Upload 15 files
Browse files- README.md +52 -3
- adapter_config.json +31 -0
- adapter_model.safetensors +3 -0
- added_tokens.json +40 -0
- all_results.json +14 -0
- config.json +30 -0
- eval_results.json +8 -0
- merges.txt +0 -0
- special_tokens_map.json +24 -0
- tokenizer.json +0 -0
- tokenizer_config.json +326 -0
- train_results.json +9 -0
- trainer_state.json +2222 -0
- training_args.bin +3 -0
- vocab.json +0 -0
README.md
CHANGED
|
@@ -1,3 +1,52 @@
|
|
| 1 |
-
---
|
| 2 |
-
license:
|
| 3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
library_name: peft
|
| 4 |
+
tags:
|
| 5 |
+
- alignment-handbook
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
base_model: microsoft/phi-1_5
|
| 8 |
+
datasets:
|
| 9 |
+
- Ritvik19/open-hermes-2_5-reformatted
|
| 10 |
+
model-index:
|
| 11 |
+
- name: openhermes-phi-1_5-sft-qlora
|
| 12 |
+
results: []
|
| 13 |
+
---
|
| 14 |
+
|
| 15 |
+
**Note**: This model card has been generated automatically according to the information the Trainer had access to.
|
| 16 |
+
Visit the [model card](https://ritvik19.github.io/small-llms/) to see the full description.
|
| 17 |
+
|
| 18 |
+
# openhermes-phi-1_5-sft-qlora
|
| 19 |
+
|
| 20 |
+
This model is a fine-tuned version of [microsoft/phi-1_5](https://huggingface.co/microsoft/phi-1_5) on the Ritvik19/open-hermes-2_5-reformatted dataset.
|
| 21 |
+
It achieves the following results on the evaluation set:
|
| 22 |
+
- Loss: 1.4192
|
| 23 |
+
|
| 24 |
+
### Training hyperparameters
|
| 25 |
+
|
| 26 |
+
The following hyperparameters were used during training:
|
| 27 |
+
- learning_rate: 0.0002
|
| 28 |
+
- train_batch_size: 1
|
| 29 |
+
- eval_batch_size: 1
|
| 30 |
+
- seed: 42
|
| 31 |
+
- distributed_type: multi-GPU
|
| 32 |
+
- gradient_accumulation_steps: 128
|
| 33 |
+
- total_train_batch_size: 128
|
| 34 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 35 |
+
- lr_scheduler_type: cosine
|
| 36 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 37 |
+
- num_epochs: 1
|
| 38 |
+
|
| 39 |
+
### Training results
|
| 40 |
+
|
| 41 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 42 |
+
|:-------------:|:------:|:----:|:---------------:|
|
| 43 |
+
| 1.3662 | 0.9994 | 1559 | 1.4192 |
|
| 44 |
+
|
| 45 |
+
|
| 46 |
+
### Framework versions
|
| 47 |
+
|
| 48 |
+
- PEFT 0.7.1
|
| 49 |
+
- Transformers 4.40.1
|
| 50 |
+
- Pytorch 2.1.2+cu121
|
| 51 |
+
- Datasets 2.19.0
|
| 52 |
+
- Tokenizers 0.19.1
|
adapter_config.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "microsoft/phi-1_5",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": false,
|
| 7 |
+
"inference_mode": true,
|
| 8 |
+
"init_lora_weights": true,
|
| 9 |
+
"layers_pattern": null,
|
| 10 |
+
"layers_to_transform": null,
|
| 11 |
+
"loftq_config": {},
|
| 12 |
+
"lora_alpha": 16,
|
| 13 |
+
"lora_dropout": 0.05,
|
| 14 |
+
"megatron_config": null,
|
| 15 |
+
"megatron_core": "megatron.core",
|
| 16 |
+
"modules_to_save": null,
|
| 17 |
+
"peft_type": "LORA",
|
| 18 |
+
"r": 16,
|
| 19 |
+
"rank_pattern": {},
|
| 20 |
+
"revision": null,
|
| 21 |
+
"target_modules": [
|
| 22 |
+
"v_proj",
|
| 23 |
+
"k_proj",
|
| 24 |
+
"o_proj",
|
| 25 |
+
"q_proj",
|
| 26 |
+
"up_proj",
|
| 27 |
+
"gate_proj",
|
| 28 |
+
"down_proj"
|
| 29 |
+
],
|
| 30 |
+
"task_type": "CAUSAL_LM"
|
| 31 |
+
}
|
adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7e10b68aad77bff7fd7a087790709cf46c9f1f701e63ec1134308eff7fc084fe
|
| 3 |
+
size 9456424
|
added_tokens.json
ADDED
|
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"\t\t": 50294,
|
| 3 |
+
"\t\t\t": 50293,
|
| 4 |
+
"\t\t\t\t": 50292,
|
| 5 |
+
"\t\t\t\t\t": 50291,
|
| 6 |
+
"\t\t\t\t\t\t": 50290,
|
| 7 |
+
"\t\t\t\t\t\t\t": 50289,
|
| 8 |
+
"\t\t\t\t\t\t\t\t": 50288,
|
| 9 |
+
"\t\t\t\t\t\t\t\t\t": 50287,
|
| 10 |
+
" ": 50286,
|
| 11 |
+
" ": 50285,
|
| 12 |
+
" ": 50284,
|
| 13 |
+
" ": 50283,
|
| 14 |
+
" ": 50282,
|
| 15 |
+
" ": 50281,
|
| 16 |
+
" ": 50280,
|
| 17 |
+
" ": 50279,
|
| 18 |
+
" ": 50278,
|
| 19 |
+
" ": 50277,
|
| 20 |
+
" ": 50276,
|
| 21 |
+
" ": 50275,
|
| 22 |
+
" ": 50274,
|
| 23 |
+
" ": 50273,
|
| 24 |
+
" ": 50272,
|
| 25 |
+
" ": 50271,
|
| 26 |
+
" ": 50270,
|
| 27 |
+
" ": 50269,
|
| 28 |
+
" ": 50268,
|
| 29 |
+
" ": 50267,
|
| 30 |
+
" ": 50266,
|
| 31 |
+
" ": 50265,
|
| 32 |
+
" ": 50264,
|
| 33 |
+
" ": 50263,
|
| 34 |
+
" ": 50262,
|
| 35 |
+
" ": 50261,
|
| 36 |
+
" ": 50260,
|
| 37 |
+
" ": 50259,
|
| 38 |
+
" ": 50258,
|
| 39 |
+
" ": 50257
|
| 40 |
+
}
|
all_results.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 0.9993739889922224,
|
| 3 |
+
"eval_loss": 1.4191993474960327,
|
| 4 |
+
"eval_runtime": 1934.5604,
|
| 5 |
+
"eval_samples": 23109,
|
| 6 |
+
"eval_samples_per_second": 7.315,
|
| 7 |
+
"eval_steps_per_second": 7.315,
|
| 8 |
+
"total_flos": 3.232184148701479e+18,
|
| 9 |
+
"train_loss": 0.016414370117774753,
|
| 10 |
+
"train_runtime": 2971.8566,
|
| 11 |
+
"train_samples": 1001538,
|
| 12 |
+
"train_samples_per_second": 67.189,
|
| 13 |
+
"train_steps_per_second": 0.525
|
| 14 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "microsoft/phi-1_5",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"PhiForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": null,
|
| 8 |
+
"embd_pdrop": 0.0,
|
| 9 |
+
"eos_token_id": null,
|
| 10 |
+
"hidden_act": "gelu_new",
|
| 11 |
+
"hidden_size": 2048,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 8192,
|
| 14 |
+
"layer_norm_eps": 1e-05,
|
| 15 |
+
"max_position_embeddings": 2048,
|
| 16 |
+
"model_type": "phi",
|
| 17 |
+
"num_attention_heads": 32,
|
| 18 |
+
"num_hidden_layers": 24,
|
| 19 |
+
"num_key_value_heads": 32,
|
| 20 |
+
"partial_rotary_factor": 0.5,
|
| 21 |
+
"qk_layernorm": false,
|
| 22 |
+
"resid_pdrop": 0.0,
|
| 23 |
+
"rope_scaling": null,
|
| 24 |
+
"rope_theta": 10000.0,
|
| 25 |
+
"tie_word_embeddings": false,
|
| 26 |
+
"torch_dtype": "bfloat16",
|
| 27 |
+
"transformers_version": "4.40.1",
|
| 28 |
+
"use_cache": true,
|
| 29 |
+
"vocab_size": 51200
|
| 30 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 0.9993739889922224,
|
| 3 |
+
"eval_loss": 1.4191993474960327,
|
| 4 |
+
"eval_runtime": 1934.5604,
|
| 5 |
+
"eval_samples": 23109,
|
| 6 |
+
"eval_samples_per_second": 7.315,
|
| 7 |
+
"eval_steps_per_second": 7.315
|
| 8 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<|endoftext|>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "<|endoftext|>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": "<|endoftext|>",
|
| 17 |
+
"unk_token": {
|
| 18 |
+
"content": "<|endoftext|>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
}
|
| 24 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,326 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"50256": {
|
| 5 |
+
"content": "<|endoftext|>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": false,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"50257": {
|
| 13 |
+
"content": " ",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": true,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": false
|
| 19 |
+
},
|
| 20 |
+
"50258": {
|
| 21 |
+
"content": " ",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": true,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": false
|
| 27 |
+
},
|
| 28 |
+
"50259": {
|
| 29 |
+
"content": " ",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": true,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false,
|
| 34 |
+
"special": false
|
| 35 |
+
},
|
| 36 |
+
"50260": {
|
| 37 |
+
"content": " ",
|
| 38 |
+
"lstrip": false,
|
| 39 |
+
"normalized": true,
|
| 40 |
+
"rstrip": false,
|
| 41 |
+
"single_word": false,
|
| 42 |
+
"special": false
|
| 43 |
+
},
|
| 44 |
+
"50261": {
|
| 45 |
+
"content": " ",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": true,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false,
|
| 50 |
+
"special": false
|
| 51 |
+
},
|
| 52 |
+
"50262": {
|
| 53 |
+
"content": " ",
|
| 54 |
+
"lstrip": false,
|
| 55 |
+
"normalized": true,
|
| 56 |
+
"rstrip": false,
|
| 57 |
+
"single_word": false,
|
| 58 |
+
"special": false
|
| 59 |
+
},
|
| 60 |
+
"50263": {
|
| 61 |
+
"content": " ",
|
| 62 |
+
"lstrip": false,
|
| 63 |
+
"normalized": true,
|
| 64 |
+
"rstrip": false,
|
| 65 |
+
"single_word": false,
|
| 66 |
+
"special": false
|
| 67 |
+
},
|
| 68 |
+
"50264": {
|
| 69 |
+
"content": " ",
|
| 70 |
+
"lstrip": false,
|
| 71 |
+
"normalized": true,
|
| 72 |
+
"rstrip": false,
|
| 73 |
+
"single_word": false,
|
| 74 |
+
"special": false
|
| 75 |
+
},
|
| 76 |
+
"50265": {
|
| 77 |
+
"content": " ",
|
| 78 |
+
"lstrip": false,
|
| 79 |
+
"normalized": true,
|
| 80 |
+
"rstrip": false,
|
| 81 |
+
"single_word": false,
|
| 82 |
+
"special": false
|
| 83 |
+
},
|
| 84 |
+
"50266": {
|
| 85 |
+
"content": " ",
|
| 86 |
+
"lstrip": false,
|
| 87 |
+
"normalized": true,
|
| 88 |
+
"rstrip": false,
|
| 89 |
+
"single_word": false,
|
| 90 |
+
"special": false
|
| 91 |
+
},
|
| 92 |
+
"50267": {
|
| 93 |
+
"content": " ",
|
| 94 |
+
"lstrip": false,
|
| 95 |
+
"normalized": true,
|
| 96 |
+
"rstrip": false,
|
| 97 |
+
"single_word": false,
|
| 98 |
+
"special": false
|
| 99 |
+
},
|
| 100 |
+
"50268": {
|
| 101 |
+
"content": " ",
|
| 102 |
+
"lstrip": false,
|
| 103 |
+
"normalized": true,
|
| 104 |
+
"rstrip": false,
|
| 105 |
+
"single_word": false,
|
| 106 |
+
"special": false
|
| 107 |
+
},
|
| 108 |
+
"50269": {
|
| 109 |
+
"content": " ",
|
| 110 |
+
"lstrip": false,
|
| 111 |
+
"normalized": true,
|
| 112 |
+
"rstrip": false,
|
| 113 |
+
"single_word": false,
|
| 114 |
+
"special": false
|
| 115 |
+
},
|
| 116 |
+
"50270": {
|
| 117 |
+
"content": " ",
|
| 118 |
+
"lstrip": false,
|
| 119 |
+
"normalized": true,
|
| 120 |
+
"rstrip": false,
|
| 121 |
+
"single_word": false,
|
| 122 |
+
"special": false
|
| 123 |
+
},
|
| 124 |
+
"50271": {
|
| 125 |
+
"content": " ",
|
| 126 |
+
"lstrip": false,
|
| 127 |
+
"normalized": true,
|
| 128 |
+
"rstrip": false,
|
| 129 |
+
"single_word": false,
|
| 130 |
+
"special": false
|
| 131 |
+
},
|
| 132 |
+
"50272": {
|
| 133 |
+
"content": " ",
|
| 134 |
+
"lstrip": false,
|
| 135 |
+
"normalized": true,
|
| 136 |
+
"rstrip": false,
|
| 137 |
+
"single_word": false,
|
| 138 |
+
"special": false
|
| 139 |
+
},
|
| 140 |
+
"50273": {
|
| 141 |
+
"content": " ",
|
| 142 |
+
"lstrip": false,
|
| 143 |
+
"normalized": true,
|
| 144 |
+
"rstrip": false,
|
| 145 |
+
"single_word": false,
|
| 146 |
+
"special": false
|
| 147 |
+
},
|
| 148 |
+
"50274": {
|
| 149 |
+
"content": " ",
|
| 150 |
+
"lstrip": false,
|
| 151 |
+
"normalized": true,
|
| 152 |
+
"rstrip": false,
|
| 153 |
+
"single_word": false,
|
| 154 |
+
"special": false
|
| 155 |
+
},
|
| 156 |
+
"50275": {
|
| 157 |
+
"content": " ",
|
