Upload folder using huggingface_hub
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- README.md +56 -1
- all_results.json +15 -0
- checkpoint-10000/config.json +26 -0
- checkpoint-10000/generation_config.json +10 -0
- checkpoint-10000/optimizer.pt +3 -0
- checkpoint-10000/pytorch_model.bin +3 -0
- checkpoint-10000/rng_state.pth +3 -0
- checkpoint-10000/scheduler.pt +3 -0
- checkpoint-10000/special_tokens_map.json +23 -0
- checkpoint-10000/tokenizer.json +0 -0
- checkpoint-10000/tokenizer.model +3 -0
- checkpoint-10000/tokenizer_config.json +34 -0
- checkpoint-10000/trainer_state.json +1219 -0
- checkpoint-10000/training_args.bin +3 -0
- checkpoint-2500/config.json +26 -0
- checkpoint-2500/generation_config.json +10 -0
- checkpoint-2500/optimizer.pt +3 -0
- checkpoint-2500/pytorch_model.bin +3 -0
- checkpoint-2500/rng_state.pth +3 -0
- checkpoint-2500/scheduler.pt +3 -0
- checkpoint-2500/special_tokens_map.json +23 -0
- checkpoint-2500/tokenizer.json +0 -0
- checkpoint-2500/tokenizer.model +3 -0
- checkpoint-2500/tokenizer_config.json +34 -0
- checkpoint-2500/trainer_state.json +319 -0
- checkpoint-2500/training_args.bin +3 -0
- checkpoint-5000/config.json +26 -0
- checkpoint-5000/generation_config.json +10 -0
- checkpoint-5000/optimizer.pt +3 -0
- checkpoint-5000/pytorch_model.bin +3 -0
- checkpoint-5000/rng_state.pth +3 -0
- checkpoint-5000/scheduler.pt +3 -0
- checkpoint-5000/special_tokens_map.json +23 -0
- checkpoint-5000/tokenizer.json +0 -0
- checkpoint-5000/tokenizer.model +3 -0
- checkpoint-5000/tokenizer_config.json +34 -0
- checkpoint-5000/trainer_state.json +619 -0
- checkpoint-5000/training_args.bin +3 -0
- checkpoint-7500/config.json +26 -0
- checkpoint-7500/generation_config.json +10 -0
- checkpoint-7500/optimizer.pt +3 -0
- checkpoint-7500/pytorch_model.bin +3 -0
- checkpoint-7500/rng_state.pth +3 -0
- checkpoint-7500/scheduler.pt +3 -0
- checkpoint-7500/special_tokens_map.json +23 -0
- checkpoint-7500/tokenizer.json +0 -0
- checkpoint-7500/tokenizer.model +3 -0
- checkpoint-7500/tokenizer_config.json +34 -0
- checkpoint-7500/trainer_state.json +919 -0
- checkpoint-7500/training_args.bin +3 -0
README.md
CHANGED
|
@@ -1,3 +1,58 @@
|
|
| 1 |
---
|
| 2 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
+
base_model: ./model
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
metrics:
|
| 6 |
+
- accuracy
|
| 7 |
+
model-index:
|
| 8 |
+
- name: core2
|
| 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 |
+
# core2
|
| 16 |
+
|
| 17 |
+
This model is a fine-tuned version of [./model](https://huggingface.co/./model) on an unknown dataset.
|
| 18 |
+
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 2.5063
|
| 20 |
+
- Accuracy: 0.4398
|
| 21 |
+
|
| 22 |
+
## Model description
|
| 23 |
+
|
| 24 |
+
More information needed
|
| 25 |
+
|
| 26 |
+
## Intended uses & limitations
|
| 27 |
+
|
| 28 |
+
More information needed
|
| 29 |
+
|
| 30 |
+
## Training and evaluation data
|
| 31 |
+
|
| 32 |
+
More information needed
|
| 33 |
+
|
| 34 |
+
## Training procedure
|
| 35 |
+
|
| 36 |
+
### Training hyperparameters
|
| 37 |
+
|
| 38 |
+
The following hyperparameters were used during training:
|
| 39 |
+
- learning_rate: 0.0005
|
| 40 |
+
- train_batch_size: 1
|
| 41 |
+
- eval_batch_size: 8
|
| 42 |
+
- seed: 42
|
| 43 |
+
- gradient_accumulation_steps: 32
|
| 44 |
+
- total_train_batch_size: 32
|
| 45 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 46 |
+
- lr_scheduler_type: linear
|
| 47 |
+
- num_epochs: 2.0
|
| 48 |
+
|
| 49 |
+
### Training results
|
| 50 |
+
|
| 51 |
+
|
| 52 |
+
|
| 53 |
+
### Framework versions
|
| 54 |
+
|
| 55 |
+
- Transformers 4.34.0.dev0
|
| 56 |
+
- Pytorch 2.0.1+cu117
|
| 57 |
+
- Datasets 2.14.5
|
| 58 |
+
- Tokenizers 0.13.3
|
all_results.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.0,
|
| 3 |
+
"eval_accuracy": 0.4398296543832928,
|
| 4 |
+
"eval_loss": 2.506345748901367,
|
| 5 |
+
"eval_runtime": 1.8254,
|
| 6 |
+
"eval_samples": 129,
|
| 7 |
+
"eval_samples_per_second": 70.668,
|
| 8 |
+
"eval_steps_per_second": 9.313,
|
| 9 |
+
"perplexity": 12.260046813591257,
|
| 10 |
+
"train_loss": 2.7760973889075786,
|
| 11 |
+
"train_runtime": 9463.0789,
|
| 12 |
+
"train_samples": 175957,
|
| 13 |
+
"train_samples_per_second": 37.188,
|
| 14 |
+
"train_steps_per_second": 1.162
|
| 15 |
+
}
|
checkpoint-10000/config.json
ADDED
|
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "./model",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"LlamaForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"bos_token_id": 1,
|
| 7 |
+
"eos_token_id": 2,
|
| 8 |
+
"hidden_act": "silu",
|
| 9 |
+
"hidden_size": 4096,
|
| 10 |
+
"initializer_range": 0.02,
|
| 11 |
+
"intermediate_size": 11008,
|
| 12 |
+
"max_position_embeddings": 4096,
|
| 13 |
+
"model_type": "llama",
|
| 14 |
+
"num_attention_heads": 32,
|
| 15 |
+
"num_hidden_layers": 1,
|
| 16 |
+
"num_key_value_heads": 32,
|
| 17 |
+
"pretraining_tp": 1,
|
| 18 |
+
"rms_norm_eps": 1e-06,
|
| 19 |
+
"rope_scaling": null,
|
| 20 |
+
"rope_theta": 10000.0,
|
| 21 |
+
"tie_word_embeddings": false,
|
| 22 |
+
"torch_dtype": "bfloat16",
|
| 23 |
+
"transformers_version": "4.34.0.dev0",
|
| 24 |
+
"use_cache": true,
|
| 25 |
+
"vocab_size": 32000
|
| 26 |
+
}
|
checkpoint-10000/generation_config.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 1,
|
| 3 |
+
"do_sample": true,
|
| 4 |
+
"eos_token_id": 2,
|
| 5 |
+
"max_length": 4096,
|
| 6 |
+
"pad_token_id": 0,
|
| 7 |
+
"temperature": 0.6,
|
| 8 |
+
"top_p": 0.9,
|
| 9 |
+
"transformers_version": "4.34.0.dev0"
|
| 10 |
+
}
|
checkpoint-10000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:41076e3acef18331ccb4b67d45882cb5e570fbff15924546fdf459b34c982a84
|
| 3 |
+
size 1858136133
|
checkpoint-10000/pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:88c8c9e828c5523a3a2c07b1e2ed4ca85a5960252aa9c6df1cfd4ede7b97b9a5
|
| 3 |
+
size 929067029
|
checkpoint-10000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:972139d83957a9cf2600cb6eeca17287d7a5377c33a53500ae7e13fe830ad36b
|
| 3 |
+
size 14575
|
checkpoint-10000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:daaefb409ebfffab618f0f30bfe53505107cc238d04f5c370bb638f9182e397e
|
| 3 |
+
size 627
|
checkpoint-10000/special_tokens_map.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "</s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"unk_token": {
|
| 17 |
+
"content": "<unk>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
}
|
| 23 |
+
}
|
checkpoint-10000/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-10000/tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
| 3 |
+
size 499723
|
checkpoint-10000/tokenizer_config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"__type": "AddedToken",
|
| 4 |
+
"content": "<s>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false
|
| 9 |
+
},
|
| 10 |
+
"clean_up_tokenization_spaces": false,
|
| 11 |
+
"eos_token": {
|
| 12 |
+
"__type": "AddedToken",
|
| 13 |
+
"content": "</s>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": false,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false
|
| 18 |
+
},
|
| 19 |
+
"legacy": false,
|
| 20 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 21 |
+
"pad_token": null,
|
| 22 |
+
"padding_side": "right",
|
| 23 |
+
"sp_model_kwargs": {},
|
| 24 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 25 |
+
"unk_token": {
|
| 26 |
+
"__type": "AddedToken",
|
| 27 |
+
"content": "<unk>",
|
| 28 |
+
"lstrip": false,
|
| 29 |
+
"normalized": false,
|
| 30 |
+
"rstrip": false,
|
| 31 |
+
"single_word": false
|
| 32 |
+
},
|
| 33 |
+
"use_default_system_prompt": true
|
| 34 |
+
}
|
checkpoint-10000/trainer_state.json
ADDED
|
@@ -0,0 +1,1219 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.8186261416141445,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 10000,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.01,
|
| 13 |
+
"learning_rate": 0.0004977264459803565,
|
| 14 |
+
"loss": 5.874,
|
| 15 |
+
"step": 50
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.02,
|
| 19 |
+
"learning_rate": 0.0004954528919607129,
|
| 20 |
+
"loss": 4.0765,
|
| 21 |
+
"step": 100
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.03,
|
| 25 |
+
"learning_rate": 0.0004931793379410695,
|
| 26 |
+
"loss": 3.7752,
|
| 27 |
+
"step": 150
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.04,
|
| 31 |
+
"learning_rate": 0.000490905783921426,
|
| 32 |
+
"loss": 3.6357,
|
| 33 |
+
"step": 200
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.05,
|
| 37 |
+
"learning_rate": 0.0004886322299017824,
|
| 38 |
+
"loss": 3.5374,
|
| 39 |
+
"step": 250
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.05,
|
| 43 |
+
"learning_rate": 0.00048635867588213893,
|
| 44 |
+
"loss": 3.4875,
|
| 45 |
+
"step": 300
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.06,
|
| 49 |
+
"learning_rate": 0.0004840851218624955,
|
| 50 |
+
"loss": 3.411,
|
| 51 |
+
"step": 350
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.07,
|
| 55 |
+
"learning_rate": 0.00048181156784285196,
|
| 56 |
+
"loss": 3.3791,
|
| 57 |
+
"step": 400
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.08,
|
| 61 |
+
"learning_rate": 0.0004795380138232084,
|
| 62 |
+
"loss": 3.3377,
|
| 63 |
+
"step": 450
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.09,
|
| 67 |
+
"learning_rate": 0.00047726445980356494,
|
| 68 |
+
"loss": 3.292,
|
| 69 |
+
"step": 500
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.1,
|
| 73 |
+
"learning_rate": 0.00047499090578392145,
|
| 74 |
+
"loss": 3.2765,
|
| 75 |
+
"step": 550
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.11,
|
| 79 |
+
"learning_rate": 0.0004727173517642779,
|
| 80 |
+
"loss": 3.2584,
|
| 81 |
+
"step": 600
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.12,
|
| 85 |
+
"learning_rate": 0.0004704437977446344,
|
| 86 |
+
"loss": 3.2319,
|
| 87 |
+
"step": 650
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.13,
|
| 91 |
+
"learning_rate": 0.0004681702437249909,
|
| 92 |
+
"loss": 3.2021,
|
| 93 |
+
"step": 700
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.14,
|
| 97 |
+
"learning_rate": 0.00046589668970534745,
|
| 98 |
+
"loss": 3.1816,
|
| 99 |
+
"step": 750
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.15,
|
| 103 |
+
"learning_rate": 0.0004636231356857039,
|
| 104 |
+
"loss": 3.165,
|
| 105 |
+
"step": 800
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.15,
|
| 109 |
+
"learning_rate": 0.0004613495816660604,
|
| 110 |
+
"loss": 3.1436,
|
| 111 |
+
"step": 850
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 0.16,
|
| 115 |
+
"learning_rate": 0.0004590760276464169,
|
| 116 |
+
"loss": 3.1491,
|
| 117 |
+
"step": 900
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 0.17,
|
| 121 |
+
"learning_rate": 0.0004568024736267734,
|
| 122 |
+
"loss": 3.1343,
|
| 123 |
+
"step": 950
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.18,
|
| 127 |
+
"learning_rate": 0.00045452891960712986,
|
| 128 |
+
"loss": 3.1208,
|
| 129 |
+
"step": 1000
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.19,
|
| 133 |
+
"learning_rate": 0.0004522553655874864,
|
| 134 |
+
"loss": 3.0954,
|
| 135 |
+
"step": 1050
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.2,
|
| 139 |
+
"learning_rate": 0.00044998181156784284,
|
| 140 |
+
"loss": 3.0963,
|
| 141 |
+
"step": 1100
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 0.21,
|
| 145 |
+
"learning_rate": 0.00044770825754819935,
|
| 146 |
+
"loss": 3.098,
|
| 147 |
+
"step": 1150
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 0.22,
|
| 151 |
+
"learning_rate": 0.00044543470352855586,
|
| 152 |
+
"loss": 3.0695,
|
| 153 |
+
"step": 1200
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 0.23,
|
| 157 |
+
"learning_rate": 0.0004431611495089123,
|
| 158 |
+
"loss": 3.0785,
|
| 159 |
+
"step": 1250
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.24,
|
| 163 |
+
"learning_rate": 0.00044088759548926884,
|
| 164 |
+
"loss": 3.0524,
|
| 165 |
+
"step": 1300
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 0.25,
|
| 169 |
+
"learning_rate": 0.0004386140414696253,
|
| 170 |
+
"loss": 3.0275,
|
| 171 |
+
"step": 1350
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.25,
|
| 175 |
+
"learning_rate": 0.0004363404874499818,
|
| 176 |
+
"loss": 3.0368,
|
| 177 |
+
"step": 1400
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.26,
|
| 181 |
+
"learning_rate": 0.00043406693343033833,
|
| 182 |
+
"loss": 3.0177,
|
| 183 |
+
"step": 1450
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 0.27,
|
| 187 |
+
"learning_rate": 0.0004317933794106948,
|
| 188 |
+
"loss": 3.0117,
|
| 189 |
+
"step": 1500
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 0.28,
|
