Training in progress, step 5417
Browse files- README.md +53 -0
- all_results.json +9 -0
- config.json +29 -0
- generation_config.json +7 -0
- model.safetensors +3 -0
- special_tokens_map.json +30 -0
- tokenizer.json +0 -0
- tokenizer_config.json +41 -0
- train_results.json +9 -0
- trainer_state.json +1477 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,53 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
base_model: Josephgflowers/TinyLlama-Cinder-Agent-Rag
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
model-index:
|
| 7 |
+
- name: TinyLlama-Cinder-Math-Train
|
| 8 |
+
results: []
|
| 9 |
+
---
|
| 10 |
+
|
| 11 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 12 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 13 |
+
|
| 14 |
+
# TinyLlama-Cinder-Math-Train
|
| 15 |
+
|
| 16 |
+
This model is a fine-tuned version of [Josephgflowers/TinyLlama-Cinder-Agent-Rag](https://huggingface.co/Josephgflowers/TinyLlama-Cinder-Agent-Rag) on an unknown dataset.
|
| 17 |
+
|
| 18 |
+
## Model description
|
| 19 |
+
|
| 20 |
+
More information needed
|
| 21 |
+
|
| 22 |
+
## Intended uses & limitations
|
| 23 |
+
|
| 24 |
+
More information needed
|
| 25 |
+
|
| 26 |
+
## Training and evaluation data
|
| 27 |
+
|
| 28 |
+
More information needed
|
| 29 |
+
|
| 30 |
+
## Training procedure
|
| 31 |
+
|
| 32 |
+
### Training hyperparameters
|
| 33 |
+
|
| 34 |
+
The following hyperparameters were used during training:
|
| 35 |
+
- learning_rate: 5e-05
|
| 36 |
+
- train_batch_size: 12
|
| 37 |
+
- eval_batch_size: 32
|
| 38 |
+
- seed: 42
|
| 39 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 40 |
+
- lr_scheduler_type: linear
|
| 41 |
+
- num_epochs: 1.0
|
| 42 |
+
- mixed_precision_training: Native AMP
|
| 43 |
+
|
| 44 |
+
### Training results
|
| 45 |
+
|
| 46 |
+
|
| 47 |
+
|
| 48 |
+
### Framework versions
|
| 49 |
+
|
| 50 |
+
- Transformers 4.41.0.dev0
|
| 51 |
+
- Pytorch 2.2.2+cu121
|
| 52 |
+
- Datasets 2.19.1
|
| 53 |
+
- Tokenizers 0.19.1
|
all_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"total_flos": 3.1397459461543035e+18,
|
| 4 |
+
"train_loss": 0.4062042611626282,
|
| 5 |
+
"train_runtime": 286226.4367,
|
| 6 |
+
"train_samples": 246989,
|
| 7 |
+
"train_samples_per_second": 0.863,
|
| 8 |
+
"train_steps_per_second": 0.072
|
| 9 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "Josephgflowers/TinyLlama-Cinder-Math-Train",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"LlamaForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_bias": false,
|
| 7 |
+
"attention_dropout": 0.0,
|
| 8 |
+
"bos_token_id": 1,
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
+
"hidden_act": "silu",
|
| 11 |
+
"hidden_size": 2048,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 5632,
|
| 14 |
+
"max_position_embeddings": 2048,
|
| 15 |
+
"mlp_bias": false,
|
| 16 |
+
"model_type": "llama",
|
| 17 |
+
"num_attention_heads": 32,
|
| 18 |
+
"num_hidden_layers": 22,
|
| 19 |
+
"num_key_value_heads": 4,
|
| 20 |
+
"pretraining_tp": 1,
|
| 21 |
+
"rms_norm_eps": 1e-05,
|
| 22 |
+
"rope_scaling": null,
|
| 23 |
+
"rope_theta": 10000.0,
|
| 24 |
+
"tie_word_embeddings": false,
|
| 25 |
+
"torch_dtype": "float32",
|
| 26 |
+
"transformers_version": "4.41.0.dev0",
|
| 27 |
+
"use_cache": false,
|
| 28 |
+
"vocab_size": 32000
|
| 29 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 1,
|
| 3 |
+
"eos_token_id": 2,
|
| 4 |
+
"max_length": 2048,
|
| 5 |
+
"pad_token_id": 0,
|
| 6 |
+
"transformers_version": "4.41.0.dev0"
|
| 7 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f98e7a5b86f5dc56907ec422b9d7ac96360cbb6b4219cb14c14fb8deff699a8b
|
| 3 |
+
size 4400216536
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"pad_token": {
|
| 17 |
+
"content": "</s>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"unk_token": {
|
| 24 |
+
"content": "<unk>",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
}
|
| 30 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"0": {
|
| 6 |
+
"content": "<unk>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"1": {
|
| 14 |
+
"content": "<s>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"2": {
|
| 22 |
+
"content": "</s>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
}
|
| 29 |
+
},
|
| 30 |
+
"bos_token": "<s>",
|
| 31 |
+
"chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n' + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
|
| 32 |
+
"clean_up_tokenization_spaces": false,
|
| 33 |
+
"eos_token": "</s>",
|
| 34 |
+
"model_max_length": 2048,
|
| 35 |
+
"pad_token": "</s>",
|
| 36 |
+
"padding_side": "right",
|
| 37 |
+
"sp_model_kwargs": {},
|
| 38 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 39 |
+
"unk_token": "<unk>",
|
| 40 |
+
"use_default_system_prompt": false
|
| 41 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"total_flos": 3.1397459461543035e+18,
|
| 4 |
+
"train_loss": 0.4062042611626282,
|
| 5 |
+
"train_runtime": 286226.4367,
|
| 6 |
+
"train_samples": 246989,
|
| 7 |
+
"train_samples_per_second": 0.863,
|
| 8 |
+
"train_steps_per_second": 0.072
|
| 9 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1477 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 20583,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.004858378273332362,
|
| 13 |
+
"grad_norm": 66137.25,
|
| 14 |
+
"learning_rate": 4.9757081086333386e-05,
|
| 15 |
+
"loss": 0.5598,
|
| 16 |
+
"step": 100
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.009716756546664724,
|
| 20 |
+
"grad_norm": 60222.27734375,
|
| 21 |
+
"learning_rate": 4.951416217266677e-05,
|
| 22 |
+
"loss": 0.5419,
|
| 23 |
+
"step": 200
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.014575134819997084,
|
| 27 |
+
"grad_norm": 67718.328125,
|
| 28 |
+
"learning_rate": 4.927124325900015e-05,
|
| 29 |
+
"loss": 0.5491,
|
| 30 |
+
"step": 300
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.019433513093329448,
|
| 34 |
+
"grad_norm": 73856.1015625,
|
| 35 |
+
"learning_rate": 4.902832434533353e-05,
|
| 36 |
+
"loss": 0.5496,
|
| 37 |
+
"step": 400
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.024291891366661808,
|
| 41 |
+
"grad_norm": 60560.8359375,
|
| 42 |
+
"learning_rate": 4.878540543166691e-05,
|
| 43 |
+
"loss": 0.5381,
|
| 44 |
+
"step": 500
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.029150269639994168,
|
| 48 |
+
"grad_norm": 76622.125,
|
| 49 |
+
"learning_rate": 4.8542486518000295e-05,
|
| 50 |
+
