 1595 |
+
"learning_rate": 0.00018510609594808234,
|
| 1596 |
+
"loss": 0.7991,
|
| 1597 |
+
"step": 39750
|
| 1598 |
+
},
|
| 1599 |
+
{
|
| 1600 |
+
"epoch": 1.7743867275872778,
|
| 1601 |
+
"grad_norm": 1.9717811346054077,
|
| 1602 |
+
"learning_rate": 0.00018492256484014833,
|
| 1603 |
+
"loss": 0.7988,
|
| 1604 |
+
"step": 40000
|
| 1605 |
+
},
|
| 1606 |
+
{
|
| 1607 |
+
"epoch": 1.7743867275872778,
|
| 1608 |
+
"eval_bleu": 0.4059971537992098,
|
| 1609 |
+
"step": 40000,
|
| 1610 |
+
"swisstext21_eval_bleu": 0.3025584886012487
|
| 1611 |
+
},
|
| 1612 |
+
{
|
| 1613 |
+
"epoch": 1.7854766446346981,
|
| 1614 |
+
"grad_norm": 2.906183958053589,
|
| 1615 |
+
"learning_rate": 0.00018473800200617438,
|
| 1616 |
+
"loss": 0.7776,
|
| 1617 |
+
"step": 40250
|
| 1618 |
+
},
|
| 1619 |
+
{
|
| 1620 |
+
"epoch": 1.7965665616821185,
|
| 1621 |
+
"grad_norm": 2.767038106918335,
|
| 1622 |
+
"learning_rate": 0.0001845524096884182,
|
| 1623 |
+
"loss": 0.7906,
|
| 1624 |
+
"step": 40500
|
| 1625 |
+
},
|
| 1626 |
+
{
|
| 1627 |
+
"epoch": 1.7965665616821185,
|
| 1628 |
+
"eval_bleu": 0.40377715553875726,
|
| 1629 |
+
"step": 40500,
|
| 1630 |
+
"swisstext21_eval_bleu": 0.3042143768393741
|
| 1631 |
+
},
|
| 1632 |
+
{
|
| 1633 |
+
"epoch": 1.807656478729539,
|
| 1634 |
+
"grad_norm": 2.921994686126709,
|
| 1635 |
+
"learning_rate": 0.00018436579014164482,
|
| 1636 |
+
"loss": 0.8264,
|
| 1637 |
+
"step": 40750
|
| 1638 |
+
},
|
| 1639 |
+
{
|
| 1640 |
+
"epoch": 1.8187463957769596,
|
| 1641 |
+
"grad_norm": 1.9619659185409546,
|
| 1642 |
+
"learning_rate": 0.00018417814563309904,
|
| 1643 |
+
"loss": 0.8021,
|
| 1644 |
+
"step": 41000
|
| 1645 |
+
},
|
| 1646 |
+
{
|
| 1647 |
+
"epoch": 1.8187463957769596,
|
| 1648 |
+
"eval_bleu": 0.4111345004981505,
|
| 1649 |
+
"step": 41000,
|
| 1650 |
+
"swisstext21_eval_bleu": 0.31566120485475907
|
| 1651 |
+
},
|
| 1652 |
+
{
|
| 1653 |
+
"epoch": 1.82983631282438,
|
| 1654 |
+
"grad_norm": 2.688190221786499,
|
| 1655 |
+
"learning_rate": 0.00018398947844247804,
|
| 1656 |
+
"loss": 0.783,
|
| 1657 |
+
"step": 41250
|
| 1658 |
+
},
|
| 1659 |
+
{
|
| 1660 |
+
"epoch": 1.8409262298718005,
|
| 1661 |
+
"grad_norm": 3.442605972290039,
|
| 1662 |
+
"learning_rate": 0.00018379979086190345,
|
| 1663 |
+
"loss": 0.792,
|
| 1664 |
+
"step": 41500
|
| 1665 |
+
},
|
| 1666 |
+
{
|
| 1667 |
+
"epoch": 1.8409262298718005,
|
| 1668 |
+
