Upload 12 files
Browse files- README.md +54 -0
- added_tokens.json +3 -0
- all_results.json +9 -0
- config.json +35 -0
- model.safetensors +3 -0
- special_tokens_map.json +15 -0
- spm.model +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +59 -0
- train_results.json +9 -0
- trainer_state.json +2192 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
license: mit
|
| 4 |
+
base_model: microsoft/deberta-v3-large
|
| 5 |
+
tags:
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
model-index:
|
| 8 |
+
- name: mlm_output
|
| 9 |
+
results: []
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 13 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 14 |
+
|
| 15 |
+
# mlm_output
|
| 16 |
+
|
| 17 |
+
This model is a fine-tuned version of [microsoft/deberta-v3-large](https://huggingface.co/microsoft/deberta-v3-large) on an unknown dataset.
|
| 18 |
+
|
| 19 |
+
## Model description
|
| 20 |
+
|
| 21 |
+
More information needed
|
| 22 |
+
|
| 23 |
+
## Intended uses & limitations
|
| 24 |
+
|
| 25 |
+
More information needed
|
| 26 |
+
|
| 27 |
+
## Training and evaluation data
|
| 28 |
+
|
| 29 |
+
More information needed
|
| 30 |
+
|
| 31 |
+
## Training procedure
|
| 32 |
+
|
| 33 |
+
### Training hyperparameters
|
| 34 |
+
|
| 35 |
+
The following hyperparameters were used during training:
|
| 36 |
+
- learning_rate: 5e-05
|
| 37 |
+
- train_batch_size: 16
|
| 38 |
+
- eval_batch_size: 8
|
| 39 |
+
- seed: 42
|
| 40 |
+
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 41 |
+
- lr_scheduler_type: linear
|
| 42 |
+
- num_epochs: 3.0
|
| 43 |
+
- mixed_precision_training: Native AMP
|
| 44 |
+
|
| 45 |
+
### Training results
|
| 46 |
+
|
| 47 |
+
|
| 48 |
+
|
| 49 |
+
### Framework versions
|
| 50 |
+
|
| 51 |
+
- Transformers 4.52.0
|
| 52 |
+
- Pytorch 2.6.0+cu124
|
| 53 |
+
- Datasets 2.19.0
|
| 54 |
+
- Tokenizers 0.21.1
|
added_tokens.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"[MASK]": 128000
|
| 3 |
+
}
|
all_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"total_flos": 4.206282006594048e+16,
|
| 4 |
+
"train_loss": 3.0830205624302227,
|
| 5 |
+
"train_runtime": 6816.3036,
|
| 6 |
+
"train_samples": 163840,
|
| 7 |
+
"train_samples_per_second": 72.109,
|
| 8 |
+
"train_steps_per_second": 4.507
|
| 9 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"DebertaV2ForMaskedLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_probs_dropout_prob": 0.1,
|
| 6 |
+
"hidden_act": "gelu",
|
| 7 |
+
"hidden_dropout_prob": 0.1,
|
| 8 |
+
"hidden_size": 1024,
|
| 9 |
+
"initializer_range": 0.02,
|
| 10 |
+
"intermediate_size": 4096,
|
| 11 |
+
"layer_norm_eps": 1e-07,
|
| 12 |
+
"legacy": true,
|
| 13 |
+
"max_position_embeddings": 512,
|
| 14 |
+
"max_relative_positions": -1,
|
| 15 |
+
"model_type": "deberta-v2",
|
| 16 |
+
"norm_rel_ebd": "layer_norm",
|
| 17 |
+
"num_attention_heads": 16,
|
| 18 |
+
"num_hidden_layers": 24,
|
| 19 |
+
"pad_token_id": 0,
|
| 20 |
+
"pooler_dropout": 0,
|
| 21 |
+
"pooler_hidden_act": "gelu",
|
| 22 |
+
"pooler_hidden_size": 1024,
|
| 23 |
+
"pos_att_type": [
|
| 24 |
+
"p2c",
|
| 25 |
+
"c2p"
|
| 26 |
+
],
|
| 27 |
+
"position_biased_input": false,
|
| 28 |
+
"position_buckets": 256,
|
| 29 |
+
"relative_attention": true,
|
| 30 |
+
"share_att_key": true,
|
| 31 |
+
"torch_dtype": "float32",
|
| 32 |
+
"transformers_version": "4.52.0",
|
| 33 |
+
"type_vocab_size": 0,
|
| 34 |
+
"vocab_size": 128100
|
| 35 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c413b90a021dd2c1c7ec4b358b012c510e8eaca43be87a4fe4a22650db249dca
|
| 3 |
+
size 1740817016
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "[CLS]",
|
| 3 |
+
"cls_token": "[CLS]",
|
| 4 |
+
"eos_token": "[SEP]",
|
| 5 |
+
"mask_token": "[MASK]",
|
| 6 |
+
"pad_token": "[PAD]",
|
| 7 |
+
"sep_token": "[SEP]",
|
| 8 |
+
"unk_token": {
|
| 9 |
+
"content": "[UNK]",
|
| 10 |
+
"lstrip": false,
|
| 11 |
+
"normalized": true,
|
| 12 |
+
"rstrip": false,
|
| 13 |
+
"single_word": false
|
| 14 |
+
}
|
| 15 |
+
}
|
spm.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
|
| 3 |
+
size 2464616
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "[PAD]",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "[CLS]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "[SEP]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"3": {
|
| 28 |
+
"content": "[UNK]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": true,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"128000": {
|
| 36 |
+
"content": "[MASK]",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"bos_token": "[CLS]",
|
| 45 |
+
"clean_up_tokenization_spaces": false,
|
| 46 |
+
"cls_token": "[CLS]",
|
| 47 |
+
"do_lower_case": false,
|
| 48 |
+
"eos_token": "[SEP]",
|
| 49 |
+
"extra_special_tokens": {},
|
| 50 |
+
"mask_token": "[MASK]",
|
| 51 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 52 |
+
"pad_token": "[PAD]",
|
| 53 |
+
"sep_token": "[SEP]",
|
| 54 |
+
"sp_model_kwargs": {},
|
| 55 |
+
"split_by_punct": false,
|
| 56 |
+
"tokenizer_class": "DebertaV2Tokenizer",
|
| 57 |
+
"unk_token": "[UNK]",
|
| 58 |
+
"vocab_type": "spm"
|
| 59 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"total_flos": 4.206282006594048e+16,
|
| 4 |
+
"train_loss": 3.0830205624302227,
|
| 5 |
+
"train_runtime": 6816.3036,
|
| 6 |
+
"train_samples": 163840,
|
| 7 |
+
"train_samples_per_second": 72.109,
|
| 8 |
+
"train_steps_per_second": 4.507
|
| 9 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,2192 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 3.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 30720,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.009765625,
|
| 14 |
+
"grad_norm": NaN,
|
| 15 |
+
"learning_rate": 4.984375e-05,
|
| 16 |
+
"loss": 6.5469,
|
| 17 |
+
"step": 100
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.01953125,
|
| 21 |
+
"grad_norm": 15.062654495239258,
|
| 22 |
+
"learning_rate": 4.9682617187500003e-05,
|
| 23 |
+
"loss": 5.3177,
|
| 24 |
+
"step": 200
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.029296875,
|
| 28 |
+
"grad_norm": 13.20622730255127,
|
| 29 |
+
"learning_rate": 4.9519856770833334e-05,
|
| 30 |
+
"loss": 4.8951,
|
| 31 |
+
"step": 300
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.0390625,
|
| 35 |
+
"grad_norm": 14.794780731201172,
|
| 36 |
+
"learning_rate": 4.935709635416667e-05,
|
| 37 |
+
"loss": 4.8799,
|
| 38 |
+
"step": 400
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.048828125,
|
| 42 |
+
"grad_norm": 13.915122985839844,
|
| 43 |
+
"learning_rate": 4.919596354166667e-05,
|
| 44 |
+
"loss": 4.5381,
|
| 45 |
+
"step": 500
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.05859375,
|
| 49 |
+
"grad_norm": 15.835251808166504,
|
| 50 |
+
"learning_rate": 4.9033203125000005e-05,
|
| 51 |
+
"loss": 4.4279,
|
| 52 |
+
"step": 600
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.068359375,
|
| 56 |
+
"grad_norm": 14.109216690063477,
|
| 57 |
+
"learning_rate": 4.8870442708333335e-05,
|
| 58 |
+
"loss": 4.2612,
|
| 59 |
+
"step": 700
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.078125,
|
| 63 |
+
"grad_norm": 13.910305976867676,
|
| 64 |
+
"learning_rate": 4.8707682291666666e-05,
|
| 65 |
+
"loss": 4.2912,
|
| 66 |
+
"step": 800
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.087890625,
|
| 70 |
+
"grad_norm": 15.284989356994629,
|
| 71 |
+
"learning_rate": 4.854654947916667e-05,
|
| 72 |
+
"loss": 4.3003,
|
| 73 |
+
"step": 900
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.09765625,
|
| 77 |
+
"grad_norm": 16.042747497558594,
|
| 78 |
+
"learning_rate": 4.83837890625e-05,
|
| 79 |
+
"loss": 4.0609,
|
| 80 |
+
"step": 1000
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.107421875,
|
| 84 |
+
"grad_norm": 12.1378755569458,
|
| 85 |
+
"learning_rate": 4.8221028645833336e-05,
|
| 86 |
+
"loss": 4.1666,
|
| 87 |
+
"step": 1100
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.1171875,
|
| 91 |
+
"grad_norm": 13.27160930633545,
|
| 92 |
+
"learning_rate": 4.805826822916667e-05,
|
| 93 |
+
"loss": 4.1419,
|
| 94 |
+
"step": 1200
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.126953125,
|
| 98 |
+
"grad_norm": 16.022241592407227,
|
| 99 |
+
"learning_rate": 4.78955078125e-05,
|
| 100 |
+
"loss": 4.1586,
|
| 101 |
+
"step": 1300
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.13671875,
|
| 105 |
+
"grad_norm": 17.19588851928711,
|
| 106 |
+
"learning_rate": 4.7732747395833336e-05,
|
| 107 |
+
"loss": 3.9012,
|
| 108 |
+
"step": 1400
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.146484375,
|
| 112 |
+
"grad_norm": 13.319019317626953,
|
| 113 |
+
"learning_rate": 4.756998697916667e-05,
|
| 114 |
+
"loss": 4.017,
|
| 115 |
+
"step": 1500
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.15625,
|
| 119 |
+
"grad_norm": 18.409399032592773,
|
| 120 |
+
"learning_rate": 4.74072265625e-05,
|
| 121 |
+
"loss": 3.9484,
|
| 122 |
+
"step": 1600
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.166015625,
|
| 126 |
+
"grad_norm": 13.017057418823242,
|
| 127 |
+
"learning_rate": 4.7244466145833336e-05,
|
| 128 |
+
"loss": 3.9405,
|
| 129 |
+
"step": 1700