"loss": 0.5397,
|
| 51 |
+
"step": 600
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.03400864791332653,
|
| 55 |
+
"grad_norm": 55521.8203125,
|
| 56 |
+
"learning_rate": 4.829956760433367e-05,
|
| 57 |
+
"loss": 0.5339,
|
| 58 |
+
"step": 700
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.038867026186658896,
|
| 62 |
+
"grad_norm": 59273.4921875,
|
| 63 |
+
"learning_rate": 4.8056648690667055e-05,
|
| 64 |
+
"loss": 0.5342,
|
| 65 |
+
"step": 800
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.043725404459991256,
|
| 69 |
+
"grad_norm": 63513.421875,
|
| 70 |
+
"learning_rate": 4.781372977700044e-05,
|
| 71 |
+
"loss": 0.5247,
|
| 72 |
+
"step": 900
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.048583782733323616,
|
| 76 |
+
"grad_norm": 61088.77734375,
|
| 77 |
+
"learning_rate": 4.757081086333382e-05,
|
| 78 |
+
"loss": 0.5302,
|
| 79 |
+
"step": 1000
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.053442161006655976,
|
| 83 |
+
"grad_norm": 71392.75,
|
| 84 |
+
"learning_rate": 4.7327891949667204e-05,
|
| 85 |
+
"loss": 0.5261,
|
| 86 |
+
"step": 1100
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.058300539279988337,
|
| 90 |
+
"grad_norm": 72375.1328125,
|
| 91 |
+
"learning_rate": 4.708497303600059e-05,
|
| 92 |
+
"loss": 0.5153,
|
| 93 |
+
"step": 1200
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.0631589175533207,
|
| 97 |
+
"grad_norm": 65540.171875,
|
| 98 |
+
"learning_rate": 4.6842054122333964e-05,
|
| 99 |
+
"loss": 0.5068,
|
| 100 |
+
"step": 1300
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.06801729582665306,
|
| 104 |
+
"grad_norm": 63439.60546875,
|
| 105 |
+
"learning_rate": 4.659913520866735e-05,
|
| 106 |
+
"loss": 0.5087,
|
| 107 |
+
"step": 1400
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.07287567409998542,
|
| 111 |
+
"grad_norm": 56190.2265625,
|
| 112 |
+
"learning_rate": 4.635621629500073e-05,
|
| 113 |
+
"loss": 0.5074,
|
| 114 |
+
"step": 1500
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.07773405237331779,
|
| 118 |
+
"grad_norm": 72489.0234375,
|
| 119 |
+
"learning_rate": 4.6113297381334114e-05,
|
| 120 |
+
"loss": 0.5036,
|
| 121 |
+
"step": 1600
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.08259243064665014,
|
| 125 |
+
"grad_norm": 55422.61328125,
|
| 126 |
+
"learning_rate": 4.58703784676675e-05,
|
| 127 |
+
"loss": 0.4979,
|
| 128 |
+
"step": 1700
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.08745080891998251,
|
| 132 |
+
"grad_norm": 58258.125,
|
| 133 |
+
"learning_rate": 4.562745955400088e-05,
|
| 134 |
+
"loss": 0.5016,
|
| 135 |
+
"step": 1800
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.09230918719331486,
|
| 139 |
+
"grad_norm": 57958.55859375,
|
| 140 |
+
"learning_rate": 4.5384540640334264e-05,
|
| 141 |
+
"loss": 0.508,
|
| 142 |
+
"step": 1900
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.09716756546664723,
|
| 146 |
+
"grad_norm": 52961.26953125,
|
| 147 |
+
"learning_rate": 4.514162172666764e-05,
|
| 148 |
+
"loss": 0.4843,
|
| 149 |
+
"step": 2000
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.1020259437399796,
|
| 153 |
+
"grad_norm": 57415.234375,
|
| 154 |
+
"learning_rate": 4.489870281300102e-05,
|
| 155 |
+
"loss": 0.4943,
|
| 156 |
+
"step": 2100
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.10688432201331195,
|
| 160 |
+
"grad_norm": 49461.50390625,
|
| 161 |
+
"learning_rate": 4.46557838993344e-05,
|
| 162 |
+
"loss": 0.4817,
|
| 163 |
+
"step": 2200
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.11174270028664432,
|
| 167 |
+
"grad_norm": 51018.04296875,
|
| 168 |
+
"learning_rate": 4.441286498566778e-05,
|
| 169 |
+
"loss": 0.4825,
|
| 170 |
+
"step": 2300
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.11660107855997667,
|
| 174 |
+
"grad_norm": 52488.46484375,
|
| 175 |
+
"learning_rate": 4.4169946072001166e-05,
|
| 176 |
+
"loss": 0.4786,
|
| 177 |
+
"step": 2400
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.12145945683330904,
|
| 181 |
+
"grad_norm": 61512.5078125,
|
| 182 |
+
"learning_rate": 4.392702715833455e-05,
|
| 183 |
+
"loss": 0.4775,
|
| 184 |
+
"step": 2500
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.1263178351066414,
|
| 188 |
+
"grad_norm": 56490.4296875,
|
| 189 |
+
"learning_rate": 4.368410824466793e-05,
|
| 190 |
+
"loss": 0.4813,
|
| 191 |
+
"step": 2600
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.13117621337997376,
|
| 195 |
+
"grad_norm": 63387.01171875,
|
| 196 |
+
"learning_rate": 4.3441189331001316e-05,
|
| 197 |
+
"loss": 0.4744,
|
| 198 |
+
"step": 2700
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.13603459165330611,
|
| 202 |
+
"grad_norm": 62635.20703125,
|
| 203 |
+
"learning_rate": 4.31982704173347e-05,
|
| 204 |
+
"loss": 0.4758,
|
| 205 |
+
"step": 2800
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.1408929699266385,
|
| 209 |
+
"grad_norm": 52577.96875,
|
| 210 |
+
"learning_rate": 4.2955351503668076e-05,
|
| 211 |
+
"loss": 0.4867,
|
| 212 |
+
"step": 2900
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.14575134819997085,
|
| 216 |
+
"grad_norm": 54731.5,
|
| 217 |
+
"learning_rate": 4.271243259000146e-05,
|
| 218 |
+
"loss": 0.4658,
|
| 219 |
+
"step": 3000
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.1506097264733032,
|
| 223 |
+
"grad_norm": 52055.84765625,
|
| 224 |
+
"learning_rate": 4.246951367633484e-05,
|
| 225 |
+
"loss": 0.4737,
|
| 226 |
+
"step": 3100
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.15546810474663558,
|
| 230 |
+
"grad_norm": 48978.90234375,
|
| 231 |
+
"learning_rate": 4.2226594762668225e-05,
|
| 232 |
+
"loss": 0.4765,
|
| 233 |
+
"step": 3200
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.16032648301996794,
|
| 237 |
+
"grad_norm": 54819.38671875,
|
| 238 |
+
"learning_rate": 4.198367584900161e-05,
|
| 239 |
+
"loss": 0.466,
|
| 240 |
+
"step": 3300
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.1651848612933003,
|
| 244 |
+
"grad_norm": 58637.75390625,
|
| 245 |
+
"learning_rate": 4.1740756935334985e-05,
|
| 246 |
+
"loss": 0.4725,
|
| 247 |
+
"step": 3400
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.17004323956663267,
|
| 251 |
+
"grad_norm": 55842.4609375,
|
| 252 |
+
"learning_rate": 4.149783802166837e-05,
|
| 253 |
+
"loss": 0.4724,
|
| 254 |
+
"step": 3500
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.17490161783996502,
|
| 258 |
+
"grad_norm": 52083.8125,