"eval_bleu": 0.4071142980360359,
|
| 1669 |
+
"step": 41500,
|
| 1670 |
+
"swisstext21_eval_bleu": 0.30145837573503925
|
| 1671 |
+
},
|
| 1672 |
+
{
|
| 1673 |
+
"epoch": 1.8520161469192211,
|
| 1674 |
+
"grad_norm": 2.305250883102417,
|
| 1675 |
+
"learning_rate": 0.00018360908519589374,
|
| 1676 |
+
"loss": 0.7867,
|
| 1677 |
+
"step": 41750
|
| 1678 |
+
},
|
| 1679 |
+
{
|
| 1680 |
+
"epoch": 1.8631060639666415,
|
| 1681 |
+
"grad_norm": 3.7068357467651367,
|
| 1682 |
+
"learning_rate": 0.00018341736376133606,
|
| 1683 |
+
"loss": 0.7836,
|
| 1684 |
+
"step": 42000
|
| 1685 |
+
},
|
| 1686 |
+
{
|
| 1687 |
+
"epoch": 1.8631060639666415,
|
| 1688 |
+
"eval_bleu": 0.4077189407900903,
|
| 1689 |
+
"step": 42000,
|
| 1690 |
+
"swisstext21_eval_bleu": 0.31436959073853826
|
| 1691 |
+
},
|
| 1692 |
+
{
|
| 1693 |
+
"epoch": 1.874195981014062,
|
| 1694 |
+
"grad_norm": 2.5153627395629883,
|
| 1695 |
+
"learning_rate": 0.00018322462888745826,
|
| 1696 |
+
"loss": 0.7971,
|
| 1697 |
+
"step": 42250
|
| 1698 |
+
},
|
| 1699 |
+
{
|
| 1700 |
+
"epoch": 1.8852858980614826,
|
| 1701 |
+
"grad_norm": 2.1864585876464844,
|
| 1702 |
+
"learning_rate": 0.0001830308829158003,
|
| 1703 |
+
"loss": 0.7813,
|
| 1704 |
+
"step": 42500
|
| 1705 |
+
},
|
| 1706 |
+
{
|
| 1707 |
+
"epoch": 1.8852858980614826,
|
| 1708 |
+
"eval_bleu": 0.41077499870623996,
|
| 1709 |
+
"step": 42500,
|
| 1710 |
+
"swisstext21_eval_bleu": 0.3073002204386824
|
| 1711 |
+
},
|
| 1712 |
+
{
|
| 1713 |
+
"epoch": 1.896375815108903,
|
| 1714 |
+
"grad_norm": 2.703538179397583,
|
| 1715 |
+
"learning_rate": 0.00018283612820018617,
|
| 1716 |
+
"loss": 0.8096,
|
| 1717 |
+
"step": 42750
|
| 1718 |
+
},
|
| 1719 |
+
{
|
| 1720 |
+
"epoch": 1.9074657321563233,
|
| 1721 |
+
"grad_norm": 2.311037302017212,
|
| 1722 |
+
"learning_rate": 0.000182640367106695,
|
| 1723 |
+
"loss": 0.7695,
|
| 1724 |
+
"step": 43000
|
| 1725 |
+
},
|
| 1726 |
+
{
|
| 1727 |
+
"epoch": 1.9074657321563233,
|
| 1728 |
+
"eval_bleu": 0.4070896841434834,
|
| 1729 |
+
"step": 43000,
|
| 1730 |
+
"swisstext21_eval_bleu": 0.3008197269713232
|
| 1731 |
+
},
|
| 1732 |
+
{
|
| 1733 |
+
"epoch": 1.918555649203744,
|
| 1734 |
+
"grad_norm": 4.235742568969727,
|
| 1735 |
+
"learning_rate": 0.00018244360201363248,
|
| 1736 |
+
"loss": 0.7986,
|
| 1737 |
+
"step": 43250
|
| 1738 |
+
},
|
| 1739 |
+
{
|
| 1740 |
+
"epoch": 1.9296455662511645,
|
| 1741 |
+