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.17578125,
|
| 133 |
+
"grad_norm": 20.20134162902832,
|
| 134 |
+
"learning_rate": 4.7081705729166667e-05,
|
| 135 |
+
"loss": 3.8163,
|
| 136 |
+
"step": 1800
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.185546875,
|
| 140 |
+
"grad_norm": 12.69709587097168,
|
| 141 |
+
"learning_rate": 4.6918945312500004e-05,
|
| 142 |
+
"loss": 3.8031,
|
| 143 |
+
"step": 1900
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.1953125,
|
| 147 |
+
"grad_norm": 15.624823570251465,
|
| 148 |
+
"learning_rate": 4.6756184895833335e-05,
|
| 149 |
+
"loss": 3.862,
|
| 150 |
+
"step": 2000
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.205078125,
|
| 154 |
+
"grad_norm": 18.287826538085938,
|
| 155 |
+
"learning_rate": 4.659342447916667e-05,
|
| 156 |
+
"loss": 3.8113,
|
| 157 |
+
"step": 2100
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.21484375,
|
| 161 |
+
"grad_norm": 13.958403587341309,
|
| 162 |
+
"learning_rate": 4.6430664062500004e-05,
|
| 163 |
+
"loss": 3.7175,
|
| 164 |
+
"step": 2200
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.224609375,
|
| 168 |
+
"grad_norm": 14.171894073486328,
|
| 169 |
+
"learning_rate": 4.6267903645833335e-05,
|
| 170 |
+
"loss": 3.8023,
|
| 171 |
+
"step": 2300
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.234375,
|
| 175 |
+
"grad_norm": 13.721501350402832,
|
| 176 |
+
"learning_rate": 4.610514322916667e-05,
|
| 177 |
+
"loss": 3.7811,
|
| 178 |
+
"step": 2400
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.244140625,
|
| 182 |
+
"grad_norm": 15.861538887023926,
|
| 183 |
+
"learning_rate": 4.5942382812500003e-05,
|
| 184 |
+
"loss": 3.6891,
|
| 185 |
+
"step": 2500
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.25390625,
|
| 189 |
+
"grad_norm": 12.93659496307373,
|
| 190 |
+
"learning_rate": 4.577962239583334e-05,
|
| 191 |
+
"loss": 3.6613,
|
| 192 |
+
"step": 2600
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.263671875,
|
| 196 |
+
"grad_norm": 14.38327407836914,
|
| 197 |
+
"learning_rate": 4.561686197916667e-05,
|
| 198 |
+
"loss": 4.0671,
|
| 199 |
+
"step": 2700
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.2734375,
|
| 203 |
+
"grad_norm": 21.85599136352539,
|
| 204 |
+
"learning_rate": 4.54541015625e-05,
|
| 205 |
+
"loss": 3.6713,
|
| 206 |
+
"step": 2800
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.283203125,
|
| 210 |
+
"grad_norm": 16.765880584716797,
|
| 211 |
+
"learning_rate": 4.529134114583334e-05,
|
| 212 |
+
"loss": 3.787,
|
| 213 |
+
"step": 2900
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.29296875,
|
| 217 |
+
"grad_norm": 12.277482032775879,
|
| 218 |
+
"learning_rate": 4.512858072916667e-05,
|
| 219 |
+
"loss": 3.634,
|
| 220 |
+
"step": 3000
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.302734375,
|
| 224 |
+
"grad_norm": 14.076525688171387,
|
| 225 |
+
"learning_rate": 4.49658203125e-05,
|
| 226 |
+
"loss": 3.6676,
|
| 227 |
+
"step": 3100
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.3125,
|
| 231 |
+
"grad_norm": 54.203609466552734,
|
| 232 |
+
"learning_rate": 4.480305989583334e-05,
|
| 233 |
+
"loss": 3.4946,
|
| 234 |
+
"step": 3200
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.322265625,
|
| 238 |
+
"grad_norm": 17.947622299194336,
|
| 239 |
+
"learning_rate": 4.464029947916667e-05,
|
| 240 |
+
"loss": 3.6398,
|
| 241 |
+
"step": 3300
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.33203125,
|
| 245 |
+
"grad_norm": 12.46594524383545,
|
| 246 |
+
"learning_rate": 4.44775390625e-05,
|
| 247 |
+
"loss": 3.6395,
|
| 248 |
+
"step": 3400
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.341796875,
|
| 252 |
+
"grad_norm": 14.41441822052002,
|
| 253 |
+
"learning_rate": 4.431477864583334e-05,
|
| 254 |
+
"loss": 3.5954,
|
| 255 |
+
"step": 3500
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.3515625,
|
| 259 |
+
"grad_norm": 11.247319221496582,
|
| 260 |
+
"learning_rate": 4.415201822916667e-05,
|
| 261 |
+
"loss": 3.7537,
|
| 262 |
+
"step": 3600
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.361328125,
|
| 266 |
+
"grad_norm": 15.799861907958984,
|
| 267 |
+
"learning_rate": 4.39892578125e-05,
|
| 268 |
+
"loss": 3.7104,
|
| 269 |
+
"step": 3700
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.37109375,
|
| 273 |
+
"grad_norm": 13.855748176574707,
|
| 274 |
+
"learning_rate": 4.382649739583334e-05,
|
| 275 |
+
"loss": 3.6212,
|
| 276 |
+
"step": 3800
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.380859375,
|
| 280 |
+
"grad_norm": 14.83035659790039,
|
| 281 |
+
"learning_rate": 4.366373697916667e-05,
|
| 282 |
+
"loss": 3.5802,
|
| 283 |
+
"step": 3900
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.390625,
|
| 287 |
+
"grad_norm": 13.719660758972168,
|
| 288 |
+
"learning_rate": 4.35009765625e-05,
|
| 289 |
+
"loss": 3.4662,
|
| 290 |
+
"step": 4000
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.400390625,
|
| 294 |
+
"grad_norm": NaN,
|
| 295 |
+
"learning_rate": 4.333821614583334e-05,
|
| 296 |
+
"loss": 3.5461,
|
| 297 |
+
"step": 4100
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.41015625,
|
| 301 |
+
"grad_norm": 13.233614921569824,
|
| 302 |
+
"learning_rate": 4.3177083333333334e-05,
|
| 303 |
+
"loss": 3.5612,
|
| 304 |
+
"step": 4200
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.419921875,
|
| 308 |
+
"grad_norm": 16.629112243652344,
|
| 309 |
+
"learning_rate": 4.3014322916666665e-05,
|
| 310 |
+
"loss": 3.4333,
|
| 311 |
+
"step": 4300
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.4296875,
|
| 315 |
+
"grad_norm": 84.17444610595703,
|
| 316 |
+
"learning_rate": 4.28515625e-05,
|
| 317 |
+
"loss": 3.4819,
|
| 318 |
+
"step": 4400
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.439453125,
|
| 322 |
+
"grad_norm": 14.212441444396973,
|
| 323 |
+
"learning_rate": 4.268880208333333e-05,
|
| 324 |
+
"loss": 3.4069,
|
| 325 |
+
"step": 4500
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.44921875,
|
| 329 |
+
"grad_norm": 20.573959350585938,
|
| 330 |
+
"learning_rate": 4.2526041666666664e-05,
|
| 331 |
+
"loss": 3.6456,
|
| 332 |
+
"step": 4600
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.458984375,
|
| 336 |
+
"grad_norm": 13.834342956542969,
|
| 337 |
+
"learning_rate": 4.236328125e-05,
|
| 338 |
+
"loss": 3.5382,
|
| 339 |
+
"step": 4700
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.46875,
|
| 343 |
+
"grad_norm": 14.079811096191406,
|
| 344 |
+
"learning_rate": 4.220052083333333e-05,
|
| 345 |
+
"loss": 3.4105,
|
| 346 |
+
"step": 4800
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.478515625,
|
| 350 |
+
"grad_norm": 12.509760856628418,
|
| 351 |
+
"learning_rate": 4.2037760416666664e-05,
|
| 352 |
+
"loss": 3.3461,
|
| 353 |
+
"step": 4900
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.48828125,
|
| 357 |
+
"grad_norm": 14.564861297607422,
|
| 358 |
+
"learning_rate": 4.1875e-05,
|
| 359 |
+
"loss": 3.4041,
|
| 360 |
+
"step": 5000
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.498046875,
|
| 364 |
+
"grad_norm": 14.737241744995117,
|
| 365 |
+
"learning_rate": 4.171223958333333e-05,
|
| 366 |
+
"loss": 3.507,
|
| 367 |
+
"step": 5100
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.5078125,
|
| 371 |
+
"grad_norm": 15.188499450683594,
|
| 372 |
+
"learning_rate": 4.154947916666666e-05,
|
| 373 |
+
"loss": 3.4917,
|
| 374 |
+
"step": 5200
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.517578125,
|
| 378 |
+
"grad_norm": 12.736299514770508,
|
| 379 |
+
"learning_rate": 4.138671875e-05,
|
| 380 |
+
"loss": 3.3674,
|
| 381 |
+
"step": 5300
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.52734375,
|
| 385 |
+
"grad_norm": 13.326681137084961,
|
| 386 |
+
"learning_rate": 4.122395833333333e-05,
|
| 387 |
+
"loss": 3.4286,
|
| 388 |
+
"step": 5400
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.537109375,
|
| 392 |
+
"grad_norm": 12.76373291015625,
|
| 393 |
+
"learning_rate": 4.106119791666666e-05,
|
| 394 |
+
"loss": 3.4353,
|
| 395 |
+
"step": 5500
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.546875,
|
| 399 |
+
"grad_norm": 15.256406784057617,
|
| 400 |
+
"learning_rate": 4.08984375e-05,
|
| 401 |
+
"loss": 3.4297,
|
| 402 |
+
"step": 5600
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.556640625,
|
| 406 |
+
"grad_norm": 11.880370140075684,
|
| 407 |
+
"learning_rate": 4.073567708333333e-05,
|
| 408 |
+
"loss": 3.2847,
|
| 409 |
+
"step": 5700
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.56640625,
|
| 413 |
+
"grad_norm": 15.305662155151367,
|
| 414 |
+
"learning_rate": 4.057291666666667e-05,
|
| 415 |
+
"loss": 3.3476,
|
| 416 |
+
"step": 5800
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.576171875,
|
| 420 |
+
"grad_norm": 24.128557205200195,
|
| 421 |
+
"learning_rate": 4.041015625e-05,
|
| 422 |
+
"loss": 3.4455,
|
| 423 |
+
"step": 5900
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.5859375,
|
| 427 |
+
"grad_norm": 13.900318145751953,
|
| 428 |
+
"learning_rate": 4.024739583333334e-05,
|
| 429 |
+
"loss": 3.4846,
|
| 430 |
+
"step": 6000
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.595703125,