|
| 259 |
+
"learning_rate": 4.125491910800175e-05,
|
| 260 |
+
"loss": 0.4796,
|
| 261 |
+
"step": 3600
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.17975999611329738,
|
| 265 |
+
"grad_norm": 56764.9296875,
|
| 266 |
+
"learning_rate": 4.1012000194335135e-05,
|
| 267 |
+
"loss": 0.4736,
|
| 268 |
+
"step": 3700
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.18461837438662973,
|
| 272 |
+
"grad_norm": 50524.82421875,
|
| 273 |
+
"learning_rate": 4.076908128066851e-05,
|
| 274 |
+
"loss": 0.4627,
|
| 275 |
+
"step": 3800
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.1894767526599621,
|
| 279 |
+
"grad_norm": 50128.8359375,
|
| 280 |
+
"learning_rate": 4.0526162367001894e-05,
|
| 281 |
+
"loss": 0.4717,
|
| 282 |
+
"step": 3900
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.19433513093329446,
|
| 286 |
+
"grad_norm": 72415.296875,
|
| 287 |
+
"learning_rate": 4.028324345333528e-05,
|
| 288 |
+
"loss": 0.456,
|
| 289 |
+
"step": 4000
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.19919350920662682,
|
| 293 |
+
"grad_norm": 57324.921875,
|
| 294 |
+
"learning_rate": 4.004032453966866e-05,
|
| 295 |
+
"loss": 0.4505,
|
| 296 |
+
"step": 4100
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.2040518874799592,
|
| 300 |
+
"grad_norm": 60287.41796875,
|
| 301 |
+
"learning_rate": 3.9797405626002044e-05,
|
| 302 |
+
"loss": 0.4441,
|
| 303 |
+
"step": 4200
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.20891026575329155,
|
| 307 |
+
"grad_norm": 65722.1171875,
|
| 308 |
+
"learning_rate": 3.955448671233543e-05,
|
| 309 |
+
"loss": 0.4426,
|
| 310 |
+
"step": 4300
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.2137686440266239,
|
| 314 |
+
"grad_norm": 57532.5625,
|
| 315 |
+
"learning_rate": 3.931156779866881e-05,
|
| 316 |
+
"loss": 0.4532,
|
| 317 |
+
"step": 4400
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.2186270222999563,
|
| 321 |
+
"grad_norm": 60035.2265625,
|
| 322 |
+
"learning_rate": 3.906864888500219e-05,
|
| 323 |
+
"loss": 0.443,
|
| 324 |
+
"step": 4500
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.22348540057328864,
|
| 328 |
+
"grad_norm": 50842.09375,
|
| 329 |
+
"learning_rate": 3.882572997133557e-05,
|
| 330 |
+
"loss": 0.4527,
|
| 331 |
+
"step": 4600
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.228343778846621,
|
| 335 |
+
"grad_norm": 53098.82421875,
|
| 336 |
+
"learning_rate": 3.858281105766895e-05,
|
| 337 |
+
"loss": 0.441,
|
| 338 |
+
"step": 4700
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.23320215711995335,
|
| 342 |
+
"grad_norm": 52847.52734375,
|
| 343 |
+
"learning_rate": 3.833989214400233e-05,
|
| 344 |
+
"loss": 0.4437,
|
| 345 |
+
"step": 4800
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.23806053539328573,
|
| 349 |
+
"grad_norm": 55201.1953125,
|
| 350 |
+
"learning_rate": 3.809697323033571e-05,
|
| 351 |
+
"loss": 0.4534,
|
| 352 |
+
"step": 4900
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.24291891366661808,
|
| 356 |
+
"grad_norm": 55352.77734375,
|
| 357 |
+
"learning_rate": 3.7854054316669096e-05,
|
| 358 |
+
"loss": 0.4559,
|
| 359 |
+
"step": 5000
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.24777729193995043,
|
| 363 |
+
"grad_norm": 77840.125,
|
| 364 |
+
"learning_rate": 3.761113540300248e-05,
|
| 365 |
+
"loss": 0.4368,
|
| 366 |
+
"step": 5100
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.2526356702132828,
|
| 370 |
+
"grad_norm": 69213.84375,
|
| 371 |
+
"learning_rate": 3.736821648933586e-05,
|
| 372 |
+
"loss": 0.4428,
|
| 373 |
+
"step": 5200
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.25749404848661517,
|
| 377 |
+
"grad_norm": 61722.49609375,
|
| 378 |
+
"learning_rate": 3.7125297575669246e-05,
|
| 379 |
+
"loss": 0.444,
|
| 380 |
+
"step": 5300
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.2623524267599475,
|
| 384 |
+
"grad_norm": 56948.3125,
|
| 385 |
+
"learning_rate": 3.688237866200262e-05,
|
| 386 |
+
"loss": 0.4423,
|
| 387 |
+
"step": 5400
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.2672108050332799,
|
| 391 |
+
"grad_norm": 50691.4453125,
|
| 392 |
+
"learning_rate": 3.6639459748336006e-05,
|
| 393 |
+
"loss": 0.4371,
|
| 394 |
+
"step": 5500
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.27206918330661223,
|
| 398 |
+
"grad_norm": 48622.8671875,
|
| 399 |
+
"learning_rate": 3.639654083466939e-05,
|
| 400 |
+
"loss": 0.4459,
|
| 401 |
+
"step": 5600
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.27692756157994464,
|
| 405 |
+
"grad_norm": 58408.26171875,
|
| 406 |
+
"learning_rate": 3.615362192100277e-05,
|
| 407 |
+
"loss": 0.4215,
|
| 408 |
+
"step": 5700
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.281785939853277,
|
| 412 |
+
"grad_norm": 48251.1953125,
|
| 413 |
+
"learning_rate": 3.5910703007336156e-05,
|
| 414 |
+
"loss": 0.4204,
|
| 415 |
+
"step": 5800
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.28664431812660934,
|
| 419 |
+
"grad_norm": 73270.4453125,
|
| 420 |
+
"learning_rate": 3.566778409366954e-05,
|
| 421 |
+
"loss": 0.4421,
|
| 422 |
+
"step": 5900
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.2915026963999417,
|
| 426 |
+
"grad_norm": 52048.3828125,
|
| 427 |
+
"learning_rate": 3.5424865180002915e-05,
|
| 428 |
+
"loss": 0.4438,
|
| 429 |
+
"step": 6000
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.29636107467327405,
|
| 433 |
+
"grad_norm": 57475.203125,
|
| 434 |
+
"learning_rate": 3.51819462663363e-05,
|
| 435 |
+
"loss": 0.418,
|
| 436 |
+
"step": 6100
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.3012194529466064,
|
| 440 |
+
"grad_norm": 55124.11328125,
|
| 441 |
+
"learning_rate": 3.493902735266968e-05,
|
| 442 |
+
"loss": 0.4347,
|
| 443 |
+
"step": 6200
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.3060778312199388,
|
| 447 |
+
"grad_norm": 62276.3671875,
|
| 448 |
+
"learning_rate": 3.469610843900306e-05,
|
| 449 |
+
"loss": 0.4192,
|
| 450 |
+
"step": 6300
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.31093620949327117,
|
| 454 |
+
"grad_norm": 52723.7421875,
|
| 455 |
+
"learning_rate": 3.445318952533644e-05,
|
| 456 |
+
"loss": 0.4413,
|
| 457 |
+
"step": 6400
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.3157945877666035,
|
| 461 |
+
"grad_norm": 53744.6484375,
|
| 462 |
+
"learning_rate": 3.4210270611669825e-05,
|
| 463 |
+
"loss": 0.4324,
|
| 464 |
+
"step": 6500