"grad_norm": 2.413109540939331,
|
| 1742 |
+
"learning_rate": 0.0001822458353115019,
|
| 1743 |
+
"loss": 0.7802,
|
| 1744 |
+
"step": 43500
|
| 1745 |
+
},
|
| 1746 |
+
{
|
| 1747 |
+
"epoch": 1.9296455662511645,
|
| 1748 |
+
"eval_bleu": 0.3980846213733118,
|
| 1749 |
+
"step": 43500,
|
| 1750 |
+
"swisstext21_eval_bleu": 0.3008543870053332
|
| 1751 |
+
},
|
| 1752 |
+
{
|
| 1753 |
+
"epoch": 1.9407354832985848,
|
| 1754 |
+
"grad_norm": 2.620948314666748,
|
| 1755 |
+
"learning_rate": 0.00018204706940297508,
|
| 1756 |
+
"loss": 0.7653,
|
| 1757 |
+
"step": 43750
|
| 1758 |
+
},
|
| 1759 |
+
{
|
| 1760 |
+
"epoch": 1.9518254003460054,
|
| 1761 |
+
"grad_norm": 2.820128917694092,
|
| 1762 |
+
"learning_rate": 0.0001818473067028633,
|
| 1763 |
+
"loss": 0.7574,
|
| 1764 |
+
"step": 44000
|
| 1765 |
+
},
|
| 1766 |
+
{
|
| 1767 |
+
"epoch": 1.9518254003460054,
|
| 1768 |
+
"eval_bleu": 0.39885615292674625,
|
| 1769 |
+
"step": 44000,
|
| 1770 |
+
"swisstext21_eval_bleu": 0.2930218556668886
|
| 1771 |
+
},
|
| 1772 |
+
{
|
| 1773 |
+
"epoch": 1.962915317393426,
|
| 1774 |
+
"grad_norm": 2.394529342651367,
|
| 1775 |
+
"learning_rate": 0.00018164654963808783,
|
| 1776 |
+
"loss": 0.7538,
|
| 1777 |
+
"step": 44250
|
| 1778 |
+
},
|
| 1779 |
+
{
|
| 1780 |
+
"epoch": 1.9740052344408463,
|
| 1781 |
+
"grad_norm": 2.639223098754883,
|
| 1782 |
+
"learning_rate": 0.0001814448006476505,
|
| 1783 |
+
"loss": 0.8031,
|
| 1784 |
+
"step": 44500
|
| 1785 |
+
},
|
| 1786 |
+
{
|
| 1787 |
+
"epoch": 1.9740052344408463,
|
| 1788 |
+
"eval_bleu": 0.3975877229366723,
|
| 1789 |
+
"step": 44500,
|
| 1790 |
+
"swisstext21_eval_bleu": 0.3035613872071041
|
| 1791 |
+
},
|
| 1792 |
+
{
|
| 1793 |
+
"epoch": 1.9850951514882669,
|
| 1794 |
+
"grad_norm": 2.605180501937866,
|
| 1795 |
+
"learning_rate": 0.00018124206218260403,
|
| 1796 |
+
"loss": 0.7791,
|
| 1797 |
+
"step": 44750
|
| 1798 |
+
},
|
| 1799 |
+
{
|
| 1800 |
+
"epoch": 1.9961850685356874,
|
| 1801 |
+
"grad_norm": 3.3844354152679443,
|
| 1802 |
+
"learning_rate": 0.0001810383367060224,
|
| 1803 |
+
"loss": 0.7888,
|
| 1804 |
+
"step": 45000
|
| 1805 |
+
},
|
| 1806 |
+
{
|
| 1807 |
+
"epoch": 1.9961850685356874,
|
| 1808 |
+
"eval_bleu": 0.39963110189053974,
|
| 1809 |
+
"step": 45000,
|
| 1810 |
+
"swisstext21_eval_bleu": 0.3032512226222924
|
| 1811 |
+
},
|
| 1812 |
+
{
|
| 1813 |
+
"epoch": 2.007274985583108,
|
| 1814 |
+
