Upload 13 files
Browse files- README.md +67 -3
- added_tokens.json +3 -0
- all_results.json +18 -0
- config.json +43 -0
- eval_results.json +11 -0
- model.safetensors +3 -0
- special_tokens_map.json +51 -0
- spm.model +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +66 -0
- train_results.json +11 -0
- trainer_state.json +1755 -0
- training_args.bin +3 -0
README.md
CHANGED
|
@@ -1,3 +1,67 @@
|
|
| 1 |
-
---
|
| 2 |
-
|
| 3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
license: mit
|
| 4 |
+
base_model: agentlans/deberta-v3-base-zyda-2-v2
|
| 5 |
+
tags:
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
model-index:
|
| 8 |
+
- name: deberta-v3-base-zyda-2-v2-text-quality-v3
|
| 9 |
+
results: []
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
# deberta-v3-base-zyda-2-v2-text-quality-v3
|
| 13 |
+
|
| 14 |
+
This model is a fine-tuned version of [agentlans/deberta-v3-base-zyda-2-v2](https://huggingface.co/agentlans/deberta-v3-base-zyda-2-v2) on an unknown dataset.
|
| 15 |
+
It achieves the following results on the evaluation set:
|
| 16 |
+
- Loss: 0.1408
|
| 17 |
+
- Mse: 0.1408
|
| 18 |
+
- Combined Score: 0.1408
|
| 19 |
+
- Num Input Tokens Seen: 102398720
|
| 20 |
+
|
| 21 |
+
## Model description
|
| 22 |
+
|
| 23 |
+
More information needed
|
| 24 |
+
|
| 25 |
+
## Intended uses & limitations
|
| 26 |
+
|
| 27 |
+
More information needed
|
| 28 |
+
|
| 29 |
+
## Training and evaluation data
|
| 30 |
+
|
| 31 |
+
More information needed
|
| 32 |
+
|
| 33 |
+
## Training procedure
|
| 34 |
+
|
| 35 |
+
### Training hyperparameters
|
| 36 |
+
|
| 37 |
+
The following hyperparameters were used during training:
|
| 38 |
+
- learning_rate: 5e-05
|
| 39 |
+
- train_batch_size: 8
|
| 40 |
+
- eval_batch_size: 8
|
| 41 |
+
- seed: 42
|
| 42 |
+
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 43 |
+
- lr_scheduler_type: linear
|
| 44 |
+
- num_epochs: 10.0
|
| 45 |
+
|
| 46 |
+
### Training results
|
| 47 |
+
|
| 48 |
+
| Training Loss | Epoch | Step | Validation Loss | Mse | Combined Score | Input Tokens Seen |
|
| 49 |
+
|:-------------:|:-----:|:------:|:---------------:|:------:|:--------------:|:-----------------:|
|
| 50 |
+
| 0.1635 | 1.0 | 10000 | 0.1854 | 0.1854 | 0.1854 | 10239872 |
|
| 51 |
+
| 0.1241 | 2.0 | 20000 | 0.1408 | 0.1408 | 0.1408 | 20479744 |
|
| 52 |
+
| 0.0882 | 3.0 | 30000 | 0.1747 | 0.1747 | 0.1747 | 30719616 |
|
| 53 |
+
| 0.054 | 4.0 | 40000 | 0.1528 | 0.1528 | 0.1528 | 40959488 |
|
| 54 |
+
| 0.0372 | 5.0 | 50000 | 0.1480 | 0.1480 | 0.1480 | 51199360 |
|
| 55 |
+
| 0.0263 | 6.0 | 60000 | 0.1524 | 0.1524 | 0.1524 | 61439232 |
|
| 56 |
+
| 0.0203 | 7.0 | 70000 | 0.1495 | 0.1495 | 0.1495 | 71679104 |
|
| 57 |
+
| 0.0135 | 8.0 | 80000 | 0.1482 | 0.1482 | 0.1482 | 81918976 |
|
| 58 |
+
| 0.0098 | 9.0 | 90000 | 0.1450 | 0.1450 | 0.1450 | 92158848 |
|
| 59 |
+
| 0.0073 | 10.0 | 100000 | 0.1453 | 0.1453 | 0.1453 | 102398720 |
|
| 60 |
+
|
| 61 |
+
|
| 62 |
+
### Framework versions
|
| 63 |
+
|
| 64 |
+
- Transformers 4.51.3
|
| 65 |
+
- Pytorch 2.6.0+cu124
|
| 66 |
+
- Datasets 3.2.0
|
| 67 |
+
- Tokenizers 0.21.0
|
added_tokens.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"[MASK]": 128000
|
| 3 |
+
}
|
all_results.json
ADDED
|
@@ -0,0 +1,18 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"eval_combined_score": 0.14082256163832602,
|
| 4 |
+
"eval_loss": 0.14082255959510803,
|
| 5 |
+
"eval_mse": 0.14082256368154403,
|
| 6 |
+
"eval_runtime": 29.4816,
|
| 7 |
+
"eval_samples": 20000,
|
| 8 |
+
"eval_samples_per_second": 678.389,
|
| 9 |
+
"eval_steps_per_second": 84.799,
|
| 10 |
+
"num_input_tokens_seen": 102398720,
|
| 11 |
+
"total_flos": 5.262202453327104e+16,
|
| 12 |
+
"train_loss": 0.056572345192432406,
|
| 13 |
+
"train_runtime": 7202.8043,
|
| 14 |
+
"train_samples": 79999,
|
| 15 |
+
"train_samples_per_second": 111.066,
|
| 16 |
+
"train_steps_per_second": 13.883,
|
| 17 |
+
"train_tokens_per_second": 14216.507
|
| 18 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"DebertaV2ForSequenceClassification"
|
| 4 |
+
],
|
| 5 |
+
"attention_probs_dropout_prob": 0.1,
|
| 6 |
+
"finetuning_task": "text-classification",
|
| 7 |
+
"hidden_act": "gelu",
|
| 8 |
+
"hidden_dropout_prob": 0.1,
|
| 9 |
+
"hidden_size": 768,
|
| 10 |
+
"id2label": {
|
| 11 |
+
"0": "LABEL_0"
|
| 12 |
+
},
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 3072,
|
| 15 |
+
"label2id": {
|
| 16 |
+
"LABEL_0": 0
|
| 17 |
+
},
|
| 18 |
+
"layer_norm_eps": 1e-07,
|
| 19 |
+
"legacy": true,
|
| 20 |
+
"max_position_embeddings": 512,
|
| 21 |
+
"max_relative_positions": -1,
|
| 22 |
+
"model_type": "deberta-v2",
|
| 23 |
+
"norm_rel_ebd": "layer_norm",
|
| 24 |
+
"num_attention_heads": 12,
|
| 25 |
+
"num_hidden_layers": 12,
|
| 26 |
+
"pad_token_id": 0,
|
| 27 |
+
"pooler_dropout": 0,
|
| 28 |
+
"pooler_hidden_act": "gelu",
|
| 29 |
+
"pooler_hidden_size": 768,
|
| 30 |
+
"pos_att_type": [
|
| 31 |
+
"p2c",
|
| 32 |
+
"c2p"
|
| 33 |
+
],
|
| 34 |
+
"position_biased_input": false,
|
| 35 |
+
"position_buckets": 256,
|
| 36 |
+
"problem_type": "regression",
|
| 37 |
+
"relative_attention": true,
|
| 38 |
+
"share_att_key": true,
|
| 39 |
+
"torch_dtype": "float32",
|
| 40 |
+
"transformers_version": "4.51.3",
|
| 41 |
+
"type_vocab_size": 0,
|
| 42 |
+
"vocab_size": 128100
|
| 43 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"eval_combined_score": 0.14082256163832602,
|
| 4 |
+
"eval_loss": 0.14082255959510803,
|
| 5 |
+
"eval_mse": 0.14082256368154403,
|
| 6 |
+
"eval_runtime": 29.4816,
|
| 7 |
+
"eval_samples": 20000,
|
| 8 |
+
"eval_samples_per_second": 678.389,
|
| 9 |
+
"eval_steps_per_second": 84.799,
|
| 10 |
+
"num_input_tokens_seen": 102398720
|
| 11 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b1113d16a7cdd3f48c8ba92a644d96bd6a05008604551916fdf083737ab37121
|
| 3 |
+
size 737716196
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "[CLS]",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"cls_token": {
|
| 10 |
+
"content": "[CLS]",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"eos_token": {
|
| 17 |
+
"content": "[SEP]",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"mask_token": {
|
| 24 |
+
"content": "[MASK]",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"pad_token": {
|
| 31 |
+
"content": "[PAD]",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
},
|
| 37 |
+
"sep_token": {
|
| 38 |
+
"content": "[SEP]",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false
|
| 43 |
+
},
|
| 44 |
+
"unk_token": {
|
| 45 |
+
"content": "[UNK]",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": true,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false
|
| 50 |
+
}
|
| 51 |
+
}
|
spm.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
|
| 3 |
+
size 2464616
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,66 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "[PAD]",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "[CLS]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "[SEP]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"3": {
|
| 28 |
+
"content": "[UNK]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": true,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"128000": {
|
| 36 |
+
"content": "[MASK]",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"bos_token": "[CLS]",
|
| 45 |
+
"clean_up_tokenization_spaces": false,
|
| 46 |
+
"cls_token": "[CLS]",
|
| 47 |
+
"do_lower_case": false,
|
| 48 |
+
"eos_token": "[SEP]",
|
| 49 |
+
"extra_special_tokens": {},
|
| 50 |
+
"mask_token": "[MASK]",
|
| 51 |
+
"max_length": 512,
|
| 52 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 53 |
+
"pad_to_multiple_of": null,
|
| 54 |
+
"pad_token": "[PAD]",
|
| 55 |
+
"pad_token_type_id": 0,
|
| 56 |
+
"padding_side": "right",
|
| 57 |
+
"sep_token": "[SEP]",
|
| 58 |
+
"sp_model_kwargs": {},
|
| 59 |
+
"split_by_punct": false,
|
| 60 |
+
"stride": 0,
|
| 61 |
+
"tokenizer_class": "DebertaV2Tokenizer",
|
| 62 |
+
"truncation_side": "right",
|
| 63 |
+
"truncation_strategy": "longest_first",
|
| 64 |
+