| 158 |
+
"lstrip": false,
|
| 159 |
+
"normalized": true,
|
| 160 |
+
"rstrip": false,
|
| 161 |
+
"single_word": false,
|
| 162 |
+
"special": false
|
| 163 |
+
},
|
| 164 |
+
"50276": {
|
| 165 |
+
"content": " ",
|
| 166 |
+
"lstrip": false,
|
| 167 |
+
"normalized": true,
|
| 168 |
+
"rstrip": false,
|
| 169 |
+
"single_word": false,
|
| 170 |
+
"special": false
|
| 171 |
+
},
|
| 172 |
+
"50277": {
|
| 173 |
+
"content": " ",
|
| 174 |
+
"lstrip": false,
|
| 175 |
+
"normalized": true,
|
| 176 |
+
"rstrip": false,
|
| 177 |
+
"single_word": false,
|
| 178 |
+
"special": false
|
| 179 |
+
},
|
| 180 |
+
"50278": {
|
| 181 |
+
"content": " ",
|
| 182 |
+
"lstrip": false,
|
| 183 |
+
"normalized": true,
|
| 184 |
+
"rstrip": false,
|
| 185 |
+
"single_word": false,
|
| 186 |
+
"special": false
|
| 187 |
+
},
|
| 188 |
+
"50279": {
|
| 189 |
+
"content": " ",
|
| 190 |
+
"lstrip": false,
|
| 191 |
+
"normalized": true,
|
| 192 |
+
"rstrip": false,
|
| 193 |
+
"single_word": false,
|
| 194 |
+
"special": false
|
| 195 |
+
},
|
| 196 |
+
"50280": {
|
| 197 |
+
"content": " ",
|
| 198 |
+
"lstrip": false,
|
| 199 |
+
"normalized": true,
|
| 200 |
+
"rstrip": false,
|
| 201 |
+
"single_word": false,
|
| 202 |
+
"special": false
|
| 203 |
+
},
|
| 204 |
+
"50281": {
|
| 205 |
+
"content": " ",
|
| 206 |
+
"lstrip": false,
|
| 207 |
+
"normalized": true,
|
| 208 |
+
"rstrip": false,
|
| 209 |
+
"single_word": false,
|
| 210 |
+
"special": false
|
| 211 |
+
},
|
| 212 |
+
"50282": {
|
| 213 |
+
"content": " ",
|
| 214 |
+
"lstrip": false,
|
| 215 |
+
"normalized": true,
|
| 216 |
+
"rstrip": false,
|
| 217 |
+
"single_word": false,
|
| 218 |
+
"special": false
|
| 219 |
+
},
|
| 220 |
+
"50283": {
|
| 221 |
+
"content": " ",
|
| 222 |
+
"lstrip": false,
|
| 223 |
+
"normalized": true,
|
| 224 |
+
"rstrip": false,
|
| 225 |
+
"single_word": false,
|
| 226 |
+
"special": false
|
| 227 |
+
},
|
| 228 |
+
"50284": {
|
| 229 |
+
"content": " ",
|
| 230 |
+
"lstrip": false,
|
| 231 |
+
"normalized": true,
|
| 232 |
+
"rstrip": false,
|
| 233 |
+
"single_word": false,
|
| 234 |
+
"special": false
|
| 235 |
+
},
|
| 236 |
+
"50285": {
|
| 237 |
+
"content": " ",
|
| 238 |
+
"lstrip": false,
|
| 239 |
+
"normalized": true,
|
| 240 |
+
"rstrip": false,
|
| 241 |
+
"single_word": false,
|
| 242 |
+
"special": false
|
| 243 |
+
},
|
| 244 |
+
"50286": {
|
| 245 |
+
"content": " ",
|
| 246 |
+
"lstrip": false,
|
| 247 |
+
"normalized": true,
|
| 248 |
+
"rstrip": false,
|
| 249 |
+
"single_word": false,
|
| 250 |
+
"special": false
|
| 251 |
+
},
|
| 252 |
+
"50287": {
|
| 253 |
+
"content": "\t\t\t\t\t\t\t\t\t",
|
| 254 |
+
"lstrip": false,
|
| 255 |
+
"normalized": true,
|
| 256 |
+
"rstrip": false,
|
| 257 |
+
"single_word": false,
|
| 258 |
+
"special": false
|
| 259 |
+
},
|
| 260 |
+
"50288": {
|
| 261 |
+
"content": "\t\t\t\t\t\t\t\t",
|
| 262 |
+
"lstrip": false,
|
| 263 |
+
"normalized": true,
|
| 264 |
+
"rstrip": false,
|
| 265 |
+
"single_word": false,
|
| 266 |
+
"special": false
|
| 267 |
+
},
|
| 268 |
+
"50289": {
|
| 269 |
+
"content": "\t\t\t\t\t\t\t",
|
| 270 |
+
"lstrip": false,
|
| 271 |
+
"normalized": true,
|
| 272 |
+
"rstrip": false,
|
| 273 |
+
"single_word": false,
|
| 274 |
+
"special": false
|
| 275 |
+
},
|
| 276 |
+
"50290": {
|
| 277 |
+
"content": "\t\t\t\t\t\t",
|
| 278 |
+
"lstrip": false,
|
| 279 |
+
"normalized": true,
|
| 280 |
+
"rstrip": false,
|
| 281 |
+
"single_word": false,
|
| 282 |
+
"special": false
|
| 283 |
+
},
|
| 284 |
+
"50291": {
|
| 285 |
+
"content": "\t\t\t\t\t",
|
| 286 |
+
"lstrip": false,
|
| 287 |
+
"normalized": true,
|
| 288 |
+
"rstrip": false,
|
| 289 |
+
"single_word": false,
|
| 290 |
+
"special": false
|
| 291 |
+
},
|
| 292 |
+
"50292": {
|
| 293 |
+
"content": "\t\t\t\t",
|
| 294 |
+
"lstrip": false,
|
| 295 |
+
"normalized": true,
|
| 296 |
+
"rstrip": false,
|
| 297 |
+
"single_word": false,
|
| 298 |
+
"special": false
|
| 299 |
+
},
|
| 300 |
+
"50293": {
|
| 301 |
+
"content": "\t\t\t",
|
| 302 |
+
"lstrip": false,
|
| 303 |
+
"normalized": true,
|
| 304 |
+
"rstrip": false,
|
| 305 |
+
"single_word": false,
|
| 306 |
+
"special": false
|
| 307 |
+
},
|
| 308 |
+
"50294": {
|
| 309 |
+
"content": "\t\t",
|
| 310 |
+
"lstrip": false,
|
| 311 |
+
"normalized": true,
|
| 312 |
+
"rstrip": false,
|
| 313 |
+
"single_word": false,
|
| 314 |
+
"special": false
|
| 315 |
+
}
|
| 316 |
+
},
|
| 317 |
+
"bos_token": "<|endoftext|>",
|
| 318 |
+
"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 %}",
|
| 319 |
+
"clean_up_tokenization_spaces": true,
|
| 320 |
+
"eos_token": "<|endoftext|>",
|
| 321 |
+
"model_max_length": 2048,
|
| 322 |
+
"pad_token": "<|endoftext|>",
|
| 323 |
+
"return_token_type_ids": false,
|
| 324 |
+
"tokenizer_class": "CodeGenTokenizer",
|
| 325 |
+
"unk_token": "<|endoftext|>"
|
| 326 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 0.9993739889922224,
|
| 3 |
+
"total_flos": 3.232184148701479e+18,
|
| 4 |
+
"train_loss": 0.016414370117774753,
|
| 5 |
+
"train_runtime": 2971.8566,
|
| 6 |
+
"train_samples": 1001538,
|
| 7 |
+
"train_samples_per_second": 67.189,
|
| 8 |
+
"train_steps_per_second": 0.525
|
| 9 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,2222 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.9993739889922224,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 1559,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.0006410352719642222,
|
| 13 |
+
"grad_norm": 0.10498046875,
|
| 14 |
+
"learning_rate": 1.282051282051282e-06,
|
| 15 |
+
"loss": 1.8493,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.003205176359821111,
|
| 20 |
+
"grad_norm": 0.1103515625,
|
| 21 |
+
"learning_rate": 6.41025641025641e-06,
|
| 22 |
+
"loss": 1.8865,
|
| 23 |
+
"step": 5
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.006410352719642222,
|
| 27 |
+
"grad_norm": 0.1005859375,
|
| 28 |
+
"learning_rate": 1.282051282051282e-05,
|
| 29 |
+
"loss": 1.8383,
|
| 30 |
+
"step": 10
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.009615529079463333,
|
| 34 |
+
"grad_norm": 0.10693359375,
|
| 35 |
+
"learning_rate": 1.923076923076923e-05,
|
| 36 |
+
"loss": 1.8385,
|
| 37 |
+
"step": 15
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.012820705439284444,
|
| 41 |
+
"grad_norm": 0.1103515625,
|
| 42 |
+
"learning_rate": 2.564102564102564e-05,
|
| 43 |
+
"loss": 1.8346,
|
| 44 |
+
"step": 20
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.016025881799105555,
|
| 48 |
+
"grad_norm": 0.1298828125,
|
| 49 |
+
"learning_rate": 3.205128205128206e-05,
|
| 50 |
+
"loss": 1.8127,
|
| 51 |
+
"step": 25
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.019231058158926666,
|
| 55 |
+
"grad_norm": 0.1435546875,
|
| 56 |
+
"learning_rate": 3.846153846153846e-05,
|
| 57 |
+
"loss": 1.7981,
|
| 58 |
+
"step": 30
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.022436234518747777,
|
| 62 |
+
"grad_norm": 0.1494140625,
|
| 63 |
+
"learning_rate": 4.4871794871794874e-05,
|
| 64 |
+
"loss": 1.7907,
|
| 65 |
+
"step": 35
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.025641410878568888,
|
| 69 |
+
"grad_norm": 0.1416015625,
|
| 70 |
+
"learning_rate": 5.128205128205128e-05,
|
| 71 |
+
"loss": 1.7468,
|
| 72 |
+
"step": 40
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.02884658723839,
|
| 76 |
+
"grad_norm": 0.1328125,
|
| 77 |
+
"learning_rate": 5.769230769230769e-05,
|
| 78 |
+
"loss": 1.7105,
|
| 79 |
+
"step": 45
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.03205176359821111,
|
| 83 |
+
"grad_norm": 0.126953125,
|
| 84 |
+
"learning_rate": 6.410256410256412e-05,
|
| 85 |
+
"loss": 1.6887,
|
| 86 |
+
"step": 50
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.035256939958032224,
|
| 90 |
+
"grad_norm": 0.107421875,
|
| 91 |
+
"learning_rate": 7.051282051282052e-05,
|
| 92 |
+
"loss": 1.6757,
|
| 93 |
+
"step": 55
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.03846211631785333,
|
| 97 |
+
"grad_norm": 0.10009765625,
|
| 98 |
+
"learning_rate": 7.692307692307693e-05,
|
| 99 |
+
"loss": 1.6736,
|
| 100 |
+
"step": 60
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.041667292677674446,
|
| 104 |
+
"grad_norm": 0.078125,
|
| 105 |
+
"learning_rate": 8.333333333333334e-05,
|
| 106 |
+
"loss": 1.6252,
|
| 107 |
+
"step": 65
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.04487246903749555,
|
| 111 |
+
"grad_norm": 0.06201171875,
|
| 112 |
+
"learning_rate": 8.974358974358975e-05,
|
| 113 |
+
"loss": 1.5655,
|
| 114 |
+
"step": 70
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.04807764539731667,
|
| 118 |
+
"grad_norm": 0.049072265625,
|
| 119 |
+
"learning_rate": 9.615384615384617e-05,
|
| 120 |
+
"loss": 1.5646,
|
| 121 |
+
"step": 75
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.051282821757137775,
|
| 125 |
+
"grad_norm": 0.04345703125,
|
| 126 |
+
"learning_rate": 0.00010256410256410256,
|
| 127 |
+
"loss": 1.5861,
|
| 128 |
+
"step": 80
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.05448799811695889,
|
| 132 |
+
"grad_norm": 0.039794921875,
|
| 133 |
+
"learning_rate": 0.00010897435897435896,
|
| 134 |
+
"loss": 1.5379,
|
| 135 |
+
"step": 85
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.05769317447678,
|
| 139 |
+
"grad_norm": 0.0400390625,
|
| 140 |
+
"learning_rate": 0.00011538461538461538,
|
| 141 |
+
"loss": 1.5557,
|
| 142 |
+
"step": 90
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.06089835083660111,
|
| 146 |
+
"grad_norm": 0.037841796875,
|
| 147 |
+
"learning_rate": 0.00012179487179487179,
|
| 148 |
+
"loss": 1.5102,
|
| 149 |
+
"step": 95
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.06410352719642222,
|
| 153 |
+
"grad_norm": 0.038330078125,
|
| 154 |
+
"learning_rate": 0.00012820512820512823,
|
| 155 |
+
"loss": 1.5048,
|
| 156 |
+
"step": 100
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.06730870355624333,
|
| 160 |
+
"grad_norm": 0.033935546875,
|
| 161 |
+
"learning_rate": 0.00013461538461538464,
|
| 162 |
+
"loss": 1.5127,
|
| 163 |
+
"step": 105
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.07051387991606445,
|
| 167 |
+
"grad_norm": 0.03173828125,
|
| 168 |
+
"learning_rate": 0.00014102564102564104,
|
| 169 |
+
"loss": 1.5161,
|
| 170 |
+
"step": 110
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.07371905627588556,
|
| 174 |
+
"grad_norm": 0.0301513671875,
|
| 175 |
+
"learning_rate": 0.00014743589743589745,
|
| 176 |
+
"loss": 1.4948,
|
| 177 |
+
"step": 115
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.07692423263570666,
|
| 181 |
+
"grad_norm": 0.03125,
|
| 182 |
+
"learning_rate": 0.00015384615384615385,
|
| 183 |
+
"loss": 1.4584,
|
| 184 |
+
"step": 120
