Upload 14 files
Browse files- README.md +69 -0
- adapter_config.json +26 -0
- adapter_model.safetensors +3 -0
- all_results.json +11 -0
- eval_results.json +7 -0
- runs/Jan03_02-49-47_e0b4d469ca82/events.out.tfevents.1704250549.e0b4d469ca82.6302.0 +3 -0
- runs/Jan03_02-49-47_e0b4d469ca82/events.out.tfevents.1704254243.e0b4d469ca82.6302.1 +3 -0
- special_tokens_map.json +24 -0
- tokenizer.model +3 -0
- tokenizer_config.json +43 -0
- train_results.json +7 -0
- trainer_log.jsonl +143 -0
- trainer_state.json +888 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,69 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: other
|
| 3 |
+
library_name: peft
|
| 4 |
+
tags:
|
| 5 |
+
- llama-factory
|
| 6 |
+
- lora
|
| 7 |
+
- generated_from_trainer
|
| 8 |
+
base_model: meta-llama/Llama-2-13b-hf
|
| 9 |
+
model-index:
|
| 10 |
+
- name: train_2024-01-03-02-43-22
|
| 11 |
+
results: []
|
| 12 |
+
---
|
| 13 |
+
|
| 14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 15 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 16 |
+
|
| 17 |
+
# train_2024-01-03-02-43-22
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [meta-llama/Llama-2-13b-hf](https://huggingface.co/meta-llama/Llama-2-13b-hf) on the anli_train_r1_contradiction dataset.
|
| 20 |
+
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 1.0611
|
| 22 |
+
|
| 23 |
+
## Model description
|
| 24 |
+
|
| 25 |
+
More information needed
|
| 26 |
+
|
| 27 |
+
## Intended uses & limitations
|
| 28 |
+
|
| 29 |
+
More information needed
|
| 30 |
+
|
| 31 |
+
## Training and evaluation data
|
| 32 |
+
|
| 33 |
+
More information needed
|
| 34 |
+
|
| 35 |
+
## Training procedure
|
| 36 |
+
|
| 37 |
+
### Training hyperparameters
|
| 38 |
+
|
| 39 |
+
The following hyperparameters were used during training:
|
| 40 |
+
- learning_rate: 0.0002
|
| 41 |
+
- train_batch_size: 4
|
| 42 |
+
- eval_batch_size: 8
|
| 43 |
+
- seed: 42
|
| 44 |
+
- gradient_accumulation_steps: 4
|
| 45 |
+
- total_train_batch_size: 16
|
| 46 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 47 |
+
- lr_scheduler_type: cosine
|
| 48 |
+
- num_epochs: 3.0
|
| 49 |
+
- mixed_precision_training: Native AMP
|
| 50 |
+
|
| 51 |
+
### Training results
|
| 52 |
+
|
| 53 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 54 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
| 55 |
+
| 1.0228 | 0.44 | 100 | 1.0888 |
|
| 56 |
+
| 1.0068 | 0.88 | 200 | 1.0738 |
|
| 57 |
+
| 1.0218 | 1.33 | 300 | 1.0680 |
|
| 58 |
+
| 1.084 | 1.77 | 400 | 1.0611 |
|
| 59 |
+
| 0.897 | 2.21 | 500 | 1.0757 |
|
| 60 |
+
| 0.9597 | 2.65 | 600 | 1.0745 |
|
| 61 |
+
|
| 62 |
+
|
| 63 |
+
### Framework versions
|
| 64 |
+
|
| 65 |
+
- PEFT 0.7.1
|
| 66 |
+
- Transformers 4.36.2
|
| 67 |
+
- Pytorch 2.1.0+cu121
|
| 68 |
+
- Datasets 2.16.1
|
| 69 |
+
- Tokenizers 0.15.0
|
adapter_config.json
ADDED
|
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "meta-llama/Llama-2-13b-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": 0.1,
|
| 14 |
+
"megatron_config": null,
|
| 15 |
+
"megatron_core": "megatron.core",
|
| 16 |
+
"modules_to_save": null,
|
| 17 |
+
"peft_type": "LORA",
|
| 18 |
+
"r": 8,
|
| 19 |
+
"rank_pattern": {},
|
| 20 |
+
"revision": null,
|
| 21 |
+
"target_modules": [
|
| 22 |
+
"q_proj",
|
| 23 |
+
"v_proj"
|
| 24 |
+
],
|
| 25 |
+
"task_type": "CAUSAL_LM"
|
| 26 |
+
}
|
adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a0b4a88864c3ffdd465afcd0fa14bfae2014a6052f2bfa8bcaca0dab78b73038
|
| 3 |
+
size 26235704
|
all_results.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"eval_loss": 1.061107873916626,
|
| 4 |
+
"eval_runtime": 75.5544,
|
| 5 |
+
"eval_samples_per_second": 11.978,
|
| 6 |
+
"eval_steps_per_second": 1.509,
|
| 7 |
+
"train_loss": 0.9757168982232918,
|
| 8 |
+
"train_runtime": 3618.1154,
|
| 9 |
+
"train_samples_per_second": 3.0,
|
| 10 |
+
"train_steps_per_second": 0.187
|
| 11 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"eval_loss": 1.061107873916626,
|
| 4 |
+
"eval_runtime": 75.5544,
|
| 5 |
+
"eval_samples_per_second": 11.978,
|
| 6 |
+
"eval_steps_per_second": 1.509
|
| 7 |
+
}
|
runs/Jan03_02-49-47_e0b4d469ca82/events.out.tfevents.1704250549.e0b4d469ca82.6302.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6d8c4a061277a2ed1ffb875cb0d3aa2ad94293cad56e66e1c1895e4c9440b13d
|
| 3 |
+
size 28118
|
runs/Jan03_02-49-47_e0b4d469ca82/events.out.tfevents.1704254243.e0b4d469ca82.6302.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:81d5427d69571f52d9cdfa6b8517f0ef08f432552f02dfebcce14572caa4a22c
|
| 3 |
+
size 359
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "</s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": "</s>",
|
| 17 |
+
"unk_token": {
|
| 18 |
+
"content": "<unk>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
}
|
| 24 |
+
}
|
tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
| 3 |
+
size 499723
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"0": {
|
| 6 |
+
"content": "<unk>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"1": {
|
| 14 |
+
"content": "<s>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"2": {
|
| 22 |
+
"content": "</s>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
}
|
| 29 |
+
},
|
| 30 |
+
"bos_token": "<s>",
|
| 31 |
+
"clean_up_tokenization_spaces": false,
|
| 32 |
+
"eos_token": "</s>",
|
| 33 |
+
"legacy": false,
|
| 34 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 35 |
+
"pad_token": "</s>",
|
| 36 |
+
"padding_side": "right",
|
| 37 |
+
"sp_model_kwargs": {},
|
| 38 |
+
"spaces_between_special_tokens": false,
|
| 39 |
+
"split_special_tokens": false,
|
| 40 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 41 |
+
"unk_token": "<unk>",
|
| 42 |
+
"use_default_system_prompt": false
|
| 43 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"train_loss": 0.9757168982232918,
|
| 4 |
+
"train_runtime": 3618.1154,
|
| 5 |
+
"train_samples_per_second": 3.0,
|
| 6 |
+
"train_steps_per_second": 0.187
|
| 7 |
+
}
|
trainer_log.jsonl
ADDED
|
@@ -0,0 +1,143 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{"current_steps": 5, "total_steps": 678, "loss": 1.4828, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00019997316318671806, "epoch": 0.02, "percentage": 0.74, "elapsed_time": "0:00:25", "remaining_time": "0:56:40"}
|
| 2 |
+
{"current_steps": 10, "total_steps": 678, "loss": 1.1204, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00019989266715116316, "epoch": 0.04, "percentage": 1.47, "elapsed_time": "0:00:48", "remaining_time": "0:54:07"}
|
| 3 |
+
{"current_steps": 15, "total_steps": 678, "loss": 1.1449, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00019975855509847686, "epoch": 0.07, "percentage": 2.21, "elapsed_time": "0:01:12", "remaining_time": "0:53:13"}
|
| 4 |
+
{"current_steps": 20, "total_steps": 678, "loss": 1.1126, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00019957089901146148, "epoch": 0.09, "percentage": 2.95, "elapsed_time": "0:01:35", "remaining_time": "0:52:15"}
|
| 5 |
+
{"current_steps": 25, "total_steps": 678, "loss": 1.1048, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00019932979961194435, "epoch": 0.11, "percentage": 3.69, "elapsed_time": "0:01:59", "remaining_time": "0:51:50"}
|
| 6 |
+
{"current_steps": 30, "total_steps": 678, "loss": 1.2161, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0001990353863067169, "epoch": 0.13, "percentage": 4.42, "elapsed_time": "0:02:22", "remaining_time": "0:51:11"}
|
| 7 |
+
{"current_steps": 35, "total_steps": 678, "loss": 1.0051, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00019868781711807705, "epoch": 0.15, "percentage": 5.16, "elapsed_time": "0:02:45", "remaining_time": "0:50:37"}
|
| 8 |
+
{"current_steps": 40, "total_steps": 678, "loss": 1.0314, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00019828727859901317, "epoch": 0.18, "percentage": 5.9, "elapsed_time": "0:03:08", "remaining_time": "0:50:12"}
|
| 9 |
+
