update
Browse files- README.md +36 -28
- all_results.json +13 -13
- config.json +4 -2
- eval_results.json +6 -8
- pytorch_model.bin +2 -2
- tokenizer_config.json +1 -1
- train_results.json +6 -6
- trainer_state.json +998 -842
- training_args.bin +2 -2
README.md
CHANGED
|
@@ -4,23 +4,19 @@ language:
|
|
| 4 |
- he
|
| 5 |
tags:
|
| 6 |
- generated_from_trainer
|
| 7 |
-
metrics:
|
| 8 |
-
- bleu
|
| 9 |
model-index:
|
| 10 |
-
- name:
|
| 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 |
-
#
|
| 18 |
|
| 19 |
-
This model is a fine-tuned version of [/
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
-
- Loss: 1.
|
| 22 |
-
- Bleu: 30.5903
|
| 23 |
-
- Gen Len: 64.8182
|
| 24 |
|
| 25 |
## Model description
|
| 26 |
|
|
@@ -39,34 +35,46 @@ More information needed
|
|
| 39 |
### Training hyperparameters
|
| 40 |
|
| 41 |
The following hyperparameters were used during training:
|
| 42 |
-
- learning_rate:
|
| 43 |
-
- train_batch_size:
|
| 44 |
-
- eval_batch_size:
|
| 45 |
- seed: 42
|
|
|
|
|
|
|
| 46 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 47 |
- lr_scheduler_type: linear
|
| 48 |
-
- num_epochs:
|
| 49 |
- mixed_precision_training: Native AMP
|
| 50 |
|
| 51 |
### Training results
|
| 52 |
|
| 53 |
-
| Training Loss | Epoch | Step
|
| 54 |
-
|
| 55 |
-
|
|
| 56 |
-
| 1.
|
| 57 |
-
| 1.
|
| 58 |
-
| 1.
|
| 59 |
-
| 1.
|
| 60 |
-
| 1.
|
| 61 |
-
| 1.
|
| 62 |
-
| 1.
|
| 63 |
-
| 1.
|
| 64 |
-
| 1.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 65 |
|
| 66 |
|
| 67 |
### Framework versions
|
| 68 |
|
| 69 |
-
- Transformers 4.
|
| 70 |
-
- Pytorch 1.
|
| 71 |
-
- Datasets 1.
|
| 72 |
-
- Tokenizers 0.
|
|
|
|
| 4 |
- he
|
| 5 |
tags:
|
| 6 |
- generated_from_trainer
|
|
|
|
|
|
|
| 7 |
model-index:
|
| 8 |
+
- name: marian_base
|
| 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 |
+
# marian_base
|
| 16 |
|
| 17 |
+
This model is a fine-tuned version of [orendar/en_he_base](https://huggingface.co/orendar/en_he_base) on the None dataset.
|
| 18 |
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 1.6365
|
|
|
|
|
|
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
|
|
|
| 35 |
### Training hyperparameters
|
| 36 |
|
| 37 |
The following hyperparameters were used during training:
|
| 38 |
+
- learning_rate: 0.0001
|
| 39 |
+
- train_batch_size: 160
|
| 40 |
+
- eval_batch_size: 160
|
| 41 |
- seed: 42
|
| 42 |
+
- gradient_accumulation_steps: 2
|
| 43 |
+
- total_train_batch_size: 320
|
| 44 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 45 |
- lr_scheduler_type: linear
|
| 46 |
+
- num_epochs: 20.0
|
| 47 |
- mixed_precision_training: Native AMP
|
| 48 |
|
| 49 |
### Training results
|
| 50 |
|
| 51 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 52 |
+
|:-------------:|:-----:|:------:|:---------------:|
|
| 53 |
+
| 2.125 | 1.0 | 30633 | 2.0720 |
|
| 54 |
+
| 1.9288 | 2.0 | 61266 | 1.9033 |
|
| 55 |
+
| 1.8387 | 3.0 | 91899 | 1.8330 |
|
| 56 |
+
| 1.7832 | 4.0 | 122532 | 1.7864 |
|
| 57 |
+
| 1.7445 | 5.0 | 153165 | 1.7592 |
|
| 58 |
+
| 1.7152 | 6.0 | 183798 | 1.7404 |
|
| 59 |
+
| 1.6933 | 7.0 | 214431 | 1.7208 |
|
| 60 |
+
| 1.6743 | 8.0 | 245064 | 1.7005 |
|
| 61 |
+
| 1.6561 | 9.0 | 275697 | 1.6907 |
|
| 62 |
+
| 1.6431 | 10.0 | 306330 | 1.6903 |
|
| 63 |
+
| 1.6282 | 11.0 | 336963 | 1.6801 |
|
| 64 |
+
| 1.6173 | 12.0 | 367596 | 1.6714 |
|
| 65 |
+
| 1.6061 | 13.0 | 398229 | 1.6634 |
|
| 66 |
+
| 1.5971 | 14.0 | 428862 | 1.6543 |
|
| 67 |
+
| 1.5867 | 15.0 | 459495 | 1.6488 |
|
| 68 |
+
| 1.5781 | 16.0 | 490128 | 1.6447 |
|
| 69 |
+
| 1.5684 | 17.0 | 520761 | 1.6388 |
|
| 70 |
+
| 1.5597 | 18.0 | 551394 | 1.6416 |
|
| 71 |
+
| 1.5521 | 19.0 | 582027 | 1.6370 |
|
| 72 |
+
| 1.5438 | 20.0 | 612660 | 1.6365 |
|
| 73 |
|
| 74 |
|
| 75 |
### Framework versions
|
| 76 |
|
| 77 |
+
- Transformers 4.18.0.dev0
|
| 78 |
+
- Pytorch 1.11.0+cu102
|
| 79 |
+
- Datasets 1.18.4
|
| 80 |
+
- Tokenizers 0.11.6
|
all_results.json
CHANGED
|
@@ -1,15 +1,15 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"eval_bleu":
|
| 4 |
-
"eval_gen_len":
|
| 5 |
-
"eval_loss": 1.
|
| 6 |
-
"eval_runtime":
|
| 7 |
-
"eval_samples":
|
| 8 |
-
"eval_samples_per_second":
|
| 9 |
-
"eval_steps_per_second":
|
| 10 |
-
"train_loss": 1.
|
| 11 |
-
"train_runtime":
|
| 12 |
-
"train_samples":
|
| 13 |
-
"train_samples_per_second":
|
| 14 |
-
"train_steps_per_second":
|
| 15 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 20.0,
|
| 3 |
+
"eval_bleu": 8.4963,
|
| 4 |
+
"eval_gen_len": 21.6694,
|
| 5 |
+
"eval_loss": 1.636548638343811,
|
| 6 |
+
"eval_runtime": 19.1423,
|
| 7 |
+
"eval_samples": 29522,
|
| 8 |
+
"eval_samples_per_second": 1542.237,
|
| 9 |
+
"eval_steps_per_second": 9.664,
|
| 10 |
+
"train_loss": 1.7127611959194204,
|
| 11 |
+
"train_runtime": 370998.644,
|
| 12 |
+
"train_samples": 9802621,
|
| 13 |
+
"train_samples_per_second": 528.445,
|
| 14 |
+
"train_steps_per_second": 1.651
|
| 15 |
}
|
config.json
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "/
|
| 3 |
"activation_dropout": 0.0,
|
| 4 |
"activation_function": "swish",
|
| 5 |
"add_bias_logits": false,
|
|
@@ -21,6 +21,7 @@
|
|
| 21 |
"decoder_layerdrop": 0.0,
|
| 22 |
"decoder_layers": 6,
|
| 23 |
"decoder_start_token_id": 62954,
|
|
|
|
| 24 |
"do_blenderbot_90_layernorm": false,
|
| 25 |
"dropout": 0.1,
|
| 26 |
"encoder_attention_heads": 8,
|
|
@@ -52,9 +53,10 @@
|
|
| 52 |
"num_hidden_layers": 6,
|
| 53 |
"pad_token_id": 62954,
|
| 54 |
"scale_embedding": true,
|
|
|
|
| 55 |
"static_position_embeddings": true,
|
| 56 |
"torch_dtype": "float32",
|
| 57 |
-
"transformers_version": "4.
|
| 58 |
"use_cache": true,
|
| 59 |
"vocab_size": 62955
|
| 60 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "orendar/en_he_base",
|
| 3 |
"activation_dropout": 0.0,
|
| 4 |
"activation_function": "swish",
|
| 5 |
"add_bias_logits": false,
|
|
|
|
| 21 |
"decoder_layerdrop": 0.0,
|
| 22 |
"decoder_layers": 6,
|
| 23 |
"decoder_start_token_id": 62954,
|
| 24 |
+
"decoder_vocab_size": 62955,
|
| 25 |
"do_blenderbot_90_layernorm": false,
|
| 26 |
"dropout": 0.1,
|
| 27 |
"encoder_attention_heads": 8,
|
|
|
|
| 53 |
"num_hidden_layers": 6,
|
| 54 |
"pad_token_id": 62954,
|
| 55 |
"scale_embedding": true,
|
| 56 |
+
"share_encoder_decoder_embeddings": true,
|
| 57 |
"static_position_embeddings": true,
|
| 58 |
"torch_dtype": "float32",
|
| 59 |
+
"transformers_version": "4.18.0.dev0",
|
| 60 |
"use_cache": true,
|
| 61 |
"vocab_size": 62955
|
| 62 |
}
|
eval_results.json
CHANGED
|
@@ -1,10 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"
|
| 4 |
-
"
|
| 5 |
-
"
|
| 6 |
-
"
|
| 7 |
-
"
|
| 8 |
-
"eval_samples_per_second": 19.033,
|
| 9 |
-
"eval_steps_per_second": 1.19
|
| 10 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 20.0,
|
| 3 |
+
"eval_loss": 1.636548638343811,
|
| 4 |
+
"eval_runtime": 19.1423,
|
| 5 |
+
"eval_samples": 29522,
|
| 6 |
+
"eval_samples_per_second": 1542.237,
|
| 7 |
+
"eval_steps_per_second": 9.664
|
|
|
|
|
|
|
| 8 |
}
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d4013281fcccc67400b2576d4279bb88811bc3449b0615b2c227e9cabe13249a
|
| 3 |
+
size 305832709
|
tokenizer_config.json
CHANGED
|
@@ -1 +1 @@
|
|
| 1 |
-
{"source_lang": null, "target_lang": null, "unk_token": "<unk>", "eos_token": "</s>", "pad_token": "<pad>", "model_max_length": 512, "sp_model_kwargs": {}, "special_tokens_map_file": null, "tokenizer_file": null, "name_or_path": "/
|
|
|
|
| 1 |
+
{"source_lang": null, "target_lang": null, "unk_token": "<unk>", "eos_token": "</s>", "pad_token": "<pad>", "model_max_length": 512, "sp_model_kwargs": {}, "separate_vocabs": false, "special_tokens_map_file": null, "tokenizer_file": null, "name_or_path": "orendar/en_he_base", "tokenizer_class": "MarianTokenizer"}
|
train_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"train_loss": 1.
|
| 4 |
-
"train_runtime":
|
| 5 |
-
"train_samples":
|
| 6 |
-
"train_samples_per_second":
|
| 7 |
-
"train_steps_per_second":
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 20.0,
|
| 3 |
+
"train_loss": 1.7127611959194204,
|
| 4 |
+
"train_runtime": 370998.644,
|
| 5 |
+
"train_samples": 9802621,
|
| 6 |
+
"train_samples_per_second": 528.445,
|
| 7 |
+
"train_steps_per_second": 1.651
|
| 8 |
}
|
trainer_state.json
CHANGED
|
@@ -1,1253 +1,1409 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch":
|
| 5 |
-
"global_step":
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
| 9 |
"log_history": [
|
| 10 |
{
|
| 11 |
-
"epoch": 0.
|
| 12 |
-
"learning_rate":
|
| 13 |
-
"loss":
|
| 14 |
-
"step":
|
| 15 |
},
|
| 16 |
{
|
| 17 |
-
"epoch": 0.
|
| 18 |
-
"learning_rate":
|
| 19 |
-
"loss": 3.
|
| 20 |
-
"step":
|
| 21 |
},
|
| 22 |
{
|
| 23 |
-
"epoch": 0.
|
| 24 |
-
"learning_rate":
|
| 25 |
-
"loss": 2.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 26 |
"step": 30000
|
| 27 |
},
|
| 28 |
{
|
| 29 |
-
"epoch": 0
|
| 30 |
-
"
|
| 31 |
-
"
|
| 32 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 33 |
},
|
| 34 |
{
|
| 35 |
-
"epoch":
|
| 36 |
-
"learning_rate":
|
| 37 |
-
"loss": 2.
|
| 38 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 39 |
},
|
| 40 |
{
|
| 41 |
-
"epoch":
|
| 42 |
-
"learning_rate":
|
| 43 |
-
"loss":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 44 |
"step": 60000
|
| 45 |
},
|
| 46 |
{
|
| 47 |
-
"epoch": 0
|
| 48 |
-
"
|
| 49 |
-
"
|
| 50 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 51 |
},
|
| 52 |
{
|
| 53 |
-
"epoch":
|
| 54 |
-
"learning_rate":
|
| 55 |
-
"loss":
|
| 56 |
-
"step":
|
| 57 |
},
|
| 58 |
{
|
| 59 |
-
"epoch":
|
| 60 |
-
"learning_rate":
|
| 61 |
-
"loss":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 62 |
"step": 90000
|
| 63 |
},
|
| 64 |
{
|
| 65 |
-
"epoch": 0
|
| 66 |
-
"
|
| 67 |
-
"
|
| 68 |
-
"
|
|
|
|
|
|
|
| 69 |
},
|
| 70 |
{
|
| 71 |
-
"epoch":
|
| 72 |
-
"learning_rate":
|
| 73 |
-
"loss":
|
| 74 |
-
"step":
|
| 75 |
},
|
| 76 |
{
|
| 77 |
-
"epoch":
|
| 78 |
-
"learning_rate":
|
| 79 |
-
"loss":
|
| 80 |
-
"step":
|
| 81 |
},
|
| 82 |
{
|
| 83 |
-
"epoch":
|
| 84 |
-
"learning_rate":
|
| 85 |
-
"loss":
|
| 86 |
-
"step":
|
| 87 |
},
|
| 88 |
{
|
| 89 |
-
"epoch":
|
| 90 |
-
"learning_rate":
|
| 91 |
-
"loss":
|
| 92 |
-
"step":
|
| 93 |
},
|
| 94 |
{
|
| 95 |
-
"epoch":
|
| 96 |
-
"learning_rate":
|
| 97 |
-
"loss":
|
| 98 |
-
"step":
|
| 99 |
},
|
| 100 |
{
|
| 101 |
-
"epoch":
|
| 102 |
-
"learning_rate":
|
| 103 |
-
"loss":
|
| 104 |
-
"step":
|
| 105 |
},
|
| 106 |
{
|
| 107 |
-
"epoch":
|
| 108 |
-
"learning_rate":
|
| 109 |
-
"loss":
|
| 110 |
-
"step":
|
| 111 |
},
|
| 112 |
{
|
| 113 |
-
"epoch":
|
| 114 |
-
"learning_rate":
|
| 115 |
-
"loss": 1.