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.08012940899552777,
|
| 188 |
+
"grad_norm": 0.029052734375,
|
| 189 |
+
"learning_rate": 0.00016025641025641028,
|
| 190 |
+
"loss": 1.4704,
|
| 191 |
+
"step": 125
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.08333458535534889,
|
| 195 |
+
"grad_norm": 0.0279541015625,
|
| 196 |
+
"learning_rate": 0.0001666666666666667,
|
| 197 |
+
"loss": 1.4411,
|
| 198 |
+
"step": 130
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.08653976171517,
|
| 202 |
+
"grad_norm": 0.0263671875,
|
| 203 |
+
"learning_rate": 0.0001730769230769231,
|
| 204 |
+
"loss": 1.4723,
|
| 205 |
+
"step": 135
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.0897449380749911,
|
| 209 |
+
"grad_norm": 0.02685546875,
|
| 210 |
+
"learning_rate": 0.0001794871794871795,
|
| 211 |
+
"loss": 1.4505,
|
| 212 |
+
"step": 140
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.09295011443481223,
|
| 216 |
+
"grad_norm": 0.0291748046875,
|
| 217 |
+
"learning_rate": 0.0001858974358974359,
|
| 218 |
+
"loss": 1.4367,
|
| 219 |
+
"step": 145
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.09615529079463334,
|
| 223 |
+
"grad_norm": 0.0262451171875,
|
| 224 |
+
"learning_rate": 0.00019230769230769233,
|
| 225 |
+
"loss": 1.4291,
|
| 226 |
+
"step": 150
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.09936046715445444,
|
| 230 |
+
"grad_norm": 0.0390625,
|
| 231 |
+
"learning_rate": 0.00019871794871794874,
|
| 232 |
+
"loss": 1.4075,
|
| 233 |
+
"step": 155
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.10256564351427555,
|
| 237 |
+
"grad_norm": 0.03857421875,
|
| 238 |
+
"learning_rate": 0.00019999598882613538,
|
| 239 |
+
"loss": 1.4203,
|
| 240 |
+
"step": 160
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.10577081987409667,
|
| 244 |
+
"grad_norm": 0.029541015625,
|
| 245 |
+
"learning_rate": 0.00019997969398381457,
|
| 246 |
+
"loss": 1.4188,
|
| 247 |
+
"step": 165
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.10897599623391778,
|
| 251 |
+
"grad_norm": 0.025146484375,
|
| 252 |
+
"learning_rate": 0.00019995086681563726,
|
| 253 |
+
"loss": 1.4512,
|
| 254 |
+
"step": 170
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.11218117259373889,
|
| 258 |
+
"grad_norm": 0.025146484375,
|
| 259 |
+
"learning_rate": 0.0001999095109350519,
|
| 260 |
+
"loss": 1.417,
|
| 261 |
+
"step": 175
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.11538634895356,
|
| 265 |
+
"grad_norm": 0.02734375,
|
| 266 |
+
"learning_rate": 0.0001998556315259648,
|
| 267 |
+
"loss": 1.4309,
|
| 268 |
+
"step": 180
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.11859152531338112,
|
| 272 |
+
"grad_norm": 0.0255126953125,
|
| 273 |
+
"learning_rate": 0.00019978923534209054,
|
| 274 |
+
"loss": 1.4201,
|
| 275 |
+
"step": 185
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.12179670167320222,
|
| 279 |
+
"grad_norm": 0.0286865234375,
|
| 280 |
+
"learning_rate": 0.00019971033070610518,
|
| 281 |
+
"loss": 1.4187,
|
| 282 |
+
"step": 190
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.12500187803302334,
|
| 286 |
+
"grad_norm": 0.030517578125,
|
| 287 |
+
"learning_rate": 0.0001996189275086033,
|
| 288 |
+
"loss": 1.4153,
|
| 289 |
+
"step": 195
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.12820705439284444,
|
| 293 |
+
"grad_norm": 0.0272216796875,
|
| 294 |
+
"learning_rate": 0.00019951503720685784,
|
| 295 |
+
"loss": 1.4279,
|
| 296 |
+
"step": 200
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.13141223075266556,
|
| 300 |
+
"grad_norm": 0.0267333984375,
|
| 301 |
+
"learning_rate": 0.0001993986728233844,
|
| 302 |
+
"loss": 1.4052,
|
| 303 |
+
"step": 205
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.13461740711248665,
|
| 307 |
+
"grad_norm": 0.0264892578125,
|
| 308 |
+
"learning_rate": 0.0001992698489443085,
|
| 309 |
+
"loss": 1.3943,
|
| 310 |
+
"step": 210
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.13782258347230777,
|
| 314 |
+
"grad_norm": 0.032470703125,
|
| 315 |
+
"learning_rate": 0.0001991285817175375,
|
| 316 |
+
"loss": 1.3931,
|
| 317 |
+
"step": 215
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.1410277598321289,
|
| 321 |
+
"grad_norm": 0.0291748046875,
|
| 322 |
+
"learning_rate": 0.0001989748888507363,
|
| 323 |
+
"loss": 1.3931,
|
| 324 |
+
"step": 220
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.14423293619195,
|
| 328 |
+
"grad_norm": 0.03125,
|
| 329 |
+
"learning_rate": 0.00019880878960910772,
|
| 330 |
+
"loss": 1.3899,
|
| 331 |
+
"step": 225
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.1474381125517711,
|
| 335 |
+
"grad_norm": 0.0322265625,
|
| 336 |
+
"learning_rate": 0.0001986303048129778,
|
| 337 |
+
"loss": 1.4305,
|
| 338 |
+
"step": 230
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.15064328891159223,
|
| 342 |
+
"grad_norm": 0.033203125,
|
| 343 |
+
"learning_rate": 0.0001984394568351858,
|
| 344 |
+
"loss": 1.4028,
|
| 345 |
+
"step": 235
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.15384846527141333,
|
| 349 |
+
"grad_norm": 0.03369140625,
|
| 350 |
+
"learning_rate": 0.00019823626959827997,
|
| 351 |
+
"loss": 1.3758,
|
| 352 |
+
"step": 240
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.15705364163123445,
|
| 356 |
+
"grad_norm": 0.041015625,
|
| 357 |
+
"learning_rate": 0.0001980207685715186,
|
| 358 |
+
"loss": 1.407,
|
| 359 |
+
"step": 245
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.16025881799105554,
|
| 363 |
+
"grad_norm": 0.034912109375,
|
| 364 |
+
"learning_rate": 0.00019779298076767795,
|
| 365 |
+
"loss": 1.3923,
|
| 366 |
+
"step": 250
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.16346399435087666,
|
| 370 |
+
"grad_norm": 0.047119140625,
|
| 371 |
+
"learning_rate": 0.00019755293473966572,
|
| 372 |
+
"loss": 1.3967,
|
| 373 |
+
"step": 255
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.16666917071069778,
|
| 377 |
+
"grad_norm": 0.043701171875,
|
| 378 |
+
"learning_rate": 0.00019730066057694235,
|
| 379 |
+
"loss": 1.4007,
|
| 380 |
+
"step": 260
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.16987434707051888,
|
| 384 |
+
"grad_norm": 0.050048828125,
|
| 385 |
+
"learning_rate": 0.00019703618990174918,
|
| 386 |
+
"loss": 1.3978,
|
| 387 |
+
"step": 265
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.17307952343034,
|
| 391 |
+
"grad_norm": 0.048095703125,
|
| 392 |
+
"learning_rate": 0.00019675955586514468,
|
| 393 |
+
"loss": 1.3744,
|
| 394 |
+
"step": 270
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.17628469979016112,
|
| 398 |
+
"grad_norm": 0.033935546875,
|
| 399 |
+
"learning_rate": 0.00019647079314284897,
|
| 400 |
+
"loss": 1.3929,
|
| 401 |
+
"step": 275
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.1794898761499822,
|
| 405 |
+
"grad_norm": 0.033935546875,
|
| 406 |
+
"learning_rate": 0.0001961699379308974,
|
| 407 |
+
"loss": 1.4031,
|
| 408 |
+
"step": 280
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.18269505250980334,
|
| 412 |
+
"grad_norm": 0.04052734375,
|
| 413 |
+
"learning_rate": 0.0001958570279411032,
|
| 414 |
+
"loss": 1.3813,
|
| 415 |
+
"step": 285
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.18590022886962446,
|
| 419 |
+
"grad_norm": 0.052734375,
|
| 420 |
+
"learning_rate": 0.00019553210239633056,
|
| 421 |
+
"loss": 1.3956,
|
| 422 |
+
"step": 290
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.18910540522944555,
|
| 426 |
+
"grad_norm": 0.048095703125,
|
| 427 |
+
"learning_rate": 0.00019519520202557797,
|
| 428 |
+
"loss": 1.3988,
|
| 429 |
+
"step": 295
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.19231058158926667,
|
| 433 |
+
"grad_norm": 0.037109375,
|
| 434 |
+
"learning_rate": 0.00019484636905887296,
|
| 435 |
+
"loss": 1.3925,
|
| 436 |
+
"step": 300
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.19551575794908777,
|
| 440 |
+
"grad_norm": 0.036865234375,
|
| 441 |
+
"learning_rate": 0.00019448564722197853,
|
| 442 |
+
"loss": 1.376,
|
| 443 |
+
"step": 305
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.1987209343089089,
|
| 447 |
+
"grad_norm": 0.04052734375,
|
| 448 |
+
"learning_rate": 0.00019411308173091228,
|
| 449 |
+
"loss": 1.3974,
|
| 450 |
+
"step": 310
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.20192611066873,
|
| 454 |
+
"grad_norm": 0.052490234375,
|
| 455 |
+
"learning_rate": 0.0001937287192862787,
|
| 456 |
+
"loss": 1.3765,
|
| 457 |
+
"step": 315
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.2051312870285511,
|
| 461 |
+
"grad_norm": 0.059326171875,
|
| 462 |
+
"learning_rate": 0.00019333260806741502,
|
| 463 |
+
"loss": 1.3769,
|
| 464 |
+
"step": 320
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.20833646338837222,
|
| 468 |
+
"grad_norm": 0.052490234375,
|
| 469 |
+
"learning_rate": 0.00019292479772635237,
|
| 470 |
+
"loss": 1.3792,
|
| 471 |
+
"step": 325
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.21154163974819334,
|
| 475 |
+
"grad_norm": 0.048583984375,
|
| 476 |
+
"learning_rate": 0.00019250533938159166,
|
| 477 |
+
"loss": 1.3968,
|
| 478 |
+
"step": 330
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 0.21474681610801444,
|
| 482 |
+
"grad_norm": 0.040283203125,
|
| 483 |
+
"learning_rate": 0.00019207428561169608,
|
| 484 |
+
"loss": 1.38,
|
| 485 |
+
"step": 335
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.21795199246783556,
|
| 489 |
+
"grad_norm": 0.043701171875,
|
| 490 |
+
"learning_rate": 0.0001916316904487005,
|
| 491 |
+
"loss": 1.3737,
|
| 492 |
+
"step": 340
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 0.22115716882765665,
|
| 496 |
+
"grad_norm": 0.03759765625,
|
| 497 |
+
"learning_rate": 0.00019117760937133844,
|
| 498 |
+
"loss": 1.4065,
|
| 499 |
+
"step": 345
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.22436234518747777,
|
| 503 |
+
"grad_norm": 0.038330078125,
|
| 504 |
+
"learning_rate": 0.00019071209929808806,
|
| 505 |
+
"loss": 1.4012,
|
| 506 |
+
"step": 350
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.2275675215472989,
|
| 510 |
+
"grad_norm": 0.041748046875,
|
| 511 |
+
"learning_rate": 0.00019023521858003742,
|
| 512 |
+
"loss": 1.3941,
|
| 513 |
+
"step": 355
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.23077269790712,
|
| 517 |
+
"grad_norm": 0.037841796875,
|
| 518 |
+
"learning_rate": 0.00018974702699357029,
|
| 519 |
+
"loss": 1.4072,
|
| 520 |
+
"step": 360
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 0.2339778742669411,
|
| 524 |
+
"grad_norm": 0.03759765625,
|
| 525 |
+
"learning_rate": 0.00018924758573287315,
|
| 526 |
+
"loss": 1.3531,
|
| 527 |
+
"step": 365
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.23718305062676223,
|
| 531 |
+
"grad_norm": 0.03662109375,