{"current_steps": 45, "total_steps": 678, "loss": 1.0718, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00019783398573307428, "epoch": 0.2, "percentage": 6.64, "elapsed_time": "0:03:32", "remaining_time": "0:49:46"}
|
| 10 |
+
{"current_steps": 50, "total_steps": 678, "loss": 1.1571, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00019732818181898045, "epoch": 0.22, "percentage": 7.37, "elapsed_time": "0:03:55", "remaining_time": "0:49:14"}
|
| 11 |
+
{"current_steps": 55, "total_steps": 678, "loss": 1.0602, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0001967701383400357, "epoch": 0.24, "percentage": 8.11, "elapsed_time": "0:04:18", "remaining_time": "0:48:45"}
|
| 12 |
+
{"current_steps": 60, "total_steps": 678, "loss": 1.1215, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0001961601548184129, "epoch": 0.27, "percentage": 8.85, "elapsed_time": "0:04:41", "remaining_time": "0:48:20"}
|
| 13 |
+
{"current_steps": 65, "total_steps": 678, "loss": 1.1434, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00019549855865438965, "epoch": 0.29, "percentage": 9.59, "elapsed_time": "0:05:05", "remaining_time": "0:47:56"}
|
| 14 |
+
{"current_steps": 70, "total_steps": 678, "loss": 1.0844, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00019478570495062037, "epoch": 0.31, "percentage": 10.32, "elapsed_time": "0:05:28", "remaining_time": "0:47:34"}
|
| 15 |
+
{"current_steps": 75, "total_steps": 678, "loss": 1.1123, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00019402197632153992, "epoch": 0.33, "percentage": 11.06, "elapsed_time": "0:05:51", "remaining_time": "0:47:07"}
|
| 16 |
+
{"current_steps": 80, "total_steps": 678, "loss": 1.1054, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00019320778268800066, "epoch": 0.35, "percentage": 11.8, "elapsed_time": "0:06:14", "remaining_time": "0:46:42"}
|
| 17 |
+
{"current_steps": 85, "total_steps": 678, "loss": 1.0368, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00019234356105725297, "epoch": 0.38, "percentage": 12.54, "elapsed_time": "0:06:38", "remaining_time": "0:46:19"}
|
| 18 |
+
{"current_steps": 90, "total_steps": 678, "loss": 1.1195, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00019142977528838762, "epoch": 0.4, "percentage": 13.27, "elapsed_time": "0:07:01", "remaining_time": "0:45:53"}
|
| 19 |
+
{"current_steps": 95, "total_steps": 678, "loss": 1.0778, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00019046691584336577, "epoch": 0.42, "percentage": 14.01, "elapsed_time": "0:07:24", "remaining_time": "0:45:27"}
|
| 20 |
+
{"current_steps": 100, "total_steps": 678, "loss": 1.0228, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0001894554995237703, "epoch": 0.44, "percentage": 14.75, "elapsed_time": "0:07:47", "remaining_time": "0:45:01"}
|
| 21 |
+
{"current_steps": 100, "total_steps": 678, "loss": null, "eval_loss": 1.0887844562530518, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.44, "percentage": 14.75, "elapsed_time": "0:07:47", "remaining_time": "0:45:01"}
|
| 22 |
+
{"current_steps": 105, "total_steps": 678, "loss": 1.1156, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0001883960691934196, "epoch": 0.46, "percentage": 15.49, "elapsed_time": "0:09:26", "remaining_time": "0:51:31"}
|
| 23 |
+
{"current_steps": 110, "total_steps": 678, "loss": 1.0259, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00018728919348699283, "epoch": 0.49, "percentage": 16.22, "elapsed_time": "0:09:49", "remaining_time": "0:50:44"}
|
| 24 |
+
{"current_steps": 115, "total_steps": 678, "loss": 1.0112, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00018613546650482322, "epoch": 0.51, "percentage": 16.96, "elapsed_time": "0:10:12", "remaining_time": "0:49:59"}
|
| 25 |
+
{"current_steps": 120, "total_steps": 678, "loss": 1.0279, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00018493550749402278, "epoch": 0.53, "percentage": 17.7, "elapsed_time": "0:10:35", "remaining_time": "0:49:15"}
|
| 26 |
+
{"current_steps": 125, "total_steps": 678, "loss": 1.105, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00018368996051610986, "epoch": 0.55, "percentage": 18.44, "elapsed_time": "0:10:58", "remaining_time": "0:48:33"}
|
| 27 |
+
{"current_steps": 130, "total_steps": 678, "loss": 1.041, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00018239949410131802, "epoch": 0.57, "percentage": 19.17, "elapsed_time": "0:11:22", "remaining_time": "0:47:57"}
|
| 28 |
+
{"current_steps": 135, "total_steps": 678, "loss": 1.0475, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00018106480088977172, "epoch": 0.6, "percentage": 19.91, "elapsed_time": "0:11:45", "remaining_time": "0:47:17"}
|
| 29 |
+
{"current_steps": 140, "total_steps": 678, "loss": 1.0241, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00017968659725972112, "epoch": 0.62, "percentage": 20.65, "elapsed_time": "0:12:08", "remaining_time": "0:46:40"}
|
| 30 |
+
{"current_steps": 145, "total_steps": 678, "loss": 1.0071, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00017826562294303585, "epoch": 0.64, "percentage": 21.39, "elapsed_time": "0:12:32", "remaining_time": "0:46:06"}
|
| 31 |
+
{"current_steps": 150, "total_steps": 678, "loss": 0.9714, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0001768026406281642, "epoch": 0.66, "percentage": 22.12, "elapsed_time": "0:12:55", "remaining_time": "0:45:31"}
|
| 32 |
+
{"current_steps": 155, "total_steps": 678, "loss": 1.0376, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00017529843555077066, "epoch": 0.69, "percentage": 22.86, "elapsed_time": "0:13:19", "remaining_time": "0:44:58"}
|
| 33 |
+
{"current_steps": 160, "total_steps": 678, "loss": 0.9806, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00017375381507227108, "epoch": 0.71, "percentage": 23.6, "elapsed_time": "0:13:43", "remaining_time": "0:44:26"}
|
| 34 |
+
{"current_steps": 165, "total_steps": 678, "loss": 1.1022, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00017216960824649303, "epoch": 0.73, "percentage": 24.34, "elapsed_time": "0:14:07", "remaining_time": "0:43:53"}
|
| 35 |
+
{"current_steps": 170, "total_steps": 678, "loss": 0.9723, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00017054666537469213, "epoch": 0.75, "percentage": 25.07, "elapsed_time": "0:14:31", "remaining_time": "0:43:22"}
|
| 36 |
+
{"current_steps": 175, "total_steps": 678, "loss": 1.1081, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00016888585754916476, "epoch": 0.77, "percentage": 25.81, "elapsed_time": "0:14:54", "remaining_time": "0:42:51"}
|
| 37 |
+
{"current_steps": 180, "total_steps": 678, "loss": 1.0525, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00016718807618570106, "epoch": 0.8, "percentage": 26.55, "elapsed_time": "0:15:17", "remaining_time": "0:42:18"}
|
| 38 |
+
{"current_steps": 185, "total_steps": 678, "loss": 1.0761, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00016545423254513004, "epoch": 0.82, "percentage": 27.29, "elapsed_time": "0:15:41", "remaining_time": "0:41:47"}
|
| 39 |
+
{"current_steps": 190, "total_steps": 678, "loss": 1.1493, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00016368525724421248, "epoch": 0.84, "percentage": 28.02, "elapsed_time": "0:16:03", "remaining_time": "0:41:15"}
|
| 40 |
+
{"current_steps": 195, "total_steps": 678, "loss": 0.9942, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00016188209975614542, "epoch": 0.86, "percentage": 28.76, "elapsed_time": "0:16:27", "remaining_time": "0:40:45"}
|
| 41 |
+
{"current_steps": 200, "total_steps": 678, "loss": 1.0068, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00016004572790094535, "epoch": 0.88, "percentage": 29.5, "elapsed_time": "0:16:50", "remaining_time": "0:40:14"}
|
| 42 |
+
{"current_steps": 200, "total_steps": 678, "loss": null, "eval_loss": 1.0737706422805786, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.88, "percentage": 29.5, "elapsed_time": "0:16:50", "remaining_time": "0:40:14"}
|
| 43 |
+
{"current_steps": 205, "total_steps": 678, "loss": 1.0579, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00015817712732598413, "epoch": 0.91, "percentage": 30.24, "elapsed_time": "0:18:28", "remaining_time": "0:42:38"}
