Upload 12 files
Browse files- README.md +52 -3
- adapter_config.json +31 -0
- adapter_model.safetensors +3 -0
- all_results.json +14 -0
- config.json +28 -0
- eval_results.json +8 -0
- special_tokens_map.json +16 -0
- tokenizer.json +0 -0
- tokenizer_config.json +239 -0
- train_results.json +9 -0
- trainer_state.json +2173 -0
- training_args.bin +3 -0
README.md
CHANGED
|
@@ -1,3 +1,52 @@
|
|
| 1 |
-
---
|
| 2 |
-
license: apache-2.0
|
| 3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
library_name: peft
|
| 4 |
+
tags:
|
| 5 |
+
- alignment-handbook
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
base_model: allenai/OLMo-1B-hf
|
| 8 |
+
datasets:
|
| 9 |
+
- Ritvik19/open-hermes-2_5-reformatted
|
| 10 |
+
model-index:
|
| 11 |
+
- name: openhermes-1b-olmo-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-1b-olmo-sft-qlora
|
| 19 |
+
|
| 20 |
+
This model is a fine-tuned version of [allenai/OLMo-1B-hf](https://huggingface.co/allenai/OLMo-1B-hf) on the Ritvik19/open-hermes-2_5-reformatted dataset.
|
| 21 |
+
It achieves the following results on the evaluation set:
|
| 22 |
+
- Loss: 1.4363
|
| 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 |
+
| 1.2568 | 0.9996 | 1523 | 1.4363 |
|
| 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": "allenai/OLMo-1B-hf",
|
| 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 |
+
"q_proj",
|
| 24 |
+
"gate_proj",
|
| 25 |
+
"up_proj",
|
| 26 |
+
"k_proj",
|
| 27 |
+
"o_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:df9b81dcb130a8eecb29e364cb32138d5a4b1fbd4318afa321b40512f5bb0649
|
| 3 |
+
size 24147064
|
all_results.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 0.9995795432403884,
|
| 3 |
+
"eval_loss": 1.4362765550613403,
|
| 4 |
+
"eval_runtime": 1194.1268,
|
| 5 |
+
"eval_samples": 23109,
|
| 6 |
+
"eval_samples_per_second": 11.873,
|
| 7 |
+
"eval_steps_per_second": 11.873,
|
| 8 |
+
"total_flos": 2.6010044317889987e+18,
|
| 9 |
+
"train_loss": 1.1185581020360233,
|
| 10 |
+
"train_runtime": 52635.226,
|
| 11 |
+
"train_samples": 1001538,
|
| 12 |
+
"train_samples_per_second": 3.705,
|
| 13 |
+
"train_steps_per_second": 0.029
|
| 14 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "allenai/OLMo-1B-hf",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"OlmoForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_bias": false,
|
| 7 |
+
"attention_dropout": 0.0,
|
| 8 |
+
"clip_qkv": null,
|
| 9 |
+
"eos_token_id": 50279,
|
| 10 |
+
"hidden_act": "silu",
|
| 11 |
+
"hidden_size": 2048,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 8192,
|
| 14 |
+
"max_position_embeddings": 2048,
|
| 15 |
+
"model_type": "olmo",
|
| 16 |
+
"num_attention_heads": 16,
|
| 17 |
+
"num_hidden_layers": 16,
|
| 18 |
+
"num_key_value_heads": 16,
|
| 19 |
+
"pad_token_id": 1,
|
| 20 |
+
"pretraining_tp": 1,
|
| 21 |
+
"rope_scaling": null,
|
| 22 |
+
"rope_theta": 10000.0,
|
| 23 |
+
"tie_word_embeddings": true,
|
| 24 |
+
"torch_dtype": "bfloat16",
|
| 25 |
+
"transformers_version": "4.40.1",
|
| 26 |
+
"use_cache": true,
|
| 27 |
+
"vocab_size": 50304
|
| 28 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 0.9995795432403884,
|
| 3 |
+
"eval_loss": 1.4362765550613403,
|
| 4 |
+
"eval_runtime": 1194.1268,
|
| 5 |
+
"eval_samples": 23109,
|
| 6 |
+
"eval_samples_per_second": 11.873,
|
| 7 |
+
"eval_steps_per_second": 11.873
|
| 8 |
+
}
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"eos_token": {
|
| 3 |
+
"content": "<|endoftext|>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"pad_token": {
|
| 10 |
+
"content": "<|padding|>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
}
|
| 16 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,239 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"add_prefix_space": false,
|
| 5 |
+
"added_tokens_decoder": {
|
| 6 |
+
"0": {
|
| 7 |
+
"content": "|||IP_ADDRESS|||",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": true,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false,
|
| 12 |
+
"special": false
|
| 13 |
+
},
|
| 14 |
+
"1": {
|
| 15 |
+
"content": "<|padding|>",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": false,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false,
|
| 20 |
+
"special": true
|
| 21 |
+
},
|
| 22 |
+
"50254": {
|
| 23 |
+
"content": " ",
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"normalized": true,
|
| 26 |
+
"rstrip": false,
|
| 27 |
+
"single_word": false,
|
| 28 |
+
"special": false
|
| 29 |
+
},
|
| 30 |
+
"50255": {
|
| 31 |
+
"content": " ",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": true,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false,
|
| 36 |
+
"special": false
|
| 37 |
+
},
|
| 38 |
+
"50256": {
|
| 39 |
+
"content": " ",
|
| 40 |
+
"lstrip": false,
|
| 41 |
+
"normalized": true,
|
| 42 |
+
"rstrip": false,
|
| 43 |
+
"single_word": false,
|
| 44 |
+
"special": false
|
| 45 |
+
},
|
| 46 |
+
"50257": {
|
| 47 |
+
"content": " ",
|
| 48 |
+
"lstrip": false,
|
| 49 |
+
"normalized": true,
|
| 50 |
+
"rstrip": false,
|
| 51 |
+
"single_word": false,
|
| 52 |
+
"special": false
|
| 53 |
+
},
|
| 54 |
+
"50258": {
|
| 55 |
+
"content": " ",
|
| 56 |
+
"lstrip": false,
|
| 57 |
+
"normalized": true,
|
| 58 |
+
"rstrip": false,
|
| 59 |
+
"single_word": false,
|
| 60 |
+
"special": false
|
| 61 |
+
},
|
| 62 |
+
"50259": {
|
| 63 |
+
"content": " ",
|
| 64 |
+
"lstrip": false,
|
| 65 |
+
"normalized": true,
|
| 66 |
+
"rstrip": false,
|
| 67 |
+
"single_word": false,
|
| 68 |
+
"special": false
|
| 69 |
+
},
|
| 70 |
+
"50260": {
|
| 71 |
+
"content": " ",
|
| 72 |
+
"lstrip": false,
|
| 73 |
+
"normalized": true,
|
| 74 |
+
"rstrip": false,
|
| 75 |
+
"single_word": false,
|
| 76 |
+
"special": false
|
| 77 |
+
},
|
| 78 |
+
"50261": {
|
| 79 |
+
"content": " ",
|
| 80 |
+
"lstrip": false,
|
| 81 |
+
"normalized": true,
|
| 82 |
+
"rstrip": false,
|
| 83 |
+
"single_word": false,
|
| 84 |
+
"special": false
|
| 85 |
+
},
|
| 86 |
+
"50262": {
|
| 87 |
+
"content": " ",
|
| 88 |
+
"lstrip": false,
|
| 89 |
+
"normalized": true,
|
| 90 |
+
"rstrip": false,
|
| 91 |
+
"single_word": false,
|
| 92 |
+
"special": false
|
| 93 |
+
},
|
| 94 |
+
"50263": {
|
| 95 |
+
"content": " ",
|
| 96 |
+
"lstrip": false,
|
| 97 |
+
"normalized": true,
|
| 98 |
+
"rstrip": false,
|
| 99 |
+
"single_word": false,
|
| 100 |
+
"special": false
|
| 101 |
+
},
|
| 102 |
+
"50264": {
|
| 103 |
+
"content": " ",
|
| 104 |
+
"lstrip": false,
|
| 105 |
+
"normalized": true,
|
| 106 |
+
"rstrip": false,
|
| 107 |
+
"single_word": false,
|
| 108 |
+
"special": false
|
| 109 |
+
},
|
| 110 |
+
"50265": {
|
| 111 |
+
"content": " ",
|
| 112 |
+
"lstrip": false,
|
| 113 |
+
"normalized": true,
|
| 114 |
+
"rstrip": false,
|
| 115 |
+
"single_word": false,
|
| 116 |
+
"special": false
|
| 117 |
+
},
|
| 118 |
+
"50266": {
|
| 119 |
+
"content": " ",
|
| 120 |
+
"lstrip": false,
|
| 121 |
+
"normalized": true,
|
| 122 |
+
"rstrip": false,
|
| 123 |
+
"single_word": false,
|
| 124 |
+
"special": false
|
| 125 |
+
},
|
| 126 |
+
"50267": {
|
| 127 |
+
"content": " ",
|
| 128 |
+
"lstrip": false,
|
| 129 |
+
"normalized": true,
|
| 130 |
+
"rstrip": false,
|
| 131 |
+
"single_word": false,
|
| 132 |
+
"special": false
|
| 133 |
+
},
|
| 134 |
+
"50268": {
|
| 135 |
+
"content": " ",
|
| 136 |
+
"lstrip": false,
|
| 137 |
+
"normalized": true,
|
| 138 |
+
"rstrip": false,
|
| 139 |
+
"single_word": false,
|
| 140 |
+
"special": false
|
| 141 |
+
},
|
| 142 |
+
"50269": {
|
| 143 |
+
"content": " ",
|
| 144 |
+
"lstrip": false,
|
| 145 |
+
"normalized": true,
|
| 146 |
+
"rstrip": false,
|
| 147 |
+
"single_word": false,
|
| 148 |
+
"special": false
|
| 149 |
+
},
|
| 150 |
+
"50270": {
|
| 151 |
+
"content": " ",
|
| 152 |
+
"lstrip": false,
|
| 153 |
+
"normalized": true,
|
| 154 |
+
"rstrip": false,
|
| 155 |
+
"single_word": false,
|
| 156 |
+
"special": false
|
| 157 |
+
},
|
| 158 |
+
"50271": {
|
| 159 |
+
"content": " ",
|
| 160 |
+
"lstrip": false,
|
| 161 |
+
"normalized": true,
|
| 162 |
+
"rstrip": false,
|
| 163 |
+
"single_word": false,
|
| 164 |
+
"special": false
|
| 165 |
+
},
|
| 166 |
+
"50272": {
|
| 167 |
+
"content": " ",
|
| 168 |
+
"lstrip": false,
|
| 169 |
+
"normalized": true,
|
| 170 |
+
"rstrip": false,
|
| 171 |
+
"single_word": false,
|
| 172 |
+
"special": false
|
| 173 |
+
},
|
| 174 |
+
"50273": {
|
| 175 |
+
"content": " ",
|
| 176 |
+
"lstrip": false,
|
| 177 |
+
"normalized": true,
|
| 178 |
+
"rstrip": false,
|
| 179 |
+
"single_word": false,
|
| 180 |
+
"special": false
|
| 181 |
+
},
|
| 182 |
+
"50274": {
|
| 183 |
+
"content": " ",
|
| 184 |
+
"lstrip": false,
|
| 185 |
+
"normalized": true,
|
| 186 |
+
"rstrip": false,
|
| 187 |
+
"single_word": false,
|
| 188 |
+
"special": false
|
| 189 |
+
},
|
| 190 |
+
"50275": {
|
| 191 |
+
"content": " ",
|
| 192 |
+
"lstrip": false,
|
| 193 |
+
"normalized": true,
|
| 194 |
+
"rstrip": false,
|
| 195 |
+
"single_word": false,
|
| 196 |
+
"special": false
|
| 197 |
+
},
|
| 198 |
+
"50276": {
|
| 199 |
+
"content": " ",
|
| 200 |
+
"lstrip": false,
|
| 201 |
+
"normalized": true,
|
| 202 |
+
"rstrip": false,
|
| 203 |
+
"single_word": false,
|
| 204 |
+
"special": false
|
| 205 |
+
},
|
| 206 |
+
"50277": {
|
| 207 |
+
"content": "|||EMAIL_ADDRESS|||",
|
| 208 |
+
"lstrip": false,
|
| 209 |
+
"normalized": true,
|
| 210 |
+
"rstrip": false,
|
| 211 |
+
"single_word": false,
|
| 212 |
+
"special": false
|
| 213 |
+
},
|
| 214 |
+
"50278": {
|
| 215 |
+
"content": "|||PHONE_NUMBER|||",
|
| 216 |
+
"lstrip": false,
|
| 217 |
+
"normalized": true,
|
| 218 |
+
"rstrip": false,
|
| 219 |
+
"single_word": false,
|
| 220 |
+
"special": false
|
| 221 |
+
},
|
| 222 |
+
"50279": {
|
| 223 |
+
"content": "<|endoftext|>",
|
| 224 |
+
"lstrip": false,
|
| 225 |
+