|
| 532 |
+
"learning_rate": 0.00018873695740226468,
|
| 533 |
+
"loss": 1.3682,
|
| 534 |
+
"step": 370
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.24038822698658333,
|
| 538 |
+
"grad_norm": 0.047607421875,
|
| 539 |
+
"learning_rate": 0.0001882152060083484,
|
| 540 |
+
"loss": 1.3796,
|
| 541 |
+
"step": 375
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.24359340334640445,
|
| 545 |
+
"grad_norm": 0.041015625,
|
| 546 |
+
"learning_rate": 0.00018768239695198945,
|
| 547 |
+
"loss": 1.3835,
|
| 548 |
+
"step": 380
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 0.24679857970622554,
|
| 552 |
+
"grad_norm": 0.04541015625,
|
| 553 |
+
"learning_rate": 0.0001871385970201168,
|
| 554 |
+
"loss": 1.3678,
|
| 555 |
+
"step": 385
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.2500037560660467,
|
| 559 |
+
"grad_norm": 0.04345703125,
|
| 560 |
+
"learning_rate": 0.00018658387437735135,
|
| 561 |
+
"loss": 1.3778,
|
| 562 |
+
"step": 390
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 0.2532089324258678,
|
| 566 |
+
"grad_norm": 0.06396484375,
|
| 567 |
+
"learning_rate": 0.00018601829855746185,
|
| 568 |
+
"loss": 1.3811,
|
| 569 |
+
"step": 395
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.2564141087856889,
|
| 573 |
+
"grad_norm": 0.057373046875,
|
| 574 |
+
"learning_rate": 0.00018544194045464886,
|
| 575 |
+
"loss": 1.3851,
|
| 576 |
+
"step": 400
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 0.25961928514551,
|
| 580 |
+
"grad_norm": 0.0458984375,
|
| 581 |
+
"learning_rate": 0.0001848548723146581,
|
| 582 |
+
"loss": 1.3865,
|
| 583 |
+
"step": 405
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.2628244615053311,
|
| 587 |
+
"grad_norm": 0.047119140625,
|
| 588 |
+
"learning_rate": 0.00018425716772572473,
|
| 589 |
+
"loss": 1.3638,
|
| 590 |
+
"step": 410
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 0.2660296378651522,
|
| 594 |
+
"grad_norm": 0.04443359375,
|
| 595 |
+
"learning_rate": 0.00018364890160934904,
|
| 596 |
+
"loss": 1.3918,
|
| 597 |
+
"step": 415
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.2692348142249733,
|
| 601 |
+
"grad_norm": 0.042236328125,
|
| 602 |
+
"learning_rate": 0.00018303015021090525,
|
| 603 |
+
"loss": 1.3794,
|
| 604 |
+
"step": 420
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 0.27243999058479446,
|
| 608 |
+
"grad_norm": 0.06005859375,
|
| 609 |
+
"learning_rate": 0.00018240099109008412,
|
| 610 |
+
"loss": 1.3836,
|
| 611 |
+
"step": 425
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.27564516694461555,
|
| 615 |
+
"grad_norm": 0.05419921875,
|
| 616 |
+
"learning_rate": 0.000181761503111171,
|
| 617 |
+
"loss": 1.3676,
|
| 618 |
+
"step": 430
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 0.27885034330443664,
|
| 622 |
+
"grad_norm": 0.04443359375,
|
| 623 |
+
"learning_rate": 0.0001811117664331604,
|
| 624 |
+
"loss": 1.3513,
|
| 625 |
+
"step": 435
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.2820555196642578,
|
| 629 |
+
"grad_norm": 0.047607421875,
|
| 630 |
+
"learning_rate": 0.00018045186249970784,
|
| 631 |
+
"loss": 1.3602,
|
| 632 |
+
"step": 440
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 0.2852606960240789,
|
| 636 |
+
"grad_norm": 0.043212890625,
|
| 637 |
+
"learning_rate": 0.00017978187402892148,
|
| 638 |
+
"loss": 1.3468,
|
| 639 |
+
"step": 445
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.2884658723839,
|
| 643 |
+
"grad_norm": 0.05078125,
|
| 644 |
+
"learning_rate": 0.00017910188500299304,
|
| 645 |
+
"loss": 1.3651,
|
| 646 |
+
"step": 450
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 0.29167104874372113,
|
| 650 |
+
"grad_norm": 0.04296875,
|
| 651 |
+
"learning_rate": 0.00017841198065767107,
|
| 652 |
+
"loss": 1.3763,
|
| 653 |
+
"step": 455
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 0.2948762251035422,
|
| 657 |
+
"grad_norm": 0.044921875,
|
| 658 |
+
"learning_rate": 0.00017771224747157652,
|
| 659 |
+
"loss": 1.3597,
|
| 660 |
+
"step": 460
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 0.2980814014633633,
|
| 664 |
+
"grad_norm": 0.0654296875,
|
| 665 |
+
"learning_rate": 0.00017700277315536305,
|
| 666 |
+
"loss": 1.3558,
|
| 667 |
+
"step": 465
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 0.30128657782318446,
|
| 671 |
+
"grad_norm": 0.052978515625,
|
| 672 |
+
"learning_rate": 0.00017628364664072218,
|
| 673 |
+
"loss": 1.3534,
|
| 674 |
+
"step": 470
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 0.30449175418300556,
|
| 678 |
+
"grad_norm": 0.04248046875,
|
| 679 |
+
"learning_rate": 0.00017555495806923635,
|
| 680 |
+
"loss": 1.3525,
|
| 681 |
+
"step": 475
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.30769693054282665,
|
| 685 |
+
"grad_norm": 0.044189453125,
|
| 686 |
+
"learning_rate": 0.00017481679878107926,
|
| 687 |
+
"loss": 1.3715,
|
| 688 |
+
"step": 480
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 0.3109021069026478,
|
| 692 |
+
"grad_norm": 0.058837890625,
|
| 693 |
+
"learning_rate": 0.00017406926130356692,
|
| 694 |
+
"loss": 1.3689,
|
| 695 |
+
"step": 485
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 0.3141072832624689,
|
| 699 |
+
"grad_norm": 0.095703125,
|
| 700 |
+
"learning_rate": 0.00017331243933955918,
|
| 701 |
+
"loss": 1.3686,
|
| 702 |
+
"step": 490
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 0.31731245962229,
|
| 706 |
+
"grad_norm": 0.059326171875,
|
| 707 |
+
"learning_rate": 0.00017254642775571438,
|
| 708 |
+
"loss": 1.3784,
|
| 709 |
+
"step": 495
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 0.3205176359821111,
|
| 713 |
+
"grad_norm": 0.07373046875,
|
| 714 |
+
"learning_rate": 0.00017177132257059787,
|
| 715 |
+
"loss": 1.3488,
|
| 716 |
+
"step": 500
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 0.32372281234193223,
|
| 720 |
+
"grad_norm": 0.0439453125,
|
| 721 |
+
"learning_rate": 0.00017098722094264617,
|
| 722 |
+
"loss": 1.3789,
|
| 723 |
+
"step": 505
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 0.3269279887017533,
|
| 727 |
+
"grad_norm": 0.052490234375,
|
| 728 |
+
"learning_rate": 0.00017019422115798833,
|
| 729 |
+
"loss": 1.3414,
|
| 730 |
+
"step": 510
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 0.3301331650615744,
|
| 734 |
+
"grad_norm": 0.0458984375,
|
| 735 |
+
"learning_rate": 0.0001693924226181259,
|
| 736 |
+
"loss": 1.3667,
|
| 737 |
+
"step": 515
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 0.33333834142139557,
|
| 741 |
+
"grad_norm": 0.05322265625,
|
| 742 |
+
"learning_rate": 0.00016858192582747304,
|
| 743 |
+
"loss": 1.3749,
|
| 744 |
+
"step": 520
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 0.33654351778121666,
|
| 748 |
+
"grad_norm": 0.0634765625,
|
| 749 |
+
"learning_rate": 0.00016776283238075851,
|
| 750 |
+
"loss": 1.3929,
|
| 751 |
+
"step": 525
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 0.33974869414103775,
|
| 755 |
+
"grad_norm": 0.050537109375,
|
| 756 |
+
"learning_rate": 0.00016693524495029068,
|
| 757 |
+
"loss": 1.3527,
|
| 758 |
+
"step": 530
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 0.3429538705008589,
|
| 762 |
+
"grad_norm": 0.059814453125,
|
| 763 |
+
"learning_rate": 0.00016609926727308806,
|
| 764 |
+
"loss": 1.3577,
|
| 765 |
+
"step": 535
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 0.34615904686068,
|
| 769 |
+
"grad_norm": 0.07861328125,
|
| 770 |
+
"learning_rate": 0.00016525500413787554,
|
| 771 |
+
"loss": 1.3639,
|
| 772 |
+
"step": 540
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 0.3493642232205011,
|
| 776 |
+
"grad_norm": 0.0595703125,
|
| 777 |
+
"learning_rate": 0.00016440256137194965,
|
| 778 |
+
"loss": 1.3608,
|
| 779 |
+
"step": 545
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 0.35256939958032224,
|
| 783 |
+
"grad_norm": 0.052978515625,
|
| 784 |
+
"learning_rate": 0.0001635420458279131,
|
| 785 |
+
"loss": 1.3324,
|
| 786 |
+
"step": 550
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 0.35577457594014333,
|
| 790 |
+
"grad_norm": 0.062255859375,
|
| 791 |
+
"learning_rate": 0.0001626735653702809,
|
| 792 |
+
"loss": 1.3283,
|
| 793 |
+
"step": 555
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 0.3589797522999644,
|
| 797 |
+
"grad_norm": 0.04931640625,
|
| 798 |
+
"learning_rate": 0.00016179722886195967,
|
| 799 |
+
"loss": 1.3287,
|
| 800 |
+
"step": 560
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 0.3621849286597856,
|
| 804 |
+
"grad_norm": 0.0703125,
|
| 805 |
+
"learning_rate": 0.00016091314615060195,
|
| 806 |
+
"loss": 1.3799,
|
| 807 |
+
"step": 565
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 0.36539010501960667,
|
| 811 |
+
"grad_norm": 0.051025390625,
|
| 812 |
+
"learning_rate": 0.00016002142805483685,
|
| 813 |
+
"loss": 1.3399,
|
| 814 |
+
"step": 570
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 0.36859528137942776,
|
| 818 |
+
"grad_norm": 0.05908203125,
|
| 819 |
+
"learning_rate": 0.00015912218635037896,
|
| 820 |
+
"loss": 1.3698,
|
| 821 |
+
"step": 575
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 0.3718004577392489,
|
| 825 |
+
"grad_norm": 0.05078125,
|
| 826 |
+
"learning_rate": 0.0001582155337560177,
|
| 827 |
+
"loss": 1.3378,
|
| 828 |
+
"step": 580
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 0.37500563409907,
|
| 832 |
+
"grad_norm": 0.051025390625,
|
| 833 |
+
"learning_rate": 0.00015730158391948784,
|
| 834 |
+
"loss": 1.337,
|
| 835 |
+
"step": 585
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 0.3782108104588911,
|
| 839 |
+
"grad_norm": 0.0498046875,
|
| 840 |
+
"learning_rate": 0.0001563804514032242,
|
| 841 |
+
"loss": 1.3527,
|
| 842 |
+
"step": 590
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 0.3814159868187122,
|
| 846 |
+
"grad_norm": 0.052734375,
|
| 847 |
+
"learning_rate": 0.0001554522516700011,
|
| 848 |
+
"loss": 1.3583,
|
| 849 |
+
"step": 595
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 0.38462116317853334,
|
| 853 |
+
"grad_norm": 0.06201171875,
|
| 854 |
+
"learning_rate": 0.00015451710106845955,
|
| 855 |
+
"loss": 1.3421,
|
| 856 |
+
"step": 600
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 0.38782633953835444,
|
| 860 |
+
"grad_norm": 0.050537109375,
|
| 861 |
+
"learning_rate": 0.0001535751168185228,
|
| 862 |
+
"loss": 1.3577,
|
| 863 |
+
"step": 605
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 0.39103151589817553,
|
| 867 |
+
"grad_norm": 0.05517578125,
|
| 868 |
+
"learning_rate": 0.00015262641699670328,
|
| 869 |
+
"loss": 1.3706,
|
| 870 |
+
"step": 610
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 0.3942366922579967,
|
| 874 |
+
"grad_norm": 0.054931640625,
|
| 875 |
+