|
| 44 |
+
{"current_steps": 210, "total_steps": 678, "loss": 1.0985, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00015627730097695638, "epoch": 0.93, "percentage": 30.97, "elapsed_time": "0:18:52", "remaining_time": "0:42:02"}
|
| 45 |
+
{"current_steps": 215, "total_steps": 678, "loss": 1.071, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00015434726855956206, "epoch": 0.95, "percentage": 31.71, "elapsed_time": "0:19:15", "remaining_time": "0:41:28"}
|
| 46 |
+
{"current_steps": 220, "total_steps": 678, "loss": 1.0617, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00015238806599219336, "epoch": 0.97, "percentage": 32.45, "elapsed_time": "0:19:38", "remaining_time": "0:40:53"}
|
| 47 |
+
{"current_steps": 225, "total_steps": 678, "loss": 0.9789, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00015040074484992, "epoch": 0.99, "percentage": 33.19, "elapsed_time": "0:20:01", "remaining_time": "0:40:18"}
|
| 48 |
+
{"current_steps": 230, "total_steps": 678, "loss": 1.072, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00014838637180007047, "epoch": 1.02, "percentage": 33.92, "elapsed_time": "0:20:24", "remaining_time": "0:39:44"}
|
| 49 |
+
{"current_steps": 235, "total_steps": 678, "loss": 1.0098, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00014634602802971312, "epoch": 1.04, "percentage": 34.66, "elapsed_time": "0:20:47", "remaining_time": "0:39:12"}
|
| 50 |
+
{"current_steps": 240, "total_steps": 678, "loss": 1.0222, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00014428080866534396, "epoch": 1.06, "percentage": 35.4, "elapsed_time": "0:21:11", "remaining_time": "0:38:40"}
|
| 51 |
+
{"current_steps": 245, "total_steps": 678, "loss": 0.9734, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0001421918221850923, "epoch": 1.08, "percentage": 36.14, "elapsed_time": "0:21:34", "remaining_time": "0:38:08"}
|
| 52 |
+
{"current_steps": 250, "total_steps": 678, "loss": 0.9364, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00014008018982376044, "epoch": 1.1, "percentage": 36.87, "elapsed_time": "0:21:57", "remaining_time": "0:37:36"}
|
| 53 |
+
{"current_steps": 255, "total_steps": 678, "loss": 0.9735, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00013794704497101655, "epoch": 1.13, "percentage": 37.61, "elapsed_time": "0:22:21", "remaining_time": "0:37:04"}
|
| 54 |
+
{"current_steps": 260, "total_steps": 678, "loss": 1.0933, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00013579353256306287, "epoch": 1.15, "percentage": 38.35, "elapsed_time": "0:22:44", "remaining_time": "0:36:33"}
|
| 55 |
+
{"current_steps": 265, "total_steps": 678, "loss": 0.9764, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00013362080846810725, "epoch": 1.17, "percentage": 39.09, "elapsed_time": "0:23:07", "remaining_time": "0:36:03"}
|
| 56 |
+
{"current_steps": 270, "total_steps": 678, "loss": 1.0584, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00013143003886596669, "epoch": 1.19, "percentage": 39.82, "elapsed_time": "0:23:32", "remaining_time": "0:35:34"}
|
| 57 |
+
{"current_steps": 275, "total_steps": 678, "loss": 0.9116, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00012922239962213637, "epoch": 1.22, "percentage": 40.56, "elapsed_time": "0:23:55", "remaining_time": "0:35:04"}
|
| 58 |
+
{"current_steps": 280, "total_steps": 678, "loss": 1.0587, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00012699907565665982, "epoch": 1.24, "percentage": 41.3, "elapsed_time": "0:24:18", "remaining_time": "0:34:33"}
|
| 59 |
+
{"current_steps": 285, "total_steps": 678, "loss": 0.9342, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00012476126030813963, "epoch": 1.26, "percentage": 42.04, "elapsed_time": "0:24:41", "remaining_time": "0:34:02"}
|
| 60 |
+
{"current_steps": 290, "total_steps": 678, "loss": 0.9826, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00012251015469322916, "epoch": 1.28, "percentage": 42.77, "elapsed_time": "0:25:05", "remaining_time": "0:33:33"}
|
| 61 |
+
{"current_steps": 295, "total_steps": 678, "loss": 1.0656, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00012024696706194967, "epoch": 1.3, "percentage": 43.51, "elapsed_time": "0:25:28", "remaining_time": "0:33:04"}
|
| 62 |
+
{"current_steps": 300, "total_steps": 678, "loss": 1.0218, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00011797291214917881, "epoch": 1.33, "percentage": 44.25, "elapsed_time": "0:25:51", "remaining_time": "0:32:35"}
|
| 63 |
+
{"current_steps": 300, "total_steps": 678, "loss": null, "eval_loss": 1.06796395778656, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.33, "percentage": 44.25, "elapsed_time": "0:25:51", "remaining_time": "0:32:35"}
|
| 64 |
+
{"current_steps": 305, "total_steps": 678, "loss": 0.9915, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00011568921052265836, "epoch": 1.35, "percentage": 44.99, "elapsed_time": "0:27:30", "remaining_time": "0:33:38"}
|
| 65 |
+
{"current_steps": 310, "total_steps": 678, "loss": 0.9592, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00011339708792787119, "epoch": 1.37, "percentage": 45.72, "elapsed_time": "0:27:54", "remaining_time": "0:33:07"}
|
| 66 |
+
{"current_steps": 315, "total_steps": 678, "loss": 0.9875, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00011109777463013915, "epoch": 1.39, "percentage": 46.46, "elapsed_time": "0:28:17", "remaining_time": "0:32:36"}
|
| 67 |
+
{"current_steps": 320, "total_steps": 678, "loss": 1.1583, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00010879250475429523, "epoch": 1.41, "percentage": 47.2, "elapsed_time": "0:28:40", "remaining_time": "0:32:04"}
|
| 68 |
+
{"current_steps": 325, "total_steps": 678, "loss": 0.977, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00010648251562228386, "epoch": 1.44, "percentage": 47.94, "elapsed_time": "0:29:03", "remaining_time": "0:31:34"}
|
| 69 |
+
{"current_steps": 330, "total_steps": 678, "loss": 1.041, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00010416904708904548, "epoch": 1.46, "percentage": 48.67, "elapsed_time": "0:29:27", "remaining_time": "0:31:03"}
|
| 70 |
+
{"current_steps": 335, "total_steps": 678, "loss": 0.972, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00010185334087704124, "epoch": 1.48, "percentage": 49.41, "elapsed_time": "0:29:50", "remaining_time": "0:30:33"}
|
| 71 |
+
{"current_steps": 340, "total_steps": 678, "loss": 1.0115, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.953663990977568e-05, "epoch": 1.5, "percentage": 50.15, "elapsed_time": "0:30:14", "remaining_time": "0:30:03"}
|
| 72 |
+
{"current_steps": 345, "total_steps": 678, "loss": 1.0078, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.722018764467461e-05, "epoch": 1.52, "percentage": 50.88, "elapsed_time": "0:30:38", "remaining_time": "0:29:34"}
|
| 73 |
+
{"current_steps": 350, "total_steps": 678, "loss": 0.955, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.490522740567633e-05, "epoch": 1.55, "percentage": 51.62, "elapsed_time": "0:31:00", "remaining_time": "0:29:03"}
|
| 74 |
+
{"current_steps": 355, "total_steps": 678, "loss": 0.9719, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.259300171589456e-05, "epoch": 1.57, "percentage": 52.36, "elapsed_time": "0:31:23", "remaining_time": "0:28:34"}
|
| 75 |
+
{"current_steps": 360, "total_steps": 678, "loss": 0.871, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.028475163071141e-05, "epoch": 1.59, "percentage": 53.1, "elapsed_time": "0:31:47", "remaining_time": "0:28:04"}
|
| 76 |
+
{"current_steps": 365, "total_steps": 678, "loss": 0.9568, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.798171607165778e-05, "epoch": 1.61, "percentage": 53.83, "elapsed_time": "0:32:10", "remaining_time": "0:27:35"}
|
| 77 |
+
{"current_steps": 370, "total_steps": 678, "loss": 0.9466, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.568513116143919e-05, "epoch": 1.64, "percentage": 54.57, "elapsed_time": "0:32:34", "remaining_time": "0:27:06"}