|
| 116 |
-
"step":
|
| 117 |
},
|
| 118 |
{
|
| 119 |
-
"epoch":
|
| 120 |
-
"
|
| 121 |
-
"
|
| 122 |
-
"
|
| 123 |
-
"eval_runtime": 2487.0668,
|
| 124 |
-
"eval_samples_per_second": 6.902,
|
| 125 |
-
"eval_steps_per_second": 0.431,
|
| 126 |
-
"step": 188563
|
| 127 |
},
|
| 128 |
{
|
| 129 |
-
"epoch":
|
| 130 |
-
"learning_rate":
|
| 131 |
-
"loss": 1.
|
| 132 |
-
"step":
|
| 133 |
},
|
| 134 |
{
|
| 135 |
-
"epoch":
|
| 136 |
-
"
|
| 137 |
-
"
|
| 138 |
-
"
|
|
|
|
|
|
|
| 139 |
},
|
| 140 |
{
|
| 141 |
-
"epoch":
|
| 142 |
-
"learning_rate":
|
| 143 |
-
"loss": 1.
|
| 144 |
-
"step":
|
| 145 |
},
|
| 146 |
{
|
| 147 |
-
"epoch":
|
| 148 |
-
"learning_rate":
|
| 149 |
-
"loss": 1.
|
| 150 |
-
"step":
|
| 151 |
},
|
| 152 |
{
|
| 153 |
-
"epoch":
|
| 154 |
-
"learning_rate":
|
| 155 |
-
"loss": 1.
|
| 156 |
-
"step":
|
| 157 |
},
|
| 158 |
{
|
| 159 |
-
"epoch":
|
| 160 |
-
"learning_rate":
|
| 161 |
-
"loss": 1.
|
| 162 |
-
"step":
|
| 163 |
},
|
| 164 |
{
|
| 165 |
-
"epoch":
|
| 166 |
-
"learning_rate":
|
| 167 |
-
"loss": 1.
|
| 168 |
-
"step":
|
| 169 |
},
|
| 170 |
{
|
| 171 |
-
"epoch":
|
| 172 |
-
"learning_rate":
|
| 173 |
-
"loss": 1.
|
| 174 |
-
"step":
|
| 175 |
},
|
| 176 |
{
|
| 177 |
-
"epoch":
|
| 178 |
-
"learning_rate":
|
| 179 |
-
"loss": 1.
|
| 180 |
-
"step":
|
| 181 |
},
|
| 182 |
{
|
| 183 |
-
"epoch":
|
| 184 |
-
"learning_rate":
|
| 185 |
-
"loss": 1.
|
| 186 |
-
"step":
|
| 187 |
},
|
| 188 |
{
|
| 189 |
-
"epoch":
|
| 190 |
-
"learning_rate":
|
| 191 |
-
"loss": 1.
|
| 192 |
-
"step":
|
| 193 |
},
|
| 194 |
{
|
| 195 |
-
"epoch":
|
| 196 |
-
"learning_rate":
|
| 197 |
-
"loss": 1.
|
| 198 |
-
"step":
|
| 199 |
},
|
| 200 |
{
|
| 201 |
-
"epoch":
|
| 202 |
-
"learning_rate":
|
| 203 |
-
"loss": 1.
|
| 204 |
-
"step":
|
| 205 |
},
|
| 206 |
{
|
| 207 |
-
"epoch":
|
| 208 |
-
"
|
| 209 |
-
"
|
| 210 |
-
"
|
|
|
|
|
|
|
| 211 |
},
|
| 212 |
{
|
| 213 |
-
"epoch":
|
| 214 |
-
"learning_rate":
|
| 215 |
-
"loss": 1.
|
| 216 |
-
"step":
|
| 217 |
},
|
| 218 |
{
|
| 219 |
-
"epoch":
|
| 220 |
-
"learning_rate":
|
| 221 |
-
"loss": 1.
|
| 222 |
-
"step":
|
| 223 |
},
|
| 224 |
{
|
| 225 |
-
"epoch":
|
| 226 |
-
"learning_rate":
|
| 227 |
-
"loss": 1.
|
| 228 |
-
"step":
|
| 229 |
},
|
| 230 |
{
|
| 231 |
-
"epoch":
|
| 232 |
-
"learning_rate":
|
| 233 |
-
"loss": 1.
|
| 234 |
-
"step":
|
| 235 |
},
|
| 236 |
{
|
| 237 |
-
"epoch":
|
| 238 |
-
"learning_rate":
|
| 239 |
-
"loss": 1.
|
| 240 |
-
"step":
|
| 241 |
},
|
| 242 |
{
|
| 243 |
-
"epoch":
|
| 244 |
-
"
|
| 245 |
-
"
|
| 246 |
-
"
|
| 247 |
-
"eval_runtime": 2537.4407,
|
| 248 |
-
"eval_samples_per_second": 6.765,
|
| 249 |
-
"eval_steps_per_second": 0.423,
|
| 250 |
-
"step": 377126
|
| 251 |
},
|
| 252 |
{
|
| 253 |
-
"epoch":
|
| 254 |
-
"learning_rate":
|
| 255 |
-
"loss": 1.
|
| 256 |
-
"step":
|
| 257 |
},
|
| 258 |
{
|
| 259 |
-
"epoch":
|
| 260 |
-
"learning_rate":
|
| 261 |
-
"loss": 1.
|
| 262 |
-
"step":
|
| 263 |
},
|
| 264 |
{
|
| 265 |
-
"epoch":
|
| 266 |
-
"learning_rate":
|
| 267 |
-
"loss": 1.
|
| 268 |
-
"step":
|
| 269 |
},
|
| 270 |
{
|
| 271 |
-
"epoch":
|
| 272 |
-
"learning_rate":
|
| 273 |
-
"loss": 1.
|
| 274 |
-
"step":
|
| 275 |
},
|
| 276 |
{
|
| 277 |
-
"epoch":
|
| 278 |
-
"
|
| 279 |
-
"
|
| 280 |
-
"
|
|
|
|
|
|
|
| 281 |
},
|
| 282 |
{
|
| 283 |
-
"epoch":
|
| 284 |
-
"learning_rate":
|
| 285 |
-
"loss": 1.
|
| 286 |
-
"step":
|
| 287 |
},
|
| 288 |
{
|
| 289 |
-
"epoch":
|
| 290 |
-
"learning_rate":
|
| 291 |
-
"loss": 1.
|
| 292 |
-
"step":
|
| 293 |
},
|
| 294 |
{
|
| 295 |
-
"epoch":
|
| 296 |
-
"learning_rate":
|
| 297 |
-
"loss": 1.
|
| 298 |
-
"step":
|
| 299 |
},
|
| 300 |
{
|
| 301 |
-
"epoch":
|
| 302 |
-
"learning_rate":
|
| 303 |
-
"loss": 1.
|
| 304 |
-
"step":
|
| 305 |
},
|
| 306 |
{
|
| 307 |
-
"epoch":
|
| 308 |
-
"learning_rate":
|
| 309 |
-
"loss": 1.
|
| 310 |
-
"step":
|
| 311 |
},
|
| 312 |
{
|
| 313 |
-
"epoch":
|
| 314 |
-
"learning_rate":
|
| 315 |
-
"loss": 1.
|
| 316 |
-
"step":
|
| 317 |
},
|
| 318 |
{
|
| 319 |
-
"epoch":
|
| 320 |
-
"learning_rate":
|
| 321 |
-
"loss": 1.
|
| 322 |
-
"step":
|
| 323 |
},
|
| 324 |
{
|
| 325 |
-
"epoch":
|
| 326 |
-
"learning_rate":
|
| 327 |
-
"loss": 1.
|
| 328 |
-
"step":
|
| 329 |
},
|
| 330 |
{
|
| 331 |
-
"epoch":
|
| 332 |
-
"learning_rate":
|
| 333 |
-
"loss": 1.
|
| 334 |
-
"step":
|
| 335 |
},
|
| 336 |
{
|
| 337 |
-
"epoch":
|
| 338 |
-
"learning_rate":
|
| 339 |
-
"loss": 1.
|
| 340 |
-
"step":
|
| 341 |
},
|
| 342 |
{
|
| 343 |
-
"epoch":
|
| 344 |
-
"
|
| 345 |
-
"
|
| 346 |
-
"
|
|
|
|
|
|
|
| 347 |
},
|
| 348 |
{
|
| 349 |
-
"epoch":
|
| 350 |
-
"learning_rate":
|
| 351 |
-
"loss": 1.
|
| 352 |
-
"step":
|
| 353 |
},
|
| 354 |
{
|
| 355 |
-
"epoch":
|
| 356 |
-
"learning_rate":
|
| 357 |
-
"loss": 1.
|
| 358 |
-
"step":
|
| 359 |
},
|
| 360 |
{
|
| 361 |
-
"epoch":
|
| 362 |
-
"learning_rate":
|
| 363 |
-
"loss": 1.
|
| 364 |
-
"step":
|
| 365 |
},
|
| 366 |
{
|
| 367 |
-
"epoch":
|
| 368 |
-
"
|
| 369 |
-
"
|
| 370 |
-
"
|
| 371 |
-
"eval_runtime": 2571.172,
|
| 372 |
-
"eval_samples_per_second": 6.676,
|
| 373 |
-
"eval_steps_per_second": 0.417,
|
| 374 |
-
"step": 565689
|
| 375 |
-
},
|
| 376 |
-
{
|
| 377 |
-
"epoch": 3.02,
|
| 378 |
-
"learning_rate": 3.489191941154946e-05,
|
| 379 |
-
"loss": 1.7262,
|
| 380 |
-
"step": 570000
|
| 381 |
},
|
| 382 |
{
|
| 383 |
-
"epoch":
|
| 384 |
-
"learning_rate":
|
| 385 |
-
"loss": 1.
|
| 386 |
-
"step":
|
| 387 |
},
|
| 388 |
{
|
| 389 |
-
"epoch":
|
| 390 |
-
"learning_rate":
|
| 391 |
-
"loss": 1.
|
| 392 |
-
"step":
|
| 393 |
},
|
| 394 |
{
|
| 395 |
-
"epoch":
|
| 396 |
-
"learning_rate":
|
| 397 |
-
"loss": 1.
|
| 398 |
-
"step":
|
| 399 |
},
|
| 400 |
{
|
| 401 |
-
"epoch":
|
| 402 |
-
"learning_rate":
|
| 403 |
-
"loss": 1.
|
| 404 |
-
"step":
|
| 405 |
},
|
| 406 |
{
|
| 407 |
-
"epoch":
|
| 408 |
-
"learning_rate":
|
| 409 |
-
"loss": 1.
|
| 410 |
-
"step":
|
| 411 |
},
|
| 412 |
{
|
| 413 |
-
"epoch":
|
| 414 |
-
"learning_rate":
|
| 415 |
-
"loss": 1.
|
| 416 |
-
"step":
|
| 417 |
},
|
| 418 |
{
|
| 419 |
-
"epoch":
|
| 420 |
-
"
|
| 421 |
-
"
|
| 422 |
-
"
|
|
|
|
|
|
|
| 423 |
},
|
| 424 |
{
|
| 425 |
-
"epoch":
|
| 426 |
-
"learning_rate":
|
| 427 |
-
"loss": 1.
|
| 428 |
-
"step":
|
| 429 |
},
|
| 430 |
{
|
| 431 |
-
"epoch":
|
| 432 |
-
"learning_rate":
|
| 433 |
-
"loss": 1.
|
| 434 |
-
"step":
|
| 435 |
},
|
| 436 |
{
|
| 437 |
-
"epoch":
|
| 438 |
-
"learning_rate":
|
| 439 |
-
"loss": 1.
|
| 440 |
-
"step":
|
| 441 |
},
|
| 442 |
{
|
| 443 |
-
"epoch":
|
| 444 |
-
"learning_rate":
|
| 445 |
-
"loss": 1.
|
| 446 |
-
"step":
|
| 447 |
},
|
| 448 |
{
|
| 449 |
-
"epoch":
|
| 450 |
-
"learning_rate":
|
| 451 |
-
"loss": 1.
|
| 452 |
-
"step":
|
| 453 |
},
|
| 454 |
{
|
| 455 |
-
"epoch":
|
| 456 |
-
"learning_rate":
|
| 457 |
-
"loss": 1.
|
| 458 |
-
"step":
|
| 459 |
},
|
| 460 |
{
|
| 461 |
-
"epoch":
|
| 462 |
-
"learning_rate":
|
| 463 |
-
"loss": 1.
|
| 464 |
-
"step":
|
| 465 |
},
|
| 466 |
{
|
| 467 |
-
"epoch":
|
| 468 |
-
"learning_rate":
|
| 469 |
-
"loss": 1.
|
| 470 |
-
"step":
|
| 471 |
},
|
| 472 |
{
|
| 473 |
-
"epoch":
|
| 474 |
-
"learning_rate":
|
| 475 |
-
"loss": 1.
|
| 476 |
-
"step":
|
| 477 |
},
|
| 478 |
{
|
| 479 |
-
"epoch":
|
| 480 |
-
"learning_rate":
|
| 481 |
-
"loss": 1.
|
| 482 |
-
"step":
|
| 483 |
},
|
| 484 |
{
|
| 485 |
-
"epoch":
|
| 486 |
-
"
|
| 487 |
-
"
|
| 488 |
-
"
|
|
|
|
|
|
|
| 489 |
},
|
| 490 |
{
|
| 491 |
-
"epoch":
|
| 492 |
-
"
|
| 493 |
-
"
|
| 494 |
-
"
|
| 495 |
-
"eval_runtime": 2545.7813,
|
| 496 |
-
"eval_samples_per_second": 6.743,
|
| 497 |
-
"eval_steps_per_second": 0.421,
|
| 498 |
-
"step": 754252
|
| 499 |
},
|
| 500 |
{
|
| 501 |
-
"epoch":
|
| 502 |
-
"learning_rate":
|
| 503 |
-
"loss": 1.
|
| 504 |
-
"step":
|
| 505 |
},
|
| 506 |
{
|
| 507 |
-
"epoch":
|
| 508 |
-
"learning_rate":
|
| 509 |
-
"loss": 1.
|
| 510 |
-
"step":
|
| 511 |
},
|
| 512 |
{
|
| 513 |
-
"epoch":
|
| 514 |
-
"learning_rate":
|
| 515 |
-
"loss": 1.
|
| 516 |
-
"step":
|
| 517 |
},
|
| 518 |
{
|
| 519 |
-
"epoch": 4
|
| 520 |
-
"learning_rate":
|
| 521 |
-
"loss": 1.
|
| 522 |
-
"step":
|
| 523 |
},
|
| 524 |
{
|
| 525 |
-
"epoch":
|
| 526 |
-
"learning_rate":
|
| 527 |
-
"loss": 1.