| 193 |
+
"learning_rate": 0.0004295198253910513,
|
| 194 |
+
"loss": 3.0023,
|
| 195 |
+
"step": 1550
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 0.29,
|
| 199 |
+
"learning_rate": 0.0004272462713714078,
|
| 200 |
+
"loss": 2.9814,
|
| 201 |
+
"step": 1600
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 0.3,
|
| 205 |
+
"learning_rate": 0.0004249727173517643,
|
| 206 |
+
"loss": 2.9867,
|
| 207 |
+
"step": 1650
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 0.31,
|
| 211 |
+
"learning_rate": 0.0004226991633321208,
|
| 212 |
+
"loss": 2.991,
|
| 213 |
+
"step": 1700
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.32,
|
| 217 |
+
"learning_rate": 0.00042042560931247725,
|
| 218 |
+
"loss": 2.9764,
|
| 219 |
+
"step": 1750
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.33,
|
| 223 |
+
"learning_rate": 0.00041815205529283376,
|
| 224 |
+
"loss": 2.9587,
|
| 225 |
+
"step": 1800
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 0.34,
|
| 229 |
+
"learning_rate": 0.0004158785012731903,
|
| 230 |
+
"loss": 2.9651,
|
| 231 |
+
"step": 1850
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 0.35,
|
| 235 |
+
"learning_rate": 0.00041360494725354674,
|
| 236 |
+
"loss": 2.9606,
|
| 237 |
+
"step": 1900
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 0.35,
|
| 241 |
+
"learning_rate": 0.00041133139323390325,
|
| 242 |
+
"loss": 2.9448,
|
| 243 |
+
"step": 1950
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 0.36,
|
| 247 |
+
"learning_rate": 0.00040905783921425977,
|
| 248 |
+
"loss": 2.9585,
|
| 249 |
+
"step": 2000
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 0.37,
|
| 253 |
+
"learning_rate": 0.00040678428519461623,
|
| 254 |
+
"loss": 2.9607,
|
| 255 |
+
"step": 2050
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.38,
|
| 259 |
+
"learning_rate": 0.00040451073117497274,
|
| 260 |
+
"loss": 2.9199,
|
| 261 |
+
"step": 2100
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.39,
|
| 265 |
+
"learning_rate": 0.0004022371771553292,
|
| 266 |
+
"loss": 2.9303,
|
| 267 |
+
"step": 2150
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 0.4,
|
| 271 |
+
"learning_rate": 0.0003999636231356857,
|
| 272 |
+
"loss": 2.9353,
|
| 273 |
+
"step": 2200
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 0.41,
|
| 277 |
+
"learning_rate": 0.00039769006911604223,
|
| 278 |
+
"loss": 2.9123,
|
| 279 |
+
"step": 2250
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 0.42,
|
| 283 |
+
"learning_rate": 0.0003954165150963987,
|
| 284 |
+
"loss": 2.9161,
|
| 285 |
+
"step": 2300
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 0.43,
|
| 289 |
+
"learning_rate": 0.0003931429610767552,
|
| 290 |
+
"loss": 2.9146,
|
| 291 |
+
"step": 2350
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 0.44,
|
| 295 |
+
"learning_rate": 0.00039086940705711167,
|
| 296 |
+
"loss": 2.9086,
|
| 297 |
+
"step": 2400
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.45,
|
| 301 |
+
"learning_rate": 0.0003885958530374682,
|
| 302 |
+
"loss": 2.9094,
|
| 303 |
+
"step": 2450
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.45,
|
| 307 |
+
"learning_rate": 0.0003863222990178247,
|
| 308 |
+
"loss": 2.8968,
|
| 309 |
+
"step": 2500
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 0.46,
|
| 313 |
+
"learning_rate": 0.00038404874499818115,
|
| 314 |
+
"loss": 2.9008,
|
| 315 |
+
"step": 2550
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 0.47,
|
| 319 |
+
"learning_rate": 0.0003817751909785376,
|
| 320 |
+
"loss": 2.8836,
|
| 321 |
+
"step": 2600
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 0.48,
|
| 325 |
+
"learning_rate": 0.0003795016369588942,
|
| 326 |
+
"loss": 2.8773,
|
| 327 |
+
"step": 2650
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 0.49,
|
| 331 |
+
"learning_rate": 0.00037722808293925064,
|
| 332 |
+
"loss": 2.8648,
|
| 333 |
+
"step": 2700
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 0.5,
|
| 337 |
+
"learning_rate": 0.00037495452891960716,
|
| 338 |
+
"loss": 2.8699,
|
| 339 |
+
"step": 2750
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.51,
|
| 343 |
+
"learning_rate": 0.0003726809748999636,
|
| 344 |
+
"loss": 2.8693,
|
| 345 |
+
"step": 2800
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.52,
|
| 349 |
+
"learning_rate": 0.00037040742088032013,
|
| 350 |
+
"loss": 2.8619,
|
| 351 |
+
"step": 2850
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 0.53,
|
| 355 |
+
"learning_rate": 0.00036813386686067665,
|
| 356 |
+
"loss": 2.8591,
|
| 357 |
+
"step": 2900
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 0.54,
|
| 361 |
+
"learning_rate": 0.0003658603128410331,
|
| 362 |
+
"loss": 2.8614,
|
| 363 |
+
"step": 2950
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 0.55,
|
| 367 |
+
"learning_rate": 0.00036358675882138957,
|
| 368 |
+
"loss": 2.8605,
|
| 369 |
+
"step": 3000
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 0.55,
|
| 373 |
+
"learning_rate": 0.00036131320480174613,
|
| 374 |
+
"loss": 2.8357,
|
| 375 |
+
"step": 3050
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 0.56,
|
| 379 |
+
"learning_rate": 0.0003590396507821026,
|
| 380 |
+
"loss": 2.847,
|
| 381 |
+
"step": 3100
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.57,
|
| 385 |
+
"learning_rate": 0.00035676609676245905,
|
| 386 |
+
"loss": 2.8503,
|
| 387 |
+
"step": 3150
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.58,
|
| 391 |
+
"learning_rate": 0.00035449254274281557,
|
| 392 |
+
"loss": 2.8334,
|
| 393 |
+
"step": 3200
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 0.59,
|
| 397 |
+
"learning_rate": 0.0003522189887231721,
|
| 398 |
+
"loss": 2.8424,
|
| 399 |
+
"step": 3250
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 0.6,
|
| 403 |
+
"learning_rate": 0.0003499454347035286,
|
| 404 |
+
"loss": 2.8295,
|
| 405 |
+
"step": 3300
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 0.61,
|
| 409 |
+
"learning_rate": 0.00034767188068388506,
|
| 410 |
+
"loss": 2.8359,
|
| 411 |
+
"step": 3350
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 0.62,
|
| 415 |
+
"learning_rate": 0.0003453983266642415,
|
| 416 |
+
"loss": 2.8252,
|
| 417 |
+
"step": 3400
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 0.63,
|
| 421 |
+
"learning_rate": 0.00034312477264459803,
|
| 422 |
+
"loss": 2.82,
|
| 423 |
+
"step": 3450
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.64,
|
| 427 |
+
"learning_rate": 0.00034085121862495455,
|
| 428 |
+
"loss": 2.8134,
|
| 429 |
+
"step": 3500
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.65,
|
| 433 |
+
"learning_rate": 0.000338577664605311,
|
| 434 |
+
"loss": 2.8168,
|
| 435 |
+
"step": 3550
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 0.65,
|
| 439 |
+
"learning_rate": 0.0003363041105856675,
|
| 440 |
+
"loss": 2.8248,
|
| 441 |
+
"step": 3600
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 0.66,
|
| 445 |
+
"learning_rate": 0.000334030556566024,
|
| 446 |
+
"loss": 2.8096,
|
| 447 |
+
"step": 3650
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 0.67,
|
| 451 |
+
"learning_rate": 0.00033175700254638055,
|
| 452 |
+
"loss": 2.8154,
|
| 453 |
+
"step": 3700
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 0.68,
|
| 457 |
+
"learning_rate": 0.000329483448526737,
|
| 458 |
+
"loss": 2.8015,
|
| 459 |
+
"step": 3750
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 0.69,
|
| 463 |
+
"learning_rate": 0.00032720989450709347,
|
| 464 |
+
"loss": 2.8024,
|
| 465 |
+
"step": 3800
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.7,
|
| 469 |
+
"learning_rate": 0.00032493634048745,
|
| 470 |
+
"loss": 2.7998,
|
| 471 |
+
"step": 3850
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.71,
|
| 475 |
+
"learning_rate": 0.0003226627864678065,
|
| 476 |
+
"loss": 2.8011,
|
| 477 |
+
"step": 3900
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 0.72,
|
| 481 |
+
"learning_rate": 0.00032038923244816296,
|
| 482 |
+
"loss": 2.7963,
|
| 483 |
+
"step": 3950
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 0.73,
|
| 487 |
+
"learning_rate": 0.00031811567842851947,
|
| 488 |
+
"loss": 2.7863,
|
| 489 |
+
"step": 4000
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 0.74,
|
| 493 |
+
"learning_rate": 0.00031584212440887593,
|
| 494 |
+
"loss": 2.7973,
|
| 495 |
+
"step": 4050
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 0.75,
|
| 499 |
+
"learning_rate": 0.0003135685703892325,
|
| 500 |
+
"loss": 2.788,
|
| 501 |
+
"step": 4100
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 0.75,
|
| 505 |
+
"learning_rate": 0.00031129501636958896,
|
| 506 |
+
"loss": 2.8026,
|
| 507 |
+
"step": 4150
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.76,
|
| 511 |
+
"learning_rate": 0.0003090214623499454,
|
| 512 |
+
"loss": 2.7902,
|
| 513 |
+
"step": 4200
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.77,
|
| 517 |
+
"learning_rate": 0.00030674790833030193,
|
| 518 |
+
"loss": 2.7684,
|
| 519 |
+
"step": 4250
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 0.78,
|
| 523 |
+
"learning_rate": 0.00030447435431065845,
|
| 524 |
+
"loss": 2.7846,
|
| 525 |
+
"step": 4300
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 0.79,
|
| 529 |
+
"learning_rate": 0.0003022008002910149,
|
| 530 |
+
"loss": 2.7703,
|
| 531 |
+
"step": 4350
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 0.8,
|
| 535 |
+
"learning_rate": 0.0002999272462713714,
|
| 536 |
+
"loss": 2.7746,
|
| 537 |
+
"step": 4400
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 0.81,
|
| 541 |
+
"learning_rate": 0.0002976536922517279,
|
| 542 |
+
"loss": 2.7674,
|
| 543 |
+
"step": 4450
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 0.82,
|
| 547 |
+
"learning_rate": 0.00029538013823208445,
|
| 548 |
+
"loss": 2.7686,
|
| 549 |
+
"step": 4500
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.83,
|
| 553 |
+
"learning_rate": 0.0002931065842124409,
|
| 554 |
+
"loss": 2.7773,
|
| 555 |
+
"step": 4550
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.84,
|
| 559 |
+
"learning_rate": 0.00029083303019279737,
|
| 560 |
+
"loss": 2.7475,
|
| 561 |
+
"step": 4600
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 0.85,
|
| 565 |
+
"learning_rate": 0.0002885594761731539,
|
| 566 |
+
"loss": 2.7616,
|
| 567 |
+
"step": 4650
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 0.85,
|
| 571 |
+
"learning_rate": 0.00028628592215351035,
|
| 572 |
+
"loss": 2.756,
|
| 573 |
+
"step": 4700
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 0.86,
|
| 577 |
+
"learning_rate": 0.00028401236813386686,
|
| 578 |
+
"loss": 2.7548,
|
| 579 |
+
"step": 4750
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 0.87,
|
| 583 |
+
"learning_rate": 0.0002817388141142234,
|
| 584 |
+
"loss": 2.7499,
|
| 585 |
+
"step": 4800
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 0.88,
|
| 589 |
+
"learning_rate": 0.00027946526009457983,
|
| 590 |
+
"loss": 2.7637,
|
| 591 |
+
"step": 4850
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 0.89,
|
| 595 |
+
"learning_rate": 0.00027719170607493635,
|
| 596 |
+
"loss": 2.7349,
|
| 597 |
+
"step": 4900
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.9,
|
| 601 |
+
"learning_rate": 0.00027491815205529286,
|
| 602 |
+
"loss": 2.7346,
|
| 603 |
+
"step": 4950
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 0.91,
|
| 607 |
+
"learning_rate": 0.0002726445980356493,
|
| 608 |
+
"loss": 2.7384,
|
| 609 |
+
"step": 5000
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 0.92,
|
| 613 |
+
"learning_rate": 0.00027037104401600584,
|
| 614 |
+
"loss": 2.724,
|
| 615 |
+
"step": 5050
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 0.93,
|
| 619 |
+
"learning_rate": 0.0002680974899963623,
|
| 620 |
+
"loss": 2.7508,
|
| 621 |
+
"step": 5100
|
| 622 |
+
},
|
| 623 |
+
{
|
| 624 |
+
"epoch": 0.94,
|
| 625 |
+
"learning_rate": 0.0002658239359767188,
|
| 626 |
+
"loss": 2.7523,
|
| 627 |
+
"step": 5150
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 0.95,
|
| 631 |
+
"learning_rate": 0.0002635503819570753,
|
| 632 |
+
"loss": 2.7298,
|
| 633 |
+
"step": 5200
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 0.95,
|
| 637 |
+
"learning_rate": 0.0002612768279374318,
|
| 638 |
+
"loss": 2.7281,
|
| 639 |
+
"step": 5250
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.96,
|
| 643 |
+
"learning_rate": 0.0002590032739177883,
|
| 644 |
+
"loss": 2.7215,
|
| 645 |
+
"step": 5300
|
| 646 |
+
},
|
| 647 |
+
{
|
| 648 |
+
"epoch": 0.97,
|
| 649 |
+
"learning_rate": 0.0002567297198981448,
|
| 650 |
+
"loss": 2.7318,
|
| 651 |
+
"step": 5350
|
| 652 |
+
},
|
| 653 |
+
{
|
| 654 |
+
"epoch": 0.98,
|
| 655 |
+
"learning_rate": 0.0002544561658785013,
|
| 656 |
+
"loss": 2.7282,
|