|
| 78 |
+
{"current_steps": 375, "total_steps": 678, "loss": 0.8967, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.339622956046417e-05, "epoch": 1.66, "percentage": 55.31, "elapsed_time": "0:32:57", "remaining_time": "0:26:38"}
|
| 79 |
+
{"current_steps": 380, "total_steps": 678, "loss": 0.9465, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.111623980523035e-05, "epoch": 1.68, "percentage": 56.05, "elapsed_time": "0:33:21", "remaining_time": "0:26:09"}
|
| 80 |
+
{"current_steps": 385, "total_steps": 678, "loss": 0.9499, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.884638564892472e-05, "epoch": 1.7, "percentage": 56.78, "elapsed_time": "0:33:44", "remaining_time": "0:25:40"}
|
| 81 |
+
{"current_steps": 390, "total_steps": 678, "loss": 0.8955, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.658788540459062e-05, "epoch": 1.72, "percentage": 57.52, "elapsed_time": "0:34:07", "remaining_time": "0:25:12"}
|
| 82 |
+
{"current_steps": 395, "total_steps": 678, "loss": 0.8982, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.434195129121518e-05, "epoch": 1.75, "percentage": 58.26, "elapsed_time": "0:34:31", "remaining_time": "0:24:44"}
|
| 83 |
+
{"current_steps": 400, "total_steps": 678, "loss": 1.084, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.210978878308729e-05, "epoch": 1.77, "percentage": 59.0, "elapsed_time": "0:34:54", "remaining_time": "0:24:16"}
|
| 84 |
+
{"current_steps": 400, "total_steps": 678, "loss": null, "eval_loss": 1.061107873916626, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.77, "percentage": 59.0, "elapsed_time": "0:34:54", "remaining_time": "0:24:16"}
|
| 85 |
+
{"current_steps": 405, "total_steps": 678, "loss": 0.8936, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.989259596277582e-05, "epoch": 1.79, "percentage": 59.73, "elapsed_time": "0:36:34", "remaining_time": "0:24:38"}
|
| 86 |
+
{"current_steps": 410, "total_steps": 678, "loss": 0.8794, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.76915628780754e-05, "epoch": 1.81, "percentage": 60.47, "elapsed_time": "0:36:57", "remaining_time": "0:24:09"}
|
| 87 |
+
{"current_steps": 415, "total_steps": 678, "loss": 0.9631, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.55078709032644e-05, "epoch": 1.83, "percentage": 61.21, "elapsed_time": "0:37:20", "remaining_time": "0:23:39"}
|
| 88 |
+
{"current_steps": 420, "total_steps": 678, "loss": 0.9636, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.334269210501875e-05, "epoch": 1.86, "percentage": 61.95, "elapsed_time": "0:37:43", "remaining_time": "0:23:10"}
|
| 89 |
+
{"current_steps": 425, "total_steps": 678, "loss": 0.9761, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.119718861332098e-05, "epoch": 1.88, "percentage": 62.68, "elapsed_time": "0:38:06", "remaining_time": "0:22:41"}
|
| 90 |
+
{"current_steps": 430, "total_steps": 678, "loss": 0.9732, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.9072511997703226e-05, "epoch": 1.9, "percentage": 63.42, "elapsed_time": "0:38:29", "remaining_time": "0:22:12"}
|
| 91 |
+
{"current_steps": 435, "total_steps": 678, "loss": 0.995, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.696980264915777e-05, "epoch": 1.92, "percentage": 64.16, "elapsed_time": "0:38:52", "remaining_time": "0:21:43"}
|
| 92 |
+
{"current_steps": 440, "total_steps": 678, "loss": 1.0037, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.489018916804813e-05, "epoch": 1.94, "percentage": 64.9, "elapsed_time": "0:39:16", "remaining_time": "0:21:14"}
|
| 93 |
+
{"current_steps": 445, "total_steps": 678, "loss": 0.8503, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.283478775834811e-05, "epoch": 1.97, "percentage": 65.63, "elapsed_time": "0:39:39", "remaining_time": "0:20:45"}
|
| 94 |
+
{"current_steps": 450, "total_steps": 678, "loss": 0.8914, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.080470162853472e-05, "epoch": 1.99, "percentage": 66.37, "elapsed_time": "0:40:02", "remaining_time": "0:20:17"}
|
| 95 |
+
{"current_steps": 455, "total_steps": 678, "loss": 0.9531, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.880102039945624e-05, "epoch": 2.01, "percentage": 67.11, "elapsed_time": "0:40:25", "remaining_time": "0:19:48"}
|
| 96 |
+
{"current_steps": 460, "total_steps": 678, "loss": 0.9294, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.6824819519493057e-05, "epoch": 2.03, "percentage": 67.85, "elapsed_time": "0:40:48", "remaining_time": "0:19:20"}
|
| 97 |
+
{"current_steps": 465, "total_steps": 678, "loss": 0.8584, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.487715968732568e-05, "epoch": 2.06, "percentage": 68.58, "elapsed_time": "0:41:12", "remaining_time": "0:18:52"}
|
| 98 |
+
{"current_steps": 470, "total_steps": 678, "loss": 0.9285, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.29590862826191e-05, "epoch": 2.08, "percentage": 69.32, "elapsed_time": "0:41:35", "remaining_time": "0:18:24"}
|
| 99 |
+
{"current_steps": 475, "total_steps": 678, "loss": 0.8742, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.107162880492984e-05, "epoch": 2.1, "percentage": 70.06, "elapsed_time": "0:41:59", "remaining_time": "0:17:56"}
|
| 100 |
+
{"current_steps": 480, "total_steps": 678, "loss": 0.7903, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.921580032113602e-05, "epoch": 2.12, "percentage": 70.8, "elapsed_time": "0:42:23", "remaining_time": "0:17:29"}
|
| 101 |
+
{"current_steps": 485, "total_steps": 678, "loss": 0.8287, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.739259692168764e-05, "epoch": 2.14, "percentage": 71.53, "elapsed_time": "0:42:46", "remaining_time": "0:17:01"}
|
| 102 |
+
{"current_steps": 490, "total_steps": 678, "loss": 0.8967, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.560299718596889e-05, "epoch": 2.17, "percentage": 72.27, "elapsed_time": "0:43:09", "remaining_time": "0:16:33"}
|
| 103 |
+
{"current_steps": 495, "total_steps": 678, "loss": 0.841, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.3847961657058845e-05, "epoch": 2.19, "percentage": 73.01, "elapsed_time": "0:43:32", "remaining_time": "0:16:05"}
|
| 104 |
+
{"current_steps": 500, "total_steps": 678, "loss": 0.897, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.212843232617343e-05, "epoch": 2.21, "percentage": 73.75, "elapsed_time": "0:43:56", "remaining_time": "0:15:38"}
|
| 105 |
+
{"current_steps": 500, "total_steps": 678, "loss": null, "eval_loss": 1.0756696462631226, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.21, "percentage": 73.75, "elapsed_time": "0:43:56", "remaining_time": "0:15:38"}
|
| 106 |
+
{"current_steps": 505, "total_steps": 678, "loss": 0.9455, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.0445332127064275e-05, "epoch": 2.23, "percentage": 74.48, "elapsed_time": "0:45:35", "remaining_time": "0:15:37"}
|
| 107 |
+
{"current_steps": 510, "total_steps": 678, "loss": 0.9292, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.879956444064703e-05, "epoch": 2.25, "percentage": 75.22, "elapsed_time": "0:45:58", "remaining_time": "0:15:08"}
|
| 108 |
+
{"current_steps": 515, "total_steps": 678, "loss": 0.9016, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.7192012610123774e-05, "epoch": 2.28, "percentage": 75.96, "elapsed_time": "0:46:22", "remaining_time": "0:14:40"}
|
| 109 |
+
{"current_steps": 520, "total_steps": 678, "loss": 0.937, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.5623539466860813e-05, "epoch": 2.3, "percentage": 76.7, "elapsed_time": "0:46:44", "remaining_time": "0:14:12"}
|
| 110 |
+
{"current_steps": 525, "total_steps": 678, "loss": 0.8348, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.409498686727587e-05, "epoch": 2.32, "percentage": 77.43, "elapsed_time": "0:47:07", "remaining_time": "0:13:44"}
|
| 111 |
+
{"current_steps": 530, "total_steps": 678, "loss": 0.8387, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.2607175240983026e-05, "epoch": 2.34, "percentage": 78.17, "elapsed_time": "0:47:31", "remaining_time": "0:13:16"}