"normalized": false,
|
| 226 |
+
"rstrip": false,
|
| 227 |
+
"single_word": false,
|
| 228 |
+
"special": true
|
| 229 |
+
}
|
| 230 |
+
},
|
| 231 |
+
"bos_token": null,
|
| 232 |
+
"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 %}",
|
| 233 |
+
"clean_up_tokenization_spaces": true,
|
| 234 |
+
"eos_token": "<|endoftext|>",
|
| 235 |
+
"model_max_length": 2048,
|
| 236 |
+
"pad_token": "<|padding|>",
|
| 237 |
+
"tokenizer_class": "GPTNeoXTokenizer",
|
| 238 |
+
"unk_token": null
|
| 239 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 0.9995795432403884,
|
| 3 |
+
"total_flos": 2.6010044317889987e+18,
|
| 4 |
+
"train_loss": 1.1185581020360233,
|
| 5 |
+
"train_runtime": 52635.226,
|
| 6 |
+
"train_samples": 1001538,
|
| 7 |
+
"train_samples_per_second": 3.705,
|
| 8 |
+
"train_steps_per_second": 0.029
|
| 9 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,2173 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.9995795432403884,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 1523,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.000656322746710695,
|
| 13 |
+
"grad_norm": 1.0,
|
| 14 |
+
"learning_rate": 1.3071895424836602e-06,
|
| 15 |
+
"loss": 2.0939,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.003281613733553475,
|
| 20 |
+
"grad_norm": 0.9765625,
|
| 21 |
+
"learning_rate": 6.535947712418301e-06,
|
| 22 |
+
"loss": 2.0618,
|
| 23 |
+
"step": 5
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.00656322746710695,
|
| 27 |
+
"grad_norm": 0.91796875,
|
| 28 |
+
"learning_rate": 1.3071895424836602e-05,
|
| 29 |
+
"loss": 2.0432,
|
| 30 |
+
"step": 10
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.009844841200660424,
|
| 34 |
+
"grad_norm": 0.71484375,
|
| 35 |
+
"learning_rate": 1.9607843137254903e-05,
|
| 36 |
+
"loss": 2.001,
|
| 37 |
+
"step": 15
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.0131264549342139,
|
| 41 |
+
"grad_norm": 0.578125,
|
| 42 |
+
"learning_rate": 2.6143790849673204e-05,
|
| 43 |
+
"loss": 1.9571,
|
| 44 |
+
"step": 20
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.016408068667767374,
|
| 48 |
+
"grad_norm": 0.5625,
|
| 49 |
+
"learning_rate": 3.2679738562091506e-05,
|
| 50 |
+
"loss": 1.8829,
|
| 51 |
+
"step": 25
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.019689682401320848,
|
| 55 |
+
"grad_norm": 0.90234375,
|
| 56 |
+
"learning_rate": 3.9215686274509805e-05,
|
| 57 |
+
"loss": 1.8114,
|
| 58 |
+
"step": 30
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.022971296134874326,
|
| 62 |
+
"grad_norm": 0.490234375,
|
| 63 |
+
"learning_rate": 4.5751633986928104e-05,
|
| 64 |
+
"loss": 1.6748,
|
| 65 |
+
"step": 35
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.0262529098684278,
|
| 69 |
+
"grad_norm": 0.3828125,
|
| 70 |
+
"learning_rate": 5.228758169934641e-05,
|
| 71 |
+
"loss": 1.665,
|
| 72 |
+
"step": 40
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.029534523601981274,
|
| 76 |
+
"grad_norm": 0.2099609375,
|
| 77 |
+
"learning_rate": 5.882352941176471e-05,
|
| 78 |
+
"loss": 1.6295,
|
| 79 |
+
"step": 45
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.03281613733553475,
|
| 83 |
+
"grad_norm": 0.2314453125,
|
| 84 |
+
"learning_rate": 6.535947712418301e-05,
|
| 85 |
+
"loss": 1.6194,
|
| 86 |
+
"step": 50
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.036097751069088226,
|
| 90 |
+
"grad_norm": 0.18359375,
|
| 91 |
+
"learning_rate": 7.189542483660131e-05,
|
| 92 |
+
"loss": 1.5773,
|
| 93 |
+
"step": 55
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.039379364802641696,
|
| 97 |
+
"grad_norm": 0.140625,
|
| 98 |
+
"learning_rate": 7.843137254901961e-05,
|
| 99 |
+
"loss": 1.542,
|
| 100 |
+
"step": 60
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.042660978536195174,
|
| 104 |
+
"grad_norm": 0.126953125,
|
| 105 |
+
"learning_rate": 8.496732026143791e-05,
|
| 106 |
+
"loss": 1.5303,
|
| 107 |
+
"step": 65
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.04594259226974865,
|
| 111 |
+
"grad_norm": 0.1123046875,
|
| 112 |
+
"learning_rate": 9.150326797385621e-05,
|
| 113 |
+
"loss": 1.5031,
|
| 114 |
+
"step": 70
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.04922420600330212,
|
| 118 |
+
"grad_norm": 0.10595703125,
|
| 119 |
+
"learning_rate": 9.80392156862745e-05,
|
| 120 |
+
"loss": 1.5177,
|
| 121 |
+
"step": 75
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.0525058197368556,
|
| 125 |
+
"grad_norm": 0.09814453125,
|
| 126 |
+
"learning_rate": 0.00010457516339869282,
|
| 127 |
+
"loss": 1.5038,
|
| 128 |
+
"step": 80
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.05578743347040908,
|
| 132 |
+
"grad_norm": 0.09130859375,
|
| 133 |
+
"learning_rate": 0.00011111111111111112,
|
| 134 |
+
"loss": 1.4847,
|
| 135 |
+
"step": 85
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.05906904720396255,
|
| 139 |
+
"grad_norm": 0.0986328125,
|
| 140 |
+
"learning_rate": 0.00011764705882352942,
|
| 141 |
+
"loss": 1.5054,
|
| 142 |
+
"step": 90
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.062350660937516025,
|
| 146 |
+
"grad_norm": 0.09912109375,
|
| 147 |
+
"learning_rate": 0.00012418300653594771,
|
| 148 |
+
"loss": 1.4672,
|
| 149 |
+
"step": 95
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.0656322746710695,
|
| 153 |
+
"grad_norm": 0.10205078125,
|
| 154 |
+
"learning_rate": 0.00013071895424836603,
|
| 155 |
+
"loss": 1.4626,
|
| 156 |
+
"step": 100
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.06891388840462297,
|
| 160 |
+
"grad_norm": 0.1416015625,
|
| 161 |
+
"learning_rate": 0.0001372549019607843,
|
| 162 |
+
"loss": 1.451,
|
| 163 |
+
"step": 105
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.07219550213817645,
|
| 167 |
+
"grad_norm": 0.111328125,
|
| 168 |
+
"learning_rate": 0.00014379084967320262,
|
| 169 |
+
"loss": 1.4631,
|
| 170 |
+
"step": 110
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.07547711587172992,
|
| 174 |
+
"grad_norm": 0.10302734375,
|
| 175 |
+
"learning_rate": 0.0001503267973856209,
|
| 176 |
+
"loss": 1.4423,
|
| 177 |
+
"step": 115
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.07875872960528339,
|
| 181 |
+
"grad_norm": 0.1064453125,
|
| 182 |
+
"learning_rate": 0.00015686274509803922,
|
| 183 |
+
"loss": 1.4301,
|
| 184 |
+
"step": 120
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.08204034333883688,
|
| 188 |
+
"grad_norm": 0.1123046875,
|
| 189 |
+
"learning_rate": 0.00016339869281045753,
|
| 190 |
+
"loss": 1.4287,
|
| 191 |
+
"step": 125
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.08532195707239035,
|
| 195 |
+
"grad_norm": 0.162109375,
|
| 196 |
+
"learning_rate": 0.00016993464052287582,
|
| 197 |
+
"loss": 1.4294,
|
| 198 |
+
"step": 130
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.08860357080594382,
|
| 202 |
+
"grad_norm": 0.1240234375,
|
| 203 |
+
"learning_rate": 0.00017647058823529413,
|
| 204 |
+
"loss": 1.4201,
|
| 205 |
+
"step": 135
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.0918851845394973,
|
| 209 |
+
"grad_norm": 0.1494140625,
|
| 210 |
+
"learning_rate": 0.00018300653594771241,
|
| 211 |
+
"loss": 1.4044,
|
| 212 |
+
"step": 140
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.09516679827305077,
|
| 216 |
+
"grad_norm": 0.1357421875,
|
| 217 |
+
"learning_rate": 0.00018954248366013073,
|
| 218 |
+
"loss": 1.4114,
|
| 219 |
+
"step": 145
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.09844841200660424,
|
| 223 |
+
"grad_norm": 0.1552734375,
|
| 224 |
+
"learning_rate": 0.000196078431372549,
|
| 225 |
+
"loss": 1.3928,
|
| 226 |
+
"step": 150
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.10173002574015773,
|
| 230 |
+
"grad_norm": 0.162109375,
|
| 231 |
+
"learning_rate": 0.0001999989483097553,
|
| 232 |
+
"loss": 1.4054,
|
| 233 |
+
"step": 155
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.1050116394737112,
|
| 237 |
+
"grad_norm": 0.1337890625,
|
| 238 |
+
"learning_rate": 0.00019998711704854725,
|
| 239 |
+
"loss": 1.3996,
|
| 240 |
+
"step": 160
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.10829325320726467,
|
| 244 |
+
"grad_norm": 0.15625,
|
| 245 |
+
"learning_rate": 0.0001999621414738484,
|
| 246 |
+
"loss": 1.4015,
|
| 247 |
+
"step": 165
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.11157486694081815,
|
| 251 |
+
"grad_norm": 0.1455078125,
|
| 252 |
+
"learning_rate": 0.0001999240248689495,
|
| 253 |
+
"loss": 1.387,
|
| 254 |
+
"step": 170
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.11485648067437162,
|
| 258 |
+
"grad_norm": 0.140625,
|
| 259 |
+
"learning_rate": 0.00019987277224466215,
|
| 260 |
+
"loss": 1.4057,
|
| 261 |
+
"step": 175
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.1181380944079251,
|
| 265 |
+
"grad_norm": 0.142578125,
|
| 266 |
+
"learning_rate": 0.00019980839033865994,
|
| 267 |
+
"loss": 1.3844,
|
| 268 |
+
"step": 180
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.12141970814147857,
|
| 272 |
+
"grad_norm": 0.146484375,
|
| 273 |
+
"learning_rate": 0.00019973088761459287,
|
| 274 |
+
"loss": 1.3654,
|
| 275 |
+
"step": 185
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.12470132187503205,
|
| 279 |
+
"grad_norm": 0.1591796875,
|
| 280 |
+
"learning_rate": 0.00019964027426097448,
|
| 281 |
+
"loss": 1.3632,
|
| 282 |
+
"step": 190
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.12798293560858554,
|
| 286 |
+
"grad_norm": 0.154296875,
|
| 287 |
+
"learning_rate": 0.00019953656218984263,
|
| 288 |
+
"loss": 1.3982,
|
| 289 |
+
"step": 195
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.131264549342139,
|
| 293 |
+
"grad_norm": 0.146484375,
|
| 294 |
+
"learning_rate": 0.0001994197650351936,
|
| 295 |
+
"loss": 1.3842,
|
| 296 |
+
"step": 200
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.13454616307569248,