"grad_norm": 2.150728225708008,
|
| 1815 |
+
"learning_rate": 0.0001808336266929707,
|
| 1816 |
+
"loss": 0.7689,
|
| 1817 |
+
"step": 45250
|
| 1818 |
+
},
|
| 1819 |
+
{
|
| 1820 |
+
"epoch": 2.018364902630528,
|
| 1821 |
+
"grad_norm": 2.487170696258545,
|
| 1822 |
+
"learning_rate": 0.00018062793463047522,
|
| 1823 |
+
"loss": 0.7396,
|
| 1824 |
+
"step": 45500
|
| 1825 |
+
},
|
| 1826 |
+
{
|
| 1827 |
+
"epoch": 2.018364902630528,
|
| 1828 |
+
"eval_bleu": 0.40990702580569705,
|
| 1829 |
+
"step": 45500,
|
| 1830 |
+
"swisstext21_eval_bleu": 0.30612631850382593
|
| 1831 |
+
},
|
| 1832 |
+
{
|
| 1833 |
+
"epoch": 2.029454819677949,
|
| 1834 |
+
"grad_norm": 2.625516891479492,
|
| 1835 |
+
"learning_rate": 0.00018042126301749315,
|
| 1836 |
+
"loss": 0.7552,
|
| 1837 |
+
"step": 45750
|
| 1838 |
+
},
|
| 1839 |
+
{
|
| 1840 |
+
"epoch": 2.0405447367253693,
|
| 1841 |
+
"grad_norm": 2.603152275085449,
|
| 1842 |
+
"learning_rate": 0.0001802136143648824,
|
| 1843 |
+
"loss": 0.7663,
|
| 1844 |
+
"step": 46000
|
| 1845 |
+
},
|
| 1846 |
+
{
|
| 1847 |
+
"epoch": 2.0405447367253693,
|
| 1848 |
+
"eval_bleu": 0.40981514096912186,
|
| 1849 |
+
"step": 46000,
|
| 1850 |
+
"swisstext21_eval_bleu": 0.31343081754143665
|
| 1851 |
+
},
|
| 1852 |
+
{
|
| 1853 |
+
"epoch": 2.0516346537727896,
|
| 1854 |
+
"grad_norm": 3.043926239013672,
|
| 1855 |
+
"learning_rate": 0.00018000499119537073,
|
| 1856 |
+
"loss": 0.756,
|
| 1857 |
+
"step": 46250
|
| 1858 |
+
},
|
| 1859 |
+
{
|
| 1860 |
+
"epoch": 2.0627245708202104,
|
| 1861 |
+
"grad_norm": 3.889756202697754,
|
| 1862 |
+
"learning_rate": 0.00017979539604352554,
|
| 1863 |
+
"loss": 0.7379,
|
| 1864 |
+
"step": 46500
|
| 1865 |
+
},
|
| 1866 |
+
{
|
| 1867 |
+
"epoch": 2.0627245708202104,
|
| 1868 |
+
"eval_bleu": 0.4098169578968794,
|
| 1869 |
+
"step": 46500,
|
| 1870 |
+
"swisstext21_eval_bleu": 0.30999706188596005
|
| 1871 |
+
},
|
| 1872 |
+
{
|
| 1873 |
+
"epoch": 2.073814487867631,
|
| 1874 |
+
"grad_norm": 3.5386924743652344,
|
| 1875 |
+
"learning_rate": 0.0001795848314557227,
|
| 1876 |
+
"loss": 0.7438,
|
| 1877 |
+
"step": 46750
|
| 1878 |
+
},
|
| 1879 |
+
{
|
| 1880 |
+
"epoch": 2.084904404915051,
|
| 1881 |
+
"grad_norm": 2.6188015937805176,
|
| 1882 |
+
"learning_rate": 0.00017937329999011592,
|
| 1883 |
+
"loss": 0.7797,
|
| 1884 |
+
"step": 47000
|
| 1885 |
+
},
|
| 1886 |
+
{
|
| 1887 |
+
"epoch": 2.084904404915051,