| 657 |
+
"step": 5400
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"epoch": 0.99,
|
| 661 |
+
"learning_rate": 0.0002521826118588578,
|
| 662 |
+
"loss": 2.7313,
|
| 663 |
+
"step": 5450
|
| 664 |
+
},
|
| 665 |
+
{
|
| 666 |
+
"epoch": 1.0,
|
| 667 |
+
"learning_rate": 0.0002499090578392143,
|
| 668 |
+
"loss": 2.7133,
|
| 669 |
+
"step": 5500
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 1.01,
|
| 673 |
+
"learning_rate": 0.00024763550381957076,
|
| 674 |
+
"loss": 2.6344,
|
| 675 |
+
"step": 5550
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 1.02,
|
| 679 |
+
"learning_rate": 0.0002453619497999273,
|
| 680 |
+
"loss": 2.6231,
|
| 681 |
+
"step": 5600
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 1.03,
|
| 685 |
+
"learning_rate": 0.00024308839578028374,
|
| 686 |
+
"loss": 2.609,
|
| 687 |
+
"step": 5650
|
| 688 |
+
},
|
| 689 |
+
{
|
| 690 |
+
"epoch": 1.04,
|
| 691 |
+
"learning_rate": 0.00024081484176064022,
|
| 692 |
+
"loss": 2.6154,
|
| 693 |
+
"step": 5700
|
| 694 |
+
},
|
| 695 |
+
{
|
| 696 |
+
"epoch": 1.05,
|
| 697 |
+
"learning_rate": 0.00023854128774099674,
|
| 698 |
+
"loss": 2.6371,
|
| 699 |
+
"step": 5750
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 1.05,
|
| 703 |
+
"learning_rate": 0.0002362677337213532,
|
| 704 |
+
"loss": 2.6082,
|
| 705 |
+
"step": 5800
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 1.06,
|
| 709 |
+
"learning_rate": 0.0002339941797017097,
|
| 710 |
+
"loss": 2.6218,
|
| 711 |
+
"step": 5850
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 1.07,
|
| 715 |
+
"learning_rate": 0.0002317206256820662,
|
| 716 |
+
"loss": 2.6284,
|
| 717 |
+
"step": 5900
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 1.08,
|
| 721 |
+
"learning_rate": 0.00022944707166242271,
|
| 722 |
+
"loss": 2.6191,
|
| 723 |
+
"step": 5950
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 1.09,
|
| 727 |
+
"learning_rate": 0.00022717351764277917,
|
| 728 |
+
"loss": 2.6252,
|
| 729 |
+
"step": 6000
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 1.1,
|
| 733 |
+
"learning_rate": 0.0002248999636231357,
|
| 734 |
+
"loss": 2.6266,
|
| 735 |
+
"step": 6050
|
| 736 |
+
},
|
| 737 |
+
{
|
| 738 |
+
"epoch": 1.11,
|
| 739 |
+
"learning_rate": 0.00022262640960349218,
|
| 740 |
+
"loss": 2.6426,
|
| 741 |
+
"step": 6100
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 1.12,
|
| 745 |
+
"learning_rate": 0.0002203528555838487,
|
| 746 |
+
"loss": 2.6072,
|
| 747 |
+
"step": 6150
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 1.13,
|
| 751 |
+
"learning_rate": 0.00021807930156420515,
|
| 752 |
+
"loss": 2.614,
|
| 753 |
+
"step": 6200
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 1.14,
|
| 757 |
+
"learning_rate": 0.00021580574754456166,
|
| 758 |
+
"loss": 2.5959,
|
| 759 |
+
"step": 6250
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 1.15,
|
| 763 |
+
"learning_rate": 0.00021353219352491815,
|
| 764 |
+
"loss": 2.6065,
|
| 765 |
+
"step": 6300
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 1.15,
|
| 769 |
+
"learning_rate": 0.00021125863950527467,
|
| 770 |
+
"loss": 2.6163,
|
| 771 |
+
"step": 6350
|
| 772 |
+
},
|
| 773 |
+
{
|
| 774 |
+
"epoch": 1.16,
|
| 775 |
+
"learning_rate": 0.00020898508548563113,
|
| 776 |
+
"loss": 2.6083,
|
| 777 |
+
"step": 6400
|
| 778 |
+
},
|
| 779 |
+
{
|
| 780 |
+
"epoch": 1.17,
|
| 781 |
+
"learning_rate": 0.00020671153146598764,
|
| 782 |
+
"loss": 2.6119,
|
| 783 |
+
"step": 6450
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 1.18,
|
| 787 |
+
"learning_rate": 0.00020443797744634413,
|
| 788 |
+
"loss": 2.6023,
|
| 789 |
+
"step": 6500
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 1.19,
|
| 793 |
+
"learning_rate": 0.00020216442342670064,
|
| 794 |
+
"loss": 2.6086,
|
| 795 |
+
"step": 6550
|
| 796 |
+
},
|
| 797 |
+
{
|
| 798 |
+
"epoch": 1.2,
|
| 799 |
+
"learning_rate": 0.0001998908694070571,
|
| 800 |
+
"loss": 2.5988,
|
| 801 |
+
"step": 6600
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 1.21,
|
| 805 |
+
"learning_rate": 0.00019761731538741362,
|
| 806 |
+
"loss": 2.6046,
|
| 807 |
+
"step": 6650
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 1.22,
|
| 811 |
+
"learning_rate": 0.0001953437613677701,
|
| 812 |
+
"loss": 2.5929,
|
| 813 |
+
"step": 6700
|
| 814 |
+
},
|
| 815 |
+
{
|
| 816 |
+
"epoch": 1.23,
|
| 817 |
+
"learning_rate": 0.00019307020734812662,
|
| 818 |
+
"loss": 2.5935,
|
| 819 |
+
"step": 6750
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"epoch": 1.24,
|
| 823 |
+
"learning_rate": 0.00019079665332848308,
|
| 824 |
+
"loss": 2.5875,
|
| 825 |
+
"step": 6800
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 1.25,
|
| 829 |
+
"learning_rate": 0.00018852309930883956,
|
| 830 |
+
"loss": 2.6001,
|
| 831 |
+
"step": 6850
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 1.25,
|
| 835 |
+
"learning_rate": 0.00018624954528919608,
|
| 836 |
+
"loss": 2.6021,
|
| 837 |
+
"step": 6900
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 1.26,
|
| 841 |
+
"learning_rate": 0.00018397599126955257,
|
| 842 |
+
"loss": 2.5887,
|
| 843 |
+
"step": 6950
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 1.27,
|
| 847 |
+
"learning_rate": 0.00018170243724990905,
|
| 848 |
+
"loss": 2.6022,
|
| 849 |
+
"step": 7000
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 1.28,
|
| 853 |
+
"learning_rate": 0.00017942888323026554,
|
| 854 |
+
"loss": 2.5965,
|
| 855 |
+
"step": 7050
|
| 856 |
+
},
|
| 857 |
+
{
|
| 858 |
+
"epoch": 1.29,
|
| 859 |
+
"learning_rate": 0.00017715532921062205,
|
| 860 |
+
"loss": 2.5879,
|
| 861 |
+
"step": 7100
|
| 862 |
+
},
|
| 863 |
+
{
|
| 864 |
+
"epoch": 1.3,
|
| 865 |
+
"learning_rate": 0.00017488177519097854,
|
| 866 |
+
"loss": 2.5935,
|
| 867 |
+
"step": 7150
|
| 868 |
+
},
|
| 869 |
+
{
|
| 870 |
+
"epoch": 1.31,
|
| 871 |
+
"learning_rate": 0.00017260822117133503,
|
| 872 |
+
"loss": 2.6041,
|
| 873 |
+
"step": 7200
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 1.32,
|
| 877 |
+
"learning_rate": 0.00017033466715169152,
|
| 878 |
+
"loss": 2.6041,
|
| 879 |
+
"step": 7250
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 1.33,
|
| 883 |
+
"learning_rate": 0.00016806111313204803,
|
| 884 |
+
"loss": 2.6024,
|
| 885 |
+
"step": 7300
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 1.34,
|
| 889 |
+
"learning_rate": 0.00016578755911240452,
|
| 890 |
+
"loss": 2.5995,
|
| 891 |
+
"step": 7350
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 1.35,
|
| 895 |
+
"learning_rate": 0.000163514005092761,
|
| 896 |
+
"loss": 2.5959,
|
| 897 |
+
"step": 7400
|
| 898 |
+
},
|
| 899 |
+
{
|
| 900 |
+
"epoch": 1.35,
|
| 901 |
+
"learning_rate": 0.0001612404510731175,
|
| 902 |
+
"loss": 2.579,
|
| 903 |
+
"step": 7450
|
| 904 |
+
},
|
| 905 |
+
{
|
| 906 |
+
"epoch": 1.36,
|
| 907 |
+
"learning_rate": 0.000158966897053474,
|
| 908 |
+
"loss": 2.5807,
|
| 909 |
+
"step": 7500
|
| 910 |
+
},
|
| 911 |
+
{
|
| 912 |
+
"epoch": 1.37,
|
| 913 |
+
"learning_rate": 0.0001566933430338305,
|
| 914 |
+
"loss": 2.5922,
|
| 915 |
+
"step": 7550
|
| 916 |
+
},
|
| 917 |
+
{
|
| 918 |
+
"epoch": 1.38,
|
| 919 |
+
"learning_rate": 0.00015441978901418698,
|
| 920 |
+
"loss": 2.5729,
|
| 921 |
+
"step": 7600
|
| 922 |
+
},
|
| 923 |
+
{
|
| 924 |
+
"epoch": 1.39,
|
| 925 |
+
"learning_rate": 0.00015214623499454347,
|
| 926 |
+
"loss": 2.5677,
|
| 927 |
+
"step": 7650
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 1.4,
|
| 931 |
+
"learning_rate": 0.00014987268097489998,
|
| 932 |
+
"loss": 2.5841,
|
| 933 |
+
"step": 7700
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 1.41,
|
| 937 |
+
"learning_rate": 0.00014759912695525647,
|
| 938 |
+
"loss": 2.5908,
|
| 939 |
+
"step": 7750
|
| 940 |
+
},
|
| 941 |
+
{
|
| 942 |
+
"epoch": 1.42,
|
| 943 |
+
"learning_rate": 0.00014532557293561296,
|
| 944 |
+
"loss": 2.5857,
|
| 945 |
+
"step": 7800
|
| 946 |
+
},
|
| 947 |
+
{
|
| 948 |
+
"epoch": 1.43,
|
| 949 |
+
"learning_rate": 0.00014305201891596944,
|
| 950 |
+
"loss": 2.588,
|
| 951 |
+
"step": 7850
|
| 952 |
+
},
|
| 953 |
+
{
|
| 954 |
+
"epoch": 1.44,
|
| 955 |
+
"learning_rate": 0.00014077846489632596,
|
| 956 |
+
"loss": 2.5843,
|
| 957 |
+
"step": 7900
|
| 958 |
+
},
|
| 959 |
+
{
|
| 960 |
+
"epoch": 1.45,
|
| 961 |
+
"learning_rate": 0.00013850491087668244,
|
| 962 |
+
"loss": 2.5802,
|
| 963 |
+
"step": 7950
|
| 964 |
+
},
|
| 965 |
+
{
|
| 966 |
+
"epoch": 1.45,
|
| 967 |
+
"learning_rate": 0.0001362313568570389,
|
| 968 |
+
"loss": 2.5631,
|
| 969 |
+
"step": 8000
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 1.46,
|
| 973 |
+
"learning_rate": 0.00013395780283739542,
|
| 974 |
+
"loss": 2.5767,
|
| 975 |
+
"step": 8050
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 1.47,
|
| 979 |
+
"learning_rate": 0.0001316842488177519,
|
| 980 |
+
"loss": 2.563,
|
| 981 |
+
"step": 8100
|
| 982 |
+
},
|
| 983 |
+
{
|
| 984 |
+
"epoch": 1.48,
|
| 985 |
+
"learning_rate": 0.00012941069479810842,
|
| 986 |
+
"loss": 2.5844,
|
| 987 |
+
"step": 8150
|
| 988 |
+
},
|
| 989 |
+
{
|
| 990 |
+
"epoch": 1.49,
|
| 991 |
+
"learning_rate": 0.00012713714077846488,
|
| 992 |
+
"loss": 2.5721,
|
| 993 |
+
"step": 8200
|
| 994 |
+
},
|
| 995 |
+
{
|
| 996 |
+
"epoch": 1.5,
|
| 997 |
+
"learning_rate": 0.0001248635867588214,
|
| 998 |
+
"loss": 2.5871,
|
| 999 |
+
"step": 8250
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 1.51,
|
| 1003 |
+
"learning_rate": 0.00012259003273917788,
|
| 1004 |
+
"loss": 2.5781,
|
| 1005 |
+
"step": 8300
|
| 1006 |
+
},
|
| 1007 |
+
{
|
| 1008 |
+
"epoch": 1.52,
|
| 1009 |
+
"learning_rate": 0.00012031647871953438,
|
| 1010 |
+
"loss": 2.5646,
|
| 1011 |
+
"step": 8350
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 1.53,
|
| 1015 |
+
"learning_rate": 0.00011804292469989088,
|
| 1016 |
+
"loss": 2.5614,
|
| 1017 |
+
"step": 8400
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 1.54,
|
| 1021 |
+
"learning_rate": 0.00011576937068024737,
|
| 1022 |
+
"loss": 2.568,
|
| 1023 |
+
"step": 8450
|
| 1024 |
+
},
|
| 1025 |
+
{
|
| 1026 |
+
"epoch": 1.55,
|
| 1027 |
+
"learning_rate": 0.00011349581666060387,
|
| 1028 |
+
"loss": 2.5592,
|
| 1029 |
+
"step": 8500
|
| 1030 |
+
},
|
| 1031 |
+
{
|
| 1032 |
+
"epoch": 1.55,
|
| 1033 |
+
"learning_rate": 0.00011122226264096034,
|
| 1034 |
+
"loss": 2.5672,
|
| 1035 |
+
"step": 8550
|
| 1036 |
+
},
|
| 1037 |
+
{
|
| 1038 |
+
"epoch": 1.56,
|
| 1039 |
+
"learning_rate": 0.00010894870862131685,
|
| 1040 |
+
"loss": 2.5649,
|
| 1041 |
+
"step": 8600
|
| 1042 |
+
},
|
| 1043 |
+
{
|
| 1044 |
+
"epoch": 1.57,
|
| 1045 |
+
"learning_rate": 0.00010667515460167333,
|
| 1046 |
+
"loss": 2.5686,
|
| 1047 |
+
"step": 8650
|
| 1048 |
+
},
|
| 1049 |
+
{
|
| 1050 |
+
"epoch": 1.58,
|
| 1051 |
+
"learning_rate": 0.00010440160058202983,
|
| 1052 |
+
"loss": 2.5758,
|
| 1053 |
+
"step": 8700
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 1.59,
|
| 1057 |
+
"learning_rate": 0.00010212804656238632,
|
| 1058 |
+
"loss": 2.565,
|
| 1059 |
+
"step": 8750
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 1.6,
|
| 1063 |
+
"learning_rate": 9.985449254274281e-05,
|
| 1064 |
+
"loss": 2.5904,
|
| 1065 |
+
"step": 8800
|
| 1066 |
+
},
|
| 1067 |
+
{
|
| 1068 |
+
"epoch": 1.61,
|
| 1069 |
+
"learning_rate": 9.758093852309931e-05,
|
| 1070 |
+
"loss": 2.5668,
|
| 1071 |
+
"step": 8850
|
| 1072 |
+
},
|
| 1073 |
+
{
|
| 1074 |
+
"epoch": 1.62,
|
| 1075 |
+
"learning_rate": 9.53073845034558e-05,
|
| 1076 |
+
"loss": 2.5714,
|
| 1077 |
+
"step": 8900
|
| 1078 |
+
},
|
| 1079 |
+
{
|
| 1080 |
+
"epoch": 1.63,
|
| 1081 |
+
"learning_rate": 9.30338304838123e-05,
|
| 1082 |
+
"loss": 2.5511,
|
| 1083 |
+
"step": 8950
|
| 1084 |
+
},
|
| 1085 |
+
{
|
| 1086 |
+
"epoch": 1.64,
|
| 1087 |
+
"learning_rate": 9.076027646416878e-05,
|
| 1088 |
+
"loss": 2.5756,
|
| 1089 |
+
"step": 9000
|
| 1090 |
+
},
|
| 1091 |
+
{
|
| 1092 |
+
"epoch": 1.65,
|
| 1093 |
+
"learning_rate": 8.848672244452528e-05,
|
| 1094 |
+
"loss": 2.5688,
|
| 1095 |
+
"step": 9050
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 1.65,
|
| 1099 |
+
"learning_rate": 8.621316842488177e-05,
|
| 1100 |
+
"loss": 2.5567,
|
| 1101 |
+
"step": 9100
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 1.66,
|
| 1105 |
+
"learning_rate": 8.393961440523827e-05,
|
| 1106 |
+
"loss": 2.561,
|
| 1107 |
+
"step": 9150
|
| 1108 |
+
},
|
| 1109 |
+
{
|
| 1110 |
+
"epoch": 1.67,
|
| 1111 |
+
"learning_rate": 8.166606038559476e-05,
|
| 1112 |
+
"loss": 2.5525,
|
| 1113 |
+
"step": 9200
|
| 1114 |
+
},
|
| 1115 |
+
{
|
| 1116 |
+
"epoch": 1.68,
|
| 1117 |
+
"learning_rate": 7.939250636595126e-05,
|
| 1118 |
+
"loss": 2.5665,
|
| 1119 |
+
"step": 9250