|
| 300 |
+
"grad_norm": 0.1640625,
|
| 301 |
+
"learning_rate": 0.0001992898981511896,
|
| 302 |
+
"loss": 1.3528,
|
| 303 |
+
"step": 205
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.13782777680924593,
|
| 307 |
+
"grad_norm": 0.173828125,
|
| 308 |
+
"learning_rate": 0.0001991469786101404,
|
| 309 |
+
"loss": 1.3811,
|
| 310 |
+
"step": 210
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.14110939054279942,
|
| 314 |
+
"grad_norm": 0.162109375,
|
| 315 |
+
"learning_rate": 0.00019899102520025896,
|
| 316 |
+
"loss": 1.3594,
|
| 317 |
+
"step": 215
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.1443910042763529,
|
| 321 |
+
"grad_norm": 0.1865234375,
|
| 322 |
+
"learning_rate": 0.0001988220584231916,
|
| 323 |
+
"loss": 1.3675,
|
| 324 |
+
"step": 220
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.14767261800990636,
|
| 328 |
+
"grad_norm": 0.15234375,
|
| 329 |
+
"learning_rate": 0.00019864010049132287,
|
| 330 |
+
"loss": 1.3532,
|
| 331 |
+
"step": 225
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.15095423174345984,
|
| 335 |
+
"grad_norm": 0.1455078125,
|
| 336 |
+
"learning_rate": 0.0001984451753248553,
|
| 337 |
+
"loss": 1.3672,
|
| 338 |
+
"step": 230
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.15423584547701333,
|
| 342 |
+
"grad_norm": 0.1689453125,
|
| 343 |
+
"learning_rate": 0.0001982373085486651,
|
| 344 |
+
"loss": 1.3553,
|
| 345 |
+
"step": 235
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.15751745921056678,
|
| 349 |
+
"grad_norm": 0.1396484375,
|
| 350 |
+
"learning_rate": 0.00019801652748893347,
|
| 351 |
+
"loss": 1.3303,
|
| 352 |
+
"step": 240
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.16079907294412027,
|
| 356 |
+
"grad_norm": 0.1396484375,
|
| 357 |
+
"learning_rate": 0.00019778286116955407,
|
| 358 |
+
"loss": 1.35,
|
| 359 |
+
"step": 245
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.16408068667767375,
|
| 363 |
+
"grad_norm": 0.1484375,
|
| 364 |
+
"learning_rate": 0.00019753634030831782,
|
| 365 |
+
"loss": 1.3451,
|
| 366 |
+
"step": 250
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.1673623004112272,
|
| 370 |
+
"grad_norm": 0.1357421875,
|
| 371 |
+
"learning_rate": 0.00019727699731287465,
|
| 372 |
+
"loss": 1.3604,
|
| 373 |
+
"step": 255
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.1706439141447807,
|
| 377 |
+
"grad_norm": 0.15625,
|
| 378 |
+
"learning_rate": 0.00019700486627647305,
|
| 379 |
+
"loss": 1.3418,
|
| 380 |
+
"step": 260
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.17392552787833418,
|
| 384 |
+
"grad_norm": 0.171875,
|
| 385 |
+
"learning_rate": 0.0001967199829734784,
|
| 386 |
+
"loss": 1.3463,
|
| 387 |
+
"step": 265
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.17720714161188764,
|
| 391 |
+
"grad_norm": 0.1533203125,
|
| 392 |
+
"learning_rate": 0.00019642238485466989,
|
| 393 |
+
"loss": 1.357,
|
| 394 |
+
"step": 270
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.18048875534544112,
|
| 398 |
+
"grad_norm": 0.1455078125,
|
| 399 |
+
"learning_rate": 0.00019611211104231724,
|
| 400 |
+
"loss": 1.3678,
|
| 401 |
+
"step": 275
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.1837703690789946,
|
| 405 |
+
"grad_norm": 0.134765625,
|
| 406 |
+
"learning_rate": 0.0001957892023250379,
|
| 407 |
+
"loss": 1.3296,
|
| 408 |
+
"step": 280
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.18705198281254806,
|
| 412 |
+
"grad_norm": 0.154296875,
|
| 413 |
+
"learning_rate": 0.00019545370115243462,
|
| 414 |
+
"loss": 1.3445,
|
| 415 |
+
"step": 285
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.19033359654610155,
|
| 419 |
+
"grad_norm": 0.146484375,
|
| 420 |
+
"learning_rate": 0.00019510565162951537,
|
| 421 |
+
"loss": 1.3407,
|
| 422 |
+
"step": 290
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.19361521027965503,
|
| 426 |
+
"grad_norm": 0.1484375,
|
| 427 |
+
"learning_rate": 0.00019474509951089507,
|
| 428 |
+
"loss": 1.3419,
|
| 429 |
+
"step": 295
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.1968968240132085,
|
| 433 |
+
"grad_norm": 0.1357421875,
|
| 434 |
+
"learning_rate": 0.00019437209219478084,
|
| 435 |
+
"loss": 1.349,
|
| 436 |
+
"step": 300
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.20017843774676197,
|
| 440 |
+
"grad_norm": 0.1728515625,
|
| 441 |
+
"learning_rate": 0.00019398667871674082,
|
| 442 |
+
"loss": 1.3282,
|
| 443 |
+
"step": 305
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.20346005148031546,
|
| 447 |
+
"grad_norm": 0.1669921875,
|
| 448 |
+
"learning_rate": 0.00019358890974325817,
|
| 449 |
+
"loss": 1.3115,
|
| 450 |
+
"step": 310
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.2067416652138689,
|
| 454 |
+
"grad_norm": 0.1396484375,
|
| 455 |
+
"learning_rate": 0.00019317883756507026,
|
| 456 |
+
"loss": 1.339,
|
| 457 |
+
"step": 315
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.2100232789474224,
|
| 461 |
+
"grad_norm": 0.1435546875,
|
| 462 |
+
"learning_rate": 0.0001927565160902948,
|
| 463 |
+
"loss": 1.3186,
|
| 464 |
+
"step": 320
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.21330489268097588,
|
| 468 |
+
"grad_norm": 0.1494140625,
|
| 469 |
+
"learning_rate": 0.00019232200083734265,
|
| 470 |
+
"loss": 1.3434,
|
| 471 |
+
"step": 325
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.21658650641452934,
|
| 475 |
+
"grad_norm": 0.1455078125,
|
| 476 |
+
"learning_rate": 0.00019187534892761986,
|
| 477 |
+
"loss": 1.3186,
|
| 478 |
+
"step": 330
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 0.21986812014808282,
|
| 482 |
+
"grad_norm": 0.1435546875,
|
| 483 |
+
"learning_rate": 0.0001914166190780181,
|
| 484 |
+
"loss": 1.3394,
|
| 485 |
+
"step": 335
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.2231497338816363,
|
| 489 |
+
"grad_norm": 0.1416015625,
|
| 490 |
+
"learning_rate": 0.00019094587159319585,
|
| 491 |
+
"loss": 1.317,
|
| 492 |
+
"step": 340
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 0.22643134761518977,
|
| 496 |
+
"grad_norm": 0.142578125,
|
| 497 |
+
"learning_rate": 0.00019046316835765083,
|
| 498 |
+
"loss": 1.3344,
|
| 499 |
+
"step": 345
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.22971296134874325,
|
| 503 |
+
"grad_norm": 0.1650390625,
|
| 504 |
+
"learning_rate": 0.00018996857282758462,
|
| 505 |
+
"loss": 1.3402,
|
| 506 |
+
"step": 350
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.2329945750822967,
|
| 510 |
+
"grad_norm": 0.1455078125,
|
| 511 |
+
"learning_rate": 0.00018946215002256061,
|
| 512 |
+
"loss": 1.3396,
|
| 513 |
+
"step": 355
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.2362761888158502,
|
| 517 |
+
"grad_norm": 0.1591796875,
|
| 518 |
+
"learning_rate": 0.00018894396651695662,
|
| 519 |
+
"loss": 1.3289,
|
| 520 |
+
"step": 360
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 0.23955780254940368,
|
| 524 |
+
"grad_norm": 0.1396484375,
|
| 525 |
+
"learning_rate": 0.00018841409043121306,
|
| 526 |
+
"loss": 1.3274,
|
| 527 |
+
"step": 365
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.24283941628295713,
|
| 531 |
+
"grad_norm": 0.1416015625,
|
| 532 |
+
"learning_rate": 0.0001878725914228776,
|
| 533 |
+
"loss": 1.3312,
|
| 534 |
+
"step": 370
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.24612103001651062,
|
| 538 |
+
"grad_norm": 0.14453125,
|
| 539 |
+
"learning_rate": 0.00018731954067744834,
|
| 540 |
+
"loss": 1.3258,
|
| 541 |
+
"step": 375
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.2494026437500641,
|
| 545 |
+
"grad_norm": 0.150390625,
|
| 546 |
+
"learning_rate": 0.00018675501089901542,
|
| 547 |
+
"loss": 1.3224,
|
| 548 |
+
"step": 380
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 0.25268425748361756,
|
| 552 |
+
"grad_norm": 0.1474609375,
|
| 553 |
+
"learning_rate": 0.00018617907630070352,
|
| 554 |
+
"loss": 1.3219,
|
| 555 |
+
"step": 385
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.25596587121717107,
|
| 559 |
+
"grad_norm": 0.1337890625,
|
| 560 |
+
"learning_rate": 0.0001855918125949157,
|
| 561 |
+
"loss": 1.3191,
|
| 562 |
+
"step": 390
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 0.2592474849507245,
|
| 566 |
+
"grad_norm": 0.1435546875,
|
| 567 |
+
"learning_rate": 0.00018499329698338035,
|
| 568 |
+
"loss": 1.3183,
|
| 569 |
+
"step": 395
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.262529098684278,
|
| 573 |
+
"grad_norm": 0.1474609375,
|
| 574 |
+
"learning_rate": 0.0001843836081470022,
|
| 575 |
+
"loss": 1.3154,
|
| 576 |
+
"step": 400
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 0.2658107124178315,
|
| 580 |
+
"grad_norm": 0.142578125,
|
| 581 |
+
"learning_rate": 0.0001837628262355188,
|
| 582 |
+
"loss": 1.3131,
|
| 583 |
+
"step": 405
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.26909232615138495,
|
| 587 |
+
"grad_norm": 0.14453125,
|
| 588 |
+
"learning_rate": 0.00018313103285696425,
|
| 589 |
+
"loss": 1.3211,
|
| 590 |
+
"step": 410
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 0.2723739398849384,
|
| 594 |
+
"grad_norm": 0.150390625,
|
| 595 |
+
"learning_rate": 0.00018248831106694086,
|
| 596 |
+
"loss": 1.3082,
|
| 597 |
+
"step": 415
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.27565555361849187,
|
| 601 |
+
"grad_norm": 0.15234375,
|
| 602 |
+
"learning_rate": 0.00018183474535770068,
|
| 603 |
+
"loss": 1.3046,
|
| 604 |
+
"step": 420
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 0.2789371673520454,
|
| 608 |
+
"grad_norm": 0.1748046875,
|
| 609 |
+
"learning_rate": 0.00018117042164703814,
|
| 610 |
+
"loss": 1.3026,
|
| 611 |
+
"step": 425
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.28221878108559884,
|
| 615 |
+
"grad_norm": 0.1484375,
|
| 616 |
+
"learning_rate": 0.00018049542726699533,