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.32065296603993587,
|
| 468 |
+
"grad_norm": 44454.984375,
|
| 469 |
+
"learning_rate": 3.396735169800321e-05,
|
| 470 |
+
"loss": 0.4269,
|
| 471 |
+
"step": 6600
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.3255113443132682,
|
| 475 |
+
"grad_norm": 52088.671875,
|
| 476 |
+
"learning_rate": 3.372443278433659e-05,
|
| 477 |
+
"loss": 0.4317,
|
| 478 |
+
"step": 6700
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 0.3303697225866006,
|
| 482 |
+
"grad_norm": 50359.18359375,
|
| 483 |
+
"learning_rate": 3.3481513870669974e-05,
|
| 484 |
+
"loss": 0.4102,
|
| 485 |
+
"step": 6800
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.33522810085993293,
|
| 489 |
+
"grad_norm": 54712.453125,
|
| 490 |
+
"learning_rate": 3.323859495700336e-05,
|
| 491 |
+
"loss": 0.4194,
|
| 492 |
+
"step": 6900
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 0.34008647913326534,
|
| 496 |
+
"grad_norm": 49144.39453125,
|
| 497 |
+
"learning_rate": 3.2995676043336734e-05,
|
| 498 |
+
"loss": 0.414,
|
| 499 |
+
"step": 7000
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.3449448574065977,
|
| 503 |
+
"grad_norm": 48121.30078125,
|
| 504 |
+
"learning_rate": 3.275275712967012e-05,
|
| 505 |
+
"loss": 0.4203,
|
| 506 |
+
"step": 7100
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.34980323567993005,
|
| 510 |
+
"grad_norm": 60245.484375,
|
| 511 |
+
"learning_rate": 3.25098382160035e-05,
|
| 512 |
+
"loss": 0.4227,
|
| 513 |
+
"step": 7200
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.3546616139532624,
|
| 517 |
+
"grad_norm": 53339.56640625,
|
| 518 |
+
"learning_rate": 3.226691930233688e-05,
|
| 519 |
+
"loss": 0.4235,
|
| 520 |
+
"step": 7300
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 0.35951999222659475,
|
| 524 |
+
"grad_norm": 61334.859375,
|
| 525 |
+
"learning_rate": 3.202400038867026e-05,
|
| 526 |
+
"loss": 0.4318,
|
| 527 |
+
"step": 7400
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.3643783704999271,
|
| 531 |
+
"grad_norm": 61368.46484375,
|
| 532 |
+
"learning_rate": 3.1781081475003643e-05,
|
| 533 |
+
"loss": 0.4223,
|
| 534 |
+
"step": 7500
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.36923674877325946,
|
| 538 |
+
"grad_norm": 67382.265625,
|
| 539 |
+
"learning_rate": 3.153816256133703e-05,
|
| 540 |
+
"loss": 0.4053,
|
| 541 |
+
"step": 7600
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.37409512704659187,
|
| 545 |
+
"grad_norm": 56739.12890625,
|
| 546 |
+
"learning_rate": 3.129524364767041e-05,
|
| 547 |
+
"loss": 0.4121,
|
| 548 |
+
"step": 7700
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 0.3789535053199242,
|
| 552 |
+
"grad_norm": 51203.3203125,
|
| 553 |
+
"learning_rate": 3.105232473400379e-05,
|
| 554 |
+
"loss": 0.432,
|
| 555 |
+
"step": 7800
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.3838118835932566,
|
| 559 |
+
"grad_norm": 58815.6484375,
|
| 560 |
+
"learning_rate": 3.080940582033717e-05,
|
| 561 |
+
"loss": 0.405,
|
| 562 |
+
"step": 7900
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 0.38867026186658893,
|
| 566 |
+
"grad_norm": 59941.88671875,
|
| 567 |
+
"learning_rate": 3.056648690667055e-05,
|
| 568 |
+
"loss": 0.425,
|
| 569 |
+
"step": 8000
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.3935286401399213,
|
| 573 |
+
"grad_norm": 53543.46484375,
|
| 574 |
+
"learning_rate": 3.0323567993003936e-05,
|
| 575 |
+
"loss": 0.4103,
|
| 576 |
+
"step": 8100
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 0.39838701841325364,
|
| 580 |
+
"grad_norm": 55630.40625,
|
| 581 |
+
"learning_rate": 3.008064907933732e-05,
|
| 582 |
+
"loss": 0.3964,
|
| 583 |
+
"step": 8200
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.40324539668658604,
|
| 587 |
+
"grad_norm": 52717.6953125,
|
| 588 |
+
"learning_rate": 2.9837730165670703e-05,
|
| 589 |
+
"loss": 0.3989,
|
| 590 |
+
"step": 8300
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 0.4081037749599184,
|
| 594 |
+
"grad_norm": 50914.84375,
|
| 595 |
+
"learning_rate": 2.9594811252004086e-05,
|
| 596 |
+
"loss": 0.4097,
|
| 597 |
+
"step": 8400
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.41296215323325075,
|
| 601 |
+
"grad_norm": 61387.0390625,
|
| 602 |
+
"learning_rate": 2.9351892338337466e-05,
|
| 603 |
+
"loss": 0.4051,
|
| 604 |
+
"step": 8500
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 0.4178205315065831,
|
| 608 |
+
"grad_norm": 45076.01953125,
|
| 609 |
+
"learning_rate": 2.910897342467085e-05,
|
| 610 |
+
"loss": 0.4012,
|
| 611 |
+
"step": 8600
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.42267890977991546,
|
| 615 |
+
"grad_norm": 54953.07421875,
|
| 616 |
+
"learning_rate": 2.8866054511004225e-05,
|
| 617 |
+
"loss": 0.4202,
|
| 618 |
+
"step": 8700
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 0.4275372880532478,
|
| 622 |
+
"grad_norm": 59405.3828125,
|
| 623 |
+
"learning_rate": 2.862313559733761e-05,
|
| 624 |
+
"loss": 0.3931,
|
| 625 |
+
"step": 8800
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.43239566632658016,
|
| 629 |
+
"grad_norm": 61979.93359375,
|
| 630 |
+
"learning_rate": 2.8380216683670992e-05,
|
| 631 |
+
"loss": 0.3987,
|
| 632 |
+
"step": 8900
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 0.4372540445999126,
|
| 636 |
+
"grad_norm": 46517.14453125,
|
| 637 |
+
"learning_rate": 2.813729777000437e-05,
|
| 638 |
+
"loss": 0.4135,
|
| 639 |
+
"step": 9000
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.4421124228732449,
|
| 643 |
+
"grad_norm": 57222.25,
|
| 644 |
+
"learning_rate": 2.7894378856337755e-05,
|
| 645 |
+
"loss": 0.4048,
|
| 646 |
+
"step": 9100
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 0.4469708011465773,
|
| 650 |
+
"grad_norm": 60419.09375,
|
| 651 |
+
"learning_rate": 2.7651459942671138e-05,
|
| 652 |
+
"loss": 0.4008,
|
| 653 |
+
"step": 9200
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 0.45182917941990963,
|
| 657 |
+
"grad_norm": 42610.984375,
|
| 658 |
+
"learning_rate": 2.740854102900452e-05,
|
| 659 |
+
"loss": 0.3975,
|
| 660 |
+
"step": 9300
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 0.456687557693242,
|
| 664 |
+
"grad_norm": 58822.0234375,
|
| 665 |
+
"learning_rate": 2.71656221153379e-05,
|
| 666 |
+
"loss": 0.3923,
|
| 667 |
+
"step": 9400
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 0.46154593596657434,
|
| 671 |
+
"grad_norm": 47564.5234375,
|
| 672 |
+