"unk_token": "[UNK]",
|
| 65 |
+
"vocab_type": "spm"
|
| 66 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"num_input_tokens_seen": 102398720,
|
| 4 |
+
"total_flos": 5.262202453327104e+16,
|
| 5 |
+
"train_loss": 0.056572345192432406,
|
| 6 |
+
"train_runtime": 7202.8043,
|
| 7 |
+
"train_samples": 79999,
|
| 8 |
+
"train_samples_per_second": 111.066,
|
| 9 |
+
"train_steps_per_second": 13.883,
|
| 10 |
+
"train_tokens_per_second": 14216.507
|
| 11 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1755 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": 20000,
|
| 3 |
+
"best_metric": 0.14082255959510803,
|
| 4 |
+
"best_model_checkpoint": "/media/user/Expansion1/deberta-v3-base-zyda-2-v2-text-quality-v3/checkpoint-20000",
|
| 5 |
+
"epoch": 10.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 100000,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.05,
|
| 14 |
+
"grad_norm": 11.949178695678711,
|
| 15 |
+
"learning_rate": 4.97505e-05,
|
| 16 |
+
"loss": 0.3835,
|
| 17 |
+
"num_input_tokens_seen": 512000,
|
| 18 |
+
"step": 500
|
| 19 |
+
},
|
| 20 |
+
{
|
| 21 |
+
"epoch": 0.1,
|
| 22 |
+
"grad_norm": 3.623898506164551,
|
| 23 |
+
"learning_rate": 4.95005e-05,
|
| 24 |
+
"loss": 0.2484,
|
| 25 |
+
"num_input_tokens_seen": 1024000,
|
| 26 |
+
"step": 1000
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.15,
|
| 30 |
+
"grad_norm": 3.0655770301818848,
|
| 31 |
+
"learning_rate": 4.9250500000000006e-05,
|
| 32 |
+
"loss": 0.2332,
|
| 33 |
+
"num_input_tokens_seen": 1536000,
|
| 34 |
+
"step": 1500
|
| 35 |
+
},
|
| 36 |
+
{
|
| 37 |
+
"epoch": 0.2,
|
| 38 |
+
"grad_norm": 8.194499015808105,
|
| 39 |
+
"learning_rate": 4.9000500000000006e-05,
|
| 40 |
+
"loss": 0.2097,
|
| 41 |
+
"num_input_tokens_seen": 2048000,
|
| 42 |
+
"step": 2000
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"epoch": 0.25,
|
| 46 |
+
"grad_norm": 1.8507510423660278,
|
| 47 |
+
"learning_rate": 4.875050000000001e-05,
|
| 48 |
+
"loss": 0.1988,
|
| 49 |
+
"num_input_tokens_seen": 2560000,
|
| 50 |
+
"step": 2500
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.3,
|
| 54 |
+
"grad_norm": 2.8679802417755127,
|
| 55 |
+
"learning_rate": 4.85005e-05,
|
| 56 |
+
"loss": 0.1957,
|
| 57 |
+
"num_input_tokens_seen": 3072000,
|
| 58 |
+
"step": 3000
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.35,
|
| 62 |
+
"grad_norm": 3.2234883308410645,
|
| 63 |
+
"learning_rate": 4.82505e-05,
|
| 64 |
+
"loss": 0.1793,
|
| 65 |
+
"num_input_tokens_seen": 3584000,
|
| 66 |
+
"step": 3500
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.4,
|
| 70 |
+
"grad_norm": 4.360517978668213,
|
| 71 |
+
"learning_rate": 4.80005e-05,
|
| 72 |
+
"loss": 0.1816,
|
| 73 |
+
"num_input_tokens_seen": 4096000,
|
| 74 |
+
"step": 4000
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.45,
|
| 78 |
+
"grad_norm": 5.652502536773682,
|
| 79 |
+
"learning_rate": 4.77505e-05,
|
| 80 |
+
"loss": 0.1855,
|
| 81 |
+
"num_input_tokens_seen": 4608000,
|
| 82 |
+
"step": 4500
|
| 83 |
+
},
|
| 84 |
+
{
|
| 85 |
+
"epoch": 0.5,
|
| 86 |
+
"grad_norm": 3.757875919342041,
|
| 87 |
+
"learning_rate": 4.7500500000000004e-05,
|
| 88 |
+
"loss": 0.1751,
|
| 89 |
+
"num_input_tokens_seen": 5120000,
|
| 90 |
+
"step": 5000
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 0.55,
|
| 94 |
+
"grad_norm": 3.0092484951019287,
|
| 95 |
+
"learning_rate": 4.7250500000000004e-05,
|
| 96 |
+
"loss": 0.1785,
|
| 97 |
+
"num_input_tokens_seen": 5632000,
|
| 98 |
+
"step": 5500
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.6,
|
| 102 |
+
"grad_norm": 7.830347061157227,
|
| 103 |
+
"learning_rate": 4.7000500000000005e-05,
|
| 104 |
+
"loss": 0.1711,
|
| 105 |
+
"num_input_tokens_seen": 6144000,
|
| 106 |
+
"step": 6000
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 0.65,
|
| 110 |
+
"grad_norm": 2.926468849182129,
|
| 111 |
+
"learning_rate": 4.6750500000000006e-05,
|
| 112 |
+
"loss": 0.168,
|
| 113 |
+
"num_input_tokens_seen": 6656000,
|
| 114 |
+
"step": 6500
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.7,
|
| 118 |
+
"grad_norm": 3.43612003326416,
|
| 119 |
+
"learning_rate": 4.65005e-05,
|
| 120 |
+
"loss": 0.1772,
|
| 121 |
+
"num_input_tokens_seen": 7168000,
|
| 122 |
+
"step": 7000
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.75,
|
| 126 |
+
"grad_norm": 2.3997323513031006,
|
| 127 |
+
"learning_rate": 4.62505e-05,
|
| 128 |
+
"loss": 0.1632,
|
| 129 |
+
"num_input_tokens_seen": 7680000,
|
| 130 |
+
"step": 7500
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 0.8,
|
| 134 |
+
"grad_norm": 12.628423690795898,
|
| 135 |
+
"learning_rate": 4.60005e-05,
|
| 136 |
+
"loss": 0.1714,
|
| 137 |
+
"num_input_tokens_seen": 8192000,
|
| 138 |
+
"step": 8000
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 0.85,
|
| 142 |
+
"grad_norm": 1.8220003843307495,
|
| 143 |
+
"learning_rate": 4.57505e-05,
|
| 144 |
+
"loss": 0.1613,
|
| 145 |
+
"num_input_tokens_seen": 8704000,
|
| 146 |
+
"step": 8500
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 0.9,
|
| 150 |
+
"grad_norm": 2.2584903240203857,
|
| 151 |
+
"learning_rate": 4.55005e-05,
|
| 152 |
+
"loss": 0.1547,
|
| 153 |
+
"num_input_tokens_seen": 9216000,
|
| 154 |
+
"step": 9000
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 0.95,
|
| 158 |
+
"grad_norm": 1.5416566133499146,
|
| 159 |
+
"learning_rate": 4.52505e-05,
|
| 160 |
+
"loss": 0.1594,
|
| 161 |
+
"num_input_tokens_seen": 9728000,
|
| 162 |
+
"step": 9500
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 1.0,
|
| 166 |
+
"grad_norm": 2.472825288772583,
|
| 167 |
+
"learning_rate": 4.5000500000000004e-05,
|
| 168 |
+
"loss": 0.1635,
|
| 169 |
+
"num_input_tokens_seen": 10239872,
|
| 170 |
+
"step": 10000
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 1.0,
|
| 174 |
+
"eval_combined_score": 0.18538867612314003,
|
| 175 |
+
"eval_loss": 0.18538866937160492,
|
| 176 |
+
"eval_mse": 0.18538868287467514,
|
| 177 |
+
"eval_runtime": 29.5714,
|
| 178 |
+
"eval_samples_per_second": 676.329,
|
| 179 |
+
"eval_steps_per_second": 84.541,
|
| 180 |
+
"num_input_tokens_seen": 10239872,
|
| 181 |
+
"step": 10000
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 1.05,
|
| 185 |
+
"grad_norm": 2.986963987350464,
|
| 186 |
+
"learning_rate": 4.47505e-05,
|
| 187 |
+
"loss": 0.1226,
|
| 188 |
+
"num_input_tokens_seen": 10751872,
|
| 189 |
+
"step": 10500
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 1.1,
|
| 193 |
+
"grad_norm": 0.7588199973106384,
|
| 194 |
+
"learning_rate": 4.45005e-05,
|
| 195 |
+
"loss": 0.1172,
|
| 196 |
+
"num_input_tokens_seen": 11263872,
|
| 197 |
+
"step": 11000
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 1.15,
|
| 201 |
+
"grad_norm": 0.8432678580284119,
|
| 202 |
+
"learning_rate": 4.42505e-05,
|
| 203 |
+
"loss": 0.1186,
|
| 204 |
+
"num_input_tokens_seen": 11775872,
|
| 205 |
+
"step": 11500
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 1.2,
|
| 209 |
+
"grad_norm": 12.563228607177734,
|
| 210 |
+
"learning_rate": 4.40005e-05,
|
| 211 |
+
"loss": 0.1139,
|
| 212 |
+
"num_input_tokens_seen": 12287872,
|
| 213 |
+
"step": 12000
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 1.25,
|
| 217 |
+
"grad_norm": 2.207587242126465,
|
| 218 |
+
"learning_rate": 4.37505e-05,
|
| 219 |
+
"loss": 0.121,
|
| 220 |
+
"num_input_tokens_seen": 12799872,
|
| 221 |
+
"step": 12500
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 1.3,
|
| 225 |
+
"grad_norm": 1.978637456893921,
|
| 226 |
+
"learning_rate": 4.35005e-05,
|
| 227 |
+
"loss": 0.1114,
|
| 228 |
+
"num_input_tokens_seen": 13311872,
|
| 229 |
+
"step": 13000
|
| 230 |
+
},
|
| 231 |
+
{
|
| 232 |
+
"epoch": 1.35,
|
| 233 |
+
"grad_norm": 5.6478729248046875,
|
| 234 |
+
"learning_rate": 4.32505e-05,
|
| 235 |
+
"loss": 0.1182,
|
| 236 |
+
"num_input_tokens_seen": 13823872,
|
| 237 |
+
"step": 13500
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 1.4,
|
| 241 |
+
"grad_norm": 3.0157413482666016,
|
| 242 |
+
"learning_rate": 4.30005e-05,
|
| 243 |
+
"loss": 0.1099,
|
| 244 |
+
"num_input_tokens_seen": 14335872,