"learning_rate": 0.0001516711205213016,
|
| 876 |
+
"loss": 1.3439,
|
| 877 |
+
"step": 615
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 0.3974418686178178,
|
| 881 |
+
"grad_norm": 0.0478515625,
|
| 882 |
+
"learning_rate": 0.00015070934713750042,
|
| 883 |
+
"loss": 1.3353,
|
| 884 |
+
"step": 620
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 0.40064704497763887,
|
| 888 |
+
"grad_norm": 0.048583984375,
|
| 889 |
+
"learning_rate": 0.00014974121740235456,
|
| 890 |
+
"loss": 1.3489,
|
| 891 |
+
"step": 625
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 0.40385222133746,
|
| 895 |
+
"grad_norm": 0.057373046875,
|
| 896 |
+
"learning_rate": 0.00014876685266967924,
|
| 897 |
+
"loss": 1.3481,
|
| 898 |
+
"step": 630
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 0.4070573976972811,
|
| 902 |
+
"grad_norm": 0.053466796875,
|
| 903 |
+
"learning_rate": 0.00014778637507483866,
|
| 904 |
+
"loss": 1.3533,
|
| 905 |
+
"step": 635
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 0.4102625740571022,
|
| 909 |
+
"grad_norm": 0.06494140625,
|
| 910 |
+
"learning_rate": 0.0001467999075194363,
|
| 911 |
+
"loss": 1.3522,
|
| 912 |
+
"step": 640
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 0.41346775041692335,
|
| 916 |
+
"grad_norm": 0.06689453125,
|
| 917 |
+
"learning_rate": 0.00014580757365590963,
|
| 918 |
+
"loss": 1.3712,
|
| 919 |
+
"step": 645
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 0.41667292677674445,
|
| 923 |
+
"grad_norm": 0.053955078125,
|
| 924 |
+
"learning_rate": 0.00014480949787203014,
|
| 925 |
+
"loss": 1.3606,
|
| 926 |
+
"step": 650
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 0.41987810313656554,
|
| 930 |
+
"grad_norm": 0.046875,
|
| 931 |
+
"learning_rate": 0.0001438058052753118,
|
| 932 |
+
"loss": 1.3488,
|
| 933 |
+
"step": 655
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 0.4230832794963867,
|
| 937 |
+
"grad_norm": 0.058837890625,
|
| 938 |
+
"learning_rate": 0.00014279662167732867,
|
| 939 |
+
"loss": 1.342,
|
| 940 |
+
"step": 660
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 0.4262884558562078,
|
| 944 |
+
"grad_norm": 0.07080078125,
|
| 945 |
+
"learning_rate": 0.00014178207357794486,
|
| 946 |
+
"loss": 1.3712,
|
| 947 |
+
"step": 665
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 0.4294936322160289,
|
| 951 |
+
"grad_norm": 0.05029296875,
|
| 952 |
+
"learning_rate": 0.00014076228814945778,
|
| 953 |
+
"loss": 1.3227,
|
| 954 |
+
"step": 670
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 0.43269880857585,
|
| 958 |
+
"grad_norm": 0.06982421875,
|
| 959 |
+
"learning_rate": 0.00013973739322065728,
|
| 960 |
+
"loss": 1.3201,
|
| 961 |
+
"step": 675
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 0.4359039849356711,
|
| 965 |
+
"grad_norm": 0.05029296875,
|
| 966 |
+
"learning_rate": 0.00013870751726080256,
|
| 967 |
+
"loss": 1.3406,
|
| 968 |
+
"step": 680
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 0.4391091612954922,
|
| 972 |
+
"grad_norm": 0.06201171875,
|
| 973 |
+
"learning_rate": 0.00013767278936351854,
|
| 974 |
+
"loss": 1.3636,
|
| 975 |
+
"step": 685
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 0.4423143376553133,
|
| 979 |
+
"grad_norm": 0.0458984375,
|
| 980 |
+
"learning_rate": 0.0001366333392306143,
|
| 981 |
+
"loss": 1.3576,
|
| 982 |
+
"step": 690
|
| 983 |
+
},
|
| 984 |
+
{
|
| 985 |
+
"epoch": 0.44551951401513445,
|
| 986 |
+
"grad_norm": 0.06005859375,
|
| 987 |
+
"learning_rate": 0.00013558929715582515,
|
| 988 |
+
"loss": 1.3517,
|
| 989 |
+
"step": 695
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 0.44872469037495555,
|
| 993 |
+
"grad_norm": 0.05126953125,
|
| 994 |
+
"learning_rate": 0.00013454079400848027,
|
| 995 |
+
"loss": 1.3376,
|
| 996 |
+
"step": 700
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 0.45192986673477664,
|
| 1000 |
+
"grad_norm": 0.059326171875,
|
| 1001 |
+
"learning_rate": 0.00013348796121709862,
|
| 1002 |
+
"loss": 1.3633,
|
| 1003 |
+
"step": 705
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 0.4551350430945978,
|
| 1007 |
+
"grad_norm": 0.05078125,
|
| 1008 |
+
"learning_rate": 0.00013243093075291444,
|
| 1009 |
+
"loss": 1.3217,
|
| 1010 |
+
"step": 710
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 0.4583402194544189,
|
| 1014 |
+
"grad_norm": 0.056884765625,
|
| 1015 |
+
"learning_rate": 0.00013136983511333482,
|
| 1016 |
+
"loss": 1.3265,
|
| 1017 |
+
"step": 715
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 0.46154539581424,
|
| 1021 |
+
"grad_norm": 0.05859375,
|
| 1022 |
+
"learning_rate": 0.00013030480730533145,
|
| 1023 |
+
"loss": 1.3451,
|
| 1024 |
+
"step": 720
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 0.4647505721740611,
|
| 1028 |
+
"grad_norm": 0.054443359375,
|
| 1029 |
+
"learning_rate": 0.00012923598082876812,
|
| 1030 |
+
"loss": 1.376,
|
| 1031 |
+
"step": 725
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 0.4679557485338822,
|
| 1035 |
+
"grad_norm": 0.058349609375,
|
| 1036 |
+
"learning_rate": 0.0001281634896596669,
|
| 1037 |
+
"loss": 1.3524,
|
| 1038 |
+
"step": 730
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"epoch": 0.4711609248937033,
|
| 1042 |
+
"grad_norm": 0.0634765625,
|
| 1043 |
+
"learning_rate": 0.00012708746823341446,
|
| 1044 |
+
"loss": 1.3599,
|
| 1045 |
+
"step": 735
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 0.47436610125352446,
|
| 1049 |
+
"grad_norm": 0.053466796875,
|
| 1050 |
+
"learning_rate": 0.00012600805142791042,
|
| 1051 |
+
"loss": 1.3416,
|
| 1052 |
+
"step": 740
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 0.47757127761334556,
|
| 1056 |
+
"grad_norm": 0.055419921875,
|
| 1057 |
+
"learning_rate": 0.000124925374546661,
|
| 1058 |
+
"loss": 1.3574,
|
| 1059 |
+
"step": 745
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 0.48077645397316665,
|
| 1063 |
+
"grad_norm": 0.052978515625,
|
| 1064 |
+
"learning_rate": 0.0001238395733018187,
|
| 1065 |
+
"loss": 1.3574,
|
| 1066 |
+
"step": 750
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 0.4839816303329878,
|
| 1070 |
+
"grad_norm": 0.053466796875,
|
| 1071 |
+
"learning_rate": 0.00012275078379717089,
|
| 1072 |
+
"loss": 1.3341,
|
| 1073 |
+
"step": 755
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 0.4871868066928089,
|
| 1077 |
+
"grad_norm": 0.0556640625,
|
| 1078 |
+
"learning_rate": 0.00012165914251107952,
|
| 1079 |
+
"loss": 1.3241,
|
| 1080 |
+
"step": 760
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 0.49039198305263,
|
| 1084 |
+
"grad_norm": 0.054443359375,
|
| 1085 |
+
"learning_rate": 0.00012056478627937365,
|
| 1086 |
+
"loss": 1.3788,
|
| 1087 |
+
"step": 765
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 0.4935971594124511,
|
| 1091 |
+
"grad_norm": 0.049560546875,
|
| 1092 |
+
"learning_rate": 0.00011946785227819726,
|
| 1093 |
+
"loss": 1.3581,
|
| 1094 |
+
"step": 770
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 0.49680233577227223,
|
| 1098 |
+
"grad_norm": 0.05615234375,
|
| 1099 |
+
"learning_rate": 0.00011836847800681443,
|
| 1100 |
+
"loss": 1.3328,
|
| 1101 |
+
"step": 775
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 0.5000075121320934,
|
| 1105 |
+
"grad_norm": 0.0556640625,
|
| 1106 |
+
"learning_rate": 0.00011726680127037401,
|
| 1107 |
+
"loss": 1.3533,
|
| 1108 |
+
"step": 780
|
| 1109 |
+
},
|
| 1110 |
+
{
|
| 1111 |
+
"epoch": 0.5032126884919145,
|
| 1112 |
+
"grad_norm": 0.05419921875,
|
| 1113 |
+
"learning_rate": 0.00011616296016263582,
|
| 1114 |
+
"loss": 1.3622,
|
| 1115 |
+
"step": 785
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 0.5064178648517356,
|
| 1119 |
+
"grad_norm": 0.049072265625,
|
| 1120 |
+
"learning_rate": 0.00011505709304866084,
|
| 1121 |
+
"loss": 1.3446,
|
| 1122 |
+
"step": 790
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 0.5096230412115567,
|
| 1126 |
+
"grad_norm": 0.0712890625,
|
| 1127 |
+
"learning_rate": 0.00011394933854746733,
|
| 1128 |
+
"loss": 1.3384,
|
| 1129 |
+
"step": 795
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 0.5128282175713778,
|
| 1133 |
+
"grad_norm": 0.055908203125,
|
| 1134 |
+
"learning_rate": 0.00011283983551465511,
|
| 1135 |
+
"loss": 1.3378,
|
| 1136 |
+
"step": 800
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 0.5160333939311988,
|
| 1140 |
+
"grad_norm": 0.060791015625,
|
| 1141 |
+
"learning_rate": 0.00011172872302500017,
|
| 1142 |
+
"loss": 1.3656,
|
| 1143 |
+
"step": 805
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 0.51923857029102,
|
| 1147 |
+
"grad_norm": 0.0791015625,
|
| 1148 |
+
"learning_rate": 0.00011061614035502193,
|
| 1149 |
+
"loss": 1.3521,
|
| 1150 |
+
"step": 810
|
| 1151 |
+
},
|
| 1152 |
+
{
|
| 1153 |
+
"epoch": 0.5224437466508411,
|
| 1154 |
+
"grad_norm": 0.05859375,
|
| 1155 |
+
"learning_rate": 0.00010950222696552486,
|
| 1156 |
+
"loss": 1.3614,
|
| 1157 |
+
"step": 815
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 0.5256489230106622,
|
| 1161 |
+
"grad_norm": 0.08203125,
|
| 1162 |
+
"learning_rate": 0.00010838712248411753,
|
| 1163 |
+
"loss": 1.3314,
|
| 1164 |
+
"step": 820
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 0.5288540993704833,
|
| 1168 |
+
"grad_norm": 0.05322265625,
|
| 1169 |
+
"learning_rate": 0.00010727096668771036,
|
| 1170 |
+
"loss": 1.338,
|
| 1171 |
+
"step": 825
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 0.5320592757303044,
|
| 1175 |
+
"grad_norm": 0.0556640625,
|
| 1176 |
+
"learning_rate": 0.0001061538994849946,
|
| 1177 |
+
"loss": 1.3611,
|
| 1178 |
+
"step": 830
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 0.5352644520901255,
|
| 1182 |
+
"grad_norm": 0.06201171875,
|
| 1183 |
+
"learning_rate": 0.00010503606089890529,
|
| 1184 |
+
"loss": 1.3175,
|
| 1185 |
+
"step": 835
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 0.5384696284499466,
|
| 1189 |
+
"grad_norm": 0.05712890625,
|
| 1190 |
+
"learning_rate": 0.00010391759104906928,
|
| 1191 |
+
"loss": 1.3525,
|
| 1192 |
+
"step": 840
|
| 1193 |
+
},
|
| 1194 |
+
{
|
| 1195 |
+
"epoch": 0.5416748048097678,
|
| 1196 |
+
"grad_norm": 0.0498046875,
|
| 1197 |
+
"learning_rate": 0.00010279863013424154,
|
| 1198 |
+
"loss": 1.3313,
|
| 1199 |
+
"step": 845
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 0.5448799811695889,
|
| 1203 |
+
"grad_norm": 0.051025390625,
|
| 1204 |
+
"learning_rate": 0.00010167931841473142,
|
| 1205 |
+
"loss": 1.3349,
|
| 1206 |
+
"step": 850
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"epoch": 0.54808515752941,
|
| 1210 |
+
"grad_norm": 0.06298828125,
|
| 1211 |
+
"learning_rate": 0.00010055979619482112,
|
| 1212 |
+
"loss": 1.3408,
|
| 1213 |
+
"step": 855