|
| 434 |
+
"grad_norm": 11.240140914916992,
|
| 435 |
+
"learning_rate": 4.008463541666667e-05,
|
| 436 |
+
"loss": 3.4453,
|
| 437 |
+
"step": 6100
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 0.60546875,
|
| 441 |
+
"grad_norm": 14.209588050842285,
|
| 442 |
+
"learning_rate": 3.9921875e-05,
|
| 443 |
+
"loss": 3.3685,
|
| 444 |
+
"step": 6200
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.615234375,
|
| 448 |
+
"grad_norm": 16.545690536499023,
|
| 449 |
+
"learning_rate": 3.975911458333334e-05,
|
| 450 |
+
"loss": 3.3857,
|
| 451 |
+
"step": 6300
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 0.625,
|
| 455 |
+
"grad_norm": 12.255586624145508,
|
| 456 |
+
"learning_rate": 3.959635416666667e-05,
|
| 457 |
+
"loss": 3.3588,
|
| 458 |
+
"step": 6400
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.634765625,
|
| 462 |
+
"grad_norm": 15.788583755493164,
|
| 463 |
+
"learning_rate": 3.9433593750000006e-05,
|
| 464 |
+
"loss": 3.4022,
|
| 465 |
+
"step": 6500
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.64453125,
|
| 469 |
+
"grad_norm": 11.233269691467285,
|
| 470 |
+
"learning_rate": 3.92724609375e-05,
|
| 471 |
+
"loss": 3.3202,
|
| 472 |
+
"step": 6600
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 0.654296875,
|
| 476 |
+
"grad_norm": 16.585798263549805,
|
| 477 |
+
"learning_rate": 3.910970052083334e-05,
|
| 478 |
+
"loss": 3.2925,
|
| 479 |
+
"step": 6700
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 0.6640625,
|
| 483 |
+
"grad_norm": 15.305195808410645,
|
| 484 |
+
"learning_rate": 3.894694010416667e-05,
|
| 485 |
+
"loss": 3.3162,
|
| 486 |
+
"step": 6800
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 0.673828125,
|
| 490 |
+
"grad_norm": 11.933198928833008,
|
| 491 |
+
"learning_rate": 3.87841796875e-05,
|
| 492 |
+
"loss": 3.3133,
|
| 493 |
+
"step": 6900
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 0.68359375,
|
| 497 |
+
"grad_norm": 15.607390403747559,
|
| 498 |
+
"learning_rate": 3.862141927083334e-05,
|
| 499 |
+
"loss": 3.3407,
|
| 500 |
+
"step": 7000
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 0.693359375,
|
| 504 |
+
"grad_norm": 9.2060546875,
|
| 505 |
+
"learning_rate": 3.845865885416667e-05,
|
| 506 |
+
"loss": 3.3973,
|
| 507 |
+
"step": 7100
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.703125,
|
| 511 |
+
"grad_norm": 17.788448333740234,
|
| 512 |
+
"learning_rate": 3.82958984375e-05,
|
| 513 |
+
"loss": 3.261,
|
| 514 |
+
"step": 7200
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 0.712890625,
|
| 518 |
+
"grad_norm": 13.37771224975586,
|
| 519 |
+
"learning_rate": 3.813313802083334e-05,
|
| 520 |
+
"loss": 3.3159,
|
| 521 |
+
"step": 7300
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 0.72265625,
|
| 525 |
+
"grad_norm": 13.427688598632812,
|
| 526 |
+
"learning_rate": 3.797037760416667e-05,
|
| 527 |
+
"loss": 3.2451,
|
| 528 |
+
"step": 7400
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 0.732421875,
|
| 532 |
+
"grad_norm": 12.314142227172852,
|
| 533 |
+
"learning_rate": 3.78076171875e-05,
|
| 534 |
+
"loss": 3.2721,
|
| 535 |
+
"step": 7500
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 0.7421875,
|
| 539 |
+
"grad_norm": 11.418351173400879,
|
| 540 |
+
"learning_rate": 3.764485677083334e-05,
|
| 541 |
+
"loss": 3.2943,
|
| 542 |
+
"step": 7600
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 0.751953125,
|
| 546 |
+
"grad_norm": 16.546539306640625,
|
| 547 |
+
"learning_rate": 3.748209635416667e-05,
|
| 548 |
+
"loss": 3.2243,
|
| 549 |
+
"step": 7700
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.76171875,
|
| 553 |
+
"grad_norm": 16.984668731689453,
|
| 554 |
+
"learning_rate": 3.73193359375e-05,
|
| 555 |
+
"loss": 3.3024,
|
| 556 |
+
"step": 7800
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 0.771484375,
|
| 560 |
+
"grad_norm": 11.702521324157715,
|
| 561 |
+
"learning_rate": 3.715657552083334e-05,
|
| 562 |
+
"loss": 3.1967,
|
| 563 |
+
"step": 7900
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 0.78125,
|
| 567 |
+
"grad_norm": 12.537822723388672,
|
| 568 |
+
"learning_rate": 3.699381510416667e-05,
|
| 569 |
+
"loss": 3.2535,
|
| 570 |
+
"step": 8000
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 0.791015625,
|
| 574 |
+
"grad_norm": 13.640584945678711,
|
| 575 |
+
"learning_rate": 3.68310546875e-05,
|
| 576 |
+
"loss": 3.1677,
|
| 577 |
+
"step": 8100
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 0.80078125,
|
| 581 |
+
"grad_norm": 15.423649787902832,
|
| 582 |
+
"learning_rate": 3.6668294270833336e-05,
|
| 583 |
+
"loss": 3.2641,
|
| 584 |
+
"step": 8200
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 0.810546875,
|
| 588 |
+
"grad_norm": 12.065776824951172,
|
| 589 |
+
"learning_rate": 3.650553385416667e-05,
|
| 590 |
+
"loss": 3.1169,
|
| 591 |
+
"step": 8300
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 0.8203125,
|
| 595 |
+
"grad_norm": 14.259243965148926,
|
| 596 |
+
"learning_rate": 3.63427734375e-05,
|
| 597 |
+
"loss": 3.2357,
|
| 598 |
+
"step": 8400
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 0.830078125,
|
| 602 |
+
"grad_norm": 17.08042335510254,
|
| 603 |
+
"learning_rate": 3.6180013020833336e-05,
|
| 604 |
+
"loss": 3.3104,
|
| 605 |
+
"step": 8500
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 0.83984375,
|
| 609 |
+
"grad_norm": 10.867400169372559,
|
| 610 |
+
"learning_rate": 3.601725260416667e-05,
|
| 611 |
+
"loss": 3.296,
|
| 612 |
+
"step": 8600
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 0.849609375,
|
| 616 |
+
"grad_norm": 13.106012344360352,
|
| 617 |
+
"learning_rate": 3.58544921875e-05,
|
| 618 |
+
"loss": 3.2956,
|
| 619 |
+
"step": 8700
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 0.859375,
|
| 623 |
+
"grad_norm": 15.86103630065918,
|
| 624 |
+
"learning_rate": 3.5691731770833335e-05,
|
| 625 |
+
"loss": 3.2569,
|
| 626 |
+
"step": 8800
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 0.869140625,
|
| 630 |
+
"grad_norm": 11.86782169342041,
|
| 631 |
+
"learning_rate": 3.5528971354166666e-05,
|
| 632 |
+
"loss": 3.1775,
|
| 633 |
+
"step": 8900
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 0.87890625,
|
| 637 |
+
"grad_norm": 13.925124168395996,
|
| 638 |
+
"learning_rate": 3.53662109375e-05,
|
| 639 |
+
"loss": 3.1556,
|
| 640 |
+
"step": 9000
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 0.888671875,
|
| 644 |
+
"grad_norm": 15.298331260681152,
|
| 645 |
+
"learning_rate": 3.5203450520833335e-05,
|
| 646 |
+
"loss": 3.2081,
|
| 647 |
+
"step": 9100
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 0.8984375,
|
| 651 |
+
"grad_norm": 12.989383697509766,
|
| 652 |
+
"learning_rate": 3.5040690104166666e-05,
|
| 653 |
+
"loss": 3.2758,
|
| 654 |
+
"step": 9200
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 0.908203125,
|
| 658 |
+
"grad_norm": 12.797562599182129,
|
| 659 |
+
"learning_rate": 3.48779296875e-05,
|
| 660 |
+
"loss": 3.0895,
|
| 661 |
+
"step": 9300
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 0.91796875,
|
| 665 |
+
"grad_norm": 10.773366928100586,
|
| 666 |
+
"learning_rate": 3.4715169270833335e-05,
|
| 667 |
+
"loss": 3.1352,
|
| 668 |
+
"step": 9400
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 0.927734375,
|
| 672 |
+
"grad_norm": 13.436513900756836,
|
| 673 |
+
"learning_rate": 3.4552408854166665e-05,
|
| 674 |
+
"loss": 3.2934,
|
| 675 |
+
"step": 9500
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 0.9375,
|
| 679 |
+
"grad_norm": 12.20578670501709,
|
| 680 |
+
"learning_rate": 3.4389648437499996e-05,
|
| 681 |
+
"loss": 3.22,
|
| 682 |
+
"step": 9600
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 0.947265625,
|
| 686 |
+
"grad_norm": 15.03205680847168,
|
| 687 |
+
"learning_rate": 3.4226888020833334e-05,
|
| 688 |
+
"loss": 3.1925,
|
| 689 |
+
"step": 9700
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 0.95703125,
|
| 693 |
+
"grad_norm": 15.373735427856445,
|
| 694 |
+
"learning_rate": 3.4064127604166665e-05,
|
| 695 |
+
"loss": 3.1056,
|
| 696 |
+
"step": 9800
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 0.966796875,
|
| 700 |
+
"grad_norm": 13.795890808105469,
|
| 701 |
+
"learning_rate": 3.39013671875e-05,
|
| 702 |
+
"loss": 3.1484,
|
| 703 |
+
"step": 9900
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 0.9765625,
|
| 707 |
+
"grad_norm": 15.731973648071289,
|
| 708 |
+
"learning_rate": 3.3738606770833334e-05,
|
| 709 |
+
"loss": 3.2102,
|
| 710 |
+
"step": 10000
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 0.986328125,
|
| 714 |
+
"grad_norm": 14.516192436218262,
|
| 715 |
+
"learning_rate": 3.3575846354166665e-05,
|
| 716 |
+
"loss": 3.1795,
|
| 717 |
+
"step": 10100
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 0.99609375,
|
| 721 |
+
"grad_norm": 11.511063575744629,
|
| 722 |
+
"learning_rate": 3.34130859375e-05,
|
| 723 |
+
"loss": 3.1479,
|
| 724 |
+
"step": 10200
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 1.005859375,
|
| 728 |
+
"grad_norm": 13.947763442993164,
|
| 729 |
+
"learning_rate": 3.325032552083333e-05,
|
| 730 |
+
"loss": 3.1697,
|
| 731 |
+