"learning_rate": 2.6922703201671284e-05,
|
| 673 |
+
"loss": 0.391,
|
| 674 |
+
"step": 9500
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 0.4664043142399067,
|
| 678 |
+
"grad_norm": 48113.20703125,
|
| 679 |
+
"learning_rate": 2.6679784288004668e-05,
|
| 680 |
+
"loss": 0.4064,
|
| 681 |
+
"step": 9600
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.4712626925132391,
|
| 685 |
+
"grad_norm": 49079.30078125,
|
| 686 |
+
"learning_rate": 2.6436865374338048e-05,
|
| 687 |
+
"loss": 0.4077,
|
| 688 |
+
"step": 9700
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 0.47612107078657145,
|
| 692 |
+
"grad_norm": 53815.7890625,
|
| 693 |
+
"learning_rate": 2.619394646067143e-05,
|
| 694 |
+
"loss": 0.3844,
|
| 695 |
+
"step": 9800
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 0.4809794490599038,
|
| 699 |
+
"grad_norm": 45962.41796875,
|
| 700 |
+
"learning_rate": 2.5951027547004814e-05,
|
| 701 |
+
"loss": 0.3925,
|
| 702 |
+
"step": 9900
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 0.48583782733323616,
|
| 706 |
+
"grad_norm": 50792.91015625,
|
| 707 |
+
"learning_rate": 2.570810863333819e-05,
|
| 708 |
+
"loss": 0.3838,
|
| 709 |
+
"step": 10000
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 0.4906962056065685,
|
| 713 |
+
"grad_norm": 44864.3046875,
|
| 714 |
+
"learning_rate": 2.5465189719671574e-05,
|
| 715 |
+
"loss": 0.3924,
|
| 716 |
+
"step": 10100
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 0.49555458387990087,
|
| 720 |
+
"grad_norm": 50477.6015625,
|
| 721 |
+
"learning_rate": 2.5222270806004954e-05,
|
| 722 |
+
"loss": 0.3875,
|
| 723 |
+
"step": 10200
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 0.5004129621532333,
|
| 727 |
+
"grad_norm": 46136.0859375,
|
| 728 |
+
"learning_rate": 2.4979351892338337e-05,
|
| 729 |
+
"loss": 0.3956,
|
| 730 |
+
"step": 10300
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 0.5052713404265656,
|
| 734 |
+
"grad_norm": 57640.59765625,
|
| 735 |
+
"learning_rate": 2.473643297867172e-05,
|
| 736 |
+
"loss": 0.38,
|
| 737 |
+
"step": 10400
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 0.510129718699898,
|
| 741 |
+
"grad_norm": 60448.453125,
|
| 742 |
+
"learning_rate": 2.4493514065005103e-05,
|
| 743 |
+
"loss": 0.3925,
|
| 744 |
+
"step": 10500
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 0.5149880969732303,
|
| 748 |
+
"grad_norm": 43668.453125,
|
| 749 |
+
"learning_rate": 2.4250595151338483e-05,
|
| 750 |
+
"loss": 0.3966,
|
| 751 |
+
"step": 10600
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 0.5198464752465627,
|
| 755 |
+
"grad_norm": 51975.83203125,
|
| 756 |
+
"learning_rate": 2.4007676237671866e-05,
|
| 757 |
+
"loss": 0.399,
|
| 758 |
+
"step": 10700
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 0.524704853519895,
|
| 762 |
+
"grad_norm": 60277.078125,
|
| 763 |
+
"learning_rate": 2.376475732400525e-05,
|
| 764 |
+
"loss": 0.3968,
|
| 765 |
+
"step": 10800
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 0.5295632317932274,
|
| 769 |
+
"grad_norm": 47762.875,
|
| 770 |
+
"learning_rate": 2.3521838410338633e-05,
|
| 771 |
+
"loss": 0.3937,
|
| 772 |
+
"step": 10900
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 0.5344216100665597,
|
| 776 |
+
"grad_norm": 62721.125,
|
| 777 |
+
"learning_rate": 2.327891949667201e-05,
|
| 778 |
+
"loss": 0.3871,
|
| 779 |
+
"step": 11000
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 0.5392799883398921,
|
| 783 |
+
"grad_norm": 41137.8515625,
|
| 784 |
+
"learning_rate": 2.3036000583005392e-05,
|
| 785 |
+
"loss": 0.3814,
|
| 786 |
+
"step": 11100
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 0.5441383666132245,
|
| 790 |
+
"grad_norm": 50033.2734375,
|
| 791 |
+
"learning_rate": 2.2793081669338776e-05,
|
| 792 |
+
"loss": 0.3987,
|
| 793 |
+
"step": 11200
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 0.5489967448865569,
|
| 797 |
+
"grad_norm": 50574.140625,
|
| 798 |
+
"learning_rate": 2.255016275567216e-05,
|
| 799 |
+
"loss": 0.3741,
|
| 800 |
+
"step": 11300
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 0.5538551231598893,
|
| 804 |
+
"grad_norm": 46732.82421875,
|
| 805 |
+
"learning_rate": 2.230724384200554e-05,
|
| 806 |
+
"loss": 0.3775,
|
| 807 |
+
"step": 11400
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 0.5587135014332216,
|
| 811 |
+
"grad_norm": 57961.8671875,
|
| 812 |
+
"learning_rate": 2.2064324928338922e-05,
|
| 813 |
+
"loss": 0.3826,
|
| 814 |
+
"step": 11500
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 0.563571879706554,
|
| 818 |
+
"grad_norm": 43375.69140625,
|
| 819 |
+
"learning_rate": 2.1821406014672302e-05,
|
| 820 |
+
"loss": 0.3823,
|
| 821 |
+
"step": 11600
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 0.5684302579798863,
|
| 825 |
+
"grad_norm": 49148.40234375,
|
| 826 |
+
"learning_rate": 2.1578487101005685e-05,
|
| 827 |
+
"loss": 0.3782,
|
| 828 |
+
"step": 11700
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 0.5732886362532187,
|
| 832 |
+
"grad_norm": 60182.703125,
|
| 833 |
+
"learning_rate": 2.133556818733907e-05,
|
| 834 |
+
"loss": 0.3804,
|
| 835 |
+
"step": 11800
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 0.578147014526551,
|
| 839 |
+
"grad_norm": 47590.46484375,
|
| 840 |
+
"learning_rate": 2.1092649273672448e-05,
|
| 841 |
+
"loss": 0.3974,
|
| 842 |
+
"step": 11900
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 0.5830053927998834,
|
| 846 |
+
"grad_norm": 65701.859375,
|
| 847 |
+
"learning_rate": 2.084973036000583e-05,
|
| 848 |
+
"loss": 0.3798,
|
| 849 |
+
"step": 12000
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 0.5878637710732157,
|
| 853 |
+
"grad_norm": 43476.69140625,
|
| 854 |
+
"learning_rate": 2.0606811446339215e-05,
|
| 855 |
+
"loss": 0.378,
|
| 856 |
+
"step": 12100
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 0.5927221493465481,
|
| 860 |
+
"grad_norm": 43104.83203125,
|
| 861 |
+
"learning_rate": 2.0363892532672595e-05,
|
| 862 |
+
"loss": 0.3718,
|
| 863 |
+
"step": 12200
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 0.5975805276198805,
|
| 867 |
+
"grad_norm": 58024.0546875,
|
| 868 |
+
"learning_rate": 2.0120973619005974e-05,
|
| 869 |
+
"loss": 0.3837,
|
| 870 |
+
"step": 12300
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 0.6024389058932128,
|
| 874 |
+
"grad_norm": 56071.4765625,
|
| 875 |
+
"learning_rate": 1.9878054705339358e-05,
|
| 876 |
+