|
| 112 |
+
{"current_steps": 535, "total_steps": 678, "loss": 0.7736, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.1160903150438605e-05, "epoch": 2.36, "percentage": 78.91, "elapsed_time": "0:47:55", "remaining_time": "0:12:48"}
|
| 113 |
+
{"current_steps": 540, "total_steps": 678, "loss": 0.8672, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.9756946862323535e-05, "epoch": 2.39, "percentage": 79.65, "elapsed_time": "0:48:18", "remaining_time": "0:12:20"}
|
| 114 |
+
{"current_steps": 545, "total_steps": 678, "loss": 0.8688, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.839605993089307e-05, "epoch": 2.41, "percentage": 80.38, "elapsed_time": "0:48:42", "remaining_time": "0:11:53"}
|
| 115 |
+
{"current_steps": 550, "total_steps": 678, "loss": 0.8631, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.707897279351671e-05, "epoch": 2.43, "percentage": 81.12, "elapsed_time": "0:49:06", "remaining_time": "0:11:25"}
|
| 116 |
+
{"current_steps": 555, "total_steps": 678, "loss": 0.9171, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.580639237862608e-05, "epoch": 2.45, "percentage": 81.86, "elapsed_time": "0:49:28", "remaining_time": "0:10:57"}
|
| 117 |
+
{"current_steps": 560, "total_steps": 678, "loss": 0.9134, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.4579001726280828e-05, "epoch": 2.48, "percentage": 82.6, "elapsed_time": "0:49:52", "remaining_time": "0:10:30"}
|
| 118 |
+
{"current_steps": 565, "total_steps": 678, "loss": 0.8363, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.339745962155613e-05, "epoch": 2.5, "percentage": 83.33, "elapsed_time": "0:50:16", "remaining_time": "0:10:03"}
|
| 119 |
+
{"current_steps": 570, "total_steps": 678, "loss": 0.8862, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.2262400240949023e-05, "epoch": 2.52, "percentage": 84.07, "elapsed_time": "0:50:38", "remaining_time": "0:09:35"}
|
| 120 |
+
{"current_steps": 575, "total_steps": 678, "loss": 0.9154, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.1174432811992685e-05, "epoch": 2.54, "percentage": 84.81, "elapsed_time": "0:51:02", "remaining_time": "0:09:08"}
|
| 121 |
+
{"current_steps": 580, "total_steps": 678, "loss": 0.9423, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.013414128626211e-05, "epoch": 2.56, "percentage": 85.55, "elapsed_time": "0:51:24", "remaining_time": "0:08:41"}
|
| 122 |
+
{"current_steps": 585, "total_steps": 678, "loss": 0.8462, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.142084025945984e-06, "epoch": 2.59, "percentage": 86.28, "elapsed_time": "0:51:48", "remaining_time": "0:08:14"}
|
| 123 |
+
{"current_steps": 590, "total_steps": 678, "loss": 0.8019, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.19879350415349e-06, "epoch": 2.61, "percentage": 87.02, "elapsed_time": "0:52:11", "remaining_time": "0:07:47"}
|
| 124 |
+
{"current_steps": 595, "total_steps": 678, "loss": 0.861, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.30477601911671e-06, "epoch": 2.63, "percentage": 87.76, "elapsed_time": "0:52:34", "remaining_time": "0:07:20"}
|
| 125 |
+
{"current_steps": 600, "total_steps": 678, "loss": 0.9597, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.460511422441984e-06, "epoch": 2.65, "percentage": 88.5, "elapsed_time": "0:52:57", "remaining_time": "0:06:53"}
|
| 126 |
+
{"current_steps": 600, "total_steps": 678, "loss": null, "eval_loss": 1.0745042562484741, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.65, "percentage": 88.5, "elapsed_time": "0:52:57", "remaining_time": "0:06:53"}
|
| 127 |
+
{"current_steps": 605, "total_steps": 678, "loss": 0.7797, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.66645286155616e-06, "epoch": 2.67, "percentage": 89.23, "elapsed_time": "0:54:36", "remaining_time": "0:06:35"}
|
| 128 |
+
{"current_steps": 610, "total_steps": 678, "loss": 0.9222, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.923026536485875e-06, "epoch": 2.7, "percentage": 89.97, "elapsed_time": "0:55:00", "remaining_time": "0:06:07"}
|
| 129 |
+
{"current_steps": 615, "total_steps": 678, "loss": 0.9732, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.230631471100655e-06, "epoch": 2.72, "percentage": 90.71, "elapsed_time": "0:55:23", "remaining_time": "0:05:40"}
|
| 130 |
+
{"current_steps": 620, "total_steps": 678, "loss": 0.7366, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.5896392989422377e-06, "epoch": 2.74, "percentage": 91.45, "elapsed_time": "0:55:47", "remaining_time": "0:05:13"}
|
| 131 |
+
{"current_steps": 625, "total_steps": 678, "loss": 0.9243, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.000394063755396e-06, "epoch": 2.76, "percentage": 92.18, "elapsed_time": "0:56:10", "remaining_time": "0:04:45"}
|
| 132 |
+
{"current_steps": 630, "total_steps": 678, "loss": 0.9263, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.4632120348272003e-06, "epoch": 2.78, "percentage": 92.92, "elapsed_time": "0:56:34", "remaining_time": "0:04:18"}
|
| 133 |
+
{"current_steps": 635, "total_steps": 678, "loss": 0.8541, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.9783815372338423e-06, "epoch": 2.81, "percentage": 93.66, "elapsed_time": "0:56:57", "remaining_time": "0:03:51"}
|
| 134 |
+
{"current_steps": 640, "total_steps": 678, "loss": 0.828, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.5461627970860814e-06, "epoch": 2.83, "percentage": 94.4, "elapsed_time": "0:57:21", "remaining_time": "0:03:24"}
|
| 135 |
+
{"current_steps": 645, "total_steps": 678, "loss": 0.8446, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.1667878018564171e-06, "epoch": 2.85, "percentage": 95.13, "elapsed_time": "0:57:45", "remaining_time": "0:02:57"}
|
| 136 |
+
{"current_steps": 650, "total_steps": 678, "loss": 0.7749, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.404601758630892e-07, "epoch": 2.87, "percentage": 95.87, "elapsed_time": "0:58:08", "remaining_time": "0:02:30"}
|
| 137 |
+
{"current_steps": 655, "total_steps": 678, "loss": 0.8738, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.673550709774267e-07, "epoch": 2.9, "percentage": 96.61, "elapsed_time": "0:58:32", "remaining_time": "0:02:03"}
|
| 138 |
+
{"current_steps": 660, "total_steps": 678, "loss": 0.895, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.4761907261356976e-07, "epoch": 2.92, "percentage": 97.35, "elapsed_time": "0:58:55", "remaining_time": "0:01:36"}
|
| 139 |
+
{"current_steps": 665, "total_steps": 678, "loss": 0.8552, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.813701210506946e-07, "epoch": 2.94, "percentage": 98.08, "elapsed_time": "0:59:18", "remaining_time": "0:01:09"}
|
| 140 |
+
{"current_steps": 670, "total_steps": 678, "loss": 0.8475, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.869744813023937e-08, "epoch": 2.96, "percentage": 98.82, "elapsed_time": "0:59:41", "remaining_time": "0:00:42"}
|
| 141 |
+
{"current_steps": 675, "total_steps": 678, "loss": 0.9076, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.661529361892907e-09, "epoch": 2.98, "percentage": 99.56, "elapsed_time": "1:00:04", "remaining_time": "0:00:16"}
|
| 142 |
+
{"current_steps": 678, "total_steps": 678, "loss": null, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "1:00:18", "remaining_time": "0:00:00"}
|
| 143 |
+
{"current_steps": 114, "total_steps": 114, "loss": null, "eval_loss": 1.061107873916626, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "1:01:33", "remaining_time": "0:00:00"}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,888 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 1.061107873916626,
|
| 3 |
+
"best_model_checkpoint": "saves/LLaMA2-13B/lora/train_2024-01-03-02-43-22/checkpoint-400",
|
| 4 |
+
"epoch": 2.9966850828729283,
|
| 5 |
+
"eval_steps": 100,
|
| 6 |
+
"global_step": 678,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.02,
|
| 13 |
+
"learning_rate": 0.00019997316318671806,
|
| 14 |
+
"loss": 1.4828,
|
| 15 |
+
"step": 5