|
| 245 |
+
"step": 14000
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 1.45,
|
| 249 |
+
"grad_norm": 2.2837512493133545,
|
| 250 |
+
"learning_rate": 4.2750500000000003e-05,
|
| 251 |
+
"loss": 0.1154,
|
| 252 |
+
"num_input_tokens_seen": 14847872,
|
| 253 |
+
"step": 14500
|
| 254 |
+
},
|
| 255 |
+
{
|
| 256 |
+
"epoch": 1.5,
|
| 257 |
+
"grad_norm": 2.124837875366211,
|
| 258 |
+
"learning_rate": 4.2500500000000004e-05,
|
| 259 |
+
"loss": 0.1163,
|
| 260 |
+
"num_input_tokens_seen": 15359872,
|
| 261 |
+
"step": 15000
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 1.55,
|
| 265 |
+
"grad_norm": 1.8782966136932373,
|
| 266 |
+
"learning_rate": 4.2250500000000005e-05,
|
| 267 |
+
"loss": 0.1167,
|
| 268 |
+
"num_input_tokens_seen": 15871872,
|
| 269 |
+
"step": 15500
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 1.6,
|
| 273 |
+
"grad_norm": 1.085688591003418,
|
| 274 |
+
"learning_rate": 4.2000500000000006e-05,
|
| 275 |
+
"loss": 0.1156,
|
| 276 |
+
"num_input_tokens_seen": 16383872,
|
| 277 |
+
"step": 16000
|
| 278 |
+
},
|
| 279 |
+
{
|
| 280 |
+
"epoch": 1.65,
|
| 281 |
+
"grad_norm": 1.9874955415725708,
|
| 282 |
+
"learning_rate": 4.1750500000000006e-05,
|
| 283 |
+
"loss": 0.1183,
|
| 284 |
+
"num_input_tokens_seen": 16895872,
|
| 285 |
+
"step": 16500
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 1.7,
|
| 289 |
+
"grad_norm": 2.6902706623077393,
|
| 290 |
+
"learning_rate": 4.15005e-05,
|
| 291 |
+
"loss": 0.1112,
|
| 292 |
+
"num_input_tokens_seen": 17407872,
|
| 293 |
+
"step": 17000
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 1.75,
|
| 297 |
+
"grad_norm": 3.0735440254211426,
|
| 298 |
+
"learning_rate": 4.12505e-05,
|
| 299 |
+
"loss": 0.1159,
|
| 300 |
+
"num_input_tokens_seen": 17919872,
|
| 301 |
+
"step": 17500
|
| 302 |
+
},
|
| 303 |
+
{
|
| 304 |
+
"epoch": 1.8,
|
| 305 |
+
"grad_norm": 2.936267614364624,
|
| 306 |
+
"learning_rate": 4.10005e-05,
|
| 307 |
+
"loss": 0.1187,
|
| 308 |
+
"num_input_tokens_seen": 18431872,
|
| 309 |
+
"step": 18000
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 1.85,
|
| 313 |
+
"grad_norm": 3.598895311355591,
|
| 314 |
+
"learning_rate": 4.07505e-05,
|
| 315 |
+
"loss": 0.1147,
|
| 316 |
+
"num_input_tokens_seen": 18943872,
|
| 317 |
+
"step": 18500
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 1.9,
|
| 321 |
+
"grad_norm": 3.655381917953491,
|
| 322 |
+
"learning_rate": 4.05005e-05,
|
| 323 |
+
"loss": 0.1387,
|
| 324 |
+
"num_input_tokens_seen": 19455872,
|
| 325 |
+
"step": 19000
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 1.95,
|
| 329 |
+
"grad_norm": 9.855778694152832,
|
| 330 |
+
"learning_rate": 4.0250500000000004e-05,
|
| 331 |
+
"loss": 0.1238,
|
| 332 |
+
"num_input_tokens_seen": 19967872,
|
| 333 |
+
"step": 19500
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 2.0,
|
| 337 |
+
"grad_norm": 2.558746337890625,
|
| 338 |
+
"learning_rate": 4.0000500000000004e-05,
|
| 339 |
+
"loss": 0.1241,
|
| 340 |
+
"num_input_tokens_seen": 20479744,
|
| 341 |
+
"step": 20000
|
| 342 |
+
},
|
| 343 |
+
{
|
| 344 |
+
"epoch": 2.0,
|
| 345 |
+
"eval_combined_score": 0.14082256163832602,
|
| 346 |
+
"eval_loss": 0.14082255959510803,
|
| 347 |
+
"eval_mse": 0.14082256368154403,
|
| 348 |
+
"eval_runtime": 30.1283,
|
| 349 |
+
"eval_samples_per_second": 663.828,
|
| 350 |
+
"eval_steps_per_second": 82.979,
|
| 351 |
+
"num_input_tokens_seen": 20479744,
|
| 352 |
+
"step": 20000
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 2.05,
|
| 356 |
+
"grad_norm": 1.3755764961242676,
|
| 357 |
+
"learning_rate": 3.97505e-05,
|
| 358 |
+
"loss": 0.0804,
|
| 359 |
+
"num_input_tokens_seen": 20991744,
|
| 360 |
+
"step": 20500
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 2.1,
|
| 364 |
+
"grad_norm": 3.242955207824707,
|
| 365 |
+
"learning_rate": 3.95005e-05,
|
| 366 |
+
"loss": 0.0795,
|
| 367 |
+
"num_input_tokens_seen": 21503744,
|
| 368 |
+
"step": 21000
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 2.15,
|
| 372 |
+
"grad_norm": 2.4045000076293945,
|
| 373 |
+
"learning_rate": 3.92505e-05,
|
| 374 |
+
"loss": 0.0814,
|
| 375 |
+
"num_input_tokens_seen": 22015744,
|
| 376 |
+
"step": 21500
|
| 377 |
+
},
|
| 378 |
+
{
|
| 379 |
+
"epoch": 2.2,
|
| 380 |
+
"grad_norm": 2.5508718490600586,
|
| 381 |
+
"learning_rate": 3.90005e-05,
|
| 382 |
+
"loss": 0.0848,
|
| 383 |
+
"num_input_tokens_seen": 22527744,
|
| 384 |
+
"step": 22000
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 2.25,
|
| 388 |
+
"grad_norm": 2.8529911041259766,
|
| 389 |
+
"learning_rate": 3.87505e-05,
|
| 390 |
+
"loss": 0.081,
|
| 391 |
+
"num_input_tokens_seen": 23039744,
|
| 392 |
+
"step": 22500
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 2.3,
|
| 396 |
+
"grad_norm": 10.657905578613281,
|
| 397 |
+
"learning_rate": 3.85005e-05,
|
| 398 |
+
"loss": 0.0786,
|
| 399 |
+
"num_input_tokens_seen": 23551744,
|
| 400 |
+
"step": 23000
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"epoch": 2.35,
|
| 404 |
+
"grad_norm": 2.378411293029785,
|
| 405 |
+
"learning_rate": 3.82505e-05,
|
| 406 |
+
"loss": 0.0823,
|
| 407 |
+
"num_input_tokens_seen": 24063744,
|
| 408 |
+
"step": 23500
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 2.4,
|
| 412 |
+
"grad_norm": 2.6125261783599854,
|
| 413 |
+
"learning_rate": 3.80005e-05,
|
| 414 |
+
"loss": 0.0787,
|
| 415 |
+
"num_input_tokens_seen": 24575744,
|
| 416 |
+
"step": 24000
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 2.45,
|
| 420 |
+
"grad_norm": 1.3133174180984497,
|
| 421 |
+
"learning_rate": 3.77505e-05,
|
| 422 |
+
"loss": 0.0761,
|
| 423 |
+
"num_input_tokens_seen": 25087744,
|
| 424 |
+
"step": 24500
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"epoch": 2.5,
|
| 428 |
+
"grad_norm": 3.3419981002807617,
|
| 429 |
+
"learning_rate": 3.75005e-05,
|
| 430 |
+
"loss": 0.0775,
|
| 431 |
+
"num_input_tokens_seen": 25599744,
|
| 432 |
+
"step": 25000
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 2.55,
|
| 436 |
+
"grad_norm": 2.1734654903411865,
|
| 437 |
+
"learning_rate": 3.72505e-05,
|
| 438 |
+
"loss": 0.0846,
|
| 439 |
+
"num_input_tokens_seen": 26111744,
|
| 440 |
+
"step": 25500
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 2.6,
|
| 444 |
+
"grad_norm": 3.2352869510650635,
|
| 445 |
+
"learning_rate": 3.70005e-05,
|
| 446 |
+
"loss": 0.0817,
|
| 447 |
+
"num_input_tokens_seen": 26623744,
|
| 448 |
+
"step": 26000
|
| 449 |
+
},
|
| 450 |
+
{
|
| 451 |
+
"epoch": 2.65,
|
| 452 |
+
"grad_norm": 3.37646746635437,
|
| 453 |
+
"learning_rate": 3.675050000000001e-05,
|
| 454 |
+
"loss": 0.0816,
|
| 455 |
+
"num_input_tokens_seen": 27135744,
|
| 456 |
+
"step": 26500
|
| 457 |
+
},
|
| 458 |
+
{
|
| 459 |
+
"epoch": 2.7,
|
| 460 |
+
"grad_norm": 2.5875842571258545,
|
| 461 |
+
"learning_rate": 3.650050000000001e-05,
|
| 462 |
+
"loss": 0.0843,
|
| 463 |
+
"num_input_tokens_seen": 27647744,
|
| 464 |
+
"step": 27000
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 2.75,
|
| 468 |
+
"grad_norm": 7.768916606903076,
|
| 469 |
+
"learning_rate": 3.62505e-05,
|
| 470 |
+
"loss": 0.089,
|
| 471 |
+
"num_input_tokens_seen": 28159744,
|
| 472 |
+
"step": 27500
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 2.8,
|
| 476 |
+
"grad_norm": 2.6333940029144287,
|
| 477 |
+
"learning_rate": 3.60005e-05,
|
| 478 |
+
"loss": 0.1209,
|
| 479 |
+
"num_input_tokens_seen": 28671744,
|
| 480 |
+
"step": 28000
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 2.85,
|
| 484 |
+
"grad_norm": 3.4022088050842285,
|
| 485 |
+
"learning_rate": 3.57505e-05,
|
| 486 |
+
"loss": 0.082,
|
| 487 |
+
"num_input_tokens_seen": 29183744,
|
| 488 |
+
"step": 28500
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 2.9,
|
| 492 |
+
"grad_norm": 1.5310307741165161,
|
| 493 |
+
"learning_rate": 3.5500500000000003e-05,
|
| 494 |
+
"loss": 0.0813,
|
| 495 |
+
"num_input_tokens_seen": 29695744,
|
| 496 |
+
"step": 29000
|
| 497 |
+
},
|
| 498 |
+
{
|
| 499 |
+
"epoch": 2.95,
|
| 500 |
+
"grad_norm": 3.3515617847442627,
|
| 501 |
+