"loss": 0.3789,
|
| 877 |
+
"step": 12400
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 0.6072972841665452,
|
| 881 |
+
"grad_norm": 56979.65625,
|
| 882 |
+
"learning_rate": 1.963513579167274e-05,
|
| 883 |
+
"loss": 0.3726,
|
| 884 |
+
"step": 12500
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 0.6121556624398776,
|
| 888 |
+
"grad_norm": 48315.94140625,
|
| 889 |
+
"learning_rate": 1.9392216878006124e-05,
|
| 890 |
+
"loss": 0.3697,
|
| 891 |
+
"step": 12600
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 0.61701404071321,
|
| 895 |
+
"grad_norm": 48739.546875,
|
| 896 |
+
"learning_rate": 1.9149297964339504e-05,
|
| 897 |
+
"loss": 0.3849,
|
| 898 |
+
"step": 12700
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 0.6218724189865423,
|
| 902 |
+
"grad_norm": 49214.71875,
|
| 903 |
+
"learning_rate": 1.8906379050672887e-05,
|
| 904 |
+
"loss": 0.3646,
|
| 905 |
+
"step": 12800
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 0.6267307972598747,
|
| 909 |
+
"grad_norm": 46501.2265625,
|
| 910 |
+
"learning_rate": 1.866346013700627e-05,
|
| 911 |
+
"loss": 0.3693,
|
| 912 |
+
"step": 12900
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 0.631589175533207,
|
| 916 |
+
"grad_norm": 69907.9609375,
|
| 917 |
+
"learning_rate": 1.842054122333965e-05,
|
| 918 |
+
"loss": 0.3737,
|
| 919 |
+
"step": 13000
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 0.6364475538065394,
|
| 923 |
+
"grad_norm": 47973.73046875,
|
| 924 |
+
"learning_rate": 1.817762230967303e-05,
|
| 925 |
+
"loss": 0.3875,
|
| 926 |
+
"step": 13100
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 0.6413059320798717,
|
| 930 |
+
"grad_norm": 58501.1796875,
|
| 931 |
+
"learning_rate": 1.7934703396006413e-05,
|
| 932 |
+
"loss": 0.3778,
|
| 933 |
+
"step": 13200
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 0.6461643103532041,
|
| 937 |
+
"grad_norm": 61768.96875,
|
| 938 |
+
"learning_rate": 1.7691784482339797e-05,
|
| 939 |
+
"loss": 0.384,
|
| 940 |
+
"step": 13300
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 0.6510226886265364,
|
| 944 |
+
"grad_norm": 46427.80859375,
|
| 945 |
+
"learning_rate": 1.744886556867318e-05,
|
| 946 |
+
"loss": 0.365,
|
| 947 |
+
"step": 13400
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 0.6558810668998688,
|
| 951 |
+
"grad_norm": 58254.9453125,
|
| 952 |
+
"learning_rate": 1.720594665500656e-05,
|
| 953 |
+
"loss": 0.3641,
|
| 954 |
+
"step": 13500
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 0.6607394451732012,
|
| 958 |
+
"grad_norm": 49971.00390625,
|
| 959 |
+
"learning_rate": 1.696302774133994e-05,
|
| 960 |
+
"loss": 0.363,
|
| 961 |
+
"step": 13600
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 0.6655978234465335,
|
| 965 |
+
"grad_norm": 56874.12890625,
|
| 966 |
+
"learning_rate": 1.6720108827673323e-05,
|
| 967 |
+
"loss": 0.3795,
|
| 968 |
+
"step": 13700
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 0.6704562017198659,
|
| 972 |
+
"grad_norm": 51813.33984375,
|
| 973 |
+
"learning_rate": 1.6477189914006706e-05,
|
| 974 |
+
"loss": 0.3809,
|
| 975 |
+
"step": 13800
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 0.6753145799931982,
|
| 979 |
+
"grad_norm": 51388.640625,
|
| 980 |
+
"learning_rate": 1.6234271000340086e-05,
|
| 981 |
+
"loss": 0.3649,
|
| 982 |
+
"step": 13900
|
| 983 |
+
},
|
| 984 |
+
{
|
| 985 |
+
"epoch": 0.6801729582665307,
|
| 986 |
+
"grad_norm": 50291.19921875,
|
| 987 |
+
"learning_rate": 1.599135208667347e-05,
|
| 988 |
+
"loss": 0.3609,
|
| 989 |
+
"step": 14000
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 0.685031336539863,
|
| 993 |
+
"grad_norm": 57660.2578125,
|
| 994 |
+
"learning_rate": 1.5748433173006852e-05,
|
| 995 |
+
"loss": 0.3719,
|
| 996 |
+
"step": 14100
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 0.6898897148131954,
|
| 1000 |
+
"grad_norm": 67932.59375,
|
| 1001 |
+
"learning_rate": 1.5505514259340236e-05,
|
| 1002 |
+
"loss": 0.3685,
|
| 1003 |
+
"step": 14200
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 0.6947480930865277,
|
| 1007 |
+
"grad_norm": 54271.5234375,
|
| 1008 |
+
"learning_rate": 1.5262595345673615e-05,
|
| 1009 |
+
"loss": 0.376,
|
| 1010 |
+
"step": 14300
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 0.6996064713598601,
|
| 1014 |
+
"grad_norm": 45938.90234375,
|
| 1015 |
+
"learning_rate": 1.5019676432006995e-05,
|
| 1016 |
+
"loss": 0.3555,
|
| 1017 |
+
"step": 14400
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 0.7044648496331924,
|
| 1021 |
+
"grad_norm": 65276.1328125,
|
| 1022 |
+
"learning_rate": 1.4776757518340378e-05,
|
| 1023 |
+
"loss": 0.382,
|
| 1024 |
+
"step": 14500
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 0.7093232279065248,
|
| 1028 |
+
"grad_norm": 52780.53125,
|
| 1029 |
+
"learning_rate": 1.453383860467376e-05,
|
| 1030 |
+
"loss": 0.3627,
|
| 1031 |
+
"step": 14600
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 0.7141816061798572,
|
| 1035 |
+
"grad_norm": 66279.4375,
|
| 1036 |
+
"learning_rate": 1.4290919691007143e-05,
|
| 1037 |
+
"loss": 0.3726,
|
| 1038 |
+
"step": 14700
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"epoch": 0.7190399844531895,
|
| 1042 |
+
"grad_norm": 48593.3359375,
|
| 1043 |
+
"learning_rate": 1.4048000777340525e-05,
|
| 1044 |
+
"loss": 0.3623,
|
| 1045 |
+
"step": 14800
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 0.7238983627265219,
|
| 1049 |
+
"grad_norm": 47858.83203125,
|
| 1050 |
+
"learning_rate": 1.3805081863673908e-05,
|
| 1051 |
+
"loss": 0.3605,
|
| 1052 |
+
"step": 14900
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 0.7287567409998542,
|
| 1056 |
+
"grad_norm": 55828.08203125,
|
| 1057 |
+
"learning_rate": 1.3562162950007288e-05,
|
| 1058 |
+
"loss": 0.3559,
|
| 1059 |
+
"step": 15000
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 0.7336151192731866,
|
| 1063 |
+
"grad_norm": 50614.34765625,
|
| 1064 |
+
"learning_rate": 1.331924403634067e-05,
|
| 1065 |
+
"loss": 0.3534,
|
| 1066 |
+
"step": 15100
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 0.7384734975465189,
|
| 1070 |
+
"grad_norm": 48779.75,
|
| 1071 |
+
"learning_rate": 1.3076325122674053e-05,
|
| 1072 |
+
"loss": 0.3593,
|
| 1073 |
+
"step": 15200
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 0.7433318758198514,
|
| 1077 |
+
"grad_norm": 50229.625,
|
| 1078 |
+
"learning_rate": 1.2833406209007434e-05,
|
| 1079 |
+
"loss": 0.3594,