|
| 617 |
+
"loss": 1.3265,
|
| 618 |
+
"step": 430
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 0.2855003948191523,
|
| 622 |
+
"grad_norm": 0.142578125,
|
| 623 |
+
"learning_rate": 0.00017980985095238124,
|
| 624 |
+
"loss": 1.2958,
|
| 625 |
+
"step": 435
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.2887820085527058,
|
| 629 |
+
"grad_norm": 0.1767578125,
|
| 630 |
+
"learning_rate": 0.00017911378282910675,
|
| 631 |
+
"loss": 1.311,
|
| 632 |
+
"step": 440
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 0.29206362228625926,
|
| 636 |
+
"grad_norm": 0.138671875,
|
| 637 |
+
"learning_rate": 0.00017840731440233674,
|
| 638 |
+
"loss": 1.3126,
|
| 639 |
+
"step": 445
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.2953452360198127,
|
| 643 |
+
"grad_norm": 0.1435546875,
|
| 644 |
+
"learning_rate": 0.00017769053854446053,
|
| 645 |
+
"loss": 1.303,
|
| 646 |
+
"step": 450
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 0.29862684975336623,
|
| 650 |
+
"grad_norm": 0.1484375,
|
| 651 |
+
"learning_rate": 0.00017696354948288327,
|
| 652 |
+
"loss": 1.3106,
|
| 653 |
+
"step": 455
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 0.3019084634869197,
|
| 657 |
+
"grad_norm": 0.14453125,
|
| 658 |
+
"learning_rate": 0.00017622644278763843,
|
| 659 |
+
"loss": 1.2993,
|
| 660 |
+
"step": 460
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 0.30519007722047314,
|
| 664 |
+
"grad_norm": 0.1455078125,
|
| 665 |
+
"learning_rate": 0.00017547931535882445,
|
| 666 |
+
"loss": 1.3031,
|
| 667 |
+
"step": 465
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 0.30847169095402666,
|
| 671 |
+
"grad_norm": 0.134765625,
|
| 672 |
+
"learning_rate": 0.000174722265413866,
|
| 673 |
+
"loss": 1.3175,
|
| 674 |
+
"step": 470
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 0.3117533046875801,
|
| 678 |
+
"grad_norm": 0.1484375,
|
| 679 |
+
"learning_rate": 0.0001739553924746025,
|
| 680 |
+
"loss": 1.3086,
|
| 681 |
+
"step": 475
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.31503491842113357,
|
| 685 |
+
"grad_norm": 0.1669921875,
|
| 686 |
+
"learning_rate": 0.0001731787973542049,
|
| 687 |
+
"loss": 1.3364,
|
| 688 |
+
"step": 480
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 0.3183165321546871,
|
| 692 |
+
"grad_norm": 0.150390625,
|
| 693 |
+
"learning_rate": 0.0001723925821439227,
|
| 694 |
+
"loss": 1.3103,
|
| 695 |
+
"step": 485
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 0.32159814588824054,
|
| 699 |
+
"grad_norm": 0.13671875,
|
| 700 |
+
"learning_rate": 0.00017159685019966316,
|
| 701 |
+
"loss": 1.3312,
|
| 702 |
+
"step": 490
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 0.324879759621794,
|
| 706 |
+
"grad_norm": 0.142578125,
|
| 707 |
+
"learning_rate": 0.00017079170612840404,
|
| 708 |
+
"loss": 1.3064,
|
| 709 |
+
"step": 495
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 0.3281613733553475,
|
| 713 |
+
"grad_norm": 0.1357421875,
|
| 714 |
+
"learning_rate": 0.00016997725577444205,
|
| 715 |
+
"loss": 1.3109,
|
| 716 |
+
"step": 500
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 0.33144298708890096,
|
| 720 |
+
"grad_norm": 0.1318359375,
|
| 721 |
+
"learning_rate": 0.0001691536062054783,
|
| 722 |
+
"loss": 1.3083,
|
| 723 |
+
"step": 505
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 0.3347246008224544,
|
| 727 |
+
"grad_norm": 0.1376953125,
|
| 728 |
+
"learning_rate": 0.0001683208656985436,
|
| 729 |
+
"loss": 1.2997,
|
| 730 |
+
"step": 510
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 0.33800621455600793,
|
| 734 |
+
"grad_norm": 0.140625,
|
| 735 |
+
"learning_rate": 0.00016747914372576393,
|
| 736 |
+
"loss": 1.3161,
|
| 737 |
+
"step": 515
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 0.3412878282895614,
|
| 741 |
+
"grad_norm": 0.1376953125,
|
| 742 |
+
"learning_rate": 0.00016662855093996945,
|
| 743 |
+
"loss": 1.2811,
|
| 744 |
+
"step": 520
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 0.34456944202311485,
|
| 748 |
+
"grad_norm": 0.14453125,
|
| 749 |
+
"learning_rate": 0.00016576919916014808,
|
| 750 |
+
"loss": 1.3146,
|
| 751 |
+
"step": 525
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 0.34785105575666836,
|
| 755 |
+
"grad_norm": 0.13671875,
|
| 756 |
+
"learning_rate": 0.00016490120135674566,
|
| 757 |
+
"loss": 1.2922,
|
| 758 |
+
"step": 530
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 0.3511326694902218,
|
| 762 |
+
"grad_norm": 0.146484375,
|
| 763 |
+
"learning_rate": 0.00016402467163681493,
|
| 764 |
+
"loss": 1.2962,
|
| 765 |
+
"step": 535
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 0.3544142832237753,
|
| 769 |
+
"grad_norm": 0.138671875,
|
| 770 |
+
"learning_rate": 0.00016313972522901491,
|
| 771 |
+
"loss": 1.3008,
|
| 772 |
+
"step": 540
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 0.3576958969573288,
|
| 776 |
+
"grad_norm": 0.1455078125,
|
| 777 |
+
"learning_rate": 0.00016224647846846315,
|
| 778 |
+
"loss": 1.3042,
|
| 779 |
+
"step": 545
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 0.36097751069088224,
|
| 783 |
+
"grad_norm": 0.134765625,
|
| 784 |
+
"learning_rate": 0.00016134504878144204,
|
| 785 |
+
"loss": 1.2876,
|
| 786 |
+
"step": 550
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 0.3642591244244357,
|
| 790 |
+
"grad_norm": 0.1474609375,
|
| 791 |
+
"learning_rate": 0.00016043555466996206,
|
| 792 |
+
"loss": 1.3086,
|
| 793 |
+
"step": 555
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 0.3675407381579892,
|
| 797 |
+
"grad_norm": 0.1513671875,
|
| 798 |
+
"learning_rate": 0.0001595181156961836,
|
| 799 |
+
"loss": 1.2894,
|
| 800 |
+
"step": 560
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 0.37082235189154267,
|
| 804 |
+
"grad_norm": 0.1357421875,
|
| 805 |
+
"learning_rate": 0.00015859285246669913,
|
| 806 |
+
"loss": 1.2933,
|
| 807 |
+
"step": 565
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 0.3741039656250961,
|
| 811 |
+
"grad_norm": 0.1435546875,
|
| 812 |
+
"learning_rate": 0.00015765988661667834,
|
| 813 |
+
"loss": 1.2885,
|
| 814 |
+
"step": 570
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 0.37738557935864964,
|
| 818 |
+
"grad_norm": 0.150390625,
|
| 819 |
+
"learning_rate": 0.00015671934079387797,
|
| 820 |
+
"loss": 1.2719,
|
| 821 |
+
"step": 575
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 0.3806671930922031,
|
| 825 |
+
"grad_norm": 0.1337890625,
|
| 826 |
+
"learning_rate": 0.00015577133864251848,
|
| 827 |
+
"loss": 1.3012,
|
| 828 |
+
"step": 580
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 0.38394880682575655,
|
| 832 |
+
"grad_norm": 0.1337890625,
|
| 833 |
+
"learning_rate": 0.00015481600478702996,
|
| 834 |
+
"loss": 1.3046,
|
| 835 |
+
"step": 585
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 0.38723042055931006,
|
| 839 |
+
"grad_norm": 0.142578125,
|
| 840 |
+
"learning_rate": 0.0001538534648156686,
|
| 841 |
+
"loss": 1.3017,
|
| 842 |
+
"step": 590
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 0.3905120342928635,
|
| 846 |
+
"grad_norm": 0.13671875,
|
| 847 |
+
"learning_rate": 0.00015288384526400734,
|
| 848 |
+
"loss": 1.307,
|
| 849 |
+
"step": 595
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 0.393793648026417,
|
| 853 |
+
"grad_norm": 0.134765625,
|
| 854 |
+
"learning_rate": 0.00015190727359830109,
|
| 855 |
+
"loss": 1.2755,
|
| 856 |
+
"step": 600
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 0.3970752617599705,
|
| 860 |
+
"grad_norm": 0.1357421875,
|
| 861 |
+
"learning_rate": 0.00015092387819873014,
|
| 862 |
+
"loss": 1.2961,
|
| 863 |
+
"step": 605
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 0.40035687549352394,
|
| 867 |
+
"grad_norm": 0.1416015625,
|
| 868 |
+
"learning_rate": 0.0001499337883425235,
|
| 869 |
+
"loss": 1.2989,
|
| 870 |
+
"step": 610
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 0.4036384892270774,
|
| 874 |
+
"grad_norm": 0.138671875,
|
| 875 |
+
"learning_rate": 0.0001489371341869638,
|
| 876 |
+
"loss": 1.2897,
|
| 877 |
+
"step": 615
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 0.4069201029606309,
|
| 881 |
+
"grad_norm": 0.1435546875,
|
| 882 |
+
"learning_rate": 0.00014793404675227684,
|
| 883 |
+
"loss": 1.3068,
|
| 884 |
+
"step": 620
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 0.41020171669418437,
|
| 888 |
+
"grad_norm": 0.1416015625,
|
| 889 |
+
"learning_rate": 0.00014692465790440792,
|
| 890 |
+
"loss": 1.28,
|
| 891 |
+
"step": 625
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 0.4134833304277378,
|
| 895 |
+
"grad_norm": 0.13671875,
|
| 896 |
+
"learning_rate": 0.0001459091003376865,
|
| 897 |
+
"loss": 1.274,
|
| 898 |
+
"step": 630
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 0.41676494416129134,
|
| 902 |
+
"grad_norm": 0.1474609375,
|
| 903 |
+
"learning_rate": 0.00014488750755738223,
|
| 904 |
+
"loss": 1.3007,
|
| 905 |
+
"step": 635
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 0.4200465578948448,
|
| 909 |
+
"grad_norm": 0.14453125,
|
| 910 |
+
"learning_rate": 0.00014386001386215434,
|
| 911 |
+
"loss": 1.2852,
|
| 912 |
+
"step": 640
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 0.42332817162839825,
|
| 916 |
+
"grad_norm": 0.138671875,
|
| 917 |
+
"learning_rate": 0.0001428267543263969,
|
| 918 |
+
"loss": 1.2861,
|
| 919 |
+
"step": 645
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 0.42660978536195177,
|
| 923 |
+
"grad_norm": 0.1376953125,
|
| 924 |
+
"learning_rate": 0.00014178786478248162,
|
| 925 |
+
"loss": 1.2873,
|
| 926 |
+
"step": 650
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 0.4298913990955052,
|
| 930 |
+
"grad_norm": 0.140625,
|
| 931 |
+
"learning_rate": 0.0001407434818029015,
|
| 932 |
+
"loss": 1.283,