"learning_rate": 3.5250500000000004e-05,
|
| 502 |
+
"loss": 0.0856,
|
| 503 |
+
"num_input_tokens_seen": 30207744,
|
| 504 |
+
"step": 29500
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 3.0,
|
| 508 |
+
"grad_norm": 1.5893547534942627,
|
| 509 |
+
"learning_rate": 3.5000500000000005e-05,
|
| 510 |
+
"loss": 0.0882,
|
| 511 |
+
"num_input_tokens_seen": 30719616,
|
| 512 |
+
"step": 30000
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 3.0,
|
| 516 |
+
"eval_combined_score": 0.1746896443902683,
|
| 517 |
+
"eval_loss": 0.1746896207332611,
|
| 518 |
+
"eval_mse": 0.17468963824495307,
|
| 519 |
+
"eval_runtime": 29.4701,
|
| 520 |
+
"eval_samples_per_second": 678.654,
|
| 521 |
+
"eval_steps_per_second": 84.832,
|
| 522 |
+
"num_input_tokens_seen": 30719616,
|
| 523 |
+
"step": 30000
|
| 524 |
+
},
|
| 525 |
+
{
|
| 526 |
+
"epoch": 3.05,
|
| 527 |
+
"grad_norm": 1.333294153213501,
|
| 528 |
+
"learning_rate": 3.4750500000000006e-05,
|
| 529 |
+
"loss": 0.0562,
|
| 530 |
+
"num_input_tokens_seen": 31231616,
|
| 531 |
+
"step": 30500
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 3.1,
|
| 535 |
+
"grad_norm": 0.8254738450050354,
|
| 536 |
+
"learning_rate": 3.45005e-05,
|
| 537 |
+
"loss": 0.053,
|
| 538 |
+
"num_input_tokens_seen": 31743616,
|
| 539 |
+
"step": 31000
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 3.15,
|
| 543 |
+
"grad_norm": 1.7611359357833862,
|
| 544 |
+
"learning_rate": 3.42505e-05,
|
| 545 |
+
"loss": 0.0533,
|
| 546 |
+
"num_input_tokens_seen": 32255616,
|
| 547 |
+
"step": 31500
|
| 548 |
+
},
|
| 549 |
+
{
|
| 550 |
+
"epoch": 3.2,
|
| 551 |
+
"grad_norm": 1.1055493354797363,
|
| 552 |
+
"learning_rate": 3.40005e-05,
|
| 553 |
+
"loss": 0.0557,
|
| 554 |
+
"num_input_tokens_seen": 32767616,
|
| 555 |
+
"step": 32000
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 3.25,
|
| 559 |
+
"grad_norm": 1.6912920475006104,
|
| 560 |
+
"learning_rate": 3.37505e-05,
|
| 561 |
+
"loss": 0.0557,
|
| 562 |
+
"num_input_tokens_seen": 33279616,
|
| 563 |
+
"step": 32500
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 3.3,
|
| 567 |
+
"grad_norm": 2.5604867935180664,
|
| 568 |
+
"learning_rate": 3.35005e-05,
|
| 569 |
+
"loss": 0.0619,
|
| 570 |
+
"num_input_tokens_seen": 33791616,
|
| 571 |
+
"step": 33000
|
| 572 |
+
},
|
| 573 |
+
{
|
| 574 |
+
"epoch": 3.35,
|
| 575 |
+
"grad_norm": 1.7852438688278198,
|
| 576 |
+
"learning_rate": 3.32505e-05,
|
| 577 |
+
"loss": 0.0564,
|
| 578 |
+
"num_input_tokens_seen": 34303616,
|
| 579 |
+
"step": 33500
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 3.4,
|
| 583 |
+
"grad_norm": 2.84659481048584,
|
| 584 |
+
"learning_rate": 3.3000500000000004e-05,
|
| 585 |
+
"loss": 0.0563,
|
| 586 |
+
"num_input_tokens_seen": 34815616,
|
| 587 |
+
"step": 34000
|
| 588 |
+
},
|
| 589 |
+
{
|
| 590 |
+
"epoch": 3.45,
|
| 591 |
+
"grad_norm": 2.0315301418304443,
|
| 592 |
+
"learning_rate": 3.27505e-05,
|
| 593 |
+
"loss": 0.054,
|
| 594 |
+
"num_input_tokens_seen": 35327616,
|
| 595 |
+
"step": 34500
|
| 596 |
+
},
|
| 597 |
+
{
|
| 598 |
+
"epoch": 3.5,
|
| 599 |
+
"grad_norm": 1.9043070077896118,
|
| 600 |
+
"learning_rate": 3.25005e-05,
|
| 601 |
+
"loss": 0.0583,
|
| 602 |
+
"num_input_tokens_seen": 35839616,
|
| 603 |
+
"step": 35000
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 3.55,
|
| 607 |
+
"grad_norm": 1.7389405965805054,
|
| 608 |
+
"learning_rate": 3.22505e-05,
|
| 609 |
+
"loss": 0.0544,
|
| 610 |
+
"num_input_tokens_seen": 36351616,
|
| 611 |
+
"step": 35500
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 3.6,
|
| 615 |
+
"grad_norm": 0.8132746815681458,
|
| 616 |
+
"learning_rate": 3.20005e-05,
|
| 617 |
+
"loss": 0.055,
|
| 618 |
+
"num_input_tokens_seen": 36863616,
|
| 619 |
+
"step": 36000
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 3.65,
|
| 623 |
+
"grad_norm": 1.8100671768188477,
|
| 624 |
+
"learning_rate": 3.17505e-05,
|
| 625 |
+
"loss": 0.0558,
|
| 626 |
+
"num_input_tokens_seen": 37375616,
|
| 627 |
+
"step": 36500
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 3.7,
|
| 631 |
+
"grad_norm": 10.433902740478516,
|
| 632 |
+
"learning_rate": 3.15005e-05,
|
| 633 |
+
"loss": 0.0568,
|
| 634 |
+
"num_input_tokens_seen": 37887616,
|
| 635 |
+
"step": 37000
|
| 636 |
+
},
|
| 637 |
+
{
|
| 638 |
+
"epoch": 3.75,
|
| 639 |
+
"grad_norm": 0.7512624263763428,
|
| 640 |
+
"learning_rate": 3.12505e-05,
|
| 641 |
+
"loss": 0.0541,
|
| 642 |
+
"num_input_tokens_seen": 38399616,
|
| 643 |
+
"step": 37500
|
| 644 |
+
},
|
| 645 |
+
{
|
| 646 |
+
"epoch": 3.8,
|
| 647 |
+
"grad_norm": 1.3957535028457642,
|
| 648 |
+
"learning_rate": 3.1000499999999996e-05,
|
| 649 |
+
"loss": 0.0546,
|
| 650 |
+
"num_input_tokens_seen": 38911616,
|
| 651 |
+
"step": 38000
|
| 652 |
+
},
|
| 653 |
+
{
|
| 654 |
+
"epoch": 3.85,
|
| 655 |
+
"grad_norm": 1.069032073020935,
|
| 656 |
+
"learning_rate": 3.0750499999999996e-05,
|
| 657 |
+
"loss": 0.0547,
|
| 658 |
+
"num_input_tokens_seen": 39423616,
|
| 659 |
+
"step": 38500
|
| 660 |
+
},
|
| 661 |
+
{
|
| 662 |
+
"epoch": 3.9,
|
| 663 |
+
"grad_norm": 3.4046223163604736,
|
| 664 |
+
"learning_rate": 3.0500500000000004e-05,
|
| 665 |
+
"loss": 0.0567,
|
| 666 |
+
"num_input_tokens_seen": 39935616,
|
| 667 |
+
"step": 39000
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 3.95,
|
| 671 |
+
"grad_norm": 1.5711253881454468,
|
| 672 |
+
"learning_rate": 3.0250500000000005e-05,
|
| 673 |
+
"loss": 0.0571,
|
| 674 |
+
"num_input_tokens_seen": 40447616,
|
| 675 |
+
"step": 39500
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 4.0,
|
| 679 |
+
"grad_norm": 2.8568646907806396,
|
| 680 |
+
"learning_rate": 3.0000500000000005e-05,
|
| 681 |
+
"loss": 0.054,
|
| 682 |
+
"num_input_tokens_seen": 40959488,
|
| 683 |
+
"step": 40000
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 4.0,
|
| 687 |
+
"eval_combined_score": 0.1528494923779644,
|
| 688 |
+
"eval_loss": 0.152849480509758,
|
| 689 |
+
"eval_mse": 0.15284948934500966,
|
| 690 |
+
"eval_runtime": 29.495,
|
| 691 |
+
"eval_samples_per_second": 678.08,
|
| 692 |
+
"eval_steps_per_second": 84.76,
|
| 693 |
+
"num_input_tokens_seen": 40959488,
|
| 694 |
+
"step": 40000
|
| 695 |
+
},
|
| 696 |
+
{
|
| 697 |
+
"epoch": 4.05,
|
| 698 |
+
"grad_norm": 1.1214642524719238,
|
| 699 |
+
"learning_rate": 2.9750500000000003e-05,
|
| 700 |
+
"loss": 0.0365,
|
| 701 |
+
"num_input_tokens_seen": 41471488,
|
| 702 |
+
"step": 40500
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 4.1,
|
| 706 |
+
"grad_norm": 2.6408936977386475,
|
| 707 |
+
"learning_rate": 2.9500500000000003e-05,
|
| 708 |
+
"loss": 0.0361,
|
| 709 |
+
"num_input_tokens_seen": 41983488,
|
| 710 |
+
"step": 41000
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 4.15,
|
| 714 |
+
"grad_norm": 1.0093015432357788,
|
| 715 |
+
"learning_rate": 2.9250500000000004e-05,
|
| 716 |
+
"loss": 0.0361,
|
| 717 |
+
"num_input_tokens_seen": 42495488,
|
| 718 |
+
"step": 41500
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 4.2,
|
| 722 |
+
"grad_norm": 2.0412521362304688,
|
| 723 |
+
"learning_rate": 2.90005e-05,
|
| 724 |
+
"loss": 0.0377,
|
| 725 |
+
"num_input_tokens_seen": 43007488,
|
| 726 |
+
"step": 42000
|
| 727 |
+
},
|
| 728 |
+
{
|
| 729 |
+
"epoch": 4.25,
|
| 730 |
+
"grad_norm": 2.0059244632720947,
|
| 731 |
+
"learning_rate": 2.8750500000000002e-05,
|
| 732 |
+
"loss": 0.0354,
|
| 733 |
+
"num_input_tokens_seen": 43519488,
|
| 734 |
+
"step": 42500
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 4.3,
|
| 738 |
+
"grad_norm": 3.214423179626465,
|
| 739 |
+
"learning_rate": 2.8500500000000003e-05,
|
| 740 |
+
"loss": 0.0373,
|
| 741 |
+
"num_input_tokens_seen": 44031488,
|
| 742 |
+
"step": 43000
|
| 743 |
+
},
|
| 744 |
+
{
|
| 745 |
+
"epoch": 4.35,
|
| 746 |
+
"grad_norm": 2.101541519165039,
|
| 747 |
+
"learning_rate": 2.8250500000000003e-05,
|
| 748 |
+
"loss": 0.0381,
|
| 749 |
+
"num_input_tokens_seen": 44543488,
|
| 750 |
+
"step": 43500
|
| 751 |
+
},
|
| 752 |
+
{
|
| 753 |
+
"epoch": 4.4,
|
| 754 |
+
"grad_norm": 0.8797721862792969,