|
| 528 |
-
"step":
|
| 529 |
},
|
| 530 |
{
|
| 531 |
-
"epoch":
|
| 532 |
-
"learning_rate":
|
| 533 |
-
"loss": 1.
|
| 534 |
-
"step":
|
| 535 |
},
|
| 536 |
{
|
| 537 |
-
"epoch":
|
| 538 |
-
"learning_rate":
|
| 539 |
-
"loss": 1.
|
| 540 |
-
"step":
|
| 541 |
},
|
| 542 |
{
|
| 543 |
-
"epoch":
|
| 544 |
-
"learning_rate":
|
| 545 |
-
"loss": 1.
|
| 546 |
-
"step":
|
| 547 |
},
|
| 548 |
{
|
| 549 |
-
"epoch":
|
| 550 |
-
"learning_rate":
|
| 551 |
-
"loss": 1.
|
| 552 |
-
"step":
|
| 553 |
},
|
| 554 |
{
|
| 555 |
-
"epoch":
|
| 556 |
-
"learning_rate":
|
| 557 |
-
"loss": 1.
|
| 558 |
-
"step":
|
| 559 |
},
|
| 560 |
{
|
| 561 |
-
"epoch":
|
| 562 |
-
"
|
| 563 |
-
"
|
| 564 |
-
"
|
|
|
|
|
|
|
| 565 |
},
|
| 566 |
{
|
| 567 |
-
"epoch":
|
| 568 |
-
"learning_rate":
|
| 569 |
-
"loss": 1.
|
| 570 |
-
"step":
|
| 571 |
},
|
| 572 |
{
|
| 573 |
-
"epoch":
|
| 574 |
-
"learning_rate":
|
| 575 |
-
"loss": 1.
|
| 576 |
-
"step":
|
| 577 |
},
|
| 578 |
{
|
| 579 |
-
"epoch":
|
| 580 |
-
"learning_rate":
|
| 581 |
-
"loss": 1.
|
| 582 |
-
"step":
|
| 583 |
},
|
| 584 |
{
|
| 585 |
-
"epoch":
|
| 586 |
-
"learning_rate":
|
| 587 |
-
"loss": 1.
|
| 588 |
-
"step":
|
| 589 |
},
|
| 590 |
{
|
| 591 |
-
"epoch":
|
| 592 |
-
"learning_rate":
|
| 593 |
-
"loss": 1.
|
| 594 |
-
"step":
|
| 595 |
},
|
| 596 |
{
|
| 597 |
-
"epoch":
|
| 598 |
-
"learning_rate":
|
| 599 |
-
"loss": 1.
|
| 600 |
-
"step":
|
| 601 |
},
|
| 602 |
{
|
| 603 |
-
"epoch":
|
| 604 |
-
"learning_rate":
|
| 605 |
-
"loss": 1.
|
| 606 |
-
"step":
|
| 607 |
},
|
| 608 |
{
|
| 609 |
-
"epoch":
|
| 610 |
-
"learning_rate":
|
| 611 |
-
"loss": 1.
|
| 612 |
-
"step":
|
| 613 |
},
|
| 614 |
{
|
| 615 |
-
"epoch":
|
| 616 |
-
"
|
| 617 |
-
"
|
| 618 |
-
"
|
| 619 |
-
"eval_runtime": 2534.3035,
|
| 620 |
-
"eval_samples_per_second": 6.773,
|
| 621 |
-
"eval_steps_per_second": 0.423,
|
| 622 |
-
"step": 942815
|
| 623 |
},
|
| 624 |
{
|
| 625 |
-
"epoch":
|
| 626 |
-
"learning_rate":
|
| 627 |
-
"loss": 1.
|
| 628 |
-
"step":
|
| 629 |
},
|
| 630 |
{
|
| 631 |
-
"epoch":
|
| 632 |
-
"
|
| 633 |
-
"
|
| 634 |
-
"
|
|
|
|
|
|
|
| 635 |
},
|
| 636 |
{
|
| 637 |
-
"epoch":
|
| 638 |
-
"learning_rate":
|
| 639 |
-
"loss": 1.
|
| 640 |
-
"step":
|
| 641 |
},
|
| 642 |
{
|
| 643 |
-
"epoch":
|
| 644 |
-
"learning_rate":
|
| 645 |
-
"loss": 1.
|
| 646 |
-
"step":
|
| 647 |
},
|
| 648 |
{
|
| 649 |
-
"epoch":
|
| 650 |
-
"learning_rate":
|
| 651 |
-
"loss": 1.
|
| 652 |
-
"step":
|
| 653 |
},
|
| 654 |
{
|
| 655 |
-
"epoch":
|
| 656 |
-
"learning_rate":
|
| 657 |
-
"loss": 1.
|
| 658 |
-
"step":
|
| 659 |
},
|
| 660 |
{
|
| 661 |
-
"epoch":
|
| 662 |
-
"learning_rate":
|
| 663 |
-
"loss": 1.
|
| 664 |
-
"step":
|
| 665 |
},
|
| 666 |
{
|
| 667 |
-
"epoch":
|
| 668 |
-
"learning_rate":
|
| 669 |
-
"loss": 1.
|
| 670 |
-
"step":
|
| 671 |
},
|
| 672 |
{
|
| 673 |
-
"epoch":
|
| 674 |
-
"learning_rate":
|
| 675 |
-
"loss": 1.
|
| 676 |
-
"step":
|
| 677 |
},
|
| 678 |
{
|
| 679 |
-
"epoch":
|
| 680 |
-
"learning_rate":
|
| 681 |
-
"loss": 1.
|
| 682 |
-
"step":
|
| 683 |
},
|
| 684 |
{
|
| 685 |
-
"epoch":
|
| 686 |
-
"learning_rate":
|
| 687 |
-
"loss": 1.
|
| 688 |
-
"step":
|
| 689 |
},
|
| 690 |
{
|
| 691 |
-
"epoch":
|
| 692 |
-
"learning_rate":
|
| 693 |
-
"loss": 1.
|
| 694 |
-
"step":
|
| 695 |
},
|
| 696 |
{
|
| 697 |
-
"epoch":
|
| 698 |
-
"
|
| 699 |
-
"
|
| 700 |
-
"
|
|
|
|
|
|
|
| 701 |
},
|
| 702 |
{
|
| 703 |
-
"epoch":
|
| 704 |
-
"learning_rate":
|
| 705 |
-
"loss": 1.
|
| 706 |
-
"step":
|
| 707 |
},
|
| 708 |
{
|
| 709 |
-
"epoch":
|
| 710 |
-
"learning_rate":
|
| 711 |
-
"loss": 1.
|
| 712 |
-
"step":
|
| 713 |
},
|
| 714 |
{
|
| 715 |
-
"epoch":
|
| 716 |
-
"learning_rate":
|
| 717 |
-
"loss": 1.
|
| 718 |
-
"step":
|
| 719 |
},
|
| 720 |
{
|
| 721 |
-
"epoch":
|
| 722 |
-
"learning_rate":
|
| 723 |
-
"loss": 1.
|
| 724 |
-
"step":
|
| 725 |
},
|
| 726 |
{
|
| 727 |
-
"epoch":
|
| 728 |
-
"learning_rate":
|
| 729 |
-
"loss": 1.
|
| 730 |
-
"step":
|
| 731 |
},
|
| 732 |
{
|
| 733 |
-
"epoch":
|
| 734 |
-
"learning_rate":
|
| 735 |
-
"loss": 1.
|
| 736 |
-
"step":
|
| 737 |
},
|
| 738 |
{
|
| 739 |
-
"epoch":
|
| 740 |
-
"
|
| 741 |
-
"
|
| 742 |
-
"
|
| 743 |
-
"eval_runtime": 2786.837,
|
| 744 |
-
"eval_samples_per_second": 6.159,
|
| 745 |
-
"eval_steps_per_second": 0.385,
|
| 746 |
-
"step": 1131378
|
| 747 |
},
|
| 748 |
{
|
| 749 |
-
"epoch":
|
| 750 |
-
"learning_rate":
|
| 751 |
-
"loss": 1.
|
| 752 |
-
"step":
|
| 753 |
},
|
| 754 |
{
|
| 755 |
-
"epoch":
|
| 756 |
-
"learning_rate":
|
| 757 |
-
"loss": 1.
|
| 758 |
-
"step":
|
| 759 |
},
|
| 760 |
{
|
| 761 |
-
"epoch":
|
| 762 |
-
"learning_rate":
|
| 763 |
-
"loss": 1.
|
| 764 |
-
"step":
|
| 765 |
},
|
| 766 |
{
|
| 767 |
-
"epoch":
|
| 768 |
-
"
|
| 769 |
-
"
|
| 770 |
-
"
|
|
|
|
|
|
|
| 771 |
},
|
| 772 |
{
|
| 773 |
-
"epoch":
|
| 774 |
-
"learning_rate":
|
| 775 |
-
"loss": 1.
|
| 776 |
-
"step":
|
| 777 |
},
|
| 778 |
{
|
| 779 |
-
"epoch":
|
| 780 |
-
"learning_rate":
|
| 781 |
-
"loss": 1.
|
| 782 |
-
"step":
|
| 783 |
},
|
| 784 |
{
|
| 785 |
-
"epoch":
|
| 786 |
-
"learning_rate":
|
| 787 |
-
"loss": 1.
|
| 788 |
-
"step":
|
| 789 |
},
|
| 790 |
{
|
| 791 |
-
"epoch":
|
| 792 |
-
"learning_rate":
|
| 793 |
-
"loss": 1.
|
| 794 |
-
"step":
|
| 795 |
},
|
| 796 |
{
|
| 797 |
-
"epoch":
|
| 798 |
-
"learning_rate":
|
| 799 |
-
"loss": 1.
|
| 800 |
-
"step":
|
| 801 |
},
|
| 802 |
{
|
| 803 |
-
"epoch":
|
| 804 |
-
"learning_rate":
|
| 805 |
-
"loss": 1.
|
| 806 |
-
"step":
|
| 807 |
},
|
| 808 |
{
|
| 809 |
-
"epoch":
|
| 810 |
-
"learning_rate":
|
| 811 |
-
"loss": 1.
|
| 812 |
-
"step":
|
| 813 |
},
|
| 814 |
{
|
| 815 |
-
"epoch":
|
| 816 |
-
"learning_rate":
|
| 817 |
-
"loss": 1.
|
| 818 |
-
"step":
|
| 819 |
},
|
| 820 |
{
|
| 821 |
-
"epoch":
|
| 822 |
-
"learning_rate":
|
| 823 |
-
"loss": 1.
|
| 824 |
-
"step":
|
| 825 |
},
|
| 826 |
{
|
| 827 |
-
"epoch":
|
| 828 |
-
"learning_rate":
|
| 829 |
-
"loss": 1.
|
| 830 |
-
"step":
|
| 831 |
},
|
| 832 |
{
|
| 833 |
-
"epoch":
|
| 834 |
-
"
|
| 835 |
-
"
|
| 836 |
-
"
|
|
|
|
|
|
|
| 837 |
},
|
| 838 |
{
|
| 839 |
-
"epoch":
|
| 840 |
-
"learning_rate":
|
| 841 |
-
"loss": 1.
|
| 842 |
-
"step":
|
| 843 |
},
|
| 844 |
{
|
| 845 |
-
"epoch":
|
| 846 |
-
"learning_rate":
|
| 847 |
-
"loss": 1.
|
| 848 |
-
"step":
|
| 849 |
},
|
| 850 |
{
|
| 851 |
-
"epoch":
|
| 852 |
-
"learning_rate":
|
| 853 |
-
"loss": 1.
|
| 854 |
-
"step":
|
| 855 |
},
|
| 856 |
{
|
| 857 |
-
"epoch":
|
| 858 |
-
"
|
| 859 |
-
"
|
| 860 |
-
"
|
| 861 |
-
"eval_runtime": 2659.0199,
|
| 862 |
-
"eval_samples_per_second": 6.455,
|
| 863 |
-
"eval_steps_per_second": 0.404,
|
| 864 |
-
"step": 1319941
|
| 865 |
},
|
| 866 |
{
|
| 867 |
-
"epoch":
|
| 868 |
-
"learning_rate":
|
| 869 |
-
"loss": 1.
|
| 870 |
-
"step":
|
| 871 |
},
|
| 872 |
{
|
| 873 |
-
"epoch":
|
| 874 |
-
"learning_rate":
|
| 875 |
-
"loss": 1.
|
| 876 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 877 |
},
|
| 878 |
{
|
| 879 |
-
"epoch":
|
| 880 |
-
"learning_rate":
|
| 881 |
"loss": 1.5864,
|
| 882 |
-
"step":
|
| 883 |
},
|
| 884 |
{
|
| 885 |
-
"epoch":
|
| 886 |
-
"learning_rate":
|
| 887 |
-
"loss": 1.
|
| 888 |
-
"step":
|
| 889 |
},
|
| 890 |
{
|
| 891 |
-
"epoch":
|
| 892 |
-
"
|
| 893 |
-
"
|
| 894 |
-
"
|
|
|
|
|
|
|
| 895 |
},
|
| 896 |
{
|
| 897 |
-
"epoch":
|
| 898 |
-
"learning_rate":
|
| 899 |
-
"loss": 1.
|
| 900 |
-
"step":
|
| 901 |
},
|
| 902 |
{
|
| 903 |
-
"epoch":
|
| 904 |
-
"learning_rate":
|
| 905 |
-
"loss": 1.
|
| 906 |
-
"step":
|
| 907 |
},
|
| 908 |
{
|
| 909 |
-
"epoch":
|
| 910 |
-
"learning_rate":
|
| 911 |
-
"loss": 1.
|
| 912 |
-
"step":
|
| 913 |
},
|
| 914 |
{
|
| 915 |
-
"epoch":
|
| 916 |
-
"learning_rate":
|
| 917 |
-
"loss": 1.
|
| 918 |
-
"step":
|
| 919 |
},
|
| 920 |
{
|
| 921 |
-
"epoch":
|
| 922 |
-
"learning_rate":
|
| 923 |
-
"loss": 1.
|
| 924 |
-
"step":
|
| 925 |
},
|
| 926 |
{
|
| 927 |
-
"epoch":
|
| 928 |
-
"learning_rate":
|
| 929 |
-
"loss": 1.
|
| 930 |
-
"step":
|
| 931 |
},
|
| 932 |
{
|
| 933 |
-
"epoch":
|
| 934 |
-
"learning_rate":
|
| 935 |
-
"loss": 1.
|
| 936 |
-
"step":
|
| 937 |
},
|
| 938 |
{
|
| 939 |
-
"epoch":
|
| 940 |
-
"learning_rate":
|
| 941 |
-
"loss": 1.
|
| 942 |
-
"step":
|
| 943 |
},
|
| 944 |
{
|
| 945 |
-
"epoch":
|
| 946 |
-
"learning_rate":
|
| 947 |
-
"loss": 1.