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 1.69,
|
| 1123 |
+
"learning_rate": 7.711895234630775e-05,
|
| 1124 |
+
"loss": 2.5686,
|
| 1125 |
+
"step": 9300
|
| 1126 |
+
},
|
| 1127 |
+
{
|
| 1128 |
+
"epoch": 1.7,
|
| 1129 |
+
"learning_rate": 7.484539832666425e-05,
|
| 1130 |
+
"loss": 2.5627,
|
| 1131 |
+
"step": 9350
|
| 1132 |
+
},
|
| 1133 |
+
{
|
| 1134 |
+
"epoch": 1.71,
|
| 1135 |
+
"learning_rate": 7.257184430702073e-05,
|
| 1136 |
+
"loss": 2.5454,
|
| 1137 |
+
"step": 9400
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 1.72,
|
| 1141 |
+
"learning_rate": 7.029829028737724e-05,
|
| 1142 |
+
"loss": 2.5677,
|
| 1143 |
+
"step": 9450
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 1.73,
|
| 1147 |
+
"learning_rate": 6.802473626773372e-05,
|
| 1148 |
+
"loss": 2.572,
|
| 1149 |
+
"step": 9500
|
| 1150 |
+
},
|
| 1151 |
+
{
|
| 1152 |
+
"epoch": 1.74,
|
| 1153 |
+
"learning_rate": 6.575118224809022e-05,
|
| 1154 |
+
"loss": 2.5468,
|
| 1155 |
+
"step": 9550
|
| 1156 |
+
},
|
| 1157 |
+
{
|
| 1158 |
+
"epoch": 1.75,
|
| 1159 |
+
"learning_rate": 6.347762822844671e-05,
|
| 1160 |
+
"loss": 2.5627,
|
| 1161 |
+
"step": 9600
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 1.75,
|
| 1165 |
+
"learning_rate": 6.12040742088032e-05,
|
| 1166 |
+
"loss": 2.5523,
|
| 1167 |
+
"step": 9650
|
| 1168 |
+
},
|
| 1169 |
+
{
|
| 1170 |
+
"epoch": 1.76,
|
| 1171 |
+
"learning_rate": 5.89305201891597e-05,
|
| 1172 |
+
"loss": 2.559,
|
| 1173 |
+
"step": 9700
|
| 1174 |
+
},
|
| 1175 |
+
{
|
| 1176 |
+
"epoch": 1.77,
|
| 1177 |
+
"learning_rate": 5.665696616951619e-05,
|
| 1178 |
+
"loss": 2.5542,
|
| 1179 |
+
"step": 9750
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 1.78,
|
| 1183 |
+
"learning_rate": 5.4383412149872686e-05,
|
| 1184 |
+
"loss": 2.5632,
|
| 1185 |
+
"step": 9800
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 1.79,
|
| 1189 |
+
"learning_rate": 5.210985813022918e-05,
|
| 1190 |
+
"loss": 2.5646,
|
| 1191 |
+
"step": 9850
|
| 1192 |
+
},
|
| 1193 |
+
{
|
| 1194 |
+
"epoch": 1.8,
|
| 1195 |
+
"learning_rate": 4.9836304110585674e-05,
|
| 1196 |
+
"loss": 2.545,
|
| 1197 |
+
"step": 9900
|
| 1198 |
+
},
|
| 1199 |
+
{
|
| 1200 |
+
"epoch": 1.81,
|
| 1201 |
+
"learning_rate": 4.756275009094216e-05,
|
| 1202 |
+
"loss": 2.5525,
|
| 1203 |
+
"step": 9950
|
| 1204 |
+
},
|
| 1205 |
+
{
|
| 1206 |
+
"epoch": 1.82,
|
| 1207 |
+
"learning_rate": 4.5289196071298655e-05,
|
| 1208 |
+
"loss": 2.5823,
|
| 1209 |
+
"step": 10000
|
| 1210 |
+
}
|
| 1211 |
+
],
|
| 1212 |
+
"logging_steps": 50,
|
| 1213 |
+
"max_steps": 10996,
|
| 1214 |
+
"num_train_epochs": 2,
|
| 1215 |
+
"save_steps": 2500,
|
| 1216 |
+
"total_flos": 6.5560796725248e+17,
|
| 1217 |
+
"trial_name": null,
|
| 1218 |
+
"trial_params": null
|
| 1219 |
+
}
|
checkpoint-10000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:efdafc920f92f7fef444725b8239e547a249e5e3d18c711b75245d4473de9d3c
|
| 3 |
+
size 4027
|
checkpoint-2500/config.json
ADDED
|
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "./core2",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"LlamaForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"bos_token_id": 1,
|
| 7 |
+
"eos_token_id": 2,
|
| 8 |
+
"hidden_act": "silu",
|
| 9 |
+
"hidden_size": 4096,
|
| 10 |
+
"initializer_range": 0.02,
|
| 11 |
+
"intermediate_size": 11008,
|
| 12 |
+
"max_position_embeddings": 4096,
|
| 13 |
+
"model_type": "llama",
|
| 14 |
+
"num_attention_heads": 32,
|
| 15 |
+
"num_hidden_layers": 1,
|
| 16 |
+
"num_key_value_heads": 32,
|
| 17 |
+
"pretraining_tp": 1,
|
| 18 |
+
"rms_norm_eps": 1e-06,
|
| 19 |
+
"rope_scaling": null,
|
| 20 |
+
"rope_theta": 10000.0,
|
| 21 |
+
"tie_word_embeddings": false,
|
| 22 |
+
"torch_dtype": "bfloat16",
|
| 23 |
+
"transformers_version": "4.34.0.dev0",
|
| 24 |
+
"use_cache": true,
|
| 25 |
+
"vocab_size": 32000
|
| 26 |
+
}
|
checkpoint-2500/generation_config.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 1,
|
| 3 |
+
"do_sample": true,
|
| 4 |
+
"eos_token_id": 2,
|
| 5 |
+
"max_length": 4096,
|
| 6 |
+
"pad_token_id": 0,
|
| 7 |
+
"temperature": 0.6,
|
| 8 |
+
"top_p": 0.9,
|
| 9 |
+
"transformers_version": "4.34.0.dev0"
|
| 10 |
+
}
|
checkpoint-2500/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:207452d1168390f8bf7e0da03e7bb9a9aa38eb6d5387b5a85d363d871c6baf5e
|
| 3 |
+
size 1858136133
|
checkpoint-2500/pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c3af8fa74fa47804a24797b9d185706e77f2ad9bd37916f1a746c442efb8adfe
|
| 3 |
+
size 929067029
|
checkpoint-2500/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b2278a87cdf86c3f9219223c847f6b27f6b7f15b8226b617f38936e8ff2cbcde
|
| 3 |
+
size 14575
|
checkpoint-2500/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4651efbde1cbaf4a0b682250b47a031d03dd4e96bb70202b5d9896030fea354c
|
| 3 |
+
size 627
|
checkpoint-2500/special_tokens_map.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "</s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"unk_token": {
|
| 17 |
+
"content": "<unk>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
}
|
| 23 |
+
}
|
checkpoint-2500/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-2500/tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
| 3 |
+
size 499723
|
checkpoint-2500/tokenizer_config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"__type": "AddedToken",
|
| 4 |
+
"content": "<s>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false
|
| 9 |
+
},
|
| 10 |
+
"clean_up_tokenization_spaces": false,
|
| 11 |
+
"eos_token": {
|
| 12 |
+
"__type": "AddedToken",
|
| 13 |
+
"content": "</s>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": false,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false
|
| 18 |
+
},
|
| 19 |
+
"legacy": false,
|
| 20 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 21 |
+
"pad_token": null,
|
| 22 |
+
"padding_side": "right",
|
| 23 |
+
"sp_model_kwargs": {},
|
| 24 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 25 |
+
"unk_token": {
|
| 26 |
+
"__type": "AddedToken",
|
| 27 |
+
"content": "<unk>",
|
| 28 |
+
"lstrip": false,
|
| 29 |
+
"normalized": false,
|
| 30 |
+
"rstrip": false,
|
| 31 |
+
"single_word": false
|
| 32 |
+
},
|
| 33 |
+
"use_default_system_prompt": true
|
| 34 |
+
}
|
checkpoint-2500/trainer_state.json
ADDED
|
@@ -0,0 +1,319 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.11366413385088402,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 2500,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.0,
|
| 13 |
+
"learning_rate": 9.977266527234701e-05,
|
| 14 |
+
"loss": 2.6296,
|
| 15 |
+
"step": 50
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.0,
|
| 19 |
+
"learning_rate": 9.954533054469402e-05,
|
| 20 |
+
"loss": 2.6156,
|
| 21 |
+
"step": 100
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.01,
|
| 25 |
+
"learning_rate": 9.931799581704102e-05,
|
| 26 |
+
"loss": 2.6035,
|
| 27 |
+
"step": 150
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.01,
|
| 31 |
+
"learning_rate": 9.909066108938801e-05,
|
| 32 |
+
"loss": 2.5399,
|
| 33 |
+
"step": 200
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.01,
|
| 37 |
+
"learning_rate": 9.886332636173502e-05,
|
| 38 |
+
"loss": 2.5857,
|
| 39 |
+
"step": 250
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.01,
|
| 43 |
+
"learning_rate": 9.863599163408202e-05,
|
| 44 |
+
"loss": 2.6078,
|
| 45 |
+
"step": 300
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.02,
|
| 49 |
+
"learning_rate": 9.840865690642903e-05,
|
| 50 |
+
"loss": 2.5931,
|
| 51 |
+
"step": 350
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.02,
|
| 55 |
+
"learning_rate": 9.818132217877604e-05,
|
| 56 |
+
"loss": 2.5919,
|
| 57 |
+
"step": 400
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.02,
|
| 61 |
+
"learning_rate": 9.795398745112304e-05,
|
| 62 |
+
"loss": 2.59,
|
| 63 |
+
"step": 450
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.02,
|
| 67 |
+
"learning_rate": 9.772665272347005e-05,
|
| 68 |
+
"loss": 2.605,
|
| 69 |
+
"step": 500
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.03,
|
| 73 |
+
"learning_rate": 9.749931799581704e-05,
|
| 74 |
+
"loss": 2.6026,
|
| 75 |
+
"step": 550
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.03,
|
| 79 |
+
"learning_rate": 9.727198326816404e-05,
|
| 80 |
+
"loss": 2.5839,
|
| 81 |
+
"step": 600
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.03,
|
| 85 |
+
"learning_rate": 9.704464854051105e-05,
|
| 86 |
+
"loss": 2.5862,
|
| 87 |
+
"step": 650
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.03,
|
| 91 |
+
"learning_rate": 9.681731381285806e-05,
|
| 92 |
+
"loss": 2.609,
|
| 93 |
+
"step": 700
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.03,
|
| 97 |
+
"learning_rate": 9.658997908520506e-05,
|
| 98 |
+
"loss": 2.5759,
|
| 99 |
+
"step": 750
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.04,
|
| 103 |
+
"learning_rate": 9.636264435755207e-05,
|
| 104 |
+
"loss": 2.6046,
|
| 105 |
+
"step": 800
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.04,
|
| 109 |
+
"learning_rate": 9.613530962989907e-05,
|
| 110 |
+
"loss": 2.5811,
|
| 111 |
+
"step": 850
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 0.04,
|
| 115 |
+
"learning_rate": 9.590797490224606e-05,
|
| 116 |
+
"loss": 2.5797,
|
| 117 |
+
"step": 900
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 0.04,
|
| 121 |
+
"learning_rate": 9.568064017459307e-05,
|
| 122 |
+
"loss": 2.5867,
|
| 123 |
+
"step": 950
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.05,
|
| 127 |
+
"learning_rate": 9.545330544694008e-05,
|
| 128 |
+
"loss": 2.5927,
|
| 129 |
+
"step": 1000
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.05,
|
| 133 |
+
"learning_rate": 9.522597071928708e-05,
|
| 134 |
+
"loss": 2.568,
|
| 135 |
+
"step": 1050
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.05,
|
| 139 |
+
"learning_rate": 9.499863599163409e-05,
|
| 140 |
+
"loss": 2.6024,
|
| 141 |
+
"step": 1100
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 0.05,
|
| 145 |
+
"learning_rate": 9.477130126398109e-05,
|
| 146 |
+
"loss": 2.5936,
|
| 147 |
+
"step": 1150
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 0.05,
|
| 151 |
+
"learning_rate": 9.45439665363281e-05,
|
| 152 |
+
"loss": 2.605,
|
| 153 |
+
"step": 1200
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 0.06,
|
| 157 |
+
"learning_rate": 9.431663180867509e-05,
|
| 158 |
+
"loss": 2.5775,
|
| 159 |
+
"step": 1250
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.06,
|
| 163 |
+
"learning_rate": 9.40892970810221e-05,
|
| 164 |
+
"loss": 2.5752,
|
| 165 |
+
"step": 1300
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 0.06,
|
| 169 |
+
"learning_rate": 9.38619623533691e-05,
|
| 170 |
+
"loss": 2.5679,
|
| 171 |
+
"step": 1350
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.06,
|
| 175 |
+
"learning_rate": 9.36346276257161e-05,
|
| 176 |
+
"loss": 2.5856,
|
| 177 |
+
"step": 1400
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.07,
|
| 181 |
+
"learning_rate": 9.340729289806311e-05,
|
| 182 |
+
"loss": 2.5787,
|
| 183 |
+
"step": 1450
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 0.07,
|
| 187 |
+
"learning_rate": 9.317995817041012e-05,
|
| 188 |
+
"loss": 2.5875,
|
| 189 |
+
"step": 1500
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 0.07,
|
| 193 |
+
"learning_rate": 9.295262344275712e-05,
|
| 194 |
+
"loss": 2.5631,
|
| 195 |
+
"step": 1550
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 0.07,
|
| 199 |
+
"learning_rate": 9.272528871510412e-05,
|
| 200 |
+
"loss": 2.583,
|
| 201 |
+
"step": 1600
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 0.08,
|
| 205 |
+
"learning_rate": 9.249795398745112e-05,
|
| 206 |
+
"loss": 2.5609,
|
| 207 |
+
"step": 1650
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 0.08,
|
| 211 |
+
"learning_rate": 9.227061925979813e-05,
|
| 212 |
+
"loss": 2.587,
|
| 213 |
+
"step": 1700
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.08,
|
| 217 |
+
"learning_rate": 9.204328453214513e-05,
|
| 218 |
+
"loss": 2.5555,
|
| 219 |
+
"step": 1750
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.08,
|
| 223 |
+
"learning_rate": 9.181594980449214e-05,
|
| 224 |
+
"loss": 2.5488,
|
| 225 |
+
"step": 1800
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 0.08,
|
| 229 |
+
"learning_rate": 9.158861507683914e-05,
|
| 230 |
+
"loss": 2.5554,
|
| 231 |
+
"step": 1850
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 0.09,
|
| 235 |
+
"learning_rate": 9.136128034918615e-05,
|
| 236 |
+
"loss": 2.5408,
|
| 237 |
+
"step": 1900
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 0.09,
|
| 241 |
+
"learning_rate": 9.113394562153314e-05,
|
| 242 |
+
"loss": 2.582,
|
| 243 |
+
"step": 1950