|
| 1888 |
+
"eval_bleu": 0.41246128940763466,
|
| 1889 |
+
"step": 47000,
|
| 1890 |
+
"swisstext21_eval_bleu": 0.30702184204438654
|
| 1891 |
+
},
|
| 1892 |
+
{
|
| 1893 |
+
"epoch": 2.095994321962472,
|
| 1894 |
+
"grad_norm": 2.863593578338623,
|
| 1895 |
+
"learning_rate": 0.0001791608042166054,
|
| 1896 |
+
"loss": 0.7603,
|
| 1897 |
+
"step": 47250
|
| 1898 |
+
},
|
| 1899 |
+
{
|
| 1900 |
+
"epoch": 2.1070842390098923,
|
| 1901 |
+
"grad_norm": 2.4948580265045166,
|
| 1902 |
+
"learning_rate": 0.00017894734671680684,
|
| 1903 |
+
"loss": 0.7707,
|
| 1904 |
+
"step": 47500
|
| 1905 |
+
},
|
| 1906 |
+
{
|
| 1907 |
+
"epoch": 2.1070842390098923,
|
| 1908 |
+
"eval_bleu": 0.40171245802431144,
|
| 1909 |
+
"step": 47500,
|
| 1910 |
+
"swisstext21_eval_bleu": 0.3080346062801903
|
| 1911 |
+
},
|
| 1912 |
+
{
|
| 1913 |
+
"epoch": 2.1181741560573126,
|
| 1914 |
+
"grad_norm": 4.000399589538574,
|
| 1915 |
+
"learning_rate": 0.0001787329300840199,
|
| 1916 |
+
"loss": 0.7699,
|
| 1917 |
+
"step": 47750
|
| 1918 |
+
},
|
| 1919 |
+
{
|
| 1920 |
+
"epoch": 2.129264073104733,
|
| 1921 |
+
"grad_norm": 3.1941723823547363,
|
| 1922 |
+
"learning_rate": 0.0001785175569231968,
|
| 1923 |
+
"loss": 0.7605,
|
| 1924 |
+
"step": 48000
|
| 1925 |
+
}
|
| 1926 |
+
],
|
| 1927 |
+
"logging_steps": 250,
|
| 1928 |
+
"max_steps": 225430,
|
| 1929 |
+
"num_input_tokens_seen": 0,
|
| 1930 |
+
"num_train_epochs": 10,
|
| 1931 |
+
"save_steps": 500,
|
| 1932 |
+
"stateful_callbacks": {
|
| 1933 |
+
"EpochAwareEarlyStoppingCallback": {
|
| 1934 |
+
"args": {
|
| 1935 |
+
"early_stopping_patience": 3,
|
| 1936 |
+
"early_stopping_threshold": 0.0
|
| 1937 |
+
},
|
| 1938 |
+
"attributes": {
|
| 1939 |
+
"early_stopping_patience_counter": 0
|
| 1940 |
+
}
|
| 1941 |
+
},
|
| 1942 |
+
"TrainerControl": {
|
| 1943 |
+
"args": {
|
| 1944 |
+
"should_epoch_stop": false,
|
| 1945 |
+
"should_evaluate": true,
|
| 1946 |
+
"should_log": false,
|
| 1947 |
+
"should_save": true,
|
| 1948 |
+
"should_training_stop": false
|
| 1949 |
+
},
|
| 1950 |
+
"attributes": {}
|
| 1951 |
+
}
|
| 1952 |
+
},
|
| 1953 |
+
"total_flos": 2.555800421400576e+19,
|
| 1954 |
+
"train_batch_size": 8,
|
| 1955 |
+
"trial_name": null,
|
| 1956 |
+
"trial_params": null
|
| 1957 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d40040bf5b7766803b5c0ad132eedacb64fb9db2f6ca25d053d4a786309f6e7e
|
| 3 |
+
size 5905
|