|
| 948 |
-
"step":
|
| 949 |
},
|
| 950 |
{
|
| 951 |
-
"epoch":
|
| 952 |
-
"learning_rate":
|
| 953 |
-
"loss": 1.
|
| 954 |
-
"step":
|
| 955 |
},
|
| 956 |
{
|
| 957 |
-
"epoch":
|
| 958 |
-
"
|
| 959 |
-
"
|
| 960 |
-
"
|
|
|
|
|
|
|
| 961 |
},
|
| 962 |
{
|
| 963 |
-
"epoch":
|
| 964 |
-
"learning_rate": 1.
|
| 965 |
-
"loss": 1.
|
| 966 |
-
"step":
|
| 967 |
},
|
| 968 |
{
|
| 969 |
-
"epoch":
|
| 970 |
-
"learning_rate": 1.
|
| 971 |
-
"loss": 1.
|
| 972 |
-
"step":
|
| 973 |
},
|
| 974 |
{
|
| 975 |
-
"epoch":
|
| 976 |
-
"learning_rate": 1.
|
| 977 |
-
"loss": 1.
|
| 978 |
-
"step":
|
| 979 |
},
|
| 980 |
{
|
| 981 |
-
"epoch":
|
| 982 |
-
"
|
| 983 |
-
"
|
| 984 |
-
"
|
| 985 |
-
"eval_runtime": 2553.3513,
|
| 986 |
-
"eval_samples_per_second": 6.723,
|
| 987 |
-
"eval_steps_per_second": 0.42,
|
| 988 |
-
"step": 1508504
|
| 989 |
},
|
| 990 |
{
|
| 991 |
-
"epoch":
|
| 992 |
-
"learning_rate":
|
| 993 |
-
"loss": 1.
|
| 994 |
-
"step":
|
| 995 |
},
|
| 996 |
{
|
| 997 |
-
"epoch":
|
| 998 |
-
"learning_rate":
|
| 999 |
-
"loss": 1.
|
| 1000 |
-
"step":
|
| 1001 |
},
|
| 1002 |
{
|
| 1003 |
-
"epoch":
|
| 1004 |
-
"learning_rate":
|
| 1005 |
-
"loss": 1.
|
| 1006 |
-
"step":
|
| 1007 |
},
|
| 1008 |
{
|
| 1009 |
-
"epoch":
|
| 1010 |
-
"learning_rate":
|
| 1011 |
-
"loss": 1.
|
| 1012 |
-
"step":
|
| 1013 |
},
|
| 1014 |
{
|
| 1015 |
-
"epoch":
|
| 1016 |
-
"learning_rate":
|
| 1017 |
-
"loss": 1.
|
| 1018 |
-
"step":
|
| 1019 |
},
|
| 1020 |
{
|
| 1021 |
-
"epoch":
|
| 1022 |
-
"learning_rate":
|
| 1023 |
-
"loss": 1.
|
| 1024 |
-
"step":
|
| 1025 |
},
|
| 1026 |
{
|
| 1027 |
-
"epoch":
|
| 1028 |
-
"
|
| 1029 |
-
"
|
| 1030 |
-
"
|
|
|
|
|
|
|
| 1031 |
},
|
| 1032 |
{
|
| 1033 |
-
"epoch":
|
| 1034 |
-
"learning_rate":
|
| 1035 |
-
"loss": 1.
|
| 1036 |
-
"step":
|
| 1037 |
},
|
| 1038 |
{
|
| 1039 |
-
"epoch":
|
| 1040 |
-
"learning_rate":
|
| 1041 |
-
"loss": 1.
|
| 1042 |
-
"step":
|
| 1043 |
},
|
| 1044 |
{
|
| 1045 |
-
"epoch":
|
| 1046 |
-
"learning_rate":
|
| 1047 |
-
"loss": 1.
|
| 1048 |
-
"step":
|
| 1049 |
},
|
| 1050 |
{
|
| 1051 |
-
"epoch":
|
| 1052 |
-
"learning_rate":
|
| 1053 |
-
"loss": 1.
|
| 1054 |
-
"step":
|
| 1055 |
},
|
| 1056 |
{
|
| 1057 |
-
"epoch":
|
| 1058 |
-
"learning_rate":
|
| 1059 |
-
"loss": 1.
|
| 1060 |
-
"step":
|
| 1061 |
},
|
| 1062 |
{
|
| 1063 |
-
"epoch":
|
| 1064 |
-
"learning_rate":
|
| 1065 |
-
"loss": 1.
|
| 1066 |
-
"step":
|
| 1067 |
},
|
| 1068 |
{
|
| 1069 |
-
"epoch":
|
| 1070 |
-
"learning_rate":
|
| 1071 |
-
"loss": 1.
|
| 1072 |
-
"step":
|
| 1073 |
},
|
| 1074 |
{
|
| 1075 |
-
"epoch":
|
| 1076 |
-
"learning_rate":
|
| 1077 |
-
"loss": 1.
|
| 1078 |
-
"step":
|
| 1079 |
},
|
| 1080 |
{
|
| 1081 |
-
"epoch":
|
| 1082 |
-
"learning_rate":
|
| 1083 |
-
"loss": 1.
|
| 1084 |
-
"step":
|
| 1085 |
},
|
| 1086 |
{
|
| 1087 |
-
"epoch":
|
| 1088 |
-
"learning_rate":
|
| 1089 |
-
"loss": 1.
|
| 1090 |
-
"step":
|
| 1091 |
},
|
| 1092 |
{
|
| 1093 |
-
"epoch":
|
| 1094 |
-
"
|
| 1095 |
-
"
|
| 1096 |
-
"
|
|
|
|
|
|
|
| 1097 |
},
|
| 1098 |
{
|
| 1099 |
-
"epoch":
|
| 1100 |
-
"learning_rate":
|
| 1101 |
-
"loss": 1.
|
| 1102 |
-
"step":
|
| 1103 |
},
|
| 1104 |
{
|
| 1105 |
-
"epoch":
|
| 1106 |
-
"
|
| 1107 |
-
"
|
| 1108 |
-
"
|
| 1109 |
-
"eval_runtime": 2749.5168,
|
| 1110 |
-
"eval_samples_per_second": 6.243,
|
| 1111 |
-
"eval_steps_per_second": 0.39,
|
| 1112 |
-
"step": 1697067
|
| 1113 |
},
|
| 1114 |
{
|
| 1115 |
-
"epoch":
|
| 1116 |
-
"learning_rate":
|
| 1117 |
-
"loss": 1.
|
| 1118 |
-
"step":
|
| 1119 |
},
|
| 1120 |
{
|
| 1121 |
-
"epoch":
|
| 1122 |
-
"learning_rate":
|
| 1123 |
-
"loss": 1.
|
| 1124 |
-
"step":
|
| 1125 |
},
|
| 1126 |
{
|
| 1127 |
-
"epoch":
|
| 1128 |
-
"learning_rate":
|
| 1129 |
-
"loss": 1.
|
| 1130 |
-
"step":
|
| 1131 |
},
|
| 1132 |
{
|
| 1133 |
-
"epoch":
|
| 1134 |
-
"learning_rate":
|
| 1135 |
-
"loss": 1.
|
| 1136 |
-
"step":
|
| 1137 |
},
|
| 1138 |
{
|
| 1139 |
-
"epoch":
|
| 1140 |
-
"learning_rate":
|
| 1141 |
-
"loss": 1.
|
| 1142 |
-
"step":
|
| 1143 |
},
|
| 1144 |
{
|
| 1145 |
-
"epoch":
|
| 1146 |
-
"learning_rate":
|
| 1147 |
-
"loss": 1.
|
| 1148 |
-
"step":
|
| 1149 |
},
|
| 1150 |
{
|
| 1151 |
-
"epoch":
|
| 1152 |
-
"learning_rate":
|
| 1153 |
-
"loss": 1.
|
| 1154 |
-
"step":
|
| 1155 |
},
|
| 1156 |
{
|
| 1157 |
-
"epoch": 9
|
| 1158 |
-
"learning_rate":
|
| 1159 |
-
"loss": 1.
|
| 1160 |
-
"step":
|
| 1161 |
},
|
| 1162 |
{
|
| 1163 |
-
"epoch":
|
| 1164 |
-
"learning_rate":
|
| 1165 |
-
"loss": 1.
|
| 1166 |
-
"step":
|
| 1167 |
},
|
| 1168 |
{
|
| 1169 |
-
"epoch":
|
| 1170 |
-
"
|
| 1171 |
-
"
|
| 1172 |
-
"
|
|
|
|
|
|
|
| 1173 |
},
|
| 1174 |
{
|
| 1175 |
-
"epoch":
|
| 1176 |
-
"learning_rate":
|
| 1177 |
-
"loss": 1.
|
| 1178 |
-
"step":
|
| 1179 |
},
|
| 1180 |
{
|
| 1181 |
-
"epoch":
|
| 1182 |
-
"learning_rate":
|
| 1183 |
-
"loss": 1.
|
| 1184 |
-
"step":
|
| 1185 |
},
|
| 1186 |
{
|
| 1187 |
-
"epoch":
|
| 1188 |
-
"learning_rate":
|
| 1189 |
-
"loss": 1.
|
| 1190 |
-
"step":
|
| 1191 |
},
|
| 1192 |
{
|
| 1193 |
-
"epoch":
|
| 1194 |
-
"learning_rate":
|
| 1195 |
-
"loss": 1.
|
| 1196 |
-
"step":
|
| 1197 |
},
|
| 1198 |
{
|
| 1199 |
-
"epoch":
|
| 1200 |
-
"learning_rate":
|
| 1201 |
-
"loss": 1.
|
| 1202 |
-
"step":
|
| 1203 |
},
|
| 1204 |
{
|
| 1205 |
-
"epoch":
|
| 1206 |
-
"learning_rate":
|
| 1207 |
-
"loss": 1.
|
| 1208 |
-
"step":
|
| 1209 |
},
|
| 1210 |
{
|
| 1211 |
-
"epoch":
|
| 1212 |
-
"learning_rate":
|
| 1213 |
-
"loss": 1.
|
| 1214 |
-
"step":
|
| 1215 |
},
|
| 1216 |
{
|
| 1217 |
-
"epoch":
|
| 1218 |
-
"learning_rate":
|
| 1219 |
-
"loss": 1.
|
| 1220 |
-
"step":
|
| 1221 |
},
|
| 1222 |
{
|
| 1223 |
-
"epoch":
|
| 1224 |
-
"learning_rate":
|
| 1225 |
-
"loss": 1.
|
| 1226 |
-
"step":
|
| 1227 |
},
|
| 1228 |
{
|
| 1229 |
-
"epoch":
|
| 1230 |
-
"
|
| 1231 |
-
"
|
| 1232 |
-
"
|
| 1233 |
-
"eval_runtime": 2548.9872,
|
| 1234 |
-
"eval_samples_per_second": 6.734,
|
| 1235 |
-
"eval_steps_per_second": 0.421,
|
| 1236 |
-
"step": 1885630
|
| 1237 |
},
|
| 1238 |
{
|
| 1239 |
-
"epoch":
|
| 1240 |
-
"
|
| 1241 |
-
"
|
| 1242 |
-
"
|
| 1243 |
-
"
|
| 1244 |
-
"
|
| 1245 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1246 |
}
|
| 1247 |
],
|
| 1248 |
-
"max_steps":
|
| 1249 |
-
"num_train_epochs":
|
| 1250 |
-
"total_flos":
|
| 1251 |
"trial_name": null,
|
| 1252 |
"trial_params": null
|
| 1253 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 19.999983677999577,
|
| 5 |
+
"global_step": 612660,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
| 9 |
"log_history": [
|
| 10 |
{
|
| 11 |
+
"epoch": 0.1,
|
| 12 |
+
"learning_rate": 9.951082166291254e-05,
|
| 13 |
+
"loss": 4.9783,
|
| 14 |
+
"step": 3000
|
| 15 |
},
|
| 16 |
{
|
| 17 |
+
"epoch": 0.2,
|
| 18 |
+
"learning_rate": 9.902115365782e-05,
|
| 19 |
+
"loss": 3.1296,
|
| 20 |
+
"step": 6000
|
| 21 |
},
|
| 22 |
{
|
| 23 |
+
"epoch": 0.29,
|
| 24 |
+
"learning_rate": 9.853148565272745e-05,
|
| 25 |
+
"loss": 2.7383,
|
| 26 |
+
"step": 9000
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.39,
|
| 30 |
+
"learning_rate": 9.804181764763491e-05,
|
| 31 |
+
"loss": 2.5447,
|
| 32 |
+
"step": 12000
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.49,
|
| 36 |
+
"learning_rate": 9.755231286521073e-05,
|
| 37 |
+
"loss": 2.4175,
|
| 38 |
+
"step": 15000
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.59,
|
| 42 |
+
"learning_rate": 9.706280808278654e-05,
|
| 43 |
+
"loss": 2.3285,
|
| 44 |
+
"step": 18000
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.69,
|
| 48 |
+
"learning_rate": 9.657346652303072e-05,
|
| 49 |
+
"loss": 2.2597,
|
| 50 |
+
"step": 21000
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.78,
|
| 54 |
+
"learning_rate": 9.608396174060654e-05,
|
| 55 |
+
"loss": 2.2072,
|
| 56 |
+
"step": 24000
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.88,
|
| 60 |
+
"learning_rate": 9.559462018085072e-05,
|
| 61 |
+
"loss": 2.1601,
|
| 62 |
+
"step": 27000
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.98,
|
| 66 |
+
"learning_rate": 9.510511539842654e-05,
|
| 67 |
+
"loss": 2.125,
|
| 68 |
"step": 30000
|
| 69 |
},
|
| 70 |
{
|
| 71 |
+
"epoch": 1.0,
|
| 72 |
+
"eval_loss": 2.072047233581543,
|
| 73 |
+
"eval_runtime": 19.2095,
|
| 74 |
+
"eval_samples_per_second": 1536.842,
|
| 75 |
+
"eval_steps_per_second": 9.631,
|
| 76 |
+
"step": 30633
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"epoch": 1.08,
|
| 80 |
+
"learning_rate": 9.461577383867072e-05,
|
| 81 |
+
"loss": 2.0771,
|
| 82 |
+
"step": 33000
|
| 83 |
+
},
|
| 84 |
+
{
|
| 85 |
+
"epoch": 1.18,
|
| 86 |
+
"learning_rate": 9.412626905624655e-05,
|
| 87 |
+
"loss": 2.0514,
|
| 88 |
+
"step": 36000
|
| 89 |
},
|
| 90 |
{
|
| 91 |
+
"epoch": 1.27,
|
| 92 |
+
"learning_rate": 9.363692749649071e-05,
|
| 93 |
+
"loss": 2.0297,
|
| 94 |
+
"step": 39000
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 1.37,
|
| 98 |
+
"learning_rate": 9.314742271406653e-05,
|
| 99 |
+
"loss": 2.0123,
|
| 100 |
+
"step": 42000
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 1.47,
|
| 104 |
+
"learning_rate": 9.265791793164235e-05,
|
| 105 |
+