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 0.09,
|
| 247 |
+
"learning_rate": 9.090661089388015e-05,
|
| 248 |
+
"loss": 2.5533,
|
| 249 |
+
"step": 2000
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 0.09,
|
| 253 |
+
"learning_rate": 9.067927616622715e-05,
|
| 254 |
+
"loss": 2.5432,
|
| 255 |
+
"step": 2050
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.1,
|
| 259 |
+
"learning_rate": 9.045194143857416e-05,
|
| 260 |
+
"loss": 2.5867,
|
| 261 |
+
"step": 2100
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.1,
|
| 265 |
+
"learning_rate": 9.022460671092116e-05,
|
| 266 |
+
"loss": 2.5343,
|
| 267 |
+
"step": 2150
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 0.1,
|
| 271 |
+
"learning_rate": 8.999727198326817e-05,
|
| 272 |
+
"loss": 2.585,
|
| 273 |
+
"step": 2200
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 0.1,
|
| 277 |
+
"learning_rate": 8.976993725561517e-05,
|
| 278 |
+
"loss": 2.5679,
|
| 279 |
+
"step": 2250
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 0.1,
|
| 283 |
+
"learning_rate": 8.954260252796217e-05,
|
| 284 |
+
"loss": 2.5515,
|
| 285 |
+
"step": 2300
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 0.11,
|
| 289 |
+
"learning_rate": 8.931526780030917e-05,
|
| 290 |
+
"loss": 2.5713,
|
| 291 |
+
"step": 2350
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 0.11,
|
| 295 |
+
"learning_rate": 8.908793307265618e-05,
|
| 296 |
+
"loss": 2.5587,
|
| 297 |
+
"step": 2400
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.11,
|
| 301 |
+
"learning_rate": 8.886059834500318e-05,
|
| 302 |
+
"loss": 2.5774,
|
| 303 |
+
"step": 2450
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.11,
|
| 307 |
+
"learning_rate": 8.863326361735019e-05,
|
| 308 |
+
"loss": 2.551,
|
| 309 |
+
"step": 2500
|
| 310 |
+
}
|
| 311 |
+
],
|
| 312 |
+
"logging_steps": 50,
|
| 313 |
+
"max_steps": 21994,
|
| 314 |
+
"num_train_epochs": 1,
|
| 315 |
+
"save_steps": 2500,
|
| 316 |
+
"total_flos": 4.097549795328e+16,
|
| 317 |
+
"trial_name": null,
|
| 318 |
+
"trial_params": null
|
| 319 |
+
}
|
checkpoint-2500/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2458e0243aaab0a29fd49a56d9466fcdd0e8ef0f37d199202b23e025f597ffca
|
| 3 |
+
size 4027
|
checkpoint-5000/config.json
ADDED
|
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "./core2",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"LlamaForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"bos_token_id": 1,
|
| 7 |
+
"eos_token_id": 2,
|
| 8 |
+
"hidden_act": "silu",
|
| 9 |
+
"hidden_size": 4096,
|
| 10 |
+
"initializer_range": 0.02,
|
| 11 |
+
"intermediate_size": 11008,
|
| 12 |
+
"max_position_embeddings": 4096,
|
| 13 |
+
"model_type": "llama",
|
| 14 |
+
"num_attention_heads": 32,
|
| 15 |
+
"num_hidden_layers": 1,
|
| 16 |
+
"num_key_value_heads": 32,
|
| 17 |
+
"pretraining_tp": 1,
|
| 18 |
+
"rms_norm_eps": 1e-06,
|
| 19 |
+
"rope_scaling": null,
|
| 20 |
+
"rope_theta": 10000.0,
|
| 21 |
+
"tie_word_embeddings": false,
|
| 22 |
+
"torch_dtype": "bfloat16",
|
| 23 |
+
"transformers_version": "4.34.0.dev0",
|
| 24 |
+
"use_cache": true,
|
| 25 |
+
"vocab_size": 32000
|
| 26 |
+
}
|
checkpoint-5000/generation_config.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 1,
|
| 3 |
+
"do_sample": true,
|
| 4 |
+
"eos_token_id": 2,
|
| 5 |
+
"max_length": 4096,
|
| 6 |
+
"pad_token_id": 0,
|
| 7 |
+
"temperature": 0.6,
|
| 8 |
+
"top_p": 0.9,
|
| 9 |
+
"transformers_version": "4.34.0.dev0"
|
| 10 |
+
}
|
checkpoint-5000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:704531a229cf5dc6fe0f5961f4f2867a29e55bf4fddef7b8c204b1054dbd40ab
|
| 3 |
+
size 1858136133
|
checkpoint-5000/pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8cfe8c3937d90ccd5a9a795bca91d29acb89c21869e7bfe0b28a6999060659f0
|
| 3 |
+
size 929067029
|
checkpoint-5000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b2278a87cdf86c3f9219223c847f6b27f6b7f15b8226b617f38936e8ff2cbcde
|
| 3 |
+
size 14575
|
checkpoint-5000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d5192a1ee8b34f588f041e4906a7eb6bf85582d9fd03cfb971cdcda7ba896f86
|
| 3 |
+
size 627
|
checkpoint-5000/special_tokens_map.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "</s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"unk_token": {
|
| 17 |
+
"content": "<unk>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
}
|
| 23 |
+
}
|
checkpoint-5000/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-5000/tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
| 3 |
+
size 499723
|
checkpoint-5000/tokenizer_config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"__type": "AddedToken",
|
| 4 |
+
"content": "<s>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false
|
| 9 |
+
},
|
| 10 |
+
"clean_up_tokenization_spaces": false,
|
| 11 |
+
"eos_token": {
|
| 12 |
+
"__type": "AddedToken",
|
| 13 |
+
"content": "</s>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": false,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false
|
| 18 |
+
},
|
| 19 |
+
"legacy": false,
|
| 20 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 21 |
+
"pad_token": null,
|
| 22 |
+
"padding_side": "right",
|
| 23 |
+
"sp_model_kwargs": {},
|
| 24 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 25 |
+
"unk_token": {
|
| 26 |
+
"__type": "AddedToken",
|
| 27 |
+
"content": "<unk>",
|
| 28 |
+
"lstrip": false,
|
| 29 |
+
"normalized": false,
|
| 30 |
+
"rstrip": false,
|
| 31 |
+
"single_word": false
|
| 32 |
+
},
|
| 33 |
+
"use_default_system_prompt": true
|
| 34 |
+
}
|
checkpoint-5000/trainer_state.json
ADDED
|
@@ -0,0 +1,619 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.22732826770176803,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 5000,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.0,
|
| 13 |
+
"learning_rate": 9.977266527234701e-05,
|
| 14 |
+
"loss": 2.6296,
|
| 15 |
+
"step": 50
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.0,
|
| 19 |
+
"learning_rate": 9.954533054469402e-05,
|
| 20 |
+
"loss": 2.6156,
|
| 21 |
+
"step": 100
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.01,
|
| 25 |
+
"learning_rate": 9.931799581704102e-05,
|
| 26 |
+
"loss": 2.6035,
|
| 27 |
+
"step": 150
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.01,
|
| 31 |
+
"learning_rate": 9.909066108938801e-05,
|
| 32 |
+
"loss": 2.5399,
|
| 33 |
+
"step": 200
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.01,
|
| 37 |
+
"learning_rate": 9.886332636173502e-05,
|
| 38 |
+
"loss": 2.5857,
|
| 39 |
+
"step": 250
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.01,
|
| 43 |
+
"learning_rate": 9.863599163408202e-05,
|
| 44 |
+
"loss": 2.6078,
|
| 45 |
+
"step": 300
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.02,
|
| 49 |
+
"learning_rate": 9.840865690642903e-05,
|
| 50 |
+
"loss": 2.5931,
|
| 51 |
+
"step": 350
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.02,
|
| 55 |
+
"learning_rate": 9.818132217877604e-05,
|
| 56 |
+
"loss": 2.5919,
|
| 57 |
+
"step": 400
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.02,
|
| 61 |
+
"learning_rate": 9.795398745112304e-05,
|
| 62 |
+
"loss": 2.59,
|
| 63 |
+
"step": 450
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.02,
|
| 67 |
+
"learning_rate": 9.772665272347005e-05,
|
| 68 |
+
"loss": 2.605,
|
| 69 |
+
"step": 500
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.03,
|
| 73 |
+
"learning_rate": 9.749931799581704e-05,
|
| 74 |
+
"loss": 2.6026,
|
| 75 |
+
"step": 550
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.03,
|
| 79 |
+
"learning_rate": 9.727198326816404e-05,
|
| 80 |
+
"loss": 2.5839,
|
| 81 |
+
"step": 600
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.03,
|
| 85 |
+
"learning_rate": 9.704464854051105e-05,
|
| 86 |
+
"loss": 2.5862,
|
| 87 |
+
"step": 650
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.03,
|
| 91 |
+
"learning_rate": 9.681731381285806e-05,
|
| 92 |
+
"loss": 2.609,
|
| 93 |
+
"step": 700
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.03,
|
| 97 |
+
"learning_rate": 9.658997908520506e-05,
|
| 98 |
+
"loss": 2.5759,
|
| 99 |
+
"step": 750
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.04,
|
| 103 |
+
"learning_rate": 9.636264435755207e-05,
|
| 104 |
+
"loss": 2.6046,
|
| 105 |
+
"step": 800
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.04,
|
| 109 |
+
"learning_rate": 9.613530962989907e-05,
|
| 110 |
+
"loss": 2.5811,
|
| 111 |
+
"step": 850
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 0.04,
|
| 115 |
+
"learning_rate": 9.590797490224606e-05,
|
| 116 |
+
"loss": 2.5797,
|
| 117 |
+
"step": 900
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 0.04,
|
| 121 |
+
"learning_rate": 9.568064017459307e-05,
|
| 122 |
+
"loss": 2.5867,
|
| 123 |
+
"step": 950
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.05,
|
| 127 |
+
"learning_rate": 9.545330544694008e-05,
|
| 128 |
+
"loss": 2.5927,
|
| 129 |
+
"step": 1000
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.05,
|
| 133 |
+
"learning_rate": 9.522597071928708e-05,
|
| 134 |
+
"loss": 2.568,
|
| 135 |
+
"step": 1050
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.05,
|
| 139 |
+
"learning_rate": 9.499863599163409e-05,
|
| 140 |
+
"loss": 2.6024,
|
| 141 |
+
"step": 1100
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 0.05,
|
| 145 |
+
"learning_rate": 9.477130126398109e-05,
|
| 146 |
+
"loss": 2.5936,
|
| 147 |
+
"step": 1150
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 0.05,
|
| 151 |
+
"learning_rate": 9.45439665363281e-05,
|
| 152 |
+
"loss": 2.605,
|
| 153 |
+
"step": 1200
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 0.06,
|
| 157 |
+
"learning_rate": 9.431663180867509e-05,
|
| 158 |
+
"loss": 2.5775,
|
| 159 |
+
"step": 1250
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.06,
|
| 163 |
+
"learning_rate": 9.40892970810221e-05,
|
| 164 |
+
"loss": 2.5752,
|
| 165 |
+
"step": 1300
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 0.06,
|
| 169 |
+
"learning_rate": 9.38619623533691e-05,
|
| 170 |
+
"loss": 2.5679,
|
| 171 |
+
"step": 1350
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.06,
|
| 175 |
+
"learning_rate": 9.36346276257161e-05,
|
| 176 |
+
"loss": 2.5856,
|
| 177 |
+
"step": 1400
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.07,
|
| 181 |
+
"learning_rate": 9.340729289806311e-05,
|
| 182 |
+
"loss": 2.5787,
|
| 183 |
+
"step": 1450
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 0.07,
|
| 187 |
+
"learning_rate": 9.317995817041012e-05,
|
| 188 |
+
"loss": 2.5875,
|
| 189 |
+
"step": 1500
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 0.07,
|
| 193 |
+
"learning_rate": 9.295262344275712e-05,
|
| 194 |
+
"loss": 2.5631,
|
| 195 |
+
"step": 1550
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 0.07,
|
| 199 |
+
"learning_rate": 9.272528871510412e-05,
|
| 200 |
+
"loss": 2.583,
|
| 201 |
+
"step": 1600
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 0.08,
|
| 205 |
+
"learning_rate": 9.249795398745112e-05,
|
| 206 |
+
"loss": 2.5609,
|
| 207 |
+
"step": 1650
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 0.08,
|
| 211 |
+
"learning_rate": 9.227061925979813e-05,
|
| 212 |
+
"loss": 2.587,
|
| 213 |
+
"step": 1700
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.08,
|
| 217 |
+
"learning_rate": 9.204328453214513e-05,
|
| 218 |
+
"loss": 2.5555,
|
| 219 |
+
"step": 1750
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.08,
|
| 223 |
+
"learning_rate": 9.181594980449214e-05,
|
| 224 |
+
"loss": 2.5488,
|
| 225 |
+
"step": 1800
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 0.08,
|
| 229 |
+
"learning_rate": 9.158861507683914e-05,
|
| 230 |
+
"loss": 2.5554,
|
| 231 |
+
"step": 1850
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 0.09,
|
| 235 |
+
"learning_rate": 9.136128034918615e-05,
|
| 236 |
+
"loss": 2.5408,
|
| 237 |
+
"step": 1900
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 0.09,
|
| 241 |
+
"learning_rate": 9.113394562153314e-05,
|
| 242 |
+
"loss": 2.582,
|
| 243 |
+
"step": 1950
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 0.09,
|
| 247 |
+
"learning_rate": 9.090661089388015e-05,
|
| 248 |
+
"loss": 2.5533,
|
| 249 |
+
"step": 2000
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 0.09,
|
| 253 |
+
"learning_rate": 9.067927616622715e-05,
|
| 254 |
+
"loss": 2.5432,
|
| 255 |
+
"step": 2050
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.1,
|
| 259 |
+
"learning_rate": 9.045194143857416e-05,
|
| 260 |
+
"loss": 2.5867,
|
| 261 |
+
"step": 2100
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.1,
|
| 265 |
+
"learning_rate": 9.022460671092116e-05,
|
| 266 |
+
"loss": 2.5343,
|
| 267 |
+
"step": 2150
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 0.1,
|
| 271 |