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 0.5512903338892311,
|
| 1217 |
+
"grad_norm": 0.058837890625,
|
| 1218 |
+
"learning_rate": 9.944020380517889e-05,
|
| 1219 |
+
"loss": 1.3175,
|
| 1220 |
+
"step": 860
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 0.5544955102490522,
|
| 1224 |
+
"grad_norm": 0.050048828125,
|
| 1225 |
+
"learning_rate": 9.832068158526862e-05,
|
| 1226 |
+
"loss": 1.3375,
|
| 1227 |
+
"step": 865
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 0.5577006866088733,
|
| 1231 |
+
"grad_norm": 0.0498046875,
|
| 1232 |
+
"learning_rate": 9.720136986575848e-05,
|
| 1233 |
+
"loss": 1.3475,
|
| 1234 |
+
"step": 870
|
| 1235 |
+
},
|
| 1236 |
+
{
|
| 1237 |
+
"epoch": 0.5609058629686945,
|
| 1238 |
+
"grad_norm": 0.051513671875,
|
| 1239 |
+
"learning_rate": 9.608240895093076e-05,
|
| 1240 |
+
"loss": 1.3295,
|
| 1241 |
+
"step": 875
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 0.5641110393285156,
|
| 1245 |
+
"grad_norm": 0.046142578125,
|
| 1246 |
+
"learning_rate": 9.496393910109472e-05,
|
| 1247 |
+
"loss": 1.3429,
|
| 1248 |
+
"step": 880
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 0.5673162156883367,
|
| 1252 |
+
"grad_norm": 0.04443359375,
|
| 1253 |
+
"learning_rate": 9.384610051500545e-05,
|
| 1254 |
+
"loss": 1.3293,
|
| 1255 |
+
"step": 885
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 0.5705213920481578,
|
| 1259 |
+
"grad_norm": 0.052734375,
|
| 1260 |
+
"learning_rate": 9.272903331228968e-05,
|
| 1261 |
+
"loss": 1.3498,
|
| 1262 |
+
"step": 890
|
| 1263 |
+
},
|
| 1264 |
+
{
|
| 1265 |
+
"epoch": 0.5737265684079789,
|
| 1266 |
+
"grad_norm": 0.062255859375,
|
| 1267 |
+
"learning_rate": 9.161287751588248e-05,
|
| 1268 |
+
"loss": 1.3351,
|
| 1269 |
+
"step": 895
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 0.5769317447678,
|
| 1273 |
+
"grad_norm": 0.064453125,
|
| 1274 |
+
"learning_rate": 9.049777303447516e-05,
|
| 1275 |
+
"loss": 1.353,
|
| 1276 |
+
"step": 900
|
| 1277 |
+
},
|
| 1278 |
+
{
|
| 1279 |
+
"epoch": 0.5801369211276212,
|
| 1280 |
+
"grad_norm": 0.0556640625,
|
| 1281 |
+
"learning_rate": 8.938385964497808e-05,
|
| 1282 |
+
"loss": 1.3363,
|
| 1283 |
+
"step": 905
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 0.5833420974874423,
|
| 1287 |
+
"grad_norm": 0.06201171875,
|
| 1288 |
+
"learning_rate": 8.827127697499984e-05,
|
| 1289 |
+
"loss": 1.3696,
|
| 1290 |
+
"step": 910
|
| 1291 |
+
},
|
| 1292 |
+
{
|
| 1293 |
+
"epoch": 0.5865472738472634,
|
| 1294 |
+
"grad_norm": 0.080078125,
|
| 1295 |
+
"learning_rate": 8.71601644853449e-05,
|
| 1296 |
+
"loss": 1.3481,
|
| 1297 |
+
"step": 915
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 0.5897524502070844,
|
| 1301 |
+
"grad_norm": 0.06884765625,
|
| 1302 |
+
"learning_rate": 8.605066145253268e-05,
|
| 1303 |
+
"loss": 1.3256,
|
| 1304 |
+
"step": 920
|
| 1305 |
+
},
|
| 1306 |
+
{
|
| 1307 |
+
"epoch": 0.5929576265669055,
|
| 1308 |
+
"grad_norm": 0.051513671875,
|
| 1309 |
+
"learning_rate": 8.494290695133917e-05,
|
| 1310 |
+
"loss": 1.3544,
|
| 1311 |
+
"step": 925
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 0.5961628029267266,
|
| 1315 |
+
"grad_norm": 0.05810546875,
|
| 1316 |
+
"learning_rate": 8.383703983736419e-05,
|
| 1317 |
+
"loss": 1.3443,
|
| 1318 |
+
"step": 930
|
| 1319 |
+
},
|
| 1320 |
+
{
|
| 1321 |
+
"epoch": 0.5993679792865477,
|
| 1322 |
+
"grad_norm": 0.06103515625,
|
| 1323 |
+
"learning_rate": 8.2733198729626e-05,
|
| 1324 |
+
"loss": 1.3816,
|
| 1325 |
+
"step": 935
|
| 1326 |
+
},
|
| 1327 |
+
{
|
| 1328 |
+
"epoch": 0.6025731556463689,
|
| 1329 |
+
"grad_norm": 0.046142578125,
|
| 1330 |
+
"learning_rate": 8.163152199318558e-05,
|
| 1331 |
+
"loss": 1.3247,
|
| 1332 |
+
"step": 940
|
| 1333 |
+
},
|
| 1334 |
+
{
|
| 1335 |
+
"epoch": 0.60577833200619,
|
| 1336 |
+
"grad_norm": 0.053466796875,
|
| 1337 |
+
"learning_rate": 8.053214772180277e-05,
|
| 1338 |
+
"loss": 1.3532,
|
| 1339 |
+
"step": 945
|
| 1340 |
+
},
|
| 1341 |
+
{
|
| 1342 |
+
"epoch": 0.6089835083660111,
|
| 1343 |
+
"grad_norm": 0.05419921875,
|
| 1344 |
+
"learning_rate": 7.94352137206264e-05,
|
| 1345 |
+
"loss": 1.3443,
|
| 1346 |
+
"step": 950
|
| 1347 |
+
},
|
| 1348 |
+
{
|
| 1349 |
+
"epoch": 0.6121886847258322,
|
| 1350 |
+
"grad_norm": 0.047119140625,
|
| 1351 |
+
"learning_rate": 7.83408574889205e-05,
|
| 1352 |
+
"loss": 1.3327,
|
| 1353 |
+
"step": 955
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"epoch": 0.6153938610856533,
|
| 1357 |
+
"grad_norm": 0.0537109375,
|
| 1358 |
+
"learning_rate": 7.724921620282916e-05,
|
| 1359 |
+
"loss": 1.334,
|
| 1360 |
+
"step": 960
|
| 1361 |
+
},
|
| 1362 |
+
{
|
| 1363 |
+
"epoch": 0.6185990374454744,
|
| 1364 |
+
"grad_norm": 0.0703125,
|
| 1365 |
+
"learning_rate": 7.616042669818133e-05,
|
| 1366 |
+
"loss": 1.3572,
|
| 1367 |
+
"step": 965
|
| 1368 |
+
},
|
| 1369 |
+
{
|
| 1370 |
+
"epoch": 0.6218042138052956,
|
| 1371 |
+
"grad_norm": 0.055419921875,
|
| 1372 |
+
"learning_rate": 7.507462545333903e-05,
|
| 1373 |
+
"loss": 1.3322,
|
| 1374 |
+
"step": 970
|
| 1375 |
+
},
|
| 1376 |
+
{
|
| 1377 |
+
"epoch": 0.6250093901651167,
|
| 1378 |
+
"grad_norm": 0.07958984375,
|
| 1379 |
+
"learning_rate": 7.399194857208961e-05,
|
| 1380 |
+
"loss": 1.3222,
|
| 1381 |
+
"step": 975
|
| 1382 |
+
},
|
| 1383 |
+
{
|
| 1384 |
+
"epoch": 0.6282145665249378,
|
| 1385 |
+
"grad_norm": 0.05078125,
|
| 1386 |
+
"learning_rate": 7.291253176658561e-05,
|
| 1387 |
+
"loss": 1.3375,
|
| 1388 |
+
"step": 980
|
| 1389 |
+
},
|
| 1390 |
+
{
|
| 1391 |
+
"epoch": 0.6314197428847589,
|
| 1392 |
+
"grad_norm": 0.08251953125,
|
| 1393 |
+
"learning_rate": 7.183651034033313e-05,
|
| 1394 |
+
"loss": 1.3397,
|
| 1395 |
+
"step": 985
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"epoch": 0.63462491924458,
|
| 1399 |
+
"grad_norm": 0.04931640625,
|
| 1400 |
+
"learning_rate": 7.07640191712319e-05,
|
| 1401 |
+
"loss": 1.34,
|
| 1402 |
+
"step": 990
|
| 1403 |
+
},
|
| 1404 |
+
{
|
| 1405 |
+
"epoch": 0.6378300956044011,
|
| 1406 |
+
"grad_norm": 0.049072265625,
|
| 1407 |
+
"learning_rate": 6.969519269466857e-05,
|
| 1408 |
+
"loss": 1.3344,
|
| 1409 |
+
"step": 995
|
| 1410 |
+
},
|
| 1411 |
+
{
|
| 1412 |
+
"epoch": 0.6410352719642222,
|
| 1413 |
+
"grad_norm": 0.052490234375,
|
| 1414 |
+
"learning_rate": 6.863016488666517e-05,
|
| 1415 |
+
"loss": 1.3475,
|
| 1416 |
+
"step": 1000
|
| 1417 |
+
},
|
| 1418 |
+
{
|
| 1419 |
+
"epoch": 0.6442404483240434,
|
| 1420 |
+
"grad_norm": 0.04736328125,
|
| 1421 |
+
"learning_rate": 6.756906924708558e-05,
|
| 1422 |
+
"loss": 1.3317,
|
| 1423 |
+
"step": 1005
|
| 1424 |
+
},
|
| 1425 |
+
{
|
| 1426 |
+
"epoch": 0.6474456246838645,
|
| 1427 |
+
"grad_norm": 0.050537109375,
|
| 1428 |
+
"learning_rate": 6.651203878290139e-05,
|
| 1429 |
+
"loss": 1.3243,
|
| 1430 |
+
"step": 1010
|
| 1431 |
+
},
|
| 1432 |
+
{
|
| 1433 |
+
"epoch": 0.6506508010436856,
|
| 1434 |
+
"grad_norm": 0.053955078125,
|
| 1435 |
+
"learning_rate": 6.545920599151975e-05,
|
| 1436 |
+
"loss": 1.3351,
|
| 1437 |
+
"step": 1015
|
| 1438 |
+
},
|
| 1439 |
+
{
|
| 1440 |
+
"epoch": 0.6538559774035066,
|
| 1441 |
+
"grad_norm": 0.058837890625,
|
| 1442 |
+
"learning_rate": 6.441070284417487e-05,
|
| 1443 |
+
"loss": 1.3536,
|
| 1444 |
+
"step": 1020
|
| 1445 |
+
},
|
| 1446 |
+
{
|
| 1447 |
+
"epoch": 0.6570611537633277,
|
| 1448 |
+
"grad_norm": 0.060791015625,
|
| 1449 |
+
"learning_rate": 6.336666076938572e-05,
|
| 1450 |
+
"loss": 1.3064,
|
| 1451 |
+
"step": 1025
|
| 1452 |
+
},
|
| 1453 |
+
{
|
| 1454 |
+
"epoch": 0.6602663301231488,
|
| 1455 |
+
"grad_norm": 0.056396484375,
|
| 1456 |
+
"learning_rate": 6.232721063648148e-05,
|
| 1457 |
+
"loss": 1.3496,
|
| 1458 |
+
"step": 1030
|
| 1459 |
+
},
|
| 1460 |
+
{
|
| 1461 |
+
"epoch": 0.66347150648297,
|
| 1462 |
+
"grad_norm": 0.0478515625,
|
| 1463 |
+
"learning_rate": 6.12924827391975e-05,
|
| 1464 |
+
"loss": 1.3487,
|
| 1465 |
+
"step": 1035
|
| 1466 |
+
},
|
| 1467 |
+
{
|
| 1468 |
+
"epoch": 0.6666766828427911,
|
| 1469 |
+
"grad_norm": 0.05126953125,
|
| 1470 |
+
"learning_rate": 6.026260677934272e-05,
|
| 1471 |
+
"loss": 1.3241,
|
| 1472 |
+
"step": 1040
|
| 1473 |
+
},
|
| 1474 |
+
{
|
| 1475 |
+
"epoch": 0.6698818592026122,
|
| 1476 |
+
"grad_norm": 0.0478515625,
|
| 1477 |
+
"learning_rate": 5.9237711850542246e-05,
|
| 1478 |
+
"loss": 1.3454,
|
| 1479 |
+
"step": 1045
|
| 1480 |
+
},
|
| 1481 |
+
{
|
| 1482 |
+
"epoch": 0.6730870355624333,
|
| 1483 |
+
"grad_norm": 0.046142578125,
|
| 1484 |
+
"learning_rate": 5.8217926422055126e-05,
|
| 1485 |
+
"loss": 1.3364,
|
| 1486 |
+
"step": 1050
|
| 1487 |
+
},
|
| 1488 |
+
{
|
| 1489 |
+
"epoch": 0.6762922119222544,
|
| 1490 |
+
"grad_norm": 0.054443359375,
|
| 1491 |
+
"learning_rate": 5.7203378322671355e-05,
|
| 1492 |
+
"loss": 1.3152,
|
| 1493 |
+
"step": 1055
|
| 1494 |
+
},
|
| 1495 |
+
{
|
| 1496 |
+
"epoch": 0.6794973882820755,
|
| 1497 |
+
"grad_norm": 0.0546875,
|
| 1498 |
+
"learning_rate": 5.619419472468823e-05,
|
| 1499 |
+
"loss": 1.3486,
|
| 1500 |
+
"step": 1060
|
| 1501 |
+
},
|
| 1502 |
+
{
|
| 1503 |
+
"epoch": 0.6827025646418967,
|
| 1504 |
+
"grad_norm": 0.05029296875,
|
| 1505 |
+
"learning_rate": 5.519050212796986e-05,
|
| 1506 |
+
"loss": 1.3301,
|
| 1507 |
+
"step": 1065
|
| 1508 |
+
},
|
| 1509 |
+
{
|
| 1510 |
+
"epoch": 0.6859077410017178,
|
| 1511 |
+
"grad_norm": 0.051513671875,
|
| 1512 |
+
"learning_rate": 5.419242634409039e-05,
|
| 1513 |
+
"loss": 1.3279,
|
| 1514 |
+
"step": 1070
|
| 1515 |
+
},
|
| 1516 |
+
{
|
| 1517 |
+
"epoch": 0.6891129173615389,
|
| 1518 |
+
"grad_norm": 0.0478515625,
|
| 1519 |
+
"learning_rate": 5.32000924805637e-05,
|
| 1520 |
+
"loss": 1.3415,
|
| 1521 |
+
"step": 1075
|
| 1522 |
+
},
|
| 1523 |
+
{
|
| 1524 |
+
"epoch": 0.69231809372136,
|
| 1525 |
+
"grad_norm": 0.04638671875,
|
| 1526 |
+
"learning_rate": 5.2213624925161386e-05,
|
| 1527 |
+
"loss": 1.3449,
|
| 1528 |
+
"step": 1080
|
| 1529 |
+
},
|
| 1530 |
+
{
|
| 1531 |
+
"epoch": 0.6955232700811811,
|
| 1532 |
+
"grad_norm": 0.04541015625,
|
| 1533 |
+
"learning_rate": 5.123314733032074e-05,
|
| 1534 |
+
"loss": 1.3442,
|
| 1535 |
+
"step": 1085
|
| 1536 |
+
},
|
| 1537 |
+
{
|
| 1538 |
+
"epoch": 0.6987284464410022,
|
| 1539 |
+
"grad_norm": 0.04736328125,
|
| 1540 |
+
"learning_rate": 5.0258782597645446e-05,
|
| 1541 |
+
"loss": 1.3309,
|
| 1542 |
+
"step": 1090
|
| 1543 |
+
},
|
| 1544 |
+
{
|
| 1545 |
+
"epoch": 0.7019336228008233,
|
| 1546 |
+
"grad_norm": 0.0478515625,
|
| 1547 |
+
"learning_rate": 4.929065286249959e-05,
|
| 1548 |
+
"loss": 1.3564,
|
| 1549 |
+
"step": 1095
|
| 1550 |
+
},
|
| 1551 |
+
{
|
| 1552 |
+
"epoch": 0.7051387991606445,
|
| 1553 |
+
"grad_norm": 0.048095703125,
|