"loss": 1.9955,
|
| 106 |
+
"step": 45000
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 1.57,
|
| 110 |
+
"learning_rate": 9.216857637188653e-05,
|
| 111 |
+
"loss": 1.9803,
|
| 112 |
+
"step": 48000
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"epoch": 1.66,
|
| 116 |
+
"learning_rate": 9.167907158946235e-05,
|
| 117 |
+
"loss": 1.9667,
|
| 118 |
+
"step": 51000
|
| 119 |
+
},
|
| 120 |
+
{
|
| 121 |
+
"epoch": 1.76,
|
| 122 |
+
"learning_rate": 9.118973002970654e-05,
|
| 123 |
+
"loss": 1.9505,
|
| 124 |
+
"step": 54000
|
| 125 |
},
|
| 126 |
{
|
| 127 |
+
"epoch": 1.86,
|
| 128 |
+
"learning_rate": 9.070022524728234e-05,
|
| 129 |
+
"loss": 1.9381,
|
| 130 |
+
"step": 57000
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 1.96,
|
| 134 |
+
"learning_rate": 9.021088368752652e-05,
|
| 135 |
+
"loss": 1.9288,
|
| 136 |
"step": 60000
|
| 137 |
},
|
| 138 |
{
|
| 139 |
+
"epoch": 2.0,
|
| 140 |
+
"eval_loss": 1.9032506942749023,
|
| 141 |
+
"eval_runtime": 19.1781,
|
| 142 |
+
"eval_samples_per_second": 1539.357,
|
| 143 |
+
"eval_steps_per_second": 9.646,
|
| 144 |
+
"step": 61266
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 2.06,
|
| 148 |
+
"learning_rate": 8.972137890510235e-05,
|
| 149 |
+
"loss": 1.9011,
|
| 150 |
+
"step": 63000
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 2.15,
|
| 154 |
+
"learning_rate": 8.923203734534653e-05,
|
| 155 |
+
"loss": 1.8834,
|
| 156 |
+
"step": 66000
|
| 157 |
},
|
| 158 |
{
|
| 159 |
+
"epoch": 2.25,
|
| 160 |
+
"learning_rate": 8.874253256292235e-05,
|
| 161 |
+
"loss": 1.8807,
|
| 162 |
+
"step": 69000
|
| 163 |
},
|
| 164 |
{
|
| 165 |
+
"epoch": 2.35,
|
| 166 |
+
"learning_rate": 8.825319100316653e-05,
|
| 167 |
+
"loss": 1.8737,
|
| 168 |
+
"step": 72000
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 2.45,
|
| 172 |
+
"learning_rate": 8.776368622074233e-05,
|
| 173 |
+
"loss": 1.8686,
|
| 174 |
+
"step": 75000
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 2.55,
|
| 178 |
+
"learning_rate": 8.727434466098652e-05,
|
| 179 |
+
"loss": 1.861,
|
| 180 |
+
"step": 78000
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 2.64,
|
| 184 |
+
"learning_rate": 8.678483987856234e-05,
|
| 185 |
+
"loss": 1.8549,
|
| 186 |
+
"step": 81000
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 2.74,
|
| 190 |
+
"learning_rate": 8.629549831880652e-05,
|
| 191 |
+
"loss": 1.8503,
|
| 192 |
+
"step": 84000
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 2.84,
|
| 196 |
+
"learning_rate": 8.580599353638234e-05,
|
| 197 |
+
"loss": 1.8446,
|
| 198 |
+
"step": 87000
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 2.94,
|
| 202 |
+
"learning_rate": 8.531665197662652e-05,
|
| 203 |
+
"loss": 1.8387,
|
| 204 |
"step": 90000
|
| 205 |
},
|
| 206 |
{
|
| 207 |
+
"epoch": 3.0,
|
| 208 |
+
"eval_loss": 1.833019733428955,
|
| 209 |
+
"eval_runtime": 19.0959,
|
| 210 |
+
"eval_samples_per_second": 1545.988,
|
| 211 |
+
"eval_steps_per_second": 9.688,
|
| 212 |
+
"step": 91899
|
| 213 |
},
|
| 214 |
{
|
| 215 |
+
"epoch": 3.04,
|
| 216 |
+
"learning_rate": 8.482714719420234e-05,
|
| 217 |
+
"loss": 1.8222,
|
| 218 |
+
"step": 93000
|
| 219 |
},
|
| 220 |
{
|
| 221 |
+
"epoch": 3.13,
|
| 222 |
+
"learning_rate": 8.433764241177815e-05,
|
| 223 |
+
"loss": 1.8037,
|
| 224 |
+
"step": 96000
|
| 225 |
},
|
| 226 |
{
|
| 227 |
+
"epoch": 3.23,
|
| 228 |
+
"learning_rate": 8.384830085202233e-05,
|
| 229 |
+
"loss": 1.8017,
|
| 230 |
+
"step": 99000
|
| 231 |
},
|
| 232 |
{
|
| 233 |
+
"epoch": 3.33,
|
| 234 |
+
"learning_rate": 8.335879606959815e-05,
|
| 235 |
+
"loss": 1.8018,
|
| 236 |
+
"step": 102000
|
| 237 |
},
|
| 238 |
{
|
| 239 |
+
"epoch": 3.43,
|
| 240 |
+
"learning_rate": 8.286945450984233e-05,
|
| 241 |
+
"loss": 1.7984,
|
| 242 |
+
"step": 105000
|
| 243 |
},
|
| 244 |
{
|
| 245 |
+
"epoch": 3.53,
|
| 246 |
+
"learning_rate": 8.237994972741815e-05,
|
| 247 |
+
"loss": 1.796,
|
| 248 |
+
"step": 108000
|
| 249 |
},
|
| 250 |
{
|
| 251 |
+
"epoch": 3.62,
|
| 252 |
+
"learning_rate": 8.189060816766233e-05,
|
| 253 |
+
"loss": 1.7942,
|
| 254 |
+
"step": 111000
|
| 255 |
},
|
| 256 |
{
|
| 257 |
+
"epoch": 3.72,
|
| 258 |
+
"learning_rate": 8.140110338523814e-05,
|
| 259 |
+
"loss": 1.7905,
|
| 260 |
+
"step": 114000
|
| 261 |
},
|
| 262 |
{
|
| 263 |
+
"epoch": 3.82,
|
| 264 |
+
"learning_rate": 8.091176182548232e-05,
|
| 265 |
+
"loss": 1.7885,
|
| 266 |
+
"step": 117000
|
|
|
|
|
|
|
|
|
|
|
|
|
| 267 |
},
|
| 268 |
{
|
| 269 |
+
"epoch": 3.92,
|
| 270 |
+
"learning_rate": 8.042225704305814e-05,
|
| 271 |
+
"loss": 1.7832,
|
| 272 |
+
"step": 120000
|
| 273 |
},
|
| 274 |
{
|
| 275 |
+
"epoch": 4.0,
|
| 276 |
+
"eval_loss": 1.7864413261413574,
|
| 277 |
+
"eval_runtime": 19.3546,
|
| 278 |
+
"eval_samples_per_second": 1525.321,
|
| 279 |
+
"eval_steps_per_second": 9.558,
|
| 280 |
+
"step": 122532
|
| 281 |
},
|
| 282 |
{
|
| 283 |
+
"epoch": 4.02,
|
| 284 |
+
"learning_rate": 7.993291548330233e-05,
|
| 285 |
+
"loss": 1.7754,
|
| 286 |
+
"step": 123000
|
| 287 |
},
|
| 288 |
{
|
| 289 |
+
"epoch": 4.11,
|
| 290 |
+
"learning_rate": 7.944341070087814e-05,
|
| 291 |
+
"loss": 1.7507,
|
| 292 |
+
"step": 126000
|
| 293 |
},
|
| 294 |
{
|
| 295 |
+
"epoch": 4.21,
|
| 296 |
+
"learning_rate": 7.895406914112233e-05,
|
| 297 |
+
"loss": 1.7526,
|
| 298 |
+
"step": 129000
|
| 299 |
},
|
| 300 |
{
|
| 301 |
+
"epoch": 4.31,
|
| 302 |
+
"learning_rate": 7.846456435869815e-05,
|
| 303 |
+
"loss": 1.7541,
|
| 304 |
+
"step": 132000
|
| 305 |
},
|
| 306 |
{
|
| 307 |
+
"epoch": 4.41,
|
| 308 |
+
"learning_rate": 7.797522279894231e-05,
|
| 309 |
+
"loss": 1.7537,
|
| 310 |
+
"step": 135000
|
| 311 |
},
|
| 312 |
{
|
| 313 |
+
"epoch": 4.5,
|
| 314 |
+
"learning_rate": 7.748571801651814e-05,
|
| 315 |
+
"loss": 1.7541,
|
| 316 |
+
"step": 138000
|
| 317 |
},
|
| 318 |
{
|
| 319 |
+
"epoch": 4.6,
|
| 320 |
+
"learning_rate": 7.699621323409395e-05,
|
| 321 |
+
"loss": 1.7505,
|
| 322 |
+
"step": 141000
|
| 323 |
},
|
| 324 |
{
|
| 325 |
+
"epoch": 4.7,
|
| 326 |
+
"learning_rate": 7.650687167433813e-05,
|
| 327 |
+
"loss": 1.7475,
|
| 328 |
+
"step": 144000
|
| 329 |
},
|
| 330 |
{
|
| 331 |
+
"epoch": 4.8,
|
| 332 |
+
"learning_rate": 7.601736689191396e-05,
|
| 333 |
+
"loss": 1.7477,
|
| 334 |
+
"step": 147000
|
| 335 |
},
|
| 336 |
{
|
| 337 |
+
"epoch": 4.9,
|
| 338 |
+
"learning_rate": 7.552802533215814e-05,
|
| 339 |
+
"loss": 1.7461,
|
| 340 |
+
"step": 150000
|
| 341 |
},
|
| 342 |
{
|
| 343 |
+
"epoch": 4.99,
|
| 344 |
+
"learning_rate": 7.503852054973394e-05,
|
| 345 |
+
"loss": 1.7445,
|
| 346 |
+
"step": 153000
|
| 347 |
},
|
| 348 |
{
|
| 349 |
+
"epoch": 5.0,
|
| 350 |
+
"eval_loss": 1.7591967582702637,
|
| 351 |
+
"eval_runtime": 19.1359,
|
| 352 |
+
"eval_samples_per_second": 1542.756,
|
| 353 |
+
"eval_steps_per_second": 9.668,
|
| 354 |
+
"step": 153165
|
| 355 |
},
|
| 356 |
{
|
| 357 |
+
"epoch": 5.09,
|
| 358 |
+
"learning_rate": 7.454917898997813e-05,
|
| 359 |
+
"loss": 1.7143,
|
| 360 |
+
"step": 156000
|
| 361 |
},
|
| 362 |
{
|
| 363 |
+
"epoch": 5.19,
|
| 364 |
+
"learning_rate": 7.405967420755395e-05,
|
| 365 |
+
"loss": 1.7177,
|
| 366 |
+
"step": 159000
|
| 367 |
},
|
| 368 |
{
|
| 369 |
+
"epoch": 5.29,
|
| 370 |
+
"learning_rate": 7.357033264779813e-05,
|
| 371 |
+
"loss": 1.7188,
|
| 372 |
+
"step": 162000
|
| 373 |
},
|
| 374 |
{
|
| 375 |
+
"epoch": 5.39,
|
| 376 |
+
"learning_rate": 7.308082786537395e-05,
|
| 377 |
+
"loss": 1.7198,
|
| 378 |
+
"step": 165000
|
| 379 |
},
|
| 380 |
{
|
| 381 |
+
"epoch": 5.48,
|
| 382 |
+
"learning_rate": 7.259148630561813e-05,
|
| 383 |
+
"loss": 1.7202,
|
| 384 |
+
"step": 168000
|
| 385 |
},
|
| 386 |
{
|
| 387 |
+
"epoch": 5.58,
|
| 388 |
+
"learning_rate": 7.210198152319395e-05,
|
| 389 |
+
"loss": 1.7184,
|
| 390 |
+
"step": 171000
|
|
|
|
|
|
|
|
|
|
|
|
|
| 391 |
},
|
| 392 |
{
|
| 393 |
+
"epoch": 5.68,
|
| 394 |
+
"learning_rate": 7.161247674076976e-05,
|
| 395 |
+
"loss": 1.719,
|
| 396 |
+
"step": 174000
|
| 397 |
},
|
| 398 |
{
|
| 399 |
+
"epoch": 5.78,
|
| 400 |
+
"learning_rate": 7.112313518101394e-05,
|
| 401 |
+
"loss": 1.7173,
|
| 402 |
+
"step": 177000
|
| 403 |
},
|
| 404 |
{
|
| 405 |
+
"epoch": 5.88,
|
| 406 |
+
"learning_rate": 7.063363039858976e-05,
|
| 407 |
+
"loss": 1.7176,
|
| 408 |
+
"step": 180000
|
| 409 |
},
|
| 410 |
{
|
| 411 |
+
"epoch": 5.97,
|
| 412 |
+
"learning_rate": 7.014428883883394e-05,
|
| 413 |
+
"loss": 1.7152,
|
| 414 |
+
"step": 183000
|
| 415 |
},
|
| 416 |
{
|
| 417 |
+
"epoch": 6.0,
|
| 418 |
+
"eval_loss": 1.740378975868225,
|
| 419 |
+
"eval_runtime": 19.1537,
|
| 420 |
+
"eval_samples_per_second": 1541.325,
|
| 421 |
+
"eval_steps_per_second": 9.659,
|
| 422 |
+
"step": 183798
|
| 423 |
},
|
| 424 |
{
|
| 425 |
+
"epoch": 6.07,
|
| 426 |
+
"learning_rate": 6.965478405640976e-05,
|
| 427 |
+
"loss": 1.6926,
|
| 428 |
+
"step": 186000
|
| 429 |
},
|
| 430 |
{
|
| 431 |
+
"epoch": 6.17,
|
| 432 |
+
"learning_rate": 6.916544249665395e-05,
|
| 433 |
+
"loss": 1.6889,
|
| 434 |
+
"step": 189000
|
| 435 |
},
|
| 436 |
{
|
| 437 |
+
"epoch": 6.27,
|
| 438 |
+
"learning_rate": 6.867593771422975e-05,