+
"learning_rate": 8.999727198326817e-05,
|
| 272 |
+
"loss": 2.585,
|
| 273 |
+
"step": 2200
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 0.1,
|
| 277 |
+
"learning_rate": 8.976993725561517e-05,
|
| 278 |
+
"loss": 2.5679,
|
| 279 |
+
"step": 2250
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 0.1,
|
| 283 |
+
"learning_rate": 8.954260252796217e-05,
|
| 284 |
+
"loss": 2.5515,
|
| 285 |
+
"step": 2300
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 0.11,
|
| 289 |
+
"learning_rate": 8.931526780030917e-05,
|
| 290 |
+
"loss": 2.5713,
|
| 291 |
+
"step": 2350
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 0.11,
|
| 295 |
+
"learning_rate": 8.908793307265618e-05,
|
| 296 |
+
"loss": 2.5587,
|
| 297 |
+
"step": 2400
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.11,
|
| 301 |
+
"learning_rate": 8.886059834500318e-05,
|
| 302 |
+
"loss": 2.5774,
|
| 303 |
+
"step": 2450
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.11,
|
| 307 |
+
"learning_rate": 8.863326361735019e-05,
|
| 308 |
+
"loss": 2.551,
|
| 309 |
+
"step": 2500
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 0.12,
|
| 313 |
+
"learning_rate": 8.84059288896972e-05,
|
| 314 |
+
"loss": 2.5685,
|
| 315 |
+
"step": 2550
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 0.12,
|
| 319 |
+
"learning_rate": 8.81785941620442e-05,
|
| 320 |
+
"loss": 2.5707,
|
| 321 |
+
"step": 2600
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 0.12,
|
| 325 |
+
"learning_rate": 8.795125943439119e-05,
|
| 326 |
+
"loss": 2.568,
|
| 327 |
+
"step": 2650
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 0.12,
|
| 331 |
+
"learning_rate": 8.77239247067382e-05,
|
| 332 |
+
"loss": 2.5536,
|
| 333 |
+
"step": 2700
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 0.13,
|
| 337 |
+
"learning_rate": 8.74965899790852e-05,
|
| 338 |
+
"loss": 2.5406,
|
| 339 |
+
"step": 2750
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.13,
|
| 343 |
+
"learning_rate": 8.726925525143221e-05,
|
| 344 |
+
"loss": 2.5572,
|
| 345 |
+
"step": 2800
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.13,
|
| 349 |
+
"learning_rate": 8.704192052377921e-05,
|
| 350 |
+
"loss": 2.5749,
|
| 351 |
+
"step": 2850
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 0.13,
|
| 355 |
+
"learning_rate": 8.681458579612622e-05,
|
| 356 |
+
"loss": 2.5607,
|
| 357 |
+
"step": 2900
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 0.13,
|
| 361 |
+
"learning_rate": 8.658725106847322e-05,
|
| 362 |
+
"loss": 2.5612,
|
| 363 |
+
"step": 2950
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 0.14,
|
| 367 |
+
"learning_rate": 8.635991634082023e-05,
|
| 368 |
+
"loss": 2.5626,
|
| 369 |
+
"step": 3000
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 0.14,
|
| 373 |
+
"learning_rate": 8.613258161316724e-05,
|
| 374 |
+
"loss": 2.5677,
|
| 375 |
+
"step": 3050
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 0.14,
|
| 379 |
+
"learning_rate": 8.590524688551423e-05,
|
| 380 |
+
"loss": 2.5072,
|
| 381 |
+
"step": 3100
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.14,
|
| 385 |
+
"learning_rate": 8.567791215786123e-05,
|
| 386 |
+
"loss": 2.562,
|
| 387 |
+
"step": 3150
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.15,
|
| 391 |
+
"learning_rate": 8.545057743020824e-05,
|
| 392 |
+
"loss": 2.5786,
|
| 393 |
+
"step": 3200
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 0.15,
|
| 397 |
+
"learning_rate": 8.522324270255524e-05,
|
| 398 |
+
"loss": 2.5388,
|
| 399 |
+
"step": 3250
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 0.15,
|
| 403 |
+
"learning_rate": 8.499590797490225e-05,
|
| 404 |
+
"loss": 2.538,
|
| 405 |
+
"step": 3300
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 0.15,
|
| 409 |
+
"learning_rate": 8.476857324724926e-05,
|
| 410 |
+
"loss": 2.5448,
|
| 411 |
+
"step": 3350
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 0.15,
|
| 415 |
+
"learning_rate": 8.454123851959626e-05,
|
| 416 |
+
"loss": 2.5306,
|
| 417 |
+
"step": 3400
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 0.16,
|
| 421 |
+
"learning_rate": 8.431390379194327e-05,
|
| 422 |
+
"loss": 2.5647,
|
| 423 |
+
"step": 3450
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.16,
|
| 427 |
+
"learning_rate": 8.408656906429027e-05,
|
| 428 |
+
"loss": 2.5386,
|
| 429 |
+
"step": 3500
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.16,
|
| 433 |
+
"learning_rate": 8.385923433663728e-05,
|
| 434 |
+
"loss": 2.5376,
|
| 435 |
+
"step": 3550
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 0.16,
|
| 439 |
+
"learning_rate": 8.363189960898427e-05,
|
| 440 |
+
"loss": 2.535,
|
| 441 |
+
"step": 3600
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 0.17,
|
| 445 |
+
"learning_rate": 8.340456488133128e-05,
|
| 446 |
+
"loss": 2.5476,
|
| 447 |
+
"step": 3650
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 0.17,
|
| 451 |
+
"learning_rate": 8.317723015367828e-05,
|
| 452 |
+
"loss": 2.5462,
|
| 453 |
+
"step": 3700
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 0.17,
|
| 457 |
+
"learning_rate": 8.294989542602529e-05,
|
| 458 |
+
"loss": 2.5795,
|
| 459 |
+
"step": 3750
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 0.17,
|
| 463 |
+
"learning_rate": 8.272256069837229e-05,
|
| 464 |
+
"loss": 2.5425,
|
| 465 |
+
"step": 3800
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.18,
|
| 469 |
+
"learning_rate": 8.24952259707193e-05,
|
| 470 |
+
"loss": 2.5663,
|
| 471 |
+
"step": 3850
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.18,
|
| 475 |
+
"learning_rate": 8.22678912430663e-05,
|
| 476 |
+
"loss": 2.5376,
|
| 477 |
+
"step": 3900
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 0.18,
|
| 481 |
+
"learning_rate": 8.204055651541331e-05,
|
| 482 |
+
"loss": 2.5695,
|
| 483 |
+
"step": 3950
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 0.18,
|
| 487 |
+
"learning_rate": 8.18132217877603e-05,
|
| 488 |
+
"loss": 2.5112,
|
| 489 |
+
"step": 4000
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 0.18,
|
| 493 |
+
"learning_rate": 8.15858870601073e-05,
|
| 494 |
+
"loss": 2.5255,
|
| 495 |
+
"step": 4050
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 0.19,
|
| 499 |
+
"learning_rate": 8.135855233245431e-05,
|
| 500 |
+
"loss": 2.5448,
|
| 501 |
+
"step": 4100
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 0.19,
|
| 505 |
+
"learning_rate": 8.113121760480132e-05,
|
| 506 |
+
"loss": 2.5483,
|
| 507 |
+
"step": 4150
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.19,
|
| 511 |
+
"learning_rate": 8.090388287714832e-05,
|
| 512 |
+
"loss": 2.5319,
|
| 513 |
+
"step": 4200
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.19,
|
| 517 |
+
"learning_rate": 8.067654814949533e-05,
|
| 518 |
+
"loss": 2.5655,
|
| 519 |
+
"step": 4250
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 0.2,
|
| 523 |
+
"learning_rate": 8.044921342184233e-05,
|
| 524 |
+
"loss": 2.5399,
|
| 525 |
+
"step": 4300
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 0.2,
|
| 529 |
+
"learning_rate": 8.022187869418933e-05,
|
| 530 |
+
"loss": 2.5485,
|
| 531 |
+
"step": 4350
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 0.2,
|
| 535 |
+
"learning_rate": 7.999454396653633e-05,
|
| 536 |
+
"loss": 2.5196,
|
| 537 |
+
"step": 4400
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 0.2,
|
| 541 |
+
"learning_rate": 7.976720923888334e-05,
|
| 542 |
+
"loss": 2.5554,
|
| 543 |
+
"step": 4450
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 0.2,
|
| 547 |
+
"learning_rate": 7.953987451123034e-05,
|
| 548 |
+
"loss": 2.583,
|
| 549 |
+
"step": 4500
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.21,
|
| 553 |
+
"learning_rate": 7.931253978357735e-05,
|
| 554 |
+
"loss": 2.5643,
|
| 555 |
+
"step": 4550
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.21,
|
| 559 |
+
"learning_rate": 7.908520505592435e-05,
|
| 560 |
+
"loss": 2.5345,
|
| 561 |
+
"step": 4600
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 0.21,
|
| 565 |
+
"learning_rate": 7.885787032827136e-05,
|
| 566 |
+
"loss": 2.5393,
|
| 567 |
+
"step": 4650
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 0.21,
|
| 571 |
+
"learning_rate": 7.863053560061835e-05,
|
| 572 |
+
"loss": 2.5349,
|
| 573 |
+
"step": 4700
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 0.22,
|
| 577 |
+
"learning_rate": 7.840320087296536e-05,
|
| 578 |
+
"loss": 2.54,
|
| 579 |
+
"step": 4750
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 0.22,
|
| 583 |
+
"learning_rate": 7.817586614531236e-05,
|
| 584 |
+
"loss": 2.5526,
|
| 585 |
+
"step": 4800
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 0.22,
|
| 589 |
+
"learning_rate": 7.794853141765937e-05,
|
| 590 |
+
"loss": 2.5419,
|
| 591 |
+
"step": 4850
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 0.22,
|
| 595 |
+
"learning_rate": 7.772119669000637e-05,
|
| 596 |
+
"loss": 2.5122,
|
| 597 |
+
"step": 4900
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.23,
|
| 601 |
+
"learning_rate": 7.749386196235338e-05,
|
| 602 |
+
"loss": 2.5247,
|
| 603 |
+
"step": 4950
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 0.23,
|
| 607 |
+
"learning_rate": 7.726652723470039e-05,
|
| 608 |
+
"loss": 2.5516,
|
| 609 |
+
"step": 5000
|
| 610 |
+
}
|
| 611 |
+
],
|
| 612 |
+
"logging_steps": 50,
|
| 613 |
+
"max_steps": 21994,
|
| 614 |
+
"num_train_epochs": 1,
|
| 615 |
+
"save_steps": 2500,
|
| 616 |
+
"total_flos": 8.195099590656e+16,
|
| 617 |
+
"trial_name": null,
|
| 618 |
+
"trial_params": null
|
| 619 |
+
}
|
checkpoint-5000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:efdafc920f92f7fef444725b8239e547a249e5e3d18c711b75245d4473de9d3c
|
| 3 |
+
size 4027
|
checkpoint-7500/config.json
ADDED
|
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "./model",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"LlamaForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"bos_token_id": 1,
|
| 7 |
+
"eos_token_id": 2,
|
| 8 |
+
"hidden_act": "silu",
|
| 9 |
+
"hidden_size": 4096,
|
| 10 |
+
"initializer_range": 0.02,
|
| 11 |
+
"intermediate_size": 11008,
|
| 12 |
+
"max_position_embeddings": 4096,
|
| 13 |
+
"model_type": "llama",
|
| 14 |
+
"num_attention_heads": 32,
|
| 15 |
+
"num_hidden_layers": 1,
|
| 16 |
+
"num_key_value_heads": 32,
|
| 17 |
+
"pretraining_tp": 1,
|
| 18 |
+
"rms_norm_eps": 1e-06,
|
| 19 |
+
"rope_scaling": null,
|
| 20 |
+
"rope_theta": 10000.0,
|
| 21 |
+
"tie_word_embeddings": false,
|
| 22 |
+
"torch_dtype": "bfloat16",
|
| 23 |
+
"transformers_version": "4.34.0.dev0",
|
| 24 |
+
"use_cache": true,
|
| 25 |
+
"vocab_size": 32000
|
| 26 |
+
}
|
checkpoint-7500/generation_config.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 1,
|
| 3 |
+
"do_sample": true,
|
| 4 |
+
"eos_token_id": 2,
|
| 5 |
+
"max_length": 4096,
|
| 6 |
+
"pad_token_id": 0,
|
| 7 |
+
"temperature": 0.6,
|
| 8 |
+
"top_p": 0.9,
|
| 9 |
+
"transformers_version": "4.34.0.dev0"
|
| 10 |
+
}
|
checkpoint-7500/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b821b817163fa3de34652be1509fd5796aafd26971cfac99bbbfa1aaf179617d
|
| 3 |
+
size 1858136133
|
checkpoint-7500/pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1f235329dcf7f3834f0cf92eea595b0c831138ab3a067d79812dc337820172cb
|
| 3 |
+
size 929067029
|
checkpoint-7500/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:972139d83957a9cf2600cb6eeca17287d7a5377c33a53500ae7e13fe830ad36b
|
| 3 |
+
size 14575
|
checkpoint-7500/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:435941218fd7059259cfb526648ebee61a8d078cdc01596cdb74aff24219bcd8
|
| 3 |
+
size 627
|
checkpoint-7500/special_tokens_map.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "</s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"unk_token": {
|
| 17 |
+
"content": "<unk>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
}
|
| 23 |
+
}
|
checkpoint-7500/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-7500/tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
| 3 |
+
size 499723
|
checkpoint-7500/tokenizer_config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"__type": "AddedToken",
|
| 4 |
+
"content": "<s>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false
|
| 9 |
+
},
|
| 10 |
+
"clean_up_tokenization_spaces": false,
|
| 11 |
+
"eos_token": {
|
| 12 |
+
"__type": "AddedToken",
|
| 13 |
+
"content": "</s>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": false,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false
|
| 18 |
+
},
|
| 19 |
+
"legacy": false,
|
| 20 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 21 |
+
"pad_token": null,
|
| 22 |
+
"padding_side": "right",
|
| 23 |
+
"sp_model_kwargs": {},
|
| 24 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 25 |