| 1554 |
+
"learning_rate": 4.832887947869841e-05,
|
| 1555 |
+
"loss": 1.3578,
|
| 1556 |
+
"step": 1100
|
| 1557 |
+
},
|
| 1558 |
+
{
|
| 1559 |
+
"epoch": 0.7083439755204656,
|
| 1560 |
+
"grad_norm": 0.047119140625,
|
| 1561 |
+
"learning_rate": 4.737358300329673e-05,
|
| 1562 |
+
"loss": 1.3417,
|
| 1563 |
+
"step": 1105
|
| 1564 |
+
},
|
| 1565 |
+
{
|
| 1566 |
+
"epoch": 0.7115491518802867,
|
| 1567 |
+
"grad_norm": 0.05029296875,
|
| 1568 |
+
"learning_rate": 4.642488318147723e-05,
|
| 1569 |
+
"loss": 1.3259,
|
| 1570 |
+
"step": 1110
|
| 1571 |
+
},
|
| 1572 |
+
{
|
| 1573 |
+
"epoch": 0.7147543282401078,
|
| 1574 |
+
"grad_norm": 0.052001953125,
|
| 1575 |
+
"learning_rate": 4.548289893154051e-05,
|
| 1576 |
+
"loss": 1.3568,
|
| 1577 |
+
"step": 1115
|
| 1578 |
+
},
|
| 1579 |
+
{
|
| 1580 |
+
"epoch": 0.7179595045999289,
|
| 1581 |
+
"grad_norm": 0.047607421875,
|
| 1582 |
+
"learning_rate": 4.4547748329998925e-05,
|
| 1583 |
+
"loss": 1.3211,
|
| 1584 |
+
"step": 1120
|
| 1585 |
+
},
|
| 1586 |
+
{
|
| 1587 |
+
"epoch": 0.72116468095975,
|
| 1588 |
+
"grad_norm": 0.05126953125,
|
| 1589 |
+
"learning_rate": 4.361954859677584e-05,
|
| 1590 |
+
"loss": 1.3398,
|
| 1591 |
+
"step": 1125
|
| 1592 |
+
},
|
| 1593 |
+
{
|
| 1594 |
+
"epoch": 0.7243698573195712,
|
| 1595 |
+
"grad_norm": 0.048095703125,
|
| 1596 |
+
"learning_rate": 4.2698416080512204e-05,
|
| 1597 |
+
"loss": 1.3266,
|
| 1598 |
+
"step": 1130
|
| 1599 |
+
},
|
| 1600 |
+
{
|
| 1601 |
+
"epoch": 0.7275750336793922,
|
| 1602 |
+
"grad_norm": 0.050048828125,
|
| 1603 |
+
"learning_rate": 4.1784466243982324e-05,
|
| 1604 |
+
"loss": 1.3447,
|
| 1605 |
+
"step": 1135
|
| 1606 |
+
},
|
| 1607 |
+
{
|
| 1608 |
+
"epoch": 0.7307802100392133,
|
| 1609 |
+
"grad_norm": 0.052001953125,
|
| 1610 |
+
"learning_rate": 4.0877813649621076e-05,
|
| 1611 |
+
"loss": 1.3385,
|
| 1612 |
+
"step": 1140
|
| 1613 |
+
},
|
| 1614 |
+
{
|
| 1615 |
+
"epoch": 0.7339853863990344,
|
| 1616 |
+
"grad_norm": 0.04638671875,
|
| 1617 |
+
"learning_rate": 3.997857194516319e-05,
|
| 1618 |
+
"loss": 1.3403,
|
| 1619 |
+
"step": 1145
|
| 1620 |
+
},
|
| 1621 |
+
{
|
| 1622 |
+
"epoch": 0.7371905627588555,
|
| 1623 |
+
"grad_norm": 0.05078125,
|
| 1624 |
+
"learning_rate": 3.9086853849398065e-05,
|
| 1625 |
+
"loss": 1.3503,
|
| 1626 |
+
"step": 1150
|
| 1627 |
+
},
|
| 1628 |
+
{
|
| 1629 |
+
"epoch": 0.7403957391186766,
|
| 1630 |
+
"grad_norm": 0.06396484375,
|
| 1631 |
+
"learning_rate": 3.8202771138040336e-05,
|
| 1632 |
+
"loss": 1.3354,
|
| 1633 |
+
"step": 1155
|
| 1634 |
+
},
|
| 1635 |
+
{
|
| 1636 |
+
"epoch": 0.7436009154784978,
|
| 1637 |
+
"grad_norm": 0.05078125,
|
| 1638 |
+
"learning_rate": 3.732643462971912e-05,
|
| 1639 |
+
"loss": 1.3258,
|
| 1640 |
+
"step": 1160
|
| 1641 |
+
},
|
| 1642 |
+
{
|
| 1643 |
+
"epoch": 0.7468060918383189,
|
| 1644 |
+
"grad_norm": 0.049560546875,
|
| 1645 |
+
"learning_rate": 3.6457954172086896e-05,
|
| 1646 |
+
"loss": 1.3493,
|
| 1647 |
+
"step": 1165
|
| 1648 |
+
},
|
| 1649 |
+
{
|
| 1650 |
+
"epoch": 0.75001126819814,
|
| 1651 |
+
"grad_norm": 0.046875,
|
| 1652 |
+
"learning_rate": 3.559743862805034e-05,
|
| 1653 |
+
"loss": 1.3275,
|
| 1654 |
+
"step": 1170
|
| 1655 |
+
},
|
| 1656 |
+
{
|
| 1657 |
+
"epoch": 0.7532164445579611,
|
| 1658 |
+
"grad_norm": 0.045654296875,
|
| 1659 |
+
"learning_rate": 3.47449958621245e-05,
|
| 1660 |
+
"loss": 1.3148,
|
| 1661 |
+
"step": 1175
|
| 1662 |
+
},
|
| 1663 |
+
{
|
| 1664 |
+
"epoch": 0.7564216209177822,
|
| 1665 |
+
"grad_norm": 0.051513671875,
|
| 1666 |
+
"learning_rate": 3.390073272691198e-05,
|
| 1667 |
+
"loss": 1.3338,
|
| 1668 |
+
"step": 1180
|
| 1669 |
+
},
|
| 1670 |
+
{
|
| 1671 |
+
"epoch": 0.7596267972776033,
|
| 1672 |
+
"grad_norm": 0.049072265625,
|
| 1673 |
+
"learning_rate": 3.306475504970931e-05,
|
| 1674 |
+
"loss": 1.2935,
|
| 1675 |
+
"step": 1185
|
| 1676 |
+
},
|
| 1677 |
+
{
|
| 1678 |
+
"epoch": 0.7628319736374244,
|
| 1679 |
+
"grad_norm": 0.04833984375,
|
| 1680 |
+
"learning_rate": 3.2237167619241495e-05,
|
| 1681 |
+
"loss": 1.3275,
|
| 1682 |
+
"step": 1190
|
| 1683 |
+
},
|
| 1684 |
+
{
|
| 1685 |
+
"epoch": 0.7660371499972456,
|
| 1686 |
+
"grad_norm": 0.056396484375,
|
| 1687 |
+
"learning_rate": 3.141807417252697e-05,
|
| 1688 |
+
"loss": 1.3461,
|
| 1689 |
+
"step": 1195
|
| 1690 |
+
},
|
| 1691 |
+
{
|
| 1692 |
+
"epoch": 0.7692423263570667,
|
| 1693 |
+
"grad_norm": 0.04345703125,
|
| 1694 |
+
"learning_rate": 3.060757738187409e-05,
|
| 1695 |
+
"loss": 1.3394,
|
| 1696 |
+
"step": 1200
|
| 1697 |
+
},
|
| 1698 |
+
{
|
| 1699 |
+
"epoch": 0.7724475027168878,
|
| 1700 |
+
"grad_norm": 0.053955078125,
|
| 1701 |
+
"learning_rate": 2.980577884201169e-05,
|
| 1702 |
+
"loss": 1.3511,
|
| 1703 |
+
"step": 1205
|
| 1704 |
+
},
|
| 1705 |
+
{
|
| 1706 |
+
"epoch": 0.7756526790767089,
|
| 1707 |
+
"grad_norm": 0.04736328125,
|
| 1708 |
+
"learning_rate": 2.9012779057353855e-05,
|
| 1709 |
+
"loss": 1.3213,
|
| 1710 |
+
"step": 1210
|
| 1711 |
+
},
|
| 1712 |
+
{
|
| 1713 |
+
"epoch": 0.77885785543653,
|
| 1714 |
+
"grad_norm": 0.0576171875,
|
| 1715 |
+
"learning_rate": 2.822867742940214e-05,
|
| 1716 |
+
"loss": 1.3384,
|
| 1717 |
+
"step": 1215
|
| 1718 |
+
},
|
| 1719 |
+
{
|
| 1720 |
+
"epoch": 0.7820630317963511,
|
| 1721 |
+
"grad_norm": 0.04833984375,
|
| 1722 |
+
"learning_rate": 2.745357224428563e-05,
|
| 1723 |
+
"loss": 1.343,
|
| 1724 |
+
"step": 1220
|
| 1725 |
+
},
|
| 1726 |
+
{
|
| 1727 |
+
"epoch": 0.7852682081561723,
|
| 1728 |
+
"grad_norm": 0.049560546875,
|
| 1729 |
+
"learning_rate": 2.6687560660440858e-05,
|
| 1730 |
+
"loss": 1.3541,
|
| 1731 |
+
"step": 1225
|
| 1732 |
+
},
|
| 1733 |
+
{
|
| 1734 |
+
"epoch": 0.7884733845159934,
|
| 1735 |
+
"grad_norm": 0.047607421875,
|
| 1736 |
+
"learning_rate": 2.593073869643312e-05,
|
| 1737 |
+
"loss": 1.3491,
|
| 1738 |
+
"step": 1230
|
| 1739 |
+
},
|
| 1740 |
+
{
|
| 1741 |
+
"epoch": 0.7916785608758145,
|
| 1742 |
+
"grad_norm": 0.04248046875,
|
| 1743 |
+
"learning_rate": 2.518320121892076e-05,
|
| 1744 |
+
"loss": 1.3439,
|
| 1745 |
+
"step": 1235
|
| 1746 |
+
},
|
| 1747 |
+
{
|
| 1748 |
+
"epoch": 0.7948837372356355,
|
| 1749 |
+
"grad_norm": 0.04736328125,
|
| 1750 |
+
"learning_rate": 2.4445041930763678e-05,
|
| 1751 |
+
"loss": 1.3236,
|
| 1752 |
+
"step": 1240
|
| 1753 |
+
},
|
| 1754 |
+
{
|
| 1755 |
+
"epoch": 0.7980889135954566,
|
| 1756 |
+
"grad_norm": 0.0478515625,
|
| 1757 |
+
"learning_rate": 2.371635335927781e-05,
|
| 1758 |
+
"loss": 1.3505,
|
| 1759 |
+
"step": 1245
|
| 1760 |
+
},
|
| 1761 |
+
{
|
| 1762 |
+
"epoch": 0.8012940899552777,
|
| 1763 |
+
"grad_norm": 0.0517578125,
|
| 1764 |
+
"learning_rate": 2.2997226844636977e-05,
|
| 1765 |
+
"loss": 1.3223,
|
| 1766 |
+
"step": 1250
|
| 1767 |
+
},
|
| 1768 |
+
{
|
| 1769 |
+
"epoch": 0.8044992663150989,
|
| 1770 |
+
"grad_norm": 0.046630859375,
|
| 1771 |
+
"learning_rate": 2.2287752528423468e-05,
|
| 1772 |
+
"loss": 1.3282,
|
| 1773 |
+
"step": 1255
|
| 1774 |
+
},
|
| 1775 |
+
{
|
| 1776 |
+
"epoch": 0.80770444267492,
|
| 1777 |
+
"grad_norm": 0.046875,
|
| 1778 |
+
"learning_rate": 2.1588019342328968e-05,
|
| 1779 |
+
"loss": 1.3294,
|
| 1780 |
+
"step": 1260
|
| 1781 |
+
},
|
| 1782 |
+
{
|
| 1783 |
+
"epoch": 0.8109096190347411,
|
| 1784 |
+
"grad_norm": 0.0439453125,
|
| 1785 |
+
"learning_rate": 2.089811499700699e-05,
|
| 1786 |
+
"loss": 1.3356,
|
| 1787 |
+
"step": 1265
|
| 1788 |
+
},
|
| 1789 |
+
{
|
| 1790 |
+
"epoch": 0.8141147953945622,
|
| 1791 |
+
"grad_norm": 0.045654296875,
|
| 1792 |
+
"learning_rate": 2.021812597107855e-05,
|
| 1793 |
+
"loss": 1.3486,
|
| 1794 |
+
"step": 1270
|
| 1795 |
+
},
|
| 1796 |
+
{
|
| 1797 |
+
"epoch": 0.8173199717543833,
|
| 1798 |
+
"grad_norm": 0.04931640625,
|
| 1799 |
+
"learning_rate": 1.954813750029216e-05,
|
| 1800 |
+
"loss": 1.3492,
|
| 1801 |
+
"step": 1275
|
| 1802 |
+
},
|
| 1803 |
+
{
|
| 1804 |
+
"epoch": 0.8205251481142044,
|
| 1805 |
+
"grad_norm": 0.05126953125,
|
| 1806 |
+
"learning_rate": 1.8888233566839653e-05,
|
| 1807 |
+
"loss": 1.329,
|
| 1808 |
+
"step": 1280
|
| 1809 |
+
},
|
| 1810 |
+
{
|
| 1811 |
+
"epoch": 0.8237303244740255,
|
| 1812 |
+
"grad_norm": 0.048095703125,
|
| 1813 |
+
"learning_rate": 1.8238496888828982e-05,
|
| 1814 |
+
"loss": 1.317,
|
| 1815 |
+
"step": 1285
|
| 1816 |
+
},
|
| 1817 |
+
{
|
| 1818 |
+
"epoch": 0.8269355008338467,
|
| 1819 |
+
"grad_norm": 0.051513671875,
|
| 1820 |
+
"learning_rate": 1.759900890991589e-05,
|
| 1821 |
+
"loss": 1.3177,
|
| 1822 |
+
"step": 1290
|
| 1823 |
+
},
|
| 1824 |
+
{
|
| 1825 |
+
"epoch": 0.8301406771936678,
|
| 1826 |
+
"grad_norm": 0.0458984375,
|
| 1827 |
+
"learning_rate": 1.696984978909476e-05,
|
| 1828 |
+
"loss": 1.323,
|
| 1829 |
+
"step": 1295
|
| 1830 |
+
},
|
| 1831 |
+
{
|
| 1832 |
+
"epoch": 0.8333458535534889,
|
| 1833 |
+
"grad_norm": 0.0439453125,
|
| 1834 |
+
"learning_rate": 1.6351098390650966e-05,
|
| 1835 |
+
"loss": 1.3517,
|
| 1836 |
+
"step": 1300
|
| 1837 |
+
},
|
| 1838 |
+
{
|
| 1839 |
+
"epoch": 0.83655102991331,
|
| 1840 |
+
"grad_norm": 0.052978515625,
|
| 1841 |
+
"learning_rate": 1.5742832274275288e-05,
|
| 1842 |
+
"loss": 1.35,
|
| 1843 |
+
"step": 1305
|
| 1844 |
+
},
|
| 1845 |
+
{
|
| 1846 |
+
"epoch": 0.8397562062731311,
|
| 1847 |
+
"grad_norm": 0.049072265625,
|
| 1848 |
+
"learning_rate": 1.514512768534193e-05,
|
| 1849 |
+
"loss": 1.3614,
|
| 1850 |
+
"step": 1310
|
| 1851 |
+
},
|
| 1852 |
+
{
|
| 1853 |
+
"epoch": 0.8429613826329522,
|
| 1854 |
+
"grad_norm": 0.0439453125,
|
| 1855 |
+
"learning_rate": 1.4558059545351143e-05,
|
| 1856 |
+
"loss": 1.3389,
|
| 1857 |
+
"step": 1315
|
| 1858 |
+
},
|
| 1859 |
+
{
|
| 1860 |
+
"epoch": 0.8461665589927734,
|
| 1861 |
+
"grad_norm": 0.04541015625,
|
| 1862 |
+
"learning_rate": 1.3981701442538153e-05,
|
| 1863 |
+
"loss": 1.3272,
|
| 1864 |
+
"step": 1320
|
| 1865 |
+
},
|
| 1866 |
+
{
|
| 1867 |
+
"epoch": 0.8493717353525945,
|
| 1868 |
+
"grad_norm": 0.048583984375,
|
| 1869 |
+
"learning_rate": 1.3416125622648668e-05,
|
| 1870 |
+
"loss": 1.3324,
|
| 1871 |
+
"step": 1325
|
| 1872 |
+
},
|
| 1873 |
+
{
|
| 1874 |
+
"epoch": 0.8525769117124156,
|
| 1875 |
+
"grad_norm": 0.04541015625,
|
| 1876 |
+
"learning_rate": 1.286140297988323e-05,
|
| 1877 |
+
"loss": 1.3352,
|
| 1878 |
+
"step": 1330
|
| 1879 |
+
},
|
| 1880 |
+
{
|
| 1881 |
+
"epoch": 0.8557820880722367,
|
| 1882 |
+
"grad_norm": 0.04443359375,
|
| 1883 |
+
"learning_rate": 1.231760304801054e-05,
|
| 1884 |
+
"loss": 1.3361,
|
| 1885 |
+
"step": 1335
|
| 1886 |
+
},
|
| 1887 |
+
{
|
| 1888 |
+
"epoch": 0.8589872644320578,
|
| 1889 |
+
"grad_norm": 0.047119140625,
|
| 1890 |
+
"learning_rate": 1.1784793991651621e-05,
|
| 1891 |
+
"loss": 1.3252,