|
| 755 |
+
"learning_rate": 2.80005e-05,
|
| 756 |
+
"loss": 0.0381,
|
| 757 |
+
"num_input_tokens_seen": 45055488,
|
| 758 |
+
"step": 44000
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 4.45,
|
| 762 |
+
"grad_norm": 2.0589728355407715,
|
| 763 |
+
"learning_rate": 2.77505e-05,
|
| 764 |
+
"loss": 0.036,
|
| 765 |
+
"num_input_tokens_seen": 45567488,
|
| 766 |
+
"step": 44500
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 4.5,
|
| 770 |
+
"grad_norm": 2.5758140087127686,
|
| 771 |
+
"learning_rate": 2.7500500000000002e-05,
|
| 772 |
+
"loss": 0.0372,
|
| 773 |
+
"num_input_tokens_seen": 46079488,
|
| 774 |
+
"step": 45000
|
| 775 |
+
},
|
| 776 |
+
{
|
| 777 |
+
"epoch": 4.55,
|
| 778 |
+
"grad_norm": 1.531252145767212,
|
| 779 |
+
"learning_rate": 2.72505e-05,
|
| 780 |
+
"loss": 0.0381,
|
| 781 |
+
"num_input_tokens_seen": 46591488,
|
| 782 |
+
"step": 45500
|
| 783 |
+
},
|
| 784 |
+
{
|
| 785 |
+
"epoch": 4.6,
|
| 786 |
+
"grad_norm": 1.053691029548645,
|
| 787 |
+
"learning_rate": 2.70005e-05,
|
| 788 |
+
"loss": 0.0396,
|
| 789 |
+
"num_input_tokens_seen": 47103488,
|
| 790 |
+
"step": 46000
|
| 791 |
+
},
|
| 792 |
+
{
|
| 793 |
+
"epoch": 4.65,
|
| 794 |
+
"grad_norm": 1.031100869178772,
|
| 795 |
+
"learning_rate": 2.67505e-05,
|
| 796 |
+
"loss": 0.0376,
|
| 797 |
+
"num_input_tokens_seen": 47615488,
|
| 798 |
+
"step": 46500
|
| 799 |
+
},
|
| 800 |
+
{
|
| 801 |
+
"epoch": 4.7,
|
| 802 |
+
"grad_norm": 0.8592771887779236,
|
| 803 |
+
"learning_rate": 2.65005e-05,
|
| 804 |
+
"loss": 0.0381,
|
| 805 |
+
"num_input_tokens_seen": 48127488,
|
| 806 |
+
"step": 47000
|
| 807 |
+
},
|
| 808 |
+
{
|
| 809 |
+
"epoch": 4.75,
|
| 810 |
+
"grad_norm": 3.529454231262207,
|
| 811 |
+
"learning_rate": 2.62505e-05,
|
| 812 |
+
"loss": 0.0406,
|
| 813 |
+
"num_input_tokens_seen": 48639488,
|
| 814 |
+
"step": 47500
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 4.8,
|
| 818 |
+
"grad_norm": 1.2595094442367554,
|
| 819 |
+
"learning_rate": 2.60005e-05,
|
| 820 |
+
"loss": 0.044,
|
| 821 |
+
"num_input_tokens_seen": 49151488,
|
| 822 |
+
"step": 48000
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 4.85,
|
| 826 |
+
"grad_norm": 1.0460163354873657,
|
| 827 |
+
"learning_rate": 2.57505e-05,
|
| 828 |
+
"loss": 0.0411,
|
| 829 |
+
"num_input_tokens_seen": 49663488,
|
| 830 |
+
"step": 48500
|
| 831 |
+
},
|
| 832 |
+
{
|
| 833 |
+
"epoch": 4.9,
|
| 834 |
+
"grad_norm": 0.7415432333946228,
|
| 835 |
+
"learning_rate": 2.55005e-05,
|
| 836 |
+
"loss": 0.0376,
|
| 837 |
+
"num_input_tokens_seen": 50175488,
|
| 838 |
+
"step": 49000
|
| 839 |
+
},
|
| 840 |
+
{
|
| 841 |
+
"epoch": 4.95,
|
| 842 |
+
"grad_norm": 0.9863350987434387,
|
| 843 |
+
"learning_rate": 2.5250499999999998e-05,
|
| 844 |
+
"loss": 0.039,
|
| 845 |
+
"num_input_tokens_seen": 50687488,
|
| 846 |
+
"step": 49500
|
| 847 |
+
},
|
| 848 |
+
{
|
| 849 |
+
"epoch": 5.0,
|
| 850 |
+
"grad_norm": 2.2840659618377686,
|
| 851 |
+
"learning_rate": 2.50005e-05,
|
| 852 |
+
"loss": 0.0372,
|
| 853 |
+
"num_input_tokens_seen": 51199360,
|
| 854 |
+
"step": 50000
|
| 855 |
+
},
|
| 856 |
+
{
|
| 857 |
+
"epoch": 5.0,
|
| 858 |
+
"eval_combined_score": 0.14802570643204935,
|
| 859 |
+
"eval_loss": 0.14802570641040802,
|
| 860 |
+
"eval_mse": 0.14802570645369068,
|
| 861 |
+
"eval_runtime": 29.5199,
|
| 862 |
+
"eval_samples_per_second": 677.508,
|
| 863 |
+
"eval_steps_per_second": 84.689,
|
| 864 |
+
"num_input_tokens_seen": 51199360,
|
| 865 |
+
"step": 50000
|
| 866 |
+
},
|
| 867 |
+
{
|
| 868 |
+
"epoch": 5.05,
|
| 869 |
+
"grad_norm": 1.0202912092208862,
|
| 870 |
+
"learning_rate": 2.4750500000000003e-05,
|
| 871 |
+
"loss": 0.0253,
|
| 872 |
+
"num_input_tokens_seen": 51711360,
|
| 873 |
+
"step": 50500
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 5.1,
|
| 877 |
+
"grad_norm": 1.1298741102218628,
|
| 878 |
+
"learning_rate": 2.45005e-05,
|
| 879 |
+
"loss": 0.0269,
|
| 880 |
+
"num_input_tokens_seen": 52223360,
|
| 881 |
+
"step": 51000
|
| 882 |
+
},
|
| 883 |
+
{
|
| 884 |
+
"epoch": 5.15,
|
| 885 |
+
"grad_norm": 1.2378206253051758,
|
| 886 |
+
"learning_rate": 2.42505e-05,
|
| 887 |
+
"loss": 0.0258,
|
| 888 |
+
"num_input_tokens_seen": 52735360,
|
| 889 |
+
"step": 51500
|
| 890 |
+
},
|
| 891 |
+
{
|
| 892 |
+
"epoch": 5.2,
|
| 893 |
+
"grad_norm": 1.6293431520462036,
|
| 894 |
+
"learning_rate": 2.4000500000000002e-05,
|
| 895 |
+
"loss": 0.0272,
|
| 896 |
+
"num_input_tokens_seen": 53247360,
|
| 897 |
+
"step": 52000
|
| 898 |
+
},
|
| 899 |
+
{
|
| 900 |
+
"epoch": 5.25,
|
| 901 |
+
"grad_norm": 3.9734299182891846,
|
| 902 |
+
"learning_rate": 2.37505e-05,
|
| 903 |
+
"loss": 0.0272,
|
| 904 |
+
"num_input_tokens_seen": 53759360,
|
| 905 |
+
"step": 52500
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 5.3,
|
| 909 |
+
"grad_norm": 0.6598159074783325,
|
| 910 |
+
"learning_rate": 2.35005e-05,
|
| 911 |
+
"loss": 0.0262,
|
| 912 |
+
"num_input_tokens_seen": 54271360,
|
| 913 |
+
"step": 53000
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 5.35,
|
| 917 |
+
"grad_norm": 0.6012576818466187,
|
| 918 |
+
"learning_rate": 2.32505e-05,
|
| 919 |
+
"loss": 0.027,
|
| 920 |
+
"num_input_tokens_seen": 54783360,
|
| 921 |
+
"step": 53500
|
| 922 |
+
},
|
| 923 |
+
{
|
| 924 |
+
"epoch": 5.4,
|
| 925 |
+
"grad_norm": 2.462887763977051,
|
| 926 |
+
"learning_rate": 2.30005e-05,
|
| 927 |
+
"loss": 0.0268,
|
| 928 |
+
"num_input_tokens_seen": 55295360,
|
| 929 |
+
"step": 54000
|
| 930 |
+
},
|
| 931 |
+
{
|
| 932 |
+
"epoch": 5.45,
|
| 933 |
+
"grad_norm": 2.0268304347991943,
|
| 934 |
+
"learning_rate": 2.2750500000000002e-05,
|
| 935 |
+
"loss": 0.0263,
|
| 936 |
+
"num_input_tokens_seen": 55807360,
|
| 937 |
+
"step": 54500
|
| 938 |
+
},
|
| 939 |
+
{
|
| 940 |
+
"epoch": 5.5,
|
| 941 |
+
"grad_norm": 0.8000567555427551,
|
| 942 |
+
"learning_rate": 2.2500500000000003e-05,
|
| 943 |
+
"loss": 0.0282,
|
| 944 |
+
"num_input_tokens_seen": 56319360,
|
| 945 |
+
"step": 55000
|
| 946 |
+
},
|
| 947 |
+
{
|
| 948 |
+
"epoch": 5.55,
|
| 949 |
+
"grad_norm": 1.5781893730163574,
|
| 950 |
+
"learning_rate": 2.2250500000000003e-05,
|
| 951 |
+
"loss": 0.0265,
|
| 952 |
+
"num_input_tokens_seen": 56831360,
|
| 953 |
+
"step": 55500
|
| 954 |
+
},
|
| 955 |
+
{
|
| 956 |
+
"epoch": 5.6,
|
| 957 |
+
"grad_norm": 1.2630614042282104,
|
| 958 |
+
"learning_rate": 2.20005e-05,
|
| 959 |
+
"loss": 0.0257,
|
| 960 |
+
"num_input_tokens_seen": 57343360,
|
| 961 |
+
"step": 56000
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 5.65,
|
| 965 |
+
"grad_norm": 1.3778091669082642,
|
| 966 |
+
"learning_rate": 2.17505e-05,
|
| 967 |
+
"loss": 0.0271,
|
| 968 |
+
"num_input_tokens_seen": 57855360,
|
| 969 |
+
"step": 56500
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 5.7,
|
| 973 |
+
"grad_norm": 1.0909324884414673,
|
| 974 |
+
"learning_rate": 2.1500500000000002e-05,
|
| 975 |
+
"loss": 0.026,
|
| 976 |
+
"num_input_tokens_seen": 58367360,
|
| 977 |
+
"step": 57000
|
| 978 |
+
},
|
| 979 |
+
{
|
| 980 |
+
"epoch": 5.75,
|
| 981 |
+
"grad_norm": 3.5209500789642334,
|
| 982 |
+
"learning_rate": 2.1250500000000003e-05,
|
| 983 |
+
"loss": 0.0264,
|
| 984 |
+
"num_input_tokens_seen": 58879360,
|
| 985 |
+
"step": 57500
|
| 986 |
+
},
|
| 987 |
+
{
|
| 988 |
+
"epoch": 5.8,
|
| 989 |
+
"grad_norm": 1.4671865701675415,
|
| 990 |
+
"learning_rate": 2.10005e-05,
|
| 991 |
+
"loss": 0.0265,
|
| 992 |
+
"num_input_tokens_seen": 59391360,
|
| 993 |
+
"step": 58000
|
| 994 |
+
},
|
| 995 |
+
{
|
| 996 |
+
"epoch": 5.85,
|
| 997 |
+
"grad_norm": 1.6409125328063965,
|
| 998 |
+
"learning_rate": 2.07505e-05,
|
| 999 |
+
"loss": 0.0268,
|
| 1000 |
+
"num_input_tokens_seen": 59903360,
|
| 1001 |
+
"step": 58500
|
| 1002 |
+
},
|
| 1003 |
+
{
|
| 1004 |
+
"epoch": 5.9,
|
| 1005 |
+
"grad_norm": 1.4418998956680298,
|
| 1006 |
+
"learning_rate": 2.05005e-05,
|
| 1007 |
+
"loss": 0.0262,
|
| 1008 |
+
"num_input_tokens_seen": 60415360,
|
| 1009 |
+
"step": 59000
|
| 1010 |
+
},
|
| 1011 |
+
{
|
| 1012 |
+
"epoch": 5.95,
|
| 1013 |
+