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.04,
|
| 19 |
+
"learning_rate": 0.00019989266715116316,
|
| 20 |
+
"loss": 1.1204,
|
| 21 |
+
"step": 10
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.07,
|
| 25 |
+
"learning_rate": 0.00019975855509847686,
|
| 26 |
+
"loss": 1.1449,
|
| 27 |
+
"step": 15
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.09,
|
| 31 |
+
"learning_rate": 0.00019957089901146148,
|
| 32 |
+
"loss": 1.1126,
|
| 33 |
+
"step": 20
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.11,
|
| 37 |
+
"learning_rate": 0.00019932979961194435,
|
| 38 |
+
"loss": 1.1048,
|
| 39 |
+
"step": 25
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.13,
|
| 43 |
+
"learning_rate": 0.0001990353863067169,
|
| 44 |
+
"loss": 1.2161,
|
| 45 |
+
"step": 30
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.15,
|
| 49 |
+
"learning_rate": 0.00019868781711807705,
|
| 50 |
+
"loss": 1.0051,
|
| 51 |
+
"step": 35
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.18,
|
| 55 |
+
"learning_rate": 0.00019828727859901317,
|
| 56 |
+
"loss": 1.0314,
|
| 57 |
+
"step": 40
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.2,
|
| 61 |
+
"learning_rate": 0.00019783398573307428,
|
| 62 |
+
"loss": 1.0718,
|
| 63 |
+
"step": 45
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.22,
|
| 67 |
+
"learning_rate": 0.00019732818181898045,
|
| 68 |
+
"loss": 1.1571,
|
| 69 |
+
"step": 50
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.24,
|
| 73 |
+
"learning_rate": 0.0001967701383400357,
|
| 74 |
+
"loss": 1.0602,
|
| 75 |
+
"step": 55
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.27,
|
| 79 |
+
"learning_rate": 0.0001961601548184129,
|
| 80 |
+
"loss": 1.1215,
|
| 81 |
+
"step": 60
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.29,
|
| 85 |
+
"learning_rate": 0.00019549855865438965,
|
| 86 |
+
"loss": 1.1434,
|
| 87 |
+
"step": 65
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.31,
|
| 91 |
+
"learning_rate": 0.00019478570495062037,
|
| 92 |
+
"loss": 1.0844,
|
| 93 |
+
"step": 70
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.33,
|
| 97 |
+
"learning_rate": 0.00019402197632153992,
|
| 98 |
+
"loss": 1.1123,
|
| 99 |
+
"step": 75
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.35,
|
| 103 |
+
"learning_rate": 0.00019320778268800066,
|
| 104 |
+
"loss": 1.1054,
|
| 105 |
+
"step": 80
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.38,
|
| 109 |
+
"learning_rate": 0.00019234356105725297,
|
| 110 |
+
"loss": 1.0368,
|
| 111 |
+
"step": 85
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 0.4,
|
| 115 |
+
"learning_rate": 0.00019142977528838762,
|
| 116 |
+
"loss": 1.1195,
|
| 117 |
+
"step": 90
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 0.42,
|
| 121 |
+
"learning_rate": 0.00019046691584336577,
|
| 122 |
+
"loss": 1.0778,
|
| 123 |
+
"step": 95
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.44,
|
| 127 |
+
"learning_rate": 0.0001894554995237703,
|
| 128 |
+
"loss": 1.0228,
|
| 129 |
+
"step": 100
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.44,
|
| 133 |
+
"eval_loss": 1.0887844562530518,
|
| 134 |
+
"eval_runtime": 75.527,
|
| 135 |
+
"eval_samples_per_second": 11.982,
|
| 136 |
+
"eval_steps_per_second": 1.509,
|
| 137 |
+
"step": 100
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 0.46,
|
| 141 |
+
"learning_rate": 0.0001883960691934196,
|
| 142 |
+
"loss": 1.1156,
|
| 143 |
+
"step": 105
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.49,
|
| 147 |
+
"learning_rate": 0.00018728919348699283,
|
| 148 |
+
"loss": 1.0259,
|
| 149 |
+
"step": 110
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.51,
|
| 153 |
+
"learning_rate": 0.00018613546650482322,
|
| 154 |
+
"loss": 1.0112,
|
| 155 |
+
"step": 115
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 0.53,
|
| 159 |
+
"learning_rate": 0.00018493550749402278,
|
| 160 |
+
"loss": 1.0279,
|
| 161 |
+
"step": 120
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 0.55,
|
| 165 |
+
"learning_rate": 0.00018368996051610986,
|
| 166 |
+
"loss": 1.105,
|
| 167 |
+
"step": 125
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 0.57,
|
| 171 |
+
"learning_rate": 0.00018239949410131802,
|
| 172 |
+
"loss": 1.041,
|
| 173 |
+
"step": 130
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 0.6,
|
| 177 |
+
"learning_rate": 0.00018106480088977172,
|
| 178 |
+
"loss": 1.0475,
|
| 179 |
+
"step": 135
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 0.62,
|
| 183 |
+
"learning_rate": 0.00017968659725972112,
|
| 184 |
+
"loss": 1.0241,
|
| 185 |
+
"step": 140
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.64,
|
| 189 |
+
"learning_rate": 0.00017826562294303585,
|
| 190 |
+
"loss": 1.0071,
|
| 191 |
+
"step": 145
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.66,
|
| 195 |
+
"learning_rate": 0.0001768026406281642,
|
| 196 |
+
"loss": 0.9714,
|
| 197 |
+
"step": 150
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 0.69,
|
| 201 |
+
"learning_rate": 0.00017529843555077066,
|
| 202 |
+
"loss": 1.0376,
|
| 203 |
+
"step": 155
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 0.71,
|
| 207 |
+
"learning_rate": 0.00017375381507227108,
|
| 208 |
+
"loss": 0.9806,
|
| 209 |
+
"step": 160
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 0.73,
|
| 213 |
+
"learning_rate": 0.00017216960824649303,
|
| 214 |
+
"loss": 1.1022,
|
| 215 |
+
"step": 165
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 0.75,
|
| 219 |
+
"learning_rate": 0.00017054666537469213,
|
| 220 |
+
"loss": 0.9723,
|
| 221 |
+
"step": 170
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 0.77,
|
| 225 |
+
"learning_rate": 0.00016888585754916476,
|
| 226 |
+
"loss": 1.1081,
|
| 227 |
+
"step": 175
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.8,
|
| 231 |
+
"learning_rate": 0.00016718807618570106,
|
| 232 |
+
"loss": 1.0525,
|
| 233 |
+
"step": 180
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.82,
|
| 237 |
+
"learning_rate": 0.00016545423254513004,
|
| 238 |
+
"loss": 1.0761,
|
| 239 |
+
"step": 185
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 0.84,
|
| 243 |
+
"learning_rate": 0.00016368525724421248,
|
| 244 |
+
"loss": 1.1493,
|
| 245 |
+
"step": 190
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 0.86,
|
| 249 |
+
"learning_rate": 0.00016188209975614542,
|
| 250 |
+
"loss": 0.9942,
|
| 251 |
+
"step": 195
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 0.88,
|
| 255 |
+
"learning_rate": 0.00016004572790094535,
|
| 256 |
+
"loss": 1.0068,
|
| 257 |
+
"step": 200
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 0.88,
|
| 261 |
+
"eval_loss": 1.0737706422805786,
|
| 262 |
+
"eval_runtime": 75.4895,
|
| 263 |
+
"eval_samples_per_second": 11.988,
|
| 264 |
+
"eval_steps_per_second": 1.51,
|
| 265 |
+
"step": 200
|
| 266 |
+
},
|
| 267 |
+
{
|
| 268 |
+
"epoch": 0.91,
|
| 269 |
+
"learning_rate": 0.00015817712732598413,
|
| 270 |
+
"loss": 1.0579,
|
| 271 |
+
"step": 205
|
| 272 |
+
},
|
| 273 |
+
{
|
| 274 |
+
"epoch": 0.93,
|
| 275 |
+
"learning_rate": 0.00015627730097695638,
|
| 276 |
+
"loss": 1.0985,
|
| 277 |
+
"step": 210
|
| 278 |
+
},
|
| 279 |
+
{
|
| 280 |
+
"epoch": 0.95,
|
| 281 |
+
"learning_rate": 0.00015434726855956206,
|
| 282 |
+
"loss": 1.071,
|
| 283 |
+
"step": 215
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.97,
|
| 287 |
+
"learning_rate": 0.00015238806599219336,
|
| 288 |
+
"loss": 1.0617,
|
| 289 |
+
"step": 220
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.99,
|
| 293 |
+
"learning_rate": 0.00015040074484992,
|
| 294 |
+
"loss": 0.9789,
|
| 295 |
+
"step": 225
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 1.02,
|
| 299 |
+
"learning_rate": 0.00014838637180007047,
|
| 300 |
+
"loss": 1.072,
|
| 301 |
+
"step": 230
|
| 302 |
+
},
|
| 303 |
+
{
|
| 304 |
+
"epoch": 1.04,
|
| 305 |
+
"learning_rate": 0.00014634602802971312,
|
| 306 |
+
"loss": 1.0098,
|
| 307 |
+
"step": 235
|
| 308 |
+
},
|
| 309 |
+
{
|
| 310 |
+
"epoch": 1.06,
|
| 311 |
+