|
| 439 |
+
"loss": 1.6923,
|
| 440 |
+
"step": 192000
|
| 441 |
},
|
| 442 |
{
|
| 443 |
+
"epoch": 6.37,
|
| 444 |
+
"learning_rate": 6.818659615447393e-05,
|
| 445 |
+
"loss": 1.693,
|
| 446 |
+
"step": 195000
|
| 447 |
},
|
| 448 |
{
|
| 449 |
+
"epoch": 6.46,
|
| 450 |
+
"learning_rate": 6.769709137204976e-05,
|
| 451 |
+
"loss": 1.694,
|
| 452 |
+
"step": 198000
|
| 453 |
},
|
| 454 |
{
|
| 455 |
+
"epoch": 6.56,
|
| 456 |
+
"learning_rate": 6.720774981229393e-05,
|
| 457 |
+
"loss": 1.6948,
|
| 458 |
+
"step": 201000
|
| 459 |
},
|
| 460 |
{
|
| 461 |
+
"epoch": 6.66,
|
| 462 |
+
"learning_rate": 6.671824502986975e-05,
|
| 463 |
+
"loss": 1.6944,
|
| 464 |
+
"step": 204000
|
| 465 |
},
|
| 466 |
{
|
| 467 |
+
"epoch": 6.76,
|
| 468 |
+
"learning_rate": 6.622874024744557e-05,
|
| 469 |
+
"loss": 1.6934,
|
| 470 |
+
"step": 207000
|
| 471 |
},
|
| 472 |
{
|
| 473 |
+
"epoch": 6.86,
|
| 474 |
+
"learning_rate": 6.573939868768974e-05,
|
| 475 |
+
"loss": 1.6926,
|
| 476 |
+
"step": 210000
|
| 477 |
},
|
| 478 |
{
|
| 479 |
+
"epoch": 6.95,
|
| 480 |
+
"learning_rate": 6.524989390526556e-05,
|
| 481 |
+
"loss": 1.6933,
|
| 482 |
+
"step": 213000
|
| 483 |
},
|
| 484 |
{
|
| 485 |
+
"epoch": 7.0,
|
| 486 |
+
"eval_loss": 1.7208322286605835,
|
| 487 |
+
"eval_runtime": 19.2921,
|
| 488 |
+
"eval_samples_per_second": 1530.262,
|
| 489 |
+
"eval_steps_per_second": 9.589,
|
| 490 |
+
"step": 214431
|
| 491 |
},
|
| 492 |
{
|
| 493 |
+
"epoch": 7.05,
|
| 494 |
+
"learning_rate": 6.476055234550975e-05,
|
| 495 |
+
"loss": 1.6773,
|
| 496 |
+
"step": 216000
|
| 497 |
},
|
| 498 |
{
|
| 499 |
+
"epoch": 7.15,
|
| 500 |
+
"learning_rate": 6.427104756308556e-05,
|
| 501 |
+
"loss": 1.6671,
|
| 502 |
+
"step": 219000
|
| 503 |
},
|
| 504 |
{
|
| 505 |
+
"epoch": 7.25,
|
| 506 |
+
"learning_rate": 6.378170600332975e-05,
|
| 507 |
+
"loss": 1.6695,
|
| 508 |
+
"step": 222000
|
| 509 |
},
|
| 510 |
{
|
| 511 |
+
"epoch": 7.35,
|
| 512 |
+
"learning_rate": 6.329220122090557e-05,
|
| 513 |
+
"loss": 1.6707,
|
| 514 |
+
"step": 225000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 515 |
},
|
| 516 |
{
|
| 517 |
+
"epoch": 7.44,
|
| 518 |
+
"learning_rate": 6.280285966114975e-05,
|
| 519 |
+
"loss": 1.674,
|
| 520 |
+
"step": 228000
|
| 521 |
},
|
| 522 |
{
|
| 523 |
+
"epoch": 7.54,
|
| 524 |
+
"learning_rate": 6.231335487872557e-05,
|
| 525 |
+
"loss": 1.6726,
|
| 526 |
+
"step": 231000
|
| 527 |
},
|
| 528 |
{
|
| 529 |
+
"epoch": 7.64,
|
| 530 |
+
"learning_rate": 6.182401331896974e-05,
|
| 531 |
+
"loss": 1.6739,
|
| 532 |
+
"step": 234000
|
| 533 |
},
|
| 534 |
{
|
| 535 |
+
"epoch": 7.74,
|
| 536 |
+
"learning_rate": 6.133450853654555e-05,
|
| 537 |
+
"loss": 1.6755,
|
| 538 |
+
"step": 237000
|
| 539 |
},
|
| 540 |
{
|
| 541 |
+
"epoch": 7.83,
|
| 542 |
+
"learning_rate": 6.084516697678973e-05,
|
| 543 |
+
"loss": 1.6726,
|
| 544 |
+
"step": 240000
|
| 545 |
},
|
| 546 |
{
|
| 547 |
+
"epoch": 7.93,
|
| 548 |
+
"learning_rate": 6.035566219436556e-05,
|
| 549 |
+
"loss": 1.6743,
|
| 550 |
+
"step": 243000
|
| 551 |
},
|
| 552 |
{
|
| 553 |
+
"epoch": 8.0,
|
| 554 |
+
"eval_loss": 1.7004761695861816,
|
| 555 |
+
"eval_runtime": 19.351,
|
| 556 |
+
"eval_samples_per_second": 1525.608,
|
| 557 |
+
"eval_steps_per_second": 9.56,
|
| 558 |
+
"step": 245064
|
| 559 |
},
|
| 560 |
{
|
| 561 |
+
"epoch": 8.03,
|
| 562 |
+
"learning_rate": 5.986632063460974e-05,
|
| 563 |
+
"loss": 1.6642,
|
| 564 |
+
"step": 246000
|
| 565 |
},
|
| 566 |
{
|
| 567 |
+
"epoch": 8.13,
|
| 568 |
+
"learning_rate": 5.9376815852185555e-05,
|
| 569 |
+
"loss": 1.6475,
|
| 570 |
+
"step": 249000
|
| 571 |
},
|
| 572 |
{
|
| 573 |
+
"epoch": 8.23,
|
| 574 |
+
"learning_rate": 5.888747429242973e-05,
|
| 575 |
+
"loss": 1.6525,
|
| 576 |
+
"step": 252000
|
| 577 |
},
|
| 578 |
{
|
| 579 |
+
"epoch": 8.32,
|
| 580 |
+
"learning_rate": 5.839796951000556e-05,
|
| 581 |
+
"loss": 1.653,
|
| 582 |
+
"step": 255000
|
| 583 |
},
|
| 584 |
{
|
| 585 |
+
"epoch": 8.42,
|
| 586 |
+
"learning_rate": 5.7908627950249736e-05,
|
| 587 |
+
"loss": 1.6556,
|
| 588 |
+
"step": 258000
|
| 589 |
},
|
| 590 |
{
|
| 591 |
+
"epoch": 8.52,
|
| 592 |
+
"learning_rate": 5.741912316782555e-05,
|
| 593 |
+
"loss": 1.6556,
|
| 594 |
+
"step": 261000
|
| 595 |
},
|
| 596 |
{
|
| 597 |
+
"epoch": 8.62,
|
| 598 |
+
"learning_rate": 5.692961838540136e-05,
|
| 599 |
+
"loss": 1.6565,
|
| 600 |
+
"step": 264000
|
| 601 |
},
|
| 602 |
{
|
| 603 |
+
"epoch": 8.72,
|
| 604 |
+
"learning_rate": 5.6440276825645545e-05,
|
| 605 |
+
"loss": 1.6567,
|
| 606 |
+
"step": 267000
|
| 607 |
},
|
| 608 |
{
|
| 609 |
+
"epoch": 8.81,
|
| 610 |
+
"learning_rate": 5.5950772043221364e-05,
|
| 611 |
+
"loss": 1.6574,
|
| 612 |
+
"step": 270000
|
| 613 |
},
|
| 614 |
{
|
| 615 |
+
"epoch": 8.91,
|
| 616 |
+
"learning_rate": 5.546143048346555e-05,
|
| 617 |
+
"loss": 1.6561,
|
| 618 |
+
"step": 273000
|
| 619 |
},
|
| 620 |
{
|
| 621 |
+
"epoch": 9.0,
|
| 622 |
+
"eval_loss": 1.6906808614730835,
|
| 623 |
+
"eval_runtime": 19.2999,
|
| 624 |
+
"eval_samples_per_second": 1529.642,
|
| 625 |
+
"eval_steps_per_second": 9.586,
|
| 626 |
+
"step": 275697
|
| 627 |
},
|
| 628 |
{
|
| 629 |
+
"epoch": 9.01,
|
| 630 |
+
"learning_rate": 5.497192570104136e-05,
|
| 631 |
+
"loss": 1.6546,
|
| 632 |
+
"step": 276000
|
|
|
|
|
|
|
|
|
|
|
|
|
| 633 |
},
|
| 634 |
{
|
| 635 |
+
"epoch": 9.11,
|
| 636 |
+
"learning_rate": 5.4482584141285545e-05,
|
| 637 |
+
"loss": 1.6302,
|
| 638 |
+
"step": 279000
|
| 639 |
},
|
| 640 |
{
|
| 641 |
+
"epoch": 9.21,
|
| 642 |
+
"learning_rate": 5.3993079358861364e-05,
|
| 643 |
+
"loss": 1.6356,
|
| 644 |
+
"step": 282000
|
| 645 |
},
|
| 646 |
{
|
| 647 |
+
"epoch": 9.3,
|
| 648 |
+
"learning_rate": 5.3503574576437175e-05,
|
| 649 |
+
"loss": 1.6375,
|
| 650 |
+
"step": 285000
|
| 651 |
},
|
| 652 |
{
|
| 653 |
+
"epoch": 9.4,
|
| 654 |
+
"learning_rate": 5.301423301668136e-05,
|
| 655 |
+
"loss": 1.6399,
|
| 656 |
+
"step": 288000
|
| 657 |
},
|
| 658 |
{
|
| 659 |
+
"epoch": 9.5,
|
| 660 |
+
"learning_rate": 5.252472823425718e-05,
|
| 661 |
+
"loss": 1.6404,
|
| 662 |
+
"step": 291000
|
| 663 |
},
|
| 664 |
{
|
| 665 |
+
"epoch": 9.6,
|
| 666 |
+
"learning_rate": 5.203538667450135e-05,
|
| 667 |
+
"loss": 1.642,
|
| 668 |
+
"step": 294000
|
| 669 |
},
|
| 670 |
{
|
| 671 |
+
"epoch": 9.7,
|
| 672 |
+
"learning_rate": 5.1545881892077175e-05,
|
| 673 |
+
"loss": 1.642,
|
| 674 |
+
"step": 297000
|
| 675 |
},
|
| 676 |
{
|
| 677 |
+
"epoch": 9.79,
|
| 678 |
+
"learning_rate": 5.105654033232135e-05,
|
| 679 |
+
"loss": 1.6421,
|
| 680 |
+
"step": 300000
|
| 681 |
},
|
| 682 |
{
|
| 683 |
+
"epoch": 9.89,
|
| 684 |
+
"learning_rate": 5.0567035549897165e-05,
|
| 685 |
+
"loss": 1.6417,
|
| 686 |
+
"step": 303000
|
| 687 |
},
|
| 688 |
{
|
| 689 |
+
"epoch": 9.99,
|
| 690 |
+
"learning_rate": 5.007753076747299e-05,
|
| 691 |
+
"loss": 1.6431,
|
| 692 |
+
"step": 306000
|
| 693 |
},
|
| 694 |
{
|
| 695 |
+
"epoch": 10.0,
|
| 696 |
+
"eval_loss": 1.690254807472229,
|
| 697 |
+
"eval_runtime": 19.1786,
|
| 698 |
+
"eval_samples_per_second": 1539.322,
|
| 699 |
+
"eval_steps_per_second": 9.646,
|
| 700 |
+
"step": 306330
|
| 701 |
},
|
| 702 |
{
|
| 703 |
+
"epoch": 10.09,
|
| 704 |
+
"learning_rate": 4.9588189207717175e-05,
|
| 705 |
+
"loss": 1.6191,
|
| 706 |
+
"step": 309000
|
| 707 |
},
|
| 708 |
{
|
| 709 |
+
"epoch": 10.19,
|
| 710 |
+
"learning_rate": 4.909868442529299e-05,
|
| 711 |
+
"loss": 1.6215,
|
| 712 |
+
"step": 312000
|
| 713 |
},
|
| 714 |
{
|
| 715 |
+
"epoch": 10.28,
|
| 716 |
+
"learning_rate": 4.8609342865537165e-05,
|
| 717 |
+
"loss": 1.6247,
|
| 718 |
+
"step": 315000
|
| 719 |
},
|
| 720 |
{
|
| 721 |
+
"epoch": 10.38,
|
| 722 |
+
"learning_rate": 4.8119838083112984e-05,
|
| 723 |
+
"loss": 1.6244,
|
| 724 |
+
"step": 318000
|
| 725 |
},
|
| 726 |
{
|
| 727 |
+
"epoch": 10.48,
|
| 728 |
+
"learning_rate": 4.76303333006888e-05,
|
| 729 |
+
"loss": 1.6261,
|
| 730 |
+
"step": 321000
|
| 731 |
},
|
| 732 |
{
|
| 733 |
+
"epoch": 10.58,
|
| 734 |
+
"learning_rate": 4.714099174093298e-05,
|
| 735 |
+
"loss": 1.6288,
|
| 736 |
+
"step": 324000
|
| 737 |
},
|
| 738 |
{
|
| 739 |
+
"epoch": 10.67,
|
| 740 |
+
"learning_rate": 4.66514869585088e-05,
|
| 741 |
+
"loss": 1.6289,
|
| 742 |
+
"step": 327000
|
| 743 |
},
|
| 744 |
{
|
| 745 |
+
"epoch": 10.77,
|
| 746 |
+
"learning_rate": 4.6162145398752984e-05,
|
| 747 |
+
"loss": 1.6295,
|
| 748 |
+
"step": 330000
|
| 749 |
},
|
| 750 |
{
|
| 751 |
+
"epoch": 10.87,
|
| 752 |
+
"learning_rate": 4.5672640616328796e-05,
|
| 753 |
+
"loss": 1.6295,
|
| 754 |
+
"step": 333000
|
|
|
|
|
|
|
|
|
|
|
|
|
| 755 |
},
|
| 756 |
{
|
| 757 |
+
"epoch": 10.97,
|
| 758 |
+
"learning_rate": 4.5183135833904614e-05,
|
| 759 |
+
"loss": 1.6282,
|
| 760 |
+
"step": 336000
|
| 761 |
},
|
| 762 |
{
|
| 763 |
+
"epoch": 11.0,
|
| 764 |
+
"eval_loss": 1.6800603866577148,
|
| 765 |
+
"eval_runtime": 19.1041,
|
| 766 |
+
"eval_samples_per_second": 1545.321,
|
| 767 |
+
"eval_steps_per_second": 9.684,
|
| 768 |
+
"step": 336963
|
| 769 |
},
|
| 770 |
{
|
| 771 |
+
"epoch": 11.07,