|
| 1892 |
+
"step": 1340
|
| 1893 |
+
},
|
| 1894 |
+
{
|
| 1895 |
+
"epoch": 0.8621924407918788,
|
| 1896 |
+
"grad_norm": 0.044189453125,
|
| 1897 |
+
"learning_rate": 1.1263042597735362e-05,
|
| 1898 |
+
"loss": 1.3468,
|
| 1899 |
+
"step": 1345
|
| 1900 |
+
},
|
| 1901 |
+
{
|
| 1902 |
+
"epoch": 0.8653976171517,
|
| 1903 |
+
"grad_norm": 0.046630859375,
|
| 1904 |
+
"learning_rate": 1.0752414267126875e-05,
|
| 1905 |
+
"loss": 1.3301,
|
| 1906 |
+
"step": 1350
|
| 1907 |
+
},
|
| 1908 |
+
{
|
| 1909 |
+
"epoch": 0.8686027935115211,
|
| 1910 |
+
"grad_norm": 0.05029296875,
|
| 1911 |
+
"learning_rate": 1.0252973006429733e-05,
|
| 1912 |
+
"loss": 1.36,
|
| 1913 |
+
"step": 1355
|
| 1914 |
+
},
|
| 1915 |
+
{
|
| 1916 |
+
"epoch": 0.8718079698713422,
|
| 1917 |
+
"grad_norm": 0.047119140625,
|
| 1918 |
+
"learning_rate": 9.764781419962577e-06,
|
| 1919 |
+
"loss": 1.3482,
|
| 1920 |
+
"step": 1360
|
| 1921 |
+
},
|
| 1922 |
+
{
|
| 1923 |
+
"epoch": 0.8750131462311633,
|
| 1924 |
+
"grad_norm": 0.04638671875,
|
| 1925 |
+
"learning_rate": 9.287900701911944e-06,
|
| 1926 |
+
"loss": 1.3232,
|
| 1927 |
+
"step": 1365
|
| 1928 |
+
},
|
| 1929 |
+
{
|
| 1930 |
+
"epoch": 0.8782183225909844,
|
| 1931 |
+
"grad_norm": 0.04931640625,
|
| 1932 |
+
"learning_rate": 8.822390628661582e-06,
|
| 1933 |
+
"loss": 1.3571,
|
| 1934 |
+
"step": 1370
|
| 1935 |
+
},
|
| 1936 |
+
{
|
| 1937 |
+
"epoch": 0.8814234989508055,
|
| 1938 |
+
"grad_norm": 0.044921875,
|
| 1939 |
+
"learning_rate": 8.368309551299536e-06,
|
| 1940 |
+
"loss": 1.3274,
|
| 1941 |
+
"step": 1375
|
| 1942 |
+
},
|
| 1943 |
+
{
|
| 1944 |
+
"epoch": 0.8846286753106266,
|
| 1945 |
+
"grad_norm": 0.04541015625,
|
| 1946 |
+
"learning_rate": 7.92571438830394e-06,
|
| 1947 |
+
"loss": 1.3656,
|
| 1948 |
+
"step": 1380
|
| 1949 |
+
},
|
| 1950 |
+
{
|
| 1951 |
+
"epoch": 0.8878338516704478,
|
| 1952 |
+
"grad_norm": 0.046142578125,
|
| 1953 |
+
"learning_rate": 7.494660618408378e-06,
|
| 1954 |
+
"loss": 1.3659,
|
| 1955 |
+
"step": 1385
|
| 1956 |
+
},
|
| 1957 |
+
{
|
| 1958 |
+
"epoch": 0.8910390280302689,
|
| 1959 |
+
"grad_norm": 0.04541015625,
|
| 1960 |
+
"learning_rate": 7.075202273647652e-06,
|
| 1961 |
+
"loss": 1.3305,
|
| 1962 |
+
"step": 1390
|
| 1963 |
+
},
|
| 1964 |
+
{
|
| 1965 |
+
"epoch": 0.89424420439009,
|
| 1966 |
+
"grad_norm": 0.046875,
|
| 1967 |
+
"learning_rate": 6.667391932584999e-06,
|
| 1968 |
+
"loss": 1.36,
|
| 1969 |
+
"step": 1395
|
| 1970 |
+
},
|
| 1971 |
+
{
|
| 1972 |
+
"epoch": 0.8974493807499111,
|
| 1973 |
+
"grad_norm": 0.0458984375,
|
| 1974 |
+
"learning_rate": 6.271280713721317e-06,
|
| 1975 |
+
"loss": 1.3382,
|
| 1976 |
+
"step": 1400
|
| 1977 |
+
},
|
| 1978 |
+
{
|
| 1979 |
+
"epoch": 0.9006545571097322,
|
| 1980 |
+
"grad_norm": 0.04638671875,
|
| 1981 |
+
"learning_rate": 5.886918269087716e-06,
|
| 1982 |
+
"loss": 1.326,
|
| 1983 |
+
"step": 1405
|
| 1984 |
+
},
|
| 1985 |
+
{
|
| 1986 |
+
"epoch": 0.9038597334695533,
|
| 1987 |
+
"grad_norm": 0.046875,
|
| 1988 |
+
"learning_rate": 5.514352778021492e-06,
|
| 1989 |
+
"loss": 1.3602,
|
| 1990 |
+
"step": 1410
|
| 1991 |
+
},
|
| 1992 |
+
{
|
| 1993 |
+
"epoch": 0.9070649098293745,
|
| 1994 |
+
"grad_norm": 0.046142578125,
|
| 1995 |
+
"learning_rate": 5.153630941127063e-06,
|
| 1996 |
+
"loss": 1.3407,
|
| 1997 |
+
"step": 1415
|
| 1998 |
+
},
|
| 1999 |
+
{
|
| 2000 |
+
"epoch": 0.9102700861891956,
|
| 2001 |
+
"grad_norm": 0.046875,
|
| 2002 |
+
"learning_rate": 4.804797974422026e-06,
|
| 2003 |
+
"loss": 1.3241,
|
| 2004 |
+
"step": 1420
|
| 2005 |
+
},
|
| 2006 |
+
{
|
| 2007 |
+
"epoch": 0.9134752625490167,
|
| 2008 |
+
"grad_norm": 0.050537109375,
|
| 2009 |
+
"learning_rate": 4.4678976036694355e-06,
|
| 2010 |
+
"loss": 1.3324,
|
| 2011 |
+
"step": 1425
|
| 2012 |
+
},
|
| 2013 |
+
{
|
| 2014 |
+
"epoch": 0.9166804389088378,
|
| 2015 |
+
"grad_norm": 0.04443359375,
|
| 2016 |
+
"learning_rate": 4.142972058896811e-06,
|
| 2017 |
+
"loss": 1.3267,
|
| 2018 |
+
"step": 1430
|
| 2019 |
+
},
|
| 2020 |
+
{
|
| 2021 |
+
"epoch": 0.9198856152686589,
|
| 2022 |
+
"grad_norm": 0.044921875,
|
| 2023 |
+
"learning_rate": 3.830062069102602e-06,
|
| 2024 |
+
"loss": 1.3496,
|
| 2025 |
+
"step": 1435
|
| 2026 |
+
},
|
| 2027 |
+
{
|
| 2028 |
+
"epoch": 0.92309079162848,
|
| 2029 |
+
"grad_norm": 0.046630859375,
|
| 2030 |
+
"learning_rate": 3.529206857151035e-06,
|
| 2031 |
+
"loss": 1.3481,
|
| 2032 |
+
"step": 1440
|
| 2033 |
+
},
|
| 2034 |
+
{
|
| 2035 |
+
"epoch": 0.9262959679883012,
|
| 2036 |
+
"grad_norm": 0.04345703125,
|
| 2037 |
+
"learning_rate": 3.240444134855347e-06,
|
| 2038 |
+
"loss": 1.3433,
|
| 2039 |
+
"step": 1445
|
| 2040 |
+
},
|
| 2041 |
+
{
|
| 2042 |
+
"epoch": 0.9295011443481223,
|
| 2043 |
+
"grad_norm": 0.045654296875,
|
| 2044 |
+
"learning_rate": 2.963810098250841e-06,
|
| 2045 |
+
"loss": 1.3555,
|
| 2046 |
+
"step": 1450
|
| 2047 |
+
},
|
| 2048 |
+
{
|
| 2049 |
+
"epoch": 0.9327063207079433,
|
| 2050 |
+
"grad_norm": 0.044921875,
|
| 2051 |
+
"learning_rate": 2.6993394230576674e-06,
|
| 2052 |
+
"loss": 1.3218,
|
| 2053 |
+
"step": 1455
|
| 2054 |
+
},
|
| 2055 |
+
{
|
| 2056 |
+
"epoch": 0.9359114970677644,
|
| 2057 |
+
"grad_norm": 0.04638671875,
|
| 2058 |
+
"learning_rate": 2.4470652603343023e-06,
|
| 2059 |
+
"loss": 1.346,
|
| 2060 |
+
"step": 1460
|
| 2061 |
+
},
|
| 2062 |
+
{
|
| 2063 |
+
"epoch": 0.9391166734275855,
|
| 2064 |
+
"grad_norm": 0.044677734375,
|
| 2065 |
+
"learning_rate": 2.2070192323220607e-06,
|
| 2066 |
+
"loss": 1.3551,
|
| 2067 |
+
"step": 1465
|
| 2068 |
+
},
|
| 2069 |
+
{
|
| 2070 |
+
"epoch": 0.9423218497874066,
|
| 2071 |
+
"grad_norm": 0.0439453125,
|
| 2072 |
+
"learning_rate": 1.9792314284813986e-06,
|
| 2073 |
+
"loss": 1.3262,
|
| 2074 |
+
"step": 1470
|
| 2075 |
+
},
|
| 2076 |
+
{
|
| 2077 |
+
"epoch": 0.9455270261472277,
|
| 2078 |
+
"grad_norm": 0.04736328125,
|
| 2079 |
+
"learning_rate": 1.763730401720065e-06,
|
| 2080 |
+
"loss": 1.3257,
|
| 2081 |
+
"step": 1475
|
| 2082 |
+
},
|
| 2083 |
+
{
|
| 2084 |
+
"epoch": 0.9487322025070489,
|
| 2085 |
+
"grad_norm": 0.046142578125,
|
| 2086 |
+
"learning_rate": 1.5605431648141878e-06,
|
| 2087 |
+
"loss": 1.3158,
|
| 2088 |
+
"step": 1480
|
| 2089 |
+
},
|
| 2090 |
+
{
|
| 2091 |
+
"epoch": 0.95193737886687,
|
| 2092 |
+
"grad_norm": 0.044677734375,
|
| 2093 |
+
"learning_rate": 1.3696951870222018e-06,
|
| 2094 |
+
"loss": 1.3637,
|
| 2095 |
+
"step": 1485
|
| 2096 |
+
},
|
| 2097 |
+
{
|
| 2098 |
+
"epoch": 0.9551425552266911,
|
| 2099 |
+
"grad_norm": 0.053466796875,
|
| 2100 |
+
"learning_rate": 1.1912103908922945e-06,
|
| 2101 |
+
"loss": 1.3337,
|
| 2102 |
+
"step": 1490
|
| 2103 |
+
},
|
| 2104 |
+
{
|
| 2105 |
+
"epoch": 0.9583477315865122,
|
| 2106 |
+
"grad_norm": 0.050048828125,
|
| 2107 |
+
"learning_rate": 1.0251111492637244e-06,
|
| 2108 |
+
"loss": 1.3557,
|
| 2109 |
+
"step": 1495
|
| 2110 |
+
},
|
| 2111 |
+
{
|
| 2112 |
+
"epoch": 0.9615529079463333,
|
| 2113 |
+
"grad_norm": 0.05126953125,
|
| 2114 |
+
"learning_rate": 8.714182824624883e-07,
|
| 2115 |
+
"loss": 1.3373,
|
| 2116 |
+
"step": 1500
|
| 2117 |
+
},
|
| 2118 |
+
{
|
| 2119 |
+
"epoch": 0.9647580843061544,
|
| 2120 |
+
"grad_norm": 0.0458984375,
|
| 2121 |
+
"learning_rate": 7.301510556914859e-07,
|
| 2122 |
+
"loss": 1.3274,
|
| 2123 |
+
"step": 1505
|
| 2124 |
+
},
|
| 2125 |
+
{
|
| 2126 |
+
"epoch": 0.9679632606659756,
|
| 2127 |
+
"grad_norm": 0.05224609375,
|
| 2128 |
+
"learning_rate": 6.01327176615607e-07,
|
| 2129 |
+
"loss": 1.3894,
|
| 2130 |
+
"step": 1510
|
| 2131 |
+
},
|
| 2132 |
+
{
|
| 2133 |
+
"epoch": 0.9711684370257967,
|
| 2134 |
+
"grad_norm": 0.045166015625,
|
| 2135 |
+
"learning_rate": 4.84962793142163e-07,
|
| 2136 |
+
"loss": 1.3419,
|
| 2137 |
+
"step": 1515
|
| 2138 |
+
},
|
| 2139 |
+
{
|
| 2140 |
+
"epoch": 0.9743736133856178,
|
| 2141 |
+
"grad_norm": 0.044677734375,
|
| 2142 |
+
"learning_rate": 3.8107249139672783e-07,
|
| 2143 |
+
"loss": 1.3321,
|
| 2144 |
+
"step": 1520
|
| 2145 |
+
},
|
| 2146 |
+
{
|
| 2147 |
+
"epoch": 0.9775787897454389,
|
| 2148 |
+
"grad_norm": 0.0478515625,
|
| 2149 |
+
"learning_rate": 2.89669293894812e-07,
|
| 2150 |
+
"loss": 1.3497,
|
| 2151 |
+
"step": 1525
|
| 2152 |
+
},
|
| 2153 |
+
{
|
| 2154 |
+
"epoch": 0.98078396610526,
|
| 2155 |
+
"grad_norm": 0.049072265625,
|
| 2156 |
+
"learning_rate": 2.1076465790946798e-07,
|
| 2157 |
+
"loss": 1.3518,
|
| 2158 |
+
"step": 1530
|
| 2159 |
+
},
|
| 2160 |
+
{
|
| 2161 |
+
"epoch": 0.9839891424650811,
|
| 2162 |
+
"grad_norm": 0.04638671875,
|
| 2163 |
+
"learning_rate": 1.443684740351947e-07,
|
| 2164 |
+
"loss": 1.3224,
|
| 2165 |
+
"step": 1535
|
| 2166 |
+
},
|
| 2167 |
+
{
|
| 2168 |
+
"epoch": 0.9871943188249022,
|
| 2169 |
+
"grad_norm": 0.049072265625,
|
| 2170 |
+
"learning_rate": 9.048906494811826e-08,
|
| 2171 |
+
"loss": 1.3513,
|
| 2172 |
+
"step": 1540
|
| 2173 |
+
},
|
| 2174 |
+
{
|
| 2175 |
+
"epoch": 0.9903994951847234,
|
| 2176 |
+
"grad_norm": 0.050048828125,
|
| 2177 |
+
"learning_rate": 4.9133184362748497e-08,
|
| 2178 |
+
"loss": 1.3494,
|
| 2179 |
+
"step": 1545
|
| 2180 |
+
},
|
| 2181 |
+
{
|
| 2182 |
+
"epoch": 0.9936046715445445,
|
| 2183 |
+
"grad_norm": 0.04443359375,
|
| 2184 |
+
"learning_rate": 2.0306016185456244e-08,
|
| 2185 |
+
"loss": 1.3344,
|
| 2186 |
+
"step": 1550
|
| 2187 |
+
},
|
| 2188 |
+
{
|
| 2189 |
+
"epoch": 0.9968098479043656,
|
| 2190 |
+
"grad_norm": 0.047119140625,
|
| 2191 |
+
"learning_rate": 4.011173864637563e-09,
|
| 2192 |
+
"loss": 1.3662,
|
| 2193 |
+
"step": 1555
|
| 2194 |
+
},
|
| 2195 |
+
{
|
| 2196 |
+
"epoch": 0.9993739889922224,
|
| 2197 |
+
"eval_loss": 1.4191993474960327,
|
| 2198 |
+
"eval_runtime": 1938.5869,
|
| 2199 |
+
"eval_samples_per_second": 7.3,
|
| 2200 |
+
"eval_steps_per_second": 7.3,
|
| 2201 |
+
"step": 1559
|
| 2202 |
+
},
|
| 2203 |
+
{
|
| 2204 |
+
"epoch": 0.9993739889922224,
|
| 2205 |
+
"step": 1559,
|
| 2206 |
+
"total_flos": 3.232184148701479e+18,
|
| 2207 |
+
"train_loss": 0.016414370117774753,
|
| 2208 |
+
"train_runtime": 2971.8566,
|
| 2209 |
+
"train_samples_per_second": 67.189,
|
| 2210 |
+
"train_steps_per_second": 0.525
|
| 2211 |
+
}
|
| 2212 |
+
],
|
| 2213 |
+
"logging_steps": 5,
|
| 2214 |
+
"max_steps": 1559,
|
| 2215 |
+
"num_input_tokens_seen": 0,
|
| 2216 |
+
"num_train_epochs": 1,
|
| 2217 |
+
"save_steps": 20,
|
| 2218 |
+
"total_flos": 3.232184148701479e+18,
|
| 2219 |
+
"train_batch_size": 1,
|
| 2220 |
+
"trial_name": null,
|
| 2221 |
+
"trial_params": null
|
| 2222 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e9368167a7c8c2e5afaeb29db0e275336ff5bb5ad11c57c441e568b0c63b3082
|
| 3 |
+
size 5112
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|