|
| 933 |
+
"step": 655
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 0.4331730128290587,
|
| 937 |
+
"grad_norm": 0.1376953125,
|
| 938 |
+
"learning_rate": 0.00013969374268231713,
|
| 939 |
+
"loss": 1.2828,
|
| 940 |
+
"step": 660
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 0.4364546265626122,
|
| 944 |
+
"grad_norm": 0.1376953125,
|
| 945 |
+
"learning_rate": 0.0001386387854195076,
|
| 946 |
+
"loss": 1.2577,
|
| 947 |
+
"step": 665
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 0.43973624029616565,
|
| 951 |
+
"grad_norm": 0.134765625,
|
| 952 |
+
"learning_rate": 0.0001375787486992294,
|
| 953 |
+
"loss": 1.3003,
|
| 954 |
+
"step": 670
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 0.4430178540297191,
|
| 958 |
+
"grad_norm": 0.1435546875,
|
| 959 |
+
"learning_rate": 0.00013651377187398492,
|
| 960 |
+
"loss": 1.2879,
|
| 961 |
+
"step": 675
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 0.4462994677632726,
|
| 965 |
+
"grad_norm": 0.140625,
|
| 966 |
+
"learning_rate": 0.00013544399494570307,
|
| 967 |
+
"loss": 1.2947,
|
| 968 |
+
"step": 680
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 0.4495810814968261,
|
| 972 |
+
"grad_norm": 0.1376953125,
|
| 973 |
+
"learning_rate": 0.0001343695585473346,
|
| 974 |
+
"loss": 1.263,
|
| 975 |
+
"step": 685
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 0.45286269523037953,
|
| 979 |
+
"grad_norm": 0.1328125,
|
| 980 |
+
"learning_rate": 0.00013329060392436456,
|
| 981 |
+
"loss": 1.2842,
|
| 982 |
+
"step": 690
|
| 983 |
+
},
|
| 984 |
+
{
|
| 985 |
+
"epoch": 0.456144308963933,
|
| 986 |
+
"grad_norm": 0.14453125,
|
| 987 |
+
"learning_rate": 0.00013220727291624415,
|
| 988 |
+
"loss": 1.2789,
|
| 989 |
+
"step": 695
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 0.4594259226974865,
|
| 993 |
+
"grad_norm": 0.1396484375,
|
| 994 |
+
"learning_rate": 0.00013111970793774439,
|
| 995 |
+
"loss": 1.2638,
|
| 996 |
+
"step": 700
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 0.46270753643103996,
|
| 1000 |
+
"grad_norm": 0.1318359375,
|
| 1001 |
+
"learning_rate": 0.00013002805196023448,
|
| 1002 |
+
"loss": 1.2978,
|
| 1003 |
+
"step": 705
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 0.4659891501645934,
|
| 1007 |
+
"grad_norm": 0.13671875,
|
| 1008 |
+
"learning_rate": 0.0001289324484928865,
|
| 1009 |
+
"loss": 1.2863,
|
| 1010 |
+
"step": 710
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 0.4692707638981469,
|
| 1014 |
+
"grad_norm": 0.1318359375,
|
| 1015 |
+
"learning_rate": 0.0001278330415638099,
|
| 1016 |
+
"loss": 1.2774,
|
| 1017 |
+
"step": 715
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 0.4725523776317004,
|
| 1021 |
+
"grad_norm": 0.1357421875,
|
| 1022 |
+
"learning_rate": 0.0001267299757011175,
|
| 1023 |
+
"loss": 1.2741,
|
| 1024 |
+
"step": 720
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 0.47583399136525384,
|
| 1028 |
+
"grad_norm": 0.1328125,
|
| 1029 |
+
"learning_rate": 0.00012562339591392572,
|
| 1030 |
+
"loss": 1.2904,
|
| 1031 |
+
"step": 725
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 0.47911560509880735,
|
| 1035 |
+
"grad_norm": 0.1318359375,
|
| 1036 |
+
"learning_rate": 0.00012451344767329178,
|
| 1037 |
+
"loss": 1.2737,
|
| 1038 |
+
"step": 730
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"epoch": 0.4823972188323608,
|
| 1042 |
+
"grad_norm": 0.140625,
|
| 1043 |
+
"learning_rate": 0.00012340027689309,
|
| 1044 |
+
"loss": 1.2958,
|
| 1045 |
+
"step": 735
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 0.48567883256591426,
|
| 1049 |
+
"grad_norm": 0.1435546875,
|
| 1050 |
+
"learning_rate": 0.0001222840299108301,
|
| 1051 |
+
"loss": 1.2914,
|
| 1052 |
+
"step": 740
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 0.4889604462994678,
|
| 1056 |
+
"grad_norm": 0.1435546875,
|
| 1057 |
+
"learning_rate": 0.0001211648534684194,
|
| 1058 |
+
"loss": 1.3006,
|
| 1059 |
+
"step": 745
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 0.49224206003302123,
|
| 1063 |
+
"grad_norm": 0.134765625,
|
| 1064 |
+
"learning_rate": 0.00012004289469287229,
|
| 1065 |
+
"loss": 1.2698,
|
| 1066 |
+
"step": 750
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 0.4955236737665747,
|
| 1070 |
+
"grad_norm": 0.146484375,
|
| 1071 |
+
"learning_rate": 0.00011891830107696891,
|
| 1072 |
+
"loss": 1.2954,
|
| 1073 |
+
"step": 755
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 0.4988052875001282,
|
| 1077 |
+
"grad_norm": 0.138671875,
|
| 1078 |
+
"learning_rate": 0.00011779122045986567,
|
| 1079 |
+
"loss": 1.2682,
|
| 1080 |
+
"step": 760
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 0.5020869012336817,
|
| 1084 |
+
"grad_norm": 0.1337890625,
|
| 1085 |
+
"learning_rate": 0.00011666180100766036,
|
| 1086 |
+
"loss": 1.2779,
|
| 1087 |
+
"step": 765
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 0.5053685149672351,
|
| 1091 |
+
"grad_norm": 0.1318359375,
|
| 1092 |
+
"learning_rate": 0.00011553019119391412,
|
| 1093 |
+
"loss": 1.2848,
|
| 1094 |
+
"step": 770
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 0.5086501287007886,
|
| 1098 |
+
"grad_norm": 0.1376953125,
|
| 1099 |
+
"learning_rate": 0.00011439653978013334,
|
| 1100 |
+
"loss": 1.2788,
|
| 1101 |
+
"step": 775
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 0.5119317424343421,
|
| 1105 |
+
"grad_norm": 0.146484375,
|
| 1106 |
+
"learning_rate": 0.0001132609957962131,
|
| 1107 |
+
"loss": 1.2696,
|
| 1108 |
+
"step": 780
|
| 1109 |
+
},
|
| 1110 |
+
{
|
| 1111 |
+
"epoch": 0.5152133561678955,
|
| 1112 |
+
"grad_norm": 0.1337890625,
|
| 1113 |
+
"learning_rate": 0.00011212370852084603,
|
| 1114 |
+
"loss": 1.272,
|
| 1115 |
+
"step": 785
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 0.518494969901449,
|
| 1119 |
+
"grad_norm": 0.13671875,
|
| 1120 |
+
"learning_rate": 0.00011098482746189786,
|
| 1121 |
+
"loss": 1.2893,
|
| 1122 |
+
"step": 790
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 0.5217765836350026,
|
| 1126 |
+
"grad_norm": 0.138671875,
|
| 1127 |
+
"learning_rate": 0.00010984450233675334,
|
| 1128 |
+
"loss": 1.2761,
|
| 1129 |
+
"step": 795
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 0.525058197368556,
|
| 1133 |
+
"grad_norm": 0.142578125,
|
| 1134 |
+
"learning_rate": 0.0001087028830526342,
|
| 1135 |
+
"loss": 1.2472,
|
| 1136 |
+
"step": 800
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 0.5283398111021095,
|
| 1140 |
+
"grad_norm": 0.1416015625,
|
| 1141 |
+
"learning_rate": 0.00010756011968689242,
|
| 1142 |
+
"loss": 1.2683,
|
| 1143 |
+
"step": 805
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 0.531621424835663,
|
| 1147 |
+
"grad_norm": 0.1396484375,
|
| 1148 |
+
"learning_rate": 0.00010641636246728095,
|
| 1149 |
+
"loss": 1.2535,
|
| 1150 |
+
"step": 810
|
| 1151 |
+
},
|
| 1152 |
+
{
|
| 1153 |
+
"epoch": 0.5349030385692164,
|
| 1154 |
+
"grad_norm": 0.134765625,
|
| 1155 |
+
"learning_rate": 0.00010527176175220499,
|
| 1156 |
+
"loss": 1.2508,
|
| 1157 |
+
"step": 815
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 0.5381846523027699,
|
| 1161 |
+
"grad_norm": 0.138671875,
|
| 1162 |
+
"learning_rate": 0.0001041264680109556,
|
| 1163 |
+
"loss": 1.2801,
|
| 1164 |
+
"step": 820
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 0.5414662660363233,
|
| 1168 |
+
"grad_norm": 0.142578125,
|
| 1169 |
+
"learning_rate": 0.00010298063180392917,
|
| 1170 |
+
"loss": 1.2661,
|
| 1171 |
+
"step": 825
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 0.5447478797698768,
|
| 1175 |
+
"grad_norm": 0.134765625,
|
| 1176 |
+
"learning_rate": 0.0001018344037628346,
|
| 1177 |
+
"loss": 1.2817,
|
| 1178 |
+
"step": 830
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 0.5480294935034303,
|
| 1182 |
+
"grad_norm": 0.134765625,
|
| 1183 |
+
"learning_rate": 0.00010068793457089141,
|
| 1184 |
+
"loss": 1.2881,
|
| 1185 |
+
"step": 835
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 0.5513111072369837,
|
| 1189 |
+
"grad_norm": 0.134765625,
|
| 1190 |
+
"learning_rate": 9.954137494302079e-05,
|
| 1191 |
+
"loss": 1.2755,
|
| 1192 |
+
"step": 840
|
| 1193 |
+
},
|
| 1194 |
+
{
|
| 1195 |
+
"epoch": 0.5545927209705372,
|
| 1196 |
+
"grad_norm": 0.1396484375,
|
| 1197 |
+
"learning_rate": 9.839487560603266e-05,
|
| 1198 |
+
"loss": 1.2741,
|
| 1199 |
+
"step": 845
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 0.5578743347040908,
|
| 1203 |
+
"grad_norm": 0.1357421875,
|
| 1204 |
+
"learning_rate": 9.724858727881107e-05,
|
| 1205 |
+
"loss": 1.304,
|
| 1206 |
+
"step": 850
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"epoch": 0.5611559484376442,
|
| 1210 |
+
"grad_norm": 0.13671875,
|
| 1211 |
+
"learning_rate": 9.610266065250077e-05,
|
| 1212 |
+
"loss": 1.2742,
|
| 1213 |
+
"step": 855
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 0.5644375621711977,
|
| 1217 |
+
"grad_norm": 0.13671875,
|
| 1218 |
+
"learning_rate": 9.495724637069718e-05,
|
| 1219 |
+
"loss": 1.2988,
|
| 1220 |
+
"step": 860
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 0.5677191759047512,
|
| 1224 |
+
"grad_norm": 0.1337890625,
|
| 1225 |
+
"learning_rate": 9.381249500964294e-05,
|
| 1226 |
+
"loss": 1.2753,
|
| 1227 |
+
"step": 865
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 0.5710007896383046,
|
| 1231 |
+
"grad_norm": 0.1376953125,
|
| 1232 |
+
"learning_rate": 9.266855705843309e-05,
|
| 1233 |
+
"loss": 1.273,
|
| 1234 |
+
"step": 870
|
| 1235 |
+
},
|
| 1236 |
+
{
|
| 1237 |
+
"epoch": 0.5742824033718581,
|
| 1238 |
+
"grad_norm": 0.13671875,
|
| 1239 |
+
"learning_rate": 9.152558289923177e-05,
|
| 1240 |
+
"loss": 1.2702,
|
| 1241 |
+
"step": 875
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 0.5775640171054116,
|
| 1245 |
+
"grad_norm": 0.1396484375,