"learning_rate": 0.00014428080866534396,
|
| 312 |
+
"loss": 1.0222,
|
| 313 |
+
"step": 240
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 1.08,
|
| 317 |
+
"learning_rate": 0.0001421918221850923,
|
| 318 |
+
"loss": 0.9734,
|
| 319 |
+
"step": 245
|
| 320 |
+
},
|
| 321 |
+
{
|
| 322 |
+
"epoch": 1.1,
|
| 323 |
+
"learning_rate": 0.00014008018982376044,
|
| 324 |
+
"loss": 0.9364,
|
| 325 |
+
"step": 250
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 1.13,
|
| 329 |
+
"learning_rate": 0.00013794704497101655,
|
| 330 |
+
"loss": 0.9735,
|
| 331 |
+
"step": 255
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 1.15,
|
| 335 |
+
"learning_rate": 0.00013579353256306287,
|
| 336 |
+
"loss": 1.0933,
|
| 337 |
+
"step": 260
|
| 338 |
+
},
|
| 339 |
+
{
|
| 340 |
+
"epoch": 1.17,
|
| 341 |
+
"learning_rate": 0.00013362080846810725,
|
| 342 |
+
"loss": 0.9764,
|
| 343 |
+
"step": 265
|
| 344 |
+
},
|
| 345 |
+
{
|
| 346 |
+
"epoch": 1.19,
|
| 347 |
+
"learning_rate": 0.00013143003886596669,
|
| 348 |
+
"loss": 1.0584,
|
| 349 |
+
"step": 270
|
| 350 |
+
},
|
| 351 |
+
{
|
| 352 |
+
"epoch": 1.22,
|
| 353 |
+
"learning_rate": 0.00012922239962213637,
|
| 354 |
+
"loss": 0.9116,
|
| 355 |
+
"step": 275
|
| 356 |
+
},
|
| 357 |
+
{
|
| 358 |
+
"epoch": 1.24,
|
| 359 |
+
"learning_rate": 0.00012699907565665982,
|
| 360 |
+
"loss": 1.0587,
|
| 361 |
+
"step": 280
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 1.26,
|
| 365 |
+
"learning_rate": 0.00012476126030813963,
|
| 366 |
+
"loss": 0.9342,
|
| 367 |
+
"step": 285
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 1.28,
|
| 371 |
+
"learning_rate": 0.00012251015469322916,
|
| 372 |
+
"loss": 0.9826,
|
| 373 |
+
"step": 290
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 1.3,
|
| 377 |
+
"learning_rate": 0.00012024696706194967,
|
| 378 |
+
"loss": 1.0656,
|
| 379 |
+
"step": 295
|
| 380 |
+
},
|
| 381 |
+
{
|
| 382 |
+
"epoch": 1.33,
|
| 383 |
+
"learning_rate": 0.00011797291214917881,
|
| 384 |
+
"loss": 1.0218,
|
| 385 |
+
"step": 300
|
| 386 |
+
},
|
| 387 |
+
{
|
| 388 |
+
"epoch": 1.33,
|
| 389 |
+
"eval_loss": 1.06796395778656,
|
| 390 |
+
"eval_runtime": 75.5412,
|
| 391 |
+
"eval_samples_per_second": 11.98,
|
| 392 |
+
"eval_steps_per_second": 1.509,
|
| 393 |
+
"step": 300
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 1.35,
|
| 397 |
+
"learning_rate": 0.00011568921052265836,
|
| 398 |
+
"loss": 0.9915,
|
| 399 |
+
"step": 305
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 1.37,
|
| 403 |
+
"learning_rate": 0.00011339708792787119,
|
| 404 |
+
"loss": 0.9592,
|
| 405 |
+
"step": 310
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 1.39,
|
| 409 |
+
"learning_rate": 0.00011109777463013915,
|
| 410 |
+
"loss": 0.9875,
|
| 411 |
+
"step": 315
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 1.41,
|
| 415 |
+
"learning_rate": 0.00010879250475429523,
|
| 416 |
+
"loss": 1.1583,
|
| 417 |
+
"step": 320
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 1.44,
|
| 421 |
+
"learning_rate": 0.00010648251562228386,
|
| 422 |
+
"loss": 0.977,
|
| 423 |
+
"step": 325
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 1.46,
|
| 427 |
+
"learning_rate": 0.00010416904708904548,
|
| 428 |
+
"loss": 1.041,
|
| 429 |
+
"step": 330
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 1.48,
|
| 433 |
+
"learning_rate": 0.00010185334087704124,
|
| 434 |
+
"loss": 0.972,
|
| 435 |
+
"step": 335
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 1.5,
|
| 439 |
+
"learning_rate": 9.953663990977568e-05,
|
| 440 |
+
"loss": 1.0115,
|
| 441 |
+
"step": 340
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 1.52,
|
| 445 |
+
"learning_rate": 9.722018764467461e-05,
|
| 446 |
+
"loss": 1.0078,
|
| 447 |
+
"step": 345
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 1.55,
|
| 451 |
+
"learning_rate": 9.490522740567633e-05,
|
| 452 |
+
"loss": 0.955,
|
| 453 |
+
"step": 350
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 1.57,
|
| 457 |
+
"learning_rate": 9.259300171589456e-05,
|
| 458 |
+
"loss": 0.9719,
|
| 459 |
+
"step": 355
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 1.59,
|
| 463 |
+
"learning_rate": 9.028475163071141e-05,
|
| 464 |
+
"loss": 0.871,
|
| 465 |
+
"step": 360
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 1.61,
|
| 469 |
+
"learning_rate": 8.798171607165778e-05,
|
| 470 |
+
"loss": 0.9568,
|
| 471 |
+
"step": 365
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 1.64,
|
| 475 |
+
"learning_rate": 8.568513116143919e-05,
|
| 476 |
+
"loss": 0.9466,
|
| 477 |
+
"step": 370
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 1.66,
|
| 481 |
+
"learning_rate": 8.339622956046417e-05,
|
| 482 |
+
"loss": 0.8967,
|
| 483 |
+
"step": 375
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 1.68,
|
| 487 |
+
"learning_rate": 8.111623980523035e-05,
|
| 488 |
+
"loss": 0.9465,
|
| 489 |
+
"step": 380
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 1.7,
|
| 493 |
+
"learning_rate": 7.884638564892472e-05,
|
| 494 |
+
"loss": 0.9499,
|
| 495 |
+
"step": 385
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 1.72,
|
| 499 |
+
"learning_rate": 7.658788540459062e-05,
|
| 500 |
+
"loss": 0.8955,
|
| 501 |
+
"step": 390
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 1.75,
|
| 505 |
+
"learning_rate": 7.434195129121518e-05,
|
| 506 |
+
"loss": 0.8982,
|
| 507 |
+
"step": 395
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 1.77,
|
| 511 |
+
"learning_rate": 7.210978878308729e-05,
|
| 512 |
+
"loss": 1.084,
|
| 513 |
+
"step": 400
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 1.77,
|
| 517 |
+
"eval_loss": 1.061107873916626,
|
| 518 |
+
"eval_runtime": 75.5635,
|
| 519 |
+
"eval_samples_per_second": 11.977,
|
| 520 |
+
"eval_steps_per_second": 1.509,
|
| 521 |
+
"step": 400
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 1.79,
|
| 525 |
+
"learning_rate": 6.989259596277582e-05,
|
| 526 |
+
"loss": 0.8936,
|
| 527 |
+
"step": 405
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 1.81,
|
| 531 |
+
"learning_rate": 6.76915628780754e-05,
|
| 532 |
+
"loss": 0.8794,
|
| 533 |
+
"step": 410
|
| 534 |
+
},
|
| 535 |
+
{
|
| 536 |
+
"epoch": 1.83,
|
| 537 |
+
"learning_rate": 6.55078709032644e-05,
|
| 538 |
+
"loss": 0.9631,
|
| 539 |
+
"step": 415
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 1.86,
|
| 543 |
+
"learning_rate": 6.334269210501875e-05,
|
| 544 |
+
"loss": 0.9636,
|
| 545 |
+
"step": 420
|
| 546 |
+
},
|
| 547 |
+
{
|
| 548 |
+
"epoch": 1.88,
|
| 549 |
+
"learning_rate": 6.119718861332098e-05,
|
| 550 |
+
"loss": 0.9761,
|
| 551 |
+
"step": 425
|
| 552 |
+
},
|
| 553 |
+
{
|
| 554 |
+
"epoch": 1.9,
|
| 555 |
+
"learning_rate": 5.9072511997703226e-05,
|
| 556 |
+
"loss": 0.9732,
|
| 557 |
+
"step": 430
|
| 558 |
+
},
|
| 559 |
+
{
|
| 560 |
+
"epoch": 1.92,
|
| 561 |
+
"learning_rate": 5.696980264915777e-05,
|
| 562 |
+
"loss": 0.995,
|
| 563 |
+
"step": 435
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 1.94,
|
| 567 |
+
"learning_rate": 5.489018916804813e-05,
|
| 568 |
+
"loss": 1.0037,
|
| 569 |
+
"step": 440
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 1.97,
|
| 573 |
+
"learning_rate": 5.283478775834811e-05,
|
| 574 |
+
"loss": 0.8503,
|
| 575 |
+
"step": 445
|
| 576 |
+
},
|
| 577 |
+
{
|
| 578 |
+
"epoch": 1.99,
|
| 579 |
+
"learning_rate": 5.080470162853472e-05,
|
| 580 |
+
"loss": 0.8914,
|
| 581 |
+
"step": 450
|
| 582 |
+
},
|
| 583 |
+
{
|
| 584 |
+
"epoch": 2.01,
|
| 585 |
+
"learning_rate": 4.880102039945624e-05,
|
| 586 |
+
"loss": 0.9531,
|
| 587 |
+
"step": 455
|
| 588 |
+
},
|
| 589 |
+
{
|
| 590 |
+
"epoch": 2.03,
|
| 591 |
+
"learning_rate": 4.6824819519493057e-05,
|
| 592 |
+
"loss": 0.9294,
|
| 593 |
+
"step": 460
|
| 594 |
+
},
|
| 595 |
+
{
|
| 596 |
+
"epoch": 2.06,
|
| 597 |
+
"learning_rate": 4.487715968732568e-05,
|
| 598 |
+
"loss": 0.8584,
|
| 599 |
+
"step": 465
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 2.08,
|
| 603 |
+
"learning_rate": 4.29590862826191e-05,