"grad_norm": 1.3441293239593506,
|
| 1014 |
+
"learning_rate": 2.02505e-05,
|
| 1015 |
+
"loss": 0.0257,
|
| 1016 |
+
"num_input_tokens_seen": 60927360,
|
| 1017 |
+
"step": 59500
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 6.0,
|
| 1021 |
+
"grad_norm": 0.8778462409973145,
|
| 1022 |
+
"learning_rate": 2.00005e-05,
|
| 1023 |
+
"loss": 0.0263,
|
| 1024 |
+
"num_input_tokens_seen": 61439232,
|
| 1025 |
+
"step": 60000
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 6.0,
|
| 1029 |
+
"eval_combined_score": 0.15236617343673117,
|
| 1030 |
+
"eval_loss": 0.15236616134643555,
|
| 1031 |
+
"eval_mse": 0.1523661706258656,
|
| 1032 |
+
"eval_runtime": 29.4149,
|
| 1033 |
+
"eval_samples_per_second": 679.926,
|
| 1034 |
+
"eval_steps_per_second": 84.991,
|
| 1035 |
+
"num_input_tokens_seen": 61439232,
|
| 1036 |
+
"step": 60000
|
| 1037 |
+
},
|
| 1038 |
+
{
|
| 1039 |
+
"epoch": 6.05,
|
| 1040 |
+
"grad_norm": 1.4335697889328003,
|
| 1041 |
+
"learning_rate": 1.97505e-05,
|
| 1042 |
+
"loss": 0.0181,
|
| 1043 |
+
"num_input_tokens_seen": 61951232,
|
| 1044 |
+
"step": 60500
|
| 1045 |
+
},
|
| 1046 |
+
{
|
| 1047 |
+
"epoch": 6.1,
|
| 1048 |
+
"grad_norm": 1.1381551027297974,
|
| 1049 |
+
"learning_rate": 1.95005e-05,
|
| 1050 |
+
"loss": 0.0197,
|
| 1051 |
+
"num_input_tokens_seen": 62463232,
|
| 1052 |
+
"step": 61000
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 6.15,
|
| 1056 |
+
"grad_norm": 0.7046132683753967,
|
| 1057 |
+
"learning_rate": 1.92505e-05,
|
| 1058 |
+
"loss": 0.0186,
|
| 1059 |
+
"num_input_tokens_seen": 62975232,
|
| 1060 |
+
"step": 61500
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"epoch": 6.2,
|
| 1064 |
+
"grad_norm": 1.008306860923767,
|
| 1065 |
+
"learning_rate": 1.9000500000000002e-05,
|
| 1066 |
+
"loss": 0.0192,
|
| 1067 |
+
"num_input_tokens_seen": 63487232,
|
| 1068 |
+
"step": 62000
|
| 1069 |
+
},
|
| 1070 |
+
{
|
| 1071 |
+
"epoch": 6.25,
|
| 1072 |
+
"grad_norm": 2.0765221118927,
|
| 1073 |
+
"learning_rate": 1.8750500000000003e-05,
|
| 1074 |
+
"loss": 0.0185,
|
| 1075 |
+
"num_input_tokens_seen": 63999232,
|
| 1076 |
+
"step": 62500
|
| 1077 |
+
},
|
| 1078 |
+
{
|
| 1079 |
+
"epoch": 6.3,
|
| 1080 |
+
"grad_norm": 1.2361551523208618,
|
| 1081 |
+
"learning_rate": 1.85005e-05,
|
| 1082 |
+
"loss": 0.0179,
|
| 1083 |
+
"num_input_tokens_seen": 64511232,
|
| 1084 |
+
"step": 63000
|
| 1085 |
+
},
|
| 1086 |
+
{
|
| 1087 |
+
"epoch": 6.35,
|
| 1088 |
+
"grad_norm": 0.7231354117393494,
|
| 1089 |
+
"learning_rate": 1.82505e-05,
|
| 1090 |
+
"loss": 0.0194,
|
| 1091 |
+
"num_input_tokens_seen": 65023232,
|
| 1092 |
+
"step": 63500
|
| 1093 |
+
},
|
| 1094 |
+
{
|
| 1095 |
+
"epoch": 6.4,
|
| 1096 |
+
"grad_norm": 0.779230535030365,
|
| 1097 |
+
"learning_rate": 1.80005e-05,
|
| 1098 |
+
"loss": 0.0198,
|
| 1099 |
+
"num_input_tokens_seen": 65535232,
|
| 1100 |
+
"step": 64000
|
| 1101 |
+
},
|
| 1102 |
+
{
|
| 1103 |
+
"epoch": 6.45,
|
| 1104 |
+
"grad_norm": 0.7320069074630737,
|
| 1105 |
+
"learning_rate": 1.77505e-05,
|
| 1106 |
+
"loss": 0.0187,
|
| 1107 |
+
"num_input_tokens_seen": 66047232,
|
| 1108 |
+
"step": 64500
|
| 1109 |
+
},
|
| 1110 |
+
{
|
| 1111 |
+
"epoch": 6.5,
|
| 1112 |
+
"grad_norm": 0.8597579598426819,
|
| 1113 |
+
"learning_rate": 1.75005e-05,
|
| 1114 |
+
"loss": 0.0191,
|
| 1115 |
+
"num_input_tokens_seen": 66559232,
|
| 1116 |
+
"step": 65000
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 6.55,
|
| 1120 |
+
"grad_norm": 1.4109529256820679,
|
| 1121 |
+
"learning_rate": 1.72505e-05,
|
| 1122 |
+
"loss": 0.0192,
|
| 1123 |
+
"num_input_tokens_seen": 67071232,
|
| 1124 |
+
"step": 65500
|
| 1125 |
+
},
|
| 1126 |
+
{
|
| 1127 |
+
"epoch": 6.6,
|
| 1128 |
+
"grad_norm": 1.4900848865509033,
|
| 1129 |
+
"learning_rate": 1.70005e-05,
|
| 1130 |
+
"loss": 0.0173,
|
| 1131 |
+
"num_input_tokens_seen": 67583232,
|
| 1132 |
+
"step": 66000
|
| 1133 |
+
},
|
| 1134 |
+
{
|
| 1135 |
+
"epoch": 6.65,
|
| 1136 |
+
"grad_norm": 1.3828743696212769,
|
| 1137 |
+
"learning_rate": 1.6750499999999998e-05,
|
| 1138 |
+
"loss": 0.0176,
|
| 1139 |
+
"num_input_tokens_seen": 68095232,
|
| 1140 |
+
"step": 66500
|
| 1141 |
+
},
|
| 1142 |
+
{
|
| 1143 |
+
"epoch": 6.7,
|
| 1144 |
+
"grad_norm": 0.6733376383781433,
|
| 1145 |
+
"learning_rate": 1.6500500000000002e-05,
|
| 1146 |
+
"loss": 0.019,
|
| 1147 |
+
"num_input_tokens_seen": 68607232,
|
| 1148 |
+
"step": 67000
|
| 1149 |
+
},
|
| 1150 |
+
{
|
| 1151 |
+
"epoch": 6.75,
|
| 1152 |
+
"grad_norm": 0.4570697546005249,
|
| 1153 |
+
"learning_rate": 1.6250500000000003e-05,
|
| 1154 |
+
"loss": 0.0181,
|
| 1155 |
+
"num_input_tokens_seen": 69119232,
|
| 1156 |
+
"step": 67500
|
| 1157 |
+
},
|
| 1158 |
+
{
|
| 1159 |
+
"epoch": 6.8,
|
| 1160 |
+
"grad_norm": 0.9463149309158325,
|
| 1161 |
+
"learning_rate": 1.60005e-05,
|
| 1162 |
+
"loss": 0.0174,
|
| 1163 |
+
"num_input_tokens_seen": 69631232,
|
| 1164 |
+
"step": 68000
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 6.85,
|
| 1168 |
+
"grad_norm": 0.9304377436637878,
|
| 1169 |
+
"learning_rate": 1.57505e-05,
|
| 1170 |
+
"loss": 0.0185,
|
| 1171 |
+
"num_input_tokens_seen": 70143232,
|
| 1172 |
+
"step": 68500
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 6.9,
|
| 1176 |
+
"grad_norm": 0.8526313304901123,
|
| 1177 |
+
"learning_rate": 1.5500500000000002e-05,
|
| 1178 |
+
"loss": 0.0185,
|
| 1179 |
+
"num_input_tokens_seen": 70655232,
|
| 1180 |
+
"step": 69000
|
| 1181 |
+
},
|
| 1182 |
+
{
|
| 1183 |
+
"epoch": 6.95,
|
| 1184 |
+
"grad_norm": 1.6793274879455566,
|
| 1185 |
+
"learning_rate": 1.52505e-05,
|
| 1186 |
+
"loss": 0.0194,
|
| 1187 |
+
"num_input_tokens_seen": 71167232,
|
| 1188 |
+
"step": 69500
|
| 1189 |
+
},
|
| 1190 |
+
{
|
| 1191 |
+
"epoch": 7.0,
|
| 1192 |
+
"grad_norm": 1.2873644828796387,
|
| 1193 |
+
"learning_rate": 1.5000500000000001e-05,
|
| 1194 |
+
"loss": 0.0203,
|
| 1195 |
+
"num_input_tokens_seen": 71679104,
|
| 1196 |
+
"step": 70000
|
| 1197 |
+
},
|
| 1198 |
+
{
|
| 1199 |
+
"epoch": 7.0,
|
| 1200 |
+
"eval_combined_score": 0.1494929350818927,
|
| 1201 |
+
"eval_loss": 0.14949294924736023,
|
| 1202 |
+
"eval_mse": 0.14949293581758635,
|
| 1203 |
+
"eval_runtime": 29.5374,
|
| 1204 |
+
"eval_samples_per_second": 677.107,
|
| 1205 |
+
"eval_steps_per_second": 84.638,
|
| 1206 |
+
"num_input_tokens_seen": 71679104,
|
| 1207 |
+
"step": 70000
|
| 1208 |
+
},
|
| 1209 |
+
{
|
| 1210 |
+
"epoch": 7.05,
|
| 1211 |
+
"grad_norm": 0.8493014574050903,
|
| 1212 |
+
"learning_rate": 1.47505e-05,
|
| 1213 |
+
"loss": 0.014,
|
| 1214 |
+
"num_input_tokens_seen": 72191104,
|
| 1215 |
+
"step": 70500
|
| 1216 |
+
},
|
| 1217 |
+
{
|
| 1218 |
+
"epoch": 7.1,
|
| 1219 |
+
"grad_norm": 0.6162556409835815,
|
| 1220 |
+
"learning_rate": 1.45005e-05,
|
| 1221 |
+
"loss": 0.0145,
|
| 1222 |
+
"num_input_tokens_seen": 72703104,
|
| 1223 |
+
"step": 71000
|
| 1224 |
+
},
|
| 1225 |
+
{
|
| 1226 |
+
"epoch": 7.15,
|
| 1227 |
+
"grad_norm": 0.6198768019676208,
|
| 1228 |
+
"learning_rate": 1.42505e-05,
|
| 1229 |
+
"loss": 0.0135,
|
| 1230 |
+
"num_input_tokens_seen": 73215104,
|
| 1231 |
+
"step": 71500
|
| 1232 |
+
},
|
| 1233 |
+
{
|
| 1234 |
+
"epoch": 7.2,
|
| 1235 |
+
"grad_norm": 0.6122292876243591,
|
| 1236 |
+
"learning_rate": 1.40005e-05,
|
| 1237 |
+
"loss": 0.0138,
|
| 1238 |
+
"num_input_tokens_seen": 73727104,
|
| 1239 |
+
"step": 72000
|
| 1240 |
+
},
|
| 1241 |
+
{
|
| 1242 |
+
"epoch": 7.25,
|
| 1243 |
+
"grad_norm": 0.8132468461990356,
|
| 1244 |
+
"learning_rate": 1.37505e-05,
|
| 1245 |
+
"loss": 0.0136,
|
| 1246 |
+
"num_input_tokens_seen": 74239104,
|
| 1247 |
+
"step": 72500
|
| 1248 |
+
},
|
| 1249 |
+
{
|
| 1250 |
+
"epoch": 7.3,
|
| 1251 |
+
"grad_norm": 0.791746973991394,
|
| 1252 |
+
"learning_rate": 1.3500499999999999e-05,
|
| 1253 |
+
"loss": 0.0136,
|
| 1254 |
+
"num_input_tokens_seen": 74751104,
|
| 1255 |
+
"step": 73000
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 7.35,
|
| 1259 |
+
"grad_norm": 1.6126739978790283,
|
| 1260 |
+
"learning_rate": 1.3250500000000001e-05,
|
| 1261 |
+