|
| 1080 |
+
"step": 15300
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 0.7481902540931837,
|
| 1084 |
+
"grad_norm": 47616.875,
|
| 1085 |
+
"learning_rate": 1.2590487295340816e-05,
|
| 1086 |
+
"loss": 0.3417,
|
| 1087 |
+
"step": 15400
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 0.7530486323665161,
|
| 1091 |
+
"grad_norm": 51565.13671875,
|
| 1092 |
+
"learning_rate": 1.2347568381674197e-05,
|
| 1093 |
+
"loss": 0.3556,
|
| 1094 |
+
"step": 15500
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 0.7579070106398484,
|
| 1098 |
+
"grad_norm": 159462.1875,
|
| 1099 |
+
"learning_rate": 1.210464946800758e-05,
|
| 1100 |
+
"loss": 0.3641,
|
| 1101 |
+
"step": 15600
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 0.7627653889131808,
|
| 1105 |
+
"grad_norm": 54541.4375,
|
| 1106 |
+
"learning_rate": 1.1861730554340962e-05,
|
| 1107 |
+
"loss": 0.362,
|
| 1108 |
+
"step": 15700
|
| 1109 |
+
},
|
| 1110 |
+
{
|
| 1111 |
+
"epoch": 0.7676237671865132,
|
| 1112 |
+
"grad_norm": 60987.12109375,
|
| 1113 |
+
"learning_rate": 1.1618811640674344e-05,
|
| 1114 |
+
"loss": 0.3573,
|
| 1115 |
+
"step": 15800
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 0.7724821454598455,
|
| 1119 |
+
"grad_norm": 51971.9765625,
|
| 1120 |
+
"learning_rate": 1.1375892727007725e-05,
|
| 1121 |
+
"loss": 0.3595,
|
| 1122 |
+
"step": 15900
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 0.7773405237331779,
|
| 1126 |
+
"grad_norm": 53555.78515625,
|
| 1127 |
+
"learning_rate": 1.1132973813341108e-05,
|
| 1128 |
+
"loss": 0.3617,
|
| 1129 |
+
"step": 16000
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 0.7821989020065102,
|
| 1133 |
+
"grad_norm": 50965.8984375,
|
| 1134 |
+
"learning_rate": 1.0890054899674488e-05,
|
| 1135 |
+
"loss": 0.356,
|
| 1136 |
+
"step": 16100
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 0.7870572802798426,
|
| 1140 |
+
"grad_norm": 52491.86328125,
|
| 1141 |
+
"learning_rate": 1.0647135986007871e-05,
|
| 1142 |
+
"loss": 0.3442,
|
| 1143 |
+
"step": 16200
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 0.7919156585531749,
|
| 1147 |
+
"grad_norm": 46180.28515625,
|
| 1148 |
+
"learning_rate": 1.0404217072341253e-05,
|
| 1149 |
+
"loss": 0.3618,
|
| 1150 |
+
"step": 16300
|
| 1151 |
+
},
|
| 1152 |
+
{
|
| 1153 |
+
"epoch": 0.7967740368265073,
|
| 1154 |
+
"grad_norm": 43963.23828125,
|
| 1155 |
+
"learning_rate": 1.0161298158674636e-05,
|
| 1156 |
+
"loss": 0.3451,
|
| 1157 |
+
"step": 16400
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 0.8016324150998396,
|
| 1161 |
+
"grad_norm": 50149.4140625,
|
| 1162 |
+
"learning_rate": 9.918379245008016e-06,
|
| 1163 |
+
"loss": 0.3515,
|
| 1164 |
+
"step": 16500
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 0.8064907933731721,
|
| 1168 |
+
"grad_norm": 64846.9609375,
|
| 1169 |
+
"learning_rate": 9.6754603313414e-06,
|
| 1170 |
+
"loss": 0.3593,
|
| 1171 |
+
"step": 16600
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 0.8113491716465044,
|
| 1175 |
+
"grad_norm": 59240.46484375,
|
| 1176 |
+
"learning_rate": 9.432541417674781e-06,
|
| 1177 |
+
"loss": 0.345,
|
| 1178 |
+
"step": 16700
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 0.8162075499198368,
|
| 1182 |
+
"grad_norm": 51653.4765625,
|
| 1183 |
+
"learning_rate": 9.189622504008162e-06,
|
| 1184 |
+
"loss": 0.3486,
|
| 1185 |
+
"step": 16800
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 0.8210659281931691,
|
| 1189 |
+
"grad_norm": 56696.0703125,
|
| 1190 |
+
"learning_rate": 8.946703590341544e-06,
|
| 1191 |
+
"loss": 0.3514,
|
| 1192 |
+
"step": 16900
|
| 1193 |
+
},
|
| 1194 |
+
{
|
| 1195 |
+
"epoch": 0.8259243064665015,
|
| 1196 |
+
"grad_norm": 44659.8515625,
|
| 1197 |
+
"learning_rate": 8.703784676674927e-06,
|
| 1198 |
+
"loss": 0.3538,
|
| 1199 |
+
"step": 17000
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 0.8307826847398339,
|
| 1203 |
+
"grad_norm": 62480.4453125,
|
| 1204 |
+
"learning_rate": 8.460865763008307e-06,
|
| 1205 |
+
"loss": 0.3553,
|
| 1206 |
+
"step": 17100
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"epoch": 0.8356410630131662,
|
| 1210 |
+
"grad_norm": 49702.1796875,
|
| 1211 |
+
"learning_rate": 8.21794684934169e-06,
|
| 1212 |
+
"loss": 0.355,
|
| 1213 |
+
"step": 17200
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 0.8404994412864986,
|
| 1217 |
+
"grad_norm": 51918.6171875,
|
| 1218 |
+
"learning_rate": 7.975027935675072e-06,
|
| 1219 |
+
"loss": 0.3516,
|
| 1220 |
+
"step": 17300
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 0.8453578195598309,
|
| 1224 |
+
"grad_norm": 70460.1875,
|
| 1225 |
+
"learning_rate": 7.732109022008453e-06,
|
| 1226 |
+
"loss": 0.3485,
|
| 1227 |
+
"step": 17400
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 0.8502161978331633,
|
| 1231 |
+
"grad_norm": 39541.1328125,
|
| 1232 |
+
"learning_rate": 7.489190108341836e-06,
|
| 1233 |
+
"loss": 0.3682,
|
| 1234 |
+
"step": 17500
|
| 1235 |
+
},
|
| 1236 |
+
{
|
| 1237 |
+
"epoch": 0.8550745761064956,
|
| 1238 |
+
"grad_norm": 55487.01171875,
|
| 1239 |
+
"learning_rate": 7.246271194675218e-06,
|
| 1240 |
+
"loss": 0.3634,
|
| 1241 |
+
"step": 17600
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 0.859932954379828,
|
| 1245 |
+
"grad_norm": 61263.55859375,
|
| 1246 |
+
"learning_rate": 7.0033522810086005e-06,
|
| 1247 |
+
"loss": 0.3661,
|
| 1248 |
+
"step": 17700
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 0.8647913326531603,
|
| 1252 |
+
"grad_norm": 51811.1875,
|
| 1253 |
+
"learning_rate": 6.760433367341981e-06,
|
| 1254 |
+
"loss": 0.3545,
|
| 1255 |
+
"step": 17800
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 0.8696497109264928,
|
| 1259 |
+
"grad_norm": 58568.05078125,
|
| 1260 |
+
"learning_rate": 6.517514453675364e-06,
|
| 1261 |
+
"loss": 0.3511,
|
| 1262 |
+
"step": 17900
|
| 1263 |
+
},
|
| 1264 |
+
{
|
| 1265 |
+
"epoch": 0.8745080891998251,
|
| 1266 |
+
"grad_norm": 42418.73828125,
|
| 1267 |
+
"learning_rate": 6.274595540008746e-06,
|
| 1268 |
+
"loss": 0.3462,
|
| 1269 |
+
"step": 18000
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 0.8793664674731575,
|
| 1273 |
+
"grad_norm": 66980.625,
|
| 1274 |
+
"learning_rate": 6.0316766263421275e-06,
|
| 1275 |
+
"loss": 0.3429,
|
| 1276 |
+
"step": 18100
|
| 1277 |
+
},
|
| 1278 |
+
{
|
| 1279 |
+
"epoch": 0.8842248457464899,
|
| 1280 |
+
"grad_norm": 51797.6875,
|
| 1281 |
+