"step": 10300
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 1.015625,
|
| 735 |
+
"grad_norm": 9.85244369506836,
|
| 736 |
+
"learning_rate": 3.308756510416667e-05,
|
| 737 |
+
"loss": 3.1739,
|
| 738 |
+
"step": 10400
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 1.025390625,
|
| 742 |
+
"grad_norm": 21.973459243774414,
|
| 743 |
+
"learning_rate": 3.29248046875e-05,
|
| 744 |
+
"loss": 2.9587,
|
| 745 |
+
"step": 10500
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 1.03515625,
|
| 749 |
+
"grad_norm": 11.420741081237793,
|
| 750 |
+
"learning_rate": 3.276204427083334e-05,
|
| 751 |
+
"loss": 3.1121,
|
| 752 |
+
"step": 10600
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 1.044921875,
|
| 756 |
+
"grad_norm": 10.605298042297363,
|
| 757 |
+
"learning_rate": 3.259928385416667e-05,
|
| 758 |
+
"loss": 3.0928,
|
| 759 |
+
"step": 10700
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 1.0546875,
|
| 763 |
+
"grad_norm": 15.158004760742188,
|
| 764 |
+
"learning_rate": 3.24365234375e-05,
|
| 765 |
+
"loss": 3.0272,
|
| 766 |
+
"step": 10800
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 1.064453125,
|
| 770 |
+
"grad_norm": 12.386876106262207,
|
| 771 |
+
"learning_rate": 3.227376302083334e-05,
|
| 772 |
+
"loss": 3.055,
|
| 773 |
+
"step": 10900
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 1.07421875,
|
| 777 |
+
"grad_norm": 14.404585838317871,
|
| 778 |
+
"learning_rate": 3.211100260416667e-05,
|
| 779 |
+
"loss": 3.0203,
|
| 780 |
+
"step": 11000
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 1.083984375,
|
| 784 |
+
"grad_norm": 14.187972068786621,
|
| 785 |
+
"learning_rate": 3.19482421875e-05,
|
| 786 |
+
"loss": 3.1315,
|
| 787 |
+
"step": 11100
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 1.09375,
|
| 791 |
+
"grad_norm": 11.506830215454102,
|
| 792 |
+
"learning_rate": 3.178548177083334e-05,
|
| 793 |
+
"loss": 3.0323,
|
| 794 |
+
"step": 11200
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 1.103515625,
|
| 798 |
+
"grad_norm": 14.504237174987793,
|
| 799 |
+
"learning_rate": 3.162272135416667e-05,
|
| 800 |
+
"loss": 2.9987,
|
| 801 |
+
"step": 11300
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 1.11328125,
|
| 805 |
+
"grad_norm": 12.95081615447998,
|
| 806 |
+
"learning_rate": 3.14599609375e-05,
|
| 807 |
+
"loss": 2.9773,
|
| 808 |
+
"step": 11400
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 1.123046875,
|
| 812 |
+
"grad_norm": 12.512577056884766,
|
| 813 |
+
"learning_rate": 3.129720052083334e-05,
|
| 814 |
+
"loss": 3.1454,
|
| 815 |
+
"step": 11500
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 1.1328125,
|
| 819 |
+
"grad_norm": 11.951395988464355,
|
| 820 |
+
"learning_rate": 3.113444010416667e-05,
|
| 821 |
+
"loss": 2.9314,
|
| 822 |
+
"step": 11600
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 1.142578125,
|
| 826 |
+
"grad_norm": 16.119001388549805,
|
| 827 |
+
"learning_rate": 3.09716796875e-05,
|
| 828 |
+
"loss": 2.9137,
|
| 829 |
+
"step": 11700
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 1.15234375,
|
| 833 |
+
"grad_norm": 10.542379379272461,
|
| 834 |
+
"learning_rate": 3.080891927083334e-05,
|
| 835 |
+
"loss": 3.1176,
|
| 836 |
+
"step": 11800
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 1.162109375,
|
| 840 |
+
"grad_norm": 14.544652938842773,
|
| 841 |
+
"learning_rate": 3.064615885416667e-05,
|
| 842 |
+
"loss": 2.9937,
|
| 843 |
+
"step": 11900
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 1.171875,
|
| 847 |
+
"grad_norm": 11.01784896850586,
|
| 848 |
+
"learning_rate": 3.04833984375e-05,
|
| 849 |
+
"loss": 3.0301,
|
| 850 |
+
"step": 12000
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 1.181640625,
|
| 854 |
+
"grad_norm": 12.359283447265625,
|
| 855 |
+
"learning_rate": 3.0320638020833337e-05,
|
| 856 |
+
"loss": 2.9277,
|
| 857 |
+
"step": 12100
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 1.19140625,
|
| 861 |
+
"grad_norm": 18.171897888183594,
|
| 862 |
+
"learning_rate": 3.015787760416667e-05,
|
| 863 |
+
"loss": 3.0673,
|
| 864 |
+
"step": 12200
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 1.201171875,
|
| 868 |
+
"grad_norm": 12.454042434692383,
|
| 869 |
+
"learning_rate": 2.99951171875e-05,
|
| 870 |
+
"loss": 2.9398,
|
| 871 |
+
"step": 12300
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 1.2109375,
|
| 875 |
+
"grad_norm": 12.611340522766113,
|
| 876 |
+
"learning_rate": 2.9832356770833337e-05,
|
| 877 |
+
"loss": 2.926,
|
| 878 |
+
"step": 12400
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 1.220703125,
|
| 882 |
+
"grad_norm": 12.207980155944824,
|
| 883 |
+
"learning_rate": 2.9669596354166668e-05,
|
| 884 |
+
"loss": 2.9713,
|
| 885 |
+
"step": 12500
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 1.23046875,
|
| 889 |
+
"grad_norm": 11.924321174621582,
|
| 890 |
+
"learning_rate": 2.95068359375e-05,
|
| 891 |
+
"loss": 3.0734,
|
| 892 |
+
"step": 12600
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 1.240234375,
|
| 896 |
+
"grad_norm": 10.981707572937012,
|
| 897 |
+
"learning_rate": 2.9344075520833337e-05,
|
| 898 |
+
"loss": 2.983,
|
| 899 |
+
"step": 12700
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 1.25,
|
| 903 |
+
"grad_norm": 9.699291229248047,
|
| 904 |
+
"learning_rate": 2.9181315104166667e-05,
|
| 905 |
+
"loss": 3.0235,
|
| 906 |
+
"step": 12800
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 1.259765625,
|
| 910 |
+
"grad_norm": 11.410511016845703,
|
| 911 |
+
"learning_rate": 2.90185546875e-05,
|
| 912 |
+
"loss": 3.081,
|
| 913 |
+
"step": 12900
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 1.26953125,
|
| 917 |
+
"grad_norm": 20.204944610595703,
|
| 918 |
+
"learning_rate": 2.8855794270833336e-05,
|
| 919 |
+
"loss": 2.958,
|
| 920 |
+
"step": 13000
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 1.279296875,
|
| 924 |
+
"grad_norm": 9.388766288757324,
|
| 925 |
+
"learning_rate": 2.8693033854166667e-05,
|
| 926 |
+
"loss": 3.0007,
|
| 927 |
+
"step": 13100
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 1.2890625,
|
| 931 |
+
"grad_norm": 11.05562973022461,
|
| 932 |
+
"learning_rate": 2.8530273437499998e-05,
|
| 933 |
+
"loss": 3.0186,
|
| 934 |
+
"step": 13200
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 1.298828125,
|
| 938 |
+
"grad_norm": 12.052275657653809,
|
| 939 |
+
"learning_rate": 2.8367513020833336e-05,
|
| 940 |
+
"loss": 2.9891,
|
| 941 |
+
"step": 13300
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 1.30859375,
|
| 945 |
+
"grad_norm": 17.93643569946289,
|
| 946 |
+
"learning_rate": 2.8204752604166667e-05,
|
| 947 |
+
"loss": 2.9863,
|
| 948 |
+
"step": 13400
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 1.318359375,
|
| 952 |
+
"grad_norm": 16.745187759399414,
|
| 953 |
+
"learning_rate": 2.8041992187499998e-05,
|
| 954 |
+
"loss": 2.963,
|
| 955 |
+
"step": 13500
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 1.328125,
|
| 959 |
+
"grad_norm": 11.541468620300293,
|
| 960 |
+
"learning_rate": 2.7879231770833335e-05,
|
| 961 |
+
"loss": 3.0955,
|
| 962 |
+
"step": 13600
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 1.337890625,
|
| 966 |
+
"grad_norm": 12.31360912322998,
|
| 967 |
+
"learning_rate": 2.7716471354166666e-05,
|
| 968 |
+
"loss": 3.0445,
|
| 969 |
+
"step": 13700
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 1.34765625,
|
| 973 |
+
"grad_norm": 12.349579811096191,
|
| 974 |
+
"learning_rate": 2.75537109375e-05,
|
| 975 |
+
"loss": 2.9165,
|
| 976 |
+
"step": 13800
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 1.357421875,
|
| 980 |
+
"grad_norm": 11.030657768249512,
|
| 981 |
+
"learning_rate": 2.7390950520833335e-05,
|
| 982 |
+
"loss": 2.9315,
|
| 983 |
+
"step": 13900
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 1.3671875,
|
| 987 |
+
"grad_norm": 14.333861351013184,
|
| 988 |
+
"learning_rate": 2.722819010416667e-05,
|
| 989 |
+
"loss": 3.0059,
|
| 990 |
+
"step": 14000
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 1.376953125,
|
| 994 |
+
"grad_norm": 15.17336368560791,
|
| 995 |
+
"learning_rate": 2.70654296875e-05,
|
| 996 |
+
"loss": 3.0364,
|
| 997 |
+
"step": 14100
|
| 998 |
+
},
|
| 999 |
+
{
|
| 1000 |
+
"epoch": 1.38671875,
|
| 1001 |
+
"grad_norm": 14.133316040039062,
|
| 1002 |
+
"learning_rate": 2.6902669270833338e-05,
|
| 1003 |
+
"loss": 3.0579,
|
| 1004 |
+
"step": 14200
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 1.396484375,
|
| 1008 |
+
"grad_norm": 11.148407936096191,
|
| 1009 |
+
"learning_rate": 2.673990885416667e-05,
|
| 1010 |
+
"loss": 2.975,
|
| 1011 |
+
"step": 14300
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 1.40625,
|
| 1015 |
+
"grad_norm": 14.075923919677734,
|
| 1016 |
+
"learning_rate": 2.65771484375e-05,
|
| 1017 |
+
"loss": 3.0044,
|
| 1018 |
+
"step": 14400
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"epoch": 1.416015625,
|
| 1022 |
+
"grad_norm": 14.998821258544922,
|
| 1023 |
+
"learning_rate": 2.6414388020833337e-05,
|
| 1024 |
+
"loss": 2.9768,
|
| 1025 |
+
"step": 14500
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 1.42578125,