+
"unk_token": {
|
| 26 |
+
"__type": "AddedToken",
|
| 27 |
+
"content": "<unk>",
|
| 28 |
+
"lstrip": false,
|
| 29 |
+
"normalized": false,
|
| 30 |
+
"rstrip": false,
|
| 31 |
+
"single_word": false
|
| 32 |
+
},
|
| 33 |
+
"use_default_system_prompt": true
|
| 34 |
+
}
|
checkpoint-7500/trainer_state.json
ADDED
|
@@ -0,0 +1,919 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.3639696062106084,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 7500,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.01,
|
| 13 |
+
"learning_rate": 0.0004977264459803565,
|
| 14 |
+
"loss": 5.874,
|
| 15 |
+
"step": 50
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.02,
|
| 19 |
+
"learning_rate": 0.0004954528919607129,
|
| 20 |
+
"loss": 4.0765,
|
| 21 |
+
"step": 100
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.03,
|
| 25 |
+
"learning_rate": 0.0004931793379410695,
|
| 26 |
+
"loss": 3.7752,
|
| 27 |
+
"step": 150
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.04,
|
| 31 |
+
"learning_rate": 0.000490905783921426,
|
| 32 |
+
"loss": 3.6357,
|
| 33 |
+
"step": 200
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.05,
|
| 37 |
+
"learning_rate": 0.0004886322299017824,
|
| 38 |
+
"loss": 3.5374,
|
| 39 |
+
"step": 250
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.05,
|
| 43 |
+
"learning_rate": 0.00048635867588213893,
|
| 44 |
+
"loss": 3.4875,
|
| 45 |
+
"step": 300
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.06,
|
| 49 |
+
"learning_rate": 0.0004840851218624955,
|
| 50 |
+
"loss": 3.411,
|
| 51 |
+
"step": 350
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.07,
|
| 55 |
+
"learning_rate": 0.00048181156784285196,
|
| 56 |
+
"loss": 3.3791,
|
| 57 |
+
"step": 400
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.08,
|
| 61 |
+
"learning_rate": 0.0004795380138232084,
|
| 62 |
+
"loss": 3.3377,
|
| 63 |
+
"step": 450
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.09,
|
| 67 |
+
"learning_rate": 0.00047726445980356494,
|
| 68 |
+
"loss": 3.292,
|
| 69 |
+
"step": 500
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.1,
|
| 73 |
+
"learning_rate": 0.00047499090578392145,
|
| 74 |
+
"loss": 3.2765,
|
| 75 |
+
"step": 550
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.11,
|
| 79 |
+
"learning_rate": 0.0004727173517642779,
|
| 80 |
+
"loss": 3.2584,
|
| 81 |
+
"step": 600
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.12,
|
| 85 |
+
"learning_rate": 0.0004704437977446344,
|
| 86 |
+
"loss": 3.2319,
|
| 87 |
+
"step": 650
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.13,
|
| 91 |
+
"learning_rate": 0.0004681702437249909,
|
| 92 |
+
"loss": 3.2021,
|
| 93 |
+
"step": 700
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.14,
|
| 97 |
+
"learning_rate": 0.00046589668970534745,
|
| 98 |
+
"loss": 3.1816,
|
| 99 |
+
"step": 750
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.15,
|
| 103 |
+
"learning_rate": 0.0004636231356857039,
|
| 104 |
+
"loss": 3.165,
|
| 105 |
+
"step": 800
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.15,
|
| 109 |
+
"learning_rate": 0.0004613495816660604,
|
| 110 |
+
"loss": 3.1436,
|
| 111 |
+
"step": 850
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 0.16,
|
| 115 |
+
"learning_rate": 0.0004590760276464169,
|
| 116 |
+
"loss": 3.1491,
|
| 117 |
+
"step": 900
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 0.17,
|
| 121 |
+
"learning_rate": 0.0004568024736267734,
|
| 122 |
+
"loss": 3.1343,
|
| 123 |
+
"step": 950
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.18,
|
| 127 |
+
"learning_rate": 0.00045452891960712986,
|
| 128 |
+
"loss": 3.1208,
|
| 129 |
+
"step": 1000
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.19,
|
| 133 |
+
"learning_rate": 0.0004522553655874864,
|
| 134 |
+
"loss": 3.0954,
|
| 135 |
+
"step": 1050
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.2,
|
| 139 |
+
"learning_rate": 0.00044998181156784284,
|
| 140 |
+
"loss": 3.0963,
|
| 141 |
+
"step": 1100
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 0.21,
|
| 145 |
+
"learning_rate": 0.00044770825754819935,
|
| 146 |
+
"loss": 3.098,
|
| 147 |
+
"step": 1150
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 0.22,
|
| 151 |
+
"learning_rate": 0.00044543470352855586,
|
| 152 |
+
"loss": 3.0695,
|
| 153 |
+
"step": 1200
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 0.23,
|
| 157 |
+
"learning_rate": 0.0004431611495089123,
|
| 158 |
+
"loss": 3.0785,
|
| 159 |
+
"step": 1250
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.24,
|
| 163 |
+
"learning_rate": 0.00044088759548926884,
|
| 164 |
+
"loss": 3.0524,
|
| 165 |
+
"step": 1300
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 0.25,
|
| 169 |
+
"learning_rate": 0.0004386140414696253,
|
| 170 |
+
"loss": 3.0275,
|
| 171 |
+
"step": 1350
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.25,
|
| 175 |
+
"learning_rate": 0.0004363404874499818,
|
| 176 |
+
"loss": 3.0368,
|
| 177 |
+
"step": 1400
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.26,
|
| 181 |
+
"learning_rate": 0.00043406693343033833,
|
| 182 |
+
"loss": 3.0177,
|
| 183 |
+
"step": 1450
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 0.27,
|
| 187 |
+
"learning_rate": 0.0004317933794106948,
|
| 188 |
+
"loss": 3.0117,
|
| 189 |
+
"step": 1500
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 0.28,
|
| 193 |
+
"learning_rate": 0.0004295198253910513,
|
| 194 |
+
"loss": 3.0023,
|
| 195 |
+
"step": 1550
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 0.29,
|
| 199 |
+
"learning_rate": 0.0004272462713714078,
|
| 200 |
+
"loss": 2.9814,
|
| 201 |
+
"step": 1600
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 0.3,
|
| 205 |
+
"learning_rate": 0.0004249727173517643,
|
| 206 |
+
"loss": 2.9867,
|
| 207 |
+
"step": 1650
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 0.31,
|
| 211 |
+
"learning_rate": 0.0004226991633321208,
|
| 212 |
+
"loss": 2.991,
|
| 213 |
+
"step": 1700
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.32,
|
| 217 |
+
"learning_rate": 0.00042042560931247725,
|
| 218 |
+
"loss": 2.9764,
|
| 219 |
+
"step": 1750
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.33,
|
| 223 |
+
"learning_rate": 0.00041815205529283376,
|
| 224 |
+
"loss": 2.9587,
|
| 225 |
+
"step": 1800
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 0.34,
|
| 229 |
+
"learning_rate": 0.0004158785012731903,
|
| 230 |
+
"loss": 2.9651,
|
| 231 |
+
"step": 1850
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 0.35,
|
| 235 |
+
"learning_rate": 0.00041360494725354674,
|
| 236 |
+
"loss": 2.9606,
|
| 237 |
+
"step": 1900
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 0.35,
|
| 241 |
+
"learning_rate": 0.00041133139323390325,
|
| 242 |
+
"loss": 2.9448,
|
| 243 |
+
"step": 1950
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 0.36,
|
| 247 |
+
"learning_rate": 0.00040905783921425977,
|
| 248 |
+
"loss": 2.9585,
|
| 249 |
+
"step": 2000
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 0.37,
|
| 253 |
+
"learning_rate": 0.00040678428519461623,
|
| 254 |
+
"loss": 2.9607,
|
| 255 |
+
"step": 2050
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.38,
|
| 259 |
+
"learning_rate": 0.00040451073117497274,
|
| 260 |
+
"loss": 2.9199,
|
| 261 |
+
"step": 2100
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.39,
|
| 265 |
+
"learning_rate": 0.0004022371771553292,
|
| 266 |
+
"loss": 2.9303,
|
| 267 |
+
"step": 2150
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 0.4,
|
| 271 |
+
"learning_rate": 0.0003999636231356857,
|
| 272 |
+
"loss": 2.9353,
|
| 273 |
+
"step": 2200
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 0.41,
|
| 277 |
+
"learning_rate": 0.00039769006911604223,
|
| 278 |
+
"loss": 2.9123,
|
| 279 |
+
"step": 2250
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 0.42,
|
| 283 |
+
"learning_rate": 0.0003954165150963987,
|
| 284 |
+
"loss": 2.9161,
|
| 285 |
+
"step": 2300
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 0.43,
|
| 289 |
+
"learning_rate": 0.0003931429610767552,
|
| 290 |
+
"loss": 2.9146,
|
| 291 |
+
"step": 2350
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 0.44,
|
| 295 |
+
"learning_rate": 0.00039086940705711167,
|
| 296 |
+
"loss": 2.9086,
|
| 297 |
+
"step": 2400
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.45,
|
| 301 |
+
"learning_rate": 0.0003885958530374682,
|
| 302 |
+
"loss": 2.9094,
|
| 303 |
+
"step": 2450
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.45,
|
| 307 |
+
"learning_rate": 0.0003863222990178247,
|
| 308 |
+
"loss": 2.8968,
|
| 309 |
+
"step": 2500
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 0.46,
|
| 313 |
+
"learning_rate": 0.00038404874499818115,
|
| 314 |
+
"loss": 2.9008,
|
| 315 |
+
"step": 2550
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 0.47,
|
| 319 |
+
"learning_rate": 0.0003817751909785376,
|
| 320 |
+
"loss": 2.8836,
|
| 321 |
+
"step": 2600
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 0.48,
|
| 325 |
+
"learning_rate": 0.0003795016369588942,
|
| 326 |
+
"loss": 2.8773,
|
| 327 |
+
"step": 2650
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 0.49,
|
| 331 |
+
"learning_rate": 0.00037722808293925064,
|
| 332 |
+
"loss": 2.8648,
|
| 333 |
+
"step": 2700
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 0.5,
|
| 337 |
+
"learning_rate": 0.00037495452891960716,
|
| 338 |
+
"loss": 2.8699,
|
| 339 |
+
"step": 2750
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.51,
|
| 343 |
+
"learning_rate": 0.0003726809748999636,
|
| 344 |
+
"loss": 2.8693,
|
| 345 |
+
"step": 2800
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.52,
|
| 349 |
+
"learning_rate": 0.00037040742088032013,
|
| 350 |
+
"loss": 2.8619,
|
| 351 |
+
"step": 2850
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 0.53,
|
| 355 |
+
"learning_rate": 0.00036813386686067665,
|
| 356 |
+
"loss": 2.8591,
|
| 357 |
+
"step": 2900
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 0.54,
|
| 361 |
+
"learning_rate": 0.0003658603128410331,
|
| 362 |
+
"loss": 2.8614,
|
| 363 |
+
"step": 2950
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 0.55,
|
| 367 |
+
"learning_rate": 0.00036358675882138957,
|
| 368 |
+
"loss": 2.8605,
|
| 369 |
+
"step": 3000
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 0.55,
|
| 373 |
+
"learning_rate": 0.00036131320480174613,
|
| 374 |
+
"loss": 2.8357,
|
| 375 |
+
"step": 3050
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 0.56,
|
| 379 |
+
"learning_rate": 0.0003590396507821026,
|
| 380 |
+
"loss": 2.847,
|
| 381 |
+
"step": 3100
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.57,
|
| 385 |
+
"learning_rate": 0.00035676609676245905,
|
| 386 |
+
"loss": 2.8503,
|
| 387 |
+
"step": 3150
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.58,
|
| 391 |
+
"learning_rate": 0.00035449254274281557,
|
| 392 |
+
"loss": 2.8334,
|
| 393 |
+
"step": 3200
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 0.59,
|
| 397 |
+
"learning_rate": 0.0003522189887231721,
|
| 398 |
+
"loss": 2.8424,
|
| 399 |
+
"step": 3250
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 0.6,
|
| 403 |
+
"learning_rate": 0.0003499454347035286,
|
| 404 |
+
"loss": 2.8295,
|
| 405 |
+
"step": 3300
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 0.61,
|
| 409 |
+
"learning_rate": 0.00034767188068388506,
|
| 410 |
+
"loss": 2.8359,
|
| 411 |
+
"step": 3350
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 0.62,
|
| 415 |
+
"learning_rate": 0.0003453983266642415,
|
| 416 |
+
"loss": 2.8252,
|
| 417 |
+
"step": 3400
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 0.63,
|
| 421 |
+
"learning_rate": 0.00034312477264459803,
|
| 422 |
+
"loss": 2.82,
|
| 423 |
+
"step": 3450
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.64,
|
| 427 |
+
"learning_rate": 0.00034085121862495455,
|
| 428 |
+
"loss": 2.8134,
|
| 429 |
+
"step": 3500
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.65,
|
| 433 |
+
"learning_rate": 0.000338577664605311,
|
| 434 |
+
"loss": 2.8168,
|
| 435 |
+
"step": 3550
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 0.65,
|
| 439 |
+
"learning_rate": 0.0003363041105856675,
|
| 440 |
+
"loss": 2.8248,
|
| 441 |
+
"step": 3600
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 0.66,
|
| 445 |
+
"learning_rate": 0.000334030556566024,
|
| 446 |
+
"loss": 2.8096,
|
| 447 |
+
"step": 3650
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 0.67,
|
| 451 |
+
"learning_rate": 0.00033175700254638055,
|
| 452 |
+
"loss": 2.8154,
|
| 453 |
+
"step": 3700
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 0.68,
|
| 457 |
+
"learning_rate": 0.000329483448526737,
|
| 458 |
+
"loss": 2.8015,
|
| 459 |
+
"step": 3750