|
| 1246 |
+
"learning_rate": 9.038372278750287e-05,
|
| 1247 |
+
"loss": 1.2854,
|
| 1248 |
+
"step": 880
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 0.580845630838965,
|
| 1252 |
+
"grad_norm": 0.140625,
|
| 1253 |
+
"learning_rate": 8.92431268322576e-05,
|
| 1254 |
+
"loss": 1.285,
|
| 1255 |
+
"step": 885
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 0.5841272445725185,
|
| 1259 |
+
"grad_norm": 0.1318359375,
|
| 1260 |
+
"learning_rate": 8.810394497632102e-05,
|
| 1261 |
+
"loss": 1.2743,
|
| 1262 |
+
"step": 890
|
| 1263 |
+
},
|
| 1264 |
+
{
|
| 1265 |
+
"epoch": 0.587408858306072,
|
| 1266 |
+
"grad_norm": 0.142578125,
|
| 1267 |
+
"learning_rate": 8.696632697662063e-05,
|
| 1268 |
+
"loss": 1.2741,
|
| 1269 |
+
"step": 895
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 0.5906904720396254,
|
| 1273 |
+
"grad_norm": 0.13671875,
|
| 1274 |
+
"learning_rate": 8.58304223844993e-05,
|
| 1275 |
+
"loss": 1.2847,
|
| 1276 |
+
"step": 900
|
| 1277 |
+
},
|
| 1278 |
+
{
|
| 1279 |
+
"epoch": 0.593972085773179,
|
| 1280 |
+
"grad_norm": 0.1376953125,
|
| 1281 |
+
"learning_rate": 8.469638052605513e-05,
|
| 1282 |
+
"loss": 1.2753,
|
| 1283 |
+
"step": 905
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 0.5972536995067325,
|
| 1287 |
+
"grad_norm": 0.138671875,
|
| 1288 |
+
"learning_rate": 8.356435048251126e-05,
|
| 1289 |
+
"loss": 1.2679,
|
| 1290 |
+
"step": 910
|
| 1291 |
+
},
|
| 1292 |
+
{
|
| 1293 |
+
"epoch": 0.6005353132402859,
|
| 1294 |
+
"grad_norm": 0.1650390625,
|
| 1295 |
+
"learning_rate": 8.243448107061729e-05,
|
| 1296 |
+
"loss": 1.2631,
|
| 1297 |
+
"step": 915
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 0.6038169269738394,
|
| 1301 |
+
"grad_norm": 0.134765625,
|
| 1302 |
+
"learning_rate": 8.130692082308624e-05,
|
| 1303 |
+
"loss": 1.2655,
|
| 1304 |
+
"step": 920
|
| 1305 |
+
},
|
| 1306 |
+
{
|
| 1307 |
+
"epoch": 0.6070985407073929,
|
| 1308 |
+
"grad_norm": 0.130859375,
|
| 1309 |
+
"learning_rate": 8.01818179690681e-05,
|
| 1310 |
+
"loss": 1.3186,
|
| 1311 |
+
"step": 925
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 0.6103801544409463,
|
| 1315 |
+
"grad_norm": 0.1337890625,
|
| 1316 |
+
"learning_rate": 7.90593204146638e-05,
|
| 1317 |
+
"loss": 1.2895,
|
| 1318 |
+
"step": 930
|
| 1319 |
+
},
|
| 1320 |
+
{
|
| 1321 |
+
"epoch": 0.6136617681744998,
|
| 1322 |
+
"grad_norm": 0.1337890625,
|
| 1323 |
+
"learning_rate": 7.793957572348131e-05,
|
| 1324 |
+
"loss": 1.2751,
|
| 1325 |
+
"step": 935
|
| 1326 |
+
},
|
| 1327 |
+
{
|
| 1328 |
+
"epoch": 0.6169433819080533,
|
| 1329 |
+
"grad_norm": 0.13671875,
|
| 1330 |
+
"learning_rate": 7.682273109723712e-05,
|
| 1331 |
+
"loss": 1.2663,
|
| 1332 |
+
"step": 940
|
| 1333 |
+
},
|
| 1334 |
+
{
|
| 1335 |
+
"epoch": 0.6202249956416067,
|
| 1336 |
+
"grad_norm": 0.1357421875,
|
| 1337 |
+
"learning_rate": 7.570893335640487e-05,
|
| 1338 |
+
"loss": 1.2706,
|
| 1339 |
+
"step": 945
|
| 1340 |
+
},
|
| 1341 |
+
{
|
| 1342 |
+
"epoch": 0.6235066093751602,
|
| 1343 |
+
"grad_norm": 0.13671875,
|
| 1344 |
+
"learning_rate": 7.459832892091455e-05,
|
| 1345 |
+
"loss": 1.2638,
|
| 1346 |
+
"step": 950
|
| 1347 |
+
},
|
| 1348 |
+
{
|
| 1349 |
+
"epoch": 0.6267882231087137,
|
| 1350 |
+
"grad_norm": 0.134765625,
|
| 1351 |
+
"learning_rate": 7.349106379090381e-05,
|
| 1352 |
+
"loss": 1.275,
|
| 1353 |
+
"step": 955
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"epoch": 0.6300698368422671,
|
| 1357 |
+
"grad_norm": 0.1328125,
|
| 1358 |
+
"learning_rate": 7.23872835275252e-05,
|
| 1359 |
+
"loss": 1.272,
|
| 1360 |
+
"step": 960
|
| 1361 |
+
},
|
| 1362 |
+
{
|
| 1363 |
+
"epoch": 0.6333514505758207,
|
| 1364 |
+
"grad_norm": 0.1337890625,
|
| 1365 |
+
"learning_rate": 7.128713323381032e-05,
|
| 1366 |
+
"loss": 1.2768,
|
| 1367 |
+
"step": 965
|
| 1368 |
+
},
|
| 1369 |
+
{
|
| 1370 |
+
"epoch": 0.6366330643093742,
|
| 1371 |
+
"grad_norm": 0.1318359375,
|
| 1372 |
+
"learning_rate": 7.019075753559468e-05,
|
| 1373 |
+
"loss": 1.2743,
|
| 1374 |
+
"step": 970
|
| 1375 |
+
},
|
| 1376 |
+
{
|
| 1377 |
+
"epoch": 0.6399146780429276,
|
| 1378 |
+
"grad_norm": 0.13671875,
|
| 1379 |
+
"learning_rate": 6.909830056250527e-05,
|
| 1380 |
+
"loss": 1.2707,
|
| 1381 |
+
"step": 975
|
| 1382 |
+
},
|
| 1383 |
+
{
|
| 1384 |
+
"epoch": 0.6431962917764811,
|
| 1385 |
+
"grad_norm": 0.1337890625,
|
| 1386 |
+
"learning_rate": 6.800990592901315e-05,
|
| 1387 |
+
"loss": 1.2844,
|
| 1388 |
+
"step": 980
|
| 1389 |
+
},
|
| 1390 |
+
{
|
| 1391 |
+
"epoch": 0.6464779055100346,
|
| 1392 |
+
"grad_norm": 0.1376953125,
|
| 1393 |
+
"learning_rate": 6.692571671555398e-05,
|
| 1394 |
+
"loss": 1.264,
|
| 1395 |
+
"step": 985
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"epoch": 0.649759519243588,
|
| 1399 |
+
"grad_norm": 0.1435546875,
|
| 1400 |
+
"learning_rate": 6.584587544971854e-05,
|
| 1401 |
+
"loss": 1.2481,
|
| 1402 |
+
"step": 990
|
| 1403 |
+
},
|
| 1404 |
+
{
|
| 1405 |
+
"epoch": 0.6530411329771415,
|
| 1406 |
+
"grad_norm": 0.130859375,
|
| 1407 |
+
"learning_rate": 6.477052408751616e-05,
|
| 1408 |
+
"loss": 1.2738,
|
| 1409 |
+
"step": 995
|
| 1410 |
+
},
|
| 1411 |
+
{
|
| 1412 |
+
"epoch": 0.656322746710695,
|
| 1413 |
+
"grad_norm": 0.1337890625,
|
| 1414 |
+
"learning_rate": 6.369980399471306e-05,
|
| 1415 |
+
"loss": 1.2806,
|
| 1416 |
+
"step": 1000
|
| 1417 |
+
},
|
| 1418 |
+
{
|
| 1419 |
+
"epoch": 0.6596043604442484,
|
| 1420 |
+
"grad_norm": 0.13671875,
|
| 1421 |
+
"learning_rate": 6.263385592824857e-05,
|
| 1422 |
+
"loss": 1.2911,
|
| 1423 |
+
"step": 1005
|
| 1424 |
+
},
|
| 1425 |
+
{
|
| 1426 |
+
"epoch": 0.6628859741778019,
|
| 1427 |
+
"grad_norm": 0.134765625,
|
| 1428 |
+
"learning_rate": 6.157282001773095e-05,
|
| 1429 |
+
"loss": 1.2794,
|
| 1430 |
+
"step": 1010
|
| 1431 |
+
},
|
| 1432 |
+
{
|
| 1433 |
+
"epoch": 0.6661675879113554,
|
| 1434 |
+
"grad_norm": 0.134765625,
|
| 1435 |
+
"learning_rate": 6.051683574701616e-05,
|
| 1436 |
+
"loss": 1.2664,
|
| 1437 |
+
"step": 1015
|
| 1438 |
+
},
|
| 1439 |
+
{
|
| 1440 |
+
"epoch": 0.6694492016449088,
|
| 1441 |
+
"grad_norm": 0.142578125,
|
| 1442 |
+
"learning_rate": 5.946604193587134e-05,
|
| 1443 |
+
"loss": 1.2674,
|
| 1444 |
+
"step": 1020
|
| 1445 |
+
},
|
| 1446 |
+
{
|
| 1447 |
+
"epoch": 0.6727308153784624,
|
| 1448 |
+
"grad_norm": 0.1357421875,
|
| 1449 |
+
"learning_rate": 5.842057672172525e-05,
|
| 1450 |
+
"loss": 1.2696,
|
| 1451 |
+
"step": 1025
|
| 1452 |
+
},
|
| 1453 |
+
{
|
| 1454 |
+
"epoch": 0.6760124291120159,
|
| 1455 |
+
"grad_norm": 0.138671875,
|
| 1456 |
+
"learning_rate": 5.738057754150905e-05,
|
| 1457 |
+
"loss": 1.2657,
|
| 1458 |
+
"step": 1030
|
| 1459 |
+
},
|
| 1460 |
+
{
|
| 1461 |
+
"epoch": 0.6792940428455693,
|
| 1462 |
+
"grad_norm": 0.1318359375,
|
| 1463 |
+
"learning_rate": 5.634618111358865e-05,
|
| 1464 |
+
"loss": 1.2726,
|
| 1465 |
+
"step": 1035
|
| 1466 |
+
},
|
| 1467 |
+
{
|
| 1468 |
+
"epoch": 0.6825756565791228,
|
| 1469 |
+
"grad_norm": 0.134765625,
|
| 1470 |
+
"learning_rate": 5.531752341979173e-05,
|
| 1471 |
+
"loss": 1.2842,
|
| 1472 |
+
"step": 1040
|
| 1473 |
+
},
|
| 1474 |
+
{
|
| 1475 |
+
"epoch": 0.6858572703126763,
|
| 1476 |
+
"grad_norm": 0.134765625,
|
| 1477 |
+
"learning_rate": 5.429473968753157e-05,
|
| 1478 |
+
"loss": 1.265,
|
| 1479 |
+
"step": 1045
|
| 1480 |
+
},
|
| 1481 |
+
{
|
| 1482 |
+
"epoch": 0.6891388840462297,
|
| 1483 |
+
"grad_norm": 0.13671875,
|
| 1484 |
+
"learning_rate": 5.327796437203019e-05,
|
| 1485 |
+
"loss": 1.2795,
|
| 1486 |
+
"step": 1050
|
| 1487 |
+
},
|
| 1488 |
+
{
|
| 1489 |
+
"epoch": 0.6924204977797832,
|
| 1490 |
+
"grad_norm": 0.1328125,
|
| 1491 |
+
"learning_rate": 5.226733113864242e-05,
|
| 1492 |
+
"loss": 1.2817,
|
| 1493 |
+
"step": 1055
|
| 1494 |
+
},
|
| 1495 |
+
{
|
| 1496 |
+
"epoch": 0.6957021115133367,
|
| 1497 |
+
"grad_norm": 0.13671875,
|
| 1498 |
+
"learning_rate": 5.126297284528485e-05,
|
| 1499 |
+
"loss": 1.2538,
|
| 1500 |
+
"step": 1060
|
| 1501 |
+
},
|
| 1502 |
+
{
|
| 1503 |
+
"epoch": 0.6989837252468901,
|
| 1504 |
+
"grad_norm": 0.1416015625,
|
| 1505 |
+
"learning_rate": 5.0265021524969857e-05,
|
| 1506 |
+
"loss": 1.2608,
|
| 1507 |
+
"step": 1065
|
| 1508 |
+
},
|
| 1509 |
+
{
|
| 1510 |
+
"epoch": 0.7022653389804436,
|
| 1511 |
+
"grad_norm": 0.1318359375,
|
| 1512 |
+
"learning_rate": 4.927360836844868e-05,
|
| 1513 |
+
"loss": 1.2743,
|
| 1514 |
+
"step": 1070
|
| 1515 |
+
},
|
| 1516 |
+
{
|
| 1517 |
+
"epoch": 0.7055469527139971,
|
| 1518 |
+
"grad_norm": 0.1357421875,
|
| 1519 |
+
"learning_rate": 4.82888637069651e-05,
|
| 1520 |
+
"loss": 1.2725,
|
| 1521 |
+
"step": 1075
|
| 1522 |
+
},
|
| 1523 |
+
{
|
| 1524 |
+
"epoch": 0.7088285664475505,
|
| 1525 |
+
"grad_norm": 0.1328125,
|
| 1526 |
+
"learning_rate": 4.731091699512215e-05,
|
| 1527 |
+
"loss": 1.2578,
|
| 1528 |
+
"step": 1080
|
| 1529 |
+
},
|
| 1530 |
+
{
|
| 1531 |
+
"epoch": 0.7121101801811041,
|
| 1532 |
+
"grad_norm": 0.1357421875,
|
| 1533 |
+
"learning_rate": 4.6339896793863804e-05,
|
| 1534 |
+
"loss": 1.2784,
|
| 1535 |
+
"step": 1085
|
| 1536 |
+
},
|
| 1537 |
+
{
|
| 1538 |
+
"epoch": 0.7153917939146576,
|
| 1539 |
+
"grad_norm": 0.13671875,
|
| 1540 |
+
"learning_rate": 4.537593075357451e-05,
|
| 1541 |
+
"loss": 1.2708,
|
| 1542 |
+
"step": 1090
|
| 1543 |
+
},
|
| 1544 |
+
{
|
| 1545 |
+
"epoch": 0.718673407648211,
|
| 1546 |
+
"grad_norm": 0.13671875,
|
| 1547 |
+
"learning_rate": 4.441914559729825e-05,
|
| 1548 |
+
"loss": 1.2797,
|
| 1549 |
+
"step": 1095
|
| 1550 |
+
},
|
| 1551 |
+
{
|
| 1552 |
+
"epoch": 0.7219550213817645,
|
| 1553 |
+
"grad_norm": 0.13671875,
|
| 1554 |
+
"learning_rate": 4.346966710407937e-05,
|
| 1555 |
+
"loss": 1.3013,
|
| 1556 |
+
"step": 1100
|
| 1557 |
+
},
|