|
| 1029 |
+
"grad_norm": 12.305022239685059,
|
| 1030 |
+
"learning_rate": 2.6251627604166668e-05,
|
| 1031 |
+
"loss": 2.9711,
|
| 1032 |
+
"step": 14600
|
| 1033 |
+
},
|
| 1034 |
+
{
|
| 1035 |
+
"epoch": 1.435546875,
|
| 1036 |
+
"grad_norm": 16.09569549560547,
|
| 1037 |
+
"learning_rate": 2.609049479166667e-05,
|
| 1038 |
+
"loss": 2.8913,
|
| 1039 |
+
"step": 14700
|
| 1040 |
+
},
|
| 1041 |
+
{
|
| 1042 |
+
"epoch": 1.4453125,
|
| 1043 |
+
"grad_norm": 10.328545570373535,
|
| 1044 |
+
"learning_rate": 2.5927734375e-05,
|
| 1045 |
+
"loss": 2.9569,
|
| 1046 |
+
"step": 14800
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 1.455078125,
|
| 1050 |
+
"grad_norm": 10.365655899047852,
|
| 1051 |
+
"learning_rate": 2.576497395833333e-05,
|
| 1052 |
+
"loss": 2.9558,
|
| 1053 |
+
"step": 14900
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 1.46484375,
|
| 1057 |
+
"grad_norm": 11.824304580688477,
|
| 1058 |
+
"learning_rate": 2.560221354166667e-05,
|
| 1059 |
+
"loss": 2.906,
|
| 1060 |
+
"step": 15000
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"epoch": 1.474609375,
|
| 1064 |
+
"grad_norm": 13.518112182617188,
|
| 1065 |
+
"learning_rate": 2.5439453125e-05,
|
| 1066 |
+
"loss": 2.9135,
|
| 1067 |
+
"step": 15100
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"epoch": 1.484375,
|
| 1071 |
+
"grad_norm": 13.241069793701172,
|
| 1072 |
+
"learning_rate": 2.527669270833333e-05,
|
| 1073 |
+
"loss": 2.8683,
|
| 1074 |
+
"step": 15200
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 1.494140625,
|
| 1078 |
+
"grad_norm": 10.397425651550293,
|
| 1079 |
+
"learning_rate": 2.5115559895833336e-05,
|
| 1080 |
+
"loss": 2.9151,
|
| 1081 |
+
"step": 15300
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 1.50390625,
|
| 1085 |
+
"grad_norm": 9.971900939941406,
|
| 1086 |
+
"learning_rate": 2.495279947916667e-05,
|
| 1087 |
+
"loss": 2.8387,
|
| 1088 |
+
"step": 15400
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 1.513671875,
|
| 1092 |
+
"grad_norm": 12.148921966552734,
|
| 1093 |
+
"learning_rate": 2.47900390625e-05,
|
| 1094 |
+
"loss": 3.0045,
|
| 1095 |
+
"step": 15500
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 1.5234375,
|
| 1099 |
+
"grad_norm": 12.122273445129395,
|
| 1100 |
+
"learning_rate": 2.4627278645833336e-05,
|
| 1101 |
+
"loss": 2.8201,
|
| 1102 |
+
"step": 15600
|
| 1103 |
+
},
|
| 1104 |
+
{
|
| 1105 |
+
"epoch": 1.533203125,
|
| 1106 |
+
"grad_norm": 10.754613876342773,
|
| 1107 |
+
"learning_rate": 2.446451822916667e-05,
|
| 1108 |
+
"loss": 3.0412,
|
| 1109 |
+
"step": 15700
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 1.54296875,
|
| 1113 |
+
"grad_norm": 12.5385103225708,
|
| 1114 |
+
"learning_rate": 2.43017578125e-05,
|
| 1115 |
+
"loss": 2.9698,
|
| 1116 |
+
"step": 15800
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 1.552734375,
|
| 1120 |
+
"grad_norm": 12.530341148376465,
|
| 1121 |
+
"learning_rate": 2.4138997395833335e-05,
|
| 1122 |
+
"loss": 2.9844,
|
| 1123 |
+
"step": 15900
|
| 1124 |
+
},
|
| 1125 |
+
{
|
| 1126 |
+
"epoch": 1.5625,
|
| 1127 |
+
"grad_norm": 12.995160102844238,
|
| 1128 |
+
"learning_rate": 2.397623697916667e-05,
|
| 1129 |
+
"loss": 2.9505,
|
| 1130 |
+
"step": 16000
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 1.572265625,
|
| 1134 |
+
"grad_norm": 11.06143856048584,
|
| 1135 |
+
"learning_rate": 2.38134765625e-05,
|
| 1136 |
+
"loss": 2.9299,
|
| 1137 |
+
"step": 16100
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 1.58203125,
|
| 1141 |
+
"grad_norm": 11.600089073181152,
|
| 1142 |
+
"learning_rate": 2.3650716145833335e-05,
|
| 1143 |
+
"loss": 2.9184,
|
| 1144 |
+
"step": 16200
|
| 1145 |
+
},
|
| 1146 |
+
{
|
| 1147 |
+
"epoch": 1.591796875,
|
| 1148 |
+
"grad_norm": 9.294841766357422,
|
| 1149 |
+
"learning_rate": 2.348795572916667e-05,
|
| 1150 |
+
"loss": 3.0312,
|
| 1151 |
+
"step": 16300
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 1.6015625,
|
| 1155 |
+
"grad_norm": 13.555610656738281,
|
| 1156 |
+
"learning_rate": 2.33251953125e-05,
|
| 1157 |
+
"loss": 2.899,
|
| 1158 |
+
"step": 16400
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"epoch": 1.611328125,
|
| 1162 |
+
"grad_norm": 11.077611923217773,
|
| 1163 |
+
"learning_rate": 2.3162434895833334e-05,
|
| 1164 |
+
"loss": 2.9032,
|
| 1165 |
+
"step": 16500
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"epoch": 1.62109375,
|
| 1169 |
+
"grad_norm": 12.092378616333008,
|
| 1170 |
+
"learning_rate": 2.299967447916667e-05,
|
| 1171 |
+
"loss": 3.0475,
|
| 1172 |
+
"step": 16600
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 1.630859375,
|
| 1176 |
+
"grad_norm": 18.95319175720215,
|
| 1177 |
+
"learning_rate": 2.28369140625e-05,
|
| 1178 |
+
"loss": 2.8485,
|
| 1179 |
+
"step": 16700
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 1.640625,
|
| 1183 |
+
"grad_norm": 20.765520095825195,
|
| 1184 |
+
"learning_rate": 2.2674153645833334e-05,
|
| 1185 |
+
"loss": 3.0211,
|
| 1186 |
+
"step": 16800
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 1.650390625,
|
| 1190 |
+
"grad_norm": 19.739500045776367,
|
| 1191 |
+
"learning_rate": 2.2511393229166668e-05,
|
| 1192 |
+
"loss": 3.0398,
|
| 1193 |
+
"step": 16900
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 1.66015625,
|
| 1197 |
+
"grad_norm": 12.64313793182373,
|
| 1198 |
+
"learning_rate": 2.23486328125e-05,
|
| 1199 |
+
"loss": 2.8028,
|
| 1200 |
+
"step": 17000
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 1.669921875,
|
| 1204 |
+
"grad_norm": 19.063640594482422,
|
| 1205 |
+
"learning_rate": 2.2185872395833333e-05,
|
| 1206 |
+
"loss": 2.896,
|
| 1207 |
+
"step": 17100
|
| 1208 |
+
},
|
| 1209 |
+
{
|
| 1210 |
+
"epoch": 1.6796875,
|
| 1211 |
+
"grad_norm": 23.34886932373047,
|
| 1212 |
+
"learning_rate": 2.2023111979166668e-05,
|
| 1213 |
+
"loss": 2.9162,
|
| 1214 |
+
"step": 17200
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 1.689453125,
|
| 1218 |
+
"grad_norm": 11.44904899597168,
|
| 1219 |
+
"learning_rate": 2.1860351562500002e-05,
|
| 1220 |
+
"loss": 2.9423,
|
| 1221 |
+
"step": 17300
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 1.69921875,
|
| 1225 |
+
"grad_norm": 16.1793155670166,
|
| 1226 |
+
"learning_rate": 2.1697591145833336e-05,
|
| 1227 |
+
"loss": 2.917,
|
| 1228 |
+
"step": 17400
|
| 1229 |
+
},
|
| 1230 |
+
{
|
| 1231 |
+
"epoch": 1.708984375,
|
| 1232 |
+
"grad_norm": 9.111202239990234,
|
| 1233 |
+
"learning_rate": 2.1534830729166667e-05,
|
| 1234 |
+
"loss": 2.9147,
|
| 1235 |
+
"step": 17500
|
| 1236 |
+
},
|
| 1237 |
+
{
|
| 1238 |
+
"epoch": 1.71875,
|
| 1239 |
+
"grad_norm": 12.297972679138184,
|
| 1240 |
+
"learning_rate": 2.13720703125e-05,
|
| 1241 |
+
"loss": 2.8541,
|
| 1242 |
+
"step": 17600
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"epoch": 1.728515625,
|
| 1246 |
+
"grad_norm": 14.833362579345703,
|
| 1247 |
+
"learning_rate": 2.1209309895833336e-05,
|
| 1248 |
+
"loss": 2.9548,
|
| 1249 |
+
"step": 17700
|
| 1250 |
+
},
|
| 1251 |
+
{
|
| 1252 |
+
"epoch": 1.73828125,
|
| 1253 |
+
"grad_norm": 11.36043643951416,
|
| 1254 |
+
"learning_rate": 2.1048177083333334e-05,
|
| 1255 |
+
"loss": 2.8732,
|
| 1256 |
+
"step": 17800
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 1.748046875,
|
| 1260 |
+
"grad_norm": 12.69233512878418,
|
| 1261 |
+
"learning_rate": 2.088541666666667e-05,
|
| 1262 |
+
"loss": 2.9447,
|
| 1263 |
+
"step": 17900
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 1.7578125,
|
| 1267 |
+
"grad_norm": 13.44200611114502,
|
| 1268 |
+
"learning_rate": 2.072265625e-05,
|
| 1269 |
+
"loss": 2.8824,
|
| 1270 |
+
"step": 18000
|
| 1271 |
+
},
|
| 1272 |
+
{
|
| 1273 |
+
"epoch": 1.767578125,
|
| 1274 |
+
"grad_norm": 10.753628730773926,
|
| 1275 |
+
"learning_rate": 2.05615234375e-05,
|
| 1276 |
+
"loss": 2.8455,
|
| 1277 |
+
"step": 18100
|
| 1278 |
+
},
|
| 1279 |
+
{
|
| 1280 |
+
"epoch": 1.77734375,
|
| 1281 |
+
"grad_norm": 13.760424613952637,
|
| 1282 |
+
"learning_rate": 2.0398763020833335e-05,
|
| 1283 |
+
"loss": 2.9853,
|
| 1284 |
+
"step": 18200
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 1.787109375,
|
| 1288 |
+
"grad_norm": 16.471168518066406,
|
| 1289 |
+
"learning_rate": 2.023600260416667e-05,
|
| 1290 |
+
"loss": 2.8303,
|
| 1291 |
+
"step": 18300
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 1.796875,
|
| 1295 |
+
"grad_norm": 13.708788871765137,
|
| 1296 |
+
"learning_rate": 2.0073242187500004e-05,
|
| 1297 |
+
"loss": 2.9086,
|
| 1298 |
+
"step": 18400
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 1.806640625,
|
| 1302 |
+
"grad_norm": 13.522102355957031,
|
| 1303 |
+
"learning_rate": 1.9912109375000002e-05,
|
| 1304 |
+
"loss": 2.9567,
|
| 1305 |
+
"step": 18500
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 1.81640625,
|
| 1309 |
+
"grad_norm": 14.42663288116455,
|
| 1310 |
+
"learning_rate": 1.9749348958333333e-05,
|
| 1311 |
+
"loss": 2.8666,
|
| 1312 |
+
"step": 18600
|
| 1313 |
+
},
|
| 1314 |
+
{
|
| 1315 |
+
"epoch": 1.826171875,
|
| 1316 |
+
"grad_norm": 10.03260326385498,
|
| 1317 |
+
"learning_rate": 1.9586588541666667e-05,
|
| 1318 |
+