|
| 772 |
+
"learning_rate": 4.46937942741488e-05,
|
| 773 |
+
"loss": 1.6134,
|
| 774 |
+
"step": 339000
|
| 775 |
},
|
| 776 |
{
|
| 777 |
+
"epoch": 11.16,
|
| 778 |
+
"learning_rate": 4.420428949172462e-05,
|
| 779 |
+
"loss": 1.6072,
|
| 780 |
+
"step": 342000
|
| 781 |
},
|
| 782 |
{
|
| 783 |
+
"epoch": 11.26,
|
| 784 |
+
"learning_rate": 4.371494793196879e-05,
|
| 785 |
+
"loss": 1.6099,
|
| 786 |
+
"step": 345000
|
| 787 |
},
|
| 788 |
{
|
| 789 |
+
"epoch": 11.36,
|
| 790 |
+
"learning_rate": 4.322544314954461e-05,
|
| 791 |
+
"loss": 1.6137,
|
| 792 |
+
"step": 348000
|
| 793 |
},
|
| 794 |
{
|
| 795 |
+
"epoch": 11.46,
|
| 796 |
+
"learning_rate": 4.273610158978879e-05,
|
| 797 |
+
"loss": 1.6136,
|
| 798 |
+
"step": 351000
|
| 799 |
},
|
| 800 |
{
|
| 801 |
+
"epoch": 11.56,
|
| 802 |
+
"learning_rate": 4.224659680736461e-05,
|
| 803 |
+
"loss": 1.6151,
|
| 804 |
+
"step": 354000
|
| 805 |
},
|
| 806 |
{
|
| 807 |
+
"epoch": 11.65,
|
| 808 |
+
"learning_rate": 4.175725524760879e-05,
|
| 809 |
+
"loss": 1.6166,
|
| 810 |
+
"step": 357000
|
| 811 |
},
|
| 812 |
{
|
| 813 |
+
"epoch": 11.75,
|
| 814 |
+
"learning_rate": 4.126775046518461e-05,
|
| 815 |
+
"loss": 1.6179,
|
| 816 |
+
"step": 360000
|
| 817 |
},
|
| 818 |
{
|
| 819 |
+
"epoch": 11.85,
|
| 820 |
+
"learning_rate": 4.077840890542879e-05,
|
| 821 |
+
"loss": 1.6174,
|
| 822 |
+
"step": 363000
|
| 823 |
},
|
| 824 |
{
|
| 825 |
+
"epoch": 11.95,
|
| 826 |
+
"learning_rate": 4.0288904123004604e-05,
|
| 827 |
+
"loss": 1.6173,
|
| 828 |
+
"step": 366000
|
| 829 |
},
|
| 830 |
{
|
| 831 |
+
"epoch": 12.0,
|
| 832 |
+
"eval_loss": 1.6714136600494385,
|
| 833 |
+
"eval_runtime": 19.2107,
|
| 834 |
+
"eval_samples_per_second": 1536.747,
|
| 835 |
+
"eval_steps_per_second": 9.63,
|
| 836 |
+
"step": 367596
|
| 837 |
},
|
| 838 |
{
|
| 839 |
+
"epoch": 12.05,
|
| 840 |
+
"learning_rate": 3.979939934058042e-05,
|
| 841 |
+
"loss": 1.6063,
|
| 842 |
+
"step": 369000
|
| 843 |
},
|
| 844 |
{
|
| 845 |
+
"epoch": 12.14,
|
| 846 |
+
"learning_rate": 3.931005778082461e-05,
|
| 847 |
+
"loss": 1.5969,
|
| 848 |
+
"step": 372000
|
| 849 |
},
|
| 850 |
{
|
| 851 |
+
"epoch": 12.24,
|
| 852 |
+
"learning_rate": 3.882055299840042e-05,
|
| 853 |
+
"loss": 1.5998,
|
| 854 |
+
"step": 375000
|
| 855 |
},
|
| 856 |
{
|
| 857 |
+
"epoch": 12.34,
|
| 858 |
+
"learning_rate": 3.83312114386446e-05,
|
| 859 |
+
"loss": 1.6011,
|
| 860 |
+
"step": 378000
|
| 861 |
},
|
| 862 |
{
|
| 863 |
+
"epoch": 12.44,
|
| 864 |
+
"learning_rate": 3.784154343355205e-05,
|
| 865 |
+
"loss": 1.6034,
|
| 866 |
+
"step": 381000
|
| 867 |
},
|
| 868 |
{
|
| 869 |
+
"epoch": 12.54,
|
| 870 |
+
"learning_rate": 3.7352201873796235e-05,
|
| 871 |
+
"loss": 1.6035,
|
| 872 |
+
"step": 384000
|
| 873 |
},
|
| 874 |
{
|
| 875 |
+
"epoch": 12.63,
|
| 876 |
+
"learning_rate": 3.686269709137205e-05,
|
| 877 |
+
"loss": 1.6054,
|
| 878 |
+
"step": 387000
|
|
|
|
|
|
|
|
|
|
|
|
|
| 879 |
},
|
| 880 |
{
|
| 881 |
+
"epoch": 12.73,
|
| 882 |
+
"learning_rate": 3.637335553161623e-05,
|
| 883 |
+
"loss": 1.6055,
|
| 884 |
+
"step": 390000
|
| 885 |
},
|
| 886 |
{
|
| 887 |
+
"epoch": 12.83,
|
| 888 |
+
"learning_rate": 3.588385074919205e-05,
|
| 889 |
+
"loss": 1.6057,
|
| 890 |
+
"step": 393000
|
| 891 |
},
|
| 892 |
{
|
| 893 |
+
"epoch": 12.93,
|
| 894 |
+
"learning_rate": 3.539434596676787e-05,
|
| 895 |
+
"loss": 1.6061,
|
| 896 |
+
"step": 396000
|
| 897 |
},
|
| 898 |
{
|
| 899 |
+
"epoch": 13.0,
|
| 900 |
+
"eval_loss": 1.6634231805801392,
|
| 901 |
+
"eval_runtime": 19.238,
|
| 902 |
+
"eval_samples_per_second": 1534.564,
|
| 903 |
+
"eval_steps_per_second": 9.616,
|
| 904 |
+
"step": 398229
|
| 905 |
},
|
| 906 |
{
|
| 907 |
+
"epoch": 13.03,
|
| 908 |
+
"learning_rate": 3.4905004407012046e-05,
|
| 909 |
+
"loss": 1.5995,
|
| 910 |
+
"step": 399000
|
| 911 |
},
|
| 912 |
{
|
| 913 |
+
"epoch": 13.12,
|
| 914 |
+
"learning_rate": 3.4415499624587865e-05,
|
| 915 |
+
"loss": 1.5849,
|
| 916 |
+
"step": 402000
|
| 917 |
},
|
| 918 |
{
|
| 919 |
+
"epoch": 13.22,
|
| 920 |
+
"learning_rate": 3.392615806483205e-05,
|
| 921 |
+
"loss": 1.5894,
|
| 922 |
+
"step": 405000
|
| 923 |
},
|
| 924 |
{
|
| 925 |
+
"epoch": 13.32,
|
| 926 |
+
"learning_rate": 3.343665328240786e-05,
|
| 927 |
+
"loss": 1.5914,
|
| 928 |
+
"step": 408000
|
| 929 |
},
|
| 930 |
{
|
| 931 |
+
"epoch": 13.42,
|
| 932 |
+
"learning_rate": 3.294731172265204e-05,
|
| 933 |
+
"loss": 1.5917,
|
| 934 |
+
"step": 411000
|
| 935 |
},
|
| 936 |
{
|
| 937 |
+
"epoch": 13.51,
|
| 938 |
+
"learning_rate": 3.245780694022786e-05,
|
| 939 |
+
"loss": 1.5933,
|
| 940 |
+
"step": 414000
|
| 941 |
},
|
| 942 |
{
|
| 943 |
+
"epoch": 13.61,
|
| 944 |
+
"learning_rate": 3.196830215780368e-05,
|
| 945 |
+
"loss": 1.5926,
|
| 946 |
+
"step": 417000
|
| 947 |
},
|
| 948 |
{
|
| 949 |
+
"epoch": 13.71,
|
| 950 |
+
"learning_rate": 3.1478960598047855e-05,
|
| 951 |
+
"loss": 1.5956,
|
| 952 |
+
"step": 420000
|
| 953 |
},
|
| 954 |
{
|
| 955 |
+
"epoch": 13.81,
|
| 956 |
+
"learning_rate": 3.0989455815623674e-05,
|
| 957 |
+
"loss": 1.5953,
|
| 958 |
+
"step": 423000
|
| 959 |
},
|
| 960 |
{
|
| 961 |
+
"epoch": 13.91,
|
| 962 |
+
"learning_rate": 3.0500114255867855e-05,
|
| 963 |
+
"loss": 1.5971,
|
| 964 |
+
"step": 426000
|
| 965 |
},
|
| 966 |
{
|
| 967 |
+
"epoch": 14.0,
|
| 968 |
+
"eval_loss": 1.6542909145355225,
|
| 969 |
+
"eval_runtime": 19.1669,
|
| 970 |
+
"eval_samples_per_second": 1540.259,
|
| 971 |
+
"eval_steps_per_second": 9.652,
|
| 972 |
+
"step": 428862
|
| 973 |
},
|
| 974 |
{
|
| 975 |
+
"epoch": 14.0,
|
| 976 |
+
"learning_rate": 3.0010609473443674e-05,
|
| 977 |
+
"loss": 1.5959,
|
| 978 |
+
"step": 429000
|
| 979 |
},
|
| 980 |
{
|
| 981 |
+
"epoch": 14.1,
|
| 982 |
+
"learning_rate": 2.9521267913687855e-05,
|
| 983 |
+
"loss": 1.5752,
|
| 984 |
+
"step": 432000
|
| 985 |
},
|
| 986 |
{
|
| 987 |
+
"epoch": 14.2,
|
| 988 |
+
"learning_rate": 2.9031763131263674e-05,
|
| 989 |
+
"loss": 1.5775,
|
| 990 |
+
"step": 435000
|
| 991 |
},
|
| 992 |
{
|
| 993 |
+
"epoch": 14.3,
|
| 994 |
+
"learning_rate": 2.854225834883949e-05,
|
| 995 |
+
"loss": 1.5814,
|
| 996 |
+
"step": 438000
|
|
|
|
|
|
|
|
|
|
|
|
|
| 997 |
},
|
| 998 |
{
|
| 999 |
+
"epoch": 14.4,
|
| 1000 |
+
"learning_rate": 2.8052916789083673e-05,
|
| 1001 |
+
"loss": 1.5814,
|
| 1002 |
+
"step": 441000
|
| 1003 |
},
|
| 1004 |
{
|
| 1005 |
+
"epoch": 14.49,
|
| 1006 |
+
"learning_rate": 2.7563412006659482e-05,
|
| 1007 |
+
"loss": 1.5837,
|
| 1008 |
+
"step": 444000
|
| 1009 |
+
},
|
| 1010 |
+
{
|
| 1011 |
+
"epoch": 14.59,
|
| 1012 |
+
"learning_rate": 2.7074070446903667e-05,
|
| 1013 |
+
"loss": 1.585,
|
| 1014 |
+
"step": 447000
|
| 1015 |
+
},
|
| 1016 |
+
{
|
| 1017 |
+
"epoch": 14.69,
|
| 1018 |
+
"learning_rate": 2.6584565664479482e-05,
|
| 1019 |
+
"loss": 1.5868,
|
| 1020 |
+
"step": 450000
|
| 1021 |
+
},
|
| 1022 |
+
{
|
| 1023 |
+
"epoch": 14.79,
|
| 1024 |
+
"learning_rate": 2.60950608820553e-05,
|
| 1025 |
+
"loss": 1.5854,
|
| 1026 |
+
"step": 453000
|
| 1027 |
},
|
| 1028 |
{
|
| 1029 |
+
"epoch": 14.89,
|
| 1030 |
+
"learning_rate": 2.5605719322299482e-05,
|
| 1031 |
"loss": 1.5864,
|
| 1032 |
+
"step": 456000
|
| 1033 |
},
|
| 1034 |
{
|
| 1035 |
+
"epoch": 14.98,
|
| 1036 |
+
"learning_rate": 2.51162145398753e-05,
|
| 1037 |
+
"loss": 1.5867,
|
| 1038 |
+
"step": 459000
|
| 1039 |
},
|
| 1040 |
{
|
| 1041 |
+
"epoch": 15.0,
|
| 1042 |
+
"eval_loss": 1.6488285064697266,
|
| 1043 |
+
"eval_runtime": 19.1177,
|
| 1044 |
+
"eval_samples_per_second": 1544.224,
|
| 1045 |
+
"eval_steps_per_second": 9.677,
|
| 1046 |
+
"step": 459495
|
| 1047 |
},
|
| 1048 |
{
|
| 1049 |
+
"epoch": 15.08,
|
| 1050 |
+
"learning_rate": 2.4626709757451116e-05,
|
| 1051 |
+
"loss": 1.5695,
|
| 1052 |
+
"step": 462000
|
| 1053 |
},
|
| 1054 |
{
|
| 1055 |
+
"epoch": 15.18,
|
| 1056 |
+
"learning_rate": 2.4137368197695297e-05,
|
| 1057 |
+
"loss": 1.5714,
|
| 1058 |
+
"step": 465000
|
| 1059 |
},
|
| 1060 |
{
|
| 1061 |
+
"epoch": 15.28,
|
| 1062 |
+
"learning_rate": 2.3647863415271113e-05,
|
| 1063 |
+
"loss": 1.5721,
|
| 1064 |
+
"step": 468000
|
| 1065 |
},
|
| 1066 |
{
|
| 1067 |
+
"epoch": 15.38,
|
| 1068 |
+
"learning_rate": 2.315835863284693e-05,
|
| 1069 |
+
"loss": 1.5729,
|
| 1070 |
+
"step": 471000
|
| 1071 |
},
|
| 1072 |
{
|
| 1073 |
+
"epoch": 15.47,
|
| 1074 |
+
"learning_rate": 2.2669017073091113e-05,
|
| 1075 |
+
"loss": 1.5728,
|
| 1076 |
+
"step": 474000
|
| 1077 |
},
|
| 1078 |
{
|
| 1079 |
+
"epoch": 15.57,
|
| 1080 |
+
"learning_rate": 2.2179512290666928e-05,
|
| 1081 |
+
"loss": 1.5739,
|
| 1082 |
+
"step": 477000
|
| 1083 |
},
|
| 1084 |
{
|
| 1085 |
+
"epoch": 15.67,
|
| 1086 |
+
"learning_rate": 2.1690007508242746e-05,
|
| 1087 |
+
"loss": 1.5756,
|
| 1088 |
+
"step": 480000
|
| 1089 |
},
|
| 1090 |
{
|
| 1091 |
+
"epoch": 15.77,
|
| 1092 |
+
"learning_rate": 2.1200665948486928e-05,
|
| 1093 |
+
"loss": 1.5774,
|
| 1094 |
+
"step": 483000
|
| 1095 |
},
|
| 1096 |
{
|
| 1097 |
+
"epoch": 15.87,
|
| 1098 |
+
"learning_rate": 2.0711161166062743e-05,
|
| 1099 |
+
"loss": 1.5772,
|
| 1100 |
+
"step": 486000