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 0.69,
|
| 463 |
+
"learning_rate": 0.00032720989450709347,
|
| 464 |
+
"loss": 2.8024,
|
| 465 |
+
"step": 3800
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.7,
|
| 469 |
+
"learning_rate": 0.00032493634048745,
|
| 470 |
+
"loss": 2.7998,
|
| 471 |
+
"step": 3850
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.71,
|
| 475 |
+
"learning_rate": 0.0003226627864678065,
|
| 476 |
+
"loss": 2.8011,
|
| 477 |
+
"step": 3900
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 0.72,
|
| 481 |
+
"learning_rate": 0.00032038923244816296,
|
| 482 |
+
"loss": 2.7963,
|
| 483 |
+
"step": 3950
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 0.73,
|
| 487 |
+
"learning_rate": 0.00031811567842851947,
|
| 488 |
+
"loss": 2.7863,
|
| 489 |
+
"step": 4000
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 0.74,
|
| 493 |
+
"learning_rate": 0.00031584212440887593,
|
| 494 |
+
"loss": 2.7973,
|
| 495 |
+
"step": 4050
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 0.75,
|
| 499 |
+
"learning_rate": 0.0003135685703892325,
|
| 500 |
+
"loss": 2.788,
|
| 501 |
+
"step": 4100
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 0.75,
|
| 505 |
+
"learning_rate": 0.00031129501636958896,
|
| 506 |
+
"loss": 2.8026,
|
| 507 |
+
"step": 4150
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.76,
|
| 511 |
+
"learning_rate": 0.0003090214623499454,
|
| 512 |
+
"loss": 2.7902,
|
| 513 |
+
"step": 4200
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.77,
|
| 517 |
+
"learning_rate": 0.00030674790833030193,
|
| 518 |
+
"loss": 2.7684,
|
| 519 |
+
"step": 4250
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 0.78,
|
| 523 |
+
"learning_rate": 0.00030447435431065845,
|
| 524 |
+
"loss": 2.7846,
|
| 525 |
+
"step": 4300
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 0.79,
|
| 529 |
+
"learning_rate": 0.0003022008002910149,
|
| 530 |
+
"loss": 2.7703,
|
| 531 |
+
"step": 4350
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 0.8,
|
| 535 |
+
"learning_rate": 0.0002999272462713714,
|
| 536 |
+
"loss": 2.7746,
|
| 537 |
+
"step": 4400
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 0.81,
|
| 541 |
+
"learning_rate": 0.0002976536922517279,
|
| 542 |
+
"loss": 2.7674,
|
| 543 |
+
"step": 4450
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 0.82,
|
| 547 |
+
"learning_rate": 0.00029538013823208445,
|
| 548 |
+
"loss": 2.7686,
|
| 549 |
+
"step": 4500
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.83,
|
| 553 |
+
"learning_rate": 0.0002931065842124409,
|
| 554 |
+
"loss": 2.7773,
|
| 555 |
+
"step": 4550
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.84,
|
| 559 |
+
"learning_rate": 0.00029083303019279737,
|
| 560 |
+
"loss": 2.7475,
|
| 561 |
+
"step": 4600
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 0.85,
|
| 565 |
+
"learning_rate": 0.0002885594761731539,
|
| 566 |
+
"loss": 2.7616,
|
| 567 |
+
"step": 4650
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 0.85,
|
| 571 |
+
"learning_rate": 0.00028628592215351035,
|
| 572 |
+
"loss": 2.756,
|
| 573 |
+
"step": 4700
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 0.86,
|
| 577 |
+
"learning_rate": 0.00028401236813386686,
|
| 578 |
+
"loss": 2.7548,
|
| 579 |
+
"step": 4750
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 0.87,
|
| 583 |
+
"learning_rate": 0.0002817388141142234,
|
| 584 |
+
"loss": 2.7499,
|
| 585 |
+
"step": 4800
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 0.88,
|
| 589 |
+
"learning_rate": 0.00027946526009457983,
|
| 590 |
+
"loss": 2.7637,
|
| 591 |
+
"step": 4850
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 0.89,
|
| 595 |
+
"learning_rate": 0.00027719170607493635,
|
| 596 |
+
"loss": 2.7349,
|
| 597 |
+
"step": 4900
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.9,
|
| 601 |
+
"learning_rate": 0.00027491815205529286,
|
| 602 |
+
"loss": 2.7346,
|
| 603 |
+
"step": 4950
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 0.91,
|
| 607 |
+
"learning_rate": 0.0002726445980356493,
|
| 608 |
+
"loss": 2.7384,
|
| 609 |
+
"step": 5000
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 0.92,
|
| 613 |
+
"learning_rate": 0.00027037104401600584,
|
| 614 |
+
"loss": 2.724,
|
| 615 |
+
"step": 5050
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 0.93,
|
| 619 |
+
"learning_rate": 0.0002680974899963623,
|
| 620 |
+
"loss": 2.7508,
|
| 621 |
+
"step": 5100
|
| 622 |
+
},
|
| 623 |
+
{
|
| 624 |
+
"epoch": 0.94,
|
| 625 |
+
"learning_rate": 0.0002658239359767188,
|
| 626 |
+
"loss": 2.7523,
|
| 627 |
+
"step": 5150
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 0.95,
|
| 631 |
+
"learning_rate": 0.0002635503819570753,
|
| 632 |
+
"loss": 2.7298,
|
| 633 |
+
"step": 5200
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 0.95,
|
| 637 |
+
"learning_rate": 0.0002612768279374318,
|
| 638 |
+
"loss": 2.7281,
|
| 639 |
+
"step": 5250
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.96,
|
| 643 |
+
"learning_rate": 0.0002590032739177883,
|
| 644 |
+
"loss": 2.7215,
|
| 645 |
+
"step": 5300
|
| 646 |
+
},
|
| 647 |
+
{
|
| 648 |
+
"epoch": 0.97,
|
| 649 |
+
"learning_rate": 0.0002567297198981448,
|
| 650 |
+
"loss": 2.7318,
|
| 651 |
+
"step": 5350
|
| 652 |
+
},
|
| 653 |
+
{
|
| 654 |
+
"epoch": 0.98,
|
| 655 |
+
"learning_rate": 0.0002544561658785013,
|
| 656 |
+
"loss": 2.7282,
|
| 657 |
+
"step": 5400
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"epoch": 0.99,
|
| 661 |
+
"learning_rate": 0.0002521826118588578,
|
| 662 |
+
"loss": 2.7313,
|
| 663 |
+
"step": 5450
|
| 664 |
+
},
|
| 665 |
+
{
|
| 666 |
+
"epoch": 1.0,
|
| 667 |
+
"learning_rate": 0.0002499090578392143,
|
| 668 |
+
"loss": 2.7133,
|
| 669 |
+
"step": 5500
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 1.01,
|
| 673 |
+
"learning_rate": 0.00024763550381957076,
|
| 674 |
+
"loss": 2.6344,
|
| 675 |
+
"step": 5550
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 1.02,
|
| 679 |
+
"learning_rate": 0.0002453619497999273,
|
| 680 |
+
"loss": 2.6231,
|
| 681 |
+
"step": 5600
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 1.03,
|
| 685 |
+
"learning_rate": 0.00024308839578028374,
|
| 686 |
+
"loss": 2.609,
|
| 687 |
+
"step": 5650
|
| 688 |
+
},
|
| 689 |
+
{
|
| 690 |
+
"epoch": 1.04,
|
| 691 |
+
"learning_rate": 0.00024081484176064022,
|
| 692 |
+
"loss": 2.6154,
|
| 693 |
+
"step": 5700
|
| 694 |
+
},
|
| 695 |
+
{
|
| 696 |
+
"epoch": 1.05,
|
| 697 |
+
"learning_rate": 0.00023854128774099674,
|
| 698 |
+
"loss": 2.6371,
|
| 699 |
+
"step": 5750
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 1.05,
|
| 703 |
+
"learning_rate": 0.0002362677337213532,
|
| 704 |
+
"loss": 2.6082,
|
| 705 |
+
"step": 5800
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 1.06,
|
| 709 |
+
"learning_rate": 0.0002339941797017097,
|
| 710 |
+
"loss": 2.6218,
|
| 711 |
+
"step": 5850
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 1.07,
|
| 715 |
+
"learning_rate": 0.0002317206256820662,
|
| 716 |
+
"loss": 2.6284,
|
| 717 |
+
"step": 5900
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 1.08,
|
| 721 |
+
"learning_rate": 0.00022944707166242271,
|
| 722 |
+
"loss": 2.6191,
|
| 723 |
+
"step": 5950
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 1.09,
|
| 727 |
+
"learning_rate": 0.00022717351764277917,
|
| 728 |
+
"loss": 2.6252,
|
| 729 |
+
"step": 6000
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 1.1,
|
| 733 |
+
"learning_rate": 0.0002248999636231357,
|
| 734 |
+
"loss": 2.6266,
|
| 735 |
+
"step": 6050
|
| 736 |
+
},
|
| 737 |
+
{
|
| 738 |
+
"epoch": 1.11,
|
| 739 |
+
"learning_rate": 0.00022262640960349218,
|
| 740 |
+
"loss": 2.6426,
|
| 741 |
+
"step": 6100
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 1.12,
|
| 745 |
+
"learning_rate": 0.0002203528555838487,
|
| 746 |
+
"loss": 2.6072,
|
| 747 |
+
"step": 6150
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 1.13,
|
| 751 |
+
"learning_rate": 0.00021807930156420515,
|
| 752 |
+
"loss": 2.614,
|
| 753 |
+
"step": 6200
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 1.14,
|
| 757 |
+
"learning_rate": 0.00021580574754456166,
|
| 758 |
+
"loss": 2.5959,
|
| 759 |
+
"step": 6250
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 1.15,
|
| 763 |
+
"learning_rate": 0.00021353219352491815,
|
| 764 |
+
"loss": 2.6065,
|
| 765 |
+
"step": 6300
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 1.15,
|
| 769 |
+
"learning_rate": 0.00021125863950527467,
|
| 770 |
+
"loss": 2.6163,
|
| 771 |
+
"step": 6350
|
| 772 |
+
},
|
| 773 |
+
{
|
| 774 |
+
"epoch": 1.16,
|
| 775 |
+
"learning_rate": 0.00020898508548563113,
|
| 776 |
+
"loss": 2.6083,
|
| 777 |
+
"step": 6400
|
| 778 |
+
},
|
| 779 |
+
{
|
| 780 |
+
"epoch": 1.17,
|
| 781 |
+
"learning_rate": 0.00020671153146598764,
|
| 782 |
+
"loss": 2.6119,
|
| 783 |
+
"step": 6450
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 1.18,
|
| 787 |
+
"learning_rate": 0.00020443797744634413,
|
| 788 |
+
"loss": 2.6023,
|
| 789 |
+
"step": 6500
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 1.19,
|
| 793 |
+
"learning_rate": 0.00020216442342670064,
|
| 794 |
+
"loss": 2.6086,
|
| 795 |
+
"step": 6550
|
| 796 |
+
},
|
| 797 |
+
{
|
| 798 |
+
"epoch": 1.2,
|
| 799 |
+
"learning_rate": 0.0001998908694070571,
|
| 800 |
+
"loss": 2.5988,
|
| 801 |
+
"step": 6600
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 1.21,
|
| 805 |
+
"learning_rate": 0.00019761731538741362,
|
| 806 |
+
"loss": 2.6046,
|
| 807 |
+
"step": 6650
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 1.22,
|
| 811 |
+
"learning_rate": 0.0001953437613677701,
|
| 812 |
+
"loss": 2.5929,
|
| 813 |
+
"step": 6700
|
| 814 |
+
},
|
| 815 |
+
{
|
| 816 |
+
"epoch": 1.23,
|
| 817 |
+
"learning_rate": 0.00019307020734812662,
|
| 818 |
+
"loss": 2.5935,
|
| 819 |
+
"step": 6750
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"epoch": 1.24,
|
| 823 |
+
"learning_rate": 0.00019079665332848308,
|
| 824 |
+
"loss": 2.5875,
|
| 825 |
+
"step": 6800
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 1.25,
|
| 829 |
+
"learning_rate": 0.00018852309930883956,
|
| 830 |
+
"loss": 2.6001,
|
| 831 |
+
"step": 6850
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 1.25,
|
| 835 |
+
"learning_rate": 0.00018624954528919608,
|
| 836 |
+
"loss": 2.6021,
|
| 837 |
+
"step": 6900
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 1.26,
|
| 841 |
+
"learning_rate": 0.00018397599126955257,
|
| 842 |
+
"loss": 2.5887,
|
| 843 |
+
"step": 6950
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 1.27,
|
| 847 |
+
"learning_rate": 0.00018170243724990905,
|
| 848 |
+
"loss": 2.6022,
|
| 849 |
+
"step": 7000
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 1.28,
|
| 853 |
+
"learning_rate": 0.00017942888323026554,
|
| 854 |
+
"loss": 2.5965,
|
| 855 |
+
"step": 7050
|
| 856 |
+
},
|
| 857 |
+
{
|
| 858 |
+
"epoch": 1.29,
|
| 859 |
+
"learning_rate": 0.00017715532921062205,
|
| 860 |
+
"loss": 2.5879,
|
| 861 |
+
"step": 7100
|
| 862 |
+
},
|
| 863 |
+
{
|
| 864 |
+
"epoch": 1.3,
|
| 865 |
+
"learning_rate": 0.00017488177519097854,
|
| 866 |
+
"loss": 2.5935,
|
| 867 |
+
"step": 7150
|
| 868 |
+
},
|
| 869 |
+
{
|
| 870 |
+
"epoch": 1.31,
|
| 871 |
+
"learning_rate": 0.00017260822117133503,
|
| 872 |
+
"loss": 2.6041,
|
| 873 |
+
"step": 7200
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 1.32,
|
| 877 |
+
"learning_rate": 0.00017033466715169152,
|
| 878 |
+
"loss": 2.6041,
|
| 879 |
+
"step": 7250
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 1.33,
|
| 883 |
+
"learning_rate": 0.00016806111313204803,
|
| 884 |
+
"loss": 2.6024,
|
| 885 |
+
"step": 7300
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 1.34,
|
| 889 |
+
"learning_rate": 0.00016578755911240452,
|
| 890 |
+
"loss": 2.5995,
|
| 891 |
+
"step": 7350
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 1.35,
|
| 895 |
+
"learning_rate": 0.000163514005092761,
|
| 896 |
+
"loss": 2.5959,
|
| 897 |
+
"step": 7400
|
| 898 |
+
},
|
| 899 |
+
{
|
| 900 |
+
"epoch": 1.35,
|
| 901 |
+
"learning_rate": 0.0001612404510731175,
|
| 902 |
+
"loss": 2.579,
|
| 903 |
+
"step": 7450
|
| 904 |
+
},
|
| 905 |
+
{
|
| 906 |
+
"epoch": 1.36,
|
| 907 |
+
"learning_rate": 0.000158966897053474,
|
| 908 |
+
"loss": 2.5807,
|
| 909 |
+
"step": 7500
|
| 910 |
+
}
|
| 911 |
+
],
|
| 912 |
+
"logging_steps": 50,
|
| 913 |
+
"max_steps": 10996,
|
| 914 |
+
"num_train_epochs": 2,
|
| 915 |
+
"save_steps": 2500,
|
| 916 |
+
"total_flos": 4.9170597543936e+17,
|
| 917 |
+
"trial_name": null,
|
| 918 |
+
"trial_params": null
|
| 919 |
+
}
|
checkpoint-7500/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:efdafc920f92f7fef444725b8239e547a249e5e3d18c711b75245d4473de9d3c
|
| 3 |
+
size 4027
|