"loss": 2.9193,
|
| 1319 |
+
"step": 18700
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 1.8359375,
|
| 1323 |
+
"grad_norm": 10.757763862609863,
|
| 1324 |
+
"learning_rate": 1.9423828125e-05,
|
| 1325 |
+
"loss": 3.0071,
|
| 1326 |
+
"step": 18800
|
| 1327 |
+
},
|
| 1328 |
+
{
|
| 1329 |
+
"epoch": 1.845703125,
|
| 1330 |
+
"grad_norm": 12.414703369140625,
|
| 1331 |
+
"learning_rate": 1.9261067708333332e-05,
|
| 1332 |
+
"loss": 2.9446,
|
| 1333 |
+
"step": 18900
|
| 1334 |
+
},
|
| 1335 |
+
{
|
| 1336 |
+
"epoch": 1.85546875,
|
| 1337 |
+
"grad_norm": 12.182251930236816,
|
| 1338 |
+
"learning_rate": 1.9098307291666667e-05,
|
| 1339 |
+
"loss": 2.9584,
|
| 1340 |
+
"step": 19000
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"epoch": 1.865234375,
|
| 1344 |
+
"grad_norm": 13.588275909423828,
|
| 1345 |
+
"learning_rate": 1.8935546875e-05,
|
| 1346 |
+
"loss": 2.8303,
|
| 1347 |
+
"step": 19100
|
| 1348 |
+
},
|
| 1349 |
+
{
|
| 1350 |
+
"epoch": 1.875,
|
| 1351 |
+
"grad_norm": 11.538961410522461,
|
| 1352 |
+
"learning_rate": 1.8772786458333332e-05,
|
| 1353 |
+
"loss": 2.9129,
|
| 1354 |
+
"step": 19200
|
| 1355 |
+
},
|
| 1356 |
+
{
|
| 1357 |
+
"epoch": 1.884765625,
|
| 1358 |
+
"grad_norm": 14.856468200683594,
|
| 1359 |
+
"learning_rate": 1.8610026041666666e-05,
|
| 1360 |
+
"loss": 2.8229,
|
| 1361 |
+
"step": 19300
|
| 1362 |
+
},
|
| 1363 |
+
{
|
| 1364 |
+
"epoch": 1.89453125,
|
| 1365 |
+
"grad_norm": 12.910444259643555,
|
| 1366 |
+
"learning_rate": 1.8447265625e-05,
|
| 1367 |
+
"loss": 2.9851,
|
| 1368 |
+
"step": 19400
|
| 1369 |
+
},
|
| 1370 |
+
{
|
| 1371 |
+
"epoch": 1.904296875,
|
| 1372 |
+
"grad_norm": 12.187970161437988,
|
| 1373 |
+
"learning_rate": 1.828450520833333e-05,
|
| 1374 |
+
"loss": 2.863,
|
| 1375 |
+
"step": 19500
|
| 1376 |
+
},
|
| 1377 |
+
{
|
| 1378 |
+
"epoch": 1.9140625,
|
| 1379 |
+
"grad_norm": 16.951251983642578,
|
| 1380 |
+
"learning_rate": 1.8121744791666666e-05,
|
| 1381 |
+
"loss": 2.8726,
|
| 1382 |
+
"step": 19600
|
| 1383 |
+
},
|
| 1384 |
+
{
|
| 1385 |
+
"epoch": 1.923828125,
|
| 1386 |
+
"grad_norm": 10.626237869262695,
|
| 1387 |
+
"learning_rate": 1.7958984375e-05,
|
| 1388 |
+
"loss": 2.79,
|
| 1389 |
+
"step": 19700
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 1.93359375,
|
| 1393 |
+
"grad_norm": 13.63193416595459,
|
| 1394 |
+
"learning_rate": 1.7796223958333334e-05,
|
| 1395 |
+
"loss": 2.8807,
|
| 1396 |
+
"step": 19800
|
| 1397 |
+
},
|
| 1398 |
+
{
|
| 1399 |
+
"epoch": 1.943359375,
|
| 1400 |
+
"grad_norm": 12.877738952636719,
|
| 1401 |
+
"learning_rate": 1.763346354166667e-05,
|
| 1402 |
+
"loss": 2.7945,
|
| 1403 |
+
"step": 19900
|
| 1404 |
+
},
|
| 1405 |
+
{
|
| 1406 |
+
"epoch": 1.953125,
|
| 1407 |
+
"grad_norm": 12.08793830871582,
|
| 1408 |
+
"learning_rate": 1.7470703125000003e-05,
|
| 1409 |
+
"loss": 2.8932,
|
| 1410 |
+
"step": 20000
|
| 1411 |
+
},
|
| 1412 |
+
{
|
| 1413 |
+
"epoch": 1.962890625,
|
| 1414 |
+
"grad_norm": 12.529877662658691,
|
| 1415 |
+
"learning_rate": 1.7307942708333334e-05,
|
| 1416 |
+
"loss": 2.9178,
|
| 1417 |
+
"step": 20100
|
| 1418 |
+
},
|
| 1419 |
+
{
|
| 1420 |
+
"epoch": 1.97265625,
|
| 1421 |
+
"grad_norm": 12.949920654296875,
|
| 1422 |
+
"learning_rate": 1.7145182291666668e-05,
|
| 1423 |
+
"loss": 2.8207,
|
| 1424 |
+
"step": 20200
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 1.982421875,
|
| 1428 |
+
"grad_norm": 16.327682495117188,
|
| 1429 |
+
"learning_rate": 1.6982421875000003e-05,
|
| 1430 |
+
"loss": 2.9098,
|
| 1431 |
+
"step": 20300
|
| 1432 |
+
},
|
| 1433 |
+
{
|
| 1434 |
+
"epoch": 1.9921875,
|
| 1435 |
+
"grad_norm": 13.496146202087402,
|
| 1436 |
+
"learning_rate": 1.6819661458333334e-05,
|
| 1437 |
+
"loss": 2.7364,
|
| 1438 |
+
"step": 20400
|
| 1439 |
+
},
|
| 1440 |
+
{
|
| 1441 |
+
"epoch": 2.001953125,
|
| 1442 |
+
"grad_norm": 18.41584014892578,
|
| 1443 |
+
"learning_rate": 1.6656901041666668e-05,
|
| 1444 |
+
"loss": 2.8233,
|
| 1445 |
+
"step": 20500
|
| 1446 |
+
},
|
| 1447 |
+
{
|
| 1448 |
+
"epoch": 2.01171875,
|
| 1449 |
+
"grad_norm": 14.442363739013672,
|
| 1450 |
+
"learning_rate": 1.6494140625000002e-05,
|
| 1451 |
+
"loss": 2.7373,
|
| 1452 |
+
"step": 20600
|
| 1453 |
+
},
|
| 1454 |
+
{
|
| 1455 |
+
"epoch": 2.021484375,
|
| 1456 |
+
"grad_norm": 13.7149019241333,
|
| 1457 |
+
"learning_rate": 1.6331380208333333e-05,
|
| 1458 |
+
"loss": 2.7693,
|
| 1459 |
+
"step": 20700
|
| 1460 |
+
},
|
| 1461 |
+
{
|
| 1462 |
+
"epoch": 2.03125,
|
| 1463 |
+
"grad_norm": 17.81890296936035,
|
| 1464 |
+
"learning_rate": 1.6168619791666667e-05,
|
| 1465 |
+
"loss": 2.7528,
|
| 1466 |
+
"step": 20800
|
| 1467 |
+
},
|
| 1468 |
+
{
|
| 1469 |
+
"epoch": 2.041015625,
|
| 1470 |
+
"grad_norm": 11.57737922668457,
|
| 1471 |
+
"learning_rate": 1.6007486979166666e-05,
|
| 1472 |
+
"loss": 2.7167,
|
| 1473 |
+
"step": 20900
|
| 1474 |
+
},
|
| 1475 |
+
{
|
| 1476 |
+
"epoch": 2.05078125,
|
| 1477 |
+
"grad_norm": 12.967355728149414,
|
| 1478 |
+
"learning_rate": 1.58447265625e-05,
|
| 1479 |
+
"loss": 2.7034,
|
| 1480 |
+
"step": 21000
|
| 1481 |
+
},
|
| 1482 |
+
{
|
| 1483 |
+
"epoch": 2.060546875,
|
| 1484 |
+
"grad_norm": 10.983343124389648,
|
| 1485 |
+
"learning_rate": 1.568359375e-05,
|
| 1486 |
+
"loss": 2.7766,
|
| 1487 |
+
"step": 21100
|
| 1488 |
+
},
|
| 1489 |
+
{
|
| 1490 |
+
"epoch": 2.0703125,
|
| 1491 |
+
"grad_norm": 16.468509674072266,
|
| 1492 |
+
"learning_rate": 1.5520833333333336e-05,
|
| 1493 |
+
"loss": 2.7992,
|
| 1494 |
+
"step": 21200
|
| 1495 |
+
},
|
| 1496 |
+
{
|
| 1497 |
+
"epoch": 2.080078125,
|
| 1498 |
+
"grad_norm": 16.79848861694336,
|
| 1499 |
+
"learning_rate": 1.535807291666667e-05,
|
| 1500 |
+
"loss": 2.7826,
|
| 1501 |
+
"step": 21300
|
| 1502 |
+
},
|
| 1503 |
+
{
|
| 1504 |
+
"epoch": 2.08984375,
|
| 1505 |
+
"grad_norm": 16.537952423095703,
|
| 1506 |
+
"learning_rate": 1.5195312500000001e-05,
|
| 1507 |
+
"loss": 2.7119,
|
| 1508 |
+
"step": 21400
|
| 1509 |
+
},
|
| 1510 |
+
{
|
| 1511 |
+
"epoch": 2.099609375,
|
| 1512 |
+
"grad_norm": 11.28368854522705,
|
| 1513 |
+
"learning_rate": 1.5032552083333335e-05,
|
| 1514 |
+
"loss": 2.7093,
|
| 1515 |
+
"step": 21500
|
| 1516 |
+
},
|
| 1517 |
+
{
|
| 1518 |
+
"epoch": 2.109375,
|
| 1519 |
+
"grad_norm": 58.54060745239258,
|
| 1520 |
+
"learning_rate": 1.4869791666666668e-05,
|
| 1521 |
+
"loss": 2.7219,
|
| 1522 |
+
"step": 21600
|
| 1523 |
+
},
|
| 1524 |
+
{
|
| 1525 |
+
"epoch": 2.119140625,
|
| 1526 |
+
"grad_norm": 12.917949676513672,
|
| 1527 |
+
"learning_rate": 1.470703125e-05,
|
| 1528 |
+
"loss": 2.8239,
|
| 1529 |
+
"step": 21700
|
| 1530 |
+
},
|
| 1531 |
+
{
|
| 1532 |
+
"epoch": 2.12890625,
|
| 1533 |
+
"grad_norm": 18.68291664123535,
|
| 1534 |
+
"learning_rate": 1.4544270833333335e-05,
|
| 1535 |
+
"loss": 2.7574,
|
| 1536 |
+
"step": 21800
|
| 1537 |
+
},
|
| 1538 |
+
{
|
| 1539 |
+
"epoch": 2.138671875,
|
| 1540 |
+
"grad_norm": 11.076837539672852,
|
| 1541 |
+
"learning_rate": 1.4381510416666669e-05,
|
| 1542 |
+
"loss": 2.8418,
|
| 1543 |
+
"step": 21900
|
| 1544 |
+
},
|
| 1545 |
+
{
|
| 1546 |
+
"epoch": 2.1484375,
|
| 1547 |
+
"grad_norm": 16.057594299316406,
|
| 1548 |
+
"learning_rate": 1.421875e-05,
|
| 1549 |
+
"loss": 2.822,
|
| 1550 |
+
"step": 22000
|
| 1551 |
+
},
|
| 1552 |
+
{
|
| 1553 |
+
"epoch": 2.158203125,
|
| 1554 |
+
"grad_norm": 17.087045669555664,
|
| 1555 |
+
"learning_rate": 1.4055989583333334e-05,
|
| 1556 |
+
"loss": 2.7588,
|
| 1557 |
+
"step": 22100
|
| 1558 |
+
},
|
| 1559 |
+
{
|
| 1560 |
+
"epoch": 2.16796875,
|
| 1561 |
+
"grad_norm": 11.648773193359375,
|
| 1562 |
+
"learning_rate": 1.3893229166666669e-05,
|
| 1563 |
+
"loss": 2.717,
|
| 1564 |
+
"step": 22200
|
| 1565 |
+
},
|
| 1566 |
+
{
|
| 1567 |
+
"epoch": 2.177734375,
|
| 1568 |
+
"grad_norm": 12.739274024963379,
|
| 1569 |
+
"learning_rate": 1.373046875e-05,
|
| 1570 |
+
"loss": 2.6956,
|
| 1571 |
+
"step": 22300
|
| 1572 |
+
},
|
| 1573 |
+
{
|
| 1574 |
+
"epoch": 2.1875,
|
| 1575 |
+
"grad_norm": 10.17639446258545,
|
| 1576 |
+
"learning_rate": 1.3567708333333334e-05,
|
| 1577 |
+
"loss": 2.8241,
|
| 1578 |
+
"step": 22400
|
| 1579 |
+
},
|
| 1580 |
+
{
|
| 1581 |
+
"epoch": 2.197265625,
|
| 1582 |
+
"grad_norm": 13.572341918945312,
|
| 1583 |
+
"learning_rate": 1.3404947916666668e-05,
|
| 1584 |
+
"loss": 2.7858,
|
| 1585 |
+
"step": 22500
|
| 1586 |
+
},
|
| 1587 |
+
{
|
| 1588 |
+
"epoch": 2.20703125,
|
| 1589 |
+
"grad_norm": 14.310699462890625,
|
| 1590 |
+
"learning_rate": 1.3242187500000001e-05,
|
| 1591 |
+
"loss": 2.6909,
|
| 1592 |
+
"step": 22600
|
| 1593 |
+
},
|
| 1594 |
+
{
|
| 1595 |
+
"epoch": 2.216796875,
|
| 1596 |
+
"grad_norm": 11.991633415222168,
|
| 1597 |
+
"learning_rate": 1.3079427083333335e-05,
|
| 1598 |
+
"loss": 2.7708,
|
| 1599 |
+
"step": 22700
|
| 1600 |
+
},
|
| 1601 |
+
{
|
| 1602 |
+
"epoch": 2.2265625,
|
| 1603 |
+
"grad_norm": 14.214717864990234,
|
| 1604 |
+
"learning_rate": 1.2916666666666668e-05,
|
| 1605 |
+
"loss": 2.7603,
|
| 1606 |
+
"step": 22800
|
| 1607 |
+
},
|
| 1608 |
+
{
|
| 1609 |
+
"epoch": 2.236328125,
|
| 1610 |
+
"grad_norm": 16.019987106323242,
|
| 1611 |
+