"loss": 0.0139,
|
| 1262 |
+
"num_input_tokens_seen": 75263104,
|
| 1263 |
+
"step": 73500
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 7.4,
|
| 1267 |
+
"grad_norm": 1.348046898841858,
|
| 1268 |
+
"learning_rate": 1.3000500000000002e-05,
|
| 1269 |
+
"loss": 0.0149,
|
| 1270 |
+
"num_input_tokens_seen": 75775104,
|
| 1271 |
+
"step": 74000
|
| 1272 |
+
},
|
| 1273 |
+
{
|
| 1274 |
+
"epoch": 7.45,
|
| 1275 |
+
"grad_norm": 1.5154032707214355,
|
| 1276 |
+
"learning_rate": 1.2750500000000001e-05,
|
| 1277 |
+
"loss": 0.0133,
|
| 1278 |
+
"num_input_tokens_seen": 76287104,
|
| 1279 |
+
"step": 74500
|
| 1280 |
+
},
|
| 1281 |
+
{
|
| 1282 |
+
"epoch": 7.5,
|
| 1283 |
+
"grad_norm": 1.3086836338043213,
|
| 1284 |
+
"learning_rate": 1.2500500000000002e-05,
|
| 1285 |
+
"loss": 0.0134,
|
| 1286 |
+
"num_input_tokens_seen": 76799104,
|
| 1287 |
+
"step": 75000
|
| 1288 |
+
},
|
| 1289 |
+
{
|
| 1290 |
+
"epoch": 7.55,
|
| 1291 |
+
"grad_norm": 1.3077424764633179,
|
| 1292 |
+
"learning_rate": 1.22505e-05,
|
| 1293 |
+
"loss": 0.0134,
|
| 1294 |
+
"num_input_tokens_seen": 77311104,
|
| 1295 |
+
"step": 75500
|
| 1296 |
+
},
|
| 1297 |
+
{
|
| 1298 |
+
"epoch": 7.6,
|
| 1299 |
+
"grad_norm": 1.377185344696045,
|
| 1300 |
+
"learning_rate": 1.2000500000000001e-05,
|
| 1301 |
+
"loss": 0.0128,
|
| 1302 |
+
"num_input_tokens_seen": 77823104,
|
| 1303 |
+
"step": 76000
|
| 1304 |
+
},
|
| 1305 |
+
{
|
| 1306 |
+
"epoch": 7.65,
|
| 1307 |
+
"grad_norm": 1.2250688076019287,
|
| 1308 |
+
"learning_rate": 1.17505e-05,
|
| 1309 |
+
"loss": 0.0146,
|
| 1310 |
+
"num_input_tokens_seen": 78335104,
|
| 1311 |
+
"step": 76500
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 7.7,
|
| 1315 |
+
"grad_norm": 0.8044687509536743,
|
| 1316 |
+
"learning_rate": 1.15005e-05,
|
| 1317 |
+
"loss": 0.0132,
|
| 1318 |
+
"num_input_tokens_seen": 78847104,
|
| 1319 |
+
"step": 77000
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 7.75,
|
| 1323 |
+
"grad_norm": 0.8126741647720337,
|
| 1324 |
+
"learning_rate": 1.12505e-05,
|
| 1325 |
+
"loss": 0.0134,
|
| 1326 |
+
"num_input_tokens_seen": 79359104,
|
| 1327 |
+
"step": 77500
|
| 1328 |
+
},
|
| 1329 |
+
{
|
| 1330 |
+
"epoch": 7.8,
|
| 1331 |
+
"grad_norm": 0.6075248122215271,
|
| 1332 |
+
"learning_rate": 1.10005e-05,
|
| 1333 |
+
"loss": 0.0131,
|
| 1334 |
+
"num_input_tokens_seen": 79871104,
|
| 1335 |
+
"step": 78000
|
| 1336 |
+
},
|
| 1337 |
+
{
|
| 1338 |
+
"epoch": 7.85,
|
| 1339 |
+
"grad_norm": 1.874189853668213,
|
| 1340 |
+
"learning_rate": 1.0750500000000002e-05,
|
| 1341 |
+
"loss": 0.0134,
|
| 1342 |
+
"num_input_tokens_seen": 80383104,
|
| 1343 |
+
"step": 78500
|
| 1344 |
+
},
|
| 1345 |
+
{
|
| 1346 |
+
"epoch": 7.9,
|
| 1347 |
+
"grad_norm": 0.5488854646682739,
|
| 1348 |
+
"learning_rate": 1.05005e-05,
|
| 1349 |
+
"loss": 0.0137,
|
| 1350 |
+
"num_input_tokens_seen": 80895104,
|
| 1351 |
+
"step": 79000
|
| 1352 |
+
},
|
| 1353 |
+
{
|
| 1354 |
+
"epoch": 7.95,
|
| 1355 |
+
"grad_norm": 1.5739060640335083,
|
| 1356 |
+
"learning_rate": 1.0250500000000001e-05,
|
| 1357 |
+
"loss": 0.0131,
|
| 1358 |
+
"num_input_tokens_seen": 81407104,
|
| 1359 |
+
"step": 79500
|
| 1360 |
+
},
|
| 1361 |
+
{
|
| 1362 |
+
"epoch": 8.0,
|
| 1363 |
+
"grad_norm": 1.897755742073059,
|
| 1364 |
+
"learning_rate": 1.00005e-05,
|
| 1365 |
+
"loss": 0.0135,
|
| 1366 |
+
"num_input_tokens_seen": 81918976,
|
| 1367 |
+
"step": 80000
|
| 1368 |
+
},
|
| 1369 |
+
{
|
| 1370 |
+
"epoch": 8.0,
|
| 1371 |
+
"eval_combined_score": 0.1482119562218898,
|
| 1372 |
+
"eval_loss": 0.14821195602416992,
|
| 1373 |
+
"eval_mse": 0.14821195641960966,
|
| 1374 |
+
"eval_runtime": 29.5069,
|
| 1375 |
+
"eval_samples_per_second": 677.807,
|
| 1376 |
+
"eval_steps_per_second": 84.726,
|
| 1377 |
+
"num_input_tokens_seen": 81918976,
|
| 1378 |
+
"step": 80000
|
| 1379 |
+
},
|
| 1380 |
+
{
|
| 1381 |
+
"epoch": 8.05,
|
| 1382 |
+
"grad_norm": 0.39859962463378906,
|
| 1383 |
+
"learning_rate": 9.7505e-06,
|
| 1384 |
+
"loss": 0.0107,
|
| 1385 |
+
"num_input_tokens_seen": 82430976,
|
| 1386 |
+
"step": 80500
|
| 1387 |
+
},
|
| 1388 |
+
{
|
| 1389 |
+
"epoch": 8.1,
|
| 1390 |
+
"grad_norm": 1.8892147541046143,
|
| 1391 |
+
"learning_rate": 9.500500000000002e-06,
|
| 1392 |
+
"loss": 0.01,
|
| 1393 |
+
"num_input_tokens_seen": 82942976,
|
| 1394 |
+
"step": 81000
|
| 1395 |
+
},
|
| 1396 |
+
{
|
| 1397 |
+
"epoch": 8.15,
|
| 1398 |
+
"grad_norm": 0.7789964079856873,
|
| 1399 |
+
"learning_rate": 9.2505e-06,
|
| 1400 |
+
"loss": 0.0111,
|
| 1401 |
+
"num_input_tokens_seen": 83454976,
|
| 1402 |
+
"step": 81500
|
| 1403 |
+
},
|
| 1404 |
+
{
|
| 1405 |
+
"epoch": 8.2,
|
| 1406 |
+
"grad_norm": 0.6423227787017822,
|
| 1407 |
+
"learning_rate": 9.000500000000001e-06,
|
| 1408 |
+
"loss": 0.011,
|
| 1409 |
+
"num_input_tokens_seen": 83966976,
|
| 1410 |
+
"step": 82000
|
| 1411 |
+
},
|
| 1412 |
+
{
|
| 1413 |
+
"epoch": 8.25,
|
| 1414 |
+
"grad_norm": 0.6862022876739502,
|
| 1415 |
+
"learning_rate": 8.7505e-06,
|
| 1416 |
+
"loss": 0.0105,
|
| 1417 |
+
"num_input_tokens_seen": 84478976,
|
| 1418 |
+
"step": 82500
|
| 1419 |
+
},
|
| 1420 |
+
{
|
| 1421 |
+
"epoch": 8.3,
|
| 1422 |
+
"grad_norm": 0.6521459817886353,
|
| 1423 |
+
"learning_rate": 8.5005e-06,
|
| 1424 |
+
"loss": 0.011,
|
| 1425 |
+
"num_input_tokens_seen": 84990976,
|
| 1426 |
+
"step": 83000
|
| 1427 |
+
},
|
| 1428 |
+
{
|
| 1429 |
+
"epoch": 8.35,
|
| 1430 |
+
"grad_norm": 1.0782101154327393,
|
| 1431 |
+
"learning_rate": 8.2505e-06,
|
| 1432 |
+
"loss": 0.01,
|
| 1433 |
+
"num_input_tokens_seen": 85502976,
|
| 1434 |
+
"step": 83500
|
| 1435 |
+
},
|
| 1436 |
+
{
|
| 1437 |
+
"epoch": 8.4,
|
| 1438 |
+
"grad_norm": 0.32573211193084717,
|
| 1439 |
+
"learning_rate": 8.0005e-06,
|
| 1440 |
+
"loss": 0.0102,
|
| 1441 |
+
"num_input_tokens_seen": 86014976,
|
| 1442 |
+
"step": 84000
|
| 1443 |
+
},
|
| 1444 |
+
{
|
| 1445 |
+
"epoch": 8.45,
|
| 1446 |
+
"grad_norm": 0.4790741205215454,
|
| 1447 |
+
"learning_rate": 7.750500000000001e-06,
|
| 1448 |
+
"loss": 0.0097,
|
| 1449 |
+
"num_input_tokens_seen": 86526976,
|
| 1450 |
+
"step": 84500
|
| 1451 |
+
},
|
| 1452 |
+
{
|
| 1453 |
+
"epoch": 8.5,
|
| 1454 |
+
"grad_norm": 5.938267230987549,
|
| 1455 |
+
"learning_rate": 7.5005000000000004e-06,
|
| 1456 |
+
"loss": 0.0099,
|
| 1457 |
+
"num_input_tokens_seen": 87038976,
|
| 1458 |
+
"step": 85000
|
| 1459 |
+
},
|
| 1460 |
+
{
|
| 1461 |
+
"epoch": 8.55,
|
| 1462 |
+
"grad_norm": 0.3625955283641815,
|
| 1463 |
+
"learning_rate": 7.2505e-06,
|
| 1464 |
+
"loss": 0.0101,
|
| 1465 |
+
"num_input_tokens_seen": 87550976,
|
| 1466 |
+
"step": 85500
|
| 1467 |
+
},
|
| 1468 |
+
{
|
| 1469 |
+
"epoch": 8.6,
|
| 1470 |
+
"grad_norm": 1.664149522781372,
|
| 1471 |
+
"learning_rate": 7.0005e-06,
|
| 1472 |
+
"loss": 0.0103,
|
| 1473 |
+
"num_input_tokens_seen": 88062976,
|
| 1474 |
+
"step": 86000
|
| 1475 |
+
},
|
| 1476 |
+
{
|
| 1477 |
+
"epoch": 8.65,
|
| 1478 |
+
"grad_norm": 0.35580164194107056,
|
| 1479 |
+
"learning_rate": 6.7505e-06,
|
| 1480 |
+
"loss": 0.0097,
|
| 1481 |
+
"num_input_tokens_seen": 88574976,
|
| 1482 |
+
"step": 86500
|
| 1483 |
+
},
|
| 1484 |
+
{
|
| 1485 |
+
"epoch": 8.7,
|
| 1486 |
+
"grad_norm": 0.814786434173584,
|
| 1487 |
+
"learning_rate": 6.5005e-06,
|
| 1488 |
+
"loss": 0.0099,
|
| 1489 |
+
"num_input_tokens_seen": 89086976,
|
| 1490 |
+
"step": 87000
|
| 1491 |
+
},
|
| 1492 |
+
{
|
| 1493 |
+
"epoch": 8.75,
|
| 1494 |
+
"grad_norm": 0.479640930891037,
|
| 1495 |
+
"learning_rate": 6.2505000000000005e-06,
|
| 1496 |
+
"loss": 0.0101,
|
| 1497 |
+
"num_input_tokens_seen": 89598976,
|
| 1498 |
+
"step": 87500
|
| 1499 |
+
},
|
| 1500 |
+
{
|
| 1501 |
+
"epoch": 8.8,
|
| 1502 |
+
"grad_norm": 0.4606671929359436,
|
| 1503 |
+
"learning_rate": 6.0005e-06,
|
| 1504 |
+
"loss": 0.0094,
|
| 1505 |
+
"num_input_tokens_seen": 90110976,
|
| 1506 |
+
"step": 88000
|
| 1507 |
+
},
|
| 1508 |
+
{
|
| 1509 |
+
"epoch": 8.85,
|
| 1510 |
+
"grad_norm": 2.0643467903137207,
|
| 1511 |
+
"learning_rate": 5.7505e-06,
|
| 1512 |
+
"loss": 0.0099,
|