"learning_rate": 5.788757712675509e-06,
|
| 1282 |
+
"loss": 0.3457,
|
| 1283 |
+
"step": 18200
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 0.8890832240198222,
|
| 1287 |
+
"grad_norm": 51049.6640625,
|
| 1288 |
+
"learning_rate": 5.5458387990088915e-06,
|
| 1289 |
+
"loss": 0.3462,
|
| 1290 |
+
"step": 18300
|
| 1291 |
+
},
|
| 1292 |
+
{
|
| 1293 |
+
"epoch": 0.8939416022931546,
|
| 1294 |
+
"grad_norm": 53216.921875,
|
| 1295 |
+
"learning_rate": 5.302919885342273e-06,
|
| 1296 |
+
"loss": 0.3482,
|
| 1297 |
+
"step": 18400
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 0.8987999805664869,
|
| 1301 |
+
"grad_norm": 52944.14453125,
|
| 1302 |
+
"learning_rate": 5.0600009716756545e-06,
|
| 1303 |
+
"loss": 0.3429,
|
| 1304 |
+
"step": 18500
|
| 1305 |
+
},
|
| 1306 |
+
{
|
| 1307 |
+
"epoch": 0.9036583588398193,
|
| 1308 |
+
"grad_norm": 55617.85546875,
|
| 1309 |
+
"learning_rate": 4.817082058009037e-06,
|
| 1310 |
+
"loss": 0.3496,
|
| 1311 |
+
"step": 18600
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 0.9085167371131516,
|
| 1315 |
+
"grad_norm": 51810.25390625,
|
| 1316 |
+
"learning_rate": 4.5741631443424185e-06,
|
| 1317 |
+
"loss": 0.3406,
|
| 1318 |
+
"step": 18700
|
| 1319 |
+
},
|
| 1320 |
+
{
|
| 1321 |
+
"epoch": 0.913375115386484,
|
| 1322 |
+
"grad_norm": 62037.01171875,
|
| 1323 |
+
"learning_rate": 4.331244230675801e-06,
|
| 1324 |
+
"loss": 0.3393,
|
| 1325 |
+
"step": 18800
|
| 1326 |
+
},
|
| 1327 |
+
{
|
| 1328 |
+
"epoch": 0.9182334936598163,
|
| 1329 |
+
"grad_norm": 55568.06640625,
|
| 1330 |
+
"learning_rate": 4.088325317009182e-06,
|
| 1331 |
+
"loss": 0.3412,
|
| 1332 |
+
"step": 18900
|
| 1333 |
+
},
|
| 1334 |
+
{
|
| 1335 |
+
"epoch": 0.9230918719331487,
|
| 1336 |
+
"grad_norm": 55022.734375,
|
| 1337 |
+
"learning_rate": 3.845406403342564e-06,
|
| 1338 |
+
"loss": 0.3297,
|
| 1339 |
+
"step": 19000
|
| 1340 |
+
},
|
| 1341 |
+
{
|
| 1342 |
+
"epoch": 0.927950250206481,
|
| 1343 |
+
"grad_norm": 59076.30078125,
|
| 1344 |
+
"learning_rate": 3.6024874896759463e-06,
|
| 1345 |
+
"loss": 0.3311,
|
| 1346 |
+
"step": 19100
|
| 1347 |
+
},
|
| 1348 |
+
{
|
| 1349 |
+
"epoch": 0.9328086284798134,
|
| 1350 |
+
"grad_norm": 55583.625,
|
| 1351 |
+
"learning_rate": 3.3595685760093283e-06,
|
| 1352 |
+
"loss": 0.3334,
|
| 1353 |
+
"step": 19200
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"epoch": 0.9376670067531458,
|
| 1357 |
+
"grad_norm": 44107.91015625,
|
| 1358 |
+
"learning_rate": 3.1166496623427103e-06,
|
| 1359 |
+
"loss": 0.3287,
|
| 1360 |
+
"step": 19300
|
| 1361 |
+
},
|
| 1362 |
+
{
|
| 1363 |
+
"epoch": 0.9425253850264782,
|
| 1364 |
+
"grad_norm": 43654.265625,
|
| 1365 |
+
"learning_rate": 2.8737307486760922e-06,
|
| 1366 |
+
"loss": 0.3501,
|
| 1367 |
+
"step": 19400
|
| 1368 |
+
},
|
| 1369 |
+
{
|
| 1370 |
+
"epoch": 0.9473837632998106,
|
| 1371 |
+
"grad_norm": 53803.21875,
|
| 1372 |
+
"learning_rate": 2.630811835009474e-06,
|
| 1373 |
+
"loss": 0.3418,
|
| 1374 |
+
"step": 19500
|
| 1375 |
+
},
|
| 1376 |
+
{
|
| 1377 |
+
"epoch": 0.9522421415731429,
|
| 1378 |
+
"grad_norm": 67202.1953125,
|
| 1379 |
+
"learning_rate": 2.3878929213428557e-06,
|
| 1380 |
+
"loss": 0.3343,
|
| 1381 |
+
"step": 19600
|
| 1382 |
+
},
|
| 1383 |
+
{
|
| 1384 |
+
"epoch": 0.9571005198464753,
|
| 1385 |
+
"grad_norm": 57509.7734375,
|
| 1386 |
+
"learning_rate": 2.1449740076762377e-06,
|
| 1387 |
+
"loss": 0.3397,
|
| 1388 |
+
"step": 19700
|
| 1389 |
+
},
|
| 1390 |
+
{
|
| 1391 |
+
"epoch": 0.9619588981198076,
|
| 1392 |
+
"grad_norm": 45354.30859375,
|
| 1393 |
+
"learning_rate": 1.9020550940096197e-06,
|
| 1394 |
+
"loss": 0.3467,
|
| 1395 |
+
"step": 19800
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"epoch": 0.96681727639314,
|
| 1399 |
+
"grad_norm": 51548.08984375,
|
| 1400 |
+
"learning_rate": 1.6591361803430016e-06,
|
| 1401 |
+
"loss": 0.3619,
|
| 1402 |
+
"step": 19900
|
| 1403 |
+
},
|
| 1404 |
+
{
|
| 1405 |
+
"epoch": 0.9716756546664723,
|
| 1406 |
+
"grad_norm": 65316.8515625,
|
| 1407 |
+
"learning_rate": 1.4162172666763834e-06,
|
| 1408 |
+
"loss": 0.3216,
|
| 1409 |
+
"step": 20000
|
| 1410 |
+
},
|
| 1411 |
+
{
|
| 1412 |
+
"epoch": 0.9765340329398047,
|
| 1413 |
+
"grad_norm": 48864.44921875,
|
| 1414 |
+
"learning_rate": 1.1732983530097653e-06,
|
| 1415 |
+
"loss": 0.3303,
|
| 1416 |
+
"step": 20100
|
| 1417 |
+
},
|
| 1418 |
+
{
|
| 1419 |
+
"epoch": 0.981392411213137,
|
| 1420 |
+
"grad_norm": 48878.0,
|
| 1421 |
+
"learning_rate": 9.303794393431472e-07,
|
| 1422 |
+
"loss": 0.3492,
|
| 1423 |
+
"step": 20200
|
| 1424 |
+
},
|
| 1425 |
+
{
|
| 1426 |
+
"epoch": 0.9862507894864694,
|
| 1427 |
+
"grad_norm": 43658.50390625,
|
| 1428 |
+
"learning_rate": 6.874605256765293e-07,
|
| 1429 |
+
"loss": 0.3306,
|
| 1430 |
+
"step": 20300
|
| 1431 |
+
},
|
| 1432 |
+
{
|
| 1433 |
+
"epoch": 0.9911091677598017,
|
| 1434 |
+
"grad_norm": 58298.01171875,
|
| 1435 |
+
"learning_rate": 4.4454161200991114e-07,
|
| 1436 |
+
"loss": 0.3366,
|
| 1437 |
+
"step": 20400
|
| 1438 |
+
},
|
| 1439 |
+
{
|
| 1440 |
+
"epoch": 0.9959675460331341,
|
| 1441 |
+
"grad_norm": 49216.18359375,
|
| 1442 |
+
"learning_rate": 2.01622698343293e-07,
|
| 1443 |
+
"loss": 0.3288,
|
| 1444 |
+
"step": 20500
|
| 1445 |
+
},
|
| 1446 |
+
{
|
| 1447 |
+
"epoch": 1.0,
|
| 1448 |
+
"step": 20583,
|
| 1449 |
+
"total_flos": 3.1397459461543035e+18,
|
| 1450 |
+
"train_loss": 0.4062042611626282,
|
| 1451 |
+
"train_runtime": 286226.4367,
|
| 1452 |
+
"train_samples_per_second": 0.863,
|
| 1453 |
+
"train_steps_per_second": 0.072
|
| 1454 |
+
}
|
| 1455 |
+
],
|
| 1456 |
+
"logging_steps": 100,
|
| 1457 |
+
"max_steps": 20583,
|
| 1458 |
+
"num_input_tokens_seen": 0,
|
| 1459 |
+
"num_train_epochs": 1,
|
| 1460 |
+
"save_steps": 20583,
|
| 1461 |
+
"stateful_callbacks": {
|
| 1462 |
+
"TrainerControl": {
|
| 1463 |
+
"args": {
|
| 1464 |
+
"should_epoch_stop": false,
|
| 1465 |
+
"should_evaluate": false,
|
| 1466 |
+
"should_log": false,
|
| 1467 |
+
"should_save": true,
|
| 1468 |
+
"should_training_stop": true
|
| 1469 |
+
},
|
| 1470 |
+
"attributes": {}
|
| 1471 |
+
}
|
| 1472 |
+
},
|
| 1473 |
+
"total_flos": 3.1397459461543035e+18,
|
| 1474 |
+
"train_batch_size": 12,
|
| 1475 |
+
"trial_name": null,
|
| 1476 |
+
"trial_params": null
|
| 1477 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:034a720a60e13bfe2028b711a3cf3e3c12bc7154c84082f409e426f7d9db5944
|
| 3 |
+
size 5112
|