| 1558 |
+
{
|
| 1559 |
+
"epoch": 0.725236635115318,
|
| 1560 |
+
"grad_norm": 0.134765625,
|
| 1561 |
+
"learning_rate": 4.2527620092428e-05,
|
| 1562 |
+
"loss": 1.2535,
|
| 1563 |
+
"step": 1105
|
| 1564 |
+
},
|
| 1565 |
+
{
|
| 1566 |
+
"epoch": 0.7285182488488714,
|
| 1567 |
+
"grad_norm": 0.1337890625,
|
| 1568 |
+
"learning_rate": 4.159312840391086e-05,
|
| 1569 |
+
"loss": 1.2779,
|
| 1570 |
+
"step": 1110
|
| 1571 |
+
},
|
| 1572 |
+
{
|
| 1573 |
+
"epoch": 0.7317998625824249,
|
| 1574 |
+
"grad_norm": 0.134765625,
|
| 1575 |
+
"learning_rate": 4.066631488687166e-05,
|
| 1576 |
+
"loss": 1.2659,
|
| 1577 |
+
"step": 1115
|
| 1578 |
+
},
|
| 1579 |
+
{
|
| 1580 |
+
"epoch": 0.7350814763159784,
|
| 1581 |
+
"grad_norm": 0.1337890625,
|
| 1582 |
+
"learning_rate": 3.974730138028095e-05,
|
| 1583 |
+
"loss": 1.2653,
|
| 1584 |
+
"step": 1120
|
| 1585 |
+
},
|
| 1586 |
+
{
|
| 1587 |
+
"epoch": 0.7383630900495318,
|
| 1588 |
+
"grad_norm": 0.130859375,
|
| 1589 |
+
"learning_rate": 3.883620869771943e-05,
|
| 1590 |
+
"loss": 1.2735,
|
| 1591 |
+
"step": 1125
|
| 1592 |
+
},
|
| 1593 |
+
{
|
| 1594 |
+
"epoch": 0.7416447037830853,
|
| 1595 |
+
"grad_norm": 0.134765625,
|
| 1596 |
+
"learning_rate": 3.79331566114957e-05,
|
| 1597 |
+
"loss": 1.2653,
|
| 1598 |
+
"step": 1130
|
| 1599 |
+
},
|
| 1600 |
+
{
|
| 1601 |
+
"epoch": 0.7449263175166388,
|
| 1602 |
+
"grad_norm": 0.134765625,
|
| 1603 |
+
"learning_rate": 3.703826383690099e-05,
|
| 1604 |
+
"loss": 1.262,
|
| 1605 |
+
"step": 1135
|
| 1606 |
+
},
|
| 1607 |
+
{
|
| 1608 |
+
"epoch": 0.7482079312501922,
|
| 1609 |
+
"grad_norm": 0.1328125,
|
| 1610 |
+
"learning_rate": 3.6151648016602794e-05,
|
| 1611 |
+
"loss": 1.2491,
|
| 1612 |
+
"step": 1140
|
| 1613 |
+
},
|
| 1614 |
+
{
|
| 1615 |
+
"epoch": 0.7514895449837458,
|
| 1616 |
+
"grad_norm": 0.1357421875,
|
| 1617 |
+
"learning_rate": 3.527342570517975e-05,
|
| 1618 |
+
"loss": 1.2551,
|
| 1619 |
+
"step": 1145
|
| 1620 |
+
},
|
| 1621 |
+
{
|
| 1622 |
+
"epoch": 0.7547711587172993,
|
| 1623 |
+
"grad_norm": 0.1328125,
|
| 1624 |
+
"learning_rate": 3.44037123537991e-05,
|
| 1625 |
+
"loss": 1.2605,
|
| 1626 |
+
"step": 1150
|
| 1627 |
+
},
|
| 1628 |
+
{
|
| 1629 |
+
"epoch": 0.7580527724508527,
|
| 1630 |
+
"grad_norm": 0.134765625,
|
| 1631 |
+
"learning_rate": 3.3542622295039593e-05,
|
| 1632 |
+
"loss": 1.2621,
|
| 1633 |
+
"step": 1155
|
| 1634 |
+
},
|
| 1635 |
+
{
|
| 1636 |
+
"epoch": 0.7613343861844062,
|
| 1637 |
+
"grad_norm": 0.12890625,
|
| 1638 |
+
"learning_rate": 3.269026872786145e-05,
|
| 1639 |
+
"loss": 1.2798,
|
| 1640 |
+
"step": 1160
|
| 1641 |
+
},
|
| 1642 |
+
{
|
| 1643 |
+
"epoch": 0.7646159999179597,
|
| 1644 |
+
"grad_norm": 0.1318359375,
|
| 1645 |
+
"learning_rate": 3.184676370272488e-05,
|
| 1646 |
+
"loss": 1.2823,
|
| 1647 |
+
"step": 1165
|
| 1648 |
+
},
|
| 1649 |
+
{
|
| 1650 |
+
"epoch": 0.7678976136515131,
|
| 1651 |
+
"grad_norm": 0.1318359375,
|
| 1652 |
+
"learning_rate": 3.1012218106860345e-05,
|
| 1653 |
+
"loss": 1.284,
|
| 1654 |
+
"step": 1170
|
| 1655 |
+
},
|
| 1656 |
+
{
|
| 1657 |
+
"epoch": 0.7711792273850666,
|
| 1658 |
+
"grad_norm": 0.1357421875,
|
| 1659 |
+
"learning_rate": 3.0186741649690963e-05,
|
| 1660 |
+
"loss": 1.2825,
|
| 1661 |
+
"step": 1175
|
| 1662 |
+
},
|
| 1663 |
+
{
|
| 1664 |
+
"epoch": 0.7744608411186201,
|
| 1665 |
+
"grad_norm": 0.1337890625,
|
| 1666 |
+
"learning_rate": 2.937044284841026e-05,
|
| 1667 |
+
"loss": 1.2561,
|
| 1668 |
+
"step": 1180
|
| 1669 |
+
},
|
| 1670 |
+
{
|
| 1671 |
+
"epoch": 0.7777424548521735,
|
| 1672 |
+
"grad_norm": 0.1337890625,
|
| 1673 |
+
"learning_rate": 2.8563429013716514e-05,
|
| 1674 |
+
"loss": 1.2587,
|
| 1675 |
+
"step": 1185
|
| 1676 |
+
},
|
| 1677 |
+
{
|
| 1678 |
+
"epoch": 0.781024068585727,
|
| 1679 |
+
"grad_norm": 0.1328125,
|
| 1680 |
+
"learning_rate": 2.7765806235705594e-05,
|
| 1681 |
+
"loss": 1.2545,
|
| 1682 |
+
"step": 1190
|
| 1683 |
+
},
|
| 1684 |
+
{
|
| 1685 |
+
"epoch": 0.7843056823192806,
|
| 1686 |
+
"grad_norm": 0.1337890625,
|
| 1687 |
+
"learning_rate": 2.6977679369924357e-05,
|
| 1688 |
+
"loss": 1.2553,
|
| 1689 |
+
"step": 1195
|
| 1690 |
+
},
|
| 1691 |
+
{
|
| 1692 |
+
"epoch": 0.787587296052834,
|
| 1693 |
+
"grad_norm": 0.1337890625,
|
| 1694 |
+
"learning_rate": 2.6199152023586503e-05,
|
| 1695 |
+
"loss": 1.2713,
|
| 1696 |
+
"step": 1200
|
| 1697 |
+
},
|
| 1698 |
+
{
|
| 1699 |
+
"epoch": 0.7908689097863875,
|
| 1700 |
+
"grad_norm": 0.1318359375,
|
| 1701 |
+
"learning_rate": 2.5430326541952087e-05,
|
| 1702 |
+
"loss": 1.2593,
|
| 1703 |
+
"step": 1205
|
| 1704 |
+
},
|
| 1705 |
+
{
|
| 1706 |
+
"epoch": 0.794150523519941,
|
| 1707 |
+
"grad_norm": 0.13671875,
|
| 1708 |
+
"learning_rate": 2.4671303994873373e-05,
|
| 1709 |
+
"loss": 1.2509,
|
| 1710 |
+
"step": 1210
|
| 1711 |
+
},
|
| 1712 |
+
{
|
| 1713 |
+
"epoch": 0.7974321372534944,
|
| 1714 |
+
"grad_norm": 0.1328125,
|
| 1715 |
+
"learning_rate": 2.3922184163508254e-05,
|
| 1716 |
+
"loss": 1.2682,
|
| 1717 |
+
"step": 1215
|
| 1718 |
+
},
|
| 1719 |
+
{
|
| 1720 |
+
"epoch": 0.8007137509870479,
|
| 1721 |
+
"grad_norm": 0.134765625,
|
| 1722 |
+
"learning_rate": 2.3183065527202718e-05,
|
| 1723 |
+
"loss": 1.2596,
|
| 1724 |
+
"step": 1220
|
| 1725 |
+
},
|
| 1726 |
+
{
|
| 1727 |
+
"epoch": 0.8039953647206014,
|
| 1728 |
+
"grad_norm": 0.1337890625,
|
| 1729 |
+
"learning_rate": 2.245404525054515e-05,
|
| 1730 |
+
"loss": 1.2634,
|
| 1731 |
+
"step": 1225
|
| 1732 |
+
},
|
| 1733 |
+
{
|
| 1734 |
+
"epoch": 0.8072769784541548,
|
| 1735 |
+
"grad_norm": 0.130859375,
|
| 1736 |
+
"learning_rate": 2.1735219170592734e-05,
|
| 1737 |
+
"loss": 1.2717,
|
| 1738 |
+
"step": 1230
|
| 1739 |
+
},
|
| 1740 |
+
{
|
| 1741 |
+
"epoch": 0.8105585921877083,
|
| 1742 |
+
"grad_norm": 0.1357421875,
|
| 1743 |
+
"learning_rate": 2.1026681784272872e-05,
|
| 1744 |
+
"loss": 1.2607,
|
| 1745 |
+
"step": 1235
|
| 1746 |
+
},
|
| 1747 |
+
{
|
| 1748 |
+
"epoch": 0.8138402059212618,
|
| 1749 |
+
"grad_norm": 0.1337890625,
|
| 1750 |
+
"learning_rate": 2.0328526235960565e-05,
|
| 1751 |
+
"loss": 1.2733,
|
| 1752 |
+
"step": 1240
|
| 1753 |
+
},
|
| 1754 |
+
{
|
| 1755 |
+
"epoch": 0.8171218196548152,
|
| 1756 |
+
"grad_norm": 0.1318359375,
|
| 1757 |
+
"learning_rate": 1.9640844305233642e-05,
|
| 1758 |
+
"loss": 1.2696,
|
| 1759 |
+
"step": 1245
|
| 1760 |
+
},
|
| 1761 |
+
{
|
| 1762 |
+
"epoch": 0.8204034333883687,
|
| 1763 |
+
"grad_norm": 0.1318359375,
|
| 1764 |
+
"learning_rate": 1.8963726394807424e-05,
|
| 1765 |
+
"loss": 1.2779,
|
| 1766 |
+
"step": 1250
|
| 1767 |
+
},
|
| 1768 |
+
{
|
| 1769 |
+
"epoch": 0.8236850471219223,
|
| 1770 |
+
"grad_norm": 0.1328125,
|
| 1771 |
+
"learning_rate": 1.8297261518650456e-05,
|
| 1772 |
+
"loss": 1.2668,
|
| 1773 |
+
"step": 1255
|
| 1774 |
+
},
|
| 1775 |
+
{
|
| 1776 |
+
"epoch": 0.8269666608554757,
|
| 1777 |
+
"grad_norm": 0.130859375,
|
| 1778 |
+
"learning_rate": 1.7641537290282472e-05,
|
| 1779 |
+
"loss": 1.2646,
|
| 1780 |
+
"step": 1260
|
| 1781 |
+
},
|
| 1782 |
+
{
|
| 1783 |
+
"epoch": 0.8302482745890292,
|
| 1784 |
+
"grad_norm": 0.130859375,
|
| 1785 |
+
"learning_rate": 1.699663991125705e-05,
|
| 1786 |
+
"loss": 1.2696,
|
| 1787 |
+
"step": 1265
|
| 1788 |
+
},
|
| 1789 |
+
{
|
| 1790 |
+
"epoch": 0.8335298883225827,
|
| 1791 |
+
"grad_norm": 0.12890625,
|
| 1792 |
+
"learning_rate": 1.636265415982936e-05,
|
| 1793 |
+
"loss": 1.2604,
|
| 1794 |
+
"step": 1270
|
| 1795 |
+
},
|
| 1796 |
+
{
|
| 1797 |
+
"epoch": 0.8368115020561361,
|
| 1798 |
+
"grad_norm": 0.1328125,
|
| 1799 |
+
"learning_rate": 1.5739663379811122e-05,
|
| 1800 |
+
"loss": 1.2664,
|
| 1801 |
+
"step": 1275
|
| 1802 |
+
},
|
| 1803 |
+
{
|
| 1804 |
+
"epoch": 0.8400931157896896,
|
| 1805 |
+
"grad_norm": 0.130859375,
|
| 1806 |
+
"learning_rate": 1.512774946961445e-05,
|
| 1807 |
+
"loss": 1.2804,
|
| 1808 |
+
"step": 1280
|
| 1809 |
+
},
|
| 1810 |
+
{
|
| 1811 |
+
"epoch": 0.8433747295232431,
|
| 1812 |
+
"grad_norm": 0.1337890625,
|
| 1813 |
+
"learning_rate": 1.4526992871485345e-05,
|
| 1814 |
+
"loss": 1.2641,
|
| 1815 |
+
"step": 1285
|
| 1816 |
+
},
|
| 1817 |
+
{
|
| 1818 |
+
"epoch": 0.8466563432567965,
|
| 1819 |
+
"grad_norm": 0.1298828125,
|
| 1820 |
+
"learning_rate": 1.3937472560928733e-05,
|
| 1821 |
+
"loss": 1.2795,
|
| 1822 |
+
"step": 1290
|
| 1823 |
+
},
|
| 1824 |
+
{
|
| 1825 |
+
"epoch": 0.84993795699035,
|
| 1826 |
+
"grad_norm": 0.1318359375,
|
| 1827 |
+
"learning_rate": 1.3359266036326412e-05,
|
| 1828 |
+
"loss": 1.2659,
|
| 1829 |
+
"step": 1295
|
| 1830 |
+
},
|
| 1831 |
+
{
|
| 1832 |
+
"epoch": 0.8532195707239035,
|
| 1833 |
+
"grad_norm": 0.1337890625,
|
| 1834 |
+
"learning_rate": 1.2792449308749076e-05,
|
| 1835 |
+
"loss": 1.2643,
|
| 1836 |
+
"step": 1300
|
| 1837 |
+
},
|
| 1838 |
+
{
|
| 1839 |
+
"epoch": 0.8565011844574569,
|
| 1840 |
+
"grad_norm": 0.1298828125,
|
| 1841 |
+
"learning_rate": 1.2237096891963862e-05,
|
| 1842 |
+
"loss": 1.2812,
|
| 1843 |
+
"step": 1305
|
| 1844 |
+
},
|
| 1845 |
+
{
|
| 1846 |
+
"epoch": 0.8597827981910104,
|
| 1847 |
+
"grad_norm": 0.1298828125,
|
| 1848 |
+
"learning_rate": 1.1693281792638877e-05,
|
| 1849 |
+
"loss": 1.2669,
|
| 1850 |
+
"step": 1310
|
| 1851 |
+
},
|
| 1852 |
+
{
|
| 1853 |
+
"epoch": 0.863064411924564,
|
| 1854 |
+
"grad_norm": 0.1298828125,
|
| 1855 |
+
"learning_rate": 1.1161075500745543e-05,
|
| 1856 |
+
"loss": 1.2734,
|
| 1857 |
+
"step": 1315
|
| 1858 |
+
},
|
| 1859 |
+
{
|
| 1860 |
+
"epoch": 0.8663460256581174,
|
| 1861 |
+
"grad_norm": 0.1318359375,
|
| 1862 |
+
"learning_rate": 1.0640547980160742e-05,
|
| 1863 |
+
"loss": 1.2607,
|
| 1864 |
+
"step": 1320
|
| 1865 |
+
},
|
| 1866 |
+
{
|
| 1867 |
+
"epoch": 0.8696276393916709,
|
| 1868 |
+
"grad_norm": 0.1298828125,
|
| 1869 |