"learning_rate": 1.275390625e-05,
|
| 1612 |
+
"loss": 2.7493,
|
| 1613 |
+
"step": 22900
|
| 1614 |
+
},
|
| 1615 |
+
{
|
| 1616 |
+
"epoch": 2.24609375,
|
| 1617 |
+
"grad_norm": 11.817761421203613,
|
| 1618 |
+
"learning_rate": 1.2591145833333335e-05,
|
| 1619 |
+
"loss": 2.7647,
|
| 1620 |
+
"step": 23000
|
| 1621 |
+
},
|
| 1622 |
+
{
|
| 1623 |
+
"epoch": 2.255859375,
|
| 1624 |
+
"grad_norm": 16.247276306152344,
|
| 1625 |
+
"learning_rate": 1.2430013020833335e-05,
|
| 1626 |
+
"loss": 2.7605,
|
| 1627 |
+
"step": 23100
|
| 1628 |
+
},
|
| 1629 |
+
{
|
| 1630 |
+
"epoch": 2.265625,
|
| 1631 |
+
"grad_norm": 11.79404067993164,
|
| 1632 |
+
"learning_rate": 1.2267252604166667e-05,
|
| 1633 |
+
"loss": 2.7058,
|
| 1634 |
+
"step": 23200
|
| 1635 |
+
},
|
| 1636 |
+
{
|
| 1637 |
+
"epoch": 2.275390625,
|
| 1638 |
+
"grad_norm": 12.77724838256836,
|
| 1639 |
+
"learning_rate": 1.2104492187500001e-05,
|
| 1640 |
+
"loss": 2.7446,
|
| 1641 |
+
"step": 23300
|
| 1642 |
+
},
|
| 1643 |
+
{
|
| 1644 |
+
"epoch": 2.28515625,
|
| 1645 |
+
"grad_norm": 11.609589576721191,
|
| 1646 |
+
"learning_rate": 1.1941731770833334e-05,
|
| 1647 |
+
"loss": 2.7794,
|
| 1648 |
+
"step": 23400
|
| 1649 |
+
},
|
| 1650 |
+
{
|
| 1651 |
+
"epoch": 2.294921875,
|
| 1652 |
+
"grad_norm": 13.240425109863281,
|
| 1653 |
+
"learning_rate": 1.1780598958333334e-05,
|
| 1654 |
+
"loss": 2.8056,
|
| 1655 |
+
"step": 23500
|
| 1656 |
+
},
|
| 1657 |
+
{
|
| 1658 |
+
"epoch": 2.3046875,
|
| 1659 |
+
"grad_norm": 15.682677268981934,
|
| 1660 |
+
"learning_rate": 1.1617838541666668e-05,
|
| 1661 |
+
"loss": 2.7102,
|
| 1662 |
+
"step": 23600
|
| 1663 |
+
},
|
| 1664 |
+
{
|
| 1665 |
+
"epoch": 2.314453125,
|
| 1666 |
+
"grad_norm": 15.334482192993164,
|
| 1667 |
+
"learning_rate": 1.1455078125e-05,
|
| 1668 |
+
"loss": 2.8026,
|
| 1669 |
+
"step": 23700
|
| 1670 |
+
},
|
| 1671 |
+
{
|
| 1672 |
+
"epoch": 2.32421875,
|
| 1673 |
+
"grad_norm": 11.944014549255371,
|
| 1674 |
+
"learning_rate": 1.1292317708333335e-05,
|
| 1675 |
+
"loss": 2.7106,
|
| 1676 |
+
"step": 23800
|
| 1677 |
+
},
|
| 1678 |
+
{
|
| 1679 |
+
"epoch": 2.333984375,
|
| 1680 |
+
"grad_norm": 13.437361717224121,
|
| 1681 |
+
"learning_rate": 1.1129557291666668e-05,
|
| 1682 |
+
"loss": 2.6837,
|
| 1683 |
+
"step": 23900
|
| 1684 |
+
},
|
| 1685 |
+
{
|
| 1686 |
+
"epoch": 2.34375,
|
| 1687 |
+
"grad_norm": 15.150136947631836,
|
| 1688 |
+
"learning_rate": 1.0966796875e-05,
|
| 1689 |
+
"loss": 2.7095,
|
| 1690 |
+
"step": 24000
|
| 1691 |
+
},
|
| 1692 |
+
{
|
| 1693 |
+
"epoch": 2.353515625,
|
| 1694 |
+
"grad_norm": 13.133088111877441,
|
| 1695 |
+
"learning_rate": 1.0804036458333335e-05,
|
| 1696 |
+
"loss": 2.7609,
|
| 1697 |
+
"step": 24100
|
| 1698 |
+
},
|
| 1699 |
+
{
|
| 1700 |
+
"epoch": 2.36328125,
|
| 1701 |
+
"grad_norm": 12.005653381347656,
|
| 1702 |
+
"learning_rate": 1.0641276041666667e-05,
|
| 1703 |
+
"loss": 2.7086,
|
| 1704 |
+
"step": 24200
|
| 1705 |
+
},
|
| 1706 |
+
{
|
| 1707 |
+
"epoch": 2.373046875,
|
| 1708 |
+
"grad_norm": 20.258712768554688,
|
| 1709 |
+
"learning_rate": 1.0478515625e-05,
|
| 1710 |
+
"loss": 2.8082,
|
| 1711 |
+
"step": 24300
|
| 1712 |
+
},
|
| 1713 |
+
{
|
| 1714 |
+
"epoch": 2.3828125,
|
| 1715 |
+
"grad_norm": 14.602194786071777,
|
| 1716 |
+
"learning_rate": 1.0315755208333334e-05,
|
| 1717 |
+
"loss": 2.6246,
|
| 1718 |
+
"step": 24400
|
| 1719 |
+
},
|
| 1720 |
+
{
|
| 1721 |
+
"epoch": 2.392578125,
|
| 1722 |
+
"grad_norm": 13.00714111328125,
|
| 1723 |
+
"learning_rate": 1.0152994791666667e-05,
|
| 1724 |
+
"loss": 2.8249,
|
| 1725 |
+
"step": 24500
|
| 1726 |
+
},
|
| 1727 |
+
{
|
| 1728 |
+
"epoch": 2.40234375,
|
| 1729 |
+
"grad_norm": 11.645508766174316,
|
| 1730 |
+
"learning_rate": 9.990234375e-06,
|
| 1731 |
+
"loss": 2.7555,
|
| 1732 |
+
"step": 24600
|
| 1733 |
+
},
|
| 1734 |
+
{
|
| 1735 |
+
"epoch": 2.412109375,
|
| 1736 |
+
"grad_norm": 17.61017417907715,
|
| 1737 |
+
"learning_rate": 9.827473958333334e-06,
|
| 1738 |
+
"loss": 2.6942,
|
| 1739 |
+
"step": 24700
|
| 1740 |
+
},
|
| 1741 |
+
{
|
| 1742 |
+
"epoch": 2.421875,
|
| 1743 |
+
"grad_norm": 12.34157943725586,
|
| 1744 |
+
"learning_rate": 9.664713541666668e-06,
|
| 1745 |
+
"loss": 2.7215,
|
| 1746 |
+
"step": 24800
|
| 1747 |
+
},
|
| 1748 |
+
{
|
| 1749 |
+
"epoch": 2.431640625,
|
| 1750 |
+
"grad_norm": 12.765501976013184,
|
| 1751 |
+
"learning_rate": 9.501953125e-06,
|
| 1752 |
+
"loss": 2.5747,
|
| 1753 |
+
"step": 24900
|
| 1754 |
+
},
|
| 1755 |
+
{
|
| 1756 |
+
"epoch": 2.44140625,
|
| 1757 |
+
"grad_norm": 12.85317611694336,
|
| 1758 |
+
"learning_rate": 9.339192708333335e-06,
|
| 1759 |
+
"loss": 2.7917,
|
| 1760 |
+
"step": 25000
|
| 1761 |
+
},
|
| 1762 |
+
{
|
| 1763 |
+
"epoch": 2.451171875,
|
| 1764 |
+
"grad_norm": 12.610406875610352,
|
| 1765 |
+
"learning_rate": 9.176432291666668e-06,
|
| 1766 |
+
"loss": 2.8635,
|
| 1767 |
+
"step": 25100
|
| 1768 |
+
},
|
| 1769 |
+
{
|
| 1770 |
+
"epoch": 2.4609375,
|
| 1771 |
+
"grad_norm": 12.031999588012695,
|
| 1772 |
+
"learning_rate": 9.013671875e-06,
|
| 1773 |
+
"loss": 2.6288,
|
| 1774 |
+
"step": 25200
|
| 1775 |
+
},
|
| 1776 |
+
{
|
| 1777 |
+
"epoch": 2.470703125,
|
| 1778 |
+
"grad_norm": 10.63759994506836,
|
| 1779 |
+
"learning_rate": 8.850911458333335e-06,
|
| 1780 |
+
"loss": 2.7396,
|
| 1781 |
+
"step": 25300
|
| 1782 |
+
},
|
| 1783 |
+
{
|
| 1784 |
+
"epoch": 2.48046875,
|
| 1785 |
+
"grad_norm": 18.768993377685547,
|
| 1786 |
+
"learning_rate": 8.688151041666667e-06,
|
| 1787 |
+
"loss": 2.6733,
|
| 1788 |
+
"step": 25400
|
| 1789 |
+
},
|
| 1790 |
+
{
|
| 1791 |
+
"epoch": 2.490234375,
|
| 1792 |
+
"grad_norm": 9.411011695861816,
|
| 1793 |
+
"learning_rate": 8.525390625e-06,
|
| 1794 |
+
"loss": 2.7355,
|
| 1795 |
+
"step": 25500
|
| 1796 |
+
},
|
| 1797 |
+
{
|
| 1798 |
+
"epoch": 2.5,
|
| 1799 |
+
"grad_norm": 11.31039810180664,
|
| 1800 |
+
"learning_rate": 8.362630208333334e-06,
|
| 1801 |
+
"loss": 2.6648,
|
| 1802 |
+
"step": 25600
|
| 1803 |
+
},
|
| 1804 |
+
{
|
| 1805 |
+
"epoch": 2.509765625,
|
| 1806 |
+
"grad_norm": 11.34940242767334,
|
| 1807 |
+
"learning_rate": 8.199869791666667e-06,
|
| 1808 |
+
"loss": 2.6185,
|
| 1809 |
+
"step": 25700
|
| 1810 |
+
},
|
| 1811 |
+
{
|
| 1812 |
+
"epoch": 2.51953125,
|
| 1813 |
+
"grad_norm": 13.539913177490234,
|
| 1814 |
+
"learning_rate": 8.037109375e-06,
|
| 1815 |
+
"loss": 2.6344,
|
| 1816 |
+
"step": 25800
|
| 1817 |
+
},
|
| 1818 |
+
{
|
| 1819 |
+
"epoch": 2.529296875,
|
| 1820 |
+
"grad_norm": 12.985583305358887,
|
| 1821 |
+
"learning_rate": 7.874348958333334e-06,
|
| 1822 |
+
"loss": 2.7028,
|
| 1823 |
+
"step": 25900
|
| 1824 |
+
},
|
| 1825 |
+
{
|
| 1826 |
+
"epoch": 2.5390625,
|
| 1827 |
+
"grad_norm": 23.021692276000977,
|
| 1828 |
+
"learning_rate": 7.711588541666666e-06,
|
| 1829 |
+
"loss": 2.6719,
|
| 1830 |
+
"step": 26000
|
| 1831 |
+
},
|
| 1832 |
+
{
|
| 1833 |
+
"epoch": 2.548828125,
|
| 1834 |
+
"grad_norm": 14.796003341674805,
|
| 1835 |
+
"learning_rate": 7.548828125e-06,
|
| 1836 |
+
"loss": 2.669,
|
| 1837 |
+
"step": 26100
|
| 1838 |
+
},
|
| 1839 |
+
{
|
| 1840 |
+
"epoch": 2.55859375,
|
| 1841 |
+
"grad_norm": 16.303749084472656,
|
| 1842 |
+
"learning_rate": 7.386067708333334e-06,
|
| 1843 |
+
"loss": 2.5954,
|
| 1844 |
+
"step": 26200
|
| 1845 |
+
},
|
| 1846 |
+
{
|
| 1847 |
+
"epoch": 2.568359375,
|
| 1848 |
+
"grad_norm": 10.631623268127441,
|
| 1849 |
+
"learning_rate": 7.223307291666667e-06,
|
| 1850 |
+
"loss": 2.669,
|
| 1851 |
+
"step": 26300
|
| 1852 |
+
},
|
| 1853 |
+
{
|
| 1854 |
+
"epoch": 2.578125,
|
| 1855 |
+
"grad_norm": 13.405618667602539,
|
| 1856 |
+
"learning_rate": 7.060546875e-06,
|
| 1857 |
+
"loss": 2.7102,
|
| 1858 |
+
"step": 26400
|
| 1859 |
+
},
|
| 1860 |
+
{
|
| 1861 |
+
"epoch": 2.587890625,
|
| 1862 |
+
"grad_norm": 16.89972496032715,
|
| 1863 |
+
"learning_rate": 6.897786458333335e-06,
|
| 1864 |
+
"loss": 2.7198,
|
| 1865 |
+
"step": 26500
|
| 1866 |
+
},
|
| 1867 |
+
{
|
| 1868 |
+
"epoch": 2.59765625,
|
| 1869 |
+
"grad_norm": 14.60909652709961,
|
| 1870 |
+
"learning_rate": 6.735026041666667e-06,
|
| 1871 |
+
"loss": 2.686,
|
| 1872 |
+
"step": 26600
|
| 1873 |
+
},
|
| 1874 |
+
{
|
| 1875 |
+
"epoch": 2.607421875,
|
| 1876 |
+
"grad_norm": 16.859573364257812,
|
| 1877 |
+
"learning_rate": 6.572265625e-06,
|
| 1878 |
+
"loss": 2.7073,
|
| 1879 |
+
"step": 26700
|
| 1880 |
+
},
|
| 1881 |
+
{
|
| 1882 |
+
"epoch": 2.6171875,
|
| 1883 |
+
"grad_norm": 12.876221656799316,
|
| 1884 |
+
"learning_rate": 6.409505208333334e-06,
|
| 1885 |
+
"loss": 2.66,
|
| 1886 |
+
"step": 26800
|
| 1887 |
+
},
|
| 1888 |
+
{
|
| 1889 |
+
"epoch": 2.626953125,
|
| 1890 |
+
"grad_norm": 12.116389274597168,
|
| 1891 |
+
"learning_rate": 6.246744791666667e-06,
|
| 1892 |
+
"loss": 2.6773,
|
| 1893 |
+
"step": 26900
|
| 1894 |
+
},
|
| 1895 |
+
{
|
| 1896 |
+
"epoch": 2.63671875,
|
| 1897 |
+
"grad_norm": 13.397444725036621,
|
| 1898 |
+
"learning_rate": 6.083984375e-06,
|
| 1899 |
+
"loss": 2.5832,
|
| 1900 |
+
"step": 27000
|
| 1901 |
+
},
|
| 1902 |
+
{
|
| 1903 |
+
"epoch": 2.646484375,
|
| 1904 |
+
"grad_norm": 14.27937126159668,
|
| 1905 |
+