|
| 604 |
+
"loss": 0.9285,
|
| 605 |
+
"step": 470
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 2.1,
|
| 609 |
+
"learning_rate": 4.107162880492984e-05,
|
| 610 |
+
"loss": 0.8742,
|
| 611 |
+
"step": 475
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 2.12,
|
| 615 |
+
"learning_rate": 3.921580032113602e-05,
|
| 616 |
+
"loss": 0.7903,
|
| 617 |
+
"step": 480
|
| 618 |
+
},
|
| 619 |
+
{
|
| 620 |
+
"epoch": 2.14,
|
| 621 |
+
"learning_rate": 3.739259692168764e-05,
|
| 622 |
+
"loss": 0.8287,
|
| 623 |
+
"step": 485
|
| 624 |
+
},
|
| 625 |
+
{
|
| 626 |
+
"epoch": 2.17,
|
| 627 |
+
"learning_rate": 3.560299718596889e-05,
|
| 628 |
+
"loss": 0.8967,
|
| 629 |
+
"step": 490
|
| 630 |
+
},
|
| 631 |
+
{
|
| 632 |
+
"epoch": 2.19,
|
| 633 |
+
"learning_rate": 3.3847961657058845e-05,
|
| 634 |
+
"loss": 0.841,
|
| 635 |
+
"step": 495
|
| 636 |
+
},
|
| 637 |
+
{
|
| 638 |
+
"epoch": 2.21,
|
| 639 |
+
"learning_rate": 3.212843232617343e-05,
|
| 640 |
+
"loss": 0.897,
|
| 641 |
+
"step": 500
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 2.21,
|
| 645 |
+
"eval_loss": 1.0756696462631226,
|
| 646 |
+
"eval_runtime": 75.5409,
|
| 647 |
+
"eval_samples_per_second": 11.98,
|
| 648 |
+
"eval_steps_per_second": 1.509,
|
| 649 |
+
"step": 500
|
| 650 |
+
},
|
| 651 |
+
{
|
| 652 |
+
"epoch": 2.23,
|
| 653 |
+
"learning_rate": 3.0445332127064275e-05,
|
| 654 |
+
"loss": 0.9455,
|
| 655 |
+
"step": 505
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 2.25,
|
| 659 |
+
"learning_rate": 2.879956444064703e-05,
|
| 660 |
+
"loss": 0.9292,
|
| 661 |
+
"step": 510
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 2.28,
|
| 665 |
+
"learning_rate": 2.7192012610123774e-05,
|
| 666 |
+
"loss": 0.9016,
|
| 667 |
+
"step": 515
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 2.3,
|
| 671 |
+
"learning_rate": 2.5623539466860813e-05,
|
| 672 |
+
"loss": 0.937,
|
| 673 |
+
"step": 520
|
| 674 |
+
},
|
| 675 |
+
{
|
| 676 |
+
"epoch": 2.32,
|
| 677 |
+
"learning_rate": 2.409498686727587e-05,
|
| 678 |
+
"loss": 0.8348,
|
| 679 |
+
"step": 525
|
| 680 |
+
},
|
| 681 |
+
{
|
| 682 |
+
"epoch": 2.34,
|
| 683 |
+
"learning_rate": 2.2607175240983026e-05,
|
| 684 |
+
"loss": 0.8387,
|
| 685 |
+
"step": 530
|
| 686 |
+
},
|
| 687 |
+
{
|
| 688 |
+
"epoch": 2.36,
|
| 689 |
+
"learning_rate": 2.1160903150438605e-05,
|
| 690 |
+
"loss": 0.7736,
|
| 691 |
+
"step": 535
|
| 692 |
+
},
|
| 693 |
+
{
|
| 694 |
+
"epoch": 2.39,
|
| 695 |
+
"learning_rate": 1.9756946862323535e-05,
|
| 696 |
+
"loss": 0.8672,
|
| 697 |
+
"step": 540
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 2.41,
|
| 701 |
+
"learning_rate": 1.839605993089307e-05,
|
| 702 |
+
"loss": 0.8688,
|
| 703 |
+
"step": 545
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 2.43,
|
| 707 |
+
"learning_rate": 1.707897279351671e-05,
|
| 708 |
+
"loss": 0.8631,
|
| 709 |
+
"step": 550
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 2.45,
|
| 713 |
+
"learning_rate": 1.580639237862608e-05,
|
| 714 |
+
"loss": 0.9171,
|
| 715 |
+
"step": 555
|
| 716 |
+
},
|
| 717 |
+
{
|
| 718 |
+
"epoch": 2.48,
|
| 719 |
+
"learning_rate": 1.4579001726280828e-05,
|
| 720 |
+
"loss": 0.9134,
|
| 721 |
+
"step": 560
|
| 722 |
+
},
|
| 723 |
+
{
|
| 724 |
+
"epoch": 2.5,
|
| 725 |
+
"learning_rate": 1.339745962155613e-05,
|
| 726 |
+
"loss": 0.8363,
|
| 727 |
+
"step": 565
|
| 728 |
+
},
|
| 729 |
+
{
|
| 730 |
+
"epoch": 2.52,
|
| 731 |
+
"learning_rate": 1.2262400240949023e-05,
|
| 732 |
+
"loss": 0.8862,
|
| 733 |
+
"step": 570
|
| 734 |
+
},
|
| 735 |
+
{
|
| 736 |
+
"epoch": 2.54,
|
| 737 |
+
"learning_rate": 1.1174432811992685e-05,
|
| 738 |
+
"loss": 0.9154,
|
| 739 |
+
"step": 575
|
| 740 |
+
},
|
| 741 |
+
{
|
| 742 |
+
"epoch": 2.56,
|
| 743 |
+
"learning_rate": 1.013414128626211e-05,
|
| 744 |
+
"loss": 0.9423,
|
| 745 |
+
"step": 580
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 2.59,
|
| 749 |
+
"learning_rate": 9.142084025945984e-06,
|
| 750 |
+
"loss": 0.8462,
|
| 751 |
+
"step": 585
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 2.61,
|
| 755 |
+
"learning_rate": 8.19879350415349e-06,
|
| 756 |
+
"loss": 0.8019,
|
| 757 |
+
"step": 590
|
| 758 |
+
},
|
| 759 |
+
{
|
| 760 |
+
"epoch": 2.63,
|
| 761 |
+
"learning_rate": 7.30477601911671e-06,
|
| 762 |
+
"loss": 0.861,
|
| 763 |
+
"step": 595
|
| 764 |
+
},
|
| 765 |
+
{
|
| 766 |
+
"epoch": 2.65,
|
| 767 |
+
"learning_rate": 6.460511422441984e-06,
|
| 768 |
+
"loss": 0.9597,
|
| 769 |
+
"step": 600
|
| 770 |
+
},
|
| 771 |
+
{
|
| 772 |
+
"epoch": 2.65,
|
| 773 |
+
"eval_loss": 1.0745042562484741,
|
| 774 |
+
"eval_runtime": 75.5387,
|
| 775 |
+
"eval_samples_per_second": 11.981,
|
| 776 |
+
"eval_steps_per_second": 1.509,
|
| 777 |
+
"step": 600
|
| 778 |
+
},
|
| 779 |
+
{
|
| 780 |
+
"epoch": 2.67,
|
| 781 |
+
"learning_rate": 5.66645286155616e-06,
|
| 782 |
+
"loss": 0.7797,
|
| 783 |
+
"step": 605
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 2.7,
|
| 787 |
+
"learning_rate": 4.923026536485875e-06,
|
| 788 |
+
"loss": 0.9222,
|
| 789 |
+
"step": 610
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 2.72,
|
| 793 |
+
"learning_rate": 4.230631471100655e-06,
|
| 794 |
+
"loss": 0.9732,
|
| 795 |
+
"step": 615
|
| 796 |
+
},
|
| 797 |
+
{
|
| 798 |
+
"epoch": 2.74,
|
| 799 |
+
"learning_rate": 3.5896392989422377e-06,
|
| 800 |
+
"loss": 0.7366,
|
| 801 |
+
"step": 620
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 2.76,
|
| 805 |
+
"learning_rate": 3.000394063755396e-06,
|
| 806 |
+
"loss": 0.9243,
|
| 807 |
+
"step": 625
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 2.78,
|
| 811 |
+
"learning_rate": 2.4632120348272003e-06,
|
| 812 |
+
"loss": 0.9263,
|
| 813 |
+
"step": 630
|
| 814 |
+
},
|
| 815 |
+
{
|
| 816 |
+
"epoch": 2.81,
|
| 817 |
+
"learning_rate": 1.9783815372338423e-06,
|
| 818 |
+
"loss": 0.8541,
|
| 819 |
+
"step": 635
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"epoch": 2.83,
|
| 823 |
+
"learning_rate": 1.5461627970860814e-06,
|
| 824 |
+
"loss": 0.828,
|
| 825 |
+
"step": 640
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 2.85,
|
| 829 |
+
"learning_rate": 1.1667878018564171e-06,
|
| 830 |
+
"loss": 0.8446,
|
| 831 |
+
"step": 645
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 2.87,
|
| 835 |
+
"learning_rate": 8.404601758630892e-07,
|
| 836 |
+
"loss": 0.7749,
|
| 837 |
+
"step": 650
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 2.9,
|
| 841 |
+
"learning_rate": 5.673550709774267e-07,
|
| 842 |
+
"loss": 0.8738,
|
| 843 |
+
"step": 655
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 2.92,
|
| 847 |
+
"learning_rate": 3.4761907261356976e-07,
|
| 848 |
+
"loss": 0.895,
|
| 849 |
+
"step": 660
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 2.94,
|
| 853 |
+
"learning_rate": 1.813701210506946e-07,
|
| 854 |
+
"loss": 0.8552,
|
| 855 |
+
"step": 665
|
| 856 |
+
},
|
| 857 |
+
{
|
| 858 |
+
"epoch": 2.96,
|
| 859 |
+
"learning_rate": 6.869744813023937e-08,
|
| 860 |
+
"loss": 0.8475,
|
| 861 |
+
"step": 670
|
| 862 |
+
},
|
| 863 |
+
{
|
| 864 |
+
"epoch": 2.98,
|
| 865 |
+
"learning_rate": 9.661529361892907e-09,
|
| 866 |
+
"loss": 0.9076,
|
| 867 |
+
"step": 675
|
| 868 |
+
},
|
| 869 |
+
{
|
| 870 |
+
"epoch": 3.0,
|
| 871 |
+
"step": 678,
|
| 872 |
+
"total_flos": 1.5685942606774272e+17,
|
| 873 |
+
"train_loss": 0.9757168982232918,
|
| 874 |
+
"train_runtime": 3618.1154,
|
| 875 |
+
"train_samples_per_second": 3.0,
|
| 876 |
+
"train_steps_per_second": 0.187
|
| 877 |
+
}
|
| 878 |
+
],
|
| 879 |
+
"logging_steps": 5,
|
| 880 |
+
"max_steps": 678,
|
| 881 |
+
"num_input_tokens_seen": 0,
|
| 882 |
+
"num_train_epochs": 3,
|
| 883 |
+
"save_steps": 100,
|
| 884 |
+
"total_flos": 1.5685942606774272e+17,
|
| 885 |
+
"train_batch_size": 4,
|
| 886 |
+
"trial_name": null,
|
| 887 |
+
"trial_params": null
|
| 888 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c8f3fda749ef742620436ea1dc1427c111735aa4ba53fdc18fb8f38a62d141f0
|
| 3 |
+
size 4920
|