|
| 1101 |
},
|
| 1102 |
{
|
| 1103 |
+
"epoch": 15.96,
|
| 1104 |
+
"learning_rate": 2.022165638363856e-05,
|
| 1105 |
+
"loss": 1.5781,
|
| 1106 |
+
"step": 489000
|
| 1107 |
},
|
| 1108 |
{
|
| 1109 |
+
"epoch": 16.0,
|
| 1110 |
+
"eval_loss": 1.6446890830993652,
|
| 1111 |
+
"eval_runtime": 19.0262,
|
| 1112 |
+
"eval_samples_per_second": 1551.652,
|
| 1113 |
+
"eval_steps_per_second": 9.723,
|
| 1114 |
+
"step": 490128
|
| 1115 |
},
|
| 1116 |
{
|
| 1117 |
+
"epoch": 16.06,
|
| 1118 |
+
"learning_rate": 1.9732314823882743e-05,
|
| 1119 |
+
"loss": 1.5652,
|
| 1120 |
+
"step": 492000
|
| 1121 |
},
|
| 1122 |
{
|
| 1123 |
+
"epoch": 16.16,
|
| 1124 |
+
"learning_rate": 1.924281004145856e-05,
|
| 1125 |
+
"loss": 1.5612,
|
| 1126 |
+
"step": 495000
|
| 1127 |
},
|
| 1128 |
{
|
| 1129 |
+
"epoch": 16.26,
|
| 1130 |
+
"learning_rate": 1.8753305259034377e-05,
|
| 1131 |
+
"loss": 1.5634,
|
| 1132 |
+
"step": 498000
|
| 1133 |
},
|
| 1134 |
{
|
| 1135 |
+
"epoch": 16.35,
|
| 1136 |
+
"learning_rate": 1.8263800476610192e-05,
|
| 1137 |
+
"loss": 1.5648,
|
| 1138 |
+
"step": 501000
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1139 |
},
|
| 1140 |
{
|
| 1141 |
+
"epoch": 16.45,
|
| 1142 |
+
"learning_rate": 1.7774458916854374e-05,
|
| 1143 |
+
"loss": 1.5664,
|
| 1144 |
+
"step": 504000
|
| 1145 |
},
|
| 1146 |
{
|
| 1147 |
+
"epoch": 16.55,
|
| 1148 |
+
"learning_rate": 1.728495413443019e-05,
|
| 1149 |
+
"loss": 1.5656,
|
| 1150 |
+
"step": 507000
|
| 1151 |
},
|
| 1152 |
{
|
| 1153 |
+
"epoch": 16.65,
|
| 1154 |
+
"learning_rate": 1.679561257467437e-05,
|
| 1155 |
+
"loss": 1.5676,
|
| 1156 |
+
"step": 510000
|
| 1157 |
},
|
| 1158 |
{
|
| 1159 |
+
"epoch": 16.75,
|
| 1160 |
+
"learning_rate": 1.630610779225019e-05,
|
| 1161 |
+
"loss": 1.566,
|
| 1162 |
+
"step": 513000
|
| 1163 |
},
|
| 1164 |
{
|
| 1165 |
+
"epoch": 16.84,
|
| 1166 |
+
"learning_rate": 1.5816603009826008e-05,
|
| 1167 |
+
"loss": 1.5691,
|
| 1168 |
+
"step": 516000
|
| 1169 |
},
|
| 1170 |
{
|
| 1171 |
+
"epoch": 16.94,
|
| 1172 |
+
"learning_rate": 1.5327098227401823e-05,
|
| 1173 |
+
"loss": 1.5684,
|
| 1174 |
+
"step": 519000
|
| 1175 |
},
|
| 1176 |
{
|
| 1177 |
+
"epoch": 17.0,
|
| 1178 |
+
"eval_loss": 1.6387931108474731,
|
| 1179 |
+
"eval_runtime": 19.1639,
|
| 1180 |
+
"eval_samples_per_second": 1540.501,
|
| 1181 |
+
"eval_steps_per_second": 9.654,
|
| 1182 |
+
"step": 520761
|
| 1183 |
},
|
| 1184 |
{
|
| 1185 |
+
"epoch": 17.04,
|
| 1186 |
+
"learning_rate": 1.4837756667646002e-05,
|
| 1187 |
+
"loss": 1.5616,
|
| 1188 |
+
"step": 522000
|
| 1189 |
},
|
| 1190 |
{
|
| 1191 |
+
"epoch": 17.14,
|
| 1192 |
+
"learning_rate": 1.434825188522182e-05,
|
| 1193 |
+
"loss": 1.5545,
|
| 1194 |
+
"step": 525000
|
| 1195 |
},
|
| 1196 |
{
|
| 1197 |
+
"epoch": 17.24,
|
| 1198 |
+
"learning_rate": 1.3858747102797636e-05,
|
| 1199 |
+
"loss": 1.5551,
|
| 1200 |
+
"step": 528000
|
| 1201 |
},
|
| 1202 |
{
|
| 1203 |
+
"epoch": 17.33,
|
| 1204 |
+
"learning_rate": 1.3369405543041818e-05,
|
| 1205 |
+
"loss": 1.5558,
|
| 1206 |
+
"step": 531000
|
| 1207 |
},
|
| 1208 |
{
|
| 1209 |
+
"epoch": 17.43,
|
| 1210 |
+
"learning_rate": 1.2879900760617636e-05,
|
| 1211 |
+
"loss": 1.5587,
|
| 1212 |
+
"step": 534000
|
| 1213 |
},
|
| 1214 |
{
|
| 1215 |
+
"epoch": 17.53,
|
| 1216 |
+
"learning_rate": 1.2390559200861816e-05,
|
| 1217 |
+
"loss": 1.5585,
|
| 1218 |
+
"step": 537000
|
| 1219 |
},
|
| 1220 |
{
|
| 1221 |
+
"epoch": 17.63,
|
| 1222 |
+
"learning_rate": 1.1901054418437633e-05,
|
| 1223 |
+
"loss": 1.5579,
|
| 1224 |
+
"step": 540000
|
| 1225 |
},
|
| 1226 |
{
|
| 1227 |
+
"epoch": 17.73,
|
| 1228 |
+
"learning_rate": 1.141154963601345e-05,
|
| 1229 |
+
"loss": 1.5586,
|
| 1230 |
+
"step": 543000
|
| 1231 |
},
|
| 1232 |
{
|
| 1233 |
+
"epoch": 17.82,
|
| 1234 |
+
"learning_rate": 1.0922208076257631e-05,
|
| 1235 |
+
"loss": 1.559,
|
| 1236 |
+
"step": 546000
|
| 1237 |
},
|
| 1238 |
{
|
| 1239 |
+
"epoch": 17.92,
|
| 1240 |
+
"learning_rate": 1.0432703293833448e-05,
|
| 1241 |
+
"loss": 1.5597,
|
| 1242 |
+
"step": 549000
|
| 1243 |
},
|
| 1244 |
{
|
| 1245 |
+
"epoch": 18.0,
|
| 1246 |
+
"eval_loss": 1.6415975093841553,
|
| 1247 |
+
"eval_runtime": 19.1825,
|
| 1248 |
+
"eval_samples_per_second": 1539.008,
|
| 1249 |
+
"eval_steps_per_second": 9.644,
|
| 1250 |
+
"step": 551394
|
| 1251 |
},
|
| 1252 |
{
|
| 1253 |
+
"epoch": 18.02,
|
| 1254 |
+
"learning_rate": 9.94336173407763e-06,
|
| 1255 |
+
"loss": 1.5579,
|
| 1256 |
+
"step": 552000
|
| 1257 |
},
|
| 1258 |
{
|
| 1259 |
+
"epoch": 18.12,
|
| 1260 |
+
"learning_rate": 9.453856951653447e-06,
|
| 1261 |
+
"loss": 1.5465,
|
| 1262 |
+
"step": 555000
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1263 |
},
|
| 1264 |
{
|
| 1265 |
+
"epoch": 18.22,
|
| 1266 |
+
"learning_rate": 8.964352169229264e-06,
|
| 1267 |
+
"loss": 1.5491,
|
| 1268 |
+
"step": 558000
|
| 1269 |
},
|
| 1270 |
{
|
| 1271 |
+
"epoch": 18.31,
|
| 1272 |
+
"learning_rate": 8.475010609473443e-06,
|
| 1273 |
+
"loss": 1.5495,
|
| 1274 |
+
"step": 561000
|
| 1275 |
},
|
| 1276 |
{
|
| 1277 |
+
"epoch": 18.41,
|
| 1278 |
+
"learning_rate": 7.985505827049262e-06,
|
| 1279 |
+
"loss": 1.5498,
|
| 1280 |
+
"step": 564000
|
| 1281 |
},
|
| 1282 |
{
|
| 1283 |
+
"epoch": 18.51,
|
| 1284 |
+
"learning_rate": 7.496001044625078e-06,
|
| 1285 |
+
"loss": 1.5514,
|
| 1286 |
+
"step": 567000
|
| 1287 |
},
|
| 1288 |
{
|
| 1289 |
+
"epoch": 18.61,
|
| 1290 |
+
"learning_rate": 7.006659484869258e-06,
|
| 1291 |
+
"loss": 1.5508,
|
| 1292 |
+
"step": 570000
|
| 1293 |
},
|
| 1294 |
{
|
| 1295 |
+
"epoch": 18.71,
|
| 1296 |
+
"learning_rate": 6.517154702445076e-06,
|
| 1297 |
+
"loss": 1.5516,
|
| 1298 |
+
"step": 573000
|
| 1299 |
},
|
| 1300 |
{
|
| 1301 |
+
"epoch": 18.8,
|
| 1302 |
+
"learning_rate": 6.027649920020892e-06,
|
| 1303 |
+
"loss": 1.5508,
|
| 1304 |
+
"step": 576000
|
| 1305 |
},
|
| 1306 |
{
|
| 1307 |
+
"epoch": 18.9,
|
| 1308 |
+
"learning_rate": 5.538308360265074e-06,
|
| 1309 |
+
"loss": 1.5515,
|
| 1310 |
+
"step": 579000
|
| 1311 |
},
|
| 1312 |
{
|
| 1313 |
+
"epoch": 19.0,
|
| 1314 |
+
"learning_rate": 5.048803577840891e-06,
|
| 1315 |
+
"loss": 1.5521,
|
| 1316 |
+
"step": 582000
|
| 1317 |
},
|
| 1318 |
{
|
| 1319 |
+
"epoch": 19.0,
|
| 1320 |
+
"eval_loss": 1.6370400190353394,
|
| 1321 |
+
"eval_runtime": 19.1163,
|
| 1322 |
+
"eval_samples_per_second": 1544.337,
|
| 1323 |
+
"eval_steps_per_second": 9.678,
|
| 1324 |
+
"step": 582027
|
| 1325 |
},
|
| 1326 |
{
|
| 1327 |
+
"epoch": 19.1,
|
| 1328 |
+
"learning_rate": 4.559298795416708e-06,
|
| 1329 |
+
"loss": 1.5413,
|
| 1330 |
+
"step": 585000
|
| 1331 |
},
|
| 1332 |
{
|
| 1333 |
+
"epoch": 19.19,
|
| 1334 |
+
"learning_rate": 4.069957235660889e-06,
|
| 1335 |
+
"loss": 1.5435,
|
| 1336 |
+
"step": 588000
|
| 1337 |
},
|
| 1338 |
{
|
| 1339 |
+
"epoch": 19.29,
|
| 1340 |
+
"learning_rate": 3.580452453236706e-06,
|
| 1341 |
+
"loss": 1.5432,
|
| 1342 |
+
"step": 591000
|
| 1343 |
},
|
| 1344 |
{
|
| 1345 |
+
"epoch": 19.39,
|
| 1346 |
+
"learning_rate": 3.091110893480887e-06,
|
| 1347 |
+
"loss": 1.5437,
|
| 1348 |
+
"step": 594000
|
| 1349 |
},
|
| 1350 |
{
|
| 1351 |
+
"epoch": 19.49,
|
| 1352 |
+
"learning_rate": 2.6016061110567034e-06,
|
| 1353 |
+
"loss": 1.5431,
|
| 1354 |
+
"step": 597000
|
| 1355 |
},
|
| 1356 |
{
|
| 1357 |
+
"epoch": 19.59,
|
| 1358 |
+
"learning_rate": 2.1121013286325204e-06,
|
| 1359 |
+
"loss": 1.5431,
|
| 1360 |
+
"step": 600000
|
| 1361 |
},
|
| 1362 |
{
|
| 1363 |
+
"epoch": 19.68,
|
| 1364 |
+
"learning_rate": 1.6225965462083374e-06,
|
| 1365 |
+
"loss": 1.5441,
|
| 1366 |
+
"step": 603000
|
| 1367 |
},
|
| 1368 |
{
|
| 1369 |
+
"epoch": 19.78,
|
| 1370 |
+
"learning_rate": 1.1332549864525185e-06,
|
| 1371 |
+
"loss": 1.544,
|
| 1372 |
+
"step": 606000
|
| 1373 |
},
|
| 1374 |
{
|
| 1375 |
+
"epoch": 19.88,
|
| 1376 |
+
"learning_rate": 6.437502040283355e-07,
|
| 1377 |
+
"loss": 1.5469,
|
| 1378 |
+
"step": 609000
|
| 1379 |
},
|
| 1380 |
{
|
| 1381 |
+
"epoch": 19.98,
|
| 1382 |
+
"learning_rate": 1.5440864427251657e-07,
|
| 1383 |
+
"loss": 1.5438,
|
| 1384 |
+
"step": 612000
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1385 |
},
|
| 1386 |
{
|
| 1387 |
+
"epoch": 20.0,
|
| 1388 |
+
"eval_loss": 1.636548638343811,
|
| 1389 |
+
"eval_runtime": 19.1335,
|
| 1390 |
+
"eval_samples_per_second": 1542.949,
|
| 1391 |
+
"eval_steps_per_second": 9.669,
|
| 1392 |
+
"step": 612660
|
| 1393 |
+
},
|
| 1394 |
+
{
|
| 1395 |
+
"epoch": 20.0,
|
| 1396 |
+
"step": 612660,
|
| 1397 |
+
"total_flos": 3.3229272051886326e+18,
|
| 1398 |
+
"train_loss": 1.7127611959194204,
|
| 1399 |
+
"train_runtime": 370998.644,
|
| 1400 |
+
"train_samples_per_second": 528.445,
|
| 1401 |
+
"train_steps_per_second": 1.651
|
| 1402 |
}
|
| 1403 |
],
|
| 1404 |
+
"max_steps": 612660,
|
| 1405 |
+
"num_train_epochs": 20,
|
| 1406 |
+
"total_flos": 3.3229272051886326e+18,
|
| 1407 |
"trial_name": null,
|
| 1408 |
"trial_params": null
|
| 1409 |
}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d220a222eaa112c7526da4c022bc47671ef21a5434ed8334421ef750c4071bc4
|
| 3 |
+
size 3183
|