+
"learning_rate": 1.0131767659469205e-05,
|
| 1870 |
+
"loss": 1.2717,
|
| 1871 |
+
"step": 1325
|
| 1872 |
+
},
|
| 1873 |
+
{
|
| 1874 |
+
"epoch": 0.8729092531252244,
|
| 1875 |
+
"grad_norm": 0.1376953125,
|
| 1876 |
+
"learning_rate": 9.634801422967887e-06,
|
| 1877 |
+
"loss": 1.2767,
|
| 1878 |
+
"step": 1330
|
| 1879 |
+
},
|
| 1880 |
+
{
|
| 1881 |
+
"epoch": 0.8761908668587778,
|
| 1882 |
+
"grad_norm": 0.1337890625,
|
| 1883 |
+
"learning_rate": 9.149714601873516e-06,
|
| 1884 |
+
"loss": 1.274,
|
| 1885 |
+
"step": 1335
|
| 1886 |
+
},
|
| 1887 |
+
{
|
| 1888 |
+
"epoch": 0.8794724805923313,
|
| 1889 |
+
"grad_norm": 0.1328125,
|
| 1890 |
+
"learning_rate": 8.67657096573391e-06,
|
| 1891 |
+
"loss": 1.2553,
|
| 1892 |
+
"step": 1340
|
| 1893 |
+
},
|
| 1894 |
+
{
|
| 1895 |
+
"epoch": 0.8827540943258848,
|
| 1896 |
+
"grad_norm": 0.1279296875,
|
| 1897 |
+
"learning_rate": 8.215432714045024e-06,
|
| 1898 |
+
"loss": 1.2758,
|
| 1899 |
+
"step": 1345
|
| 1900 |
+
},
|
| 1901 |
+
{
|
| 1902 |
+
"epoch": 0.8860357080594382,
|
| 1903 |
+
"grad_norm": 0.1279296875,
|
| 1904 |
+
"learning_rate": 7.766360468074074e-06,
|
| 1905 |
+
"loss": 1.288,
|
| 1906 |
+
"step": 1350
|
| 1907 |
+
},
|
| 1908 |
+
{
|
| 1909 |
+
"epoch": 0.8893173217929917,
|
| 1910 |
+
"grad_norm": 0.1318359375,
|
| 1911 |
+
"learning_rate": 7.32941326289035e-06,
|
| 1912 |
+
"loss": 1.2421,
|
| 1913 |
+
"step": 1355
|
| 1914 |
+
},
|
| 1915 |
+
{
|
| 1916 |
+
"epoch": 0.8925989355265452,
|
| 1917 |
+
"grad_norm": 0.130859375,
|
| 1918 |
+
"learning_rate": 6.904648539604364e-06,
|
| 1919 |
+
"loss": 1.2517,
|
| 1920 |
+
"step": 1360
|
| 1921 |
+
},
|
| 1922 |
+
{
|
| 1923 |
+
"epoch": 0.8958805492600986,
|
| 1924 |
+
"grad_norm": 0.1328125,
|
| 1925 |
+
"learning_rate": 6.4921221378167915e-06,
|
| 1926 |
+
"loss": 1.2712,
|
| 1927 |
+
"step": 1365
|
| 1928 |
+
},
|
| 1929 |
+
{
|
| 1930 |
+
"epoch": 0.8991621629936521,
|
| 1931 |
+
"grad_norm": 0.12890625,
|
| 1932 |
+
"learning_rate": 6.091888288277569e-06,
|
| 1933 |
+
"loss": 1.264,
|
| 1934 |
+
"step": 1370
|
| 1935 |
+
},
|
| 1936 |
+
{
|
| 1937 |
+
"epoch": 0.9024437767272055,
|
| 1938 |
+
"grad_norm": 0.1328125,
|
| 1939 |
+
"learning_rate": 5.70399960575696e-06,
|
| 1940 |
+
"loss": 1.2713,
|
| 1941 |
+
"step": 1375
|
| 1942 |
+
},
|
| 1943 |
+
{
|
| 1944 |
+
"epoch": 0.9057253904607591,
|
| 1945 |
+
"grad_norm": 0.1337890625,
|
| 1946 |
+
"learning_rate": 5.328507082128642e-06,
|
| 1947 |
+
"loss": 1.272,
|
| 1948 |
+
"step": 1380
|
| 1949 |
+
},
|
| 1950 |
+
{
|
| 1951 |
+
"epoch": 0.9090070041943126,
|
| 1952 |
+
"grad_norm": 0.12890625,
|
| 1953 |
+
"learning_rate": 4.965460079666362e-06,
|
| 1954 |
+
"loss": 1.2672,
|
| 1955 |
+
"step": 1385
|
| 1956 |
+
},
|
| 1957 |
+
{
|
| 1958 |
+
"epoch": 0.912288617927866,
|
| 1959 |
+
"grad_norm": 0.1298828125,
|
| 1960 |
+
"learning_rate": 4.61490632455478e-06,
|
| 1961 |
+
"loss": 1.2732,
|
| 1962 |
+
"step": 1390
|
| 1963 |
+
},
|
| 1964 |
+
{
|
| 1965 |
+
"epoch": 0.9155702316614195,
|
| 1966 |
+
"grad_norm": 0.130859375,
|
| 1967 |
+
"learning_rate": 4.2768919006153876e-06,
|
| 1968 |
+
"loss": 1.2467,
|
| 1969 |
+
"step": 1395
|
| 1970 |
+
},
|
| 1971 |
+
{
|
| 1972 |
+
"epoch": 0.918851845394973,
|
| 1973 |
+
"grad_norm": 0.1328125,
|
| 1974 |
+
"learning_rate": 3.951461243248311e-06,
|
| 1975 |
+
"loss": 1.2634,
|
| 1976 |
+
"step": 1400
|
| 1977 |
+
},
|
| 1978 |
+
{
|
| 1979 |
+
"epoch": 0.9221334591285264,
|
| 1980 |
+
"grad_norm": 0.130859375,
|
| 1981 |
+
"learning_rate": 3.638657133590817e-06,
|
| 1982 |
+
"loss": 1.2571,
|
| 1983 |
+
"step": 1405
|
| 1984 |
+
},
|
| 1985 |
+
{
|
| 1986 |
+
"epoch": 0.9254150728620799,
|
| 1987 |
+
"grad_norm": 0.134765625,
|
| 1988 |
+
"learning_rate": 3.3385206928933097e-06,
|
| 1989 |
+
"loss": 1.2528,
|
| 1990 |
+
"step": 1410
|
| 1991 |
+
},
|
| 1992 |
+
{
|
| 1993 |
+
"epoch": 0.9286966865956334,
|
| 1994 |
+
"grad_norm": 0.130859375,
|
| 1995 |
+
"learning_rate": 3.0510913771135463e-06,
|
| 1996 |
+
"loss": 1.2647,
|
| 1997 |
+
"step": 1415
|
| 1998 |
+
},
|
| 1999 |
+
{
|
| 2000 |
+
"epoch": 0.9319783003291868,
|
| 2001 |
+
"grad_norm": 0.1337890625,
|
| 2002 |
+
"learning_rate": 2.7764069717297724e-06,
|
| 2003 |
+
"loss": 1.2769,
|
| 2004 |
+
"step": 1420
|
| 2005 |
+
},
|
| 2006 |
+
{
|
| 2007 |
+
"epoch": 0.9352599140627403,
|
| 2008 |
+
"grad_norm": 0.1318359375,
|
| 2009 |
+
"learning_rate": 2.5145035867733312e-06,
|
| 2010 |
+
"loss": 1.2616,
|
| 2011 |
+
"step": 1425
|
| 2012 |
+
},
|
| 2013 |
+
{
|
| 2014 |
+
"epoch": 0.9385415277962939,
|
| 2015 |
+
"grad_norm": 0.1357421875,
|
| 2016 |
+
"learning_rate": 2.265415652081804e-06,
|
| 2017 |
+
"loss": 1.2698,
|
| 2018 |
+
"step": 1430
|
| 2019 |
+
},
|
| 2020 |
+
{
|
| 2021 |
+
"epoch": 0.9418231415298473,
|
| 2022 |
+
"grad_norm": 0.1337890625,
|
| 2023 |
+
"learning_rate": 2.0291759127727294e-06,
|
| 2024 |
+
"loss": 1.2415,
|
| 2025 |
+
"step": 1435
|
| 2026 |
+
},
|
| 2027 |
+
{
|
| 2028 |
+
"epoch": 0.9451047552634008,
|
| 2029 |
+
"grad_norm": 0.1279296875,
|
| 2030 |
+
"learning_rate": 1.8058154249389502e-06,
|
| 2031 |
+
"loss": 1.2907,
|
| 2032 |
+
"step": 1440
|
| 2033 |
+
},
|
| 2034 |
+
{
|
| 2035 |
+
"epoch": 0.9483863689969543,
|
| 2036 |
+
"grad_norm": 0.130859375,
|
| 2037 |
+
"learning_rate": 1.5953635515660425e-06,
|
| 2038 |
+
"loss": 1.2786,
|
| 2039 |
+
"step": 1445
|
| 2040 |
+
},
|
| 2041 |
+
{
|
| 2042 |
+
"epoch": 0.9516679827305077,
|
| 2043 |
+
"grad_norm": 0.1337890625,
|
| 2044 |
+
"learning_rate": 1.3978479586721716e-06,
|
| 2045 |
+
"loss": 1.2634,
|
| 2046 |
+
"step": 1450
|
| 2047 |
+
},
|
| 2048 |
+
{
|
| 2049 |
+
"epoch": 0.9549495964640612,
|
| 2050 |
+
"grad_norm": 0.1337890625,
|
| 2051 |
+
"learning_rate": 1.2132946116711897e-06,
|
| 2052 |
+
"loss": 1.2866,
|
| 2053 |
+
"step": 1455
|
| 2054 |
+
},
|
| 2055 |
+
{
|
| 2056 |
+
"epoch": 0.9582312101976147,
|
| 2057 |
+
"grad_norm": 0.12890625,
|
| 2058 |
+
"learning_rate": 1.0417277719591667e-06,
|
| 2059 |
+
"loss": 1.2671,
|
| 2060 |
+
"step": 1460
|
| 2061 |
+
},
|
| 2062 |
+
{
|
| 2063 |
+
"epoch": 0.9615128239311681,
|
| 2064 |
+
"grad_norm": 0.1328125,
|
| 2065 |
+
"learning_rate": 8.831699937249859e-07,
|
| 2066 |
+
"loss": 1.251,
|
| 2067 |
+
"step": 1465
|
| 2068 |
+
},
|
| 2069 |
+
{
|
| 2070 |
+
"epoch": 0.9647944376647216,
|
| 2071 |
+
"grad_norm": 0.1318359375,
|
| 2072 |
+
"learning_rate": 7.376421209854267e-07,
|
| 2073 |
+
"loss": 1.2793,
|
| 2074 |
+
"step": 1470
|
| 2075 |
+
},
|
| 2076 |
+
{
|
| 2077 |
+
"epoch": 0.9680760513982751,
|
| 2078 |
+
"grad_norm": 0.126953125,
|
| 2079 |
+
"learning_rate": 6.051632848449562e-07,
|
| 2080 |
+
"loss": 1.2684,
|
| 2081 |
+
"step": 1475
|
| 2082 |
+
},
|
| 2083 |
+
{
|
| 2084 |
+
"epoch": 0.9713576651318285,
|
| 2085 |
+
"grad_norm": 0.1318359375,
|
| 2086 |
+
"learning_rate": 4.857509009807304e-07,
|
| 2087 |
+
"loss": 1.2605,
|
| 2088 |
+
"step": 1480
|
| 2089 |
+
},
|
| 2090 |
+
{
|
| 2091 |
+
"epoch": 0.974639278865382,
|
| 2092 |
+
"grad_norm": 0.130859375,
|
| 2093 |
+
"learning_rate": 3.7942066735321414e-07,
|
| 2094 |
+
"loss": 1.2608,
|
| 2095 |
+
"step": 1485
|
| 2096 |
+
},
|
| 2097 |
+
{
|
| 2098 |
+
"epoch": 0.9779208925989356,
|
| 2099 |
+
"grad_norm": 0.1318359375,
|
| 2100 |
+
"learning_rate": 2.861865621424431e-07,
|
| 2101 |
+
"loss": 1.2735,
|
| 2102 |
+
"step": 1490
|
| 2103 |
+
},
|
| 2104 |
+
{
|
| 2105 |
+
"epoch": 0.981202506332489,
|
| 2106 |
+
"grad_norm": 0.130859375,
|
| 2107 |
+
"learning_rate": 2.060608419105048e-07,
|
| 2108 |
+
"loss": 1.2788,
|
| 2109 |
+
"step": 1495
|
| 2110 |
+
},
|
| 2111 |
+
{
|
| 2112 |
+
"epoch": 0.9844841200660425,
|
| 2113 |
+
"grad_norm": 0.2451171875,
|
| 2114 |
+
"learning_rate": 1.3905403999024957e-07,
|
| 2115 |
+
"loss": 1.264,
|
| 2116 |
+
"step": 1500
|
| 2117 |
+
},
|
| 2118 |
+
{
|
| 2119 |
+
"epoch": 0.987765733799596,
|
| 2120 |
+
"grad_norm": 0.130859375,
|
| 2121 |
+
"learning_rate": 8.517496510059841e-08,
|
| 2122 |
+
"loss": 1.2673,
|
| 2123 |
+
"step": 1505
|
| 2124 |
+
},
|
| 2125 |
+
{
|
| 2126 |
+
"epoch": 0.9910473475331494,
|
| 2127 |
+
"grad_norm": 0.12890625,
|
| 2128 |
+
"learning_rate": 4.4430700188569095e-08,
|
| 2129 |
+
"loss": 1.2753,
|
| 2130 |
+
"step": 1510
|
| 2131 |
+
},
|
| 2132 |
+
{
|
| 2133 |
+
"epoch": 0.9943289612667029,
|
| 2134 |
+
"grad_norm": 0.130859375,
|
| 2135 |
+
"learning_rate": 1.6826601498098894e-08,
|
| 2136 |
+
"loss": 1.2567,
|
| 2137 |
+
"step": 1515
|
| 2138 |
+
},
|
| 2139 |
+
{
|
| 2140 |
+
"epoch": 0.9976105750002564,
|
| 2141 |
+
"grad_norm": 0.1337890625,
|
| 2142 |
+
"learning_rate": 2.3662978659633183e-09,
|
| 2143 |
+
"loss": 1.2568,
|
| 2144 |
+
"step": 1520
|
| 2145 |
+
},
|
| 2146 |
+
{
|
| 2147 |
+
"epoch": 0.9995795432403884,
|
| 2148 |
+
"eval_loss": 1.4362765550613403,
|
| 2149 |
+
"eval_runtime": 1174.833,
|
| 2150 |
+
"eval_samples_per_second": 12.068,
|
| 2151 |
+
"eval_steps_per_second": 12.068,
|
| 2152 |
+
"step": 1523
|
| 2153 |
+
},
|
| 2154 |
+
{
|
| 2155 |
+
"epoch": 0.9995795432403884,
|
| 2156 |
+
"step": 1523,
|
| 2157 |
+
"total_flos": 2.6010044317889987e+18,
|
| 2158 |
+
"train_loss": 1.1185581020360233,
|
| 2159 |
+
"train_runtime": 52635.226,
|
| 2160 |
+
"train_samples_per_second": 3.705,
|
| 2161 |
+
"train_steps_per_second": 0.029
|
| 2162 |
+
}
|
| 2163 |
+
],
|
| 2164 |
+
"logging_steps": 5,
|
| 2165 |
+
"max_steps": 1523,
|
| 2166 |
+
"num_input_tokens_seen": 0,
|
| 2167 |
+
"num_train_epochs": 1,
|
| 2168 |
+
"save_steps": 20,
|
| 2169 |
+
"total_flos": 2.6010044317889987e+18,
|
| 2170 |
+
"train_batch_size": 1,
|
| 2171 |
+
"trial_name": null,
|
| 2172 |
+
"trial_params": null
|
| 2173 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:49a5b07a8390176d99de8b393d805cca520f78c66ea718286e0390f5210c9daa
|
| 3 |
+
size 5112
|