"learning_rate": 5.921223958333334e-06,
|
| 1906 |
+
"loss": 2.7137,
|
| 1907 |
+
"step": 27100
|
| 1908 |
+
},
|
| 1909 |
+
{
|
| 1910 |
+
"epoch": 2.65625,
|
| 1911 |
+
"grad_norm": 12.069489479064941,
|
| 1912 |
+
"learning_rate": 5.758463541666667e-06,
|
| 1913 |
+
"loss": 2.6435,
|
| 1914 |
+
"step": 27200
|
| 1915 |
+
},
|
| 1916 |
+
{
|
| 1917 |
+
"epoch": 2.666015625,
|
| 1918 |
+
"grad_norm": 11.179854393005371,
|
| 1919 |
+
"learning_rate": 5.595703125e-06,
|
| 1920 |
+
"loss": 2.707,
|
| 1921 |
+
"step": 27300
|
| 1922 |
+
},
|
| 1923 |
+
{
|
| 1924 |
+
"epoch": 2.67578125,
|
| 1925 |
+
"grad_norm": 11.071802139282227,
|
| 1926 |
+
"learning_rate": 5.432942708333333e-06,
|
| 1927 |
+
"loss": 2.6166,
|
| 1928 |
+
"step": 27400
|
| 1929 |
+
},
|
| 1930 |
+
{
|
| 1931 |
+
"epoch": 2.685546875,
|
| 1932 |
+
"grad_norm": 14.306278228759766,
|
| 1933 |
+
"learning_rate": 5.270182291666667e-06,
|
| 1934 |
+
"loss": 2.6747,
|
| 1935 |
+
"step": 27500
|
| 1936 |
+
},
|
| 1937 |
+
{
|
| 1938 |
+
"epoch": 2.6953125,
|
| 1939 |
+
"grad_norm": 14.3062744140625,
|
| 1940 |
+
"learning_rate": 5.107421875e-06,
|
| 1941 |
+
"loss": 2.5382,
|
| 1942 |
+
"step": 27600
|
| 1943 |
+
},
|
| 1944 |
+
{
|
| 1945 |
+
"epoch": 2.705078125,
|
| 1946 |
+
"grad_norm": 14.975716590881348,
|
| 1947 |
+
"learning_rate": 4.944661458333334e-06,
|
| 1948 |
+
"loss": 2.7215,
|
| 1949 |
+
"step": 27700
|
| 1950 |
+
},
|
| 1951 |
+
{
|
| 1952 |
+
"epoch": 2.71484375,
|
| 1953 |
+
"grad_norm": 14.584077835083008,
|
| 1954 |
+
"learning_rate": 4.781901041666667e-06,
|
| 1955 |
+
"loss": 2.7351,
|
| 1956 |
+
"step": 27800
|
| 1957 |
+
},
|
| 1958 |
+
{
|
| 1959 |
+
"epoch": 2.724609375,
|
| 1960 |
+
"grad_norm": 11.181657791137695,
|
| 1961 |
+
"learning_rate": 4.619140625e-06,
|
| 1962 |
+
"loss": 2.576,
|
| 1963 |
+
"step": 27900
|
| 1964 |
+
},
|
| 1965 |
+
{
|
| 1966 |
+
"epoch": 2.734375,
|
| 1967 |
+
"grad_norm": 10.974489212036133,
|
| 1968 |
+
"learning_rate": 4.456380208333333e-06,
|
| 1969 |
+
"loss": 2.7631,
|
| 1970 |
+
"step": 28000
|
| 1971 |
+
},
|
| 1972 |
+
{
|
| 1973 |
+
"epoch": 2.744140625,
|
| 1974 |
+
"grad_norm": 15.731523513793945,
|
| 1975 |
+
"learning_rate": 4.295247395833334e-06,
|
| 1976 |
+
"loss": 2.5512,
|
| 1977 |
+
"step": 28100
|
| 1978 |
+
},
|
| 1979 |
+
{
|
| 1980 |
+
"epoch": 2.75390625,
|
| 1981 |
+
"grad_norm": 12.23338794708252,
|
| 1982 |
+
"learning_rate": 4.132486979166667e-06,
|
| 1983 |
+
"loss": 2.6233,
|
| 1984 |
+
"step": 28200
|
| 1985 |
+
},
|
| 1986 |
+
{
|
| 1987 |
+
"epoch": 2.763671875,
|
| 1988 |
+
"grad_norm": 9.420981407165527,
|
| 1989 |
+
"learning_rate": 3.9697265625e-06,
|
| 1990 |
+
"loss": 2.6464,
|
| 1991 |
+
"step": 28300
|
| 1992 |
+
},
|
| 1993 |
+
{
|
| 1994 |
+
"epoch": 2.7734375,
|
| 1995 |
+
"grad_norm": 10.947881698608398,
|
| 1996 |
+
"learning_rate": 3.8069661458333335e-06,
|
| 1997 |
+
"loss": 2.6197,
|
| 1998 |
+
"step": 28400
|
| 1999 |
+
},
|
| 2000 |
+
{
|
| 2001 |
+
"epoch": 2.783203125,
|
| 2002 |
+
"grad_norm": 17.761030197143555,
|
| 2003 |
+
"learning_rate": 3.644205729166667e-06,
|
| 2004 |
+
"loss": 2.6341,
|
| 2005 |
+
"step": 28500
|
| 2006 |
+
},
|
| 2007 |
+
{
|
| 2008 |
+
"epoch": 2.79296875,
|
| 2009 |
+
"grad_norm": 15.768482208251953,
|
| 2010 |
+
"learning_rate": 3.4814453125e-06,
|
| 2011 |
+
"loss": 2.653,
|
| 2012 |
+
"step": 28600
|
| 2013 |
+
},
|
| 2014 |
+
{
|
| 2015 |
+
"epoch": 2.802734375,
|
| 2016 |
+
"grad_norm": 13.388958930969238,
|
| 2017 |
+
"learning_rate": 3.3186848958333335e-06,
|
| 2018 |
+
"loss": 2.5511,
|
| 2019 |
+
"step": 28700
|
| 2020 |
+
},
|
| 2021 |
+
{
|
| 2022 |
+
"epoch": 2.8125,
|
| 2023 |
+
"grad_norm": 11.864120483398438,
|
| 2024 |
+
"learning_rate": 3.155924479166667e-06,
|
| 2025 |
+
"loss": 2.7781,
|
| 2026 |
+
"step": 28800
|
| 2027 |
+
},
|
| 2028 |
+
{
|
| 2029 |
+
"epoch": 2.822265625,
|
| 2030 |
+
"grad_norm": 11.44416618347168,
|
| 2031 |
+
"learning_rate": 2.9931640625e-06,
|
| 2032 |
+
"loss": 2.6667,
|
| 2033 |
+
"step": 28900
|
| 2034 |
+
},
|
| 2035 |
+
{
|
| 2036 |
+
"epoch": 2.83203125,
|
| 2037 |
+
"grad_norm": 13.012479782104492,
|
| 2038 |
+
"learning_rate": 2.8304036458333335e-06,
|
| 2039 |
+
"loss": 2.6217,
|
| 2040 |
+
"step": 29000
|
| 2041 |
+
},
|
| 2042 |
+
{
|
| 2043 |
+
"epoch": 2.841796875,
|
| 2044 |
+
"grad_norm": 14.73644733428955,
|
| 2045 |
+
"learning_rate": 2.667643229166667e-06,
|
| 2046 |
+
"loss": 2.606,
|
| 2047 |
+
"step": 29100
|
| 2048 |
+
},
|
| 2049 |
+
{
|
| 2050 |
+
"epoch": 2.8515625,
|
| 2051 |
+
"grad_norm": 12.075024604797363,
|
| 2052 |
+
"learning_rate": 2.5048828125e-06,
|
| 2053 |
+
"loss": 2.5863,
|
| 2054 |
+
"step": 29200
|
| 2055 |
+
},
|
| 2056 |
+
{
|
| 2057 |
+
"epoch": 2.861328125,
|
| 2058 |
+
"grad_norm": 14.664973258972168,
|
| 2059 |
+
"learning_rate": 2.3421223958333335e-06,
|
| 2060 |
+
"loss": 2.7423,
|
| 2061 |
+
"step": 29300
|
| 2062 |
+
},
|
| 2063 |
+
{
|
| 2064 |
+
"epoch": 2.87109375,
|
| 2065 |
+
"grad_norm": 14.096378326416016,
|
| 2066 |
+
"learning_rate": 2.179361979166667e-06,
|
| 2067 |
+
"loss": 2.7122,
|
| 2068 |
+
"step": 29400
|
| 2069 |
+
},
|
| 2070 |
+
{
|
| 2071 |
+
"epoch": 2.880859375,
|
| 2072 |
+
"grad_norm": 12.812738418579102,
|
| 2073 |
+
"learning_rate": 2.0166015625e-06,
|
| 2074 |
+
"loss": 2.7648,
|
| 2075 |
+
"step": 29500
|
| 2076 |
+
},
|
| 2077 |
+
{
|
| 2078 |
+
"epoch": 2.890625,
|
| 2079 |
+
"grad_norm": 16.189590454101562,
|
| 2080 |
+
"learning_rate": 1.8538411458333335e-06,
|
| 2081 |
+
"loss": 2.669,
|
| 2082 |
+
"step": 29600
|
| 2083 |
+
},
|
| 2084 |
+
{
|
| 2085 |
+
"epoch": 2.900390625,
|
| 2086 |
+
"grad_norm": 14.232686996459961,
|
| 2087 |
+
"learning_rate": 1.6910807291666667e-06,
|
| 2088 |
+
"loss": 2.6242,
|
| 2089 |
+
"step": 29700
|
| 2090 |
+
},
|
| 2091 |
+
{
|
| 2092 |
+
"epoch": 2.91015625,
|
| 2093 |
+
"grad_norm": 16.499113082885742,
|
| 2094 |
+
"learning_rate": 1.5283203125000002e-06,
|
| 2095 |
+
"loss": 2.7261,
|
| 2096 |
+
"step": 29800
|
| 2097 |
+
},
|
| 2098 |
+
{
|
| 2099 |
+
"epoch": 2.919921875,
|
| 2100 |
+
"grad_norm": 10.421613693237305,
|
| 2101 |
+
"learning_rate": 1.3655598958333332e-06,
|
| 2102 |
+
"loss": 2.5805,
|
| 2103 |
+
"step": 29900
|
| 2104 |
+
},
|
| 2105 |
+
{
|
| 2106 |
+
"epoch": 2.9296875,
|
| 2107 |
+
"grad_norm": 11.867895126342773,
|
| 2108 |
+
"learning_rate": 1.2027994791666667e-06,
|
| 2109 |
+
"loss": 2.6225,
|
| 2110 |
+
"step": 30000
|
| 2111 |
+
},
|
| 2112 |
+
{
|
| 2113 |
+
"epoch": 2.939453125,
|
| 2114 |
+
"grad_norm": 14.396392822265625,
|
| 2115 |
+
"learning_rate": 1.0400390625000002e-06,
|
| 2116 |
+
"loss": 2.591,
|
| 2117 |
+
"step": 30100
|
| 2118 |
+
},
|
| 2119 |
+
{
|
| 2120 |
+
"epoch": 2.94921875,
|
| 2121 |
+
"grad_norm": 26.637563705444336,
|
| 2122 |
+
"learning_rate": 8.772786458333333e-07,
|
| 2123 |
+
"loss": 2.6324,
|
| 2124 |
+
"step": 30200
|
| 2125 |
+
},
|
| 2126 |
+
{
|
| 2127 |
+
"epoch": 2.958984375,
|
| 2128 |
+
"grad_norm": 13.43743896484375,
|
| 2129 |
+
"learning_rate": 7.145182291666667e-07,
|
| 2130 |
+
"loss": 2.7171,
|
| 2131 |
+
"step": 30300
|
| 2132 |
+
},
|
| 2133 |
+
{
|
| 2134 |
+
"epoch": 2.96875,
|
| 2135 |
+
"grad_norm": 13.423970222473145,
|
| 2136 |
+
"learning_rate": 5.517578125000001e-07,
|
| 2137 |
+
"loss": 2.5509,
|
| 2138 |
+
"step": 30400
|
| 2139 |
+
},
|
| 2140 |
+
{
|
| 2141 |
+
"epoch": 2.978515625,
|
| 2142 |
+
"grad_norm": 12.26883316040039,
|
| 2143 |
+
"learning_rate": 3.889973958333334e-07,
|
| 2144 |
+
"loss": 2.6303,
|
| 2145 |
+
"step": 30500
|
| 2146 |
+
},
|
| 2147 |
+
{
|
| 2148 |
+
"epoch": 2.98828125,
|
| 2149 |
+
"grad_norm": 13.305875778198242,
|
| 2150 |
+
"learning_rate": 2.262369791666667e-07,
|
| 2151 |
+
"loss": 2.6542,
|
| 2152 |
+
"step": 30600
|
| 2153 |
+
},
|
| 2154 |
+
{
|
| 2155 |
+
"epoch": 2.998046875,
|
| 2156 |
+
"grad_norm": 18.230594635009766,
|
| 2157 |
+
"learning_rate": 6.347656250000001e-08,
|
| 2158 |
+
"loss": 2.6088,
|
| 2159 |
+
"step": 30700
|
| 2160 |
+
},
|
| 2161 |
+
{
|
| 2162 |
+
"epoch": 3.0,
|
| 2163 |
+
"step": 30720,
|
| 2164 |
+
"total_flos": 4.206282006594048e+16,
|
| 2165 |
+
"train_loss": 3.0830205624302227,
|
| 2166 |
+
"train_runtime": 6816.3036,
|
| 2167 |
+
"train_samples_per_second": 72.109,
|
| 2168 |
+
"train_steps_per_second": 4.507
|
| 2169 |
+
}
|
| 2170 |
+
],
|
| 2171 |
+
"logging_steps": 100,
|
| 2172 |
+
"max_steps": 30720,
|
| 2173 |
+
"num_input_tokens_seen": 0,
|
| 2174 |
+
"num_train_epochs": 3,
|
| 2175 |
+
"save_steps": 1000,
|
| 2176 |
+
"stateful_callbacks": {
|
| 2177 |
+
"TrainerControl": {
|
| 2178 |
+
"args": {
|
| 2179 |
+
"should_epoch_stop": false,
|
| 2180 |
+
"should_evaluate": false,
|
| 2181 |
+
"should_log": false,
|
| 2182 |
+
"should_save": true,
|
| 2183 |
+
"should_training_stop": true
|
| 2184 |
+
},
|
| 2185 |
+
"attributes": {}
|
| 2186 |
+
}
|
| 2187 |
+
},
|
| 2188 |
+
"total_flos": 4.206282006594048e+16,
|
| 2189 |
+
"train_batch_size": 16,
|
| 2190 |
+
"trial_name": null,
|
| 2191 |
+
"trial_params": null
|
| 2192 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:65446e104857d9065085080ad419ad131c6bbd56fe4e6736d3aa6873e107fd71
|
| 3 |
+
size 5304
|