| 1513 |
+
"num_input_tokens_seen": 90622976,
|
| 1514 |
+
"step": 88500
|
| 1515 |
+
},
|
| 1516 |
+
{
|
| 1517 |
+
"epoch": 8.9,
|
| 1518 |
+
"grad_norm": 0.6785427331924438,
|
| 1519 |
+
"learning_rate": 5.5005e-06,
|
| 1520 |
+
"loss": 0.0103,
|
| 1521 |
+
"num_input_tokens_seen": 91134976,
|
| 1522 |
+
"step": 89000
|
| 1523 |
+
},
|
| 1524 |
+
{
|
| 1525 |
+
"epoch": 8.95,
|
| 1526 |
+
"grad_norm": 0.6333959102630615,
|
| 1527 |
+
"learning_rate": 5.250500000000001e-06,
|
| 1528 |
+
"loss": 0.01,
|
| 1529 |
+
"num_input_tokens_seen": 91646976,
|
| 1530 |
+
"step": 89500
|
| 1531 |
+
},
|
| 1532 |
+
{
|
| 1533 |
+
"epoch": 9.0,
|
| 1534 |
+
"grad_norm": 0.8463544249534607,
|
| 1535 |
+
"learning_rate": 5.000500000000001e-06,
|
| 1536 |
+
"loss": 0.0098,
|
| 1537 |
+
"num_input_tokens_seen": 92158848,
|
| 1538 |
+
"step": 90000
|
| 1539 |
+
},
|
| 1540 |
+
{
|
| 1541 |
+
"epoch": 9.0,
|
| 1542 |
+
"eval_combined_score": 0.14495953552467267,
|
| 1543 |
+
"eval_loss": 0.14495953917503357,
|
| 1544 |
+
"eval_mse": 0.1449595318743118,
|
| 1545 |
+
"eval_runtime": 29.5073,
|
| 1546 |
+
"eval_samples_per_second": 677.799,
|
| 1547 |
+
"eval_steps_per_second": 84.725,
|
| 1548 |
+
"num_input_tokens_seen": 92158848,
|
| 1549 |
+
"step": 90000
|
| 1550 |
+
},
|
| 1551 |
+
{
|
| 1552 |
+
"epoch": 9.05,
|
| 1553 |
+
"grad_norm": 0.39637425541877747,
|
| 1554 |
+
"learning_rate": 4.7505000000000005e-06,
|
| 1555 |
+
"loss": 0.0082,
|
| 1556 |
+
"num_input_tokens_seen": 92670848,
|
| 1557 |
+
"step": 90500
|
| 1558 |
+
},
|
| 1559 |
+
{
|
| 1560 |
+
"epoch": 9.1,
|
| 1561 |
+
"grad_norm": 0.7424957752227783,
|
| 1562 |
+
"learning_rate": 4.5005e-06,
|
| 1563 |
+
"loss": 0.0085,
|
| 1564 |
+
"num_input_tokens_seen": 93182848,
|
| 1565 |
+
"step": 91000
|
| 1566 |
+
},
|
| 1567 |
+
{
|
| 1568 |
+
"epoch": 9.15,
|
| 1569 |
+
"grad_norm": 0.8151483535766602,
|
| 1570 |
+
"learning_rate": 4.2505e-06,
|
| 1571 |
+
"loss": 0.008,
|
| 1572 |
+
"num_input_tokens_seen": 93694848,
|
| 1573 |
+
"step": 91500
|
| 1574 |
+
},
|
| 1575 |
+
{
|
| 1576 |
+
"epoch": 9.2,
|
| 1577 |
+
"grad_norm": 1.604078769683838,
|
| 1578 |
+
"learning_rate": 4.0005e-06,
|
| 1579 |
+
"loss": 0.0086,
|
| 1580 |
+
"num_input_tokens_seen": 94206848,
|
| 1581 |
+
"step": 92000
|
| 1582 |
+
},
|
| 1583 |
+
{
|
| 1584 |
+
"epoch": 9.25,
|
| 1585 |
+
"grad_norm": 0.42909368872642517,
|
| 1586 |
+
"learning_rate": 3.7505e-06,
|
| 1587 |
+
"loss": 0.0084,
|
| 1588 |
+
"num_input_tokens_seen": 94718848,
|
| 1589 |
+
"step": 92500
|
| 1590 |
+
},
|
| 1591 |
+
{
|
| 1592 |
+
"epoch": 9.3,
|
| 1593 |
+
"grad_norm": 0.6759423017501831,
|
| 1594 |
+
"learning_rate": 3.5005e-06,
|
| 1595 |
+
"loss": 0.0077,
|
| 1596 |
+
"num_input_tokens_seen": 95230848,
|
| 1597 |
+
"step": 93000
|
| 1598 |
+
},
|
| 1599 |
+
{
|
| 1600 |
+
"epoch": 9.35,
|
| 1601 |
+
"grad_norm": 0.5954917669296265,
|
| 1602 |
+
"learning_rate": 3.2505e-06,
|
| 1603 |
+
"loss": 0.0081,
|
| 1604 |
+
"num_input_tokens_seen": 95742848,
|
| 1605 |
+
"step": 93500
|
| 1606 |
+
},
|
| 1607 |
+
{
|
| 1608 |
+
"epoch": 9.4,
|
| 1609 |
+
"grad_norm": 0.6435306072235107,
|
| 1610 |
+
"learning_rate": 3.0005000000000003e-06,
|
| 1611 |
+
"loss": 0.0079,
|
| 1612 |
+
"num_input_tokens_seen": 96254848,
|
| 1613 |
+
"step": 94000
|
| 1614 |
+
},
|
| 1615 |
+
{
|
| 1616 |
+
"epoch": 9.45,
|
| 1617 |
+
"grad_norm": 0.8906601071357727,
|
| 1618 |
+
"learning_rate": 2.7505e-06,
|
| 1619 |
+
"loss": 0.008,
|
| 1620 |
+
"num_input_tokens_seen": 96766848,
|
| 1621 |
+
"step": 94500
|
| 1622 |
+
},
|
| 1623 |
+
{
|
| 1624 |
+
"epoch": 9.5,
|
| 1625 |
+
"grad_norm": 1.4101794958114624,
|
| 1626 |
+
"learning_rate": 2.5005e-06,
|
| 1627 |
+
"loss": 0.0075,
|
| 1628 |
+
"num_input_tokens_seen": 97278848,
|
| 1629 |
+
"step": 95000
|
| 1630 |
+
},
|
| 1631 |
+
{
|
| 1632 |
+
"epoch": 9.55,
|
| 1633 |
+
"grad_norm": 0.7406792044639587,
|
| 1634 |
+
"learning_rate": 2.2505000000000003e-06,
|
| 1635 |
+
"loss": 0.0078,
|
| 1636 |
+
"num_input_tokens_seen": 97790848,
|
| 1637 |
+
"step": 95500
|
| 1638 |
+
},
|
| 1639 |
+
{
|
| 1640 |
+
"epoch": 9.6,
|
| 1641 |
+
"grad_norm": 1.437361240386963,
|
| 1642 |
+
"learning_rate": 2.0004999999999997e-06,
|
| 1643 |
+
"loss": 0.0077,
|
| 1644 |
+
"num_input_tokens_seen": 98302848,
|
| 1645 |
+
"step": 96000
|
| 1646 |
+
},
|
| 1647 |
+
{
|
| 1648 |
+
"epoch": 9.65,
|
| 1649 |
+
"grad_norm": 0.4781911373138428,
|
| 1650 |
+
"learning_rate": 1.7505e-06,
|
| 1651 |
+
"loss": 0.0078,
|
| 1652 |
+
"num_input_tokens_seen": 98814848,
|
| 1653 |
+
"step": 96500
|
| 1654 |
+
},
|
| 1655 |
+
{
|
| 1656 |
+
"epoch": 9.7,
|
| 1657 |
+
"grad_norm": 0.5876700282096863,
|
| 1658 |
+
"learning_rate": 1.5005e-06,
|
| 1659 |
+
"loss": 0.0075,
|
| 1660 |
+
"num_input_tokens_seen": 99326848,
|
| 1661 |
+
"step": 97000
|
| 1662 |
+
},
|
| 1663 |
+
{
|
| 1664 |
+
"epoch": 9.75,
|
| 1665 |
+
"grad_norm": 0.933368980884552,
|
| 1666 |
+
"learning_rate": 1.2505000000000001e-06,
|
| 1667 |
+
"loss": 0.008,
|
| 1668 |
+
"num_input_tokens_seen": 99838848,
|
| 1669 |
+
"step": 97500
|
| 1670 |
+
},
|
| 1671 |
+
{
|
| 1672 |
+
"epoch": 9.8,
|
| 1673 |
+
"grad_norm": 0.7791544198989868,
|
| 1674 |
+
"learning_rate": 1.0005e-06,
|
| 1675 |
+
"loss": 0.0075,
|
| 1676 |
+
"num_input_tokens_seen": 100350848,
|
| 1677 |
+
"step": 98000
|
| 1678 |
+
},
|
| 1679 |
+
{
|
| 1680 |
+
"epoch": 9.85,
|
| 1681 |
+
"grad_norm": 0.45317134261131287,
|
| 1682 |
+
"learning_rate": 7.505000000000001e-07,
|
| 1683 |
+
"loss": 0.0078,
|
| 1684 |
+
"num_input_tokens_seen": 100862848,
|
| 1685 |
+
"step": 98500
|
| 1686 |
+
},
|
| 1687 |
+
{
|
| 1688 |
+
"epoch": 9.9,
|
| 1689 |
+
"grad_norm": 1.5439448356628418,
|
| 1690 |
+
"learning_rate": 5.005e-07,
|
| 1691 |
+
"loss": 0.0074,
|
| 1692 |
+
"num_input_tokens_seen": 101374848,
|
| 1693 |
+
"step": 99000
|
| 1694 |
+
},
|
| 1695 |
+
{
|
| 1696 |
+
"epoch": 9.95,
|
| 1697 |
+
"grad_norm": 0.5587248206138611,
|
| 1698 |
+
"learning_rate": 2.5049999999999997e-07,
|
| 1699 |
+
"loss": 0.0079,
|
| 1700 |
+
"num_input_tokens_seen": 101886848,
|
| 1701 |
+
"step": 99500
|
| 1702 |
+
},
|
| 1703 |
+
{
|
| 1704 |
+
"epoch": 10.0,
|
| 1705 |
+
"grad_norm": 0.6633381247520447,
|
| 1706 |
+
"learning_rate": 5e-10,
|
| 1707 |
+
"loss": 0.0073,
|
| 1708 |
+
"num_input_tokens_seen": 102398720,
|
| 1709 |
+
"step": 100000
|
| 1710 |
+
},
|
| 1711 |
+
{
|
| 1712 |
+
"epoch": 10.0,
|
| 1713 |
+
"eval_combined_score": 0.14527450438803524,
|
| 1714 |
+
"eval_loss": 0.14527450501918793,
|
| 1715 |
+
"eval_mse": 0.14527450375688256,
|
| 1716 |
+
"eval_runtime": 29.5752,
|
| 1717 |
+
"eval_samples_per_second": 676.241,
|
| 1718 |
+
"eval_steps_per_second": 84.53,
|
| 1719 |
+
"num_input_tokens_seen": 102398720,
|
| 1720 |
+
"step": 100000
|
| 1721 |
+
},
|
| 1722 |
+
{
|
| 1723 |
+
"epoch": 10.0,
|
| 1724 |
+
"num_input_tokens_seen": 102398720,
|
| 1725 |
+
"step": 100000,
|
| 1726 |
+
"total_flos": 5.262202453327104e+16,
|
| 1727 |
+
"train_loss": 0.056572345192432406,
|
| 1728 |
+
"train_runtime": 7202.8043,
|
| 1729 |
+
"train_samples_per_second": 111.066,
|
| 1730 |
+
"train_steps_per_second": 13.883,
|
| 1731 |
+
"train_tokens_per_second": 14216.507
|
| 1732 |
+
}
|
| 1733 |
+
],
|
| 1734 |
+
"logging_steps": 500,
|
| 1735 |
+
"max_steps": 100000,
|
| 1736 |
+
"num_input_tokens_seen": 102398720,
|
| 1737 |
+
"num_train_epochs": 10,
|
| 1738 |
+
"save_steps": 500,
|
| 1739 |
+
"stateful_callbacks": {
|
| 1740 |
+
"TrainerControl": {
|
| 1741 |
+
"args": {
|
| 1742 |
+
"should_epoch_stop": false,
|
| 1743 |
+
"should_evaluate": false,
|
| 1744 |
+
"should_log": false,
|
| 1745 |
+
"should_save": true,
|
| 1746 |
+
"should_training_stop": true
|
| 1747 |
+
},
|
| 1748 |
+
"attributes": {}
|
| 1749 |
+
}
|
| 1750 |
+
},
|
| 1751 |
+
"total_flos": 5.262202453327104e+16,
|
| 1752 |
+
"train_batch_size": 8,
|
| 1753 |
+
"trial_name": null,
|
| 1754 |
+
"trial_params": null
|
| 1755 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e337466c451a702eaa21da343acdcf2393707145066dd65c69ab6082990338da
|
| 3 |
+
size 5432
|